diff --git a/Documentation/PCI/endpoint/pci-vntb-howto.rst b/Documentation/PCI/endpoint/pci-vntb-howto.rst index 9a7a2f0a68498e..3679f5c3025494 100644 --- a/Documentation/PCI/endpoint/pci-vntb-howto.rst +++ b/Documentation/PCI/endpoint/pci-vntb-howto.rst @@ -52,14 +52,14 @@ pci-epf-vntb device, the following commands can be used:: # cd /sys/kernel/config/pci_ep/ # mkdir functions/pci_epf_vntb/func1 -The "mkdir func1" above creates the pci-epf-ntb function device that will +The "mkdir func1" above creates the pci-epf-vntb function device that will be probed by pci_epf_vntb driver. The PCI endpoint framework populates the directory with the following configurable fields:: - # ls functions/pci_epf_ntb/func1 - baseclass_code deviceid msi_interrupts pci-epf-ntb.0 + # ls functions/pci_epf_vntb/func1 + baseclass_code deviceid msi_interrupts pci-epf-vntb.0 progif_code secondary subsys_id vendorid cache_line_size interrupt_pin msix_interrupts primary revid subclass_code subsys_vendor_id @@ -111,13 +111,13 @@ A sample configuration for virtual NTB driver for virtual PCI bus:: # echo 0x080A > functions/pci_epf_vntb/func1/pci_epf_vntb.0/vntb_pid # echo 0x10 > functions/pci_epf_vntb/func1/pci_epf_vntb.0/vbus_number -Binding pci-epf-ntb Device to EP Controller +Binding pci-epf-vntb Device to EP Controller -------------------------------------------- NTB function device should be attached to PCI endpoint controllers connected to the host. - # ln -s controllers/5f010000.pcie_ep functions/pci-epf-ntb/func1/primary + # ln -s controllers/5f010000.pcie_ep functions/pci_epf_vntb/func1/primary Once the above step is completed, the PCI endpoint controllers are ready to establish a link with the host. @@ -139,7 +139,7 @@ lspci Output at Host side ------------------------- Note that the devices listed here correspond to the values populated in -"Creating pci-epf-ntb Device" section above:: +"Creating pci-epf-vntb Device" section above:: # lspci 00:00.0 PCI bridge: Freescale Semiconductor Inc Device 0000 (rev 01) @@ -152,7 +152,7 @@ lspci Output at EP Side / Virtual PCI bus ----------------------------------------- Note that the devices listed here correspond to the values populated in -"Creating pci-epf-ntb Device" section above:: +"Creating pci-epf-vntb Device" section above:: # lspci 10:00.0 Unassigned class [ffff]: Dawicontrol Computersysteme GmbH Device 1234 (rev ff) diff --git a/Documentation/admin-guide/LSM/Smack.rst b/Documentation/admin-guide/LSM/Smack.rst index 6d44f4fdbf59ff..c5ed775f2d107b 100644 --- a/Documentation/admin-guide/LSM/Smack.rst +++ b/Documentation/admin-guide/LSM/Smack.rst @@ -601,10 +601,15 @@ specification. Task Attribute ~~~~~~~~~~~~~~ -The Smack label of a process can be read from /proc//attr/current. A -process can read its own Smack label from /proc/self/attr/current. A +The Smack label of a process can be read from ``/proc//attr/current``. A +process can read its own Smack label from ``/proc/self/attr/current``. A privileged process can change its own Smack label by writing to -/proc/self/attr/current but not the label of another process. +``/proc/self/attr/current`` but not the label of another process. + +Format of writing is : only the label or the label followed by one of the +3 trailers: ``\n`` (by common agreement for ``/proc/...`` interfaces), +``\0`` (because some applications incorrectly include it), +``\n\0`` (because we think some applications may incorrectly include it). File Attribute ~~~~~~~~~~~~~~ @@ -696,6 +701,11 @@ sockets. A privileged program may set this to match the label of another task with which it hopes to communicate. +UNIX domain socket (UDS) with a BSD address functions both as a file in a +filesystem and as a socket. As a file, it carries the SMACK64 attribute. This +attribute is not involved in Smack security enforcement and is immutably +assigned the label "*". + Smack Netlabel Exceptions ~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/devicetree/bindings/arm/apple.yaml b/Documentation/devicetree/bindings/arm/apple.yaml index 5c2629ec3d4cbc..13e0a79ca5b3b2 100644 --- a/Documentation/devicetree/bindings/arm/apple.yaml +++ b/Documentation/devicetree/bindings/arm/apple.yaml @@ -96,6 +96,13 @@ description: | - MacBook Pro (13-inch, M2, 2022) - Mac mini (M2, 2023) + Devices based on the "M3" SoC: + + - MacBook Air (13-inch, M3, 2024) + - MacBook Air (15-inch, M3, 2024) + - MacBook Pro (14-inch, M3, 2023) + - iMac (24-inch, M3, 2023) + Devices based on the "M1 Pro", "M1 Max" and "M1 Ultra" SoCs: - MacBook Pro (14-inch, M1 Pro, 2021) @@ -116,6 +123,14 @@ description: | - Mac Studio (M2 Ultra, 2023) - Mac Pro (M2 Ultra, 2023) + Devices based on the "M3 Pro", "M3 Max" and "M3 Ultra" SoCs: + + - MacBook Pro (14-inch, M3 Pro, 2023) + - MacBook Pro (14-inch, M3 Max, 2023) + - MacBook Pro (16-inch, M3 Pro, 2023) + - MacBook Pro (16-inch, M3 Max, 2023) + - Mac Studio (M3 Ultra, 2025) + The compatible property should follow this format: compatible = "apple,", "apple,", "apple,arm-platform"; @@ -297,6 +312,17 @@ properties: - const: apple,t8112 - const: apple,arm-platform + - description: Apple M2 SoC based platforms + items: + - enum: + - apple,j433 # iMac (24-inch, 2x USB-C, M3, 2023) + - apple,j434 # iMac (24-inch, 4x USB-C, M3, 2023) + - apple,j504 # MacBook Pro (13-inch, M3, 2023) + - apple,j613 # MacBook Air (13-inch, M3, 2024) + - apple,j615 # MacBook Air (15-inch, M3, 2024) + - const: apple,t8122 + - const: apple,arm-platform + - description: Apple M1 Pro SoC based platforms items: - enum: @@ -347,6 +373,36 @@ properties: - const: apple,t6022 - const: apple,arm-platform + - description: Apple M3 Pro SoC based platforms + items: + - enum: + - apple,j514s # MacBook Pro (14-inch, M3 Pro, 2023) + - apple,j516s # MacBook Pro (16-inch, M3 Pro, 2023) + - const: apple,t6030 + - const: apple,arm-platform + + - description: Apple M3 Max SoC based platforms + oneOf: + - items: + - enum: + - apple,j514c # MacBook Pro (14-inch, M3 Max, 16 cores, 2023) + - apple,j516c # MacBook Pro (16-inch, M3 Max, 16 cores, 2023) + - const: apple,t6031 + - const: apple,arm-platform + - items: + - enum: + - apple,j514m # MacBook Pro (14-inch, M3 Max, 14 cores, 2023) + - apple,j516m # MacBook Pro (16-inch, M3 Max, 14 cores, 2023) + - const: apple,t6034 + - const: apple,arm-platform + + - description: Apple M3 Ultra SoC based platforms + items: + - enum: + - apple,j575d # Mac Studio (M3 Ultra, 2025) + - const: apple,t6032 + - const: apple,arm-platform + additionalProperties: true ... diff --git a/Documentation/devicetree/bindings/arm/apple/apple,pmgr.yaml b/Documentation/devicetree/bindings/arm/apple/apple,pmgr.yaml index b88f41a225a385..44f1bd3e9e2491 100644 --- a/Documentation/devicetree/bindings/arm/apple/apple,pmgr.yaml +++ b/Documentation/devicetree/bindings/arm/apple/apple,pmgr.yaml @@ -36,7 +36,10 @@ properties: - const: syscon - const: simple-mfd - items: - - const: apple,t6020-pmgr + - enum: + - apple,t6020-pmgr + - apple,t6030-pmgr + - apple,t8122-pmgr - const: apple,t8103-pmgr - const: syscon - const: simple-mfd diff --git a/Documentation/devicetree/bindings/arm/cpus.yaml b/Documentation/devicetree/bindings/arm/cpus.yaml index 736b7ab1bd0a02..e1fd73281657df 100644 --- a/Documentation/devicetree/bindings/arm/cpus.yaml +++ b/Documentation/devicetree/bindings/arm/cpus.yaml @@ -85,11 +85,13 @@ properties: - apple,avalanche - apple,blizzard - apple,cyclone + - apple,everest - apple,firestorm - apple,hurricane-zephyr - apple,icestorm - apple,mistral - apple,monsoon + - apple,sawtooth - apple,twister - apple,typhoon - arm,arm710t diff --git a/Documentation/devicetree/bindings/dma/apple,sio.yaml b/Documentation/devicetree/bindings/dma/apple,sio.yaml new file mode 100644 index 00000000000000..0e3780ad9dd79a --- /dev/null +++ b/Documentation/devicetree/bindings/dma/apple,sio.yaml @@ -0,0 +1,111 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/dma/apple,sio.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Apple SIO Coprocessor + +description: + SIO is a coprocessor on Apple M1 and later chips (and maybe also on earlier + chips). Its role is to offload SPI, UART and DisplayPort audio transfers, + being a pretend DMA controller. + +maintainers: + - Martin Povišer + +allOf: + - $ref: dma-controller.yaml# + +properties: + compatible: + items: + - enum: + - apple,t6000-sio + - apple,t8103-sio + - const: apple,sio + + reg: + maxItems: 1 + + '#dma-cells': + const: 1 + description: + DMA clients specify a single cell that corresponds to the RTKit endpoint + number used for arranging the transfers in question + + dma-channels: + maximum: 128 + + mboxes: + maxItems: 1 + + iommus: + maxItems: 1 + + power-domains: + maxItems: 1 + + memory-region: + minItems: 2 + maxItems: 8 + description: + A number of references to reserved memory regions among which are the DATA/TEXT + sections of coprocessor executable firmware and also auxiliary firmware data + describing the available DMA-enabled peripherals + + apple,sio-firmware-params: + $ref: /schemas/types.yaml#/definitions/uint32-array + description: | + Parameters in the form of opaque key/value pairs that are to be sent to the SIO + coprocesssor once it boots. These parameters can point into the reserved memory + regions (in device address space). + + Note that unlike Apple's firmware, we treat the parameters, and the data they + refer to, as opaque. Apple embed short data blobs into their SIO devicetree node + that describe the DMA-enabled peripherals (presumably with defined semantics). + Their driver processes those blobs and sets up data structure in mapped device + memory, then references this memory in the parameters sent to the SIO. At the + level of description we are opting for in this binding, we assume the job of + constructing those data structures has been done in advance, leaving behind an + opaque list of key/value parameter pairs to be sent by a prospective driver. + + This approach is chosen for two reasons: + + - It means we don't need to try to understand the semantics of Apple's blobs + as long as we know the transformation we need to do from Apple's devicetree + data to SIO data (which can be shoved away into a loader). It also means the + semantics of Apple's blobs (or of something to replace them) need not be part + of the binding and be kept up with Apple's firmware changes in the future. + + - It leaves less work for the driver attaching on this binding. Instead the work + is done upfront in the loader which can be better suited for keeping up with + Apple's firmware changes. + +required: + - compatible + - reg + - '#dma-cells' + - dma-channels + - mboxes + - iommus + - power-domains + +additionalProperties: false + +examples: + - | + sio: dma-controller@36400000 { + compatible = "apple,t8103-sio", "apple,sio"; + reg = <0x36400000 0x8000>; + dma-channels = <128>; + #dma-cells = <1>; + mboxes = <&sio_mbox>; + iommus = <&sio_dart 0>; + power-domains = <&ps_sio_cpu>; + memory-region = <&sio_text>, <&sio_data>, + <&sio_auxdata1>, <&sio_auxdata2>; /* Filled by loader */ + apple,sio-firmware-params = <0xb 0x10>, <0xc 0x1b80>, <0xf 0x14>, + <0x10 0x1e000>, <0x30d 0x34>, <0x30e 0x4000>, + <0x1a 0x38>, <0x1b 0x50>; /* Filled by loader */ + }; diff --git a/Documentation/devicetree/bindings/hwmon/apple,smc-hwmon.yaml b/Documentation/devicetree/bindings/hwmon/apple,smc-hwmon.yaml new file mode 100644 index 00000000000000..2eec317bc4b3e6 --- /dev/null +++ b/Documentation/devicetree/bindings/hwmon/apple,smc-hwmon.yaml @@ -0,0 +1,86 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/hwmon/apple,smc-hwmon.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Apple SMC Hardware Monitoring + +description: + Apple's System Management Controller (SMC) exposes a vast array of + hardware monitoring sensors, including temperature probes, current and + voltage sense, power meters, and fan speeds. It also provides endpoints + to manually control the speed of each fan individually. Each Apple + Silicon device exposes a different set of endpoints via SMC keys. This + is true even when two machines share an SoC. The CPU core temperature + sensor keys on an M1 Mac mini are different to those on an M1 MacBook + Pro, for example. + +maintainers: + - James Calligeros + +$defs: + sensor: + type: object + + properties: + apple,key-id: + $ref: /schemas/types.yaml#/definitions/string + pattern: "^[A-Za-z0-9]{4}$" + description: The SMC FourCC key of the desired sensor. + Must match the node's suffix. + + label: + description: Human-readable name for the sensor + + required: + - apple,key-id + +properties: + compatible: + const: apple,smc-hwmon + +patternProperties: + "^current-[A-Za-z0-9]{4}$": + $ref: "#/$defs/sensor" + unevaluatedProperties: false + + "^fan-[A-Za-z0-9]{4}$": + $ref: "#/$defs/sensor" + unevaluatedProperties: false + + properties: + apple,fan-minimum: + $ref: /schemas/types.yaml#/definitions/string + pattern: "^[A-Za-z0-9]{4}$" + description: SMC key containing the fan's minimum speed + + apple,fan-maximum: + $ref: /schemas/types.yaml#/definitions/string + pattern: "^[A-Za-z0-9]{4}$" + description: SMC key containing the fan's maximum speed + + apple,fan-target: + $ref: /schemas/types.yaml#/definitions/string + pattern: "^[A-Za-z0-9]{4}$" + description: Writeable endpoint for setting desired fan speed + + apple,fan-mode: + $ref: /schemas/types.yaml#/definitions/string + pattern: "^[A-Za-z0-9]{4}$" + description: Writeable key to enable/disable manual fan control + + + "^power-[A-Za-z0-9]{4}$": + $ref: "#/$defs/sensor" + unevaluatedProperties: false + + "^temperature-[A-Za-z0-9]{4}$": + $ref: "#/$defs/sensor" + unevaluatedProperties: false + + "^voltage-[A-Za-z0-9]{4}$": + $ref: "#/$defs/sensor" + unevaluatedProperties: false + +additionalProperties: false diff --git a/Documentation/devicetree/bindings/i2c/apple,i2c.yaml b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml index 500a965bdb7a84..ea320e8a22b02e 100644 --- a/Documentation/devicetree/bindings/i2c/apple,i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml @@ -22,7 +22,10 @@ properties: compatible: oneOf: - items: - - const: apple,t6020-i2c + - enum: + - apple,t6020-i2c + - apple,t6030-i2c + - apple,t8122-i2c - const: apple,t8103-i2c - items: - enum: diff --git a/Documentation/devicetree/bindings/interrupt-controller/apple,aic2.yaml b/Documentation/devicetree/bindings/interrupt-controller/apple,aic2.yaml index ee5a0dfff43781..f43249c469bea3 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/apple,aic2.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/apple,aic2.yaml @@ -4,10 +4,10 @@ $id: http://devicetree.org/schemas/interrupt-controller/apple,aic2.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Apple Interrupt Controller 2 +title: Apple Interrupt Controller 2 and 3 maintainers: - - Hector Martin + - Janne Grunau description: | The Apple Interrupt Controller 2 is a simple interrupt controller present on @@ -28,14 +28,24 @@ description: | which do not go through a discrete interrupt controller. It also handles FIQ-based Fast IPIs. + The Apple Interrupt Controller 3 is in its base functionality very similar to + the Apple Interrupt Controller 2 and uses the same device tree bindings. It is + found on Apple ARM SoCs platforms starting with t8122 (M3). + properties: compatible: - items: - - enum: - - apple,t8112-aic - - apple,t6000-aic - - apple,t6020-aic - - const: apple,aic2 + oneOf: + - items: + - enum: + - apple,t8112-aic + - apple,t6000-aic + - apple,t6020-aic + - const: apple,aic2 + - items: + - enum: + - apple,t6030-aic3 + - const: apple,t8122-aic3 + - const: apple,t8122-aic3 interrupt-controller: true @@ -117,7 +127,9 @@ allOf: properties: compatible: contains: - const: apple,t8112-aic + enum: + - apple,t8112-aic + - apple,t8122-aic3 then: properties: '#interrupt-cells': @@ -141,4 +153,13 @@ examples: <0x2 0x8e10c000 0x0 0x4>; reg-names = "core", "event"; }; + + aic-t8122: interrupt-controller@2d1000000 { + compatible = "apple,t8122-aic3"; + #interrupt-cells = <3>; + interrupt-controller; + reg = <0x2 0xd1000000 0x0 0xc000>, + <0x2 0xd1040000 0x0 0x4>; + reg-names = "core", "event"; + }; }; diff --git a/Documentation/devicetree/bindings/media/qcom,qcs8300-camss.yaml b/Documentation/devicetree/bindings/media/qcom,qcs8300-camss.yaml index 80a4540a22dc23..e5f170aa4d9ee7 100644 --- a/Documentation/devicetree/bindings/media/qcom,qcs8300-camss.yaml +++ b/Documentation/devicetree/bindings/media/qcom,qcs8300-camss.yaml @@ -120,6 +120,14 @@ properties: items: - const: top + vdda-phy-supply: + description: + Phandle to a 0.88V regulator supply to CSI PHYs. + + vdda-pll-supply: + description: + Phandle to 1.2V regulator supply to CSI PHYs pll block. + ports: $ref: /schemas/graph.yaml#/properties/ports @@ -160,6 +168,8 @@ required: - power-domains - power-domain-names - ports + - vdda-phy-supply + - vdda-pll-supply additionalProperties: false @@ -328,6 +338,9 @@ examples: power-domains = <&camcc CAM_CC_TITAN_TOP_GDSC>; power-domain-names = "top"; + vdda-phy-supply = <&vreg_l4a_0p88>; + vdda-pll-supply = <&vreg_l1c_1p2>; + ports { #address-cells = <1>; #size-cells = <0>; diff --git a/Documentation/devicetree/bindings/mfd/apple,smc.yaml b/Documentation/devicetree/bindings/mfd/apple,smc.yaml index 5429538f7e2e91..34ce048619f5f7 100644 --- a/Documentation/devicetree/bindings/mfd/apple,smc.yaml +++ b/Documentation/devicetree/bindings/mfd/apple,smc.yaml @@ -46,6 +46,12 @@ properties: reboot: $ref: /schemas/power/reset/apple,smc-reboot.yaml + rtc: + $ref: /schemas/rtc/apple,smc-rtc.yaml + + hwmon: + $ref: /schemas/hwmon/apple,smc-hwmon.yaml + additionalProperties: false required: @@ -80,5 +86,44 @@ examples: nvmem-cell-names = "shutdown_flag", "boot_stage", "boot_error_count", "panic_count"; }; + + rtc { + compatible = "apple,smc-rtc"; + nvmem-cells = <&rtc_offset>; + nvmem-cell-names = "rtc_offset"; + }; + + hwmon { + compatible = "apple,smc-hwmon"; + + current-ID0R { + apple,key-id = "ID0R"; + label = "AC Input Current"; + }; + + fan-F0Ac { + apple,key-id = "F0Ac"; + apple,fan-minimum = "F0Mn"; + apple,fan-maximum = "F0Mx"; + apple,fan-target = "F0Tg"; + apple,fan-mode = "F0Md"; + label = "Fan 1"; + }; + + power-PSTR { + apple,key-id = "PSTR"; + label = "Total System Power"; + }; + + temperature-TW0P { + apple,key-id = "TW0P"; + label = "WiFi/BT Module Temperature"; + }; + + voltage-VD0R { + apple,key-id = "VD0R"; + label = "AC Input Voltage"; + }; + }; }; }; diff --git a/Documentation/devicetree/bindings/mmc/aspeed,sdhci.yaml b/Documentation/devicetree/bindings/mmc/aspeed,sdhci.yaml index 9fce8cd7b0b62b..d24950ccea9522 100644 --- a/Documentation/devicetree/bindings/mmc/aspeed,sdhci.yaml +++ b/Documentation/devicetree/bindings/mmc/aspeed,sdhci.yaml @@ -41,7 +41,7 @@ properties: patternProperties: "^sdhci@[0-9a-f]+$": type: object - $ref: mmc-controller.yaml + $ref: sdhci-common.yaml unevaluatedProperties: false properties: diff --git a/Documentation/devicetree/bindings/pci/amlogic,axg-pcie.yaml b/Documentation/devicetree/bindings/pci/amlogic,axg-pcie.yaml index 79a21ba0f9fd62..c8258ef4032834 100644 --- a/Documentation/devicetree/bindings/pci/amlogic,axg-pcie.yaml +++ b/Documentation/devicetree/bindings/pci/amlogic,axg-pcie.yaml @@ -36,13 +36,13 @@ properties: reg: items: - - description: External local bus interface registers + - description: Data Bus Interface registers - description: Meson designed configuration registers - description: PCIe configuration space reg-names: items: - - const: elbi + - const: dbi - const: cfg - const: config @@ -113,7 +113,7 @@ examples: pcie: pcie@f9800000 { compatible = "amlogic,axg-pcie", "snps,dw-pcie"; reg = <0xf9800000 0x400000>, <0xff646000 0x2000>, <0xf9f00000 0x100000>; - reg-names = "elbi", "cfg", "config"; + reg-names = "dbi", "cfg", "config"; interrupts = ; clocks = <&pclk>, <&clk_port>, <&clk_phy>; clock-names = "pclk", "port", "general"; diff --git a/Documentation/devicetree/bindings/pci/apple,pcie.yaml b/Documentation/devicetree/bindings/pci/apple,pcie.yaml index c0852be04f6ded..c0eb0ec87f946e 100644 --- a/Documentation/devicetree/bindings/pci/apple,pcie.yaml +++ b/Documentation/devicetree/bindings/pci/apple,pcie.yaml @@ -82,6 +82,27 @@ properties: power-domains: maxItems: 1 +patternProperties: + "^pci@": + $ref: /schemas/pci/pci-bus.yaml# + type: object + description: A single PCI root port + + properties: + reg: + maxItems: 1 + + pwren-gpios: + description: Optional GPIO to power on the device + maxItems: 1 + + required: + - reset-gpios + - interrupt-controller + - "#interrupt-cells" + - interrupt-map-mask + - interrupt-map + required: - compatible - reg @@ -161,7 +182,7 @@ examples: pinctrl-0 = <&pcie_pins>; pinctrl-names = "default"; - pci@0,0 { + port00: pci@0,0 { device_type = "pci"; reg = <0x0 0x0 0x0 0x0 0x0>; reset-gpios = <&pinctrl_ap 152 0>; @@ -169,9 +190,17 @@ examples: #address-cells = <3>; #size-cells = <2>; ranges; + + interrupt-controller; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &port00 0 0 0 0>, + <0 0 0 2 &port00 0 0 0 1>, + <0 0 0 3 &port00 0 0 0 2>, + <0 0 0 4 &port00 0 0 0 3>; }; - pci@1,0 { + port01: pci@1,0 { device_type = "pci"; reg = <0x800 0x0 0x0 0x0 0x0>; reset-gpios = <&pinctrl_ap 153 0>; @@ -179,9 +208,17 @@ examples: #address-cells = <3>; #size-cells = <2>; ranges; + + interrupt-controller; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &port01 0 0 0 0>, + <0 0 0 2 &port01 0 0 0 1>, + <0 0 0 3 &port01 0 0 0 2>, + <0 0 0 4 &port01 0 0 0 3>; }; - pci@2,0 { + port02: pci@2,0 { device_type = "pci"; reg = <0x1000 0x0 0x0 0x0 0x0>; reset-gpios = <&pinctrl_ap 33 0>; @@ -189,6 +226,14 @@ examples: #address-cells = <3>; #size-cells = <2>; ranges; + + interrupt-controller; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &port02 0 0 0 0>, + <0 0 0 2 &port02 0 0 0 1>, + <0 0 0 3 &port02 0 0 0 2>, + <0 0 0 4 &port02 0 0 0 3>; }; }; }; diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sc7280.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sc7280.yaml index 4d0a915566030f..f760807b5feb6f 100644 --- a/Documentation/devicetree/bindings/pci/qcom,pcie-sc7280.yaml +++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sc7280.yaml @@ -76,6 +76,11 @@ properties: items: - const: pci +required: + - power-domains + - resets + - reset-names + allOf: - $ref: qcom,pcie-common.yaml# diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sc8280xp.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sc8280xp.yaml index 15ba2385eb73c4..b6fb0e37cec59b 100644 --- a/Documentation/devicetree/bindings/pci/qcom,pcie-sc8280xp.yaml +++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sc8280xp.yaml @@ -61,6 +61,9 @@ properties: required: - interconnects - interconnect-names + - power-domains + - resets + - reset-names allOf: - $ref: qcom,pcie-common.yaml# diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8150.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8150.yaml index 26b247a41785fa..17c0d58af37c6c 100644 --- a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8150.yaml +++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8150.yaml @@ -74,6 +74,11 @@ properties: items: - const: pci +required: + - power-domains + - resets + - reset-names + allOf: - $ref: qcom,pcie-common.yaml# diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8250.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8250.yaml index af4dae68d50873..591f1a1eddde1c 100644 --- a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8250.yaml +++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8250.yaml @@ -83,6 +83,11 @@ properties: items: - const: pci +required: + - power-domains + - resets + - reset-names + allOf: - $ref: qcom,pcie-common.yaml# diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8350.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8350.yaml index dde3079adbb331..299473af51d19a 100644 --- a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8350.yaml +++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8350.yaml @@ -73,6 +73,11 @@ properties: items: - const: pci +required: + - power-domains + - resets + - reset-names + allOf: - $ref: qcom,pcie-common.yaml# diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8450.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8450.yaml index 6e0a6d8f0ed070..6a17d753122c64 100644 --- a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8450.yaml +++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8450.yaml @@ -77,6 +77,11 @@ properties: items: - const: pci +required: + - power-domains + - resets + - reset-names + allOf: - $ref: qcom,pcie-common.yaml# diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8550.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8550.yaml index 38b561e23c1fda..29d7df7aca60b0 100644 --- a/Documentation/devicetree/bindings/pci/qcom,pcie-sm8550.yaml +++ b/Documentation/devicetree/bindings/pci/qcom,pcie-sm8550.yaml @@ -83,6 +83,11 @@ properties: - const: pci # PCIe core reset - const: link_down # PCIe link down reset +required: + - power-domains + - resets + - reset-names + allOf: - $ref: qcom,pcie-common.yaml# diff --git a/Documentation/devicetree/bindings/phy/apple,atcphy.yaml b/Documentation/devicetree/bindings/phy/apple,atcphy.yaml new file mode 100644 index 00000000000000..0acac7e3ee67ef --- /dev/null +++ b/Documentation/devicetree/bindings/phy/apple,atcphy.yaml @@ -0,0 +1,222 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/phy/apple,atcphy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Apple Type-C PHY (ATCPHY) + +maintainers: + - Sven Peter + +description: > + The Apple Type-C PHY (ATCPHY) is a combined PHY for USB 2.0, USB 3.x, + USB4/Thunderbolt, and DisplayPort connectivity via Type-C ports found in + Apple Silicon SoCs. + + The PHY handles muxing between these different protocols and also provides the + reset controller for the attached DWC3 USB controller. + + It is designed for USB4 operation and does not handle individual differential + pairs as distinct DisplayPort lanes. Any reference to lane in this binding + hence refers to two differential pairs (RX and TX) as used in USB terminology. + + In order to correctly setup these lanes for the various modes calibration + values copied from Apple's firmware and converted to the format described + below by our bootloader m1n1 are required. Without these only USB2 operation + is possible. + +allOf: + - $ref: /schemas/usb/usb-switch.yaml# + +$defs: + apple,tunable: + $ref: /schemas/types.yaml#/definitions/uint32-matrix + items: + items: + - description: Register offset + - description: Mask to be applied to the register value + - description: Bits to be set after applying the mask + description: > + List of (register offset, mask, value) tuples copied from Apple's Device + Tree by our bootloader m1n1 and used to configure the PHY. These values + even vary for a single product/device and likely contain calibration + values determined by Apple at manufacturing time. + Unless otherwise noted these tunables are always applied to the core + register region. + +properties: + compatible: + oneOf: + - items: + - enum: + - apple,t6000-atcphy + - apple,t6020-atcphy + - apple,t8112-atcphy + - const: apple,t8103-atcphy + - const: apple,t8103-atcphy + + reg: + items: + - description: Common controls for all PHYs (USB2/3/4, DisplayPort, TBT) + - description: DisplayPort Alternate Mode PHY specific controls + - description: Type-C PHY AXI to Apple Fabric interconnect controls + - description: USB2 PHY specific controls + - description: USB3 PIPE interface controls + + reg-names: + items: + - const: core + - const: lpdptx + - const: axi2af + - const: usb2phy + - const: pipehandler + + "#phy-cells": + const: 1 + + "#reset-cells": + const: 0 + + mode-switch: true + orientation-switch: true + + power-domains: + maxItems: 1 + + ports: + $ref: /schemas/graph.yaml#/properties/ports + properties: + port@0: + $ref: /schemas/graph.yaml#/properties/port + description: Outgoing connection to the SS port of the Type-C connector. + + port@1: + $ref: /schemas/graph.yaml#/properties/port + description: Incoming endpoint from the USB3 controller. + + port@2: + $ref: /schemas/graph.yaml#/properties/port + description: Incoming endpoint from the DisplayPort controller. + + port@3: + $ref: /schemas/graph.yaml#/properties/port + description: Incoming endpoint from the USB4/Thunderbolt controller. + + apple,tunable-common-a: + $ref: "#/$defs/apple,tunable" + description: > + Common tunables required for all modes, applied before tunable-axi2af. + + apple,tunable-axi2af: + $ref: "#/$defs/apple,tunable" + description: > + AXI to Apple Fabric tunables, required for all modes. Unlike all other + tunables these are applied to the axi2af region. + + apple,tunable-common-b: + $ref: "#/$defs/apple,tunable" + description: > + Common tunables required for all modes, applied after tunable-axi2af. + + apple,tunable-lane0-usb: + $ref: "#/$defs/apple,tunable" + description: USB3 tunables for lane 0. + + apple,tunable-lane1-usb: + $ref: "#/$defs/apple,tunable" + description: USB3 tunables for lane 1. + + apple,tunable-lane0-cio: + $ref: "#/$defs/apple,tunable" + description: USB4/Thunderbolt ("Converged IO") tunables for lane 0. + + apple,tunable-lane1-cio: + $ref: "#/$defs/apple,tunable" + description: USB4/Thunderbolt ("Converged IO") tunables for lane 1. + + apple,tunable-lane0-dp: + $ref: "#/$defs/apple,tunable" + description: > + DisplayPort tunables for lane 0. + + Note that lane here refers to a USB RX and TX pair re-used for DisplayPort + and not to an individual DisplayPort differential lane. + + apple,tunable-lane1-dp: + $ref: "#/$defs/apple,tunable" + description: > + DisplayPort tunables for lane 1. + + Note that lane here refers to a USB RX and TX pair re-used for DisplayPort + and not to an individual DisplayPort differential lane. + +required: + - compatible + - reg + - reg-names + - "#phy-cells" + - "#reset-cells" + - orientation-switch + - mode-switch + - power-domains + - ports + +additionalProperties: false + +examples: + - | + phy@83000000 { + compatible = "apple,t8103-atcphy"; + reg = <0x83000000 0x4c000>, + <0x83050000 0x8000>, + <0x80000000 0x4000>, + <0x82a90000 0x4000>, + <0x82a84000 0x4000>; + reg-names = "core", "lpdptx", "axi2af", "usb2phy", + "pipehandler"; + + #phy-cells = <1>; + #reset-cells = <0>; + + orientation-switch; + mode-switch; + power-domains = <&ps_atc0_usb>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + endpoint { + remote-endpoint = <&typec_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + + endpoint { + remote-endpoint = <&dwc3_ss_out>; + }; + }; + + port@2 { + reg = <2>; + + endpoint { + remote-endpoint = <&dcp_dp_out>; + }; + }; + + port@3 { + reg = <3>; + + endpoint { + remote-endpoint = <&acio_tbt_out>; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml index eb97181cbb9579..bfc4d75f50ff9e 100644 --- a/Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml @@ -37,12 +37,15 @@ properties: - description: PLL register block clocks: - maxItems: 2 + minItems: 2 + maxItems: 3 clock-names: + minItems: 2 items: - const: aux - const: cfg_ahb + - const: ref "#clock-cells": const: 1 @@ -64,6 +67,29 @@ required: - "#clock-cells" - "#phy-cells" +allOf: + - if: + properties: + compatible: + enum: + - qcom,x1e80100-dp-phy + then: + properties: + clocks: + minItems: 3 + maxItems: 3 + clock-names: + minItems: 3 + maxItems: 3 + else: + properties: + clocks: + minItems: 2 + maxItems: 2 + clock-names: + minItems: 2 + maxItems: 2 + additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/pinctrl/apple,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/apple,pinctrl.yaml index 665ec79a69f1db..1d9e101745fbc7 100644 --- a/Documentation/devicetree/bindings/pinctrl/apple,pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/apple,pinctrl.yaml @@ -18,7 +18,10 @@ properties: compatible: oneOf: - items: - - const: apple,t6020-pinctrl + - enum: + - apple,t6020-pinctrl + - apple,t6030-pinctrl + - apple,t8122-pinctrl - const: apple,t8103-pinctrl - items: # Do not add additional SoC to this list. diff --git a/Documentation/devicetree/bindings/power/apple,pmgr-pwrstate.yaml b/Documentation/devicetree/bindings/power/apple,pmgr-pwrstate.yaml index caf15188099921..9e3b394bf64d00 100644 --- a/Documentation/devicetree/bindings/power/apple,pmgr-pwrstate.yaml +++ b/Documentation/devicetree/bindings/power/apple,pmgr-pwrstate.yaml @@ -43,7 +43,10 @@ properties: - apple,t6000-pmgr-pwrstate - const: apple,pmgr-pwrstate - items: - - const: apple,t6020-pmgr-pwrstate + - enum: + - apple,t6020-pmgr-pwrstate + - apple,t6030-pmgr-pwrstate + - apple,t8122-pmgr-pwrstate - const: apple,t8103-pmgr-pwrstate reg: @@ -80,6 +83,18 @@ properties: minimum: 0 maximum: 15 + apple,force-disable: + description: + Forces this device to be disabled (bus access blocked) when the power + domain is powered down. + type: boolean + + apple,force-reset: + description: + Forces a reset/error recovery of the power control logic when the power + domain is powered down. + type: boolean + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/pwm/apple,s5l-fpwm.yaml b/Documentation/devicetree/bindings/pwm/apple,s5l-fpwm.yaml index 04519b0c581d0e..dffb72896da47b 100644 --- a/Documentation/devicetree/bindings/pwm/apple,s5l-fpwm.yaml +++ b/Documentation/devicetree/bindings/pwm/apple,s5l-fpwm.yaml @@ -18,8 +18,10 @@ properties: - enum: - apple,t8103-fpwm - apple,t8112-fpwm + - apple,t8122-fpwm - apple,t6000-fpwm - apple,t6020-fpwm + - apple,t6030-fpwm - const: apple,s5l-fpwm reg: diff --git a/Documentation/devicetree/bindings/rtc/apple,smc-rtc.yaml b/Documentation/devicetree/bindings/rtc/apple,smc-rtc.yaml new file mode 100644 index 00000000000000..607b610665a28b --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/apple,smc-rtc.yaml @@ -0,0 +1,35 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/apple,smc-rtc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Apple SMC RTC + +description: + Apple Silicon Macs (M1, etc.) have an RTC that is part of the PMU IC, + but most of the PMU functionality is abstracted out by the SMC. + An additional RTC offset stored inside NVMEM is required to compute + the current date/time. + +maintainers: + - Sven Peter + +properties: + compatible: + const: apple,smc-rtc + + nvmem-cells: + items: + - description: 48bit RTC offset, specified in 32768 (2^15) Hz clock ticks + + nvmem-cell-names: + items: + - const: rtc_offset + +required: + - compatible + - nvmem-cells + - nvmem-cell-names + +additionalProperties: false diff --git a/Documentation/devicetree/bindings/serial/renesas,rsci.yaml b/Documentation/devicetree/bindings/serial/renesas,rsci.yaml index f50d8e02f47643..6b1f827a335b37 100644 --- a/Documentation/devicetree/bindings/serial/renesas,rsci.yaml +++ b/Documentation/devicetree/bindings/serial/renesas,rsci.yaml @@ -54,8 +54,6 @@ properties: power-domains: maxItems: 1 - uart-has-rtscts: false - required: - compatible - reg diff --git a/Documentation/devicetree/bindings/slimbus/slimbus.yaml b/Documentation/devicetree/bindings/slimbus/slimbus.yaml index 89017d9cda1093..5a941610ce4edd 100644 --- a/Documentation/devicetree/bindings/slimbus/slimbus.yaml +++ b/Documentation/devicetree/bindings/slimbus/slimbus.yaml @@ -75,16 +75,22 @@ examples: #size-cells = <1>; ranges; - slim@28080000 { + controller@28080000 { compatible = "qcom,slim-ngd-v1.5.0"; reg = <0x091c0000 0x2c000>; interrupts = ; - #address-cells = <2>; + dmas = <&slimbam 3>, <&slimbam 4>; + dma-names = "rx", "tx"; + #address-cells = <1>; #size-cells = <0>; - - audio-codec@1,0 { + slim@1 { + reg = <1>; + #address-cells = <2>; + #size-cells = <0>; + codec@1,0 { compatible = "slim217,1a0"; reg = <1 0>; + }; }; + }; }; - }; diff --git a/Documentation/devicetree/bindings/sound/apple,macaudio.yaml b/Documentation/devicetree/bindings/sound/apple,macaudio.yaml new file mode 100644 index 00000000000000..8fe22dec3015d6 --- /dev/null +++ b/Documentation/devicetree/bindings/sound/apple,macaudio.yaml @@ -0,0 +1,162 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/sound/apple,macaudio.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Apple Silicon Macs integrated sound peripherals + +description: + This binding represents the overall machine-level integration of sound + peripherals on 'Apple Silicon' machines by Apple. + +maintainers: + - Martin Povišer + +properties: + compatible: + items: + - enum: + - apple,j274-macaudio + - apple,j293-macaudio + - apple,j314-macaudio + - const: apple,macaudio + + "#address-cells": + const: 1 + + "#size-cells": + const: 0 + + model: + description: + Model name for presentation to users + $ref: /schemas/types.yaml#/definitions/string + +patternProperties: + "^dai-link(@[0-9a-f]+)?$": + description: | + Node for each sound peripheral such as the speaker array, headphones jack, + or microphone. + type: object + + additionalProperties: false + + properties: + reg: + maxItems: 1 + + link-name: + description: | + Name for the peripheral, expecting 'Speaker' or 'Speakers' if this is + the speaker array. + $ref: /schemas/types.yaml#/definitions/string + + cpu: + type: object + + properties: + sound-dai: + description: | + DAI list with CPU-side I2S ports involved in this peripheral. + minItems: 1 + maxItems: 2 + + required: + - sound-dai + + codec: + type: object + + properties: + sound-dai: + minItems: 1 + maxItems: 8 + description: | + DAI list with the CODEC-side DAIs connected to the above CPU-side + DAIs and involved in this sound peripheral. + + The list is in left/right order if applicable. If there are more + than one CPU-side DAIs (there can be two), the CODECs must be + listed first those connected to the first CPU, then those + connected to the second. + + In addition, on some machines with many speaker codecs, the CODECs + are listed in this fixed order: + + J293: Left Front, Left Rear, Right Front, Right Rear + J314: Left Woofer 1, Left Tweeter, Left Woofer 2, + Right Woofer 1, Right Tweeter, Right Woofer 2 + + required: + - sound-dai + + required: + - reg + - cpu + - codec + +required: + - compatible + - model + +additionalProperties: false + +examples: + - | + mca: mca@9b600000 { + compatible = "apple,t6000-mca", "apple,mca"; + reg = <0x9b600000 0x10000>, + <0x9b500000 0x20000>; + + clocks = <&nco 0>, <&nco 1>, <&nco 2>, <&nco 3>; + power-domains = <&ps_audio_p>, <&ps_mca0>, <&ps_mca1>, + <&ps_mca2>, <&ps_mca3>; + dmas = <&admac 0>, <&admac 1>, <&admac 2>, <&admac 3>, + <&admac 4>, <&admac 5>, <&admac 6>, <&admac 7>, + <&admac 8>, <&admac 9>, <&admac 10>, <&admac 11>, + <&admac 12>, <&admac 13>, <&admac 14>, <&admac 15>; + dma-names = "tx0a", "rx0a", "tx0b", "rx0b", + "tx1a", "rx1a", "tx1b", "rx1b", + "tx2a", "rx2a", "tx2b", "rx2b", + "tx3a", "rx3a", "tx3b", "rx3b"; + + #sound-dai-cells = <1>; + }; + + sound { + compatible = "apple,j314-macaudio", "apple,macaudio"; + model = "MacBook Pro J314 integrated audio"; + + #address-cells = <1>; + #size-cells = <0>; + + dai-link@0 { + reg = <0>; + link-name = "Speakers"; + + cpu { + sound-dai = <&mca 0>, <&mca 1>; + }; + codec { + sound-dai = <&speaker_left_woof1>, + <&speaker_left_tweet>, + <&speaker_left_woof2>, + <&speaker_right_woof1>, + <&speaker_right_tweet>, + <&speaker_right_woof2>; + }; + }; + + dai-link@1 { + reg = <1>; + link-name = "Headphones Jack"; + + cpu { + sound-dai = <&mca 2>; + }; + codec { + sound-dai = <&jack_codec>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/sound/asahi-kasei,ak4458.yaml b/Documentation/devicetree/bindings/sound/asahi-kasei,ak4458.yaml index 1fdbeecc5eff9d..3a3313ea0890a4 100644 --- a/Documentation/devicetree/bindings/sound/asahi-kasei,ak4458.yaml +++ b/Documentation/devicetree/bindings/sound/asahi-kasei,ak4458.yaml @@ -21,10 +21,10 @@ properties: reg: maxItems: 1 - avdd-supply: + AVDD-supply: description: Analog power supply - dvdd-supply: + DVDD-supply: description: Digital power supply reset-gpios: @@ -60,7 +60,7 @@ allOf: properties: dsd-path: false -additionalProperties: false +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/sound/asahi-kasei,ak5558.yaml b/Documentation/devicetree/bindings/sound/asahi-kasei,ak5558.yaml index d3d494ae8abfeb..dc8f85f266bf30 100644 --- a/Documentation/devicetree/bindings/sound/asahi-kasei,ak5558.yaml +++ b/Documentation/devicetree/bindings/sound/asahi-kasei,ak5558.yaml @@ -19,10 +19,10 @@ properties: reg: maxItems: 1 - avdd-supply: + AVDD-supply: description: A 1.8V supply that powers up the AVDD pin. - dvdd-supply: + DVDD-supply: description: A 1.2V supply that powers up the DVDD pin. reset-gpios: diff --git a/Documentation/devicetree/bindings/usb/apple,dwc3.yaml b/Documentation/devicetree/bindings/usb/apple,dwc3.yaml new file mode 100644 index 00000000000000..f70c33f32c5d61 --- /dev/null +++ b/Documentation/devicetree/bindings/usb/apple,dwc3.yaml @@ -0,0 +1,80 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/usb/apple,dwc3.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Apple Silicon DWC3 USB controller + +maintainers: + - Sven Peter + +description: + Apple Silicon SoCs use a Synopsys DesignWare DWC3 based controller for each of + their Type-C ports. + +allOf: + - $ref: snps,dwc3-common.yaml# + +properties: + compatible: + oneOf: + - items: + - enum: + - apple,t6000-dwc3 + - apple,t6020-dwc3 + - apple,t8112-dwc3 + - const: apple,t8103-dwc3 + - const: apple,t8103-dwc3 + + reg: + items: + - description: Core DWC3 region + - description: Apple-specific DWC3 region + + reg-names: + items: + - const: dwc3-core + - const: dwc3-apple + + interrupts: + maxItems: 1 + + iommus: + maxItems: 2 + + resets: + maxItems: 1 + + power-domains: + maxItems: 1 + +required: + - compatible + - reg + - reg-names + - interrupts + - iommus + - resets + - power-domains + - usb-role-switch + +unevaluatedProperties: false + +examples: + - | + #include + #include + + usb@82280000 { + compatible = "apple,t8103-dwc3"; + reg = <0x82280000 0xcd00>, <0x8228cd00 0x3200>; + reg-names = "dwc3-core", "dwc3-apple"; + interrupts = ; + iommus = <&dwc3_0_dart_0 0>, <&dwc3_0_dart_1 1>; + + power-domains = <&ps_atc0_usb>; + resets = <&atcphy0>; + + usb-role-switch; + }; diff --git a/Documentation/devicetree/bindings/watchdog/apple,wdt.yaml b/Documentation/devicetree/bindings/watchdog/apple,wdt.yaml index 05602678c070d7..db0d11aa0a3e15 100644 --- a/Documentation/devicetree/bindings/watchdog/apple,wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/apple,wdt.yaml @@ -16,7 +16,10 @@ properties: compatible: oneOf: - items: - - const: apple,t6020-wdt + - enum: + - apple,t6020-wdt + - apple,t6030-wdt + - apple,t8122-wdt - const: apple,t8103-wdt - items: - enum: diff --git a/Documentation/driver-api/dpll.rst b/Documentation/driver-api/dpll.rst index be1fc643b645e3..83118c728ed90c 100644 --- a/Documentation/driver-api/dpll.rst +++ b/Documentation/driver-api/dpll.rst @@ -198,26 +198,28 @@ be requested with the same attribute with ``DPLL_CMD_DEVICE_SET`` command. ================================== ====================================== Device may also provide ability to adjust a signal phase on a pin. -If pin phase adjustment is supported, minimal and maximal values that pin -handle shall be provide to the user on ``DPLL_CMD_PIN_GET`` respond -with ``DPLL_A_PIN_PHASE_ADJUST_MIN`` and ``DPLL_A_PIN_PHASE_ADJUST_MAX`` +If pin phase adjustment is supported, minimal and maximal values and +granularity that pin handle shall be provided to the user on +``DPLL_CMD_PIN_GET`` respond with ``DPLL_A_PIN_PHASE_ADJUST_MIN``, +``DPLL_A_PIN_PHASE_ADJUST_MAX`` and ``DPLL_A_PIN_PHASE_ADJUST_GRAN`` attributes. Configured phase adjust value is provided with ``DPLL_A_PIN_PHASE_ADJUST`` attribute of a pin, and value change can be requested with the same attribute with ``DPLL_CMD_PIN_SET`` command. - =============================== ====================================== - ``DPLL_A_PIN_ID`` configured pin id - ``DPLL_A_PIN_PHASE_ADJUST_MIN`` attr minimum value of phase adjustment - ``DPLL_A_PIN_PHASE_ADJUST_MAX`` attr maximum value of phase adjustment - ``DPLL_A_PIN_PHASE_ADJUST`` attr configured value of phase - adjustment on parent dpll device - ``DPLL_A_PIN_PARENT_DEVICE`` nested attribute for requesting - configuration on given parent dpll - device - ``DPLL_A_PIN_PARENT_ID`` parent dpll device id - ``DPLL_A_PIN_PHASE_OFFSET`` attr measured phase difference - between a pin and parent dpll device - =============================== ====================================== + ================================ ========================================== + ``DPLL_A_PIN_ID`` configured pin id + ``DPLL_A_PIN_PHASE_ADJUST_GRAN`` attr granularity of phase adjustment value + ``DPLL_A_PIN_PHASE_ADJUST_MIN`` attr minimum value of phase adjustment + ``DPLL_A_PIN_PHASE_ADJUST_MAX`` attr maximum value of phase adjustment + ``DPLL_A_PIN_PHASE_ADJUST`` attr configured value of phase + adjustment on parent dpll device + ``DPLL_A_PIN_PARENT_DEVICE`` nested attribute for requesting + configuration on given parent dpll + device + ``DPLL_A_PIN_PARENT_ID`` parent dpll device id + ``DPLL_A_PIN_PHASE_OFFSET`` attr measured phase difference + between a pin and parent dpll device + ================================ ========================================== All phase related values are provided in pico seconds, which represents time difference between signals phase. The negative value means that @@ -384,6 +386,8 @@ according to attribute purpose. frequencies ``DPLL_A_PIN_ANY_FREQUENCY_MIN`` attr minimum value of frequency ``DPLL_A_PIN_ANY_FREQUENCY_MAX`` attr maximum value of frequency + ``DPLL_A_PIN_PHASE_ADJUST_GRAN`` attr granularity of phase + adjustment value ``DPLL_A_PIN_PHASE_ADJUST_MIN`` attr minimum value of phase adjustment ``DPLL_A_PIN_PHASE_ADJUST_MAX`` attr maximum value of phase diff --git a/Documentation/hwmon/g762.rst b/Documentation/hwmon/g762.rst index 0371b3365c48cf..f224552a2d3cc0 100644 --- a/Documentation/hwmon/g762.rst +++ b/Documentation/hwmon/g762.rst @@ -17,7 +17,7 @@ done via a userland daemon like fancontrol. Note that those entries do not provide ways to setup the specific hardware characteristics of the system (reference clock, pulses per fan revolution, ...); Those can be modified via devicetree bindings -documented in Documentation/devicetree/bindings/hwmon/g762.txt or +documented in Documentation/devicetree/bindings/hwmon/gmt,g762.yaml or using a specific platform_data structure in board initialization file (see include/linux/platform_data/g762.h). diff --git a/Documentation/hwmon/macsmc-hwmon.rst b/Documentation/hwmon/macsmc-hwmon.rst new file mode 100644 index 00000000000000..6903f76df62bf2 --- /dev/null +++ b/Documentation/hwmon/macsmc-hwmon.rst @@ -0,0 +1,71 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +Kernel driver macsmc-hwmon +========================== + +Supported hardware + + * Apple Silicon Macs (M1 and up) + +Author: James Calligeros + +Description +----------- + +macsmc-hwmon exposes the Apple System Management controller's +temperature, voltage, current and power sensors, as well as +fan speed and control capabilities, via hwmon. + +Because each Apple Silicon Mac exposes a different set of sensors +(e.g. the MacBooks expose battery telemetry that is not present on +the desktop Macs), sensors present on any given machine are described +via Devicetree. The driver picks these up and registers them with +hwmon when probed. + +Manual fan speed is supported via the fan_control module parameter. This +is disabled by default and marked as unsafe, as it cannot be proven that +the system will fail safe if overheating due to manual fan control being +used. + +sysfs interface +--------------- + +currX_input + Ammeter value + +currX_label + Ammeter label + +fanX_input + Current fan speed + +fanX_label + Fan label + +fanX_min + Minimum possible fan speed + +fanX_max + Maximum possible fan speed + +fanX_target + Current fan setpoint + +inX_input + Voltmeter value + +inX_label + Voltmeter label + +powerX_input + Power meter value + +powerX_label + Power meter label + +tempX_input + Temperature sensor value + +tempX_label + Temperature sensor label + diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 80728f6f9bc876..78d0724d7e12ce 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -440,6 +440,12 @@ attribute-sets: doc: | Capable pin provides list of pins that can be bound to create a reference-sync pin pair. + - + name: phase-adjust-gran + type: u32 + doc: | + Granularity of phase adjustment, in picoseconds. The value of + phase adjustment must be a multiple of this granularity. - name: pin-parent-device @@ -616,6 +622,7 @@ operations: - capabilities - parent-device - parent-pin + - phase-adjust-gran - phase-adjust-min - phase-adjust-max - phase-adjust diff --git a/Documentation/netlink/specs/fou.yaml b/Documentation/netlink/specs/fou.yaml index 8e7974ec453fca..331f1b342b3adb 100644 --- a/Documentation/netlink/specs/fou.yaml +++ b/Documentation/netlink/specs/fou.yaml @@ -39,6 +39,8 @@ attribute-sets: - name: ipproto type: u8 + checks: + min: 1 - name: type type: u8 diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index a06cb99d66dcdc..7a637e87005fee 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -3195,12 +3195,13 @@ enhanced_dad - BOOLEAN =========== ratelimit - INTEGER - Limit the maximal rates for sending ICMPv6 messages. + Limit the maximal rates for sending ICMPv6 messages to a particular + peer. 0 to disable any limiting, - otherwise the minimal space between responses in milliseconds. + otherwise the space between responses in milliseconds. - Default: 1000 + Default: 100 ratemask - list of comma separated ranges For ICMPv6 message types matching the ranges in the ratemask, limit diff --git a/Documentation/process/2.Process.rst b/Documentation/process/2.Process.rst index ef3b116492df08..f4fc0da8999d90 100644 --- a/Documentation/process/2.Process.rst +++ b/Documentation/process/2.Process.rst @@ -104,8 +104,10 @@ kernels go out with a handful of known regressions though, hopefully, none of them are serious. Once a stable release is made, its ongoing maintenance is passed off to the -"stable team," currently Greg Kroah-Hartman. The stable team will release -occasional updates to the stable release using the 5.x.y numbering scheme. +"stable team," currently consists of Greg Kroah-Hartman and Sasha Levin. The +stable team will release occasional updates to the stable release using the +5.x.y numbering scheme. + To be considered for an update release, a patch must (1) fix a significant bug, and (2) already be merged into the mainline for the next development kernel. Kernels will typically receive stable updates for a little more diff --git a/Documentation/tools/rtla/common_appendix.rst b/Documentation/tools/rtla/common_appendix.txt similarity index 100% rename from Documentation/tools/rtla/common_appendix.rst rename to Documentation/tools/rtla/common_appendix.txt diff --git a/Documentation/tools/rtla/common_hist_options.rst b/Documentation/tools/rtla/common_hist_options.txt similarity index 100% rename from Documentation/tools/rtla/common_hist_options.rst rename to Documentation/tools/rtla/common_hist_options.txt diff --git a/Documentation/tools/rtla/common_options.rst b/Documentation/tools/rtla/common_options.txt similarity index 100% rename from Documentation/tools/rtla/common_options.rst rename to Documentation/tools/rtla/common_options.txt diff --git a/Documentation/tools/rtla/common_osnoise_description.rst b/Documentation/tools/rtla/common_osnoise_description.txt similarity index 100% rename from Documentation/tools/rtla/common_osnoise_description.rst rename to Documentation/tools/rtla/common_osnoise_description.txt diff --git a/Documentation/tools/rtla/common_osnoise_options.rst b/Documentation/tools/rtla/common_osnoise_options.txt similarity index 100% rename from Documentation/tools/rtla/common_osnoise_options.rst rename to Documentation/tools/rtla/common_osnoise_options.txt diff --git a/Documentation/tools/rtla/common_timerlat_aa.rst b/Documentation/tools/rtla/common_timerlat_aa.txt similarity index 100% rename from Documentation/tools/rtla/common_timerlat_aa.rst rename to Documentation/tools/rtla/common_timerlat_aa.txt diff --git a/Documentation/tools/rtla/common_timerlat_description.rst b/Documentation/tools/rtla/common_timerlat_description.txt similarity index 100% rename from Documentation/tools/rtla/common_timerlat_description.rst rename to Documentation/tools/rtla/common_timerlat_description.txt diff --git a/Documentation/tools/rtla/common_timerlat_options.rst b/Documentation/tools/rtla/common_timerlat_options.txt similarity index 100% rename from Documentation/tools/rtla/common_timerlat_options.rst rename to Documentation/tools/rtla/common_timerlat_options.txt diff --git a/Documentation/tools/rtla/common_top_options.rst b/Documentation/tools/rtla/common_top_options.txt similarity index 100% rename from Documentation/tools/rtla/common_top_options.rst rename to Documentation/tools/rtla/common_top_options.txt diff --git a/Documentation/tools/rtla/rtla-hwnoise.rst b/Documentation/tools/rtla/rtla-hwnoise.rst index 3a7163c02ac8e8..26512b15fe7ba5 100644 --- a/Documentation/tools/rtla/rtla-hwnoise.rst +++ b/Documentation/tools/rtla/rtla-hwnoise.rst @@ -29,11 +29,11 @@ collection of the tracer output. OPTIONS ======= -.. include:: common_osnoise_options.rst +.. include:: common_osnoise_options.txt -.. include:: common_top_options.rst +.. include:: common_top_options.txt -.. include:: common_options.rst +.. include:: common_options.txt EXAMPLE ======= @@ -106,4 +106,4 @@ AUTHOR ====== Written by Daniel Bristot de Oliveira -.. include:: common_appendix.rst +.. include:: common_appendix.txt diff --git a/Documentation/tools/rtla/rtla-osnoise-hist.rst b/Documentation/tools/rtla/rtla-osnoise-hist.rst index 1fc60ef2610677..007521c865d97e 100644 --- a/Documentation/tools/rtla/rtla-osnoise-hist.rst +++ b/Documentation/tools/rtla/rtla-osnoise-hist.rst @@ -15,7 +15,7 @@ SYNOPSIS DESCRIPTION =========== -.. include:: common_osnoise_description.rst +.. include:: common_osnoise_description.txt The **rtla osnoise hist** tool collects all **osnoise:sample_threshold** occurrence in a histogram, displaying the results in a user-friendly way. @@ -24,11 +24,11 @@ collection of the tracer output. OPTIONS ======= -.. include:: common_osnoise_options.rst +.. include:: common_osnoise_options.txt -.. include:: common_hist_options.rst +.. include:: common_hist_options.txt -.. include:: common_options.rst +.. include:: common_options.txt EXAMPLE ======= @@ -65,4 +65,4 @@ AUTHOR ====== Written by Daniel Bristot de Oliveira -.. include:: common_appendix.rst +.. include:: common_appendix.txt diff --git a/Documentation/tools/rtla/rtla-osnoise-top.rst b/Documentation/tools/rtla/rtla-osnoise-top.rst index b1cbd7bcd4aed2..6ccadae3894570 100644 --- a/Documentation/tools/rtla/rtla-osnoise-top.rst +++ b/Documentation/tools/rtla/rtla-osnoise-top.rst @@ -15,7 +15,7 @@ SYNOPSIS DESCRIPTION =========== -.. include:: common_osnoise_description.rst +.. include:: common_osnoise_description.txt **rtla osnoise top** collects the periodic summary from the *osnoise* tracer, including the counters of the occurrence of the interference source, @@ -26,11 +26,11 @@ collection of the tracer output. OPTIONS ======= -.. include:: common_osnoise_options.rst +.. include:: common_osnoise_options.txt -.. include:: common_top_options.rst +.. include:: common_top_options.txt -.. include:: common_options.rst +.. include:: common_options.txt EXAMPLE ======= @@ -60,4 +60,4 @@ AUTHOR ====== Written by Daniel Bristot de Oliveira -.. include:: common_appendix.rst +.. include:: common_appendix.txt diff --git a/Documentation/tools/rtla/rtla-osnoise.rst b/Documentation/tools/rtla/rtla-osnoise.rst index c129b206ce3484..540d2bf6c15247 100644 --- a/Documentation/tools/rtla/rtla-osnoise.rst +++ b/Documentation/tools/rtla/rtla-osnoise.rst @@ -14,7 +14,7 @@ SYNOPSIS DESCRIPTION =========== -.. include:: common_osnoise_description.rst +.. include:: common_osnoise_description.txt The *osnoise* tracer outputs information in two ways. It periodically prints a summary of the noise of the operating system, including the counters of @@ -56,4 +56,4 @@ AUTHOR ====== Written by Daniel Bristot de Oliveira -.. include:: common_appendix.rst +.. include:: common_appendix.txt diff --git a/Documentation/tools/rtla/rtla-timerlat-hist.rst b/Documentation/tools/rtla/rtla-timerlat-hist.rst index 4923a362129bbd..f56fe546411bd4 100644 --- a/Documentation/tools/rtla/rtla-timerlat-hist.rst +++ b/Documentation/tools/rtla/rtla-timerlat-hist.rst @@ -16,7 +16,7 @@ SYNOPSIS DESCRIPTION =========== -.. include:: common_timerlat_description.rst +.. include:: common_timerlat_description.txt The **rtla timerlat hist** displays a histogram of each tracer event occurrence. This tool uses the periodic information, and the @@ -25,13 +25,13 @@ occurrence. This tool uses the periodic information, and the OPTIONS ======= -.. include:: common_timerlat_options.rst +.. include:: common_timerlat_options.txt -.. include:: common_hist_options.rst +.. include:: common_hist_options.txt -.. include:: common_options.rst +.. include:: common_options.txt -.. include:: common_timerlat_aa.rst +.. include:: common_timerlat_aa.txt EXAMPLE ======= @@ -110,4 +110,4 @@ AUTHOR ====== Written by Daniel Bristot de Oliveira -.. include:: common_appendix.rst +.. include:: common_appendix.txt diff --git a/Documentation/tools/rtla/rtla-timerlat-top.rst b/Documentation/tools/rtla/rtla-timerlat-top.rst index 50968cdd2095a1..7dbe625d0c4243 100644 --- a/Documentation/tools/rtla/rtla-timerlat-top.rst +++ b/Documentation/tools/rtla/rtla-timerlat-top.rst @@ -16,7 +16,7 @@ SYNOPSIS DESCRIPTION =========== -.. include:: common_timerlat_description.rst +.. include:: common_timerlat_description.txt The **rtla timerlat top** displays a summary of the periodic output from the *timerlat* tracer. It also provides information for each @@ -26,13 +26,13 @@ seem with the option **-T**. OPTIONS ======= -.. include:: common_timerlat_options.rst +.. include:: common_timerlat_options.txt -.. include:: common_top_options.rst +.. include:: common_top_options.txt -.. include:: common_options.rst +.. include:: common_options.txt -.. include:: common_timerlat_aa.rst +.. include:: common_timerlat_aa.txt **--aa-only** *us* @@ -133,4 +133,4 @@ AUTHOR ------ Written by Daniel Bristot de Oliveira -.. include:: common_appendix.rst +.. include:: common_appendix.txt diff --git a/Documentation/tools/rtla/rtla-timerlat.rst b/Documentation/tools/rtla/rtla-timerlat.rst index 20e2d259467fd0..ce9f57e038c37f 100644 --- a/Documentation/tools/rtla/rtla-timerlat.rst +++ b/Documentation/tools/rtla/rtla-timerlat.rst @@ -14,7 +14,7 @@ SYNOPSIS DESCRIPTION =========== -.. include:: common_timerlat_description.rst +.. include:: common_timerlat_description.txt The **rtla timerlat top** mode displays a summary of the periodic output from the *timerlat* tracer. The **rtla timerlat hist** mode displays @@ -51,4 +51,4 @@ AUTHOR ====== Written by Daniel Bristot de Oliveira -.. include:: common_appendix.rst +.. include:: common_appendix.txt diff --git a/Documentation/tools/rtla/rtla.rst b/Documentation/tools/rtla/rtla.rst index fc0d233efcd5df..2a5fb7004ad448 100644 --- a/Documentation/tools/rtla/rtla.rst +++ b/Documentation/tools/rtla/rtla.rst @@ -45,4 +45,4 @@ AUTHOR ====== Daniel Bristot de Oliveira -.. include:: common_appendix.rst +.. include:: common_appendix.txt diff --git a/Documentation/trace/events-pci.rst b/Documentation/trace/events-pci.rst new file mode 100644 index 00000000000000..03ff4ad30ddfa1 --- /dev/null +++ b/Documentation/trace/events-pci.rst @@ -0,0 +1,74 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=========================== +Subsystem Trace Points: PCI +=========================== + +Overview +======== +The PCI tracing system provides tracepoints to monitor critical hardware events +that can impact system performance and reliability. These events normally show +up here: + + /sys/kernel/tracing/events/pci + +Cf. include/trace/events/pci.h for the events definitions. + +Available Tracepoints +===================== + +pci_hp_event +------------ + +Monitors PCI hotplug events including card insertion/removal and link +state changes. +:: + + pci_hp_event "%s slot:%s, event:%s\n" + +**Event Types**: + +* ``LINK_UP`` - PCIe link established +* ``LINK_DOWN`` - PCIe link lost +* ``CARD_PRESENT`` - Card detected in slot +* ``CARD_NOT_PRESENT`` - Card removed from slot + +**Example Usage**:: + + # Enable the tracepoint + echo 1 > /sys/kernel/debug/tracing/events/pci/pci_hp_event/enable + + # Monitor events (the following output is generated when a device is hotplugged) + cat /sys/kernel/debug/tracing/trace_pipe + irq/51-pciehp-88 [001] ..... 1311.177459: pci_hp_event: 0000:00:02.0 slot:10, event:CARD_PRESENT + + irq/51-pciehp-88 [001] ..... 1311.177566: pci_hp_event: 0000:00:02.0 slot:10, event:LINK_UP + +pcie_link_event +--------------- + +Monitors PCIe link speed changes and provides detailed link status information. +:: + + pcie_link_event "%s type:%d, reason:%d, cur_bus_speed:%d, max_bus_speed:%d, width:%u, flit_mode:%u, status:%s\n" + +**Parameters**: + +* ``type`` - PCIe device type (4=Root Port, etc.) +* ``reason`` - Reason for link change: + + - ``0`` - Link retrain + - ``1`` - Bus enumeration + - ``2`` - Bandwidth notification enable + - ``3`` - Bandwidth notification IRQ + - ``4`` - Hotplug event + + +**Example Usage**:: + + # Enable the tracepoint + echo 1 > /sys/kernel/debug/tracing/events/pci/pcie_link_event/enable + + # Monitor events (the following output is generated when a device is hotplugged) + cat /sys/kernel/debug/tracing/trace_pipe + irq/51-pciehp-88 [001] ..... 381.545386: pcie_link_event: 0000:00:02.0 type:4, reason:4, cur_bus_speed:20, max_bus_speed:23, width:1, flit_mode:0, status:DLLLA diff --git a/Documentation/trace/index.rst b/Documentation/trace/index.rst index b4a429dc4f7ad6..0a40bfabcf19bf 100644 --- a/Documentation/trace/index.rst +++ b/Documentation/trace/index.rst @@ -54,6 +54,7 @@ applications. events-power events-nmi events-msr + events-pci boottime-trace histogram histogram-design diff --git a/MAINTAINERS b/MAINTAINERS index e8f06145fb54c9..09c412afa9050f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1871,6 +1871,13 @@ L: linux-input@vger.kernel.org S: Odd fixes F: drivers/input/mouse/bcm5974.c +APPLE DRM DISPLAY DRIVER +M: Janne Grunau +L: dri-devel@lists.freedesktop.org +S: Maintained +T: git git://anongit.freedesktop.org/drm/drm-misc +F: drivers/gpu/drm/apple/ + APPLE PCIE CONTROLLER DRIVER M: Marc Zyngier L: linux-pci@vger.kernel.org @@ -2397,9 +2404,11 @@ M: Martin Povišer L: asahi@lists.linux.dev L: linux-sound@vger.kernel.org S: Maintained +F: Documentation/devicetree/bindings/dma/apple,sio.yaml F: Documentation/devicetree/bindings/sound/adi,ssm3515.yaml F: Documentation/devicetree/bindings/sound/cirrus,cs42l84.yaml F: Documentation/devicetree/bindings/sound/apple,* +F: drivers/dma/apple-sio.c F: sound/soc/apple/* F: sound/soc/codecs/cs42l83-i2c.c F: sound/soc/codecs/cs42l84.* @@ -2423,6 +2432,7 @@ F: Documentation/devicetree/bindings/cpufreq/apple,cluster-cpufreq.yaml F: Documentation/devicetree/bindings/dma/apple,admac.yaml F: Documentation/devicetree/bindings/gpio/apple,smc-gpio.yaml F: Documentation/devicetree/bindings/gpu/apple,agx.yaml +F: Documentation/devicetree/bindings/hwmon/apple,smc-hwmon.yaml F: Documentation/devicetree/bindings/i2c/apple,i2c.yaml F: Documentation/devicetree/bindings/input/touchscreen/apple,z2-multitouch.yaml F: Documentation/devicetree/bindings/interrupt-controller/apple,* @@ -2436,22 +2446,28 @@ F: Documentation/devicetree/bindings/nvme/apple,nvme-ans.yaml F: Documentation/devicetree/bindings/nvmem/apple,efuses.yaml F: Documentation/devicetree/bindings/nvmem/apple,spmi-nvmem.yaml F: Documentation/devicetree/bindings/pci/apple,pcie.yaml +F: Documentation/devicetree/bindings/phy/apple,atcphy.yaml F: Documentation/devicetree/bindings/pinctrl/apple,pinctrl.yaml F: Documentation/devicetree/bindings/power/apple* F: Documentation/devicetree/bindings/power/reset/apple,smc-reboot.yaml F: Documentation/devicetree/bindings/pwm/apple,s5l-fpwm.yaml +F: Documentation/devicetree/bindings/rtc/apple,smc-rtc.yaml F: Documentation/devicetree/bindings/spi/apple,spi.yaml F: Documentation/devicetree/bindings/spmi/apple,spmi.yaml +F: Documentation/devicetree/bindings/usb/apple,dwc3.yaml F: Documentation/devicetree/bindings/watchdog/apple,wdt.yaml +F: Documentation/hwmon/macsmc-hwmon.rst F: arch/arm64/boot/dts/apple/ F: drivers/bluetooth/hci_bcm4377.c F: drivers/clk/clk-apple-nco.c F: drivers/cpufreq/apple-soc-cpufreq.c F: drivers/dma/apple-admac.c F: drivers/gpio/gpio-macsmc.c +F: drivers/hwmon/macsmc-hwmon.c F: drivers/pmdomain/apple/ F: drivers/i2c/busses/i2c-pasemi-core.c F: drivers/i2c/busses/i2c-pasemi-platform.c +F: drivers/input/misc/macsmc-input.c F: drivers/input/touchscreen/apple_z2.c F: drivers/iommu/apple-dart.c F: drivers/iommu/io-pgtable-dart.c @@ -2460,12 +2476,15 @@ F: drivers/mfd/macsmc.c F: drivers/nvme/host/apple.c F: drivers/nvmem/apple-efuses.c F: drivers/nvmem/apple-spmi-nvmem.c +F: drivers/phy/apple/ F: drivers/pinctrl/pinctrl-apple-gpio.c F: drivers/power/reset/macsmc-reboot.c F: drivers/pwm/pwm-apple.c +F: drivers/rtc/rtc-macsmc.c F: drivers/soc/apple/* F: drivers/spi/spi-apple.c F: drivers/spmi/spmi-apple-controller.c +F: drivers/usb/dwc3/dwc3-apple.c F: drivers/video/backlight/apple_dwi_bl.c F: drivers/watchdog/apple_wdt.c F: include/dt-bindings/interrupt-controller/apple-aic.h @@ -17420,6 +17439,8 @@ F: include/linux/module*.h F: kernel/module/ F: lib/test_kmod.c F: lib/tests/module/ +F: rust/kernel/module_param.rs +F: rust/macros/module.rs F: scripts/module* F: tools/testing/selftests/kmod/ F: tools/testing/selftests/module/ diff --git a/Makefile b/Makefile index a082a1d7c7d9b4..e4aa2e76ea563a 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 18 -SUBLEVEL = 0 +SUBLEVEL = 15 EXTRAVERSION = NAME = Baby Opossum Posse @@ -1440,6 +1440,15 @@ ifneq ($(wildcard $(resolve_btfids_O)),) $(Q)$(MAKE) -sC $(srctree)/tools/bpf/resolve_btfids O=$(resolve_btfids_O) clean endif +PHONY += objtool_clean + +objtool_O = $(abspath $(objtree))/tools/objtool + +objtool_clean: +ifneq ($(wildcard $(objtool_O)),) + $(Q)$(MAKE) -sC $(abs_srctree)/tools/objtool O=$(objtool_O) srctree=$(abs_srctree) clean +endif + tools/: FORCE $(Q)mkdir -p $(objtree)/tools $(Q)$(MAKE) O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/ @@ -1590,7 +1599,8 @@ MRPROPER_FILES += include/config include/generated \ certs/x509.genkey \ vmlinux-gdb.py \ rpmbuild \ - rust/libmacros.so rust/libmacros.dylib + rust/libmacros.so rust/libmacros.dylib \ + rust/libpin_init_internal.so rust/libpin_init_internal.dylib # clean - Delete most, but leave enough to build external modules # @@ -1602,7 +1612,7 @@ vmlinuxclean: $(Q)$(CONFIG_SHELL) $(srctree)/scripts/link-vmlinux.sh clean $(Q)$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) clean) -clean: archclean vmlinuxclean resolve_btfids_clean +clean: archclean vmlinuxclean resolve_btfids_clean objtool_clean # mrproper - Delete all generated files, including .config # diff --git a/arch/alpha/include/uapi/asm/ioctls.h b/arch/alpha/include/uapi/asm/ioctls.h index 971311605288fa..a09d04b49cc658 100644 --- a/arch/alpha/include/uapi/asm/ioctls.h +++ b/arch/alpha/include/uapi/asm/ioctls.h @@ -23,10 +23,10 @@ #define TCSETSW _IOW('t', 21, struct termios) #define TCSETSF _IOW('t', 22, struct termios) -#define TCGETA _IOR('t', 23, struct termio) -#define TCSETA _IOW('t', 24, struct termio) -#define TCSETAW _IOW('t', 25, struct termio) -#define TCSETAF _IOW('t', 28, struct termio) +#define TCGETA 0x40127417 +#define TCSETA 0x80127418 +#define TCSETAW 0x80127419 +#define TCSETAF 0x8012741c #define TCSBRK _IO('t', 29) #define TCXONC _IO('t', 30) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 4fb985b76e97f7..70cd3b5b5a0599 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1215,7 +1215,7 @@ config HIGHMEM config HIGHPTE bool "Allocate 2nd-level pagetables from highmem" if EXPERT - depends on HIGHMEM + depends on HIGHMEM && !PREEMPT_RT default y help The VM uses one page of physical memory for each page table. diff --git a/arch/arm/boot/dts/allwinner/sun5i-a13-utoo-p66.dts b/arch/arm/boot/dts/allwinner/sun5i-a13-utoo-p66.dts index be486d28d04fae..428cab5a0e906e 100644 --- a/arch/arm/boot/dts/allwinner/sun5i-a13-utoo-p66.dts +++ b/arch/arm/boot/dts/allwinner/sun5i-a13-utoo-p66.dts @@ -102,6 +102,7 @@ /* The P66 uses a different EINT then the reference design */ interrupts = <6 9 IRQ_TYPE_EDGE_FALLING>; /* EINT9 (PG9) */ /* The icn8318 binding expects wake-gpios instead of power-gpios */ + /delete-property/ power-gpios; wake-gpios = <&pio 1 3 GPIO_ACTIVE_HIGH>; /* PB3 */ touchscreen-size-x = <800>; touchscreen-size-y = <480>; diff --git a/arch/arm/boot/dts/microchip/sama5d2.dtsi b/arch/arm/boot/dts/microchip/sama5d2.dtsi index 17430d7f20555f..fde890f18d201b 100644 --- a/arch/arm/boot/dts/microchip/sama5d2.dtsi +++ b/arch/arm/boot/dts/microchip/sama5d2.dtsi @@ -571,7 +571,7 @@ AT91_XDMAC_DT_PER_IF(1) | AT91_XDMAC_DT_PERID(12))>; dma-names = "tx", "rx"; - atmel,fifo-size = <16>; + atmel,fifo-size = <32>; status = "disabled"; }; @@ -642,7 +642,7 @@ AT91_XDMAC_DT_PER_IF(1) | AT91_XDMAC_DT_PERID(14))>; dma-names = "tx", "rx"; - atmel,fifo-size = <16>; + atmel,fifo-size = <32>; status = "disabled"; }; @@ -854,7 +854,7 @@ AT91_XDMAC_DT_PER_IF(1) | AT91_XDMAC_DT_PERID(16))>; dma-names = "tx", "rx"; - atmel,fifo-size = <16>; + atmel,fifo-size = <32>; status = "disabled"; }; @@ -925,7 +925,7 @@ AT91_XDMAC_DT_PER_IF(1) | AT91_XDMAC_DT_PERID(18))>; dma-names = "tx", "rx"; - atmel,fifo-size = <16>; + atmel,fifo-size = <32>; status = "disabled"; }; @@ -997,7 +997,7 @@ AT91_XDMAC_DT_PER_IF(1) | AT91_XDMAC_DT_PERID(20))>; dma-names = "tx", "rx"; - atmel,fifo-size = <16>; + atmel,fifo-size = <32>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/microchip/sama7d65.dtsi b/arch/arm/boot/dts/microchip/sama7d65.dtsi index e53e2dd6d530c0..868045c650a733 100644 --- a/arch/arm/boot/dts/microchip/sama7d65.dtsi +++ b/arch/arm/boot/dts/microchip/sama7d65.dtsi @@ -527,7 +527,7 @@ interrupts = ; clocks = <&pmc PMC_TYPE_PERIPHERAL 37>; #address-cells = <1>; - #size-cells = <1>; + #size-cells = <0>; dmas = <&dma0 AT91_XDMAC_DT_PERID(12)>, <&dma0 AT91_XDMAC_DT_PERID(11)>; dma-names = "tx", "rx"; @@ -557,7 +557,7 @@ dma-names = "tx", "rx"; atmel,use-dma-rx; atmel,use-dma-tx; - atmel,fifo-size = <16>; + atmel,fifo-size = <32>; atmel,usart-mode = ; status = "disabled"; }; @@ -618,7 +618,7 @@ clocks = <&pmc PMC_TYPE_PERIPHERAL 40>; clock-names = "usart"; atmel,usart-mode = ; - atmel,fifo-size = <16>; + atmel,fifo-size = <32>; status = "disabled"; }; }; @@ -643,7 +643,7 @@ dma-names = "tx", "rx"; atmel,use-dma-rx; atmel,use-dma-tx; - atmel,fifo-size = <16>; + atmel,fifo-size = <32>; atmel,usart-mode = ; status = "disabled"; }; @@ -676,7 +676,7 @@ flx9: flexcom@e2820000 { compatible = "microchip,sama7d65-flexcom", "atmel,sama5d2-flexcom"; reg = <0xe2820000 0x200>; - ranges = <0x0 0xe281c000 0x800>; + ranges = <0x0 0xe2820000 0x800>; clocks = <&pmc PMC_TYPE_PERIPHERAL 43>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/microchip/sama7g5.dtsi b/arch/arm/boot/dts/microchip/sama7g5.dtsi index 381cbcfcb34a14..03ef3d9aaeec62 100644 --- a/arch/arm/boot/dts/microchip/sama7g5.dtsi +++ b/arch/arm/boot/dts/microchip/sama7g5.dtsi @@ -824,7 +824,7 @@ dma-names = "tx", "rx"; atmel,use-dma-rx; atmel,use-dma-tx; - atmel,fifo-size = <16>; + atmel,fifo-size = <32>; status = "disabled"; }; }; @@ -850,7 +850,7 @@ dma-names = "tx", "rx"; atmel,use-dma-rx; atmel,use-dma-tx; - atmel,fifo-size = <16>; + atmel,fifo-size = <32>; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-ba16.dtsi b/arch/arm/boot/dts/nxp/imx/imx6q-ba16.dtsi index 53013b12c2ecbf..02d66523668d26 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6q-ba16.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6q-ba16.dtsi @@ -337,7 +337,7 @@ pinctrl-0 = <&pinctrl_rtc>; reg = <0x32>; interrupt-parent = <&gpio4>; - interrupts = <10 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <10 IRQ_TYPE_LEVEL_LOW>; }; }; diff --git a/arch/arm/boot/dts/nxp/lpc/lpc32xx.dtsi b/arch/arm/boot/dts/nxp/lpc/lpc32xx.dtsi index 2236901a003130..8e9ed93da129e8 100644 --- a/arch/arm/boot/dts/nxp/lpc/lpc32xx.dtsi +++ b/arch/arm/boot/dts/nxp/lpc/lpc32xx.dtsi @@ -302,6 +302,7 @@ mpwm: pwm@400e8000 { compatible = "nxp,lpc3220-motor-pwm"; reg = <0x400e8000 0x78>; + clocks = <&clk LPC32XX_CLK_MCPWM>; #pwm-cells = <3>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/renesas/r8a7793-gose.dts b/arch/arm/boot/dts/renesas/r8a7793-gose.dts index 45b267ec267943..5c6928c941aca9 100644 --- a/arch/arm/boot/dts/renesas/r8a7793-gose.dts +++ b/arch/arm/boot/dts/renesas/r8a7793-gose.dts @@ -373,7 +373,6 @@ port@3 { reg = <3>; adv7180_out: endpoint { - bus-width = <8>; remote-endpoint = <&vin1ep>; }; }; diff --git a/arch/arm/boot/dts/renesas/r9a06g032-rzn1d400-db.dts b/arch/arm/boot/dts/renesas/r9a06g032-rzn1d400-db.dts index 3258b2e274346d..4a72aa7663f252 100644 --- a/arch/arm/boot/dts/renesas/r9a06g032-rzn1d400-db.dts +++ b/arch/arm/boot/dts/renesas/r9a06g032-rzn1d400-db.dts @@ -308,8 +308,6 @@ &switch { status = "okay"; - #address-cells = <1>; - #size-cells = <0>; pinctrl-names = "default"; pinctrl-0 = <&pins_eth3>, <&pins_eth4>, <&pins_mdio1>; diff --git a/arch/arm/boot/dts/samsung/exynos4210-i9100.dts b/arch/arm/boot/dts/samsung/exynos4210-i9100.dts index df229fb8a16beb..8a635bee59fa9b 100644 --- a/arch/arm/boot/dts/samsung/exynos4210-i9100.dts +++ b/arch/arm/boot/dts/samsung/exynos4210-i9100.dts @@ -853,6 +853,7 @@ #size-cells = <0>; non-removable; + cap-power-off-card; bus-width = <4>; mmc-pwrseq = <&wlan_pwrseq>; vmmc-supply = <&vtf_reg>; diff --git a/arch/arm/boot/dts/samsung/exynos4210-trats.dts b/arch/arm/boot/dts/samsung/exynos4210-trats.dts index 95e0e01b6ff6b7..6bd902cb8f4ad2 100644 --- a/arch/arm/boot/dts/samsung/exynos4210-trats.dts +++ b/arch/arm/boot/dts/samsung/exynos4210-trats.dts @@ -518,6 +518,7 @@ #size-cells = <0>; non-removable; + cap-power-off-card; bus-width = <4>; mmc-pwrseq = <&wlan_pwrseq>; vmmc-supply = <&tflash_reg>; diff --git a/arch/arm/boot/dts/samsung/exynos4210-universal_c210.dts b/arch/arm/boot/dts/samsung/exynos4210-universal_c210.dts index bdc30f8cf748f5..91490693432b68 100644 --- a/arch/arm/boot/dts/samsung/exynos4210-universal_c210.dts +++ b/arch/arm/boot/dts/samsung/exynos4210-universal_c210.dts @@ -610,6 +610,7 @@ #size-cells = <0>; non-removable; + cap-power-off-card; bus-width = <4>; mmc-pwrseq = <&wlan_pwrseq>; vmmc-supply = <&ldo5_reg>; diff --git a/arch/arm/boot/dts/samsung/exynos4412-midas.dtsi b/arch/arm/boot/dts/samsung/exynos4412-midas.dtsi index 05ddddb565ee36..48245b1665a69c 100644 --- a/arch/arm/boot/dts/samsung/exynos4412-midas.dtsi +++ b/arch/arm/boot/dts/samsung/exynos4412-midas.dtsi @@ -1440,6 +1440,7 @@ #address-cells = <1>; #size-cells = <0>; non-removable; + cap-power-off-card; bus-width = <4>; mmc-pwrseq = <&wlan_pwrseq>; diff --git a/arch/arm/boot/dts/st/stm32mp157c-phycore-stm32mp15-som.dtsi b/arch/arm/boot/dts/st/stm32mp157c-phycore-stm32mp15-som.dtsi index bf0c32027baf76..370b2afbf15bf0 100644 --- a/arch/arm/boot/dts/st/stm32mp157c-phycore-stm32mp15-som.dtsi +++ b/arch/arm/boot/dts/st/stm32mp157c-phycore-stm32mp15-som.dtsi @@ -185,13 +185,13 @@ interrupt-parent = <&gpioi>; vio-supply = <&v3v3>; vcc-supply = <&v3v3>; + st,sample-time = <4>; + st,mod-12b = <1>; + st,ref-sel = <0>; + st,adc-freq = <1>; touchscreen { compatible = "st,stmpe-ts"; - st,sample-time = <4>; - st,mod-12b = <1>; - st,ref-sel = <0>; - st,adc-freq = <1>; st,ave-ctrl = <1>; st,touch-det-delay = <2>; st,settling = <2>; diff --git a/arch/arm/boot/dts/ti/omap/am335x-bone-common.dtsi b/arch/arm/boot/dts/ti/omap/am335x-bone-common.dtsi index ad1e60a9b6fde8..b75dabfa56ae76 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-bone-common.dtsi +++ b/arch/arm/boot/dts/ti/omap/am335x-bone-common.dtsi @@ -16,7 +16,7 @@ }; chosen { - stdout-path = &uart0; + stdout-path = "serial0:115200n8"; }; leds { diff --git a/arch/arm/boot/dts/ti/omap/am335x-boneblue.dts b/arch/arm/boot/dts/ti/omap/am335x-boneblue.dts index f579df4c2c540d..d430f0bef16537 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-boneblue.dts +++ b/arch/arm/boot/dts/ti/omap/am335x-boneblue.dts @@ -13,7 +13,7 @@ compatible = "ti,am335x-bone-blue", "ti,am33xx"; chosen { - stdout-path = &uart0; + stdout-path = "serial0:115200n8"; }; leds { diff --git a/arch/arm/boot/dts/ti/omap/am335x-chiliboard.dts b/arch/arm/boot/dts/ti/omap/am335x-chiliboard.dts index 648e97fe1dfd5e..ae5bc589849722 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-chiliboard.dts +++ b/arch/arm/boot/dts/ti/omap/am335x-chiliboard.dts @@ -12,7 +12,7 @@ "ti,am33xx"; chosen { - stdout-path = &uart0; + stdout-path = "serial0:115200n8"; }; leds { diff --git a/arch/arm/boot/dts/ti/omap/am335x-evm.dts b/arch/arm/boot/dts/ti/omap/am335x-evm.dts index 20222f82f21bfd..856fa1191ed24e 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-evm.dts +++ b/arch/arm/boot/dts/ti/omap/am335x-evm.dts @@ -23,7 +23,7 @@ }; chosen { - stdout-path = &uart0; + stdout-path = "serial0:115200n8"; }; vbat: fixedregulator0 { diff --git a/arch/arm/boot/dts/ti/omap/am335x-evmsk.dts b/arch/arm/boot/dts/ti/omap/am335x-evmsk.dts index eba888dcd60e7f..d8baccdf8bc463 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-evmsk.dts +++ b/arch/arm/boot/dts/ti/omap/am335x-evmsk.dts @@ -30,7 +30,7 @@ }; chosen { - stdout-path = &uart0; + stdout-path = "serial0:115200n8"; }; vbat: fixedregulator0 { diff --git a/arch/arm/boot/dts/ti/omap/am335x-guardian.dts b/arch/arm/boot/dts/ti/omap/am335x-guardian.dts index 4b070e634b2810..6ce3a2d029eedc 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-guardian.dts +++ b/arch/arm/boot/dts/ti/omap/am335x-guardian.dts @@ -14,7 +14,7 @@ compatible = "bosch,am335x-guardian", "ti,am33xx"; chosen { - stdout-path = &uart0; + stdout-path = "serial0:115200n8"; tick-timer = &timer2; }; diff --git a/arch/arm/boot/dts/ti/omap/am335x-icev2.dts b/arch/arm/boot/dts/ti/omap/am335x-icev2.dts index 6f0f4fba043b96..ba488bba6925de 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-icev2.dts +++ b/arch/arm/boot/dts/ti/omap/am335x-icev2.dts @@ -22,7 +22,7 @@ }; chosen { - stdout-path = &uart3; + stdout-path = "serial3:115200n8"; }; vbat: fixedregulator0 { diff --git a/arch/arm/boot/dts/ti/omap/am335x-myirtech-myd.dts b/arch/arm/boot/dts/ti/omap/am335x-myirtech-myd.dts index 06a352f98b220b..476a6bdaf43f38 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-myirtech-myd.dts +++ b/arch/arm/boot/dts/ti/omap/am335x-myirtech-myd.dts @@ -15,7 +15,7 @@ compatible = "myir,myd-am335x", "myir,myc-am335x", "ti,am33xx"; chosen { - stdout-path = &uart0; + stdout-path = "serial0:115200n8"; }; clk12m: clk12m { diff --git a/arch/arm/boot/dts/ti/omap/am335x-netcom-plus-2xx.dts b/arch/arm/boot/dts/ti/omap/am335x-netcom-plus-2xx.dts index f66d57bb685ee1..f0519ab3014160 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-netcom-plus-2xx.dts +++ b/arch/arm/boot/dts/ti/omap/am335x-netcom-plus-2xx.dts @@ -222,10 +222,10 @@ "ModeA1", "ModeA2", "ModeA3", - "NC", - "NC", - "NC", - "NC", + "ModeB0", + "ModeB1", + "ModeB2", + "ModeB3", "NC", "NC", "NC", diff --git a/arch/arm/boot/dts/ti/omap/am335x-osd3358-sm-red.dts b/arch/arm/boot/dts/ti/omap/am335x-osd3358-sm-red.dts index d28d3972884765..23caaaabf35134 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-osd3358-sm-red.dts +++ b/arch/arm/boot/dts/ti/omap/am335x-osd3358-sm-red.dts @@ -147,7 +147,7 @@ }; chosen { - stdout-path = &uart0; + stdout-path = "serial0:115200n8"; }; leds { diff --git a/arch/arm/boot/dts/ti/omap/am335x-pdu001.dts b/arch/arm/boot/dts/ti/omap/am335x-pdu001.dts index c9ccb9de21ad7b..9f611debc20907 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-pdu001.dts +++ b/arch/arm/boot/dts/ti/omap/am335x-pdu001.dts @@ -21,7 +21,7 @@ compatible = "ti,am33xx"; chosen { - stdout-path = &uart3; + stdout-path = "serial3:115200n8"; }; cpus { diff --git a/arch/arm/boot/dts/ti/omap/am335x-pocketbeagle.dts b/arch/arm/boot/dts/ti/omap/am335x-pocketbeagle.dts index 78ce860e59b3de..24d9f90fad01f7 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-pocketbeagle.dts +++ b/arch/arm/boot/dts/ti/omap/am335x-pocketbeagle.dts @@ -15,7 +15,7 @@ compatible = "ti,am335x-pocketbeagle", "ti,am335x-bone", "ti,am33xx"; chosen { - stdout-path = &uart0; + stdout-path = "serial0:115200n8"; }; leds { diff --git a/arch/arm/boot/dts/ti/omap/am335x-sl50.dts b/arch/arm/boot/dts/ti/omap/am335x-sl50.dts index f3524e5ee43e27..1dc4e344efd63e 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-sl50.dts +++ b/arch/arm/boot/dts/ti/omap/am335x-sl50.dts @@ -25,7 +25,7 @@ }; chosen { - stdout-path = &uart0; + stdout-path = "serial0:115200n8"; }; leds { diff --git a/arch/arm/boot/dts/ti/omap/omap3-beagle-xm.dts b/arch/arm/boot/dts/ti/omap/omap3-beagle-xm.dts index 08ee0f8ea68fda..71b39a923d37c6 100644 --- a/arch/arm/boot/dts/ti/omap/omap3-beagle-xm.dts +++ b/arch/arm/boot/dts/ti/omap/omap3-beagle-xm.dts @@ -291,7 +291,7 @@ }; twl_power: power { - compatible = "ti,twl4030-power-beagleboard-xm", "ti,twl4030-power-idle-osc-off"; + compatible = "ti,twl4030-power-idle-osc-off"; ti,use_poweroff; }; }; diff --git a/arch/arm/boot/dts/ti/omap/omap3-n900.dts b/arch/arm/boot/dts/ti/omap/omap3-n900.dts index c50ca572d1b9b5..7db73d9bed9e4b 100644 --- a/arch/arm/boot/dts/ti/omap/omap3-n900.dts +++ b/arch/arm/boot/dts/ti/omap/omap3-n900.dts @@ -508,7 +508,7 @@ }; twl_power: power { - compatible = "ti,twl4030-power-n900", "ti,twl4030-power-idle-osc-off"; + compatible = "ti,twl4030-power-idle-osc-off"; ti,use_poweroff; }; }; diff --git a/arch/arm/include/asm/string.h b/arch/arm/include/asm/string.h index 6c607c68f3ad75..c35250c4991bc7 100644 --- a/arch/arm/include/asm/string.h +++ b/arch/arm/include/asm/string.h @@ -42,7 +42,10 @@ static inline void *memset32(uint32_t *p, uint32_t v, __kernel_size_t n) extern void *__memset64(uint64_t *, uint32_t low, __kernel_size_t, uint32_t hi); static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n) { - return __memset64(p, v, n * 8, v >> 32); + if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) + return __memset64(p, v, n * 8, v >> 32); + else + return __memset64(p, v >> 32, n * 8, v); } /* diff --git a/arch/arm/include/asm/word-at-a-time.h b/arch/arm/include/asm/word-at-a-time.h index f9a3897b06e7ff..5023f98d8293d5 100644 --- a/arch/arm/include/asm/word-at-a-time.h +++ b/arch/arm/include/asm/word-at-a-time.h @@ -67,7 +67,7 @@ static inline unsigned long find_zero(unsigned long mask) */ static inline unsigned long load_unaligned_zeropad(const void *addr) { - unsigned long ret, offset; + unsigned long ret, tmp; /* Load word from unaligned pointer addr */ asm( @@ -75,9 +75,9 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) "2:\n" " .pushsection .text.fixup,\"ax\"\n" " .align 2\n" - "3: and %1, %2, #0x3\n" - " bic %2, %2, #0x3\n" - " ldr %0, [%2]\n" + "3: bic %1, %2, #0x3\n" + " ldr %0, [%1]\n" + " and %1, %2, #0x3\n" " lsl %1, %1, #0x3\n" #ifndef __ARMEB__ " lsr %0, %0, %1\n" @@ -90,7 +90,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) " .align 3\n" " .long 1b, 3b\n" " .popsection" - : "=&r" (ret), "=&r" (offset) + : "=&r" (ret), "=&r" (tmp) : "r" (addr), "Qo" (*(unsigned long *)addr)); return ret; diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c index e38a30477f3d70..566c40f0f7c77b 100644 --- a/arch/arm/kernel/vdso.c +++ b/arch/arm/kernel/vdso.c @@ -161,6 +161,7 @@ static void __init patch_vdso(void *ehdr) vdso_nullpatch_one(&einfo, "__vdso_gettimeofday"); vdso_nullpatch_one(&einfo, "__vdso_clock_gettime"); vdso_nullpatch_one(&einfo, "__vdso_clock_gettime64"); + vdso_nullpatch_one(&einfo, "__vdso_clock_getres"); } } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 6663ffd23f252e..5a97bc145a980a 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -443,6 +443,9 @@ config KASAN_SHADOW_OFFSET config UNWIND_TABLES bool +config ARM64_ACTLR_STATE + bool + source "arch/arm64/Kconfig.platforms" menu "Kernel Features" @@ -2268,6 +2271,16 @@ config ARM64_DEBUG_PRIORITY_MASKING If unsure, say N endif # ARM64_PSEUDO_NMI +config ARM64_MEMORY_MODEL_CONTROL + bool "Runtime memory model control" + select ARM64_ACTLR_STATE + help + Some ARM64 CPUs support runtime switching of the CPU memory + model, which can be useful to emulate other CPU architectures + which have different memory models. Say Y to enable support + for the PR_SET_MEM_MODEL/PR_GET_MEM_MODEL prctl() calls on + CPUs with this feature. + config RELOCATABLE bool "Build a relocatable kernel image" if EXPERT select ARCH_HAS_RELR diff --git a/arch/arm64/boot/dts/amlogic/amlogic-c3.dtsi b/arch/arm64/boot/dts/amlogic/amlogic-c3.dtsi index 07aaaf71ea9aed..f226df3ce153ba 100644 --- a/arch/arm64/boot/dts/amlogic/amlogic-c3.dtsi +++ b/arch/arm64/boot/dts/amlogic/amlogic-c3.dtsi @@ -969,6 +969,10 @@ no-sd; resets = <&reset RESET_SD_EMMC_A>; status = "disabled"; + + assigned-clocks = <&clkc_periphs CLKID_SD_EMMC_A>; + assigned-clock-rates = <24000000>; + }; sd: mmc@8a000 { @@ -984,6 +988,9 @@ no-sdio; resets = <&reset RESET_SD_EMMC_B>; status = "disabled"; + + assigned-clocks = <&clkc_periphs CLKID_SD_EMMC_B>; + assigned-clock-rates = <24000000>; }; nand: nand-controller@8d000 { diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi index 04fb130ac7c6a4..bbf94a1f92a107 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi @@ -1960,6 +1960,9 @@ <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_B>; + + assigned-clocks = <&clkc CLKID_SD_EMMC_B_CLK0>; + assigned-clock-rates = <24000000>; }; sd_emmc_c: mmc@7000 { @@ -1972,6 +1975,9 @@ <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_C>; + + assigned-clocks = <&clkc CLKID_SD_EMMC_C_CLK0>; + assigned-clock-rates = <24000000>; }; nfc: nand-controller@7800 { diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index dcc927a9da8024..8d8ab775404d91 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -2431,6 +2431,9 @@ <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_A>; + + assigned-clocks = <&clkc CLKID_SD_EMMC_A_CLK0>; + assigned-clock-rates = <24000000>; }; sd_emmc_b: mmc@ffe05000 { @@ -2443,6 +2446,9 @@ <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_B>; + + assigned-clocks = <&clkc CLKID_SD_EMMC_B_CLK0>; + assigned-clock-rates = <24000000>; }; sd_emmc_c: mmc@ffe07000 { @@ -2455,6 +2461,9 @@ <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_C>; + + assigned-clocks = <&clkc CLKID_SD_EMMC_C_CLK0>; + assigned-clock-rates = <24000000>; }; usb: usb@ffe09000 { diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b.dtsi index f04efa8282561c..23358d94844c94 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12b.dtsi @@ -87,7 +87,7 @@ i-cache-line-size = <32>; i-cache-size = <0x8000>; i-cache-sets = <32>; - next-level-cache = <&l2_cache_l>; + next-level-cache = <&l2_cache_b>; #cooling-cells = <2>; }; @@ -103,7 +103,7 @@ i-cache-line-size = <32>; i-cache-size = <0x8000>; i-cache-sets = <32>; - next-level-cache = <&l2_cache_l>; + next-level-cache = <&l2_cache_b>; #cooling-cells = <2>; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi index f69923da07febd..a9c830a570cc6c 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi @@ -824,6 +824,9 @@ <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_A>; + + assigned-clocks = <&clkc CLKID_SD_EMMC_A_CLK0>; + assigned-clock-rates = <24000000>; }; &sd_emmc_b { @@ -832,6 +835,9 @@ <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_B>; + + assigned-clocks = <&clkc CLKID_SD_EMMC_B_CLK0>; + assigned-clock-rates = <24000000>; }; &sd_emmc_c { @@ -840,6 +846,9 @@ <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_C>; + + assigned-clocks = <&clkc CLKID_SD_EMMC_C_CLK0>; + assigned-clock-rates = <24000000>; }; &simplefb_hdmi { diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index ba535010a3c91d..e202d84f067205 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -894,6 +894,9 @@ <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_A>; + + assigned-clocks = <&clkc CLKID_SD_EMMC_A_CLK0>; + assigned-clock-rates = <24000000>; }; &sd_emmc_b { @@ -902,6 +905,9 @@ <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_B>; + + assigned-clocks = <&clkc CLKID_SD_EMMC_B_CLK0>; + assigned-clock-rates = <24000000>; }; &sd_emmc_c { @@ -910,6 +916,9 @@ <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_C>; + + assigned-clocks = <&clkc CLKID_SD_EMMC_C_CLK0>; + assigned-clock-rates = <24000000>; }; &simplefb_hdmi { diff --git a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi index 9d99ed2994dfa2..dfc0a30a6e61be 100644 --- a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi @@ -819,13 +819,16 @@ reg = <0x0 0xfe088000 0x0 0x800>; interrupts = ; clocks = <&clkc_periphs CLKID_SDEMMC_A>, - <&xtal>, + <&clkc_periphs CLKID_SD_EMMC_A>, <&clkc_pll CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_A>; cap-sdio-irq; keep-power-in-suspend; status = "disabled"; + + assigned-clocks = <&clkc_periphs CLKID_SD_EMMC_A>; + assigned-clock-rates = <24000000>; }; sd: mmc@fe08a000 { @@ -838,6 +841,9 @@ clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_B>; status = "disabled"; + + assigned-clocks = <&clkc_periphs CLKID_SD_EMMC_B>; + assigned-clock-rates = <24000000>; }; emmc: mmc@fe08c000 { @@ -845,13 +851,16 @@ reg = <0x0 0xfe08c000 0x0 0x800>; interrupts = ; clocks = <&clkc_periphs CLKID_NAND>, - <&xtal>, + <&clkc_periphs CLKID_SD_EMMC_C>, <&clkc_pll CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_NAND_EMMC>; no-sdio; no-sd; status = "disabled"; + + assigned-clocks = <&clkc_periphs CLKID_SD_EMMC_C>; + assigned-clock-rates = <24000000>; }; }; }; diff --git a/arch/arm64/boot/dts/apple/Makefile b/arch/arm64/boot/dts/apple/Makefile index 4eebcd85c90fcf..d253f08c98329e 100644 --- a/arch/arm64/boot/dts/apple/Makefile +++ b/arch/arm64/boot/dts/apple/Makefile @@ -91,3 +91,6 @@ dtb-$(CONFIG_ARCH_APPLE) += t8112-j413.dtb dtb-$(CONFIG_ARCH_APPLE) += t8112-j415.dtb dtb-$(CONFIG_ARCH_APPLE) += t8112-j473.dtb dtb-$(CONFIG_ARCH_APPLE) += t8112-j493.dtb +dtb-$(CONFIG_ARCH_APPLE) += t8122-j433.dtb +dtb-$(CONFIG_ARCH_APPLE) += t8122-j434.dtb +dtb-$(CONFIG_ARCH_APPLE) += t8122-j504.dtb diff --git a/arch/arm64/boot/dts/apple/hwmon-common.dtsi b/arch/arm64/boot/dts/apple/hwmon-common.dtsi new file mode 100644 index 00000000000000..2a74d9a114abb6 --- /dev/null +++ b/arch/arm64/boot/dts/apple/hwmon-common.dtsi @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * hwmon sensors expected on all systems + * + * Copyright The Asahi Linux Contributors + */ + +&smc_hwmon { + power-PSTR { + apple,key-id = "PSTR"; + label = "Total System Power"; + }; + power-PDTR { + apple,key-id = "PDTR"; + label = "AC Input Power"; + }; + power-PMVR { + apple,key-id = "PMVR"; + label = "3.8 V Rail Power"; + }; + temperature-TH0x { + apple,key-id = "TH0x"; + label = "NAND Flash Temperature"; + }; + voltage-VD0R { + apple,key-id = "VD0R"; + label = "AC Input Voltage"; + }; + current-ID0R { + apple,key-id = "ID0R"; + label = "AC Input Current"; + }; +}; diff --git a/arch/arm64/boot/dts/apple/hwmon-fan-dual.dtsi b/arch/arm64/boot/dts/apple/hwmon-fan-dual.dtsi new file mode 100644 index 00000000000000..61c34692f1cd5a --- /dev/null +++ b/arch/arm64/boot/dts/apple/hwmon-fan-dual.dtsi @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * Copyright The Asahi Linux Contributors + * + * Fan hwmon sensors for machines with 2 fan. + */ + +#include "hwmon-fan.dtsi" + +&smc_hwmon { + fan-F0Ac { + label = "Fan 1"; + }; + fan-F1Ac { + apple,key-id = "F1Ac"; + label = "Fan 2"; + apple,fan-minimum = "F1Mn"; + apple,fan-maximum = "F1Mx"; + apple,fan-target = "F1Tg"; + apple,fan-mode = "F1Md"; + }; +}; diff --git a/arch/arm64/boot/dts/apple/hwmon-fan.dtsi b/arch/arm64/boot/dts/apple/hwmon-fan.dtsi new file mode 100644 index 00000000000000..180eb8d7441f44 --- /dev/null +++ b/arch/arm64/boot/dts/apple/hwmon-fan.dtsi @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * Copyright The Asahi Linux Contributors + * + * Fan hwmon sensors for machines with a single fan. + */ + +&smc_hwmon { + fan-F0Ac { + apple,key-id = "F0Ac"; + label = "Fan"; + apple,fan-minimum = "F0Mn"; + apple,fan-maximum = "F0Mx"; + apple,fan-target = "F0Tg"; + apple,fan-mode = "F0Md"; + }; +}; diff --git a/arch/arm64/boot/dts/apple/hwmon-laptop.dtsi b/arch/arm64/boot/dts/apple/hwmon-laptop.dtsi new file mode 100644 index 00000000000000..4afb91ee69fe76 --- /dev/null +++ b/arch/arm64/boot/dts/apple/hwmon-laptop.dtsi @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * hwmon sensors expected on all laptops + * + * Copyright The Asahi Linux Contributors + */ + +&smc_hwmon { + power-PHPC { + apple,key-id = "PHPC"; + label = "Heatpipe Power"; + }; + temperature-TB0T { + apple,key-id = "TB0T"; + label = "Battery Hotspot"; + }; + temperature-TCHP { + apple,key-id = "TCHP"; + label = "Charge Regulator Temp"; + }; + temperature-TW0P { + apple,key-id = "TW0P"; + label = "WiFi/BT Module Temp"; + }; + voltage-SBAV { + apple,key-id = "SBAV"; + label = "Battery Voltage"; + }; + voltage-VD0R { + apple,key-id = "VD0R"; + label = "Charger Input Voltage"; + }; +}; diff --git a/arch/arm64/boot/dts/apple/hwmon-mini.dtsi b/arch/arm64/boot/dts/apple/hwmon-mini.dtsi new file mode 100644 index 00000000000000..7fd86e911acfe7 --- /dev/null +++ b/arch/arm64/boot/dts/apple/hwmon-mini.dtsi @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * hwmon sensors common to the Mac mini desktop + * models, but not the Studio or Pro. + * + * Copyright The Asahi Linux Contributors + */ + +#include "hwmon-fan.dtsi" + +&smc_hwmon { + temperature-TW0P { + apple,key-id = "TW0P"; + label = "WiFi/BT Module Temp"; + }; +}; diff --git a/arch/arm64/boot/dts/apple/isp-common.dtsi b/arch/arm64/boot/dts/apple/isp-common.dtsi new file mode 100644 index 00000000000000..739e6e9e66e740 --- /dev/null +++ b/arch/arm64/boot/dts/apple/isp-common.dtsi @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * Common ISP configuration for Apple silicon platforms. + * + * Copyright The Asahi Linux Contributors + */ + +/ { + aliases { + isp = &isp; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + isp_heap: isp-heap { + compatible = "apple,asc-mem"; + /* Filled in by bootloder */ + reg = <0 0 0 0>; + no-map; + }; + }; +}; + +&isp { + memory-region = <&isp_heap>; + memory-region-names = "heap"; + status = "okay"; +}; + +&isp_dart0 { + status = "okay"; +}; + +&isp_dart1 { + status = "okay"; +}; + +&isp_dart2 { + status = "okay"; +}; + +&ps_isp_sys { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/apple/isp-imx248.dtsi b/arch/arm64/boot/dts/apple/isp-imx248.dtsi new file mode 100644 index 00000000000000..0a4ac1a0152c2c --- /dev/null +++ b/arch/arm64/boot/dts/apple/isp-imx248.dtsi @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * ISP configuration for platforms with IMX248 sensor. + * + * Copyright The Asahi Linux Contributors + */ + +#include "isp-common.dtsi" + +&isp { + apple,temporal-filter = <0>; + + sensor-presets { + /* 1280x720 */ + preset0 { + apple,config-index = <0>; + apple,input-size = <1296 736>; + apple,output-size = <1280 720>; + apple,crop = <8 8 1280 720>; + }; + /* 960x720 (4:3) */ + preset1 { + apple,config-index = <0>; + apple,input-size = <1296 736>; + apple,output-size = <960 720>; + apple,crop = <168 8 960 720>; + }; + /* 960x540 (16:9) */ + preset2 { + apple,config-index = <0>; + apple,input-size = <1296 736>; + apple,output-size = <960 540>; + apple,crop = <8 8 1280 720>; + }; + /* 640x480 (4:3) */ + preset3 { + apple,config-index = <0>; + apple,input-size = <1296 736>; + apple,output-size = <640 480>; + apple,crop = <168 8 960 720>; + }; + /* 640x360 (16:9) */ + preset4 { + apple,config-index = <0>; + apple,input-size = <1296 736>; + apple,output-size = <640 360>; + apple,crop = <8 8 1280 720>; + }; + /* 320x180 (16:9) */ + preset5 { + apple,config-index = <0>; + apple,input-size = <1296 736>; + apple,output-size = <320 180>; + apple,crop = <8 8 1280 720>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/apple/isp-imx364.dtsi b/arch/arm64/boot/dts/apple/isp-imx364.dtsi new file mode 100644 index 00000000000000..55484d86523657 --- /dev/null +++ b/arch/arm64/boot/dts/apple/isp-imx364.dtsi @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * ISP configuration for platforms with IMX364 sensor. + * + * Copyright The Asahi Linux Contributors + */ + +#include "isp-common.dtsi" + +&isp { + apple,temporal-filter = <0>; + + sensor-presets { + /* 1920x1080 */ + preset0 { + apple,config-index = <0>; + apple,input-size = <1920 1080>; + apple,output-size = <1920 1080>; + apple,crop = <0 0 1920 1080>; + }; + /* 1440x720 (4:3) */ + preset1 { + apple,config-index = <0>; + apple,input-size = <1920 1080>; + apple,output-size = <1440 1080>; + apple,crop = <240 0 1440 1080>; + }; + /* 1280x720 (16:9) */ + preset2 { + apple,config-index = <0>; + apple,input-size = <1920 1080>; + apple,output-size = <1280 720>; + apple,crop = <0 0 1920 1080>; + }; + /* 960x720 (4:3) */ + preset3{ + apple,config-index = <0>; + apple,input-size = <1920 1080>; + apple,output-size = <960 720>; + apple,crop = <240 0 1440 1080>; + }; + /* 960x540 (16:9) */ + preset4 { + apple,config-index = <0>; + apple,input-size = <1920 1080>; + apple,output-size = <960 540>; + apple,crop = <0 0 1920 1080>; + }; + /* 640x480 (4:3) */ + preset5 { + apple,config-index = <0>; + apple,input-size = <1920 1080>; + apple,output-size = <640 480>; + apple,crop = <240 0 1440 1080>; + }; + /* 640x360 (16:9) */ + preset6 { + apple,config-index = <0>; + apple,input-size = <1920 1080>; + apple,output-size = <640 360>; + apple,crop = <0 0 1920 1080>; + }; + /* 320x180 (16:9) */ + preset7 { + apple,config-index = <0>; + apple,input-size = <1920 1080>; + apple,output-size = <320 180>; + apple,crop = <0 0 1920 1080>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/apple/isp-imx558-cfg0.dtsi b/arch/arm64/boot/dts/apple/isp-imx558-cfg0.dtsi new file mode 100644 index 00000000000000..729b97829cbb7e --- /dev/null +++ b/arch/arm64/boot/dts/apple/isp-imx558-cfg0.dtsi @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * ISP configuration for platforms with IMX558 sensor in + * config #0 mode. + * + * These platforms enable MLVNR for all configs except + * #0, which we don't support. Config #0 is an uncropped + * square 1920x1920 sensor, with dark corners. + * Therefore, we synthesize common resolutions by using + * crop/scale while always choosing config #0. + * + * Copyright The Asahi Linux Contributors + */ + +#include "isp-common.dtsi" + +&isp { + apple,temporal-filter = <0>; + + sensor-presets { + /* 1920x1080 */ + preset0 { + apple,config-index = <0>; + apple,input-size = <1920 1920>; + apple,output-size = <1920 1080>; + apple,crop = <0 420 1920 1080>; + }; + /* 1080x1920 */ + preset1 { + apple,config-index = <0>; + apple,input-size = <1920 1920>; + apple,output-size = <1080 1920>; + apple,crop = <420 0 1080 1920>; + }; + /* 1920x1440 */ + preset2 { + apple,config-index = <0>; + apple,input-size = <1920 1920>; + apple,output-size = <1920 1440>; + apple,crop = <0 240 1920 1440>; + }; + /* 1440x1920 */ + preset3 { + apple,config-index = <0>; + apple,input-size = <1920 1920>; + apple,output-size = <1440 1920>; + apple,crop = <240 0 1440 1920>; + }; + /* 1280x720 */ + preset4 { + apple,config-index = <0>; + apple,input-size = <1920 1920>; + apple,output-size = <1280 720>; + apple,crop = <0 420 1920 1080>; + }; + /* 720x1280 */ + preset5 { + apple,config-index = <0>; + apple,input-size = <1920 1920>; + apple,output-size = <720 1280>; + apple,crop = <420 0 1080 1920>; + }; + /* 1280x960 */ + preset6 { + apple,config-index = <0>; + apple,input-size = <1920 1920>; + apple,output-size = <1280 960>; + apple,crop = <0 240 1920 1440>; + }; + /* 960x1280 */ + preset7 { + apple,config-index = <0>; + apple,input-size = <1920 1920>; + apple,output-size = <960 1280>; + apple,crop = <240 0 1440 1920>; + }; + /* 640x480 */ + preset8 { + apple,config-index = <0>; + apple,input-size = <1920 1920>; + apple,output-size = <640 480>; + apple,crop = <0 240 1920 1440>; + }; + /* 480x640 */ + preset9 { + apple,config-index = <0>; + apple,input-size = <1920 1920>; + apple,output-size = <480 640>; + apple,crop = <240 0 1440 1920>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/apple/isp-imx558.dtsi b/arch/arm64/boot/dts/apple/isp-imx558.dtsi new file mode 100644 index 00000000000000..d55854c883f5b6 --- /dev/null +++ b/arch/arm64/boot/dts/apple/isp-imx558.dtsi @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * ISP configuration for platforms with IMX558 sensor. + * + * Copyright The Asahi Linux Contributors + */ + +#include "isp-common.dtsi" + +&isp { + apple,temporal-filter = <0>; + + sensor-presets { + /* 1920x1080 */ + preset0 { + apple,config-index = <1>; + apple,input-size = <1920 1080>; + apple,output-size = <1920 1080>; + apple,crop = <0 0 1920 1080>; + }; + /* 1080x1920 */ + preset1 { + apple,config-index = <2>; + apple,input-size = <1080 1920>; + apple,output-size = <1080 1920>; + apple,crop = <0 0 1080 1920>; + }; + /* 1760x1328 */ + preset2 { + apple,config-index = <3>; + apple,input-size = <1760 1328>; + apple,output-size = <1760 1328>; + apple,crop = <0 0 1760 1328>; + }; + /* 1328x1760 */ + preset3 { + apple,config-index = <4>; + apple,input-size = <1328 1760>; + apple,output-size = < 1328 1760>; + apple,crop = <0 0 1328 1760>; + }; + /* 1152x1152 */ + preset4 { + apple,config-index = <5>; + apple,input-size = <1152 1152>; + apple,output-size = <1152 1152>; + apple,crop = <0 0 1152 1152>; + }; + /* 1280x720 */ + preset5 { + apple,config-index = <1>; + apple,input-size = <1920 1080>; + apple,output-size = <1280 720>; + apple,crop = <0 0 1920 1080>; + }; + /* 720x1280 */ + preset6 { + apple,config-index = <2>; + apple,input-size = <1080 1920>; + apple,output-size = <720 1280>; + apple,crop = <0 0 1080 1920>; + }; + /* 1280x960 */ + preset7 { + apple,config-index = <3>; + apple,input-size = <1760 1328>; + apple,output-size = <1280 960>; + apple,crop = <0 4 1760 1320>; + }; + /* 960x1280 */ + preset8 { + apple,config-index = <4>; + apple,input-size = <1328 1760>; + apple,output-size = <960 1280>; + apple,crop = <4 0 1320 1760>; + }; + /* 640x480 */ + preset9 { + apple,config-index = <3>; + apple,input-size = <1760 1328>; + apple,output-size = <640 480>; + apple,crop = <0 4 1760 1320>; + }; + /* 480x640 */ + preset10 { + apple,config-index = <4>; + apple,input-size = <1328 1760>; + apple,output-size = <480 640>; + apple,crop = <4 0 1320 1760>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/apple/t6000-j314s.dts b/arch/arm64/boot/dts/apple/t6000-j314s.dts index 1430b91ff1b152..afa86668440f04 100644 --- a/arch/arm64/boot/dts/apple/t6000-j314s.dts +++ b/arch/arm64/boot/dts/apple/t6000-j314s.dts @@ -24,3 +24,20 @@ &bluetooth0 { brcm,board-type = "apple,maldives"; }; + +&panel { + compatible = "apple,panel-j314", "apple,panel-mini-led", "apple,panel"; + width-mm = <302>; + height-mm = <196>; + adj-height-mm = <189>; +}; + +&aop_audio { + apple,chassis-name = "J314"; + apple,machine-kind = "MacBook Pro"; +}; + +&sound { + compatible = "apple,j314-macaudio", "apple,macaudio"; + model = "MacBook Pro J314"; +}; diff --git a/arch/arm64/boot/dts/apple/t6000-j316s.dts b/arch/arm64/boot/dts/apple/t6000-j316s.dts index da0cbe7d96736b..ddfc3c530923c7 100644 --- a/arch/arm64/boot/dts/apple/t6000-j316s.dts +++ b/arch/arm64/boot/dts/apple/t6000-j316s.dts @@ -24,3 +24,20 @@ &bluetooth0 { brcm,board-type = "apple,madagascar"; }; + +&panel { + compatible = "apple,panel-j316", "apple,panel-mini-led", "apple,panel"; + width-mm = <346>; + height-mm = <223>; + adj-height-mm = <216>; +}; + +&aop_audio { + apple,chassis-name = "J316"; + apple,machine-kind = "MacBook Pro"; +}; + +&sound { + compatible = "apple,j316-macaudio", "apple,macaudio"; + model = "MacBook Pro J316"; +}; diff --git a/arch/arm64/boot/dts/apple/t6000.dtsi b/arch/arm64/boot/dts/apple/t6000.dtsi index 0ad77c98073fe6..c9e4e52d9aac92 100644 --- a/arch/arm64/boot/dts/apple/t6000.dtsi +++ b/arch/arm64/boot/dts/apple/t6000.dtsi @@ -9,6 +9,8 @@ /* This chip is just a cut down version of t6001, so include it and disable the missing parts */ +#define GPU_REPEAT(x) + #include "t6001.dtsi" / { @@ -18,5 +20,5 @@ /delete-node/ &pmgr_south; &gpu { - compatible = "apple,agx-g13s"; + compatible = "apple,agx-t6000", "apple,agx-g13x"; }; diff --git a/arch/arm64/boot/dts/apple/t6001-j314c.dts b/arch/arm64/boot/dts/apple/t6001-j314c.dts index c37097dcfdb304..245df6d03ee422 100644 --- a/arch/arm64/boot/dts/apple/t6001-j314c.dts +++ b/arch/arm64/boot/dts/apple/t6001-j314c.dts @@ -24,3 +24,20 @@ &bluetooth0 { brcm,board-type = "apple,maldives"; }; + +&panel { + compatible = "apple,panel-j314", "apple,panel-mini-led", "apple,panel"; + width-mm = <302>; + height-mm = <196>; + adj-height-mm = <189>; +}; + +&aop_audio { + apple,chassis-name = "J314"; + apple,machine-kind = "MacBook Pro"; +}; + +&sound { + compatible = "apple,j314-macaudio", "apple,macaudio"; + model = "MacBook Pro J314"; +}; diff --git a/arch/arm64/boot/dts/apple/t6001-j316c.dts b/arch/arm64/boot/dts/apple/t6001-j316c.dts index 3bc6e0c3294cf9..a000d497b705fa 100644 --- a/arch/arm64/boot/dts/apple/t6001-j316c.dts +++ b/arch/arm64/boot/dts/apple/t6001-j316c.dts @@ -24,3 +24,20 @@ &bluetooth0 { brcm,board-type = "apple,madagascar"; }; + +&panel { + compatible = "apple,panel-j316", "apple,panel-mini-led", "apple,panel"; + width-mm = <346>; + height-mm = <223>; + adj-height-mm = <216>; +}; + +&aop_audio { + apple,chassis-name = "J316"; + apple,machine-kind = "MacBook Pro"; +}; + +&sound { + compatible = "apple,j316-macaudio", "apple,macaudio"; + model = "MacBook Pro J316"; +}; diff --git a/arch/arm64/boot/dts/apple/t6001-j375c.dts b/arch/arm64/boot/dts/apple/t6001-j375c.dts index 2e7c23714d4d00..f3f98f03800908 100644 --- a/arch/arm64/boot/dts/apple/t6001-j375c.dts +++ b/arch/arm64/boot/dts/apple/t6001-j375c.dts @@ -24,3 +24,39 @@ &bluetooth0 { brcm,board-type = "apple,okinawa"; }; + +&dpaudio0 { + status = "okay"; +}; + +&sound { + compatible = "apple,j375-macaudio", "apple,macaudio"; + model = "Mac Studio J375"; +}; + +&pinctrl_ap { + usb_hub_oe-hog { + gpio-hog; + gpios = <230 0>; + input; + line-name = "usb-hub-oe"; + }; + + usb_hub_rst-hog { + gpio-hog; + gpios = <231 GPIO_ACTIVE_LOW>; + output-low; + line-name = "usb-hub-rst"; + }; +}; + +&gpu { + apple,avg-power-ki-only = <0.6375>; + apple,avg-power-kp = <0.58>; + apple,avg-power-target-filter-tc = <1>; + apple,perf-base-pstate = <3>; + apple,ppm-ki = <5.8>; + apple,ppm-kp = <0.355>; +}; + +#include "hwmon-fan-dual.dtsi" diff --git a/arch/arm64/boot/dts/apple/t6001.dtsi b/arch/arm64/boot/dts/apple/t6001.dtsi index ffbe823b71bc8d..3ac838c9b803b6 100644 --- a/arch/arm64/boot/dts/apple/t6001.dtsi +++ b/arch/arm64/boot/dts/apple/t6001.dtsi @@ -11,10 +11,15 @@ #include #include #include +#include #include #include "multi-die-cpp.h" +#ifndef GPU_REPEAT +# define GPU_REPEAT(x) +#endif + #include "t600x-common.dtsi" / { @@ -27,6 +32,8 @@ ranges; nonposted-mmio; + /* Required to get >32-bit DMA via DARTs */ + dma-ranges = <0 0 0 0 0xffffffff 0xffffc000>; // filled via templated includes at the end of the file }; @@ -64,5 +71,5 @@ }; &gpu { - compatible = "apple,agx-g13c", "apple,agx-g13s"; + compatible = "apple,agx-t6001", "apple,agx-g13c", "apple,agx-g13s"; }; diff --git a/arch/arm64/boot/dts/apple/t6002-j375d.dts b/arch/arm64/boot/dts/apple/t6002-j375d.dts index 2b7f80119618ad..5cf30cd162b679 100644 --- a/arch/arm64/boot/dts/apple/t6002-j375d.dts +++ b/arch/arm64/boot/dts/apple/t6002-j375d.dts @@ -15,6 +15,19 @@ / { compatible = "apple,j375d", "apple,t6002", "apple,arm-platform"; model = "Apple Mac Studio (M1 Ultra, 2022)"; + aliases { + atcphy4 = &atcphy0_die1; + atcphy5 = &atcphy1_die1; + }; +}; + +&dpaudio0 { + status = "okay"; +}; + +&sound { + compatible = "apple,j375-macaudio", "apple,macaudio"; + model = "Mac Studio J375"; }; /* USB Type C */ @@ -26,6 +39,30 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <174 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec4: connector { + compatible = "usb-c-connector"; + label = "USB-C Front Right"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec4_connector_hs: endpoint { + remote-endpoint = <&dwc3_4_hs>; + }; + }; + port@1 { + reg = <1>; + typec4_connector_ss: endpoint { + remote-endpoint = <&atcphy4_typec_lanes>; + }; + }; + }; + }; }; /* front-left */ @@ -35,6 +72,30 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <174 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec5: connector { + compatible = "usb-c-connector"; + label = "USB-C Front Left"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec5_connector_hs: endpoint { + remote-endpoint = <&dwc3_5_hs>; + }; + }; + port@1 { + reg = <1>; + typec5_connector_ss: endpoint { + remote-endpoint = <&atcphy5_typec_lanes>; + }; + }; + }; + }; }; }; @@ -46,6 +107,106 @@ brcm,board-type = "apple,okinawa"; }; +/* USB controllers on die 1 */ +&dwc3_0_die1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_4_hs: endpoint { + remote-endpoint = <&typec4_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_4_ss: endpoint { + remote-endpoint = <&atcphy4_usb3>; + }; + }; + }; +}; + +&dwc3_1_die1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_5_hs: endpoint { + remote-endpoint = <&typec5_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_5_ss: endpoint { + remote-endpoint = <&atcphy5_usb3>; + }; + }; + }; +}; + +/* Type-C PHYs */ +&atcphy0_die1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy4_typec_lanes: endpoint { + remote-endpoint = <&typec4_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy4_usb3: endpoint { + remote-endpoint = <&dwc3_4_ss>; + }; + }; + }; +}; + +&atcphy1_die1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy5_typec_lanes: endpoint { + remote-endpoint = <&typec5_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy5_usb3: endpoint { + remote-endpoint = <&dwc3_5_ss>; + }; + }; + }; +}; + +/* delete unused USB nodes on die 1 */ + +/delete-node/ &dwc3_2_dart_0_die1; +/delete-node/ &dwc3_2_dart_1_die1; +/delete-node/ &dwc3_2_die1; +/delete-node/ &atcphy2_die1; +/delete-node/ &atcphy2_xbar_die1; + +/delete-node/ &dwc3_3_dart_0_die1; +/delete-node/ &dwc3_3_dart_1_die1; +/delete-node/ &dwc3_3_die1; +/delete-node/ &atcphy3_die1; +/delete-node/ &atcphy3_xbar_die1; + /* delete unused always-on power-domains on die 1 */ /delete-node/ &ps_atc2_usb_aon_die1; @@ -56,3 +217,14 @@ /delete-node/ &ps_disp0_cpu0_die1; /delete-node/ &ps_disp0_fe_die1; + +&gpu { + apple,avg-power-ki-only = <0.6375>; + apple,avg-power-kp = <0.58>; + apple,avg-power-target-filter-tc = <1>; + apple,perf-base-pstate = <3>; + apple,ppm-ki = <5.8>; + apple,ppm-kp = <0.355>; +}; + +#include "hwmon-fan-dual.dtsi" diff --git a/arch/arm64/boot/dts/apple/t6002.dtsi b/arch/arm64/boot/dts/apple/t6002.dtsi index 8fb648836b538b..9bf333e0cf2d66 100644 --- a/arch/arm64/boot/dts/apple/t6002.dtsi +++ b/arch/arm64/boot/dts/apple/t6002.dtsi @@ -11,10 +11,15 @@ #include #include #include +#include #include #include "multi-die-cpp.h" +#ifndef GPU_REPEAT +# define GPU_REPEAT(x) +#endif + #include "t600x-common.dtsi" / { @@ -235,6 +240,8 @@ <0x5 0x80000000 0x5 0x80000000 0x1 0x80000000>, <0x7 0x0 0x7 0x0 0xf 0x80000000>; nonposted-mmio; + /* Required to get >32-bit DMA via DARTs */ + dma-ranges = <0 0 0 0 0xffffffff 0xffffc000>; // filled via templated includes at the end of the file }; @@ -246,6 +253,8 @@ ranges = <0x2 0x0 0x22 0x0 0x4 0x0>, <0x7 0x0 0x27 0x0 0xf 0x80000000>; nonposted-mmio; + /* Required to get >32-bit DMA via DARTs */ + dma-ranges = <0 0 0 0 0xffffffff 0xffffc000>; // filled via templated includes at the end of the file }; @@ -296,11 +305,21 @@ }; }; +&dcpext0_die1 { + // TODO: verify + apple,bw-scratch = <&pmgr_dcp 0 4 0x9c0>; +}; + +&dcpext1_die1 { + // TODO: verify + apple,bw-scratch = <&pmgr_dcp 0 4 0x9c8>; +}; + &ps_gfx { // On t6002, the die0 GPU power domain needs both AFR power domains power-domains = <&ps_afr>, <&ps_afr_die1>; }; &gpu { - compatible = "apple,agx-g13d", "apple,agx-g13s"; + compatible = "apple,agx-t6002", "apple,agx-g13d", "apple,agx-g13s"; }; diff --git a/arch/arm64/boot/dts/apple/t600x-common.dtsi b/arch/arm64/boot/dts/apple/t600x-common.dtsi index e20234ef213538..f37feaea4c2191 100644 --- a/arch/arm64/boot/dts/apple/t600x-common.dtsi +++ b/arch/arm64/boot/dts/apple/t600x-common.dtsi @@ -229,26 +229,31 @@ opp-hz = /bits/ 64 <600000000>; opp-level = <1>; clock-latency-ns = <7500>; + opp-microwatt = <47296>; }; opp02 { opp-hz = /bits/ 64 <972000000>; opp-level = <2>; clock-latency-ns = <23000>; + opp-microwatt = <99715>; }; opp03 { opp-hz = /bits/ 64 <1332000000>; opp-level = <3>; clock-latency-ns = <29000>; + opp-microwatt = <188860>; }; opp04 { opp-hz = /bits/ 64 <1704000000>; opp-level = <4>; clock-latency-ns = <40000>; + opp-microwatt = <288891>; }; opp05 { opp-hz = /bits/ 64 <2064000000>; opp-level = <5>; clock-latency-ns = <50000>; + opp-microwatt = <412979>; }; }; @@ -259,82 +264,139 @@ opp-hz = /bits/ 64 <600000000>; opp-level = <1>; clock-latency-ns = <8000>; + opp-microwatt = <290230>; }; opp02 { opp-hz = /bits/ 64 <828000000>; opp-level = <2>; clock-latency-ns = <18000>; + opp-microwatt = <449013>; }; opp03 { opp-hz = /bits/ 64 <1056000000>; opp-level = <3>; clock-latency-ns = <19000>; + opp-microwatt = <647097>; }; opp04 { opp-hz = /bits/ 64 <1296000000>; opp-level = <4>; clock-latency-ns = <23000>; + opp-microwatt = <865620>; }; opp05 { opp-hz = /bits/ 64 <1524000000>; opp-level = <5>; clock-latency-ns = <24000>; + opp-microwatt = <1112838>; }; opp06 { opp-hz = /bits/ 64 <1752000000>; opp-level = <6>; clock-latency-ns = <28000>; + opp-microwatt = <1453271>; }; opp07 { opp-hz = /bits/ 64 <1980000000>; opp-level = <7>; clock-latency-ns = <31000>; + opp-microwatt = <1776667>; }; opp08 { opp-hz = /bits/ 64 <2208000000>; opp-level = <8>; clock-latency-ns = <45000>; + opp-microwatt = <2366690>; }; opp09 { opp-hz = /bits/ 64 <2448000000>; opp-level = <9>; clock-latency-ns = <49000>; + opp-microwatt = <2892193>; }; opp10 { opp-hz = /bits/ 64 <2676000000>; opp-level = <10>; clock-latency-ns = <53000>; + opp-microwatt = <3475417>; }; opp11 { opp-hz = /bits/ 64 <2904000000>; opp-level = <11>; clock-latency-ns = <56000>; + opp-microwatt = <3959410>; }; opp12 { opp-hz = /bits/ 64 <3036000000>; opp-level = <12>; clock-latency-ns = <56000>; + opp-microwatt = <4540620>; }; - /* Not available until CPU deep sleep is implemented opp13 { opp-hz = /bits/ 64 <3132000000>; opp-level = <13>; clock-latency-ns = <56000>; + opp-microwatt = <4745031>; turbo-mode; }; opp14 { opp-hz = /bits/ 64 <3168000000>; opp-level = <14>; clock-latency-ns = <56000>; + opp-microwatt = <4822390>; turbo-mode; }; opp15 { opp-hz = /bits/ 64 <3228000000>; opp-level = <15>; clock-latency-ns = <56000>; + opp-microwatt = <4951324>; turbo-mode; }; - */ + }; + + gpu_opp: opp-table-gpu { + compatible = "operating-points-v2"; + + /* + * NOTE: The voltage and power values are device-specific and + * must be filled in by the bootloader. + */ + opp00 { + opp-hz = /bits/ 64 <0>; + opp-microvolt = GPU_REPEAT(400000); + opp-microwatt = <0>; + }; + opp01 { + opp-hz = /bits/ 64 <388800000>; + opp-microvolt = GPU_REPEAT(634000); + opp-microwatt = <25011450>; + }; + opp02 { + opp-hz = /bits/ 64 <486000000>; + opp-microvolt = GPU_REPEAT(650000); + opp-microwatt = <31681170>; + }; + opp03 { + opp-hz = /bits/ 64 <648000000>; + opp-microvolt = GPU_REPEAT(668000); + opp-microwatt = <41685750>; + }; + opp04 { + opp-hz = /bits/ 64 <777600000>; + opp-microvolt = GPU_REPEAT(715000); + opp-microwatt = <56692620>; + }; + opp05 { + opp-hz = /bits/ 64 <972000000>; + opp-microvolt = GPU_REPEAT(778000); + opp-microwatt = <83371500>; + }; + opp06 { + opp-hz = /bits/ 64 <1296000000>; + opp-microvolt = GPU_REPEAT(903000); + opp-microwatt = <166743000>; + }; }; pmu-e { @@ -373,6 +435,40 @@ clock-output-names = "clk_200m"; }; + clk_disp0: clock-disp0 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <237333328>; + clock-output-names = "clk_disp0"; + }; + + clk_dispext0: clock-dispext0 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + clock-output-names = "clk_dispext0"; + }; + + clk_dispext0_die1: clock-dispext0_die1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + clock-output-names = "clk_dispext0_die1"; + }; + + clk_dispext1: clock-dispext1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + clock-output-names = "clk_dispext1"; + }; + + clk_dispext1_die1: clock-dispext1_die1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + clock-output-names = "clk_dispext1_die1"; + }; /* * This is a fabulated representation of the input clock * to NCO since we don't know the true clock tree. @@ -401,15 +497,15 @@ }; uat_handoff: uat-handoff { - status = "disabled"; + reg = <0 0 0 0>; }; uat_pagetables: uat-pagetables { - status = "disabled"; + reg = <0 0 0 0>; }; uat_ttbs: uat-ttbs { - status = "disabled"; + reg = <0 0 0 0>; }; }; }; diff --git a/arch/arm64/boot/dts/apple/t600x-die0.dtsi b/arch/arm64/boot/dts/apple/t600x-die0.dtsi index 3603b276a2abcf..95ac52ef753a62 100644 --- a/arch/arm64/boot/dts/apple/t600x-die0.dtsi +++ b/arch/arm64/boot/dts/apple/t600x-die0.dtsi @@ -24,6 +24,22 @@ power-domains = <&ps_aic>; }; + pmgr_misc: power-management@28e20c000 { + compatible = "apple,t6000-pmgr-misc"; + #address-cells = <1>; + #size-cells = <1>; + reg = <0x2 0x8e20c000 0 0x400>, + <0x2 0x8e20c800 0 0x400>; + reg-names = "fabric-ps", "dcs-ps"; + apple,dcs-min-ps = <7>; + }; + + pmgr_dcp: power-management@28e3d0000 { + reg = <0x2 0x8e3d0000 0x0 0x4000>; + reg-names = "dcp-fw-pmgr"; + #apple,bw-scratch-cells = <3>; + }; + smc: smc@290400000 { compatible = "apple,t6000-smc", "apple,smc"; reg = <0x2 0x90400000 0x0 0x4000>, @@ -37,12 +53,22 @@ #gpio-cells = <2>; }; + smc_hwmon: hwmon { + compatible = "apple,smc-hwmon"; + }; + + smc_rtc: rtc { + compatible = "apple,smc-rtc"; + nvmem-cells = <&rtc_offset>; + nvmem-cell-names = "rtc_offset"; + }; + smc_reboot: reboot { compatible = "apple,smc-reboot"; nvmem-cells = <&shutdown_flag>, <&boot_stage>, - <&boot_error_count>, <&panic_count>; + <&boot_error_count>, <&panic_count>, <&pm_setting>; nvmem-cell-names = "shutdown_flag", "boot_stage", - "boot_error_count", "panic_count"; + "boot_error_count", "panic_count", "pm_setting"; }; }; @@ -145,22 +171,198 @@ interrupts = ; }; - sio_dart_0: iommu@39b004000 { + aop_mbox: mbox@293408000 { + compatible = "apple,t6000-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x93408000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + status = "disabled"; + }; + + aop_dart: iommu@293808000 { compatible = "apple,t6000-dart"; - reg = <0x3 0x9b004000 0x0 0x4000>; + reg = <0x2 0x93808000 0x0 0x4000>; + #iommu-cells = <1>; interrupt-parent = <&aic>; - interrupts = ; + interrupts = ; + status = "disabled"; + }; + + aop_admac: dma-controller@293980000 { + compatible = "apple,t6000-admac", "apple,admac"; + reg = <0x2 0x93980000 0x0 0x34000>; + #dma-cells = <1>; + dma-channels = <16>; + interrupts-extended = <0>, + <0>, + <&aic AIC_IRQ 0 600 IRQ_TYPE_LEVEL_HIGH>, + <0>; + iommus = <&aop_dart 7>; + status = "disabled"; + }; + + aop: aop@293c00000 { + compatible = "apple,t6000-aop"; + reg = <0x2 0x93c00000 0x0 0x250000>, + <0x2 0x93400000 0x0 0x6c000>; + mboxes = <&aop_mbox>; + mbox-names = "mbox"; + iommus = <&aop_dart 0>; + + status = "disabled"; + + aop_audio: audio { + compatible = "apple,t6000-aop-audio", "apple,aop-audio"; + dmas = <&aop_admac 1>; + dma-names = "dma"; + }; + + aop_als: als { + compatible = "apple,t6000-aop-als", "apple,aop-als"; + // intentionally empty + }; + + las { + compatible = "apple,t6000-aop-las", "apple,aop-las"; + }; + }; + + disp0_dart: iommu@38b304000 { + compatible = "apple,t6000-dart"; + reg = <0x3 0x8b304000 0x0 0x4000>; #iommu-cells = <1>; - power-domains = <&ps_sio_cpu>; + interrupt-parent = <&aic>; + interrupts = ; + status = "disabled"; + power-domains = <&ps_disp0_cpu0>; + apple,dma-range = <0x0 0x0 0x0 0xfc000000>; }; - sio_dart_1: iommu@39b008000 { + dcp_dart: iommu@38b30c000 { compatible = "apple,t6000-dart"; - reg = <0x3 0x9b008000 0x0 0x8000>; + reg = <0x3 0x8b30c000 0x0 0x4000>; + #iommu-cells = <1>; interrupt-parent = <&aic>; - interrupts = ; + interrupts = ; + power-domains = <&ps_disp0_cpu0>; + apple,dma-range = <0x1f0 0x0 0x0 0xfc000000>; + }; + + sep_dart: iommu@3952c0000 { + compatible = "apple,t6000-dart"; + reg = <0x3 0x952c0000 0x0 0x4000>; #iommu-cells = <1>; - power-domains = <&ps_sio_cpu>; + interrupt-parent = <&aic>; + interrupts = ; + }; + + sep: sep@396400000 { + compatible = "apple,sep"; + reg = <0x3 0x96400000 0x0 0x6C000>; + mboxes = <&sep_mbox>; + mbox-names = "mbox"; + iommus = <&sep_dart 0>; + power-domains = <&ps_sep>; + status = "disabled"; + }; + + sep_mbox: mbox@396408000 { + compatible = "apple,t6000-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x3 0x96408000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + }; + + dpaudio0: audio-controller@39b500000 { + compatible = "apple,t6000-dpaudio", "apple,dpaudio"; + reg = <0x3 0x9b500000 0x0 0x4000>; + dmas = <&sio 0x64>; + dma-names = "tx"; + power-domains = <&ps_dpa0>; + reset-domains = <&ps_dpa0>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dpaudio0_dcp: endpoint { + remote-endpoint = <&dcp_audio>; + }; + }; + }; + }; + + dcp_mbox: mbox@38bc08000 { + compatible = "apple,t6000-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x3 0x8bc08000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&ps_disp0_cpu0>; + }; + + dcp: dcp@38bc00000 { + compatible = "apple,t6000-dcp", "apple,dcp"; + mboxes = <&dcp_mbox>; + mbox-names = "mbox"; + iommus = <&dcp_dart 0>; + + reg-names = "coproc", "disp-0", "disp-1", "disp-2", "disp-3"; + reg = <0x3 0x8bc00000 0x0 0x4000>, + <0x3 0x8a000000 0x0 0x3000000>, + <0x3 0x8b320000 0x0 0x4000>, + <0x3 0x8b344000 0x0 0x4000>, + <0x3 0x8b800000 0x0 0x800000>; + apple,bw-scratch = <&pmgr_dcp 0 4 0x988>; + power-domains = <&ps_disp0_cpu0>; + resets = <&ps_disp0_cpu0>; + clocks = <&clk_disp0>; + phandle = <&dcp>; + // required bus properties for 'piodma' subdevice + #address-cells = <2>; + #size-cells = <2>; + + disp0_piodma: piodma { + iommus = <&disp0_dart 4>; + phandle = <&disp0_piodma>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dcp_audio: endpoint { + remote-endpoint = <&dpaudio0_dcp>; + }; + }; + }; + }; + + display: display-subsystem { + compatible = "apple,display-subsystem"; + iommus = <&disp0_dart 0>; + /* generate phandle explicitly for use in loader */ + phandle = <&display>; }; fpwm0: pwm@39b030000 { @@ -327,10 +529,10 @@ "tx2a", "rx2a", "tx2b", "rx2b", "tx3a", "rx3a", "tx3b", "rx3b"; interrupt-parent = <&aic>; - interrupts = , + interrupts = , + , , - , - ; + ; power-domains = <&ps_audio_p>, <&ps_mca0>, <&ps_mca1>, <&ps_mca2>, <&ps_mca3>; resets = <&ps_audio_p>; @@ -350,6 +552,43 @@ "hw-cal-a", "hw-cal-b", "globals"; apple,firmware-abi = <0 0 0>; + + apple,firmware-version = <12 3 0>; + apple,firmware-compat = <12 3 0>; + + operating-points-v2 = <&gpu_opp>; + apple,perf-base-pstate = <1>; + apple,min-sram-microvolt = <790000>; + apple,avg-power-filter-tc-ms = <1000>; + apple,avg-power-ki-only = <2.4>; + apple,avg-power-kp = <1.5>; + apple,avg-power-min-duty-cycle = <40>; + apple,avg-power-target-filter-tc = <125>; + apple,fast-die0-integral-gain = <500.0>; + apple,fast-die0-proportional-gain = <72.0>; + apple,perf-boost-ce-step = <50>; + apple,perf-boost-min-util = <90>; + apple,perf-filter-drop-threshold = <0>; + apple,perf-filter-time-constant = <5>; + apple,perf-filter-time-constant2 = <50>; + apple,perf-integral-gain = <6.3>; + apple,perf-integral-gain2 = <0.197392>; + apple,perf-integral-min-clamp = <0>; + apple,perf-proportional-gain = <15.75>; + apple,perf-proportional-gain2 = <6.853981>; + apple,perf-tgt-utilization = <85>; + apple,power-sample-period = <8>; + apple,ppm-filter-time-constant-ms = <100>; + apple,ppm-ki = <30.0>; + apple,ppm-kp = <1.5>; + apple,pwr-filter-time-constant = <313>; + apple,pwr-integral-gain = <0.0202129>; + apple,pwr-integral-min-clamp = <0>; + apple,pwr-min-duty-cycle = <40>; + apple,pwr-proportional-gain = <5.2831855>; + + apple,core-leak-coef = GPU_REPEAT(1200.0); + apple,sram-leak-coef = GPU_REPEAT(20.0); }; agx_mbox: mbox@406408000 { @@ -365,6 +604,55 @@ #mbox-cells = <0>; }; + isp_dart0: iommu@3860e8000 { + compatible = "apple,t6000-dart"; + reg = <0x3 0x860e8000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>; + status = "disabled"; + }; + + isp_dart1: iommu@3860f4000 { + compatible = "apple,t6000-dart"; + reg = <0x3 0x860f4000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>; + status = "disabled"; + }; + + isp_dart2: iommu@3860fc000 { + compatible = "apple,t6000-dart"; + reg = <0x3 0x860fc000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>; + status = "disabled"; + }; + + isp: isp@384000000 { + compatible = "apple,t6000-isp", "apple,isp"; + iommus = <&isp_dart0 0>, <&isp_dart1 0>, <&isp_dart2 0>; + reg-names = "coproc", "mbox", "gpio", "mbox2"; + reg = <0x3 0x84000000 0x0 0x2000000>, + <0x3 0x86104000 0x0 0x100>, + <0x3 0x86104170 0x0 0x100>, + <0x3 0x861043f0 0x0 0x100>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>, <&ps_isp_set0>, + <&ps_isp_set1>, <&ps_isp_fe>, <&ps_isp_set3>, + <&ps_isp_set4>, <&ps_isp_set5>, <&ps_isp_set6>, + <&ps_isp_set7>, <&ps_isp_set8>; + apple,dart-vm-size = <0x0 0xa0000000>; + + status = "disabled"; + }; + pcie0_dart_0: iommu@581008000 { compatible = "apple,t6000-dart"; reg = <0x5 0x81008000 0x0 0x4000>; @@ -442,6 +730,8 @@ pinctrl-0 = <&pcie_pins>; pinctrl-names = "default"; + dma-coherent; + port00: pci@0,0 { device_type = "pci"; reg = <0x0 0x0 0x0 0x0 0x0>; diff --git a/arch/arm64/boot/dts/apple/t600x-dieX.dtsi b/arch/arm64/boot/dts/apple/t600x-dieX.dtsi index a32ff0c9d7b0c2..9916450e30bbb6 100644 --- a/arch/arm64/boot/dts/apple/t600x-dieX.dtsi +++ b/arch/arm64/boot/dts/apple/t600x-dieX.dtsi @@ -24,6 +24,160 @@ #performance-domain-cells = <0>; }; + DIE_NODE(dispext0_dart): iommu@289304000 { + compatible = "apple,t6000-dart"; + reg = <0x2 0x89304000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_dispext0_cpu0)>; + apple,dma-range = <0x0 0x0 0x0 0xfc000000>; + status = "disabled"; + }; + + DIE_NODE(dcpext0_dart): iommu@28930c000 { + compatible = "apple,t6000-dart"; + reg = <0x2 0x8930c000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_dispext0_cpu0)>; + apple,dma-range = <0x1f0 0x0 0x0 0xfc000000>; + status = "disabled"; + }; + + DIE_NODE(dcpext0_mbox): mbox@289c08000 { + compatible = "apple,t6000-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x89c08000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&DIE_NODE(ps_dispext0_cpu0)>; + resets = <&DIE_NODE(ps_dispext0_cpu0)>; + status = "disabled"; + }; + + DIE_NODE(dcpext0): dcp@289c00000 { + compatible = "apple,t6000-dcpext", "apple,dcpext"; + mboxes = <&DIE_NODE(dcpext0_mbox)>; + mbox-names = "mbox"; + iommus = <&DIE_NODE(dcpext0_dart) 0>; + + reg-names = "coproc", "disp-0", "disp-1", "disp-2", "disp-3"; + reg = <0x2 0x89c00000 0x0 0x4000>, + <0x2 0x88000000 0x0 0x3000000>, + <0x2 0x89320000 0x0 0x4000>, + <0x2 0x89344000 0x0 0x4000>, + <0x2 0x89800000 0x0 0x800000>; + apple,bw-scratch = <&pmgr_dcp 0 4 0x990>; + power-domains = <&DIE_NODE(ps_dispext0_cpu0)>; + resets = <&DIE_NODE(ps_dispext0_cpu0)>; + clocks = <&DIE_NODE(clk_dispext0)>; + phandle = <&DIE_NODE(dcpext0)>; + apple,dcp-index = <1>; + status = "disabled"; + // required bus properties for 'piodma' subdevice + #address-cells = <2>; + #size-cells = <2>; + + piodma { + iommus = <&DIE_NODE(dispext0_dart) 4>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + DIE_NODE(dcpext0_audio): endpoint { + remote-endpoint = <&DIE_NODE(dpaudio1_dcp)>; + }; + }; + }; + }; + + DIE_NODE(dispext1_dart): iommu@28c304000 { + compatible = "apple,t6000-dart", "apple,t8110-dart"; + reg = <0x2 0x8c304000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_dispext1_cpu0)>; + apple,dma-range = <0x0 0x0 0x0 0xfc000000>; + status = "disabled"; + }; + + DIE_NODE(dcpext1_dart): iommu@28c30c000 { + compatible = "apple,t6000-dart", "apple,t8110-dart"; + reg = <0x2 0x8c30c000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_dispext1_cpu0)>; + apple,dma-range = <0x1f0 0x0 0x0 0xfc000000>; + status = "disabled"; + }; + + DIE_NODE(dcpext1_mbox): mbox@28cc08000 { + compatible = "apple,t6000-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x8cc08000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&DIE_NODE(ps_dispext1_cpu0)>; + resets = <&DIE_NODE(ps_dispext1_cpu0)>; + status = "disabled"; + }; + + DIE_NODE(dcpext1): dcp@28cc00000 { + compatible = "apple,t6000-dcpext", "apple,dcpext"; + mboxes = <&DIE_NODE(dcpext1_mbox)>; + mbox-names = "mbox"; + iommus = <&DIE_NODE(dcpext1_dart) 0>; + + reg-names = "coproc", "disp-0", "disp-1", "disp-2", "disp-3"; + reg = <0x2 0x8cc00000 0x0 0x4000>, + <0x2 0x8b000000 0x0 0x3000000>, + <0x2 0x8c320000 0x0 0x4000>, + <0x2 0x8c344000 0x0 0x4000>, + <0x2 0x8c800000 0x0 0x800000>; + apple,bw-scratch = <&pmgr_dcp 0 4 0x998>; + power-domains = <&DIE_NODE(ps_dispext1_cpu0)>; + resets = <&DIE_NODE(ps_dispext1_cpu0)>; + clocks = <&DIE_NODE(clk_dispext1)>; + phandle = <&DIE_NODE(dcpext1)>; + apple,dcp-index = <2>; + status = "disabled"; + // required bus properties for 'piodma' subdevice + #address-cells = <2>; + #size-cells = <2>; + + piodma { + iommus = <&DIE_NODE(dispext1_dart) 4>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + DIE_NODE(dcpext1_audio): endpoint { + remote-endpoint = <&DIE_NODE(dpaudio2_dcp)>; + }; + }; + }; + }; + DIE_NODE(pmgr): power-management@28e080000 { compatible = "apple,t6000-pmgr", "apple,pmgr", "syscon", "simple-mfd"; #address-cells = <1>; @@ -74,6 +228,193 @@ reg = <0x2 0x92280000 0 0x4000>; }; + DIE_NODE(efuse): efuse@2922bc000 { + compatible = "apple,t6000-efuses", "apple,efuses"; + reg = <0x2 0x922bc000 0x0 0x2000>; + #address-cells = <1>; + #size-cells = <1>; + + DIE_NODE(atcphy0_auspll_rodco_bias_adjust): efuse@a10,22 { + reg = <0xa10 4>; + bits = <22 3>; + }; + + DIE_NODE(atcphy0_auspll_rodco_encap): efuse@a10,25 { + reg = <0xa10 4>; + bits = <25 2>; + }; + + DIE_NODE(atcphy0_auspll_dtc_vreg_adjust): efuse@a10,27 { + reg = <0xa10 4>; + bits = <27 3>; + }; + + DIE_NODE(atcphy0_auspll_fracn_dll_start_capcode): efuse@a10,30 { + reg = <0xa10 4>; + bits = <30 2>; + }; + + DIE_NODE(atcphy0_aus_cmn_shm_vreg_trim): efuse@a14,0 { + reg = <0xa14 4>; + bits = <0 5>; + }; + + DIE_NODE(atcphy0_cio3pll_dco_coarsebin0): efuse@a14,5 { + reg = <0xa14 4>; + bits = <5 6>; + }; + + DIE_NODE(atcphy0_cio3pll_dco_coarsebin1): efuse@a14,11 { + reg = <0xa14 4>; + bits = <11 6>; + }; + + DIE_NODE(atcphy0_cio3pll_dll_start_capcode): efuse@a14,17 { + reg = <0xa14 4>; + bits = <17 2>; + }; + + DIE_NODE(atcphy0_cio3pll_dtc_vreg_adjust): efuse@a14,19 { + reg = <0xa14 4>; + bits = <19 3>; + }; + + DIE_NODE(atcphy1_auspll_rodco_bias_adjust): efuse@a18,0 { + reg = <0xa18 4>; + bits = <0 3>; + }; + + DIE_NODE(atcphy1_auspll_rodco_encap): efuse@a18,3 { + reg = <0xa18 4>; + bits = <3 2>; + }; + + DIE_NODE(atcphy1_auspll_dtc_vreg_adjust): efuse@a18,5 { + reg = <0xa18 4>; + bits = <5 3>; + }; + + DIE_NODE(atcphy1_auspll_fracn_dll_start_capcode): efuse@a18,8 { + reg = <0xa18 4>; + bits = <8 2>; + }; + + DIE_NODE(atcphy1_aus_cmn_shm_vreg_trim): efuse@a18,10 { + reg = <0xa18 4>; + bits = <10 5>; + }; + + DIE_NODE(atcphy1_cio3pll_dco_coarsebin0): efuse@a18,15 { + reg = <0xa18 4>; + bits = <15 6>; + }; + + DIE_NODE(atcphy1_cio3pll_dco_coarsebin1): efuse@a18,21 { + reg = <0xa18 4>; + bits = <21 6>; + }; + + DIE_NODE(atcphy1_cio3pll_dll_start_capcode): efuse@a18,27 { + reg = <0xa18 4>; + bits = <27 2>; + }; + + DIE_NODE(atcphy1_cio3pll_dtc_vreg_adjust): efuse@a18,29 { + reg = <0xa18 4>; + bits = <29 3>; + }; + + DIE_NODE(atcphy2_auspll_rodco_bias_adjust): efuse@a1c,10 { + reg = <0xa1c 4>; + bits = <10 3>; + }; + + DIE_NODE(atcphy2_auspll_rodco_encap): efuse@a1c,13 { + reg = <0xa1c 4>; + bits = <13 2>; + }; + + DIE_NODE(atcphy2_auspll_dtc_vreg_adjust): efuse@a1c,15 { + reg = <0xa1c 4>; + bits = <15 3>; + }; + + DIE_NODE(atcphy2_auspll_fracn_dll_start_capcode): efuse@a1c,18 { + reg = <0xa1c 4>; + bits = <18 2>; + }; + + DIE_NODE(atcphy2_aus_cmn_shm_vreg_trim): efuse@a1c,20 { + reg = <0xa1c 4>; + bits = <20 5>; + }; + + DIE_NODE(atcphy2_cio3pll_dco_coarsebin0): efuse@a1c,25 { + reg = <0xa1c 4>; + bits = <25 6>; + }; + + DIE_NODE(atcphy2_cio3pll_dco_coarsebin1): efuse@a1c,31 { + reg = <0xa1c 8>; + bits = <31 6>; + }; + + DIE_NODE(atcphy2_cio3pll_dll_start_capcode): efuse@a20,5 { + reg = <0xa20 4>; + bits = <5 2>; + }; + + DIE_NODE(atcphy2_cio3pll_dtc_vreg_adjust): efuse@a20,7 { + reg = <0xa20 4>; + bits = <7 3>; + }; + + DIE_NODE(atcphy3_auspll_rodco_bias_adjust): efuse@a20,20 { + reg = <0xa20 4>; + bits = <20 3>; + }; + + DIE_NODE(atcphy3_auspll_rodco_encap): efuse@a20,23 { + reg = <0xa20 4>; + bits = <23 2>; + }; + + DIE_NODE(atcphy3_auspll_dtc_vreg_adjust): efuse@a20,25 { + reg = <0xa20 4>; + bits = <25 3>; + }; + + DIE_NODE(atcphy3_auspll_fracn_dll_start_capcode): efuse@a20,28 { + reg = <0xa20 4>; + bits = <28 2>; + }; + + DIE_NODE(atcphy3_aus_cmn_shm_vreg_trim): efuse@a20,30 { + reg = <0xa20 8>; + bits = <30 5>; + }; + + DIE_NODE(atcphy3_cio3pll_dco_coarsebin0): efuse@a24,3 { + reg = <0xa24 4>; + bits = <3 6>; + }; + + DIE_NODE(atcphy3_cio3pll_dco_coarsebin1): efuse@a24,9 { + reg = <0xa24 4>; + bits = <9 6>; + }; + + DIE_NODE(atcphy3_cio3pll_dll_start_capcode): efuse@a24,15 { + reg = <0xa24 4>; + bits = <15 2>; + }; + + DIE_NODE(atcphy3_cio3pll_dtc_vreg_adjust): efuse@a24,17 { + reg = <0xa24 4>; + bits = <17 3>; + }; + }; + DIE_NODE(pinctrl_aop): pinctrl@293820000 { compatible = "apple,t6000-pinctrl", "apple,pinctrl"; reg = <0x2 0x93820000 0x0 0x4000>; @@ -95,6 +436,24 @@ ; }; + DIE_NODE(sio_dart_0): iommu@39b004000 { + compatible = "apple,t6000-dart"; + reg = <0x3 0x9b004000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + #iommu-cells = <1>; + power-domains = <&DIE_NODE(ps_sio_cpu)>; + }; + + DIE_NODE(sio_dart_1): iommu@39b008000 { + compatible = "apple,t6000-dart"; + reg = <0x3 0x9b008000 0x0 0x8000>; + interrupt-parent = <&aic>; + interrupts = ; + #iommu-cells = <1>; + power-domains = <&DIE_NODE(ps_sio_cpu)>; + }; + DIE_NODE(pinctrl_ap): pinctrl@39b028000 { compatible = "apple,t6000-pinctrl", "apple,pinctrl"; reg = <0x3 0x9b028000 0x0 0x4000>; @@ -119,3 +478,437 @@ interrupt-controller; #interrupt-cells = <2>; }; + + DIE_NODE(sio_mbox): mbox@39bc08000 { + compatible = "apple,t6000-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x3 0x9bc08000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&DIE_NODE(ps_sio_cpu)>; + }; + + DIE_NODE(sio): sio@39bc00000 { + compatible = "apple,t6000-sio", "apple,sio"; + reg = <0x3 0x9bc00000 0x0 0x8000>; + dma-channels = <128>; + #dma-cells = <1>; + mboxes = <&DIE_NODE(sio_mbox)>; + iommus = <&DIE_NODE(sio_dart_0) 0>, <&DIE_NODE(sio_dart_1) 0>; + power-domains = <&DIE_NODE(ps_sio_cpu)>; + resets = <&DIE_NODE(ps_sio)>; /* TODO: verify reset does something */ + status = "disabled"; + }; + + DIE_NODE(dpaudio1): audio-controller@39b504000 { + compatible = "apple,t6000-dpaudio", "apple,dpaudio"; + reg = <0x3 0x9b540000 0x0 0x4000>; + dmas = <&DIE_NODE(sio) 0x66>; + dma-names = "tx"; + power-domains = <&DIE_NODE(ps_dpa1)>; + reset-domains = <&DIE_NODE(ps_dpa1)>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + DIE_NODE(dpaudio1_dcp): endpoint { + remote-endpoint = <&DIE_NODE(dcpext0_audio)>; + }; + }; + }; + }; + + DIE_NODE(dpaudio2): audio-controller@39b508000 { + compatible = "apple,t6000-dpaudio", "apple,dpaudio"; + reg = <0x3 0x9b580000 0x0 0x4000>; + dmas = <&DIE_NODE(sio) 0x68>; + dma-names = "tx"; + power-domains = <&DIE_NODE(ps_dpa2)>; + reset-domains = <&DIE_NODE(ps_dpa2)>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + DIE_NODE(dpaudio2_dcp): endpoint { + remote-endpoint = <&DIE_NODE(dcpext1_audio)>; + }; + }; + }; + }; + + /* + * omit dpaudio3 / 4 as long as the linked dcpext nodes don't exist + * + DIE_NODE(dpaudio3): audio-controller@39b50c000 { + compatible = "apple,t6000-dpaudio", "apple,dpaudio"; + reg = <0x3 0x9b5c0000 0x0 0x4000>; + dmas = <&DIE_NODE(sio) 0x6a>; + dma-names = "tx"; + power-domains = <&DIE_NODE(ps_dpa3)>; + reset-domains = <&DIE_NODE(ps_dpa3)>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + DIE_NODE(dpaudio3_dcp): endpoint { + remote-endpoint = <&DIE_NODE(dcpext2_audio)>; + }; + }; + }; + }; + + DIE_NODE(dpaudio4): audio-controller@39b510000 { + compatible = "apple,t6000-dpaudio", "apple,dpaudio"; + reg = <0x3 0x9b500000 0x0 0x4000>; + dmas = <&DIE_NODE(sio) 0x6c>; + dma-names = "tx"; + power-domains = <&DIE_NODE(ps_dpa4)>; + reset-domains = <&DIE_NODE(ps_dpa4)>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + DIE_NODE(dpaudio4_dcp): endpoint { + remote-endpoint = <&DIE_NODE(dcpext3_audio)>; + }; + }; + }; + }; + */ + + DIE_NODE(dwc3_0): usb@702280000 { + compatible = "apple,t6000-dwc3", "apple,t8103-dwc3"; + reg = <0x7 0x02280000 0x0 0xcd00>, <0x7 0x0228cd00 0x0 0x3200>; + reg-names = "dwc3-core", "dwc3-apple"; + interrupt-parent = <&aic>; + interrupts = ; + dr_mode = "otg"; + usb-role-switch; + role-switch-default-mode = "host"; + iommus = <&DIE_NODE(dwc3_0_dart_0) 0>, + <&DIE_NODE(dwc3_0_dart_1) 1>; + power-domains = <&DIE_NODE(ps_atc0_usb)>; + resets = <&DIE_NODE(atcphy0)>; + phys = <&DIE_NODE(atcphy0) PHY_TYPE_USB2>, <&DIE_NODE(atcphy0) PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + }; + + DIE_NODE(dwc3_0_dart_0): iommu@702f00000 { + compatible = "apple,t6000-dart"; + reg = <0x7 0x02f00000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc0_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(dwc3_0_dart_1): iommu@702f80000 { + compatible = "apple,t6000-dart"; + reg = <0x7 0x02f80000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc0_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(atcphy0): phy@703000000 { + compatible = "apple,t6000-atcphy", "apple,t8103-atcphy"; + reg = <0x7 0x03000000 0x0 0x4c000>, + <0x7 0x03050000 0x0 0x8000>, + <0x7 0x00000000 0x0 0x4000>, + <0x7 0x02a90000 0x0 0x4000>, + <0x7 0x02a84000 0x0 0x4000>; + reg-names = "core", "lpdptx", "axi2af", "usb2phy", + "pipehandler"; + + #phy-cells = <1>; + #reset-cells = <0>; + + nvmem-cells = <&DIE_NODE(atcphy0_aus_cmn_shm_vreg_trim)>, + <&DIE_NODE(atcphy0_auspll_rodco_encap)>, + <&DIE_NODE(atcphy0_auspll_rodco_bias_adjust)>, + <&DIE_NODE(atcphy0_auspll_fracn_dll_start_capcode)>, + <&DIE_NODE(atcphy0_auspll_dtc_vreg_adjust)>, + <&DIE_NODE(atcphy0_cio3pll_dco_coarsebin0)>, + <&DIE_NODE(atcphy0_cio3pll_dco_coarsebin1)>, + <&DIE_NODE(atcphy0_cio3pll_dll_start_capcode)>, + <&DIE_NODE(atcphy0_cio3pll_dtc_vreg_adjust)>; + nvmem-cell-names = "aus_cmn_shm_vreg_trim", + "auspll_rodco_encap", + "auspll_rodco_bias_adjust", + "auspll_fracn_dll_start_capcode", + "auspll_dtc_vreg_adjust", + "cio3pll_dco_coarsebin0", + "cio3pll_dco_coarsebin1", + "cio3pll_dll_start_capcode", + "cio3pll_dtc_vreg_adjust"; + + orientation-switch; + mode-switch; + power-domains = <&DIE_NODE(ps_atc0_usb)>; + }; + + DIE_NODE(atcphy0_xbar): mux@70304c000 { + compatible = "apple,t6000-display-crossbar"; + reg = <0x7 0x0304c000 0x0 0x4000>; + #mux-control-cells = <1>; + power-domains = <&DIE_NODE(ps_atc0_usb)>; + status = "disabled"; + }; + + DIE_NODE(dwc3_1): usb@b02280000 { + compatible = "apple,t6000-dwc3", "apple,t8103-dwc3"; + reg = <0xb 0x02280000 0x0 0xcd00>, <0xb 0x0228cd00 0x0 0x3200>; + reg-names = "dwc3-core", "dwc3-apple"; + interrupt-parent = <&aic>; + interrupts = ; + dr_mode = "otg"; + usb-role-switch; + role-switch-default-mode = "host"; + iommus = <&DIE_NODE(dwc3_1_dart_0) 0>, + <&DIE_NODE(dwc3_1_dart_1) 1>; + power-domains = <&DIE_NODE(ps_atc1_usb)>; + resets = <&DIE_NODE(atcphy1)>; + phys = <&DIE_NODE(atcphy1) PHY_TYPE_USB2>, <&DIE_NODE(atcphy1) PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + }; + + DIE_NODE(dwc3_1_dart_0): iommu@b02f00000 { + compatible = "apple,t6000-dart"; + reg = <0xb 0x02f00000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc1_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(dwc3_1_dart_1): iommu@b02f80000 { + compatible = "apple,t6000-dart"; + reg = <0xb 0x02f80000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc1_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(atcphy1): phy@b03000000 { + compatible = "apple,t6000-atcphy", "apple,t8103-atcphy"; + reg = <0xb 0x03000000 0x0 0x4c000>, + <0xb 0x03050000 0x0 0x8000>, + <0xb 0x00000000 0x0 0x4000>, + <0xb 0x02a90000 0x0 0x4000>, + <0xb 0x02a84000 0x0 0x4000>; + reg-names = "core", "lpdptx", "axi2af", "usb2phy", + "pipehandler"; + + #phy-cells = <1>; + #reset-cells = <0>; + + nvmem-cells = <&DIE_NODE(atcphy1_aus_cmn_shm_vreg_trim)>, + <&DIE_NODE(atcphy1_auspll_rodco_encap)>, + <&DIE_NODE(atcphy1_auspll_rodco_bias_adjust)>, + <&DIE_NODE(atcphy1_auspll_fracn_dll_start_capcode)>, + <&DIE_NODE(atcphy1_auspll_dtc_vreg_adjust)>, + <&DIE_NODE(atcphy1_cio3pll_dco_coarsebin0)>, + <&DIE_NODE(atcphy1_cio3pll_dco_coarsebin1)>, + <&DIE_NODE(atcphy1_cio3pll_dll_start_capcode)>, + <&DIE_NODE(atcphy1_cio3pll_dtc_vreg_adjust)>; + nvmem-cell-names = "aus_cmn_shm_vreg_trim", + "auspll_rodco_encap", + "auspll_rodco_bias_adjust", + "auspll_fracn_dll_start_capcode", + "auspll_dtc_vreg_adjust", + "cio3pll_dco_coarsebin0", + "cio3pll_dco_coarsebin1", + "cio3pll_dll_start_capcode", + "cio3pll_dtc_vreg_adjust"; + + orientation-switch; + mode-switch; + power-domains = <&DIE_NODE(ps_atc1_usb)>; + }; + + DIE_NODE(atcphy1_xbar): mux@b0304c000 { + compatible = "apple,t6000-display-crossbar"; + reg = <0xb 0x0304c000 0x0 0x4000>; + #mux-control-cells = <1>; + power-domains = <&DIE_NODE(ps_atc1_usb)>; + status = "disabled"; + }; + + DIE_NODE(dwc3_2): usb@f02280000 { + compatible = "apple,t6000-dwc3", "apple,t8103-dwc3"; + reg = <0xf 0x02280000 0x0 0xcd00>, <0xf 0x0228cd00 0x0 0x3200>; + reg-names = "dwc3-core", "dwc3-apple"; + interrupt-parent = <&aic>; + interrupts = ; + dr_mode = "otg"; + usb-role-switch; + role-switch-default-mode = "host"; + iommus = <&DIE_NODE(dwc3_2_dart_0) 0>, + <&DIE_NODE(dwc3_2_dart_1) 1>; + power-domains = <&DIE_NODE(ps_atc2_usb)>; + resets = <&DIE_NODE(atcphy2)>; + phys = <&DIE_NODE(atcphy2) PHY_TYPE_USB2>, <&DIE_NODE(atcphy2) PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + }; + + DIE_NODE(dwc3_2_dart_0): iommu@f02f00000 { + compatible = "apple,t6000-dart"; + reg = <0xf 0x02f00000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc2_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(dwc3_2_dart_1): iommu@f02f80000 { + compatible = "apple,t6000-dart"; + reg = <0xf 0x02f80000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc2_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(atcphy2): phy@f03000000 { + compatible = "apple,t6000-atcphy", "apple,t8103-atcphy"; + reg = <0xf 0x03000000 0x0 0x4c000>, + <0xf 0x03050000 0x0 0x8000>, + <0xf 0x00000000 0x0 0x4000>, + <0xf 0x02a90000 0x0 0x4000>, + <0xf 0x02a84000 0x0 0x4000>; + reg-names = "core", "lpdptx", "axi2af", "usb2phy", + "pipehandler"; + + #phy-cells = <1>; + #reset-cells = <0>; + + nvmem-cells = <&DIE_NODE(atcphy2_aus_cmn_shm_vreg_trim)>, + <&DIE_NODE(atcphy2_auspll_rodco_encap)>, + <&DIE_NODE(atcphy2_auspll_rodco_bias_adjust)>, + <&DIE_NODE(atcphy2_auspll_fracn_dll_start_capcode)>, + <&DIE_NODE(atcphy2_auspll_dtc_vreg_adjust)>, + <&DIE_NODE(atcphy2_cio3pll_dco_coarsebin0)>, + <&DIE_NODE(atcphy2_cio3pll_dco_coarsebin1)>, + <&DIE_NODE(atcphy2_cio3pll_dll_start_capcode)>, + <&DIE_NODE(atcphy2_cio3pll_dtc_vreg_adjust)>; + nvmem-cell-names = "aus_cmn_shm_vreg_trim", + "auspll_rodco_encap", + "auspll_rodco_bias_adjust", + "auspll_fracn_dll_start_capcode", + "auspll_dtc_vreg_adjust", + "cio3pll_dco_coarsebin0", + "cio3pll_dco_coarsebin1", + "cio3pll_dll_start_capcode", + "cio3pll_dtc_vreg_adjust"; + + orientation-switch; + mode-switch; + power-domains = <&DIE_NODE(ps_atc2_usb)>; + }; + + DIE_NODE(atcphy2_xbar): mux@f0304c000 { + compatible = "apple,t6000-display-crossbar"; + reg = <0xf 0x0304c000 0x0 0x4000>; + #mux-control-cells = <1>; + power-domains = <&DIE_NODE(ps_atc2_usb)>; + status = "disabled"; + }; + + DIE_NODE(dwc3_3): usb@1302280000 { + compatible = "apple,t6000-dwc3", "apple,t8103-dwc3"; + reg = <0x13 0x02280000 0x0 0xcd00>, <0x13 0x0228cd00 0x0 0x3200>; + reg-names = "dwc3-core", "dwc3-apple"; + interrupt-parent = <&aic>; + interrupts = ; + dr_mode = "otg"; + usb-role-switch; + role-switch-default-mode = "host"; + iommus = <&DIE_NODE(dwc3_3_dart_0) 0>, + <&DIE_NODE(dwc3_3_dart_1) 1>; + power-domains = <&DIE_NODE(ps_atc3_usb)>; + resets = <&DIE_NODE(atcphy3)>; + phys = <&DIE_NODE(atcphy3) PHY_TYPE_USB2>, <&DIE_NODE(atcphy3) PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + }; + + DIE_NODE(dwc3_3_dart_0): iommu@1302f00000 { + compatible = "apple,t6000-dart"; + reg = <0x13 0x02f00000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc3_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(dwc3_3_dart_1): iommu@1302f80000 { + compatible = "apple,t6000-dart"; + reg = <0x13 0x02f80000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc3_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(atcphy3): phy@1303000000 { + compatible = "apple,t6000-atcphy", "apple,t8103-atcphy"; + reg = <0x13 0x03000000 0x0 0x4c000>, + <0x13 0x03050000 0x0 0x8000>, + <0x13 0x00000000 0x0 0x4000>, + <0x13 0x02a90000 0x0 0x4000>, + <0x13 0x02a84000 0x0 0x4000>; + reg-names = "core", "lpdptx", "axi2af", "usb2phy", + "pipehandler"; + + #phy-cells = <1>; + #reset-cells = <0>; + + nvmem-cells = <&DIE_NODE(atcphy3_aus_cmn_shm_vreg_trim)>, + <&DIE_NODE(atcphy3_auspll_rodco_encap)>, + <&DIE_NODE(atcphy3_auspll_rodco_bias_adjust)>, + <&DIE_NODE(atcphy3_auspll_fracn_dll_start_capcode)>, + <&DIE_NODE(atcphy3_auspll_dtc_vreg_adjust)>, + <&DIE_NODE(atcphy3_cio3pll_dco_coarsebin0)>, + <&DIE_NODE(atcphy3_cio3pll_dco_coarsebin1)>, + <&DIE_NODE(atcphy3_cio3pll_dll_start_capcode)>, + <&DIE_NODE(atcphy3_cio3pll_dtc_vreg_adjust)>; + nvmem-cell-names = "aus_cmn_shm_vreg_trim", + "auspll_rodco_encap", + "auspll_rodco_bias_adjust", + "auspll_fracn_dll_start_capcode", + "auspll_dtc_vreg_adjust", + "cio3pll_dco_coarsebin0", + "cio3pll_dco_coarsebin1", + "cio3pll_dll_start_capcode", + "cio3pll_dtc_vreg_adjust"; + + orientation-switch; + mode-switch; + power-domains = <&DIE_NODE(ps_atc3_usb)>; + }; + + DIE_NODE(atcphy3_xbar): mux@130304c000 { + compatible = "apple,t6000-display-crossbar"; + reg = <0x13 0x0304c000 0x0 0x4000>; + #mux-control-cells = <1>; + power-domains = <&DIE_NODE(ps_atc3_usb)>; + status = "disabled"; + }; diff --git a/arch/arm64/boot/dts/apple/t600x-j314-j316.dtsi b/arch/arm64/boot/dts/apple/t600x-j314-j316.dtsi index c0aac59a6fae4f..8d030df13bf5f8 100644 --- a/arch/arm64/boot/dts/apple/t600x-j314-j316.dtsi +++ b/arch/arm64/boot/dts/apple/t600x-j314-j316.dtsi @@ -12,9 +12,20 @@ #include / { + chassis-type = "laptop"; + aliases { + atcphy0 = &atcphy0; + atcphy1 = &atcphy1; + atcphy2 = &atcphy2; + atcphy3 = &atcphy3; bluetooth0 = &bluetooth0; + dcp = &dcp; + dcpext0 = &dcpext0; + disp0 = &display; + disp0_piodma = &disp0_piodma; serial0 = &serial0; + sio = &sio; wifi0 = &wifi0; }; @@ -30,6 +41,9 @@ reg = <0 0 0 0>; /* To be filled by loader */ /* Format properties will be added by loader */ status = "disabled"; + panel = <&panel>; + post-init-providers = <&panel>; + power-domains = <&ps_disp0_cpu0>; }; }; @@ -55,6 +69,76 @@ status = "okay"; }; +&dcp { + panel: panel { + apple,max-brightness = <500>; + }; +}; + +&display { + iommus = <&disp0_dart 0>, <&dispext0_dart 0>; +}; + +&dispext0_dart { + status = "okay"; +}; + +&dcpext0_dart { + status = "okay"; +}; + +&dcpext0_mbox { + status = "okay"; +}; + +&dcpext0 { + /* enabled by the loader */ + apple,connector-type = "HDMI-A"; + + /* HDMI HPD gpio, used as interrupt*/ + hdmi-hpd-gpios = <&pinctrl_nub 15 GPIO_ACTIVE_HIGH>; + + hdmi-pwren-gpios = <&smc_gpio 23 GPIO_ACTIVE_HIGH>; + dp2hdmi-pwren-gpios = <&smc_gpio 6 GPIO_ACTIVE_HIGH>; + + phys = <&atcphy3 PHY_TYPE_DP>; + phy-names = "dp-phy"; + mux-controls = <&atcphy3_xbar 0>; + mux-control-names = "dp-xbar"; + mux-index = <0>; + apple,dptx-phy = <3>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@1 { + reg = <1>; + + decpext0_dpout: endpoint { + remote-endpoint = <&atcphy3_dp>; + }; + }; + }; +}; + +/* remove once m1n1 enables sio nodes after setup */ +&sio { + status = "okay"; +}; + +&dpaudio1 { + status = "okay"; +}; + +&atcphy3_xbar { + status = "okay"; +}; + +&ps_atc3_common { + apple,always-on; /* Needs to stay on for HDMI resume */ +}; + /* USB Type C */ &i2c0 { hpm0: usb-pd@38 { @@ -63,6 +147,30 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <174 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec0: connector { + compatible = "usb-c-connector"; + label = "USB-C Left Rear"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec0_connector_hs: endpoint { + remote-endpoint = <&dwc3_0_hs>; + }; + }; + port@1 { + reg = <1>; + typec0_connector_ss: endpoint { + remote-endpoint = <&atcphy0_typec_lanes>; + }; + }; + }; + }; }; hpm1: usb-pd@3f { @@ -71,6 +179,30 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <174 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec1: connector { + compatible = "usb-c-connector"; + label = "USB-C Left Front"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec1_connector_hs: endpoint { + remote-endpoint = <&dwc3_1_hs>; + }; + }; + port@1 { + reg = <1>; + typec1_connector_ss: endpoint { + remote-endpoint = <&atcphy1_typec_lanes>; + }; + }; + }; + }; }; hpm2: usb-pd@3b { @@ -79,6 +211,30 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <174 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec2: connector { + compatible = "usb-c-connector"; + label = "USB-C Right"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec2_connector_hs: endpoint { + remote-endpoint = <&dwc3_2_hs>; + }; + }; + port@1 { + reg = <1>; + typec2_connector_ss: endpoint { + remote-endpoint = <&atcphy2_typec_lanes>; + }; + }; + }; + }; }; /* MagSafe port */ @@ -91,14 +247,138 @@ }; }; +/* Virtual regulator representing the shared shutdown GPIO */ +/ { + speaker_sdz: fixed-regulator-sn012776-sdz { + compatible = "regulator-fixed"; + regulator-name = "sn012776-sdz"; + startup-delay-us = <5000>; + gpios = <&pinctrl_ap 178 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; +}; + +&i2c1 { + status = "okay"; + + speaker_left_tweet: codec@3a { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x3a>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Left Tweeter"; + interrupts-extended = <&pinctrl_ap 179 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <8>; + ti,vmon-slot-no = <10>; + }; + + speaker_left_woof1: codec@38 { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x38>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Left Woofer 1"; + interrupts-extended = <&pinctrl_ap 179 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <0>; + ti,vmon-slot-no = <2>; + ti,sdout-force-zero-mask = <0xf0f0f0>; + }; + + speaker_left_woof2: codec@39 { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x39>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Left Woofer 2"; + interrupts-extended = <&pinctrl_ap 179 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <16>; + ti,vmon-slot-no = <18>; + }; +}; + +&i2c2 { + status = "okay"; + + jack_codec: codec@4b { + compatible = "cirrus,cs42l84"; + reg = <0x4b>; + reset-gpios = <&pinctrl_nub 4 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + interrupts-extended = <&pinctrl_ap 180 IRQ_TYPE_LEVEL_LOW>; + sound-name-prefix = "Jack"; + }; +}; + +&i2c3 { + status = "okay"; + + speaker_right_tweet: codec@3d { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x3d>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Right Tweeter"; + interrupts-extended = <&pinctrl_ap 179 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <12>; + ti,vmon-slot-no = <14>; + }; + + speaker_right_woof1: codec@3b { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x3b>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Right Woofer 1"; + interrupts-extended = <&pinctrl_ap 179 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <4>; + ti,vmon-slot-no = <6>; + ti,sdout-force-zero-mask = <0x0f0f0f>; + }; + + speaker_right_woof2: codec@3c { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x3c>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Right Woofer 2"; + interrupts-extended = <&pinctrl_ap 179 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <20>; + ti,vmon-slot-no = <22>; + }; +}; + &nco_clkref { clock-frequency = <1068000000>; }; +#ifndef NO_SPI_TRACKPAD +&spi3 { + status = "okay"; + + hid-transport@0 { + compatible = "apple,spi-hid-transport"; + reg = <0>; + spi-max-frequency = <8000000>; + /* + * Apple's ADT specifies 20us CS change delays, and the + * SPI HID interface metadata specifies 45us. Using either + * seems not to be reliable, but adding both works, so + * best guess is they are cumulative. + */ + spi-cs-setup-delay-ns = <65000>; + spi-cs-hold-delay-ns = <65000>; + spi-cs-inactive-delay-ns = <250000>; + spien-gpios = <&pinctrl_ap 194 0>; + interrupts-extended = <&pinctrl_nub 6 IRQ_TYPE_LEVEL_LOW>; + }; +}; +#endif + /* PCIe devices */ &port00 { /* WLAN */ bus-range = <1 1>; + pwren-gpios = <&smc_gpio 13 GPIO_ACTIVE_HIGH>; wifi0: wifi@0,0 { compatible = "pci14e4,4433"; reg = <0x10000 0x0 0x0 0x0 0x0>; @@ -118,6 +398,8 @@ &port01 { /* SD card reader */ bus-range = <2 2>; + pwren-gpios = <&smc_gpio 26 GPIO_ACTIVE_HIGH>; + status = "okay"; sdhci0: mmc@0,0 { compatible = "pci17a0,9755"; reg = <0x20000 0x0 0x0 0x0 0x0>; @@ -130,4 +412,235 @@ status = "okay"; }; +&pcie0_dart_1 { + status = "okay"; +}; + +/* USB controllers */ +&dwc3_0 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_0_hs: endpoint { + remote-endpoint = <&typec0_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_0_ss: endpoint { + remote-endpoint = <&atcphy0_usb3>; + }; + }; + }; +}; + +&dwc3_1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_1_hs: endpoint { + remote-endpoint = <&typec1_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_1_ss: endpoint { + remote-endpoint = <&atcphy1_usb3>; + }; + }; + }; +}; + +&dwc3_2 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_2_hs: endpoint { + remote-endpoint = <&typec2_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_2_ss: endpoint { + remote-endpoint = <&atcphy2_usb3>; + }; + }; + }; +}; + +/* + * ps_atc3_usb_aon power-domain is always-on to keep dwc3 working over suspend. + * atc3 is used exclusively for the DP-to-HDMI so do not keep this always on. + */ +&ps_atc3_usb_aon { + /delete-property/ apple,always-on; +}; + +/* ATC3 is used for DisplayPort -> HDMI only */ +&dwc3_3_dart_0 { + status = "disabled"; +}; + +&dwc3_3_dart_1 { + status = "disabled"; +}; + +&dwc3_3 { + status = "disabled"; +}; + +/* Delete unused dwc3_3 to prevent dt_disable_missing_devs() from disabling + * atcphy3 via phandle references from a disablecd device. + */ +/delete-node/ &dwc3_3; + +/* Type-C PHYs */ +&atcphy0 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy0_typec_lanes: endpoint { + remote-endpoint = <&typec0_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy0_usb3: endpoint { + remote-endpoint = <&dwc3_0_ss>; + }; + }; + }; +}; + +&atcphy1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy1_typec_lanes: endpoint { + remote-endpoint = <&typec1_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy1_usb3: endpoint { + remote-endpoint = <&dwc3_1_ss>; + }; + }; + }; +}; + +&atcphy2 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy2_typec_lanes: endpoint { + remote-endpoint = <&typec2_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy2_usb3: endpoint { + remote-endpoint = <&dwc3_2_ss>; + }; + }; + }; +}; + +&atcphy3 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@2 { + reg = <2>; + atcphy3_dp: endpoint { + remote-endpoint = <&decpext0_dpout>; + }; + }; + }; +}; + +&aop_mbox { + status = "okay"; +}; + +&aop_dart { + status = "okay"; +}; + +&aop_admac { + status = "okay"; +}; + +&aop { + status = "okay"; +}; + +/ { + sound: sound { + /* compatible is set per machine */ + + dai-link@0 { + link-name = "Speakers"; + + cpu { + sound-dai = <&mca 0>, <&mca 1>; + }; + codec { + sound-dai = <&speaker_left_woof1>, + <&speaker_left_tweet>, + <&speaker_left_woof2>, + <&speaker_right_woof1>, + <&speaker_right_tweet>, + <&speaker_right_woof2>; + }; + }; + + dai-link@1 { + link-name = "Headphone Jack"; + + cpu { + sound-dai = <&mca 2>; + }; + codec { + sound-dai = <&jack_codec>; + }; + }; + }; +}; + #include "spi1-nvram.dtsi" + +#include "isp-imx558.dtsi" + +&isp { + apple,platform-id = <3>; +}; + +#include "hwmon-common.dtsi" +#include "hwmon-fan-dual.dtsi" +#include "hwmon-laptop.dtsi" diff --git a/arch/arm64/boot/dts/apple/t600x-j375.dtsi b/arch/arm64/boot/dts/apple/t600x-j375.dtsi index c0fb93ae72f4d4..a5ee97241214d6 100644 --- a/arch/arm64/boot/dts/apple/t600x-j375.dtsi +++ b/arch/arm64/boot/dts/apple/t600x-j375.dtsi @@ -10,10 +10,22 @@ */ / { + chassis-type = "desktop"; + aliases { + atcphy0 = &atcphy0; + atcphy1 = &atcphy1; + atcphy2 = &atcphy2; + atcphy3 = &atcphy3; bluetooth0 = &bluetooth0; + #ifndef NO_DCP + dcp = &dcp; + disp0 = &display; + disp0_piodma = &disp0_piodma; + #endif ethernet0 = ðernet0; serial0 = &serial0; + sio = &sio; wifi0 = &wifi0; }; @@ -29,6 +41,7 @@ reg = <0 0 0 0>; /* To be filled by loader */ /* Format properties will be added by loader */ status = "disabled"; + power-domains = <&ps_disp0_cpu0>; }; }; @@ -42,6 +55,15 @@ status = "okay"; }; +&dcp { + apple,connector-type = "HDMI-A"; +}; + +/* remove once m1n1 enables sio nodes after setup */ +&sio { + status = "okay"; +}; + /* USB Type C */ &i2c0 { hpm0: usb-pd@38 { @@ -50,6 +72,30 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <174 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec0: connector { + compatible = "usb-c-connector"; + label = "USB-C Back Left"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec0_connector_hs: endpoint { + remote-endpoint = <&dwc3_0_hs>; + }; + }; + port@1 { + reg = <1>; + typec0_connector_ss: endpoint { + remote-endpoint = <&atcphy0_typec_lanes>; + }; + }; + }; + }; }; hpm1: usb-pd@3f { @@ -58,6 +104,30 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <174 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec1: connector { + compatible = "usb-c-connector"; + label = "USB-C Back Left Middle"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec1_connector_hs: endpoint { + remote-endpoint = <&dwc3_1_hs>; + }; + }; + port@1 { + reg = <1>; + typec1_connector_ss: endpoint { + remote-endpoint = <&atcphy1_typec_lanes>; + }; + }; + }; + }; }; hpm2: usb-pd@3b { @@ -66,6 +136,30 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <174 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec2: connector { + compatible = "usb-c-connector"; + label = "USB-C Back Right Middle"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec2_connector_hs: endpoint { + remote-endpoint = <&dwc3_2_hs>; + }; + }; + port@1 { + reg = <1>; + typec2_connector_ss: endpoint { + remote-endpoint = <&atcphy2_typec_lanes>; + }; + }; + }; + }; }; hpm3: usb-pd@3c { @@ -74,6 +168,228 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <174 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec3: connector { + compatible = "usb-c-connector"; + label = "USB-C Back Right"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec3_connector_hs: endpoint { + remote-endpoint = <&dwc3_3_hs>; + }; + }; + port@1 { + reg = <1>; + typec3_connector_ss: endpoint { + remote-endpoint = <&atcphy3_typec_lanes>; + }; + }; + }; + }; + }; +}; + +/* USB controllers */ +&dwc3_0 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_0_hs: endpoint { + remote-endpoint = <&typec0_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_0_ss: endpoint { + remote-endpoint = <&atcphy0_usb3>; + }; + }; + }; +}; + +&dwc3_1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_1_hs: endpoint { + remote-endpoint = <&typec1_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_1_ss: endpoint { + remote-endpoint = <&atcphy1_usb3>; + }; + }; + }; +}; + +&dwc3_2 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_2_hs: endpoint { + remote-endpoint = <&typec2_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_2_ss: endpoint { + remote-endpoint = <&atcphy2_usb3>; + }; + }; + }; +}; + +&dwc3_3 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_3_hs: endpoint { + remote-endpoint = <&typec3_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_3_ss: endpoint { + remote-endpoint = <&atcphy3_usb3>; + }; + }; + }; +}; + +/* Type-C PHYs */ +&atcphy0 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy0_typec_lanes: endpoint { + remote-endpoint = <&typec0_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy0_usb3: endpoint { + remote-endpoint = <&dwc3_0_ss>; + }; + }; + }; +}; + +&atcphy1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy1_typec_lanes: endpoint { + remote-endpoint = <&typec1_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy1_usb3: endpoint { + remote-endpoint = <&dwc3_1_ss>; + }; + }; + }; +}; + +&atcphy2 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy2_typec_lanes: endpoint { + remote-endpoint = <&typec2_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy2_usb3: endpoint { + remote-endpoint = <&dwc3_2_ss>; + }; + }; + }; +}; + +&atcphy3 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy3_typec_lanes: endpoint { + remote-endpoint = <&typec3_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy3_usb3: endpoint { + remote-endpoint = <&dwc3_3_ss>; + }; + }; + }; +}; + +/* Audio */ +&i2c1 { + status = "okay"; + + speaker: codec@38 { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x38>; + shutdown-gpios = <&pinctrl_ap 178 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + interrupts-extended = <&pinctrl_ap 179 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <0>; + ti,vmon-slot-no = <2>; + }; +}; + +&i2c2 { + status = "okay"; + + jack_codec: codec@4b { + compatible = "cirrus,cs42l84"; + reg = <0x4b>; + reset-gpios = <&pinctrl_nub 4 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + interrupts-extended = <&pinctrl_ap 180 IRQ_TYPE_LEVEL_LOW>; + sound-name-prefix = "Jack"; }; }; @@ -81,10 +397,39 @@ clock-frequency = <1068000000>; }; +/ { + sound: sound { + /* compatible is set per machine */ + + dai-link@0 { + link-name = "Speaker"; + + cpu { + sound-dai = <&mca 0>; + }; + codec { + sound-dai = <&speaker>; + }; + }; + + dai-link@1 { + link-name = "Headphone Jack"; + + cpu { + sound-dai = <&mca 2>; + }; + codec { + sound-dai = <&jack_codec>; + }; + }; + }; +}; + /* PCIe devices */ &port00 { /* WLAN */ bus-range = <1 1>; + pwren-gpios = <&smc_gpio 13 GPIO_ACTIVE_HIGH>; wifi0: wifi@0,0 { compatible = "pci14e4,4433"; reg = <0x10000 0x0 0x0 0x0 0x0>; @@ -104,6 +449,7 @@ &port01 { /* SD card reader */ bus-range = <2 2>; + pwren-gpios = <&smc_gpio 26 GPIO_ACTIVE_HIGH>; sdhci0: mmc@0,0 { compatible = "pci17a0,9755"; reg = <0x20000 0x0 0x0 0x0 0x0>; @@ -126,6 +472,7 @@ &port03 { /* USB xHCI */ bus-range = <4 4>; + pwren-gpios = <&smc_gpio 20 GPIO_ACTIVE_HIGH>; status = "okay"; }; @@ -139,3 +486,5 @@ }; #include "spi1-nvram.dtsi" + +#include "hwmon-common.dtsi" diff --git a/arch/arm64/boot/dts/apple/t600x-pmgr.dtsi b/arch/arm64/boot/dts/apple/t600x-pmgr.dtsi index 0bd44753b76a0c..1429554ed54505 100644 --- a/arch/arm64/boot/dts/apple/t600x-pmgr.dtsi +++ b/arch/arm64/boot/dts/apple/t600x-pmgr.dtsi @@ -396,6 +396,7 @@ #reset-cells = <0>; label = DIE_LABEL(dispext0_cpu0); power-domains = <&DIE_NODE(ps_dispext0_fe)>; + apple,min-state = <4>; }; DIE_NODE(ps_dispext1_cpu0): power-controller@2a8 { @@ -405,6 +406,7 @@ #reset-cells = <0>; label = DIE_LABEL(dispext1_cpu0); power-domains = <&DIE_NODE(ps_dispext1_fe)>; + apple,min-state = <4>; }; DIE_NODE(ps_ane_sys_cpu): power-controller@2c8 { @@ -824,7 +826,7 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = DIE_LABEL(sio_cpu); - power-domains = <&DIE_NODE(ps_sio)>; + power-domains = <&DIE_NODE(ps_sio) &DIE_NODE(ps_uart_p) &DIE_NODE(ps_spi_p) &DIE_NODE(ps_audio_p)>; }; DIE_NODE(ps_fpwm0): power-controller@190 { @@ -1113,6 +1115,7 @@ #reset-cells = <0>; label = DIE_LABEL(mca0); power-domains = <&DIE_NODE(ps_audio_p)>, <&DIE_NODE(ps_sio_adma)>; + apple,externally-clocked; }; DIE_NODE(ps_mca1): power-controller@290 { @@ -1122,6 +1125,7 @@ #reset-cells = <0>; label = DIE_LABEL(mca1); power-domains = <&DIE_NODE(ps_audio_p)>, <&DIE_NODE(ps_sio_adma)>; + apple,externally-clocked; }; DIE_NODE(ps_mca2): power-controller@298 { @@ -1131,6 +1135,7 @@ #reset-cells = <0>; label = DIE_LABEL(mca2); power-domains = <&DIE_NODE(ps_audio_p)>, <&DIE_NODE(ps_sio_adma)>; + apple,externally-clocked; }; DIE_NODE(ps_mca3): power-controller@2a0 { @@ -1140,6 +1145,7 @@ #reset-cells = <0>; label = DIE_LABEL(mca3); power-domains = <&DIE_NODE(ps_audio_p)>, <&DIE_NODE(ps_sio_adma)>; + apple,externally-clocked; }; DIE_NODE(ps_dpa0): power-controller@2a8 { @@ -1293,7 +1299,6 @@ #reset-cells = <0>; label = DIE_LABEL(disp0_fe); power-domains = <&DIE_NODE(ps_afnc2_lw0)>; - apple,always-on; /* TODO: figure out if we can enable PM here */ }; DIE_NODE(ps_disp0_cpu0): power-controller@350 { @@ -1303,7 +1308,6 @@ #reset-cells = <0>; label = DIE_LABEL(disp0_cpu0); power-domains = <&DIE_NODE(ps_disp0_fe)>; - apple,always-on; /* TODO: figure out if we can enable PM here */ apple,min-state = <4>; }; @@ -1368,6 +1372,7 @@ #reset-cells = <0>; label = DIE_LABEL(isp_sys); power-domains = <&DIE_NODE(ps_afnc2_lw1)>; + status = "disabled"; }; DIE_NODE(ps_venc_sys): power-controller@3b0 { @@ -1385,12 +1390,6 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = DIE_LABEL(ans2); - /* - * The ADT makes ps_apcie_st[1]_sys depend on ps_ans2 instead, - * but we'd rather have a single power domain for the downstream - * device to depend on, so use this node as the child. - * This makes more sense anyway (since ANS2 uses APCIE_ST). - */ power-domains = <&DIE_NODE(ps_afnc2_lw0)>; }; @@ -1456,6 +1455,86 @@ label = DIE_LABEL(venc_me1); power-domains = <&DIE_NODE(ps_venc_me0)>; }; + + /* There is a dependency tree involved with these PDs, + * but we do not express it here since the ISP driver + * is supposed to sequence them in the right order anyway + * (and we do not know the exact tree structure). + * + * This also works around spurious parent PD activation + * on machines with ISP disabled (desktops). + */ + DIE_NODE(ps_isp_set0): power-controller@4000 { + compatible = "apple,t6000-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4000 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = DIE_LABEL(isp_set0); + }; + + DIE_NODE(ps_isp_set1): power-controller@4010 { + compatible = "apple,t6000-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4010 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = DIE_LABEL(isp_set1); + }; + + DIE_NODE(ps_isp_fe): power-controller@4008 { + compatible = "apple,t6000-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4008 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = DIE_LABEL(ps_isp_fe); + }; + + DIE_NODE(ps_isp_set3): power-controller@4028 { + compatible = "apple,t6000-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4028 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = DIE_LABEL(isp_set3); + }; + + DIE_NODE(ps_isp_set4): power-controller@4020 { + compatible = "apple,t6000-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4020 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = DIE_LABEL(isp_set4); + }; + + DIE_NODE(ps_isp_set5): power-controller@4030 { + compatible = "apple,t6000-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4030 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = DIE_LABEL(isp_set5); + }; + + DIE_NODE(ps_isp_set6): power-controller@4018 { + compatible = "apple,t6000-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4018 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = DIE_LABEL(isp_set6); + }; + + DIE_NODE(ps_isp_set7): power-controller@4038 { + compatible = "apple,t6000-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4038 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = DIE_LABEL(isp_set7); + }; + + DIE_NODE(ps_isp_set8): power-controller@4040 { + compatible = "apple,t6000-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4040 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = DIE_LABEL(isp_set8); + }; }; &DIE_NODE(pmgr_south) { @@ -1715,6 +1794,7 @@ #reset-cells = <0>; label = DIE_LABEL(dispext2_cpu0); power-domains = <&DIE_NODE(ps_dispext2_fe)>; + apple,min-state = <4>; }; DIE_NODE(ps_dispext3_fe): power-controller@210 { @@ -1733,6 +1813,7 @@ #reset-cells = <0>; label = DIE_LABEL(dispext3_cpu0); power-domains = <&DIE_NODE(ps_dispext3_fe)>; + apple,min-state = <4>; }; DIE_NODE(ps_msr1): power-controller@250 { @@ -1881,6 +1962,7 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = DIE_LABEL(msg); + apple,always-on; /* Core AON device? */ }; DIE_NODE(ps_nub_gpio): power-controller@80 { diff --git a/arch/arm64/boot/dts/apple/t6020-j414s.dts b/arch/arm64/boot/dts/apple/t6020-j414s.dts index 631c54c5f03dee..a227069727dd8f 100644 --- a/arch/arm64/boot/dts/apple/t6020-j414s.dts +++ b/arch/arm64/boot/dts/apple/t6020-j414s.dts @@ -24,3 +24,24 @@ &bluetooth0 { brcm,board-type = "apple,tokara"; }; + +&panel { + compatible = "apple,panel-j414", "apple,panel-mini-led", "apple,panel"; + width-mm = <302>; + height-mm = <196>; + adj-height-mm = <189>; +}; + +&aop_audio { + apple,chassis-name = "J414"; + apple,machine-kind = "MacBook Pro"; +}; + +&sound { + compatible = "apple,j414-macaudio", "apple,j314-macaudio", "apple,macaudio"; + model = "MacBook Pro J414"; +}; + +&mtp_mt { + firmware-name = "apple/tpmtfw-j414s.bin"; +}; diff --git a/arch/arm64/boot/dts/apple/t6020-j416s.dts b/arch/arm64/boot/dts/apple/t6020-j416s.dts index c277ed5889a214..3ea2b1d52593e2 100644 --- a/arch/arm64/boot/dts/apple/t6020-j416s.dts +++ b/arch/arm64/boot/dts/apple/t6020-j416s.dts @@ -24,3 +24,24 @@ &bluetooth0 { brcm,board-type = "apple,amami"; }; + +&panel { + compatible = "apple,panel-j416", "apple,panel-mini-led", "apple,panel"; + width-mm = <346>; + height-mm = <223>; + adj-height-mm = <216>; +}; + +&aop_audio { + apple,chassis-name = "J416"; + apple,machine-kind = "MacBook Pro"; +}; + +&sound { + compatible = "apple,j416-macaudio", "apple,j316-macaudio", "apple,macaudio"; + model = "MacBook Pro J416"; +}; + +&mtp_mt { + firmware-name = "apple/tpmtfw-j416s.bin"; +}; diff --git a/arch/arm64/boot/dts/apple/t6020-j474s.dts b/arch/arm64/boot/dts/apple/t6020-j474s.dts index 7c7ad5b8ad189e..12dfe9693502ad 100644 --- a/arch/arm64/boot/dts/apple/t6020-j474s.dts +++ b/arch/arm64/boot/dts/apple/t6020-j474s.dts @@ -45,3 +45,84 @@ <0x200 &pcie0_dart_2 1 1>, <0x300 &pcie0_dart_3 1 1>; }; + +&port02 { + bus-range = <2 2>; +}; + +ðernet0 { + reg = <0x20000 0x0 0x0 0x0 0x0>; +}; + +&port03 { + bus-range = <3 3>; +}; + +&sound { + compatible = "apple,j474-macaudio", "apple,j473-macaudio", "apple,macaudio"; + model = "Mac mini J474"; +}; + +&lpdptxphy { + status = "okay"; +}; + +#define USE_DCPEXT0 1 + +#if USE_DCPEXT0 +/ { + aliases { + dcpext0 = &dcpext0; + /delete-property/ dcp; + }; +}; + +&framebuffer0 { + power-domains = <&ps_dispext0_cpu0>, <&ps_dptx_phy_ps>; +}; + +&dcp { + status = "disabled"; +}; +&display { + iommus = <&dispext0_dart 0>; +}; +&dispext0_dart { + status = "okay"; +}; +&dcpext0_dart { + status = "okay"; +}; +&dcpext0_mbox { + status = "okay"; +}; +&dpaudio1 { + status = "okay"; +}; +&dcpext0 { +#else +&dpaudio0 { + status = "okay"; +}; +&dcp { +#endif + status = "okay"; + apple,connector-type = "HDMI-A"; + + /* HDMI HPD gpio, used as interrupt*/ + hdmi-hpd-gpios = <&pinctrl_aop 25 GPIO_ACTIVE_HIGH>; + + hdmi-pwren-gpios = <&smc_gpio 23 GPIO_ACTIVE_HIGH>; + dp2hdmi-pwren-gpios = <&smc_gpio 25 GPIO_ACTIVE_HIGH>; + + phys = <&lpdptxphy>; + phy-names = "dp-phy"; + apple,dptx-phy = <4>; +}; + +&gpu { + /* Apple does not do this, but they probably should */ + apple,perf-base-pstate = <3>; +}; + +#include "hwmon-mini.dtsi" diff --git a/arch/arm64/boot/dts/apple/t6020.dtsi b/arch/arm64/boot/dts/apple/t6020.dtsi index bffa66a3ffff3f..482a1e5f53d0a6 100644 --- a/arch/arm64/boot/dts/apple/t6020.dtsi +++ b/arch/arm64/boot/dts/apple/t6020.dtsi @@ -9,6 +9,8 @@ /* This chip is just a cut down version of t6021, so include it and disable the missing parts */ +#define GPU_REPEAT(x) + #include "t6021.dtsi" / { @@ -18,5 +20,12 @@ /delete-node/ &pmgr_south; &gpu { - compatible = "apple,agx-g14s"; + compatible = "apple,agx-t6020", "apple,agx-g14x", "apple,agx-g14s"; + + apple,avg-power-filter-tc-ms = <302>; + apple,avg-power-ki-only = <2.6375>; + apple,avg-power-kp = <0.18>; + apple,fast-die0-integral-gain = <1350.0>; + apple,ppm-filter-time-constant-ms = <32>; + apple,ppm-ki = <28.0>; }; diff --git a/arch/arm64/boot/dts/apple/t6021-j414c.dts b/arch/arm64/boot/dts/apple/t6021-j414c.dts index cdcf0740714dcf..fab3b03ff3c452 100644 --- a/arch/arm64/boot/dts/apple/t6021-j414c.dts +++ b/arch/arm64/boot/dts/apple/t6021-j414c.dts @@ -24,3 +24,24 @@ &bluetooth0 { brcm,board-type = "apple,tokara"; }; + +&panel { + compatible = "apple,panel-j414", "apple,panel-mini-led", "apple,panel"; + width-mm = <302>; + height-mm = <196>; + adj-height-mm = <189>; +}; + +&aop_audio { + apple,chassis-name = "J414"; + apple,machine-kind = "MacBook Pro"; +}; + +&sound { + compatible = "apple,j414-macaudio", "apple,j314-macaudio", "apple,macaudio"; + model = "MacBook Pro J414"; +}; + +&mtp_mt { + firmware-name = "apple/tpmtfw-j414c.bin"; +}; diff --git a/arch/arm64/boot/dts/apple/t6021-j416c.dts b/arch/arm64/boot/dts/apple/t6021-j416c.dts index 6d8146b9417036..b476e235639ffc 100644 --- a/arch/arm64/boot/dts/apple/t6021-j416c.dts +++ b/arch/arm64/boot/dts/apple/t6021-j416c.dts @@ -17,6 +17,26 @@ model = "Apple MacBook Pro (16-inch, M2 Max, 2023)"; }; +/* This machine model (only) has two extra boost CPU P-states * + * Disabled: Only the highest CPU bin (38 GPU cores) has this. + * Keep this disabled until m1n1 learns how to remove these OPPs + * for unsupported machines, otherwise it breaks cpufreq. +&avalanche_opp { + opp18 { + opp-hz = /bits/ 64 <3528000000>; + opp-level = <18>; + clock-latency-ns = <67000>; + turbo-mode; + }; + opp19 { + opp-hz = /bits/ 64 <3696000000>; + opp-level = <19>; + clock-latency-ns = <67000>; + turbo-mode; + }; +}; +*/ + &wifi0 { brcm,board-type = "apple,amami"; }; @@ -24,3 +44,24 @@ &bluetooth0 { brcm,board-type = "apple,amami"; }; + +&panel { + compatible = "apple,panel-j416", "apple,panel-mini-led", "apple,panel"; + width-mm = <346>; + height-mm = <223>; + adj-height-mm = <216>; +}; + +&aop_audio { + apple,chassis-name = "J416"; + apple,machine-kind = "MacBook Pro"; +}; + +&sound { + compatible = "apple,j416-macaudio", "apple,j316-macaudio", "apple,macaudio"; + model = "MacBook Pro J416"; +}; + +&mtp_mt { + firmware-name = "apple/tpmtfw-j416c.bin"; +}; diff --git a/arch/arm64/boot/dts/apple/t6021-j475c.dts b/arch/arm64/boot/dts/apple/t6021-j475c.dts index 533e3577487469..e4321cfc556838 100644 --- a/arch/arm64/boot/dts/apple/t6021-j475c.dts +++ b/arch/arm64/boot/dts/apple/t6021-j475c.dts @@ -29,9 +29,99 @@ /* enable PCIe port01 with SDHCI */ &port01 { + pwren-gpios = <&smc_gpio 22 GPIO_ACTIVE_HIGH>; status = "okay"; }; &pcie0_dart_1 { status = "okay"; }; + +&pinctrl_ap { + usb_hub_oe-hog { + gpio-hog; + gpios = <231 0>; + input; + line-name = "usb-hub-oe"; + }; + + usb_hub_rst-hog { + gpio-hog; + gpios = <232 GPIO_ACTIVE_LOW>; + output-low; + line-name = "usb-hub-rst"; + }; +}; + +&sound { + compatible = "apple,j475-macaudio", "apple,j375-macaudio", "apple,macaudio"; + model = "Mac Studio J475"; +}; + +&lpdptxphy { + status = "okay"; +}; + + +#define USE_DCPEXT0 1 + +#if USE_DCPEXT0 +/ { + aliases { + dcpext0 = &dcpext0; + /delete-property/ dcp; + }; +}; + +&framebuffer0 { + power-domains = <&ps_dispext0_cpu0>, <&ps_dptx_phy_ps>; +}; + +&dcp { + status = "disabled"; +}; +&display { + iommus = <&dispext0_dart 0>; +}; +&dispext0_dart { + status = "okay"; +}; +&dcpext0_dart { + status = "okay"; +}; +&dcpext0_mbox { + status = "okay"; +}; +&dpaudio1 { + status = "okay"; +}; +&dcpext0 { +#else +&dpaudio0 { + status = "okay"; +}; +&dcp { +#endif + status = "okay"; + apple,connector-type = "HDMI-A"; + + /* HDMI HPD gpio, used as interrupt*/ + hdmi-hpd-gpios = <&pinctrl_aop 25 GPIO_ACTIVE_HIGH>; + + hdmi-pwren-gpios = <&smc_gpio 23 GPIO_ACTIVE_HIGH>; + dp2hdmi-pwren-gpios = <&smc_gpio 25 GPIO_ACTIVE_HIGH>; + + phys = <&lpdptxphy>; + phy-names = "dp-phy"; + apple,dptx-phy = <4>; +}; + +&gpu { + apple,idleoff-standby-timer = <3000>; + apple,perf-base-pstate = <5>; + apple,perf-boost-ce-step = <100>; + apple,perf-boost-min-util = <75>; + apple,perf-tgt-utilization = <70>; +}; + +#include "hwmon-fan-dual.dtsi" diff --git a/arch/arm64/boot/dts/apple/t6021.dtsi b/arch/arm64/boot/dts/apple/t6021.dtsi index 62907ad6a54683..bb0e66851f1b59 100644 --- a/arch/arm64/boot/dts/apple/t6021.dtsi +++ b/arch/arm64/boot/dts/apple/t6021.dtsi @@ -16,6 +16,13 @@ #include "multi-die-cpp.h" +#ifndef GPU_REPEAT +# define GPU_REPEAT(x) +#endif +#ifndef GPU_DIE_REPEAT +# define GPU_DIE_REPEAT(x) +#endif + #include "t602x-common.dtsi" / { @@ -28,6 +35,8 @@ ranges; nonposted-mmio; + /* Required to get >32-bit DMA via DARTs */ + dma-ranges = <0 0 0 0 0xffffffff 0xffffc000>; // filled via templated includes at the end of the file }; @@ -65,5 +74,12 @@ }; &gpu { - compatible = "apple,agx-g14c", "apple,agx-g14s"; + compatible = "apple,agx-t6021", "apple,agx-g14x", "apple,agx-g14c", "apple,agx-g14s"; + + apple,avg-power-filter-tc-ms = <300>; + apple,avg-power-ki-only = <1.5125>; + apple,avg-power-kp = <0.38>; + apple,fast-die0-integral-gain = <700.0>; + apple,ppm-filter-time-constant-ms = <34>; + apple,ppm-ki = <18.0>; }; diff --git a/arch/arm64/boot/dts/apple/t6022-j180d.dts b/arch/arm64/boot/dts/apple/t6022-j180d.dts index dca6bd167c225a..4a528c28031805 100644 --- a/arch/arm64/boot/dts/apple/t6022-j180d.dts +++ b/arch/arm64/boot/dts/apple/t6022-j180d.dts @@ -11,13 +11,28 @@ #include "t6022.dtsi" #include "t6022-jxxxd.dtsi" +#include "t6022-pcie-ge.dtsi" / { compatible = "apple,j180d", "apple,t6022", "apple,arm-platform"; model = "Apple Mac Pro (M2 Ultra, 2023)"; + chassis-type = "server"; + aliases { - nvram = &nvram; + atcphy0 = &atcphy0; + atcphy1 = &atcphy1; + atcphy2 = &atcphy2; + atcphy3 = &atcphy3; + atcphy4 = &atcphy0_die1; + atcphy5 = &atcphy1_die1; + atcphy6 = &atcphy2_die1; + atcphy7 = &atcphy3_die1; + bluetooth0 = &bluetooth0; + dcpext0 = &dcpext0; + ethernet0 = ðernet0; + ethernet1 = ðernet1; serial0 = &serial0; + wifi0 = &wifi0; }; chosen { @@ -36,6 +51,13 @@ }; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + /* To be filled by loader */ + }; + memory@10000000000 { device_type = "memory"; reg = <0x100 0 0x2 0>; /* To be filled by loader */ @@ -46,6 +68,46 @@ status = "okay"; }; +&lpdptxphy { + status = "okay"; +}; + +&display { + iommus = <&dispext0_dart_die1 0>, <&dispext0_dart 0>; +}; + +&dispext0_dart { + status = "okay"; +}; + +&dcpext0_dart { + status = "okay"; +}; + +&dcpext0_mbox { + status = "okay"; +}; + +&dcpext0 { + status = "okay"; + apple,connector-type = "HDMI-A"; + + /* HDMI HPD gpio, used as interrupt*/ + hdmi-hpd-gpios = <&pinctrl_aop 25 GPIO_ACTIVE_HIGH>; + + // shared between dp2hdmi-gpio0 / dp2hdmi-gpio1 + // hdmi-pwren-gpios = <&smc_gpio 23 GPIO_ACTIVE_HIGH>; + + phys = <&lpdptxphy>; + phy-names = "dp-phy"; + apple,dptx-phy = <4>; + apple,dptx-die = <0>; +}; + +&dpaudio1 { + status = "okay"; +}; + /* USB Type C Rear */ &i2c0 { hpm2: usb-pd@3b { @@ -54,6 +116,30 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <44 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec2: connector { + compatible = "usb-c-connector"; + label = "USB-C Back 1"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec2_connector_hs: endpoint { + remote-endpoint = <&dwc3_2_hs>; + }; + }; + port@1 { + reg = <1>; + typec2_connector_ss: endpoint { + remote-endpoint = <&atcphy2_typec_lanes>; + }; + }; + }; + }; }; hpm3: usb-pd@3c { @@ -62,6 +148,30 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <44 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec3: connector { + compatible = "usb-c-connector"; + label = "USB-C Back 2"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec3_connector_hs: endpoint { + remote-endpoint = <&dwc3_3_hs>; + }; + }; + port@1 { + reg = <1>; + typec3_connector_ss: endpoint { + remote-endpoint = <&atcphy3_typec_lanes>; + }; + }; + }; + }; }; /* hpm4 and hpm5 included from t6022-jxxxd.dtsi */ @@ -72,6 +182,30 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <44 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec6: connector { + compatible = "usb-c-connector"; + label = "USB-C Back 5"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec6_connector_hs: endpoint { + remote-endpoint = <&dwc3_6_hs>; + }; + }; + port@1 { + reg = <1>; + typec6_connector_ss: endpoint { + remote-endpoint = <&atcphy6_typec_lanes>; + }; + }; + }; + }; }; hpm7: usb-pd@3e { @@ -80,9 +214,41 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <44 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec7: connector { + compatible = "usb-c-connector"; + label = "USB-C Back 6"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec7_connector_hs: endpoint { + remote-endpoint = <&dwc3_7_hs>; + }; + }; + port@1 { + reg = <1>; + typec7_connector_ss: endpoint { + remote-endpoint = <&atcphy7_typec_lanes>; + }; + }; + }; + }; }; }; +&typec4 { + label = "USB-C Back 3"; +}; + +&typec5 { + label = "USB-C Back 4"; +}; + /* USB Type C Front */ &i2c3 { status = "okay"; @@ -93,6 +259,30 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <60 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec0: connector { + compatible = "usb-c-connector"; + label = "USB-C Top Right"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec0_connector_hs: endpoint { + remote-endpoint = <&dwc3_0_hs>; + }; + }; + port@1 { + reg = <1>; + typec0_connector_ss: endpoint { + remote-endpoint = <&atcphy0_typec_lanes>; + }; + }; + }; + }; }; hpm1: usb-pd@3f { @@ -101,9 +291,711 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <60 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec1: connector { + compatible = "usb-c-connector"; + label = "USB-C Top Left"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec1_connector_hs: endpoint { + remote-endpoint = <&dwc3_1_hs>; + }; + }; + port@1 { + reg = <1>; + typec1_connector_ss: endpoint { + remote-endpoint = <&atcphy1_typec_lanes>; + }; + }; + }; + }; + }; +}; + +/* USB controllers */ +&dwc3_0 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_0_hs: endpoint { + remote-endpoint = <&typec0_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_0_ss: endpoint { + remote-endpoint = <&atcphy0_usb3>; + }; + }; + }; +}; + +&dwc3_1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_1_hs: endpoint { + remote-endpoint = <&typec1_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_1_ss: endpoint { + remote-endpoint = <&atcphy1_usb3>; + }; + }; + }; +}; + +&dwc3_2 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_2_hs: endpoint { + remote-endpoint = <&typec2_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_2_ss: endpoint { + remote-endpoint = <&atcphy2_usb3>; + }; + }; + }; +}; + +&dwc3_3 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_3_hs: endpoint { + remote-endpoint = <&typec3_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_3_ss: endpoint { + remote-endpoint = <&atcphy3_usb3>; + }; + }; }; }; +/* USB controllers on die 1 */ +&dwc3_2_die1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_6_hs: endpoint { + remote-endpoint = <&typec6_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_6_ss: endpoint { + remote-endpoint = <&atcphy6_usb3>; + }; + }; + }; +}; + +&dwc3_3_die1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_7_hs: endpoint { + remote-endpoint = <&typec7_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_7_ss: endpoint { + remote-endpoint = <&atcphy7_usb3>; + }; + }; + }; +}; + +/* Type-C PHYs */ +&atcphy0 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy0_typec_lanes: endpoint { + remote-endpoint = <&typec0_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy0_usb3: endpoint { + remote-endpoint = <&dwc3_0_ss>; + }; + }; + }; +}; + +&atcphy1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy1_typec_lanes: endpoint { + remote-endpoint = <&typec1_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy1_usb3: endpoint { + remote-endpoint = <&dwc3_1_ss>; + }; + }; + }; +}; + +&atcphy2 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy2_typec_lanes: endpoint { + remote-endpoint = <&typec2_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy2_usb3: endpoint { + remote-endpoint = <&dwc3_2_ss>; + }; + }; + }; +}; + +&atcphy3 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy3_typec_lanes: endpoint { + remote-endpoint = <&typec3_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy3_usb3: endpoint { + remote-endpoint = <&dwc3_3_ss>; + }; + }; + }; +}; + +&atcphy2_die1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy6_typec_lanes: endpoint { + remote-endpoint = <&typec6_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy6_usb3: endpoint { + remote-endpoint = <&dwc3_6_ss>; + }; + }; + }; +}; + +&atcphy3_die1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy7_typec_lanes: endpoint { + remote-endpoint = <&typec7_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy7_usb3: endpoint { + remote-endpoint = <&dwc3_7_ss>; + }; + }; + }; +}; + +/* Audio */ +&i2c1 { + status = "okay"; + + speaker_tweeter: codec@38 { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x38>; + shutdown-gpios = <&pinctrl_ap 57 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + sound-name-prefix = "Tweeter"; + interrupts-extended = <&pinctrl_ap 58 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <4>; + ti,vmon-slot-no = <6>; + }; + + speaker_woofer: codec@39 { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x39>; + shutdown-gpios = <&pinctrl_ap 57 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + sound-name-prefix = "Woofer"; + interrupts-extended = <&pinctrl_ap 58 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <0>; + ti,vmon-slot-no = <2>; + }; +}; + +&i2c2 { + status = "okay"; + + jack_codec: codec@4b { + compatible = "cirrus,cs42l84"; + reg = <0x4b>; + reset-gpios = <&pinctrl_nub 8 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + interrupts-extended = <&pinctrl_ap 59 IRQ_TYPE_LEVEL_LOW>; + sound-name-prefix = "Jack"; + }; +}; + +&nco_clkref { + clock-frequency = <1068000000>; +}; + +/ { + sound: sound { + compatible = "apple,j180-macaudio", "apple,macaudio"; + model = "Mac Pro J180"; + + dai-link@0 { + link-name = "Speakers"; + /* + * DANGER ZONE: You can blow your speakers! + * + * The drivers are not ready, and unless you are careful + * to attenuate the audio stream, you run the risk of + * blowing your speakers. + */ + status = "disabled"; + cpu { + sound-dai = <&mca 0>; + }; + codec { + sound-dai = <&speaker_woofer>, <&speaker_tweeter>; + }; + }; + + dai-link@1 { + link-name = "Headphone Jack"; + + cpu { + sound-dai = <&mca 2>; + }; + codec { + sound-dai = <&jack_codec>; + }; + }; + }; +}; + +/* PCIe devices */ +&port_ge00 { + bus-range = <0x01 0x09>; + + pci@0,0 { + // compatible = "pci11f8,4000", "pciclass,060400", "pciclass,0604"; + device_type = "pci"; + reg = <0x10000 0x00 0x00 0x00 0x00>; + bus-range = <0x02 0x07>; + + #address-cells = <0x03>; + #size-cells = <0x02>; + ranges = <0x82010000 0x00 0x80000000 0x82010000 0x00 0x80000000 0x00 0x500000>, + <0xc3010000 0x18 0x00000000 0xc3010000 0x18 0x00000000 0x00 0x500000>; + + #interrupt-cells = <0x01>; + interrupt-map-mask = <0xffff00 0x00 0x00 0x07>; + interrupt-map = <0x20000 0x00 0x00 0x01 &port_ge00 0x00 0x00 0x00 0x00>, + <0x20000 0x00 0x00 0x02 &port_ge00 0x00 0x00 0x00 0x01>, + <0x20000 0x00 0x00 0x03 &port_ge00 0x00 0x00 0x00 0x02>, + <0x20000 0x00 0x00 0x04 &port_ge00 0x00 0x00 0x00 0x03>, + <0x20800 0x00 0x00 0x01 &port_ge00 0x00 0x00 0x00 0x01>, + <0x20800 0x00 0x00 0x02 &port_ge00 0x00 0x00 0x00 0x02>, + <0x20800 0x00 0x00 0x03 &port_ge00 0x00 0x00 0x00 0x03>, + <0x20800 0x00 0x00 0x04 &port_ge00 0x00 0x00 0x00 0x00>, + <0x21000 0x00 0x00 0x01 &port_ge00 0x00 0x00 0x00 0x02>, + <0x21000 0x00 0x00 0x02 &port_ge00 0x00 0x00 0x00 0x03>, + <0x21000 0x00 0x00 0x03 &port_ge00 0x00 0x00 0x00 0x00>, + <0x21000 0x00 0x00 0x04 &port_ge00 0x00 0x00 0x00 0x01>, + <0x21800 0x00 0x00 0x01 &port_ge00 0x00 0x00 0x00 0x03>, + <0x21800 0x00 0x00 0x02 &port_ge00 0x00 0x00 0x00 0x00>, + <0x21800 0x00 0x00 0x03 &port_ge00 0x00 0x00 0x00 0x01>, + <0x21800 0x00 0x00 0x04 &port_ge00 0x00 0x00 0x00 0x02>, + <0x22000 0x00 0x00 0x01 &port_ge00 0x00 0x00 0x00 0x00>, + <0x22000 0x00 0x00 0x02 &port_ge00 0x00 0x00 0x00 0x01>, + <0x22000 0x00 0x00 0x03 &port_ge00 0x00 0x00 0x00 0x02>, + <0x22000 0x00 0x00 0x04 &port_ge00 0x00 0x00 0x00 0x03>; + + /* pci-slot1-dsp, PCIe slot-1 */ + pci@0,0 { + compatible = "pci11f8,4000", "pciclass,060400", "pciclass,0604"; + device_type = "pci"; + reg = <0x20000 0x00 0x00 0x00 0x00>; + bus-range = <0x03 0x03>; + + #address-cells = <0x03>; + #size-cells = <0x02>; + ranges; + }; + + /* pci-slot2-dsp, PCIe slot-2 */ + pci@1,0 { + compatible = "pci11f8,4000", "pciclass,060400", "pciclass,0604"; + device_type = "pci"; + reg = <0x20800 0x00 0x00 0x00 0x00>; + bus-range = <0x04 0x04>; + + #address-cells = <0x03>; + #size-cells = <0x02>; + ranges; + }; + + /* pci-slot3-dsp, PCIe slot-3 */ + pci@2,0 { + compatible = "pci11f8,4000", "pciclass,060400", "pciclass,0604"; + device_type = "pci"; + reg = <0x21000 0x00 0x00 0x00 0x00>; + bus-range = <0x05 0x05>; + + #address-cells = <0x03>; + #size-cells = <0x02>; + ranges; + }; + + /* pci-slot4-dsp, PCIe slot-4 */ + pci@3,0 { + compatible = "pci11f8,4000", "pciclass,060400", "pciclass,0604"; + device_type = "pci"; + reg = <0x21800 0x00 0x00 0x00 0x00>; + bus-range = <0x06 0x06>; + + #address-cells = <0x03>; + #size-cells = <0x02>; + ranges; + }; + + /* pci-slot5-dsp, PCIe slot-5 */ + pci@4,0 { + compatible = "pci11f8,4000", "pciclass,060400", "pciclass,0604"; + device_type = "pci"; + reg = <0x22000 0x00 0x00 0x00 0x00>; + bus-range = <0x07 0x07>; + + #address-cells = <0x03>; + #size-cells = <0x02>; + ranges; + }; + + }; +}; + +&port_ge00_die1 { + bus-range = <0x01 0x09>; + + /* + * Add mulptiple "reset-gpios" since there is no mechanismen to access + * PERST# for devices behind the PCIe switch. + * The "pwren" GPIO is from the wifi/bt chip which faces the same + * problem without pci-pwrctrl integration. + */ + reset-gpios = <&pinctrl_ap 4 GPIO_ACTIVE_LOW>, + <&pinctrl_ap 6 GPIO_ACTIVE_LOW>, + <&pinctrl_ap 7 GPIO_ACTIVE_LOW>, + <&pinctrl_ap_die1 9 GPIO_ACTIVE_LOW>; + pwren-gpios = <&smc_gpio 13 GPIO_ACTIVE_HIGH>; + + pci@0,0 { + device_type = "pci"; + reg = <0x10000 0x00 0x00 0x00 0x00>; + bus-range = <0x02 0x09>; + + #address-cells = <3>; + #size-cells = <2>; + ranges; + + interrupt-controller; + #interrupt-cells = <1>; + interrupt-map-mask = <0xffff00 0x00 0x00 0x07>; + interrupt-map = <0x20000 0x00 0x00 0x01 &port_ge00_die1 0x00 0x00 0x00 0x00>, + <0x20000 0x00 0x00 0x02 &port_ge00_die1 0x00 0x00 0x00 0x01>, + <0x20000 0x00 0x00 0x03 &port_ge00_die1 0x00 0x00 0x00 0x02>, + <0x20000 0x00 0x00 0x04 &port_ge00_die1 0x00 0x00 0x00 0x03>, + <0x20800 0x00 0x00 0x01 &port_ge00_die1 0x00 0x00 0x00 0x01>, + <0x20800 0x00 0x00 0x02 &port_ge00_die1 0x00 0x00 0x00 0x02>, + <0x20800 0x00 0x00 0x03 &port_ge00_die1 0x00 0x00 0x00 0x03>, + <0x20800 0x00 0x00 0x04 &port_ge00_die1 0x00 0x00 0x00 0x00>, + <0x21000 0x00 0x00 0x01 &port_ge00_die1 0x00 0x00 0x00 0x02>, + <0x21000 0x00 0x00 0x02 &port_ge00_die1 0x00 0x00 0x00 0x03>, + <0x21000 0x00 0x00 0x03 &port_ge00_die1 0x00 0x00 0x00 0x00>, + <0x21000 0x00 0x00 0x04 &port_ge00_die1 0x00 0x00 0x00 0x01>, + <0x21800 0x00 0x00 0x01 &port_ge00_die1 0x00 0x00 0x00 0x03>, + <0x21800 0x00 0x00 0x02 &port_ge00_die1 0x00 0x00 0x00 0x00>, + <0x21800 0x00 0x00 0x03 &port_ge00_die1 0x00 0x00 0x00 0x01>, + <0x21800 0x00 0x00 0x04 &port_ge00_die1 0x00 0x00 0x00 0x02>, + <0x22000 0x00 0x00 0x01 &port_ge00_die1 0x00 0x00 0x00 0x00>, + <0x22000 0x00 0x00 0x02 &port_ge00_die1 0x00 0x00 0x00 0x01>, + <0x22000 0x00 0x00 0x03 &port_ge00_die1 0x00 0x00 0x00 0x02>, + <0x22000 0x00 0x00 0x04 &port_ge00_die1 0x00 0x00 0x00 0x03>, + <0x22800 0x00 0x00 0x01 &port_ge00_die1 0x00 0x00 0x00 0x01>, + <0x22800 0x00 0x00 0x02 &port_ge00_die1 0x00 0x00 0x00 0x02>, + <0x22800 0x00 0x00 0x03 &port_ge00_die1 0x00 0x00 0x00 0x03>, + <0x22800 0x00 0x00 0x04 &port_ge00_die1 0x00 0x00 0x00 0x00>, + <0x23000 0x00 0x00 0x01 &port_ge00_die1 0x00 0x00 0x00 0x02>, + <0x23000 0x00 0x00 0x02 &port_ge00_die1 0x00 0x00 0x00 0x03>, + <0x23000 0x00 0x00 0x03 &port_ge00_die1 0x00 0x00 0x00 0x00>, + <0x23000 0x00 0x00 0x04 &port_ge00_die1 0x00 0x00 0x00 0x01>; + + /* pci-usba-dsp, internal USB-A port */ + pci@0,0 { + compatible = "pci11f8,4000", "pciclass,060400", "pciclass,0604"; + device_type = "pci"; + reg = <0x20000 0x00 0x00 0x00 0x00>; + bus-range = <0x03 0x03>; + + #address-cells = <3>; + #size-cells = <2>; + ranges; + + interrupt-controller; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0x30000 0x00 0x00 0x02 &port_ge00_die1 0x00 0x00 0x00 0x00>, + <0x30000 0x00 0x00 0x03 &port_ge00_die1 0x00 0x00 0x00 0x01>, + <0x30000 0x00 0x00 0x04 &port_ge00_die1 0x00 0x00 0x00 0x02>; + + /* temporarily handled in the root port */ + // reset-gpios = <&pinctrl_ap 6 GPIO_ACTIVE_LOW>; + }; + + /* pci-sata-dsp, internal AHCI controller */ + pci@1,0 { + compatible = "pci11f8,4000", "pciclass,060400", "pciclass,0604"; + device_type = "pci"; + reg = <0x20800 0x00 0x00 0x00 0x00>; + bus-range = <0x04 0x04>; + + #address-cells = <3>; + #size-cells = <2>; + ranges; + + interrupt-controller; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0x40000 0x00 0x00 0x01 &port_ge00_die1 0x00 0x00 0x00 0x00>, + <0x40000 0x00 0x00 0x02 &port_ge00_die1 0x00 0x00 0x00 0x01>, + <0x40000 0x00 0x00 0x03 &port_ge00_die1 0x00 0x00 0x00 0x02>; + }; + + /* pci-bio-dsp, I/O board USB-A ports */ + pci@2,0 { + compatible = "pci11f8,4000", "pciclass,060400", "pciclass,0604"; + device_type = "pci"; + reg = <0x21000 0x00 0x00 0x00 0x00>; + bus-range = <0x05 0x05>; + + #address-cells = <3>; + #size-cells = <2>; + ranges; + + interrupt-controller; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0x50000 0x00 0x00 0x01 &port_ge00_die1 0x00 0x00 0x00 0x01>, + <0x50000 0x00 0x00 0x02 &port_ge00_die1 0x00 0x00 0x00 0x02>, + <0x50000 0x00 0x00 0x04 &port_ge00_die1 0x00 0x00 0x00 0x00>; + + /* temporarily handled in the root port */ + // reset-gpios = <&pinctrl_ap 7 GPIO_ACTIVE_LOW>; + }; + + /* pci-lan-dsp, Qtion AQC113 10G etherner controller (0) */ + pci@3,0 { + compatible = "pci11f8,4000", "pciclass,060400", "pciclass,0604"; + device_type = "pci"; + reg = <0x21800 0x00 0x00 0x00 0x00>; + bus-range = <0x06 0x06>; + + #address-cells = <3>; + #size-cells = <2>; + ranges; + + interrupt-controller; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0x60000 0x00 0x00 0x01 &port_ge00_die1 0x00 0x00 0x00 0x02>, + <0x60000 0x00 0x00 0x03 &port_ge00_die1 0x00 0x00 0x00 0x00>, + <0x60000 0x00 0x00 0x04 &port_ge00_die1 0x00 0x00 0x00 0x01>; + + ethernet0: ethernet@0,0 { + reg = <0x60000 0x0 0x0 0x0 0x0>; + /* To be filled by the loader */ + local-mac-address = [00 10 18 00 00 00]; + }; + }; + + /* pci-lan-b-dsp, Qtion AQC113 10G etherner controller (1) */ + pci@4,0 { + compatible = "pci11f8,4000", "pciclass,060400", "pciclass,0604"; + device_type = "pci"; + reg = <0x22000 0x00 0x00 0x00 0x00>; + bus-range = <0x07 0x07>; + + #address-cells = <3>; + #size-cells = <2>; + ranges; + + interrupt-controller; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0x70000 0x00 0x00 0x02 &port_ge00_die1 0x00 0x00 0x00 0x00>, + <0x70000 0x00 0x00 0x03 &port_ge00_die1 0x00 0x00 0x00 0x01>, + <0x70000 0x00 0x00 0x04 &port_ge00_die1 0x00 0x00 0x00 0x02>; + + ethernet1: ethernet@0,0 { + reg = <0x70000 0x0 0x0 0x0 0x0>; + /* To be filled by the loader */ + local-mac-address = [00 10 18 00 00 00]; + }; + }; + + /* pci-wifibt-dsp, Broadcom BCM4388 Wlan/BT */ + pci@5,0 { + compatible = "pci11f8,4000", "pciclass,060400", "pciclass,0604"; + device_type = "pci"; + reg = <0x22800 0x00 0x00 0x00 0x00>; + bus-range = <0x08 0x08>; + + #address-cells = <3>; + #size-cells = <2>; + ranges; + + interrupt-controller; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0x80000 0x00 0x00 0x01 &port_ge00_die1 0x00 0x00 0x00 0x00>, + <0x80000 0x00 0x00 0x02 &port_ge00_die1 0x00 0x00 0x00 0x01>, + <0x80000 0x00 0x00 0x03 &port_ge00_die1 0x00 0x00 0x00 0x02>, + <0x80100 0x00 0x00 0x01 &port_ge00_die1 0x00 0x00 0x00 0x00>, + <0x80100 0x00 0x00 0x02 &port_ge00_die1 0x00 0x00 0x00 0x01>, + <0x80100 0x00 0x00 0x03 &port_ge00_die1 0x00 0x00 0x00 0x02>; + + /* temporarily handled in the root port */ + // reset-gpios = <&pinctrl_ap 4 GPIO_ACTIVE_LOW>; + // pwren-gpios = <&smc_gpio 13 GPIO_ACTIVE_HIGH>; + + wifi0: wifi@0,0 { + reg = <0x80000 0x0 0x0 0x0 0x0>; + compatible = "pci14e4,4433"; + brcm,board-type = "apple,sumatra"; + apple,antenna-sku = "XX"; + /* To be filled by the loader */ + local-mac-address = [00 10 18 00 00 10]; + }; + + bluetooth0: network@0,1 { + compatible = "pci14e4,5f71"; + brcm,board-type = "apple,sumatra"; + // reg = <0x80100 0x0 0x0 0x0 0x0>; + /* To be filled by the loader */ + local-bd-address = [00 00 00 00 00 00]; + }; + }; + + /* pci-slot6-dsp, PCIe slot-6 */ + pci@6,0 { + compatible = "pci11f8,4000", "pciclass,060400", "pciclass,0604"; + device_type = "pci"; + reg = <0x23000 0x00 0x00 0x00 0x00>; + bus-range = <0x09 0x09>; + + #address-cells = <3>; + #size-cells = <2>; + ranges; + }; + }; +}; + +&pcie_ge { + status = "ok"; +}; + +&pcie_ge_dart { + status = "ok"; +}; + +&pcie_ge_die1 { + status = "ok"; +}; + +&pcie_ge_dart_die1 { + status = "ok"; +}; + /* * Delete unused PCIe nodes, the Mac Pro uses slightly different PCIe * controllers with a single port connected to a PM40100 PCIe switch diff --git a/arch/arm64/boot/dts/apple/t6022-j475d.dts b/arch/arm64/boot/dts/apple/t6022-j475d.dts index 736594544f79b5..cdfc78a1703c7a 100644 --- a/arch/arm64/boot/dts/apple/t6022-j475d.dts +++ b/arch/arm64/boot/dts/apple/t6022-j475d.dts @@ -9,6 +9,8 @@ /dts-v1/; +#define NO_DCP + #include "t6022.dtsi" #include "t602x-j474-j475.dtsi" #include "t6022-jxxxd.dtsi" @@ -16,14 +18,31 @@ / { compatible = "apple,j475d", "apple,t6022", "apple,arm-platform"; model = "Apple Mac Studio (M2 Ultra, 2023)"; + + aliases { + atcphy4 = &atcphy0_die1; + atcphy5 = &atcphy1_die1; + /delete-property/ dcp; + /delete-property/ sio; + }; +}; + +&sio { + status = "disabled"; }; &framebuffer0 { power-domains = <&ps_dispext0_cpu0_die1>, <&ps_dptx_phy_ps_die1>; }; +&dcpext0_die1 { + // J180 misses "function-dp2hdmi_pwr_en" + dp2hdmi-pwren-gpios = <&smc_gpio 25 GPIO_ACTIVE_HIGH>; +}; + /* enable PCIe port01 with SDHCI */ &port01 { + pwren-gpios = <&smc_gpio 22 GPIO_ACTIVE_HIGH>; status = "okay"; }; @@ -31,6 +50,34 @@ status = "okay"; }; +&typec4 { + label = "USB-C Front Right"; +}; + +&typec5 { + label = "USB-C Front Left"; +}; + +/* delete unused USB nodes on die 1 */ +/delete-node/ &dwc3_2_dart_0_die1; +/delete-node/ &dwc3_2_dart_1_die1; +/delete-node/ &dwc3_2_die1; +/delete-node/ &atcphy2_die1; +/delete-node/ &atcphy2_xbar_die1; + +/delete-node/ &dwc3_3_dart_0_die1; +/delete-node/ &dwc3_3_dart_1_die1; +/delete-node/ &dwc3_3_die1; +/delete-node/ &atcphy3_die1; +/delete-node/ &atcphy3_xbar_die1; + +/* delete unused always-on power-domains on die 1 */ +/delete-node/ &ps_atc2_usb_aon_die1; +/delete-node/ &ps_atc2_usb_die1; + +/delete-node/ &ps_atc3_usb_aon_die1; +/delete-node/ &ps_atc3_usb_die1; + &wifi0 { compatible = "pci14e4,4434"; brcm,board-type = "apple,canary"; @@ -40,3 +87,10 @@ compatible = "pci14e4,5f72"; brcm,board-type = "apple,canary"; }; + +&sound { + compatible = "apple,j475-macaudio", "apple,j375-macaudio", "apple,macaudio"; + model = "Mac Studio J475"; +}; + +#include "hwmon-fan-dual.dtsi" diff --git a/arch/arm64/boot/dts/apple/t6022-jxxxd.dtsi b/arch/arm64/boot/dts/apple/t6022-jxxxd.dtsi index 4f7bf2ebfe397d..f11b017dc0496f 100644 --- a/arch/arm64/boot/dts/apple/t6022-jxxxd.dtsi +++ b/arch/arm64/boot/dts/apple/t6022-jxxxd.dtsi @@ -9,6 +9,62 @@ * Copyright The Asahi Linux Contributors */ +/ { + aliases { + dcpext4 = &dcpext0_die1; + disp0 = &display; + sio1 = &sio_die1; + }; +}; + +&lpdptxphy_die1 { + status = "okay"; +}; + +&display { + iommus = <&dispext0_dart_die1 0>; +}; + +&dispext0_dart_die1 { + status = "okay"; +}; + +&dcpext0_dart_die1 { + status = "okay"; +}; + +&dcpext0_mbox_die1 { + status = "okay"; +}; + +&dcpext0_die1 { + status = "okay"; + apple,connector-type = "HDMI-A"; + + /* HDMI HPD gpio, used as interrupt*/ + hdmi-hpd-gpios = <&pinctrl_aop 41 GPIO_ACTIVE_HIGH>; + + hdmi-pwren-gpios = <&smc_gpio 23 GPIO_ACTIVE_HIGH>; + // J180 misses "function-dp2hdmi_pwr_en" + // dp2hdmi-pwren-gpios = <&smc_gpio 25 GPIO_ACTIVE_HIGH>; + + phys = <&lpdptxphy_die1>; + phy-names = "dp-phy"; + apple,dptx-phy = <4>; + apple,dptx-die = <1>; +}; + +&dpaudio1_die1 { + status = "okay"; +}; + +/* delete missing dcp0/disp0 */ +/delete-node/ &disp0_dart; +/delete-node/ &dcp_dart; +/delete-node/ &dcp_mbox; +/delete-node/ &dcp; +/delete-node/ &dpaudio0; + /* delete power-domains for missing disp0 / disp0_die1 */ /delete-node/ &ps_disp0_cpu0; /delete-node/ &ps_disp0_fe; @@ -25,6 +81,29 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <44 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec4: connector { + compatible = "usb-c-connector"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec4_connector_hs: endpoint { + remote-endpoint = <&dwc3_4_hs>; + }; + }; + port@1 { + reg = <1>; + typec4_connector_ss: endpoint { + remote-endpoint = <&atcphy4_typec_lanes>; + }; + }; + }; + }; }; /* front-left */ @@ -34,5 +113,115 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <44 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec5: connector { + compatible = "usb-c-connector"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec5_connector_hs: endpoint { + remote-endpoint = <&dwc3_5_hs>; + }; + }; + port@1 { + reg = <1>; + typec5_connector_ss: endpoint { + remote-endpoint = <&atcphy5_typec_lanes>; + }; + }; + }; + }; + }; +}; + + +/* USB controllers on die 1 */ +&dwc3_0_die1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_4_hs: endpoint { + remote-endpoint = <&typec4_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_4_ss: endpoint { + remote-endpoint = <&atcphy4_usb3>; + }; + }; + }; +}; + +&dwc3_1_die1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_5_hs: endpoint { + remote-endpoint = <&typec5_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_5_ss: endpoint { + remote-endpoint = <&atcphy5_usb3>; + }; + }; + }; +}; + +/* Type-C PHYs */ +&atcphy0_die1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy4_typec_lanes: endpoint { + remote-endpoint = <&typec4_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy4_usb3: endpoint { + remote-endpoint = <&dwc3_4_ss>; + }; + }; + }; +}; + +&atcphy1_die1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy5_typec_lanes: endpoint { + remote-endpoint = <&typec5_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy5_usb3: endpoint { + remote-endpoint = <&dwc3_5_ss>; + }; + }; }; }; diff --git a/arch/arm64/boot/dts/apple/t6022-pcie-ge.dtsi b/arch/arm64/boot/dts/apple/t6022-pcie-ge.dtsi new file mode 100644 index 00000000000000..f78c483c29133f --- /dev/null +++ b/arch/arm64/boot/dts/apple/t6022-pcie-ge.dtsi @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * Include PCIe-GE nodes presen on both dies of T6022 (M2 Ultra) in the + * Mac Pro (2023). + * + * Copyright The Asahi Linux Contributors + */ + +#define DIE +#define DIE_NO 0 + +&die0 { + #include "t602x-pcie-ge.dtsi" +}; + +#undef DIE +#undef DIE_NO + +#define DIE _die1 +#define DIE_NO 1 + +&die1 { + #include "t602x-pcie-ge.dtsi" +}; + +#undef DIE +#undef DIE_NO diff --git a/arch/arm64/boot/dts/apple/t6022.dtsi b/arch/arm64/boot/dts/apple/t6022.dtsi index e73bf2f7510ae2..f17c9a4f59e482 100644 --- a/arch/arm64/boot/dts/apple/t6022.dtsi +++ b/arch/arm64/boot/dts/apple/t6022.dtsi @@ -16,6 +16,13 @@ #include "multi-die-cpp.h" +#ifndef GPU_REPEAT +# define GPU_REPEAT(x) +#endif +#ifndef GPU_DIE_REPEAT +# define GPU_DIE_REPEAT(x) +#endif + #include "t602x-common.dtsi" / { @@ -339,11 +346,38 @@ }; }; +&dcpext0_die1 { + apple,bw-scratch = <&pmgr_dcp 0 4 0x1240>; +}; + +&dcpext1_die1 { + apple,bw-scratch = <&pmgr_dcp 0 4 0x1248>; +}; + &ps_gfx { // On t6022, the die0 GPU power domain needs both AFR power domains power-domains = <&ps_afr>, <&ps_afr_die1>; }; &gpu { - compatible = "apple,agx-g14d", "apple,agx-g14s"; + compatible = "apple,agx-t6022", "apple,agx-g14x", "apple,agx-g14d", "apple,agx-g14s"; + + apple,avg-power-filter-tc-ms = <302>; + apple,avg-power-ki-only = <1.0125>; + apple,avg-power-kp = <0.15>; + apple,fast-die0-integral-gain = <9.6>; + apple,fast-die0-proportional-gain = <24.0>; + apple,idleoff-standby-timer = <3000>; + apple,perf-base-pstate = <5>; + apple,perf-boost-ce-step = <100>; + apple,perf-boost-min-util = <75>; + apple,perf-tgt-utilization = <70>; + apple,ppm-ki = <11.0>; + apple,ppm-kp = <0.15>; +}; + +&pinctrl_ap_die1 { + pcie_ge_pins_die1: pcie-ge1-pins { + pinmux = ; + }; }; diff --git a/arch/arm64/boot/dts/apple/t602x-common.dtsi b/arch/arm64/boot/dts/apple/t602x-common.dtsi index 9c800a391e7e87..2905234ad6d40b 100644 --- a/arch/arm64/boot/dts/apple/t602x-common.dtsi +++ b/arch/arm64/boot/dts/apple/t602x-common.dtsi @@ -387,6 +387,134 @@ }; }; + gpu_opp: opp-table-gpu { + compatible = "operating-points-v2"; + + /* + * NOTE: The voltage and power values are device-specific and + * must be filled in by the bootloader. + */ + opp00 { + opp-hz = /bits/ 64 <0>; + opp-microvolt = GPU_REPEAT(400000); + opp-microwatt = <0>; + }; + opp01 { + opp-hz = /bits/ 64 <444000000>; + opp-microvolt = GPU_REPEAT(637000); + opp-microwatt = <4295000>; + }; + opp02 { + opp-hz = /bits/ 64 <612000000>; + opp-microvolt = GPU_REPEAT(656000); + opp-microwatt = <6251000>; + }; + opp03 { + opp-hz = /bits/ 64 <808000000>; + opp-microvolt = GPU_REPEAT(687000); + opp-microwatt = <8625000>; + }; + opp04 { + opp-hz = /bits/ 64 <968000000>; + opp-microvolt = GPU_REPEAT(725000); + opp-microwatt = <11948000>; + }; + opp05 { + opp-hz = /bits/ 64 <1110000000>; + opp-microvolt = GPU_REPEAT(790000); + opp-microwatt = <15071000>; + }; + opp06 { + opp-hz = /bits/ 64 <1236000000>; + opp-microvolt = GPU_REPEAT(843000); + opp-microwatt = <18891000>; + }; + opp07 { + opp-hz = /bits/ 64 <1338000000>; + opp-microvolt = GPU_REPEAT(887000); + opp-microwatt = <21960000>; + }; + opp08 { + opp-hz = /bits/ 64 <1398000000>; + opp-microvolt = GPU_REPEAT(918000); + opp-microwatt = <22800000>; + }; + }; + + gpu_cs_opp: opp-table-gpu-cs { + compatible = "operating-points-v2"; + + /* + * NOTE: The voltage and power values are device-specific and + * must be filled in by the bootloader. + */ + opp00 { + opp-hz = /bits/ 64 <24>; + opp-microvolt = GPU_DIE_REPEAT(668000); + }; + opp01 { + opp-hz = /bits/ 64 <444000000>; + opp-microvolt = GPU_DIE_REPEAT(668000); + }; + opp02 { + opp-hz = /bits/ 64 <612000000>; + opp-microvolt = GPU_DIE_REPEAT(678000); + }; + opp03 { + opp-hz = /bits/ 64 <808000000>; + opp-microvolt = GPU_DIE_REPEAT(737000); + }; + opp04 { + opp-hz = /bits/ 64 <1024000000>; + opp-microvolt = GPU_DIE_REPEAT(815000); + }; + opp05 { + opp-hz = /bits/ 64 <1140000000>; + opp-microvolt = GPU_DIE_REPEAT(862000); + }; + opp06 { + opp-hz = /bits/ 64 <1236000000>; + opp-microvolt = GPU_DIE_REPEAT(893000); + }; + }; + + gpu_afr_opp: opp-table-gpu-afr { + compatible = "operating-points-v2"; + + /* + * NOTE: The voltage and power values are device-specific and + * must be filled in by the bootloader. + */ + opp00 { + opp-hz = /bits/ 64 <24>; + opp-microvolt = GPU_DIE_REPEAT(668000); + }; + opp01 { + opp-hz = /bits/ 64 <400000000>; + opp-microvolt = GPU_DIE_REPEAT(668000); + }; + opp02 { + opp-hz = /bits/ 64 <552000000>; + opp-microvolt = GPU_DIE_REPEAT(678000); + }; + opp03 { + opp-hz = /bits/ 64 <760000000>; + opp-microvolt = GPU_DIE_REPEAT(737000); + }; + opp04 { + opp-hz = /bits/ 64 <980000000>; + opp-microvolt = GPU_DIE_REPEAT(815000); + }; + opp05 { + opp-hz = /bits/ 64 <1098000000>; + opp-microvolt = GPU_DIE_REPEAT(862000); + }; + opp06 { + opp-hz = /bits/ 64 <1200000000>; + opp-microvolt = GPU_DIE_REPEAT(893000); + }; + }; + pmu-e { compatible = "apple,blizzard-pmu"; interrupt-parent = <&aic>; @@ -423,6 +551,41 @@ clock-output-names = "clk_200m"; }; + clk_disp0: clock-disp0 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <257142848>; /* TODO: check */ + clock-output-names = "clk_disp0"; + }; + + clk_dispext0: clock-dispext0 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + clock-output-names = "clk_dispext0"; + }; + + clk_dispext0_die1: clock-dispext0_die1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + clock-output-names = "clk_dispext0_die1"; + }; + + clk_dispext1: clock-dispext1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + clock-output-names = "clk_dispext1"; + }; + + clk_dispext1_die1: clock-dispext1_die1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + clock-output-names = "clk_dispext1_die1"; + }; + /* * This is a fabulated representation of the input clock * to NCO since we don't know the true clock tree. @@ -451,15 +614,15 @@ }; uat_handoff: uat-handoff { - status = "disabled"; + reg = <0 0 0 0>; }; uat_pagetables: uat-pagetables { - status = "disabled"; + reg = <0 0 0 0>; }; uat_ttbs: uat-ttbs { - status = "disabled"; + reg = <0 0 0 0>; }; }; }; diff --git a/arch/arm64/boot/dts/apple/t602x-die0.dtsi b/arch/arm64/boot/dts/apple/t602x-die0.dtsi index 2e7d2bf08ddc82..8221037da27000 100644 --- a/arch/arm64/boot/dts/apple/t602x-die0.dtsi +++ b/arch/arm64/boot/dts/apple/t602x-die0.dtsi @@ -7,7 +7,7 @@ */ nco: clock-controller@28e03c000 { - compatible = "apple,t6020-nco", "apple,t8103-nco"; + compatible = "apple,t6020-nco", "apple,t8103-nco", "apple,nco"; reg = <0x2 0x8e03c000 0x0 0x14000>; clocks = <&nco_clkref>; #clock-cells = <1>; @@ -23,8 +23,23 @@ power-domains = <&ps_aic>; }; + pmgr_misc: power-management@28e20c000 { + compatible = "apple,t6020-pmgr-misc", "apple,t6000-pmgr-misc"; + #address-cells = <1>; + #size-cells = <1>; + reg = <0x2 0x8e20c000 0 0x400>, + <0x2 0x8e20c400 0 0x400>; + reg-names = "fabric-ps", "dcs-ps"; + }; + + pmgr_dcp: power-management@28e3d0000 { + reg = <0x2 0x8e3d0000 0x0 0x4000>; + reg-names = "dcp-fw-pmgr"; + #apple,bw-scratch-cells = <3>; + }; + nub_spmi0: spmi@29e114000 { - compatible = "apple,t6020-spmi", "apple,t8103-spmi"; + compatible = "apple,t6020-spmi", "apple,t8103-spmi", "apple,spmi"; reg = <0x2 0x9e114000 0x0 0x100>; #address-cells = <2>; #size-cells = <0>; @@ -81,28 +96,15 @@ }; wdt: watchdog@29e2c4000 { - compatible = "apple,t6020-wdt", "apple,t8103-wdt"; + compatible = "apple,t6020-wdt", "apple,t8103-wdt", "apple,wdt"; reg = <0x2 0x9e2c4000 0x0 0x4000>; clocks = <&clkref>; interrupt-parent = <&aic>; interrupts = ; }; - smc_mbox: mbox@2a2408000 { - compatible = "apple,t6020-asc-mailbox", "apple,asc-mailbox-v4"; - reg = <0x2 0xa2408000 0x0 0x4000>; - interrupt-parent = <&aic>; - interrupts = , - , - , - ; - interrupt-names = "send-empty", "send-not-empty", - "recv-empty", "recv-not-empty"; - #mbox-cells = <0>; - }; - smc: smc@2a2400000 { - compatible = "apple,t6020-smc", "apple,t8103-smc"; + compatible = "apple,t6020-smc", "apple,smc"; reg = <0x2 0xa2400000 0x0 0x4000>, <0x2 0xa3e00000 0x0 0x100000>; reg-names = "smc", "sram"; @@ -114,17 +116,40 @@ #gpio-cells = <2>; }; + smc_hwmon: hwmon { + compatible = "apple,smc-hwmon"; + }; + + smc_rtc: rtc { + compatible = "apple,smc-rtc"; + nvmem-cells = <&rtc_offset>; + nvmem-cell-names = "rtc_offset"; + }; + smc_reboot: reboot { compatible = "apple,smc-reboot"; nvmem-cells = <&shutdown_flag>, <&boot_stage>, - <&boot_error_count>, <&panic_count>; + <&boot_error_count>, <&panic_count>, <&pm_setting>; nvmem-cell-names = "shutdown_flag", "boot_stage", - "boot_error_count", "panic_count"; + "boot_error_count", "panic_count", "pm_setting"; }; }; + smc_mbox: mbox@2a2408000 { + compatible = "apple,t6020-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0xa2408000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + }; + pinctrl_smc: pinctrl@2a2820000 { - compatible = "apple,t6020-pinctrl", "apple,t8103-pinctrl"; + compatible = "apple,t6020-pinctrl", "apple,t8103-pinctrl", "apple,pinctrl"; reg = <0x2 0xa2820000 0x0 0x4000>; gpio-controller; @@ -144,13 +169,309 @@ ; }; - sio_dart: iommu@39b008000 { + aop_mbox: mbox@2a6408000 { + compatible = "apple,t6020-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0xa6408000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + status = "disabled"; + }; + + aop_dart: iommu@2a6808000 { compatible = "apple,t6020-dart", "apple,t8110-dart"; - reg = <0x3 0x9b008000 0x0 0x8000>; + reg = <0x2 0xa6808000 0x0 0x4000>; + #iommu-cells = <1>; interrupt-parent = <&aic>; - interrupts = ; + interrupts = ; + status = "disabled"; + // apple,dma-range = <0x100 0x0 0x300 0x0>; + }; + + aop_admac: dma-controller@2a6980000 { + compatible = "apple,t6020-admac", "apple,admac"; + reg = <0x2 0xa6980000 0x0 0x34000>; + #dma-cells = <1>; + dma-channels = <16>; + interrupts-extended = <0>, + <0>, + <&aic AIC_IRQ 0 631 IRQ_TYPE_LEVEL_HIGH>, + <0>; + iommus = <&aop_dart 10>; + status = "disabled"; + }; + + aop: aop@2a6c00000 { + compatible = "apple,t6020-aop"; + reg = <0x2 0xa6c00000 0x0 0x250000>, + <0x2 0xa6400000 0x0 0x6c000>; + mboxes = <&aop_mbox>; + mbox-names = "mbox"; + iommus = <&aop_dart 0>; + + status = "disabled"; + + aop_audio: audio { + compatible = "apple,t6020-aop-audio", "apple,aop-audio"; + dmas = <&aop_admac 1>; + dma-names = "dma"; + }; + + aop_als: als { + compatible = "apple,t6020-aop-als", "apple,aop-als"; + // intentionally empty + }; + + las { + compatible = "apple,t6020-aop-las", "apple,aop-las"; + }; + }; + + mtp: mtp@2a9400000 { + compatible = "apple,t6020-mtp", "apple,t6020-rtk-helper-asc4", "apple,mtp", "apple,rtk-helper-asc4"; + reg = <0x2 0xa9400000 0x0 0x4000>, + <0x2 0xa9c00000 0x0 0x100000>; + reg-names = "asc", "sram"; + mboxes = <&mtp_mbox>; + iommus = <&mtp_dart 1>; + #helper-cells = <0>; + + status = "disabled"; + }; + + mtp_mbox: mbox@2a9408000 { + compatible = "apple,t6020-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0xa9408000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + + status = "disabled"; + }; + + mtp_dart: iommu@2a9808000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x2 0xa9808000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; #iommu-cells = <1>; - power-domains = <&ps_sio_cpu>; + + apple,dma-range = <0x100 0x0 0x1 0x0>; + + status = "disabled"; + }; + + mtp_dockchannel: fifo@2a9b14000 { + compatible = "apple,t6020-dockchannel", "apple,dockchannel"; + reg = <0x2 0xa9b14000 0x0 0x4000>; + reg-names = "irq"; + interrupt-parent = <&aic>; + interrupts = ; + + ranges = <0 0x2 0xa9b28000 0x20000>; + nonposted-mmio; + #address-cells = <1>; + #size-cells = <1>; + + interrupt-controller; + #interrupt-cells = <2>; + + status = "disabled"; + + mtp_hid: input@8000 { + compatible = "apple,dockchannel-hid"; + reg = <0x8000 0x4000>, + <0xc000 0x4000>, + <0x0000 0x4000>, + <0x4000 0x4000>; + reg-names = "config", "data", + "rmt-config", "rmt-data"; + iommus = <&mtp_dart 1>; + interrupt-parent = <&mtp_dockchannel>; + interrupts = <2 IRQ_TYPE_LEVEL_HIGH>, + <3 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "tx", "rx"; + + apple,fifo-size = <0x800>; + apple,helper-cpu = <&mtp>; + }; + + }; + + isp_dart0: iommu@3860e8000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x3 0x860e8000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>; + + apple,dma-range = <0x100 0x0 0x1 0x0>; + status = "disabled"; + }; + + isp_dart1: iommu@3860f4000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x3 0x860f4000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>; + + apple,dma-range = <0x100 0x0 0x1 0x0>; + status = "disabled"; + }; + + isp_dart2: iommu@3860fc000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x3 0x860fc000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>; + + apple,dma-range = <0x100 0x0 0x1 0x0>; + status = "disabled"; + }; + + isp: isp@384000000 { + compatible = "apple,t6020-isp", "apple,isp"; + iommus = <&isp_dart0 0>, <&isp_dart1 0>, <&isp_dart2 0>; + reg-names = "coproc", "mbox", "gpio", "mbox2"; + reg = <0x3 0x84000000 0x0 0x2000000>, + <0x3 0x86104000 0x0 0x100>, + <0x3 0x86104170 0x0 0x100>, + <0x3 0x861043f0 0x0 0x100>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_cpu>, <&ps_isp_fe>, + <&ps_dprx>, <&ps_isp_vis>, <&ps_isp_be>, + <&ps_isp_clr>, <&ps_isp_raw>; + apple,dart-vm-size = <0x0 0xa0000000>; + + status = "disabled"; + }; + + disp0_dart: iommu@389304000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x3 0x89304000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + status = "disabled"; + power-domains = <&ps_disp0_cpu0>; + apple,dma-range = <0x100 0x0 0x10 0x0>; + }; + + dcp_dart: iommu@38930c000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x3 0x8930c000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_disp0_cpu0>; + apple,dma-range = <0x100 0x0 0x10 0x0>; + }; + + dcp_mbox: mbox@389c08000 { + compatible = "apple,t6020-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x3 0x89c08000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&ps_disp0_cpu0>; + }; + + dcp: dcp@389c00000 { + compatible = "apple,t6020-dcp", "apple,dcp"; + mboxes = <&dcp_mbox>; + mbox-names = "mbox"; + iommus = <&dcp_dart 5>; + + reg-names = "coproc", "disp-0", "disp-1", "disp-2", "disp-3"; + reg = <0x3 0x89c00000 0x0 0x4000>, // check? + <0x3 0x88000000 0x0 0x61c000>, + <0x3 0x89320000 0x0 0x4000>, + <0x3 0x89344000 0x0 0x4000>, + <0x3 0x89800000 0x0 0x800000>; + apple,bw-scratch = <&pmgr_dcp 0 4 0x1208>; + power-domains = <&ps_disp0_cpu0>; + resets = <&ps_disp0_cpu0>; + clocks = <&clk_disp0>; + phandle = <&dcp>; + // required bus properties for 'piodma' subdevice + #address-cells = <2>; + #size-cells = <2>; + + disp0_piodma: piodma { + iommus = <&disp0_dart 4>; + phandle = <&disp0_piodma>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dcp_audio: endpoint { + remote-endpoint = <&dpaudio0_dcp>; + }; + }; + }; + }; + + display: display-subsystem { + compatible = "apple,display-subsystem"; + iommus = <&disp0_dart 0>; + /* generate phandle explicitly for use in loader */ + phandle = <&display>; + }; + + sep_dart: iommu@394ac0000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x3 0x94ac0000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + status = "disabled"; + }; + + sep: sep@396400000 { + compatible = "apple,sep"; + reg = <0x3 0x96400000 0x0 0x6C000>; + mboxes = <&sep_mbox>; + mbox-names = "mbox"; + iommus = <&sep_dart 0>; + power-domains = <&ps_sep>; + status = "disabled"; + }; + + sep_mbox: mbox@396408000 { + compatible = "apple,t6020-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x3 0x96408000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; }; fpwm0: pwm@39b030000 { @@ -163,7 +484,7 @@ }; i2c0: i2c@39b040000 { - compatible = "apple,t6020-i2c", "apple,t8103-i2c"; + compatible = "apple,t6020-i2c", "apple,t8103-i2c", "apple,i2c"; reg = <0x3 0x9b040000 0x0 0x4000>; clocks = <&clkref>; interrupt-parent = <&aic>; @@ -176,7 +497,7 @@ }; i2c1: i2c@39b044000 { - compatible = "apple,t6020-i2c", "apple,t8103-i2c"; + compatible = "apple,t6020-i2c", "apple,t8103-i2c", "apple,i2c"; reg = <0x3 0x9b044000 0x0 0x4000>; clocks = <&clkref>; interrupt-parent = <&aic>; @@ -190,7 +511,7 @@ }; i2c2: i2c@39b048000 { - compatible = "apple,t6020-i2c", "apple,t8103-i2c"; + compatible = "apple,t6020-i2c", "apple,t8103-i2c", "apple,i2c"; reg = <0x3 0x9b048000 0x0 0x4000>; clocks = <&clkref>; interrupt-parent = <&aic>; @@ -204,7 +525,7 @@ }; i2c3: i2c@39b04c000 { - compatible = "apple,t6020-i2c", "apple,t8103-i2c"; + compatible = "apple,t6020-i2c", "apple,t8103-i2c", "apple,i2c"; reg = <0x3 0x9b04c000 0x0 0x4000>; clocks = <&clkref>; interrupt-parent = <&aic>; @@ -218,7 +539,7 @@ }; i2c4: i2c@39b050000 { - compatible = "apple,t6020-i2c", "apple,t8103-i2c"; + compatible = "apple,t6020-i2c", "apple,t8103-i2c", "apple,i2c"; reg = <0x3 0x9b050000 0x0 0x4000>; clocks = <&clkref>; interrupt-parent = <&aic>; @@ -232,7 +553,7 @@ }; i2c5: i2c@39b054000 { - compatible = "apple,t6020-i2c", "apple,t8103-i2c"; + compatible = "apple,t6020-i2c", "apple,t8103-i2c", "apple,i2c"; reg = <0x3 0x9b054000 0x0 0x4000>; clocks = <&clkref>; interrupt-parent = <&aic>; @@ -246,7 +567,7 @@ }; i2c6: i2c@39b054000 { - compatible = "apple,t6020-i2c", "apple,t8103-i2c"; + compatible = "apple,t6020-i2c", "apple,t8103-i2c", "apple,i2c"; reg = <0x3 0x9b054000 0x0 0x4000>; clocks = <&clkref>; interrupt-parent = <&aic>; @@ -260,7 +581,7 @@ }; i2c7: i2c@39b054000 { - compatible = "apple,t6020-i2c", "apple,t8103-i2c"; + compatible = "apple,t6020-i2c", "apple,t8103-i2c", "apple,i2c"; reg = <0x3 0x9b054000 0x0 0x4000>; clocks = <&clkref>; interrupt-parent = <&aic>; @@ -274,7 +595,7 @@ }; i2c8: i2c@39b054000 { - compatible = "apple,t6020-i2c", "apple,t8103-i2c"; + compatible = "apple,t6020-i2c", "apple,t8103-i2c", "apple,i2c"; reg = <0x3 0x9b054000 0x0 0x4000>; clocks = <&clkref>; interrupt-parent = <&aic>; @@ -288,7 +609,7 @@ }; spi1: spi@39b104000 { - compatible = "apple,t6020-spi", "apple,t8103-spi"; + compatible = "apple,t6020-spi", "apple,t8103-spi", "apple,spi"; reg = <0x3 0x9b104000 0x0 0x4000>; interrupt-parent = <&aic>; interrupts = ; @@ -302,7 +623,7 @@ }; spi2: spi@39b108000 { - compatible = "apple,t6020-spi", "apple,t8103-spi"; + compatible = "apple,t6020-spi", "apple,t8103-spi", "apple,spi"; reg = <0x3 0x9b108000 0x0 0x4000>; interrupt-parent = <&aic>; interrupts = ; @@ -316,7 +637,7 @@ }; spi4: spi@39b110000 { - compatible = "apple,t6020-spi", "apple,t8103-spi"; + compatible = "apple,t6020-spi", "apple,t8103-spi", "apple,spi"; reg = <0x3 0x9b110000 0x0 0x4000>; interrupt-parent = <&aic>; interrupts = ; @@ -346,7 +667,7 @@ }; admac: dma-controller@39b400000 { - compatible = "apple,t6020-admac", "apple,t8103-admac"; + compatible = "apple,t6020-admac", "apple,t8103-admac", "apple,admac"; reg = <0x3 0x9b400000 0x0 0x34000>; #dma-cells = <1>; dma-channels = <16>; @@ -359,8 +680,29 @@ resets = <&ps_audio_p>; }; + dpaudio0: audio-controller@39b500000 { + compatible = "apple,t6020-dpaudio", "apple,dpaudio"; + reg = <0x3 0x9b500000 0x0 0x4000>; + dmas = <&sio 0x64>; + dma-names = "tx"; + power-domains = <&ps_dpa0>; + reset-domains = <&ps_dpa0>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dpaudio0_dcp: endpoint { + remote-endpoint = <&dcp_audio>; + }; + }; + }; + }; + mca: mca@39b600000 { - compatible = "apple,t6020-mca", "apple,t8103-mca"; + compatible = "apple,t6020-mca", "apple,t8103-mca", "apple,mca"; reg = <0x3 0x9b600000 0x0 0x10000>, <0x3 0x9b500000 0x0 0x20000>; clocks = <&nco 0>, <&nco 1>, <&nco 2>, <&nco 3>; @@ -388,6 +730,14 @@ reg = <0x4 0x6400000 0 0x40000>, <0x4 0x4000000 0 0x1000000>; reg-names = "asc", "sgx"; + interrupt-parent = <&aic>; + interrupts = , + , + , + , + , + , + ; mboxes = <&agx_mbox>; power-domains = <&ps_gfx>; memory-region = <&uat_ttbs>, <&uat_pagetables>, <&uat_handoff>, @@ -396,6 +746,55 @@ "hw-cal-a", "hw-cal-b", "globals"; apple,firmware-abi = <0 0 0>; + apple,firmware-version = <0 0 0>; + apple,firmware-compat = <0 0 0>; + + operating-points-v2 = <&gpu_opp>; + apple,cs-opp = <&gpu_cs_opp>; + apple,afr-opp = <&gpu_afr_opp>; + + apple,min-sram-microvolt = <790000>; + apple,csafr-min-sram-microvolt = <812000>; + apple,perf-base-pstate = <1>; + + apple,avg-power-min-duty-cycle = <40>; + apple,avg-power-target-filter-tc = <1>; + apple,fast-die0-proportional-gain = <34.0>; + apple,perf-boost-ce-step = <50>; + apple,perf-boost-min-util = <90>; + apple,perf-filter-drop-threshold = <0>; + apple,perf-filter-time-constant = <5>; + apple,perf-filter-time-constant2 = <200>; + apple,perf-integral-gain = <1.62>; + apple,perf-integral-gain2 = <1.62>; + apple,perf-integral-min-clamp = <0>; + apple,perf-proportional-gain2 = <5.4>; + apple,perf-proportional-gain = <5.4>; + apple,perf-tgt-utilization = <85>; + apple,power-sample-period = <8>; + apple,ppm-filter-time-constant-ms = <34>; + apple,ppm-ki = <18.0>; + apple,ppm-kp = <0.1>; + apple,pwr-filter-time-constant = <313>; + apple,pwr-integral-gain = <0.0202129>; + apple,pwr-integral-min-clamp = <0>; + apple,pwr-min-duty-cycle = <40>; + apple,pwr-proportional-gain = <5.2831855>; + apple,pwr-sample-period-aic-clks = <200000>; + apple,se-engagement-criteria = <700>; + apple,se-filter-time-constant = <9>; + apple,se-filter-time-constant-1 = <3>; + apple,se-inactive-threshold = <2500>; + apple,se-ki = <-50.0>; + apple,se-ki-1 = <-100.0>; + apple,se-kp = <-5.0>; + apple,se-kp-1 = <-10.0>; + apple,se-reset-criteria = <50>; + + apple,core-leak-coef = GPU_REPEAT(1200.0); + apple,sram-leak-coef = GPU_REPEAT(20.0); + apple,cs-leak-coef = GPU_DIE_REPEAT(400.0); + apple,afr-leak-coef = GPU_DIE_REPEAT(200.0); }; agx_mbox: mbox@406408000 { @@ -455,6 +854,8 @@ pinctrl-0 = <&pcie_pins>; pinctrl-names = "default"; + dma-coherent; + port00: pci@0,0 { device_type = "pci"; reg = <0x0 0x0 0x0 0x0 0x0>; diff --git a/arch/arm64/boot/dts/apple/t602x-dieX.dtsi b/arch/arm64/boot/dts/apple/t602x-dieX.dtsi index cb07fd82b32e67..8d0b6ec133a9ad 100644 --- a/arch/arm64/boot/dts/apple/t602x-dieX.dtsi +++ b/arch/arm64/boot/dts/apple/t602x-dieX.dtsi @@ -23,6 +23,83 @@ #performance-domain-cells = <0>; }; + DIE_NODE(dispext0_dart): iommu@289304000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x2 0x89304000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_dispext0_cpu0)>; + apple,dma-range = <0x100 0x0 0x10 0x0>; + status = "disabled"; + }; + + DIE_NODE(dcpext0_dart): iommu@28930c000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x2 0x8930c000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_dispext0_cpu0)>; + apple,dma-range = <0x100 0x0 0x10 0x0>; + status = "disabled"; + }; + + DIE_NODE(dcpext0_mbox): mbox@289c08000 { + compatible = "apple,t6020-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x89c08000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&DIE_NODE(ps_dispext0_cpu0)>; + resets = <&DIE_NODE(ps_dispext0_cpu0)>; + status = "disabled"; + }; + + DIE_NODE(dcpext0): dcp@289c00000 { + compatible = "apple,t6020-dcpext", "apple,dcpext"; + mboxes = <&DIE_NODE(dcpext0_mbox)>; + mbox-names = "mbox"; + iommus = <&DIE_NODE(dcpext0_dart) 5>; + + reg-names = "coproc", "disp-0", "disp-1", "disp-2", "disp-3"; + reg = <0x2 0x89c00000 0x0 0x4000>, + <0x2 0x88000000 0x0 0x4000000>, + <0x2 0x89320000 0x0 0x4000>, + <0x2 0x89344000 0x0 0x4000>, + <0x2 0x89800000 0x0 0x800000>; + apple,bw-scratch = <&pmgr_dcp 0 4 0x1210>; + power-domains = <&DIE_NODE(ps_dispext0_cpu0)>; + resets = <&DIE_NODE(ps_dispext0_cpu0)>; + clocks = <&DIE_NODE(clk_dispext0)>; + phandle = <&DIE_NODE(dcpext0)>; + apple,dcp-index = <1>; + status = "disabled"; + // required bus properties for 'piodma' subdevice + #address-cells = <2>; + #size-cells = <2>; + + piodma { + iommus = <&DIE_NODE(dispext0_dart) 4>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + DIE_NODE(dcpext0_audio): endpoint { + remote-endpoint = <&DIE_NODE(dpaudio1_dcp)>; + }; + }; + }; + }; + DIE_NODE(pmgr): power-management@28e080000 { compatible = "apple,t6020-pmgr", "apple,t8103-pmgr", "syscon", "simple-mfd"; #address-cells = <1>; @@ -45,7 +122,7 @@ }; DIE_NODE(pinctrl_nub): pinctrl@29e1f0000 { - compatible = "apple,t6020-pinctrl", "apple,t8103-pinctrl"; + compatible = "apple,t6020-pinctrl", "apple,t8103-pinctrl", "apple,pinctrl"; reg = <0x2 0x9e1f0000 0x0 0x4000>; power-domains = <&DIE_NODE(ps_nub_gpio)>; @@ -73,8 +150,15 @@ reg = <0x2 0x9e280000 0 0x4000>; }; + DIE_NODE(efuse): efuse@29e2cc000 { + compatible = "apple,t6020-efuses", "apple,efuses"; + reg = <0x2 0x9e2cc000 0x0 0x2000>; + #address-cells = <1>; + #size-cells = <1>; + }; + DIE_NODE(pinctrl_aop): pinctrl@2a6820000 { - compatible = "apple,t6020-pinctrl", "apple,t8103-pinctrl"; + compatible = "apple,t6020-pinctrl", "apple,t8103-pinctrl", "apple,pinctrl"; reg = <0x2 0xa6820000 0x0 0x4000>; gpio-controller; @@ -94,8 +178,95 @@ ; }; + DIE_NODE(dispext1_dart): iommu@315304000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x3 0x15304000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_dispext1_cpu0)>; + apple,dma-range = <0x100 0x0 0x10 0x0>; + status = "disabled"; + }; + + DIE_NODE(dcpext1_dart): iommu@31530c000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x3 0x1530c000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_dispext1_cpu0)>; + apple,dma-range = <0x100 0x0 0x10 0x0>; + status = "disabled"; + }; + + DIE_NODE(dcpext1_mbox): mbox@315c08000 { + compatible = "apple,t6020-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x3 0x15c08000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&DIE_NODE(ps_dispext1_cpu0)>; + resets = <&DIE_NODE(ps_dispext1_cpu0)>; + status = "disabled"; + }; + + DIE_NODE(dcpext1): dcp@315c00000 { + compatible = "apple,t6020-dcpext", "apple,dcpext"; + mboxes = <&DIE_NODE(dcpext1_mbox)>; + mbox-names = "mbox"; + iommus = <&DIE_NODE(dcpext1_dart) 5>; + + reg-names = "coproc", "disp-0", "disp-1", "disp-2", "disp-3"; + reg = <0x3 0x15c00000 0x0 0x4000>, + <0x3 0x14000000 0x0 0x4000000>, + <0x3 0x15320000 0x0 0x4000>, + <0x3 0x15344000 0x0 0x4000>, + <0x3 0x15800000 0x0 0x800000>; + apple,bw-scratch = <&pmgr_dcp 0 4 0x1218>; + power-domains = <&DIE_NODE(ps_dispext1_cpu0)>; + resets = <&DIE_NODE(ps_dispext1_cpu0)>; + clocks = <&DIE_NODE(clk_dispext1)>; + phandle = <&DIE_NODE(dcpext1)>; + apple,dcp-index = <2>; + status = "disabled"; + // required bus properties for 'piodma' subdevice + #address-cells = <2>; + #size-cells = <2>; + + piodma { + iommus = <&DIE_NODE(dispext1_dart) 4>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + DIE_NODE(dcpext1_audio): endpoint { + remote-endpoint = <&DIE_NODE(dpaudio2_dcp)>; + }; + }; + }; + }; + + DIE_NODE(sio_dart): iommu@39b008000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x3 0x9b008000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + #iommu-cells = <1>; + power-domains = <&DIE_NODE(ps_sio)>; + //apple,dma-range = <0x100 0x0001c000 0x2ff 0xfffe4000>; + }; + DIE_NODE(pinctrl_ap): pinctrl@39b028000 { - compatible = "apple,t6020-pinctrl", "apple,t8103-pinctrl"; + compatible = "apple,t6020-pinctrl", "apple,t8103-pinctrl", "apple,pinctrl"; reg = <0x3 0x9b028000 0x0 0x4000>; interrupt-parent = <&aic>; @@ -119,6 +290,131 @@ #interrupt-cells = <2>; }; + DIE_NODE(sio_mbox): mbox@39bc08000 { + compatible = "apple,t6020-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x3 0x9bc08000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&DIE_NODE(ps_sio_cpu)>; + }; + + DIE_NODE(sio): sio@39bc00000 { + compatible = "apple,t6020-sio", "apple,sio"; + reg = <0x3 0x9bc00000 0x0 0x8000>; + dma-channels = <128>; + #dma-cells = <1>; + mboxes = <&DIE_NODE(sio_mbox)>; + iommus = <&DIE_NODE(sio_dart) 0>; + power-domains = <&DIE_NODE(ps_sio_cpu)>; + resets = <&DIE_NODE(ps_sio_cpu)>; + status = "disabled"; + }; + + DIE_NODE(dpaudio1): audio-controller@39b504000 { + compatible = "apple,t6020-dpaudio", "apple,dpaudio"; + reg = <0x3 0x9b540000 0x0 0x4000>; + dmas = <&DIE_NODE(sio) 0x66>; + dma-names = "tx"; + power-domains = <&DIE_NODE(ps_dpa1)>; + reset-domains = <&DIE_NODE(ps_dpa1)>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + DIE_NODE(dpaudio1_dcp): endpoint { + remote-endpoint = <&DIE_NODE(dcpext0_audio)>; + }; + }; + }; + }; + + DIE_NODE(dpaudio2): audio-controller@39b508000 { + compatible = "apple,t6020-dpaudio", "apple,dpaudio"; + reg = <0x3 0x9b580000 0x0 0x4000>; + dmas = <&DIE_NODE(sio) 0x68>; + dma-names = "tx"; + power-domains = <&DIE_NODE(ps_dpa2)>; + reset-domains = <&DIE_NODE(ps_dpa2)>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + DIE_NODE(dpaudio2_dcp): endpoint { + remote-endpoint = <&DIE_NODE(dcpext1_audio)>; + }; + }; + }; + }; + + /* + * omit dpaudio3 / 4 as long as the linked dcpext nodes don't exist + * + DIE_NODE(dpaudio3): audio-controller@39b50c000 { + compatible = "apple,t6020-dpaudio", "apple,dpaudio"; + reg = <0x3 0x9b5c0000 0x0 0x4000>; + dmas = <&DIE_NODE(sio) 0x6a>; + dma-names = "tx"; + power-domains = <&DIE_NODE(ps_dpa3)>; + reset-domains = <&DIE_NODE(ps_dpa3)>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + DIE_NODE(dpaudio3_dcp): endpoint { + remote-endpoint = <&DIE_NODE(dcpext2_audio)>; + }; + }; + }; + }; + + DIE_NODE(dpaudio4): audio-controller@39b510000 { + compatible = "apple,t6020-dpaudio", "apple,dpaudio"; + reg = <0x3 0x9b500000 0x0 0x4000>; + dmas = <&DIE_NODE(sio) 0x6c>; + dma-names = "tx"; + power-domains = <&DIE_NODE(ps_dpa4)>; + reset-domains = <&DIE_NODE(ps_dpa4)>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + DIE_NODE(dpaudio4_dcp): endpoint { + remote-endpoint = <&DIE_NODE(dcpext3_audio)>; + }; + }; + }; + }; + */ + + DIE_NODE(lpdptxphy): phy@39c000000 { + compatible = "apple,t6020-dptx-phy", "apple,dptx-phy"; + reg = <0x3 0x9c000000 0x0 0x4000>, + <0x3 0x9c040000 0x0 0xc000>; + reg-names = "core", "dptx"; + power-domains = <&DIE_NODE(ps_dptx_phy_ps)>; + #phy-cells = <0>; + #reset-cells = <0>; + status = "disabled"; /* only exposed on desktop devices */ + }; + DIE_NODE(pmgr_gfx): power-management@404e80000 { compatible = "apple,t6020-pmgr", "apple,t8103-pmgr", "syscon", "simple-mfd"; #address-cells = <1>; @@ -126,3 +422,247 @@ reg = <0x4 0x4e80000 0 0x4000>; }; + + DIE_NODE(dwc3_0): usb@702280000 { + compatible = "apple,t6020-dwc3", "apple,t8103-dwc3"; + reg = <0x7 0x02280000 0x0 0xcd00>, <0x7 0x0228cd00 0x0 0x3200>; + reg-names = "dwc3-core", "dwc3-apple"; + interrupt-parent = <&aic>; + interrupts = ; + dr_mode = "otg"; + usb-role-switch; + role-switch-default-mode = "host"; + iommus = <&DIE_NODE(dwc3_0_dart_0) 0>, + <&DIE_NODE(dwc3_0_dart_1) 1>; + power-domains = <&DIE_NODE(ps_atc0_usb)>; + resets = <&DIE_NODE(atcphy0)>; + phys = <&DIE_NODE(atcphy0) PHY_TYPE_USB2>, <&DIE_NODE(atcphy0) PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + }; + + DIE_NODE(dwc3_0_dart_0): iommu@702f00000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x7 0x02f00000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc0_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(dwc3_0_dart_1): iommu@702f80000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x7 0x02f80000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc0_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(atcphy0): phy@703000000 { + compatible = "apple,t6020-atcphy", "apple,t8103-atcphy"; + reg = <0x7 0x03000000 0x0 0x4c000>, + <0x7 0x03050000 0x0 0x8000>, + <0x7 0x00000000 0x0 0x4000>, + <0x7 0x02a90000 0x0 0x4000>, + <0x7 0x02a84000 0x0 0x4000>; + reg-names = "core", "lpdptx", "axi2af", "usb2phy", + "pipehandler"; + + #phy-cells = <1>; + #reset-cells = <0>; + + orientation-switch; + mode-switch; + power-domains = <&DIE_NODE(ps_atc0_usb)>; + }; + + DIE_NODE(atcphy0_xbar): mux@70304c000 { + compatible = "apple,t6020-display-crossbar"; + reg = <0x7 0x0304c000 0x0 0x4000>; + #mux-control-cells = <1>; + power-domains = <&DIE_NODE(ps_atc0_usb)>; + status = "disabled"; + }; + + DIE_NODE(dwc3_1): usb@b02280000 { + compatible = "apple,t6020-dwc3", "apple,t8103-dwc3"; + reg = <0xb 0x02280000 0x0 0xcd00>, <0xb 0x0228cd00 0x0 0x3200>; + reg-names = "dwc3-core", "dwc3-apple"; + interrupt-parent = <&aic>; + interrupts = ; + dr_mode = "otg"; + usb-role-switch; + role-switch-default-mode = "host"; + iommus = <&DIE_NODE(dwc3_1_dart_0) 0>, + <&DIE_NODE(dwc3_1_dart_1) 1>; + power-domains = <&DIE_NODE(ps_atc1_usb)>; + resets = <&DIE_NODE(atcphy1)>; + phys = <&DIE_NODE(atcphy1) PHY_TYPE_USB2>, <&DIE_NODE(atcphy1) PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + }; + + DIE_NODE(dwc3_1_dart_0): iommu@b02f00000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0xb 0x02f00000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc1_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(dwc3_1_dart_1): iommu@b02f80000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0xb 0x02f80000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc1_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(atcphy1): phy@b03000000 { + compatible = "apple,t6020-atcphy", "apple,t8103-atcphy"; + reg = <0xb 0x03000000 0x0 0x4c000>, + <0xb 0x03050000 0x0 0x8000>, + <0xb 0x00000000 0x0 0x4000>, + <0xb 0x02a90000 0x0 0x4000>, + <0xb 0x02a84000 0x0 0x4000>; + reg-names = "core", "lpdptx", "axi2af", "usb2phy", + "pipehandler"; + + #phy-cells = <1>; + #reset-cells = <0>; + + orientation-switch; + mode-switch; + power-domains = <&DIE_NODE(ps_atc1_usb)>; + }; + + DIE_NODE(atcphy1_xbar): mux@b0304c000 { + compatible = "apple,t6020-display-crossbar"; + reg = <0xb 0x0304c000 0x0 0x4000>; + #mux-control-cells = <1>; + power-domains = <&DIE_NODE(ps_atc1_usb)>; + status = "disabled"; + }; + + DIE_NODE(dwc3_2): usb@f02280000 { + compatible = "apple,t6020-dwc3", "apple,t8103-dwc3"; + reg = <0xf 0x02280000 0x0 0xcd00>, <0xf 0x0228cd00 0x0 0x3200>; + reg-names = "dwc3-core", "dwc3-apple"; + interrupt-parent = <&aic>; + interrupts = ; + dr_mode = "otg"; + usb-role-switch; + role-switch-default-mode = "host"; + iommus = <&DIE_NODE(dwc3_2_dart_0) 0>, + <&DIE_NODE(dwc3_2_dart_1) 1>; + power-domains = <&DIE_NODE(ps_atc2_usb)>; + resets = <&DIE_NODE(atcphy2)>; + phys = <&DIE_NODE(atcphy2) PHY_TYPE_USB2>, <&DIE_NODE(atcphy2) PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + }; + + DIE_NODE(dwc3_2_dart_0): iommu@f02f00000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0xf 0x02f00000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc2_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(dwc3_2_dart_1): iommu@f02f80000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0xf 0x02f80000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc2_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(atcphy2): phy@f03000000 { + compatible = "apple,t6020-atcphy", "apple,t8103-atcphy"; + reg = <0xf 0x03000000 0x0 0x4c000>, + <0xf 0x03050000 0x0 0x8000>, + <0xf 0x00000000 0x0 0x4000>, + <0xf 0x02a90000 0x0 0x4000>, + <0xf 0x02a84000 0x0 0x4000>; + reg-names = "core", "lpdptx", "axi2af", "usb2phy", + "pipehandler"; + + #phy-cells = <1>; + #reset-cells = <0>; + + orientation-switch; + mode-switch; + power-domains = <&DIE_NODE(ps_atc2_usb)>; + }; + + DIE_NODE(atcphy2_xbar): mux@f0304c000 { + compatible = "apple,t6020-display-crossbar"; + reg = <0xf 0x0304c000 0x0 0x4000>; + #mux-control-cells = <1>; + power-domains = <&DIE_NODE(ps_atc2_usb)>; + status = "disabled"; + }; + + DIE_NODE(dwc3_3): usb@1302280000 { + compatible = "apple,t6020-dwc3", "apple,t8103-dwc3"; + reg = <0x13 0x02280000 0x0 0xcd00>, <0x13 0x0228cd00 0x0 0x3200>; + reg-names = "dwc3-core", "dwc3-apple"; + interrupt-parent = <&aic>; + interrupts = ; + dr_mode = "otg"; + usb-role-switch; + role-switch-default-mode = "host"; + iommus = <&DIE_NODE(dwc3_3_dart_0) 0>, + <&DIE_NODE(dwc3_3_dart_1) 1>; + power-domains = <&DIE_NODE(ps_atc3_usb)>; + resets = <&DIE_NODE(atcphy3)>; + phys = <&DIE_NODE(atcphy3) PHY_TYPE_USB2>, <&DIE_NODE(atcphy3) PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + }; + + DIE_NODE(dwc3_3_dart_0): iommu@1302f00000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x13 0x02f00000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc3_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(dwc3_3_dart_1): iommu@1302f80000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x13 0x02f80000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_atc3_usb)>; + #iommu-cells = <1>; + }; + + DIE_NODE(atcphy3): phy@1303000000 { + compatible = "apple,t6020-atcphy", "apple,t8103-atcphy"; + reg = <0x13 0x03000000 0x0 0x4c000>, + <0x13 0x03050000 0x0 0x8000>, + <0x13 0x00000000 0x0 0x4000>, + <0x13 0x02a90000 0x0 0x4000>, + <0x13 0x02a84000 0x0 0x4000>; + reg-names = "core", "lpdptx", "axi2af", "usb2phy", + "pipehandler"; + + #phy-cells = <1>; + #reset-cells = <0>; + + orientation-switch; + mode-switch; + power-domains = <&DIE_NODE(ps_atc3_usb)>; + }; + + DIE_NODE(atcphy3_xbar): mux@130304c000 { + compatible = "apple,t6020-display-crossbar"; + reg = <0x13 0x0304c000 0x0 0x4000>; + #mux-control-cells = <1>; + power-domains = <&DIE_NODE(ps_atc3_usb)>; + status = "disabled"; + }; diff --git a/arch/arm64/boot/dts/apple/t602x-gpio-pins.dtsi b/arch/arm64/boot/dts/apple/t602x-gpio-pins.dtsi index e41b6475f79218..c5de99bd2e5cf3 100644 --- a/arch/arm64/boot/dts/apple/t602x-gpio-pins.dtsi +++ b/arch/arm64/boot/dts/apple/t602x-gpio-pins.dtsi @@ -78,4 +78,8 @@ , ; }; + + pcie_ge_pins: pcie-ge-pins { + pinmux = ; + }; }; diff --git a/arch/arm64/boot/dts/apple/t602x-j414-j416.dtsi b/arch/arm64/boot/dts/apple/t602x-j414-j416.dtsi index 0e806d8ddf81b1..0057e6a9465f9d 100644 --- a/arch/arm64/boot/dts/apple/t602x-j414-j416.dtsi +++ b/arch/arm64/boot/dts/apple/t602x-j414-j416.dtsi @@ -14,12 +14,31 @@ * the GPIO indices. */ +#define NO_SPI_TRACKPAD #include "t600x-j314-j316.dtsi" +/ { + aliases { + keyboard = &keyboard; + }; +}; + &framebuffer0 { power-domains = <&ps_disp0_cpu0>, <&ps_dptx_phy_ps>; }; +/* HACK: keep dptx_phy_ps power-domain always-on + * it is unclear how to sequence with dcp for the integrated display + */ +&ps_dptx_phy_ps { + apple,always-on; +}; + +&dcpext0 { + /* HDMI HPD gpio, used as interrupt*/ + hdmi-hpd-gpios = <&pinctrl_aop 25 GPIO_ACTIVE_HIGH>; +}; + &hpm0 { interrupts = <44 IRQ_TYPE_LEVEL_LOW>; }; @@ -36,6 +55,40 @@ interrupts = <44 IRQ_TYPE_LEVEL_LOW>; }; +/* Redefine GPIO for SDZ */ +&speaker_sdz { + gpios = <&pinctrl_ap 57 GPIO_ACTIVE_HIGH>; +}; + +&speaker_left_tweet { + interrupts-extended = <&pinctrl_ap 58 IRQ_TYPE_LEVEL_LOW>; +}; + +&speaker_left_woof1 { + interrupts-extended = <&pinctrl_ap 58 IRQ_TYPE_LEVEL_LOW>; +}; + +&speaker_left_woof2 { + interrupts-extended = <&pinctrl_ap 58 IRQ_TYPE_LEVEL_LOW>; +}; + +&speaker_right_tweet { + interrupts-extended = <&pinctrl_ap 58 IRQ_TYPE_LEVEL_LOW>; +}; + +&speaker_right_woof1 { + interrupts-extended = <&pinctrl_ap 58 IRQ_TYPE_LEVEL_LOW>; +}; + +&speaker_right_woof2 { + interrupts-extended = <&pinctrl_ap 58 IRQ_TYPE_LEVEL_LOW>; +}; + +&jack_codec { + reset-gpios = <&pinctrl_nub 8 GPIO_ACTIVE_HIGH>; + interrupts-extended = <&pinctrl_ap 59 IRQ_TYPE_LEVEL_LOW>; +}; + &wifi0 { compatible = "pci14e4,4434"; }; @@ -43,3 +96,56 @@ &bluetooth0 { compatible = "pci14e4,5f72"; }; + +&port01 { + pwren-gpios = <&smc_gpio 22 GPIO_ACTIVE_HIGH>; +}; + +&ps_mtp_fabric { + status = "okay"; +}; + +&mtp { + status = "okay"; +}; + +&mtp_mbox { + status = "okay"; +}; + +&mtp_dart { + status = "okay"; +}; + +&mtp_dockchannel { + status = "okay"; +}; + +&mtp_hid { + apple,afe-reset-gpios = <&smc_gpio 25 GPIO_ACTIVE_LOW>; + apple,stm-reset-gpios = <&smc_gpio 26 GPIO_ACTIVE_LOW>; + + mtp_mt: multi-touch { + }; + + keyboard: keyboard { + hid-country-code = <0>; + apple,keyboard-layout-id = <0>; + }; + + stm { + }; + + actuator { + }; + + tp_accel { + }; +}; + +&isp { + apple,platform-id = <7>; + /delete-node/ sensor-presets; /* Override j31[46] below */ +}; + +#include "isp-imx558-cfg0.dtsi" diff --git a/arch/arm64/boot/dts/apple/t602x-j474-j475.dtsi b/arch/arm64/boot/dts/apple/t602x-j474-j475.dtsi index ee12fea5b12cb3..287348628eb177 100644 --- a/arch/arm64/boot/dts/apple/t602x-j474-j475.dtsi +++ b/arch/arm64/boot/dts/apple/t602x-j474-j475.dtsi @@ -36,3 +36,23 @@ &hpm3 { interrupts = <44 IRQ_TYPE_LEVEL_LOW>; }; + +/* PCIe devices */ +&port00 { + pwren-gpios = <&smc_gpio 13 GPIO_ACTIVE_HIGH>; +}; + +&port03 { + /* USB xHCI */ + pwren-gpios = <&smc_gpio 19 GPIO_ACTIVE_HIGH>; +}; + +&speaker { + shutdown-gpios = <&pinctrl_ap 57 GPIO_ACTIVE_HIGH>; + interrupts-extended = <&pinctrl_ap 58 IRQ_TYPE_LEVEL_LOW>; +}; + +&jack_codec { + reset-gpios = <&pinctrl_nub 8 GPIO_ACTIVE_HIGH>; + interrupts-extended = <&pinctrl_ap 59 IRQ_TYPE_LEVEL_LOW>; +}; diff --git a/arch/arm64/boot/dts/apple/t602x-nvme.dtsi b/arch/arm64/boot/dts/apple/t602x-nvme.dtsi index 590cec8ac804c0..eb8c4e359079e5 100644 --- a/arch/arm64/boot/dts/apple/t602x-nvme.dtsi +++ b/arch/arm64/boot/dts/apple/t602x-nvme.dtsi @@ -26,7 +26,7 @@ }; DIE_NODE(nvme): nvme@34bcc0000 { - compatible = "apple,t6020-nvme-ans2", "apple,t8103-nvme-ans2"; + compatible = "apple,t6020-nvme-ans2", "apple,t8103-nvme-ans2", "apple,nvme-ans2"; reg = <0x3 0x4bcc0000 0x0 0x40000>, <0x3 0x47400000 0x0 0x4000>; reg-names = "nvme", "ans"; interrupt-parent = <&aic>; diff --git a/arch/arm64/boot/dts/apple/t602x-pcie-ge.dtsi b/arch/arm64/boot/dts/apple/t602x-pcie-ge.dtsi new file mode 100644 index 00000000000000..4a509cae0e5766 --- /dev/null +++ b/arch/arm64/boot/dts/apple/t602x-pcie-ge.dtsi @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * PCIe-GE Nodes present on both dies of a T6022 (M2 Ultra) and M2 Pro/Max but + * only used on T6022 in the Mac Pro (2023). + * + * Copyright The Asahi Linux Contributors + */ + + DIE_NODE(pcie_ge): pcie@1680000000 { + compatible = "apple,t6020-pcie-ge", "apple,t6020-pcie"; + device_type = "pci"; + + reg = <0x16 0x80000000 0x0 0x1000000>, /* config */ + <0x16 0x91000000 0x0 0x4000>, /* rc */ + <0x16 0x94008000 0x0 0x4000>, /* port0 */ + <0x16 0x9e01c000 0x0 0x4000>, /* phy0 */ + <0x16 0x9401c000 0x0 0x1000>; /* ltssm0 */ + reg-names = "config", "rc", "port0", "phy0", "ltssm0"; + + interrupt-parent = <&aic>; + interrupts = ; + + msi-controller; + msi-parent = <&DIE_NODE(pcie_ge)>; + msi-ranges = <&aic AIC_IRQ DIE_NO 1672 IRQ_TYPE_EDGE_RISING 128>; + + iommu-map = <0x000 &DIE_NODE(pcie_ge_dart) 0 0>, + <0x100 &DIE_NODE(pcie_ge_dart) 1 1>, + <0x200 &DIE_NODE(pcie_ge_dart) 2 2>, + <0x300 &DIE_NODE(pcie_ge_dart) 3 3>, + <0x400 &DIE_NODE(pcie_ge_dart) 4 4>, + <0x500 &DIE_NODE(pcie_ge_dart) 5 5>, + <0x600 &DIE_NODE(pcie_ge_dart) 6 6>, + <0x700 &DIE_NODE(pcie_ge_dart) 7 7>, + <0x800 &DIE_NODE(pcie_ge_dart) 8 8>, + <0x900 &DIE_NODE(pcie_ge_dart) 9 9>, + <0xa00 &DIE_NODE(pcie_ge_dart) 10 10>, + <0xb00 &DIE_NODE(pcie_ge_dart) 11 11>, + <0xc00 &DIE_NODE(pcie_ge_dart) 12 12>, + <0xd00 &DIE_NODE(pcie_ge_dart) 13 13>, + <0xe00 &DIE_NODE(pcie_ge_dart) 14 14>, + <0xf00 &DIE_NODE(pcie_ge_dart) 15 15>; + iommu-map-mask = <0xff00>; + + bus-range = <0 15>; + #address-cells = <3>; + #size-cells = <2>; + ranges = <0x43000000 0x18 0x00000000 0x18 0x00000000 0x4 0x00000000>, + <0x02000000 0x00 0x80000000 0x17 0x80000000 0x0 0x80000000>; + + power-domains = <&DIE_NODE(ps_apcie_ge_sys)>; + pinctrl-0 = <&DIE_NODE(pcie_ge_pins)>; + pinctrl-names = "default"; + + dma-coherent; + + status = "disabled"; + + DIE_NODE(port_ge00): pci@0,0 { + device_type = "pci"; + reg = <0x0 0x0 0x0 0x0 0x0>; + reset-gpios = <&DIE_NODE(pinctrl_ap) 9 GPIO_ACTIVE_LOW>; + + #address-cells = <3>; + #size-cells = <2>; + ranges; + + interrupt-controller; + #interrupt-cells = <1>; + + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &DIE_NODE(port_ge00) 0 0 0 0>, + <0 0 0 2 &DIE_NODE(port_ge00) 0 0 0 1>, + <0 0 0 3 &DIE_NODE(port_ge00) 0 0 0 2>, + <0 0 0 4 &DIE_NODE(port_ge00) 0 0 0 3>; + }; + }; + + DIE_NODE(pcie_ge_dart): iommu@1694000000 { + compatible = "apple,t6020-dart", "apple,t8110-dart"; + reg = <0x16 0x94000000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&DIE_NODE(ps_apcie_ge_sys)>; + status = "disabled"; + }; diff --git a/arch/arm64/boot/dts/apple/t602x-pmgr.dtsi b/arch/arm64/boot/dts/apple/t602x-pmgr.dtsi index f5382a2faf0b25..b9233f252e6ca7 100644 --- a/arch/arm64/boot/dts/apple/t602x-pmgr.dtsi +++ b/arch/arm64/boot/dts/apple/t602x-pmgr.dtsi @@ -7,7 +7,7 @@ &DIE_NODE(pmgr) { DIE_NODE(ps_afi): power-controller@100 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x100 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -16,7 +16,7 @@ }; DIE_NODE(ps_aic): power-controller@108 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x108 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -25,7 +25,7 @@ }; DIE_NODE(ps_dwi): power-controller@110 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x110 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -33,7 +33,7 @@ }; DIE_NODE(ps_pms): power-controller@118 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x118 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -42,7 +42,7 @@ }; DIE_NODE(ps_gpio): power-controller@120 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x120 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -51,7 +51,7 @@ }; DIE_NODE(ps_soc_dpe): power-controller@128 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x128 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -60,7 +60,7 @@ }; DIE_NODE(ps_pms_c1ppt): power-controller@130 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x130 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -69,7 +69,7 @@ }; DIE_NODE(ps_pmgr_soc_ocla): power-controller@138 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x138 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -78,7 +78,7 @@ }; DIE_NODE(ps_amcc0): power-controller@168 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x168 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -87,7 +87,7 @@ }; DIE_NODE(ps_amcc2): power-controller@170 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x170 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -96,7 +96,7 @@ }; DIE_NODE(ps_dcs_00): power-controller@178 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x178 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -105,7 +105,7 @@ }; DIE_NODE(ps_dcs_01): power-controller@180 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x180 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -114,7 +114,7 @@ }; DIE_NODE(ps_dcs_02): power-controller@188 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x188 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -123,7 +123,7 @@ }; DIE_NODE(ps_dcs_03): power-controller@190 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x190 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -132,7 +132,7 @@ }; DIE_NODE(ps_dcs_08): power-controller@198 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x198 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -141,7 +141,7 @@ }; DIE_NODE(ps_dcs_09): power-controller@1a0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1a0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -150,7 +150,7 @@ }; DIE_NODE(ps_dcs_10): power-controller@1a8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1a8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -159,7 +159,7 @@ }; DIE_NODE(ps_dcs_11): power-controller@1b0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1b0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -168,7 +168,7 @@ }; DIE_NODE(ps_afnc1_ioa): power-controller@1b8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1b8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -178,7 +178,7 @@ }; DIE_NODE(ps_afc): power-controller@1d0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1d0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -187,7 +187,7 @@ }; DIE_NODE(ps_afnc0_ioa): power-controller@1e8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1e8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -197,7 +197,7 @@ }; DIE_NODE(ps_afnc1_ls): power-controller@1f0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1f0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -207,7 +207,7 @@ }; DIE_NODE(ps_afnc0_ls): power-controller@1f8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1f8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -217,7 +217,7 @@ }; DIE_NODE(ps_afnc1_lw0): power-controller@200 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x200 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -227,7 +227,7 @@ }; DIE_NODE(ps_afnc1_lw1): power-controller@208 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x208 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -237,7 +237,7 @@ }; DIE_NODE(ps_afnc1_lw2): power-controller@210 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x210 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -247,7 +247,7 @@ }; DIE_NODE(ps_afnc0_lw0): power-controller@218 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x218 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -257,7 +257,7 @@ }; DIE_NODE(ps_scodec): power-controller@220 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x220 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -266,7 +266,7 @@ }; DIE_NODE(ps_atc0_common): power-controller@228 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x228 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -275,7 +275,7 @@ }; DIE_NODE(ps_atc1_common): power-controller@230 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x230 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -284,7 +284,7 @@ }; DIE_NODE(ps_atc2_common): power-controller@238 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x238 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -293,7 +293,7 @@ }; DIE_NODE(ps_atc3_common): power-controller@240 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x240 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -302,7 +302,7 @@ }; DIE_NODE(ps_dispext1_sys): power-controller@248 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x248 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -311,7 +311,7 @@ }; DIE_NODE(ps_pms_bridge): power-controller@250 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x250 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -321,7 +321,7 @@ }; DIE_NODE(ps_dispext0_sys): power-controller@258 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x258 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -330,7 +330,7 @@ }; DIE_NODE(ps_ane_sys): power-controller@260 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x260 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -339,7 +339,7 @@ }; DIE_NODE(ps_avd_sys): power-controller@268 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x268 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -348,7 +348,7 @@ }; DIE_NODE(ps_atc0_cio): power-controller@270 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x270 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -357,7 +357,7 @@ }; DIE_NODE(ps_atc0_pcie): power-controller@278 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x278 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -366,7 +366,7 @@ }; DIE_NODE(ps_atc1_cio): power-controller@280 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x280 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -375,7 +375,7 @@ }; DIE_NODE(ps_atc1_pcie): power-controller@288 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x288 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -384,7 +384,7 @@ }; DIE_NODE(ps_atc2_cio): power-controller@290 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x290 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -393,7 +393,7 @@ }; DIE_NODE(ps_atc2_pcie): power-controller@298 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x298 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -402,7 +402,7 @@ }; DIE_NODE(ps_atc3_cio): power-controller@2a0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2a0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -411,7 +411,7 @@ }; DIE_NODE(ps_atc3_pcie): power-controller@2a8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2a8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -420,7 +420,7 @@ }; DIE_NODE(ps_dispext1_fe): power-controller@2b0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2b0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -429,7 +429,7 @@ }; DIE_NODE(ps_dispext1_cpu0): power-controller@2b8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2b8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -439,7 +439,7 @@ }; DIE_NODE(ps_dispext0_fe): power-controller@2c0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2c0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -447,8 +447,9 @@ power-domains = <&DIE_NODE(ps_dispext0_sys)>; }; + /* PMP is only present on die 0 of the M2 Ultra */ DIE_NODE(ps_pmp): power-controller@2c8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2c8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -456,7 +457,7 @@ }; DIE_NODE(ps_pms_sram): power-controller@2d0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2d0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -464,7 +465,7 @@ }; DIE_NODE(ps_dispext0_cpu0): power-controller@2d8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2d8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -474,7 +475,7 @@ }; DIE_NODE(ps_ane_cpu): power-controller@2e0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2e0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -483,7 +484,7 @@ }; DIE_NODE(ps_atc0_cio_pcie): power-controller@2e8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2e8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -492,7 +493,7 @@ }; DIE_NODE(ps_atc0_cio_usb): power-controller@2f0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2f0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -501,7 +502,7 @@ }; DIE_NODE(ps_atc1_cio_pcie): power-controller@2f8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2f8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -510,7 +511,7 @@ }; DIE_NODE(ps_atc1_cio_usb): power-controller@300 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x300 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -519,7 +520,7 @@ }; DIE_NODE(ps_atc2_cio_pcie): power-controller@308 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x308 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -528,7 +529,7 @@ }; DIE_NODE(ps_atc2_cio_usb): power-controller@310 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x310 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -537,7 +538,7 @@ }; DIE_NODE(ps_atc3_cio_pcie): power-controller@318 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x318 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -546,7 +547,7 @@ }; DIE_NODE(ps_atc3_cio_usb): power-controller@320 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x320 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -555,7 +556,7 @@ }; DIE_NODE(ps_trace_fab): power-controller@390 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x390 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -563,7 +564,7 @@ }; DIE_NODE(ps_ane_sys_mpm): power-controller@4000 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4000 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -572,7 +573,7 @@ }; DIE_NODE(ps_ane_td): power-controller@4008 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4008 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -581,7 +582,7 @@ }; DIE_NODE(ps_ane_base): power-controller@4010 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4010 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -590,7 +591,7 @@ }; DIE_NODE(ps_ane_set1): power-controller@4018 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4018 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -599,7 +600,7 @@ }; DIE_NODE(ps_ane_set2): power-controller@4020 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4020 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -608,7 +609,7 @@ }; DIE_NODE(ps_ane_set3): power-controller@4028 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4028 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -617,7 +618,7 @@ }; DIE_NODE(ps_ane_set4): power-controller@4030 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4030 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -628,7 +629,7 @@ &DIE_NODE(pmgr_south) { DIE_NODE(ps_amcc4): power-controller@100 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x100 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -637,7 +638,7 @@ }; DIE_NODE(ps_amcc5): power-controller@108 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x108 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -646,7 +647,7 @@ }; DIE_NODE(ps_amcc6): power-controller@110 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x110 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -655,7 +656,7 @@ }; DIE_NODE(ps_amcc7): power-controller@118 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x118 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -664,7 +665,7 @@ }; DIE_NODE(ps_dcs_16): power-controller@120 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x120 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -673,7 +674,7 @@ }; DIE_NODE(ps_dcs_17): power-controller@128 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x128 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -682,7 +683,7 @@ }; DIE_NODE(ps_dcs_18): power-controller@130 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x130 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -691,7 +692,7 @@ }; DIE_NODE(ps_dcs_19): power-controller@138 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x138 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -700,7 +701,7 @@ }; DIE_NODE(ps_dcs_20): power-controller@140 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x140 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -709,7 +710,7 @@ }; DIE_NODE(ps_dcs_21): power-controller@148 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x148 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -718,7 +719,7 @@ }; DIE_NODE(ps_dcs_22): power-controller@150 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x150 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -727,7 +728,7 @@ }; DIE_NODE(ps_dcs_23): power-controller@158 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x158 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -736,7 +737,7 @@ }; DIE_NODE(ps_dcs_24): power-controller@160 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x160 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -745,7 +746,7 @@ }; DIE_NODE(ps_dcs_25): power-controller@168 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x168 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -754,7 +755,7 @@ }; DIE_NODE(ps_dcs_26): power-controller@170 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x170 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -763,7 +764,7 @@ }; DIE_NODE(ps_dcs_27): power-controller@178 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x178 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -772,7 +773,7 @@ }; DIE_NODE(ps_dcs_28): power-controller@180 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x180 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -781,7 +782,7 @@ }; DIE_NODE(ps_dcs_29): power-controller@188 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x188 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -790,7 +791,7 @@ }; DIE_NODE(ps_dcs_30): power-controller@190 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x190 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -799,7 +800,7 @@ }; DIE_NODE(ps_dcs_31): power-controller@198 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x198 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -808,7 +809,7 @@ }; DIE_NODE(ps_afnc4_ioa): power-controller@1a0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1a0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -818,7 +819,7 @@ }; DIE_NODE(ps_afnc4_ls): power-controller@1a8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1a8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -828,7 +829,7 @@ }; DIE_NODE(ps_afnc4_lw0): power-controller@1b0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1b0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -838,7 +839,7 @@ }; DIE_NODE(ps_afnc5_ioa): power-controller@1b8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1b8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -848,7 +849,7 @@ }; DIE_NODE(ps_afnc5_ls): power-controller@1c0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1c0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -858,7 +859,7 @@ }; DIE_NODE(ps_afnc5_lw0): power-controller@1c8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1c8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -868,7 +869,7 @@ }; DIE_NODE(ps_dispext2_sys): power-controller@1d0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1d0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -876,7 +877,7 @@ }; DIE_NODE(ps_msr1): power-controller@1d8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1d8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -884,7 +885,7 @@ }; DIE_NODE(ps_dispext2_fe): power-controller@1e0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1e0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -893,7 +894,7 @@ }; DIE_NODE(ps_dispext2_cpu0): power-controller@1e8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1e8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -903,7 +904,7 @@ }; DIE_NODE(ps_msr1_ase_core): power-controller@1f0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1f0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -912,7 +913,7 @@ }; DIE_NODE(ps_dispext3_sys): power-controller@220 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x220 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -920,7 +921,7 @@ }; DIE_NODE(ps_venc1_sys): power-controller@228 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x228 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -928,7 +929,7 @@ }; DIE_NODE(ps_dispext3_fe): power-controller@230 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x230 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -937,7 +938,7 @@ }; DIE_NODE(ps_dispext3_cpu0): power-controller@238 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x238 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -947,7 +948,7 @@ }; DIE_NODE(ps_venc1_dma): power-controller@4000 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4000 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -956,7 +957,7 @@ }; DIE_NODE(ps_venc1_pipe4): power-controller@4008 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4008 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -965,7 +966,7 @@ }; DIE_NODE(ps_venc1_pipe5): power-controller@4010 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4010 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -974,7 +975,7 @@ }; DIE_NODE(ps_venc1_me0): power-controller@4018 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4018 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -983,7 +984,7 @@ }; DIE_NODE(ps_venc1_me1): power-controller@4020 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4020 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -994,7 +995,7 @@ &DIE_NODE(pmgr_east) { DIE_NODE(ps_clvr_spmi0): power-controller@100 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x100 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1003,7 +1004,7 @@ }; DIE_NODE(ps_clvr_spmi1): power-controller@108 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x108 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1012,7 +1013,7 @@ }; DIE_NODE(ps_clvr_spmi2): power-controller@110 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x110 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1021,7 +1022,7 @@ }; DIE_NODE(ps_clvr_spmi3): power-controller@118 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x118 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1030,7 +1031,7 @@ }; DIE_NODE(ps_clvr_spmi4): power-controller@120 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x120 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1039,7 +1040,7 @@ }; DIE_NODE(ps_ispsens0): power-controller@128 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x128 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1047,7 +1048,7 @@ }; DIE_NODE(ps_ispsens1): power-controller@130 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x130 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1055,7 +1056,7 @@ }; DIE_NODE(ps_ispsens2): power-controller@138 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x138 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1063,7 +1064,7 @@ }; DIE_NODE(ps_ispsens3): power-controller@140 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x140 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1071,7 +1072,7 @@ }; DIE_NODE(ps_afnc6_ioa): power-controller@148 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x148 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1081,7 +1082,7 @@ }; DIE_NODE(ps_afnc6_ls): power-controller@150 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x150 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1091,7 +1092,7 @@ }; DIE_NODE(ps_afnc6_lw0): power-controller@158 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x158 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1101,7 +1102,7 @@ }; DIE_NODE(ps_afnc2_ioa): power-controller@160 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x160 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1111,7 +1112,7 @@ }; DIE_NODE(ps_afnc2_ls): power-controller@168 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x168 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1121,7 +1122,7 @@ }; DIE_NODE(ps_afnc2_lw0): power-controller@170 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x170 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1131,7 +1132,7 @@ }; DIE_NODE(ps_afnc2_lw1): power-controller@178 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x178 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1141,7 +1142,7 @@ }; DIE_NODE(ps_afnc3_ioa): power-controller@180 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x180 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1151,7 +1152,7 @@ }; DIE_NODE(ps_afnc3_ls): power-controller@188 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x188 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1161,7 +1162,7 @@ }; DIE_NODE(ps_afnc3_lw0): power-controller@190 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x190 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1171,7 +1172,7 @@ }; DIE_NODE(ps_apcie_gp): power-controller@198 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x198 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1180,7 +1181,7 @@ }; DIE_NODE(ps_apcie_st): power-controller@1a0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1a0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1189,7 +1190,7 @@ }; DIE_NODE(ps_ans2): power-controller@1a8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1a8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1198,7 +1199,7 @@ }; DIE_NODE(ps_disp0_sys): power-controller@1b0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1b0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1207,7 +1208,7 @@ }; DIE_NODE(ps_jpg): power-controller@1b8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1b8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1216,7 +1217,7 @@ }; DIE_NODE(ps_sio): power-controller@1c0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1c0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1225,7 +1226,7 @@ }; DIE_NODE(ps_isp_sys): power-controller@1c8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1c8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1235,7 +1236,7 @@ }; DIE_NODE(ps_disp0_fe): power-controller@1d0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1d0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1244,7 +1245,7 @@ }; DIE_NODE(ps_disp0_cpu0): power-controller@1d8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1d8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1254,16 +1255,16 @@ }; DIE_NODE(ps_sio_cpu): power-controller@1e0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1e0 4>; #power-domain-cells = <0>; #reset-cells = <0>; label = DIE_LABEL(sio_cpu); - power-domains = <&DIE_NODE(ps_sio)>; + power-domains = <&DIE_NODE(ps_sio) &DIE_NODE(ps_uart_p) &DIE_NODE(ps_spi_p) &DIE_NODE(ps_audio_p)>; }; DIE_NODE(ps_fpwm0): power-controller@1e8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1e8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1272,7 +1273,7 @@ }; DIE_NODE(ps_fpwm1): power-controller@1f0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1f0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1281,7 +1282,7 @@ }; DIE_NODE(ps_fpwm2): power-controller@1f8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x1f8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1290,7 +1291,7 @@ }; DIE_NODE(ps_i2c0): power-controller@200 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x200 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1299,7 +1300,7 @@ }; DIE_NODE(ps_i2c1): power-controller@208 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x208 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1308,7 +1309,7 @@ }; DIE_NODE(ps_i2c2): power-controller@210 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x210 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1317,7 +1318,7 @@ }; DIE_NODE(ps_i2c3): power-controller@218 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x218 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1326,7 +1327,7 @@ }; DIE_NODE(ps_i2c4): power-controller@220 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x220 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1335,7 +1336,7 @@ }; DIE_NODE(ps_i2c5): power-controller@228 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x228 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1344,7 +1345,7 @@ }; DIE_NODE(ps_i2c6): power-controller@230 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x230 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1353,7 +1354,7 @@ }; DIE_NODE(ps_i2c7): power-controller@238 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x238 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1362,7 +1363,7 @@ }; DIE_NODE(ps_i2c8): power-controller@240 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x240 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1371,7 +1372,7 @@ }; DIE_NODE(ps_spi_p): power-controller@248 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x248 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1380,7 +1381,7 @@ }; DIE_NODE(ps_sio_spmi0): power-controller@250 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x250 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1389,7 +1390,7 @@ }; DIE_NODE(ps_sio_spmi1): power-controller@258 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x258 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1398,7 +1399,7 @@ }; DIE_NODE(ps_sio_spmi2): power-controller@260 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x260 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1407,7 +1408,7 @@ }; DIE_NODE(ps_uart_p): power-controller@268 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x268 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1416,7 +1417,7 @@ }; DIE_NODE(ps_audio_p): power-controller@270 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x270 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1425,7 +1426,7 @@ }; DIE_NODE(ps_sio_adma): power-controller@278 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x278 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1434,7 +1435,7 @@ }; DIE_NODE(ps_aes): power-controller@280 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x280 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1444,7 +1445,7 @@ }; DIE_NODE(ps_dptx_phy_ps): power-controller@288 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x288 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1453,7 +1454,7 @@ }; DIE_NODE(ps_spi0): power-controller@2d8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2d8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1462,7 +1463,7 @@ }; DIE_NODE(ps_spi1): power-controller@2e0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2e0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1471,7 +1472,7 @@ }; DIE_NODE(ps_spi2): power-controller@2e8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2e8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1480,7 +1481,7 @@ }; DIE_NODE(ps_spi3): power-controller@2f0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2f0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1489,7 +1490,7 @@ }; DIE_NODE(ps_spi4): power-controller@2f8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x2f8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1498,7 +1499,7 @@ }; DIE_NODE(ps_spi5): power-controller@300 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x300 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1507,7 +1508,7 @@ }; DIE_NODE(ps_uart_n): power-controller@308 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x308 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1516,7 +1517,7 @@ }; DIE_NODE(ps_uart0): power-controller@310 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x310 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1525,7 +1526,7 @@ }; DIE_NODE(ps_amcc1): power-controller@318 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x318 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1534,7 +1535,7 @@ }; DIE_NODE(ps_amcc3): power-controller@320 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x320 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1543,7 +1544,7 @@ }; DIE_NODE(ps_dcs_04): power-controller@328 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x328 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1552,7 +1553,7 @@ }; DIE_NODE(ps_dcs_05): power-controller@330 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x330 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1561,7 +1562,7 @@ }; DIE_NODE(ps_dcs_06): power-controller@338 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x338 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1570,7 +1571,7 @@ }; DIE_NODE(ps_dcs_07): power-controller@340 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x340 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1579,7 +1580,7 @@ }; DIE_NODE(ps_dcs_12): power-controller@348 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x348 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1588,7 +1589,7 @@ }; DIE_NODE(ps_dcs_13): power-controller@350 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x350 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1597,7 +1598,7 @@ }; DIE_NODE(ps_dcs_14): power-controller@358 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x358 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1606,7 +1607,7 @@ }; DIE_NODE(ps_dcs_15): power-controller@360 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x360 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1615,7 +1616,7 @@ }; DIE_NODE(ps_uart1): power-controller@368 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x368 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1624,7 +1625,7 @@ }; DIE_NODE(ps_uart2): power-controller@370 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x370 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1633,7 +1634,7 @@ }; DIE_NODE(ps_uart3): power-controller@378 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x378 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1642,7 +1643,7 @@ }; DIE_NODE(ps_uart4): power-controller@380 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x380 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1651,7 +1652,7 @@ }; DIE_NODE(ps_uart5): power-controller@388 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x388 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1660,7 +1661,7 @@ }; DIE_NODE(ps_uart6): power-controller@390 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x390 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1669,43 +1670,47 @@ }; DIE_NODE(ps_mca0): power-controller@398 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x398 4>; #power-domain-cells = <0>; #reset-cells = <0>; label = DIE_LABEL(mca0); power-domains = <&DIE_NODE(ps_audio_p)>, <&DIE_NODE(ps_sio_adma)>; + apple,externally-clocked; }; DIE_NODE(ps_mca1): power-controller@3a0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x3a0 4>; #power-domain-cells = <0>; #reset-cells = <0>; label = DIE_LABEL(mca1); power-domains = <&DIE_NODE(ps_audio_p)>, <&DIE_NODE(ps_sio_adma)>; + apple,externally-clocked; }; DIE_NODE(ps_mca2): power-controller@3a8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x3a8 4>; #power-domain-cells = <0>; #reset-cells = <0>; label = DIE_LABEL(mca2); power-domains = <&DIE_NODE(ps_audio_p)>, <&DIE_NODE(ps_sio_adma)>; + apple,externally-clocked; }; DIE_NODE(ps_mca3): power-controller@3b0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x3b0 4>; #power-domain-cells = <0>; #reset-cells = <0>; label = DIE_LABEL(mca3); power-domains = <&DIE_NODE(ps_audio_p)>, <&DIE_NODE(ps_sio_adma)>; + apple,externally-clocked; }; DIE_NODE(ps_dpa0): power-controller@3b8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x3b8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1714,7 +1719,7 @@ }; DIE_NODE(ps_dpa1): power-controller@3c0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x3c0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1723,7 +1728,7 @@ }; DIE_NODE(ps_dpa2): power-controller@3c8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x3c8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1732,7 +1737,7 @@ }; DIE_NODE(ps_dpa3): power-controller@3d0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x3d0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1741,7 +1746,7 @@ }; DIE_NODE(ps_msr0): power-controller@3d8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x3d8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1749,7 +1754,7 @@ }; DIE_NODE(ps_venc_sys): power-controller@3e0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x3e0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1757,7 +1762,7 @@ }; DIE_NODE(ps_dpa4): power-controller@3e8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x3e8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1766,7 +1771,7 @@ }; DIE_NODE(ps_msr0_ase_core): power-controller@3f0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x3f0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1775,7 +1780,7 @@ }; DIE_NODE(ps_apcie_gpshr_sys): power-controller@3f8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x3f8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1784,7 +1789,7 @@ }; DIE_NODE(ps_apcie_st_sys): power-controller@408 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x408 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1793,7 +1798,7 @@ }; DIE_NODE(ps_apcie_st1_sys): power-controller@410 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x410 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1802,7 +1807,7 @@ }; DIE_NODE(ps_apcie_gp_sys): power-controller@418 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x418 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1812,7 +1817,7 @@ }; DIE_NODE(ps_apcie_ge_sys): power-controller@420 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x420 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1821,7 +1826,7 @@ }; DIE_NODE(ps_apcie_phy_sw): power-controller@428 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x428 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1830,7 +1835,7 @@ }; DIE_NODE(ps_sep): power-controller@c00 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xc00 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1847,16 +1852,17 @@ * have to enable/disable everything in the per-model DTs. */ DIE_NODE(ps_isp_cpu): power-controller@4000 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4000 4>; #power-domain-cells = <0>; #reset-cells = <0>; label = DIE_LABEL(isp_cpu); /* power-domains = <&DIE_NODE(ps_isp_sys)>; */ + apple,force-disable; }; DIE_NODE(ps_isp_fe): power-controller@4008 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4008 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1865,7 +1871,7 @@ }; DIE_NODE(ps_dprx): power-controller@4010 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4010 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1874,7 +1880,7 @@ }; DIE_NODE(ps_isp_vis): power-controller@4018 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4018 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1883,7 +1889,7 @@ }; DIE_NODE(ps_isp_be): power-controller@4020 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4020 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1892,7 +1898,7 @@ }; DIE_NODE(ps_isp_raw): power-controller@4028 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4028 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1901,7 +1907,7 @@ }; DIE_NODE(ps_isp_clr): power-controller@4030 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x4030 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1910,7 +1916,7 @@ }; DIE_NODE(ps_venc_dma): power-controller@8000 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x8000 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1919,7 +1925,7 @@ }; DIE_NODE(ps_venc_pipe4): power-controller@8008 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x8008 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1928,7 +1934,7 @@ }; DIE_NODE(ps_venc_pipe5): power-controller@8010 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x8010 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1937,7 +1943,7 @@ }; DIE_NODE(ps_venc_me0): power-controller@8018 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x8018 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1946,7 +1952,7 @@ }; DIE_NODE(ps_venc_me1): power-controller@8020 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x8020 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1955,7 +1961,7 @@ }; DIE_NODE(ps_prores): power-controller@c000 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xc000 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1966,7 +1972,7 @@ &DIE_NODE(pmgr_mini) { DIE_NODE(ps_debug): power-controller@58 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x58 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1975,7 +1981,7 @@ }; DIE_NODE(ps_nub_spmi0): power-controller@60 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x60 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1984,7 +1990,7 @@ }; DIE_NODE(ps_nub_spmi1): power-controller@68 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x68 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -1993,7 +1999,7 @@ }; DIE_NODE(ps_nub_aon): power-controller@70 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x70 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2002,7 +2008,7 @@ }; DIE_NODE(ps_msg): power-controller@78 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x78 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2011,7 +2017,7 @@ }; DIE_NODE(ps_nub_gpio): power-controller@80 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x80 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2020,7 +2026,7 @@ }; DIE_NODE(ps_nub_fabric): power-controller@88 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x88 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2029,7 +2035,7 @@ }; DIE_NODE(ps_atc0_usb_aon): power-controller@90 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x90 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2038,7 +2044,7 @@ }; DIE_NODE(ps_atc1_usb_aon): power-controller@98 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x98 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2047,7 +2053,7 @@ }; DIE_NODE(ps_atc2_usb_aon): power-controller@a0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xa0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2056,7 +2062,7 @@ }; DIE_NODE(ps_atc3_usb_aon): power-controller@a8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xa8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2065,7 +2071,7 @@ }; DIE_NODE(ps_mtp_fabric): power-controller@b0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xb0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2076,7 +2082,7 @@ }; DIE_NODE(ps_nub_sram): power-controller@b8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xb8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2085,7 +2091,7 @@ }; DIE_NODE(ps_debug_switch): power-controller@c0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xc0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2094,7 +2100,7 @@ }; DIE_NODE(ps_atc0_usb): power-controller@c8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xc8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2103,7 +2109,7 @@ }; DIE_NODE(ps_atc1_usb): power-controller@d0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xd0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2112,7 +2118,7 @@ }; DIE_NODE(ps_atc2_usb): power-controller@d8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xd8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2121,7 +2127,7 @@ }; DIE_NODE(ps_atc3_usb): power-controller@e0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xe0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2132,7 +2138,7 @@ #if 0 /* MTP stuff is self-managed */ DIE_NODE(ps_mtp_gpio): power-controller@e8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xe8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2142,7 +2148,7 @@ }; DIE_NODE(ps_mtp_base): power-controller@f0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xf0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2152,7 +2158,7 @@ }; DIE_NODE(ps_mtp_periph): power-controller@f8 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0xf8 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2162,7 +2168,7 @@ }; DIE_NODE(ps_mtp_spi0): power-controller@100 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x100 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2172,7 +2178,7 @@ }; DIE_NODE(ps_mtp_i2cm0): power-controller@108 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x108 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2182,7 +2188,7 @@ }; DIE_NODE(ps_mtp_uart0): power-controller@110 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x110 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2192,7 +2198,7 @@ }; DIE_NODE(ps_mtp_cpu): power-controller@118 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x118 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2202,7 +2208,7 @@ }; DIE_NODE(ps_mtp_scm_fabric): power-controller@120 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x120 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2212,7 +2218,7 @@ }; DIE_NODE(ps_mtp_sram): power-controller@128 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x128 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2222,7 +2228,7 @@ }; DIE_NODE(ps_mtp_dma): power-controller@130 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x130 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2235,7 +2241,7 @@ &DIE_NODE(pmgr_gfx) { DIE_NODE(ps_gpx): power-controller@0 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x0 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2245,7 +2251,7 @@ }; DIE_NODE(ps_afr): power-controller@100 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x100 4>; #power-domain-cells = <0>; #reset-cells = <0>; @@ -2255,7 +2261,7 @@ }; DIE_NODE(ps_gfx): power-controller@108 { - compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + compatible = "apple,t6020-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x108 4>; #power-domain-cells = <0>; #reset-cells = <0>; diff --git a/arch/arm64/boot/dts/apple/t8103-j274.dts b/arch/arm64/boot/dts/apple/t8103-j274.dts index 1c3e37f86d46d7..f55683c48784b8 100644 --- a/arch/arm64/boot/dts/apple/t8103-j274.dts +++ b/arch/arm64/boot/dts/apple/t8103-j274.dts @@ -15,12 +15,27 @@ / { compatible = "apple,j274", "apple,t8103", "apple,arm-platform"; model = "Apple Mac mini (M1, 2020)"; + chassis-type = "desktop"; aliases { ethernet0 = ðernet0; + sio = &sio; }; }; +&dcp { + apple,connector-type = "HDMI-A"; +}; + +/* remove once m1n1 enables sio nodes after setup */ +&sio { + status = "okay"; +}; + +&dpaudio0 { + status = "okay"; +}; + &bluetooth0 { brcm,board-type = "apple,atlantisb"; }; @@ -29,6 +44,18 @@ brcm,board-type = "apple,atlantisb"; }; +/* + * Provide labels for the USB type C ports. + */ + +&typec0 { + label = "USB-C Back-left"; +}; + +&typec1 { + label = "USB-C Back-right"; +}; + /* * Force the bus number assignments so that we can declare some of the * on-board devices and properties that are populated by the bootloader @@ -58,6 +85,65 @@ status = "okay"; }; +&i2c1 { + speaker_amp: codec@31 { + compatible = "ti,tas5770l", "ti,tas2770"; + reg = <0x31>; + shutdown-gpios = <&pinctrl_ap 181 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + ti,imon-slot-no = <0>; + ti,vmon-slot-no = <2>; + ti,sdout-zero-fill; + }; +}; + &i2c2 { status = "okay"; + + jack_codec: codec@48 { + compatible = "cirrus,cs42l83"; + reg = <0x48>; + reset-gpios = <&pinctrl_nub 11 GPIO_ACTIVE_HIGH>; + interrupt-parent = <&pinctrl_ap>; + interrupts = <183 IRQ_TYPE_LEVEL_LOW>; + #sound-dai-cells = <0>; + cirrus,ts-inv = <1>; + sound-name-prefix = "Jack"; + }; }; + +/ { + sound { + compatible = "apple,j274-macaudio", "apple,macaudio"; + model = "Mac mini J274"; + + dai-link@0 { + link-name = "Speaker"; + + cpu { + sound-dai = <&mca 0>; + }; + codec { + sound-dai = <&speaker_amp>; + }; + }; + + dai-link@1 { + link-name = "Headphone Jack"; + + cpu { + sound-dai = <&mca 2>; + }; + codec { + sound-dai = <&jack_codec>; + }; + }; + + }; +}; + +&gpu { + apple,perf-base-pstate = <3>; +}; + +#include "hwmon-mini.dtsi" diff --git a/arch/arm64/boot/dts/apple/t8103-j293.dts b/arch/arm64/boot/dts/apple/t8103-j293.dts index 5b3c42e9f0e677..6fa04626b1d08b 100644 --- a/arch/arm64/boot/dts/apple/t8103-j293.dts +++ b/arch/arm64/boot/dts/apple/t8103-j293.dts @@ -16,6 +16,7 @@ / { compatible = "apple,j293", "apple,t8103", "apple,arm-platform"; model = "Apple MacBook Pro (13-inch, M1, 2020)"; + chassis-type = "laptop"; /* * All of those are used by the bootloader to pass calibration @@ -23,6 +24,7 @@ */ aliases { touchbar0 = &touchbar0; + sep = &sep; }; led-controller { @@ -38,6 +40,20 @@ }; }; +&dcp { + panel: panel { + compatible = "apple,panel-j293", "apple,panel"; + width-mm = <286>; + height-mm = <179>; + apple,max-brightness = <525>; + }; +}; + +&framebuffer0 { + panel = <&panel>; + post-init-providers = <&panel>; +}; + &bluetooth0 { brcm,board-type = "apple,honshu"; }; @@ -46,8 +62,117 @@ brcm,board-type = "apple,honshu"; }; +/* + * Provide labels for the USB type C ports. + */ + +&typec0 { + label = "USB-C Left-back"; +}; + +&typec1 { + label = "USB-C Left-front"; +}; + +&spi3 { + status = "okay"; + + hid-transport@0 { + compatible = "apple,spi-hid-transport"; + reg = <0>; + spi-max-frequency = <8000000>; + /* + * Apple's ADT specifies 20us CS change delays, and the + * SPI HID interface metadata specifies 45us. Using either + * seems not to be reliable, but adding both works, so + * best guess is they are cumulative. + */ + spi-cs-setup-delay-ns = <65000>; + spi-cs-hold-delay-ns = <65000>; + spi-cs-inactive-delay-ns = <250000>; + spien-gpios = <&pinctrl_ap 195 0>; + interrupts-extended = <&pinctrl_nub 13 IRQ_TYPE_LEVEL_LOW>; + }; +}; + +/* Virtual regulator representing the shared shutdown GPIO */ +/ { + speaker_sdz: fixed-regulator-tas5770-sdz { + compatible = "regulator-fixed"; + regulator-name = "tas5770-sdz"; + startup-delay-us = <5000>; + gpios = <&pinctrl_ap 181 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; +}; + +&i2c1 { + speaker_left_rear: codec@31 { + compatible = "ti,tas5770l", "ti,tas2770"; + reg = <0x31>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Left Rear"; + interrupts-extended = <&pinctrl_ap 182 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <8>; + ti,vmon-slot-no = <10>; + ti,pdm-slot-no = <12>; + }; + + speaker_left_front: codec@32 { + compatible = "ti,tas5770l", "ti,tas2770"; + reg = <0x32>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Left Front"; + interrupts-extended = <&pinctrl_ap 182 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <0>; + ti,vmon-slot-no = <2>; + ti,pdm-slot-no = <4>; + ti,sdout-pull-down; + }; +}; + &i2c2 { status = "okay"; + + jack_codec: codec@48 { + compatible = "cirrus,cs42l83"; + reg = <0x48>; + reset-gpios = <&pinctrl_nub 11 GPIO_ACTIVE_HIGH>; + interrupt-parent = <&pinctrl_ap>; + interrupts = <183 IRQ_TYPE_LEVEL_LOW>; + #sound-dai-cells = <0>; + cirrus,ts-inv = <1>; + sound-name-prefix = "Jack"; + }; +}; + +&i2c3 { + speaker_right_rear: codec@34 { + compatible = "ti,tas5770l", "ti,tas2770"; + reg = <0x34>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Right Rear"; + interrupts-extended = <&pinctrl_ap 182 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <12>; + ti,vmon-slot-no = <14>; + ti,pdm-slot-no = <16>; + }; + + speaker_right_front: codec@35 { + compatible = "ti,tas5770l", "ti,tas2770"; + reg = <0x35>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Right Front"; + interrupts-extended = <&pinctrl_ap 182 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <4>; + ti,vmon-slot-no = <6>; + ti,pdm-slot-no = <8>; + ti,sdout-pull-down; + }; }; &i2c4 { @@ -119,3 +244,67 @@ &displaydfr_dart { status = "okay"; }; + +&aop_mbox { + status = "okay"; +}; + +&aop_dart { + status = "okay"; +}; + +&aop_admac { + status = "okay"; +}; + +&aop { + status = "okay"; +}; + +&sep { + status = "okay"; +}; + +&aop_audio { + apple,chassis-name = "J293"; + apple,machine-kind = "MacBook Pro"; +}; + +/ { + sound { + compatible = "apple,j293-macaudio", "apple,macaudio"; + model = "MacBook Pro J293"; + + dai-link@0 { + link-name = "Speakers"; + + cpu { + sound-dai = <&mca 0>, <&mca 1>; + }; + codec { + sound-dai = <&speaker_left_front>, <&speaker_left_rear>, + <&speaker_right_front>, <&speaker_right_rear>; + }; + }; + + dai-link@1 { + link-name = "Headphone Jack"; + + cpu { + sound-dai = <&mca 2>; + }; + codec { + sound-dai = <&jack_codec>; + }; + }; + }; +}; + +#include "isp-imx248.dtsi" + +&isp { + apple,platform-id = <1>; +}; + +#include "hwmon-fan.dtsi" +#include "hwmon-laptop.dtsi" diff --git a/arch/arm64/boot/dts/apple/t8103-j313.dts b/arch/arm64/boot/dts/apple/t8103-j313.dts index 97a4344d8dca68..883ba4a1f0100a 100644 --- a/arch/arm64/boot/dts/apple/t8103-j313.dts +++ b/arch/arm64/boot/dts/apple/t8103-j313.dts @@ -16,6 +16,11 @@ / { compatible = "apple,j313", "apple,t8103", "apple,arm-platform"; model = "Apple MacBook Air (M1, 2020)"; + chassis-type = "laptop"; + + aliases { + sep = &sep; + }; led-controller { compatible = "pwm-leds"; @@ -30,6 +35,20 @@ }; }; +&dcp { + panel: panel { + compatible = "apple,panel-j313", "apple,panel"; + width-mm = <286>; + height-mm = <179>; + apple,max-brightness = <420>; + }; +}; + +&framebuffer0 { + panel = <&panel>; + post-init-providers = <&panel>; +}; + &bluetooth0 { brcm,board-type = "apple,shikoku"; }; @@ -41,3 +60,148 @@ &fpwm1 { status = "okay"; }; + +/* + * Provide labels for the USB type C ports. + */ + +&typec0 { + label = "USB-C Left-back"; +}; + +&typec1 { + label = "USB-C Left-front"; +}; + +&spi3 { + status = "okay"; + + hid-transport@0 { + compatible = "apple,spi-hid-transport"; + reg = <0>; + spi-max-frequency = <8000000>; + /* + * Apple's ADT specifies 20us CS change delays, and the + * SPI HID interface metadata specifies 45us. Using either + * seems not to be reliable, but adding both works, so + * best guess is they are cumulative. + */ + spi-cs-setup-delay-ns = <65000>; + spi-cs-hold-delay-ns = <65000>; + spi-cs-inactive-delay-ns = <250000>; + spien-gpios = <&pinctrl_ap 195 0>; + interrupts-extended = <&pinctrl_nub 13 IRQ_TYPE_LEVEL_LOW>; + }; +}; + +/* Virtual regulator representing the shared shutdown GPIO */ +/ { + speaker_sdz: fixed-regulator-tas5770-sdz { + compatible = "regulator-fixed"; + regulator-name = "tas5770-sdz"; + startup-delay-us = <5000>; + gpios = <&pinctrl_ap 181 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; +}; + +&i2c1 { + speaker_left: codec@31 { + compatible = "ti,tas5770l", "ti,tas2770"; + reg = <0x31>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Left"; + interrupts-extended = <&pinctrl_ap 182 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <0>; + ti,vmon-slot-no = <2>; + ti,sdout-zero-fill; + }; +}; + +&i2c3 { + speaker_right: codec@34 { + compatible = "ti,tas5770l", "ti,tas2770"; + reg = <0x34>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Right"; + interrupts-extended = <&pinctrl_ap 182 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <4>; + ti,vmon-slot-no = <6>; + ti,sdout-zero-fill; + }; + + jack_codec: codec@48 { + compatible = "cirrus,cs42l83"; + reg = <0x48>; + reset-gpios = <&pinctrl_nub 11 GPIO_ACTIVE_HIGH>; + interrupt-parent = <&pinctrl_ap>; + interrupts = <183 IRQ_TYPE_LEVEL_LOW>; + #sound-dai-cells = <0>; + cirrus,ts-inv = <1>; + sound-name-prefix = "Jack"; + }; +}; + +&aop_mbox { + status = "okay"; +}; + +&aop_dart { + status = "okay"; +}; + +&aop_admac { + status = "okay"; +}; + +&aop { + status = "okay"; +}; + +&sep { + status = "okay"; +}; + +&aop_audio { + apple,chassis-name = "J313"; + apple,machine-kind = "MacBook Air"; +}; + +/ { + sound { + compatible = "apple,j313-macaudio", "apple,macaudio"; + model = "MacBook Air J313"; + + dai-link@0 { + link-name = "Speakers"; + + cpu { + sound-dai = <&mca 0>, <&mca 1>; + }; + codec { + sound-dai = <&speaker_left>, <&speaker_right>; + }; + }; + + dai-link@1 { + link-name = "Headphone Jack"; + + cpu { + sound-dai = <&mca 2>; + }; + codec { + sound-dai = <&jack_codec>; + }; + }; + }; +}; + +#include "isp-imx248.dtsi" + +&isp { + apple,platform-id = <1>; +}; + +#include "hwmon-laptop.dtsi" diff --git a/arch/arm64/boot/dts/apple/t8103-j456.dts b/arch/arm64/boot/dts/apple/t8103-j456.dts index 58c8e43789b486..c7da4815fb94c0 100644 --- a/arch/arm64/boot/dts/apple/t8103-j456.dts +++ b/arch/arm64/boot/dts/apple/t8103-j456.dts @@ -15,12 +15,27 @@ / { compatible = "apple,j456", "apple,t8103", "apple,arm-platform"; model = "Apple iMac (24-inch, 4x USB-C, M1, 2021)"; + chassis-type = "all-in-one"; aliases { ethernet0 = ðernet0; }; }; +&dcp { + panel: panel { + compatible = "apple,panel-j456", "apple,panel"; + width-mm = <522>; + height-mm = <294>; + apple,max-brightness = <525>; + }; +}; + +&framebuffer0 { + panel = <&panel>; + post-init-providers = <&panel>; +}; + &bluetooth0 { brcm,board-type = "apple,capri"; }; @@ -47,6 +62,18 @@ }; }; +/* + * Provide labels for the USB type C ports. + */ + +&typec0 { + label = "USB-C Back-right"; +}; + +&typec1 { + label = "USB-C Back-right-middle"; +}; + /* * Force the bus number assignments so that we can declare some of the * on-board devices and properties that are populated by the bootloader @@ -75,3 +102,72 @@ &pcie0_dart_2 { status = "okay"; }; + +&i2c1 { + jack_codec: codec@48 { + compatible = "cirrus,cs42l83"; + reg = <0x48>; + reset-gpios = <&pinctrl_nub 11 GPIO_ACTIVE_HIGH>; + interrupt-parent = <&pinctrl_ap>; + interrupts = <183 IRQ_TYPE_LEVEL_LOW>; + #sound-dai-cells = <0>; + cirrus,ts-inv = <1>; + sound-name-prefix = "Jack"; + }; +}; + +&aop_mbox { + status = "okay"; +}; + +&aop_dart { + status = "okay"; +}; + +&aop_admac { + status = "okay"; +}; + +&aop { + status = "okay"; +}; + +&sep { + status = "okay"; +}; + +&aop_audio { + apple,chassis-name = "J456"; + apple,machine-kind = "iMac"; + apple,no-beamforming; +}; + +/ { + sound { + compatible = "apple,j456-macaudio", "apple,macaudio"; + model = "iMac J456"; + + dai-link@1 { + link-name = "Headphone Jack"; + + cpu { + sound-dai = <&mca 2>; + }; + codec { + sound-dai = <&jack_codec>; + }; + }; + }; +}; + +&gpu { + apple,perf-base-pstate = <3>; +}; + +#include "isp-imx364.dtsi" + +&isp { + apple,platform-id = <2>; +}; + +#include "hwmon-fan-dual.dtsi" diff --git a/arch/arm64/boot/dts/apple/t8103-j457.dts b/arch/arm64/boot/dts/apple/t8103-j457.dts index 7089ccf3ce5566..fc0f28fb1c4367 100644 --- a/arch/arm64/boot/dts/apple/t8103-j457.dts +++ b/arch/arm64/boot/dts/apple/t8103-j457.dts @@ -15,12 +15,27 @@ / { compatible = "apple,j457", "apple,t8103", "apple,arm-platform"; model = "Apple iMac (24-inch, 2x USB-C, M1, 2021)"; + chassis-type = "all-in-one"; aliases { ethernet0 = ðernet0; }; }; +&dcp { + panel: panel { + compatible = "apple,panel-j457", "apple,panel"; + width-mm = <522>; + height-mm = <294>; + apple,max-brightness = <525>; + }; +}; + +&framebuffer0 { + panel = <&panel>; + post-init-providers = <&panel>; +}; + /* * Adjust pcie0's iommu-map to account for the disabled port01. */ @@ -37,6 +52,18 @@ brcm,board-type = "apple,santorini"; }; +/* + * Provide labels for the USB type C ports. + */ + +&typec0 { + label = "USB-C Back-right"; +}; + +&typec1 { + label = "USB-C Back-left"; +}; + /* * Force the bus number assignments so that we can declare some of the * on-board devices and properties that are populated by the bootloader @@ -56,3 +83,72 @@ &pcie0_dart_2 { status = "okay"; }; + +&i2c1 { + jack_codec: codec@48 { + compatible = "cirrus,cs42l83"; + reg = <0x48>; + reset-gpios = <&pinctrl_nub 11 GPIO_ACTIVE_HIGH>; + interrupt-parent = <&pinctrl_ap>; + interrupts = <183 IRQ_TYPE_LEVEL_LOW>; + #sound-dai-cells = <0>; + cirrus,ts-inv = <1>; + sound-name-prefix = "Jack"; + }; +}; + +&aop_mbox { + status = "okay"; +}; + +&aop_dart { + status = "okay"; +}; + +&aop_admac { + status = "okay"; +}; + +&aop { + status = "okay"; +}; + +&sep { + status = "okay"; +}; + +&aop_audio { + apple,chassis-name = "J457"; + apple,machine-kind = "iMac"; + apple,no-beamforming; +}; + +/ { + sound { + compatible = "apple,j457-macaudio", "apple,macaudio"; + model = "iMac J457"; + + dai-link@1 { + link-name = "Headphone Jack"; + + cpu { + sound-dai = <&mca 2>; + }; + codec { + sound-dai = <&jack_codec>; + }; + }; + }; +}; + +&gpu { + apple,perf-base-pstate = <3>; +}; + +#include "isp-imx364.dtsi" + +&isp { + apple,platform-id = <2>; +}; + +#include "hwmon-fan.dtsi" diff --git a/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi b/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi index 0c8206156bfefd..67a57fc507df92 100644 --- a/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi +++ b/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi @@ -12,9 +12,14 @@ / { aliases { bluetooth0 = &bluetooth0; + dcp = &dcp; + disp0 = &display; + disp0_piodma = &disp0_piodma; serial0 = &serial0; serial2 = &serial2; wifi0 = &wifi0; + atcphy0 = &atcphy0; + atcphy1 = &atcphy1; }; chosen { @@ -27,11 +32,19 @@ framebuffer0: framebuffer@0 { compatible = "apple,simple-framebuffer", "simple-framebuffer"; reg = <0 0 0 0>; /* To be filled by loader */ + power-domains = <&ps_disp0_cpu0>; /* Format properties will be added by loader */ status = "disabled"; }; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + /* To be filled by loader */ + }; + memory@800000000 { device_type = "memory"; reg = <0x8 0 0x2 0>; /* To be filled by loader */ @@ -53,6 +66,29 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <106 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec0: connector { + compatible = "usb-c-connector"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec0_connector_hs: endpoint { + remote-endpoint = <&dwc3_0_hs>; + }; + }; + port@1 { + reg = <1>; + typec0_connector_ss: endpoint { + remote-endpoint = <&atcphy0_typec_lanes>; + }; + }; + }; + }; }; hpm1: usb-pd@3f { @@ -61,6 +97,115 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <106 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec1: connector { + compatible = "usb-c-connector"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec1_connector_hs: endpoint { + remote-endpoint = <&dwc3_1_hs>; + }; + }; + port@1 { + reg = <1>; + typec1_connector_ss: endpoint { + remote-endpoint = <&atcphy1_typec_lanes>; + }; + }; + }; + }; + }; +}; + +/* USB controllers */ +&dwc3_0 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_0_hs: endpoint { + remote-endpoint = <&typec0_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_0_ss: endpoint { + remote-endpoint = <&atcphy0_usb3>; + }; + }; + }; +}; + +&dwc3_1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_1_hs: endpoint { + remote-endpoint = <&typec1_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_1_ss: endpoint { + remote-endpoint = <&atcphy1_usb3>; + }; + }; + }; +}; + +/* Type-C PHYs */ +&atcphy0 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy0_typec_lanes: endpoint { + remote-endpoint = <&typec0_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy0_usb3: endpoint { + remote-endpoint = <&dwc3_0_ss>; + }; + }; + }; +}; + +&atcphy1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy1_typec_lanes: endpoint { + remote-endpoint = <&typec1_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy1_usb3: endpoint { + remote-endpoint = <&dwc3_1_ss>; + }; + }; }; }; @@ -71,6 +216,7 @@ */ &port00 { bus-range = <1 1>; + pwren-gpios = <&smc_gpio 13 GPIO_ACTIVE_HIGH>; wifi0: wifi@0,0 { compatible = "pci14e4,4425"; reg = <0x10000 0x0 0x0 0x0 0x0>; @@ -91,4 +237,6 @@ clock-frequency = <900000000>; }; +#include "hwmon-common.dtsi" + #include "spi1-nvram.dtsi" diff --git a/arch/arm64/boot/dts/apple/t8103-pmgr.dtsi b/arch/arm64/boot/dts/apple/t8103-pmgr.dtsi index c41c57d63997a5..5d3846d44e3578 100644 --- a/arch/arm64/boot/dts/apple/t8103-pmgr.dtsi +++ b/arch/arm64/boot/dts/apple/t8103-pmgr.dtsi @@ -234,7 +234,7 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = "sio_cpu"; - power-domains = <&ps_sio>; + power-domains = <&ps_sio &ps_uart_p &ps_spi_p &ps_dpa0>; }; ps_fpwm0: power-controller@1d8 { @@ -493,6 +493,7 @@ #reset-cells = <0>; label = "mca0"; power-domains = <&ps_audio_p>, <&ps_sio_adma>; + apple,externally-clocked; }; ps_mca1: power-controller@2c0 { @@ -502,6 +503,7 @@ #reset-cells = <0>; label = "mca1"; power-domains = <&ps_audio_p>, <&ps_sio_adma>; + apple,externally-clocked; }; ps_mca2: power-controller@2c8 { @@ -511,6 +513,7 @@ #reset-cells = <0>; label = "mca2"; power-domains = <&ps_audio_p>, <&ps_sio_adma>; + apple,externally-clocked; }; ps_mca3: power-controller@2d0 { @@ -520,6 +523,7 @@ #reset-cells = <0>; label = "mca3"; power-domains = <&ps_audio_p>, <&ps_sio_adma>; + apple,externally-clocked; }; ps_mca4: power-controller@2d8 { @@ -529,6 +533,7 @@ #reset-cells = <0>; label = "mca4"; power-domains = <&ps_audio_p>, <&ps_sio_adma>; + apple,externally-clocked; }; ps_mca5: power-controller@2e0 { @@ -538,6 +543,7 @@ #reset-cells = <0>; label = "mca5"; power-domains = <&ps_audio_p>, <&ps_sio_adma>; + apple,externally-clocked; }; ps_dpa0: power-controller@2e8 { @@ -645,8 +651,7 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = "disp0_fe"; - power-domains = <&ps_rmx>; - apple,always-on; /* TODO: figure out if we can enable PM here */ + power-domains = <&ps_rmx>, <&ps_pmp>; }; ps_dispext_fe: power-controller@368 { @@ -655,7 +660,7 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = "dispext_fe"; - power-domains = <&ps_rmx>; + power-domains = <&ps_rmx>, <&ps_pmp>; }; ps_dispext_cpu0: power-controller@378 { @@ -717,6 +722,7 @@ #reset-cells = <0>; label = "apcie_gp"; power-domains = <&ps_apcie>; + apple,always-on; /* Breaks things if shut down */ }; ps_ans2: power-controller@3f0 { @@ -733,6 +739,7 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = "gfx"; + power-domains = <&ps_pmp>; }; ps_dcs4: power-controller@320 { @@ -805,6 +812,7 @@ #reset-cells = <0>; label = "isp_sys"; power-domains = <&ps_rmx>; + status = "disabled"; }; ps_venc_sys: power-controller@408 { @@ -1000,9 +1008,125 @@ #reset-cells = <0>; label = "disp0_cpu0"; power-domains = <&ps_disp0_fe>; - apple,always-on; /* TODO: figure out if we can enable PM here */ apple,min-state = <4>; }; + + /* There is a dependency tree involved with these PDs, + * but we do not express it here since the ISP driver + * is supposed to sequence them in the right order anyway + * (and we do not know the exact tree structure). + * + * This also works around spurious parent PD activation + * on machines with ISP disabled (desktops). + */ + ps_isp_set0: power-controller@4000 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4000 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set0"; + apple,force-disable; + }; + + ps_isp_set1: power-controller@4008 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4008 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set1"; + apple,force-disable; + apple,force-reset; + }; + + ps_isp_set2: power-controller@4010 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4010 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set2"; + apple,force-disable; + apple,force-reset; + }; + + ps_isp_fe: power-controller@4018 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4018 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_fe"; + }; + + ps_isp_set4: power-controller@4020 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4020 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set4"; + }; + + ps_isp_set5: power-controller@4028 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4028 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set5"; + }; + + ps_isp_set6: power-controller@4030 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4030 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set6"; + }; + + ps_isp_set7: power-controller@4038 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4038 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set7"; + }; + + ps_isp_set8: power-controller@4040 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4040 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set8"; + }; + + ps_isp_set9: power-controller@4048 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4048 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set9"; + }; + + ps_isp_set10: power-controller@4050 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4050 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set10"; + }; + + ps_isp_set11: power-controller@4058 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4058 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set11"; + }; + + ps_isp_set12: power-controller@4060 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4060 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set12"; + }; }; &pmgr_mini { @@ -1095,6 +1219,7 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = "msg"; + apple,always-on; /* Core AON device? */ }; ps_atc0_usb_aon: power-controller@88 { @@ -1103,6 +1228,7 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = "atc0_usb_aon"; + apple,always-on; /* Needs to stay on for dwc3 to work */ }; ps_atc1_usb_aon: power-controller@90 { @@ -1111,6 +1237,7 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = "atc1_usb_aon"; + apple,always-on; /* Needs to stay on for dwc3 to work */ }; ps_atc0_usb: power-controller@98 { diff --git a/arch/arm64/boot/dts/apple/t8103.dtsi b/arch/arm64/boot/dts/apple/t8103.dtsi index 8b7b2788796874..06f54772813ff8 100644 --- a/arch/arm64/boot/dts/apple/t8103.dtsi +++ b/arch/arm64/boot/dts/apple/t8103.dtsi @@ -12,6 +12,7 @@ #include #include #include +#include / { compatible = "apple,t8103", "apple,arm-platform"; @@ -193,26 +194,31 @@ opp-hz = /bits/ 64 <600000000>; opp-level = <1>; clock-latency-ns = <7500>; + opp-microwatt = <47296>; }; opp02 { opp-hz = /bits/ 64 <972000000>; opp-level = <2>; clock-latency-ns = <22000>; + opp-microwatt = <99715>; }; opp03 { opp-hz = /bits/ 64 <1332000000>; opp-level = <3>; clock-latency-ns = <27000>; + opp-microwatt = <188860>; }; opp04 { opp-hz = /bits/ 64 <1704000000>; opp-level = <4>; clock-latency-ns = <33000>; + opp-microwatt = <288891>; }; opp05 { opp-hz = /bits/ 64 <2064000000>; opp-level = <5>; clock-latency-ns = <50000>; + opp-microwatt = <412979>; }; }; @@ -223,83 +229,140 @@ opp-hz = /bits/ 64 <600000000>; opp-level = <1>; clock-latency-ns = <8000>; + opp-microwatt = <290230>; }; opp02 { opp-hz = /bits/ 64 <828000000>; opp-level = <2>; clock-latency-ns = <19000>; + opp-microwatt = <449013>; }; opp03 { opp-hz = /bits/ 64 <1056000000>; opp-level = <3>; clock-latency-ns = <21000>; + opp-microwatt = <647097>; }; opp04 { opp-hz = /bits/ 64 <1284000000>; opp-level = <4>; clock-latency-ns = <23000>; + opp-microwatt = <865620>; }; opp05 { opp-hz = /bits/ 64 <1500000000>; opp-level = <5>; clock-latency-ns = <24000>; + opp-microwatt = <1112838>; }; opp06 { opp-hz = /bits/ 64 <1728000000>; opp-level = <6>; clock-latency-ns = <29000>; + opp-microwatt = <1453271>; }; opp07 { opp-hz = /bits/ 64 <1956000000>; opp-level = <7>; clock-latency-ns = <31000>; + opp-microwatt = <1776667>; }; opp08 { opp-hz = /bits/ 64 <2184000000>; opp-level = <8>; clock-latency-ns = <34000>; + opp-microwatt = <2366690>; }; opp09 { opp-hz = /bits/ 64 <2388000000>; opp-level = <9>; clock-latency-ns = <36000>; + opp-microwatt = <2892193>; }; opp10 { opp-hz = /bits/ 64 <2592000000>; opp-level = <10>; clock-latency-ns = <51000>; + opp-microwatt = <3475417>; }; opp11 { opp-hz = /bits/ 64 <2772000000>; opp-level = <11>; clock-latency-ns = <54000>; + opp-microwatt = <3959410>; }; opp12 { opp-hz = /bits/ 64 <2988000000>; opp-level = <12>; clock-latency-ns = <55000>; + opp-microwatt = <4540620>; }; -#if 0 /* Not available until CPU deep sleep is implemented */ opp13 { opp-hz = /bits/ 64 <3096000000>; opp-level = <13>; clock-latency-ns = <55000>; + opp-microwatt = <4745031>; turbo-mode; }; opp14 { opp-hz = /bits/ 64 <3144000000>; opp-level = <14>; clock-latency-ns = <56000>; + opp-microwatt = <4822390>; turbo-mode; }; opp15 { opp-hz = /bits/ 64 <3204000000>; opp-level = <15>; clock-latency-ns = <56000>; + opp-microwatt = <4951324>; turbo-mode; }; -#endif + }; + + gpu_opp: opp-table-gpu { + compatible = "operating-points-v2"; + + /* + * NOTE: The voltage and power values are device-specific and + * must be filled in by the bootloader. + */ + opp00 { + opp-hz = /bits/ 64 <0>; + opp-microvolt = <400000>; + opp-microwatt = <0>; + }; + opp01 { + opp-hz = /bits/ 64 <396000000>; + opp-microvolt = <603000>; + opp-microwatt = <3714690>; + }; + opp02 { + opp-hz = /bits/ 64 <528000000>; + opp-microvolt = <640000>; + opp-microwatt = <5083260>; + }; + opp03 { + opp-hz = /bits/ 64 <720000000>; + opp-microvolt = <690000>; + opp-microwatt = <7429380>; + }; + opp04 { + opp-hz = /bits/ 64 <924000000>; + opp-microvolt = <784000>; + opp-microwatt = <11730600>; + }; + opp05 { + opp-hz = /bits/ 64 <1128000000>; + opp-microvolt = <862000>; + opp-microwatt = <17009370>; + }; + opp06 { + opp-hz = /bits/ 64 <1278000000>; + opp-microvolt = <931000>; + opp-microwatt = <19551000>; + }; }; timer { @@ -345,6 +408,22 @@ clock-output-names = "clk_200m"; }; + /* Pixel clock? frequency in Hz (compare: 4K@60 VGA clock 533.250 MHz) */ + clk_disp0: clock-disp0 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <533333328>; + clock-output-names = "clk_disp0"; + }; + + /* Pixel clock? frequency in Hz (compare: 4K@60 VGA clock 533.250 MHz) */ + clk_dispext0: clock-dispext0 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + clock-output-names = "clk_dispext0"; + }; + /* * This is a fabulated representation of the input clock * to NCO since we don't know the true clock tree. @@ -373,15 +452,15 @@ }; uat_handoff: uat-handoff { - status = "disabled"; + reg = <0 0 0 0>; }; uat_pagetables: uat-pagetables { - status = "disabled"; + reg = <0 0 0 0>; }; uat_ttbs: uat-ttbs { - status = "disabled"; + reg = <0 0 0 0>; }; }; @@ -392,9 +471,11 @@ ranges; nonposted-mmio; + /* Required to get >32-bit DMA via DARTs */ + dma-ranges = <0 0 0 0 0xffffffff 0xffffc000>; gpu: gpu@206400000 { - compatible = "apple,agx-g13g"; + compatible = "apple,agx-t8103", "apple,agx-g13g"; reg = <0x2 0x6400000 0 0x40000>, <0x2 0x4000000 0 0x1000000>; reg-names = "asc", "sgx"; @@ -406,6 +487,40 @@ "hw-cal-a", "hw-cal-b", "globals"; apple,firmware-abi = <0 0 0>; + + apple,firmware-version = <12 3 0>; + apple,firmware-compat = <12 3 0>; + + operating-points-v2 = <&gpu_opp>; + apple,perf-base-pstate = <1>; + apple,min-sram-microvolt = <850000>; + apple,avg-power-filter-tc-ms = <1000>; + apple,avg-power-ki-only = <7.5>; + apple,avg-power-kp = <4.0>; + apple,avg-power-min-duty-cycle = <40>; + apple,avg-power-target-filter-tc = <125>; + apple,fast-die0-integral-gain = <200.0>; + apple,fast-die0-proportional-gain = <5.0>; + apple,perf-filter-drop-threshold = <0>; + apple,perf-filter-time-constant = <5>; + apple,perf-filter-time-constant2 = <50>; + apple,perf-integral-gain2 = <0.197392>; + apple,perf-integral-min-clamp = <0>; + apple,perf-proportional-gain2 = <6.853981>; + apple,perf-tgt-utilization = <85>; + apple,power-sample-period = <8>; + apple,power-zones = <30000 100 6875>; + apple,ppm-filter-time-constant-ms = <100>; + apple,ppm-ki = <91.5>; + apple,ppm-kp = <6.9>; + apple,pwr-filter-time-constant = <313>; + apple,pwr-integral-gain = <0.0202129>; + apple,pwr-integral-min-clamp = <0>; + apple,pwr-min-duty-cycle = <40>; + apple,pwr-proportional-gain = <5.2831855>; + + apple,core-leak-coef = <1000.0>; + apple,sram-leak-coef = <45.0>; }; agx_mbox: mbox@206408000 { @@ -492,6 +607,146 @@ }; }; + disp0_dart: iommu@231304000 { + compatible = "apple,t8103-dart"; + reg = <0x2 0x31304000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_disp0_cpu0>; + apple,dma-range = <0x0 0x0 0x0 0xfc000000>; + status = "disabled"; + }; + + dcp_dart: iommu@23130c000 { + compatible = "apple,t8103-dart"; + reg = <0x2 0x3130c000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + apple,dma-range = <0xf 0x00000000 0x0 0xfc000000>; + power-domains = <&ps_disp0_cpu0>; + }; + + dcp_mbox: mbox@231c08000 { + compatible = "apple,t8103-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x31c08000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&ps_disp0_cpu0>; + resets = <&ps_disp0_cpu0>; + }; + + dcp: dcp@231c00000 { + compatible = "apple,t8103-dcp", "apple,dcp"; + mboxes = <&dcp_mbox>; + mbox-names = "mbox"; + iommus = <&dcp_dart 0>; + + reg-names = "coproc", "disp-0", "disp-1", "disp-2", + "disp-3", "disp-4"; + reg = <0x2 0x31c00000 0x0 0x4000>, + <0x2 0x30000000 0x0 0x3e8000>, + <0x2 0x31320000 0x0 0x4000>, + <0x2 0x31344000 0x0 0x4000>, + <0x2 0x31800000 0x0 0x800000>, + <0x2 0x3b3d0000 0x0 0x4000>; + apple,bw-scratch = <&pmgr_dcp 0 5 0x14>; + apple,bw-doorbell = <&pmgr_dcp 1 6>; + power-domains = <&ps_disp0_cpu0>; + resets = <&ps_disp0_cpu0>; + clocks = <&clk_disp0>; + phandle = <&dcp>; + // required bus properties for 'piodma' subdevice + #address-cells = <2>; + #size-cells = <2>; + + disp0_piodma: piodma { + iommus = <&disp0_dart 4>; + phandle = <&disp0_piodma>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dcp_audio: endpoint { + remote-endpoint = <&dpaudio0_dcp>; + }; + }; + }; + }; + + display: display-subsystem { + compatible = "apple,display-subsystem"; + /* disp_dart0 must be 1st since it is locked */ + iommus = <&disp0_dart 0>; + /* generate phandle explicitly for use in loader */ + phandle = <&display>; + }; + + isp_dart0: iommu@22c0e8000 { + compatible = "apple,t8103-dart"; + reg = <0x2 0x2c0e8000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>; + + status = "disabled"; + }; + + isp_dart1: iommu@22c0f4000 { + compatible = "apple,t8103-dart"; + reg = <0x2 0x2c0f4000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>; + + status = "disabled"; + }; + + isp_dart2: iommu@22c0fc000 { + compatible = "apple,t8103-dart"; + reg = <0x2 0x2c0fc000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>; + + status = "disabled"; + }; + + isp: isp@22a000000 { + compatible = "apple,t8103-isp", "apple,isp"; + iommus = <&isp_dart0 0>, <&isp_dart1 0>, <&isp_dart2 0>; + reg-names = "coproc", "mbox", "gpio", "mbox2"; + reg = <0x2 0x2a000000 0x0 0x2000000>, + <0x2 0x2c104000 0x0 0x100>, + <0x2 0x2c104170 0x0 0x100>, + <0x2 0x2c1043f0 0x0 0x100>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>, <&ps_isp_set0>, + <&ps_isp_set1>, <&ps_isp_set2>, <&ps_isp_fe>, + <&ps_isp_set4>, <&ps_isp_set5>, <&ps_isp_set6>, + <&ps_isp_set7>, <&ps_isp_set8>, <&ps_isp_set9>, + <&ps_isp_set10>, <&ps_isp_set11>, + <&ps_isp_set12>; + + apple,dart-vm-size = <0x0 0xa0000000>; + + status = "disabled"; + }; + sio_dart: iommu@235004000 { compatible = "apple,t8103-dart"; reg = <0x2 0x35004000 0x0 0x4000>; @@ -647,6 +902,32 @@ status = "disabled"; }; + sio_mbox: mbox@236408000 { + compatible = "apple,t8103-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x36408000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&ps_sio>; + }; + + sio: sio@236400000 { + compatible = "apple,t8103-sio", "apple,sio"; + reg = <0x2 0x36400000 0x0 0x8000>; + dma-channels = <128>; + #dma-cells = <1>; + mboxes = <&sio_mbox>; + iommus = <&sio_dart 0>; + power-domains = <&ps_sio_cpu>; + resets = <&ps_sio>; /* TODO: verify reset does something */ + status = "disabled"; + }; + admac: dma-controller@238200000 { compatible = "apple,t8103-admac", "apple,admac"; reg = <0x2 0x38200000 0x0 0x34000>; @@ -661,6 +942,48 @@ resets = <&ps_audio_p>; }; + dpaudio0: audio-controller@238330000 { + compatible = "apple,t8103-dpaudio", "apple,dpaudio"; + reg = <0x2 0x38330000 0x0 0x4000>; + dmas = <&sio 0x64>; + dma-names = "tx"; + power-domains = <&ps_dpa0>; + reset-domains = <&ps_dpa0>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dpaudio0_dcp: endpoint { + remote-endpoint = <&dcp_audio>; + }; + }; + }; + }; + + dpaudio1: audio-controller@238334000 { + compatible = "apple,t8103-dpaudio", "apple,dpaudio"; + reg = <0x2 0x38334000 0x0 0x4000>; + dmas = <&sio 0x66>; + dma-names = "tx"; + power-domains = <&ps_dpa1>; + reset-domains = <&ps_dpa1>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dpaudio1_dcp: endpoint { + remote-endpoint = <&dcpext_audio>; + }; + }; + }; + }; + mca: i2s@238400000 { compatible = "apple,t8103-mca", "apple,mca"; reg = <0x2 0x38400000 0x0 0x18000>, @@ -729,6 +1052,14 @@ reg = <0x2 0x3b700000 0 0x14000>; }; + pmgr_dcp: power-management@23b738000 { + reg = <0x2 0x3b738000 0x0 0x1000>, + <0x2 0x3bc3c000 0x0 0x1000>; + reg-names = "dcp-bw-scratch", "dcp-bw-doorbell"; + #apple,bw-scratch-cells = <3>; + #apple,bw-doorbell-cells = <2>; + }; + pinctrl_ap: pinctrl@23c100000 { compatible = "apple,t8103-pinctrl", "apple,pinctrl"; reg = <0x2 0x3c100000 0x0 0x100000>; @@ -909,12 +1240,22 @@ #gpio-cells = <2>; }; + smc_hwmon: hwmon { + compatible = "apple,smc-hwmon"; + }; + + smc_rtc: rtc { + compatible = "apple,smc-rtc"; + nvmem-cells = <&rtc_offset>; + nvmem-cell-names = "rtc_offset"; + }; + smc_reboot: reboot { compatible = "apple,smc-reboot"; nvmem-cells = <&shutdown_flag>, <&boot_stage>, - <&boot_error_count>, <&panic_count>; + <&boot_error_count>, <&panic_count>, <&pm_setting>; nvmem-cell-names = "shutdown_flag", "boot_stage", - "boot_error_count", "panic_count"; + "boot_error_count", "panic_count", "pm_setting"; }; }; @@ -952,6 +1293,36 @@ ; }; + sep_dart: iommu@2412c0000 { + compatible = "apple,t8103-dart"; + reg = <0x2 0x412c0000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + }; + + sep: sep@242400000 { + compatible = "apple,sep"; + reg = <0x2 0x42400000 0x0 0x6C000>; + mboxes = <&sep_mbox>; + mbox-names = "mbox"; + iommus = <&sep_dart 0>; + status = "disabled"; + }; + + sep_mbox: mbox@242408000 { + compatible = "apple,t8103-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x42408000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + }; + pinctrl_aop: pinctrl@24a820000 { compatible = "apple,t8103-pinctrl", "apple,pinctrl"; reg = <0x2 0x4a820000 0x0 0x4000>; @@ -973,6 +1344,147 @@ ; }; + aop_mbox: mbox@24a408000 { + compatible = "apple,t8103-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x4a408000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + status = "disabled"; + }; + + aop_dart: iommu@24a808000 { + compatible = "apple,t8103-dart"; + reg = <0x2 0x4a808000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + status = "disabled"; + }; + + aop_admac: dma-controller@24a980000 { + compatible = "apple,t8103-admac", "apple,admac"; + reg = <0x2 0x4a980000 0x0 0x34000>; + #dma-cells = <1>; + dma-channels = <16>; + interrupts-extended = <0>, + <0>, + <&aic AIC_IRQ 321 IRQ_TYPE_LEVEL_HIGH>, + <0>; + iommus = <&aop_dart 7>; + status = "disabled"; + }; + + aop: aop@24ac00000 { + compatible = "apple,t8103-aop"; + reg = <0x2 0x4ac00000 0x0 0x1e0000>, + <0x2 0x4a400000 0x0 0x6c000>; + mboxes = <&aop_mbox>; + mbox-names = "mbox"; + iommus = <&aop_dart 0>; + + status = "disabled"; + + aop_audio: audio { + compatible = "apple,t8103-aop-audio", "apple,aop-audio"; + dmas = <&aop_admac 1>; + dma-names = "dma"; + }; + + aop_als: als { + compatible = "apple,t8103-aop-als", "apple,aop-als"; + // intentionally empty + }; + + las { + compatible = "apple,t8103-aop-las", "apple,aop-las"; + }; + }; + + dispext0_dart: iommu@271304000 { + compatible = "apple,t8103-dart"; + reg = <0x2 0x71304000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_dispext_cpu0>; + apple,dma-range = <0x0 0x0 0x0 0xfc000000>; + status = "disabled"; + }; + + dcpext_dart: iommu@27130c000 { + compatible = "apple,t8103-dart"; + reg = <0x2 0x7130c000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_dispext_cpu0>; + apple,dma-range = <0xf 0x00000000 0x0 0xfc000000>; + status = "disabled"; + }; + + dcpext_mbox: mbox@271c08000 { + compatible = "apple,t8103-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x71c08000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&ps_dispext_cpu0>; + resets = <&ps_dispext_cpu0>; + status = "disabled"; + }; + + dcpext: dcp@271c00000 { + compatible = "apple,t8103-dcpext", "apple,dcpext"; + mboxes = <&dcpext_mbox>; + mbox-names = "mbox"; + iommus = <&dcpext_dart 0>; + phandle = <&dcpext>; + + reg-names = "coproc", "disp-0", "disp-1", "disp-2", + "disp-3", "disp-4"; + reg = <0x2 0x71c00000 0x0 0x4000>, + <0x2 0x70000000 0x0 0x118000>, + <0x2 0x71320000 0x0 0x4000>, + <0x2 0x71344000 0x0 0x4000>, + <0x2 0x71800000 0x0 0x800000>, + <0x2 0x3b3d0000 0x0 0x4000>; + apple,bw-scratch = <&pmgr_dcp 0 5 0x18>; + apple,bw-doorbell = <&pmgr_dcp 1 6>; + power-domains = <&ps_dispext_cpu0>; + resets = <&ps_dispext_cpu0>; + clocks = <&clk_dispext0>; + status = "disabled"; + // required bus properties for 'piodma' subdevice + #address-cells = <2>; + #size-cells = <2>; + + piodma { + iommus = <&dispext0_dart 4>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dcpext_audio: endpoint { + remote-endpoint = <&dpaudio1_dcp>; + }; + }; + }; + }; + ans_mbox: mbox@277408000 { compatible = "apple,t8103-asc-mailbox", "apple,asc-mailbox-v4"; reg = <0x2 0x77408000 0x0 0x4000>; @@ -1007,6 +1519,265 @@ resets = <&ps_ans2>; }; + efuse@23d2bc000 { + compatible = "apple,t8103-efuses", "apple,efuses"; + reg = <0x2 0x3d2bc000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <1>; + atcphy0_auspll_rodco_bias_adjust: efuse@430,26 { + reg = <0x430 4>; + bits = <26 3>; + }; + + atcphy0_auspll_rodco_encap: efuse@430,29 { + reg = <0x430 4>; + bits = <29 2>; + }; + + atcphy0_auspll_dtc_vreg_adjust: efuse@430,31 { + reg = <0x430 8>; + bits = <31 3>; + }; + + atcphy0_auspll_fracn_dll_start_capcode: efuse@434,2 { + reg = <0x434 4>; + bits = <2 2>; + }; + + atcphy0_aus_cmn_shm_vreg_trim: efuse@434,4 { + reg = <0x434 4>; + bits = <4 5>; + }; + + atcphy0_cio3pll_dco_coarsebin0: efuse@434,9 { + reg = <0x434 4>; + bits = <9 6>; + }; + + atcphy0_cio3pll_dco_coarsebin1: efuse@434,15 { + reg = <0x434 4>; + bits = <15 6>; + }; + + atcphy0_cio3pll_dll_start_capcode: efuse@434,21 { + reg = <0x434 4>; + bits = <21 2>; + }; + + atcphy0_cio3pll_dtc_vreg_adjust: efuse@434,23 { + reg = <0x434 0x4>; + bits = <23 3>; + }; + + atcphy1_auspll_rodco_bias_adjust: efuse@438,4 { + reg = <0x438 4>; + bits = <4 3>; + }; + + atcphy1_auspll_rodco_encap: efuse@438,7 { + reg = <0x438 4>; + bits = <7 2>; + }; + + atcphy1_auspll_dtc_vreg_adjust: efuse@438,9 { + reg = <0x438 4>; + bits = <9 3>; + }; + + atcphy1_auspll_fracn_dll_start_capcode: efuse@438,12 { + reg = <0x438 4>; + bits = <12 2>; + }; + + atcphy1_aus_cmn_shm_vreg_trim: efuse@438,14 { + reg = <0x438 4>; + bits = <14 5>; + }; + + atcphy1_cio3pll_dco_coarsebin0: efuse@438,19 { + reg = <0x438 4>; + bits = <19 6>; + }; + + atcphy1_cio3pll_dco_coarsebin1: efuse@438,25 { + reg = <0x438 4>; + bits = <25 6>; + }; + + atcphy1_cio3pll_dll_start_capcode: efuse@438,31 { + reg = <0x438 4>; + bits = <31 1>; + }; + + atcphy1_cio3pll_dll_start_capcode_workaround: efuse@43c,0 { + reg = <0x43c 0x4>; + bits = <0 1>; + }; + + atcphy1_cio3pll_dtc_vreg_adjust: efuse@43c,1 { + reg = <0x43c 0x4>; + bits = <1 3>; + }; + }; + + dwc3_0: usb@382280000 { + compatible = "apple,t8103-dwc3"; + reg = <0x3 0x82280000 0x0 0xcd00>, <0x3 0x8228cd00 0x0 0x3200>; + reg-names = "dwc3-core", "dwc3-apple"; + interrupt-parent = <&aic>; + interrupts = ; + dr_mode = "otg"; + usb-role-switch; + role-switch-default-mode = "host"; + iommus = <&dwc3_0_dart_0 0>, <&dwc3_0_dart_1 1>; + power-domains = <&ps_atc0_usb>; + resets = <&atcphy0>; + phys = <&atcphy0 PHY_TYPE_USB2>, <&atcphy0 PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + }; + + dwc3_0_dart_0: iommu@382f00000 { + compatible = "apple,t8103-dart"; + reg = <0x3 0x82f00000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + #iommu-cells = <1>; + power-domains = <&ps_atc0_usb>; + }; + + dwc3_0_dart_1: iommu@382f80000 { + compatible = "apple,t8103-dart"; + reg = <0x3 0x82f80000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + #iommu-cells = <1>; + power-domains = <&ps_atc0_usb>; + }; + + atcphy0: phy@383000000 { + compatible = "apple,t8103-atcphy"; + reg = <0x3 0x83000000 0x0 0x4c000>, + <0x3 0x83050000 0x0 0x8000>, + <0x3 0x80000000 0x0 0x4000>, + <0x3 0x82a90000 0x0 0x4000>, + <0x3 0x82a84000 0x0 0x4000>; + reg-names = "core", "lpdptx", "axi2af", "usb2phy", + "pipehandler"; + + #phy-cells = <1>; + #reset-cells = <0>; + + nvmem-cells = <&atcphy0_aus_cmn_shm_vreg_trim>, + <&atcphy0_auspll_rodco_encap>, + <&atcphy0_auspll_rodco_bias_adjust>, + <&atcphy0_auspll_fracn_dll_start_capcode>, + <&atcphy0_auspll_dtc_vreg_adjust>, + <&atcphy0_cio3pll_dco_coarsebin0>, + <&atcphy0_cio3pll_dco_coarsebin1>, + <&atcphy0_cio3pll_dll_start_capcode>, + <&atcphy0_cio3pll_dtc_vreg_adjust>; + nvmem-cell-names = "aus_cmn_shm_vreg_trim", + "auspll_rodco_encap", + "auspll_rodco_bias_adjust", + "auspll_fracn_dll_start_capcode", + "auspll_dtc_vreg_adjust", + "cio3pll_dco_coarsebin0", + "cio3pll_dco_coarsebin1", + "cio3pll_dll_start_capcode", + "cio3pll_dtc_vreg_adjust"; + + orientation-switch; + mode-switch; + power-domains = <&ps_atc0_usb>; + }; + + atcphy0_xbar: mux@38304c000 { + compatible = "apple,t8103-display-crossbar"; + reg = <0x3 0x8304c000 0x0 0x4000>; + #mux-control-cells = <1>; + power-domains = <&ps_atc0_usb>; + }; + + dwc3_1: usb@502280000 { + compatible = "apple,t8103-dwc3"; + reg = <0x5 0x02280000 0x0 0xcd00>, <0x5 0x0228cd00 0x0 0x3200>; + reg-names = "dwc3-core", "dwc3-apple"; + interrupt-parent = <&aic>; + interrupts = ; + dr_mode = "otg"; + usb-role-switch; + role-switch-default-mode = "host"; + iommus = <&dwc3_1_dart_0 0>, <&dwc3_1_dart_1 1>; + power-domains = <&ps_atc1_usb>; + resets = <&atcphy1>; + phys = <&atcphy1 PHY_TYPE_USB2>, <&atcphy1 PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + }; + + dwc3_1_dart_0: iommu@502f00000 { + compatible = "apple,t8103-dart"; + reg = <0x5 0x02f00000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + #iommu-cells = <1>; + power-domains = <&ps_atc1_usb>; + }; + + dwc3_1_dart_1: iommu@502f80000 { + compatible = "apple,t8103-dart"; + reg = <0x5 0x02f80000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + #iommu-cells = <1>; + power-domains = <&ps_atc1_usb>; + }; + + atcphy1: phy@503000000 { + compatible = "apple,t8103-atcphy"; + reg = <0x5 0x03000000 0x0 0x4c000>, + <0x5 0x03050000 0x0 0x8000>, + <0x5 0x0 0x0 0x4000>, + <0x5 0x02a90000 0x0 0x4000>, + <0x5 0x02a84000 0x0 0x4000>; + reg-names = "core", "lpdptx", "axi2af", "usb2phy", + "pipehandler"; + + nvmem-cells = <&atcphy1_aus_cmn_shm_vreg_trim>, + <&atcphy1_auspll_rodco_encap>, + <&atcphy1_auspll_rodco_bias_adjust>, + <&atcphy1_auspll_fracn_dll_start_capcode>, + <&atcphy1_auspll_dtc_vreg_adjust>, + <&atcphy1_cio3pll_dco_coarsebin0>, + <&atcphy1_cio3pll_dco_coarsebin1>, + <&atcphy1_cio3pll_dll_start_capcode>, + <&atcphy1_cio3pll_dtc_vreg_adjust>, + <&atcphy1_cio3pll_dll_start_capcode_workaround>; + nvmem-cell-names = "aus_cmn_shm_vreg_trim", + "auspll_rodco_encap", + "auspll_rodco_bias_adjust", + "auspll_fracn_dll_start_capcode", + "auspll_dtc_vreg_adjust", + "cio3pll_dco_coarsebin0", + "cio3pll_dco_coarsebin1", + "cio3pll_dll_start_capcode", + "cio3pll_dtc_vreg_adjust", + "cio3pll_dll_start_capcode_workaround"; + + #phy-cells = <1>; + #reset-cells = <0>; + + orientation-switch; + mode-switch; + power-domains = <&ps_atc1_usb>; + }; + + atcphy1_xbar: mux@50304c000 { + compatible = "apple,t8103-display-crossbar"; + reg = <0x5 0x0304c000 0x0 0x4000>; + #mux-control-cells = <1>; + power-domains = <&ps_atc1_usb>; + }; + pcie0_dart_0: iommu@681008000 { compatible = "apple,t8103-dart"; reg = <0x6 0x81008000 0x0 0x4000>; @@ -1072,6 +1843,8 @@ pinctrl-0 = <&pcie_pins>; pinctrl-names = "default"; + dma-coherent; + port00: pci@0,0 { device_type = "pci"; reg = <0x0 0x0 0x0 0x0 0x0>; diff --git a/arch/arm64/boot/dts/apple/t8112-j413.dts b/arch/arm64/boot/dts/apple/t8112-j413.dts index 6f69658623bf89..20285be747d965 100644 --- a/arch/arm64/boot/dts/apple/t8112-j413.dts +++ b/arch/arm64/boot/dts/apple/t8112-j413.dts @@ -16,9 +16,11 @@ / { compatible = "apple,j413", "apple,t8112", "apple,arm-platform"; model = "Apple MacBook Air (13-inch, M2, 2022)"; + chassis-type = "laptop"; aliases { bluetooth0 = &bluetooth0; + keyboard = &keyboard; wifi0 = &wifi0; }; @@ -35,6 +37,21 @@ }; }; +&dcp { + panel: panel { + compatible = "apple,panel-j413", "apple,panel"; + width-mm = <290>; + height-mm = <189>; + adj-height-mm = <181>; + apple,max-brightness = <525>; + }; +}; + +&framebuffer0 { + panel = <&panel>; + post-init-providers = <&panel>; +}; + /* * Force the bus number assignments so that we can declare some of the * on-board devices and properties that are populated by the bootloader @@ -42,6 +59,7 @@ */ &port00 { bus-range = <1 1>; + pwren-gpios = <&smc_gpio 13 GPIO_ACTIVE_HIGH>; wifi0: wifi@0,0 { compatible = "pci14e4,4433"; reg = <0x10000 0x0 0x0 0x0 0x0>; @@ -60,6 +78,18 @@ }; }; +/* + * Provide labels for the USB type C ports. + */ + +&typec0 { + label = "USB-C Left-back"; +}; + +&typec1 { + label = "USB-C Left-front"; +}; + &i2c0 { /* MagSafe port */ hpm5: usb-pd@3a { @@ -71,6 +101,76 @@ }; }; +/* Virtual regulator representing the shared shutdown GPIO */ +/ { + speaker_sdz: fixed-regulator-sn012776-sdz { + compatible = "regulator-fixed"; + regulator-name = "sn012776-sdz"; + startup-delay-us = <5000>; + gpios = <&pinctrl_ap 88 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; +}; + +&i2c1 { + speaker_left_woof: codec@38 { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x38>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Left Woofer"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <0>; + ti,vmon-slot-no = <2>; + ti,sdout-force-zero-mask = <0xf0f0>; + }; + + speaker_left_tweet: codec@39 { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x39>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Left Tweeter"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <8>; + ti,vmon-slot-no = <10>; + }; +}; + +&i2c3 { + speaker_right_woof: codec@3b { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x3b>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Right Woofer"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <4>; + ti,vmon-slot-no = <6>; + ti,sdout-force-zero-mask = <0x0f0f>; + }; + + speaker_right_tweet: codec@3c { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x3c>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Right Tweeter"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <12>; + ti,vmon-slot-no = <14>; + }; + + jack_codec: codec@4b { + compatible = "cirrus,cs42l84"; + reg = <0x4b>; + reset-gpios = <&pinctrl_nub 12 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + interrupts-extended = <&pinctrl_ap 149 IRQ_TYPE_LEVEL_LOW>; + sound-name-prefix = "Jack"; + }; +}; + &i2c4 { status = "okay"; }; @@ -78,3 +178,98 @@ &fpwm1 { status = "okay"; }; + +&aop_mbox { + status = "okay"; +}; + +&aop_dart { + status = "okay"; +}; + +&aop_admac { + status = "okay"; +}; + +&aop { + status = "okay"; +}; + +&aop_audio { + apple,chassis-name = "J413"; + apple,machine-kind = "MacBook Air"; +}; + +/ { + sound { + compatible = "apple,j413-macaudio", "apple,macaudio"; + model = "MacBook Air J413"; + + dai-link@0 { + link-name = "Speakers"; + + cpu { + sound-dai = <&mca 0>, <&mca 1>; + }; + codec { + sound-dai = <&speaker_left_woof>, <&speaker_left_tweet>, + <&speaker_right_woof>, <&speaker_right_tweet>; + }; + }; + + dai-link@1 { + link-name = "Headphone Jack"; + + cpu { + sound-dai = <&mca 2>; + }; + codec { + sound-dai = <&jack_codec>; + }; + }; + }; +}; + +&mtp { + status = "okay"; +}; +&mtp_mbox { + status = "okay"; +}; +&mtp_dart { + status = "okay"; +}; +&mtp_dockchannel { + status = "okay"; +}; +&mtp_hid { + apple,afe-reset-gpios = <&smc_gpio 8 GPIO_ACTIVE_LOW>; + apple,stm-reset-gpios = <&smc_gpio 24 GPIO_ACTIVE_LOW>; + + multi-touch { + firmware-name = "apple/tpmtfw-j413.bin"; + }; + + keyboard: keyboard { + hid-country-code = <0>; + apple,keyboard-layout-id = <0>; + }; + + stm { + }; + + actuator { + }; + + tp_accel { + }; +}; + +#include "isp-imx558-cfg0.dtsi" + +&isp { + apple,platform-id = <14>; + apple,temporal-filter = <1>; +}; + +#include "hwmon-laptop.dtsi" diff --git a/arch/arm64/boot/dts/apple/t8112-j415.dts b/arch/arm64/boot/dts/apple/t8112-j415.dts index b54e218e5384ca..c2c32ca5577eff 100644 --- a/arch/arm64/boot/dts/apple/t8112-j415.dts +++ b/arch/arm64/boot/dts/apple/t8112-j415.dts @@ -16,9 +16,11 @@ / { compatible = "apple,j415", "apple,t8112", "apple,arm-platform"; model = "Apple MacBook Air (15-inch, M2, 2023)"; + chassis-type = "laptop"; aliases { bluetooth0 = &bluetooth0; + keyboard = &keyboard; wifi0 = &wifi0; }; @@ -35,6 +37,21 @@ }; }; +&dcp { + panel: panel { + compatible = "apple,panel-j415", "apple,panel"; + width-mm = <327>; + height-mm = <211>; + adj-height-mm = <204>; + apple,max-brightness = <500>; + }; +}; + +&framebuffer0 { + panel = <&panel>; + post-init-providers = <&panel>; +}; + /* * Force the bus number assignments so that we can declare some of the * on-board devices and properties that are populated by the bootloader @@ -42,6 +59,7 @@ */ &port00 { bus-range = <1 1>; + pwren-gpios = <&smc_gpio 13 GPIO_ACTIVE_HIGH>; wifi0: wifi@0,0 { compatible = "pci14e4,4433"; reg = <0x10000 0x0 0x0 0x0 0x0>; @@ -60,6 +78,18 @@ }; }; +/* + * Provide labels for the USB type C ports. + */ + +&typec0 { + label = "USB-C Left-back"; +}; + +&typec1 { + label = "USB-C Left-front"; +}; + &i2c0 { /* MagSafe port */ hpm5: usb-pd@3a { @@ -71,6 +101,98 @@ }; }; +/* Virtual regulator representing the shared shutdown GPIO */ +/ { + speaker_sdz: fixed-regulator-sn012776-sdz { + compatible = "regulator-fixed"; + regulator-name = "sn012776-sdz"; + startup-delay-us = <5000>; + gpios = <&pinctrl_ap 88 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; +}; + +&i2c1 { + speaker_left_woof1: codec@38 { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x38>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Left Woofer 1"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <0>; + ti,vmon-slot-no = <2>; + ti,sdout-force-zero-mask = <0xf0f0f0>; + }; + + speaker_left_tweet: codec@39 { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x39>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Left Tweeter"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <8>; + ti,vmon-slot-no = <10>; + }; + + speaker_left_woof2: codec@3a { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x3a>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Left Woofer 2"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <16>; + ti,vmon-slot-no = <18>; + }; +}; + +&i2c3 { + speaker_right_woof1: codec@3b { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x3b>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Right Woofer 1"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <4>; + ti,vmon-slot-no = <6>; + ti,sdout-force-zero-mask = <0x0f0f0f>; + }; + + speaker_right_tweet: codec@3c { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x3c>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Right Tweeter"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <12>; + ti,vmon-slot-no = <14>; + }; + + speaker_right_woof2: codec@3d { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x3d>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Right Woofer 2"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <20>; + ti,vmon-slot-no = <22>; + }; + + jack_codec: codec@4b { + compatible = "cirrus,cs42l84"; + reg = <0x4b>; + reset-gpios = <&pinctrl_nub 12 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + interrupts-extended = <&pinctrl_ap 149 IRQ_TYPE_LEVEL_LOW>; + sound-name-prefix = "Jack"; + }; +}; + &i2c4 { status = "okay"; }; @@ -78,3 +200,102 @@ &fpwm1 { status = "okay"; }; + +&aop_mbox { + status = "okay"; +}; + +&aop_dart { + status = "okay"; +}; + +&aop_admac { + status = "okay"; +}; + +&aop { + status = "okay"; +}; + +&aop_audio { + apple,chassis-name = "J415"; + apple,machine-kind = "MacBook Air"; +}; + +/ { + sound { + compatible = "apple,j415-macaudio", "apple,macaudio"; + model = "MacBook Air J415"; + + dai-link@0 { + link-name = "Speakers"; + + cpu { + sound-dai = <&mca 0>, <&mca 1>; + }; + codec { + sound-dai = <&speaker_left_woof1>, + <&speaker_left_tweet>, + <&speaker_left_woof2>, + <&speaker_right_woof1>, + <&speaker_right_tweet>, + <&speaker_right_woof2>; + }; + }; + + dai-link@1 { + link-name = "Headphone Jack"; + + cpu { + sound-dai = <&mca 2>; + }; + codec { + sound-dai = <&jack_codec>; + }; + }; + }; +}; + +&mtp { + status = "okay"; +}; +&mtp_mbox { + status = "okay"; +}; +&mtp_dart { + status = "okay"; +}; +&mtp_dockchannel { + status = "okay"; +}; +&mtp_hid { + apple,afe-reset-gpios = <&smc_gpio 8 GPIO_ACTIVE_LOW>; + apple,stm-reset-gpios = <&smc_gpio 24 GPIO_ACTIVE_LOW>; + + multi-touch { + firmware-name = "apple/tpmtfw-j415.bin"; + }; + + keyboard: keyboard { + hid-country-code = <0>; + apple,keyboard-layout-id = <0>; + }; + + stm { + }; + + actuator { + }; + + tp_accel { + }; +}; + +#include "isp-imx558-cfg0.dtsi" + +&isp { + apple,platform-id = <15>; + apple,temporal-filter = <1>; +}; + +#include "hwmon-laptop.dtsi" diff --git a/arch/arm64/boot/dts/apple/t8112-j473.dts b/arch/arm64/boot/dts/apple/t8112-j473.dts index 06fe257f08be49..4fc96779806ea3 100644 --- a/arch/arm64/boot/dts/apple/t8112-j473.dts +++ b/arch/arm64/boot/dts/apple/t8112-j473.dts @@ -15,12 +15,85 @@ / { compatible = "apple,j473", "apple,t8112", "apple,arm-platform"; model = "Apple Mac mini (M2, 2023)"; + chassis-type = "desktop"; aliases { + bluetooth0 = &bluetooth0; + /delete-property/ dcp; + dcpext = &dcpext; ethernet0 = ðernet0; + sio = &sio; + wifi0 = &wifi0; }; }; +&framebuffer0 { + power-domains = <&ps_dispext_cpu0>, <&ps_dptx_ext_phy>; +}; + +&dptxphy { + status = "okay"; +}; + +&dcp { + status = "disabled"; +}; + +&display { + iommus = <&dispext0_dart 0>; +}; +&dispext0_dart { + status = "okay"; +}; +&dcpext_dart { + status = "okay"; +}; +&dcpext_mbox { + status = "okay"; +}; +&dcpext { + status = "okay"; + apple,connector-type = "HDMI-A"; + + /* HDMI HPD gpio, used as interrupt*/ + hdmi-hpd-gpios = <&pinctrl_aop 49 GPIO_ACTIVE_HIGH>; + + hdmi-pwren-gpios = <&smc_gpio 21 GPIO_ACTIVE_HIGH>; + dp2hdmi-pwren-gpios = <&smc_gpio 22 GPIO_ACTIVE_HIGH>; + + phys = <&dptxphy>; + phy-names = "dp-phy"; + apple,dptx-phy = <5>; +}; + +/* remove once m1n1 enables sio nodes after setup */ +&sio { + status = "okay"; +}; + +&dpaudio1 { + status = "okay"; +}; + +/* + * Keep the power-domains used for the HDMI port on. + */ +&framebuffer0 { + power-domains = <&ps_dispext_cpu0>, <&ps_dptx_ext_phy>; +}; + +/* + * The M2 Mac mini uses dispext for the HDMI output so it's not necessary to + * keep disp0 power-domains always-on. + */ +&ps_disp0_sys { + /delete-property/ apple,always-on; +}; + +&ps_disp0_fe { + /delete-property/ apple,always-on; +}; + /* * Force the bus number assignments so that we can declare some of the * on-board devices and properties that are populated by the bootloader @@ -28,10 +101,28 @@ */ &port00 { bus-range = <1 1>; + pwren-gpios = <&smc_gpio 13 GPIO_ACTIVE_HIGH>; + wifi0: wifi@0,0 { + compatible = "pci14e4,4434"; + reg = <0x10000 0x0 0x0 0x0 0x0>; + /* To be filled by the loader */ + local-mac-address = [00 10 18 00 00 10]; + apple,antenna-sku = "XX"; + brcm,board-type = "apple,miyake"; + }; + + bluetooth0: bluetooth@0,1 { + compatible = "pci14e4,5f72"; + reg = <0x10100 0x0 0x0 0x0 0x0>; + /* To be filled by the loader */ + local-bd-address = [00 00 00 00 00 00]; + brcm,board-type = "apple,miyake"; + }; }; &port01 { bus-range = <2 2>; + pwren-gpios = <&smc_gpio 24 GPIO_ACTIVE_HIGH>; status = "okay"; }; @@ -52,3 +143,75 @@ &pcie2_dart { status = "okay"; }; + +/* + * Provide labels for the USB type C ports. + */ + +&typec0 { + label = "USB-C Back-left"; +}; + +&typec1 { + label = "USB-C Back-right"; +}; + +&i2c1 { + speaker_amp: codec@38 { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x38>; + shutdown-gpios = <&pinctrl_ap 88 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + interrupt-parent = <&pinctrl_ap>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <0>; + ti,vmon-slot-no = <2>; + }; + + jack_codec: codec@4b { + compatible = "cirrus,cs42l84"; + reg = <0x4b>; + reset-gpios = <&pinctrl_nub 12 GPIO_ACTIVE_HIGH>; + interrupt-parent = <&pinctrl_ap>; + interrupts = <149 IRQ_TYPE_LEVEL_LOW>; + #sound-dai-cells = <0>; + cirrus,ts-inv = <1>; + sound-name-prefix = "Jack"; + }; +}; + +/ { + sound { + compatible = "apple,j473-macaudio", "apple,macaudio"; + model = "Mac mini J473"; + + dai-link@0 { + link-name = "Speaker"; + + cpu { + sound-dai = <&mca 0>; + }; + codec { + sound-dai = <&speaker_amp>; + }; + }; + + dai-link@1 { + link-name = "Headphone Jack"; + + cpu { + sound-dai = <&mca 2>; + }; + codec { + sound-dai = <&jack_codec>; + }; + }; + + }; +}; + +&gpu { + apple,perf-base-pstate = <3>; +}; + +#include "hwmon-mini.dtsi" diff --git a/arch/arm64/boot/dts/apple/t8112-j493.dts b/arch/arm64/boot/dts/apple/t8112-j493.dts index fb8ad7d4c65a8f..368c4a9cc01758 100644 --- a/arch/arm64/boot/dts/apple/t8112-j493.dts +++ b/arch/arm64/boot/dts/apple/t8112-j493.dts @@ -16,6 +16,7 @@ / { compatible = "apple,j493", "apple,t8112", "apple,arm-platform"; model = "Apple MacBook Pro (13-inch, M2, 2022)"; + chassis-type = "laptop"; /* * All of those are used by the bootloader to pass calibration @@ -23,6 +24,7 @@ */ aliases { bluetooth0 = &bluetooth0; + keyboard = &keyboard; touchbar0 = &touchbar0; wifi0 = &wifi0; }; @@ -50,6 +52,20 @@ apple,always-on; }; +&dcp { + panel: panel { + compatible = "apple,panel-j493", "apple,panel"; + width-mm = <286>; + height-mm = <179>; + apple,max-brightness = <525>; + }; +}; + +&framebuffer0 { + panel = <&panel>; + post-init-providers = <&panel>; +}; + &display_dfr { status = "okay"; }; @@ -90,6 +106,7 @@ */ &port00 { bus-range = <1 1>; + pwren-gpios = <&smc_gpio 13 GPIO_ACTIVE_HIGH>; wifi0: wifi@0,0 { compatible = "pci14e4,4425"; reg = <0x10000 0x0 0x0 0x0 0x0>; @@ -108,6 +125,88 @@ }; }; +/* + * Provide labels for the USB type C ports. + */ + +&typec0 { + label = "USB-C Left-back"; +}; + +&typec1 { + label = "USB-C Left-front"; +}; + +/* Virtual regulator representing the shared shutdown GPIO */ +/ { + speaker_sdz: fixed-regulator-sn012776-sdz { + compatible = "regulator-fixed"; + regulator-name = "sn012776-sdz"; + startup-delay-us = <5000>; + gpios = <&pinctrl_ap 88 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; +}; + +&i2c1 { + speaker_left_rear: codec@38 { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x38>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Left Rear"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <8>; + ti,vmon-slot-no = <10>; + }; + + speaker_left_front: codec@39 { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x39>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Left Front"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <0>; + ti,vmon-slot-no = <2>; + ti,sdout-force-zero-mask = <0xf0f0>; + }; +}; + +&i2c3 { + speaker_right_rear: codec@3b { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x3b>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Right Rear"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <12>; + ti,vmon-slot-no = <14>; + }; + + speaker_right_front: codec@3c { + compatible = "ti,sn012776", "ti,tas2764"; + reg = <0x3c>; + SDZ-supply = <&speaker_sdz>; + #sound-dai-cells = <0>; + sound-name-prefix = "Right Front"; + interrupts-extended = <&pinctrl_ap 11 IRQ_TYPE_LEVEL_LOW>; + ti,imon-slot-no = <4>; + ti,vmon-slot-no = <6>; + ti,sdout-force-zero-mask = <0x0f0f>; + }; + + jack_codec: codec@4b { + compatible = "cirrus,cs42l84"; + reg = <0x4b>; + reset-gpios = <&pinctrl_nub 12 GPIO_ACTIVE_HIGH>; + #sound-dai-cells = <0>; + interrupts-extended = <&pinctrl_ap 149 IRQ_TYPE_LEVEL_LOW>; + sound-name-prefix = "Jack"; + }; +}; + &i2c4 { status = "okay"; }; @@ -133,3 +232,98 @@ touchscreen-inverted-y; }; }; + +&aop_mbox { + status = "okay"; +}; + +&aop_dart { + status = "okay"; +}; + +&aop_admac { + status = "okay"; +}; + +&aop { + status = "okay"; +}; + +&aop_audio { + apple,chassis-name = "J493"; + apple,machine-kind = "MacBook Pro"; +}; + +/ { + sound { + compatible = "apple,j493-macaudio", "apple,macaudio"; + model = "MacBook Pro J493"; + + dai-link@0 { + link-name = "Speakers"; + + cpu { + sound-dai = <&mca 0>, <&mca 1>; + }; + codec { + sound-dai = <&speaker_left_front>, <&speaker_left_rear>, + <&speaker_right_front>, <&speaker_right_rear>; + }; + }; + + dai-link@1 { + link-name = "Headphone Jack"; + + cpu { + sound-dai = <&mca 2>; + }; + codec { + sound-dai = <&jack_codec>; + }; + }; + }; +}; + +&mtp { + status = "okay"; +}; +&mtp_mbox { + status = "okay"; +}; +&mtp_dart { + status = "okay"; +}; +&mtp_dockchannel { + status = "okay"; +}; +&mtp_hid { + apple,afe-reset-gpios = <&smc_gpio 8 GPIO_ACTIVE_LOW>; + apple,stm-reset-gpios = <&smc_gpio 24 GPIO_ACTIVE_LOW>; + + multi-touch { + firmware-name = "apple/tpmtfw-j493.bin"; + }; + + keyboard: keyboard { + hid-country-code = <0>; + apple,keyboard-layout-id = <0>; + }; + + stm { + }; + + actuator { + }; + + tp_accel { + }; +}; + +#include "isp-imx248.dtsi" + +&isp { + apple,platform-id = <6>; +}; + +#include "hwmon-fan.dtsi" +#include "hwmon-laptop.dtsi" diff --git a/arch/arm64/boot/dts/apple/t8112-jxxx.dtsi b/arch/arm64/boot/dts/apple/t8112-jxxx.dtsi index 6da35496a4c88d..fb957f785d82c5 100644 --- a/arch/arm64/boot/dts/apple/t8112-jxxx.dtsi +++ b/arch/arm64/boot/dts/apple/t8112-jxxx.dtsi @@ -11,6 +11,11 @@ / { aliases { + atcphy0 = &atcphy0; + atcphy1 = &atcphy1; + dcp = &dcp; + disp0 = &display; + disp0_piodma = &disp0_piodma; serial0 = &serial0; serial2 = &serial2; }; @@ -25,6 +30,7 @@ framebuffer0: framebuffer@0 { compatible = "apple,simple-framebuffer", "simple-framebuffer"; reg = <0 0 0 0>; /* To be filled by loader */ + power-domains = <&ps_disp0_cpu0>; /* Format properties will be added by loader */ status = "disabled"; }; @@ -53,6 +59,29 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <8 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec0: connector { + compatible = "usb-c-connector"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec0_connector_hs: endpoint { + remote-endpoint = <&dwc3_0_hs>; + }; + }; + port@1 { + reg = <1>; + typec0_connector_ss: endpoint { + remote-endpoint = <&atcphy0_typec_lanes>; + }; + }; + }; + }; }; hpm1: usb-pd@3f { @@ -61,6 +90,115 @@ interrupt-parent = <&pinctrl_ap>; interrupts = <8 IRQ_TYPE_LEVEL_LOW>; interrupt-names = "irq"; + + typec1: connector { + compatible = "usb-c-connector"; + power-role = "dual"; + data-role = "dual"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + typec1_connector_hs: endpoint { + remote-endpoint = <&dwc3_1_hs>; + }; + }; + port@1 { + reg = <1>; + typec1_connector_ss: endpoint { + remote-endpoint = <&atcphy1_typec_lanes>; + }; + }; + }; + }; + }; +}; + +/* USB controllers */ +&dwc3_0 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_0_hs: endpoint { + remote-endpoint = <&typec0_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_0_ss: endpoint { + remote-endpoint = <&atcphy0_usb3>; + }; + }; + }; +}; + +&dwc3_1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dwc3_1_hs: endpoint { + remote-endpoint = <&typec1_connector_hs>; + }; + }; + + port@1 { + reg = <1>; + dwc3_1_ss: endpoint { + remote-endpoint = <&atcphy1_usb3>; + }; + }; + }; +}; + +/* Type-C PHYs */ +&atcphy0 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy0_typec_lanes: endpoint { + remote-endpoint = <&typec0_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy0_usb3: endpoint { + remote-endpoint = <&dwc3_0_ss>; + }; + }; + }; +}; + +&atcphy1 { + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + atcphy1_typec_lanes: endpoint { + remote-endpoint = <&typec1_connector_ss>; + }; + }; + + port@1 { + reg = <1>; + atcphy1_usb3: endpoint { + remote-endpoint = <&dwc3_1_ss>; + }; + }; }; }; @@ -80,4 +218,6 @@ clock-frequency = <900000000>; }; +#include "hwmon-common.dtsi" + #include "spi1-nvram.dtsi" diff --git a/arch/arm64/boot/dts/apple/t8112-pmgr.dtsi b/arch/arm64/boot/dts/apple/t8112-pmgr.dtsi index 7c050c6f2707a1..ab8ec9bd4e4401 100644 --- a/arch/arm64/boot/dts/apple/t8112-pmgr.dtsi +++ b/arch/arm64/boot/dts/apple/t8112-pmgr.dtsi @@ -176,7 +176,7 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = "sio_cpu"; - power-domains = <&ps_sio>; + power-domains = <&ps_sio &ps_uart_p &ps_spi_p &ps_dpa0>; }; ps_fpwm0: power-controller@1c8 { @@ -465,6 +465,7 @@ #reset-cells = <0>; label = "mca0"; power-domains = <&ps_sio_adma>, <&ps_audio_p>; + apple,externally-clocked; }; ps_mca1: power-controller@2c8 { @@ -474,6 +475,7 @@ #reset-cells = <0>; label = "mca1"; power-domains = <&ps_sio_adma>, <&ps_audio_p>; + apple,externally-clocked; }; ps_mca2: power-controller@2d0 { @@ -483,6 +485,7 @@ #reset-cells = <0>; label = "mca2"; power-domains = <&ps_sio_adma>, <&ps_audio_p>; + apple,externally-clocked; }; ps_mca3: power-controller@2d8 { @@ -492,6 +495,7 @@ #reset-cells = <0>; label = "mca3"; power-domains = <&ps_sio_adma>, <&ps_audio_p>; + apple,externally-clocked; }; ps_mca4: power-controller@2e0 { @@ -501,6 +505,7 @@ #reset-cells = <0>; label = "mca4"; power-domains = <&ps_sio_adma>, <&ps_audio_p>; + apple,externally-clocked; }; ps_mca5: power-controller@2e8 { @@ -510,6 +515,7 @@ #reset-cells = <0>; label = "mca5"; power-domains = <&ps_sio_adma>, <&ps_audio_p>; + apple,externally-clocked; }; ps_mcc: power-controller@2f0 { @@ -663,7 +669,6 @@ #reset-cells = <0>; label = "disp0_sys"; power-domains = <&ps_rmx1>; - apple,always-on; /* TODO: figure out if we can enable PM here */ }; ps_disp0_fe: power-controller@378 { @@ -672,8 +677,7 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = "disp0_fe"; - power-domains = <&ps_disp0_sys>; - apple,always-on; /* TODO: figure out if we can enable PM here */ + power-domains = <&ps_disp0_sys>, <&ps_pmp>; }; ps_dispext_sys: power-controller@380 { @@ -691,7 +695,7 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = "dispext_fe"; - power-domains = <&ps_dispext_sys>; + power-domains = <&ps_dispext_sys>, <&ps_pmp>; }; ps_dispext_cpu0: power-controller@3c8 { @@ -773,7 +777,6 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = "pmp"; - apple,always-on; }; ps_pms_sram: power-controller@418 { @@ -818,6 +821,7 @@ #reset-cells = <0>; label = "isp_sys"; power-domains = <&ps_rmx1>; + status = "disabled"; }; ps_venc_sys: power-controller@440 { @@ -964,6 +968,123 @@ apple,always-on; }; + /* There is a dependency tree involved with these PDs, + * but we do not express it here since the ISP driver + * is supposed to sequence them in the right order anyway + * (and we do not know the exact tree structure). + * + * This also works around spurious parent PD activation + * on machines with ISP disabled (desktops). + */ + ps_isp_set0: power-controller@4000 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4000 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set0"; + apple,force-disable; + }; + + ps_isp_set1: power-controller@4008 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4008 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set1"; + apple,force-disable; + apple,force-reset; + }; + + ps_isp_set2: power-controller@4010 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4010 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set2"; + apple,force-disable; + apple,force-reset; + }; + + ps_isp_fe: power-controller@4018 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4018 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_fe"; + }; + + ps_isp_set4: power-controller@4020 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4020 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set4"; + }; + + ps_isp_set5: power-controller@4028 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4028 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set5"; + }; + + ps_isp_set6: power-controller@4030 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4030 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set6"; + }; + + ps_isp_set7: power-controller@4038 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4038 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set7"; + }; + + ps_isp_set8: power-controller@4040 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4040 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set8"; + }; + + ps_isp_set9: power-controller@4048 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4048 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set9"; + }; + + ps_isp_set12: power-controller@4050 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4050 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set10"; + }; + + ps_isp_set10: power-controller@4058 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4058 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set11"; + }; + + ps_isp_set11: power-controller@4060 { + compatible = "apple,t8103-pmgr-pwrstate", "apple,pmgr-pwrstate"; + reg = <0x4060 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_set12"; + }; + ps_venc_dma: power-controller@8000 { compatible = "apple,t8112-pmgr-pwrstate", "apple,pmgr-pwrstate"; reg = <0x8000 4>; @@ -1064,6 +1185,7 @@ #power-domain-cells = <0>; #reset-cells = <0>; label = "msg"; + apple,always-on; /* Core AON device? */ }; ps_nub_gpio: power-controller@80 { diff --git a/arch/arm64/boot/dts/apple/t8112.dtsi b/arch/arm64/boot/dts/apple/t8112.dtsi index 3f79878b25af1f..89c902f5289b9e 100644 --- a/arch/arm64/boot/dts/apple/t8112.dtsi +++ b/arch/arm64/boot/dts/apple/t8112.dtsi @@ -11,6 +11,7 @@ #include #include #include +#include #include / { @@ -194,36 +195,43 @@ opp-hz = /bits/ 64 <600000000>; opp-level = <1>; clock-latency-ns = <7500>; + opp-microwatt = <26000>; }; opp02 { opp-hz = /bits/ 64 <912000000>; opp-level = <2>; clock-latency-ns = <20000>; + opp-microwatt = <56000>; }; opp03 { opp-hz = /bits/ 64 <1284000000>; opp-level = <3>; clock-latency-ns = <22000>; + opp-microwatt = <88000>; }; opp04 { opp-hz = /bits/ 64 <1752000000>; opp-level = <4>; clock-latency-ns = <30000>; + opp-microwatt = <155000>; }; opp05 { opp-hz = /bits/ 64 <2004000000>; opp-level = <5>; clock-latency-ns = <35000>; + opp-microwatt = <231000>; }; opp06 { opp-hz = /bits/ 64 <2256000000>; opp-level = <6>; clock-latency-ns = <39000>; + opp-microwatt = <254000>; }; opp07 { opp-hz = /bits/ 64 <2424000000>; opp-level = <7>; clock-latency-ns = <53000>; + opp-microwatt = <351000>; }; }; @@ -235,93 +243,161 @@ opp-hz = /bits/ 64 <660000000>; opp-level = <1>; clock-latency-ns = <9000>; + opp-microwatt = <133000>; }; opp02 { opp-hz = /bits/ 64 <924000000>; opp-level = <2>; clock-latency-ns = <19000>; + opp-microwatt = <212000>; }; opp03 { opp-hz = /bits/ 64 <1188000000>; opp-level = <3>; clock-latency-ns = <22000>; + opp-microwatt = <261000>; }; opp04 { opp-hz = /bits/ 64 <1452000000>; opp-level = <4>; clock-latency-ns = <24000>; + opp-microwatt = <345000>; }; opp05 { opp-hz = /bits/ 64 <1704000000>; opp-level = <5>; clock-latency-ns = <26000>; + opp-microwatt = <441000>; }; opp06 { opp-hz = /bits/ 64 <1968000000>; opp-level = <6>; clock-latency-ns = <28000>; + opp-microwatt = <619000>; }; opp07 { opp-hz = /bits/ 64 <2208000000>; opp-level = <7>; clock-latency-ns = <30000>; + opp-microwatt = <740000>; }; opp08 { opp-hz = /bits/ 64 <2400000000>; opp-level = <8>; clock-latency-ns = <33000>; + opp-microwatt = <855000>; }; opp09 { opp-hz = /bits/ 64 <2568000000>; opp-level = <9>; clock-latency-ns = <34000>; + opp-microwatt = <1006000>; }; opp10 { opp-hz = /bits/ 64 <2724000000>; opp-level = <10>; clock-latency-ns = <36000>; + opp-microwatt = <1217000>; }; opp11 { opp-hz = /bits/ 64 <2868000000>; opp-level = <11>; clock-latency-ns = <41000>; + opp-microwatt = <1534000>; }; opp12 { opp-hz = /bits/ 64 <2988000000>; opp-level = <12>; clock-latency-ns = <42000>; + opp-microwatt = <1714000>; }; opp13 { opp-hz = /bits/ 64 <3096000000>; opp-level = <13>; clock-latency-ns = <44000>; + opp-microwatt = <1877000>; }; opp14 { opp-hz = /bits/ 64 <3204000000>; opp-level = <14>; clock-latency-ns = <46000>; + opp-microwatt = <2159000>; }; - /* Not available until CPU deep sleep is implemented */ -#if 0 opp15 { opp-hz = /bits/ 64 <3324000000>; opp-level = <15>; clock-latency-ns = <62000>; + opp-microwatt = <2393000>; turbo-mode; }; opp16 { opp-hz = /bits/ 64 <3408000000>; opp-level = <16>; clock-latency-ns = <62000>; + opp-microwatt = <2497000>; turbo-mode; }; opp17 { opp-hz = /bits/ 64 <3504000000>; opp-level = <17>; clock-latency-ns = <62000>; + opp-microwatt = <2648000>; turbo-mode; }; -#endif + }; + + gpu_opp: opp-table-gpu { + compatible = "operating-points-v2"; + + /* + * NOTE: The voltage and power values are device-specific and + * must be filled in by the bootloader. + */ + opp00 { + opp-hz = /bits/ 64 <0>; + opp-microvolt = <400000>; + opp-microwatt = <0>; + }; + opp01 { + opp-hz = /bits/ 64 <444000000>; + opp-microvolt = <603000>; + opp-microwatt = <4295000>; + }; + opp02 { + opp-hz = /bits/ 64 <612000000>; + opp-microvolt = <675000>; + opp-microwatt = <6251000>; + }; + opp03 { + opp-hz = /bits/ 64 <808000000>; + opp-microvolt = <710000>; + opp-microwatt = <8625000>; + }; + opp04 { + opp-hz = /bits/ 64 <968000000>; + opp-microvolt = <775000>; + opp-microwatt = <11948000>; + }; + opp05 { + opp-hz = /bits/ 64 <1110000000>; + opp-microvolt = <820000>; + opp-microwatt = <15071000>; + }; + opp06 { + opp-hz = /bits/ 64 <1236000000>; + opp-microvolt = <875000>; + opp-microwatt = <18891000>; + }; + opp07 { + opp-hz = /bits/ 64 <1338000000>; + opp-microvolt = <915000>; + opp-microwatt = <21960000>; + }; + opp08 { + opp-hz = /bits/ 64 <1398000000>; + opp-microvolt = <950000>; + opp-microwatt = <22800000>; + }; }; timer { @@ -370,6 +446,22 @@ clock-output-names = "nco_ref"; }; + /* Pixel clock? frequency in Hz (compare: 4K@60 VGA clock 533.250 MHz) */ + clk_disp0: clock-disp0 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <533333328>; + clock-output-names = "clk_disp0"; + }; + + /* Pixel clock? frequency in Hz (compare: 4K@60 VGA clock 533.250 MHz) */ + clk_dispext0: clock-dispext0 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + clock-output-names = "clk_dispext0"; + }; + reserved-memory { #address-cells = <2>; #size-cells = <2>; @@ -388,15 +480,15 @@ }; uat_handoff: uat-handoff { - status = "disabled"; + reg = <0 0 0 0>; }; uat_pagetables: uat-pagetables { - status = "disabled"; + reg = <0 0 0 0>; }; uat_ttbs: uat-ttbs { - status = "disabled"; + reg = <0 0 0 0>; }; }; @@ -407,9 +499,11 @@ ranges; nonposted-mmio; + /* Required to get >32-bit DMA via DARTs */ + dma-ranges = <0 0 0 0 0xffffffff 0xffffc000>; gpu: gpu@206400000 { - compatible = "apple,agx-g14g"; + compatible = "apple,agx-t8112", "apple,agx-g14g"; reg = <0x2 0x6400000 0 0x40000>, <0x2 0x4000000 0 0x1000000>; reg-names = "asc", "sgx"; @@ -421,6 +515,37 @@ "hw-cal-a", "hw-cal-b", "globals"; apple,firmware-abi = <0 0 0>; + apple,firmware-version = <12 4 0>; + apple,firmware-compat = <12 4 0>; + + operating-points-v2 = <&gpu_opp>; + apple,perf-base-pstate = <1>; + apple,min-sram-microvolt = <780000>; + apple,avg-power-filter-tc-ms = <300>; + apple,avg-power-ki-only = <9.375>; + apple,avg-power-kp = <3.22>; + apple,avg-power-min-duty-cycle = <40>; + apple,avg-power-target-filter-tc = <1>; + apple,fast-die0-integral-gain = <200.0>; + apple,fast-die0-proportional-gain = <5.0>; + apple,perf-boost-ce-step = <50>; + apple,perf-boost-min-util = <90>; + apple,perf-filter-drop-threshold = <0>; + apple,perf-filter-time-constant = <5>; + apple,perf-filter-time-constant2 = <200>; + apple,perf-integral-gain = <5.94>; + apple,perf-integral-gain2 = <5.94>; + apple,perf-integral-min-clamp = <0>; + apple,perf-proportional-gain = <14.85>; + apple,perf-proportional-gain2 = <14.85>; + apple,perf-tgt-utilization = <85>; + apple,power-sample-period = <8>; + apple,ppm-filter-time-constant-ms = <34>; + apple,ppm-ki = <205.0>; + apple,ppm-kp = <0.75>; + apple,pwr-min-duty-cycle = <40>; + apple,core-leak-coef = <1920.0>; + apple,sram-leak-coef = <74.0>; }; agx_mbox: mbox@206408000 { @@ -507,6 +632,140 @@ }; }; + isp_dart0: iommu@22c4a8000 { + compatible = "apple,t8110-dart"; + reg = <0x2 0x2c4a8000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>; + status = "disabled"; + }; + + isp_dart1: iommu@22c4b4000 { + compatible = "apple,t8110-dart"; + reg = <0x2 0x2c4b4000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>; + status = "disabled"; + }; + + isp_dart2: iommu@22c4bc000 { + compatible = "apple,t8110-dart"; + reg = <0x2 0x2c4bc000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>; + status = "disabled"; + }; + + isp: isp@22a000000 { + compatible = "apple,t8112-isp", "apple,isp"; + iommus = <&isp_dart0 0>, <&isp_dart1 0>, <&isp_dart2 0>; + reg-names = "coproc", "mbox", "gpio", "mbox2"; + reg = <0x2 0x2a000000 0x0 0x2000000>, + <0x2 0x2c4c4000 0x0 0x100>, + <0x2 0x2c4c41b0 0x0 0x100>, + <0x2 0x2c4c4430 0x0 0x100>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_isp_sys>, <&ps_isp_set0>, + <&ps_isp_set1>, <&ps_isp_set2>, <&ps_isp_fe>, + <&ps_isp_set4>, <&ps_isp_set5>, <&ps_isp_set6>, + <&ps_isp_set7>, <&ps_isp_set8>, <&ps_isp_set9>, + <&ps_isp_set10>, <&ps_isp_set11>, + <&ps_isp_set12>; + + apple,dart-vm-size = <0x0 0xa0000000>; + status = "disabled"; + }; + + disp0_dart: iommu@231304000 { + compatible = "apple,t8112-dart", "apple,t8110-dart"; + reg = <0x2 0x31304000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_disp0_cpu0>; + apple,dma-range = <0x0 0x0 0xf 0xffff0000>; + status = "disabled"; + }; + + dcp_dart: iommu@23130c000 { + compatible = "apple,t8112-dart", "apple,t8110-dart"; + reg = <0x2 0x3130c000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_disp0_cpu0>; + apple,dma-range = <0x8 0x00000000 0x7 0xffff0000>; + }; + + dcp_mbox: mbox@231c08000 { + compatible = "apple,t8112-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x31c08000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&ps_disp0_cpu0>; + resets = <&ps_disp0_cpu0>; + }; + + dcp: dcp@231c00000 { + compatible = "apple,t8112-dcp", "apple,dcp"; + mboxes = <&dcp_mbox>; + mbox-names = "mbox"; + iommus = <&dcp_dart 5>; + + /* the ADT has 2 additional regs which seems to be unused */ + reg-names = "coproc", "disp-0", "disp-1", "disp-2", "disp-3"; + reg = <0x2 0x31c00000 0x0 0x4000>, + <0x2 0x30000000 0x0 0x61c000>, + <0x2 0x31320000 0x0 0x4000>, + <0x2 0x31344000 0x0 0x4000>, + <0x2 0x31800000 0x0 0x800000>; + apple,bw-scratch = <&pmgr_dcp 0 4 0x5d8>; + power-domains = <&ps_disp0_cpu0>; + resets = <&ps_disp0_cpu0>; + clocks = <&clk_disp0>; + phandle = <&dcp>; + // required bus properties for 'piodma' subdevice + #address-cells = <2>; + #size-cells = <2>; + + disp0_piodma: piodma { + iommus = <&disp0_dart 4>; + phandle = <&disp0_piodma>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dcp_audio: endpoint { + remote-endpoint = <&dpaudio0_dcp>; + }; + }; + }; + }; + + display: display-subsystem { + compatible = "apple,display-subsystem"; + /* disp_dart0 must be 1st since it is locked */ + iommus = <&disp0_dart 0>; + /* generate phandle explicitly for use in loader */ + phandle = <&display>; + }; + sio_dart: iommu@235004000 { compatible = "apple,t8110-dart"; reg = <0x2 0x35004000 0x0 0x4000>; @@ -651,6 +910,32 @@ status = "disabled"; }; + sio_mbox: mbox@236408000 { + compatible = "apple,t8112-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x36408000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&ps_sio_cpu>; + }; + + sio: sio@236400000 { + compatible = "apple,t8112-sio", "apple,sio"; + reg = <0x2 0x36400000 0x0 0x8000>; + dma-channels = <128>; + #dma-cells = <1>; + mboxes = <&sio_mbox>; + iommus = <&sio_dart 0>; + power-domains = <&ps_sio_cpu>; + resets = <&ps_sio>; /* TODO: verify reset does something */ + status = "disabled"; + }; + admac: dma-controller@238200000 { compatible = "apple,t8112-admac", "apple,admac"; reg = <0x2 0x38200000 0x0 0x34000>; @@ -665,6 +950,48 @@ resets = <&ps_audio_p>; }; + dpaudio0: audio-controller@238330000 { + compatible = "apple,t8112-dpaudio", "apple,dpaudio"; + reg = <0x2 0x38330000 0x0 0x4000>; + dmas = <&sio 0x64>; + dma-names = "tx"; + power-domains = <&ps_dpa0>; + reset-domains = <&ps_dpa0>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dpaudio0_dcp: endpoint { + remote-endpoint = <&dcp_audio>; + }; + }; + }; + }; + + dpaudio1: audio-controller@238334000 { + compatible = "apple,t8112-dpaudio", "apple,dpaudio"; + reg = <0x2 0x38334000 0x0 0x4000>; + dmas = <&sio 0x66>; + dma-names = "tx"; + power-domains = <&ps_dpa1>; + reset-domains = <&ps_dpa1>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dpaudio1_dcp: endpoint { + remote-endpoint = <&dcpext_audio>; + }; + }; + }; + }; + mca: i2s@238400000 { compatible = "apple,t8112-mca", "apple,mca"; reg = <0x2 0x38400000 0x0 0x18000>, @@ -736,6 +1063,12 @@ /* child nodes are added in t8103-pmgr.dtsi */ }; + pmgr_dcp: power-management@23b3d0000 { + reg = <0x2 0x3b3d0000 0x0 0x4000>; + reg-names = "dcp-bw-scratch"; + #apple,bw-scratch-cells = <3>; + }; + pinctrl_ap: pinctrl@23c100000 { compatible = "apple,t8112-pinctrl", "apple,pinctrl"; reg = <0x2 0x3c100000 0x0 0x100000>; @@ -804,6 +1137,17 @@ }; }; + dptxphy: phy@23c500000 { + compatible = "apple,t8112-dptx-phy", "apple,dptx-phy"; + reg = <0x2 0x3c500000 0x0 0x4000>, + <0x2 0x3c540000 0x0 0xc000>; + reg-names = "core", "dptx"; + power-domains = <&ps_dptx_ext_phy>; + #phy-cells = <0>; + #reset-cells = <0>; + status = "disabled"; /* only used on j473 */ + }; + pinctrl_nub: pinctrl@23d1f0000 { compatible = "apple,t8112-pinctrl", "apple,pinctrl"; reg = <0x2 0x3d1f0000 0x0 0x4000>; @@ -842,6 +1186,103 @@ interrupts = ; }; + efuse@23d2c8000 { + compatible = "apple,t8112-efuses", "apple,efuses"; + reg = <0x2 0x3d2c8000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <1>; + + atcphy0_auspll_rodco_bias_adjust: efuse@480,20 { + reg = <0x480 4>; + bits = <20 3>; + }; + + atcphy0_auspll_rodco_encap: efuse@480,23 { + reg = <0x480 4>; + bits = <23 2>; + }; + + atcphy0_auspll_dtc_vreg_adjust: efuse@480,25 { + reg = <0x480 4>; + bits = <25 3>; + }; + + atcphy0_auspll_fracn_dll_start_capcode: efuse@480,28 { + reg = <0x480 4>; + bits = <28 2>; + }; + + atcphy0_aus_cmn_shm_vreg_trim: efuse@480,30 { + reg = <0x480 8>; + bits = <30 5>; + }; + + atcphy0_cio3pll_dco_coarsebin0: efuse@484,3 { + reg = <0x484 4>; + bits = <3 6>; + }; + + atcphy0_cio3pll_dco_coarsebin1: efuse@484,9 { + reg = <0x484 4>; + bits = <9 6>; + }; + + atcphy0_cio3pll_dll_start_capcode: efuse@484,15 { + reg = <0x484 4>; + bits = <15 2>; + }; + + atcphy0_cio3pll_dtc_vreg_adjust: efuse@484,17 { + reg = <0x484 0x4>; + bits = <17 3>; + }; + + atcphy1_auspll_rodco_bias_adjust: efuse@484,30 { + reg = <0x484 8>; + bits = <30 3>; + }; + + atcphy1_auspll_rodco_encap: efuse@488,1 { + reg = <0x488 8>; + bits = <1 2>; + }; + + atcphy1_auspll_dtc_vreg_adjust: efuse@488,3 { + reg = <0x488 4>; + bits = <3 3>; + }; + + atcphy1_auspll_fracn_dll_start_capcode: efuse@488,6 { + reg = <0x488 4>; + bits = <6 2>; + }; + + atcphy1_aus_cmn_shm_vreg_trim: efuse@488,8 { + reg = <0x488 4>; + bits = <8 5>; + }; + + atcphy1_cio3pll_dco_coarsebin0: efuse@488,13 { + reg = <0x488 4>; + bits = <13 6>; + }; + + atcphy1_cio3pll_dco_coarsebin1: efuse@488,19 { + reg = <0x488 4>; + bits = <19 6>; + }; + + atcphy1_cio3pll_dll_start_capcode: efuse@488,25 { + reg = <0x488 4>; + bits = <25 2>; + }; + + atcphy1_cio3pll_dtc_vreg_adjust: efuse@488,27 { + reg = <0x488 0x4>; + bits = <27 3>; + }; + }; + nub_spmi: spmi@23d714000 { compatible = "apple,t8112-spmi", "apple,spmi"; reg = <0x2 0x3d714000 0x0 0x100>; @@ -912,12 +1353,22 @@ #gpio-cells = <2>; }; + smc_hwmon: hwmon { + compatible = "apple,smc-hwmon"; + }; + + smc_rtc: rtc { + compatible = "apple,smc-rtc"; + nvmem-cells = <&rtc_offset>; + nvmem-cell-names = "rtc_offset"; + }; + smc_reboot: reboot { compatible = "apple,smc-reboot"; nvmem-cells = <&shutdown_flag>, <&boot_stage>, - <&boot_error_count>, <&panic_count>; + <&boot_error_count>, <&panic_count>, <&pm_setting>; nvmem-cell-names = "shutdown_flag", "boot_stage", - "boot_error_count", "panic_count"; + "boot_error_count", "panic_count", "pm_setting"; }; }; @@ -976,6 +1427,250 @@ ; }; + aop_mbox: mbox@24a408000 { + compatible = "apple,t8112-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x4a408000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + status = "disabled"; + }; + + aop_dart: iommu@24a808000 { + compatible = "apple,t8112-dart", "apple,t8110-dart"; + reg = <0x2 0x4a808000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + status = "disabled"; + }; + + aop_admac: dma-controller@24a980000 { + compatible = "apple,t8112-admac", "apple,admac"; + reg = <0x2 0x4a980000 0x0 0x34000>; + #dma-cells = <1>; + dma-channels = <16>; + interrupts-extended = <0>, + <0>, + <&aic AIC_IRQ 359 IRQ_TYPE_LEVEL_HIGH>, + <0>; + iommus = <&aop_dart 10>; + status = "disabled"; + }; + + aop: aop@24ac00000 { + compatible = "apple,t8112-aop"; + reg = <0x2 0x4ac00000 0x0 0x1e0000>, + <0x2 0x4a400000 0x0 0x6c000>; + mboxes = <&aop_mbox>; + mbox-names = "mbox"; + iommus = <&aop_dart 0>; + + status = "disabled"; + + aop_audio: audio { + compatible = "apple,t8112-aop-audio", "apple,aop-audio"; + dmas = <&aop_admac 1>; + dma-names = "dma"; + }; + + aop_als: als { + compatible = "apple,t8112-aop-als", "apple,aop-als"; + // intentionally empty + }; + + las { + compatible = "apple,t8112-aop-las", "apple,aop-las"; + }; + }; + + mtp: mtp@24e400000 { + compatible = "apple,t8112-mtp", "apple,t8112-rtk-helper-asc4", "apple,mtp", "apple,rtk-helper-asc4"; + reg = <0x2 0x4e400000 0x0 0x4000>, + <0x2 0x4ec00000 0x0 0x100000>; + reg-names = "asc", "sram"; + mboxes = <&mtp_mbox>; + iommus = <&mtp_dart 1>; + #helper-cells = <0>; + + status = "disabled"; + }; + + mtp_mbox: mbox@24e408000 { + compatible = "apple,t8112-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x4e408000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + + status = "disabled"; + }; + + mtp_dart: iommu@24e808000 { + compatible = "apple,t8112-dart", "apple,t8110-dart"; + reg = <0x2 0x4e808000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + #iommu-cells = <1>; + + status = "disabled"; + }; + + mtp_dockchannel: fifo@24eb14000 { + compatible = "apple,t8112-dockchannel", "apple,dockchannel"; + reg = <0x2 0x4eb14000 0x0 0x4000>; + reg-names = "irq"; + interrupt-parent = <&aic>; + interrupts = ; + + ranges = <0 0x2 0x4eb28000 0x20000>; + nonposted-mmio; + #address-cells = <1>; + #size-cells = <1>; + + interrupt-controller; + #interrupt-cells = <2>; + + status = "disabled"; + + mtp_hid: input@8000 { + compatible = "apple,dockchannel-hid"; + reg = <0x8000 0x4000>, + <0xc000 0x4000>, + <0x0000 0x4000>, + <0x4000 0x4000>; + reg-names = "config", "data", + "rmt-config", "rmt-data"; + iommus = <&mtp_dart 1>; + interrupt-parent = <&mtp_dockchannel>; + interrupts = <2 IRQ_TYPE_LEVEL_HIGH>, + <3 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "tx", "rx"; + + apple,fifo-size = <0x800>; + apple,helper-cpu = <&mtp>; + }; + + }; + + sep_dart: iommu@25d2c0000 { + compatible = "apple,t8112-dart", "apple,t8110-dart"; + reg = <0x2 0x5d2c0000 0x0 0x4000>; + #iommu-cells = <1>; + interrupt-parent = <&aic>; + interrupts = ; + }; + + sep: sep@25e400000 { + compatible = "apple,sep"; + reg = <0x2 0x5e400000 0x0 0x6C000>; + mboxes = <&sep_mbox>; + mbox-names = "mbox"; + iommus = <&sep_dart 0>; + status = "disabled"; + }; + + sep_mbox: mbox@25e408000 { + compatible = "apple,t8112-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x5e408000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + }; + + dispext0_dart: iommu@271304000 { + compatible = "apple,t8112-dart", "apple,t8110-dart"; + reg = <0x2 0x71304000 0x0 0x4000>; + #iommu-cells = <1>; + apple,dma-range = <0x0 0x0 0xf 0xffff0000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_dispext_cpu0>; + status = "disabled"; + }; + + dcpext_dart: iommu@27130c000 { + compatible = "apple,t8112-dart", "apple,t8110-dart"; + reg = <0x2 0x7130c000 0x0 0x4000>; + #iommu-cells = <1>; + apple,dma-range = <0x8 0x0 0x7 0xffff0000>; + interrupt-parent = <&aic>; + interrupts = ; + power-domains = <&ps_dispext_cpu0>; + status = "disabled"; + }; + + dcpext_mbox: mbox@271c08000 { + compatible = "apple,t8112-asc-mailbox", "apple,asc-mailbox-v4"; + reg = <0x2 0x71c08000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = , + , + , + ; + interrupt-names = "send-empty", "send-not-empty", + "recv-empty", "recv-not-empty"; + #mbox-cells = <0>; + power-domains = <&ps_dispext_cpu0>; + resets = <&ps_dispext_cpu0>; + status = "disabled"; + }; + + dcpext: dcp@271c00000 { + compatible = "apple,t8112-dcpext", "apple,dcpext"; + mboxes = <&dcpext_mbox>; + mbox-names = "mbox"; + iommus = <&dcpext_dart 5>; + phandle = <&dcpext>; + + /* the ADT has 2 additional regs which seems to be unused */ + reg-names = "coproc", "disp-0", "disp-1", "disp-2", "disp-3"; + reg = <0x2 0x71c00000 0x0 0x4000>, + <0x2 0x70000000 0x0 0x61C000>, + <0x2 0x71320000 0x0 0x4000>, + <0x2 0x71344000 0x0 0x4000>, + <0x2 0x71800000 0x0 0x800000>; + apple,bw-scratch = <&pmgr_dcp 0 4 0x5e0>; + power-domains = <&ps_dispext_cpu0>; + resets = <&ps_dispext_cpu0>; + clocks = <&clk_dispext0>; + apple,dcp-index = <1>; + status = "disabled"; + // required bus properties for 'piodma' subdevice + #address-cells = <2>; + #size-cells = <2>; + + piodma { + iommus = <&dispext0_dart 4>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + dcpext_audio: endpoint { + remote-endpoint = <&dpaudio1_dcp>; + }; + }; + }; + }; + ans_mbox: mbox@277408000 { compatible = "apple,t8112-asc-mailbox", "apple,asc-mailbox-v4"; reg = <0x2 0x77408000 0x0 0x4000>; @@ -1010,6 +1705,162 @@ resets = <&ps_ans>; }; + dwc3_0: usb@382280000 { + compatible = "apple,t8112-dwc3", "apple,t8103-dwc3"; + reg = <0x3 0x82280000 0x0 0xcd00>, <0x3 0x8228cd00 0x0 0x3200>; + reg-names = "dwc3-core", "dwc3-apple"; + interrupt-parent = <&aic>; + interrupts = ; + dr_mode = "otg"; + usb-role-switch; + role-switch-default-mode = "host"; + iommus = <&dwc3_0_dart_0 0>, <&dwc3_0_dart_1 1>; + power-domains = <&ps_atc0_usb>; + resets = <&atcphy0>; + phys = <&atcphy0 PHY_TYPE_USB2>, <&atcphy0 PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + }; + + dwc3_0_dart_0: iommu@382f00000 { + compatible = "apple,t8110-dart"; + reg = <0x3 0x82f00000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + #iommu-cells = <1>; + power-domains = <&ps_atc0_usb>; + }; + + dwc3_0_dart_1: iommu@382f80000 { + compatible = "apple,t8110-dart"; + reg = <0x3 0x82f80000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + #iommu-cells = <1>; + power-domains = <&ps_atc0_usb>; + }; + + atcphy0: phy@383000000 { + compatible = "apple,t8112-atcphy", "apple,t8103-atcphy"; + reg = <0x3 0x83000000 0x0 0x4c000>, + <0x3 0x83050000 0x0 0x8000>, + <0x3 0x80000000 0x0 0x4000>, + <0x3 0x82a90000 0x0 0x4000>, + <0x3 0x82a84000 0x0 0x4000>; + reg-names = "core", "lpdptx", "axi2af", "usb2phy", + "pipehandler"; + + #phy-cells = <1>; + #reset-cells = <0>; + + nvmem-cells = <&atcphy0_aus_cmn_shm_vreg_trim>, + <&atcphy0_auspll_rodco_encap>, + <&atcphy0_auspll_rodco_bias_adjust>, + <&atcphy0_auspll_fracn_dll_start_capcode>, + <&atcphy0_auspll_dtc_vreg_adjust>, + <&atcphy0_cio3pll_dco_coarsebin0>, + <&atcphy0_cio3pll_dco_coarsebin1>, + <&atcphy0_cio3pll_dll_start_capcode>, + <&atcphy0_cio3pll_dtc_vreg_adjust>; + nvmem-cell-names = "aus_cmn_shm_vreg_trim", + "auspll_rodco_encap", + "auspll_rodco_bias_adjust", + "auspll_fracn_dll_start_capcode", + "auspll_dtc_vreg_adjust", + "cio3pll_dco_coarsebin0", + "cio3pll_dco_coarsebin1", + "cio3pll_dll_start_capcode", + "cio3pll_dtc_vreg_adjust"; + + orientation-switch; + mode-switch; + power-domains = <&ps_atc0_usb>; + }; + + atcphy0_xbar: mux@38304c000 { + compatible = "apple,t8112-display-crossbar", "apple,t8103-display-crossbar"; + reg = <0x3 0x8304c000 0x0 0x4000>; + #mux-control-cells = <1>; + power-domains = <&ps_atc0_usb>; + }; + + dwc3_1: usb@502280000 { + compatible = "apple,t8112-dwc3", "apple,t8103-dwc3"; + reg = <0x5 0x02280000 0x0 0xcd00>, <0x5 0x0228cd00 0x0 0x3200>; + reg-names = "dwc3-core", "dwc3-apple"; + interrupt-parent = <&aic>; + interrupts = ; + dr_mode = "otg"; + usb-role-switch; + role-switch-default-mode = "host"; + iommus = <&dwc3_1_dart_0 0>, <&dwc3_1_dart_1 1>; + power-domains = <&ps_atc1_usb>; + resets = <&atcphy1>; + phys = <&atcphy1 PHY_TYPE_USB2>, <&atcphy1 PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + }; + + dwc3_1_dart_0: iommu@502f00000 { + compatible = "apple,t8110-dart"; + reg = <0x5 0x02f00000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + #iommu-cells = <1>; + power-domains = <&ps_atc1_usb>; + }; + + dwc3_1_dart_1: iommu@502f80000 { + compatible = "apple,t8110-dart"; + reg = <0x5 0x02f80000 0x0 0x4000>; + interrupt-parent = <&aic>; + interrupts = ; + #iommu-cells = <1>; + power-domains = <&ps_atc1_usb>; + }; + + atcphy1: phy@503000000 { + compatible = "apple,t8112-atcphy", "apple,t8103-atcphy"; + reg = <0x5 0x03000000 0x0 0x4c000>, + <0x5 0x03050000 0x0 0x8000>, + <0x5 0x0 0x0 0x4000>, + <0x5 0x02a90000 0x0 0x4000>, + <0x5 0x02a84000 0x0 0x4000>; + reg-names = "core", "lpdptx", "axi2af", "usb2phy", + "pipehandler"; + + #phy-cells = <1>; + #reset-cells = <0>; + + nvmem-cells = <&atcphy1_aus_cmn_shm_vreg_trim>, + <&atcphy1_auspll_rodco_encap>, + <&atcphy1_auspll_rodco_bias_adjust>, + <&atcphy1_auspll_fracn_dll_start_capcode>, + <&atcphy1_auspll_dtc_vreg_adjust>, + <&atcphy1_cio3pll_dco_coarsebin0>, + <&atcphy1_cio3pll_dco_coarsebin1>, + <&atcphy1_cio3pll_dll_start_capcode>, + <&atcphy1_cio3pll_dtc_vreg_adjust>; + nvmem-cell-names = "aus_cmn_shm_vreg_trim", + "auspll_rodco_encap", + "auspll_rodco_bias_adjust", + "auspll_fracn_dll_start_capcode", + "auspll_dtc_vreg_adjust", + "cio3pll_dco_coarsebin0", + "cio3pll_dco_coarsebin1", + "cio3pll_dll_start_capcode", + "cio3pll_dtc_vreg_adjust"; + + orientation-switch; + mode-switch; + power-domains = <&ps_atc1_usb>; + }; + + atcphy1_xbar: mux@50304c000 { + compatible = "apple,t8112-display-crossbar", "apple,t8103-display-crossbar"; + reg = <0x5 0x0304c000 0x0 0x4000>; + #mux-control-cells = <1>; + power-domains = <&ps_atc1_usb>; + }; + pcie0_dart: iommu@681008000 { compatible = "apple,t8110-dart"; reg = <0x6 0x81008000 0x0 0x4000>; @@ -1087,6 +1938,8 @@ pinctrl-0 = <&pcie_pins>; pinctrl-names = "default"; + dma-coherent; + port00: pci@0,0 { device_type = "pci"; reg = <0x0 0x0 0x0 0x0 0x0>; diff --git a/arch/arm64/boot/dts/apple/t8122-j433.dts b/arch/arm64/boot/dts/apple/t8122-j433.dts new file mode 100644 index 00000000000000..61fff420571574 --- /dev/null +++ b/arch/arm64/boot/dts/apple/t8122-j433.dts @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * Apple iMac (24-inch, 2x USB-C, M3, 2023) + * + * target-type: J433 + * + * Copyright The Asahi Linux Contributors + */ + +/dts-v1/; + +#include "t8122.dtsi" +#include "t8122-usbpd-i2c.dtsi" +#include "t8122-jxxx.dtsi" + +/ { + compatible = "apple,j433", "apple,t8122", "apple,arm-platform"; + model = "Apple iMac (24-inch, 2x USB-C, M3, 2023)"; +}; + + diff --git a/arch/arm64/boot/dts/apple/t8122-j434.dts b/arch/arm64/boot/dts/apple/t8122-j434.dts new file mode 100644 index 00000000000000..16ef556a07037e --- /dev/null +++ b/arch/arm64/boot/dts/apple/t8122-j434.dts @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * Apple iMac (24-inch, 4x USB-C, M3, 2023) + * + * target-type: J434 + * + * Copyright The Asahi Linux Contributors + */ + +/dts-v1/; + +#include "t8122.dtsi" +#include "t8122-usbpd-i2c.dtsi" +#include "t8122-jxxx.dtsi" + +/ { + compatible = "apple,j434", "apple,t8122", "apple,arm-platform"; + model = "Apple iMac (24-inch, 4x USB-C, M3, 2023)"; +}; + + diff --git a/arch/arm64/boot/dts/apple/t8122-j504.dts b/arch/arm64/boot/dts/apple/t8122-j504.dts new file mode 100644 index 00000000000000..464491b55b019c --- /dev/null +++ b/arch/arm64/boot/dts/apple/t8122-j504.dts @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * Apple MacBook Pro (14-inch, M3, 2023) + * + * target-type: J504 + * + * Copyright The Asahi Linux Contributors + */ + +/dts-v1/; + +#include "t8122.dtsi" +#include "t8122-usbpd-i2c.dtsi" +#include "t8122-jxxx.dtsi" +#include + +/ { + compatible = "apple,j504", "apple,t8122", "apple,arm-platform"; + model = "Apple MacBook Pro (14-inch, M3, 2023)"; + + led-controller { + compatible = "pwm-leds"; + led-0 { + pwms = <&fpwm1 0 40000>; + label = "kbd_backlight"; + function = LED_FUNCTION_KBD_BACKLIGHT; + color = ; + max-brightness = <255>; + default-state = "keep"; + }; + }; +}; + +&fpwm1 { + status = "okay"; +}; + diff --git a/arch/arm64/boot/dts/apple/t8122-jxxx.dtsi b/arch/arm64/boot/dts/apple/t8122-jxxx.dtsi new file mode 100644 index 00000000000000..dd85f0c9fb1e11 --- /dev/null +++ b/arch/arm64/boot/dts/apple/t8122-jxxx.dtsi @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * Apple M3 MacBook Air/Pro and iMac (M3, 2023/2024) + * + * This file contains parts common to all Apple M3 devices using the t8122. + * + * target-type: J433, J434, J504, J613, J615 + * + * Copyright The Asahi Linux Contributors + */ + +/ { + aliases { + serial0 = &serial0; + }; + + chosen { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + stdout-path = "serial0"; + + framebuffer0: framebuffer@0 { + compatible = "apple,simple-framebuffer", "simple-framebuffer"; + reg = <0 0 0 0>; /* To be filled by loader */ + power-domains = <&ps_disp_cpu>, <&ps_dptx_ext_phy>; + /* Format properties will be added by loader */ + status = "disabled"; + }; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + /* To be filled by loader */ + }; + + memory@800000000 { + device_type = "memory"; + reg = <0x8 0 0x2 0>; /* To be filled by loader */ + }; +}; + +&serial0 { + status = "okay"; +}; diff --git a/arch/arm64/boot/dts/apple/t8122-pmgr.dtsi b/arch/arm64/boot/dts/apple/t8122-pmgr.dtsi new file mode 100644 index 00000000000000..e5c5602b85fe66 --- /dev/null +++ b/arch/arm64/boot/dts/apple/t8122-pmgr.dtsi @@ -0,0 +1,1165 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * PMGR Power domains for the Apple T8122 "M3" SoC + * + * Copyright The Asahi Linux Contributors + */ + +&pmgr { + ps_ecpm: power-controller@40 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x40 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "ecpm"; + }; + + ps_pcpm: power-controller@48 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x48 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "pcpm"; + }; + + ps_sbr: power-controller@100 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x100 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "sbr"; + apple,always-on; /* Core device */ + }; + + ps_msg: power-controller@108 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x108 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "msg"; + }; + + ps_aic: power-controller@110 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x110 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "aic"; + apple,always-on; /* Core device */ + }; + + ps_dwi: power-controller@118 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x118 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dwi"; + }; + + ps_gpio: power-controller@120 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x120 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "gpio"; + }; + + ps_pms_busif: power-controller@128 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x128 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "pms_busif"; + apple,always-on; /* Core device */ + }; + + ps_pms: power-controller@130 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x130 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "pms"; + apple,always-on; /* Core device */ + }; + + ps_pms_fpwm0: power-controller@138 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x138 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "pms_fpwm0"; + power-domains = <&ps_pms>; + }; + + ps_pms_fpwm1: power-controller@140 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x140 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "pms_fpwm1"; + power-domains = <&ps_pms>; + }; + + ps_pms_fpwm2: power-controller@148 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x148 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "pms_fpwm2"; + power-domains = <&ps_pms>; + }; + + ps_pms_fpwm3: power-controller@150 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x150 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "pms_fpwm3"; + power-domains = <&ps_pms>; + }; + + ps_pms_fpwm4: power-controller@158 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x158 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "pms_fpwm4"; + power-domains = <&ps_pms>; + }; + + ps_pms_c1ppt: power-controller@160 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x160 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "pms_c1ppt"; + }; + + ps_soc_rc: power-controller@168 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x168 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "soc_rc"; + }; + + ps_soc_dpe: power-controller@170 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x170 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "soc_dpe"; + apple,always-on; + }; + + ps_pmgr_soc_ocla: power-controller@178 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x178 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "pmgr_soc_ocla"; + power-domains = <&ps_pms>; + }; + + ps_ispsens0: power-controller@180 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x180 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "ispsens0"; + }; + + ps_ispsens1: power-controller@188 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x188 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "ispsens1"; + }; + + ps_ispsens2: power-controller@190 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x190 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "ispsens2"; + }; + + ps_ispsens3: power-controller@198 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x198 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "ispsens3"; + }; + + ps_aft0: power-controller@1a8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x1a8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "aft0"; + }; + + ps_ioa0: power-controller@1b0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x1b0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "ioa0"; + apple,always-on; + }; + + ps_ap_tmm: power-controller@1b8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x1b8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "ap_tmm"; + }; + + ps_disp_sys: power-controller@1d8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x1d8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "disp_sys"; + apple,always-on; /* TODO: figure out if we can enable PM here */ + }; + + ps_gfx: power-controller@1e0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x1e0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "gfx"; + }; + + ps_isp_sys: power-controller@1e8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x1e8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "isp_sys"; + }; + + ps_avd_sys: power-controller@1f0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x1f0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "avd_sys"; + }; + + ps_jpg: power-controller@200 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x200 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "jpg"; + }; + + ps_disp_fe: power-controller@208 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x208 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "disp_fe"; + power-domains = <&ps_disp_sys>; + apple,always-on; /* TODO: figure out if we can enable PM here */ + }; + + ps_sio_cpu: power-controller@210 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x210 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "sio_cpu"; + }; + + ps_fpwm0: power-controller@218 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x218 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "fpwm0"; + }; + + ps_fpwm1: power-controller@220 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x220 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "fpwm1"; + }; + + ps_fpwm2: power-controller@228 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x228 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "fpwm2"; + }; + + ps_i2c0: power-controller@230 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x230 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "i2c0"; + }; + + ps_i2c1: power-controller@238 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x238 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "i2c1"; + }; + + ps_i2c2: power-controller@240 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x240 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "i2c2"; + }; + + ps_i2c3: power-controller@248 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x248 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "i2c3"; + }; + + ps_i2c4: power-controller@250 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x250 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "i2c4"; + }; + + ps_i2c5: power-controller@258 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x258 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "i2c5"; + }; + + ps_i2c6: power-controller@260 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x260 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "i2c6"; + }; + + ps_i2c7: power-controller@268 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x268 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "i2c7"; + }; + + ps_i2c8: power-controller@270 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x270 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "i2c8"; + }; + + ps_spi_p: power-controller@278 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x278 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "spi_p"; + }; + + ps_uart_p: power-controller@280 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x280 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "uart_p"; + }; + + ps_audio_p: power-controller@288 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x288 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "audio_p"; + }; + + ps_aes: power-controller@290 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x290 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "aes"; + }; + + ps_spi0: power-controller@298 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x298 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "spi0"; + power-domains = <&ps_spi_p>; + }; + + ps_spi1: power-controller@2a0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x2a0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "spi1"; + power-domains = <&ps_spi_p>; + }; + + ps_spi2: power-controller@2a8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x2a8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "spi2"; + power-domains = <&ps_spi_p>; + }; + + ps_spi3: power-controller@2b0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x2b0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "spi3"; + power-domains = <&ps_spi_p>; + }; + + ps_spi4: power-controller@2b8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x2b8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "spi4"; + power-domains = <&ps_spi_p>; + }; + + ps_spi5: power-controller@2c0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x2c0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "spi5"; + power-domains = <&ps_spi_p>; + }; + + ps_qspi: power-controller@2c8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x2c8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "qspi"; + power-domains = <&ps_spi_p>; + }; + + ps_uart_n: power-controller@2d0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x2d0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "uart_n"; + power-domains = <&ps_uart_p>; + }; + + ps_uart0: power-controller@2d8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x2d8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "uart0"; + power-domains = <&ps_uart_p>; + }; + + ps_uart1: power-controller@2e0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x2e0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "uart1"; + power-domains = <&ps_uart_p>; + }; + + ps_uart2: power-controller@2e8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x2e8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "uart2"; + power-domains = <&ps_uart_p>; + }; + + ps_uart3: power-controller@2f0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x2f0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "uart3"; + power-domains = <&ps_uart_p>; + }; + + ps_uart4: power-controller@2f8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x2f8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "uart4"; + power-domains = <&ps_uart_p>; + }; + + ps_uart5: power-controller@300 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x300 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "uart5"; + power-domains = <&ps_uart_p>; + }; + + ps_uart6: power-controller@308 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x308 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "uart6"; + power-domains = <&ps_uart_p>; + }; + + ps_sio_adma: power-controller@310 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x310 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "sio_adma"; + power-domains = <&ps_fpwm0>; + }; + + ps_dpa0: power-controller@318 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x318 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dpa0"; + power-domains = <&ps_audio_p>; + }; + + ps_dcs0: power-controller@330 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x330 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dcs0"; + apple,always-on; + }; + + ps_dcs2: power-controller@338 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x338 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dcs2"; + apple,always-on; + }; + + ps_dcs1: power-controller@340 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x340 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dcs1"; + apple,always-on; + }; + + ps_dcs3: power-controller@348 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x348 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dcs3"; + apple,always-on; + }; + + ps_dcs4: power-controller@358 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x358 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dcs4"; + apple,always-on; + }; + + ps_dcs5: power-controller@360 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x360 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dcs5"; + apple,always-on; + }; + + ps_dcs6: power-controller@368 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x368 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dcs6"; + apple,always-on; + }; + + ps_dcs7: power-controller@370 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x370 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dcs7"; + apple,always-on; + }; + + ps_dpa1: power-controller@378 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x378 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dpa1"; + power-domains = <&ps_audio_p>; + }; + + ps_dpa2: power-controller@380 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x380 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dpa2"; + power-domains = <&ps_audio_p>; + }; + + ps_dpa3: power-controller@388 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x388 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dpa3"; + power-domains = <&ps_audio_p>; + }; + + ps_dpa4: power-controller@390 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x390 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dpa4"; + power-domains = <&ps_audio_p>; + }; + + ps_mca0: power-controller@398 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x398 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "mca0"; + power-domains = <&ps_sio_adma>, <&ps_audio_p>; + }; + + ps_mca1: power-controller@3a0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x3a0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "mca1"; + power-domains = <&ps_sio_adma>, <&ps_audio_p>; + }; + + ps_mca2: power-controller@3a8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x3a8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "mca2"; + power-domains = <&ps_sio_adma>, <&ps_audio_p>; + }; + + ps_trace_fab: power-controller@3b0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x3b0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "trace_fab"; + }; + + ps_mca3: power-controller@3b8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x3b8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "mca3"; + power-domains = <&ps_sio_adma>, <&ps_audio_p>; + }; + + ps_ioa1: power-controller@3c0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x3c0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "ioa1"; + apple,always-on; + }; + + ps_apcie: power-controller@3f0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x3f0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "apcie"; + }; + + ps_ans: power-controller@3f8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x3f8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "ans"; + }; + + ps_atc0_common: power-controller@400 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x400 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc0_common"; + }; + + ps_atc1_common: power-controller@408 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x408 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc1_common"; + }; + + ps_dispext_sys: power-controller@410 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x410 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dispext_sys"; + }; + + ps_venc_sys: power-controller@418 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x418 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "venc_sys"; + }; + + ps_scodec: power-controller@420 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x420 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "scodec"; + }; + + ps_msr: power-controller@428 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x428 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "msr"; + power-domains = <&ps_aft0>; + }; + + ps_dptx_ext_phy: power-controller@430 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x430 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dptx_ext_phy"; + }; + + ps_ane_sys: power-controller@438 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x438 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "ane_sys"; + }; + + ps_apcie_gp: power-controller@440 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x440 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "apcie_gp"; + power-domains = <&ps_apcie>; + }; + + ps_apcie_st: power-controller@448 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x448 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "apcie_st"; + power-domains = <&ps_ans>, <&ps_apcie>; + }; + + ps_pmp: power-controller@450 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x450 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "pmp"; + apple,always-on; + }; + + ps_pms_sram: power-controller@458 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x458 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "pms_sram"; + apple,always-on; + }; + + ps_atc0_pcie: power-controller@460 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x460 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc0_pcie"; + power-domains = <&ps_atc0_common>; + }; + + ps_atc0_cio: power-controller@468 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x468 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc0_cio"; + power-domains = <&ps_atc0_common>; + }; + + ps_atc1_pcie: power-controller@470 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x470 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc1_pcie"; + power-domains = <&ps_atc1_common>; + }; + + ps_atc1_cio: power-controller@478 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x478 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc1_cio"; + power-domains = <&ps_atc1_common>; + }; + + ps_dispext_fe: power-controller@480 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x480 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dispext_fe"; + power-domains = <&ps_dispext_sys>; + }; + + ps_dispext_cpu: power-controller@488 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x488 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "dispext_cpu"; + power-domains = <&ps_dispext_fe>; + apple,min-state = <4>; + }; + + ps_scodec_stream: power-controller@490 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x490 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "scodec_stream"; + power-domains = <&ps_scodec>; + }; + + ps_msr_ase_core: power-controller@498 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x498 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "msr_ase_core"; + power-domains = <&ps_msr>; + }; + + ps_apcie_phy_sw: power-controller@4a0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x4a0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "apcie_phy_sw"; + power-domains = <&ps_apcie_st>, <&ps_apcie_gp>; + }; + + ps_atc0_cio_pcie: power-controller@4a8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x4a8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc0_cio_pcie"; + power-domains = <&ps_atc0_cio>; + }; + + ps_atc0_cio_usb: power-controller@4b0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x4b0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc0_cio_usb"; + power-domains = <&ps_atc0_cio>; + }; + + ps_atc1_cio_pcie: power-controller@4b8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x4b8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc1_cio_pcie"; + power-domains = <&ps_atc1_cio>; + }; + + ps_atc1_cio_usb: power-controller@4c0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x4c0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc1_cio_usb"; + power-domains = <&ps_atc1_cio>; + }; + + ps_sep: power-controller@c00 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0xc00 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "sep"; + apple,always-on; + }; + + ps_venc_dma: power-controller@8000 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x8000 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "venc_dma"; + power-domains = <&ps_venc_sys>; + }; + + ps_venc_pipe4: power-controller@8008 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x8008 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "venc_pipe4"; + power-domains = <&ps_venc_dma>; + }; + + ps_venc_pipe5: power-controller@8010 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x8010 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "venc_pipe5"; + power-domains = <&ps_venc_dma>; + }; + + ps_venc_me0: power-controller@8018 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x8018 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "venc_me0"; + power-domains = <&ps_venc_dma>; + }; + + ps_venc_me1: power-controller@8020 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x8020 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "venc_me1"; + power-domains = <&ps_venc_me0>; + }; + + ps_disp_cpu: power-controller@10000 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x10000 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "disp_cpu"; + power-domains = <&ps_disp_fe>; + apple,min-state = <4>; + }; +}; + +&pmgr_mini { + + ps_debug_gated: power-controller@0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "debug_gated"; + apple,always-on; + }; + + ps_nub_spmi0: power-controller@58 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x58 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "nub_spmi0"; + apple,always-on; + }; + + ps_nub_spmi1: power-controller@60 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x60 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "nub_spmi1"; + apple,always-on; + }; + + ps_nub_spmi2: power-controller@68 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x68 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "nub_spmi2"; + apple,always-on; + }; + + ps_nub_spmi_a0: power-controller@70 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x70 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "nub_spmi_a0"; + apple,always-on; + }; + + ps_nub_aon: power-controller@78 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x78 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "nub_aon"; + apple,always-on; + }; + + ps_nub_spi0: power-controller@80 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x80 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "nub_spi0"; + apple,always-on; + }; + + ps_nub_ocla: power-controller@88 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x88 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "nub_ocla"; + apple,always-on; + }; + + ps_nub_gpio: power-controller@90 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x90 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "nub_gpio"; + apple,always-on; + }; + + ps_nub_fabric: power-controller@98 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0x98 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "nub_fabric"; + apple,always-on; + }; + + ps_nub_sram: power-controller@a0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0xa0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "nub_sram"; + apple,always-on; + }; + + ps_debug_switch: power-controller@a8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0xa8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "debug_switch"; + apple,always-on; + }; + + ps_atc0_usb_aon: power-controller@b0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0xb0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc0_usb_aon"; + }; + + ps_atc1_usb_aon: power-controller@b8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0xb8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc1_usb_aon"; + }; + + ps_atc0_usb: power-controller@c0 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0xc0 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc0_usb"; + power-domains = <&ps_atc0_usb_aon>, <&ps_atc0_common>; + }; + + ps_atc1_usb: power-controller@c8 { + compatible = "apple,t8122-pmgr-pwrstate", "apple,t8103-pmgr-pwrstate"; + reg = <0xc8 4>; + #power-domain-cells = <0>; + #reset-cells = <0>; + label = "atc1_usb"; + power-domains = <&ps_atc1_usb_aon>, <&ps_atc1_common>; + }; +}; diff --git a/arch/arm64/boot/dts/apple/t8122-usbpd-i2c.dtsi b/arch/arm64/boot/dts/apple/t8122-usbpd-i2c.dtsi new file mode 100644 index 00000000000000..112c5199cabdd4 --- /dev/null +++ b/arch/arm64/boot/dts/apple/t8122-usbpd-i2c.dtsi @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * Apple M3 MacBook Pro and iMac (M3, 2023) I2C based USB PD controller nodes + * + * This file contains nodes for t8122 devices using I2C based cd321x USB Type-C + * port controllers. The are used in the M3 MacBook Pro and iMacs but not in the + * M3 Macbook Airs. + * + * target-type: J433, J434, J504 + * + * Copyright The Asahi Linux Contributors + */ + +&i2c0 { + status = "okay"; + + hpm0: usb-pd@38 { + compatible = "apple,cd321x"; + reg = <0x38>; + interrupt-parent = <&pinctrl_ap>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "irq"; + }; + + hpm1: usb-pd@3f { + compatible = "apple,cd321x"; + reg = <0x3f>; + interrupt-parent = <&pinctrl_ap>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "irq"; + }; +}; diff --git a/arch/arm64/boot/dts/apple/t8122.dtsi b/arch/arm64/boot/dts/apple/t8122.dtsi new file mode 100644 index 00000000000000..2e2cf30f3cd510 --- /dev/null +++ b/arch/arm64/boot/dts/apple/t8122.dtsi @@ -0,0 +1,451 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * Apple T8122 "M3" SoC + * + * Other names: H15G + * + * Copyright The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include +#include + +/ { + compatible = "apple,t8122", "apple,arm-platform"; + + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu_e0>; + }; + core1 { + cpu = <&cpu_e1>; + }; + core2 { + cpu = <&cpu_e2>; + }; + core3 { + cpu = <&cpu_e3>; + }; + }; + + cluster1 { + core0 { + cpu = <&cpu_p0>; + }; + core1 { + cpu = <&cpu_p1>; + }; + core2 { + cpu = <&cpu_p2>; + }; + core3 { + cpu = <&cpu_p3>; + }; + }; + }; + + cpu_e0: cpu@0 { + compatible = "apple,sawtooth"; + device_type = "cpu"; + reg = <0x0 0x0>; + enable-method = "spin-table"; + cpu-release-addr = <0 0>; /* To be filled by loader */ + next-level-cache = <&l2_cache_0>; + i-cache-size = <0x20000>; + d-cache-size = <0x10000>; + }; + + cpu_e1: cpu@1 { + compatible = "apple,sawtooth"; + device_type = "cpu"; + reg = <0x0 0x1>; + enable-method = "spin-table"; + cpu-release-addr = <0 0>; /* To be filled by loader */ + next-level-cache = <&l2_cache_0>; + i-cache-size = <0x20000>; + d-cache-size = <0x10000>; + }; + + cpu_e2: cpu@2 { + compatible = "apple,sawtooth"; + device_type = "cpu"; + reg = <0x0 0x2>; + enable-method = "spin-table"; + cpu-release-addr = <0 0>; /* To be filled by loader */ + next-level-cache = <&l2_cache_0>; + i-cache-size = <0x20000>; + d-cache-size = <0x10000>; + }; + + cpu_e3: cpu@3 { + compatible = "apple,sawtooth"; + device_type = "cpu"; + reg = <0x0 0x3>; + enable-method = "spin-table"; + cpu-release-addr = <0 0>; /* To be filled by loader */ + next-level-cache = <&l2_cache_0>; + i-cache-size = <0x20000>; + d-cache-size = <0x10000>; + }; + + cpu_p0: cpu@10100 { + compatible = "apple,everest"; + device_type = "cpu"; + reg = <0x0 0x10100>; + enable-method = "spin-table"; + cpu-release-addr = <0 0>; /* To be filled by loader */ + next-level-cache = <&l2_cache_1>; + i-cache-size = <0x30000>; + d-cache-size = <0x20000>; + }; + + cpu_p1: cpu@10101 { + compatible = "apple,everest"; + device_type = "cpu"; + reg = <0x0 0x10101>; + enable-method = "spin-table"; + cpu-release-addr = <0 0>; /* To be filled by loader */ + next-level-cache = <&l2_cache_1>; + i-cache-size = <0x30000>; + d-cache-size = <0x20000>; + }; + + cpu_p2: cpu@10102 { + compatible = "apple,everest"; + device_type = "cpu"; + reg = <0x0 0x10102>; + enable-method = "spin-table"; + cpu-release-addr = <0 0>; /* To be filled by loader */ + next-level-cache = <&l2_cache_1>; + i-cache-size = <0x30000>; + d-cache-size = <0x20000>; + }; + + cpu_p3: cpu@10103 { + compatible = "apple,everest"; + device_type = "cpu"; + reg = <0x0 0x10103>; + enable-method = "spin-table"; + cpu-release-addr = <0 0>; /* To be filled by loader */ + next-level-cache = <&l2_cache_1>; + i-cache-size = <0x30000>; + d-cache-size = <0x20000>; + }; + + l2_cache_0: l2-cache-0 { + compatible = "cache"; + cache-level = <2>; + cache-unified; + cache-size = <0x400000>; + }; + + l2_cache_1: l2-cache-1 { + compatible = "cache"; + cache-level = <2>; + cache-unified; + cache-size = <0x1000000>; + }; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupt-parent = <&aic>; + interrupt-names = "phys", "virt", "hyp-phys", "hyp-virt"; + interrupts = , + , + , + ; + }; + + clkref: clock-ref { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <24000000>; + clock-output-names = "clkref"; + }; + + // clk_200m: clock-200m { + // compatible = "fixed-clock"; + // #clock-cells = <0>; + // clock-frequency = <200000000>; + // clock-output-names = "clk_200m"; + // }; + + soc { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + + ranges; + nonposted-mmio; + /* Required to get >32-bit DMA via DARTs */ + dma-ranges = <0 0 0 0 0xffffffff 0xffffc000>; + + i2c0: i2c@235010000 { + compatible = "apple,t8122-i2c", "apple,t8103-i2c"; + reg = <0x2 0x35010000 0x0 0x4000>; + clocks = <&clkref>; + interrupt-parent = <&aic>; + interrupts = ; + pinctrl-0 = <&i2c0_pins>; + pinctrl-names = "default"; + #address-cells = <0x1>; + #size-cells = <0x0>; + power-domains = <&ps_i2c0>; + status = "disabled"; + }; + + i2c1: i2c@235014000 { + compatible = "apple,t8122-i2c", "apple,t8103-i2c"; + reg = <0x2 0x35014000 0x0 0x4000>; + clocks = <&clkref>; + interrupt-parent = <&aic>; + interrupts = ; + pinctrl-0 = <&i2c1_pins>; + pinctrl-names = "default"; + #address-cells = <0x1>; + #size-cells = <0x0>; + power-domains = <&ps_i2c1>; + status = "disabled"; + }; + + i2c2: i2c@235018000 { + compatible = "apple,t8122-i2c", "apple,t8103-i2c"; + reg = <0x2 0x35018000 0x0 0x4000>; + clocks = <&clkref>; + interrupt-parent = <&aic>; + interrupts = ; + pinctrl-0 = <&i2c2_pins>; + pinctrl-names = "default"; + #address-cells = <0x1>; + #size-cells = <0x0>; + power-domains = <&ps_i2c2>; + status = "disabled"; + }; + + i2c3: i2c@23501c000 { + compatible = "apple,t8122-i2c", "apple,t8103-i2c"; + reg = <0x2 0x3501c000 0x0 0x4000>; + clocks = <&clkref>; + interrupt-parent = <&aic>; + interrupts = ; + pinctrl-0 = <&i2c3_pins>; + pinctrl-names = "default"; + #address-cells = <0x1>; + #size-cells = <0x0>; + power-domains = <&ps_i2c3>; + status = "disabled"; + }; + + i2c4: i2c@235020000 { + compatible = "apple,t8122-i2c", "apple,t8103-i2c"; + reg = <0x2 0x35020000 0x0 0x4000>; + clocks = <&clkref>; + interrupt-parent = <&aic>; + interrupts = ; + pinctrl-0 = <&i2c4_pins>; + pinctrl-names = "default"; + #address-cells = <0x1>; + #size-cells = <0x0>; + power-domains = <&ps_i2c4>; + status = "disabled"; + }; + + fpwm1: pwm@2a1044000 { + compatible = "apple,t8122-fpwm", "apple,s5l-fpwm"; + reg = <0x2 0xa1044000 0x0 0x4000>; + power-domains = <&ps_fpwm1>; + clocks = <&clkref>; + #pwm-cells = <2>; + status = "disabled"; + }; + + serial0: serial@2a1200000 { + compatible = "apple,s5l-uart"; + reg = <0x2 0xa1200000 0x0 0x1000>; + reg-io-width = <4>; + interrupt-parent = <&aic>; + interrupts = ; + /* + * TODO: figure out the clocking properly, there may + * be a third selectable clock. + */ + clocks = <&clkref>, <&clkref>; + clock-names = "uart", "clk_uart_baud0"; + power-domains = <&ps_uart0>; + status = "disabled"; + }; + + aic: interrupt-controller@2d1000000 { + compatible = "apple,t8122-aic3"; + #interrupt-cells = <3>; + interrupt-controller; + reg = <0x2 0xd1000000 0x0 0x184000>, + <0x2 0xd1040000 0x0 0x4>; + reg-names = "core", "event"; + power-domains = <&ps_aic>; + + affinities { + e-core-pmu-affinity { + apple,fiq-index = ; + cpus = <&cpu_e0 &cpu_e1 &cpu_e2 &cpu_e3>; + }; + + p-core-pmu-affinity { + apple,fiq-index = ; + cpus = <&cpu_p0 &cpu_p1 &cpu_p2 &cpu_p3>; + }; + }; + }; + + pmgr: power-management@2d0700000 { + compatible = "apple,t8122-pmgr", "apple,t8103-pmgr", "syscon", "simple-mfd"; + #address-cells = <1>; + #size-cells = <1>; + reg = <0x2 0xd0700000 0 0x10000>; + /* child nodes are added in t8122-pmgr.dtsi */ + }; + + pinctrl_ap: pinctrl@2c7100000 { + compatible = "apple,t8122-pinctrl", "apple,t8103-pinctrl"; + reg = <0x2 0xc7100000 0x0 0x100000>; + power-domains = <&ps_gpio>; + + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pinctrl_ap 0 0 224>; + apple,npins = <224>; + + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&aic>; + interrupts = , + , + , + , + , + , + ; + + i2c0_pins: i2c0-pins { + pinmux = , + ; + }; + + i2c1_pins: i2c1-pins { + pinmux = , + ; + }; + + i2c2_pins: i2c2-pins { + pinmux = , + ; + }; + + i2c3_pins: i2c3-pins { + pinmux = , + ; + }; + + i2c4_pins: i2c4-pins { + pinmux = , + ; + }; + + }; + + pinctrl_nub: pinctrl@2e41f0000 { + compatible = "apple,t8122-pinctrl", "apple,t8103-pinctrl"; + reg = <0x2 0xe41f0000 0x0 0x4000>; + power-domains = <&ps_nub_gpio>; + + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pinctrl_nub 0 0 32>; + apple,npins = <32>; + + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&aic>; + interrupts = , + , + , + , + , + , + ; + }; + + pmgr_mini: power-management@2e4280000 { + compatible = "apple,t8122-pmgr", "apple,t8103-pmgr", "syscon", "simple-mfd"; + #address-cells = <1>; + #size-cells = <1>; + reg = <0x2 0xe4280000 0 0x4000>; + /* child nodes are added in t8122-pmgr.dtsi */ + }; + + wdt: watchdog@2e42b0000 { + compatible = "apple,t8122-wdt", "apple,t8103-wdt"; + reg = <0x2 0xe42b0000 0x0 0x4000>; + clocks = <&clkref>; + interrupt-parent = <&aic>; + interrupts = ; + }; + + pinctrl_smc: pinctrl@2ec820000 { + compatible = "apple,t8122-pinctrl", "apple,t8103-pinctrl"; + reg = <0x2 0xec820000 0x0 0x4000>; + + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pinctrl_smc 0 0 18>; + apple,npins = <18>; + + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&aic>; + interrupts = , + , + , + , + , + , + ; + }; + + pinctrl_aop: pinctrl@2f4824000 { + compatible = "apple,t8122-pinctrl", "apple,t8103-pinctrl"; + reg = <0x2 0xf4824000 0x0 0x4000>; + + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pinctrl_aop 0 0 54>; + apple,npins = <54>; + + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&aic>; + interrupts = , + , + , + , + , + , + ; + }; + }; +}; + +#include "t8122-pmgr.dtsi" diff --git a/arch/arm64/boot/dts/exynos/google/gs101.dtsi b/arch/arm64/boot/dts/exynos/google/gs101.dtsi index 31c99526470d0b..c01ff4e1b0d5d3 100644 --- a/arch/arm64/boot/dts/exynos/google/gs101.dtsi +++ b/arch/arm64/boot/dts/exynos/google/gs101.dtsi @@ -288,7 +288,7 @@ cmu_misc: clock-controller@10010000 { compatible = "google,gs101-cmu-misc"; - reg = <0x10010000 0x8000>; + reg = <0x10010000 0x10000>; #clock-cells = <1>; clocks = <&cmu_top CLK_DOUT_CMU_MISC_BUS>, <&cmu_top CLK_DOUT_CMU_MISC_SSS>; @@ -365,7 +365,7 @@ cmu_peric0: clock-controller@10800000 { compatible = "google,gs101-cmu-peric0"; - reg = <0x10800000 0x4000>; + reg = <0x10800000 0x10000>; #clock-cells = <1>; clocks = <&ext_24_5m>, <&cmu_top CLK_DOUT_CMU_PERIC0_BUS>, @@ -911,7 +911,7 @@ cmu_peric1: clock-controller@10c00000 { compatible = "google,gs101-cmu-peric1"; - reg = <0x10c00000 0x4000>; + reg = <0x10c00000 0x10000>; #clock-cells = <1>; clocks = <&ext_24_5m>, <&cmu_top CLK_DOUT_CMU_PERIC1_BUS>, @@ -1265,7 +1265,7 @@ cmu_hsi0: clock-controller@11000000 { compatible = "google,gs101-cmu-hsi0"; - reg = <0x11000000 0x4000>; + reg = <0x11000000 0x10000>; #clock-cells = <1>; clocks = <&ext_24_5m>, @@ -1332,7 +1332,7 @@ cmu_hsi2: clock-controller@14400000 { compatible = "google,gs101-cmu-hsi2"; - reg = <0x14400000 0x4000>; + reg = <0x14400000 0x10000>; #clock-cells = <1>; clocks = <&ext_24_5m>, <&cmu_top CLK_DOUT_CMU_HSI2_BUS>, @@ -1395,16 +1395,16 @@ cmu_apm: clock-controller@17400000 { compatible = "google,gs101-cmu-apm"; - reg = <0x17400000 0x8000>; + reg = <0x17400000 0x10000>; #clock-cells = <1>; clocks = <&ext_24_5m>; clock-names = "oscclk"; }; - sysreg_apm: syscon@174204e0 { + sysreg_apm: syscon@17420000 { compatible = "google,gs101-apm-sysreg", "syscon"; - reg = <0x174204e0 0x1000>; + reg = <0x17420000 0x10000>; }; pmu_system_controller: system-controller@17460000 { @@ -1497,7 +1497,7 @@ cmu_top: clock-controller@1e080000 { compatible = "google,gs101-cmu-top"; - reg = <0x1e080000 0x8000>; + reg = <0x1e080000 0x10000>; #clock-cells = <1>; clocks = <&ext_24_5m>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi index 752caa38eb03bf..266038fbbef976 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi @@ -351,17 +351,6 @@ >; }; - pinctrl_usdhc1: usdhc1grp { - fsl,pins = < - MX8MM_IOMUXC_SD1_CLK_USDHC1_CLK 0x190 - MX8MM_IOMUXC_SD1_CMD_USDHC1_CMD 0x1d0 - MX8MM_IOMUXC_SD1_DATA0_USDHC1_DATA0 0x1d0 - MX8MM_IOMUXC_SD1_DATA1_USDHC1_DATA1 0x1d0 - MX8MM_IOMUXC_SD1_DATA2_USDHC1_DATA2 0x1d0 - MX8MM_IOMUXC_SD1_DATA3_USDHC1_DATA3 0x1d0 - >; - }; - pinctrl_usdhc2: usdhc2grp { fsl,pins = < MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x190 diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi index 68c2e0156a5c81..f8303b7e2bd22b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi @@ -113,6 +113,7 @@ ethphy0f: ethernet-phy@1 { /* SMSC LAN8740Ai */ compatible = "ethernet-phy-id0007.c110", "ethernet-phy-ieee802.3-c22"; + clocks = <&clk IMX8MP_CLK_ENET_QOS>; interrupt-parent = <&gpio3>; interrupts = <19 IRQ_TYPE_LEVEL_LOW>; pinctrl-0 = <&pinctrl_ethphy0>; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts index f7346b3d35fe53..a122f2ed5f5314 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts @@ -704,7 +704,7 @@ fsl,pins = , , , - ; + ; }; pinctrl_gpt1: gpt1grp { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts index 4eedd00d83b9fc..ac05c05193c5be 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts @@ -860,7 +860,7 @@ fsl,pins = , , , - ; + ; }; pinctrl_hoggpio2: hoggpio2grp { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81-moduline-display-106.dts b/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81-moduline-display-106.dts index 88ad422c27603b..399230144ce39c 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81-moduline-display-106.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81-moduline-display-106.dts @@ -9,7 +9,7 @@ #include "imx8mp-tx8p-ml81.dtsi" / { - compatible = "gocontroll,moduline-display", "fsl,imx8mp"; + compatible = "gocontroll,moduline-display-106", "karo,tx8p-ml81", "fsl,imx8mp"; chassis-type = "embedded"; hardware = "Moduline Display V1.06"; model = "GOcontroll Moduline Display baseboard"; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81.dtsi index fe8ba16eb40e71..761ee046eb72ef 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-tx8p-ml81.dtsi @@ -47,6 +47,7 @@ <&clk IMX8MP_SYS_PLL2_100M>, <&clk IMX8MP_SYS_PLL2_50M>; assigned-clock-rates = <266000000>, <100000000>, <50000000>; + nvmem-cells = <ð_mac1>; phy-handle = <ðphy0>; phy-mode = "rmii"; pinctrl-0 = <&pinctrl_eqos>; @@ -75,6 +76,10 @@ }; }; +&fec { + nvmem-cells = <ð_mac2>; +}; + &gpio1 { gpio-line-names = "SODIMM_152", "SODIMM_42", diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw702x.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw702x.dtsi index cbf0c9a740faa6..fb159199b39de3 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw702x.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw702x.dtsi @@ -395,13 +395,6 @@ status = "okay"; }; -/* off-board header */ -&uart1 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_uart1>; - status = "okay"; -}; - /* console */ &uart2 { pinctrl-names = "default"; @@ -409,25 +402,6 @@ status = "okay"; }; -/* off-board header */ -&uart3 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_uart3>; - status = "okay"; -}; - -/* off-board */ -&usdhc1 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_usdhc1>; - bus-width = <4>; - non-removable; - status = "okay"; - bus-width = <4>; - non-removable; - status = "okay"; -}; - /* eMMC */ &usdhc3 { pinctrl-names = "default", "state_100mhz", "state_200mhz"; @@ -523,13 +497,6 @@ >; }; - pinctrl_uart1: uart1grp { - fsl,pins = < - MX8MP_IOMUXC_UART1_RXD__UART1_DCE_RX 0x140 - MX8MP_IOMUXC_UART1_TXD__UART1_DCE_TX 0x140 - >; - }; - pinctrl_uart2: uart2grp { fsl,pins = < MX8MP_IOMUXC_UART2_RXD__UART2_DCE_RX 0x140 @@ -537,24 +504,6 @@ >; }; - pinctrl_uart3: uart3grp { - fsl,pins = < - MX8MP_IOMUXC_UART3_RXD__UART3_DCE_RX 0x140 - MX8MP_IOMUXC_UART3_TXD__UART3_DCE_TX 0x140 - >; - }; - - pinctrl_usdhc1: usdhc1grp { - fsl,pins = < - MX8MP_IOMUXC_SD1_CLK__USDHC1_CLK 0x190 - MX8MP_IOMUXC_SD1_CMD__USDHC1_CMD 0x1d0 - MX8MP_IOMUXC_SD1_DATA0__USDHC1_DATA0 0x1d0 - MX8MP_IOMUXC_SD1_DATA1__USDHC1_DATA1 0x1d0 - MX8MP_IOMUXC_SD1_DATA2__USDHC1_DATA2 0x1d0 - MX8MP_IOMUXC_SD1_DATA3__USDHC1_DATA3 0x1d0 - >; - }; - pinctrl_usdhc3: usdhc3grp { fsl,pins = < MX8MP_IOMUXC_NAND_WE_B__USDHC3_CLK 0x190 diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi index cf747ec6fa16eb..76020ef89bf3e8 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi @@ -365,17 +365,6 @@ >; }; - pinctrl_usdhc1: usdhc1grp { - fsl,pins = < - MX8MP_IOMUXC_SD1_CLK__USDHC1_CLK 0x190 - MX8MP_IOMUXC_SD1_CMD__USDHC1_CMD 0x1d0 - MX8MP_IOMUXC_SD1_DATA0__USDHC1_DATA0 0x1d0 - MX8MP_IOMUXC_SD1_DATA1__USDHC1_DATA1 0x1d0 - MX8MP_IOMUXC_SD1_DATA2__USDHC1_DATA2 0x1d0 - MX8MP_IOMUXC_SD1_DATA3__USDHC1_DATA3 0x1d0 - >; - }; - pinctrl_usdhc2: usdhc2grp { fsl,pins = < MX8MP_IOMUXC_SD2_CLK__USDHC2_CLK 0x190 diff --git a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts index 9c0b6b8d6459de..df99fe88cf4ac2 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts +++ b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts @@ -256,6 +256,7 @@ regulator-max-microvolt = <3000000>; gpio = <&lsio_gpio4 7 GPIO_ACTIVE_HIGH>; enable-active-high; + off-on-delay-us = <4800>; }; reg_audio: regulator-audio { @@ -560,7 +561,7 @@ compatible = "isil,isl29023"; reg = <0x44>; interrupt-parent = <&lsio_gpio4>; - interrupts = <11 IRQ_TYPE_EDGE_FALLING>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; }; pressure-sensor@60 { diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi index d4856b8590e0c5..e186c31bfd482e 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi @@ -171,25 +171,25 @@ &lpuart0 { compatible = "fsl,imx8qm-lpuart", "fsl,imx8qxp-lpuart"; - dmas = <&edma2 13 0 0>, <&edma2 12 0 1>; + dmas = <&edma2 12 0 FSL_EDMA_RX>, <&edma2 13 0 0>; dma-names = "rx","tx"; }; &lpuart1 { compatible = "fsl,imx8qm-lpuart", "fsl,imx8qxp-lpuart"; - dmas = <&edma2 15 0 0>, <&edma2 14 0 1>; + dmas = <&edma2 14 0 FSL_EDMA_RX>, <&edma2 15 0 0>; dma-names = "rx","tx"; }; &lpuart2 { compatible = "fsl,imx8qm-lpuart", "fsl,imx8qxp-lpuart"; - dmas = <&edma2 17 0 0>, <&edma2 16 0 1>; + dmas = <&edma2 16 0 FSL_EDMA_RX>, <&edma2 17 0 0>; dma-names = "rx","tx"; }; &lpuart3 { compatible = "fsl,imx8qm-lpuart", "fsl,imx8qxp-lpuart"; - dmas = <&edma2 19 0 0>, <&edma2 18 0 1>; + dmas = <&edma2 18 0 FSL_EDMA_RX>, <&edma2 19 0 0>; dma-names = "rx","tx"; }; diff --git a/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts b/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts index 148243470dd4ab..0953c25ef55768 100644 --- a/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts @@ -61,6 +61,7 @@ fan0: pwm-fan { compatible = "pwm-fan"; + fan-supply = <®_vcc_12v>; #cooling-cells = <2>; cooling-levels = <64 128 192 255>; pwms = <&tpm6 0 4000000 PWM_POLARITY_INVERTED>; diff --git a/arch/arm64/boot/dts/freescale/imx95-tqma9596sa.dtsi b/arch/arm64/boot/dts/freescale/imx95-tqma9596sa.dtsi index 180124cc5bce1f..16c40d11d3b5d8 100644 --- a/arch/arm64/boot/dts/freescale/imx95-tqma9596sa.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95-tqma9596sa.dtsi @@ -115,7 +115,7 @@ flash0: flash@0 { compatible = "jedec,spi-nor"; reg = <0>; - spi-max-frequency = <80000000>; + spi-max-frequency = <66000000>; spi-tx-bus-width = <4>; spi-rx-bus-width = <4>; vcc-supply = <®_1v8>; @@ -617,7 +617,7 @@ fsl,pins = ; }; - pinctrl_tpm5: tpm4grp { + pinctrl_tpm5: tpm5grp { fsl,pins = ; }; diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi index 6da961eb3fe5cc..583c5f7a84b546 100644 --- a/arch/arm64/boot/dts/freescale/imx95.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95.dtsi @@ -806,7 +806,7 @@ interrupts = ; #address-cells = <3>; #size-cells = <0>; - clocks = <&scmi_clk IMX95_CLK_BUSAON>, + clocks = <&scmi_clk IMX95_CLK_BUSWAKEUP>, <&scmi_clk IMX95_CLK_I3C2SLOW>; clock-names = "pclk", "fast_clk"; status = "disabled"; diff --git a/arch/arm64/boot/dts/freescale/mba8mx.dtsi b/arch/arm64/boot/dts/freescale/mba8mx.dtsi index 79daba930ad648..3e41da4d6122be 100644 --- a/arch/arm64/boot/dts/freescale/mba8mx.dtsi +++ b/arch/arm64/boot/dts/freescale/mba8mx.dtsi @@ -185,7 +185,7 @@ reset-assert-us = <500000>; reset-deassert-us = <500>; interrupt-parent = <&expander2>; - interrupts = <6 IRQ_TYPE_EDGE_FALLING>; + interrupts = <6 IRQ_TYPE_LEVEL_LOW>; }; }; }; diff --git a/arch/arm64/boot/dts/mediatek/Makefile b/arch/arm64/boot/dts/mediatek/Makefile index a4df4c21399eef..b50799b2a65fbd 100644 --- a/arch/arm64/boot/dts/mediatek/Makefile +++ b/arch/arm64/boot/dts/mediatek/Makefile @@ -104,6 +104,8 @@ dtb-$(CONFIG_ARCH_MEDIATEK) += mt8390-genio-700-evk.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8395-kontron-3-5-sbc-i1200.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8395-radxa-nio-12l.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8395-radxa-nio-12l-8-hd-panel.dtbo +mt8395-radxa-nio-12l-8-hd-panel-dtbs := mt8395-radxa-nio-12l.dtb mt8395-radxa-nio-12l-8-hd-panel.dtbo +dtb-$(CONFIG_ARCH_MEDIATEK) += mt8395-radxa-nio-12l-8-hd-panel.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8516-pumpkin.dtb # Device tree overlays support diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts index cce326aec1aa59..40af5656d6f15f 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts @@ -91,7 +91,7 @@ &pio { bt_pins_wakeup: bt-pins-wakeup { - piins-bt-wakeup { + pins-bt-wakeup { pinmux = ; input-enable; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi index 960d8955d018c1..27ce4b31cc99de 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi @@ -1812,15 +1812,23 @@ #size-cells = <0>; port@0 { + #address-cells = <1>; + #size-cells = <0>; reg = <0>; - ovl_2l1_in: endpoint { + + ovl_2l1_in: endpoint@1 { + reg = <1>; remote-endpoint = <&mmsys_ep_ext>; }; }; port@1 { + #address-cells = <1>; + #size-cells = <0>; reg = <1>; - ovl_2l1_out: endpoint { + + ovl_2l1_out: endpoint@1 { + reg = <1>; remote-endpoint = <&rdma1_in>; }; }; @@ -1872,15 +1880,23 @@ #size-cells = <0>; port@0 { + #address-cells = <1>; + #size-cells = <0>; reg = <0>; - rdma1_in: endpoint { + + rdma1_in: endpoint@1 { + reg = <1>; remote-endpoint = <&ovl_2l1_out>; }; }; port@1 { + #address-cells = <1>; + #size-cells = <0>; reg = <1>; - rdma1_out: endpoint { + + rdma1_out: endpoint@1 { + reg = <1>; remote-endpoint = <&dpi_in>; }; }; @@ -2076,15 +2092,24 @@ #size-cells = <0>; port@0 { + #address-cells = <1>; + #size-cells = <0>; reg = <0>; - dpi_in: endpoint { + + dpi_in: endpoint@1 { + reg = <1>; remote-endpoint = <&rdma1_out>; }; }; port@1 { + #address-cells = <1>; + #size-cells = <0>; reg = <1>; - dpi_out: endpoint { }; + + dpi_out: endpoint@1 { + reg = <1>; + }; }; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi index ec452d65703149..c7adafaa83288d 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi @@ -3067,7 +3067,7 @@ jpgdec@0,10000 { compatible = "mediatek,mt8195-jpgdec-hw"; - reg = <0 0 0x10000 0x10000>;/* JPGDEC_C1 */ + reg = <0 0x10000 0 0x10000>;/* JPGDEC_C1 */ iommus = <&iommu_vdo M4U_PORT_L19_JPGDEC_WDMA0>, <&iommu_vdo M4U_PORT_L19_JPGDEC_BSDMA0>, <&iommu_vdo M4U_PORT_L19_JPGDEC_WDMA1>, diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi index df034dbb82853e..5657045c53d90d 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi @@ -9,6 +9,7 @@ #include #include #include +#include / { compatible = "nvidia,tegra234"; @@ -127,6 +128,56 @@ pinmux: pinmux@2430000 { compatible = "nvidia,tegra234-pinmux"; reg = <0x0 0x2430000 0x0 0x19100>; + + pex_rst_c4_in_state: pinmux-pex-rst-c4-in { + pex_rst { + nvidia,pins = "pex_l4_rst_n_pl1"; + nvidia,function = "rsvd1"; + nvidia,pull = ; + nvidia,tristate = ; + nvidia,enable-input = ; + }; + }; + + pex_rst_c5_in_state: pinmux-pex-rst-c5-in { + pex_rst { + nvidia,pins = "pex_l5_rst_n_paf1"; + nvidia,function = "rsvd1"; + nvidia,pull = ; + nvidia,tristate = ; + nvidia,enable-input = ; + }; + }; + + pex_rst_c6_in_state: pinmux-pex-rst-c6-in { + pex_rst { + nvidia,pins = "pex_l6_rst_n_paf3"; + nvidia,function = "rsvd1"; + nvidia,pull = ; + nvidia,tristate = ; + nvidia,enable-input = ; + }; + }; + + pex_rst_c7_in_state: pinmux-pex-rst-c7-in { + pex_rst { + nvidia,pins = "pex_l7_rst_n_pag1"; + nvidia,function = "rsvd1"; + nvidia,pull = ; + nvidia,tristate = ; + nvidia,enable-input = ; + }; + }; + + pex_rst_c10_in_state: pinmux-pex-rst-c10-in { + pex_rst { + nvidia,pins = "pex_l10_rst_n_pag7"; + nvidia,function = "rsvd1"; + nvidia,pull = ; + nvidia,tristate = ; + nvidia,enable-input = ; + }; + }; }; gpcdma: dma-controller@2600000 { @@ -4630,6 +4681,8 @@ <&bpmp TEGRA234_RESET_PEX2_CORE_10>; reset-names = "apb", "core"; + pinctrl-names = "default"; + pinctrl-0 = <&pex_rst_c10_in_state>; interrupts = ; /* controller interrupt */ interrupt-names = "intr"; @@ -4881,6 +4934,8 @@ <&bpmp TEGRA234_RESET_PEX0_CORE_4>; reset-names = "apb", "core"; + pinctrl-names = "default"; + pinctrl-0 = <&pex_rst_c4_in_state>; interrupts = ; /* controller interrupt */ interrupt-names = "intr"; nvidia,bpmp = <&bpmp 4>; @@ -5023,6 +5078,8 @@ <&bpmp TEGRA234_RESET_PEX1_CORE_5>; reset-names = "apb", "core"; + pinctrl-names = "default"; + pinctrl-0 = <&pex_rst_c5_in_state>; interrupts = ; /* controller interrupt */ interrupt-names = "intr"; @@ -5115,6 +5172,8 @@ <&bpmp TEGRA234_RESET_PEX1_CORE_6>; reset-names = "apb", "core"; + pinctrl-names = "default"; + pinctrl-0 = <&pex_rst_c6_in_state>; interrupts = ; /* controller interrupt */ interrupt-names = "intr"; @@ -5207,6 +5266,8 @@ <&bpmp TEGRA234_RESET_PEX2_CORE_7>; reset-names = "apb", "core"; + pinctrl-names = "default"; + pinctrl-0 = <&pex_rst_c7_in_state>; interrupts = ; /* controller interrupt */ interrupt-names = "intr"; diff --git a/arch/arm64/boot/dts/qcom/ipq5424.dtsi b/arch/arm64/boot/dts/qcom/ipq5424.dtsi index ef2b52f3597d9b..227d5ce2975151 100644 --- a/arch/arm64/boot/dts/qcom/ipq5424.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq5424.dtsi @@ -213,7 +213,7 @@ }; tfa@8a832000 { - reg = <0x0 0x8a832000 0x0 0x7d000>; + reg = <0x0 0x8a832000 0x0 0x80000>; no-map; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/qcom/lemans.dtsi b/arch/arm64/boot/dts/qcom/lemans.dtsi index cf685cb186edca..c2d2200d845b38 100644 --- a/arch/arm64/boot/dts/qcom/lemans.dtsi +++ b/arch/arm64/boot/dts/qcom/lemans.dtsi @@ -4106,6 +4106,7 @@ <&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_USB2 0>; interconnect-names = "usb-ddr", "apps-usb"; + qcom,select-utmi-as-pipe-clk; wakeup-source; iommus = <&apps_smmu 0x020 0x0>; diff --git a/arch/arm64/boot/dts/qcom/msm8994-msft-lumia-octagon.dtsi b/arch/arm64/boot/dts/qcom/msm8994-msft-lumia-octagon.dtsi index 4c983b10dd9252..7ace3540ef0a0e 100644 --- a/arch/arm64/boot/dts/qcom/msm8994-msft-lumia-octagon.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8994-msft-lumia-octagon.dtsi @@ -378,7 +378,7 @@ status = "okay"; sideinteraction: touch@2c { - compatible = "ad,ad7147_captouch"; + compatible = "adi,ad7147_captouch"; reg = <0x2c>; pinctrl-names = "default", "sleep"; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index c75b522f6eba66..33608b1d7d060b 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -3496,6 +3496,9 @@ <&gcc GCC_USB20_MASTER_CLK>; assigned-clock-rates = <19200000>, <60000000>; + interconnects = <&pnoc MASTER_USB_HS &bimc SLAVE_EBI_CH0>, + <&bimc MASTER_AMPSS_M0 &pnoc SLAVE_USB_HS>; + interconnect-names = "usb-ddr", "apps-usb"; power-domains = <&gcc USB30_GDSC>; qcom,select-utmi-as-pipe-clk; status = "disabled"; diff --git a/arch/arm64/boot/dts/qcom/qcm2290.dtsi b/arch/arm64/boot/dts/qcom/qcm2290.dtsi index 08141b41de2462..e0e400fdd2497e 100644 --- a/arch/arm64/boot/dts/qcom/qcm2290.dtsi +++ b/arch/arm64/boot/dts/qcom/qcm2290.dtsi @@ -1503,8 +1503,12 @@ gpu: gpu@5900000 { compatible = "qcom,adreno-07000200", "qcom,adreno"; - reg = <0x0 0x05900000 0x0 0x40000>; - reg-names = "kgsl_3d0_reg_memory"; + reg = <0x0 0x05900000 0x0 0x40000>, + <0x0 0x0599e000 0x0 0x1000>, + <0x0 0x05961000 0x0 0x800>; + reg-names = "kgsl_3d0_reg_memory", + "cx_mem", + "cx_dbgc"; interrupts = ; @@ -1685,25 +1689,25 @@ }; }; - camss: camss@5c6e000 { + camss: camss@5c11000 { compatible = "qcom,qcm2290-camss"; - reg = <0x0 0x5c6e000 0x0 0x1000>, + reg = <0x0 0x5c11000 0x0 0x1000>, + <0x0 0x5c6e000 0x0 0x1000>, <0x0 0x5c75000 0x0 0x1000>, <0x0 0x5c52000 0x0 0x1000>, <0x0 0x5c53000 0x0 0x1000>, <0x0 0x5c66000 0x0 0x400>, <0x0 0x5c68000 0x0 0x400>, - <0x0 0x5c11000 0x0 0x1000>, <0x0 0x5c6f000 0x0 0x4000>, <0x0 0x5c76000 0x0 0x4000>; - reg-names = "csid0", + reg-names = "top", + "csid0", "csid1", "csiphy0", "csiphy1", "csitpg0", "csitpg1", - "top", "vfe0", "vfe1"; diff --git a/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts b/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts index 519e458e1a8908..36d5750584831d 100644 --- a/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts +++ b/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts @@ -47,6 +47,8 @@ stride = <(1224 * 4)>; format = "a8r8g8b8"; clocks = <&gcc GCC_DISP_HF_AXI_CLK>; + vci-supply = <&vreg_oled_vci>; + dvdd-supply = <&vreg_oled_dvdd>; }; }; diff --git a/arch/arm64/boot/dts/qcom/qcm6490-shift-otter.dts b/arch/arm64/boot/dts/qcom/qcm6490-shift-otter.dts index eb8efba1b9dda4..cc99925798873c 100644 --- a/arch/arm64/boot/dts/qcom/qcm6490-shift-otter.dts +++ b/arch/arm64/boot/dts/qcom/qcm6490-shift-otter.dts @@ -118,6 +118,11 @@ no-map; }; + removed_mem: removed@c0000000 { + reg = <0x0 0xc0000000 0x0 0x5100000>; + no-map; + }; + rmtfs_mem: rmtfs@f8500000 { compatible = "qcom,rmtfs-mem"; reg = <0x0 0xf8500000 0x0 0x600000>; diff --git a/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts b/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts index 67ba508e92ba1f..3eedfb2cf4799c 100644 --- a/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts +++ b/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts @@ -649,7 +649,7 @@ &uart3 { /delete-property/ interrupts; interrupts-extended = <&intc GIC_SPI 330 IRQ_TYPE_LEVEL_HIGH>, - <&tlmm 11 IRQ_TYPE_LEVEL_HIGH>; + <&tlmm 11 IRQ_TYPE_EDGE_FALLING>; pinctrl-0 = <&uart3_default>; pinctrl-1 = <&uart3_sleep>; pinctrl-names = "default", "sleep"; diff --git a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts index bdf2d66e40c625..44ca3e61c33d49 100644 --- a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts +++ b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts @@ -694,7 +694,7 @@ &uart3 { interrupts-extended = <&intc GIC_SPI 330 IRQ_TYPE_LEVEL_HIGH>, - <&tlmm 11 IRQ_TYPE_LEVEL_HIGH>; + <&tlmm 11 IRQ_TYPE_EDGE_FALLING>; pinctrl-0 = <&uart3_default>; pinctrl-1 = <&uart3_sleep>; pinctrl-names = "default", "sleep"; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi index 279e5e6beae209..d89938e17e0930 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi @@ -967,8 +967,8 @@ <&aggre1_noc MASTER_QUP_2 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma2 0 6 QCOM_GPI_SPI>, - <&gpi_dma2 1 6 QCOM_GPI_SPI>; + dmas = <&gpi_dma2 0 0 QCOM_GPI_I2C>, + <&gpi_dma2 1 0 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -989,8 +989,8 @@ <&aggre1_noc MASTER_QUP_2 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma2 0 0 QCOM_GPI_I2C>, - <&gpi_dma2 1 0 QCOM_GPI_I2C>; + dmas = <&gpi_dma2 0 0 QCOM_GPI_SPI>, + <&gpi_dma2 1 0 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1011,8 +1011,8 @@ <&aggre1_noc MASTER_QUP_2 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma2 0 0 QCOM_GPI_SPI>, - <&gpi_dma2 1 0 QCOM_GPI_SPI>; + dmas = <&gpi_dma2 0 1 QCOM_GPI_I2C>, + <&gpi_dma2 1 1 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1033,8 +1033,8 @@ <&aggre1_noc MASTER_QUP_2 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma2 0 1 QCOM_GPI_I2C>, - <&gpi_dma2 1 1 QCOM_GPI_I2C>; + dmas = <&gpi_dma2 0 1 QCOM_GPI_SPI>, + <&gpi_dma2 1 1 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1069,8 +1069,8 @@ <&aggre1_noc MASTER_QUP_2 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma2 0 1 QCOM_GPI_SPI>, - <&gpi_dma2 1 1 QCOM_GPI_SPI>; + dmas = <&gpi_dma2 0 2 QCOM_GPI_I2C>, + <&gpi_dma2 1 2 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1091,8 +1091,8 @@ <&aggre1_noc MASTER_QUP_2 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma2 0 2 QCOM_GPI_I2C>, - <&gpi_dma2 1 2 QCOM_GPI_I2C>; + dmas = <&gpi_dma2 0 2 QCOM_GPI_SPI>, + <&gpi_dma2 1 2 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1131,8 +1131,8 @@ <&aggre1_noc MASTER_QUP_2 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma2 0 2 QCOM_GPI_SPI>, - <&gpi_dma2 1 2 QCOM_GPI_SPI>; + dmas = <&gpi_dma2 0 3 QCOM_GPI_I2C>, + <&gpi_dma2 1 3 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1153,8 +1153,8 @@ <&aggre1_noc MASTER_QUP_2 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma2 0 3 QCOM_GPI_I2C>, - <&gpi_dma2 1 3 QCOM_GPI_I2C>; + dmas = <&gpi_dma2 0 3 QCOM_GPI_SPI>, + <&gpi_dma2 1 3 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1175,8 +1175,8 @@ <&aggre1_noc MASTER_QUP_2 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma2 0 3 QCOM_GPI_SPI>, - <&gpi_dma2 1 3 QCOM_GPI_SPI>; + dmas = <&gpi_dma2 0 4 QCOM_GPI_I2C>, + <&gpi_dma2 1 4 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1197,8 +1197,8 @@ <&aggre1_noc MASTER_QUP_2 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma2 0 4 QCOM_GPI_I2C>, - <&gpi_dma2 1 4 QCOM_GPI_I2C>; + dmas = <&gpi_dma2 0 4 QCOM_GPI_SPI>, + <&gpi_dma2 1 4 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1241,8 +1241,8 @@ <&aggre1_noc MASTER_QUP_2 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma2 0 4 QCOM_GPI_SPI>, - <&gpi_dma2 1 4 QCOM_GPI_SPI>; + dmas = <&gpi_dma2 0 5 QCOM_GPI_SPI>, + <&gpi_dma2 1 5 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1285,8 +1285,8 @@ <&aggre1_noc MASTER_QUP_2 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma2 0 5 QCOM_GPI_SPI>, - <&gpi_dma2 1 5 QCOM_GPI_SPI>; + dmas = <&gpi_dma2 0 6 QCOM_GPI_SPI>, + <&gpi_dma2 1 6 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1338,7 +1338,7 @@ }; }; - gpi_dma0: dma-controller@900000 { + gpi_dma0: dma-controller@900000 { compatible = "qcom,sc8280xp-gpi-dma", "qcom,sm6350-gpi-dma"; reg = <0 0x00900000 0 0x60000>; @@ -1393,8 +1393,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 7 QCOM_GPI_I2C>, - <&gpi_dma0 1 7 QCOM_GPI_I2C>; + dmas = <&gpi_dma0 0 0 QCOM_GPI_I2C>, + <&gpi_dma0 1 0 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1415,8 +1415,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 0 QCOM_GPI_I2C>, - <&gpi_dma0 1 0 QCOM_GPI_I2C>; + dmas = <&gpi_dma0 0 0 QCOM_GPI_SPI>, + <&gpi_dma0 1 0 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1437,8 +1437,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 0 QCOM_GPI_SPI>, - <&gpi_dma0 1 0 QCOM_GPI_SPI>; + dmas = <&gpi_dma0 0 1 QCOM_GPI_I2C>, + <&gpi_dma0 1 1 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1459,8 +1459,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 1 QCOM_GPI_I2C>, - <&gpi_dma0 1 1 QCOM_GPI_I2C>; + dmas = <&gpi_dma0 0 1 QCOM_GPI_SPI>, + <&gpi_dma0 1 1 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1481,8 +1481,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 1 QCOM_GPI_SPI>, - <&gpi_dma0 1 1 QCOM_GPI_SPI>; + dmas = <&gpi_dma0 0 2 QCOM_GPI_I2C>, + <&gpi_dma0 1 2 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1503,8 +1503,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 2 QCOM_GPI_I2C>, - <&gpi_dma0 1 2 QCOM_GPI_I2C>; + dmas = <&gpi_dma0 0 2 QCOM_GPI_SPI>, + <&gpi_dma0 1 2 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1539,8 +1539,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 2 QCOM_GPI_SPI>, - <&gpi_dma0 1 2 QCOM_GPI_SPI>; + dmas = <&gpi_dma0 0 3 QCOM_GPI_I2C>, + <&gpi_dma0 1 3 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1561,8 +1561,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 3 QCOM_GPI_I2C>, - <&gpi_dma0 1 3 QCOM_GPI_I2C>; + dmas = <&gpi_dma0 0 3 QCOM_GPI_SPI>, + <&gpi_dma0 1 3 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1583,8 +1583,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 3 QCOM_GPI_SPI>, - <&gpi_dma0 1 3 QCOM_GPI_SPI>; + dmas = <&gpi_dma0 0 4 QCOM_GPI_I2C>, + <&gpi_dma0 1 4 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1605,8 +1605,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 4 QCOM_GPI_I2C>, - <&gpi_dma0 1 4 QCOM_GPI_I2C>; + dmas = <&gpi_dma0 0 4 QCOM_GPI_SPI>, + <&gpi_dma0 1 4 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1627,8 +1627,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 4 QCOM_GPI_SPI>, - <&gpi_dma0 1 4 QCOM_GPI_SPI>; + dmas = <&gpi_dma0 0 5 QCOM_GPI_I2C>, + <&gpi_dma0 1 5 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1649,8 +1649,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 5 QCOM_GPI_I2C>, - <&gpi_dma0 1 5 QCOM_GPI_I2C>; + dmas = <&gpi_dma0 0 5 QCOM_GPI_SPI>, + <&gpi_dma0 1 5 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1671,8 +1671,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 5 QCOM_GPI_SPI>, - <&gpi_dma0 1 5 QCOM_GPI_SPI>; + dmas = <&gpi_dma0 0 6 QCOM_GPI_I2C>, + <&gpi_dma0 1 6 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1693,8 +1693,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 6 QCOM_GPI_I2C>, - <&gpi_dma0 1 6 QCOM_GPI_I2C>; + dmas = <&gpi_dma0 0 6 QCOM_GPI_SPI>, + <&gpi_dma0 1 6 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1715,8 +1715,8 @@ <&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma0 0 6 QCOM_GPI_SPI>, - <&gpi_dma0 1 6 QCOM_GPI_SPI>; + dmas = <&gpi_dma0 0 7 QCOM_GPI_I2C>, + <&gpi_dma0 1 7 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1800,8 +1800,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 7 QCOM_GPI_I2C>, - <&gpi_dma1 1 7 QCOM_GPI_I2C>; + dmas = <&gpi_dma1 0 0 QCOM_GPI_I2C>, + <&gpi_dma1 1 0 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1822,8 +1822,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 0 QCOM_GPI_I2C>, - <&gpi_dma1 1 0 QCOM_GPI_I2C>; + dmas = <&gpi_dma1 0 0 QCOM_GPI_SPI>, + <&gpi_dma1 1 0 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1844,8 +1844,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 0 QCOM_GPI_SPI>, - <&gpi_dma1 1 0 QCOM_GPI_SPI>; + dmas = <&gpi_dma1 0 1 QCOM_GPI_I2C>, + <&gpi_dma1 1 1 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1866,8 +1866,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 1 QCOM_GPI_I2C>, - <&gpi_dma1 1 1 QCOM_GPI_I2C>; + dmas = <&gpi_dma1 0 1 QCOM_GPI_SPI>, + <&gpi_dma1 1 1 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1888,8 +1888,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 1 QCOM_GPI_SPI>, - <&gpi_dma1 1 1 QCOM_GPI_SPI>; + dmas = <&gpi_dma1 0 2 QCOM_GPI_I2C>, + <&gpi_dma1 1 2 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1910,8 +1910,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 2 QCOM_GPI_I2C>, - <&gpi_dma1 1 2 QCOM_GPI_I2C>; + dmas = <&gpi_dma1 0 2 QCOM_GPI_SPI>, + <&gpi_dma1 1 2 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1932,8 +1932,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 2 QCOM_GPI_SPI>, - <&gpi_dma1 1 2 QCOM_GPI_SPI>; + dmas = <&gpi_dma1 0 3 QCOM_GPI_I2C>, + <&gpi_dma1 1 3 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1954,8 +1954,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 3 QCOM_GPI_I2C>, - <&gpi_dma1 1 3 QCOM_GPI_I2C>; + dmas = <&gpi_dma1 0 3 QCOM_GPI_SPI>, + <&gpi_dma1 1 3 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -1976,8 +1976,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 3 QCOM_GPI_SPI>, - <&gpi_dma1 1 3 QCOM_GPI_SPI>; + dmas = <&gpi_dma1 0 4 QCOM_GPI_I2C>, + <&gpi_dma1 1 4 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -1998,8 +1998,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 4 QCOM_GPI_I2C>, - <&gpi_dma1 1 4 QCOM_GPI_I2C>; + dmas = <&gpi_dma1 0 4 QCOM_GPI_SPI>, + <&gpi_dma1 1 4 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -2020,8 +2020,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 4 QCOM_GPI_SPI>, - <&gpi_dma1 1 4 QCOM_GPI_SPI>; + dmas = <&gpi_dma1 0 5 QCOM_GPI_I2C>, + <&gpi_dma1 1 5 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -2042,8 +2042,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 5 QCOM_GPI_I2C>, - <&gpi_dma1 1 5 QCOM_GPI_I2C>; + dmas = <&gpi_dma1 0 5 QCOM_GPI_SPI>, + <&gpi_dma1 1 5 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -2064,8 +2064,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 5 QCOM_GPI_SPI>, - <&gpi_dma1 1 5 QCOM_GPI_SPI>; + dmas = <&gpi_dma1 0 6 QCOM_GPI_I2C>, + <&gpi_dma1 1 6 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -2086,8 +2086,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 6 QCOM_GPI_I2C>, - <&gpi_dma1 1 6 QCOM_GPI_I2C>; + dmas = <&gpi_dma1 0 6 QCOM_GPI_SPI>, + <&gpi_dma1 1 6 QCOM_GPI_SPI>; dma-names = "tx", "rx"; @@ -2108,8 +2108,8 @@ <&aggre1_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>; interconnect-names = "qup-core", "qup-config", "qup-memory"; - dmas = <&gpi_dma1 0 6 QCOM_GPI_SPI>, - <&gpi_dma1 1 6 QCOM_GPI_SPI>; + dmas = <&gpi_dma1 0 7 QCOM_GPI_I2C>, + <&gpi_dma1 1 7 QCOM_GPI_I2C>; dma-names = "tx", "rx"; @@ -5773,8 +5773,12 @@ clocks = <&rpmhcc RPMH_CXO_CLK>; clock-names = "xo"; - power-domains = <&rpmhpd SC8280XP_NSP>; - power-domain-names = "nsp"; + power-domains = <&rpmhpd SC8280XP_NSP>, + <&rpmhpd SC8280XP_CX>, + <&rpmhpd SC8280XP_MXC>; + power-domain-names = "nsp", + "cx", + "mxc"; memory-region = <&pil_nsp0_mem>; @@ -5904,8 +5908,12 @@ clocks = <&rpmhcc RPMH_CXO_CLK>; clock-names = "xo"; - power-domains = <&rpmhpd SC8280XP_NSP>; - power-domain-names = "nsp"; + power-domains = <&rpmhpd SC8280XP_NSP>, + <&rpmhpd SC8280XP_CX>, + <&rpmhpd SC8280XP_MXC>; + power-domain-names = "nsp", + "cx", + "mxc"; memory-region = <&pil_nsp1_mem>; diff --git a/arch/arm64/boot/dts/qcom/sdm630.dtsi b/arch/arm64/boot/dts/qcom/sdm630.dtsi index 8b1a45a4e56ed1..b383e480a394d4 100644 --- a/arch/arm64/boot/dts/qcom/sdm630.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm630.dtsi @@ -598,8 +598,8 @@ }; gpu_speed_bin: gpu-speed-bin@41a0 { - reg = <0x41a2 0x1>; - bits = <5 7>; + reg = <0x41a2 0x2>; + bits = <5 8>; }; }; diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts index 8abf3e909502f3..5147d6d3cc26bf 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts @@ -379,6 +379,12 @@ regulator-initial-mode = ; }; + vreg_l23a_3p3: ldo23 { + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3312000>; + regulator-initial-mode = ; + }; + vreg_l24a_3p075: ldo24 { regulator-min-microvolt = <3088000>; regulator-max-microvolt = <3088000>; @@ -850,7 +856,6 @@ status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&qup_spi0_default>; - cs-gpios = <&tlmm 3 GPIO_ACTIVE_LOW>; can@0 { compatible = "microchip,mcp2517fd"; @@ -1156,6 +1161,7 @@ vdd-1.8-xo-supply = <&vreg_l7a_1p8>; vdd-1.3-rfa-supply = <&vreg_l17a_1p3>; vdd-3.3-ch0-supply = <&vreg_l25a_3p3>; + vdd-3.3-ch1-supply = <&vreg_l23a_3p3>; qcom,snoc-host-cap-8bit-quirk; qcom,calibration-variant = "Thundercomm_DB845C"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi index dcfffb271fcf31..1036305231b208 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi @@ -160,7 +160,6 @@ gpio = <&tlmm 88 0>; enable-active-high; - regulator-boot-on; }; }; @@ -257,7 +256,7 @@ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; regulator-initial-mode = ; - regulator-always-on; + regulator-boot-on; }; vreg_l17a_1p3: ldo17 { @@ -803,8 +802,8 @@ bias-disable; }; - tri_state_key_default: tri-state-key-default-state { - pins = "gpio40", "gpio42", "gpio26"; + alert_slider_default: alert-slider-default-state { + pins = "gpio126", "gpio52", "gpio24"; function = "gpio"; drive-strength = <2>; bias-disable; diff --git a/arch/arm64/boot/dts/qcom/sdm845-samsung-starqltechn.dts b/arch/arm64/boot/dts/qcom/sdm845-samsung-starqltechn.dts index 75a53f0bbebd07..493c69e9917461 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-samsung-starqltechn.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-samsung-starqltechn.dts @@ -158,7 +158,7 @@ }; }; - i2c21 { + i2c-21 { compatible = "i2c-gpio"; sda-gpios = <&tlmm 127 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; scl-gpios = <&tlmm 128 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; @@ -599,15 +599,15 @@ &i2c14 { status = "okay"; - pmic@66 { + max77705: pmic@66 { compatible = "maxim,max77705"; reg = <0x66>; + #interrupt-cells = <1>; interrupt-parent = <&pm8998_gpios>; interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + interrupt-controller; pinctrl-0 = <&pmic_int_default>; pinctrl-names = "default"; - #address-cells = <1>; - #size-cells = <0>; leds { compatible = "maxim,max77705-rgb"; @@ -646,8 +646,8 @@ reg = <0x69>; compatible = "maxim,max77705-charger"; monitored-battery = <&battery>; - interrupt-parent = <&pm8998_gpios>; - interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + interrupt-parent = <&max77705>; + interrupts = <0>; }; fuel-gauge@36 { @@ -655,8 +655,8 @@ compatible = "maxim,max77705-battery"; power-supplies = <&max77705_charger>; maxim,rsns-microohm = <5000>; - interrupt-parent = <&pm8998_gpios>; - interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + interrupt-parent = <&max77705>; + interrupts = <2>; }; }; diff --git a/arch/arm64/boot/dts/qcom/sm6115.dtsi b/arch/arm64/boot/dts/qcom/sm6115.dtsi index 91fc36b59abf96..8b8395f6a2dfc2 100644 --- a/arch/arm64/boot/dts/qcom/sm6115.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6115.dtsi @@ -1715,8 +1715,12 @@ gpu: gpu@5900000 { compatible = "qcom,adreno-610.0", "qcom,adreno"; - reg = <0x0 0x05900000 0x0 0x40000>; - reg-names = "kgsl_3d0_reg_memory"; + reg = <0x0 0x05900000 0x0 0x40000>, + <0x0 0x0599e000 0x0 0x1000>, + <0x0 0x05961000 0x0 0x800>; + reg-names = "kgsl_3d0_reg_memory", + "cx_mem", + "cx_dbgc"; /* There's no (real) GMU, so we have to handle quite a bunch of clocks! */ clocks = <&gpucc GPU_CC_GX_GFX3D_CLK>, diff --git a/arch/arm64/boot/dts/qcom/sm6150.dtsi b/arch/arm64/boot/dts/qcom/sm6150.dtsi index 3d2a1cb02b628a..363b9f436cd0a2 100644 --- a/arch/arm64/boot/dts/qcom/sm6150.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6150.dtsi @@ -398,7 +398,6 @@ qup_opp_table: opp-table-qup { compatible = "operating-points-v2"; - opp-shared; opp-75000000 { opp-hz = /bits/ 64 <75000000>; @@ -1260,10 +1259,10 @@ <&gcc GCC_AGGRE_UFS_PHY_AXI_CLK>, <&gcc GCC_UFS_PHY_AHB_CLK>, <&gcc GCC_UFS_PHY_UNIPRO_CORE_CLK>, - <&gcc GCC_UFS_PHY_ICE_CORE_CLK>, <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_UFS_PHY_TX_SYMBOL_0_CLK>, - <&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>; + <&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>, + <&gcc GCC_UFS_PHY_ICE_CORE_CLK>; clock-names = "core_clk", "bus_aggr_clk", "iface_clk", diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi index 8459b27cacc72a..19a7b9f9ea8bcf 100644 --- a/arch/arm64/boot/dts/qcom/sm6350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi @@ -1180,11 +1180,11 @@ <0 0>, <0 0>, <37500000 150000000>, - <75000000 300000000>, <0 0>, <0 0>, <0 0>, - <0 0>; + <0 0>, + <75000000 300000000>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8250-samsung-common.dtsi b/arch/arm64/boot/dts/qcom/sm8250-samsung-common.dtsi index cf3d917addd828..ef7ea4f72bf999 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-samsung-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250-samsung-common.dtsi @@ -159,7 +159,8 @@ }; &tlmm { - gpio-reserved-ranges = <40 4>; /* I2C (Unused) */ + gpio-reserved-ranges = <20 4>, /* SPI (fingerprint scanner) */ + <40 4>; /* Unused */ }; &usb_1 { diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi index 7724dba75db79a..e294dc9c68c9ac 100644 --- a/arch/arm64/boot/dts/qcom/sm8550.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi @@ -4097,8 +4097,6 @@ usb_1: usb@a600000 { compatible = "qcom,sm8550-dwc3", "qcom,snps-dwc3"; reg = <0x0 0x0a600000 0x0 0xfc100>; - #address-cells = <1>; - #size-cells = <0>; clocks = <&gcc GCC_CFG_NOC_USB3_PRIM_AXI_CLK>, <&gcc GCC_USB30_PRIM_MASTER_CLK>, diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi index ebf1971b1bfbeb..d22a26a416ccc1 100644 --- a/arch/arm64/boot/dts/qcom/sm8650.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi @@ -3988,6 +3988,8 @@ iommus = <&apps_smmu 0x60 0>; + dma-coherent; + lanes-per-direction = <2>; qcom,ice = <&ice>; @@ -5113,9 +5115,6 @@ dma-coherent; - #address-cells = <1>; - #size-cells = <0>; - status = "disabled"; ports { diff --git a/arch/arm64/boot/dts/qcom/sm8750-mtp.dts b/arch/arm64/boot/dts/qcom/sm8750-mtp.dts index 3bbb53b7c71f3c..45b5f758156700 100644 --- a/arch/arm64/boot/dts/qcom/sm8750-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8750-mtp.dts @@ -960,9 +960,6 @@ }; &pcie0 { - wake-gpios = <&tlmm 104 GPIO_ACTIVE_HIGH>; - perst-gpios = <&tlmm 102 GPIO_ACTIVE_LOW>; - pinctrl-0 = <&pcie0_default_state>; pinctrl-names = "default"; @@ -977,6 +974,9 @@ }; &pcieport0 { + wake-gpios = <&tlmm 104 GPIO_ACTIVE_HIGH>; + reset-gpios = <&tlmm 102 GPIO_ACTIVE_LOW>; + wifi@0 { compatible = "pci17cb,1107"; reg = <0x10000 0x0 0x0 0x0 0x0>; diff --git a/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi b/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi index cc64558ed5e6fa..847b678f040c00 100644 --- a/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi +++ b/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi @@ -1023,7 +1023,6 @@ }; &mdss_dp0_out { - data-lanes = <0 1>; link-frequencies = /bits/ 64 <1620000000 2700000000 5400000000 8100000000>; }; @@ -1032,13 +1031,15 @@ }; &mdss_dp1_out { - data-lanes = <0 1>; link-frequencies = /bits/ 64 <1620000000 2700000000 5400000000 8100000000>; }; &mdss_dp3 { /delete-property/ #sound-dai-cells; + pinctrl-0 = <&edp0_hpd_default>; + pinctrl-names = "default"; + status = "okay"; aux-bus { diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi index 51576d9c935dec..512a75da4f13f1 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi @@ -791,8 +791,8 @@ #address-cells = <2>; #size-cells = <2>; - dma-ranges = <0 0 0 0 0x10 0>; - ranges = <0 0 0 0 0x10 0>; + dma-ranges = <0 0 0 0 0x100 0>; + ranges = <0 0 0 0 0x100 0>; gcc: clock-controller@100000 { compatible = "qcom,x1e80100-gcc"; @@ -2910,7 +2910,7 @@ reg = <0 0x00fda000 0 0x4000>; clocks = <&gcc GCC_USB3_SEC_PHY_AUX_CLK>, - <&rpmhcc RPMH_CXO_CLK>, + <&tcsr TCSR_USB4_1_CLKREF_EN>, <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>, <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>; clock-names = "aux", @@ -2981,7 +2981,7 @@ reg = <0 0x00fdf000 0 0x4000>; clocks = <&gcc GCC_USB3_TERT_PHY_AUX_CLK>, - <&rpmhcc RPMH_CXO_CLK>, + <&tcsr TCSR_USB4_2_CLKREF_EN>, <&gcc GCC_USB3_TERT_PHY_COM_AUX_CLK>, <&gcc GCC_USB3_TERT_PHY_PIPE_CLK>; clock-names = "aux", @@ -4922,6 +4922,7 @@ interconnect-names = "usb-ddr", "apps-usb"; + qcom,select-utmi-as-pipe-clk; wakeup-source; status = "disabled"; @@ -4939,15 +4940,8 @@ dma-coherent; - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - - usb_2_dwc3_hs: endpoint { - }; + port { + usb_2_dwc3_hs: endpoint { }; }; }; diff --git a/arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts b/arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts index 1da8e476b2193d..ff07d984cbf299 100644 --- a/arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts +++ b/arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts @@ -119,13 +119,13 @@ }; /* Page 27 / DSI to Display */ - mini-dp-con { + dp-con { compatible = "dp-connector"; label = "CN6"; type = "full-size"; port { - mini_dp_con_in: endpoint { + dp_con_in: endpoint { remote-endpoint = <&sn65dsi86_out>; }; }; @@ -407,7 +407,7 @@ port@1 { reg = <1>; sn65dsi86_out: endpoint { - remote-endpoint = <&mini_dp_con_in>; + remote-endpoint = <&dp_con_in>; }; }; }; diff --git a/arch/arm64/boot/dts/renesas/r9a09g047e57-smarc.dts b/arch/arm64/boot/dts/renesas/r9a09g047e57-smarc.dts index 08e814c03fa855..ed6fcdc337a0bd 100644 --- a/arch/arm64/boot/dts/renesas/r9a09g047e57-smarc.dts +++ b/arch/arm64/boot/dts/renesas/r9a09g047e57-smarc.dts @@ -8,7 +8,6 @@ /dts-v1/; /* Switch selection settings */ -#define SW_LCD_EN 0 #define SW_GPIO8_CAN0_STB 0 #define SW_GPIO9_CAN1_STB 0 #define SW_LCD_EN 0 diff --git a/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi b/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi index 5c91002c99c483..5384a43837c1d4 100644 --- a/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi +++ b/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi @@ -154,8 +154,7 @@ ctrl-pins { pinmux = , /* SD0_CLK */ , /* SD0_CMD */ - , /* SD0_CD */ - ; /* SD0_WP */ + ; /* SD0_CD */ }; }; @@ -212,6 +211,7 @@ pinctrl-names = "default", "state_uhs"; vmmc-supply = <®_3p3v>; vqmmc-supply = <&vqmmc_sdhi0>; + wp-gpios = <&pinctrl RZT2H_GPIO(22, 6) GPIO_ACTIVE_HIGH>; bus-width = <4>; sd-uhs-sdr50; sd-uhs-sdr104; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts index e7d4a2f9a95eaa..78a7775c3b2263 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts @@ -424,7 +424,6 @@ &pcie0 { ep-gpios = <&gpio2 RK_PD4 GPIO_ACTIVE_HIGH>; - max-link-speed = <2>; num-lanes = <2>; pinctrl-names = "default"; status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi index 8d94d9f91a5c66..3a9a10f531bdb2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi @@ -71,7 +71,6 @@ }; &pcie0 { - max-link-speed = <1>; num-lanes = <1>; vpcie3v3-supply = <&vcc3v3_sys>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts index 2dca1dca20b8ba..5de964d369b09a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts @@ -40,13 +40,13 @@ button-up { label = "Volume Up"; linux,code = ; - press-threshold-microvolt = <100000>; + press-threshold-microvolt = <2000>; }; button-down { label = "Volume Down"; linux,code = ; - press-threshold-microvolt = <600000>; + press-threshold-microvolt = <300000>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-rock-3c.dts b/arch/arm64/boot/dts/rockchip/rk3566-rock-3c.dts index 6224d72813e593..80ac40555e023a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-rock-3c.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-rock-3c.dts @@ -466,6 +466,7 @@ compatible = "belling,bl24c16a", "atmel,24c16"; reg = <0x50>; pagesize = <16>; + vcc-supply = <&vcca1v8_pmu>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3576-nanopi-m5.dts b/arch/arm64/boot/dts/rockchip/rk3576-nanopi-m5.dts index cce34c541f7c5f..bb2cc2814b83f2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576-nanopi-m5.dts +++ b/arch/arm64/boot/dts/rockchip/rk3576-nanopi-m5.dts @@ -201,6 +201,7 @@ pinctrl-names = "default"; pinctrl-0 = <&hp_det_l>; + simple-audio-card,bitclock-master = <&masterdai>; simple-audio-card,format = "i2s"; simple-audio-card,hp-det-gpios = <&gpio2 RK_PD6 GPIO_ACTIVE_LOW>; simple-audio-card,mclk-fs = <256>; @@ -211,15 +212,16 @@ "Headphones", "HPOR", "IN1P", "Microphone Jack"; simple-audio-card,widgets = - "Headphone", "Headphone Jack", + "Headphone", "Headphones", "Microphone", "Microphone Jack"; simple-audio-card,codec { sound-dai = <&rt5616>; }; - simple-audio-card,cpu { + masterdai: simple-audio-card,cpu { sound-dai = <&sai2>; + system-clock-frequency = <12288000>; }; }; }; @@ -727,10 +729,12 @@ rt5616: audio-codec@1b { compatible = "realtek,rt5616"; reg = <0x1b>; - assigned-clocks = <&cru CLK_SAI2_MCLKOUT>; + assigned-clocks = <&cru CLK_SAI2_MCLKOUT_TO_IO>; assigned-clock-rates = <12288000>; - clocks = <&cru CLK_SAI2_MCLKOUT>; + clocks = <&cru CLK_SAI2_MCLKOUT_TO_IO>; clock-names = "mclk"; + pinctrl-0 = <&sai2m0_mclk>; + pinctrl-names = "default"; #sound-dai-cells = <0>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3576.dtsi b/arch/arm64/boot/dts/rockchip/rk3576.dtsi index a86fc6b4e8c458..c72343e7a0456e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3576.dtsi @@ -1261,7 +1261,7 @@ gpu: gpu@27800000 { compatible = "rockchip,rk3576-mali", "arm,mali-bifrost"; - reg = <0x0 0x27800000 0x0 0x200000>; + reg = <0x0 0x27800000 0x0 0x20000>; assigned-clocks = <&scmi_clk SCMI_CLK_GPU>; assigned-clock-rates = <198000000>; clocks = <&cru CLK_GPU>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi index e2500e31c434a8..2973f6bae17165 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi @@ -1200,7 +1200,7 @@ status = "disabled"; }; - rknn_mmu_1: iommu@fdac9000 { + rknn_mmu_1: iommu@fdaca000 { compatible = "rockchip,rk3588-iommu", "rockchip,rk3568-iommu"; reg = <0x0 0xfdaca000 0x0 0x100>; interrupts = ; @@ -1230,7 +1230,7 @@ status = "disabled"; }; - rknn_mmu_2: iommu@fdad9000 { + rknn_mmu_2: iommu@fdada000 { compatible = "rockchip,rk3588-iommu", "rockchip,rk3568-iommu"; reg = <0x0 0xfdada000 0x0 0x100>; interrupts = ; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-5bp-5t.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-5bp-5t.dtsi index 3bbe78810ec6f2..7aac77dfc5f165 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-5bp-5t.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-5bp-5t.dtsi @@ -331,12 +331,12 @@ data-role = "dual"; /* fusb302 supports PD Rev 2.0 Ver 1.2 */ pd-revision = /bits/ 8 <0x2 0x0 0x1 0x2>; - power-role = "sink"; - try-power-role = "sink"; op-sink-microwatt = <1000000>; sink-pdos = , ; + source-pdos = + ; altmodes { displayport { diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-plus.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-plus.dts index 5e984a44120e40..07a840d9b38595 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-plus.dts @@ -110,6 +110,11 @@ }; }; +&usb_con { + power-role = "dual"; + try-power-role = "sink"; +}; + &usbdp_phy0 { pinctrl-names = "default"; pinctrl-0 = <&usbc_sbu_dc>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts index 8ef01010d985ba..da13dafcbc823b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts @@ -49,6 +49,10 @@ }; }; +&usb_con { + power-role = "sink"; +}; + &usbdp_phy0 { pinctrl-names = "default"; pinctrl-0 = <&usbc_sbu_dc>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts index c1763835f53d48..0dd90c744380b7 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts @@ -130,6 +130,10 @@ }; }; +&usb_con { + power-role = "source"; +}; + &usbdp_phy0 { pinctrl-names = "default"; pinctrl-0 = <&usbc_sbu_dc>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts index 19a08f7794e675..041a0fff22ccbd 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts @@ -228,6 +228,13 @@ regulator-off-in-suspend; }; }; + + eeprom: eeprom@50 { + compatible = "belling,bl24c16a", "atmel,24c16"; + reg = <0x50>; + pagesize = <16>; + vcc-supply = <&vcc_3v3_pmu>; + }; }; &i2c2 { @@ -249,12 +256,6 @@ regulator-off-in-suspend; }; }; - - eeprom: eeprom@50 { - compatible = "belling,bl24c16a", "atmel,24c16"; - reg = <0x50>; - pagesize = <16>; - }; }; &i2c3 { @@ -600,7 +601,7 @@ }; }; - vcc_3v3_s3: dcdc-reg8 { + vcc_3v3_pmu: vcc_3v3_s3: dcdc-reg8 { regulator-name = "vcc_3v3_s3"; regulator-always-on; regulator-boot-on; diff --git a/arch/arm64/boot/dts/st/stm32mp257f-ev1.dts b/arch/arm64/boot/dts/st/stm32mp257f-ev1.dts index 6e165073f7329d..bb6d6393d2e46d 100644 --- a/arch/arm64/boot/dts/st/stm32mp257f-ev1.dts +++ b/arch/arm64/boot/dts/st/stm32mp257f-ev1.dts @@ -266,6 +266,7 @@ &ommanager { memory-region = <&mm_ospi1>; + memory-region-names = "ospi1"; pinctrl-0 = <&ospi_port1_clk_pins_a &ospi_port1_io03_pins_a &ospi_port1_cs0_pins_a>; diff --git a/arch/arm64/boot/dts/ti/k3-am62-lp-sk-nand.dtso b/arch/arm64/boot/dts/ti/k3-am62-lp-sk-nand.dtso index 173ac60723b649..b4daa674eaa1e6 100644 --- a/arch/arm64/boot/dts/ti/k3-am62-lp-sk-nand.dtso +++ b/arch/arm64/boot/dts/ti/k3-am62-lp-sk-nand.dtso @@ -14,7 +14,7 @@ }; &main_pmx0 { - gpmc0_pins_default: gpmc0-pins-default { + gpmc0_pins_default: gpmc0-default-pins { pinctrl-single,pins = < AM62X_IOPAD(0x003c, PIN_INPUT, 0) /* (K19) GPMC0_AD0 */ AM62X_IOPAD(0x0040, PIN_INPUT, 0) /* (L19) GPMC0_AD1 */ diff --git a/arch/arm64/boot/dts/ti/k3-am62d2-evm.dts b/arch/arm64/boot/dts/ti/k3-am62d2-evm.dts index 83af889e790aeb..9a74df221f2ad3 100644 --- a/arch/arm64/boot/dts/ti/k3-am62d2-evm.dts +++ b/arch/arm64/boot/dts/ti/k3-am62d2-evm.dts @@ -146,6 +146,7 @@ regulator-name = "vdd_mmc1"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; + vin-supply = <&vcc_3v3_sys>; regulator-boot-on; enable-active-high; gpio = <&exp1 3 GPIO_ACTIVE_HIGH>; @@ -165,14 +166,16 @@ }; vddshv_sdio: regulator-6 { + /* output of TLV7103318QDSERQ1 */ compatible = "regulator-gpio"; regulator-name = "vddshv_sdio"; pinctrl-names = "default"; pinctrl-0 = <&vddshv_sdio_pins_default>; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; + vin-supply = <&vcc_5v0>; regulator-boot-on; - gpios = <&main_gpio1 31 GPIO_ACTIVE_HIGH>; + gpios = <&main_gpio0 59 GPIO_ACTIVE_HIGH>; states = <1800000 0x0>, <3300000 0x1>; bootph-all; @@ -198,7 +201,7 @@ pmic_irq_pins_default: pmic-irq-default-pins { pinctrl-single,pins = < - AM62DX_MCU_IOPAD(0x000, PIN_INPUT, 7) /* (E11) MCU_GPIO0_0 */ + AM62DX_IOPAD(0x01f4, PIN_INPUT, 7) /* (F17) EXTINTn.GPIO1_31 */ >; }; @@ -334,7 +337,7 @@ vddshv_sdio_pins_default: vddshv-sdio-default-pins { pinctrl-single,pins = < - AM62DX_IOPAD(0x1f4, PIN_OUTPUT, 7) /* (M19) GPMC0_CLK.GPIO1_31 */ + AM62DX_IOPAD(0x00f0, PIN_INPUT, 7) /* (Y21) GPIO0_59 */ >; bootph-all; }; diff --git a/arch/arm64/boot/dts/ti/k3-am62p.dtsi b/arch/arm64/boot/dts/ti/k3-am62p.dtsi index 75a15c368c11b0..dd24c40c7965d7 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62p.dtsi @@ -59,7 +59,7 @@ <0x00 0x01000000 0x00 0x01000000 0x00 0x01b28400>, /* First peripheral window */ <0x00 0x08000000 0x00 0x08000000 0x00 0x00200000>, /* Main CPSW */ <0x00 0x0e000000 0x00 0x0e000000 0x00 0x01d20000>, /* Second peripheral window */ - <0x00 0x0fd00000 0x00 0x0fd00000 0x00 0x00020000>, /* GPU */ + <0x00 0x0fd80000 0x00 0x0fd80000 0x00 0x00080000>, /* GPU */ <0x00 0x20000000 0x00 0x20000000 0x00 0x0a008000>, /* Third peripheral window */ <0x00 0x30040000 0x00 0x30040000 0x00 0x00080000>, /* PRUSS-M */ <0x00 0x30101000 0x00 0x30101000 0x00 0x00010100>, /* CSI window */ diff --git a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-peb-c-010.dtso b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-peb-c-010.dtso index 7fc73cfacadb8c..1176a52d560b71 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-peb-c-010.dtso +++ b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-peb-c-010.dtso @@ -30,13 +30,10 @@ <&main_pktdma 0xc206 15>, /* egress slice 1 */ <&main_pktdma 0xc207 15>, /* egress slice 1 */ <&main_pktdma 0x4200 15>, /* ingress slice 0 */ - <&main_pktdma 0x4201 15>, /* ingress slice 1 */ - <&main_pktdma 0x4202 0>, /* mgmnt rsp slice 0 */ - <&main_pktdma 0x4203 0>; /* mgmnt rsp slice 1 */ + <&main_pktdma 0x4201 15>; /* ingress slice 1 */ dma-names = "tx0-0", "tx0-1", "tx0-2", "tx0-3", "tx1-0", "tx1-1", "tx1-2", "tx1-3", - "rx0", "rx1", - "rxmgm0", "rxmgm1"; + "rx0", "rx1"; firmware-name = "ti-pruss/am65x-sr2-pru0-prueth-fw.elf", "ti-pruss/am65x-sr2-rtu0-prueth-fw.elf", diff --git a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-x27-gpio1-spi1-uart3.dtso b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-x27-gpio1-spi1-uart3.dtso index 996c42ec4253e2..bea8efa3e90941 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-x27-gpio1-spi1-uart3.dtso +++ b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-x27-gpio1-spi1-uart3.dtso @@ -20,13 +20,13 @@ }; &main_pmx0 { - main_gpio1_exp_header_gpio_pins_default: main-gpio1-exp-header-gpio-pins-default { + main_gpio1_exp_header_gpio_pins_default: main-gpio1-exp-header-gpio-default-pins { pinctrl-single,pins = < AM64X_IOPAD(0x0220, PIN_INPUT, 7) /* (D14) SPI1_CS1.GPIO1_48 */ >; }; - main_spi1_pins_default: main-spi1-pins-default { + main_spi1_pins_default: main-spi1-default-pins { pinctrl-single,pins = < AM64X_IOPAD(0x0224, PIN_INPUT, 0) /* (C14) SPI1_CLK */ AM64X_IOPAD(0x021C, PIN_OUTPUT, 0) /* (B14) SPI1_CS0 */ @@ -35,7 +35,7 @@ >; }; - main_uart3_pins_default: main-uart3-pins-default { + main_uart3_pins_default: main-uart3-default-pins { pinctrl-single,pins = < AM64X_IOPAD(0x0048, PIN_INPUT, 2) /* (U20) GPMC0_AD3.UART3_RXD */ AM64X_IOPAD(0x004c, PIN_OUTPUT, 2) /* (U18) GPMC0_AD4.UART3_TXD */ @@ -52,7 +52,7 @@ &main_spi1 { pinctrl-names = "default"; pinctrl-0 = <&main_spi1_pins_default>; - ti,pindir-d0-out-d1-in = <1>; + ti,pindir-d0-out-d1-in; status = "okay"; }; diff --git a/arch/arm64/boot/dts/ti/k3-am69-sk.dts b/arch/arm64/boot/dts/ti/k3-am69-sk.dts index 5896e57b5b9ed6..0e2d12cb051da8 100644 --- a/arch/arm64/boot/dts/ti/k3-am69-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-am69-sk.dts @@ -236,8 +236,8 @@ main_i2c0_pins_default: main-i2c0-default-pins { pinctrl-single,pins = < - J784S4_IOPAD(0x0e0, PIN_INPUT_PULLUP, 0) /* (AN36) I2C0_SCL */ - J784S4_IOPAD(0x0e4, PIN_INPUT_PULLUP, 0) /* (AP37) I2C0_SDA */ + J784S4_IOPAD(0x0e0, PIN_INPUT, 0) /* (AN36) I2C0_SCL */ + J784S4_IOPAD(0x0e4, PIN_INPUT, 0) /* (AP37) I2C0_SDA */ >; }; @@ -416,8 +416,8 @@ mcu_i2c0_pins_default: mcu-i2c0-default-pins { pinctrl-single,pins = < - J784S4_WKUP_IOPAD(0x0a0, PIN_INPUT_PULLUP, 0) /* (M35) MCU_I2C0_SCL */ - J784S4_WKUP_IOPAD(0x0a4, PIN_INPUT_PULLUP, 0) /* (G34) MCU_I2C0_SDA */ + J784S4_WKUP_IOPAD(0x0a0, PIN_INPUT, 0) /* (M35) MCU_I2C0_SCL */ + J784S4_WKUP_IOPAD(0x0a4, PIN_INPUT, 0) /* (G34) MCU_I2C0_SDA */ >; }; diff --git a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts index 5e5784ef6f8585..77dcc160eda3f7 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts @@ -474,6 +474,12 @@ J721E_IOPAD(0x234, PIN_INPUT, 7) /* (U3) EXT_REFCLK1.GPIO1_12 */ >; }; + + vdd_sd_dv_pins_default: vdd-sd-dv-default-pins { + pinctrl-single,pins = < + J721E_IOPAD(0x1dc, PIN_OUTPUT, 7) /* (Y1) SPI1_CLK.GPIO0_118 */ + >; + }; }; &wkup_pmx0 { @@ -536,12 +542,6 @@ >; }; - vdd_sd_dv_pins_default: vdd-sd-dv-default-pins { - pinctrl-single,pins = < - J721E_IOPAD(0x1dc, PIN_OUTPUT, 7) /* (Y1) SPI1_CLK.GPIO0_118 */ - >; - }; - wkup_uart0_pins_default: wkup-uart0-default-pins { pinctrl-single,pins = < J721E_WKUP_IOPAD(0xa0, PIN_INPUT, 0) /* (J29) WKUP_UART0_RXD */ diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-evm-common.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-evm-common.dtsi index 419c1a70e028d0..2834f0a8bbee05 100644 --- a/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-evm-common.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-evm-common.dtsi @@ -270,8 +270,8 @@ main_i2c0_pins_default: main-i2c0-default-pins { pinctrl-single,pins = < - J784S4_IOPAD(0x0e0, PIN_INPUT_PULLUP, 0) /* (AN36) I2C0_SCL */ - J784S4_IOPAD(0x0e4, PIN_INPUT_PULLUP, 0) /* (AP37) I2C0_SDA */ + J784S4_IOPAD(0x0e0, PIN_INPUT, 0) /* (AN36) I2C0_SCL */ + J784S4_IOPAD(0x0e4, PIN_INPUT, 0) /* (AP37) I2C0_SDA */ >; }; diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-main-common.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-main-common.dtsi index 9cc0901d58fbf9..c2636e624f18ba 100644 --- a/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-main-common.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j784s4-j742s2-main-common.dtsi @@ -2378,42 +2378,6 @@ assigned-clock-parents = <&k3_clks 351 4>; }; - watchdog4: watchdog@2240000 { - compatible = "ti,j7-rti-wdt"; - reg = <0x00 0x2240000 0x00 0x100>; - clocks = <&k3_clks 352 0>; - power-domains = <&k3_pds 352 TI_SCI_PD_EXCLUSIVE>; - assigned-clocks = <&k3_clks 352 0>; - assigned-clock-parents = <&k3_clks 352 4>; - }; - - watchdog5: watchdog@2250000 { - compatible = "ti,j7-rti-wdt"; - reg = <0x00 0x2250000 0x00 0x100>; - clocks = <&k3_clks 353 0>; - power-domains = <&k3_pds 353 TI_SCI_PD_EXCLUSIVE>; - assigned-clocks = <&k3_clks 353 0>; - assigned-clock-parents = <&k3_clks 353 4>; - }; - - watchdog6: watchdog@2260000 { - compatible = "ti,j7-rti-wdt"; - reg = <0x00 0x2260000 0x00 0x100>; - clocks = <&k3_clks 354 0>; - power-domains = <&k3_pds 354 TI_SCI_PD_EXCLUSIVE>; - assigned-clocks = <&k3_clks 354 0>; - assigned-clock-parents = <&k3_clks 354 4>; - }; - - watchdog7: watchdog@2270000 { - compatible = "ti,j7-rti-wdt"; - reg = <0x00 0x2270000 0x00 0x100>; - clocks = <&k3_clks 355 0>; - power-domains = <&k3_pds 355 TI_SCI_PD_EXCLUSIVE>; - assigned-clocks = <&k3_clks 355 0>; - assigned-clock-parents = <&k3_clks 355 4>; - }; - /* * The following RTI instances are coupled with MCU R5Fs, c7x and * GPU so keeping them reserved as these will be used by their diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi index 0160fe0da98388..78fcd0c40abcfa 100644 --- a/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi @@ -6,17 +6,40 @@ */ &cbass_main { - c71_3: dsp@67800000 { - compatible = "ti,j721s2-c71-dsp"; - reg = <0x00 0x67800000 0x00 0x00080000>, - <0x00 0x67e00000 0x00 0x0000c000>; - reg-names = "l2sram", "l1dram"; - resets = <&k3_reset 40 1>; - firmware-name = "j784s4-c71_3-fw"; - ti,sci = <&sms>; - ti,sci-dev-id = <40>; - ti,sci-proc-ids = <0x33 0xff>; - status = "disabled"; + watchdog4: watchdog@2240000 { + compatible = "ti,j7-rti-wdt"; + reg = <0x00 0x2240000 0x00 0x100>; + clocks = <&k3_clks 352 0>; + power-domains = <&k3_pds 352 TI_SCI_PD_EXCLUSIVE>; + assigned-clocks = <&k3_clks 352 0>; + assigned-clock-parents = <&k3_clks 352 4>; + }; + + watchdog5: watchdog@2250000 { + compatible = "ti,j7-rti-wdt"; + reg = <0x00 0x2250000 0x00 0x100>; + clocks = <&k3_clks 353 0>; + power-domains = <&k3_pds 353 TI_SCI_PD_EXCLUSIVE>; + assigned-clocks = <&k3_clks 353 0>; + assigned-clock-parents = <&k3_clks 353 4>; + }; + + watchdog6: watchdog@2260000 { + compatible = "ti,j7-rti-wdt"; + reg = <0x00 0x2260000 0x00 0x100>; + clocks = <&k3_clks 354 0>; + power-domains = <&k3_pds 354 TI_SCI_PD_EXCLUSIVE>; + assigned-clocks = <&k3_clks 354 0>; + assigned-clock-parents = <&k3_clks 354 4>; + }; + + watchdog7: watchdog@2270000 { + compatible = "ti,j7-rti-wdt"; + reg = <0x00 0x2270000 0x00 0x100>; + clocks = <&k3_clks 355 0>; + power-domains = <&k3_pds 355 TI_SCI_PD_EXCLUSIVE>; + assigned-clocks = <&k3_clks 355 0>; + assigned-clock-parents = <&k3_clks 355 4>; }; pcie2_rc: pcie@2920000 { @@ -113,6 +136,19 @@ status = "disabled"; }; }; + + c71_3: dsp@67800000 { + compatible = "ti,j721s2-c71-dsp"; + reg = <0x00 0x67800000 0x00 0x00080000>, + <0x00 0x67e00000 0x00 0x0000c000>; + reg-names = "l2sram", "l1dram"; + resets = <&k3_reset 40 1>; + firmware-name = "j784s4-c71_3-fw"; + ti,sci = <&sms>; + ti,sci-dev-id = <40>; + ti,sci-proc-ids = <0x33 0xff>; + status = "disabled"; + }; }; &scm_conf { diff --git a/arch/arm64/configs/asahi.config b/arch/arm64/configs/asahi.config new file mode 100644 index 00000000000000..7ed0a173544025 --- /dev/null +++ b/arch/arm64/configs/asahi.config @@ -0,0 +1,74 @@ +CONFIG_RUST=y +CONFIG_ARM64_ACTLR_STATE=y +CONFIG_ARCH_APPLE=y +# CONFIG_ARM64_4K_PAGES is not set +CONFIG_ARM64_16K_PAGES=y +# CONFIG_ARM64_64K_PAGES is not set +CONFIG_ARM64_MEMORY_MODEL_CONTROL=y +CONFIG_ARM_APPLE_CPUIDLE=y +CONFIG_ARM_APPLE_SOC_CPUFREQ=m +CONFIG_BT_HCIBCM4377=m +CONFIG_PCIE_APPLE=m +CONFIG_NVME_APPLE=m +CONFIG_BRCMFMAC=m +CONFIG_BRCMFMAC_PCIE=y +CONFIG_TOUCHSCREEN_APPLE_Z2=m +CONFIG_INPUT_MACSMC_INPUT=m +CONFIG_I2C_APPLE=m +CONFIG_SPI_APPLE=m +CONFIG_SPMI_APPLE=m +CONFIG_PINCTRL_APPLE_GPIO=m +CONFIG_GPIO_MACSMC=m +CONFIG_POWER_RESET_MACSMC=m +CONFIG_CHARGER_MACSMC=m +CONFIG_SENSORS_MACSMC_HWMON=m +CONFIG_APPLE_WATCHDOG=m +CONFIG_VIDEO_APPLE_ISP=m +CONFIG_DRM=y +CONFIG_DRM_ASAHI=m +CONFIG_DRM_ADP=m +CONFIG_DRM_APPLE=m +CONFIG_DRM_APPLE_AUDIO=y +CONFIG_SND_SOC_APPLE_AOP_AUDIO=m +CONFIG_SND_SOC_APPLE_MCA=m +CONFIG_SND_SOC_APPLE_MACAUDIO=m +CONFIG_SND_SOC_CS42L83=m +CONFIG_SND_SOC_CS42L84=m +CONFIG_SND_SOC_TAS2764=m +CONFIG_SND_SOC_TAS2770=m +CONFIG_HID_APPLE=m +CONFIG_HID_MAGICMOUSE=m +CONFIG_SERIAL_SAMSUNG=y +CONFIG_SERIAL_SAMSUNG_CONSOLE=y +CONFIG_HID_DOCKCHANNEL=m +CONFIG_SPI_HID_APPLE_OF=m +CONFIG_SPI_HID_APPLE_CORE=m +CONFIG_USB_DWC3_APPLE=m +CONFIG_USB_XHCI_PCI_ASMEDIA=y +CONFIG_RTC_DRV_MACSMC=m +CONFIG_APPLE_ADMAC=m +CONFIG_APPLE_SIO=m +CONFIG_MFD_MACSMC=m +CONFIG_COMMON_CLK_APPLE_NCO=m +CONFIG_APPLE_DART=m +CONFIG_APPLE_DOCKCHANNEL=m +CONFIG_APPLE_MAILBOX=y +CONFIG_APPLE_PMGR_MISC=y +CONFIG_APPLE_RTKIT=y +CONFIG_APPLE_RTKIT_HELPER=m +CONFIG_APPLE_SART=m +CONFIG_RUST_APPLE_RTKIT=y +CONFIG_APPLE_AOP=m +CONFIG_APPLE_SEP=m +CONFIG_APPLE_PMGR_PWRSTATE=y +CONFIG_IIO_AOP_SENSOR_LAS=m +CONFIG_IIO_AOP_SENSOR_ALS=m +CONFIG_RUST_FW_LOADER_ABSTRACTIONS=y +CONFIG_PWM_APPLE=m +CONFIG_APPLE_AIC=y +CONFIG_PHY_APPLE_ATC=m +CONFIG_PHY_APPLE_DPTX=m +CONFIG_APPLE_M1_CPU_PMU=y +CONFIG_NVMEM_APPLE_EFUSES=m +CONFIG_NVMEM_APPLE_SPMI=m +CONFIG_MUX_APPLE_DPXBAR=m diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 1a48faad2473a9..32861d08a3b827 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -662,7 +662,6 @@ CONFIG_PINCTRL_LPASS_LPI=m CONFIG_PINCTRL_SC7280_LPASS_LPI=m CONFIG_PINCTRL_SM6115_LPASS_LPI=m CONFIG_PINCTRL_SM8250_LPASS_LPI=m -CONFIG_PINCTRL_SM8350_LPASS_LPI=m CONFIG_PINCTRL_SM8450_LPASS_LPI=m CONFIG_PINCTRL_SC8280XP_LPASS_LPI=m CONFIG_PINCTRL_SM8550_LPASS_LPI=m diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 4995b6e2233501..9625570dc35359 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -133,7 +133,7 @@ static int ghash_finup(struct shash_desc *desc, const u8 *src, u8 buf[GHASH_BLOCK_SIZE] = {}; memcpy(buf, src, len); - ghash_do_simd_update(1, ctx->digest, src, key, NULL, + ghash_do_simd_update(1, ctx->digest, buf, key, NULL, pmull_ghash_update_p8); memzero_explicit(buf, sizeof(buf)); } diff --git a/arch/arm64/include/asm/apple_cpufeature.h b/arch/arm64/include/asm/apple_cpufeature.h new file mode 100644 index 00000000000000..4370d91ffa3ec9 --- /dev/null +++ b/arch/arm64/include/asm/apple_cpufeature.h @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifndef __ASM_APPLE_CPUFEATURES_H +#define __ASM_APPLE_CPUFEATURES_H + +#include +#include + +#define AIDR_APPLE_TSO_SHIFT 9 +#define AIDR_APPLE_TSO BIT(9) + +#define ACTLR_APPLE_TSO_SHIFT 1 +#define ACTLR_APPLE_TSO BIT(1) + +#endif diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index e223cbf350e49c..ccea6e4b696186 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -955,6 +955,12 @@ static inline unsigned int get_vmid_bits(u64 mmfr1) return 8; } +static __always_inline bool system_has_actlr_state(void) +{ + return IS_ENABLED(CONFIG_ARM64_ACTLR_STATE) && + alternative_has_cap_unlikely(ARM64_HAS_TSO_APPLE); +} + s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, s64 cur); struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id); @@ -1078,6 +1084,10 @@ static inline bool cpu_has_lpa2(void) #endif } +void __init init_cpucap_indirect_list_impdef(void); +void __init init_cpucap_indirect_list_from_array(const struct arm64_cpu_capabilities *caps); +bool cpufeature_matches(u64 reg, const struct arm64_cpu_capabilities *entry); + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index c9eab316398e2e..32088a71dc10bf 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -103,6 +103,11 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) { if (!vcpu_has_run_once(vcpu)) vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS; + if (IS_ENABLED(CONFIG_ARM64_ACTLR_STATE) && ( + alternative_has_cap_unlikely(ARM64_HAS_ACTLR_VIRT) || + alternative_has_cap_unlikely(ARM64_HAS_ACTLR_VIRT_APPLE) + )) + vcpu->arch.hcr_el2 &= ~HCR_TACR; /* * For non-FWB CPUs, we trap VM ops (HCR_EL2.TVM) until M+C diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index f1505c4acb389a..41b97936f3025f 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -112,7 +112,7 @@ #define DIRECT_MAP_PHYSMEM_END __pa(PAGE_END - 1) -#define MIN_THREAD_SHIFT (14 + KASAN_THREAD_SHIFT) +#define MIN_THREAD_SHIFT (15 + KASAN_THREAD_SHIFT) /* * VMAP'd stacks are allocated at page granularity, so we must ensure that such diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 61d62bfd5a7bfc..a8dad2c6788c3e 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -194,6 +194,9 @@ struct thread_struct { u64 gcs_base; u64 gcs_size; #endif +#ifdef CONFIG_ARM64_ACTLR_STATE + u64 actlr; +#endif }; static inline unsigned int thread_get_vl(struct thread_struct *thread, diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h index 0cde2f473971e8..eb60c973555305 100644 --- a/arch/arm64/include/asm/suspend.h +++ b/arch/arm64/include/asm/suspend.h @@ -2,7 +2,7 @@ #ifndef __ASM_SUSPEND_H #define __ASM_SUSPEND_H -#define NR_CTX_REGS 13 +#define NR_CTX_REGS 14 #define NR_CALLEE_SAVED_REGS 12 /* diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 76f32e424065e5..70bf2f40a0e4dd 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -34,6 +34,7 @@ obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ cpufeature.o alternative.o cacheinfo.o \ smp.o smp_spin_table.o topology.o smccc-call.o \ syscall.o proton-pack.o idle.o patching.o pi/ \ + cpufeature_impdef.o \ rsi.o jump_label.o obj-$(CONFIG_COMPAT) += sys32.o signal32.o \ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index e25b0f84a22daf..881ff8c901498a 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1080,7 +1080,7 @@ static void init_cpu_ftr_reg(u32 sys_reg, u64 new) extern const struct arm64_cpu_capabilities arm64_errata[]; static const struct arm64_cpu_capabilities arm64_features[]; -static void __init +void __init init_cpucap_indirect_list_from_array(const struct arm64_cpu_capabilities *caps) { for (; caps->matches; caps++) { @@ -1592,8 +1592,8 @@ has_always(const struct arm64_cpu_capabilities *entry, int scope) return true; } -static bool -feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry) +bool +cpufeature_matches(u64 reg, const struct arm64_cpu_capabilities *entry) { int val, min, max; u64 tmp; @@ -1646,14 +1646,14 @@ has_user_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope) if (!mask) return false; - return feature_matches(val, entry); + return cpufeature_matches(val, entry); } static bool has_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope) { u64 val = read_scoped_sysreg(entry, scope); - return feature_matches(val, entry); + return cpufeature_matches(val, entry); } const struct cpumask *system_32bit_el0_cpumask(void) @@ -3829,6 +3829,7 @@ void __init setup_boot_cpu_features(void) * handle the boot CPU. */ init_cpucap_indirect_list(); + init_cpucap_indirect_list_impdef(); /* * Detect broken pseudo-NMI. Must be called _before_ the call to diff --git a/arch/arm64/kernel/cpufeature_impdef.c b/arch/arm64/kernel/cpufeature_impdef.c new file mode 100644 index 00000000000000..aee7571fbadb84 --- /dev/null +++ b/arch/arm64/kernel/cpufeature_impdef.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Contains implementation-defined CPU feature definitions. + */ + +#define pr_fmt(fmt) "CPU features: " fmt + +#include +#include +#include +#include +#include + +#ifdef CONFIG_ARM64_MEMORY_MODEL_CONTROL +static bool has_apple_feature(const struct arm64_cpu_capabilities *entry, int scope) +{ + u64 val; + WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible()); + + if (read_cpuid_implementor() != ARM_CPU_IMP_APPLE) + return false; + + val = read_sysreg(aidr_el1); + return cpufeature_matches(val, entry); +} + +static bool has_apple_tso(const struct arm64_cpu_capabilities *entry, int scope) +{ + u64 val; + + if (!has_apple_feature(entry, scope)) + return false; + + /* + * KVM and old versions of the macOS hypervisor will advertise TSO in + * AIDR_EL1, but then ignore writes to ACTLR_EL1. Test that the bit is + * actually writable before enabling TSO. + */ + + val = read_sysreg(actlr_el1); + write_sysreg(val ^ ACTLR_APPLE_TSO, actlr_el1); + if (!((val ^ read_sysreg(actlr_el1)) & ACTLR_APPLE_TSO)) { + pr_info_once("CPU advertises Apple TSO but it is broken, ignoring\n"); + return false; + } + + write_sysreg(val, actlr_el1); + return true; +} + +static bool has_tso_fixed(const struct arm64_cpu_capabilities *entry, int scope) +{ + /* List of CPUs that always use the TSO memory model */ + static const struct midr_range fixed_tso_list[] = { + MIDR_ALL_VERSIONS(MIDR_NVIDIA_DENVER), + MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), + MIDR_ALL_VERSIONS(MIDR_FUJITSU_A64FX), + { /* sentinel */ } + }; + + return is_midr_in_range_list(fixed_tso_list); +} +#endif + +static bool has_apple_actlr_virt_impdef(const struct arm64_cpu_capabilities *entry, int scope) +{ + u64 midr = read_cpuid_id() & MIDR_CPU_MODEL_MASK; + + return midr >= MIDR_APPLE_M1_ICESTORM && midr <= MIDR_APPLE_M1_FIRESTORM_MAX; +} + +static bool has_apple_actlr_virt(const struct arm64_cpu_capabilities *entry, int scope) +{ + u64 midr = read_cpuid_id() & MIDR_CPU_MODEL_MASK; + + return midr >= MIDR_APPLE_M2_BLIZZARD && midr <= MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, 0xfff); +} + +static const struct arm64_cpu_capabilities arm64_impdef_features[] = { +#ifdef CONFIG_ARM64_MEMORY_MODEL_CONTROL + { + .desc = "TSO memory model (Apple)", + .capability = ARM64_HAS_TSO_APPLE, + .type = ARM64_CPUCAP_EARLY_LOCAL_CPU_FEATURE, + .matches = has_apple_tso, + .field_pos = AIDR_APPLE_TSO_SHIFT, + .field_width = 1, + .sign = FTR_UNSIGNED, + .min_field_value = 1, + .max_field_value = 1, + }, + { + .desc = "TSO memory model (Fixed)", + .capability = ARM64_HAS_TSO_FIXED, + .type = ARM64_CPUCAP_EARLY_LOCAL_CPU_FEATURE, + .matches = has_tso_fixed, + }, +#endif + { + .desc = "ACTLR virtualization (IMPDEF, Apple)", + .capability = ARM64_HAS_ACTLR_VIRT_APPLE, + .type = ARM64_CPUCAP_EARLY_LOCAL_CPU_FEATURE, + .matches = has_apple_actlr_virt_impdef, + }, + { + .desc = "ACTLR virtualization (architectural?)", + .capability = ARM64_HAS_ACTLR_VIRT, + .type = ARM64_CPUCAP_EARLY_LOCAL_CPU_FEATURE, + .matches = has_apple_actlr_virt, + }, + {}, +}; + +void __init init_cpucap_indirect_list_impdef(void) +{ + init_cpucap_indirect_list_from_array(arm64_impdef_features); +} diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 18749e9a6c2da4..9717568518ba74 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -402,7 +402,7 @@ int swsusp_arch_suspend(void) * Memory allocated by get_safe_page() will be dealt with by the hibernate code, * we don't need to free it here. */ -int swsusp_arch_resume(void) +int __nocfi swsusp_arch_resume(void) { int rc; void *zero_page; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index fba7ca102a8c42..59c416cfcdd2a4 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -41,8 +41,10 @@ #include #include #include +#include #include +#include #include #include #include @@ -292,6 +294,7 @@ static void flush_gcs(void) current->thread.gcs_base = 0; current->thread.gcs_size = 0; current->thread.gcs_el0_mode = 0; + current->thread.gcs_el0_locked = 0; write_sysreg_s(GCSCRE0_EL1_nTR, SYS_GCSCRE0_EL1); write_sysreg_s(0, SYS_GCSPR_EL0); } @@ -441,6 +444,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (system_supports_poe()) p->thread.por_el0 = read_sysreg_s(SYS_POR_EL0); +#ifdef CONFIG_ARM64_ACTLR_STATE + if (system_has_actlr_state()) + p->thread.actlr = read_sysreg(actlr_el1); +#endif + if (stack_start) { if (is_compat_thread(task_thread_info(p))) childregs->compat_sp = stack_start; @@ -698,6 +706,65 @@ void update_sctlr_el1(u64 sctlr) isb(); } +#ifdef CONFIG_ARM64_MEMORY_MODEL_CONTROL +int arch_prctl_mem_model_get(struct task_struct *t) +{ + if (alternative_has_cap_unlikely(ARM64_HAS_TSO_APPLE) && + t->thread.actlr & ACTLR_APPLE_TSO) + return PR_SET_MEM_MODEL_TSO; + + return PR_SET_MEM_MODEL_DEFAULT; +} + +int arch_prctl_mem_model_set(struct task_struct *t, unsigned long val) +{ + if (alternative_has_cap_unlikely(ARM64_HAS_TSO_FIXED) && + val == PR_SET_MEM_MODEL_TSO) + return 0; + + if (alternative_has_cap_unlikely(ARM64_HAS_TSO_APPLE)) { + WARN_ON(!system_has_actlr_state()); + + switch (val) { + case PR_SET_MEM_MODEL_TSO: + t->thread.actlr |= ACTLR_APPLE_TSO; + break; + case PR_SET_MEM_MODEL_DEFAULT: + t->thread.actlr &= ~ACTLR_APPLE_TSO; + break; + default: + return -EINVAL; + } + write_sysreg(t->thread.actlr, actlr_el1); + return 0; + } + + if (val == PR_SET_MEM_MODEL_DEFAULT) + return 0; + + return -EINVAL; +} +#endif + +#ifdef CONFIG_ARM64_ACTLR_STATE +/* + * IMPDEF control register ACTLR_EL1 handling. Some CPUs use this to + * expose features that can be controlled by userspace. + */ +static void actlr_thread_switch(struct task_struct *next) +{ + if (!system_has_actlr_state()) + return; + + current->thread.actlr = read_sysreg(actlr_el1); + write_sysreg(next->thread.actlr, actlr_el1); +} +#else +static inline void actlr_thread_switch(struct task_struct *next) +{ +} +#endif + /* * Thread switching. */ @@ -717,6 +784,7 @@ struct task_struct *__switch_to(struct task_struct *prev, ptrauth_thread_switch_user(next); permission_overlay_switch(next); gcs_thread_switch(next); + actlr_thread_switch(next); /* * Complete any pending TLB or cache maintenance on this CPU in case the @@ -839,6 +907,10 @@ void arch_setup_new_exec(void) arch_prctl_spec_ctrl_set(current, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE); } + +#ifdef CONFIG_ARM64_MEMORY_MODEL_CONTROL + arch_prctl_mem_model_set(current, PR_SET_MEM_MODEL_DEFAULT); +#endif } #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 4b001121c72dbe..fd1ba43f2005a9 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -942,20 +942,18 @@ static int sve_set_common(struct task_struct *target, vq = sve_vq_from_vl(task_get_vl(target, type)); /* Enter/exit streaming mode */ - if (system_supports_sme()) { - switch (type) { - case ARM64_VEC_SVE: - target->thread.svcr &= ~SVCR_SM_MASK; - set_tsk_thread_flag(target, TIF_SVE); - break; - case ARM64_VEC_SME: - target->thread.svcr |= SVCR_SM_MASK; - set_tsk_thread_flag(target, TIF_SME); - break; - default: - WARN_ON_ONCE(1); - return -EINVAL; - } + switch (type) { + case ARM64_VEC_SVE: + target->thread.svcr &= ~SVCR_SM_MASK; + set_tsk_thread_flag(target, TIF_SVE); + break; + case ARM64_VEC_SME: + target->thread.svcr |= SVCR_SM_MASK; + set_tsk_thread_flag(target, TIF_SME); + break; + default: + WARN_ON_ONCE(1); + return -EINVAL; } /* Always zero V regs, FPSR, and FPCR */ diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 23c05dc7a8f2ac..0fa2403c6fc0e6 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -368,6 +368,14 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) */ init_task.thread_info.ttbr0 = phys_to_ttbr(__pa_symbol(reserved_pg_dir)); #endif +#ifdef CONFIG_ARM64_ACTLR_STATE + /* Store the boot CPU ACTLR_EL1 value as the default. This will only + * be actually restored during context switching iff the platform is + * known to use ACTLR_EL1 for exposable features and its layout is + * known to be the same on all CPUs. + */ + init_task.thread.actlr = read_sysreg(actlr_el1); +#endif if (boot_args[1] || boot_args[2] || boot_args[3]) { pr_err("WARNING: x1-x3 nonzero in violation of boot protocol:\n" diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 1110eeb21f572d..08ffc5a5aea4cc 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -449,12 +449,28 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) if (user->sve_size < SVE_SIG_CONTEXT_SIZE(vq)) return -EINVAL; + if (sm) { + sme_alloc(current, false); + if (!current->thread.sme_state) + return -ENOMEM; + } + sve_alloc(current, true); if (!current->thread.sve_state) { clear_thread_flag(TIF_SVE); return -ENOMEM; } + if (sm) { + current->thread.svcr |= SVCR_SM_MASK; + set_thread_flag(TIF_SME); + } else { + current->thread.svcr &= ~SVCR_SM_MASK; + set_thread_flag(TIF_SVE); + } + + current->thread.fp_type = FP_STATE_SVE; + err = __copy_from_user(current->thread.sve_state, (char __user const *)user->sve + SVE_SIG_REGS_OFFSET, @@ -462,12 +478,6 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) if (err) return -EFAULT; - if (flags & SVE_SIG_FLAG_SM) - current->thread.svcr |= SVCR_SM_MASK; - else - set_thread_flag(TIF_SVE); - current->thread.fp_type = FP_STATE_SVE; - err = read_fpsimd_context(&fpsimd, user); if (err) return err; @@ -576,6 +586,10 @@ static int restore_za_context(struct user_ctxs *user) if (user->za_size < ZA_SIG_CONTEXT_SIZE(vq)) return -EINVAL; + sve_alloc(current, false); + if (!current->thread.sve_state) + return -ENOMEM; + sme_alloc(current, true); if (!current->thread.sme_state) { current->thread.svcr &= ~SVCR_ZA_MASK; diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h index a17cbe7582de90..7c8383c809ea36 100644 --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -16,6 +16,9 @@ #include #include +#define SYS_IMP_APL_ACTLR_EL12 sys_reg(3, 6, 15, 14, 6) +#define SYS_ACTLR_EL12 sys_reg(3, 5, 1, 0, 1) + static inline bool ctxt_has_s1poe(struct kvm_cpu_context *ctxt); static inline struct kvm_vcpu *ctxt_to_vcpu(struct kvm_cpu_context *ctxt) @@ -172,6 +175,13 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) if (ctxt_has_sctlr2(ctxt)) ctxt_sys_reg(ctxt, SCTLR2_EL1) = read_sysreg_el1(SYS_SCTLR2); + + if (IS_ENABLED(CONFIG_ARM64_ACTLR_STATE)) { + if (alternative_has_cap_unlikely(ARM64_HAS_ACTLR_VIRT)) + ctxt_sys_reg(ctxt, ACTLR_EL1) = read_sysreg_s(SYS_ACTLR_EL12); + else if (alternative_has_cap_unlikely(ARM64_HAS_ACTLR_VIRT_APPLE)) + ctxt_sys_reg(ctxt, ACTLR_EL1) = read_sysreg_s(SYS_IMP_APL_ACTLR_EL12); + } } static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt) @@ -256,6 +266,13 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt, write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1), par_el1); write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1), tpidr_el1); + if (IS_ENABLED(CONFIG_ARM64_ACTLR_STATE)) { + if (alternative_has_cap_unlikely(ARM64_HAS_ACTLR_VIRT)) + write_sysreg_s(ctxt_sys_reg(ctxt, ACTLR_EL1), SYS_ACTLR_EL12); + else if (alternative_has_cap_unlikely(ARM64_HAS_ACTLR_VIRT_APPLE)) + write_sysreg_s(ctxt_sys_reg(ctxt, ACTLR_EL1), SYS_IMP_APL_ACTLR_EL12); + } + if (ctxt_has_mte(ctxt)) { write_sysreg_el1(ctxt_sys_reg(ctxt, TFSR_EL1), SYS_TFSR); write_sysreg_s(ctxt_sys_reg(ctxt, TFSRE0_EL1), SYS_TFSRE0_EL1); diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c index 6e93f78de79b17..04a23a497f2051 100644 --- a/arch/arm64/mm/gcs.c +++ b/arch/arm64/mm/gcs.c @@ -199,8 +199,8 @@ int arch_set_shadow_stack_status(struct task_struct *task, unsigned long arg) size = gcs_size(0); gcs = alloc_gcs(0, size); - if (!gcs) - return -ENOMEM; + if (IS_ERR_VALUE(gcs)) + return gcs; task->thread.gcspr_el0 = gcs + size - sizeof(u64); task->thread.gcs_base = gcs; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 2ba01dc8ef822a..aeb6fb25a951a1 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -49,6 +49,8 @@ #define NO_CONT_MAPPINGS BIT(1) #define NO_EXEC_MAPPINGS BIT(2) /* assumes FEAT_HPDS is not used */ +#define INVALID_PHYS_ADDR (-1ULL) + DEFINE_STATIC_KEY_FALSE(arm64_ptdump_lock_key); u64 kimage_voffset __ro_after_init; @@ -194,11 +196,11 @@ static void init_pte(pte_t *ptep, unsigned long addr, unsigned long end, } while (ptep++, addr += PAGE_SIZE, addr != end); } -static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, - unsigned long end, phys_addr_t phys, - pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), - int flags) +static int alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, + unsigned long end, phys_addr_t phys, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { unsigned long next; pmd_t pmd = READ_ONCE(*pmdp); @@ -213,6 +215,8 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, pmdval |= PMD_TABLE_PXN; BUG_ON(!pgtable_alloc); pte_phys = pgtable_alloc(TABLE_PTE); + if (pte_phys == INVALID_PHYS_ADDR) + return -ENOMEM; ptep = pte_set_fixmap(pte_phys); init_clear_pgtable(ptep); ptep += pte_index(addr); @@ -244,11 +248,13 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, * walker. */ pte_clear_fixmap(); + + return 0; } -static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), int flags) +static int init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), int flags) { unsigned long next; @@ -269,22 +275,29 @@ static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd), READ_ONCE(pmd_val(*pmdp)))); } else { - alloc_init_cont_pte(pmdp, addr, next, phys, prot, - pgtable_alloc, flags); + int ret; + + ret = alloc_init_cont_pte(pmdp, addr, next, phys, prot, + pgtable_alloc, flags); + if (ret) + return ret; BUG_ON(pmd_val(old_pmd) != 0 && pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp))); } phys += next - addr; } while (pmdp++, addr = next, addr != end); + + return 0; } -static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, - unsigned long end, phys_addr_t phys, - pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), - int flags) +static int alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, + unsigned long end, phys_addr_t phys, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret; unsigned long next; pud_t pud = READ_ONCE(*pudp); pmd_t *pmdp; @@ -301,6 +314,8 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, pudval |= PUD_TABLE_PXN; BUG_ON(!pgtable_alloc); pmd_phys = pgtable_alloc(TABLE_PMD); + if (pmd_phys == INVALID_PHYS_ADDR) + return -ENOMEM; pmdp = pmd_set_fixmap(pmd_phys); init_clear_pgtable(pmdp); pmdp += pmd_index(addr); @@ -320,20 +335,26 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, (flags & NO_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); - init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags); + ret = init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags); + if (ret) + goto out; pmdp += pmd_index(next) - pmd_index(addr); phys += next - addr; } while (addr = next, addr != end); +out: pmd_clear_fixmap(); + + return ret; } -static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), - int flags) +static int alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret = 0; unsigned long next; p4d_t p4d = READ_ONCE(*p4dp); pud_t *pudp; @@ -346,6 +367,8 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, p4dval |= P4D_TABLE_PXN; BUG_ON(!pgtable_alloc); pud_phys = pgtable_alloc(TABLE_PUD); + if (pud_phys == INVALID_PHYS_ADDR) + return -ENOMEM; pudp = pud_set_fixmap(pud_phys); init_clear_pgtable(pudp); pudp += pud_index(addr); @@ -375,8 +398,10 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, BUG_ON(!pgattr_change_is_safe(pud_val(old_pud), READ_ONCE(pud_val(*pudp)))); } else { - alloc_init_cont_pmd(pudp, addr, next, phys, prot, - pgtable_alloc, flags); + ret = alloc_init_cont_pmd(pudp, addr, next, phys, prot, + pgtable_alloc, flags); + if (ret) + goto out; BUG_ON(pud_val(old_pud) != 0 && pud_val(old_pud) != READ_ONCE(pud_val(*pudp))); @@ -384,14 +409,18 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, phys += next - addr; } while (pudp++, addr = next, addr != end); +out: pud_clear_fixmap(); + + return ret; } -static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), - int flags) +static int alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret; unsigned long next; pgd_t pgd = READ_ONCE(*pgdp); p4d_t *p4dp; @@ -404,6 +433,8 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, pgdval |= PGD_TABLE_PXN; BUG_ON(!pgtable_alloc); p4d_phys = pgtable_alloc(TABLE_P4D); + if (p4d_phys == INVALID_PHYS_ADDR) + return -ENOMEM; p4dp = p4d_set_fixmap(p4d_phys); init_clear_pgtable(p4dp); p4dp += p4d_index(addr); @@ -418,8 +449,10 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, next = p4d_addr_end(addr, end); - alloc_init_pud(p4dp, addr, next, phys, prot, - pgtable_alloc, flags); + ret = alloc_init_pud(p4dp, addr, next, phys, prot, + pgtable_alloc, flags); + if (ret) + goto out; BUG_ON(p4d_val(old_p4d) != 0 && p4d_val(old_p4d) != READ_ONCE(p4d_val(*p4dp))); @@ -427,15 +460,19 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, phys += next - addr; } while (p4dp++, addr = next, addr != end); +out: p4d_clear_fixmap(); + + return ret; } -static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, - unsigned long virt, phys_addr_t size, - pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), - int flags) +static int __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret; unsigned long addr, end, next; pgd_t *pgdp = pgd_offset_pgd(pgdir, virt); @@ -444,7 +481,7 @@ static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, * within a page, we cannot map the region as the caller expects. */ if (WARN_ON((phys ^ virt) & ~PAGE_MASK)) - return; + return -EINVAL; phys &= PAGE_MASK; addr = virt & PAGE_MASK; @@ -452,25 +489,45 @@ static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, do { next = pgd_addr_end(addr, end); - alloc_init_p4d(pgdp, addr, next, phys, prot, pgtable_alloc, - flags); + ret = alloc_init_p4d(pgdp, addr, next, phys, prot, pgtable_alloc, + flags); + if (ret) + return ret; phys += next - addr; } while (pgdp++, addr = next, addr != end); + + return 0; } -static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, - unsigned long virt, phys_addr_t size, - pgprot_t prot, - phys_addr_t (*pgtable_alloc)(enum pgtable_type), - int flags) +static int __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) { + int ret; + mutex_lock(&fixmap_lock); - __create_pgd_mapping_locked(pgdir, phys, virt, size, prot, - pgtable_alloc, flags); + ret = __create_pgd_mapping_locked(pgdir, phys, virt, size, prot, + pgtable_alloc, flags); mutex_unlock(&fixmap_lock); + + return ret; } -#define INVALID_PHYS_ADDR (-1ULL) +static void early_create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(enum pgtable_type), + int flags) +{ + int ret; + + ret = __create_pgd_mapping(pgdir, phys, virt, size, prot, pgtable_alloc, + flags); + if (ret) + panic("Failed to create page tables\n"); +} static phys_addr_t __pgd_pgtable_alloc(struct mm_struct *mm, gfp_t gfp, enum pgtable_type pgtable_type) @@ -511,21 +568,13 @@ try_pgd_pgtable_alloc_init_mm(enum pgtable_type pgtable_type, gfp_t gfp) static phys_addr_t __maybe_unused pgd_pgtable_alloc_init_mm(enum pgtable_type pgtable_type) { - phys_addr_t pa; - - pa = __pgd_pgtable_alloc(&init_mm, GFP_PGTABLE_KERNEL, pgtable_type); - BUG_ON(pa == INVALID_PHYS_ADDR); - return pa; + return __pgd_pgtable_alloc(&init_mm, GFP_PGTABLE_KERNEL, pgtable_type); } static phys_addr_t pgd_pgtable_alloc_special_mm(enum pgtable_type pgtable_type) { - phys_addr_t pa; - - pa = __pgd_pgtable_alloc(NULL, GFP_PGTABLE_KERNEL, pgtable_type); - BUG_ON(pa == INVALID_PHYS_ADDR); - return pa; + return __pgd_pgtable_alloc(NULL, GFP_PGTABLE_KERNEL, pgtable_type); } static void split_contpte(pte_t *ptep) @@ -935,8 +984,8 @@ void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, &phys, virt); return; } - __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, - NO_CONT_MAPPINGS); + early_create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, + NO_CONT_MAPPINGS); } void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, @@ -950,8 +999,8 @@ void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, if (page_mappings_only) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; - __create_pgd_mapping(mm->pgd, phys, virt, size, prot, - pgd_pgtable_alloc_special_mm, flags); + early_create_pgd_mapping(mm->pgd, phys, virt, size, prot, + pgd_pgtable_alloc_special_mm, flags); } static void update_mapping_prot(phys_addr_t phys, unsigned long virt, @@ -963,8 +1012,8 @@ static void update_mapping_prot(phys_addr_t phys, unsigned long virt, return; } - __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, - NO_CONT_MAPPINGS); + early_create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, + NO_CONT_MAPPINGS); /* flush the TLBs after updating live kernel mappings */ flush_tlb_kernel_range(virt, virt + size); @@ -973,8 +1022,8 @@ static void update_mapping_prot(phys_addr_t phys, unsigned long virt, static void __init __map_memblock(pgd_t *pgdp, phys_addr_t start, phys_addr_t end, pgprot_t prot, int flags) { - __create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start, - prot, early_pgtable_alloc, flags); + early_create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start, + prot, early_pgtable_alloc, flags); } void __init mark_linear_text_alias_ro(void) @@ -1207,6 +1256,8 @@ static int __init __kpti_install_ng_mappings(void *__unused) remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); if (!cpu) { + int ret; + alloc = __get_free_pages(GFP_ATOMIC | __GFP_ZERO, order); kpti_ng_temp_pgd = (pgd_t *)(alloc + (levels - 1) * PAGE_SIZE); kpti_ng_temp_alloc = kpti_ng_temp_pgd_pa = __pa(kpti_ng_temp_pgd); @@ -1227,9 +1278,11 @@ static int __init __kpti_install_ng_mappings(void *__unused) // covers the PTE[] page itself, the remaining entries are free // to be used as a ad-hoc fixmap. // - __create_pgd_mapping_locked(kpti_ng_temp_pgd, __pa(alloc), - KPTI_NG_TEMP_VA, PAGE_SIZE, PAGE_KERNEL, - kpti_ng_pgd_alloc, 0); + ret = __create_pgd_mapping_locked(kpti_ng_temp_pgd, __pa(alloc), + KPTI_NG_TEMP_VA, PAGE_SIZE, PAGE_KERNEL, + kpti_ng_pgd_alloc, 0); + if (ret) + panic("Failed to create page tables\n"); } cpu_install_idmap(); @@ -1282,9 +1335,9 @@ static int __init map_entry_trampoline(void) /* Map only the text into the trampoline page table */ memset(tramp_pg_dir, 0, PGD_SIZE); - __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, - entry_tramp_text_size(), prot, - pgd_pgtable_alloc_init_mm, NO_BLOCK_MAPPINGS); + early_create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, + entry_tramp_text_size(), prot, + pgd_pgtable_alloc_init_mm, NO_BLOCK_MAPPINGS); /* Map both the text and data into the kernel page table */ for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++) @@ -1926,23 +1979,28 @@ int arch_add_memory(int nid, u64 start, u64 size, if (force_pte_mapping()) flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; - __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), - size, params->pgprot, pgd_pgtable_alloc_init_mm, - flags); + ret = __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), + size, params->pgprot, pgd_pgtable_alloc_init_mm, + flags); + if (ret) + goto err; memblock_clear_nomap(start, size); ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, params); if (ret) - __remove_pgd_mapping(swapper_pg_dir, - __phys_to_virt(start), size); - else { - /* Address of hotplugged memory can be smaller */ - max_pfn = max(max_pfn, PFN_UP(start + size)); - max_low_pfn = max_pfn; - } + goto err; + + /* Address of hotplugged memory can be smaller */ + max_pfn = max(max_pfn, PFN_UP(start + size)); + max_low_pfn = max_pfn; + + return 0; +err: + __remove_pgd_mapping(swapper_pg_dir, + __phys_to_virt(start), size); return ret; } diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 5135f2d66958d9..b4ea86cd3a7199 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -148,6 +148,7 @@ static int change_memory_common(unsigned long addr, int numpages, unsigned long size = PAGE_SIZE * numpages; unsigned long end = start + size; struct vm_struct *area; + int ret; int i; if (!PAGE_ALIGNED(addr)) { @@ -185,8 +186,10 @@ static int change_memory_common(unsigned long addr, int numpages, if (rodata_full && (pgprot_val(set_mask) == PTE_RDONLY || pgprot_val(clear_mask) == PTE_RDONLY)) { for (i = 0; i < area->nr_pages; i++) { - __change_memory_common((u64)page_address(area->pages[i]), + ret = __change_memory_common((u64)page_address(area->pages[i]), PAGE_SIZE, set_mask, clear_mask); + if (ret) + return ret; } } diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 86818511962b61..17df19647556fe 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -100,6 +100,10 @@ SYM_FUNC_START(cpu_do_suspend) * call stack. */ str x18, [x0, #96] +alternative_if ARM64_HAS_TCR2 + mrs x2, REG_TCR2_EL1 + str x2, [x0, #104] +alternative_else_nop_endif ret SYM_FUNC_END(cpu_do_suspend) @@ -134,6 +138,10 @@ SYM_FUNC_START(cpu_do_resume) msr tcr_el1, x8 msr vbar_el1, x9 msr mdscr_el1, x10 +alternative_if ARM64_HAS_TCR2 + ldr x2, [x0, #104] + msr REG_TCR2_EL1, x2 +alternative_else_nop_endif msr sctlr_el1, x12 set_this_cpu_offset x13 diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 0c9a50a1e73e7d..83a6ca613f9c24 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1004,7 +1004,7 @@ static void __maybe_unused build_bhb_mitigation(struct jit_ctx *ctx) arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE) return; - if (capable(CAP_SYS_ADMIN)) + if (ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN)) return; if (supports_clearbhb(SCOPE_SYSTEM)) { @@ -2939,7 +2939,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type, u64 plt_target = 0ULL; bool poking_bpf_entry; - if (!__bpf_address_lookup((unsigned long)ip, &size, &offset, namebuf)) + if (!bpf_address_lookup((unsigned long)ip, &size, &offset, namebuf)) /* Only poking bpf text is supported. Since kernel function * entry is set up by ftrace, we reply on ftrace to poke kernel * functions. diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 1b32c1232d28d8..7398b50bb090a4 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -8,6 +8,8 @@ BTI # Unreliable: use system_supports_32bit_el0() instead. HAS_32BIT_EL0_DO_NOT_USE HAS_32BIT_EL1 +HAS_ACTLR_VIRT +HAS_ACTLR_VIRT_APPLE HAS_ADDRESS_AUTH HAS_ADDRESS_AUTH_ARCH_QARMA3 HAS_ADDRESS_AUTH_ARCH_QARMA5 @@ -61,6 +63,8 @@ HAS_STAGE2_FWB HAS_TCR2 HAS_TIDCP1 HAS_TLB_RANGE +HAS_TSO_APPLE +HAS_TSO_FIXED HAS_VA52 HAS_VIRT_HOST_EXTN HAS_WFXT diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index a6ca7dff421532..7ff40110898500 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -45,8 +45,8 @@ static inline void csky_cmpxchg_fixup(struct pt_regs *regs) if (trap_no(regs) != VEC_TLBMODIFIED) return; - if (instruction_pointer(regs) == csky_cmpxchg_stw) - instruction_pointer_set(regs, csky_cmpxchg_ldw); + if (instruction_pointer(regs) == (unsigned long)&csky_cmpxchg_stw) + instruction_pointer_set(regs, (unsigned long)&csky_cmpxchg_ldw); return; } #endif diff --git a/arch/loongarch/boot/dts/loongson-2k0500.dtsi b/arch/loongarch/boot/dts/loongson-2k0500.dtsi index 588ebc3bded40f..51d990890803cc 100644 --- a/arch/loongarch/boot/dts/loongson-2k0500.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k0500.dtsi @@ -131,6 +131,7 @@ reg-names = "main", "isr0"; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <2>; @@ -149,6 +150,7 @@ reg-names = "main", "isr0"; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <4>; @@ -164,6 +166,7 @@ compatible = "loongson,ls2k0500-eiointc"; reg = <0x0 0x1fe11600 0x0 0xea00>; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <1>; interrupt-parent = <&cpuintc>; interrupts = <3>; diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi index d8e01e2534dde1..830815a5da8637 100644 --- a/arch/loongarch/boot/dts/loongson-2k1000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi @@ -46,7 +46,7 @@ }; /* i2c of the dvi eeprom edid */ - i2c-gpio-0 { + i2c-0 { compatible = "i2c-gpio"; scl-gpios = <&gpio0 0 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; sda-gpios = <&gpio0 1 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; @@ -57,7 +57,7 @@ }; /* i2c of the eeprom edid */ - i2c-gpio-1 { + i2c-1 { compatible = "i2c-gpio"; scl-gpios = <&gpio0 33 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; sda-gpios = <&gpio0 32 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; @@ -114,6 +114,7 @@ <0x0 0x1fe01140 0x0 0x8>; reg-names = "main", "isr0", "isr1"; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <2>; @@ -131,6 +132,7 @@ <0x0 0x1fe01148 0x0 0x8>; reg-names = "main", "isr0", "isr1"; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <3>; @@ -437,54 +439,47 @@ gmac0: ethernet@3,0 { reg = <0x1800 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, - <13 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 12 IRQ_TYPE_LEVEL_HIGH>, + <&liointc0 13 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; status = "disabled"; }; gmac1: ethernet@3,1 { reg = <0x1900 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <14 IRQ_TYPE_LEVEL_HIGH>, - <15 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 14 IRQ_TYPE_LEVEL_HIGH>, + <&liointc0 15 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; status = "disabled"; }; ehci0: usb@4,1 { reg = <0x2100 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc1>; - interrupts = <18 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc1 18 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; ohci0: usb@4,2 { reg = <0x2200 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc1>; - interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc1 19 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; display@6,0 { reg = <0x3000 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <28 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 28 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; hda@7,0 { reg = <0x3800 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <4 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 4 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; sata: sata@8,0 { reg = <0x4000 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 19 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi index 00cc485b753b1c..ff094e60af1c9f 100644 --- a/arch/loongarch/boot/dts/loongson-2k2000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi @@ -126,6 +126,7 @@ reg = <0x0 0x1fe01400 0x0 0x64>; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <2>; @@ -140,6 +141,7 @@ compatible = "loongson,ls2k2000-eiointc"; reg = <0x0 0x1fe01600 0x0 0xea00>; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <1>; interrupt-parent = <&cpuintc>; interrupts = <3>; @@ -149,6 +151,7 @@ compatible = "loongson,pch-pic-1.0"; reg = <0x0 0x10000000 0x0 0x400>; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; loongson,pic-base-vec = <0>; interrupt-parent = <&eiointc>; @@ -291,65 +294,57 @@ gmac0: ethernet@3,0 { reg = <0x1800 0x0 0x0 0x0 0x0>; - interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, - <13 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&pic 12 IRQ_TYPE_LEVEL_HIGH>, + <&pic 13 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; - interrupt-parent = <&pic>; status = "disabled"; }; gmac1: ethernet@3,1 { reg = <0x1900 0x0 0x0 0x0 0x0>; - interrupts = <14 IRQ_TYPE_LEVEL_HIGH>, - <15 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&pic 14 IRQ_TYPE_LEVEL_HIGH>, + <&pic 15 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; - interrupt-parent = <&pic>; status = "disabled"; }; gmac2: ethernet@3,2 { reg = <0x1a00 0x0 0x0 0x0 0x0>; - interrupts = <17 IRQ_TYPE_LEVEL_HIGH>, - <18 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&pic 17 IRQ_TYPE_LEVEL_HIGH>, + <&pic 18 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; - interrupt-parent = <&pic>; status = "disabled"; }; xhci0: usb@4,0 { reg = <0x2000 0x0 0x0 0x0 0x0>; - interrupts = <48 IRQ_TYPE_LEVEL_HIGH>; - interrupt-parent = <&pic>; + interrupts-extended = <&pic 48 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; xhci1: usb@19,0 { reg = <0xc800 0x0 0x0 0x0 0x0>; - interrupts = <22 IRQ_TYPE_LEVEL_HIGH>; - interrupt-parent = <&pic>; + interrupts-extended = <&pic 22 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; display@6,1 { reg = <0x3100 0x0 0x0 0x0 0x0>; - interrupts = <28 IRQ_TYPE_LEVEL_HIGH>; - interrupt-parent = <&pic>; + interrupts-extended = <&pic 28 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; i2s@7,0 { reg = <0x3800 0x0 0x0 0x0 0x0>; - interrupts = <78 IRQ_TYPE_LEVEL_HIGH>, - <79 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&pic 78 IRQ_TYPE_LEVEL_HIGH>, + <&pic 79 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "tx", "rx"; - interrupt-parent = <&pic>; status = "disabled"; }; sata: sata@8,0 { reg = <0x4000 0x0 0x0 0x0 0x0>; - interrupts = <16 IRQ_TYPE_LEVEL_HIGH>; - interrupt-parent = <&pic>; + interrupts-extended = <&pic 16 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 03fb60432fde79..9a7029285fd510 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -297,9 +297,9 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) #define __swp_offset(x) ((x).val >> 24) #define __swp_entry(type, offset) ((swp_entry_t) { pte_val(mk_swap_pte((type), (offset))) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) -#define __swp_entry_to_pte(x) ((pte_t) { (x).val }) +#define __swp_entry_to_pte(x) __pte((x).val) #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) }) -#define __swp_entry_to_pmd(x) ((pmd_t) { (x).val | _PAGE_HUGE }) +#define __swp_entry_to_pmd(x) __pmd((x).val | _PAGE_HUGE) static inline bool pte_swp_exclusive(pte_t pte) { diff --git a/arch/loongarch/kernel/mcount_dyn.S b/arch/loongarch/kernel/mcount_dyn.S index d6b474ad1d5e55..5729c20e5b8b0e 100644 --- a/arch/loongarch/kernel/mcount_dyn.S +++ b/arch/loongarch/kernel/mcount_dyn.S @@ -94,7 +94,6 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) * at the callsite, so there is no need to restore the T series regs. */ ftrace_common_return: - PTR_L ra, sp, PT_R1 PTR_L a0, sp, PT_R4 PTR_L a1, sp, PT_R5 PTR_L a2, sp, PT_R6 @@ -104,12 +103,17 @@ ftrace_common_return: PTR_L a6, sp, PT_R10 PTR_L a7, sp, PT_R11 PTR_L fp, sp, PT_R22 - PTR_L t0, sp, PT_ERA PTR_L t1, sp, PT_R13 - PTR_ADDI sp, sp, PT_SIZE bnez t1, .Ldirect + + PTR_L ra, sp, PT_R1 + PTR_L t0, sp, PT_ERA + PTR_ADDI sp, sp, PT_SIZE jr t0 .Ldirect: + PTR_L t0, sp, PT_R1 + PTR_L ra, sp, PT_ERA + PTR_ADDI sp, sp, PT_SIZE jr t1 SYM_CODE_END(ftrace_common) @@ -161,6 +165,8 @@ SYM_CODE_END(return_to_handler) #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS SYM_CODE_START(ftrace_stub_direct_tramp) UNWIND_HINT_UNDEFINED - jr t0 + move t1, ra + move ra, t0 + jr t1 SYM_CODE_END(ftrace_stub_direct_tramp) #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c index 9d257c8519c902..e34a6fb33e11c1 100644 --- a/arch/loongarch/kernel/perf_event.c +++ b/arch/loongarch/kernel/perf_event.c @@ -626,6 +626,18 @@ static const struct loongarch_perf_event *loongarch_pmu_map_cache_event(u64 conf return pev; } +static inline bool loongarch_pmu_event_requires_counter(const struct perf_event *event) +{ + switch (event->attr.type) { + case PERF_TYPE_HARDWARE: + case PERF_TYPE_HW_CACHE: + case PERF_TYPE_RAW: + return true; + default: + return false; + } +} + static int validate_group(struct perf_event *event) { struct cpu_hw_events fake_cpuc; @@ -633,15 +645,18 @@ static int validate_group(struct perf_event *event) memset(&fake_cpuc, 0, sizeof(fake_cpuc)); - if (loongarch_pmu_alloc_counter(&fake_cpuc, &leader->hw) < 0) + if (loongarch_pmu_event_requires_counter(leader) && + loongarch_pmu_alloc_counter(&fake_cpuc, &leader->hw) < 0) return -EINVAL; for_each_sibling_event(sibling, leader) { - if (loongarch_pmu_alloc_counter(&fake_cpuc, &sibling->hw) < 0) + if (loongarch_pmu_event_requires_counter(sibling) && + loongarch_pmu_alloc_counter(&fake_cpuc, &sibling->hw) < 0) return -EINVAL; } - if (loongarch_pmu_alloc_counter(&fake_cpuc, &event->hw) < 0) + if (loongarch_pmu_event_requires_counter(event) && + loongarch_pmu_alloc_counter(&fake_cpuc, &event->hw) < 0) return -EINVAL; return 0; diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index efd9edf65603cc..d1e04f9e0f7951 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -130,6 +130,11 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) preempt_enable(); + if (IS_ENABLED(CONFIG_RANDSTRUCT)) { + memcpy(dst, src, sizeof(struct task_struct)); + return 0; + } + if (!used_math()) memcpy(dst, src, offsetof(struct task_struct, thread.fpu.fpr)); else diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c index b5e2312a2fca51..76abbb8d293160 100644 --- a/arch/loongarch/kernel/relocate.c +++ b/arch/loongarch/kernel/relocate.c @@ -183,7 +183,7 @@ static inline void __init *determine_relocation_address(void) if (kaslr_disabled()) return destination; - kernel_length = (long)_end - (long)_text; + kernel_length = (unsigned long)_end - (unsigned long)_text; random_offset = get_random_boot() << 16; random_offset &= (CONFIG_RANDOMIZE_BASE_MAX_OFFSET - 1); @@ -232,7 +232,7 @@ unsigned long __init relocate_kernel(void) early_memunmap(cmdline, COMMAND_LINE_SIZE); if (random_offset) { - kernel_length = (long)(_end) - (long)(_text); + kernel_length = (unsigned long)(_end) - (unsigned long)(_text); /* Copy the kernel to it's new location */ memcpy(location_new, _text, kernel_length); diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 25a87378e48e43..20cb6f30645683 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -56,6 +56,7 @@ #define SMBIOS_FREQLOW_MASK 0xFF #define SMBIOS_CORE_PACKAGE_OFFSET 0x23 #define SMBIOS_THREAD_PACKAGE_OFFSET 0x25 +#define SMBIOS_THREAD_PACKAGE_2_OFFSET 0x2E #define LOONGSON_EFI_ENABLE (1 << 3) unsigned long fw_arg0, fw_arg1, fw_arg2; @@ -126,7 +127,12 @@ static void __init parse_cpu_table(const struct dmi_header *dm) cpu_clock_freq = freq_temp * 1000000; loongson_sysconf.cpuname = (void *)dmi_string_parse(dm, dmi_data[16]); - loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_THREAD_PACKAGE_OFFSET); + loongson_sysconf.cores_per_package = *(u8 *)(dmi_data + SMBIOS_THREAD_PACKAGE_OFFSET); + if (dm->length >= 0x30 && loongson_sysconf.cores_per_package == 0xff) { + /* SMBIOS 3.0+ has ThreadCount2 for more than 255 threads */ + loongson_sysconf.cores_per_package = + *(u16 *)(dmi_data + SMBIOS_THREAD_PACKAGE_2_OFFSET); + } pr_info("CpuClock = %llu\n", cpu_clock_freq); } diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S index 9c23cb7e432f1f..3007e909e0d800 100644 --- a/arch/loongarch/kernel/switch.S +++ b/arch/loongarch/kernel/switch.S @@ -25,8 +25,8 @@ SYM_FUNC_START(__switch_to) stptr.d a4, a0, THREAD_SCHED_CFA #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_SMP) la t7, __stack_chk_guard - LONG_L t8, a1, TASK_STACK_CANARY - LONG_S t8, t7, 0 + ldptr.d t8, a1, TASK_STACK_CANARY + stptr.d t8, t7, 0 #endif move tp, a2 cpu_restore_nonscratch a1 diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index da5926fead4af9..8e51ce004572ca 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -535,10 +535,15 @@ asmlinkage void noinstr do_fpe(struct pt_regs *regs, unsigned long fcsr) asmlinkage void noinstr do_ade(struct pt_regs *regs) { irqentry_state_t state = irqentry_enter(regs); + unsigned int esubcode = FIELD_GET(CSR_ESTAT_ESUBCODE, regs->csr_estat); + + if ((esubcode == EXSUBCODE_ADEM) && fixup_exception(regs)) + goto out; die_if_kernel("Kernel ade access", regs); force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)regs->csr_badvaddr); +out: irqentry_exit(regs, state); } diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index a1cc116b4daceb..945ce4ed7e0b7e 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -679,6 +679,7 @@ static void kvm_eiointc_destroy(struct kvm_device *dev) kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &eiointc->device); kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &eiointc->device_vext); kfree(eiointc); + kfree(dev); } static struct kvm_device_ops kvm_eiointc_dev_ops = { diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c index 05cefd29282e8e..1058c13dba7f4f 100644 --- a/arch/loongarch/kvm/intc/ipi.c +++ b/arch/loongarch/kvm/intc/ipi.c @@ -459,6 +459,7 @@ static void kvm_ipi_destroy(struct kvm_device *dev) ipi = kvm->arch.ipi; kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &ipi->device); kfree(ipi); + kfree(dev); } static struct kvm_device_ops kvm_ipi_dev_ops = { diff --git a/arch/loongarch/kvm/intc/pch_pic.c b/arch/loongarch/kvm/intc/pch_pic.c index a698a73de399bc..4addb34bf432b1 100644 --- a/arch/loongarch/kvm/intc/pch_pic.c +++ b/arch/loongarch/kvm/intc/pch_pic.c @@ -475,6 +475,7 @@ static void kvm_pch_pic_destroy(struct kvm_device *dev) /* unregister pch pic device and free it's memory */ kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &s->device); kfree(s); + kfree(dev); } static struct kvm_device_ops kvm_pch_pic_dev_ops = { diff --git a/arch/loongarch/mm/cache.c b/arch/loongarch/mm/cache.c index 6be04d36ca0769..496916845ff764 100644 --- a/arch/loongarch/mm/cache.c +++ b/arch/loongarch/mm/cache.c @@ -160,8 +160,8 @@ void cpu_cache_init(void) static const pgprot_t protection_map[16] = { [VM_NONE] = __pgprot(_CACHE_CC | _PAGE_USER | - _PAGE_PROTNONE | _PAGE_NO_EXEC | - _PAGE_NO_READ), + _PAGE_NO_EXEC | _PAGE_NO_READ | + (_PAGE_PROTNONE ? : _PAGE_PRESENT)), [VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT | _PAGE_NO_EXEC), @@ -180,8 +180,8 @@ static const pgprot_t protection_map[16] = { [VM_EXEC | VM_WRITE | VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT), [VM_SHARED] = __pgprot(_CACHE_CC | _PAGE_USER | - _PAGE_PROTNONE | _PAGE_NO_EXEC | - _PAGE_NO_READ), + _PAGE_NO_EXEC | _PAGE_NO_READ | + (_PAGE_PROTNONE ? : _PAGE_PRESENT)), [VM_SHARED | VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT | _PAGE_NO_EXEC), diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c index 170da98ad4f551..0fc02ca0645738 100644 --- a/arch/loongarch/mm/kasan_init.c +++ b/arch/loongarch/mm/kasan_init.c @@ -40,39 +40,43 @@ static pgd_t kasan_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); #define __pte_none(early, pte) (early ? pte_none(pte) : \ ((pte_val(pte) & _PFN_MASK) == (unsigned long)__pa(kasan_early_shadow_page))) -void *kasan_mem_to_shadow(const void *addr) +static void *mem_to_shadow(const void *addr) { - if (!kasan_enabled()) { + unsigned long offset = 0; + unsigned long maddr = (unsigned long)addr; + unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff; + + if (maddr >= FIXADDR_START) return (void *)(kasan_early_shadow_page); - } else { - unsigned long maddr = (unsigned long)addr; - unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff; - unsigned long offset = 0; - - if (maddr >= FIXADDR_START) - return (void *)(kasan_early_shadow_page); - - maddr &= XRANGE_SHADOW_MASK; - switch (xrange) { - case XKPRANGE_CC_SEG: - offset = XKPRANGE_CC_SHADOW_OFFSET; - break; - case XKPRANGE_UC_SEG: - offset = XKPRANGE_UC_SHADOW_OFFSET; - break; - case XKPRANGE_WC_SEG: - offset = XKPRANGE_WC_SHADOW_OFFSET; - break; - case XKVRANGE_VC_SEG: - offset = XKVRANGE_VC_SHADOW_OFFSET; - break; - default: - WARN_ON(1); - return NULL; - } - return (void *)((maddr >> KASAN_SHADOW_SCALE_SHIFT) + offset); + maddr &= XRANGE_SHADOW_MASK; + switch (xrange) { + case XKPRANGE_CC_SEG: + offset = XKPRANGE_CC_SHADOW_OFFSET; + break; + case XKPRANGE_UC_SEG: + offset = XKPRANGE_UC_SHADOW_OFFSET; + break; + case XKPRANGE_WC_SEG: + offset = XKPRANGE_WC_SHADOW_OFFSET; + break; + case XKVRANGE_VC_SEG: + offset = XKVRANGE_VC_SHADOW_OFFSET; + break; + default: + WARN_ON(1); + return NULL; } + + return (void *)((maddr >> KASAN_SHADOW_SCALE_SHIFT) + offset); +} + +void *kasan_mem_to_shadow(const void *addr) +{ + if (kasan_enabled()) + return mem_to_shadow(addr); + else + return (void *)(kasan_early_shadow_page); } const void *kasan_shadow_to_mem(const void *shadow_addr) @@ -293,11 +297,8 @@ void __init kasan_init(void) /* Maps everything to a single page of zeroes */ kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, NUMA_NO_NODE, true); - kasan_populate_early_shadow(kasan_mem_to_shadow((void *)VMALLOC_START), - kasan_mem_to_shadow((void *)KFENCE_AREA_END)); - - /* Enable KASAN here before kasan_mem_to_shadow(). */ - kasan_init_generic(); + kasan_populate_early_shadow(mem_to_shadow((void *)VMALLOC_START), + mem_to_shadow((void *)KFENCE_AREA_END)); /* Populate the linear mapping */ for_each_mem_range(i, &pa_start, &pa_end) { @@ -307,13 +308,13 @@ void __init kasan_init(void) if (start >= end) break; - kasan_map_populate((unsigned long)kasan_mem_to_shadow(start), - (unsigned long)kasan_mem_to_shadow(end), NUMA_NO_NODE); + kasan_map_populate((unsigned long)mem_to_shadow(start), + (unsigned long)mem_to_shadow(end), NUMA_NO_NODE); } /* Populate modules mapping */ - kasan_map_populate((unsigned long)kasan_mem_to_shadow((void *)MODULES_VADDR), - (unsigned long)kasan_mem_to_shadow((void *)MODULES_END), NUMA_NO_NODE); + kasan_map_populate((unsigned long)mem_to_shadow((void *)MODULES_VADDR), + (unsigned long)mem_to_shadow((void *)MODULES_END), NUMA_NO_NODE); /* * KAsan may reuse the contents of kasan_early_shadow_pte directly, so we * should make sure that it maps the zero page read-only. @@ -328,4 +329,5 @@ void __init kasan_init(void) /* At this point kasan is fully initialized. Enable error messages */ init_task.kasan_depth = 0; + kasan_init_generic(); } diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index f97dc993640174..e9d666508ae28f 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -139,6 +139,7 @@ static void build_prologue(struct jit_ctx *ctx) stack_adjust = round_up(stack_adjust, 16); stack_adjust += bpf_stack_adjust; + move_reg(ctx, LOONGARCH_GPR_T0, LOONGARCH_GPR_RA); /* Reserve space for the move_imm + jirl instruction */ for (i = 0; i < LOONGARCH_LONG_JUMP_NINSNS; i++) emit_insn(ctx, nop); @@ -238,7 +239,7 @@ static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call) * Call the next bpf prog and skip the first instruction * of TCC initialization. */ - emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T3, 6); + emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T3, 7); } } @@ -280,6 +281,8 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx, int insn) * goto out; */ tc_ninsn = insn ? ctx->offset[insn+1] - ctx->offset[insn] : ctx->offset[0]; + emit_zext_32(ctx, a2, true); + off = offsetof(struct bpf_array, map.max_entries); emit_insn(ctx, ldwu, t1, a1, off); /* bgeu $a2, $t1, jmp_offset */ @@ -950,6 +953,22 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext emit_insn(ctx, ldd, REG_TCC, LOONGARCH_GPR_SP, tcc_ptr_off); } + if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { + const struct btf_func_model *m; + int i; + + m = bpf_jit_find_kfunc_model(ctx->prog, insn); + if (!m) + return -EINVAL; + + for (i = 0; i < m->nr_args; i++) { + u8 reg = regmap[BPF_REG_1 + i]; + bool sign = m->arg_flags[i] & BTF_FMODEL_SIGNED_ARG; + + emit_abi_ext(ctx, reg, m->arg_size[i], sign); + } + } + move_addr(ctx, t1, func_addr); emit_insn(ctx, jirl, LOONGARCH_GPR_RA, t1, 0); @@ -1265,7 +1284,7 @@ static int emit_jump_or_nops(void *target, void *ip, u32 *insns, bool is_call) return 0; } - return emit_jump_and_link(&ctx, is_call ? LOONGARCH_GPR_T0 : LOONGARCH_GPR_ZERO, (u64)target); + return emit_jump_and_link(&ctx, is_call ? LOONGARCH_GPR_RA : LOONGARCH_GPR_ZERO, (u64)target); } static int emit_call(struct jit_ctx *ctx, u64 addr) @@ -1288,6 +1307,10 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type, void *old_addr, void *new_addr) { int ret; + unsigned long size = 0; + unsigned long offset = 0; + void *image = NULL; + char namebuf[KSYM_NAME_LEN]; bool is_call = (poke_type == BPF_MOD_CALL); u32 old_insns[LOONGARCH_LONG_JUMP_NINSNS] = {[0 ... 4] = INSN_NOP}; u32 new_insns[LOONGARCH_LONG_JUMP_NINSNS] = {[0 ... 4] = INSN_NOP}; @@ -1295,9 +1318,20 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type, /* Only poking bpf text is supported. Since kernel function entry * is set up by ftrace, we rely on ftrace to poke kernel functions. */ - if (!is_bpf_text_address((unsigned long)ip)) + if (!bpf_address_lookup((unsigned long)ip, &size, &offset, namebuf)) return -ENOTSUPP; + image = ip - offset; + + /* zero offset means we're poking bpf prog entry */ + if (offset == 0) { + /* skip to the nop instruction in bpf prog entry: + * move t0, ra + * nop + */ + ip = image + LOONGARCH_INSN_SIZE; + } + ret = emit_jump_or_nops(old_addr, ip, old_insns, is_call); if (ret) return ret; @@ -1619,14 +1653,12 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i /* To traced function */ /* Ftrace jump skips 2 NOP instructions */ - if (is_kernel_text((unsigned long)orig_call)) + if (is_kernel_text((unsigned long)orig_call) || + is_module_text_address((unsigned long)orig_call)) orig_call += LOONGARCH_FENTRY_NBYTES; /* Direct jump skips 5 NOP instructions */ else if (is_bpf_text_address((unsigned long)orig_call)) orig_call += LOONGARCH_BPF_FENTRY_NBYTES; - /* Module tracing not supported - cause kernel lockups */ - else if (is_module_text_address((unsigned long)orig_call)) - return -ENOTSUPP; if (flags & BPF_TRAMP_F_CALL_ORIG) { move_addr(ctx, LOONGARCH_GPR_A0, (const u64)im); @@ -1719,12 +1751,16 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i emit_insn(ctx, ldd, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, 0); emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, 16); - if (flags & BPF_TRAMP_F_SKIP_FRAME) + if (flags & BPF_TRAMP_F_SKIP_FRAME) { /* return to parent function */ - emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_RA, 0); - else - /* return to traced function */ + move_reg(ctx, LOONGARCH_GPR_RA, LOONGARCH_GPR_T0); emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T0, 0); + } else { + /* return to traced function */ + move_reg(ctx, LOONGARCH_GPR_T1, LOONGARCH_GPR_RA); + move_reg(ctx, LOONGARCH_GPR_RA, LOONGARCH_GPR_T0); + emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T1, 0); + } } ret = ctx->idx; diff --git a/arch/loongarch/net/bpf_jit.h b/arch/loongarch/net/bpf_jit.h index 5697158fd1645f..75b6330030a9d1 100644 --- a/arch/loongarch/net/bpf_jit.h +++ b/arch/loongarch/net/bpf_jit.h @@ -88,6 +88,32 @@ static inline void emit_sext_32(struct jit_ctx *ctx, enum loongarch_gpr reg, boo emit_insn(ctx, addiw, reg, reg, 0); } +/* Emit proper extension according to ABI requirements. + * Note that it requires a value of size `size` already resides in register `reg`. + */ +static inline void emit_abi_ext(struct jit_ctx *ctx, int reg, u8 size, bool sign) +{ + /* ABI requires unsigned char/short to be zero-extended */ + if (!sign && (size == 1 || size == 2)) + return; + + switch (size) { + case 1: + emit_insn(ctx, extwb, reg, reg); + break; + case 2: + emit_insn(ctx, extwh, reg, reg); + break; + case 4: + emit_insn(ctx, addiw, reg, reg, 0); + break; + case 8: + break; + default: + pr_warn("bpf_jit: invalid size %d for extension\n", size); + } +} + static inline void move_addr(struct jit_ctx *ctx, enum loongarch_gpr rd, u64 addr) { u64 imm_11_0, imm_31_12, imm_51_32, imm_63_52; diff --git a/arch/loongarch/pci/pci.c b/arch/loongarch/pci/pci.c index d9fc5d520b3778..d923295ab8c665 100644 --- a/arch/loongarch/pci/pci.c +++ b/arch/loongarch/pci/pci.c @@ -14,6 +14,7 @@ #define PCI_DEVICE_ID_LOONGSON_HOST 0x7a00 #define PCI_DEVICE_ID_LOONGSON_DC1 0x7a06 #define PCI_DEVICE_ID_LOONGSON_DC2 0x7a36 +#define PCI_DEVICE_ID_LOONGSON_DC3 0x7a46 int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val) @@ -97,3 +98,4 @@ static void pci_fixup_vgadev(struct pci_dev *pdev) } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_DC1, pci_fixup_vgadev); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_DC2, pci_fixup_vgadev); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_DC3, pci_fixup_vgadev); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index e8683f58fd3e2a..83a6b68d8a39ae 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1408,7 +1408,6 @@ config CPU_LOONGSON32 select CPU_MIPS32 select CPU_MIPSR2 select CPU_HAS_PREFETCH - select CPU_HAS_LOAD_STORE_LR select CPU_SUPPORTS_32BIT_KERNEL select CPU_SUPPORTS_HIGHMEM select CPU_SUPPORTS_CPUFREQ diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index f39e85fd58fa99..b15615b2856907 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -54,10 +54,20 @@ static inline void ftrace_dyn_arch_init_insns(void) u32 *buf; unsigned int v1; - /* la v1, _mcount */ - v1 = 3; - buf = (u32 *)&insn_la_mcount[0]; - UASM_i_LA(&buf, v1, MCOUNT_ADDR); + /* If we are not in compat space, the number of generated + * instructions will exceed the maximum expected limit of 2. + * To prevent buffer overflow, we avoid generating them. + * insn_la_mcount will not be used later in ftrace_make_call. + */ + if (uasm_in_compat_space_p(MCOUNT_ADDR)) { + /* la v1, _mcount */ + v1 = 3; + buf = (u32 *)&insn_la_mcount[0]; + UASM_i_LA(&buf, v1, MCOUNT_ADDR); + } else { + pr_warn("ftrace: mcount address beyond 32 bits is not supported (%lX)\n", + MCOUNT_ADDR); + } /* jal (ftrace_caller + 8), jump over the first two instruction */ buf = (u32 *)&insn_jal_ftrace_caller; @@ -189,6 +199,13 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) unsigned int new; unsigned long ip = rec->ip; + /* When the code to patch does not belong to the kernel code + * space, we must use insn_la_mcount. However, if MCOUNT_ADDR + * is not in compat space, insn_la_mcount is not usable. + */ + if (!core_kernel_text(ip) && !uasm_in_compat_space_p(MCOUNT_ADDR)) + return -EFAULT; + new = core_kernel_text(ip) ? insn_jal_ftrace_caller : insn_la_mcount[0]; #ifdef CONFIG_64BIT diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c index 7f1c136ad85062..59833210542fff 100644 --- a/arch/mips/kernel/relocate.c +++ b/arch/mips/kernel/relocate.c @@ -420,7 +420,20 @@ void *__init relocate_kernel(void) goto out; /* The current thread is now within the relocated image */ +#ifndef CONFIG_CC_IS_CLANG __current_thread_info = RELOCATED(&init_thread_union); +#else + /* + * LLVM may wrongly restore $gp ($28) in epilog even if it's + * intentionally modified. Work around this by using inline + * assembly to assign $gp. $gp couldn't be listed as output or + * clobber, or LLVM will still restore its original value. + * See also LLVM upstream issue + * https://github.com/llvm/llvm-project/issues/176546 + */ + asm volatile("move $28, %0" : : + "r" (RELOCATED(&init_thread_union))); +#endif /* Return the new kernel's entry point */ kernel_entry = RELOCATED(start_kernel); diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index a673d3d68254bd..8986048f9b110b 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -425,6 +425,28 @@ void __init paging_init(void) static struct kcore_list kcore_kseg0; #endif +static inline void __init highmem_init(void) +{ +#ifdef CONFIG_HIGHMEM + unsigned long tmp; + + /* + * If CPU cannot support HIGHMEM discard the memory above highstart_pfn + */ + if (cpu_has_dc_aliases) { + memblock_remove(PFN_PHYS(highstart_pfn), -1); + return; + } + + for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) { + struct page *page = pfn_to_page(tmp); + + if (!memblock_is_memory(PFN_PHYS(tmp))) + SetPageReserved(page); + } +#endif +} + void __init arch_mm_preinit(void) { /* @@ -435,6 +457,7 @@ void __init arch_mm_preinit(void) maar_init(); setup_zero_pages(); /* Setup zeroed pages. */ + highmem_init(); #ifdef CONFIG_64BIT if ((unsigned long) &_text > (unsigned long) CKSEG0) diff --git a/arch/mips/sgi-ip22/ip22-gio.c b/arch/mips/sgi-ip22/ip22-gio.c index 5893ea4e382cae..19b70928d6dc38 100644 --- a/arch/mips/sgi-ip22/ip22-gio.c +++ b/arch/mips/sgi-ip22/ip22-gio.c @@ -372,7 +372,8 @@ static void ip22_check_gio(int slotno, unsigned long addr, int irq) gio_dev->resource.flags = IORESOURCE_MEM; gio_dev->irq = irq; dev_set_name(&gio_dev->dev, "%d", slotno); - gio_device_register(gio_dev); + if (gio_device_register(gio_dev)) + gio_dev_put(gio_dev); } else printk(KERN_INFO "GIO: slot %d : Empty\n", slotno); } diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c index 9abfe65492c65e..3de4b5933b1079 100644 --- a/arch/parisc/kernel/asm-offsets.c +++ b/arch/parisc/kernel/asm-offsets.c @@ -258,6 +258,8 @@ int main(void) BLANK(); DEFINE(TIF_BLOCKSTEP_PA_BIT, 31-TIF_BLOCKSTEP); DEFINE(TIF_SINGLESTEP_PA_BIT, 31-TIF_SINGLESTEP); + DEFINE(TIF_32BIT_PA_BIT, 31-TIF_32BIT); + BLANK(); DEFINE(ASM_PMD_SHIFT, PMD_SHIFT); DEFINE(ASM_PGDIR_SHIFT, PGDIR_SHIFT); diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index f4bf61a34701e5..e04c5d806c1051 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -1059,8 +1059,6 @@ ENTRY_CFI(intr_save) /* for os_hpmc */ STREG %r17, PT_IOR(%r29) #if defined(CONFIG_64BIT) - b,n intr_save2 - skip_save_ior: /* We have a itlb miss, and when executing code above 4 Gb on ILP64, we * need to adjust iasq/iaoq here in the same way we adjusted isr/ior @@ -1069,10 +1067,17 @@ skip_save_ior: bb,COND(>=),n %r8,PSW_W_BIT,intr_save2 LDREG PT_IASQ0(%r29), %r16 LDREG PT_IAOQ0(%r29), %r17 - /* adjust iasq/iaoq */ + /* adjust iasq0/iaoq0 */ space_adjust %r16,%r17,%r1 STREG %r16, PT_IASQ0(%r29) STREG %r17, PT_IAOQ0(%r29) + + LDREG PT_IASQ1(%r29), %r16 + LDREG PT_IAOQ1(%r29), %r17 + /* adjust iasq1/iaoq1 */ + space_adjust %r16,%r17,%r1 + STREG %r16, PT_IASQ1(%r29) + STREG %r17, PT_IAOQ1(%r29) #else skip_save_ior: #endif @@ -1841,6 +1846,10 @@ syscall_restore_rfi: extru,= %r19,TIF_BLOCKSTEP_PA_BIT,1,%r0 depi -1,7,1,%r20 /* T bit */ +#ifdef CONFIG_64BIT + extru,<> %r19,TIF_32BIT_PA_BIT,1,%r0 + depi -1,4,1,%r20 /* W bit */ +#endif STREG %r20,TASK_PT_PSW(%r1) /* Always store space registers, since sr3 can be changed (e.g. fork) */ @@ -1854,7 +1863,6 @@ syscall_restore_rfi: STREG %r25,TASK_PT_IASQ0(%r1) STREG %r25,TASK_PT_IASQ1(%r1) - /* XXX W bit??? */ /* Now if old D bit is clear, it means we didn't save all registers * on syscall entry, so do that now. This only happens on TRACEME * calls, or if someone attached to us while we were on a syscall. diff --git a/arch/powerpc/boot/addnote.c b/arch/powerpc/boot/addnote.c index 53b3b2621457d4..78704927453aa6 100644 --- a/arch/powerpc/boot/addnote.c +++ b/arch/powerpc/boot/addnote.c @@ -68,8 +68,8 @@ static int e_class = ELFCLASS32; #define PUT_16BE(off, v)(buf[off] = ((v) >> 8) & 0xff, \ buf[(off) + 1] = (v) & 0xff) #define PUT_32BE(off, v)(PUT_16BE((off), (v) >> 16L), PUT_16BE((off) + 2, (v))) -#define PUT_64BE(off, v)((PUT_32BE((off), (v) >> 32L), \ - PUT_32BE((off) + 4, (v)))) +#define PUT_64BE(off, v)((PUT_32BE((off), (unsigned long long)(v) >> 32L), \ + PUT_32BE((off) + 4, (unsigned long long)(v)))) #define GET_16LE(off) ((buf[off]) + (buf[(off)+1] << 8)) #define GET_32LE(off) (GET_16LE(off) + (GET_16LE((off)+2U) << 16U)) @@ -78,7 +78,8 @@ static int e_class = ELFCLASS32; #define PUT_16LE(off, v) (buf[off] = (v) & 0xff, \ buf[(off) + 1] = ((v) >> 8) & 0xff) #define PUT_32LE(off, v) (PUT_16LE((off), (v)), PUT_16LE((off) + 2, (v) >> 16L)) -#define PUT_64LE(off, v) (PUT_32LE((off), (v)), PUT_32LE((off) + 4, (v) >> 32L)) +#define PUT_64LE(off, v) (PUT_32LE((off), (unsigned long long)(v)), \ + PUT_32LE((off) + 4, (unsigned long long)(v) >> 32L)) #define GET_16(off) (e_data == ELFDATA2MSB ? GET_16BE(off) : GET_16LE(off)) #define GET_32(off) (e_data == ELFDATA2MSB ? GET_32BE(off) : GET_32LE(off)) diff --git a/arch/powerpc/include/asm/book3s/32/tlbflush.h b/arch/powerpc/include/asm/book3s/32/tlbflush.h index e43534da5207aa..4be2200a3c7e1e 100644 --- a/arch/powerpc/include/asm/book3s/32/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/32/tlbflush.h @@ -11,6 +11,7 @@ void hash__flush_tlb_mm(struct mm_struct *mm); void hash__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); void hash__flush_range(struct mm_struct *mm, unsigned long start, unsigned long end); +void hash__flush_gather(struct mmu_gather *tlb); #ifdef CONFIG_SMP void _tlbie(unsigned long address); @@ -29,7 +30,9 @@ void _tlbia(void); static inline void tlb_flush(struct mmu_gather *tlb) { /* 603 needs to flush the whole TLB here since it doesn't use a hash table. */ - if (!mmu_has_feature(MMU_FTR_HPTE_TABLE)) + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) + hash__flush_gather(tlb); + else _tlbia(); } diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 3463514232071e..af12e2ba8eb856 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -524,7 +524,6 @@ void slb_save_contents(struct slb_entry *slb_ptr); void slb_dump_contents(struct slb_entry *slb_ptr); extern void slb_vmalloc_update(void); -void preload_new_slb_context(unsigned long start, unsigned long sp); #ifdef CONFIG_PPC_64S_HASH_MMU void slb_set_size(u16 size); diff --git a/arch/powerpc/include/asm/crash_reserve.h b/arch/powerpc/include/asm/crash_reserve.h index 6467ce29b1fabf..d1b570ddbf98bf 100644 --- a/arch/powerpc/include/asm/crash_reserve.h +++ b/arch/powerpc/include/asm/crash_reserve.h @@ -5,4 +5,12 @@ /* crash kernel regions are Page size agliged */ #define CRASH_ALIGN PAGE_SIZE +#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION +static inline bool arch_add_crash_res_to_iomem(void) +{ + return false; +} +#define arch_add_crash_res_to_iomem arch_add_crash_res_to_iomem +#endif + #endif /* _ASM_POWERPC_CRASH_RESERVE_H */ diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 5e34611de9ef40..b7ebb4ac2c7103 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -289,6 +289,8 @@ void eeh_pe_dev_traverse(struct eeh_pe *root, void eeh_pe_restore_bars(struct eeh_pe *pe); const char *eeh_pe_loc_get(struct eeh_pe *pe); struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe); +const char *eeh_pe_loc_get_bus(struct pci_bus *bus); +struct pci_bus *eeh_pe_bus_get_nolock(struct eeh_pe *pe); void eeh_show_enabled(void); int __init eeh_init(struct eeh_ops *ops); diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h index dab63b82a8d4f3..f2009d7c8cfa75 100644 --- a/arch/powerpc/include/asm/kup.h +++ b/arch/powerpc/include/asm/kup.h @@ -134,7 +134,6 @@ static __always_inline void kuap_assert_locked(void) static __always_inline void allow_read_from_user(const void __user *from, unsigned long size) { - barrier_nospec(); allow_user_access(NULL, from, size, KUAP_READ); } @@ -146,7 +145,6 @@ static __always_inline void allow_write_to_user(void __user *to, unsigned long s static __always_inline void allow_read_write_user(void __user *to, const void __user *from, unsigned long size) { - barrier_nospec(); allow_user_access(to, from, size, KUAP_READ_WRITE); } diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 4f5a46a77fa2b6..3987a5c33558bd 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -301,6 +301,7 @@ do { \ __typeof__(sizeof(*(ptr))) __gu_size = sizeof(*(ptr)); \ \ might_fault(); \ + barrier_nospec(); \ allow_read_from_user(__gu_addr, __gu_size); \ __get_user_size_allowed(__gu_val, __gu_addr, __gu_size, __gu_err); \ prevent_read_from_user(__gu_addr, __gu_size); \ @@ -329,6 +330,7 @@ raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) { unsigned long ret; + barrier_nospec(); allow_read_write_user(to, from, n); ret = __copy_tofrom_user(to, from, n); prevent_read_write_user(to, from, n); @@ -415,6 +417,7 @@ static __must_check __always_inline bool user_access_begin(const void __user *pt might_fault(); + barrier_nospec(); allow_read_write_user((void __user *)ptr, ptr, len); return true; } @@ -431,6 +434,7 @@ user_read_access_begin(const void __user *ptr, size_t len) might_fault(); + barrier_nospec(); allow_read_from_user(ptr, len); return true; } diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 7f63f1cdc6c39e..ca00c4824e313f 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -20,6 +20,7 @@ #include #include #include +#include #define NO_SCROLL @@ -463,7 +464,7 @@ static noinline void draw_byte(unsigned char c, long locX, long locY) { unsigned char *base = calc_base(locX << 3, locY << 4); unsigned int font_index = c * 16; - const unsigned char *font = font_sun_8x16.data + font_index; + const unsigned char *font = PTRRELOC(font_sun_8x16.data) + font_index; int rb = dispDeviceRowBytes; rmci_maybe_on(); diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index ef78ff77cf8f21..028f6915853234 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -846,7 +846,7 @@ void eeh_handle_normal_event(struct eeh_pe *pe) pci_lock_rescan_remove(); - bus = eeh_pe_bus_get(pe); + bus = eeh_pe_bus_get_nolock(pe); if (!bus) { pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n", __func__, pe->phb->global_number, pe->addr); @@ -886,14 +886,15 @@ void eeh_handle_normal_event(struct eeh_pe *pe) /* Log the event */ if (pe->type & EEH_PE_PHB) { pr_err("EEH: Recovering PHB#%x, location: %s\n", - pe->phb->global_number, eeh_pe_loc_get(pe)); + pe->phb->global_number, eeh_pe_loc_get_bus(bus)); } else { struct eeh_pe *phb_pe = eeh_phb_pe_get(pe->phb); pr_err("EEH: Recovering PHB#%x-PE#%x\n", pe->phb->global_number, pe->addr); pr_err("EEH: PE location: %s, PHB location: %s\n", - eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe)); + eeh_pe_loc_get_bus(bus), + eeh_pe_loc_get_bus(eeh_pe_bus_get_nolock(phb_pe))); } #ifdef CONFIG_STACKTRACE @@ -1098,7 +1099,7 @@ void eeh_handle_normal_event(struct eeh_pe *pe) eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); - bus = eeh_pe_bus_get(pe); + bus = eeh_pe_bus_get_nolock(pe); if (bus) pci_hp_remove_devices(bus); else @@ -1222,7 +1223,7 @@ void eeh_handle_special_event(void) (phb_pe->state & EEH_PE_RECOVERING)) continue; - bus = eeh_pe_bus_get(phb_pe); + bus = eeh_pe_bus_get_nolock(phb_pe); if (!bus) { pr_err("%s: Cannot find PCI bus for " "PHB#%x-PE#%x\n", diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index e740101fadf3b1..040e8f69a4aa86 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -812,6 +812,24 @@ void eeh_pe_restore_bars(struct eeh_pe *pe) const char *eeh_pe_loc_get(struct eeh_pe *pe) { struct pci_bus *bus = eeh_pe_bus_get(pe); + return eeh_pe_loc_get_bus(bus); +} + +/** + * eeh_pe_loc_get_bus - Retrieve location code binding to the given PCI bus + * @bus: PCI bus + * + * Retrieve the location code associated with the given PCI bus. If the bus + * is a root bus, the location code is fetched from the PHB device tree node + * or root port. Otherwise, the location code is obtained from the device + * tree node of the upstream bridge of the bus. The function walks up the + * bus hierarchy if necessary, checking each node for the appropriate + * location code property ("ibm,io-base-loc-code" for root buses, + * "ibm,slot-location-code" for others). If no location code is found, + * returns "N/A". + */ +const char *eeh_pe_loc_get_bus(struct pci_bus *bus) +{ struct device_node *dn; const char *loc = NULL; @@ -838,8 +856,9 @@ const char *eeh_pe_loc_get(struct eeh_pe *pe) } /** - * eeh_pe_bus_get - Retrieve PCI bus according to the given PE + * _eeh_pe_bus_get - Retrieve PCI bus according to the given PE * @pe: EEH PE + * @do_lock: Is the caller already held the pci_lock_rescan_remove? * * Retrieve the PCI bus according to the given PE. Basically, * there're 3 types of PEs: PHB/Bus/Device. For PHB PE, the @@ -847,7 +866,7 @@ const char *eeh_pe_loc_get(struct eeh_pe *pe) * returned for BUS PE. However, we don't have associated PCI * bus for DEVICE PE. */ -struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) +static struct pci_bus *_eeh_pe_bus_get(struct eeh_pe *pe, bool do_lock) { struct eeh_dev *edev; struct pci_dev *pdev; @@ -862,11 +881,58 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) /* Retrieve the parent PCI bus of first (top) PCI device */ edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry); - pci_lock_rescan_remove(); + if (do_lock) + pci_lock_rescan_remove(); pdev = eeh_dev_to_pci_dev(edev); if (pdev) bus = pdev->bus; - pci_unlock_rescan_remove(); + if (do_lock) + pci_unlock_rescan_remove(); return bus; } + +/** + * eeh_pe_bus_get - Retrieve PCI bus associated with the given EEH PE, locking + * if needed + * @pe: Pointer to the EEH PE + * + * This function is a wrapper around _eeh_pe_bus_get(), which retrieves the PCI + * bus associated with the provided EEH PE structure. It acquires the PCI + * rescans lock to ensure safe access to shared data during the retrieval + * process. This function should be used when the caller requires the PCI bus + * while holding the rescan/remove lock, typically during operations that modify + * or inspect PCIe device state in a safe manner. + * + * RETURNS: + * A pointer to the PCI bus associated with the EEH PE, or NULL if none found. + */ + +struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) +{ + return _eeh_pe_bus_get(pe, true); +} + +/** + * eeh_pe_bus_get_nolock - Retrieve PCI bus associated with the given EEH PE + * without locking + * @pe: Pointer to the EEH PE + * + * This function is a variant of _eeh_pe_bus_get() that retrieves the PCI bus + * associated with the specified EEH PE without acquiring the + * pci_lock_rescan_remove lock. It should only be used when the caller can + * guarantee safe access to PE structures without the need for that lock, + * typically in contexts where the lock is already held locking is otherwise + * managed. + * + * RETURNS: + * pointer to the PCI bus associated with the EEH PE, or NULL if none is found. + * + * NOTE: + * Use this function carefully to avoid race conditions and data corruption. + */ + +struct pci_bus *eeh_pe_bus_get_nolock(struct eeh_pe *pe) +{ + return _eeh_pe_bus_get(pe, false); +} diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index f4a8c98772491a..1beb578c641147 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -263,10 +263,9 @@ interrupt_return: mtspr SPRN_SRR1,r12 BEGIN_FTR_SECTION + lwarx r0,0,r1 +END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) stwcx. r0,0,r1 /* to clear the reservation */ -FTR_SECTION_ELSE - lwarx r0,0,r1 -ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) lwz r3,_CCR(r1) lwz r4,_LINK(r1) @@ -306,10 +305,9 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) mtspr SPRN_SRR1,r12 BEGIN_FTR_SECTION + lwarx r0,0,r1 +END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) stwcx. r0,0,r1 /* to clear the reservation */ -FTR_SECTION_ELSE - lwarx r0,0,r1 -ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) lwz r3,_LINK(r1) lwz r4,_CTR(r1) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index eb23966ac0a9f0..a45fe147868bc4 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1897,8 +1897,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) return 0; } -void preload_new_slb_context(unsigned long start, unsigned long sp); - /* * Set up a thread for executing a new program */ @@ -1906,9 +1904,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) { #ifdef CONFIG_PPC64 unsigned long load_addr = regs->gpr[2]; /* saved by ELF_PLAT_INIT */ - - if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled()) - preload_new_slb_context(start, sp); #endif #ifdef CONFIG_PPC_TRANSACTIONAL_MEM diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index 222aa326daceef..825ab8a88f18e6 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -202,6 +202,23 @@ static void kexec_prepare_cpus_wait(int wait_state) mb(); } + +/* + * The add_cpu() call in wake_offline_cpus() can fail as cpu_bootable() + * returns false for CPUs that fail the cpu_smt_thread_allowed() check + * or non primary threads if SMT is disabled. Re-enable SMT and set the + * number of SMT threads to threads per core. + */ +static void kexec_smt_reenable(void) +{ +#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) + lock_device_hotplug(); + cpu_smt_num_threads = threads_per_core; + cpu_smt_control = CPU_SMT_ENABLED; + unlock_device_hotplug(); +#endif +} + /* * We need to make sure each present CPU is online. The next kernel will scan * the device tree and assume primary threads are online and query secondary @@ -216,6 +233,8 @@ static void wake_offline_cpus(void) { int cpu = 0; + kexec_smt_reenable(); + for_each_present_cpu(cpu) { if (!cpu_online(cpu)) { printk(KERN_INFO "kexec: Waking offline cpu %d.\n", diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c index 3702b0bdab1410..426bdca4667e7b 100644 --- a/arch/powerpc/kexec/ranges.c +++ b/arch/powerpc/kexec/ranges.c @@ -697,8 +697,8 @@ int remove_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size) * two half. */ else { + size = mem_rngs->ranges[i].end - end + 1; mem_rngs->ranges[i].end = base - 1; - size = mem_rngs->ranges[i].end - end; ret = add_mem_range(mem_ranges, end + 1, size); } } diff --git a/arch/powerpc/mm/book3s32/tlb.c b/arch/powerpc/mm/book3s32/tlb.c index 9ad6b56bfec96e..e54a7b0112322e 100644 --- a/arch/powerpc/mm/book3s32/tlb.c +++ b/arch/powerpc/mm/book3s32/tlb.c @@ -105,3 +105,12 @@ void hash__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) flush_hash_pages(mm->context.id, vmaddr, pmd_val(*pmd), 1); } EXPORT_SYMBOL(hash__flush_tlb_page); + +void hash__flush_gather(struct mmu_gather *tlb) +{ + if (tlb->fullmm || tlb->need_flush_all) + hash__flush_tlb_mm(tlb->mm); + else + hash__flush_range(tlb->mm, tlb->start, tlb->end); +} +EXPORT_SYMBOL(hash__flush_gather); diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 3aee3af614af89..c99be1286d517d 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1302,11 +1302,14 @@ static void __init htab_initialize(void) unsigned long table; unsigned long pteg_count; unsigned long prot; - phys_addr_t base = 0, size = 0, end; + phys_addr_t base = 0, size = 0, end, limit = MEMBLOCK_ALLOC_ANYWHERE; u64 i; DBG(" -> htab_initialize()\n"); + if (firmware_has_feature(FW_FEATURE_LPAR)) + limit = ppc64_rma_size; + if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) { mmu_kernel_ssize = MMU_SEGSIZE_1T; mmu_highuser_ssize = MMU_SEGSIZE_1T; @@ -1322,7 +1325,7 @@ static void __init htab_initialize(void) // Too early to use nr_cpu_ids, so use NR_CPUS tmp = memblock_phys_alloc_range(sizeof(struct stress_hpt_struct) * NR_CPUS, __alignof__(struct stress_hpt_struct), - 0, MEMBLOCK_ALLOC_ANYWHERE); + MEMBLOCK_LOW_LIMIT, limit); memset((void *)tmp, 0xff, sizeof(struct stress_hpt_struct) * NR_CPUS); stress_hpt_struct = __va(tmp); @@ -1356,11 +1359,10 @@ static void __init htab_initialize(void) mmu_hash_ops.hpte_clear_all(); #endif } else { - unsigned long limit = MEMBLOCK_ALLOC_ANYWHERE; table = memblock_phys_alloc_range(htab_size_bytes, htab_size_bytes, - 0, limit); + MEMBLOCK_LOW_LIMIT, limit); if (!table) panic("ERROR: Failed to allocate %pa bytes below %pa\n", &htab_size_bytes, &limit); diff --git a/arch/powerpc/mm/book3s64/internal.h b/arch/powerpc/mm/book3s64/internal.h index a57a25f06a215b..c26a6f0c90fcd2 100644 --- a/arch/powerpc/mm/book3s64/internal.h +++ b/arch/powerpc/mm/book3s64/internal.h @@ -24,8 +24,6 @@ static inline bool stress_hpt(void) void hpt_do_stress(unsigned long ea, unsigned long hpte_group); -void slb_setup_new_exec(void); - void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush); #endif /* ARCH_POWERPC_MM_BOOK3S64_INTERNAL_H */ diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c index 4e1e45420bd496..fb9dcf9ca59988 100644 --- a/arch/powerpc/mm/book3s64/mmu_context.c +++ b/arch/powerpc/mm/book3s64/mmu_context.c @@ -150,8 +150,6 @@ static int hash__init_new_context(struct mm_struct *mm) void hash__setup_new_exec(void) { slice_setup_new_exec(); - - slb_setup_new_exec(); } #else static inline int hash__init_new_context(struct mm_struct *mm) diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c index 6b783552403c60..7e053c561a09df 100644 --- a/arch/powerpc/mm/book3s64/slb.c +++ b/arch/powerpc/mm/book3s64/slb.c @@ -328,94 +328,6 @@ static void preload_age(struct thread_info *ti) ti->slb_preload_tail = (ti->slb_preload_tail + 1) % SLB_PRELOAD_NR; } -void slb_setup_new_exec(void) -{ - struct thread_info *ti = current_thread_info(); - struct mm_struct *mm = current->mm; - unsigned long exec = 0x10000000; - - WARN_ON(irqs_disabled()); - - /* - * preload cache can only be used to determine whether a SLB - * entry exists if it does not start to overflow. - */ - if (ti->slb_preload_nr + 2 > SLB_PRELOAD_NR) - return; - - hard_irq_disable(); - - /* - * We have no good place to clear the slb preload cache on exec, - * flush_thread is about the earliest arch hook but that happens - * after we switch to the mm and have already preloaded the SLBEs. - * - * For the most part that's probably okay to use entries from the - * previous exec, they will age out if unused. It may turn out to - * be an advantage to clear the cache before switching to it, - * however. - */ - - /* - * preload some userspace segments into the SLB. - * Almost all 32 and 64bit PowerPC executables are linked at - * 0x10000000 so it makes sense to preload this segment. - */ - if (!is_kernel_addr(exec)) { - if (preload_add(ti, exec)) - slb_allocate_user(mm, exec); - } - - /* Libraries and mmaps. */ - if (!is_kernel_addr(mm->mmap_base)) { - if (preload_add(ti, mm->mmap_base)) - slb_allocate_user(mm, mm->mmap_base); - } - - /* see switch_slb */ - asm volatile("isync" : : : "memory"); - - local_irq_enable(); -} - -void preload_new_slb_context(unsigned long start, unsigned long sp) -{ - struct thread_info *ti = current_thread_info(); - struct mm_struct *mm = current->mm; - unsigned long heap = mm->start_brk; - - WARN_ON(irqs_disabled()); - - /* see above */ - if (ti->slb_preload_nr + 3 > SLB_PRELOAD_NR) - return; - - hard_irq_disable(); - - /* Userspace entry address. */ - if (!is_kernel_addr(start)) { - if (preload_add(ti, start)) - slb_allocate_user(mm, start); - } - - /* Top of stack, grows down. */ - if (!is_kernel_addr(sp)) { - if (preload_add(ti, sp)) - slb_allocate_user(mm, sp); - } - - /* Bottom of heap, grows up. */ - if (heap && !is_kernel_addr(heap)) { - if (preload_add(ti, heap)) - slb_allocate_user(mm, heap); - } - - /* see switch_slb */ - asm volatile("isync" : : : "memory"); - - local_irq_enable(); -} - static void slb_cache_slbie_kernel(unsigned int index) { unsigned long slbie_data = get_paca()->slb_cache[index]; diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c index a6baa6166d9401..671d0dc00c6d07 100644 --- a/arch/powerpc/mm/ptdump/hashpagetable.c +++ b/arch/powerpc/mm/ptdump/hashpagetable.c @@ -216,6 +216,8 @@ static int native_find(unsigned long ea, int psize, bool primary, u64 *v, u64 vpn = hpt_vpn(ea, vsid, ssize); hash = hpt_hash(vpn, shift, ssize); want_v = hpte_encode_avpn(vpn, psize, ssize); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + want_v = hpte_old_to_new_v(want_v); /* to check in the secondary hash table, we invert the hash */ if (!primary) @@ -229,6 +231,10 @@ static int native_find(unsigned long ea, int psize, bool primary, u64 *v, u64 /* HPTE matches */ *v = be64_to_cpu(hptep->v); *r = be64_to_cpu(hptep->r); + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + *v = hpte_new_to_old_v(*v, *r); + *r = hpte_new_to_old_r(*r); + } return 0; } ++hpte_group; diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 88ad5ba7b87fd0..21f7f26a5e2f35 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -1122,7 +1122,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type, branch_flags = poke_type == BPF_MOD_CALL ? BRANCH_SET_LINK : 0; /* We currently only support poking bpf programs */ - if (!__bpf_address_lookup(bpf_func, &size, &offset, name)) { + if (!bpf_address_lookup(bpf_func, &size, &offset, name)) { pr_err("%s (0x%lx): kernel/modules are not supported\n", __func__, bpf_func); return -EOPNOTSUPP; } diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index 0823fa2da15162..310dab4bc86790 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -532,6 +532,7 @@ static int cmm_migratepage(struct balloon_dev_info *b_dev_info, spin_lock_irqsave(&b_dev_info->pages_lock, flags); balloon_page_insert(b_dev_info, newpage); + __count_vm_event(BALLOON_MIGRATE); b_dev_info->isolated_pages--; spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); @@ -550,7 +551,6 @@ static int cmm_migratepage(struct balloon_dev_info *b_dev_info, static void cmm_balloon_compaction_init(void) { - balloon_devinfo_init(&b_dev_info); b_dev_info.migratepage = cmm_migratepage; } #else /* CONFIG_BALLOON_COMPACTION */ @@ -572,6 +572,7 @@ static int cmm_init(void) if (!firmware_has_feature(FW_FEATURE_CMO) && !simulate) return -EOPNOTSUPP; + balloon_devinfo_init(&b_dev_info); cmm_balloon_compaction_init(); rc = register_oom_notifier(&cmm_oom_nb); diff --git a/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh b/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh index 06706903503b6c..baed467a016b3d 100755 --- a/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh +++ b/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh @@ -2,7 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 set -e -set -o pipefail # To debug, uncomment the following line # set -x diff --git a/arch/powerpc/tools/gcc-check-mprofile-kernel.sh b/arch/powerpc/tools/gcc-check-mprofile-kernel.sh index 73e331e7660ef1..6193b0ed0c7751 100755 --- a/arch/powerpc/tools/gcc-check-mprofile-kernel.sh +++ b/arch/powerpc/tools/gcc-check-mprofile-kernel.sh @@ -2,7 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 set -e -set -o pipefail # To debug, uncomment the following line # set -x diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile index bfc3d0b75b9b2b..5301adf5f3f5d2 100644 --- a/arch/riscv/boot/Makefile +++ b/arch/riscv/boot/Makefile @@ -31,11 +31,7 @@ $(obj)/xipImage: vmlinux FORCE endif -ifdef CONFIG_RELOCATABLE -$(obj)/Image: vmlinux.unstripped FORCE -else $(obj)/Image: vmlinux FORCE -endif $(call if_changed,objcopy) $(obj)/Image.gz: $(obj)/Image FORCE diff --git a/arch/riscv/crypto/Kconfig b/arch/riscv/crypto/Kconfig index a75d6325607b4c..14c5acb935e941 100644 --- a/arch/riscv/crypto/Kconfig +++ b/arch/riscv/crypto/Kconfig @@ -4,7 +4,8 @@ menu "Accelerated Cryptographic Algorithms for CPU (riscv)" config CRYPTO_AES_RISCV64 tristate "Ciphers: AES, modes: ECB, CBC, CTS, CTR, XTS" - depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO + depends on 64BIT && TOOLCHAIN_HAS_VECTOR_CRYPTO && \ + RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS select CRYPTO_ALGAPI select CRYPTO_LIB_AES select CRYPTO_SKCIPHER @@ -20,7 +21,8 @@ config CRYPTO_AES_RISCV64 config CRYPTO_GHASH_RISCV64 tristate "Hash functions: GHASH" - depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO + depends on 64BIT && TOOLCHAIN_HAS_VECTOR_CRYPTO && \ + RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS select CRYPTO_GCM help GCM GHASH function (NIST SP 800-38D) @@ -30,7 +32,8 @@ config CRYPTO_GHASH_RISCV64 config CRYPTO_SM3_RISCV64 tristate "Hash functions: SM3 (ShangMi 3)" - depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO + depends on 64BIT && TOOLCHAIN_HAS_VECTOR_CRYPTO && \ + RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS select CRYPTO_HASH select CRYPTO_LIB_SM3 help @@ -42,7 +45,8 @@ config CRYPTO_SM3_RISCV64 config CRYPTO_SM4_RISCV64 tristate "Ciphers: SM4 (ShangMi 4)" - depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO + depends on 64BIT && TOOLCHAIN_HAS_VECTOR_CRYPTO && \ + RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS select CRYPTO_ALGAPI select CRYPTO_SM4 help diff --git a/arch/riscv/include/asm/compat.h b/arch/riscv/include/asm/compat.h index 6081327e55f5b6..28e115eed21805 100644 --- a/arch/riscv/include/asm/compat.h +++ b/arch/riscv/include/asm/compat.h @@ -2,7 +2,7 @@ #ifndef __ASM_COMPAT_H #define __ASM_COMPAT_H -#define COMPAT_UTS_MACHINE "riscv\0\0" +#define COMPAT_UTS_MACHINE "riscv32\0\0" /* * Architecture specific compatibility types diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 5a08eb5fe99fc4..30d1ea93dde347 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -124,10 +124,6 @@ #ifdef CONFIG_64BIT #include -#define VA_USER_SV39 (UL(1) << (VA_BITS_SV39 - 1)) -#define VA_USER_SV48 (UL(1) << (VA_BITS_SV48 - 1)) -#define VA_USER_SV57 (UL(1) << (VA_BITS_SV57 - 1)) - #define MMAP_VA_BITS_64 ((VA_BITS >= VA_BITS_SV48) ? VA_BITS_SV48 : VA_BITS) #define MMAP_MIN_VA_BITS_64 (VA_BITS_SV39) #define MMAP_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_VA_BITS_64) diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index f5f4f7f85543f2..6aef591a6bfcb5 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -97,13 +97,23 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, unsigne */ #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +/* + * Use a temporary variable for the output of the asm goto to avoid a + * triggering an LLVM assertion due to sign extending the output when + * it is used in later function calls: + * https://github.com/llvm/llvm-project/issues/143795 + */ #define __get_user_asm(insn, x, ptr, label) \ +do { \ + u64 __tmp; \ asm_goto_output( \ "1:\n" \ " " insn " %0, %1\n" \ _ASM_EXTABLE_UACCESS_ERR(1b, %l2, %0) \ - : "=&r" (x) \ - : "m" (*(ptr)) : : label) + : "=&r" (__tmp) \ + : "m" (*(ptr)) : : label); \ + (x) = (__typeof__(x))(unsigned long)__tmp; \ +} while (0) #else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ #define __get_user_asm(insn, x, ptr, label) \ do { \ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index f60fce69b7259f..a01f6439d62b1a 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -3,12 +3,6 @@ # Makefile for the RISC-V Linux kernel # -ifdef CONFIG_FTRACE -CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) -endif CFLAGS_syscall_table.o += $(call cc-disable-warning, override-init) CFLAGS_compat_syscall_table.o += $(call cc-disable-warning, override-init) @@ -24,7 +18,6 @@ CFLAGS_sbi_ecall.o := -mcmodel=medany ifdef CONFIG_FTRACE CFLAGS_REMOVE_alternative.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_cpufeature.o = $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_sbi_ecall.o = $(CC_FLAGS_FTRACE) endif ifdef CONFIG_RELOCATABLE CFLAGS_alternative.o += -fno-pie @@ -43,6 +36,14 @@ CFLAGS_sbi_ecall.o += -D__NO_FORTIFY endif endif +ifdef CONFIG_FTRACE +CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_sbi_ecall.o = $(CC_FLAGS_FTRACE) +endif + always-$(KBUILD_BUILTIN) += vmlinux.lds obj-y += head.o diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 72ca768f4e9191..2367e9755524ad 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -279,23 +279,22 @@ static const unsigned int riscv_a_exts[] = { RISCV_ISA_EXT_ZALRSC, }; +#define RISCV_ISA_EXT_ZKN \ + RISCV_ISA_EXT_ZBKB, \ + RISCV_ISA_EXT_ZBKC, \ + RISCV_ISA_EXT_ZBKX, \ + RISCV_ISA_EXT_ZKND, \ + RISCV_ISA_EXT_ZKNE, \ + RISCV_ISA_EXT_ZKNH + static const unsigned int riscv_zk_bundled_exts[] = { - RISCV_ISA_EXT_ZBKB, - RISCV_ISA_EXT_ZBKC, - RISCV_ISA_EXT_ZBKX, - RISCV_ISA_EXT_ZKND, - RISCV_ISA_EXT_ZKNE, + RISCV_ISA_EXT_ZKN, RISCV_ISA_EXT_ZKR, - RISCV_ISA_EXT_ZKT, + RISCV_ISA_EXT_ZKT }; static const unsigned int riscv_zkn_bundled_exts[] = { - RISCV_ISA_EXT_ZBKB, - RISCV_ISA_EXT_ZBKC, - RISCV_ISA_EXT_ZBKX, - RISCV_ISA_EXT_ZKND, - RISCV_ISA_EXT_ZKNE, - RISCV_ISA_EXT_ZKNH, + RISCV_ISA_EXT_ZKN }; static const unsigned int riscv_zks_bundled_exts[] = { diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c index 24b3f57d467f83..aff93090c4efc7 100644 --- a/arch/riscv/kernel/suspend.c +++ b/arch/riscv/kernel/suspend.c @@ -51,10 +51,11 @@ void suspend_restore_csrs(struct suspend_context *context) #ifdef CONFIG_MMU if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SSTC)) { - csr_write(CSR_STIMECMP, context->stimecmp); #if __riscv_xlen < 64 + csr_write(CSR_STIMECMP, ULONG_MAX); csr_write(CSR_STIMECMPH, context->stimecmph); #endif + csr_write(CSR_STIMECMP, context->stimecmp); } csr_write(CSR_SATP, context->satp); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 80230de167def3..47afea4ff1a8d2 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -339,8 +339,10 @@ void do_trap_ecall_u(struct pt_regs *regs) add_random_kstack_offset(); - if (syscall >= 0 && syscall < NR_syscalls) + if (syscall >= 0 && syscall < NR_syscalls) { + syscall = array_index_nospec(syscall, NR_syscalls); syscall_handler(regs, syscall); + } /* * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c index de1f96ea62251f..4d89b94128aea8 100644 --- a/arch/riscv/kvm/vcpu_insn.c +++ b/arch/riscv/kvm/vcpu_insn.c @@ -298,6 +298,22 @@ static int system_opcode_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, return (rc <= 0) ? rc : 1; } +static bool is_load_guest_page_fault(unsigned long scause) +{ + /** + * If a g-stage page fault occurs, the direct approach + * is to let the g-stage page fault handler handle it + * naturally, however, calling the g-stage page fault + * handler here seems rather strange. + * Considering this is a corner case, we can directly + * return to the guest and re-execute the same PC, this + * will trigger a g-stage page fault again and then the + * regular g-stage page fault handler will populate + * g-stage page table. + */ + return (scause == EXC_LOAD_GUEST_PAGE_FAULT); +} + /** * kvm_riscv_vcpu_virtual_insn -- Handle virtual instruction trap * @@ -323,6 +339,8 @@ int kvm_riscv_vcpu_virtual_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, ct->sepc, &utrap); if (utrap.scause) { + if (is_load_guest_page_fault(utrap.scause)) + return 1; utrap.sepc = ct->sepc; kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); return 1; @@ -378,6 +396,8 @@ int kvm_riscv_vcpu_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run, insn = kvm_riscv_vcpu_unpriv_read(vcpu, true, ct->sepc, &utrap); if (utrap.scause) { + if (is_load_guest_page_fault(utrap.scause)) + return 1; /* Redirect trap if we failed to read instruction */ utrap.sepc = ct->sepc; kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); @@ -504,6 +524,8 @@ int kvm_riscv_vcpu_mmio_store(struct kvm_vcpu *vcpu, struct kvm_run *run, insn = kvm_riscv_vcpu_unpriv_read(vcpu, true, ct->sepc, &utrap); if (utrap.scause) { + if (is_load_guest_page_fault(utrap.scause)) + return 1; /* Redirect trap if we failed to read instruction */ utrap.sepc = ct->sepc; kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index df22b10d91415e..e60d2b823e0916 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -270,6 +270,7 @@ config S390 select SPARSE_IRQ select SWIOTLB select SYSCTL_EXCEPTION_TRACE + select SYSTEM_DATA_VERIFICATION if KEXEC_SIG select THREAD_INFO_IN_TASK select TRACE_IRQFLAGS_SUPPORT select TTY @@ -296,7 +297,7 @@ config ARCH_SUPPORTS_KEXEC_FILE def_bool y config ARCH_SUPPORTS_KEXEC_SIG - def_bool MODULE_SIG_FORMAT + def_bool y config ARCH_SUPPORTS_KEXEC_PURGATORY def_bool y diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S index 50988022f9ea32..070bc18babd0ea 100644 --- a/arch/s390/boot/vmlinux.lds.S +++ b/arch/s390/boot/vmlinux.lds.S @@ -137,6 +137,15 @@ SECTIONS } _end = .; + /* Sections to be discarded */ + /DISCARD/ : { + COMMON_DISCARDS + *(.eh_frame) + *(*__ksymtab*) + *(___kcrctab*) + *(.modinfo) + } + DWARF_DEBUG ELF_DETAILS @@ -161,12 +170,4 @@ SECTIONS *(.rela.*) *(.rela_*) } ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!") - - /* Sections to be discarded */ - /DISCARD/ : { - COMMON_DISCARDS - *(.eh_frame) - *(*__ksymtab*) - *(___kcrctab*) - } } diff --git a/arch/s390/include/asm/fpu-insn.h b/arch/s390/include/asm/fpu-insn.h index e99f8bca8e08cf..96727f3bd0dce0 100644 --- a/arch/s390/include/asm/fpu-insn.h +++ b/arch/s390/include/asm/fpu-insn.h @@ -12,6 +12,7 @@ #ifndef __ASSEMBLER__ #include +#include #include asm(".include \"asm/fpu-insn-asm.h\"\n"); @@ -393,6 +394,7 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) : [vxr] "=Q" (*(u8 *)vxr) : [index] "d" (index), [v1] "I" (v1) : "memory"); + kmsan_unpoison_memory(vxr, size); } #else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ @@ -409,6 +411,7 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) : [vxr] "=R" (*(u8 *)vxr) : [index] "d" (index), [v1] "I" (v1) : "memory", "1"); + kmsan_unpoison_memory(vxr, size); } #endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ diff --git a/arch/s390/include/uapi/asm/ipl.h b/arch/s390/include/uapi/asm/ipl.h index 2cd28af50dd439..3d64a22516994b 100644 --- a/arch/s390/include/uapi/asm/ipl.h +++ b/arch/s390/include/uapi/asm/ipl.h @@ -15,6 +15,7 @@ struct ipl_pl_hdr { #define IPL_PL_FLAG_IPLPS 0x80 #define IPL_PL_FLAG_SIPL 0x40 #define IPL_PL_FLAG_IPLSR 0x20 +#define IPL_PL_FLAG_SBP 0x10 /* IPL Parameter Block header */ struct ipl_pb_hdr { diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 961a3d60a4ddda..dcdc7e27484867 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -262,6 +262,24 @@ static struct kobj_attribute sys_##_prefix##_##_name##_attr = \ sys_##_prefix##_##_name##_show, \ sys_##_prefix##_##_name##_store) +#define DEFINE_IPL_ATTR_BOOTPROG_RW(_prefix, _name, _fmt_out, _fmt_in, _hdr, _value) \ + IPL_ATTR_SHOW_FN(_prefix, _name, _fmt_out, (unsigned long long) _value) \ +static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + const char *buf, size_t len) \ +{ \ + unsigned long long value; \ + if (sscanf(buf, _fmt_in, &value) != 1) \ + return -EINVAL; \ + (_value) = value; \ + (_hdr).flags &= ~IPL_PL_FLAG_SBP; \ + return len; \ +} \ +static struct kobj_attribute sys_##_prefix##_##_name##_attr = \ + __ATTR(_name, 0644, \ + sys_##_prefix##_##_name##_show, \ + sys_##_prefix##_##_name##_store) + #define DEFINE_IPL_ATTR_STR_RW(_prefix, _name, _fmt_out, _fmt_in, _value)\ IPL_ATTR_SHOW_FN(_prefix, _name, _fmt_out, _value) \ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ @@ -818,12 +836,13 @@ DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%llx\n", reipl_block_fcp->fcp.wwpn); DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%llx\n", reipl_block_fcp->fcp.lun); -DEFINE_IPL_ATTR_RW(reipl_fcp, bootprog, "%lld\n", "%lld\n", - reipl_block_fcp->fcp.bootprog); DEFINE_IPL_ATTR_RW(reipl_fcp, br_lba, "%lld\n", "%lld\n", reipl_block_fcp->fcp.br_lba); DEFINE_IPL_ATTR_RW(reipl_fcp, device, "0.0.%04llx\n", "0.0.%llx\n", reipl_block_fcp->fcp.devno); +DEFINE_IPL_ATTR_BOOTPROG_RW(reipl_fcp, bootprog, "%lld\n", "%lld\n", + reipl_block_fcp->hdr, + reipl_block_fcp->fcp.bootprog); static void reipl_get_ascii_loadparm(char *loadparm, struct ipl_parameter_block *ibp) @@ -942,10 +961,11 @@ DEFINE_IPL_ATTR_RW(reipl_nvme, fid, "0x%08llx\n", "%llx\n", reipl_block_nvme->nvme.fid); DEFINE_IPL_ATTR_RW(reipl_nvme, nsid, "0x%08llx\n", "%llx\n", reipl_block_nvme->nvme.nsid); -DEFINE_IPL_ATTR_RW(reipl_nvme, bootprog, "%lld\n", "%lld\n", - reipl_block_nvme->nvme.bootprog); DEFINE_IPL_ATTR_RW(reipl_nvme, br_lba, "%lld\n", "%lld\n", reipl_block_nvme->nvme.br_lba); +DEFINE_IPL_ATTR_BOOTPROG_RW(reipl_nvme, bootprog, "%lld\n", "%lld\n", + reipl_block_nvme->hdr, + reipl_block_nvme->nvme.bootprog); static struct attribute *reipl_nvme_attrs[] = { &sys_reipl_nvme_fid_attr.attr, @@ -1038,8 +1058,9 @@ static const struct bin_attribute *const reipl_eckd_bin_attrs[] = { }; DEFINE_IPL_CCW_ATTR_RW(reipl_eckd, device, reipl_block_eckd->eckd); -DEFINE_IPL_ATTR_RW(reipl_eckd, bootprog, "%lld\n", "%lld\n", - reipl_block_eckd->eckd.bootprog); +DEFINE_IPL_ATTR_BOOTPROG_RW(reipl_eckd, bootprog, "%lld\n", "%lld\n", + reipl_block_eckd->hdr, + reipl_block_eckd->eckd.bootprog); static struct attribute *reipl_eckd_attrs[] = { &sys_reipl_eckd_device_attr.attr, @@ -1567,12 +1588,13 @@ DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%llx\n", dump_block_fcp->fcp.wwpn); DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%llx\n", dump_block_fcp->fcp.lun); -DEFINE_IPL_ATTR_RW(dump_fcp, bootprog, "%lld\n", "%lld\n", - dump_block_fcp->fcp.bootprog); DEFINE_IPL_ATTR_RW(dump_fcp, br_lba, "%lld\n", "%lld\n", dump_block_fcp->fcp.br_lba); DEFINE_IPL_ATTR_RW(dump_fcp, device, "0.0.%04llx\n", "0.0.%llx\n", dump_block_fcp->fcp.devno); +DEFINE_IPL_ATTR_BOOTPROG_RW(dump_fcp, bootprog, "%lld\n", "%lld\n", + dump_block_fcp->hdr, + dump_block_fcp->fcp.bootprog); DEFINE_IPL_ATTR_SCP_DATA_RW(dump_fcp, dump_block_fcp->hdr, dump_block_fcp->fcp, @@ -1604,10 +1626,11 @@ DEFINE_IPL_ATTR_RW(dump_nvme, fid, "0x%08llx\n", "%llx\n", dump_block_nvme->nvme.fid); DEFINE_IPL_ATTR_RW(dump_nvme, nsid, "0x%08llx\n", "%llx\n", dump_block_nvme->nvme.nsid); -DEFINE_IPL_ATTR_RW(dump_nvme, bootprog, "%lld\n", "%llx\n", - dump_block_nvme->nvme.bootprog); DEFINE_IPL_ATTR_RW(dump_nvme, br_lba, "%lld\n", "%llx\n", dump_block_nvme->nvme.br_lba); +DEFINE_IPL_ATTR_BOOTPROG_RW(dump_nvme, bootprog, "%lld\n", "%llx\n", + dump_block_nvme->hdr, + dump_block_nvme->nvme.bootprog); DEFINE_IPL_ATTR_SCP_DATA_RW(dump_nvme, dump_block_nvme->hdr, dump_block_nvme->nvme, @@ -1635,8 +1658,9 @@ static const struct attribute_group dump_nvme_attr_group = { /* ECKD dump device attributes */ DEFINE_IPL_CCW_ATTR_RW(dump_eckd, device, dump_block_eckd->eckd); -DEFINE_IPL_ATTR_RW(dump_eckd, bootprog, "%lld\n", "%llx\n", - dump_block_eckd->eckd.bootprog); +DEFINE_IPL_ATTR_BOOTPROG_RW(dump_eckd, bootprog, "%lld\n", "%llx\n", + dump_block_eckd->hdr, + dump_block_eckd->eckd.bootprog); IPL_ATTR_BR_CHR_SHOW_FN(dump, dump_block_eckd->eckd); IPL_ATTR_BR_CHR_STORE_FN(dump, dump_block_eckd->eckd); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index da84c0dc6b7e0f..70df4ca5d4436c 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -697,6 +697,7 @@ static void __ref smp_get_core_info(struct sclp_core_info *info, int early) continue; info->core[info->configured].core_id = address >> smp_cpu_mt_shift; + info->core[info->configured].type = boot_core_type; info->configured++; } info->combined = info->configured; diff --git a/arch/s390/mm/gmap_helpers.c b/arch/s390/mm/gmap_helpers.c index d4c3c36855e26c..38a2d82cd88a7a 100644 --- a/arch/s390/mm/gmap_helpers.c +++ b/arch/s390/mm/gmap_helpers.c @@ -47,6 +47,7 @@ static void ptep_zap_swap_entry(struct mm_struct *mm, swp_entry_t entry) void gmap_helper_zap_one_page(struct mm_struct *mm, unsigned long vmaddr) { struct vm_area_struct *vma; + unsigned long pgstev; spinlock_t *ptl; pgste_t pgste; pte_t *ptep; @@ -65,9 +66,13 @@ void gmap_helper_zap_one_page(struct mm_struct *mm, unsigned long vmaddr) if (pte_swap(*ptep)) { preempt_disable(); pgste = pgste_get_lock(ptep); + pgstev = pgste_val(pgste); - ptep_zap_swap_entry(mm, pte_to_swp_entry(*ptep)); - pte_clear(mm, vmaddr, ptep); + if ((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED || + (pgstev & _PGSTE_GPS_ZERO)) { + ptep_zap_swap_entry(mm, pte_to_swp_entry(*ptep)); + pte_clear(mm, vmaddr, ptep); + } pgste_set_unlock(ptep, pgste); preempt_enable(); diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index a9448088e762e0..b290107170e94a 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -181,6 +181,28 @@ static int __init ofpci_debug(char *str) __setup("ofpci_debug=", ofpci_debug); +static void of_fixup_pci_pref(struct pci_dev *dev, int index, + struct resource *res) +{ + struct pci_bus_region region; + + if (!(res->flags & IORESOURCE_MEM_64)) + return; + + if (!resource_size(res)) + return; + + pcibios_resource_to_bus(dev->bus, ®ion, res); + if (region.end <= ~((u32)0)) + return; + + if (!(res->flags & IORESOURCE_PREFETCH)) { + res->flags |= IORESOURCE_PREFETCH; + pci_info(dev, "reg 0x%x: fixup: pref added to 64-bit resource\n", + index); + } +} + static unsigned long pci_parse_of_flags(u32 addr0) { unsigned long flags = 0; @@ -244,6 +266,7 @@ static void pci_parse_of_addrs(struct platform_device *op, res->end = op_res->end; res->flags = flags; res->name = pci_name(dev); + of_fixup_pci_pref(dev, i, res); pci_info(dev, "reg 0x%x: %pR\n", i, res); } diff --git a/arch/um/Kconfig b/arch/um/Kconfig index 49781bee790580..93ed850d508ed2 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -5,6 +5,7 @@ menu "UML-specific options" config UML bool default y + select ARCH_DISABLE_KASAN_INLINE if STATIC_LINK select ARCH_NEEDS_DEFER_KASAN if STATIC_LINK select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_HAS_CACHE_LINE_SIZE diff --git a/arch/um/Makefile b/arch/um/Makefile index 7be0143b5ba350..721b652ffb6584 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -46,19 +46,17 @@ ARCH_INCLUDE := -I$(srctree)/$(SHARED_HEADERS) ARCH_INCLUDE += -I$(srctree)/$(HOST_DIR)/um/shared KBUILD_CPPFLAGS += -I$(srctree)/$(HOST_DIR)/um -# -Dvmap=kernel_vmap prevents anything from referencing the libpcap.o symbol so -# named - it's a common symbol in libpcap, so we get a binary which crashes. -# -# Same things for in6addr_loopback and mktime - found in libc. For these two we -# only get link-time error, luckily. +# -Dstrrchr=kernel_strrchr (as well as the various in6addr symbols) prevents +# anything from referencing +# libc symbols with the same name, which can cause a linker error. # # -Dlongjmp=kernel_longjmp prevents anything from referencing the libpthread.a # embedded copy of longjmp, same thing for setjmp. # -# These apply to USER_CFLAGS to. +# These apply to USER_CFLAGS too. KBUILD_CFLAGS += $(CFLAGS) $(CFLAGS-y) -D__arch_um__ \ - $(ARCH_INCLUDE) $(MODE_INCLUDE) -Dvmap=kernel_vmap \ + $(ARCH_INCLUDE) $(MODE_INCLUDE) \ -Dlongjmp=kernel_longjmp -Dsetjmp=kernel_setjmp \ -Din6addr_loopback=kernel_in6addr_loopback \ -Din6addr_any=kernel_in6addr_any -Dstrrchr=kernel_strrchr \ diff --git a/arch/um/include/asm/kasan.h b/arch/um/include/asm/kasan.h index b54a4e937fd12a..81bcdc0f962e67 100644 --- a/arch/um/include/asm/kasan.h +++ b/arch/um/include/asm/kasan.h @@ -24,10 +24,6 @@ #ifdef CONFIG_KASAN void kasan_init(void); - -#if defined(CONFIG_STATIC_LINK) && defined(CONFIG_KASAN_INLINE) -#error UML does not work in KASAN_INLINE mode with STATIC_LINK enabled! -#endif #else static inline void kasan_init(void) { } #endif /* CONFIG_KASAN */ diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 9c9c66dc45f054..13d461712c9972 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -43,7 +43,9 @@ * cares about its entry, so it's OK if another processor is modifying its * entry. */ -struct task_struct *cpu_tasks[NR_CPUS]; +struct task_struct *cpu_tasks[NR_CPUS] = { + [0 ... NR_CPUS - 1] = &init_task, +}; EXPORT_SYMBOL(cpu_tasks); void free_stack(unsigned long stack, int order) diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index cfbbbf8500c345..ed2f67848a50e7 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -239,8 +239,6 @@ static struct notifier_block panic_exit_notifier = { void uml_finishsetup(void) { - cpu_tasks[0] = &init_task; - atomic_notifier_chain_register(&panic_notifier_list, &panic_exit_notifier); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index fa3b616af03a2d..a3700766a8c084 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -279,6 +279,7 @@ config X86 select HAVE_PCI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select ASYNC_KERNEL_PGTABLE_FREE if IOMMU_SVA select MMU_GATHER_RCU_TABLE_FREE select MMU_GATHER_MERGE_VMAS select HAVE_POSIX_CPU_TIMERS_TASK_WORK diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index bdd26050dff773..0e89e197e11264 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include "../string.h" #include "efi.h" @@ -168,9 +169,10 @@ asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable) * For 4- to 5-level paging transition, set up current CR3 as * the first and the only entry in a new top-level page table. */ - *trampoline_32bit = __native_read_cr3() | _PAGE_TABLE_NOENC; + *trampoline_32bit = native_read_cr3_pa() | _PAGE_TABLE_NOENC; } else { - unsigned long src; + u64 *new_cr3; + pgd_t *pgdp; /* * For 5- to 4-level paging transition, copy page table pointed @@ -180,8 +182,9 @@ asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable) * We cannot just point to the page table from trampoline as it * may be above 4G. */ - src = *(unsigned long *)__native_read_cr3() & PAGE_MASK; - memcpy(trampoline_32bit, (void *)src, PAGE_SIZE); + pgdp = (pgd_t *)native_read_cr3_pa(); + new_cr3 = (u64 *)(native_pgd_val(pgdp[0]) & PTE_PFN_MASK); + memcpy(trampoline_32bit, new_cr3, PAGE_SIZE); } toggle_la57(trampoline_32bit); diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile index 3b8ae214a6a64d..b2e9ec2f69014f 100644 --- a/arch/x86/coco/sev/Makefile +++ b/arch/x86/coco/sev/Makefile @@ -8,3 +8,5 @@ UBSAN_SANITIZE_noinstr.o := n # GCC may fail to respect __no_sanitize_address or __no_kcsan when inlining KASAN_SANITIZE_noinstr.o := n KCSAN_SANITIZE_noinstr.o := n + +GCOV_PROFILE_noinstr.o := n diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index b20661b8621d13..8868f5f5379ba8 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -763,7 +763,12 @@ static void amd_pmu_enable_all(int added) if (!test_bit(idx, cpuc->active_mask)) continue; - amd_pmu_enable_event(cpuc->events[idx]); + /* + * FIXME: cpuc->events[idx] can become NULL in a subtle race + * condition with NMI->throttle->x86_pmu_stop(). + */ + if (cpuc->events[idx]) + amd_pmu_enable_event(cpuc->events[idx]); } } diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index e8b6af199c738e..9293ce50574dad 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -656,14 +656,11 @@ static int amd_uncore_df_event_init(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; int ret = amd_uncore_event_init(event); - if (ret || pmu_version < 2) - return ret; - hwc->config = event->attr.config & (pmu_version >= 2 ? AMD64_PERFMON_V2_RAW_EVENT_MASK_NB : AMD64_RAW_EVENT_MASK_NB); - return 0; + return ret; } static int amd_uncore_df_add(struct perf_event *event, int flags) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index fa6c47b509897a..56df4855f38e93 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1344,6 +1344,7 @@ static void x86_pmu_enable(struct pmu *pmu) hwc->state |= PERF_HES_ARCH; x86_pmu_stop(event, PERF_EF_UPDATE); + cpuc->events[hwc->idx] = NULL; } /* @@ -1365,6 +1366,7 @@ static void x86_pmu_enable(struct pmu *pmu) * if cpuc->enabled = 0, then no wrmsr as * per x86_pmu_enable_event() */ + cpuc->events[hwc->idx] = event; x86_pmu_start(event, PERF_EF_RELOAD); } cpuc->n_added = 0; @@ -1531,7 +1533,6 @@ static void x86_pmu_start(struct perf_event *event, int flags) event->hw.state = 0; - cpuc->events[idx] = event; __set_bit(idx, cpuc->active_mask); static_call(x86_pmu_enable)(event); perf_event_update_userpage(event); @@ -1610,7 +1611,6 @@ void x86_pmu_stop(struct perf_event *event, int flags) if (test_bit(hwc->idx, cpuc->active_mask)) { static_call(x86_pmu_disable)(event); __clear_bit(hwc->idx, cpuc->active_mask); - cpuc->events[hwc->idx] = NULL; WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; } @@ -1648,6 +1648,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) * Not a TXN, therefore cleanup properly. */ x86_pmu_stop(event, PERF_EF_UPDATE); + cpuc->events[event->hw.idx] = NULL; for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event_list[i]) @@ -3100,8 +3101,8 @@ void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap) cap->version = x86_pmu.version; cap->num_counters_gp = x86_pmu_num_counters(NULL); cap->num_counters_fixed = x86_pmu_num_counters_fixed(NULL); - cap->bit_width_gp = x86_pmu.cntval_bits; - cap->bit_width_fixed = x86_pmu.cntval_bits; + cap->bit_width_gp = cap->num_counters_gp ? x86_pmu.cntval_bits : 0; + cap->bit_width_fixed = cap->num_counters_fixed ? x86_pmu.cntval_bits : 0; cap->events_mask = (unsigned int)x86_pmu.events_maskl; cap->events_mask_len = x86_pmu.events_mask_len; cap->pebs_ept = x86_pmu.pebs_ept; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index fe65be0b9d9c46..32d551f2646a72 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3249,6 +3249,9 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) if (!test_bit(bit, cpuc->active_mask)) continue; + /* Event may have already been cleared: */ + if (!event) + continue; /* * There may be unprocessed PEBS records in the PEBS buffer, @@ -4029,7 +4032,9 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event) if (!event->attr.exclude_kernel) flags &= ~PERF_SAMPLE_REGS_USER; if (event->attr.sample_regs_user & ~PEBS_GP_REGS) - flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR); + flags &= ~PERF_SAMPLE_REGS_USER; + if (event->attr.sample_regs_intr & ~PEBS_GP_REGS) + flags &= ~PERF_SAMPLE_REGS_INTR; return flags; } diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index ec753e39b00778..6f5286a99e0c3c 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -70,7 +70,7 @@ * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, - * ADL,RPL,MTL,ARL,LNL + * ADL,RPL,MTL,ARL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 @@ -522,7 +522,6 @@ static const struct cstate_model lnl_cstates __initconst = { BIT(PERF_CSTATE_CORE_C7_RES), .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | - BIT(PERF_CSTATE_PKG_C3_RES) | BIT(PERF_CSTATE_PKG_C6_RES) | BIT(PERF_CSTATE_PKG_C10_RES), }; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 2b969386dcddce..493e6ba51e06dc 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1558,13 +1558,22 @@ static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period struct hw_perf_event *hwc = &event->hw; unsigned int hw_event, bts_event; - if (event->attr.freq) + /* + * Only use BTS for fixed rate period==1 events. + */ + if (event->attr.freq || period != 1) + return false; + + /* + * BTS doesn't virtualize. + */ + if (event->attr.exclude_host) return false; hw_event = hwc->config & INTEL_ARCH_EVENT_MASK; bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS); - return hw_event == bts_event && period == 1; + return hw_event == bts_event; } static inline bool intel_pmu_has_bts(struct perf_event *event) diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 042e8712d8dea6..8aafccf7a52c70 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -105,7 +105,7 @@ static void hv_vtl_ap_entry(void) static int hv_vtl_bringup_vcpu(u32 target_vp_index, int cpu, u64 eip_ignored) { - u64 status; + u64 status, rsp, rip; int ret = 0; struct hv_enable_vp_vtl *input; unsigned long irq_flags; @@ -118,9 +118,11 @@ static int hv_vtl_bringup_vcpu(u32 target_vp_index, int cpu, u64 eip_ignored) struct desc_struct *gdt; struct task_struct *idle = idle_thread_get(cpu); - u64 rsp = (unsigned long)idle->thread.sp; + if (IS_ERR(idle)) + return PTR_ERR(idle); - u64 rip = (u64)&hv_vtl_ap_entry; + rsp = (unsigned long)idle->thread.sp; + rip = (u64)&hv_vtl_ap_entry; native_store_gdt(&gdt_ptr); store_idt(&idt_ptr); diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 880ca15073ed12..99017bb1031e91 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -10,7 +10,7 @@ /* * Despite that some emulators terminate on UD2, we use it for WARN(). */ -#define ASM_UD2 _ASM_BYTES(0x0f, 0x0b) +#define ASM_UD2 __ASM_FORM(ud2) #define INSN_UD2 0x0b0f #define LEN_UD2 2 diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index b08c95872eed9f..c56e1e63b89324 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -57,7 +57,7 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs) } #define arch_ftrace_partial_regs(regs) do { \ - regs->flags &= ~X86_EFLAGS_FIXED; \ + regs->flags |= X86_EFLAGS_FIXED; \ regs->cs = __KERNEL_CS; \ } while (0) diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 5a0d42464d4424..4e55d17558465d 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -87,4 +87,11 @@ static inline void panic_if_irq_remap(const char *msg) } #endif /* CONFIG_IRQ_REMAP */ + +#ifdef CONFIG_X86_POSTED_MSI +void intel_ack_posted_msi_irq(struct irq_data *irqd); +#else +#define intel_ack_posted_msi_irq NULL +#endif + #endif /* __X86_IRQ_REMAPPING_H */ diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h index ff5c7134a37aa1..dfd5c74ba41a2f 100644 --- a/arch/x86/include/asm/kfence.h +++ b/arch/x86/include/asm/kfence.h @@ -42,10 +42,35 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) { unsigned int level; pte_t *pte = lookup_address(addr, &level); + pteval_t val, new; if (WARN_ON(!pte || level != PG_LEVEL_4K)) return false; + val = pte_val(*pte); + + /* + * protect requires making the page not-present. If the PTE is + * already in the right state, there's nothing to do. + */ + if (protect != !!(val & _PAGE_PRESENT)) + return true; + + /* + * Otherwise, flip the Present bit, taking care to avoid writing an + * L1TF-vulnerable PTE (not present, without the high address bits + * set). + */ + new = val ^ _PAGE_PRESENT; + set_pte(pte, __pte(flip_protnone_guard(val, new, PTE_PFN_MASK))); + + /* + * If the page was protected (non-present) and we're making it + * present, there is no need to flush the TLB at all. + */ + if (!protect) + return true; + /* * We need to avoid IPIs, as we may get KFENCE allocations or faults * with interrupts disabled. Therefore, the below is best-effort, and @@ -53,11 +78,6 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) * lazy fault handling takes care of faults after the page is PRESENT. */ - if (protect) - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT)); - else - set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT)); - /* * Flush this CPU's TLB, assuming whoever did the allocation/free is * likely to continue running on this CPU. diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 48598d017d6f3f..b74ae7183f3ae8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2143,6 +2143,11 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); * the gfn, i.e. retrying the instruction will hit a * !PRESENT fault, which results in a new shadow page * and sends KVM back to square one. + * + * EMULTYPE_SKIP_SOFT_INT - Set in combination with EMULTYPE_SKIP to only skip + * an instruction if it could generate a given software + * interrupt, which must be encoded via + * EMULTYPE_SET_SOFT_INT_VECTOR(). */ #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) @@ -2153,6 +2158,10 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); #define EMULTYPE_PF (1 << 6) #define EMULTYPE_COMPLETE_USER_EXIT (1 << 7) #define EMULTYPE_WRITE_PF_TO_SP (1 << 8) +#define EMULTYPE_SKIP_SOFT_INT (1 << 9) + +#define EMULTYPE_SET_SOFT_INT_VECTOR(v) ((u32)((v) & 0xff) << 16) +#define EMULTYPE_GET_SOFT_INT_VECTOR(e) (((e) >> 16) & 0xff) static inline bool kvm_can_emulate_event_vectoring(int emul_type) { @@ -2378,7 +2387,6 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, int kvm_add_user_return_msr(u32 msr); int kvm_find_user_return_msr(u32 msr); int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask); -void kvm_user_return_msr_update_cache(unsigned int index, u64 val); u64 kvm_get_user_return_msr(unsigned int slot); static inline bool kvm_is_supported_user_return_msr(u32 msr) diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 50f75467f73d0f..b5dec859bc75aa 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -187,12 +187,12 @@ convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); extern void send_sigtrap(struct pt_regs *regs, int error_code, int si_code); -static inline unsigned long regs_return_value(struct pt_regs *regs) +static __always_inline unsigned long regs_return_value(struct pt_regs *regs) { return regs->ax; } -static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) +static __always_inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) { regs->ax = rc; } @@ -277,34 +277,34 @@ static __always_inline bool ip_within_syscall_gap(struct pt_regs *regs) } #endif -static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) +static __always_inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { return regs->sp; } -static inline unsigned long instruction_pointer(struct pt_regs *regs) +static __always_inline unsigned long instruction_pointer(struct pt_regs *regs) { return regs->ip; } -static inline void instruction_pointer_set(struct pt_regs *regs, - unsigned long val) +static __always_inline +void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { regs->ip = val; } -static inline unsigned long frame_pointer(struct pt_regs *regs) +static __always_inline unsigned long frame_pointer(struct pt_regs *regs) { return regs->bp; } -static inline unsigned long user_stack_pointer(struct pt_regs *regs) +static __always_inline unsigned long user_stack_pointer(struct pt_regs *regs) { return regs->sp; } -static inline void user_stack_pointer_set(struct pt_regs *regs, - unsigned long val) +static __always_inline +void user_stack_pointer_set(struct pt_regs *regs, unsigned long val) { regs->sp = val; } diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h index c9cf43d5ef238c..4220dae14a2d9f 100644 --- a/arch/x86/include/asm/vmware.h +++ b/arch/x86/include/asm/vmware.h @@ -140,7 +140,7 @@ unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1, "b" (in1), "c" (cmd), "d" (0) - : "cc", "memory"); + : "di", "si", "cc", "memory"); return out0; } @@ -165,7 +165,7 @@ unsigned long vmware_hypercall4(unsigned long cmd, unsigned long in1, "b" (in1), "c" (cmd), "d" (0) - : "cc", "memory"); + : "di", "si", "cc", "memory"); return out0; } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 5d46709c58d0b8..a92750f3079af0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -951,26 +951,14 @@ static void init_amd_zen1(struct cpuinfo_x86 *c) } } -static bool cpu_has_zenbleed_microcode(void) -{ - u32 good_rev = 0; - - switch (boot_cpu_data.x86_model) { - case 0x30 ... 0x3f: good_rev = 0x0830107b; break; - case 0x60 ... 0x67: good_rev = 0x0860010c; break; - case 0x68 ... 0x6f: good_rev = 0x08608107; break; - case 0x70 ... 0x7f: good_rev = 0x08701033; break; - case 0xa0 ... 0xaf: good_rev = 0x08a00009; break; - - default: - return false; - } - - if (boot_cpu_data.microcode < good_rev) - return false; - - return true; -} +static const struct x86_cpu_id amd_zenbleed_microcode[] = { + ZEN_MODEL_STEP_UCODE(0x17, 0x31, 0x0, 0x0830107b), + ZEN_MODEL_STEP_UCODE(0x17, 0x60, 0x1, 0x0860010c), + ZEN_MODEL_STEP_UCODE(0x17, 0x68, 0x1, 0x08608107), + ZEN_MODEL_STEP_UCODE(0x17, 0x71, 0x0, 0x08701033), + ZEN_MODEL_STEP_UCODE(0x17, 0xa0, 0x0, 0x08a00009), + {} +}; static void zen2_zenbleed_check(struct cpuinfo_x86 *c) { @@ -980,7 +968,7 @@ static void zen2_zenbleed_check(struct cpuinfo_x86 *c) if (!cpu_has(c, X86_FEATURE_AVX)) return; - if (!cpu_has_zenbleed_microcode()) { + if (!x86_match_min_microcode_rev(amd_zenbleed_microcode)) { pr_notice_once("Zenbleed: please update your microcode for the most optimal fix\n"); msr_set_bit(MSR_AMD64_DE_CFG, MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT); } else { diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c index f4a007616468ec..61eaa17749311c 100644 --- a/arch/x86/kernel/cpu/mce/threshold.c +++ b/arch/x86/kernel/cpu/mce/threshold.c @@ -85,7 +85,8 @@ void cmci_storm_end(unsigned int bank) { struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc); - __clear_bit(bank, this_cpu_ptr(mce_poll_banks)); + if (!mce_flags.amd_threshold) + __clear_bit(bank, this_cpu_ptr(mce_poll_banks)); storm->banks[bank].history = 0; storm->banks[bank].in_storm_mode = false; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index a881bf4c201143..46673530bc6f0e 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -186,50 +186,61 @@ static u32 cpuid_to_ucode_rev(unsigned int val) return p.ucode_rev; } +static u32 get_cutoff_revision(u32 rev) +{ + switch (rev >> 8) { + case 0x80012: return 0x8001277; break; + case 0x80082: return 0x800820f; break; + case 0x83010: return 0x830107c; break; + case 0x86001: return 0x860010e; break; + case 0x86081: return 0x8608108; break; + case 0x87010: return 0x8701034; break; + case 0x8a000: return 0x8a0000a; break; + case 0xa0010: return 0xa00107a; break; + case 0xa0011: return 0xa0011da; break; + case 0xa0012: return 0xa001243; break; + case 0xa0082: return 0xa00820e; break; + case 0xa1011: return 0xa101153; break; + case 0xa1012: return 0xa10124e; break; + case 0xa1081: return 0xa108109; break; + case 0xa2010: return 0xa20102f; break; + case 0xa2012: return 0xa201212; break; + case 0xa4041: return 0xa404109; break; + case 0xa5000: return 0xa500013; break; + case 0xa6012: return 0xa60120a; break; + case 0xa7041: return 0xa704109; break; + case 0xa7052: return 0xa705208; break; + case 0xa7080: return 0xa708009; break; + case 0xa70c0: return 0xa70C009; break; + case 0xaa001: return 0xaa00116; break; + case 0xaa002: return 0xaa00218; break; + case 0xb0021: return 0xb002146; break; + case 0xb0081: return 0xb008111; break; + case 0xb1010: return 0xb101046; break; + case 0xb2040: return 0xb204031; break; + case 0xb4040: return 0xb404031; break; + case 0xb4041: return 0xb404101; break; + case 0xb6000: return 0xb600031; break; + case 0xb6080: return 0xb608031; break; + case 0xb7000: return 0xb700031; break; + default: break; + + } + return 0; +} + static bool need_sha_check(u32 cur_rev) { + u32 cutoff; + if (!cur_rev) { cur_rev = cpuid_to_ucode_rev(bsp_cpuid_1_eax); pr_info_once("No current revision, generating the lowest one: 0x%x\n", cur_rev); } - switch (cur_rev >> 8) { - case 0x80012: return cur_rev <= 0x8001277; break; - case 0x80082: return cur_rev <= 0x800820f; break; - case 0x83010: return cur_rev <= 0x830107c; break; - case 0x86001: return cur_rev <= 0x860010e; break; - case 0x86081: return cur_rev <= 0x8608108; break; - case 0x87010: return cur_rev <= 0x8701034; break; - case 0x8a000: return cur_rev <= 0x8a0000a; break; - case 0xa0010: return cur_rev <= 0xa00107a; break; - case 0xa0011: return cur_rev <= 0xa0011da; break; - case 0xa0012: return cur_rev <= 0xa001243; break; - case 0xa0082: return cur_rev <= 0xa00820e; break; - case 0xa1011: return cur_rev <= 0xa101153; break; - case 0xa1012: return cur_rev <= 0xa10124e; break; - case 0xa1081: return cur_rev <= 0xa108109; break; - case 0xa2010: return cur_rev <= 0xa20102f; break; - case 0xa2012: return cur_rev <= 0xa201212; break; - case 0xa4041: return cur_rev <= 0xa404109; break; - case 0xa5000: return cur_rev <= 0xa500013; break; - case 0xa6012: return cur_rev <= 0xa60120a; break; - case 0xa7041: return cur_rev <= 0xa704109; break; - case 0xa7052: return cur_rev <= 0xa705208; break; - case 0xa7080: return cur_rev <= 0xa708009; break; - case 0xa70c0: return cur_rev <= 0xa70C009; break; - case 0xaa001: return cur_rev <= 0xaa00116; break; - case 0xaa002: return cur_rev <= 0xaa00218; break; - case 0xb0021: return cur_rev <= 0xb002146; break; - case 0xb0081: return cur_rev <= 0xb008111; break; - case 0xb1010: return cur_rev <= 0xb101046; break; - case 0xb2040: return cur_rev <= 0xb204031; break; - case 0xb4040: return cur_rev <= 0xb404031; break; - case 0xb4041: return cur_rev <= 0xb404101; break; - case 0xb6000: return cur_rev <= 0xb600031; break; - case 0xb6080: return cur_rev <= 0xb608031; break; - case 0xb7000: return cur_rev <= 0xb700031; break; - default: break; - } + cutoff = get_cutoff_revision(cur_rev); + if (cutoff) + return cur_rev <= cutoff; pr_info("You should not be seeing this. Please send the following couple of lines to x86--kernel.org\n"); pr_info("CPUID(1).EAX: 0x%x, current revision: 0x%x\n", bsp_cpuid_1_eax, cur_rev); @@ -247,7 +258,7 @@ static bool cpu_has_entrysign(void) if (fam == 0x1a) { if (model <= 0x2f || (0x40 <= model && model <= 0x4f) || - (0x60 <= model && model <= 0x6f)) + (0x60 <= model && model <= 0x7f)) return true; } @@ -494,6 +505,7 @@ static int verify_patch(const u8 *buf, size_t buf_size, u32 *patch_size) { u8 family = x86_family(bsp_cpuid_1_eax); struct microcode_header_amd *mc_hdr; + u32 cur_rev, cutoff, patch_rev; u32 sh_psize; u16 proc_id; u8 patch_fam; @@ -533,11 +545,32 @@ static int verify_patch(const u8 *buf, size_t buf_size, u32 *patch_size) proc_id = mc_hdr->processor_rev_id; patch_fam = 0xf + (proc_id >> 12); - ucode_dbg("Patch-ID 0x%08x: family: 0x%x\n", mc_hdr->patch_id, patch_fam); - if (patch_fam != family) return 1; + cur_rev = get_patch_level(); + + /* No cutoff revision means old/unaffected by signing algorithm weakness => matches */ + cutoff = get_cutoff_revision(cur_rev); + if (!cutoff) + goto ok; + + patch_rev = mc_hdr->patch_id; + + ucode_dbg("cur_rev: 0x%x, cutoff: 0x%x, patch_rev: 0x%x\n", + cur_rev, cutoff, patch_rev); + + if (cur_rev <= cutoff && patch_rev <= cutoff) + goto ok; + + if (cur_rev > cutoff && patch_rev > cutoff) + goto ok; + + return 1; + +ok: + ucode_dbg("Patch-ID 0x%08x: family: 0x%x\n", mc_hdr->patch_id, patch_fam); + return 0; } @@ -606,8 +639,6 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc) mc = (struct microcode_amd *)(buf + SECTION_HDR_SIZE); - ucode_dbg("patch_id: 0x%x\n", mc->hdr.patch_id); - if (mc_patch_matches(mc, eq_id)) { desc->psize = patch_size; desc->mc = mc; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index f75c140906d002..539edd6d6dc8c3 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -136,7 +136,7 @@ bool __init microcode_loader_disabled(void) return dis_ucode_ldr; } -static void early_parse_cmdline(void) +static void __init early_parse_cmdline(void) { char cmd_buf[64] = {}; char *s, *p = cmd_buf; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 06ca5a30140c2f..79a1f2d5f5019c 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -818,7 +818,8 @@ static __init bool get_mem_config(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) return __get_mem_config_intel(&hw_res->r_resctrl); - else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) return __rdt_get_mem_config_amd(&hw_res->r_resctrl); return false; @@ -978,7 +979,8 @@ static __init void rdt_init_res_defs(void) { if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) rdt_init_res_defs_intel(); - else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) rdt_init_res_defs_amd(); } @@ -1010,8 +1012,19 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c) c->x86_cache_occ_scale = ebx; c->x86_cache_mbm_width_offset = eax & 0xff; - if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset) - c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD; + if (!c->x86_cache_mbm_width_offset) { + switch (c->x86_vendor) { + case X86_VENDOR_AMD: + c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD; + break; + case X86_VENDOR_HYGON: + c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_HYGON; + break; + default: + /* Leave c->x86_cache_mbm_width_offset as 0 */ + break; + } + } } } diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 9f4c2f0aaf5c80..6da9bd1a188b96 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -14,6 +14,9 @@ #define MBM_CNTR_WIDTH_OFFSET_AMD 20 +/* Hygon MBM counter width as an offset from MBM_CNTR_WIDTH_BASE */ +#define MBM_CNTR_WIDTH_OFFSET_HYGON 8 + #define RMID_VAL_ERROR BIT_ULL(63) #define RMID_VAL_UNAVAIL BIT_ULL(62) diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 71ee20102a8afb..b10684dedc589f 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -181,8 +181,8 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs, * in false positive reports. Disable instrumentation to avoid those. */ __no_kmsan_checks -static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, const char *log_lvl) +static void __show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, const char *log_lvl) { struct unwind_state state; struct stack_info stack_info = {0}; @@ -303,6 +303,25 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, } } +static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, const char *log_lvl) +{ + /* + * Disable KASAN to avoid false positives during walking another + * task's stacks, as values on these stacks may change concurrently + * with task execution. + */ + bool disable_kasan = task && task != current; + + if (disable_kasan) + kasan_disable_current(); + + __show_trace_log_lvl(task, regs, stack, log_lvl); + + if (disable_kasan) + kasan_enable_current(); +} + void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) { diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e88eacb1b5bbfa..9badb21e5a5bce 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -318,10 +318,29 @@ EXPORT_SYMBOL_GPL(fpu_enable_guest_xfd_features); #ifdef CONFIG_X86_64 void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { + struct fpstate *fpstate = guest_fpu->fpstate; + fpregs_lock(); - guest_fpu->fpstate->xfd = xfd; - if (guest_fpu->fpstate->in_use) - xfd_update_state(guest_fpu->fpstate); + + /* + * KVM's guest ABI is that setting XFD[i]=1 *can* immediately revert the + * save state to its initial configuration. Likewise, KVM_GET_XSAVE does + * the same as XSAVE and returns XSTATE_BV[i]=0 whenever XFD[i]=1. + * + * If the guest's FPU state is in hardware, just update XFD: the XSAVE + * in fpu_swap_kvm_fpstate will clear XSTATE_BV[i] whenever XFD[i]=1. + * + * If however the guest's FPU state is NOT resident in hardware, clear + * disabled components in XSTATE_BV now, or a subsequent XRSTOR will + * attempt to load disabled components and generate #NM _in the host_. + */ + if (xfd && test_thread_flag(TIF_NEED_FPU_LOAD)) + fpstate->regs.xsave.header.xfeatures &= ~xfd; + + fpstate->xfd = xfd; + if (fpstate->in_use) + xfd_update_state(fpstate); + fpregs_unlock(); } EXPORT_SYMBOL_GPL(fpu_update_guest_xfd); @@ -429,6 +448,13 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, if (ustate->xsave.header.xfeatures & ~xcr0) return -EINVAL; + /* + * Disabled features must be in their initial state, otherwise XRSTOR + * causes an exception. + */ + if (WARN_ON_ONCE(ustate->xsave.header.xfeatures & kstate->xfd)) + return -EINVAL; + /* * Nullify @vpkru to preserve its current value if PKRU's bit isn't set * in the header. KVM's odd ABI is to leave PKRU untouched in this diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 28e4fd65c9da71..5f54a207ace46c 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1945,7 +1945,7 @@ static int dump_xsave_layout_desc(struct coredump_params *cprm) }; if (!dump_emit(cprm, &xc, sizeof(xc))) - return 0; + return -1; num_records++; } @@ -1983,7 +1983,7 @@ int elf_coredump_extra_notes_write(struct coredump_params *cprm) return 1; num_records = dump_xsave_layout_desc(cprm); - if (!num_records) + if (num_records < 0) return 1; /* Total size should be equal to the number of records */ diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 823dbdd0eb4109..ae94f7b0fdf16f 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -354,6 +354,9 @@ SYM_CODE_START(return_to_handler) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR + /* Store original rsp for pt_regs.sp value. */ + movq %rsp, %rdi + /* Restore return_to_handler value that got eaten by previous ret instruction. */ subq $8, %rsp UNWIND_HINT_FUNC @@ -364,7 +367,7 @@ SYM_CODE_START(return_to_handler) movq %rax, RAX(%rsp) movq %rdx, RDX(%rsp) movq %rbp, RBP(%rsp) - movq %rsp, RSP(%rsp) + movq %rdi, RSP(%rsp) movq %rsp, %rdi call ftrace_return_to_handler diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 10721a12522694..59d38411a1d99f 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -396,6 +396,7 @@ DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_nested_ipi) /* Posted Interrupt Descriptors for coalesced MSIs to be posted */ DEFINE_PER_CPU_ALIGNED(struct pi_desc, posted_msi_pi_desc); +static DEFINE_PER_CPU_CACHE_HOT(bool, posted_msi_handler_active); void intel_posted_msi_init(void) { @@ -413,6 +414,25 @@ void intel_posted_msi_init(void) this_cpu_write(posted_msi_pi_desc.ndst, destination); } +void intel_ack_posted_msi_irq(struct irq_data *irqd) +{ + irq_move_irq(irqd); + + /* + * Handle the rare case that irq_retrigger() raised the actual + * assigned vector on the target CPU, which means that it was not + * invoked via the posted MSI handler below. In that case APIC EOI + * is required as otherwise the ISR entry becomes stale and lower + * priority interrupts are never going to be delivered after that. + * + * If the posted handler invoked the device interrupt handler then + * the EOI would be premature because it would acknowledge the + * posted vector. + */ + if (unlikely(!__this_cpu_read(posted_msi_handler_active))) + apic_eoi(); +} + static __always_inline bool handle_pending_pir(unsigned long *pir, struct pt_regs *regs) { unsigned long pir_copy[NR_PIR_WORDS]; @@ -445,6 +465,8 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification) pid = this_cpu_ptr(&posted_msi_pi_desc); + /* Mark the handler active for intel_ack_posted_msi_irq() */ + __this_cpu_write(posted_msi_handler_active, true); inc_irq_stat(posted_msi_notification_count); irq_enter(); @@ -473,6 +495,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification) apic_eoi(); irq_exit(); + __this_cpu_write(posted_msi_handler_active, false); set_irq_regs(old_regs); } #endif /* X86_POSTED_MSI */ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 52524e0ca97f78..913ffb995279af 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -509,11 +509,18 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, u32 vcpu_caps[NR_KVM_CPU_CAPS]; int r; + /* + * Apply pending runtime CPUID updates to the current CPUID entries to + * avoid false positives due to mismatches on KVM-owned feature flags. + */ + if (vcpu->arch.cpuid_dynamic_bits_dirty) + kvm_update_cpuid_runtime(vcpu); + /* * Swap the existing (old) entries with the incoming (new) entries in * order to massage the new entries, e.g. to account for dynamic bits - * that KVM controls, without clobbering the current guest CPUID, which - * KVM needs to preserve in order to unwind on failure. + * that KVM controls, without losing the current guest CPUID, which KVM + * needs to preserve in order to unwind on failure. * * Similarly, save the vCPU's current cpu_caps so that the capabilities * can be updated alongside the CPUID entries when performing runtime diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 0ae7f913d7826a..8b6ec3304100ff 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2131,15 +2131,33 @@ static void advance_periodic_target_expiration(struct kvm_lapic *apic) ktime_t delta; /* - * Synchronize both deadlines to the same time source or - * differences in the periods (caused by differences in the - * underlying clocks or numerical approximation errors) will - * cause the two to drift apart over time as the errors - * accumulate. + * Use kernel time as the time source for both the hrtimer deadline and + * TSC-based deadline so that they stay synchronized. Computing each + * deadline independently will cause the two deadlines to drift apart + * over time as differences in the periods accumulate, e.g. due to + * differences in the underlying clocks or numerical approximation errors. */ apic->lapic_timer.target_expiration = ktime_add_ns(apic->lapic_timer.target_expiration, apic->lapic_timer.period); + + /* + * If the new expiration is in the past, e.g. because userspace stopped + * running the VM for an extended duration, then force the expiration + * to "now" and don't try to play catch-up with the missed events. KVM + * will only deliver a single interrupt regardless of how many events + * are pending, i.e. restarting the timer with an expiration in the + * past will do nothing more than waste host cycles, and can even lead + * to a hard lockup in extreme cases. + */ + if (ktime_before(apic->lapic_timer.target_expiration, now)) + apic->lapic_timer.target_expiration = now; + + /* + * Note, ensuring the expiration isn't in the past also prevents delta + * from going negative, which could cause the TSC deadline to become + * excessively large due to it an unsigned value. + */ delta = ktime_sub(apic->lapic_timer.target_expiration, now); apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) + nsec_to_cycles(apic->vcpu, delta); @@ -2970,9 +2988,9 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data) apic_timer_expired(apic, true); - if (lapic_is_periodic(apic)) { + if (lapic_is_periodic(apic) && !WARN_ON_ONCE(!apic->lapic_timer.period)) { advance_periodic_target_expiration(apic); - hrtimer_add_expires_ns(&ktimer->timer, ktimer->period); + hrtimer_set_expires(&ktimer->timer, ktimer->target_expiration); return HRTIMER_RESTART; } else return HRTIMER_NORESTART; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index da6e80b3ac353c..e56c9b37e2b5b9 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -613,6 +613,7 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 struct kvm_vcpu *vcpu = &svm->vcpu; nested_vmcb02_compute_g_pat(svm); + vmcb_mark_dirty(vmcb02, VMCB_NPT); /* Load the nested guest state */ if (svm->nested.vmcb12_gpa != svm->nested.last_vmcb12_gpa) { @@ -751,6 +752,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, vmcb02->control.nested_ctl = vmcb01->control.nested_ctl; vmcb02->control.iopm_base_pa = vmcb01->control.iopm_base_pa; vmcb02->control.msrpm_base_pa = vmcb01->control.msrpm_base_pa; + vmcb_mark_dirty(vmcb02, VMCB_PERM_MAP); /* * Stash vmcb02's counter if the guest hasn't moved past the guilty @@ -983,7 +985,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) if (!nested_vmcb_check_save(vcpu) || !nested_vmcb_check_controls(vcpu)) { vmcb12->control.exit_code = SVM_EXIT_ERR; - vmcb12->control.exit_code_hi = 0; + vmcb12->control.exit_code_hi = -1u; vmcb12->control.exit_info_1 = 0; vmcb12->control.exit_info_2 = 0; goto out; @@ -1016,7 +1018,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) svm->soft_int_injected = false; svm->vmcb->control.exit_code = SVM_EXIT_ERR; - svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_code_hi = -1u; svm->vmcb->control.exit_info_1 = 0; svm->vmcb->control.exit_info_2 = 0; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9d29b2e7e855d6..d758bff6e068bb 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -272,6 +272,7 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) } static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, + int emul_type, bool commit_side_effects) { struct vcpu_svm *svm = to_svm(vcpu); @@ -293,7 +294,7 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, if (unlikely(!commit_side_effects)) old_rflags = svm->vmcb->save.rflags; - if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) + if (!kvm_emulate_instruction(vcpu, emul_type)) return 0; if (unlikely(!commit_side_effects)) @@ -311,11 +312,13 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, static int svm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { - return __svm_skip_emulated_instruction(vcpu, true); + return __svm_skip_emulated_instruction(vcpu, EMULTYPE_SKIP, true); } -static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu) +static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu, u8 vector) { + const int emul_type = EMULTYPE_SKIP | EMULTYPE_SKIP_SOFT_INT | + EMULTYPE_SET_SOFT_INT_VECTOR(vector); unsigned long rip, old_rip = kvm_rip_read(vcpu); struct vcpu_svm *svm = to_svm(vcpu); @@ -331,7 +334,7 @@ static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu) * in use, the skip must not commit any side effects such as clearing * the interrupt shadow or RFLAGS.RF. */ - if (!__svm_skip_emulated_instruction(vcpu, !nrips)) + if (!__svm_skip_emulated_instruction(vcpu, emul_type, !nrips)) return -EIO; rip = kvm_rip_read(vcpu); @@ -367,7 +370,7 @@ static void svm_inject_exception(struct kvm_vcpu *vcpu) kvm_deliver_exception_payload(vcpu, ex); if (kvm_exception_is_soft(ex->vector) && - svm_update_soft_interrupt_rip(vcpu)) + svm_update_soft_interrupt_rip(vcpu, ex->vector)) return; svm->vmcb->control.event_inj = ex->vector @@ -2435,6 +2438,7 @@ static bool check_selective_cr0_intercepted(struct kvm_vcpu *vcpu, if (cr0 ^ val) { svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE; + svm->vmcb->control.exit_code_hi = 0; ret = (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE); } @@ -3633,11 +3637,12 @@ static bool svm_set_vnmi_pending(struct kvm_vcpu *vcpu) static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { + struct kvm_queued_interrupt *intr = &vcpu->arch.interrupt; struct vcpu_svm *svm = to_svm(vcpu); u32 type; - if (vcpu->arch.interrupt.soft) { - if (svm_update_soft_interrupt_rip(vcpu)) + if (intr->soft) { + if (svm_update_soft_interrupt_rip(vcpu, intr->nr)) return; type = SVM_EVTINJ_TYPE_SOFT; @@ -3645,12 +3650,10 @@ static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) type = SVM_EVTINJ_TYPE_INTR; } - trace_kvm_inj_virq(vcpu->arch.interrupt.nr, - vcpu->arch.interrupt.soft, reinjected); + trace_kvm_inj_virq(intr->nr, intr->soft, reinjected); ++vcpu->stat.irq_injections; - svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr | - SVM_EVTINJ_VALID | type; + svm->vmcb->control.event_inj = intr->nr | SVM_EVTINJ_VALID | type; } void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, @@ -4526,31 +4529,45 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, case SVM_EXIT_WRITE_CR0: { unsigned long cr0, val; - if (info->intercept == x86_intercept_cr_write) + /* + * Adjust the exit code accordingly if a CR other than CR0 is + * being written, and skip straight to the common handling as + * only CR0 has an additional selective intercept. + */ + if (info->intercept == x86_intercept_cr_write && info->modrm_reg) { icpt_info.exit_code += info->modrm_reg; - - if (icpt_info.exit_code != SVM_EXIT_WRITE_CR0 || - info->intercept == x86_intercept_clts) break; + } - if (!(vmcb12_is_intercept(&svm->nested.ctl, - INTERCEPT_SELECTIVE_CR0))) + /* + * Convert the exit_code to SVM_EXIT_CR0_SEL_WRITE if a + * selective CR0 intercept is triggered (the common logic will + * treat the selective intercept as being enabled). Note, the + * unconditional intercept has higher priority, i.e. this is + * only relevant if *only* the selective intercept is enabled. + */ + if (vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_CR0_WRITE) || + !(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0))) break; - cr0 = vcpu->arch.cr0 & ~SVM_CR0_SELECTIVE_MASK; - val = info->src_val & ~SVM_CR0_SELECTIVE_MASK; + /* CLTS never triggers INTERCEPT_SELECTIVE_CR0 */ + if (info->intercept == x86_intercept_clts) + break; + /* LMSW always triggers INTERCEPT_SELECTIVE_CR0 */ if (info->intercept == x86_intercept_lmsw) { - cr0 &= 0xfUL; - val &= 0xfUL; - /* lmsw can't clear PE - catch this here */ - if (cr0 & X86_CR0_PE) - val |= X86_CR0_PE; + icpt_info.exit_code = SVM_EXIT_CR0_SEL_WRITE; + break; } + /* + * MOV-to-CR0 only triggers INTERCEPT_SELECTIVE_CR0 if any bit + * other than SVM_CR0_SELECTIVE_MASK is changed. + */ + cr0 = vcpu->arch.cr0 & ~SVM_CR0_SELECTIVE_MASK; + val = info->src_val & ~SVM_CR0_SELECTIVE_MASK; if (cr0 ^ val) icpt_info.exit_code = SVM_EXIT_CR0_SEL_WRITE; - break; } case SVM_EXIT_READ_DR0: @@ -4611,6 +4628,7 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, if (static_cpu_has(X86_FEATURE_NRIPS)) vmcb->control.next_rip = info->next_rip; vmcb->control.exit_code = icpt_info.exit_code; + vmcb->control.exit_code_hi = 0; vmexit = nested_svm_exit_handled(svm); ret = (vmexit == NESTED_EXIT_DONE) ? X86EMUL_INTERCEPTED @@ -5267,6 +5285,8 @@ static __init void svm_set_cpu_caps(void) */ kvm_cpu_cap_clear(X86_FEATURE_BUS_LOCK_DETECT); kvm_cpu_cap_clear(X86_FEATURE_MSR_IMM); + + kvm_setup_xss_caps(); } static __init int svm_hardware_setup(void) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index dd78e64023450b..e66a16e59b1a5f 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -764,9 +764,10 @@ int nested_svm_vmexit(struct vcpu_svm *svm); static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code) { - svm->vmcb->control.exit_code = exit_code; - svm->vmcb->control.exit_info_1 = 0; - svm->vmcb->control.exit_info_2 = 0; + svm->vmcb->control.exit_code = exit_code; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; return nested_svm_vmexit(svm); } diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index bcea087b642fd0..1725c6a94f99bc 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -19,6 +19,7 @@ #include "trace.h" #include "vmx.h" #include "smm.h" +#include "x86_ops.h" static bool __read_mostly enable_shadow_vmcs = 1; module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO); @@ -5216,7 +5217,7 @@ void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, if (vmx->nested.update_vmcs01_apicv_status) { vmx->nested.update_vmcs01_apicv_status = false; - kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + vmx_refresh_apicv_exec_ctrl(vcpu); } if (vmx->nested.update_vmcs01_hwapic_isr) { diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 0a49c863c811bf..d9ffc16dfefe61 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -763,25 +763,6 @@ static bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu) return tdx_vcpu_state_details_intr_pending(vcpu_state_details); } -/* - * Compared to vmx_prepare_switch_to_guest(), there is not much to do - * as SEAMCALL/SEAMRET calls take care of most of save and restore. - */ -void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) -{ - struct vcpu_vt *vt = to_vt(vcpu); - - if (vt->guest_state_loaded) - return; - - if (likely(is_64bit_mm(current->mm))) - vt->msr_host_kernel_gs_base = current->thread.gsbase; - else - vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); - - vt->guest_state_loaded = true; -} - struct tdx_uret_msr { u32 msr; unsigned int slot; @@ -795,19 +776,38 @@ static struct tdx_uret_msr tdx_uret_msrs[] = { {.msr = MSR_TSC_AUX,}, }; -static void tdx_user_return_msr_update_cache(void) +void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { + struct vcpu_vt *vt = to_vt(vcpu); int i; + if (vt->guest_state_loaded) + return; + + if (likely(is_64bit_mm(current->mm))) + vt->msr_host_kernel_gs_base = current->thread.gsbase; + else + vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); + + vt->guest_state_loaded = true; + + /* + * Explicitly set user-return MSRs that are clobbered by the TDX-Module + * if VP.ENTER succeeds, i.e. on TD-Exit, with the values that would be + * written by the TDX-Module. Don't rely on the TDX-Module to actually + * clobber the MSRs, as the contract is poorly defined and not upheld. + * E.g. the TDX-Module will synthesize an EPT Violation without doing + * VM-Enter if it suspects a zero-step attack, and never "restore" VMM + * state. + */ for (i = 0; i < ARRAY_SIZE(tdx_uret_msrs); i++) - kvm_user_return_msr_update_cache(tdx_uret_msrs[i].slot, - tdx_uret_msrs[i].defval); + kvm_set_user_return_msr(tdx_uret_msrs[i].slot, + tdx_uret_msrs[i].defval, -1ull); } static void tdx_prepare_switch_to_host(struct kvm_vcpu *vcpu) { struct vcpu_vt *vt = to_vt(vcpu); - struct vcpu_tdx *tdx = to_tdx(vcpu); if (!vt->guest_state_loaded) return; @@ -815,11 +815,6 @@ static void tdx_prepare_switch_to_host(struct kvm_vcpu *vcpu) ++vcpu->stat.host_state_reload; wrmsrl(MSR_KERNEL_GS_BASE, vt->msr_host_kernel_gs_base); - if (tdx->guest_entered) { - tdx_user_return_msr_update_cache(); - tdx->guest_entered = false; - } - vt->guest_state_loaded = false; } @@ -1059,7 +1054,6 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) update_debugctlmsr(vcpu->arch.host_debugctl); tdx_load_host_xsave_state(vcpu); - tdx->guest_entered = true; vcpu->arch.regs_avail &= TDX_REGS_AVAIL_SET; @@ -3447,10 +3441,6 @@ static int __init __tdx_bringup(void) /* * Check if MSRs (tdx_uret_msrs) can be saved/restored * before returning to user space. - * - * this_cpu_ptr(user_return_msrs)->registered isn't checked - * because the registration is done at vcpu runtime by - * tdx_user_return_msr_update_cache(). */ tdx_uret_msrs[i].slot = kvm_find_user_return_msr(tdx_uret_msrs[i].msr); if (tdx_uret_msrs[i].slot == -1) { diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h index ca39a9391db1e3..7f258870dc4109 100644 --- a/arch/x86/kvm/vmx/tdx.h +++ b/arch/x86/kvm/vmx/tdx.h @@ -67,7 +67,6 @@ struct vcpu_tdx { u64 vp_enter_ret; enum vcpu_tdx_state state; - bool guest_entered; u64 map_gpa_next; u64 map_gpa_end; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 91b6f2f3edc2ab..c084f48e2b0b98 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -8021,6 +8021,8 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_clear(X86_FEATURE_SHSTK); kvm_cpu_cap_clear(X86_FEATURE_IBT); } + + kvm_setup_xss_caps(); } static bool vmx_is_io_intercepted(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c9c2aa6f4705e1..c075ee23aeadef 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -681,15 +681,6 @@ int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask) } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_user_return_msr); -void kvm_user_return_msr_update_cache(unsigned int slot, u64 value) -{ - struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs); - - msrs->values[slot].curr = value; - kvm_user_return_register_notifier(msrs); -} -EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_user_return_msr_update_cache); - u64 kvm_get_user_return_msr(unsigned int slot) { return this_cpu_ptr(user_return_msrs)->values[slot].curr; @@ -1045,6 +1036,13 @@ bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr) } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_require_dr); +static bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu) +{ + u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; + + return (vcpu->arch.apf.msr_en_val & mask) == mask; +} + static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) { return vcpu->arch.reserved_gpa_bits | rsvd_bits(5, 8) | rsvd_bits(1, 2); @@ -1137,15 +1135,20 @@ void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned lon } if ((cr0 ^ old_cr0) & X86_CR0_PG) { - kvm_clear_async_pf_completion_queue(vcpu); - kvm_async_pf_hash_reset(vcpu); - /* * Clearing CR0.PG is defined to flush the TLB from the guest's * perspective. */ if (!(cr0 & X86_CR0_PG)) kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + /* + * Check for async #PF completion events when enabling paging, + * as the vCPU may have previously encountered async #PFs (it's + * entirely legal for the guest to toggle paging on/off without + * waiting for the async #PF queue to drain). + */ + else if (kvm_pv_async_pf_enabled(vcpu)) + kvm_make_request(KVM_REQ_APF_READY, vcpu); } if ((cr0 ^ old_cr0) & KVM_MMU_CR0_ROLE_BITS) @@ -3650,13 +3653,6 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } -static inline bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu) -{ - u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; - - return (vcpu->arch.apf.msr_en_val & mask) == mask; -} - static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) { gpa_t gpa = data & ~0x3f; @@ -5846,9 +5842,18 @@ static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { + union fpregs_state *xstate = (union fpregs_state *)guest_xsave->region; + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; + /* + * For backwards compatibility, do not expect disabled features to be in + * their initial state. XSTATE_BV[i] must still be cleared whenever + * XFD[i]=1, or XRSTOR would cause a #NM. + */ + xstate->xsave.header.xfeatures &= ~vcpu->arch.guest_fpu.fpstate->xfd; + return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu, guest_xsave->region, kvm_caps.supported_xcr0, @@ -9337,6 +9342,23 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) return false; } +static bool is_soft_int_instruction(struct x86_emulate_ctxt *ctxt, + int emulation_type) +{ + u8 vector = EMULTYPE_GET_SOFT_INT_VECTOR(emulation_type); + + switch (ctxt->b) { + case 0xcc: + return vector == BP_VECTOR; + case 0xcd: + return vector == ctxt->src.val; + case 0xce: + return vector == OF_VECTOR; + default: + return false; + } +} + /* * Decode an instruction for emulation. The caller is responsible for handling * code breakpoints. Note, manually detecting code breakpoints is unnecessary @@ -9447,6 +9469,10 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * injecting single-step #DBs. */ if (emulation_type & EMULTYPE_SKIP) { + if (emulation_type & EMULTYPE_SKIP_SOFT_INT && + !is_soft_int_instruction(ctxt, emulation_type)) + return 0; + if (ctxt->mode != X86EMUL_MODE_PROT64) ctxt->eip = (u32)ctxt->_eip; else @@ -9928,6 +9954,23 @@ static struct notifier_block pvclock_gtod_notifier = { }; #endif +void kvm_setup_xss_caps(void) +{ + if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) + kvm_caps.supported_xss = 0; + + if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && + !kvm_cpu_cap_has(X86_FEATURE_IBT)) + kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; + + if ((kvm_caps.supported_xss & XFEATURE_MASK_CET_ALL) != XFEATURE_MASK_CET_ALL) { + kvm_cpu_cap_clear(X86_FEATURE_SHSTK); + kvm_cpu_cap_clear(X86_FEATURE_IBT); + kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; + } +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_setup_xss_caps); + static inline void kvm_ops_update(struct kvm_x86_init_ops *ops) { memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); @@ -10106,19 +10149,6 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) if (!tdp_enabled) kvm_caps.supported_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT; - if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) - kvm_caps.supported_xss = 0; - - if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && - !kvm_cpu_cap_has(X86_FEATURE_IBT)) - kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; - - if ((kvm_caps.supported_xss & XFEATURE_MASK_CET_ALL) != XFEATURE_MASK_CET_ALL) { - kvm_cpu_cap_clear(X86_FEATURE_SHSTK); - kvm_cpu_cap_clear(X86_FEATURE_IBT); - kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; - } - if (kvm_caps.has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index f3dc77f006f904..c8a561c17e9ad3 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -457,6 +457,8 @@ extern struct kvm_host_values kvm_host; extern bool enable_pmu; +void kvm_setup_xss_caps(void); + /* * Get a filtered version of KVM's supported XCR0 that strips out dynamic * features for which the current process doesn't (yet) have permission to use. diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 998bd807fc7bad..b83a06739b5118 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -821,8 +821,6 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, force_sig_pkuerr((void __user *)address, pkey); else force_sig_fault(SIGSEGV, si_code, (void __user *)address); - - local_irq_disable(); } static noinline void @@ -1474,15 +1472,12 @@ handle_page_fault(struct pt_regs *regs, unsigned long error_code, do_kern_addr_fault(regs, error_code, address); } else { do_user_addr_fault(regs, error_code, address); - /* - * User address page fault handling might have reenabled - * interrupts. Fixing up all potential exit points of - * do_user_addr_fault() and its leaf functions is just not - * doable w/o creating an unholy mess or turning the code - * upside down. - */ - local_irq_disable(); } + /* + * page fault handling might have reenabled interrupts, + * make sure to disable them again. + */ + local_irq_disable(); } DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 0e4270e20fadb5..3d9a5e4ccaa434 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1031,7 +1031,7 @@ static void __meminit free_pagetable(struct page *page, int order) free_reserved_pages(page, nr_pages); #endif } else { - __free_pages(page, order); + pagetable_free(page_ptdesc(page)); } } diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 3c306de52fd4da..834641c6049a53 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -115,12 +115,12 @@ void __init kernel_randomize_memory(void) /* * Adapt physical memory region size based on available memory, - * except when CONFIG_PCI_P2PDMA is enabled. P2PDMA exposes the - * device BAR space assuming the direct map space is large enough - * for creating a ZONE_DEVICE mapping in the direct map corresponding - * to the physical BAR address. + * except when CONFIG_ZONE_DEVICE is enabled. ZONE_DEVICE wants to map + * any physical address into the direct-map. KASLR wants to reliably + * steal some physical address bits. Those design choices are in direct + * conflict. */ - if (!IS_ENABLED(CONFIG_PCI_P2PDMA) && (memory_tb < kaslr_regions[0].size_tb)) + if (!IS_ENABLED(CONFIG_ZONE_DEVICE) && (memory_tb < kaslr_regions[0].size_tb)) kaslr_regions[0].size_tb = memory_tb; /* diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 970981893c9b80..fffb6ef1997d26 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -429,7 +429,7 @@ static void cpa_collapse_large_pages(struct cpa_data *cpa) list_for_each_entry_safe(ptdesc, tmp, &pgtables, pt_list) { list_del(&ptdesc->pt_list); - __free_page(ptdesc_page(ptdesc)); + pagetable_free(ptdesc); } } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index ddf248c3ee7dc2..2e5ecfdce73c31 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -729,7 +729,7 @@ int pmd_clear_huge(pmd_t *pmd) int pud_free_pmd_page(pud_t *pud, unsigned long addr) { pmd_t *pmd, *pmd_sv; - pte_t *pte; + struct ptdesc *pt; int i; pmd = pud_pgtable(*pud); @@ -750,8 +750,8 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr) for (i = 0; i < PTRS_PER_PMD; i++) { if (!pmd_none(pmd_sv[i])) { - pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]); - pte_free_kernel(&init_mm, pte); + pt = page_ptdesc(pmd_page(pmd_sv[i])); + pagetable_dtor_free(pt); } } @@ -772,15 +772,15 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr) */ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { - pte_t *pte; + struct ptdesc *pt; - pte = (pte_t *)pmd_page_vaddr(*pmd); + pt = page_ptdesc(pmd_page(*pmd)); pmd_clear(pmd); /* INVLPG to clear all paging-structure caches */ flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); - pte_free_kernel(&init_mm, pte); + pagetable_dtor_free(pt); return 1; } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 53282dc7d5ac5b..23b91bf9b66303 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -470,7 +470,7 @@ int __init arch_xen_unpopulated_init(struct resource **res) * driver to know how much of the physmap is unpopulated and * set an accurate initial memory target. */ - xen_released_pages += xen_extra_mem[i].n_pfns; + xen_unpopulated_pages += xen_extra_mem[i].n_pfns; /* Zero so region is not also added to the balloon driver. */ xen_extra_mem[i].n_pfns = 0; } diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 4806cc28d7ca77..b74ff8bc7f2a8d 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -108,7 +108,7 @@ static int xen_cpu_dead_pv(unsigned int cpu); * calls. */ DEFINE_PER_CPU(bool, xen_in_preemptible_hcall); -EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall); +EXPORT_PER_CPU_SYMBOL_GPL(xen_in_preemptible_hcall); /* * In case of scheduling the flag must be cleared and restored after diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 9fb9f353315025..6a75fe1c7a5c0e 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -380,7 +380,7 @@ static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from) blkg_rwstat_add_aux(&to->merged, &from->merged); blkg_rwstat_add_aux(&to->service_time, &from->service_time); blkg_rwstat_add_aux(&to->wait_time, &from->wait_time); - bfq_stat_add_aux(&from->time, &from->time); + bfq_stat_add_aux(&to->time, &from->time); bfq_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum); bfq_stat_add_aux(&to->avg_queue_size_samples, &from->avg_queue_size_samples); diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 4a8d3d96bfe492..6e54b1d3d8bc2a 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -7181,7 +7181,7 @@ static void bfq_exit_queue(struct elevator_queue *e) blk_stat_disable_accounting(bfqd->queue); blk_queue_flag_clear(QUEUE_FLAG_DISABLE_WBT_DEF, bfqd->queue); - set_bit(ELEVATOR_FLAG_ENABLE_WBT_ON_EXIT, &e->flags); + wbt_enable_default(bfqd->queue->disk); kfree(bfqd); } diff --git a/block/bio-integrity-auto.c b/block/bio-integrity-auto.c index 687952f63bbbfe..b8b7587be9679a 100644 --- a/block/bio-integrity-auto.c +++ b/block/bio-integrity-auto.c @@ -142,7 +142,7 @@ bool bio_integrity_prep(struct bio *bio) return true; set_flags = false; gfp |= __GFP_ZERO; - } else if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE) + } else if (bi->metadata_size > bi->pi_tuple_size) gfp |= __GFP_ZERO; break; default: diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 9b27963680dc34..964eebbee14d04 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -140,14 +140,21 @@ EXPORT_SYMBOL_GPL(blk_rq_integrity_map_user); bool blk_integrity_merge_rq(struct request_queue *q, struct request *req, struct request *next) { + struct bio_integrity_payload *bip, *bip_next; + if (blk_integrity_rq(req) == 0 && blk_integrity_rq(next) == 0) return true; if (blk_integrity_rq(req) == 0 || blk_integrity_rq(next) == 0) return false; - if (bio_integrity(req->bio)->bip_flags != - bio_integrity(next->bio)->bip_flags) + bip = bio_integrity(req->bio); + bip_next = bio_integrity(next->bio); + if (bip->bip_flags != bip_next->bip_flags) + return false; + + if (bip->bip_flags & BIP_CHECK_APPTAG && + bip->app_tag != bip_next->app_tag) return false; if (req->nr_integrity_segments + next->nr_integrity_segments > @@ -163,15 +170,21 @@ bool blk_integrity_merge_rq(struct request_queue *q, struct request *req, bool blk_integrity_merge_bio(struct request_queue *q, struct request *req, struct bio *bio) { + struct bio_integrity_payload *bip, *bip_bio = bio_integrity(bio); int nr_integrity_segs; - if (blk_integrity_rq(req) == 0 && bio_integrity(bio) == NULL) + if (blk_integrity_rq(req) == 0 && bip_bio == NULL) return true; - if (blk_integrity_rq(req) == 0 || bio_integrity(bio) == NULL) + if (blk_integrity_rq(req) == 0 || bip_bio == NULL) + return false; + + bip = bio_integrity(req->bio); + if (bip->bip_flags != bip_bio->bip_flags) return false; - if (bio_integrity(req->bio)->bip_flags != bio_integrity(bio)->bip_flags) + if (bip->bip_flags & BIP_CHECK_APPTAG && + bip->app_tag != bip_bio->app_tag) return false; nr_integrity_segs = blk_rq_count_integrity_sg(q, bio); diff --git a/block/blk-lib.c b/block/blk-lib.c index 3030a772d3aa01..352e3c0f8a7d7a 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -202,13 +202,13 @@ static void __blkdev_issue_zero_pages(struct block_device *bdev, unsigned int nr_vecs = __blkdev_sectors_to_bio_pages(nr_sects); struct bio *bio; - bio = bio_alloc(bdev, nr_vecs, REQ_OP_WRITE, gfp_mask); - bio->bi_iter.bi_sector = sector; - if ((flags & BLKDEV_ZERO_KILLABLE) && fatal_signal_pending(current)) break; + bio = bio_alloc(bdev, nr_vecs, REQ_OP_WRITE, gfp_mask); + bio->bi_iter.bi_sector = sector; + do { unsigned int len; diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index e0bed16485c346..128f2be9d42073 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -427,11 +427,25 @@ void blk_mq_free_sched_tags(struct elevator_tags *et, kfree(et); } -void blk_mq_free_sched_tags_batch(struct xarray *et_table, +void blk_mq_free_sched_res(struct elevator_resources *res, + struct elevator_type *type, + struct blk_mq_tag_set *set) +{ + if (res->et) { + blk_mq_free_sched_tags(res->et, set); + res->et = NULL; + } + if (res->data) { + blk_mq_free_sched_data(type, res->data); + res->data = NULL; + } +} + +void blk_mq_free_sched_res_batch(struct xarray *elv_tbl, struct blk_mq_tag_set *set) { struct request_queue *q; - struct elevator_tags *et; + struct elv_change_ctx *ctx; lockdep_assert_held_write(&set->update_nr_hwq_lock); @@ -444,13 +458,46 @@ void blk_mq_free_sched_tags_batch(struct xarray *et_table, * concurrently. */ if (q->elevator) { - et = xa_load(et_table, q->id); - if (unlikely(!et)) + ctx = xa_load(elv_tbl, q->id); + if (!ctx) { WARN_ON_ONCE(1); - else - blk_mq_free_sched_tags(et, set); + continue; + } + blk_mq_free_sched_res(&ctx->res, ctx->type, set); + } + } +} + +void blk_mq_free_sched_ctx_batch(struct xarray *elv_tbl) +{ + unsigned long i; + struct elv_change_ctx *ctx; + + xa_for_each(elv_tbl, i, ctx) { + xa_erase(elv_tbl, i); + kfree(ctx); + } +} + +int blk_mq_alloc_sched_ctx_batch(struct xarray *elv_tbl, + struct blk_mq_tag_set *set) +{ + struct request_queue *q; + struct elv_change_ctx *ctx; + + lockdep_assert_held_write(&set->update_nr_hwq_lock); + + list_for_each_entry(q, &set->tag_list, tag_set_list) { + ctx = kzalloc(sizeof(struct elv_change_ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + if (xa_insert(elv_tbl, q->id, ctx, GFP_KERNEL)) { + kfree(ctx); + return -ENOMEM; } } + return 0; } struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set, @@ -498,12 +545,33 @@ struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set, return NULL; } -int blk_mq_alloc_sched_tags_batch(struct xarray *et_table, +int blk_mq_alloc_sched_res(struct request_queue *q, + struct elevator_type *type, + struct elevator_resources *res, + unsigned int nr_hw_queues) +{ + struct blk_mq_tag_set *set = q->tag_set; + + res->et = blk_mq_alloc_sched_tags(set, nr_hw_queues, + blk_mq_default_nr_requests(set)); + if (!res->et) + return -ENOMEM; + + res->data = blk_mq_alloc_sched_data(q, type); + if (IS_ERR(res->data)) { + blk_mq_free_sched_tags(res->et, set); + return -ENOMEM; + } + + return 0; +} + +int blk_mq_alloc_sched_res_batch(struct xarray *elv_tbl, struct blk_mq_tag_set *set, unsigned int nr_hw_queues) { + struct elv_change_ctx *ctx; struct request_queue *q; - struct elevator_tags *et; - gfp_t gfp = GFP_NOIO | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; + int ret = -ENOMEM; lockdep_assert_held_write(&set->update_nr_hwq_lock); @@ -516,39 +584,44 @@ int blk_mq_alloc_sched_tags_batch(struct xarray *et_table, * concurrently. */ if (q->elevator) { - et = blk_mq_alloc_sched_tags(set, nr_hw_queues, - blk_mq_default_nr_requests(set)); - if (!et) + ctx = xa_load(elv_tbl, q->id); + if (WARN_ON_ONCE(!ctx)) { + ret = -ENOENT; + goto out_unwind; + } + + ret = blk_mq_alloc_sched_res(q, q->elevator->type, + &ctx->res, nr_hw_queues); + if (ret) goto out_unwind; - if (xa_insert(et_table, q->id, et, gfp)) - goto out_free_tags; } } return 0; -out_free_tags: - blk_mq_free_sched_tags(et, set); + out_unwind: list_for_each_entry_continue_reverse(q, &set->tag_list, tag_set_list) { if (q->elevator) { - et = xa_load(et_table, q->id); - if (et) - blk_mq_free_sched_tags(et, set); + ctx = xa_load(elv_tbl, q->id); + if (ctx) + blk_mq_free_sched_res(&ctx->res, + ctx->type, set); } } - return -ENOMEM; + return ret; } /* caller must have a reference to @e, will grab another one if successful */ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e, - struct elevator_tags *et) + struct elevator_resources *res) { unsigned int flags = q->tag_set->flags; + struct elevator_tags *et = res->et; struct blk_mq_hw_ctx *hctx; struct elevator_queue *eq; unsigned long i; int ret; - eq = elevator_alloc(q, e, et); + eq = elevator_alloc(q, e, res); if (!eq) return -ENOMEM; diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 8e21a6b1415d9d..02c40a72e9598c 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -19,18 +19,52 @@ void __blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx); void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx); int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e, - struct elevator_tags *et); + struct elevator_resources *res); void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e); void blk_mq_sched_free_rqs(struct request_queue *q); struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set, unsigned int nr_hw_queues, unsigned int nr_requests); -int blk_mq_alloc_sched_tags_batch(struct xarray *et_table, +int blk_mq_alloc_sched_res(struct request_queue *q, + struct elevator_type *type, + struct elevator_resources *res, + unsigned int nr_hw_queues); +int blk_mq_alloc_sched_res_batch(struct xarray *elv_tbl, struct blk_mq_tag_set *set, unsigned int nr_hw_queues); +int blk_mq_alloc_sched_ctx_batch(struct xarray *elv_tbl, + struct blk_mq_tag_set *set); +void blk_mq_free_sched_ctx_batch(struct xarray *elv_tbl); void blk_mq_free_sched_tags(struct elevator_tags *et, struct blk_mq_tag_set *set); -void blk_mq_free_sched_tags_batch(struct xarray *et_table, +void blk_mq_free_sched_res(struct elevator_resources *res, + struct elevator_type *type, + struct blk_mq_tag_set *set); +void blk_mq_free_sched_res_batch(struct xarray *et_table, struct blk_mq_tag_set *set); +/* + * blk_mq_alloc_sched_data() - Allocates scheduler specific data + * Returns: + * - Pointer to allocated data on success + * - NULL if no allocation needed + * - ERR_PTR(-ENOMEM) in case of failure + */ +static inline void *blk_mq_alloc_sched_data(struct request_queue *q, + struct elevator_type *e) +{ + void *sched_data; + + if (!e || !e->ops.alloc_sched_data) + return NULL; + + sched_data = e->ops.alloc_sched_data(q); + return (sched_data) ?: ERR_PTR(-ENOMEM); +} + +static inline void blk_mq_free_sched_data(struct elevator_type *e, void *data) +{ + if (e && e->ops.free_sched_data) + e->ops.free_sched_data(data); +} static inline void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) { diff --git a/block/blk-mq.c b/block/blk-mq.c index d626d32f6e576f..a03f52ab87d64d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -335,12 +336,12 @@ void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set) { struct request_queue *q; - mutex_lock(&set->tag_list_lock); - list_for_each_entry(q, &set->tag_list, tag_set_list) { + rcu_read_lock(); + list_for_each_entry_rcu(q, &set->tag_list, tag_set_list) { if (!blk_queue_skip_tagset_quiesce(q)) blk_mq_quiesce_queue_nowait(q); } - mutex_unlock(&set->tag_list_lock); + rcu_read_unlock(); blk_mq_wait_quiesce_done(set); } @@ -350,12 +351,12 @@ void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set) { struct request_queue *q; - mutex_lock(&set->tag_list_lock); - list_for_each_entry(q, &set->tag_list, tag_set_list) { + rcu_read_lock(); + list_for_each_entry_rcu(q, &set->tag_list, tag_set_list) { if (!blk_queue_skip_tagset_quiesce(q)) blk_mq_unquiesce_queue(q); } - mutex_unlock(&set->tag_list_lock); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_mq_unquiesce_tagset); @@ -3707,8 +3708,9 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_online); + int ret = 0; - if (blk_mq_hctx_has_online_cpu(hctx, cpu)) + if (!hctx->nr_ctx || blk_mq_hctx_has_online_cpu(hctx, cpu)) return 0; /* @@ -3727,12 +3729,24 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node) * frozen and there are no requests. */ if (percpu_ref_tryget(&hctx->queue->q_usage_counter)) { - while (blk_mq_hctx_has_requests(hctx)) + while (blk_mq_hctx_has_requests(hctx)) { + /* + * The wakeup capable IRQ handler of block device is + * not called during suspend. Skip the loop by checking + * pm_wakeup_pending to prevent the deadlock and improve + * suspend latency. + */ + if (pm_wakeup_pending()) { + clear_bit(BLK_MQ_S_INACTIVE, &hctx->state); + ret = -EBUSY; + break; + } msleep(5); + } percpu_ref_put(&hctx->queue->q_usage_counter); } - return 0; + return ret; } /* @@ -4294,7 +4308,7 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q) struct blk_mq_tag_set *set = q->tag_set; mutex_lock(&set->tag_list_lock); - list_del(&q->tag_set_list); + list_del_rcu(&q->tag_set_list); if (list_is_singular(&set->tag_list)) { /* just transitioned to unshared */ set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; @@ -4302,7 +4316,6 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q) blk_mq_update_tag_set_shared(set, false); } mutex_unlock(&set->tag_list_lock); - INIT_LIST_HEAD(&q->tag_set_list); } static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, @@ -4321,7 +4334,7 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, } if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED) queue_set_hctx_shared(q, true); - list_add_tail(&q->tag_set_list, &set->tag_list); + list_add_tail_rcu(&q->tag_set_list, &set->tag_list); mutex_unlock(&set->tag_list_lock); } @@ -4983,27 +4996,28 @@ struct elevator_tags *blk_mq_update_nr_requests(struct request_queue *q, * Switch back to the elevator type stored in the xarray. */ static void blk_mq_elv_switch_back(struct request_queue *q, - struct xarray *elv_tbl, struct xarray *et_tbl) + struct xarray *elv_tbl) { - struct elevator_type *e = xa_load(elv_tbl, q->id); - struct elevator_tags *t = xa_load(et_tbl, q->id); + struct elv_change_ctx *ctx = xa_load(elv_tbl, q->id); + + if (WARN_ON_ONCE(!ctx)) + return; /* The elv_update_nr_hw_queues unfreezes the queue. */ - elv_update_nr_hw_queues(q, e, t); + elv_update_nr_hw_queues(q, ctx); /* Drop the reference acquired in blk_mq_elv_switch_none. */ - if (e) - elevator_put(e); + if (ctx->type) + elevator_put(ctx->type); } /* - * Stores elevator type in xarray and set current elevator to none. It uses - * q->id as an index to store the elevator type into the xarray. + * Stores elevator name and type in ctx and set current elevator to none. */ static int blk_mq_elv_switch_none(struct request_queue *q, struct xarray *elv_tbl) { - int ret = 0; + struct elv_change_ctx *ctx; lockdep_assert_held_write(&q->tag_set->update_nr_hwq_lock); @@ -5015,10 +5029,11 @@ static int blk_mq_elv_switch_none(struct request_queue *q, * can't run concurrently. */ if (q->elevator) { + ctx = xa_load(elv_tbl, q->id); + if (WARN_ON_ONCE(!ctx)) + return -ENOENT; - ret = xa_insert(elv_tbl, q->id, q->elevator->type, GFP_KERNEL); - if (WARN_ON_ONCE(ret)) - return ret; + ctx->name = q->elevator->type->elevator_name; /* * Before we switch elevator to 'none', take a reference to @@ -5029,9 +5044,14 @@ static int blk_mq_elv_switch_none(struct request_queue *q, */ __elevator_get(q->elevator->type); + /* + * Store elevator type so that we can release the reference + * taken above later. + */ + ctx->type = q->elevator->type; elevator_set_none(q); } - return ret; + return 0; } static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, @@ -5041,7 +5061,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int prev_nr_hw_queues = set->nr_hw_queues; unsigned int memflags; int i; - struct xarray elv_tbl, et_tbl; + struct xarray elv_tbl; bool queues_frozen = false; lockdep_assert_held(&set->tag_list_lock); @@ -5055,11 +5075,12 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, memflags = memalloc_noio_save(); - xa_init(&et_tbl); - if (blk_mq_alloc_sched_tags_batch(&et_tbl, set, nr_hw_queues) < 0) - goto out_memalloc_restore; - xa_init(&elv_tbl); + if (blk_mq_alloc_sched_ctx_batch(&elv_tbl, set) < 0) + goto out_free_ctx; + + if (blk_mq_alloc_sched_res_batch(&elv_tbl, set, nr_hw_queues) < 0) + goto out_free_ctx; list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_debugfs_unregister_hctxs(q); @@ -5105,7 +5126,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, /* switch_back expects queue to be frozen */ if (!queues_frozen) blk_mq_freeze_queue_nomemsave(q); - blk_mq_elv_switch_back(q, &elv_tbl, &et_tbl); + blk_mq_elv_switch_back(q, &elv_tbl); } list_for_each_entry(q, &set->tag_list, tag_set_list) { @@ -5116,9 +5137,9 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, blk_mq_add_hw_queues_cpuhp(q); } +out_free_ctx: + blk_mq_free_sched_ctx_batch(&elv_tbl); xa_destroy(&elv_tbl); - xa_destroy(&et_tbl); -out_memalloc_restore: memalloc_noio_restore(memflags); /* Free the excess tags when nr_hw_queues shrink. */ diff --git a/block/blk-settings.c b/block/blk-settings.c index d74b13ec8e548c..f2c1940fe6f1ae 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -148,10 +148,9 @@ static int blk_validate_integrity_limits(struct queue_limits *lim) return -EINVAL; } - if (bi->pi_tuple_size > bi->metadata_size) { - pr_warn("pi_tuple_size (%u) exceeds metadata_size (%u)\n", - bi->pi_tuple_size, - bi->metadata_size); + if (bi->pi_offset + bi->pi_tuple_size > bi->metadata_size) { + pr_warn("pi_offset (%u) + pi_tuple_size (%u) exceeds metadata_size (%u)\n", + bi->pi_offset, bi->pi_tuple_size, bi->metadata_size); return -EINVAL; } diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 76c47fe9b8d68c..e0a70d26972b3b 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -143,21 +143,22 @@ queue_ra_store(struct gendisk *disk, const char *page, size_t count) { unsigned long ra_kb; ssize_t ret; - unsigned int memflags; struct request_queue *q = disk->queue; ret = queue_var_store(&ra_kb, page, count); if (ret < 0) return ret; /* - * ->ra_pages is protected by ->limits_lock because it is usually - * calculated from the queue limits by queue_limits_commit_update. + * The ->ra_pages change below is protected by ->limits_lock because it + * is usually calculated from the queue limits by + * queue_limits_commit_update(). + * + * bdi->ra_pages reads are not serialized against bdi->ra_pages writes. + * Use WRITE_ONCE() to write bdi->ra_pages once. */ mutex_lock(&q->limits_lock); - memflags = blk_mq_freeze_queue(q); - disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10); + WRITE_ONCE(disk->bdi->ra_pages, ra_kb >> (PAGE_SHIFT - 10)); mutex_unlock(&q->limits_lock); - blk_mq_unfreeze_queue(q, memflags); return ret; } @@ -375,21 +376,18 @@ static ssize_t queue_nomerges_store(struct gendisk *disk, const char *page, size_t count) { unsigned long nm; - unsigned int memflags; struct request_queue *q = disk->queue; ssize_t ret = queue_var_store(&nm, page, count); if (ret < 0) return ret; - memflags = blk_mq_freeze_queue(q); blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, q); blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, q); if (nm == 2) blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); else if (nm) blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); - blk_mq_unfreeze_queue(q, memflags); return ret; } @@ -409,7 +407,6 @@ queue_rq_affinity_store(struct gendisk *disk, const char *page, size_t count) #ifdef CONFIG_SMP struct request_queue *q = disk->queue; unsigned long val; - unsigned int memflags; ret = queue_var_store(&val, page, count); if (ret < 0) @@ -421,7 +418,6 @@ queue_rq_affinity_store(struct gendisk *disk, const char *page, size_t count) * are accessed individually using atomic test_bit operation. So we * don't grab any lock while updating these flags. */ - memflags = blk_mq_freeze_queue(q); if (val == 2) { blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, q); blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, q); @@ -432,7 +428,6 @@ queue_rq_affinity_store(struct gendisk *disk, const char *page, size_t count) blk_queue_flag_clear(QUEUE_FLAG_SAME_COMP, q); blk_queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q); } - blk_mq_unfreeze_queue(q, memflags); #endif return ret; } @@ -446,11 +441,9 @@ static ssize_t queue_poll_delay_store(struct gendisk *disk, const char *page, static ssize_t queue_poll_store(struct gendisk *disk, const char *page, size_t count) { - unsigned int memflags; ssize_t ret = count; struct request_queue *q = disk->queue; - memflags = blk_mq_freeze_queue(q); if (!(q->limits.features & BLK_FEAT_POLL)) { ret = -EINVAL; goto out; @@ -459,7 +452,6 @@ static ssize_t queue_poll_store(struct gendisk *disk, const char *page, pr_info_ratelimited("writes to the poll attribute are ignored.\n"); pr_info_ratelimited("please use driver specific parameters instead.\n"); out: - blk_mq_unfreeze_queue(q, memflags); return ret; } @@ -472,7 +464,7 @@ static ssize_t queue_io_timeout_show(struct gendisk *disk, char *page) static ssize_t queue_io_timeout_store(struct gendisk *disk, const char *page, size_t count) { - unsigned int val, memflags; + unsigned int val; int err; struct request_queue *q = disk->queue; @@ -480,9 +472,7 @@ static ssize_t queue_io_timeout_store(struct gendisk *disk, const char *page, if (err || val == 0) return -EINVAL; - memflags = blk_mq_freeze_queue(q); blk_queue_rq_timeout(q, msecs_to_jiffies(val)); - blk_mq_unfreeze_queue(q, memflags); return count; } @@ -942,7 +932,7 @@ int blk_register_queue(struct gendisk *disk) elevator_set_default(q); blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q); - wbt_enable_default(disk); + wbt_init_enable_default(disk); /* Now everything is ready and send out KOBJ_ADD uevent */ kobject_uevent(&disk->queue_kobj, KOBJ_ADD); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 2c5b64b1a724a7..c19d052a8f2f12 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -22,9 +22,7 @@ #define THROTL_QUANTUM 32 /* Throttling is performed over a slice and after that slice is renewed */ -#define DFL_THROTL_SLICE_HD (HZ / 10) -#define DFL_THROTL_SLICE_SSD (HZ / 50) -#define MAX_THROTL_SLICE (HZ) +#define DFL_THROTL_SLICE (HZ / 10) /* A workqueue to queue throttle related work */ static struct workqueue_struct *kthrotld_workqueue; @@ -1341,10 +1339,7 @@ static int blk_throtl_init(struct gendisk *disk) goto out; } - if (blk_queue_nonrot(q)) - td->throtl_slice = DFL_THROTL_SLICE_SSD; - else - td->throtl_slice = DFL_THROTL_SLICE_HD; + td->throtl_slice = DFL_THROTL_SLICE; td->track_bio_latency = !queue_is_mq(q); if (!td->track_bio_latency) blk_stat_enable_accounting(q); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index eb8037bae0bda6..0974875f77bda2 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -699,7 +699,7 @@ static void wbt_requeue(struct rq_qos *rqos, struct request *rq) /* * Enable wbt if defaults are configured that way */ -void wbt_enable_default(struct gendisk *disk) +static bool __wbt_enable_default(struct gendisk *disk) { struct request_queue *q = disk->queue; struct rq_qos *rqos; @@ -716,19 +716,31 @@ void wbt_enable_default(struct gendisk *disk) if (enable && RQWB(rqos)->enable_state == WBT_STATE_OFF_DEFAULT) RQWB(rqos)->enable_state = WBT_STATE_ON_DEFAULT; mutex_unlock(&disk->rqos_state_mutex); - return; + return false; } mutex_unlock(&disk->rqos_state_mutex); /* Queue not registered? Maybe shutting down... */ if (!blk_queue_registered(q)) - return; + return false; if (queue_is_mq(q) && enable) - wbt_init(disk); + return true; + return false; +} + +void wbt_enable_default(struct gendisk *disk) +{ + __wbt_enable_default(disk); } EXPORT_SYMBOL_GPL(wbt_enable_default); +void wbt_init_enable_default(struct gendisk *disk) +{ + if (__wbt_enable_default(disk)) + WARN_ON_ONCE(wbt_init(disk)); +} + u64 wbt_default_latency_nsec(struct request_queue *q) { /* diff --git a/block/blk-wbt.h b/block/blk-wbt.h index e5fc653b9b76f6..925f2247573834 100644 --- a/block/blk-wbt.h +++ b/block/blk-wbt.h @@ -5,6 +5,7 @@ #ifdef CONFIG_BLK_WBT int wbt_init(struct gendisk *disk); +void wbt_init_enable_default(struct gendisk *disk); void wbt_disable_default(struct gendisk *disk); void wbt_enable_default(struct gendisk *disk); @@ -16,6 +17,10 @@ u64 wbt_default_latency_nsec(struct request_queue *); #else +static inline void wbt_init_enable_default(struct gendisk *disk) +{ +} + static inline void wbt_disable_default(struct gendisk *disk) { } diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 5e2a5788dc3b29..0c812f3bd7df38 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -71,6 +71,11 @@ struct blk_zone_wplug { struct gendisk *disk; }; +static inline unsigned int disk_zone_wplugs_hash_size(struct gendisk *disk) +{ + return 1U << disk->zone_wplugs_hash_bits; +} + /* * Zone write plug flags bits: * - BLK_ZONE_WPLUG_PLUGGED: Indicates that the zone write plug is plugged, @@ -611,6 +616,8 @@ static void disk_zone_wplug_abort(struct blk_zone_wplug *zwplug) { struct bio *bio; + lockdep_assert_held(&zwplug->lock); + if (bio_list_empty(&zwplug->bio_list)) return; @@ -618,6 +625,8 @@ static void disk_zone_wplug_abort(struct blk_zone_wplug *zwplug) zwplug->disk->disk_name, zwplug->zone_no); while ((bio = bio_list_pop(&zwplug->bio_list))) blk_zone_wplug_bio_io_error(zwplug, bio); + + zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED; } /* @@ -698,71 +707,94 @@ static int disk_zone_sync_wp_offset(struct gendisk *disk, sector_t sector) disk_report_zones_cb, &args); } -static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, - unsigned int wp_offset) +static void blk_zone_reset_bio_endio(struct bio *bio) { struct gendisk *disk = bio->bi_bdev->bd_disk; - sector_t sector = bio->bi_iter.bi_sector; struct blk_zone_wplug *zwplug; - unsigned long flags; - - /* Conventional zones cannot be reset nor finished. */ - if (!bdev_zone_is_seq(bio->bi_bdev, sector)) { - bio_io_error(bio); - return true; - } /* - * No-wait reset or finish BIOs do not make much sense as the callers - * issue these as blocking operations in most cases. To avoid issues - * the BIO execution potentially failing with BLK_STS_AGAIN, warn about - * REQ_NOWAIT being set and ignore that flag. - */ - if (WARN_ON_ONCE(bio->bi_opf & REQ_NOWAIT)) - bio->bi_opf &= ~REQ_NOWAIT; - - /* - * If we have a zone write plug, set its write pointer offset to 0 - * (reset case) or to the zone size (finish case). This will abort all - * BIOs plugged for the target zone. It is fine as resetting or - * finishing zones while writes are still in-flight will result in the + * If we have a zone write plug, set its write pointer offset to 0. + * This will abort all BIOs plugged for the target zone. It is fine as + * resetting zones while writes are still in-flight will result in the * writes failing anyway. */ - zwplug = disk_get_zone_wplug(disk, sector); + zwplug = disk_get_zone_wplug(disk, bio->bi_iter.bi_sector); if (zwplug) { + unsigned long flags; + spin_lock_irqsave(&zwplug->lock, flags); - disk_zone_wplug_set_wp_offset(disk, zwplug, wp_offset); + disk_zone_wplug_set_wp_offset(disk, zwplug, 0); spin_unlock_irqrestore(&zwplug->lock, flags); disk_put_zone_wplug(zwplug); } - - return false; } -static bool blk_zone_wplug_handle_reset_all(struct bio *bio) +static void blk_zone_reset_all_bio_endio(struct bio *bio) { struct gendisk *disk = bio->bi_bdev->bd_disk; struct blk_zone_wplug *zwplug; unsigned long flags; - sector_t sector; + unsigned int i; + + if (atomic_read(&disk->nr_zone_wplugs)) { + /* Update the condition of all zone write plugs. */ + rcu_read_lock(); + for (i = 0; i < disk_zone_wplugs_hash_size(disk); i++) { + hlist_for_each_entry_rcu(zwplug, + &disk->zone_wplugs_hash[i], + node) { + spin_lock_irqsave(&zwplug->lock, flags); + disk_zone_wplug_set_wp_offset(disk, zwplug, 0); + spin_unlock_irqrestore(&zwplug->lock, flags); + } + } + rcu_read_unlock(); + } +} + +static void blk_zone_finish_bio_endio(struct bio *bio) +{ + struct block_device *bdev = bio->bi_bdev; + struct gendisk *disk = bdev->bd_disk; + struct blk_zone_wplug *zwplug; /* - * Set the write pointer offset of all zone write plugs to 0. This will - * abort all plugged BIOs. It is fine as resetting zones while writes - * are still in-flight will result in the writes failing anyway. + * If we have a zone write plug, set its write pointer offset to the + * zone size. This will abort all BIOs plugged for the target zone. It + * is fine as resetting zones while writes are still in-flight will + * result in the writes failing anyway. */ - for (sector = 0; sector < get_capacity(disk); - sector += disk->queue->limits.chunk_sectors) { - zwplug = disk_get_zone_wplug(disk, sector); - if (zwplug) { - spin_lock_irqsave(&zwplug->lock, flags); - disk_zone_wplug_set_wp_offset(disk, zwplug, 0); - spin_unlock_irqrestore(&zwplug->lock, flags); - disk_put_zone_wplug(zwplug); - } + zwplug = disk_get_zone_wplug(disk, bio->bi_iter.bi_sector); + if (zwplug) { + unsigned long flags; + + spin_lock_irqsave(&zwplug->lock, flags); + disk_zone_wplug_set_wp_offset(disk, zwplug, + bdev_zone_sectors(bdev)); + spin_unlock_irqrestore(&zwplug->lock, flags); + disk_put_zone_wplug(zwplug); } +} - return false; +void blk_zone_mgmt_bio_endio(struct bio *bio) +{ + /* If the BIO failed, we have nothing to do. */ + if (bio->bi_status != BLK_STS_OK) + return; + + switch (bio_op(bio)) { + case REQ_OP_ZONE_RESET: + blk_zone_reset_bio_endio(bio); + return; + case REQ_OP_ZONE_RESET_ALL: + blk_zone_reset_all_bio_endio(bio); + return; + case REQ_OP_ZONE_FINISH: + blk_zone_finish_bio_endio(bio); + return; + default: + return; + } } static void disk_zone_wplug_schedule_bio_work(struct gendisk *disk, @@ -1106,6 +1138,30 @@ static void blk_zone_wplug_handle_native_zone_append(struct bio *bio) disk_put_zone_wplug(zwplug); } +static bool blk_zone_wplug_handle_zone_mgmt(struct bio *bio) +{ + if (bio_op(bio) != REQ_OP_ZONE_RESET_ALL && + !bdev_zone_is_seq(bio->bi_bdev, bio->bi_iter.bi_sector)) { + /* + * Zone reset and zone finish operations do not apply to + * conventional zones. + */ + bio_io_error(bio); + return true; + } + + /* + * No-wait zone management BIOs do not make much sense as the callers + * issue these as blocking operations in most cases. To avoid issues + * with the BIO execution potentially failing with BLK_STS_AGAIN, warn + * about REQ_NOWAIT being set and ignore that flag. + */ + if (WARN_ON_ONCE(bio->bi_opf & REQ_NOWAIT)) + bio->bi_opf &= ~REQ_NOWAIT; + + return false; +} + /** * blk_zone_plug_bio - Handle a zone write BIO with zone write plugging * @bio: The BIO being submitted @@ -1153,12 +1209,9 @@ bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) case REQ_OP_WRITE_ZEROES: return blk_zone_wplug_handle_write(bio, nr_segs); case REQ_OP_ZONE_RESET: - return blk_zone_wplug_handle_reset_or_finish(bio, 0); case REQ_OP_ZONE_FINISH: - return blk_zone_wplug_handle_reset_or_finish(bio, - bdev_zone_sectors(bdev)); case REQ_OP_ZONE_RESET_ALL: - return blk_zone_wplug_handle_reset_all(bio); + return blk_zone_wplug_handle_zone_mgmt(bio); default: return false; } @@ -1332,11 +1385,6 @@ static void blk_zone_wplug_bio_work(struct work_struct *work) disk_put_zone_wplug(zwplug); } -static inline unsigned int disk_zone_wplugs_hash_size(struct gendisk *disk) -{ - return 1U << disk->zone_wplugs_hash_bits; -} - void disk_init_zone_resources(struct gendisk *disk) { spin_lock_init(&disk->zone_wplugs_lock); @@ -1516,8 +1564,13 @@ static int disk_update_zone_resources(struct gendisk *disk, { struct request_queue *q = disk->queue; unsigned int nr_seq_zones, nr_conv_zones; - unsigned int pool_size; + unsigned int pool_size, memflags; struct queue_limits lim; + int ret = 0; + + lim = queue_limits_start_update(q); + + memflags = blk_mq_freeze_queue(q); disk->nr_zones = args->nr_zones; disk->zone_capacity = args->zone_capacity; @@ -1527,11 +1580,10 @@ static int disk_update_zone_resources(struct gendisk *disk, if (nr_conv_zones >= disk->nr_zones) { pr_warn("%s: Invalid number of conventional zones %u / %u\n", disk->disk_name, nr_conv_zones, disk->nr_zones); - return -ENODEV; + ret = -ENODEV; + goto unfreeze; } - lim = queue_limits_start_update(q); - /* * Some devices can advertize zone resource limits that are larger than * the number of sequential zones of the zoned block device, e.g. a @@ -1568,7 +1620,15 @@ static int disk_update_zone_resources(struct gendisk *disk, } commit: - return queue_limits_commit_update_frozen(q, &lim); + ret = queue_limits_commit_update(q, &lim); + +unfreeze: + if (ret) + disk_free_zone_resources(disk); + + blk_mq_unfreeze_queue(q, memflags); + + return ret; } static int blk_revalidate_conv_zone(struct blk_zone *zone, unsigned int idx, @@ -1733,7 +1793,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk) sector_t zone_sectors = q->limits.chunk_sectors; sector_t capacity = get_capacity(disk); struct blk_revalidate_zone_args args = { }; - unsigned int noio_flag; + unsigned int memflags, noio_flag; int ret = -ENOMEM; if (WARN_ON_ONCE(!blk_queue_is_zoned(q))) @@ -1783,20 +1843,14 @@ int blk_revalidate_disk_zones(struct gendisk *disk) ret = -ENODEV; } - /* - * Set the new disk zone parameters only once the queue is frozen and - * all I/Os are completed. - */ if (ret > 0) - ret = disk_update_zone_resources(disk, &args); - else - pr_warn("%s: failed to revalidate zones\n", disk->disk_name); - if (ret) { - unsigned int memflags = blk_mq_freeze_queue(q); + return disk_update_zone_resources(disk, &args); - disk_free_zone_resources(disk); - blk_mq_unfreeze_queue(q, memflags); - } + pr_warn("%s: failed to revalidate zones\n", disk->disk_name); + + memflags = blk_mq_freeze_queue(q); + disk_free_zone_resources(disk); + blk_mq_unfreeze_queue(q, memflags); return ret; } diff --git a/block/blk.h b/block/blk.h index 170794632135da..37b9b6a95c11c3 100644 --- a/block/blk.h +++ b/block/blk.h @@ -11,8 +11,7 @@ #include #include "blk-crypto-internal.h" -struct elevator_type; -struct elevator_tags; +struct elv_change_ctx; /* * Default upper limit for the software max_sectors limit used for regular I/Os. @@ -333,8 +332,8 @@ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, bool blk_insert_flush(struct request *rq); -void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e, - struct elevator_tags *t); +void elv_update_nr_hw_queues(struct request_queue *q, + struct elv_change_ctx *ctx); void elevator_set_default(struct request_queue *q); void elevator_set_none(struct request_queue *q); @@ -489,9 +488,23 @@ static inline bool blk_req_bio_is_zone_append(struct request *rq, void blk_zone_write_plug_bio_merged(struct bio *bio); void blk_zone_write_plug_init_request(struct request *rq); void blk_zone_append_update_request_bio(struct request *rq, struct bio *bio); +void blk_zone_mgmt_bio_endio(struct bio *bio); void blk_zone_write_plug_bio_endio(struct bio *bio); static inline void blk_zone_bio_endio(struct bio *bio) { + /* + * Zone management BIOs may impact zone write plugs (e.g. a zone reset + * changes a zone write plug zone write pointer offset), but these + * operation do not go through zone write plugging as they may operate + * on zones that do not have a zone write + * plug. blk_zone_mgmt_bio_endio() handles the potential changes to zone + * write plugs that are present. + */ + if (op_is_zone_mgmt(bio_op(bio))) { + blk_zone_mgmt_bio_endio(bio); + return; + } + /* * For write BIOs to zoned devices, signal the completion of the BIO so * that the next write BIO can be submitted by zone write plugging. diff --git a/block/elevator.c b/block/elevator.c index e2ebfbf107b3af..a2f8b2251dc6e6 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -45,19 +45,6 @@ #include "blk-wbt.h" #include "blk-cgroup.h" -/* Holding context data for changing elevator */ -struct elv_change_ctx { - const char *name; - bool no_uevent; - - /* for unregistering old elevator */ - struct elevator_queue *old; - /* for registering new elevator */ - struct elevator_queue *new; - /* holds sched tags data */ - struct elevator_tags *et; -}; - static DEFINE_SPINLOCK(elv_list_lock); static LIST_HEAD(elv_list); @@ -134,7 +121,7 @@ static struct elevator_type *elevator_find_get(const char *name) static const struct kobj_type elv_ktype; struct elevator_queue *elevator_alloc(struct request_queue *q, - struct elevator_type *e, struct elevator_tags *et) + struct elevator_type *e, struct elevator_resources *res) { struct elevator_queue *eq; @@ -147,7 +134,8 @@ struct elevator_queue *elevator_alloc(struct request_queue *q, kobject_init(&eq->kobj, &elv_ktype); mutex_init(&eq->sysfs_lock); hash_init(eq->hash); - eq->et = et; + eq->et = res->et; + eq->elevator_data = res->data; return eq; } @@ -593,7 +581,7 @@ static int elevator_switch(struct request_queue *q, struct elv_change_ctx *ctx) } if (new_e) { - ret = blk_mq_init_sched(q, new_e, ctx->et); + ret = blk_mq_init_sched(q, new_e, &ctx->res); if (ret) goto out_unfreeze; ctx->new = q->elevator; @@ -617,7 +605,8 @@ static int elevator_switch(struct request_queue *q, struct elv_change_ctx *ctx) return ret; } -static void elv_exit_and_release(struct request_queue *q) +static void elv_exit_and_release(struct elv_change_ctx *ctx, + struct request_queue *q) { struct elevator_queue *e; unsigned memflags; @@ -629,7 +618,7 @@ static void elv_exit_and_release(struct request_queue *q) mutex_unlock(&q->elevator_lock); blk_mq_unfreeze_queue(q, memflags); if (e) { - blk_mq_free_sched_tags(e->et, q->tag_set); + blk_mq_free_sched_res(&ctx->res, ctx->type, q->tag_set); kobject_put(&e->kobj); } } @@ -640,19 +629,19 @@ static int elevator_change_done(struct request_queue *q, int ret = 0; if (ctx->old) { - bool enable_wbt = test_bit(ELEVATOR_FLAG_ENABLE_WBT_ON_EXIT, - &ctx->old->flags); + struct elevator_resources res = { + .et = ctx->old->et, + .data = ctx->old->elevator_data + }; elv_unregister_queue(q, ctx->old); - blk_mq_free_sched_tags(ctx->old->et, q->tag_set); + blk_mq_free_sched_res(&res, ctx->old->type, q->tag_set); kobject_put(&ctx->old->kobj); - if (enable_wbt) - wbt_enable_default(q->disk); } if (ctx->new) { ret = elv_register_queue(q, ctx->new, !ctx->no_uevent); if (ret) - elv_exit_and_release(q); + elv_exit_and_release(ctx, q); } return ret; } @@ -669,10 +658,10 @@ static int elevator_change(struct request_queue *q, struct elv_change_ctx *ctx) lockdep_assert_held(&set->update_nr_hwq_lock); if (strncmp(ctx->name, "none", 4)) { - ctx->et = blk_mq_alloc_sched_tags(set, set->nr_hw_queues, - blk_mq_default_nr_requests(set)); - if (!ctx->et) - return -ENOMEM; + ret = blk_mq_alloc_sched_res(q, ctx->type, &ctx->res, + set->nr_hw_queues); + if (ret) + return ret; } memflags = blk_mq_freeze_queue(q); @@ -693,11 +682,12 @@ static int elevator_change(struct request_queue *q, struct elv_change_ctx *ctx) blk_mq_unfreeze_queue(q, memflags); if (!ret) ret = elevator_change_done(q, ctx); + /* - * Free sched tags if it's allocated but we couldn't switch elevator. + * Free sched resource if it's allocated but we couldn't switch elevator. */ - if (ctx->et && !ctx->new) - blk_mq_free_sched_tags(ctx->et, set); + if (!ctx->new) + blk_mq_free_sched_res(&ctx->res, ctx->type, set); return ret; } @@ -706,32 +696,29 @@ static int elevator_change(struct request_queue *q, struct elv_change_ctx *ctx) * The I/O scheduler depends on the number of hardware queues, this forces a * reattachment when nr_hw_queues changes. */ -void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e, - struct elevator_tags *t) +void elv_update_nr_hw_queues(struct request_queue *q, + struct elv_change_ctx *ctx) { struct blk_mq_tag_set *set = q->tag_set; - struct elv_change_ctx ctx = {}; int ret = -ENODEV; WARN_ON_ONCE(q->mq_freeze_depth == 0); - if (e && !blk_queue_dying(q) && blk_queue_registered(q)) { - ctx.name = e->elevator_name; - ctx.et = t; - + if (ctx->type && !blk_queue_dying(q) && blk_queue_registered(q)) { mutex_lock(&q->elevator_lock); /* force to reattach elevator after nr_hw_queue is updated */ - ret = elevator_switch(q, &ctx); + ret = elevator_switch(q, ctx); mutex_unlock(&q->elevator_lock); } blk_mq_unfreeze_queue_nomemrestore(q); if (!ret) - WARN_ON_ONCE(elevator_change_done(q, &ctx)); + WARN_ON_ONCE(elevator_change_done(q, ctx)); + /* - * Free sched tags if it's allocated but we couldn't switch elevator. + * Free sched resource if it's allocated but we couldn't switch elevator. */ - if (t && !ctx.new) - blk_mq_free_sched_tags(t, set); + if (!ctx->new) + blk_mq_free_sched_res(&ctx->res, ctx->type, set); } /* @@ -745,7 +732,6 @@ void elevator_set_default(struct request_queue *q) .no_uevent = true, }; int err; - struct elevator_type *e; /* now we allow to switch elevator */ blk_queue_flag_clear(QUEUE_FLAG_NO_ELV_SWITCH, q); @@ -758,8 +744,8 @@ void elevator_set_default(struct request_queue *q) * have multiple queues or mq-deadline is not available, default * to "none". */ - e = elevator_find_get(ctx.name); - if (!e) + ctx.type = elevator_find_get(ctx.name); + if (!ctx.type) return; if ((q->nr_hw_queues == 1 || @@ -769,7 +755,7 @@ void elevator_set_default(struct request_queue *q) pr_warn("\"%s\" elevator initialization, failed %d, falling back to \"none\"\n", ctx.name, err); } - elevator_put(e); + elevator_put(ctx.type); } void elevator_set_none(struct request_queue *q) @@ -818,6 +804,7 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf, ctx.name = strstrip(elevator_name); elv_iosched_load_module(ctx.name); + ctx.type = elevator_find_get(ctx.name); down_read(&set->update_nr_hwq_lock); if (!blk_queue_no_elv_switch(q)) { @@ -828,6 +815,9 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf, ret = -ENOENT; } up_read(&set->update_nr_hwq_lock); + + if (ctx.type) + elevator_put(ctx.type); return ret; } diff --git a/block/elevator.h b/block/elevator.h index c4d20155065e80..02172637604234 100644 --- a/block/elevator.h +++ b/block/elevator.h @@ -32,12 +32,36 @@ struct elevator_tags { struct blk_mq_tags *tags[]; }; +struct elevator_resources { + /* holds elevator data */ + void *data; + /* holds elevator tags */ + struct elevator_tags *et; +}; + +/* Holding context data for changing elevator */ +struct elv_change_ctx { + const char *name; + bool no_uevent; + + /* for unregistering old elevator */ + struct elevator_queue *old; + /* for registering new elevator */ + struct elevator_queue *new; + /* store elevator type */ + struct elevator_type *type; + /* store elevator resources */ + struct elevator_resources res; +}; + struct elevator_mq_ops { int (*init_sched)(struct request_queue *, struct elevator_queue *); void (*exit_sched)(struct elevator_queue *); int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int); void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); void (*depth_updated)(struct request_queue *); + void *(*alloc_sched_data)(struct request_queue *); + void (*free_sched_data)(void *); bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); bool (*bio_merge)(struct request_queue *, struct bio *, unsigned int); @@ -132,7 +156,6 @@ struct elevator_queue #define ELEVATOR_FLAG_REGISTERED 0 #define ELEVATOR_FLAG_DYING 1 -#define ELEVATOR_FLAG_ENABLE_WBT_ON_EXIT 2 /* * block elevator interface @@ -163,7 +186,7 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *page, size_t count); extern bool elv_bio_merge_ok(struct request *, struct bio *); struct elevator_queue *elevator_alloc(struct request_queue *, - struct elevator_type *, struct elevator_tags *); + struct elevator_type *, struct elevator_resources *); /* * Helper functions. diff --git a/block/genhd.c b/block/genhd.c index 9bbc38d1279266..bd3a6841e5b59a 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -90,7 +90,7 @@ bool set_capacity_and_notify(struct gendisk *disk, sector_t size) (disk->flags & GENHD_FL_HIDDEN)) return false; - pr_info("%s: detected capacity change from %lld to %lld\n", + pr_info_ratelimited("%s: detected capacity change from %lld to %lld\n", disk->disk_name, capacity, size); /* diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 3e741d33142d3a..3e3719093aec72 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -71,7 +71,6 @@ struct io_stats_per_prio { * present on both sort_list[] and fifo_list[]. */ struct dd_per_prio { - struct list_head dispatch; struct rb_root sort_list[DD_DIR_COUNT]; struct list_head fifo_list[DD_DIR_COUNT]; /* Position of the most recently dispatched request. */ @@ -84,6 +83,7 @@ struct deadline_data { * run time data */ + struct list_head dispatch; struct dd_per_prio per_prio[DD_PRIO_COUNT]; /* Data direction of latest dispatched request. */ @@ -306,6 +306,19 @@ static bool started_after(struct deadline_data *dd, struct request *rq, return time_after(start_time, latest_start); } +static struct request *dd_start_request(struct deadline_data *dd, + enum dd_data_dir data_dir, + struct request *rq) +{ + u8 ioprio_class = dd_rq_ioclass(rq); + enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; + + dd->per_prio[prio].latest_pos[data_dir] = blk_rq_pos(rq); + dd->per_prio[prio].stats.dispatched++; + rq->rq_flags |= RQF_STARTED; + return rq; +} + /* * deadline_dispatch_requests selects the best request according to * read/write expire, fifo_batch, etc and with a start time <= @latest_start. @@ -316,21 +329,9 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd, { struct request *rq, *next_rq; enum dd_data_dir data_dir; - enum dd_prio prio; - u8 ioprio_class; lockdep_assert_held(&dd->lock); - if (!list_empty(&per_prio->dispatch)) { - rq = list_first_entry(&per_prio->dispatch, struct request, - queuelist); - if (started_after(dd, rq, latest_start)) - return NULL; - list_del_init(&rq->queuelist); - data_dir = rq_data_dir(rq); - goto done; - } - /* * batches are currently reads XOR writes */ @@ -410,13 +411,7 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd, */ dd->batching++; deadline_move_request(dd, per_prio, rq); -done: - ioprio_class = dd_rq_ioclass(rq); - prio = ioprio_class_to_prio[ioprio_class]; - dd->per_prio[prio].latest_pos[data_dir] = blk_rq_pos(rq); - dd->per_prio[prio].stats.dispatched++; - rq->rq_flags |= RQF_STARTED; - return rq; + return dd_start_request(dd, data_dir, rq); } /* @@ -463,6 +458,14 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx) enum dd_prio prio; spin_lock(&dd->lock); + + if (!list_empty(&dd->dispatch)) { + rq = list_first_entry(&dd->dispatch, struct request, queuelist); + list_del_init(&rq->queuelist); + dd_start_request(dd, rq_data_dir(rq), rq); + goto unlock; + } + rq = dd_dispatch_prio_aged_requests(dd, now); if (rq) goto unlock; @@ -551,10 +554,10 @@ static int dd_init_sched(struct request_queue *q, struct elevator_queue *eq) eq->elevator_data = dd; + INIT_LIST_HEAD(&dd->dispatch); for (prio = 0; prio <= DD_PRIO_MAX; prio++) { struct dd_per_prio *per_prio = &dd->per_prio[prio]; - INIT_LIST_HEAD(&per_prio->dispatch); INIT_LIST_HEAD(&per_prio->fifo_list[DD_READ]); INIT_LIST_HEAD(&per_prio->fifo_list[DD_WRITE]); per_prio->sort_list[DD_READ] = RB_ROOT; @@ -658,7 +661,7 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, trace_block_rq_insert(rq); if (flags & BLK_MQ_INSERT_AT_HEAD) { - list_add(&rq->queuelist, &per_prio->dispatch); + list_add(&rq->queuelist, &dd->dispatch); rq->fifo_time = jiffies; } else { deadline_add_rq_rb(per_prio, rq); @@ -725,8 +728,7 @@ static void dd_finish_request(struct request *rq) static bool dd_has_work_for_prio(struct dd_per_prio *per_prio) { - return !list_empty_careful(&per_prio->dispatch) || - !list_empty_careful(&per_prio->fifo_list[DD_READ]) || + return !list_empty_careful(&per_prio->fifo_list[DD_READ]) || !list_empty_careful(&per_prio->fifo_list[DD_WRITE]); } @@ -735,6 +737,9 @@ static bool dd_has_work(struct blk_mq_hw_ctx *hctx) struct deadline_data *dd = hctx->queue->elevator->elevator_data; enum dd_prio prio; + if (!list_empty_careful(&dd->dispatch)) + return true; + for (prio = 0; prio <= DD_PRIO_MAX; prio++) if (dd_has_work_for_prio(&dd->per_prio[prio])) return true; @@ -943,49 +948,39 @@ static int dd_owned_by_driver_show(void *data, struct seq_file *m) return 0; } -#define DEADLINE_DISPATCH_ATTR(prio) \ -static void *deadline_dispatch##prio##_start(struct seq_file *m, \ - loff_t *pos) \ - __acquires(&dd->lock) \ -{ \ - struct request_queue *q = m->private; \ - struct deadline_data *dd = q->elevator->elevator_data; \ - struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ - \ - spin_lock(&dd->lock); \ - return seq_list_start(&per_prio->dispatch, *pos); \ -} \ - \ -static void *deadline_dispatch##prio##_next(struct seq_file *m, \ - void *v, loff_t *pos) \ -{ \ - struct request_queue *q = m->private; \ - struct deadline_data *dd = q->elevator->elevator_data; \ - struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ - \ - return seq_list_next(v, &per_prio->dispatch, pos); \ -} \ - \ -static void deadline_dispatch##prio##_stop(struct seq_file *m, void *v) \ - __releases(&dd->lock) \ -{ \ - struct request_queue *q = m->private; \ - struct deadline_data *dd = q->elevator->elevator_data; \ - \ - spin_unlock(&dd->lock); \ -} \ - \ -static const struct seq_operations deadline_dispatch##prio##_seq_ops = { \ - .start = deadline_dispatch##prio##_start, \ - .next = deadline_dispatch##prio##_next, \ - .stop = deadline_dispatch##prio##_stop, \ - .show = blk_mq_debugfs_rq_show, \ +static void *deadline_dispatch_start(struct seq_file *m, loff_t *pos) + __acquires(&dd->lock) +{ + struct request_queue *q = m->private; + struct deadline_data *dd = q->elevator->elevator_data; + + spin_lock(&dd->lock); + return seq_list_start(&dd->dispatch, *pos); +} + +static void *deadline_dispatch_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct request_queue *q = m->private; + struct deadline_data *dd = q->elevator->elevator_data; + + return seq_list_next(v, &dd->dispatch, pos); +} + +static void deadline_dispatch_stop(struct seq_file *m, void *v) + __releases(&dd->lock) +{ + struct request_queue *q = m->private; + struct deadline_data *dd = q->elevator->elevator_data; + + spin_unlock(&dd->lock); } -DEADLINE_DISPATCH_ATTR(0); -DEADLINE_DISPATCH_ATTR(1); -DEADLINE_DISPATCH_ATTR(2); -#undef DEADLINE_DISPATCH_ATTR +static const struct seq_operations deadline_dispatch_seq_ops = { + .start = deadline_dispatch_start, + .next = deadline_dispatch_next, + .stop = deadline_dispatch_stop, + .show = blk_mq_debugfs_rq_show, +}; #define DEADLINE_QUEUE_DDIR_ATTRS(name) \ {#name "_fifo_list", 0400, \ @@ -1008,9 +1003,7 @@ static const struct blk_mq_debugfs_attr deadline_queue_debugfs_attrs[] = { {"batching", 0400, deadline_batching_show}, {"starved", 0400, deadline_starved_show}, {"async_depth", 0400, dd_async_depth_show}, - {"dispatch0", 0400, .seq_ops = &deadline_dispatch0_seq_ops}, - {"dispatch1", 0400, .seq_ops = &deadline_dispatch1_seq_ops}, - {"dispatch2", 0400, .seq_ops = &deadline_dispatch2_seq_ops}, + {"dispatch", 0400, .seq_ops = &deadline_dispatch_seq_ops}, {"owned_by_driver", 0400, dd_owned_by_driver_show}, {"queued", 0400, dd_queued_show}, {}, diff --git a/crypto/aead.c b/crypto/aead.c index 5d14b775036eeb..51ab3af691af25 100644 --- a/crypto/aead.c +++ b/crypto/aead.c @@ -120,6 +120,7 @@ static int crypto_aead_init_tfm(struct crypto_tfm *tfm) struct aead_alg *alg = crypto_aead_alg(aead); crypto_aead_set_flags(aead, CRYPTO_TFM_NEED_KEY); + crypto_aead_set_reqsize(aead, crypto_tfm_alg_reqsize(tfm)); aead->authsize = alg->maxauthsize; diff --git a/crypto/af_alg.c b/crypto/af_alg.c index ca6fdcc6c54aca..6c271e55f44d94 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -1212,15 +1212,14 @@ struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk, if (unlikely(!areq)) return ERR_PTR(-ENOMEM); + memset(areq, 0, areqlen); + ctx->inflight = true; areq->areqlen = areqlen; areq->sk = sk; areq->first_rsgl.sgl.sgt.sgl = areq->first_rsgl.sgl.sgl; - areq->last_rsgl = NULL; INIT_LIST_HEAD(&areq->rsgl_list); - areq->tsgl = NULL; - areq->tsgl_entries = 0; return areq; } diff --git a/crypto/ahash.c b/crypto/ahash.c index dfb4f5476428fc..66492ae75fcfb6 100644 --- a/crypto/ahash.c +++ b/crypto/ahash.c @@ -423,7 +423,11 @@ static int ahash_update_finish(struct ahash_request *req, int err) req->nbytes += nonzero - blen; - blen = err < 0 ? 0 : err + nonzero; + blen = 0; + if (err >= 0) { + blen = err + nonzero; + err = 0; + } if (ahash_request_isvirt(req)) memcpy(buf, req->svirt + req->nbytes - blen, blen); else @@ -661,6 +665,12 @@ int crypto_ahash_import_core(struct ahash_request *req, const void *in) in); if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; + if (crypto_ahash_block_only(tfm)) { + unsigned int reqsize = crypto_ahash_reqsize(tfm); + u8 *buf = ahash_request_ctx(req); + + buf[reqsize - 1] = 0; + } return crypto_ahash_alg(tfm)->import_core(req, in); } EXPORT_SYMBOL_GPL(crypto_ahash_import_core); @@ -674,10 +684,14 @@ int crypto_ahash_import(struct ahash_request *req, const void *in) if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; if (crypto_ahash_block_only(tfm)) { + unsigned int plen = crypto_ahash_blocksize(tfm) + 1; unsigned int reqsize = crypto_ahash_reqsize(tfm); + unsigned int ss = crypto_ahash_statesize(tfm); u8 *buf = ahash_request_ctx(req); - buf[reqsize - 1] = 0; + memcpy(buf + reqsize - plen, in + ss - plen, plen); + if (buf[reqsize - 1] >= plen) + return -EOVERFLOW; } return crypto_ahash_alg(tfm)->import(req, in); } diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index e3f1a4852737b0..4d3dfc60a16a6d 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -416,9 +416,8 @@ static int hash_accept_parent_nokey(void *private, struct sock *sk) if (!ctx) return -ENOMEM; - ctx->result = NULL; + memset(ctx, 0, len); ctx->len = len; - ctx->more = false; crypto_init_wait(&ctx->wait); ask->private = ctx; diff --git a/crypto/algif_rng.c b/crypto/algif_rng.c index 10c41adac3b1f3..1a86e40c8372e5 100644 --- a/crypto/algif_rng.c +++ b/crypto/algif_rng.c @@ -248,9 +248,8 @@ static int rng_accept_parent(void *private, struct sock *sk) if (!ctx) return -ENOMEM; + memset(ctx, 0, len); ctx->len = len; - ctx->addtl = NULL; - ctx->addtl_len = 0; /* * No seeding done at that point -- if multiple accepts are diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c index ba2d9d1ea235a7..348966ea2175c9 100644 --- a/crypto/asymmetric_keys/asymmetric_type.c +++ b/crypto/asymmetric_keys/asymmetric_type.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -141,12 +142,17 @@ struct asymmetric_key_id *asymmetric_key_generate_id(const void *val_1, size_t len_2) { struct asymmetric_key_id *kid; - - kid = kmalloc(sizeof(struct asymmetric_key_id) + len_1 + len_2, - GFP_KERNEL); + size_t kid_sz; + size_t len; + + if (check_add_overflow(len_1, len_2, &len)) + return ERR_PTR(-EOVERFLOW); + if (check_add_overflow(sizeof(struct asymmetric_key_id), len, &kid_sz)) + return ERR_PTR(-EOVERFLOW); + kid = kmalloc(kid_sz, GFP_KERNEL); if (!kid) return ERR_PTR(-ENOMEM); - kid->len = len_1 + len_2; + kid->len = len; memcpy(kid->data, val_1, len_1); memcpy(kid->data + len_1, val_2, len_2); return kid; diff --git a/crypto/authenc.c b/crypto/authenc.c index a723769c87779d..ac679ce2cb9533 100644 --- a/crypto/authenc.c +++ b/crypto/authenc.c @@ -37,7 +37,7 @@ struct authenc_request_ctx { static void authenc_request_complete(struct aead_request *req, int err) { - if (err != -EINPROGRESS) + if (err != -EINPROGRESS && err != -EBUSY) aead_request_complete(req, err); } @@ -107,27 +107,42 @@ static int crypto_authenc_setkey(struct crypto_aead *authenc, const u8 *key, return err; } -static void authenc_geniv_ahash_done(void *data, int err) +static void authenc_geniv_ahash_finish(struct aead_request *req) { - struct aead_request *req = data; struct crypto_aead *authenc = crypto_aead_reqtfm(req); struct aead_instance *inst = aead_alg_instance(authenc); struct authenc_instance_ctx *ictx = aead_instance_ctx(inst); struct authenc_request_ctx *areq_ctx = aead_request_ctx(req); struct ahash_request *ahreq = (void *)(areq_ctx->tail + ictx->reqoff); - if (err) - goto out; - scatterwalk_map_and_copy(ahreq->result, req->dst, req->assoclen + req->cryptlen, crypto_aead_authsize(authenc), 1); +} -out: +static void authenc_geniv_ahash_done(void *data, int err) +{ + struct aead_request *req = data; + + if (!err) + authenc_geniv_ahash_finish(req); aead_request_complete(req, err); } -static int crypto_authenc_genicv(struct aead_request *req, unsigned int flags) +/* + * Used when the ahash request was invoked in the async callback context + * of the previous skcipher request. Eat any EINPROGRESS notifications. + */ +static void authenc_geniv_ahash_done2(void *data, int err) +{ + struct aead_request *req = data; + + if (!err) + authenc_geniv_ahash_finish(req); + authenc_request_complete(req, err); +} + +static int crypto_authenc_genicv(struct aead_request *req, unsigned int mask) { struct crypto_aead *authenc = crypto_aead_reqtfm(req); struct aead_instance *inst = aead_alg_instance(authenc); @@ -136,6 +151,7 @@ static int crypto_authenc_genicv(struct aead_request *req, unsigned int flags) struct crypto_ahash *auth = ctx->auth; struct authenc_request_ctx *areq_ctx = aead_request_ctx(req); struct ahash_request *ahreq = (void *)(areq_ctx->tail + ictx->reqoff); + unsigned int flags = aead_request_flags(req) & ~mask; u8 *hash = areq_ctx->tail; int err; @@ -143,7 +159,8 @@ static int crypto_authenc_genicv(struct aead_request *req, unsigned int flags) ahash_request_set_crypt(ahreq, req->dst, hash, req->assoclen + req->cryptlen); ahash_request_set_callback(ahreq, flags, - authenc_geniv_ahash_done, req); + mask ? authenc_geniv_ahash_done2 : + authenc_geniv_ahash_done, req); err = crypto_ahash_digest(ahreq); if (err) @@ -159,12 +176,11 @@ static void crypto_authenc_encrypt_done(void *data, int err) { struct aead_request *areq = data; - if (err) - goto out; - - err = crypto_authenc_genicv(areq, 0); - -out: + if (err) { + aead_request_complete(areq, err); + return; + } + err = crypto_authenc_genicv(areq, CRYPTO_TFM_REQ_MAY_SLEEP); authenc_request_complete(areq, err); } @@ -199,11 +215,18 @@ static int crypto_authenc_encrypt(struct aead_request *req) if (err) return err; - return crypto_authenc_genicv(req, aead_request_flags(req)); + return crypto_authenc_genicv(req, 0); +} + +static void authenc_decrypt_tail_done(void *data, int err) +{ + struct aead_request *req = data; + + authenc_request_complete(req, err); } static int crypto_authenc_decrypt_tail(struct aead_request *req, - unsigned int flags) + unsigned int mask) { struct crypto_aead *authenc = crypto_aead_reqtfm(req); struct aead_instance *inst = aead_alg_instance(authenc); @@ -214,6 +237,7 @@ static int crypto_authenc_decrypt_tail(struct aead_request *req, struct skcipher_request *skreq = (void *)(areq_ctx->tail + ictx->reqoff); unsigned int authsize = crypto_aead_authsize(authenc); + unsigned int flags = aead_request_flags(req) & ~mask; u8 *ihash = ahreq->result + authsize; struct scatterlist *src, *dst; @@ -230,7 +254,9 @@ static int crypto_authenc_decrypt_tail(struct aead_request *req, skcipher_request_set_tfm(skreq, ctx->enc); skcipher_request_set_callback(skreq, flags, - req->base.complete, req->base.data); + mask ? authenc_decrypt_tail_done : + req->base.complete, + mask ? req : req->base.data); skcipher_request_set_crypt(skreq, src, dst, req->cryptlen - authsize, req->iv); @@ -241,12 +267,11 @@ static void authenc_verify_ahash_done(void *data, int err) { struct aead_request *req = data; - if (err) - goto out; - - err = crypto_authenc_decrypt_tail(req, 0); - -out: + if (err) { + aead_request_complete(req, err); + return; + } + err = crypto_authenc_decrypt_tail(req, CRYPTO_TFM_REQ_MAY_SLEEP); authenc_request_complete(req, err); } @@ -273,7 +298,7 @@ static int crypto_authenc_decrypt(struct aead_request *req) if (err) return err; - return crypto_authenc_decrypt_tail(req, aead_request_flags(req)); + return crypto_authenc_decrypt_tail(req, 0); } static int crypto_authenc_init_tfm(struct crypto_aead *tfm) diff --git a/crypto/authencesn.c b/crypto/authencesn.c index d1bf0fda3f2ef6..542a978663b9e7 100644 --- a/crypto/authencesn.c +++ b/crypto/authencesn.c @@ -169,6 +169,9 @@ static int crypto_authenc_esn_encrypt(struct aead_request *req) struct scatterlist *src, *dst; int err; + if (assoclen < 8) + return -EINVAL; + sg_init_table(areq_ctx->src, 2); src = scatterwalk_ffwd(areq_ctx->src, req->src, assoclen); dst = src; @@ -256,6 +259,9 @@ static int crypto_authenc_esn_decrypt(struct aead_request *req) u32 tmp[2]; int err; + if (assoclen < 8) + return -EINVAL; + cryptlen -= authsize; if (req->src != dst) diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c index 1d010e2a1b1a2e..b95e5974e327bf 100644 --- a/crypto/scatterwalk.c +++ b/crypto/scatterwalk.c @@ -101,26 +101,97 @@ void memcpy_to_sglist(struct scatterlist *sg, unsigned int start, } EXPORT_SYMBOL_GPL(memcpy_to_sglist); +/** + * memcpy_sglist() - Copy data from one scatterlist to another + * @dst: The destination scatterlist. Can be NULL if @nbytes == 0. + * @src: The source scatterlist. Can be NULL if @nbytes == 0. + * @nbytes: Number of bytes to copy + * + * The scatterlists can describe exactly the same memory, in which case this + * function is a no-op. No other overlaps are supported. + * + * Context: Any context + */ void memcpy_sglist(struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes) { - struct skcipher_walk walk = {}; + unsigned int src_offset, dst_offset; - if (unlikely(nbytes == 0)) /* in case sg == NULL */ + if (unlikely(nbytes == 0)) /* in case src and/or dst is NULL */ return; - walk.total = nbytes; - - scatterwalk_start(&walk.in, src); - scatterwalk_start(&walk.out, dst); + src_offset = src->offset; + dst_offset = dst->offset; + for (;;) { + /* Compute the length to copy this step. */ + unsigned int len = min3(src->offset + src->length - src_offset, + dst->offset + dst->length - dst_offset, + nbytes); + struct page *src_page = sg_page(src); + struct page *dst_page = sg_page(dst); + const void *src_virt; + void *dst_virt; + + if (IS_ENABLED(CONFIG_HIGHMEM)) { + /* HIGHMEM: we may have to actually map the pages. */ + const unsigned int src_oip = offset_in_page(src_offset); + const unsigned int dst_oip = offset_in_page(dst_offset); + const unsigned int limit = PAGE_SIZE; + + /* Further limit len to not cross a page boundary. */ + len = min3(len, limit - src_oip, limit - dst_oip); + + /* Compute the source and destination pages. */ + src_page += src_offset / PAGE_SIZE; + dst_page += dst_offset / PAGE_SIZE; + + if (src_page != dst_page) { + /* Copy between different pages. */ + memcpy_page(dst_page, dst_oip, + src_page, src_oip, len); + flush_dcache_page(dst_page); + } else if (src_oip != dst_oip) { + /* Copy between different parts of same page. */ + dst_virt = kmap_local_page(dst_page); + memcpy(dst_virt + dst_oip, dst_virt + src_oip, + len); + kunmap_local(dst_virt); + flush_dcache_page(dst_page); + } /* Else, it's the same memory. No action needed. */ + } else { + /* + * !HIGHMEM: no mapping needed. Just work in the linear + * buffer of each sg entry. Note that we can cross page + * boundaries, as they are not significant in this case. + */ + src_virt = page_address(src_page) + src_offset; + dst_virt = page_address(dst_page) + dst_offset; + if (src_virt != dst_virt) { + memcpy(dst_virt, src_virt, len); + if (ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE) + __scatterwalk_flush_dcache_pages( + dst_page, dst_offset, len); + } /* Else, it's the same memory. No action needed. */ + } + nbytes -= len; + if (nbytes == 0) /* No more to copy? */ + break; - skcipher_walk_first(&walk, true); - do { - if (walk.src.virt.addr != walk.dst.virt.addr) - memcpy(walk.dst.virt.addr, walk.src.virt.addr, - walk.nbytes); - skcipher_walk_done(&walk, 0); - } while (walk.nbytes); + /* + * There's more to copy. Advance the offsets by the length + * copied this step, and advance the sg entries as needed. + */ + src_offset += len; + if (src_offset >= src->offset + src->length) { + src = sg_next(src); + src_offset = src->offset; + } + dst_offset += len; + if (dst_offset >= dst->offset + dst->length) { + dst = sg_next(dst); + dst_offset = dst->offset; + } + } } EXPORT_SYMBOL_GPL(memcpy_sglist); diff --git a/crypto/seqiv.c b/crypto/seqiv.c index 2bae99e3352683..678bb4145d783a 100644 --- a/crypto/seqiv.c +++ b/crypto/seqiv.c @@ -50,6 +50,7 @@ static int seqiv_aead_encrypt(struct aead_request *req) struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv); struct aead_request *subreq = aead_request_ctx(req); crypto_completion_t compl; + bool unaligned_info; void *data; u8 *info; unsigned int ivsize = 8; @@ -68,8 +69,9 @@ static int seqiv_aead_encrypt(struct aead_request *req) memcpy_sglist(req->dst, req->src, req->assoclen + req->cryptlen); - if (unlikely(!IS_ALIGNED((unsigned long)info, - crypto_aead_alignmask(geniv) + 1))) { + unaligned_info = !IS_ALIGNED((unsigned long)info, + crypto_aead_alignmask(geniv) + 1); + if (unlikely(unaligned_info)) { info = kmemdup(req->iv, ivsize, req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : GFP_ATOMIC); @@ -89,7 +91,7 @@ static int seqiv_aead_encrypt(struct aead_request *req) scatterwalk_map_and_copy(info, req->dst, req->assoclen, ivsize, 1); err = crypto_aead_encrypt(subreq); - if (unlikely(info != req->iv)) + if (unlikely(unaligned_info)) seqiv_aead_encrypt_complete2(req, err); return err; } diff --git a/crypto/zstd.c b/crypto/zstd.c index ac318d333b6847..32a339b74f34cf 100644 --- a/crypto/zstd.c +++ b/crypto/zstd.c @@ -75,11 +75,6 @@ static int zstd_init(struct crypto_acomp *acomp_tfm) return ret; } -static void zstd_exit(struct crypto_acomp *acomp_tfm) -{ - crypto_acomp_free_streams(&zstd_streams); -} - static int zstd_compress_one(struct acomp_req *req, struct zstd_ctx *ctx, const void *src, void *dst, unsigned int *dlen) { @@ -297,7 +292,6 @@ static struct acomp_alg zstd_acomp = { .cra_module = THIS_MODULE, }, .init = zstd_init, - .exit = zstd_exit, .compress = zstd_compress, .decompress = zstd_decompress, }; @@ -310,6 +304,7 @@ static int __init zstd_mod_init(void) static void __exit zstd_mod_fini(void) { crypto_unregister_acomp(&zstd_acomp); + crypto_acomp_free_streams(&zstd_streams); } module_init(zstd_mod_init); diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index e9f9b1fa5dc1b1..4610f491f0881c 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -189,7 +189,6 @@ aie2_sched_notify(struct amdxdna_sched_job *job) up(&job->hwctx->priv->job_sem); job->job_done = true; - dma_fence_put(fence); mmput_async(job->mm); aie2_job_put(job); } @@ -204,10 +203,13 @@ aie2_sched_resp_handler(void *handle, void __iomem *data, size_t size) cmd_abo = job->cmd_bo; - if (unlikely(!data)) + if (unlikely(job->job_timeout)) { + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_TIMEOUT); + ret = -EINVAL; goto out; + } - if (unlikely(size != sizeof(u32))) { + if (unlikely(!data) || unlikely(size != sizeof(u32))) { amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT); ret = -EINVAL; goto out; @@ -260,6 +262,13 @@ aie2_sched_cmdlist_resp_handler(void *handle, void __iomem *data, size_t size) int ret = 0; cmd_abo = job->cmd_bo; + + if (unlikely(job->job_timeout)) { + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_TIMEOUT); + ret = -EINVAL; + goto out; + } + if (unlikely(!data) || unlikely(size != sizeof(u32) * 3)) { amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT); ret = -EINVAL; @@ -285,7 +294,7 @@ aie2_sched_cmdlist_resp_handler(void *handle, void __iomem *data, size_t size) ret = -EINVAL; goto out; } - amdxdna_cmd_set_state(cmd_abo, fail_cmd_status); + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ERROR); if (amdxdna_cmd_get_op(cmd_abo) == ERT_CMD_CHAIN) { struct amdxdna_cmd_chain *cc = amdxdna_cmd_get_payload(cmd_abo, NULL); @@ -308,6 +317,9 @@ aie2_sched_job_run(struct drm_sched_job *sched_job) struct dma_fence *fence; int ret; + if (hwctx->status != HWCTX_STAT_READY) + return NULL; + if (!mmget_not_zero(job->mm)) return ERR_PTR(-ESRCH); @@ -362,6 +374,7 @@ aie2_sched_job_timedout(struct drm_sched_job *sched_job) xdna = hwctx->client->xdna; trace_xdna_job(sched_job, hwctx->name, "job timedout", job->seq); + job->job_timeout = true; mutex_lock(&xdna->dev_lock); aie2_hwctx_stop(xdna, hwctx, sched_job); @@ -671,17 +684,22 @@ void aie2_hwctx_fini(struct amdxdna_hwctx *hwctx) ndev->hwctx_num--; XDNA_DBG(xdna, "%s sequence number %lld", hwctx->name, hwctx->priv->seq); - drm_sched_entity_destroy(&hwctx->priv->entity); - aie2_hwctx_wait_for_idle(hwctx); /* Request fw to destroy hwctx and cancel the rest pending requests */ + drm_sched_stop(&hwctx->priv->sched, NULL); aie2_release_resource(hwctx); + hwctx->status = HWCTX_STAT_STOP; + drm_sched_start(&hwctx->priv->sched, 0); + + mutex_unlock(&xdna->dev_lock); + drm_sched_entity_destroy(&hwctx->priv->entity); /* Wait for all submitted jobs to be completed or canceled */ wait_event(hwctx->priv->job_free_wq, atomic64_read(&hwctx->job_submit_cnt) == atomic64_read(&hwctx->job_free_cnt)); + mutex_lock(&xdna->dev_lock); drm_sched_fini(&hwctx->priv->sched); aie2_ctx_syncobj_destroy(hwctx); diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c index 87c425e3d2b99c..6e07793bbeacf8 100644 --- a/drivers/accel/amdxdna/aie2_pci.c +++ b/drivers/accel/amdxdna/aie2_pci.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "aie2_msg_priv.h" #include "aie2_pci.h" @@ -486,6 +487,11 @@ static int aie2_init(struct amdxdna_dev *xdna) unsigned long bars = 0; int i, nvec, ret; + if (!hypervisor_is_type(X86_HYPER_NATIVE)) { + XDNA_ERR(xdna, "Running under hypervisor not supported"); + return -EINVAL; + } + ndev = drmm_kzalloc(&xdna->ddev, sizeof(*ndev), GFP_KERNEL); if (!ndev) return -ENOMEM; @@ -845,7 +851,7 @@ static int aie2_get_hwctx_status(struct amdxdna_client *client, } args->buffer_size -= (u32)(array_args.buffer - args->buffer); - return ret; + return 0; } static int aie2_get_info(struct amdxdna_client *client, struct amdxdna_drm_get_info *args) @@ -898,6 +904,12 @@ static int aie2_query_ctx_status_array(struct amdxdna_client *client, drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + if (args->element_size > SZ_4K || args->num_element > SZ_1K) { + XDNA_DBG(xdna, "Invalid element size %d or number of element %d", + args->element_size, args->num_element); + return -EINVAL; + } + array_args.element_size = min(args->element_size, sizeof(struct amdxdna_drm_hwctx_entry)); array_args.buffer = args->buffer; @@ -914,7 +926,7 @@ static int aie2_query_ctx_status_array(struct amdxdna_client *client, args->num_element = (u32)((array_args.buffer - args->buffer) / args->element_size); - return ret; + return 0; } static int aie2_get_array(struct amdxdna_client *client, diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c index 4bfe4ef20550ff..856fb25086f126 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.c +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -389,6 +389,7 @@ void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job) trace_amdxdna_debug_point(job->hwctx->name, job->seq, "job release"); amdxdna_arg_bos_put(job); amdxdna_gem_put_obj(job->cmd_bo); + dma_fence_put(job->fence); } int amdxdna_cmd_submit(struct amdxdna_client *client, diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h index 7cd7a55936f099..8c1d181df6e794 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.h +++ b/drivers/accel/amdxdna/amdxdna_ctx.h @@ -105,6 +105,7 @@ struct amdxdna_sched_job { /* user can wait on this fence */ struct dma_fence *out_fence; bool job_done; + bool job_timeout; u64 seq; struct amdxdna_gem_obj *cmd_bo; size_t bo_cnt; diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c index d407a36eb41265..7f91863c3f24ce 100644 --- a/drivers/accel/amdxdna/amdxdna_gem.c +++ b/drivers/accel/amdxdna/amdxdna_gem.c @@ -392,35 +392,33 @@ static const struct dma_buf_ops amdxdna_dmabuf_ops = { .vunmap = drm_gem_dmabuf_vunmap, }; -static int amdxdna_gem_obj_vmap(struct drm_gem_object *obj, struct iosys_map *map) +static int amdxdna_gem_obj_vmap(struct amdxdna_gem_obj *abo, void **vaddr) { - struct amdxdna_gem_obj *abo = to_xdna_obj(obj); - - iosys_map_clear(map); - - dma_resv_assert_held(obj->resv); + struct iosys_map map = IOSYS_MAP_INIT_VADDR(NULL); + int ret; if (is_import_bo(abo)) - dma_buf_vmap(abo->dma_buf, map); + ret = dma_buf_vmap_unlocked(abo->dma_buf, &map); else - drm_gem_shmem_object_vmap(obj, map); - - if (!map->vaddr) - return -ENOMEM; + ret = drm_gem_vmap(to_gobj(abo), &map); - return 0; + *vaddr = map.vaddr; + return ret; } -static void amdxdna_gem_obj_vunmap(struct drm_gem_object *obj, struct iosys_map *map) +static void amdxdna_gem_obj_vunmap(struct amdxdna_gem_obj *abo) { - struct amdxdna_gem_obj *abo = to_xdna_obj(obj); + struct iosys_map map; + + if (!abo->mem.kva) + return; - dma_resv_assert_held(obj->resv); + iosys_map_set_vaddr(&map, abo->mem.kva); if (is_import_bo(abo)) - dma_buf_vunmap(abo->dma_buf, map); + dma_buf_vunmap_unlocked(abo->dma_buf, &map); else - drm_gem_shmem_object_vunmap(obj, map); + drm_gem_vunmap(to_gobj(abo), &map); } static struct dma_buf *amdxdna_gem_prime_export(struct drm_gem_object *gobj, int flags) @@ -455,7 +453,6 @@ static void amdxdna_gem_obj_free(struct drm_gem_object *gobj) { struct amdxdna_dev *xdna = to_xdna_dev(gobj->dev); struct amdxdna_gem_obj *abo = to_xdna_obj(gobj); - struct iosys_map map = IOSYS_MAP_INIT_VADDR(abo->mem.kva); XDNA_DBG(xdna, "BO type %d xdna_addr 0x%llx", abo->type, abo->mem.dev_addr); @@ -468,7 +465,7 @@ static void amdxdna_gem_obj_free(struct drm_gem_object *gobj) if (abo->type == AMDXDNA_BO_DEV_HEAP) drm_mm_takedown(&abo->mm); - drm_gem_vunmap(gobj, &map); + amdxdna_gem_obj_vunmap(abo); mutex_destroy(&abo->lock); if (is_import_bo(abo)) { @@ -489,8 +486,8 @@ static const struct drm_gem_object_funcs amdxdna_gem_shmem_funcs = { .pin = drm_gem_shmem_object_pin, .unpin = drm_gem_shmem_object_unpin, .get_sg_table = drm_gem_shmem_object_get_sg_table, - .vmap = amdxdna_gem_obj_vmap, - .vunmap = amdxdna_gem_obj_vunmap, + .vmap = drm_gem_shmem_object_vmap, + .vunmap = drm_gem_shmem_object_vunmap, .mmap = amdxdna_gem_obj_mmap, .vm_ops = &drm_gem_shmem_vm_ops, .export = amdxdna_gem_prime_export, @@ -663,7 +660,6 @@ amdxdna_drm_create_dev_heap(struct drm_device *dev, struct drm_file *filp) { struct amdxdna_client *client = filp->driver_priv; - struct iosys_map map = IOSYS_MAP_INIT_VADDR(NULL); struct amdxdna_dev *xdna = to_xdna_dev(dev); struct amdxdna_gem_obj *abo; int ret; @@ -692,12 +688,11 @@ amdxdna_drm_create_dev_heap(struct drm_device *dev, abo->mem.dev_addr = client->xdna->dev_info->dev_mem_base; drm_mm_init(&abo->mm, abo->mem.dev_addr, abo->mem.size); - ret = drm_gem_vmap(to_gobj(abo), &map); + ret = amdxdna_gem_obj_vmap(abo, &abo->mem.kva); if (ret) { XDNA_ERR(xdna, "Vmap heap bo failed, ret %d", ret); goto release_obj; } - abo->mem.kva = map.vaddr; client->dev_heap = abo; drm_gem_object_get(to_gobj(abo)); @@ -748,7 +743,6 @@ amdxdna_drm_create_cmd_bo(struct drm_device *dev, struct amdxdna_drm_create_bo *args, struct drm_file *filp) { - struct iosys_map map = IOSYS_MAP_INIT_VADDR(NULL); struct amdxdna_dev *xdna = to_xdna_dev(dev); struct amdxdna_gem_obj *abo; int ret; @@ -770,12 +764,11 @@ amdxdna_drm_create_cmd_bo(struct drm_device *dev, abo->type = AMDXDNA_BO_CMD; abo->client = filp->driver_priv; - ret = drm_gem_vmap(to_gobj(abo), &map); + ret = amdxdna_gem_obj_vmap(abo, &abo->mem.kva); if (ret) { XDNA_ERR(xdna, "Vmap cmd bo failed, ret %d", ret); goto release_obj; } - abo->mem.kva = map.vaddr; return abo; diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c index da1ac89bb78f1f..a80c77a478bff0 100644 --- a/drivers/accel/amdxdna/amdxdna_mailbox.c +++ b/drivers/accel/amdxdna/amdxdna_mailbox.c @@ -206,26 +206,34 @@ mailbox_send_msg(struct mailbox_channel *mb_chann, struct mailbox_msg *mb_msg) u32 head, tail; u32 start_addr; u32 tmp_tail; + int ret; head = mailbox_get_headptr(mb_chann, CHAN_RES_X2I); tail = mb_chann->x2i_tail; - ringbuf_size = mailbox_get_ringbuf_size(mb_chann, CHAN_RES_X2I); + ringbuf_size = mailbox_get_ringbuf_size(mb_chann, CHAN_RES_X2I) - sizeof(u32); start_addr = mb_chann->res[CHAN_RES_X2I].rb_start_addr; tmp_tail = tail + mb_msg->pkg_size; - if (tail < head && tmp_tail >= head) - goto no_space; - - if (tail >= head && (tmp_tail > ringbuf_size - sizeof(u32) && - mb_msg->pkg_size >= head)) - goto no_space; - if (tail >= head && tmp_tail > ringbuf_size - sizeof(u32)) { +check_again: + if (tail >= head && tmp_tail > ringbuf_size) { write_addr = mb_chann->mb->res.ringbuf_base + start_addr + tail; writel(TOMBSTONE, write_addr); /* tombstone is set. Write from the start of the ringbuf */ tail = 0; + tmp_tail = tail + mb_msg->pkg_size; + } + + if (tail < head && tmp_tail >= head) { + ret = read_poll_timeout(mailbox_get_headptr, head, + tmp_tail < head || tail >= head, + 1, 100, false, mb_chann, CHAN_RES_X2I); + if (ret) + return ret; + + if (tail >= head) + goto check_again; } write_addr = mb_chann->mb->res.ringbuf_base + start_addr + tail; @@ -237,9 +245,6 @@ mailbox_send_msg(struct mailbox_channel *mb_chann, struct mailbox_msg *mb_msg) mb_msg->pkg.header.id); return 0; - -no_space: - return -ENOSPC; } static int @@ -513,6 +518,7 @@ xdna_mailbox_create_channel(struct mailbox *mb, } mb_chann->bad_state = false; + mailbox_reg_write(mb_chann, mb_chann->iohub_int_addr, 0); MB_DBG(mb_chann, "Mailbox channel created (irq: %d)", mb_chann->msix_irq); return mb_chann; diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c index 569cd703729d3f..88643e28af84b9 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.c +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c @@ -88,6 +88,8 @@ static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp) ret = -ENODEV; goto unbind_sva; } + client->mm = current->mm; + mmgrab(client->mm); init_srcu_struct(&client->hwctx_srcu); xa_init_flags(&client->hwctx_xa, XA_FLAGS_ALLOC); mutex_init(&client->mm_lock); @@ -127,6 +129,7 @@ static void amdxdna_drm_close(struct drm_device *ddev, struct drm_file *filp) drm_gem_object_put(to_gobj(client->dev_heap)); iommu_sva_unbind_device(client->sva); + mmdrop(client->mm); XDNA_DBG(xdna, "pid %d closed", client->pid); kfree(client); @@ -292,7 +295,7 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id) fs_reclaim_release(GFP_KERNEL); } - xdna->notifier_wq = alloc_ordered_workqueue("notifier_wq", 0); + xdna->notifier_wq = alloc_ordered_workqueue("notifier_wq", WQ_MEM_RECLAIM); if (!xdna->notifier_wq) return -ENOMEM; diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h index 72d6696d49da81..64009ca2498271 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.h +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h @@ -128,6 +128,7 @@ struct amdxdna_client { struct iommu_sva *sva; int pasid; + struct mm_struct *mm; }; #define amdxdna_for_each_hwctx(client, hwctx_id, entry) \ diff --git a/drivers/accel/amdxdna/amdxdna_ubuf.c b/drivers/accel/amdxdna/amdxdna_ubuf.c index 077b2261cf2a04..9e3b3b055caa86 100644 --- a/drivers/accel/amdxdna/amdxdna_ubuf.c +++ b/drivers/accel/amdxdna/amdxdna_ubuf.c @@ -34,15 +34,21 @@ static struct sg_table *amdxdna_ubuf_map(struct dma_buf_attachment *attach, ret = sg_alloc_table_from_pages(sg, ubuf->pages, ubuf->nr_pages, 0, ubuf->nr_pages << PAGE_SHIFT, GFP_KERNEL); if (ret) - return ERR_PTR(ret); + goto err_free_sg; if (ubuf->flags & AMDXDNA_UBUF_FLAG_MAP_DMA) { ret = dma_map_sgtable(attach->dev, sg, direction, 0); if (ret) - return ERR_PTR(ret); + goto err_free_table; } return sg; + +err_free_table: + sg_free_table(sg); +err_free_sg: + kfree(sg); + return ERR_PTR(ret); } static void amdxdna_ubuf_unmap(struct dma_buf_attachment *attach, diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c index 59cfcf3eaded96..fda0a18e6d639b 100644 --- a/drivers/accel/ivpu/ivpu_gem.c +++ b/drivers/accel/ivpu/ivpu_gem.c @@ -27,8 +27,8 @@ static const struct drm_gem_object_funcs ivpu_gem_funcs; static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, const char *action) { ivpu_dbg(vdev, BO, - "%6s: bo %8p vpu_addr %9llx size %8zu ctx %d has_pages %d dma_mapped %d mmu_mapped %d wc %d imported %d\n", - action, bo, bo->vpu_addr, ivpu_bo_size(bo), bo->ctx_id, + "%6s: bo %8p size %9zu ctx %d vpu_addr %9llx pages %d sgt %d mmu_mapped %d wc %d imported %d\n", + action, bo, ivpu_bo_size(bo), bo->ctx_id, bo->vpu_addr, (bool)bo->base.pages, (bool)bo->base.sgt, bo->mmu_mapped, bo->base.map_wc, (bool)drm_gem_is_imported(&bo->base.base)); } @@ -43,22 +43,47 @@ static inline void ivpu_bo_unlock(struct ivpu_bo *bo) dma_resv_unlock(bo->base.base.resv); } +static struct sg_table *ivpu_bo_map_attachment(struct ivpu_device *vdev, struct ivpu_bo *bo) +{ + struct sg_table *sgt; + + drm_WARN_ON(&vdev->drm, !bo->base.base.import_attach); + + ivpu_bo_lock(bo); + + sgt = bo->base.sgt; + if (!sgt) { + sgt = dma_buf_map_attachment(bo->base.base.import_attach, DMA_BIDIRECTIONAL); + if (IS_ERR(sgt)) + ivpu_err(vdev, "Failed to map BO in IOMMU: %ld\n", PTR_ERR(sgt)); + else + bo->base.sgt = sgt; + } + + ivpu_bo_unlock(bo); + + return sgt; +} + /* - * ivpu_bo_pin() - pin the backing physical pages and map them to VPU. + * ivpu_bo_bind() - pin the backing physical pages and map them to VPU. * * This function pins physical memory pages, then maps the physical pages * to IOMMU address space and finally updates the VPU MMU page tables * to allow the VPU to translate VPU address to IOMMU address. */ -int __must_check ivpu_bo_pin(struct ivpu_bo *bo) +int __must_check ivpu_bo_bind(struct ivpu_bo *bo) { struct ivpu_device *vdev = ivpu_bo_to_vdev(bo); struct sg_table *sgt; int ret = 0; - ivpu_dbg_bo(vdev, bo, "pin"); + ivpu_dbg_bo(vdev, bo, "bind"); - sgt = drm_gem_shmem_get_pages_sgt(&bo->base); + if (bo->base.base.import_attach) + sgt = ivpu_bo_map_attachment(vdev, bo); + else + sgt = drm_gem_shmem_get_pages_sgt(&bo->base); if (IS_ERR(sgt)) { ret = PTR_ERR(sgt); ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret); @@ -99,7 +124,9 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx, ret = ivpu_mmu_context_insert_node(ctx, range, ivpu_bo_size(bo), &bo->mm_node); if (!ret) { bo->ctx = ctx; + bo->ctx_id = ctx->id; bo->vpu_addr = bo->mm_node.start; + ivpu_dbg_bo(vdev, bo, "vaddr"); } else { ivpu_err(vdev, "Failed to add BO to context %u: %d\n", ctx->id, ret); } @@ -115,7 +142,7 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo) { struct ivpu_device *vdev = ivpu_bo_to_vdev(bo); - lockdep_assert(dma_resv_held(bo->base.base.resv) || !kref_read(&bo->base.base.refcount)); + dma_resv_assert_held(bo->base.base.resv); if (bo->mmu_mapped) { drm_WARN_ON(&vdev->drm, !bo->ctx); @@ -130,13 +157,15 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo) bo->ctx = NULL; } - if (drm_gem_is_imported(&bo->base.base)) - return; - if (bo->base.sgt) { - dma_unmap_sgtable(vdev->drm.dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0); - sg_free_table(bo->base.sgt); - kfree(bo->base.sgt); + if (bo->base.base.import_attach) { + dma_buf_unmap_attachment(bo->base.base.import_attach, + bo->base.sgt, DMA_BIDIRECTIONAL); + } else { + dma_unmap_sgtable(vdev->drm.dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0); + sg_free_table(bo->base.sgt); + kfree(bo->base.sgt); + } bo->base.sgt = NULL; } } @@ -182,10 +211,11 @@ struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t siz struct drm_gem_object *ivpu_gem_prime_import(struct drm_device *dev, struct dma_buf *dma_buf) { + struct ivpu_device *vdev = to_ivpu_device(dev); struct device *attach_dev = dev->dev; struct dma_buf_attachment *attach; - struct sg_table *sgt; struct drm_gem_object *obj; + struct ivpu_bo *bo; int ret; attach = dma_buf_attach(dma_buf, attach_dev); @@ -194,25 +224,25 @@ struct drm_gem_object *ivpu_gem_prime_import(struct drm_device *dev, get_dma_buf(dma_buf); - sgt = dma_buf_map_attachment_unlocked(attach, DMA_BIDIRECTIONAL); - if (IS_ERR(sgt)) { - ret = PTR_ERR(sgt); - goto fail_detach; - } - - obj = drm_gem_shmem_prime_import_sg_table(dev, attach, sgt); + obj = drm_gem_shmem_prime_import_sg_table(dev, attach, NULL); if (IS_ERR(obj)) { ret = PTR_ERR(obj); - goto fail_unmap; + goto fail_detach; } obj->import_attach = attach; obj->resv = dma_buf->resv; + bo = to_ivpu_bo(obj); + + mutex_lock(&vdev->bo_list_lock); + list_add_tail(&bo->bo_list_node, &vdev->bo_list); + mutex_unlock(&vdev->bo_list_lock); + + ivpu_dbg(vdev, BO, "import: bo %8p size %9zu\n", bo, ivpu_bo_size(bo)); + return obj; -fail_unmap: - dma_buf_unmap_attachment_unlocked(attach, sgt, DMA_BIDIRECTIONAL); fail_detach: dma_buf_detach(dma_buf, attach); dma_buf_put(dma_buf); @@ -220,7 +250,7 @@ struct drm_gem_object *ivpu_gem_prime_import(struct drm_device *dev, return ERR_PTR(ret); } -static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags, u32 ctx_id) +static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags) { struct drm_gem_shmem_object *shmem; struct ivpu_bo *bo; @@ -238,7 +268,6 @@ static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 fla return ERR_CAST(shmem); bo = to_ivpu_bo(&shmem->base); - bo->ctx_id = ctx_id; bo->base.map_wc = flags & DRM_IVPU_BO_WC; bo->flags = flags; @@ -246,7 +275,7 @@ static struct ivpu_bo *ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 fla list_add_tail(&bo->bo_list_node, &vdev->bo_list); mutex_unlock(&vdev->bo_list_lock); - ivpu_dbg_bo(vdev, bo, "alloc"); + ivpu_dbg(vdev, BO, " alloc: bo %8p size %9llu\n", bo, size); return bo; } @@ -281,16 +310,22 @@ static void ivpu_gem_bo_free(struct drm_gem_object *obj) ivpu_dbg_bo(vdev, bo, "free"); + drm_WARN_ON(&vdev->drm, list_empty(&bo->bo_list_node)); + mutex_lock(&vdev->bo_list_lock); list_del(&bo->bo_list_node); - mutex_unlock(&vdev->bo_list_lock); drm_WARN_ON(&vdev->drm, !drm_gem_is_imported(&bo->base.base) && !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ)); drm_WARN_ON(&vdev->drm, ivpu_bo_size(bo) == 0); drm_WARN_ON(&vdev->drm, bo->base.vaddr); + ivpu_bo_lock(bo); ivpu_bo_unbind_locked(bo); + ivpu_bo_unlock(bo); + + mutex_unlock(&vdev->bo_list_lock); + drm_WARN_ON(&vdev->drm, bo->mmu_mapped); drm_WARN_ON(&vdev->drm, bo->ctx); @@ -326,7 +361,7 @@ int ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *fi if (size == 0) return -EINVAL; - bo = ivpu_bo_alloc(vdev, size, args->flags, file_priv->ctx.id); + bo = ivpu_bo_alloc(vdev, size, args->flags); if (IS_ERR(bo)) { ivpu_err(vdev, "Failed to allocate BO: %pe (ctx %u size %llu flags 0x%x)", bo, file_priv->ctx.id, args->size, args->flags); @@ -360,7 +395,7 @@ ivpu_bo_create(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(range->end)); drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(size)); - bo = ivpu_bo_alloc(vdev, size, flags, IVPU_GLOBAL_CONTEXT_MMU_SSID); + bo = ivpu_bo_alloc(vdev, size, flags); if (IS_ERR(bo)) { ivpu_err(vdev, "Failed to allocate BO: %pe (vpu_addr 0x%llx size %llu flags 0x%x)", bo, range->start, size, flags); @@ -371,7 +406,7 @@ ivpu_bo_create(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, if (ret) goto err_put; - ret = ivpu_bo_pin(bo); + ret = ivpu_bo_bind(bo); if (ret) goto err_put; diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h index aa8ff14f7aae1a..ade0d127453ff3 100644 --- a/drivers/accel/ivpu/ivpu_gem.h +++ b/drivers/accel/ivpu/ivpu_gem.h @@ -24,7 +24,7 @@ struct ivpu_bo { bool mmu_mapped; }; -int ivpu_bo_pin(struct ivpu_bo *bo); +int ivpu_bo_bind(struct ivpu_bo *bo); void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx); struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t size); diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.c b/drivers/accel/ivpu/ivpu_hw_btrs.c index afdb3b2aa72a70..aa33f562d29c12 100644 --- a/drivers/accel/ivpu/ivpu_hw_btrs.c +++ b/drivers/accel/ivpu/ivpu_hw_btrs.c @@ -752,7 +752,7 @@ int ivpu_hw_btrs_dct_get_request(struct ivpu_device *vdev, bool *enable) } } -void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u32 active_percent) +void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u8 active_percent) { u32 val = 0; u32 cmd = enable ? DCT_ENABLE : DCT_DISABLE; diff --git a/drivers/accel/ivpu/ivpu_hw_btrs.h b/drivers/accel/ivpu/ivpu_hw_btrs.h index 032c384ac3d4d5..c4c10e22f30f37 100644 --- a/drivers/accel/ivpu/ivpu_hw_btrs.h +++ b/drivers/accel/ivpu/ivpu_hw_btrs.h @@ -36,7 +36,7 @@ u32 ivpu_hw_btrs_dpu_freq_get(struct ivpu_device *vdev); bool ivpu_hw_btrs_irq_handler_mtl(struct ivpu_device *vdev, int irq); bool ivpu_hw_btrs_irq_handler_lnl(struct ivpu_device *vdev, int irq); int ivpu_hw_btrs_dct_get_request(struct ivpu_device *vdev, bool *enable); -void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u32 active_percent); +void ivpu_hw_btrs_dct_set_status(struct ivpu_device *vdev, bool enable, u8 active_percent); u32 ivpu_hw_btrs_telemetry_offset_get(struct ivpu_device *vdev); u32 ivpu_hw_btrs_telemetry_size_get(struct ivpu_device *vdev); u32 ivpu_hw_btrs_telemetry_enable_get(struct ivpu_device *vdev); diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index 060f1fc031d347..1e4caf5726474d 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -732,7 +732,7 @@ ivpu_job_prepare_bos_for_submit(struct drm_file *file, struct ivpu_job *job, u32 job->bos[i] = to_ivpu_bo(obj); - ret = ivpu_bo_pin(job->bos[i]); + ret = ivpu_bo_bind(job->bos[i]); if (ret) return ret; } @@ -1012,7 +1012,7 @@ void ivpu_context_abort_work_fn(struct work_struct *work) if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) if (ivpu_jsm_reset_engine(vdev, 0)) - return; + goto runtime_put; mutex_lock(&vdev->context_list_lock); xa_for_each(&vdev->context_xa, ctx_id, file_priv) { @@ -1036,7 +1036,7 @@ void ivpu_context_abort_work_fn(struct work_struct *work) goto runtime_put; if (ivpu_jsm_hws_resume_engine(vdev, 0)) - return; + goto runtime_put; /* * In hardware scheduling mode NPU already has stopped processing jobs * and won't send us any further notifications, thus we have to free job related resources diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index 475ddc94f1cfe3..457ccf09df5455 100644 --- a/drivers/accel/ivpu/ivpu_pm.c +++ b/drivers/accel/ivpu/ivpu_pm.c @@ -502,6 +502,11 @@ void ivpu_pm_irq_dct_work_fn(struct work_struct *work) else ret = ivpu_pm_dct_disable(vdev); - if (!ret) - ivpu_hw_btrs_dct_set_status(vdev, enable, vdev->pm->dct_active_percent); + if (!ret) { + /* Convert percent to U1.7 format */ + u8 val = DIV_ROUND_CLOSEST(vdev->pm->dct_active_percent * 128, 100); + + ivpu_hw_btrs_dct_set_status(vdev, enable, val); + } + } diff --git a/drivers/acpi/acpi_pcc.c b/drivers/acpi/acpi_pcc.c index 97064e943768ad..e3f302b9dee5f5 100644 --- a/drivers/acpi/acpi_pcc.c +++ b/drivers/acpi/acpi_pcc.c @@ -52,7 +52,7 @@ acpi_pcc_address_space_setup(acpi_handle region_handle, u32 function, struct pcc_data *data; struct acpi_pcc_info *ctx = handler_context; struct pcc_mbox_chan *pcc_chan; - static acpi_status ret; + acpi_status ret; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index fa3475da7ea9b6..b6198f73c81dfa 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -163,7 +163,9 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj, return_ACPI_STATUS(AE_NOT_EXIST); } - if (region_obj->region.space_id == ACPI_ADR_SPACE_PLATFORM_COMM) { + if (field_obj + && region_obj->region.space_id == + ACPI_ADR_SPACE_PLATFORM_COMM) { struct acpi_pcc_info *ctx = handler_desc->address_space.context; diff --git a/drivers/acpi/acpica/nswalk.c b/drivers/acpi/acpica/nswalk.c index a2ac06a26e921c..5670ff5a43cd48 100644 --- a/drivers/acpi/acpica/nswalk.c +++ b/drivers/acpi/acpica/nswalk.c @@ -169,9 +169,12 @@ acpi_ns_walk_namespace(acpi_object_type type, if (start_node == ACPI_ROOT_OBJECT) { start_node = acpi_gbl_root_node; - if (!start_node) { - return_ACPI_STATUS(AE_NO_NAMESPACE); - } + } + + /* Avoid walking the namespace if the StartNode is NULL */ + + if (!start_node) { + return_ACPI_STATUS(AE_NO_NAMESPACE); } /* Null child means "get first node" */ diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 97ee19f2cae060..56107aa0027444 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -552,26 +553,25 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, } static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, - int sev, bool sync) + int sev, bool sync) { struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata); int flags = sync ? MF_ACTION_REQUIRED : 0; + char error_type[120]; bool queued = false; int sec_sev, i; char *p; - log_arm_hw_error(err); - sec_sev = ghes_severity(gdata->error_severity); + log_arm_hw_error(err, sec_sev); if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE) return false; p = (char *)(err + 1); for (i = 0; i < err->err_info_num; i++) { struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p; - bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR); + bool is_cache = err_info->type & CPER_ARM_CACHE_ERROR; bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR); - const char *error_type = "unknown error"; /* * The field (err_info->error_info & BIT(26)) is fixed to set to @@ -585,12 +585,15 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, continue; } - if (err_info->type < ARRAY_SIZE(cper_proc_error_type_strs)) - error_type = cper_proc_error_type_strs[err_info->type]; + cper_bits_to_str(error_type, sizeof(error_type), + FIELD_GET(CPER_ARM_ERR_TYPE_MASK, err_info->type), + cper_proc_error_type_strs, + ARRAY_SIZE(cper_proc_error_type_strs)); pr_warn_ratelimited(FW_WARN GHES_PFX - "Unhandled processor error type: %s\n", - error_type); + "Unhandled processor error type 0x%02x: %s%s\n", + err_info->type, error_type, + (err_info->type & ~CPER_ARM_ERR_TYPE_MASK) ? " with reserved bit(s)" : ""); p += err_info->length; } @@ -895,11 +898,9 @@ static void ghes_do_proc(struct ghes *ghes, arch_apei_report_mem_error(sev, mem_err); queued = ghes_handle_memory_failure(gdata, sev, sync); - } - else if (guid_equal(sec_type, &CPER_SEC_PCIE)) { + } else if (guid_equal(sec_type, &CPER_SEC_PCIE)) { ghes_handle_aer(gdata); - } - else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) { + } else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) { queued = ghes_handle_arm_hw_error(gdata, sev, sync); } else if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR)) { struct cxl_cper_sec_prot_err *prot_err = acpi_hest_get_payload(gdata); diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 3bdeeee3414e68..b59b0100d03c51 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -362,7 +362,7 @@ static int send_pcc_cmd(int pcc_ss_id, u16 cmd) end: if (cmd == CMD_WRITE) { if (unlikely(ret)) { - for_each_possible_cpu(i) { + for_each_online_cpu(i) { struct cpc_desc *desc = per_cpu(cpc_desc_ptr, i); if (!desc) @@ -524,7 +524,7 @@ int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data) else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY) cpu_data->shared_type = CPUFREQ_SHARED_TYPE_ANY; - for_each_possible_cpu(i) { + for_each_online_cpu(i) { if (i == cpu) continue; @@ -1366,7 +1366,8 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps) /* Are any of the regs PCC ?*/ if (CPC_IN_PCC(highest_reg) || CPC_IN_PCC(lowest_reg) || CPC_IN_PCC(lowest_non_linear_reg) || CPC_IN_PCC(nominal_reg) || - CPC_IN_PCC(low_freq_reg) || CPC_IN_PCC(nom_freq_reg)) { + CPC_IN_PCC(low_freq_reg) || CPC_IN_PCC(nom_freq_reg) || + CPC_IN_PCC(guaranteed_reg)) { if (pcc_ss_id < 0) { pr_debug("Invalid pcc_ss_id\n"); return -ENODEV; diff --git a/drivers/acpi/fan.h b/drivers/acpi/fan.h index bedbab0e8e4e90..0d73433c388923 100644 --- a/drivers/acpi/fan.h +++ b/drivers/acpi/fan.h @@ -11,6 +11,7 @@ #define _ACPI_FAN_H_ #include +#include #define ACPI_FAN_DEVICE_IDS \ {"INT3404", }, /* Fan */ \ @@ -60,6 +61,38 @@ struct acpi_fan { struct device_attribute fine_grain_control; }; +/** + * acpi_fan_speed_valid - Check if fan speed value is valid + * @speeed: Speed value returned by the ACPI firmware + * + * Check if the fan speed value returned by the ACPI firmware is valid. This function is + * necessary as ACPI firmware implementations can return 0xFFFFFFFF to signal that the + * ACPI fan does not support speed reporting. Additionally, some buggy ACPI firmware + * implementations return a value larger than the 32-bit integer value defined by + * the ACPI specification when using placeholder values. Such invalid values are also + * detected by this function. + * + * Returns: True if the fan speed value is valid, false otherwise. + */ +static inline bool acpi_fan_speed_valid(u64 speed) +{ + return speed < U32_MAX; +} + +/** + * acpi_fan_power_valid - Check if fan power value is valid + * @power: Power value returned by the ACPI firmware + * + * Check if the fan power value returned by the ACPI firmware is valid. + * See acpi_fan_speed_valid() for details. + * + * Returns: True if the fan power value is valid, false otherwise. + */ +static inline bool acpi_fan_power_valid(u64 power) +{ + return power < U32_MAX; +} + int acpi_fan_get_fst(acpi_handle handle, struct acpi_fan_fst *fst); int acpi_fan_create_attributes(struct acpi_device *device); void acpi_fan_delete_attributes(struct acpi_device *device); diff --git a/drivers/acpi/fan_hwmon.c b/drivers/acpi/fan_hwmon.c index 4b2c2007f2d7fa..47a02ef5a60671 100644 --- a/drivers/acpi/fan_hwmon.c +++ b/drivers/acpi/fan_hwmon.c @@ -15,10 +15,6 @@ #include "fan.h" -/* Returned when the ACPI fan does not support speed reporting */ -#define FAN_SPEED_UNAVAILABLE U32_MAX -#define FAN_POWER_UNAVAILABLE U32_MAX - static struct acpi_fan_fps *acpi_fan_get_current_fps(struct acpi_fan *fan, u64 control) { unsigned int i; @@ -77,7 +73,7 @@ static umode_t acpi_fan_hwmon_is_visible(const void *drvdata, enum hwmon_sensor_ * when the associated attribute should not be created. */ for (i = 0; i < fan->fps_count; i++) { - if (fan->fps[i].power != FAN_POWER_UNAVAILABLE) + if (acpi_fan_power_valid(fan->fps[i].power)) return 0444; } @@ -106,7 +102,7 @@ static int acpi_fan_hwmon_read(struct device *dev, enum hwmon_sensor_types type, case hwmon_fan: switch (attr) { case hwmon_fan_input: - if (fst.speed == FAN_SPEED_UNAVAILABLE) + if (!acpi_fan_speed_valid(fst.speed)) return -ENODEV; if (fst.speed > LONG_MAX) @@ -134,7 +130,7 @@ static int acpi_fan_hwmon_read(struct device *dev, enum hwmon_sensor_types type, if (!fps) return -EIO; - if (fps->power == FAN_POWER_UNAVAILABLE) + if (!acpi_fan_power_valid(fps->power)) return -ENODEV; if (fps->power > LONG_MAX / MICROWATT_PER_MILLIWATT) diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 361a7721a6a873..7da5ae5594a727 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -1113,6 +1113,19 @@ static const struct dmi_system_id dmi_leave_unused_power_resources_on[] = { DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE Click Mini L9W-B"), }, }, + { + /* + * THUNDEROBOT ZERO laptop: Due to its SSDT table bug, power + * resource 'PXP' will be shut down on initialization, making + * the NVMe #2 and the NVIDIA dGPU both unavailable (they're + * both controlled by 'PXP'). + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "THUNDEROBOT"), + DMI_MATCH(DMI_PRODUCT_NAME, "ZERO"), + } + + }, {} }; diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 9b6b71a2ffb546..a4498357bd165a 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -54,7 +54,7 @@ static int map_x2apic_id(struct acpi_subtable_header *entry, if (!(apic->lapic_flags & ACPI_MADT_ENABLED)) return -ENODEV; - if (device_declaration && (apic->uid == acpi_id)) { + if (apic->uid == acpi_id && (device_declaration || acpi_id < 255)) { *apic_id = apic->local_apic_id; return 0; } diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c index 65e779be64ffcc..7644de24d2faa4 100644 --- a/drivers/acpi/processor_driver.c +++ b/drivers/acpi/processor_driver.c @@ -166,7 +166,7 @@ static int __acpi_processor_start(struct acpi_device *device) if (result && !IS_ENABLED(CONFIG_ACPI_CPU_FREQ_PSS)) dev_dbg(&device->dev, "CPPC data invalid or not present\n"); - if (!cpuidle_get_driver() || cpuidle_get_driver() == &acpi_idle_driver) + if (cpuidle_get_driver() == &acpi_idle_driver) acpi_processor_power_init(pr); acpi_pss_perf_init(pr); diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 43d5e457814e17..19737f9e1e16fa 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1472,7 +1472,7 @@ static struct fwnode_handle *acpi_graph_get_next_endpoint( if (!prev) { do { - port = fwnode_get_next_child_node(fwnode, port); + port = acpi_get_next_subnode(fwnode, port); /* * The names of the port nodes begin with "port@" * followed by the number of the port node and they also @@ -1490,13 +1490,13 @@ static struct fwnode_handle *acpi_graph_get_next_endpoint( if (!port) return NULL; - endpoint = fwnode_get_next_child_node(port, prev); + endpoint = acpi_get_next_subnode(port, prev); while (!endpoint) { - port = fwnode_get_next_child_node(fwnode, port); + port = acpi_get_next_subnode(fwnode, port); if (!port) break; if (is_acpi_graph_node(port, "port")) - endpoint = fwnode_get_next_child_node(port, NULL); + endpoint = acpi_get_next_subnode(port, NULL); } /* @@ -1714,6 +1714,7 @@ static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, if (fwnode_property_read_u32(fwnode, "reg", &endpoint->id)) fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id); + fwnode_handle_put(port_fwnode); return 0; } diff --git a/drivers/amba/tegra-ahb.c b/drivers/amba/tegra-ahb.c index c0e8b765522dc7..f23c3ed018101c 100644 --- a/drivers/amba/tegra-ahb.c +++ b/drivers/amba/tegra-ahb.c @@ -144,6 +144,7 @@ int tegra_ahb_enable_smmu(struct device_node *dn) if (!dev) return -EPROBE_DEFER; ahb = dev_get_drvdata(dev); + put_device(dev); val = gizmo_readl(ahb, AHB_ARBITRATION_XBAR_CTRL); val |= AHB_ARBITRATION_XBAR_CTRL_SMMU_INIT_DONE; gizmo_writel(ahb, val, AHB_ARBITRATION_XBAR_CTRL); diff --git a/drivers/android/binder.c b/drivers/android/binder.c index a3a1b5c33ba36a..8e2989fb56a718 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2991,6 +2991,10 @@ static void binder_set_txn_from_error(struct binder_transaction *t, int id, * @t: the binder transaction that failed * @data_size: the user provided data size for the transaction * @error: enum binder_driver_return_protocol returned to sender + * + * Note that t->buffer is not safe to access here, as it may have been + * released (or not yet allocated). Callers should guarantee all the + * transaction items used here are safe to access. */ static void binder_netlink_report(struct binder_proc *proc, struct binder_transaction *t, @@ -3780,6 +3784,14 @@ static void binder_transaction(struct binder_proc *proc, goto err_dead_proc_or_thread; } } else { + /* + * Make a transaction copy. It is not safe to access 't' after + * binder_proc_transaction() reported a pending frozen. The + * target could thaw and consume the transaction at any point. + * Instead, use a safe 't_copy' for binder_netlink_report(). + */ + struct binder_transaction t_copy = *t; + BUG_ON(target_node == NULL); BUG_ON(t->buffer->async_transaction != 1); return_error = binder_proc_transaction(t, target_proc, NULL); @@ -3790,7 +3802,7 @@ static void binder_transaction(struct binder_proc *proc, */ if (return_error == BR_TRANSACTION_PENDING_FROZEN) { tcomplete->type = BINDER_WORK_TRANSACTION_PENDING; - binder_netlink_report(proc, t, tr->data_size, + binder_netlink_report(proc, &t_copy, tr->data_size, return_error); } binder_enqueue_thread_work(thread, tcomplete); @@ -3812,8 +3824,9 @@ static void binder_transaction(struct binder_proc *proc, return; err_dead_proc_or_thread: - binder_txn_error("%d:%d dead process or thread\n", - thread->pid, proc->pid); + binder_txn_error("%d:%d %s process or thread\n", + proc->pid, thread->pid, + return_error == BR_FROZEN_REPLY ? "frozen" : "dead"); return_error_line = __LINE__; binder_dequeue_work(proc, tcomplete); err_translate_failed: diff --git a/drivers/android/binder/node.rs b/drivers/android/binder/node.rs index 08d362deaf61e5..c26d113ede9668 100644 --- a/drivers/android/binder/node.rs +++ b/drivers/android/binder/node.rs @@ -541,10 +541,10 @@ impl Node { guard = self.owner.inner.lock(); } - let death_list = core::mem::take(&mut self.inner.access_mut(&mut guard).death_list); - drop(guard); - for death in death_list { + while let Some(death) = self.inner.access_mut(&mut guard).death_list.pop_front() { + drop(guard); death.into_arc().set_dead(); + guard = self.owner.inner.lock(); } } diff --git a/drivers/android/binder/page_range.rs b/drivers/android/binder/page_range.rs index 9379038f61f513..fdd97112ef5c8b 100644 --- a/drivers/android/binder/page_range.rs +++ b/drivers/android/binder/page_range.rs @@ -727,8 +727,5 @@ unsafe extern "C" fn rust_shrink_free_page( drop(mm); drop(page); - // SAFETY: We just unlocked the lru lock, but it should be locked when we return. - unsafe { bindings::spin_lock(&raw mut (*lru).lock) }; - LRU_REMOVED_ENTRY } diff --git a/drivers/android/binder/process.rs b/drivers/android/binder/process.rs index 7607353a5e9249..ef4dbb2b571c77 100644 --- a/drivers/android/binder/process.rs +++ b/drivers/android/binder/process.rs @@ -1362,8 +1362,12 @@ impl Process { work.into_arc().cancel(); } - let delivered_deaths = take(&mut self.inner.lock().delivered_deaths); - drop(delivered_deaths); + // Clear delivered_deaths list. + // + // Scope ensures that MutexGuard is dropped while executing the body. + while let Some(delivered_death) = { self.inner.lock().delivered_deaths.pop_front() } { + drop(delivered_death); + } // Free any resources kept alive by allocated buffers. let omapping = self.inner.lock().mapping.take(); diff --git a/drivers/android/binder/rust_binderfs.c b/drivers/android/binder/rust_binderfs.c index 6b497146b698b3..c7e26753f1df59 100644 --- a/drivers/android/binder/rust_binderfs.c +++ b/drivers/android/binder/rust_binderfs.c @@ -132,8 +132,8 @@ static int binderfs_binder_device_create(struct inode *ref_inode, mutex_lock(&binderfs_minors_mutex); if (++info->device_count <= info->mount_opts.max) minor = ida_alloc_max(&binderfs_minors, - use_reserve ? BINDERFS_MAX_MINOR : - BINDERFS_MAX_MINOR_CAPPED, + use_reserve ? BINDERFS_MAX_MINOR - 1 : + BINDERFS_MAX_MINOR_CAPPED - 1, GFP_KERNEL); else minor = -ENOSPC; @@ -416,8 +416,8 @@ static int binderfs_binder_ctl_create(struct super_block *sb) /* Reserve a new minor number for the new device. */ mutex_lock(&binderfs_minors_mutex); minor = ida_alloc_max(&binderfs_minors, - use_reserve ? BINDERFS_MAX_MINOR : - BINDERFS_MAX_MINOR_CAPPED, + use_reserve ? BINDERFS_MAX_MINOR - 1 : + BINDERFS_MAX_MINOR_CAPPED - 1, GFP_KERNEL); mutex_unlock(&binderfs_minors_mutex); if (minor < 0) { diff --git a/drivers/android/binder/thread.rs b/drivers/android/binder/thread.rs index 7e34ccd394f804..67af5ff2816607 100644 --- a/drivers/android/binder/thread.rs +++ b/drivers/android/binder/thread.rs @@ -39,6 +39,10 @@ use core::{ sync::atomic::{AtomicU32, Ordering}, }; +fn is_aligned(value: usize, to: usize) -> bool { + value % to == 0 +} + /// Stores the layout of the scatter-gather entries. This is used during the `translate_objects` /// call and is discarded when it returns. struct ScatterGatherState { @@ -69,17 +73,24 @@ struct ScatterGatherEntry { } /// This entry specifies that a fixup should happen at `target_offset` of the -/// buffer. If `skip` is nonzero, then the fixup is a `binder_fd_array_object` -/// and is applied later. Otherwise if `skip` is zero, then the size of the -/// fixup is `sizeof::()` and `pointer_value` is written to the buffer. -struct PointerFixupEntry { - /// The number of bytes to skip, or zero for a `binder_buffer_object` fixup. - skip: usize, - /// The translated pointer to write when `skip` is zero. - pointer_value: u64, - /// The offset at which the value should be written. The offset is relative - /// to the original buffer. - target_offset: usize, +/// buffer. +enum PointerFixupEntry { + /// A fixup for a `binder_buffer_object`. + Fixup { + /// The translated pointer to write. + pointer_value: u64, + /// The offset at which the value should be written. The offset is relative + /// to the original buffer. + target_offset: usize, + }, + /// A skip for a `binder_fd_array_object`. + Skip { + /// The number of bytes to skip. + skip: usize, + /// The offset at which the skip should happen. The offset is relative + /// to the original buffer. + target_offset: usize, + }, } /// Return type of `apply_and_validate_fixup_in_parent`. @@ -762,8 +773,7 @@ impl Thread { parent_entry.fixup_min_offset = info.new_min_offset; parent_entry.pointer_fixups.push( - PointerFixupEntry { - skip: 0, + PointerFixupEntry::Fixup { pointer_value: buffer_ptr_in_user_space, target_offset: info.target_offset, }, @@ -789,6 +799,10 @@ impl Thread { let num_fds = usize::try_from(obj.num_fds).map_err(|_| EINVAL)?; let fds_len = num_fds.checked_mul(size_of::()).ok_or(EINVAL)?; + if !is_aligned(parent_offset, size_of::()) { + return Err(EINVAL.into()); + } + let info = sg_state.validate_parent_fixup(parent_index, parent_offset, fds_len)?; view.alloc.info_add_fd_reserve(num_fds)?; @@ -803,13 +817,16 @@ impl Thread { } }; + if !is_aligned(parent_entry.sender_uaddr, size_of::()) { + return Err(EINVAL.into()); + } + parent_entry.fixup_min_offset = info.new_min_offset; parent_entry .pointer_fixups .push( - PointerFixupEntry { + PointerFixupEntry::Skip { skip: fds_len, - pointer_value: 0, target_offset: info.target_offset, }, GFP_KERNEL, @@ -820,6 +837,7 @@ impl Thread { .sender_uaddr .checked_add(parent_offset) .ok_or(EINVAL)?; + let mut fda_bytes = KVec::new(); UserSlice::new(UserPtr::from_addr(fda_uaddr as _), fds_len) .read_all(&mut fda_bytes, GFP_KERNEL)?; @@ -871,17 +889,21 @@ impl Thread { let mut reader = UserSlice::new(UserPtr::from_addr(sg_entry.sender_uaddr), sg_entry.length).reader(); for fixup in &mut sg_entry.pointer_fixups { - let fixup_len = if fixup.skip == 0 { - size_of::() - } else { - fixup.skip + let (fixup_len, fixup_offset) = match fixup { + PointerFixupEntry::Fixup { target_offset, .. } => { + (size_of::(), *target_offset) + } + PointerFixupEntry::Skip { + skip, + target_offset, + } => (*skip, *target_offset), }; - let target_offset_end = fixup.target_offset.checked_add(fixup_len).ok_or(EINVAL)?; - if fixup.target_offset < end_of_previous_fixup || offset_end < target_offset_end { + let target_offset_end = fixup_offset.checked_add(fixup_len).ok_or(EINVAL)?; + if fixup_offset < end_of_previous_fixup || offset_end < target_offset_end { pr_warn!( "Fixups oob {} {} {} {}", - fixup.target_offset, + fixup_offset, end_of_previous_fixup, offset_end, target_offset_end @@ -890,13 +912,13 @@ impl Thread { } let copy_off = end_of_previous_fixup; - let copy_len = fixup.target_offset - end_of_previous_fixup; + let copy_len = fixup_offset - end_of_previous_fixup; if let Err(err) = alloc.copy_into(&mut reader, copy_off, copy_len) { pr_warn!("Failed copying into alloc: {:?}", err); return Err(err.into()); } - if fixup.skip == 0 { - let res = alloc.write::(fixup.target_offset, &fixup.pointer_value); + if let PointerFixupEntry::Fixup { pointer_value, .. } = fixup { + let res = alloc.write::(fixup_offset, pointer_value); if let Err(err) = res { pr_warn!("Failed copying ptr into alloc: {:?}", err); return Err(err.into()); @@ -949,25 +971,30 @@ impl Thread { let data_size = trd.data_size.try_into().map_err(|_| EINVAL)?; let aligned_data_size = ptr_align(data_size).ok_or(EINVAL)?; - let offsets_size = trd.offsets_size.try_into().map_err(|_| EINVAL)?; - let aligned_offsets_size = ptr_align(offsets_size).ok_or(EINVAL)?; - let buffers_size = tr.buffers_size.try_into().map_err(|_| EINVAL)?; - let aligned_buffers_size = ptr_align(buffers_size).ok_or(EINVAL)?; + let offsets_size: usize = trd.offsets_size.try_into().map_err(|_| EINVAL)?; + let buffers_size: usize = tr.buffers_size.try_into().map_err(|_| EINVAL)?; let aligned_secctx_size = match secctx.as_ref() { Some((_offset, ctx)) => ptr_align(ctx.len()).ok_or(EINVAL)?, None => 0, }; + if !is_aligned(offsets_size, size_of::()) { + return Err(EINVAL.into()); + } + if !is_aligned(buffers_size, size_of::()) { + return Err(EINVAL.into()); + } + // This guarantees that at least `sizeof(usize)` bytes will be allocated. let len = usize::max( aligned_data_size - .checked_add(aligned_offsets_size) - .and_then(|sum| sum.checked_add(aligned_buffers_size)) + .checked_add(offsets_size) + .and_then(|sum| sum.checked_add(buffers_size)) .and_then(|sum| sum.checked_add(aligned_secctx_size)) .ok_or(ENOMEM)?, - size_of::(), + size_of::(), ); - let secctx_off = aligned_data_size + aligned_offsets_size + aligned_buffers_size; + let secctx_off = aligned_data_size + offsets_size + buffers_size; let mut alloc = match to_process.buffer_alloc(debug_id, len, is_oneway, self.process.task.pid()) { Ok(alloc) => alloc, @@ -999,13 +1026,13 @@ impl Thread { } let offsets_start = aligned_data_size; - let offsets_end = aligned_data_size + aligned_offsets_size; + let offsets_end = aligned_data_size + offsets_size; // This state is used for BINDER_TYPE_PTR objects. let sg_state = sg_state.insert(ScatterGatherState { unused_buffer_space: UnusedBufferSpace { offset: offsets_end, - limit: len, + limit: offsets_end + buffers_size, }, sg_entries: KVec::new(), ancestors: KVec::new(), @@ -1014,12 +1041,16 @@ impl Thread { // Traverse the objects specified. let mut view = AllocationView::new(&mut alloc, data_size); for (index, index_offset) in (offsets_start..offsets_end) - .step_by(size_of::()) + .step_by(size_of::()) .enumerate() { - let offset = view.alloc.read(index_offset)?; + let offset: usize = view + .alloc + .read::(index_offset)? + .try_into() + .map_err(|_| EINVAL)?; - if offset < end_of_previous_object { + if offset < end_of_previous_object || !is_aligned(offset, size_of::()) { pr_warn!("Got transaction with invalid offset."); return Err(EINVAL.into()); } @@ -1051,7 +1082,7 @@ impl Thread { } // Update the indexes containing objects to clean up. - let offset_after_object = index_offset + size_of::(); + let offset_after_object = index_offset + size_of::(); view.alloc .set_info_offsets(offsets_start..offset_after_object); } diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c index be8e64eb39ec51..6c6f52e1c032e9 100644 --- a/drivers/android/binderfs.c +++ b/drivers/android/binderfs.c @@ -132,8 +132,8 @@ static int binderfs_binder_device_create(struct inode *ref_inode, mutex_lock(&binderfs_minors_mutex); if (++info->device_count <= info->mount_opts.max) minor = ida_alloc_max(&binderfs_minors, - use_reserve ? BINDERFS_MAX_MINOR : - BINDERFS_MAX_MINOR_CAPPED, + use_reserve ? BINDERFS_MAX_MINOR - 1 : + BINDERFS_MAX_MINOR_CAPPED - 1, GFP_KERNEL); else minor = -ENOSPC; @@ -424,8 +424,8 @@ static int binderfs_binder_ctl_create(struct super_block *sb) /* Reserve a new minor number for the new device. */ mutex_lock(&binderfs_minors_mutex); minor = ida_alloc_max(&binderfs_minors, - use_reserve ? BINDERFS_MAX_MINOR : - BINDERFS_MAX_MINOR_CAPPED, + use_reserve ? BINDERFS_MAX_MINOR - 1 : + BINDERFS_MAX_MINOR_CAPPED - 1, GFP_KERNEL); mutex_unlock(&binderfs_minors_mutex); if (minor < 0) { diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 7a7f88b3fa2b18..931d0081169b9c 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -2094,13 +2094,13 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (ap->flags & ATA_FLAG_EM) ap->em_message_type = hpriv->em_msg_type; - ahci_mark_external_port(ap); - - ahci_update_initial_lpm_policy(ap); - /* disabled/not-implemented port */ - if (!(hpriv->port_map & (1 << i))) + if (!(hpriv->port_map & (1 << i))) { ap->ops = &ata_dummy_port_ops; + } else { + ahci_mark_external_port(ap); + ahci_update_initial_lpm_policy(ap); + } } /* apply workaround for ASUS P5W DH Deluxe mainboard */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index f48fb63d7e8549..b29067759cc276 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2872,7 +2872,8 @@ static void ata_dev_config_lpm(struct ata_device *dev) static void ata_dev_print_features(struct ata_device *dev) { - if (!(dev->flags & ATA_DFLAG_FEATURES_MASK)) + if (!(dev->flags & ATA_DFLAG_FEATURES_MASK) && !dev->cpr_log && + !ata_id_has_hipm(dev->id) && !ata_id_has_dipm(dev->id)) return; ata_dev_info(dev, @@ -3116,6 +3117,11 @@ int ata_dev_configure(struct ata_device *dev) ata_mode_string(xfer_mask), cdb_intr_string, atapi_an_string, dma_dir_string); + + ata_dev_config_lpm(dev); + + if (print_info) + ata_dev_print_features(dev); } /* determine max_sectors */ @@ -4132,6 +4138,9 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = { { "ST3320[68]13AS", "SD1[5-9]", ATA_QUIRK_NONCQ | ATA_QUIRK_FIRMWARE_WARN }, + /* Seagate disks with LPM issues */ + { "ST2000DM008-2FR102", NULL, ATA_QUIRK_NOLPM }, + /* drives which fail FPDMA_AA activation (some may freeze afterwards) the ST disks also have LPM issues */ { "ST1000LM024 HN-M101MBB", NULL, ATA_QUIRK_BROKEN_FPDMA_AA | @@ -5543,6 +5552,7 @@ struct ata_port *ata_port_alloc(struct ata_host *host) mutex_init(&ap->scsi_scan_mutex); INIT_DELAYED_WORK(&ap->hotplug_task, ata_scsi_hotplug); INIT_DELAYED_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); + INIT_WORK(&ap->deferred_qc_work, ata_scsi_deferred_qc_work); INIT_LIST_HEAD(&ap->eh_done_q); init_waitqueue_head(&ap->eh_wait_q); init_completion(&ap->park_req_pending); @@ -6163,9 +6173,11 @@ static void ata_port_detach(struct ata_port *ap) /* wait till EH commits suicide */ ata_port_wait_eh(ap); - /* it better be dead now */ + /* It better be dead now and not have any remaining deferred qc. */ WARN_ON(!(ap->pflags & ATA_PFLAG_UNLOADED)); + WARN_ON(ap->deferred_qc); + cancel_work_sync(&ap->deferred_qc_work); cancel_delayed_work_sync(&ap->hotplug_task); cancel_delayed_work_sync(&ap->scsi_rescan_task); diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 2586e77ebf45d0..258e657f3527c2 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -640,12 +640,28 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, set_host_byte(scmd, DID_OK); ata_qc_for_each_raw(ap, qc, i) { - if (qc->flags & ATA_QCFLAG_ACTIVE && - qc->scsicmd == scmd) + if (qc->scsicmd != scmd) + continue; + if ((qc->flags & ATA_QCFLAG_ACTIVE) || + qc == ap->deferred_qc) break; } - if (i < ATA_MAX_QUEUE) { + if (qc == ap->deferred_qc) { + /* + * This is a deferred command that timed out while + * waiting for the command queue to drain. Since the qc + * is not active yet (deferred_qc is still set, so the + * deferred qc work has not issued the command yet), + * simply signal the timeout by finishing the SCSI + * command and clear the deferred qc to prevent the + * deferred qc work from issuing this qc. + */ + WARN_ON_ONCE(qc->flags & ATA_QCFLAG_ACTIVE); + ap->deferred_qc = NULL; + set_host_byte(scmd, DID_TIME_OUT); + scsi_eh_finish_cmd(scmd, &ap->eh_done_q); + } else if (i < ATA_MAX_QUEUE) { /* the scmd has an associated qc */ if (!(qc->flags & ATA_QCFLAG_EH)) { /* which hasn't failed yet, timeout */ @@ -917,6 +933,12 @@ static void ata_eh_set_pending(struct ata_port *ap, bool fastdrain) ap->pflags |= ATA_PFLAG_EH_PENDING; + /* + * If we have a deferred qc, requeue it so that it is retried once EH + * completes. + */ + ata_scsi_requeue_deferred_qc(ap); + if (!fastdrain) return; diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index b2817a2995d6ba..04e1e774645e24 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -909,7 +909,7 @@ static bool ata_scsi_lpm_supported(struct ata_port *ap) struct ata_link *link; struct ata_device *dev; - if (ap->flags & ATA_FLAG_NO_LPM) + if ((ap->flags & ATA_FLAG_NO_LPM) || !ap->ops->set_lpm) return false; ata_for_each_link(link, ap, EDGE) { diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 434774e71fe61e..27ad145996052f 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1657,8 +1657,77 @@ static void ata_qc_done(struct ata_queued_cmd *qc) done(cmd); } +void ata_scsi_deferred_qc_work(struct work_struct *work) +{ + struct ata_port *ap = + container_of(work, struct ata_port, deferred_qc_work); + struct ata_queued_cmd *qc; + unsigned long flags; + + spin_lock_irqsave(ap->lock, flags); + + /* + * If we still have a deferred qc and we are not in EH, issue it. In + * such case, we should not need any more deferring the qc, so warn if + * qc_defer() says otherwise. + */ + qc = ap->deferred_qc; + if (qc && !ata_port_eh_scheduled(ap)) { + WARN_ON_ONCE(ap->ops->qc_defer(qc)); + ap->deferred_qc = NULL; + ata_qc_issue(qc); + } + + spin_unlock_irqrestore(ap->lock, flags); +} + +void ata_scsi_requeue_deferred_qc(struct ata_port *ap) +{ + struct ata_queued_cmd *qc = ap->deferred_qc; + struct scsi_cmnd *scmd; + + lockdep_assert_held(ap->lock); + + /* + * If we have a deferred qc when a reset occurs or NCQ commands fail, + * do not try to be smart about what to do with this deferred command + * and simply retry it by completing it with DID_SOFT_ERROR. + */ + if (!qc) + return; + + scmd = qc->scsicmd; + ap->deferred_qc = NULL; + ata_qc_free(qc); + scmd->result = (DID_SOFT_ERROR << 16); + scsi_done(scmd); +} + +static void ata_scsi_schedule_deferred_qc(struct ata_port *ap) +{ + struct ata_queued_cmd *qc = ap->deferred_qc; + + lockdep_assert_held(ap->lock); + + /* + * If we have a deferred qc, then qc_defer() is defined and we can use + * this callback to determine if this qc is good to go, unless EH has + * been scheduled. + */ + if (!qc) + return; + + if (ata_port_eh_scheduled(ap)) { + ata_scsi_requeue_deferred_qc(ap); + return; + } + if (!ap->ops->qc_defer(qc)) + queue_work(system_highpri_wq, &ap->deferred_qc_work); +} + static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) { + struct ata_port *ap = qc->ap; struct scsi_cmnd *cmd = qc->scsicmd; u8 *cdb = cmd->cmnd; bool have_sense = qc->flags & ATA_QCFLAG_SENSE_VALID; @@ -1688,6 +1757,66 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) } ata_qc_done(qc); + + ata_scsi_schedule_deferred_qc(ap); +} + +static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) +{ + int ret; + + if (!ap->ops->qc_defer) + goto issue; + + /* + * If we already have a deferred qc, then rely on the SCSI layer to + * requeue and defer all incoming commands until the deferred qc is + * processed, once all on-going commands complete. + */ + if (ap->deferred_qc) { + ata_qc_free(qc); + return SCSI_MLQUEUE_DEVICE_BUSY; + } + + /* Check if the command needs to be deferred. */ + ret = ap->ops->qc_defer(qc); + switch (ret) { + case 0: + break; + case ATA_DEFER_LINK: + ret = SCSI_MLQUEUE_DEVICE_BUSY; + break; + case ATA_DEFER_PORT: + ret = SCSI_MLQUEUE_HOST_BUSY; + break; + default: + WARN_ON_ONCE(1); + ret = SCSI_MLQUEUE_HOST_BUSY; + break; + } + + if (ret) { + /* + * We must defer this qc: if this is not an NCQ command, keep + * this qc as a deferred one and report to the SCSI layer that + * we issued it so that it is not requeued. The deferred qc will + * be issued with the port deferred_qc_work once all on-going + * commands complete. + */ + if (!ata_is_ncq(qc->tf.protocol)) { + ap->deferred_qc = qc; + return 0; + } + + /* Force a requeue of the command to defer its execution. */ + ata_qc_free(qc); + return ret; + } + +issue: + ata_qc_issue(qc); + + return 0; } /** @@ -1713,66 +1842,49 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) * spin_lock_irqsave(host lock) * * RETURNS: - * 0 on success, SCSI_ML_QUEUE_DEVICE_BUSY if the command - * needs to be deferred. + * 0 on success, SCSI_ML_QUEUE_DEVICE_BUSY or SCSI_MLQUEUE_HOST_BUSY if the + * command needs to be deferred. */ static int ata_scsi_translate(struct ata_device *dev, struct scsi_cmnd *cmd, ata_xlat_func_t xlat_func) { struct ata_port *ap = dev->link->ap; struct ata_queued_cmd *qc; - int rc; + lockdep_assert_held(ap->lock); + + /* + * ata_scsi_qc_new() calls scsi_done(cmd) in case of failure. So we + * have nothing further to do when allocating a qc fails. + */ qc = ata_scsi_qc_new(dev, cmd); if (!qc) - goto err_mem; + return 0; /* data is present; dma-map it */ if (cmd->sc_data_direction == DMA_FROM_DEVICE || cmd->sc_data_direction == DMA_TO_DEVICE) { if (unlikely(scsi_bufflen(cmd) < 1)) { ata_dev_warn(dev, "WARNING: zero len r/w req\n"); - goto err_did; + cmd->result = (DID_ERROR << 16); + goto done; } ata_sg_init(qc, scsi_sglist(cmd), scsi_sg_count(cmd)); - qc->dma_dir = cmd->sc_data_direction; } qc->complete_fn = ata_scsi_qc_complete; if (xlat_func(qc)) - goto early_finish; + goto done; - if (ap->ops->qc_defer) { - if ((rc = ap->ops->qc_defer(qc))) - goto defer; - } - - /* select device, send command to hardware */ - ata_qc_issue(qc); + return ata_scsi_qc_issue(ap, qc); - return 0; - -early_finish: - ata_qc_free(qc); - scsi_done(cmd); - return 0; - -err_did: +done: ata_qc_free(qc); - cmd->result = (DID_ERROR << 16); scsi_done(cmd); -err_mem: return 0; - -defer: - ata_qc_free(qc); - if (rc == ATA_DEFER_LINK) - return SCSI_MLQUEUE_DEVICE_BUSY; - else - return SCSI_MLQUEUE_HOST_BUSY; } /** diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index e5b977a8d3e1e5..612fe59828180c 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -161,6 +161,8 @@ void ata_scsi_sdev_config(struct scsi_device *sdev); int ata_scsi_dev_config(struct scsi_device *sdev, struct queue_limits *lim, struct ata_device *dev); int __ata_scsi_queuecmd(struct scsi_cmnd *scmd, struct ata_device *dev); +void ata_scsi_deferred_qc_work(struct work_struct *work); +void ata_scsi_requeue_deferred_qc(struct ata_port *ap); /* libata-eh.c */ extern unsigned int ata_internal_cmd_timeout(struct ata_device *dev, u8 cmd); diff --git a/drivers/ata/pata_ftide010.c b/drivers/ata/pata_ftide010.c index c3a8384c3e04d4..c41da296eb389d 100644 --- a/drivers/ata/pata_ftide010.c +++ b/drivers/ata/pata_ftide010.c @@ -122,10 +122,10 @@ static const u8 mwdma_50_active_time[3] = {6, 2, 2}; static const u8 mwdma_50_recovery_time[3] = {6, 2, 1}; static const u8 mwdma_66_active_time[3] = {8, 3, 3}; static const u8 mwdma_66_recovery_time[3] = {8, 2, 1}; -static const u8 udma_50_setup_time[6] = {3, 3, 2, 2, 1, 1}; +static const u8 udma_50_setup_time[6] = {3, 3, 2, 2, 1, 9}; static const u8 udma_50_hold_time[6] = {3, 1, 1, 1, 1, 1}; -static const u8 udma_66_setup_time[7] = {4, 4, 3, 2, }; -static const u8 udma_66_hold_time[7] = {}; +static const u8 udma_66_setup_time[7] = {4, 4, 3, 2, 1, 9, 9}; +static const u8 udma_66_hold_time[7] = {4, 2, 1, 1, 1, 1, 1}; /* * We set 66 MHz for all MWDMA modes diff --git a/drivers/atm/he.c b/drivers/atm/he.c index ad91cc6a34fc52..92a041d5387bd8 100644 --- a/drivers/atm/he.c +++ b/drivers/atm/he.c @@ -1587,7 +1587,8 @@ he_stop(struct he_dev *he_dev) he_dev->tbrq_base, he_dev->tbrq_phys); if (he_dev->tpdrq_base) - dma_free_coherent(&he_dev->pci_dev->dev, CONFIG_TBRQ_SIZE * sizeof(struct he_tbrq), + dma_free_coherent(&he_dev->pci_dev->dev, + CONFIG_TPDRQ_SIZE * sizeof(struct he_tpdrq), he_dev->tpdrq_base, he_dev->tpdrq_phys); dma_pool_destroy(he_dev->tpd_pool); diff --git a/drivers/auxdisplay/arm-charlcd.c b/drivers/auxdisplay/arm-charlcd.c index a7eae99a48f77d..4e22882f57c9c2 100644 --- a/drivers/auxdisplay/arm-charlcd.c +++ b/drivers/auxdisplay/arm-charlcd.c @@ -323,7 +323,7 @@ static int __init charlcd_probe(struct platform_device *pdev) out_no_irq: iounmap(lcd->virtbase); out_no_memregion: - release_mem_region(lcd->phybase, SZ_4K); + release_mem_region(lcd->phybase, lcd->physize); out_no_resource: kfree(lcd); return ret; diff --git a/drivers/base/core.c b/drivers/base/core.c index f69dc9c8595455..44a2d9bbbe28ef 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2328,6 +2328,32 @@ static void fw_devlink_link_device(struct device *dev) __fw_devlink_link_to_suppliers(dev, fwnode); } +/** + * fw_devlink_count_absent_consumers - Return how many consumers have + * either not been created yet, or do not yet have a driver attached. + * @fwnode: fwnode of the supplier + */ +int fw_devlink_count_absent_consumers(struct fwnode_handle *fwnode) +{ + struct fwnode_link *link, *tmp; + struct device_link *dlink, *dtmp; + struct device *sup_dev = get_dev_from_fwnode(fwnode); + int count = 0; + + list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) + count++; + + if (!sup_dev) + return count; + + list_for_each_entry_safe(dlink, dtmp, &sup_dev->links.consumers, s_node) + if (dlink->consumer->links.status != DL_DEV_DRIVER_BOUND) + count++; + + return count; +} +EXPORT_SYMBOL_GPL(fw_devlink_count_absent_consumers); + /* Device links support end. */ static struct kobject *dev_kobj; diff --git a/drivers/base/firmware_loader/Kconfig b/drivers/base/firmware_loader/Kconfig index 752b9a9bea0388..15eff8a4b50533 100644 --- a/drivers/base/firmware_loader/Kconfig +++ b/drivers/base/firmware_loader/Kconfig @@ -38,7 +38,7 @@ config FW_LOADER_DEBUG config RUST_FW_LOADER_ABSTRACTIONS bool "Rust Firmware Loader abstractions" depends on RUST - depends on FW_LOADER=y + select FW_LOADER help This enables the Rust abstractions for the firmware loader API. diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index 6942c62fa59d12..070149fb409239 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -471,6 +471,8 @@ static int fw_decompress_xz(struct device *dev, struct fw_priv *fw_priv, static char fw_path_para[256]; static const char * const fw_path[] = { fw_path_para, + "/lib/firmware/vendor/" UTS_RELEASE, + "/lib/firmware/vendor", "/lib/firmware/updates/" UTS_RELEASE, "/lib/firmware/updates", "/lib/firmware/" UTS_RELEASE, diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 1b11a3cd4acc27..e882b5269ebec4 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1869,16 +1869,18 @@ void pm_runtime_init(struct device *dev) */ void pm_runtime_reinit(struct device *dev) { - if (!pm_runtime_enabled(dev)) { - if (dev->power.runtime_status == RPM_ACTIVE) - pm_runtime_set_suspended(dev); - if (dev->power.irq_safe) { - spin_lock_irq(&dev->power.lock); - dev->power.irq_safe = 0; - spin_unlock_irq(&dev->power.lock); - if (dev->parent) - pm_runtime_put(dev->parent); - } + if (pm_runtime_enabled(dev)) + return; + + if (dev->power.runtime_status == RPM_ACTIVE) + pm_runtime_set_suspended(dev); + + if (dev->power.irq_safe) { + spin_lock_irq(&dev->power.lock); + dev->power.irq_safe = 0; + spin_unlock_irq(&dev->power.lock); + if (dev->parent) + pm_runtime_put(dev->parent); } /* * Clear power.needs_force_resume in case it has been set by diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index 8aa28c08b2891f..c0809d18fc5406 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -83,13 +83,16 @@ EXPORT_SYMBOL_GPL(dev_pm_set_wake_irq); */ void dev_pm_clear_wake_irq(struct device *dev) { - struct wake_irq *wirq = dev->power.wakeirq; + struct wake_irq *wirq; unsigned long flags; - if (!wirq) + spin_lock_irqsave(&dev->power.lock, flags); + wirq = dev->power.wakeirq; + if (!wirq) { + spin_unlock_irqrestore(&dev->power.lock, flags); return; + } - spin_lock_irqsave(&dev->power.lock, flags); device_wakeup_detach_irq(dev); dev->power.wakeirq = NULL; spin_unlock_irqrestore(&dev->power.lock, flags); diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index d1283ff1080bbd..2f630df16bfe10 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -276,9 +276,7 @@ EXPORT_SYMBOL_GPL(wakeup_sources_read_unlock); */ struct wakeup_source *wakeup_sources_walk_start(void) { - struct list_head *ws_head = &wakeup_sources; - - return list_entry_rcu(ws_head->next, struct wakeup_source, entry); + return list_first_or_null_rcu(&wakeup_sources, struct wakeup_source, entry); } EXPORT_SYMBOL_GPL(wakeup_sources_walk_start); diff --git a/drivers/base/regmap/regcache-maple.c b/drivers/base/regmap/regcache-maple.c index 2319c30283a6d9..9cf0384ce7b95b 100644 --- a/drivers/base/regmap/regcache-maple.c +++ b/drivers/base/regmap/regcache-maple.c @@ -95,12 +95,13 @@ static int regcache_maple_write(struct regmap *map, unsigned int reg, mas_unlock(&mas); - if (ret == 0) { - kfree(lower); - kfree(upper); + if (ret) { + kfree(entry); + return ret; } - - return ret; + kfree(lower); + kfree(upper); + return 0; } static int regcache_maple_drop(struct regmap *map, unsigned int min, diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index ce9be3989a218d..ae2215d4e61c3e 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -408,9 +408,11 @@ static void regmap_lock_hwlock_irq(void *__map) static void regmap_lock_hwlock_irqsave(void *__map) { struct regmap *map = __map; + unsigned long flags = 0; hwspin_lock_timeout_irqsave(map->hwlock, UINT_MAX, - &map->spinlock_flags); + &flags); + map->spinlock_flags = flags; } static void regmap_unlock_hwlock(void *__map) diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index c73376886e7a51..1f6ac9202b66a1 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2659,9 +2659,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig * connect. */ .max_hw_sectors = DRBD_MAX_BIO_SIZE_SAFE >> 8, - .features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | - BLK_FEAT_ROTATIONAL | - BLK_FEAT_STABLE_WRITES, }; device = minor_to_device(minor); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 91f3b8afb63ce6..b502038be0a923 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -1296,6 +1296,8 @@ void drbd_reconsider_queue_parameters(struct drbd_device *device, lim.max_segments = drbd_backing_dev_max_segments(device); } else { lim.max_segments = BLK_MAX_SEGMENTS; + lim.features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | + BLK_FEAT_ROTATIONAL | BLK_FEAT_STABLE_WRITES; } lim.max_hw_sectors = new >> SECTOR_SHIFT; @@ -1318,8 +1320,24 @@ void drbd_reconsider_queue_parameters(struct drbd_device *device, lim.max_hw_discard_sectors = 0; } - if (bdev) + if (bdev) { blk_stack_limits(&lim, &b->limits, 0); + /* + * blk_set_stacking_limits() cleared the features, and + * blk_stack_limits() may or may not have inherited + * BLK_FEAT_STABLE_WRITES from the backing device. + * + * DRBD always requires stable writes because: + * 1. The same bio data is read for both local disk I/O and + * network transmission. If the page changes mid-flight, + * the local and remote copies could diverge. + * 2. When data integrity is enabled, DRBD calculates a + * checksum before sending the data. If the page changes + * between checksum calculation and transmission, the + * receiver will detect a checksum mismatch. + */ + lim.features |= BLK_FEAT_STABLE_WRITES; + } /* * If we can handle "zeroes" efficiently on the protocol, we want to do diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 5336c3c5ca362d..c28786e0fe1c85 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -329,7 +329,7 @@ static bool initialized; * This default is used whenever the current disk size is unknown. * [Now it is rather a minimum] */ -#define MAX_DISK_SIZE 4 /* 3984 */ +#define MAX_DISK_SIZE (PAGE_SIZE / 1024) /* * globals used by 'result()' diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index a853c65ac65dfe..a05ff68e58d063 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1024,9 +1024,9 @@ static void recv_work(struct work_struct *work) nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); - nbd_config_put(nbd); atomic_dec(&config->recv_threads); wake_up(&config->recv_wq); + nbd_config_put(nbd); kfree(args); } @@ -2241,12 +2241,13 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info) ret = nbd_start_device(nbd); out: - mutex_unlock(&nbd->config_lock); if (!ret) { set_bit(NBD_RT_HAS_CONFIG_REF, &config->runtime_flags); refcount_inc(&nbd->config_refs); nbd_connect_reply(info, nbd->index); } + mutex_unlock(&nbd->config_lock); + nbd_config_put(nbd); if (put_dev) nbd_put(nbd); diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 0ee55f889cfdd3..50938881219bca 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -665,12 +665,22 @@ static void nullb_add_fault_config(struct nullb_device *dev) configfs_add_default_group(&dev->init_hctx_fault_config.group, &dev->group); } +static void nullb_del_fault_config(struct nullb_device *dev) +{ + config_item_put(&dev->init_hctx_fault_config.group.cg_item); + config_item_put(&dev->requeue_config.group.cg_item); + config_item_put(&dev->timeout_config.group.cg_item); +} + #else static void nullb_add_fault_config(struct nullb_device *dev) { } +static void nullb_del_fault_config(struct nullb_device *dev) +{ +} #endif static struct @@ -702,7 +712,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item) null_del_dev(dev->nullb); mutex_unlock(&lock); } - + nullb_del_fault_config(dev); config_item_put(item); } diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index dc9e4a14b88545..8892f218a81479 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -85,10 +85,14 @@ static void ps3disk_scatter_gather(struct ps3_storage_device *dev, struct bio_vec bvec; rq_for_each_segment(bvec, req, iter) { + dev_dbg(&dev->sbd.core, "%s:%u: %u sectors from %llu\n", + __func__, __LINE__, bio_sectors(iter.bio), + iter.bio->bi_iter.bi_sector); if (gather) memcpy_from_bvec(dev->bounce_buf + offset, &bvec); else memcpy_to_bvec(&bvec, dev->bounce_buf + offset); + offset += bvec.bv_len; } } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index af0e21149dbc9e..8f441eb8b19265 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3495,11 +3495,29 @@ static void rbd_img_object_requests(struct rbd_img_request *img_req) rbd_assert(!need_exclusive_lock(img_req) || __rbd_is_lock_owner(rbd_dev)); - if (rbd_img_is_write(img_req)) { - rbd_assert(!img_req->snapc); + if (test_bit(IMG_REQ_CHILD, &img_req->flags)) { + rbd_assert(!rbd_img_is_write(img_req)); + } else { + struct request *rq = blk_mq_rq_from_pdu(img_req); + u64 off = (u64)blk_rq_pos(rq) << SECTOR_SHIFT; + u64 len = blk_rq_bytes(rq); + u64 mapping_size; + down_read(&rbd_dev->header_rwsem); - img_req->snapc = ceph_get_snap_context(rbd_dev->header.snapc); + mapping_size = rbd_dev->mapping.size; + if (rbd_img_is_write(img_req)) { + rbd_assert(!img_req->snapc); + img_req->snapc = + ceph_get_snap_context(rbd_dev->header.snapc); + } up_read(&rbd_dev->header_rwsem); + + if (unlikely(off + len > mapping_size)) { + rbd_warn(rbd_dev, "beyond EOD (%llu~%llu > %llu)", + off, len, mapping_size); + img_req->pending.result = -EIO; + return; + } } for_each_obj_request(img_req, obj_req) { @@ -4725,7 +4743,6 @@ static void rbd_queue_workfn(struct work_struct *work) struct request *rq = blk_mq_rq_from_pdu(img_request); u64 offset = (u64)blk_rq_pos(rq) << SECTOR_SHIFT; u64 length = blk_rq_bytes(rq); - u64 mapping_size; int result; /* Ignore/skip any zero-length requests */ @@ -4738,17 +4755,9 @@ static void rbd_queue_workfn(struct work_struct *work) blk_mq_start_request(rq); down_read(&rbd_dev->header_rwsem); - mapping_size = rbd_dev->mapping.size; rbd_img_capture_header(img_request); up_read(&rbd_dev->header_rwsem); - if (offset + length > mapping_size) { - rbd_warn(rbd_dev, "beyond EOD (%llu~%llu > %llu)", offset, - length, mapping_size); - result = -EIO; - goto err_img_request; - } - dout("%s rbd_dev %p img_req %p %s %llu~%llu\n", __func__, rbd_dev, img_request, obj_op_name(op_type), offset, length); diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index f1409e54010a67..d1c354636315d2 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1423,9 +1423,11 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, goto out_alloc; } - ret = ida_alloc_max(&index_ida, (1 << (MINORBITS - RNBD_PART_BITS)) - 1, - GFP_KERNEL); - if (ret < 0) { + dev->clt_device_id = ida_alloc_max(&index_ida, + (1 << (MINORBITS - RNBD_PART_BITS)) - 1, + GFP_KERNEL); + if (dev->clt_device_id < 0) { + ret = dev->clt_device_id; pr_err("Failed to initialize device '%s' from session %s, allocating idr failed, err: %d\n", pathname, sess->sessname, ret); goto out_queues; @@ -1434,10 +1436,9 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, dev->pathname = kstrdup(pathname, GFP_KERNEL); if (!dev->pathname) { ret = -ENOMEM; - goto out_queues; + goto out_ida; } - dev->clt_device_id = ret; dev->sess = sess; dev->access_mode = access_mode; dev->nr_poll_queues = nr_poll_queues; @@ -1453,6 +1454,8 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, return dev; +out_ida: + ida_free(&index_ida, dev->clt_device_id); out_queues: kfree(dev->hw_queues); out_alloc: diff --git a/drivers/block/rnbd/rnbd-clt.h b/drivers/block/rnbd/rnbd-clt.h index a48e040abe639d..fbc1ed766025c1 100644 --- a/drivers/block/rnbd/rnbd-clt.h +++ b/drivers/block/rnbd/rnbd-clt.h @@ -112,7 +112,7 @@ struct rnbd_clt_dev { struct rnbd_queue *hw_queues; u32 device_id; /* local Idr index - used to track minor number allocations. */ - u32 clt_device_id; + int clt_device_id; struct mutex lock; enum rnbd_clt_dev_state dev_state; refcount_t refcount; diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index 2df8941a6b1463..9b3fdc202e1521 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -145,18 +145,30 @@ static int process_rdma(struct rnbd_srv_session *srv_sess, priv->sess_dev = sess_dev; priv->id = id; - bio = bio_alloc(file_bdev(sess_dev->bdev_file), 1, + bio = bio_alloc(file_bdev(sess_dev->bdev_file), !!datalen, rnbd_to_bio_flags(le32_to_cpu(msg->rw)), GFP_KERNEL); - bio_add_virt_nofail(bio, data, datalen); - - bio->bi_opf = rnbd_to_bio_flags(le32_to_cpu(msg->rw)); - if (bio_has_data(bio) && - bio->bi_iter.bi_size != le32_to_cpu(msg->bi_size)) { - rnbd_srv_err_rl(sess_dev, "Datalen mismatch: bio bi_size (%u), bi_size (%u)\n", - bio->bi_iter.bi_size, msg->bi_size); - err = -EINVAL; - goto bio_put; + if (unlikely(!bio)) { + err = -ENOMEM; + goto put_sess_dev; } + + if (!datalen) { + /* + * For special requests like DISCARD and WRITE_ZEROES, the datalen is zero. + */ + bio->bi_iter.bi_size = le32_to_cpu(msg->bi_size); + } else { + bio_add_virt_nofail(bio, data, datalen); + bio->bi_opf = rnbd_to_bio_flags(le32_to_cpu(msg->rw)); + if (bio->bi_iter.bi_size != le32_to_cpu(msg->bi_size)) { + rnbd_srv_err_rl(sess_dev, + "Datalen mismatch: bio bi_size (%u), bi_size (%u)\n", + bio->bi_iter.bi_size, msg->bi_size); + err = -EINVAL; + goto bio_put; + } + } + bio->bi_end_io = rnbd_dev_bi_end_io; bio->bi_private = priv; bio->bi_iter.bi_sector = le64_to_cpu(msg->sector); @@ -170,6 +182,7 @@ static int process_rdma(struct rnbd_srv_session *srv_sess, bio_put: bio_put(bio); +put_sess_dev: rnbd_put_sess_dev(sess_dev); err: kfree(priv); diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 0c74a41a675300..965460d4fc76ea 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -155,12 +155,13 @@ struct ublk_uring_cmd_pdu { */ #define UBLK_REFCOUNT_INIT (REFCOUNT_MAX / 2) +union ublk_io_buf { + __u64 addr; + struct ublk_auto_buf_reg auto_reg; +}; + struct ublk_io { - /* userspace buffer address from io cmd */ - union { - __u64 addr; - struct ublk_auto_buf_reg buf; - }; + union ublk_io_buf buf; unsigned int flags; int res; @@ -209,9 +210,6 @@ struct ublk_queue { struct ublk_device { struct gendisk *ub_disk; - char *__queues; - - unsigned int queue_size; struct ublksrv_ctrl_dev_info dev_info; struct blk_mq_tag_set tag_set; @@ -239,6 +237,9 @@ struct ublk_device { bool canceling; pid_t ublksrv_tgid; struct delayed_work exit_work; + struct work_struct partition_scan_work; + + struct ublk_queue *queues[]; }; /* header of ublk_params */ @@ -499,7 +500,7 @@ static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq, iod->op_flags = ublk_op | ublk_req_build_flags(req); iod->nr_sectors = blk_rq_sectors(req); iod->start_sector = blk_rq_pos(req); - iod->addr = io->addr; + iod->addr = io->buf.addr; return BLK_STS_OK; } @@ -781,7 +782,7 @@ static noinline void ublk_put_device(struct ublk_device *ub) static inline struct ublk_queue *ublk_get_queue(struct ublk_device *dev, int qid) { - return (struct ublk_queue *)&(dev->__queues[qid * dev->queue_size]); + return dev->queues[qid]; } static inline bool ublk_rq_has_data(const struct request *rq) @@ -1047,7 +1048,7 @@ static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req, struct iov_iter iter; const int dir = ITER_DEST; - import_ubuf(dir, u64_to_user_ptr(io->addr), rq_bytes, &iter); + import_ubuf(dir, u64_to_user_ptr(io->buf.addr), rq_bytes, &iter); return ublk_copy_user_pages(req, 0, &iter, dir); } return rq_bytes; @@ -1068,7 +1069,7 @@ static int ublk_unmap_io(bool need_map, WARN_ON_ONCE(io->res > rq_bytes); - import_ubuf(dir, u64_to_user_ptr(io->addr), io->res, &iter); + import_ubuf(dir, u64_to_user_ptr(io->buf.addr), io->res, &iter); return ublk_copy_user_pages(req, 0, &iter, dir); } return rq_bytes; @@ -1134,7 +1135,7 @@ static blk_status_t ublk_setup_iod(struct ublk_queue *ubq, struct request *req) iod->op_flags = ublk_op | ublk_req_build_flags(req); iod->nr_sectors = blk_rq_sectors(req); iod->start_sector = blk_rq_pos(req); - iod->addr = io->addr; + iod->addr = io->buf.addr; return BLK_STS_OK; } @@ -1145,12 +1146,20 @@ static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu( return io_uring_cmd_to_pdu(ioucmd, struct ublk_uring_cmd_pdu); } +static void ublk_end_request(struct request *req, blk_status_t error) +{ + local_bh_disable(); + blk_mq_end_request(req, error); + local_bh_enable(); +} + /* todo: handle partial completion */ static inline void __ublk_complete_rq(struct request *req, struct ublk_io *io, bool need_map) { unsigned int unmapped_bytes; blk_status_t res = BLK_STS_OK; + bool requeue; /* failed read IO if nothing is read */ if (!io->res && req_op(req) == REQ_OP_READ) @@ -1182,14 +1191,30 @@ static inline void __ublk_complete_rq(struct request *req, struct ublk_io *io, if (unlikely(unmapped_bytes < io->res)) io->res = unmapped_bytes; - if (blk_update_request(req, BLK_STS_OK, io->res)) + /* + * Run bio->bi_end_io() with softirqs disabled. If the final fput + * happens off this path, then that will prevent ublk's blkdev_release() + * from being called on current's task work, see fput() implementation. + * + * Otherwise, ublk server may not provide forward progress in case of + * reading the partition table from bdev_open() with disk->open_mutex + * held, and causes dead lock as we could already be holding + * disk->open_mutex here. + * + * Preferably we would not be doing IO with a mutex held that is also + * used for release, but this work-around will suffice for now. + */ + local_bh_disable(); + requeue = blk_update_request(req, BLK_STS_OK, io->res); + local_bh_enable(); + if (requeue) blk_mq_requeue_request(req, true); else if (likely(!blk_should_fake_timeout(req->q))) __blk_mq_end_request(req, BLK_STS_OK); return; exit: - blk_mq_end_request(req, res); + ublk_end_request(req, res); } static struct io_uring_cmd *__ublk_prep_compl_io_cmd(struct ublk_io *io, @@ -1229,49 +1254,69 @@ static inline void __ublk_abort_rq(struct ublk_queue *ubq, if (ublk_nosrv_dev_should_queue_io(ubq->dev)) blk_mq_requeue_request(rq, false); else - blk_mq_end_request(rq, BLK_STS_IOERR); + ublk_end_request(rq, BLK_STS_IOERR); } static void -ublk_auto_buf_reg_fallback(const struct ublk_queue *ubq, struct ublk_io *io) +ublk_auto_buf_reg_fallback(const struct ublk_queue *ubq, unsigned tag) { - unsigned tag = io - ubq->ios; struct ublksrv_io_desc *iod = ublk_get_iod(ubq, tag); iod->op_flags |= UBLK_IO_F_NEED_REG_BUF; } -static bool ublk_auto_buf_reg(const struct ublk_queue *ubq, struct request *req, - struct ublk_io *io, unsigned int issue_flags) +enum auto_buf_reg_res { + AUTO_BUF_REG_FAIL, + AUTO_BUF_REG_FALLBACK, + AUTO_BUF_REG_OK, +}; + +static void ublk_prep_auto_buf_reg_io(const struct ublk_queue *ubq, + struct request *req, struct ublk_io *io, + struct io_uring_cmd *cmd, + enum auto_buf_reg_res res) +{ + if (res == AUTO_BUF_REG_OK) { + io->task_registered_buffers = 1; + io->buf_ctx_handle = io_uring_cmd_ctx_handle(cmd); + io->flags |= UBLK_IO_FLAG_AUTO_BUF_REG; + } + ublk_init_req_ref(ubq, io); + __ublk_prep_compl_io_cmd(io, req); +} + +static enum auto_buf_reg_res +__ublk_do_auto_buf_reg(const struct ublk_queue *ubq, struct request *req, + struct ublk_io *io, struct io_uring_cmd *cmd, + unsigned int issue_flags) { int ret; - ret = io_buffer_register_bvec(io->cmd, req, ublk_io_release, - io->buf.index, issue_flags); + ret = io_buffer_register_bvec(cmd, req, ublk_io_release, + io->buf.auto_reg.index, issue_flags); if (ret) { - if (io->buf.flags & UBLK_AUTO_BUF_REG_FALLBACK) { - ublk_auto_buf_reg_fallback(ubq, io); - return true; + if (io->buf.auto_reg.flags & UBLK_AUTO_BUF_REG_FALLBACK) { + ublk_auto_buf_reg_fallback(ubq, req->tag); + return AUTO_BUF_REG_FALLBACK; } - blk_mq_end_request(req, BLK_STS_IOERR); - return false; + ublk_end_request(req, BLK_STS_IOERR); + return AUTO_BUF_REG_FAIL; } - io->task_registered_buffers = 1; - io->buf_ctx_handle = io_uring_cmd_ctx_handle(io->cmd); - io->flags |= UBLK_IO_FLAG_AUTO_BUF_REG; - return true; + return AUTO_BUF_REG_OK; } -static bool ublk_prep_auto_buf_reg(struct ublk_queue *ubq, - struct request *req, struct ublk_io *io, - unsigned int issue_flags) +static void ublk_do_auto_buf_reg(const struct ublk_queue *ubq, struct request *req, + struct ublk_io *io, struct io_uring_cmd *cmd, + unsigned int issue_flags) { - ublk_init_req_ref(ubq, io); - if (ublk_support_auto_buf_reg(ubq) && ublk_rq_has_data(req)) - return ublk_auto_buf_reg(ubq, req, io, issue_flags); + enum auto_buf_reg_res res = __ublk_do_auto_buf_reg(ubq, req, io, cmd, + issue_flags); - return true; + if (res != AUTO_BUF_REG_FAIL) { + ublk_prep_auto_buf_reg_io(ubq, req, io, cmd, res); + io_uring_cmd_done(cmd, UBLK_IO_RES_OK, issue_flags); + } } static bool ublk_start_io(const struct ublk_queue *ubq, struct request *req, @@ -1344,8 +1389,12 @@ static void ublk_dispatch_req(struct ublk_queue *ubq, if (!ublk_start_io(ubq, req, io)) return; - if (ublk_prep_auto_buf_reg(ubq, req, io, issue_flags)) + if (ublk_support_auto_buf_reg(ubq) && ublk_rq_has_data(req)) { + ublk_do_auto_buf_reg(ubq, req, io, io->cmd, issue_flags); + } else { + ublk_init_req_ref(ubq, io); ublk_complete_io_cmd(io, req, UBLK_IO_RES_OK, issue_flags); + } } static void ublk_cmd_tw_cb(struct io_uring_cmd *cmd, @@ -1537,7 +1586,7 @@ static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) */ io->flags &= UBLK_IO_FLAG_CANCELED; io->cmd = NULL; - io->addr = 0; + io->buf.addr = 0; /* * old task is PF_EXITING, put it now @@ -1600,6 +1649,27 @@ static void ublk_put_disk(struct gendisk *disk) put_device(disk_to_dev(disk)); } +static void ublk_partition_scan_work(struct work_struct *work) +{ + struct ublk_device *ub = + container_of(work, struct ublk_device, partition_scan_work); + /* Hold disk reference to prevent UAF during concurrent teardown */ + struct gendisk *disk = ublk_get_disk(ub); + + if (!disk) + return; + + if (WARN_ON_ONCE(!test_and_clear_bit(GD_SUPPRESS_PART_SCAN, + &disk->state))) + goto out; + + mutex_lock(&disk->open_mutex); + bdev_disk_changed(disk, false); + mutex_unlock(&disk->open_mutex); +out: + ublk_put_disk(disk); +} + /* * Use this function to ensure that ->canceling is consistently set for * the device and all queues. Do not set these flags directly. @@ -1625,8 +1695,7 @@ static bool ublk_check_and_reset_active_ref(struct ublk_device *ub) { int i, j; - if (!(ub->dev_info.flags & (UBLK_F_SUPPORT_ZERO_COPY | - UBLK_F_AUTO_BUF_REG))) + if (!ublk_dev_need_req_ref(ub)) return false; for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { @@ -2045,6 +2114,7 @@ static void ublk_stop_dev(struct ublk_device *ub) mutex_lock(&ub->mutex); ublk_stop_dev_unlocked(ub); mutex_unlock(&ub->mutex); + cancel_work_sync(&ub->partition_scan_work); ublk_cancel_dev(ub); } @@ -2098,13 +2168,16 @@ static inline int ublk_check_cmd_op(u32 cmd_op) static inline int ublk_set_auto_buf_reg(struct ublk_io *io, struct io_uring_cmd *cmd) { - io->buf = ublk_sqe_addr_to_auto_buf_reg(READ_ONCE(cmd->sqe->addr)); + struct ublk_auto_buf_reg buf; + + buf = ublk_sqe_addr_to_auto_buf_reg(READ_ONCE(cmd->sqe->addr)); - if (io->buf.reserved0 || io->buf.reserved1) + if (buf.reserved0 || buf.reserved1) return -EINVAL; - if (io->buf.flags & ~UBLK_AUTO_BUF_REG_F_MASK) + if (buf.flags & ~UBLK_AUTO_BUF_REG_F_MASK) return -EINVAL; + io->buf.auto_reg = buf; return 0; } @@ -2126,7 +2199,7 @@ static int ublk_handle_auto_buf_reg(struct ublk_io *io, * this ublk request gets stuck. */ if (io->buf_ctx_handle == io_uring_cmd_ctx_handle(cmd)) - *buf_idx = io->buf.index; + *buf_idx = io->buf.auto_reg.index; } return ublk_set_auto_buf_reg(io, cmd); @@ -2154,7 +2227,7 @@ ublk_config_io_buf(const struct ublk_device *ub, struct ublk_io *io, if (ublk_dev_support_auto_buf_reg(ub)) return ublk_handle_auto_buf_reg(io, cmd, buf_idx); - io->addr = buf_addr; + io->buf.addr = buf_addr; return 0; } @@ -2351,7 +2424,7 @@ static bool ublk_get_data(const struct ublk_queue *ubq, struct ublk_io *io, */ io->flags &= ~UBLK_IO_FLAG_NEED_GET_DATA; /* update iod->addr because ublksrv may have passed a new io buffer */ - ublk_get_iod(ubq, req->tag)->addr = io->addr; + ublk_get_iod(ubq, req->tag)->addr = io->buf.addr; pr_devel("%s: update iod->addr: qid %d tag %d io_flags %x addr %llx\n", __func__, ubq->q_id, req->tag, io->flags, ublk_get_iod(ubq, req->tag)->addr); @@ -2367,7 +2440,7 @@ static int ublk_ch_uring_cmd_local(struct io_uring_cmd *cmd, u16 buf_idx = UBLK_INVALID_BUF_IDX; struct ublk_device *ub = cmd->file->private_data; struct ublk_queue *ubq; - struct ublk_io *io; + struct ublk_io *io = NULL; u32 cmd_op = cmd->cmd_op; u16 q_id = READ_ONCE(ub_src->q_id); u16 tag = READ_ONCE(ub_src->tag); @@ -2453,11 +2526,11 @@ static int ublk_ch_uring_cmd_local(struct io_uring_cmd *cmd, io->res = result; req = ublk_fill_io_cmd(io, cmd); ret = ublk_config_io_buf(ub, io, cmd, addr, &buf_idx); + if (buf_idx != UBLK_INVALID_BUF_IDX) + io_buffer_unregister_bvec(cmd, buf_idx, issue_flags); compl = ublk_need_complete_req(ub, io); /* can't touch 'ublk_io' any more */ - if (buf_idx != UBLK_INVALID_BUF_IDX) - io_buffer_unregister_bvec(cmd, buf_idx, issue_flags); if (req_op(req) == REQ_OP_ZONE_APPEND) req->__sector = addr; if (compl) @@ -2488,7 +2561,7 @@ static int ublk_ch_uring_cmd_local(struct io_uring_cmd *cmd, out: pr_devel("%s: complete: cmd op %d, tag %d ret %x io_flags %x\n", - __func__, cmd_op, tag, ret, io->flags); + __func__, cmd_op, tag, ret, io ? io->flags : 0); return ret; } @@ -2662,9 +2735,13 @@ static const struct file_operations ublk_ch_fops = { static void ublk_deinit_queue(struct ublk_device *ub, int q_id) { - int size = ublk_queue_cmd_buf_size(ub); - struct ublk_queue *ubq = ublk_get_queue(ub, q_id); - int i; + struct ublk_queue *ubq = ub->queues[q_id]; + int size, i; + + if (!ubq) + return; + + size = ublk_queue_cmd_buf_size(ub); for (i = 0; i < ubq->q_depth; i++) { struct ublk_io *io = &ubq->ios[i]; @@ -2676,57 +2753,76 @@ static void ublk_deinit_queue(struct ublk_device *ub, int q_id) if (ubq->io_cmd_buf) free_pages((unsigned long)ubq->io_cmd_buf, get_order(size)); + + kvfree(ubq); + ub->queues[q_id] = NULL; +} + +static int ublk_get_queue_numa_node(struct ublk_device *ub, int q_id) +{ + unsigned int cpu; + + /* Find first CPU mapped to this queue */ + for_each_possible_cpu(cpu) { + if (ub->tag_set.map[HCTX_TYPE_DEFAULT].mq_map[cpu] == q_id) + return cpu_to_node(cpu); + } + + return NUMA_NO_NODE; } static int ublk_init_queue(struct ublk_device *ub, int q_id) { - struct ublk_queue *ubq = ublk_get_queue(ub, q_id); + int depth = ub->dev_info.queue_depth; + int ubq_size = sizeof(struct ublk_queue) + depth * sizeof(struct ublk_io); gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO; - void *ptr; + struct ublk_queue *ubq; + struct page *page; + int numa_node; int size; + /* Determine NUMA node based on queue's CPU affinity */ + numa_node = ublk_get_queue_numa_node(ub, q_id); + + /* Allocate queue structure on local NUMA node */ + ubq = kvzalloc_node(ubq_size, GFP_KERNEL, numa_node); + if (!ubq) + return -ENOMEM; + spin_lock_init(&ubq->cancel_lock); ubq->flags = ub->dev_info.flags; ubq->q_id = q_id; - ubq->q_depth = ub->dev_info.queue_depth; + ubq->q_depth = depth; size = ublk_queue_cmd_buf_size(ub); - ptr = (void *) __get_free_pages(gfp_flags, get_order(size)); - if (!ptr) + /* Allocate I/O command buffer on local NUMA node */ + page = alloc_pages_node(numa_node, gfp_flags, get_order(size)); + if (!page) { + kvfree(ubq); return -ENOMEM; + } + ubq->io_cmd_buf = page_address(page); - ubq->io_cmd_buf = ptr; + ub->queues[q_id] = ubq; ubq->dev = ub; return 0; } static void ublk_deinit_queues(struct ublk_device *ub) { - int nr_queues = ub->dev_info.nr_hw_queues; int i; - if (!ub->__queues) - return; - - for (i = 0; i < nr_queues; i++) + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) ublk_deinit_queue(ub, i); - kvfree(ub->__queues); } static int ublk_init_queues(struct ublk_device *ub) { - int nr_queues = ub->dev_info.nr_hw_queues; - int depth = ub->dev_info.queue_depth; - int ubq_size = sizeof(struct ublk_queue) + depth * sizeof(struct ublk_io); - int i, ret = -ENOMEM; + int i, ret; - ub->queue_size = ubq_size; - ub->__queues = kvcalloc(nr_queues, ubq_size, GFP_KERNEL); - if (!ub->__queues) - return ret; - - for (i = 0; i < nr_queues; i++) { - if (ublk_init_queue(ub, i)) + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { + ret = ublk_init_queue(ub, i); + if (ret) goto fail; } @@ -2858,6 +2954,15 @@ static struct ublk_device *ublk_get_device_from_id(int idx) return ub; } +static bool ublk_validate_user_pid(struct ublk_device *ub, pid_t ublksrv_pid) +{ + rcu_read_lock(); + ublksrv_pid = pid_nr(find_vpid(ublksrv_pid)); + rcu_read_unlock(); + + return ub->ublksrv_tgid == ublksrv_pid; +} + static int ublk_ctrl_start_dev(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header) { @@ -2926,7 +3031,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, if (wait_for_completion_interruptible(&ub->completion) != 0) return -EINTR; - if (ub->ublksrv_tgid != ublksrv_pid) + if (!ublk_validate_user_pid(ub, ublksrv_pid)) return -EINVAL; mutex_lock(&ub->mutex); @@ -2945,14 +3050,22 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, disk->fops = &ub_fops; disk->private_data = ub; - ub->dev_info.ublksrv_pid = ublksrv_pid; + ub->dev_info.ublksrv_pid = ub->ublksrv_tgid; ub->ub_disk = disk; ublk_apply_params(ub); - /* don't probe partitions if any daemon task is un-trusted */ - if (ub->unprivileged_daemons) - set_bit(GD_SUPPRESS_PART_SCAN, &disk->state); + /* + * Suppress partition scan to avoid potential IO hang. + * + * If ublk server error occurs during partition scan, the IO may + * wait while holding ub->mutex, which can deadlock with other + * operations that need the mutex. Defer partition scan to async + * work. + * For unprivileged daemons, keep GD_SUPPRESS_PART_SCAN set + * permanently. + */ + set_bit(GD_SUPPRESS_PART_SCAN, &disk->state); ublk_get_device(ub); ub->dev_info.state = UBLK_S_DEV_LIVE; @@ -2969,6 +3082,10 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, set_bit(UB_STATE_USED, &ub->state); + /* Schedule async partition scan for trusted daemons */ + if (!ub->unprivileged_daemons) + schedule_work(&ub->partition_scan_work); + out_put_cdev: if (ret) { ublk_detach_disk(ub); @@ -3128,12 +3245,13 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) goto out_unlock; ret = -ENOMEM; - ub = kzalloc(sizeof(*ub), GFP_KERNEL); + ub = kzalloc(struct_size(ub, queues, info.nr_hw_queues), GFP_KERNEL); if (!ub) goto out_unlock; mutex_init(&ub->mutex); spin_lock_init(&ub->lock); mutex_init(&ub->cancel_mutex); + INIT_WORK(&ub->partition_scan_work, ublk_partition_scan_work); ret = ublk_alloc_dev_number(ub, header->dev_id); if (ret < 0) @@ -3178,17 +3296,17 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) ub->dev_info.nr_hw_queues, nr_cpu_ids); ublk_align_max_io_size(ub); - ret = ublk_init_queues(ub); + ret = ublk_add_tag_set(ub); if (ret) goto out_free_dev_number; - ret = ublk_add_tag_set(ub); + ret = ublk_init_queues(ub); if (ret) - goto out_deinit_queues; + goto out_free_tag_set; ret = -EFAULT; if (copy_to_user(argp, &ub->dev_info, sizeof(info))) - goto out_free_tag_set; + goto out_deinit_queues; /* * Add the char dev so that ublksrv daemon can be setup. @@ -3197,10 +3315,10 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) ret = ublk_add_chdev(ub); goto out_unlock; -out_free_tag_set: - blk_mq_free_tag_set(&ub->tag_set); out_deinit_queues: ublk_deinit_queues(ub); +out_free_tag_set: + blk_mq_free_tag_set(&ub->tag_set); out_free_dev_number: ublk_free_dev_number(ub); out_free_ub: @@ -3280,12 +3398,32 @@ static int ublk_ctrl_stop_dev(struct ublk_device *ub) static int ublk_ctrl_get_dev_info(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header) { + struct task_struct *p; + struct pid *pid; + struct ublksrv_ctrl_dev_info dev_info; + pid_t init_ublksrv_tgid = ub->dev_info.ublksrv_pid; void __user *argp = (void __user *)(unsigned long)header->addr; if (header->len < sizeof(struct ublksrv_ctrl_dev_info) || !header->addr) return -EINVAL; - if (copy_to_user(argp, &ub->dev_info, sizeof(ub->dev_info))) + memcpy(&dev_info, &ub->dev_info, sizeof(dev_info)); + dev_info.ublksrv_pid = -1; + + if (init_ublksrv_tgid > 0) { + rcu_read_lock(); + pid = find_pid_ns(init_ublksrv_tgid, &init_pid_ns); + p = pid_task(pid, PIDTYPE_TGID); + if (p) { + int vnr = task_tgid_vnr(p); + + if (vnr) + dev_info.ublksrv_pid = vnr; + } + rcu_read_unlock(); + } + + if (copy_to_user(argp, &dev_info, sizeof(dev_info))) return -EFAULT; return 0; @@ -3430,7 +3568,7 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, pr_devel("%s: All FETCH_REQs received, dev id %d\n", __func__, header->dev_id); - if (ub->ublksrv_tgid != ublksrv_pid) + if (!ublk_validate_user_pid(ub, ublksrv_pid)) return -EINVAL; mutex_lock(&ub->mutex); @@ -3441,7 +3579,7 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, ret = -EBUSY; goto out_unlock; } - ub->dev_info.ublksrv_pid = ublksrv_pid; + ub->dev_info.ublksrv_pid = ub->ublksrv_tgid; ub->dev_info.state = UBLK_S_DEV_LIVE; pr_devel("%s: new ublksrv_pid %d, dev id %d\n", __func__, ublksrv_pid, header->dev_id); @@ -3703,10 +3841,10 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; - ublk_ctrl_cmd_dump(cmd); - if (!(issue_flags & IO_URING_F_SQE128)) - goto out; + return -EINVAL; + + ublk_ctrl_cmd_dump(cmd); ret = ublk_check_cmd_op(cmd_op); if (ret) diff --git a/drivers/block/zloop.c b/drivers/block/zloop.c index a423228e201ba3..39a425db670c8b 100644 --- a/drivers/block/zloop.c +++ b/drivers/block/zloop.c @@ -177,7 +177,7 @@ static int zloop_update_seq_zone(struct zloop_device *zlo, unsigned int zone_no) zone->wp = zone->start; } else if (file_sectors == zlo->zone_capacity) { zone->cond = BLK_ZONE_COND_FULL; - zone->wp = zone->start + zlo->zone_size; + zone->wp = ULLONG_MAX; } else { zone->cond = BLK_ZONE_COND_CLOSED; zone->wp = zone->start + file_sectors; @@ -326,7 +326,7 @@ static int zloop_finish_zone(struct zloop_device *zlo, unsigned int zone_no) } zone->cond = BLK_ZONE_COND_FULL; - zone->wp = zone->start + zlo->zone_size; + zone->wp = ULLONG_MAX; clear_bit(ZLOOP_ZONE_SEQ_ERROR, &zone->flags); unlock: @@ -407,6 +407,10 @@ static void zloop_rw(struct zloop_cmd *cmd) mutex_lock(&zone->lock); if (is_append) { + if (zone->cond == BLK_ZONE_COND_FULL) { + ret = -EIO; + goto unlock; + } sector = zone->wp; cmd->sector = sector; } @@ -433,8 +437,10 @@ static void zloop_rw(struct zloop_cmd *cmd) * copmpletes. */ zone->wp += nr_sectors; - if (zone->wp == zone_end) + if (zone->wp == zone_end) { zone->cond = BLK_ZONE_COND_FULL; + zone->wp = ULLONG_MAX; + } } rq_for_each_bvec(tmp, rq, rq_iter) diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index a075d8ec467738..c68a8de3025b05 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -825,6 +825,11 @@ static inline bool btintel_pcie_in_d0(struct btintel_pcie_data *data) return !(data->boot_stage_cache & BTINTEL_PCIE_CSR_BOOT_STAGE_D3_STATE_READY); } +static inline bool btintel_pcie_in_device_halt(struct btintel_pcie_data *data) +{ + return data->boot_stage_cache & BTINTEL_PCIE_CSR_BOOT_STAGE_DEVICE_HALTED; +} + static void btintel_pcie_wr_sleep_cntrl(struct btintel_pcie_data *data, u32 dxstate) { @@ -1425,11 +1430,6 @@ static void btintel_pcie_msix_rx_handle(struct btintel_pcie_data *data) } } -static irqreturn_t btintel_pcie_msix_isr(int irq, void *data) -{ - return IRQ_WAKE_THREAD; -} - static inline bool btintel_pcie_is_rxq_empty(struct btintel_pcie_data *data) { return data->ia.cr_hia[BTINTEL_PCIE_RXQ_NUM] == data->ia.cr_tia[BTINTEL_PCIE_RXQ_NUM]; @@ -1531,9 +1531,9 @@ static int btintel_pcie_setup_irq(struct btintel_pcie_data *data) err = devm_request_threaded_irq(&data->pdev->dev, msix_entry->vector, - btintel_pcie_msix_isr, + NULL, btintel_pcie_irq_msix_handler, - IRQF_SHARED, + IRQF_ONESHOT | IRQF_SHARED, KBUILD_MODNAME, msix_entry); if (err) { @@ -2532,6 +2532,8 @@ static int btintel_pcie_suspend_late(struct device *dev, pm_message_t mesg) dxstate = (mesg.event == PM_EVENT_SUSPEND ? BTINTEL_PCIE_STATE_D3_HOT : BTINTEL_PCIE_STATE_D3_COLD); + data->pm_sx_event = mesg.event; + data->gp0_received = false; start = ktime_get(); @@ -2581,6 +2583,20 @@ static int btintel_pcie_resume(struct device *dev) start = ktime_get(); + /* When the system enters S4 (hibernate) mode, bluetooth device loses + * power, which results in the erasure of its loaded firmware. + * Consequently, function level reset (flr) is required on system + * resume to bring the controller back into an operational state by + * initiating a new firmware download. + */ + + if (data->pm_sx_event == PM_EVENT_FREEZE || + data->pm_sx_event == PM_EVENT_HIBERNATE) { + set_bit(BTINTEL_PCIE_CORE_HALTED, &data->flags); + btintel_pcie_reset(data->hdev); + return 0; + } + /* Refer: 6.4.11.7 -> Platform power management */ btintel_pcie_wr_sleep_cntrl(data, BTINTEL_PCIE_STATE_D0); err = wait_event_timeout(data->gp0_wait_q, data->gp0_received, @@ -2589,6 +2605,26 @@ static int btintel_pcie_resume(struct device *dev) bt_dev_err(data->hdev, "Timeout (%u ms) on alive interrupt for D0 entry", BTINTEL_DEFAULT_INTR_TIMEOUT_MS); + + /* Trigger function level reset if the controller is in error + * state during resume() to bring back the controller to + * operational mode + */ + + data->boot_stage_cache = btintel_pcie_rd_reg32(data, + BTINTEL_PCIE_CSR_BOOT_STAGE_REG); + if (btintel_pcie_in_error(data) || + btintel_pcie_in_device_halt(data)) { + bt_dev_err(data->hdev, "Controller in error state for D0 entry"); + if (!test_and_set_bit(BTINTEL_PCIE_COREDUMP_INPROGRESS, + &data->flags)) { + data->dmp_hdr.trigger_reason = + BTINTEL_PCIE_TRIGGER_REASON_FW_ASSERT; + queue_work(data->workqueue, &data->rx_work); + } + set_bit(BTINTEL_PCIE_CORE_HALTED, &data->flags); + btintel_pcie_reset(data->hdev); + } return -EBUSY; } diff --git a/drivers/bluetooth/btintel_pcie.h b/drivers/bluetooth/btintel_pcie.h index 04b21f968ad30f..48e1ae1793e5cf 100644 --- a/drivers/bluetooth/btintel_pcie.h +++ b/drivers/bluetooth/btintel_pcie.h @@ -464,6 +464,7 @@ struct btintel_pcie_dump_header { * @txq: TX Queue struct * @rxq: RX Queue struct * @alive_intr_ctxt: Alive interrupt context + * @pm_sx_event: PM event on which system got suspended */ struct btintel_pcie_data { struct pci_dev *pdev; @@ -513,6 +514,7 @@ struct btintel_pcie_data { u32 alive_intr_ctxt; struct btintel_pcie_dbgc dbgc; struct btintel_pcie_dump_header dmp_hdr; + u8 pm_sx_event; }; static inline u32 btintel_pcie_rd_reg32(struct btintel_pcie_data *data, diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index fa683bb7f0b494..a953fa9af85c64 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -504,6 +504,8 @@ static const struct usb_device_id quirks_table[] = { /* Realtek 8821CE Bluetooth devices */ { USB_DEVICE(0x13d3, 0x3529), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x13d3, 0x3533), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek 8822CE Bluetooth devices */ { USB_DEVICE(0x0bda, 0xb00c), .driver_info = BTUSB_REALTEK | @@ -525,6 +527,8 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x2001, 0x332a), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x7392, 0xe611), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek 8852AE Bluetooth devices */ { USB_DEVICE(0x0bda, 0x2852), .driver_info = BTUSB_REALTEK | @@ -585,6 +589,8 @@ static const struct usb_device_id quirks_table[] = { /* Realtek 8852BT/8852BE-VT Bluetooth devices */ { USB_DEVICE(0x0bda, 0x8520), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0489, 0xe12f), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek 8922AE Bluetooth devices */ { USB_DEVICE(0x0bda, 0x8922), .driver_info = BTUSB_REALTEK | @@ -621,6 +627,8 @@ static const struct usb_device_id quirks_table[] = { /* Additional MediaTek MT7920 Bluetooth devices */ { USB_DEVICE(0x0489, 0xe134), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0489, 0xe135), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3620), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3621), .driver_info = BTUSB_MEDIATEK | @@ -685,6 +693,8 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0489, 0xe153), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0489, 0xe170), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x04ca, 0x3804), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x04ca, 0x38e4), .driver_info = BTUSB_MEDIATEK | @@ -781,6 +791,8 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x2b89, 0x8761), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x2b89, 0x6275), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Additional Realtek 8821AE Bluetooth devices */ { USB_DEVICE(0x0b05, 0x17dc), .driver_info = BTUSB_REALTEK }, @@ -3261,6 +3273,7 @@ static const struct qca_device_info qca_devices_table[] = { static const struct qca_custom_firmware qca_custom_btfws[] = { { 0x00130201, 0x030A, "QCA2066" }, + { 0x00130201, 0x030B, "QCA2066" }, { }, }; @@ -4006,7 +4019,7 @@ static int btusb_probe(struct usb_interface *intf, return -ENODEV; } - data = devm_kzalloc(&intf->dev, sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; @@ -4029,8 +4042,10 @@ static int btusb_probe(struct usb_interface *intf, } } - if (!data->intr_ep || !data->bulk_tx_ep || !data->bulk_rx_ep) + if (!data->intr_ep || !data->bulk_tx_ep || !data->bulk_rx_ep) { + kfree(data); return -ENODEV; + } if (id->driver_info & BTUSB_AMP) { data->cmdreq_type = USB_TYPE_CLASS | 0x01; @@ -4085,8 +4100,10 @@ static int btusb_probe(struct usb_interface *intf, data->recv_acl = hci_recv_frame; hdev = hci_alloc_dev_priv(priv_size); - if (!hdev) + if (!hdev) { + kfree(data); return -ENOMEM; + } hdev->bus = HCI_USB; hci_set_drvdata(hdev, data); @@ -4359,6 +4376,7 @@ static int btusb_probe(struct usb_interface *intf, if (data->reset_gpio) gpiod_put(data->reset_gpio); hci_free_dev(hdev); + kfree(data); return err; } @@ -4407,6 +4425,7 @@ static void btusb_disconnect(struct usb_interface *intf) } hci_free_dev(hdev); + kfree(data); } #ifdef CONFIG_PM diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index d0adae3267b41e..2b28515de92c40 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -685,6 +685,8 @@ static int hci_uart_register_dev(struct hci_uart *hu) return err; } + set_bit(HCI_UART_PROTO_INIT, &hu->flags); + if (test_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags)) return 0; @@ -712,8 +714,6 @@ static int hci_uart_set_proto(struct hci_uart *hu, int id) hu->proto = p; - set_bit(HCI_UART_PROTO_INIT, &hu->flags); - err = hci_uart_register_dev(hu); if (err) { return err; diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index 25845c04e5620a..a97baf2cbcdd51 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -202,8 +202,12 @@ static ssize_t driver_override_show(struct device *dev, struct device_attribute *attr, char *buf) { struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev); + ssize_t len; - return sysfs_emit(buf, "%s\n", mc_dev->driver_override); + device_lock(dev); + len = sysfs_emit(buf, "%s\n", mc_dev->driver_override); + device_unlock(dev); + return len; } static DEVICE_ATTR_RW(driver_override); diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c index b188bbf7de042d..3d8c9729fcfc57 100644 --- a/drivers/bus/mhi/host/pci_generic.c +++ b/drivers/bus/mhi/host/pci_generic.c @@ -877,6 +877,16 @@ static const struct mhi_pci_dev_info mhi_telit_fn990b40_info = { .edl_trigger = true, }; +static const struct mhi_pci_dev_info mhi_telit_fe990b40_info = { + .name = "telit-fe990b40", + .config = &modem_telit_fn920c04_config, + .bar_num = MHI_PCI_DEFAULT_BAR_NUM, + .dma_data_width = 32, + .sideband_wake = false, + .mru_default = 32768, + .edl_trigger = true, +}; + static const struct mhi_pci_dev_info mhi_netprisma_lcur57_info = { .name = "netprisma-lcur57", .edl = "qcom/prog_firehose_sdx24.mbn", @@ -933,6 +943,9 @@ static const struct pci_device_id mhi_pci_id_table[] = { /* Telit FN990B40 (sdx72) */ { PCI_DEVICE_SUB(PCI_VENDOR_ID_QCOM, 0x0309, 0x1c5d, 0x201a), .driver_data = (kernel_ulong_t) &mhi_telit_fn990b40_info }, + /* Telit FE990B40 (sdx72) */ + { PCI_DEVICE_SUB(PCI_VENDOR_ID_QCOM, 0x0309, 0x1c5d, 0x2025), + .driver_data = (kernel_ulong_t) &mhi_telit_fe990b40_info }, { PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0309), .driver_data = (kernel_ulong_t) &mhi_qcom_sdx75_info }, /* QDU100, x100-DU */ diff --git a/drivers/bus/simple-pm-bus.c b/drivers/bus/simple-pm-bus.c index d8e029e7e53f72..5cae5581d4297c 100644 --- a/drivers/bus/simple-pm-bus.c +++ b/drivers/bus/simple-pm-bus.c @@ -142,6 +142,15 @@ static const struct of_device_id simple_pm_bus_of_match[] = { { .compatible = "simple-mfd", .data = ONLY_BUS }, { .compatible = "isa", .data = ONLY_BUS }, { .compatible = "arm,amba-bus", .data = ONLY_BUS }, + { .compatible = "apple,s5l8960x-pmgr", .data = ONLY_BUS }, + { .compatible = "apple,t7000-pmgr", .data = ONLY_BUS }, + { .compatible = "apple,s8000-pmgr", .data = ONLY_BUS }, + { .compatible = "apple,t8010-pmgr", .data = ONLY_BUS }, + { .compatible = "apple,t8015-pmgr", .data = ONLY_BUS }, + { .compatible = "apple,t8103-pmgr", .data = ONLY_BUS }, + { .compatible = "apple,t8112-pmgr", .data = ONLY_BUS }, + { .compatible = "apple,t6000-pmgr", .data = ONLY_BUS }, + { .compatible = "apple,t6020-pmgr", .data = ONLY_BUS }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, simple_pm_bus_of_match); diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 5566ad11399e7e..610354ce7f8f0d 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -48,6 +48,7 @@ enum sysc_soc { SOC_UNKNOWN, SOC_2420, SOC_2430, + SOC_AM33, SOC_3430, SOC_AM35, SOC_3630, @@ -2912,6 +2913,7 @@ static void ti_sysc_idle(struct work_struct *work) static const struct soc_device_attribute sysc_soc_match[] = { SOC_FLAG("OMAP242*", SOC_2420), SOC_FLAG("OMAP243*", SOC_2430), + SOC_FLAG("AM33*", SOC_AM33), SOC_FLAG("AM35*", SOC_AM35), SOC_FLAG("OMAP3[45]*", SOC_3430), SOC_FLAG("OMAP3[67]*", SOC_3630), @@ -3117,10 +3119,15 @@ static int sysc_check_active_timer(struct sysc *ddata) * can be dropped if we stop supporting old beagleboard revisions * A to B4 at some point. */ - if (sysc_soc->soc == SOC_3430 || sysc_soc->soc == SOC_AM35) + switch (sysc_soc->soc) { + case SOC_AM33: + case SOC_3430: + case SOC_AM35: error = -ENXIO; - else + break; + default: error = -EBUSY; + } if ((ddata->cfg.quirks & SYSC_QUIRK_NO_RESET_ON_INIT) && (ddata->cfg.quirks & SYSC_QUIRK_NO_IDLE)) diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c index 9fed9706d9cd26..c138c468f3a441 100644 --- a/drivers/char/applicom.c +++ b/drivers/char/applicom.c @@ -835,7 +835,10 @@ static long ac_ioctl(struct file *file, unsigned int cmd, unsigned long arg) ret = -ENOTTY; break; } - Dummy = readb(apbs[IndexCard].RamIO + VERS); + + if (cmd != 6) + Dummy = readb(apbs[IndexCard].RamIO + VERS); + kfree(adgl); mutex_unlock(&ac_mutex); return ret; diff --git a/drivers/char/hw_random/airoha-trng.c b/drivers/char/hw_random/airoha-trng.c index 1dbfa9505c214f..9a648f6d9fd409 100644 --- a/drivers/char/hw_random/airoha-trng.c +++ b/drivers/char/hw_random/airoha-trng.c @@ -212,6 +212,7 @@ static int airoha_trng_probe(struct platform_device *pdev) trng->rng.init = airoha_trng_init; trng->rng.cleanup = airoha_trng_cleanup; trng->rng.read = airoha_trng_read; + trng->rng.quality = 900; ret = devm_hwrng_register(dev, &trng->rng); if (ret) { diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index 018316f546215a..036de7294bbdab 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -20,23 +20,25 @@ #include #include #include +#include #include #include #include #include #include +#include #define RNG_MODULE_NAME "hw_random" #define RNG_BUFFER_SIZE (SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES) -static struct hwrng *current_rng; +static struct hwrng __rcu *current_rng; /* the current rng has been explicitly chosen by user via sysfs */ static int cur_rng_set_by_user; static struct task_struct *hwrng_fill; /* list of registered rngs */ static LIST_HEAD(rng_list); -/* Protects rng_list and current_rng */ +/* Protects rng_list, hwrng_fill and updating on current_rng */ static DEFINE_MUTEX(rng_mutex); /* Protects rng read functions, data_avail, rng_buffer and rng_fillbuf */ static DEFINE_MUTEX(reading_mutex); @@ -64,18 +66,39 @@ static size_t rng_buffer_size(void) return RNG_BUFFER_SIZE; } -static inline void cleanup_rng(struct kref *kref) +static void cleanup_rng_work(struct work_struct *work) { - struct hwrng *rng = container_of(kref, struct hwrng, ref); + struct hwrng *rng = container_of(work, struct hwrng, cleanup_work); + + /* + * Hold rng_mutex here so we serialize in case they set_current_rng + * on rng again immediately. + */ + mutex_lock(&rng_mutex); + + /* Skip if rng has been reinitialized. */ + if (kref_read(&rng->ref)) { + mutex_unlock(&rng_mutex); + return; + } if (rng->cleanup) rng->cleanup(rng); complete(&rng->cleanup_done); + mutex_unlock(&rng_mutex); +} + +static inline void cleanup_rng(struct kref *kref) +{ + struct hwrng *rng = container_of(kref, struct hwrng, ref); + + schedule_work(&rng->cleanup_work); } static int set_current_rng(struct hwrng *rng) { + struct hwrng *old_rng; int err; BUG_ON(!mutex_is_locked(&rng_mutex)); @@ -84,8 +107,14 @@ static int set_current_rng(struct hwrng *rng) if (err) return err; - drop_current_rng(); - current_rng = rng; + old_rng = rcu_dereference_protected(current_rng, + lockdep_is_held(&rng_mutex)); + rcu_assign_pointer(current_rng, rng); + + if (old_rng) { + synchronize_rcu(); + kref_put(&old_rng->ref, cleanup_rng); + } /* if necessary, start hwrng thread */ if (!hwrng_fill) { @@ -101,47 +130,56 @@ static int set_current_rng(struct hwrng *rng) static void drop_current_rng(void) { - BUG_ON(!mutex_is_locked(&rng_mutex)); - if (!current_rng) + struct hwrng *rng; + + rng = rcu_dereference_protected(current_rng, + lockdep_is_held(&rng_mutex)); + if (!rng) return; + RCU_INIT_POINTER(current_rng, NULL); + synchronize_rcu(); + + if (hwrng_fill) { + kthread_stop(hwrng_fill); + hwrng_fill = NULL; + } + /* decrease last reference for triggering the cleanup */ - kref_put(¤t_rng->ref, cleanup_rng); - current_rng = NULL; + kref_put(&rng->ref, cleanup_rng); } -/* Returns ERR_PTR(), NULL or refcounted hwrng */ +/* Returns NULL or refcounted hwrng */ static struct hwrng *get_current_rng_nolock(void) { - if (current_rng) - kref_get(¤t_rng->ref); + struct hwrng *rng; + + rng = rcu_dereference_protected(current_rng, + lockdep_is_held(&rng_mutex)); + if (rng) + kref_get(&rng->ref); - return current_rng; + return rng; } static struct hwrng *get_current_rng(void) { struct hwrng *rng; - if (mutex_lock_interruptible(&rng_mutex)) - return ERR_PTR(-ERESTARTSYS); + rcu_read_lock(); + rng = rcu_dereference(current_rng); + if (rng) + kref_get(&rng->ref); - rng = get_current_rng_nolock(); + rcu_read_unlock(); - mutex_unlock(&rng_mutex); return rng; } static void put_rng(struct hwrng *rng) { - /* - * Hold rng_mutex here so we serialize in case they set_current_rng - * on rng again immediately. - */ - mutex_lock(&rng_mutex); if (rng) kref_put(&rng->ref, cleanup_rng); - mutex_unlock(&rng_mutex); } static int hwrng_init(struct hwrng *rng) @@ -213,10 +251,6 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, while (size) { rng = get_current_rng(); - if (IS_ERR(rng)) { - err = PTR_ERR(rng); - goto out; - } if (!rng) { err = -ENODEV; goto out; @@ -303,7 +337,7 @@ static struct miscdevice rng_miscdev = { static int enable_best_rng(void) { - struct hwrng *rng, *new_rng = NULL; + struct hwrng *rng, *cur_rng, *new_rng = NULL; int ret = -ENODEV; BUG_ON(!mutex_is_locked(&rng_mutex)); @@ -321,7 +355,9 @@ static int enable_best_rng(void) new_rng = rng; } - ret = ((new_rng == current_rng) ? 0 : set_current_rng(new_rng)); + cur_rng = rcu_dereference_protected(current_rng, + lockdep_is_held(&rng_mutex)); + ret = ((new_rng == cur_rng) ? 0 : set_current_rng(new_rng)); if (!ret) cur_rng_set_by_user = 0; @@ -341,6 +377,9 @@ static ssize_t rng_current_store(struct device *dev, if (sysfs_streq(buf, "")) { err = enable_best_rng(); + } else if (sysfs_streq(buf, "none")) { + cur_rng_set_by_user = 1; + drop_current_rng(); } else { list_for_each_entry(rng, &rng_list, list) { if (sysfs_streq(rng->name, buf)) { @@ -368,8 +407,6 @@ static ssize_t rng_current_show(struct device *dev, struct hwrng *rng; rng = get_current_rng(); - if (IS_ERR(rng)) - return PTR_ERR(rng); ret = sysfs_emit(buf, "%s\n", rng ? rng->name : "none"); put_rng(rng); @@ -392,7 +429,7 @@ static ssize_t rng_available_show(struct device *dev, strlcat(buf, rng->name, PAGE_SIZE); strlcat(buf, " ", PAGE_SIZE); } - strlcat(buf, "\n", PAGE_SIZE); + strlcat(buf, "none\n", PAGE_SIZE); mutex_unlock(&rng_mutex); return strlen(buf); @@ -413,8 +450,6 @@ static ssize_t rng_quality_show(struct device *dev, struct hwrng *rng; rng = get_current_rng(); - if (IS_ERR(rng)) - return PTR_ERR(rng); if (!rng) /* no need to put_rng */ return -ENODEV; @@ -429,6 +464,7 @@ static ssize_t rng_quality_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { + struct hwrng *rng; u16 quality; int ret = -EINVAL; @@ -445,12 +481,13 @@ static ssize_t rng_quality_store(struct device *dev, goto out; } - if (!current_rng) { + rng = rcu_dereference_protected(current_rng, lockdep_is_held(&rng_mutex)); + if (!rng) { ret = -ENODEV; goto out; } - current_rng->quality = quality; + rng->quality = quality; current_quality = quality; /* obsolete */ /* the best available RNG may have changed */ @@ -486,8 +523,20 @@ static int hwrng_fillfn(void *unused) struct hwrng *rng; rng = get_current_rng(); - if (IS_ERR(rng) || !rng) + if (!rng) { + /* + * Keep the task_struct alive until kthread_stop() + * is called to avoid UAF in drop_current_rng(). + */ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + if (!kthread_should_stop()) + schedule(); + } + set_current_state(TASK_RUNNING); break; + } + mutex_lock(&reading_mutex); rc = rng_get_data(rng, rng_fillbuf, rng_buffer_size(), 1); @@ -515,14 +564,13 @@ static int hwrng_fillfn(void *unused) add_hwgenerator_randomness((void *)rng_fillbuf, rc, entropy >> 10, true); } - hwrng_fill = NULL; return 0; } int hwrng_register(struct hwrng *rng) { int err = -EINVAL; - struct hwrng *tmp; + struct hwrng *cur_rng, *tmp; if (!rng->name || (!rng->data_read && !rng->read)) goto out; @@ -537,6 +585,7 @@ int hwrng_register(struct hwrng *rng) } list_add_tail(&rng->list, &rng_list); + INIT_WORK(&rng->cleanup_work, cleanup_rng_work); init_completion(&rng->cleanup_done); complete(&rng->cleanup_done); init_completion(&rng->dying); @@ -544,16 +593,19 @@ int hwrng_register(struct hwrng *rng) /* Adjust quality field to always have a proper value */ rng->quality = min_t(u16, min_t(u16, default_quality, 1024), rng->quality ?: 1024); - if (!current_rng || - (!cur_rng_set_by_user && rng->quality > current_rng->quality)) { - /* - * Set new rng as current as the new rng source - * provides better entropy quality and was not - * chosen by userspace. - */ - err = set_current_rng(rng); - if (err) - goto out_unlock; + if (!cur_rng_set_by_user) { + cur_rng = rcu_dereference_protected(current_rng, + lockdep_is_held(&rng_mutex)); + if (!cur_rng || rng->quality > cur_rng->quality) { + /* + * Set new rng as current as the new rng source + * provides better entropy quality and was not + * chosen by userspace. + */ + err = set_current_rng(rng); + if (err) + goto out_unlock; + } } mutex_unlock(&rng_mutex); return 0; @@ -566,14 +618,17 @@ EXPORT_SYMBOL_GPL(hwrng_register); void hwrng_unregister(struct hwrng *rng) { - struct hwrng *new_rng; + struct hwrng *cur_rng; int err; mutex_lock(&rng_mutex); list_del(&rng->list); complete_all(&rng->dying); - if (current_rng == rng) { + + cur_rng = rcu_dereference_protected(current_rng, + lockdep_is_held(&rng_mutex)); + if (cur_rng == rng) { err = enable_best_rng(); if (err) { drop_current_rng(); @@ -581,17 +636,7 @@ void hwrng_unregister(struct hwrng *rng) } } - new_rng = get_current_rng_nolock(); - if (list_empty(&rng_list)) { - mutex_unlock(&rng_mutex); - if (hwrng_fill) - kthread_stop(hwrng_fill); - } else - mutex_unlock(&rng_mutex); - - if (new_rng) - put_rng(new_rng); - + mutex_unlock(&rng_mutex); wait_for_completion(&rng->cleanup_done); } EXPORT_SYMBOL_GPL(hwrng_unregister); @@ -679,7 +724,7 @@ static int __init hwrng_modinit(void) static void __exit hwrng_modexit(void) { mutex_lock(&rng_mutex); - BUG_ON(current_rng); + WARN_ON(rcu_access_pointer(current_rng)); kfree(rng_buffer); kfree(rng_fillbuf); mutex_unlock(&rng_mutex); diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 3700ab4eba3e7e..0a886399f9dafb 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -599,7 +599,8 @@ static void __ipmi_bmc_unregister(struct ipmi_smi *intf); static int __ipmi_bmc_register(struct ipmi_smi *intf, struct ipmi_device_id *id, bool guid_set, guid_t *guid, int intf_num); -static int __scan_channels(struct ipmi_smi *intf, struct ipmi_device_id *id); +static int __scan_channels(struct ipmi_smi *intf, + struct ipmi_device_id *id, bool rescan); static void free_ipmi_user(struct kref *ref) { @@ -2668,7 +2669,7 @@ static int __bmc_get_device_id(struct ipmi_smi *intf, struct bmc_device *bmc, if (__ipmi_bmc_register(intf, &id, guid_set, &guid, intf_num)) need_waiter(intf); /* Retry later on an error. */ else - __scan_channels(intf, &id); + __scan_channels(intf, &id, false); if (!intf_set) { @@ -2688,7 +2689,7 @@ static int __bmc_get_device_id(struct ipmi_smi *intf, struct bmc_device *bmc, goto out_noprocessing; } else if (memcmp(&bmc->fetch_id, &bmc->id, sizeof(bmc->id))) /* Version info changes, scan the channels again. */ - __scan_channels(intf, &bmc->fetch_id); + __scan_channels(intf, &bmc->fetch_id, true); bmc->dyn_id_expiry = jiffies + IPMI_DYN_DEV_ID_EXPIRY; @@ -3417,8 +3418,6 @@ channel_handler(struct ipmi_smi *intf, struct ipmi_recv_msg *msg) intf->channels_ready = true; wake_up(&intf->waitq); } else { - intf->channel_list = intf->wchannels + set; - intf->channels_ready = true; rv = send_channel_info_cmd(intf, intf->curr_channel); } @@ -3440,10 +3439,17 @@ channel_handler(struct ipmi_smi *intf, struct ipmi_recv_msg *msg) /* * Must be holding intf->bmc_reg_mutex to call this. */ -static int __scan_channels(struct ipmi_smi *intf, struct ipmi_device_id *id) +static int __scan_channels(struct ipmi_smi *intf, + struct ipmi_device_id *id, + bool rescan) { int rv; + if (rescan) { + /* Clear channels_ready to force channels rescan. */ + intf->channels_ready = false; + } + if (ipmi_version_major(id) > 1 || (ipmi_version_major(id) == 1 && ipmi_version_minor(id) >= 5)) { @@ -3658,7 +3664,7 @@ int ipmi_add_smi(struct module *owner, } mutex_lock(&intf->bmc_reg_mutex); - rv = __scan_channels(intf, &id); + rv = __scan_channels(intf, &id, false); mutex_unlock(&intf->bmc_reg_mutex); if (rv) goto out_err_bmc_reg; diff --git a/drivers/char/misc_minor_kunit.c b/drivers/char/misc_minor_kunit.c index 6fc8b05169c575..e930c78e1ef97e 100644 --- a/drivers/char/misc_minor_kunit.c +++ b/drivers/char/misc_minor_kunit.c @@ -166,7 +166,7 @@ static void __init miscdev_test_can_open(struct kunit *test, struct miscdevice * KUNIT_FAIL(test, "failed to create node\n"); filp = filp_open(devname, O_RDONLY, 0); - if (IS_ERR_OR_NULL(filp)) + if (IS_ERR(filp)) KUNIT_FAIL(test, "failed to open misc device: %ld\n", PTR_ERR(filp)); else fput(filp); diff --git a/drivers/char/random.c b/drivers/char/random.c index b8b24b6ed3fe43..4ba5f0c4c8b242 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1296,6 +1296,7 @@ static void __cold try_to_generate_entropy(void) struct entropy_timer_state *stack = PTR_ALIGN((void *)stack_bytes, SMP_CACHE_BYTES); unsigned int i, num_different = 0; unsigned long last = random_get_entropy(); + cpumask_var_t timer_cpus; int cpu = -1; for (i = 0; i < NUM_TRIAL_SAMPLES - 1; ++i) { @@ -1310,13 +1311,15 @@ static void __cold try_to_generate_entropy(void) atomic_set(&stack->samples, 0); timer_setup_on_stack(&stack->timer, entropy_timer, 0); + if (!alloc_cpumask_var(&timer_cpus, GFP_KERNEL)) + goto out; + while (!crng_ready() && !signal_pending(current)) { /* * Check !timer_pending() and then ensure that any previous callback has finished * executing by checking timer_delete_sync_try(), before queueing the next one. */ if (!timer_pending(&stack->timer) && timer_delete_sync_try(&stack->timer) >= 0) { - struct cpumask timer_cpus; unsigned int num_cpus; /* @@ -1326,19 +1329,19 @@ static void __cold try_to_generate_entropy(void) preempt_disable(); /* Only schedule callbacks on timer CPUs that are online. */ - cpumask_and(&timer_cpus, housekeeping_cpumask(HK_TYPE_TIMER), cpu_online_mask); - num_cpus = cpumask_weight(&timer_cpus); + cpumask_and(timer_cpus, housekeeping_cpumask(HK_TYPE_TIMER), cpu_online_mask); + num_cpus = cpumask_weight(timer_cpus); /* In very bizarre case of misconfiguration, fallback to all online. */ if (unlikely(num_cpus == 0)) { - timer_cpus = *cpu_online_mask; - num_cpus = cpumask_weight(&timer_cpus); + *timer_cpus = *cpu_online_mask; + num_cpus = cpumask_weight(timer_cpus); } /* Basic CPU round-robin, which avoids the current CPU. */ do { - cpu = cpumask_next(cpu, &timer_cpus); + cpu = cpumask_next(cpu, timer_cpus); if (cpu >= nr_cpu_ids) - cpu = cpumask_first(&timer_cpus); + cpu = cpumask_first(timer_cpus); } while (cpu == smp_processor_id() && num_cpus > 1); /* Expiring the timer at `jiffies` means it's the next tick. */ @@ -1354,6 +1357,8 @@ static void __cold try_to_generate_entropy(void) } mix_pool_bytes(&stack->entropy, sizeof(stack->entropy)); + free_cpumask_var(timer_cpus); +out: timer_delete_sync(&stack->timer); timer_destroy_on_stack(&stack->timer); } diff --git a/drivers/char/tpm/st33zp24/st33zp24.c b/drivers/char/tpm/st33zp24/st33zp24.c index 2ed7815e4899b7..e2b7451ea7ccd3 100644 --- a/drivers/char/tpm/st33zp24/st33zp24.c +++ b/drivers/char/tpm/st33zp24/st33zp24.c @@ -328,8 +328,10 @@ static int st33zp24_send(struct tpm_chip *chip, unsigned char *buf, for (i = 0; i < len - 1;) { burstcnt = get_burstcount(chip); - if (burstcnt < 0) - return burstcnt; + if (burstcnt < 0) { + ret = burstcnt; + goto out_err; + } size = min_t(int, len - i - 1, burstcnt); ret = tpm_dev->ops->send(tpm_dev->phy_id, TPM_DATA_FIFO, buf + i, size); diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index e25daf2396d37b..dfeb28866a3273 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -282,7 +282,6 @@ static void tpm_dev_release(struct device *dev) kfree(chip->work_space.context_buf); kfree(chip->work_space.session_buf); - kfree(chip->allocated_banks); #ifdef CONFIG_TCG_TPM2_HMAC kfree(chip->auth); #endif diff --git a/drivers/char/tpm/tpm1-cmd.c b/drivers/char/tpm/tpm1-cmd.c index cf64c738510529..b49a790f1bd53f 100644 --- a/drivers/char/tpm/tpm1-cmd.c +++ b/drivers/char/tpm/tpm1-cmd.c @@ -799,11 +799,6 @@ int tpm1_pm_suspend(struct tpm_chip *chip, u32 tpm_suspend_pcr) */ int tpm1_get_pcr_allocation(struct tpm_chip *chip) { - chip->allocated_banks = kcalloc(1, sizeof(*chip->allocated_banks), - GFP_KERNEL); - if (!chip->allocated_banks) - return -ENOMEM; - chip->allocated_banks[0].alg_id = TPM_ALG_SHA1; chip->allocated_banks[0].digest_size = hash_digest_size[HASH_ALGO_SHA1]; chip->allocated_banks[0].crypto_id = HASH_ALGO_SHA1; diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 7d77f6fbc1520c..58a8477cda8514 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -11,8 +11,11 @@ * used by the kernel internally. */ +#include "linux/dev_printk.h" +#include "linux/tpm.h" #include "tpm.h" #include +#include static bool disable_pcr_integrity; module_param(disable_pcr_integrity, bool, 0444); @@ -187,7 +190,11 @@ int tpm2_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, } if (!disable_pcr_integrity) { - tpm_buf_append_name(chip, &buf, pcr_idx, NULL); + rc = tpm_buf_append_name(chip, &buf, pcr_idx, NULL); + if (rc) { + tpm_buf_destroy(&buf); + return rc; + } tpm_buf_append_hmac_session(chip, &buf, 0, NULL, 0); } else { tpm_buf_append_handle(chip, &buf, pcr_idx); @@ -202,8 +209,14 @@ int tpm2_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, chip->allocated_banks[i].digest_size); } - if (!disable_pcr_integrity) - tpm_buf_fill_hmac_session(chip, &buf); + if (!disable_pcr_integrity) { + rc = tpm_buf_fill_hmac_session(chip, &buf); + if (rc) { + tpm_buf_destroy(&buf); + return rc; + } + } + rc = tpm_transmit_cmd(chip, &buf, 0, "attempting extend a PCR value"); if (!disable_pcr_integrity) rc = tpm_buf_check_hmac_response(chip, &buf, rc); @@ -261,7 +274,12 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) | TPM2_SA_CONTINUE_SESSION, NULL, 0); tpm_buf_append_u16(&buf, num_bytes); - tpm_buf_fill_hmac_session(chip, &buf); + err = tpm_buf_fill_hmac_session(chip, &buf); + if (err) { + tpm_buf_destroy(&buf); + return err; + } + err = tpm_transmit_cmd(chip, &buf, offsetof(struct tpm2_get_random_out, buffer), @@ -538,11 +556,9 @@ ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip) nr_possible_banks = be32_to_cpup( (__be32 *)&buf.data[TPM_HEADER_SIZE + 5]); - - chip->allocated_banks = kcalloc(nr_possible_banks, - sizeof(*chip->allocated_banks), - GFP_KERNEL); - if (!chip->allocated_banks) { + if (nr_possible_banks > TPM2_MAX_PCR_BANKS) { + pr_err("tpm: out of bank capacity: %u > %u\n", + nr_possible_banks, TPM2_MAX_PCR_BANKS); rc = -ENOMEM; goto out; } diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c index 6d03c224e6b210..3f389e2f6f580b 100644 --- a/drivers/char/tpm/tpm2-sessions.c +++ b/drivers/char/tpm/tpm2-sessions.c @@ -144,59 +144,80 @@ struct tpm2_auth { /* * Name Size based on TPM algorithm (assumes no hash bigger than 255) */ -static u8 name_size(const u8 *name) +static int name_size(const u8 *name) { - static u8 size_map[] = { - [TPM_ALG_SHA1] = SHA1_DIGEST_SIZE, - [TPM_ALG_SHA256] = SHA256_DIGEST_SIZE, - [TPM_ALG_SHA384] = SHA384_DIGEST_SIZE, - [TPM_ALG_SHA512] = SHA512_DIGEST_SIZE, - }; - u16 alg = get_unaligned_be16(name); - return size_map[alg] + 2; -} - -static int tpm2_parse_read_public(char *name, struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - off_t offset = TPM_HEADER_SIZE; - u32 tot_len = be32_to_cpu(head->length); - u32 val; - - /* we're starting after the header so adjust the length */ - tot_len -= TPM_HEADER_SIZE; - - /* skip public */ - val = tpm_buf_read_u16(buf, &offset); - if (val > tot_len) - return -EINVAL; - offset += val; - /* name */ - val = tpm_buf_read_u16(buf, &offset); - if (val != name_size(&buf->data[offset])) + u16 hash_alg = get_unaligned_be16(name); + + switch (hash_alg) { + case TPM_ALG_SHA1: + return SHA1_DIGEST_SIZE + 2; + case TPM_ALG_SHA256: + return SHA256_DIGEST_SIZE + 2; + case TPM_ALG_SHA384: + return SHA384_DIGEST_SIZE + 2; + case TPM_ALG_SHA512: + return SHA512_DIGEST_SIZE + 2; + default: + pr_warn("tpm: unsupported name algorithm: 0x%04x\n", hash_alg); return -EINVAL; - memcpy(name, &buf->data[offset], val); - /* forget the rest */ - return 0; + } } -static int tpm2_read_public(struct tpm_chip *chip, u32 handle, char *name) +static int tpm2_read_public(struct tpm_chip *chip, u32 handle, void *name) { + u32 mso = tpm2_handle_mso(handle); + off_t offset = TPM_HEADER_SIZE; + int rc, name_size_alg; struct tpm_buf buf; - int rc; + + if (mso != TPM2_MSO_PERSISTENT && mso != TPM2_MSO_VOLATILE && + mso != TPM2_MSO_NVRAM) { + memcpy(name, &handle, sizeof(u32)); + return sizeof(u32); + } rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_READ_PUBLIC); if (rc) return rc; tpm_buf_append_u32(&buf, handle); - rc = tpm_transmit_cmd(chip, &buf, 0, "read public"); - if (rc == TPM2_RC_SUCCESS) - rc = tpm2_parse_read_public(name, &buf); - tpm_buf_destroy(&buf); + rc = tpm_transmit_cmd(chip, &buf, 0, "TPM2_ReadPublic"); + if (rc) { + tpm_buf_destroy(&buf); + return tpm_ret_to_err(rc); + } - return rc; + /* Skip TPMT_PUBLIC: */ + offset += tpm_buf_read_u16(&buf, &offset); + + /* + * Ensure space for the length field of TPM2B_NAME and hashAlg field of + * TPMT_HA (the extra four bytes). + */ + if (offset + 4 > tpm_buf_length(&buf)) { + tpm_buf_destroy(&buf); + return -EIO; + } + + rc = tpm_buf_read_u16(&buf, &offset); + name_size_alg = name_size(&buf.data[offset]); + + if (name_size_alg < 0) + return name_size_alg; + + if (rc != name_size_alg) { + tpm_buf_destroy(&buf); + return -EIO; + } + + if (offset + rc > tpm_buf_length(&buf)) { + tpm_buf_destroy(&buf); + return -EIO; + } + + memcpy(name, &buf.data[offset], rc); + return name_size_alg; } #endif /* CONFIG_TCG_TPM2_HMAC */ @@ -221,46 +242,70 @@ static int tpm2_read_public(struct tpm_chip *chip, u32 handle, char *name) * As with most tpm_buf operations, success is assumed because failure * will be caused by an incorrect programming model and indicated by a * kernel message. + * + * Ends the authorization session on failure. */ -void tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf, - u32 handle, u8 *name) +int tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf, + u32 handle, u8 *name) { #ifdef CONFIG_TCG_TPM2_HMAC enum tpm2_mso_type mso = tpm2_handle_mso(handle); struct tpm2_auth *auth; + u16 name_size_alg; int slot; + int ret; #endif if (!tpm2_chip_auth(chip)) { tpm_buf_append_handle(chip, buf, handle); - return; + return 0; } #ifdef CONFIG_TCG_TPM2_HMAC slot = (tpm_buf_length(buf) - TPM_HEADER_SIZE) / 4; if (slot >= AUTH_MAX_NAMES) { - dev_err(&chip->dev, "TPM: too many handles\n"); - return; + dev_err(&chip->dev, "too many handles\n"); + ret = -EIO; + goto err; } auth = chip->auth; - WARN(auth->session != tpm_buf_length(buf), - "name added in wrong place\n"); + if (auth->session != tpm_buf_length(buf)) { + dev_err(&chip->dev, "session state malformed"); + ret = -EIO; + goto err; + } tpm_buf_append_u32(buf, handle); auth->session += 4; if (mso == TPM2_MSO_PERSISTENT || mso == TPM2_MSO_VOLATILE || mso == TPM2_MSO_NVRAM) { - if (!name) - tpm2_read_public(chip, handle, auth->name[slot]); + if (!name) { + ret = tpm2_read_public(chip, handle, auth->name[slot]); + if (ret < 0) + goto err; + + name_size_alg = ret; + } } else { - if (name) - dev_err(&chip->dev, "TPM: Handle does not require name but one is specified\n"); + if (name) { + dev_err(&chip->dev, "handle 0x%08x does not use a name\n", + handle); + ret = -EIO; + goto err; + } } auth->name_h[slot] = handle; if (name) - memcpy(auth->name[slot], name, name_size(name)); + memcpy(auth->name[slot], name, name_size_alg); +#endif + return 0; + +#ifdef CONFIG_TCG_TPM2_HMAC +err: + tpm2_end_auth_session(chip); + return tpm_ret_to_err(ret); #endif } EXPORT_SYMBOL_GPL(tpm_buf_append_name); @@ -533,11 +578,9 @@ static void tpm_buf_append_salt(struct tpm_buf *buf, struct tpm_chip *chip, * encryption key and encrypts the first parameter of the command * buffer with it. * - * As with most tpm_buf operations, success is assumed because failure - * will be caused by an incorrect programming model and indicated by a - * kernel message. + * Ends the authorization session on failure. */ -void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf) +int tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf) { u32 cc, handles, val; struct tpm2_auth *auth = chip->auth; @@ -549,9 +592,12 @@ void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf) u8 cphash[SHA256_DIGEST_SIZE]; struct sha256_ctx sctx; struct hmac_sha256_ctx hctx; + int ret; - if (!auth) - return; + if (!auth) { + ret = -EIO; + goto err; + } /* save the command code in BE format */ auth->ordinal = head->ordinal; @@ -560,9 +606,11 @@ void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf) i = tpm2_find_cc(chip, cc); if (i < 0) { - dev_err(&chip->dev, "Command 0x%x not found in TPM\n", cc); - return; + dev_err(&chip->dev, "command 0x%08x not found\n", cc); + ret = -EIO; + goto err; } + attrs = chip->cc_attrs_tbl[i]; handles = (attrs >> TPM2_CC_ATTR_CHANDLES) & GENMASK(2, 0); @@ -576,9 +624,9 @@ void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf) u32 handle = tpm_buf_read_u32(buf, &offset_s); if (auth->name_h[i] != handle) { - dev_err(&chip->dev, "TPM: handle %d wrong for name\n", - i); - return; + dev_err(&chip->dev, "invalid handle 0x%08x\n", handle); + ret = -EIO; + goto err; } } /* point offset_s to the start of the sessions */ @@ -609,12 +657,14 @@ void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf) offset_s += len; } if (offset_s != offset_p) { - dev_err(&chip->dev, "TPM session length is incorrect\n"); - return; + dev_err(&chip->dev, "session length is incorrect\n"); + ret = -EIO; + goto err; } if (!hmac) { - dev_err(&chip->dev, "TPM could not find HMAC session\n"); - return; + dev_err(&chip->dev, "could not find HMAC session\n"); + ret = -EIO; + goto err; } /* encrypt before HMAC */ @@ -646,8 +696,11 @@ void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf) if (mso == TPM2_MSO_PERSISTENT || mso == TPM2_MSO_VOLATILE || mso == TPM2_MSO_NVRAM) { - sha256_update(&sctx, auth->name[i], - name_size(auth->name[i])); + ret = name_size(auth->name[i]); + if (ret < 0) + goto err; + + sha256_update(&sctx, auth->name[i], ret); } else { __be32 h = cpu_to_be32(auth->name_h[i]); @@ -668,6 +721,11 @@ void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf) hmac_sha256_update(&hctx, auth->tpm_nonce, sizeof(auth->tpm_nonce)); hmac_sha256_update(&hctx, &auth->attrs, 1); hmac_sha256_final(&hctx, hmac); + return 0; + +err: + tpm2_end_auth_session(chip); + return ret; } EXPORT_SYMBOL(tpm_buf_fill_hmac_session); diff --git a/drivers/char/tpm/tpm_i2c_infineon.c b/drivers/char/tpm/tpm_i2c_infineon.c index bdf1f329a67946..8b7d32de0b2ef9 100644 --- a/drivers/char/tpm/tpm_i2c_infineon.c +++ b/drivers/char/tpm/tpm_i2c_infineon.c @@ -544,8 +544,10 @@ static int tpm_tis_i2c_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz, burstcnt = get_burstcount(chip); /* burstcnt < 0 = TPM is busy */ - if (burstcnt < 0) - return burstcnt; + if (burstcnt < 0) { + rc = burstcnt; + goto out_err; + } if (burstcnt > (len - 1 - count)) burstcnt = len - 1 - count; diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index b74a1767ca2787..61ec08404442b4 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -125,8 +125,7 @@ obj-$(CONFIG_ARCH_HISI) += hisilicon/ obj-y += imgtec/ obj-y += imx/ obj-y += ingenic/ -obj-$(CONFIG_ARCH_K3) += keystone/ -obj-$(CONFIG_ARCH_KEYSTONE) += keystone/ +obj-y += keystone/ obj-y += mediatek/ obj-$(CONFIG_ARCH_MESON) += meson/ obj-y += microchip/ diff --git a/drivers/clk/actions/owl-composite.c b/drivers/clk/actions/owl-composite.c index 00b74f8bc4375a..9540444307d6c9 100644 --- a/drivers/clk/actions/owl-composite.c +++ b/drivers/clk/actions/owl-composite.c @@ -57,15 +57,10 @@ static int owl_comp_div_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { struct owl_composite *comp = hw_to_owl_comp(hw); - long rate; - - rate = owl_divider_helper_round_rate(&comp->common, &comp->rate.div_hw, - req->rate, &req->best_parent_rate); - if (rate < 0) - return rate; + struct owl_divider_hw *div = &comp->rate.div_hw; - req->rate = rate; - return 0; + return divider_determine_rate(&comp->common.hw, req, div->table, + div->width, div->div_flags); } static unsigned long owl_comp_div_recalc_rate(struct clk_hw *hw, diff --git a/drivers/clk/actions/owl-divider.c b/drivers/clk/actions/owl-divider.c index 118f1393c6780f..316ace80e87e3b 100644 --- a/drivers/clk/actions/owl-divider.c +++ b/drivers/clk/actions/owl-divider.c @@ -13,26 +13,13 @@ #include "owl-divider.h" -long owl_divider_helper_round_rate(struct owl_clk_common *common, - const struct owl_divider_hw *div_hw, - unsigned long rate, - unsigned long *parent_rate) -{ - return divider_round_rate(&common->hw, rate, parent_rate, - div_hw->table, div_hw->width, - div_hw->div_flags); -} - static int owl_divider_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { struct owl_divider *div = hw_to_owl_divider(hw); - req->rate = owl_divider_helper_round_rate(&div->common, &div->div_hw, - req->rate, - &req->best_parent_rate); - - return 0; + return divider_determine_rate(hw, req, div->div_hw.table, + div->div_hw.width, div->div_hw.div_flags); } unsigned long owl_divider_helper_recalc_rate(struct owl_clk_common *common, diff --git a/drivers/clk/actions/owl-divider.h b/drivers/clk/actions/owl-divider.h index 083be6d80954d7..2ba957740c3813 100644 --- a/drivers/clk/actions/owl-divider.h +++ b/drivers/clk/actions/owl-divider.h @@ -56,11 +56,6 @@ static inline struct owl_divider *hw_to_owl_divider(const struct clk_hw *hw) return container_of(common, struct owl_divider, common); } -long owl_divider_helper_round_rate(struct owl_clk_common *common, - const struct owl_divider_hw *div_hw, - unsigned long rate, - unsigned long *parent_rate); - unsigned long owl_divider_helper_recalc_rate(struct owl_clk_common *common, const struct owl_divider_hw *div_hw, unsigned long parent_rate); diff --git a/drivers/clk/clk-apple-nco.c b/drivers/clk/clk-apple-nco.c index d3ced4a0f029ec..434c067968bbc1 100644 --- a/drivers/clk/clk-apple-nco.c +++ b/drivers/clk/clk-apple-nco.c @@ -320,6 +320,7 @@ static int applnco_probe(struct platform_device *pdev) } static const struct of_device_id applnco_ids[] = { + { .compatible = "apple,t8103-nco" }, { .compatible = "apple,nco" }, { } }; diff --git a/drivers/clk/clk-bm1880.c b/drivers/clk/clk-bm1880.c index dac190bc6e19a6..d2617fe16d2e42 100644 --- a/drivers/clk/clk-bm1880.c +++ b/drivers/clk/clk-bm1880.c @@ -629,10 +629,7 @@ static int bm1880_clk_div_determine_rate(struct clk_hw *hw, return 0; } - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, - div->table, div->width, div->flags); - - return 0; + return divider_determine_rate(hw, req, div->table, div->width, div->flags); } static int bm1880_clk_div_set_rate(struct clk_hw *hw, unsigned long rate, diff --git a/drivers/clk/clk-loongson1.c b/drivers/clk/clk-loongson1.c index f9f060d08a5fae..1674181a1107dc 100644 --- a/drivers/clk/clk-loongson1.c +++ b/drivers/clk/clk-loongson1.c @@ -99,10 +99,7 @@ static int ls1x_divider_determine_rate(struct clk_hw *hw, struct ls1x_clk *ls1x_clk = to_ls1x_clk(hw); const struct ls1x_clk_div_data *d = ls1x_clk->data; - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, - d->table, d->width, d->flags); - - return 0; + return divider_determine_rate(hw, req, d->table, d->width, d->flags); } static int ls1x_divider_set_rate(struct clk_hw *hw, unsigned long rate, diff --git a/drivers/clk/clk-milbeaut.c b/drivers/clk/clk-milbeaut.c index b4f9b7143eaa65..bb94d02a76cf10 100644 --- a/drivers/clk/clk-milbeaut.c +++ b/drivers/clk/clk-milbeaut.c @@ -407,10 +407,7 @@ static int m10v_clk_divider_determine_rate(struct clk_hw *hw, return 0; } - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, - divider->table, divider->width, divider->flags); - - return 0; + return divider_determine_rate(hw, req, divider->table, divider->width, divider->flags); } static int m10v_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate, diff --git a/drivers/clk/clk-versaclock3.c b/drivers/clk/clk-versaclock3.c index 1849863dbd673f..27b6cf70f3ae1b 100644 --- a/drivers/clk/clk-versaclock3.c +++ b/drivers/clk/clk-versaclock3.c @@ -523,11 +523,8 @@ static int vc3_div_determine_rate(struct clk_hw *hw, return 0; } - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, - div_data->table, - div_data->width, div_data->flags); - - return 0; + return divider_determine_rate(hw, req, div_data->table, div_data->width, + div_data->flags); } static int vc3_div_set_rate(struct clk_hw *hw, unsigned long rate, diff --git a/drivers/clk/hisilicon/clkdivider-hi6220.c b/drivers/clk/hisilicon/clkdivider-hi6220.c index 6bae18a84cb6c0..fd7ceb92d65157 100644 --- a/drivers/clk/hisilicon/clkdivider-hi6220.c +++ b/drivers/clk/hisilicon/clkdivider-hi6220.c @@ -60,10 +60,8 @@ static int hi6220_clkdiv_determine_rate(struct clk_hw *hw, { struct hi6220_clk_divider *dclk = to_hi6220_clk_divider(hw); - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, dclk->table, - dclk->width, CLK_DIVIDER_ROUND_CLOSEST); - - return 0; + return divider_determine_rate(hw, req, dclk->table, dclk->width, + CLK_DIVIDER_ROUND_CLOSEST); } static int hi6220_clkdiv_set_rate(struct clk_hw *hw, unsigned long rate, diff --git a/drivers/clk/keystone/syscon-clk.c b/drivers/clk/keystone/syscon-clk.c index c509929da85452..ecf180a7949c93 100644 --- a/drivers/clk/keystone/syscon-clk.c +++ b/drivers/clk/keystone/syscon-clk.c @@ -129,7 +129,7 @@ static int ti_syscon_gate_clk_probe(struct platform_device *pdev) if (IS_ERR(base)) return PTR_ERR(base); - regmap = regmap_init_mmio(dev, base, &ti_syscon_regmap_cfg); + regmap = devm_regmap_init_mmio(dev, base, &ti_syscon_regmap_cfg); if (IS_ERR(regmap)) return dev_err_probe(dev, PTR_ERR(regmap), "failed to get regmap\n"); diff --git a/drivers/clk/mediatek/clk-mt7981-eth.c b/drivers/clk/mediatek/clk-mt7981-eth.c index 906aec9ddff54b..0655ebb6c561f6 100644 --- a/drivers/clk/mediatek/clk-mt7981-eth.c +++ b/drivers/clk/mediatek/clk-mt7981-eth.c @@ -31,7 +31,7 @@ static const struct mtk_gate_regs sgmii0_cg_regs = { .ops = &mtk_clk_gate_ops_no_setclr_inv, \ } -static const struct mtk_gate sgmii0_clks[] __initconst = { +static const struct mtk_gate sgmii0_clks[] = { GATE_SGMII0(CLK_SGM0_TX_EN, "sgm0_tx_en", "usb_tx250m", 2), GATE_SGMII0(CLK_SGM0_RX_EN, "sgm0_rx_en", "usb_eq_rx250m", 3), GATE_SGMII0(CLK_SGM0_CK0_EN, "sgm0_ck0_en", "usb_ln0", 4), @@ -53,7 +53,7 @@ static const struct mtk_gate_regs sgmii1_cg_regs = { .ops = &mtk_clk_gate_ops_no_setclr_inv, \ } -static const struct mtk_gate sgmii1_clks[] __initconst = { +static const struct mtk_gate sgmii1_clks[] = { GATE_SGMII1(CLK_SGM1_TX_EN, "sgm1_tx_en", "usb_tx250m", 2), GATE_SGMII1(CLK_SGM1_RX_EN, "sgm1_rx_en", "usb_eq_rx250m", 3), GATE_SGMII1(CLK_SGM1_CK1_EN, "sgm1_ck1_en", "usb_ln0", 4), @@ -75,7 +75,7 @@ static const struct mtk_gate_regs eth_cg_regs = { .ops = &mtk_clk_gate_ops_no_setclr_inv, \ } -static const struct mtk_gate eth_clks[] __initconst = { +static const struct mtk_gate eth_clks[] = { GATE_ETH(CLK_ETH_FE_EN, "eth_fe_en", "netsys_2x", 6), GATE_ETH(CLK_ETH_GP2_EN, "eth_gp2_en", "sgm_325m", 7), GATE_ETH(CLK_ETH_GP1_EN, "eth_gp1_en", "sgm_325m", 8), diff --git a/drivers/clk/mediatek/clk-mt8196-mfg.c b/drivers/clk/mediatek/clk-mt8196-mfg.c index ae1eb9de79ae29..f40795b47ff1fd 100644 --- a/drivers/clk/mediatek/clk-mt8196-mfg.c +++ b/drivers/clk/mediatek/clk-mt8196-mfg.c @@ -58,24 +58,25 @@ .pcw_shift = _pcw_shift, \ .pcwbits = _pcwbits, \ .pcwibits = MT8196_INTEGER_BITS, \ + .parent_name = "mfg_eb", \ } static const struct mtk_pll_data mfg_ao_plls[] = { - PLL(CLK_MFG_AO_MFGPLL, "mfgpll", MFGPLL_CON0, MFGPLL_CON0, 0, 0, 0, - BIT(0), MFGPLL_CON1, 24, 0, 0, 0, + PLL(CLK_MFG_AO_MFGPLL, "mfgpll", MFGPLL_CON0, MFGPLL_CON0, 0, 0, + PLL_PARENT_EN, BIT(0), MFGPLL_CON1, 24, 0, 0, 0, MFGPLL_CON1, 0, 22), }; static const struct mtk_pll_data mfgsc0_ao_plls[] = { PLL(CLK_MFGSC0_AO_MFGPLL_SC0, "mfgpll-sc0", MFGPLL_SC0_CON0, - MFGPLL_SC0_CON0, 0, 0, 0, BIT(0), MFGPLL_SC0_CON1, 24, 0, 0, 0, - MFGPLL_SC0_CON1, 0, 22), + MFGPLL_SC0_CON0, 0, 0, PLL_PARENT_EN, BIT(0), MFGPLL_SC0_CON1, 24, + 0, 0, 0, MFGPLL_SC0_CON1, 0, 22), }; static const struct mtk_pll_data mfgsc1_ao_plls[] = { PLL(CLK_MFGSC1_AO_MFGPLL_SC1, "mfgpll-sc1", MFGPLL_SC1_CON0, - MFGPLL_SC1_CON0, 0, 0, 0, BIT(0), MFGPLL_SC1_CON1, 24, 0, 0, 0, - MFGPLL_SC1_CON1, 0, 22), + MFGPLL_SC1_CON0, 0, 0, PLL_PARENT_EN, BIT(0), MFGPLL_SC1_CON1, 24, + 0, 0, 0, MFGPLL_SC1_CON1, 0, 22), }; static const struct of_device_id of_match_clk_mt8196_mfg[] = { diff --git a/drivers/clk/mediatek/clk-mt8516.c b/drivers/clk/mediatek/clk-mt8516.c index 21eb052b0a539c..342a59019fea9b 100644 --- a/drivers/clk/mediatek/clk-mt8516.c +++ b/drivers/clk/mediatek/clk-mt8516.c @@ -544,7 +544,7 @@ static const struct mtk_gate_regs top5_cg_regs = { #define GATE_TOP5(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &top5_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -static const struct mtk_gate top_clks[] __initconst = { +static const struct mtk_gate top_clks[] = { /* TOP1 */ GATE_TOP1(CLK_TOP_THEM, "them", "ahb_infra_sel", 1), GATE_TOP1(CLK_TOP_APDMA, "apdma", "ahb_infra_sel", 2), diff --git a/drivers/clk/mediatek/clk-mtk.c b/drivers/clk/mediatek/clk-mtk.c index 19cd27941747aa..deafe55a96cb1d 100644 --- a/drivers/clk/mediatek/clk-mtk.c +++ b/drivers/clk/mediatek/clk-mtk.c @@ -497,14 +497,16 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, if (mcd->need_runtime_pm) { - devm_pm_runtime_enable(&pdev->dev); + r = devm_pm_runtime_enable(&pdev->dev); + if (r) + goto unmap_io; /* * Do a pm_runtime_resume_and_get() to workaround a possible * deadlock between clk_register() and the genpd framework. */ r = pm_runtime_resume_and_get(&pdev->dev); if (r) - return r; + goto unmap_io; } /* Calculate how many clk_hw_onecell_data entries to allocate */ @@ -618,11 +620,11 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, free_data: mtk_free_clk_data(clk_data); free_base: - if (mcd->shared_io && base) - iounmap(base); - if (mcd->need_runtime_pm) pm_runtime_put(&pdev->dev); +unmap_io: + if (mcd->shared_io && base) + iounmap(base); return r; } diff --git a/drivers/clk/mediatek/clk-pll.c b/drivers/clk/mediatek/clk-pll.c index cd2b6ce551c6b0..de3eb02670554f 100644 --- a/drivers/clk/mediatek/clk-pll.c +++ b/drivers/clk/mediatek/clk-pll.c @@ -358,6 +358,9 @@ struct clk_hw *mtk_clk_register_pll_ops(struct mtk_clk_pll *pll, init.name = data->name; init.flags = (data->flags & PLL_AO) ? CLK_IS_CRITICAL : 0; + if (data->flags & PLL_PARENT_EN) + init.flags |= CLK_OPS_PARENT_ENABLE; + init.ops = pll_ops; if (data->parent_name) init.parent_names = &data->parent_name; diff --git a/drivers/clk/mediatek/clk-pll.h b/drivers/clk/mediatek/clk-pll.h index d71c150ce83e4b..de5a8fb7cbcfe9 100644 --- a/drivers/clk/mediatek/clk-pll.h +++ b/drivers/clk/mediatek/clk-pll.h @@ -21,6 +21,7 @@ struct mtk_pll_div_table { #define HAVE_RST_BAR BIT(0) #define PLL_AO BIT(1) +#define PLL_PARENT_EN BIT(2) #define POSTDIV_MASK GENMASK(2, 0) struct mtk_pll_data { diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c index 185b6348251dbd..d0d4c7b6dc8277 100644 --- a/drivers/clk/meson/g12a.c +++ b/drivers/clk/meson/g12a.c @@ -777,12 +777,23 @@ static struct clk_regmap g12a_hdmi_pll_dco = { }, }; +/* + * G12/SM1 hdmi OD dividers are POWER_OF_TWO dividers but limited to /4. + * A divider value of 3 should map to /8 but instead map /4 so ignore it. + */ +static const struct clk_div_table g12a_hdmi_pll_od_div_table[] = { + { .val = 0, .div = 1 }, + { .val = 1, .div = 2 }, + { .val = 2, .div = 4 }, + { /* sentinel */ } +}; + static struct clk_regmap g12a_hdmi_pll_od = { .data = &(struct clk_regmap_div_data){ .offset = HHI_HDMI_PLL_CNTL0, .shift = 16, .width = 2, - .flags = CLK_DIVIDER_POWER_OF_TWO, + .table = g12a_hdmi_pll_od_div_table, }, .hw.init = &(struct clk_init_data){ .name = "hdmi_pll_od", @@ -800,7 +811,7 @@ static struct clk_regmap g12a_hdmi_pll_od2 = { .offset = HHI_HDMI_PLL_CNTL0, .shift = 18, .width = 2, - .flags = CLK_DIVIDER_POWER_OF_TWO, + .table = g12a_hdmi_pll_od_div_table, }, .hw.init = &(struct clk_init_data){ .name = "hdmi_pll_od2", @@ -818,7 +829,7 @@ static struct clk_regmap g12a_hdmi_pll = { .offset = HHI_HDMI_PLL_CNTL0, .shift = 20, .width = 2, - .flags = CLK_DIVIDER_POWER_OF_TWO, + .table = g12a_hdmi_pll_od_div_table, }, .hw.init = &(struct clk_init_data){ .name = "hdmi_pll", diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c index 5a229c4ffae105..ec9a3414875ac3 100644 --- a/drivers/clk/meson/gxbb.c +++ b/drivers/clk/meson/gxbb.c @@ -349,12 +349,23 @@ static struct clk_regmap gxbb_hdmi_pll = { }, }; +/* + * GXL hdmi OD dividers are POWER_OF_TWO dividers but limited to /4. + * A divider value of 3 should map to /8 but instead map /4 so ignore it. + */ +static const struct clk_div_table gxl_hdmi_pll_od_div_table[] = { + { .val = 0, .div = 1 }, + { .val = 1, .div = 2 }, + { .val = 2, .div = 4 }, + { /* sentinel */ } +}; + static struct clk_regmap gxl_hdmi_pll_od = { .data = &(struct clk_regmap_div_data){ .offset = HHI_HDMI_PLL_CNTL + 8, .shift = 21, .width = 2, - .flags = CLK_DIVIDER_POWER_OF_TWO, + .table = gxl_hdmi_pll_od_div_table, }, .hw.init = &(struct clk_init_data){ .name = "hdmi_pll_od", @@ -372,7 +383,7 @@ static struct clk_regmap gxl_hdmi_pll_od2 = { .offset = HHI_HDMI_PLL_CNTL + 8, .shift = 23, .width = 2, - .flags = CLK_DIVIDER_POWER_OF_TWO, + .table = gxl_hdmi_pll_od_div_table, }, .hw.init = &(struct clk_init_data){ .name = "hdmi_pll_od2", @@ -390,7 +401,7 @@ static struct clk_regmap gxl_hdmi_pll = { .offset = HHI_HDMI_PLL_CNTL + 8, .shift = 19, .width = 2, - .flags = CLK_DIVIDER_POWER_OF_TWO, + .table = gxl_hdmi_pll_od_div_table, }, .hw.init = &(struct clk_init_data){ .name = "hdmi_pll", diff --git a/drivers/clk/microchip/clk-core.c b/drivers/clk/microchip/clk-core.c index b34348d491f3e1..a0163441dfe5c1 100644 --- a/drivers/clk/microchip/clk-core.c +++ b/drivers/clk/microchip/clk-core.c @@ -780,15 +780,6 @@ static unsigned long sclk_get_rate(struct clk_hw *hw, unsigned long parent_rate) return parent_rate / div; } -static int sclk_determine_rate(struct clk_hw *hw, - struct clk_rate_request *req) -{ - req->rate = calc_best_divided_rate(req->rate, req->best_parent_rate, - SLEW_SYSDIV, 1); - - return 0; -} - static int sclk_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { @@ -912,7 +903,6 @@ static int sclk_init(struct clk_hw *hw) const struct clk_ops pic32_sclk_ops = { .get_parent = sclk_get_parent, .set_parent = sclk_set_parent, - .determine_rate = sclk_determine_rate, .set_rate = sclk_set_rate, .recalc_rate = sclk_get_rate, .init = sclk_init, diff --git a/drivers/clk/mvebu/cp110-system-controller.c b/drivers/clk/mvebu/cp110-system-controller.c index 03c59bf2210602..b47c8690604667 100644 --- a/drivers/clk/mvebu/cp110-system-controller.c +++ b/drivers/clk/mvebu/cp110-system-controller.c @@ -110,6 +110,25 @@ static const char * const gate_base_names[] = { [CP110_GATE_EIP197] = "eip197" }; +static unsigned long gate_flags(const u8 bit_idx) +{ + switch (bit_idx) { + case CP110_GATE_PCIE_X1_0: + case CP110_GATE_PCIE_X1_1: + case CP110_GATE_PCIE_X4: + /* + * If a port had an active link at boot time, stopping + * the clock creates a failed state from which controller + * driver can not recover. + * Prevent stopping this clock till after a driver has taken + * ownership. + */ + return CLK_IGNORE_UNUSED; + default: + return 0; + } +}; + struct cp110_gate_clk { struct clk_hw hw; struct regmap *regmap; @@ -171,6 +190,7 @@ static struct clk_hw *cp110_register_gate(const char *name, init.ops = &cp110_gate_ops; init.parent_names = &parent_name; init.num_parents = 1; + init.flags = gate_flags(bit_idx); gate->regmap = regmap; gate->bit_idx = bit_idx; diff --git a/drivers/clk/nuvoton/clk-ma35d1-divider.c b/drivers/clk/nuvoton/clk-ma35d1-divider.c index e39f53d5bf4578..e992e7c3034197 100644 --- a/drivers/clk/nuvoton/clk-ma35d1-divider.c +++ b/drivers/clk/nuvoton/clk-ma35d1-divider.c @@ -44,11 +44,8 @@ static int ma35d1_clkdiv_determine_rate(struct clk_hw *hw, { struct ma35d1_adc_clk_div *dclk = to_ma35d1_adc_clk_div(hw); - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, - dclk->table, dclk->width, - CLK_DIVIDER_ROUND_CLOSEST); - - return 0; + return divider_determine_rate(hw, req, dclk->table, dclk->width, + CLK_DIVIDER_ROUND_CLOSEST); } static int ma35d1_clkdiv_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) diff --git a/drivers/clk/nxp/clk-lpc32xx.c b/drivers/clk/nxp/clk-lpc32xx.c index 23f980cf6a2b59..ae2fa5341a2e4f 100644 --- a/drivers/clk/nxp/clk-lpc32xx.c +++ b/drivers/clk/nxp/clk-lpc32xx.c @@ -975,10 +975,8 @@ static int clk_divider_determine_rate(struct clk_hw *hw, return 0; } - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, - divider->table, divider->width, divider->flags); - - return 0; + return divider_determine_rate(hw, req, divider->table, divider->width, + divider->flags); } static int clk_divider_set_rate(struct clk_hw *hw, unsigned long rate, diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index 78a3038426136e..6fef0bfc17736b 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -531,6 +531,7 @@ config QCM_DISPCC_2290 config QCS_DISPCC_615 tristate "QCS615 Display Clock Controller" + depends on ARM64 || COMPILE_TEST select QCS_GCC_615 help Support for the display clock controller on Qualcomm Technologies, Inc @@ -586,6 +587,7 @@ config QCS_GCC_615 config QCS_GPUCC_615 tristate "QCS615 Graphics clock controller" + depends on ARM64 || COMPILE_TEST select QCS_GCC_615 help Support for the graphics clock controller on QCS615 devices. @@ -594,6 +596,7 @@ config QCS_GPUCC_615 config QCS_VIDEOCC_615 tristate "QCS615 Video Clock Controller" + depends on ARM64 || COMPILE_TEST select QCS_GCC_615 help Support for the video clock controller on QCS615 devices. @@ -1448,6 +1451,7 @@ config SA_VIDEOCC_8775P config SM_VIDEOCC_6350 tristate "SM6350 Video Clock Controller" + depends on ARM64 || COMPILE_TEST select SM_GCC_6350 select QCOM_GDSC help diff --git a/drivers/clk/qcom/camcc-sm6350.c b/drivers/clk/qcom/camcc-sm6350.c index 8aac97d29ce3ff..7df12c1311c682 100644 --- a/drivers/clk/qcom/camcc-sm6350.c +++ b/drivers/clk/qcom/camcc-sm6350.c @@ -145,15 +145,11 @@ static struct clk_alpha_pll_postdiv camcc_pll1_out_even = { static const struct alpha_pll_config camcc_pll2_config = { .l = 0x64, .alpha = 0x0, - .post_div_val = 0x3 << 8, - .post_div_mask = 0x3 << 8, - .aux_output_mask = BIT(1), - .main_output_mask = BIT(0), - .early_output_mask = BIT(3), .config_ctl_val = 0x20000800, .config_ctl_hi_val = 0x400003d2, .test_ctl_val = 0x04000400, .test_ctl_hi_val = 0x00004000, + .user_ctl_val = 0x0000030b, }; static struct clk_alpha_pll camcc_pll2 = { @@ -1693,6 +1689,8 @@ static struct clk_branch camcc_sys_tmr_clk = { }, }; +static struct gdsc titan_top_gdsc; + static struct gdsc bps_gdsc = { .gdscr = 0x6004, .en_rest_wait_val = 0x2, @@ -1702,6 +1700,7 @@ static struct gdsc bps_gdsc = { .name = "bps_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &titan_top_gdsc.pd, .flags = VOTABLE, }; @@ -1714,6 +1713,7 @@ static struct gdsc ipe_0_gdsc = { .name = "ipe_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &titan_top_gdsc.pd, .flags = VOTABLE, }; @@ -1726,6 +1726,7 @@ static struct gdsc ife_0_gdsc = { .name = "ife_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &titan_top_gdsc.pd, }; static struct gdsc ife_1_gdsc = { @@ -1737,6 +1738,7 @@ static struct gdsc ife_1_gdsc = { .name = "ife_1_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &titan_top_gdsc.pd, }; static struct gdsc ife_2_gdsc = { @@ -1748,6 +1750,7 @@ static struct gdsc ife_2_gdsc = { .name = "ife_2_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &titan_top_gdsc.pd, }; static struct gdsc titan_top_gdsc = { diff --git a/drivers/clk/qcom/camcc-sm7150.c b/drivers/clk/qcom/camcc-sm7150.c index 4a3baf5d8e858c..590548cac45bf4 100644 --- a/drivers/clk/qcom/camcc-sm7150.c +++ b/drivers/clk/qcom/camcc-sm7150.c @@ -139,13 +139,9 @@ static struct clk_fixed_factor camcc_pll1_out_even = { /* 1920MHz configuration */ static const struct alpha_pll_config camcc_pll2_config = { .l = 0x64, - .post_div_val = 0x3 << 8, - .post_div_mask = 0x3 << 8, - .early_output_mask = BIT(3), - .aux_output_mask = BIT(1), - .main_output_mask = BIT(0), .config_ctl_hi_val = 0x400003d6, .config_ctl_val = 0x20000954, + .user_ctl_val = 0x0000030b, }; static struct clk_alpha_pll camcc_pll2 = { diff --git a/drivers/clk/qcom/camcc-sm8550.c b/drivers/clk/qcom/camcc-sm8550.c index 63aed9e4c362d5..b8ece8a57a8a9d 100644 --- a/drivers/clk/qcom/camcc-sm8550.c +++ b/drivers/clk/qcom/camcc-sm8550.c @@ -3204,6 +3204,8 @@ static struct clk_branch cam_cc_sfe_1_fast_ahb_clk = { }, }; +static struct gdsc cam_cc_titan_top_gdsc; + static struct gdsc cam_cc_bps_gdsc = { .gdscr = 0x10004, .en_rest_wait_val = 0x2, @@ -3213,6 +3215,7 @@ static struct gdsc cam_cc_bps_gdsc = { .name = "cam_cc_bps_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -3225,6 +3228,7 @@ static struct gdsc cam_cc_ife_0_gdsc = { .name = "cam_cc_ife_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -3237,6 +3241,7 @@ static struct gdsc cam_cc_ife_1_gdsc = { .name = "cam_cc_ife_1_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -3249,6 +3254,7 @@ static struct gdsc cam_cc_ife_2_gdsc = { .name = "cam_cc_ife_2_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -3261,6 +3267,7 @@ static struct gdsc cam_cc_ipe_0_gdsc = { .name = "cam_cc_ipe_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -3273,6 +3280,7 @@ static struct gdsc cam_cc_sbi_gdsc = { .name = "cam_cc_sbi_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -3285,6 +3293,7 @@ static struct gdsc cam_cc_sfe_0_gdsc = { .name = "cam_cc_sfe_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; @@ -3297,6 +3306,7 @@ static struct gdsc cam_cc_sfe_1_gdsc = { .name = "cam_cc_sfe_1_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE, }; diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c index 6aeba40358c11e..a84e8bee653462 100644 --- a/drivers/clk/qcom/clk-alpha-pll.c +++ b/drivers/clk/qcom/clk-alpha-pll.c @@ -1257,11 +1257,8 @@ static int clk_alpha_pll_postdiv_determine_rate(struct clk_hw *hw, else table = clk_alpha_div_table; - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, - table, pll->width, - CLK_DIVIDER_POWER_OF_TWO); - - return 0; + return divider_determine_rate(hw, req, table, pll->width, + CLK_DIVIDER_POWER_OF_TWO); } static int clk_alpha_pll_postdiv_ro_determine_rate(struct clk_hw *hw, @@ -1617,11 +1614,8 @@ static int clk_trion_pll_postdiv_determine_rate(struct clk_hw *hw, { struct clk_alpha_pll_postdiv *pll = to_clk_alpha_pll_postdiv(hw); - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, - pll->post_div_table, - pll->width, CLK_DIVIDER_ROUND_CLOSEST); - - return 0; + return divider_determine_rate(hw, req, pll->post_div_table, pll->width, + CLK_DIVIDER_ROUND_CLOSEST); }; static int @@ -1657,11 +1651,8 @@ static int clk_alpha_pll_postdiv_fabia_determine_rate(struct clk_hw *hw, { struct clk_alpha_pll_postdiv *pll = to_clk_alpha_pll_postdiv(hw); - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, - pll->post_div_table, - pll->width, CLK_DIVIDER_ROUND_CLOSEST); - - return 0; + return divider_determine_rate(hw, req, pll->post_div_table, pll->width, + CLK_DIVIDER_ROUND_CLOSEST); } static int clk_alpha_pll_postdiv_fabia_set_rate(struct clk_hw *hw, diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index e18cb8807d7353..d0a5847f911144 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -755,7 +755,7 @@ static int clk_rcg2_get_duty_cycle(struct clk_hw *hw, struct clk_duty *duty) static int clk_rcg2_set_duty_cycle(struct clk_hw *hw, struct clk_duty *duty) { struct clk_rcg2 *rcg = to_clk_rcg2(hw); - u32 notn_m, n, m, d, not2d, mask, duty_per, cfg; + u32 notn_m, n, m, d, not2d, mask, cfg; int ret; /* Duty-cycle cannot be modified for non-MND RCGs */ @@ -774,10 +774,8 @@ static int clk_rcg2_set_duty_cycle(struct clk_hw *hw, struct clk_duty *duty) n = (~(notn_m) + m) & mask; - duty_per = (duty->num * 100) / duty->den; - /* Calculate 2d value */ - d = DIV_ROUND_CLOSEST(n * duty_per * 2, 100); + d = DIV_ROUND_CLOSEST(n * duty->num * 2, duty->den); /* * Check bit widths of 2d. If D is too big reduce duty cycle. @@ -1266,6 +1264,7 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw, if (req->max_rate < parent_req.max_rate) parent_req.max_rate = req->max_rate; + parent_req.best_parent_hw = req->best_parent_hw; ret = __clk_determine_rate(req->best_parent_hw, &parent_req); if (ret) return ret; diff --git a/drivers/clk/qcom/clk-regmap-divider.c b/drivers/clk/qcom/clk-regmap-divider.c index 4f5395f0ab6d0e..672e82caf20504 100644 --- a/drivers/clk/qcom/clk-regmap-divider.c +++ b/drivers/clk/qcom/clk-regmap-divider.c @@ -26,24 +26,16 @@ static int div_ro_determine_rate(struct clk_hw *hw, val >>= divider->shift; val &= BIT(divider->width) - 1; - req->rate = divider_ro_round_rate(hw, req->rate, - &req->best_parent_rate, NULL, - divider->width, - CLK_DIVIDER_ROUND_CLOSEST, val); - - return 0; + return divider_ro_determine_rate(hw, req, NULL, divider->width, + CLK_DIVIDER_ROUND_CLOSEST, val); } static int div_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { struct clk_regmap_div *divider = to_clk_regmap_div(hw); - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, - NULL, - divider->width, - CLK_DIVIDER_ROUND_CLOSEST); - - return 0; + return divider_determine_rate(hw, req, NULL, divider->width, + CLK_DIVIDER_ROUND_CLOSEST); } static int div_set_rate(struct clk_hw *hw, unsigned long rate, diff --git a/drivers/clk/qcom/common.c b/drivers/clk/qcom/common.c index 12159188677418..eec369d2173b5c 100644 --- a/drivers/clk/qcom/common.c +++ b/drivers/clk/qcom/common.c @@ -454,7 +454,7 @@ int qcom_cc_probe_by_index(struct platform_device *pdev, int index, base = devm_platform_ioremap_resource(pdev, index); if (IS_ERR(base)) - return -ENOMEM; + return PTR_ERR(base); regmap = devm_regmap_init_mmio(&pdev->dev, base, desc->config); if (IS_ERR(regmap)) diff --git a/drivers/clk/qcom/dispcc-sdm845.c b/drivers/clk/qcom/dispcc-sdm845.c index 2f9e9665d7e93f..78e43f6d750260 100644 --- a/drivers/clk/qcom/dispcc-sdm845.c +++ b/drivers/clk/qcom/dispcc-sdm845.c @@ -280,7 +280,7 @@ static struct clk_rcg2 disp_cc_mdss_pclk0_clk_src = { .name = "disp_cc_mdss_pclk0_clk_src", .parent_data = disp_cc_parent_data_4, .num_parents = ARRAY_SIZE(disp_cc_parent_data_4), - .flags = CLK_SET_RATE_PARENT, + .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, .ops = &clk_pixel_ops, }, }; @@ -295,7 +295,7 @@ static struct clk_rcg2 disp_cc_mdss_pclk1_clk_src = { .name = "disp_cc_mdss_pclk1_clk_src", .parent_data = disp_cc_parent_data_4, .num_parents = ARRAY_SIZE(disp_cc_parent_data_4), - .flags = CLK_SET_RATE_PARENT, + .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, .ops = &clk_pixel_ops, }, }; diff --git a/drivers/clk/qcom/dispcc-sm7150.c b/drivers/clk/qcom/dispcc-sm7150.c index bdfff246ed3fe0..923f0f38e804cb 100644 --- a/drivers/clk/qcom/dispcc-sm7150.c +++ b/drivers/clk/qcom/dispcc-sm7150.c @@ -356,7 +356,7 @@ static struct clk_rcg2 dispcc_mdss_pclk0_clk_src = { .name = "dispcc_mdss_pclk0_clk_src", .parent_data = dispcc_parent_data_4, .num_parents = ARRAY_SIZE(dispcc_parent_data_4), - .flags = CLK_SET_RATE_PARENT, + .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, .ops = &clk_pixel_ops, }, }; @@ -370,7 +370,7 @@ static struct clk_rcg2 dispcc_mdss_pclk1_clk_src = { .name = "dispcc_mdss_pclk1_clk_src", .parent_data = dispcc_parent_data_4, .num_parents = ARRAY_SIZE(dispcc_parent_data_4), - .flags = CLK_SET_RATE_PARENT, + .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, .ops = &clk_pixel_ops, }, }; diff --git a/drivers/clk/qcom/gcc-glymur.c b/drivers/clk/qcom/gcc-glymur.c index 62059120f9720b..17e860307fa108 100644 --- a/drivers/clk/qcom/gcc-glymur.c +++ b/drivers/clk/qcom/gcc-glymur.c @@ -2317,7 +2317,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .parent_data = gcc_parent_data_17, .num_parents = ARRAY_SIZE(gcc_parent_data_17), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -2339,7 +2339,7 @@ static struct clk_rcg2 gcc_sdcc4_apps_clk_src = { .parent_data = gcc_parent_data_3, .num_parents = ARRAY_SIZE(gcc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -6760,7 +6760,7 @@ static struct clk_branch gcc_usb3_prim_phy_com_aux_clk = { static struct clk_branch gcc_usb3_prim_phy_pipe_clk = { .halt_reg = 0x3f088, - .halt_check = BRANCH_HALT_DELAY, + .halt_check = BRANCH_HALT_SKIP, .hwcg_reg = 0x3f088, .hwcg_bit = 1, .clkr = { @@ -6816,7 +6816,7 @@ static struct clk_branch gcc_usb3_sec_phy_com_aux_clk = { static struct clk_branch gcc_usb3_sec_phy_pipe_clk = { .halt_reg = 0xe2078, - .halt_check = BRANCH_HALT_VOTED, + .halt_check = BRANCH_HALT_SKIP, .hwcg_reg = 0xe2078, .hwcg_bit = 1, .clkr = { @@ -6872,7 +6872,7 @@ static struct clk_branch gcc_usb3_tert_phy_com_aux_clk = { static struct clk_branch gcc_usb3_tert_phy_pipe_clk = { .halt_reg = 0xe1078, - .halt_check = BRANCH_HALT_VOTED, + .halt_check = BRANCH_HALT_SKIP, .hwcg_reg = 0xe1078, .hwcg_bit = 1, .clkr = { @@ -6961,7 +6961,7 @@ static struct clk_branch gcc_usb4_0_master_clk = { static struct clk_branch gcc_usb4_0_phy_p2rr2p_pipe_clk = { .halt_reg = 0x2b0f4, - .halt_check = BRANCH_HALT, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x2b0f4, .enable_mask = BIT(0), @@ -6979,7 +6979,7 @@ static struct clk_branch gcc_usb4_0_phy_p2rr2p_pipe_clk = { static struct clk_branch gcc_usb4_0_phy_pcie_pipe_clk = { .halt_reg = 0x2b04c, - .halt_check = BRANCH_HALT_VOTED, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x62010, .enable_mask = BIT(11), @@ -7033,7 +7033,7 @@ static struct clk_branch gcc_usb4_0_phy_rx1_clk = { static struct clk_branch gcc_usb4_0_phy_usb_pipe_clk = { .halt_reg = 0x2b0bc, - .halt_check = BRANCH_HALT_VOTED, + .halt_check = BRANCH_HALT_SKIP, .hwcg_reg = 0x2b0bc, .hwcg_bit = 1, .clkr = { @@ -7196,7 +7196,7 @@ static struct clk_branch gcc_usb4_1_master_clk = { static struct clk_branch gcc_usb4_1_phy_p2rr2p_pipe_clk = { .halt_reg = 0x2d118, - .halt_check = BRANCH_HALT, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x2d118, .enable_mask = BIT(0), @@ -7214,7 +7214,7 @@ static struct clk_branch gcc_usb4_1_phy_p2rr2p_pipe_clk = { static struct clk_branch gcc_usb4_1_phy_pcie_pipe_clk = { .halt_reg = 0x2d04c, - .halt_check = BRANCH_HALT_VOTED, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x62010, .enable_mask = BIT(12), @@ -7268,7 +7268,7 @@ static struct clk_branch gcc_usb4_1_phy_rx1_clk = { static struct clk_branch gcc_usb4_1_phy_usb_pipe_clk = { .halt_reg = 0x2d0e0, - .halt_check = BRANCH_HALT_VOTED, + .halt_check = BRANCH_HALT_SKIP, .hwcg_reg = 0x2d0e0, .hwcg_bit = 1, .clkr = { @@ -7431,7 +7431,7 @@ static struct clk_branch gcc_usb4_2_master_clk = { static struct clk_branch gcc_usb4_2_phy_p2rr2p_pipe_clk = { .halt_reg = 0xe00f8, - .halt_check = BRANCH_HALT, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0xe00f8, .enable_mask = BIT(0), @@ -7449,7 +7449,7 @@ static struct clk_branch gcc_usb4_2_phy_p2rr2p_pipe_clk = { static struct clk_branch gcc_usb4_2_phy_pcie_pipe_clk = { .halt_reg = 0xe004c, - .halt_check = BRANCH_HALT_VOTED, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x62010, .enable_mask = BIT(13), @@ -7503,7 +7503,7 @@ static struct clk_branch gcc_usb4_2_phy_rx1_clk = { static struct clk_branch gcc_usb4_2_phy_usb_pipe_clk = { .halt_reg = 0xe00c0, - .halt_check = BRANCH_HALT_VOTED, + .halt_check = BRANCH_HALT_SKIP, .hwcg_reg = 0xe00c0, .hwcg_bit = 1, .clkr = { diff --git a/drivers/clk/qcom/gcc-ipq5018.c b/drivers/clk/qcom/gcc-ipq5018.c index dcda2be8c1a519..64792cda062021 100644 --- a/drivers/clk/qcom/gcc-ipq5018.c +++ b/drivers/clk/qcom/gcc-ipq5018.c @@ -1340,6 +1340,7 @@ static struct clk_branch gcc_sleep_clk_src = { .name = "gcc_sleep_clk_src", .parent_data = gcc_sleep_clk_data, .num_parents = ARRAY_SIZE(gcc_sleep_clk_data), + .flags = CLK_IS_CRITICAL, .ops = &clk_branch2_ops, }, }, diff --git a/drivers/clk/qcom/gcc-ipq5424.c b/drivers/clk/qcom/gcc-ipq5424.c index 3d42f3d85c7a92..71afa1b86b7233 100644 --- a/drivers/clk/qcom/gcc-ipq5424.c +++ b/drivers/clk/qcom/gcc-ipq5424.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2018,2020 The Linux Foundation. All rights reserved. - * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include @@ -3284,6 +3284,7 @@ static const struct qcom_cc_desc gcc_ipq5424_desc = { .num_clk_hws = ARRAY_SIZE(gcc_ipq5424_hws), .icc_hws = icc_ipq5424_hws, .num_icc_hws = ARRAY_SIZE(icc_ipq5424_hws), + .icc_first_node_id = IPQ_APPS_ID, }; static int gcc_ipq5424_probe(struct platform_device *pdev) diff --git a/drivers/clk/qcom/gcc-milos.c b/drivers/clk/qcom/gcc-milos.c index c9d61b05bafa16..81fa09ec55d7f6 100644 --- a/drivers/clk/qcom/gcc-milos.c +++ b/drivers/clk/qcom/gcc-milos.c @@ -917,7 +917,7 @@ static struct clk_rcg2 gcc_sdcc1_apps_clk_src = { .name = "gcc_sdcc1_apps_clk_src", .parent_data = gcc_parent_data_9, .num_parents = ARRAY_SIZE(gcc_parent_data_9), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -938,7 +938,7 @@ static struct clk_rcg2 gcc_sdcc1_ice_core_clk_src = { .name = "gcc_sdcc1_ice_core_clk_src", .parent_data = gcc_parent_data_10, .num_parents = ARRAY_SIZE(gcc_parent_data_10), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -962,7 +962,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .name = "gcc_sdcc2_apps_clk_src", .parent_data = gcc_parent_data_11, .num_parents = ARRAY_SIZE(gcc_parent_data_11), - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; diff --git a/drivers/clk/qcom/gcc-msm8917.c b/drivers/clk/qcom/gcc-msm8917.c index 0a1aa623cd49af..9d1c5a9953e2c6 100644 --- a/drivers/clk/qcom/gcc-msm8917.c +++ b/drivers/clk/qcom/gcc-msm8917.c @@ -3409,7 +3409,6 @@ static struct gdsc cpp_gdsc = { .pd = { .name = "cpp_gdsc", }, - .flags = ALWAYS_ON, .pwrsts = PWRSTS_OFF_ON, }; diff --git a/drivers/clk/qcom/gcc-msm8953.c b/drivers/clk/qcom/gcc-msm8953.c index 8f29ecc74c50bf..8fe1d3e421440c 100644 --- a/drivers/clk/qcom/gcc-msm8953.c +++ b/drivers/clk/qcom/gcc-msm8953.c @@ -3946,7 +3946,6 @@ static struct gdsc cpp_gdsc = { .pd = { .name = "cpp_gdsc", }, - .flags = ALWAYS_ON, .pwrsts = PWRSTS_OFF_ON, }; diff --git a/drivers/clk/qcom/gcc-qcs615.c b/drivers/clk/qcom/gcc-qcs615.c index 9695446bc2a3c8..5b3b8dd4f114bd 100644 --- a/drivers/clk/qcom/gcc-qcs615.c +++ b/drivers/clk/qcom/gcc-qcs615.c @@ -784,7 +784,7 @@ static struct clk_rcg2 gcc_sdcc1_apps_clk_src = { .name = "gcc_sdcc1_apps_clk_src", .parent_data = gcc_parent_data_1, .num_parents = ARRAY_SIZE(gcc_parent_data_1), - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -806,7 +806,7 @@ static struct clk_rcg2 gcc_sdcc1_ice_core_clk_src = { .name = "gcc_sdcc1_ice_core_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -830,7 +830,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .name = "gcc_sdcc2_apps_clk_src", .parent_data = gcc_parent_data_8, .num_parents = ARRAY_SIZE(gcc_parent_data_8), - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; diff --git a/drivers/clk/qcom/gcc-qdu1000.c b/drivers/clk/qcom/gcc-qdu1000.c index dbe9e9437939af..915bb9b4ff8130 100644 --- a/drivers/clk/qcom/gcc-qdu1000.c +++ b/drivers/clk/qcom/gcc-qdu1000.c @@ -904,7 +904,7 @@ static struct clk_rcg2 gcc_sdcc5_apps_clk_src = { .name = "gcc_sdcc5_apps_clk_src", .parent_data = gcc_parent_data_8, .num_parents = ARRAY_SIZE(gcc_parent_data_8), - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -923,7 +923,7 @@ static struct clk_rcg2 gcc_sdcc5_ice_core_clk_src = { .name = "gcc_sdcc5_ice_core_clk_src", .parent_data = gcc_parent_data_2, .num_parents = ARRAY_SIZE(gcc_parent_data_2), - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; diff --git a/drivers/clk/qcom/gcc-sdx75.c b/drivers/clk/qcom/gcc-sdx75.c index 453a6bf8e87863..1f3cd58483a2d6 100644 --- a/drivers/clk/qcom/gcc-sdx75.c +++ b/drivers/clk/qcom/gcc-sdx75.c @@ -1033,7 +1033,7 @@ static struct clk_rcg2 gcc_sdcc1_apps_clk_src = { .name = "gcc_sdcc1_apps_clk_src", .parent_data = gcc_parent_data_17, .num_parents = ARRAY_SIZE(gcc_parent_data_17), - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -1057,7 +1057,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .name = "gcc_sdcc2_apps_clk_src", .parent_data = gcc_parent_data_18, .num_parents = ARRAY_SIZE(gcc_parent_data_18), - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; diff --git a/drivers/clk/qcom/gcc-sm4450.c b/drivers/clk/qcom/gcc-sm4450.c index e2d9e4691c5b71..023d840e9f4ef0 100644 --- a/drivers/clk/qcom/gcc-sm4450.c +++ b/drivers/clk/qcom/gcc-sm4450.c @@ -769,7 +769,7 @@ static struct clk_rcg2 gcc_sdcc1_apps_clk_src = { .parent_data = gcc_parent_data_4, .num_parents = ARRAY_SIZE(gcc_parent_data_4), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -791,7 +791,7 @@ static struct clk_rcg2 gcc_sdcc1_ice_core_clk_src = { .parent_data = gcc_parent_data_4, .num_parents = ARRAY_SIZE(gcc_parent_data_4), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -815,7 +815,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .parent_data = gcc_parent_data_6, .num_parents = ARRAY_SIZE(gcc_parent_data_6), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; diff --git a/drivers/clk/qcom/gcc-sm8450.c b/drivers/clk/qcom/gcc-sm8450.c index 65d7d52bce0343..b18bb34889ab28 100644 --- a/drivers/clk/qcom/gcc-sm8450.c +++ b/drivers/clk/qcom/gcc-sm8450.c @@ -1034,7 +1034,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .parent_data = gcc_parent_data_7, .num_parents = ARRAY_SIZE(gcc_parent_data_7), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -1057,7 +1057,7 @@ static struct clk_rcg2 gcc_sdcc4_apps_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; diff --git a/drivers/clk/qcom/gcc-sm8550.c b/drivers/clk/qcom/gcc-sm8550.c index 862a9bf73bcb5d..36a5b7de5b55d2 100644 --- a/drivers/clk/qcom/gcc-sm8550.c +++ b/drivers/clk/qcom/gcc-sm8550.c @@ -1025,7 +1025,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .parent_data = gcc_parent_data_9, .num_parents = ARRAY_SIZE(gcc_parent_data_9), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -1048,7 +1048,7 @@ static struct clk_rcg2 gcc_sdcc4_apps_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; diff --git a/drivers/clk/qcom/gcc-sm8650.c b/drivers/clk/qcom/gcc-sm8650.c index 24f98062b9dd50..2dd6444ce0365f 100644 --- a/drivers/clk/qcom/gcc-sm8650.c +++ b/drivers/clk/qcom/gcc-sm8650.c @@ -1257,7 +1257,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .parent_data = gcc_parent_data_11, .num_parents = ARRAY_SIZE(gcc_parent_data_11), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -1279,7 +1279,7 @@ static struct clk_rcg2 gcc_sdcc4_apps_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_shared_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; diff --git a/drivers/clk/qcom/gcc-sm8750.c b/drivers/clk/qcom/gcc-sm8750.c index 8092dd6b37b56f..db81569dd4b17d 100644 --- a/drivers/clk/qcom/gcc-sm8750.c +++ b/drivers/clk/qcom/gcc-sm8750.c @@ -1012,6 +1012,7 @@ static struct clk_rcg2 gcc_qupv3_wrap2_s7_clk_src = { static const struct freq_tbl ftbl_gcc_sdcc2_apps_clk_src[] = { F(400000, P_BI_TCXO, 12, 1, 4), F(25000000, P_GCC_GPLL0_OUT_EVEN, 12, 0, 0), + F(37500000, P_GCC_GPLL0_OUT_EVEN, 8, 0, 0), F(50000000, P_GCC_GPLL0_OUT_EVEN, 6, 0, 0), F(100000000, P_GCC_GPLL0_OUT_EVEN, 3, 0, 0), F(202000000, P_GCC_GPLL9_OUT_MAIN, 4, 0, 0), @@ -1029,7 +1030,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .parent_data = gcc_parent_data_8, .num_parents = ARRAY_SIZE(gcc_parent_data_8), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -1051,7 +1052,7 @@ static struct clk_rcg2 gcc_sdcc4_apps_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; diff --git a/drivers/clk/qcom/gcc-x1e80100.c b/drivers/clk/qcom/gcc-x1e80100.c index 301fc9fc32d8e6..ef8d2df188d3bf 100644 --- a/drivers/clk/qcom/gcc-x1e80100.c +++ b/drivers/clk/qcom/gcc-x1e80100.c @@ -1123,7 +1123,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .parent_data = gcc_parent_data_9, .num_parents = ARRAY_SIZE(gcc_parent_data_9), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; @@ -1145,7 +1145,7 @@ static struct clk_rcg2 gcc_sdcc4_apps_clk_src = { .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_shared_floor_ops, }, }; diff --git a/drivers/clk/qcom/mmcc-sdm660.c b/drivers/clk/qcom/mmcc-sdm660.c index b723c536dfb6ce..dbd3f561dc6d0d 100644 --- a/drivers/clk/qcom/mmcc-sdm660.c +++ b/drivers/clk/qcom/mmcc-sdm660.c @@ -2781,6 +2781,7 @@ static struct gdsc *mmcc_sdm660_gdscs[] = { }; static const struct qcom_reset_map mmcc_660_resets[] = { + [MDSS_BCR] = { 0x2300 }, [CAMSS_MICRO_BCR] = { 0x3490 }, }; diff --git a/drivers/clk/qcom/tcsrcc-glymur.c b/drivers/clk/qcom/tcsrcc-glymur.c index c1f8b6d10b7fd6..215bc2ac548da8 100644 --- a/drivers/clk/qcom/tcsrcc-glymur.c +++ b/drivers/clk/qcom/tcsrcc-glymur.c @@ -28,10 +28,10 @@ enum { }; static struct clk_branch tcsr_edp_clkref_en = { - .halt_reg = 0x1c, + .halt_reg = 0x60, .halt_check = BRANCH_HALT_DELAY, .clkr = { - .enable_reg = 0x1c, + .enable_reg = 0x60, .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "tcsr_edp_clkref_en", @@ -45,10 +45,10 @@ static struct clk_branch tcsr_edp_clkref_en = { }; static struct clk_branch tcsr_pcie_1_clkref_en = { - .halt_reg = 0x4, + .halt_reg = 0x48, .halt_check = BRANCH_HALT_DELAY, .clkr = { - .enable_reg = 0x4, + .enable_reg = 0x48, .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "tcsr_pcie_1_clkref_en", @@ -62,10 +62,10 @@ static struct clk_branch tcsr_pcie_1_clkref_en = { }; static struct clk_branch tcsr_pcie_2_clkref_en = { - .halt_reg = 0x8, + .halt_reg = 0x4c, .halt_check = BRANCH_HALT_DELAY, .clkr = { - .enable_reg = 0x8, + .enable_reg = 0x4c, .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "tcsr_pcie_2_clkref_en", @@ -79,10 +79,10 @@ static struct clk_branch tcsr_pcie_2_clkref_en = { }; static struct clk_branch tcsr_pcie_3_clkref_en = { - .halt_reg = 0x10, + .halt_reg = 0x54, .halt_check = BRANCH_HALT_DELAY, .clkr = { - .enable_reg = 0x10, + .enable_reg = 0x54, .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "tcsr_pcie_3_clkref_en", @@ -96,10 +96,10 @@ static struct clk_branch tcsr_pcie_3_clkref_en = { }; static struct clk_branch tcsr_pcie_4_clkref_en = { - .halt_reg = 0x14, + .halt_reg = 0x58, .halt_check = BRANCH_HALT_DELAY, .clkr = { - .enable_reg = 0x14, + .enable_reg = 0x58, .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "tcsr_pcie_4_clkref_en", @@ -113,10 +113,10 @@ static struct clk_branch tcsr_pcie_4_clkref_en = { }; static struct clk_branch tcsr_usb2_1_clkref_en = { - .halt_reg = 0x28, + .halt_reg = 0x6c, .halt_check = BRANCH_HALT_DELAY, .clkr = { - .enable_reg = 0x28, + .enable_reg = 0x6c, .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "tcsr_usb2_1_clkref_en", @@ -130,10 +130,10 @@ static struct clk_branch tcsr_usb2_1_clkref_en = { }; static struct clk_branch tcsr_usb2_2_clkref_en = { - .halt_reg = 0x2c, + .halt_reg = 0x70, .halt_check = BRANCH_HALT_DELAY, .clkr = { - .enable_reg = 0x2c, + .enable_reg = 0x70, .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "tcsr_usb2_2_clkref_en", @@ -147,10 +147,10 @@ static struct clk_branch tcsr_usb2_2_clkref_en = { }; static struct clk_branch tcsr_usb2_3_clkref_en = { - .halt_reg = 0x30, + .halt_reg = 0x74, .halt_check = BRANCH_HALT_DELAY, .clkr = { - .enable_reg = 0x30, + .enable_reg = 0x74, .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "tcsr_usb2_3_clkref_en", @@ -164,10 +164,10 @@ static struct clk_branch tcsr_usb2_3_clkref_en = { }; static struct clk_branch tcsr_usb2_4_clkref_en = { - .halt_reg = 0x44, + .halt_reg = 0x88, .halt_check = BRANCH_HALT_DELAY, .clkr = { - .enable_reg = 0x44, + .enable_reg = 0x88, .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "tcsr_usb2_4_clkref_en", @@ -181,10 +181,10 @@ static struct clk_branch tcsr_usb2_4_clkref_en = { }; static struct clk_branch tcsr_usb3_0_clkref_en = { - .halt_reg = 0x20, + .halt_reg = 0x64, .halt_check = BRANCH_HALT_DELAY, .clkr = { - .enable_reg = 0x20, + .enable_reg = 0x64, .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "tcsr_usb3_0_clkref_en", @@ -198,10 +198,10 @@ static struct clk_branch tcsr_usb3_0_clkref_en = { }; static struct clk_branch tcsr_usb3_1_clkref_en = { - .halt_reg = 0x24, + .halt_reg = 0x68, .halt_check = BRANCH_HALT_DELAY, .clkr = { - .enable_reg = 0x24, + .enable_reg = 0x68, .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "tcsr_usb3_1_clkref_en", @@ -215,10 +215,10 @@ static struct clk_branch tcsr_usb3_1_clkref_en = { }; static struct clk_branch tcsr_usb4_1_clkref_en = { - .halt_reg = 0x0, + .halt_reg = 0x44, .halt_check = BRANCH_HALT_DELAY, .clkr = { - .enable_reg = 0x0, + .enable_reg = 0x44, .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "tcsr_usb4_1_clkref_en", @@ -232,10 +232,10 @@ static struct clk_branch tcsr_usb4_1_clkref_en = { }; static struct clk_branch tcsr_usb4_2_clkref_en = { - .halt_reg = 0x18, + .halt_reg = 0x5c, .halt_check = BRANCH_HALT_DELAY, .clkr = { - .enable_reg = 0x18, + .enable_reg = 0x5c, .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "tcsr_usb4_2_clkref_en", @@ -268,7 +268,7 @@ static const struct regmap_config tcsr_cc_glymur_regmap_config = { .reg_bits = 32, .reg_stride = 4, .val_bits = 32, - .max_register = 0x44, + .max_register = 0x94, .fast_io = true, }; diff --git a/drivers/clk/renesas/r9a06g032-clocks.c b/drivers/clk/renesas/r9a06g032-clocks.c index dcda19318b2a9a..0f5c91b5dfa995 100644 --- a/drivers/clk/renesas/r9a06g032-clocks.c +++ b/drivers/clk/renesas/r9a06g032-clocks.c @@ -1333,9 +1333,9 @@ static int __init r9a06g032_clocks_probe(struct platform_device *pdev) if (IS_ERR(mclk)) return PTR_ERR(mclk); - clocks->reg = of_iomap(np, 0); - if (WARN_ON(!clocks->reg)) - return -ENOMEM; + clocks->reg = devm_of_iomap(dev, np, 0, NULL); + if (IS_ERR(clocks->reg)) + return PTR_ERR(clocks->reg); r9a06g032_init_h2mode(clocks); diff --git a/drivers/clk/renesas/r9a09g077-cpg.c b/drivers/clk/renesas/r9a09g077-cpg.c index af3ef6d58c87cd..d12975418a5681 100644 --- a/drivers/clk/renesas/r9a09g077-cpg.c +++ b/drivers/clk/renesas/r9a09g077-cpg.c @@ -217,7 +217,7 @@ r9a09g077_cpg_div_clk_register(struct device *dev, if (core->dtable) clk_hw = clk_hw_register_divider_table(dev, core->name, - parent_name, 0, + parent_name, CLK_SET_RATE_PARENT, addr, GET_SHIFT(core->conf), GET_WIDTH(core->conf), @@ -226,7 +226,7 @@ r9a09g077_cpg_div_clk_register(struct device *dev, &pub->rmw_lock); else clk_hw = clk_hw_register_divider(dev, core->name, - parent_name, 0, + parent_name, CLK_SET_RATE_PARENT, addr, GET_SHIFT(core->conf), GET_WIDTH(core->conf), diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c index de1cf7ba45b78b..a0a68ec0490f7c 100644 --- a/drivers/clk/renesas/renesas-cpg-mssr.c +++ b/drivers/clk/renesas/renesas-cpg-mssr.c @@ -676,53 +676,56 @@ static int __init cpg_mssr_add_clk_domain(struct device *dev, #define rcdev_to_priv(x) container_of(x, struct cpg_mssr_priv, rcdev) -static int cpg_mssr_reset(struct reset_controller_dev *rcdev, - unsigned long id) +static int cpg_mssr_reset_operate(struct reset_controller_dev *rcdev, + const char *func, bool set, unsigned long id) { struct cpg_mssr_priv *priv = rcdev_to_priv(rcdev); unsigned int reg = id / 32; unsigned int bit = id % 32; + const u16 off = set ? priv->reset_regs[reg] : priv->reset_clear_regs[reg]; u32 bitmask = BIT(bit); - dev_dbg(priv->dev, "reset %u%02u\n", reg, bit); - - /* Reset module */ - writel(bitmask, priv->pub.base0 + priv->reset_regs[reg]); - - /* Wait for at least one cycle of the RCLK clock (@ ca. 32 kHz) */ - udelay(35); + if (func) + dev_dbg(priv->dev, "%s %u%02u\n", func, reg, bit); - /* Release module from reset state */ - writel(bitmask, priv->pub.base0 + priv->reset_clear_regs[reg]); + writel(bitmask, priv->pub.base0 + off); + readl(priv->pub.base0 + off); + barrier_data(priv->pub.base0 + off); return 0; } -static int cpg_mssr_assert(struct reset_controller_dev *rcdev, unsigned long id) +static int cpg_mssr_reset(struct reset_controller_dev *rcdev, + unsigned long id) { struct cpg_mssr_priv *priv = rcdev_to_priv(rcdev); - unsigned int reg = id / 32; - unsigned int bit = id % 32; - u32 bitmask = BIT(bit); - dev_dbg(priv->dev, "assert %u%02u\n", reg, bit); + /* Reset module */ + cpg_mssr_reset_operate(rcdev, "reset", true, id); - writel(bitmask, priv->pub.base0 + priv->reset_regs[reg]); - return 0; + /* + * On R-Car Gen4, delay after SRCR has been written is 1ms. + * On older SoCs, delay after SRCR has been written is 35us + * (one cycle of the RCLK clock @ ca. 32 kHz). + */ + if (priv->reg_layout == CLK_REG_LAYOUT_RCAR_GEN4) + usleep_range(1000, 2000); + else + usleep_range(35, 1000); + + /* Release module from reset state */ + return cpg_mssr_reset_operate(rcdev, NULL, false, id); +} + +static int cpg_mssr_assert(struct reset_controller_dev *rcdev, unsigned long id) +{ + return cpg_mssr_reset_operate(rcdev, "assert", true, id); } static int cpg_mssr_deassert(struct reset_controller_dev *rcdev, unsigned long id) { - struct cpg_mssr_priv *priv = rcdev_to_priv(rcdev); - unsigned int reg = id / 32; - unsigned int bit = id % 32; - u32 bitmask = BIT(bit); - - dev_dbg(priv->dev, "deassert %u%02u\n", reg, bit); - - writel(bitmask, priv->pub.base0 + priv->reset_clear_regs[reg]); - return 0; + return cpg_mssr_reset_operate(rcdev, "deassert", false, id); } static int cpg_mssr_status(struct reset_controller_dev *rcdev, diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c index 19caf26c991bd5..2d30b1e24f013c 100644 --- a/drivers/clk/rockchip/clk.c +++ b/drivers/clk/rockchip/clk.c @@ -693,7 +693,7 @@ void rockchip_clk_register_late_branches(struct device *dev, break; } - if (!pdev) + if (IS_ERR_OR_NULL(pdev)) dev_err(dev, "failed to register device for clock %s\n", list->name); } } diff --git a/drivers/clk/samsung/clk-exynos-clkout.c b/drivers/clk/samsung/clk-exynos-clkout.c index 5f1a4f5e2e594f..5b21025338bd53 100644 --- a/drivers/clk/samsung/clk-exynos-clkout.c +++ b/drivers/clk/samsung/clk-exynos-clkout.c @@ -175,6 +175,7 @@ static int exynos_clkout_probe(struct platform_device *pdev) clkout->mux.shift = EXYNOS_CLKOUT_MUX_SHIFT; clkout->mux.lock = &clkout->slock; + clkout->data.num = EXYNOS_CLKOUT_NR_CLKS; clkout->data.hws[0] = clk_hw_register_composite(NULL, "clkout", parent_names, parent_count, &clkout->mux.hw, &clk_mux_ops, NULL, NULL, &clkout->gate.hw, @@ -185,7 +186,6 @@ static int exynos_clkout_probe(struct platform_device *pdev) goto err_unmap; } - clkout->data.num = EXYNOS_CLKOUT_NR_CLKS; ret = of_clk_add_hw_provider(clkout->np, of_clk_hw_onecell_get, &clkout->data); if (ret) goto err_clk_unreg; diff --git a/drivers/clk/sophgo/clk-sg2042-clkgen.c b/drivers/clk/sophgo/clk-sg2042-clkgen.c index 683661b71787c9..9725ac4e050a4e 100644 --- a/drivers/clk/sophgo/clk-sg2042-clkgen.c +++ b/drivers/clk/sophgo/clk-sg2042-clkgen.c @@ -180,7 +180,6 @@ static int sg2042_clk_divider_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { struct sg2042_divider_clock *divider = to_sg2042_clk_divider(hw); - unsigned long ret_rate; u32 bestdiv; /* if read only, just return current value */ @@ -191,17 +190,13 @@ static int sg2042_clk_divider_determine_rate(struct clk_hw *hw, bestdiv = readl(divider->reg) >> divider->shift; bestdiv &= clk_div_mask(divider->width); } - ret_rate = DIV_ROUND_UP_ULL((u64)req->best_parent_rate, bestdiv); - } else { - ret_rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, NULL, - divider->width, divider->div_flags); - } + req->rate = DIV_ROUND_UP_ULL((u64)req->best_parent_rate, bestdiv); - pr_debug("--> %s: divider_round_rate: val = %ld\n", - clk_hw_get_name(hw), ret_rate); - req->rate = ret_rate; + return 0; + } - return 0; + return divider_determine_rate(hw, req, NULL, divider->width, + divider->div_flags); } static int sg2042_clk_divider_set_rate(struct clk_hw *hw, diff --git a/drivers/clk/spacemit/Makefile b/drivers/clk/spacemit/Makefile index 5ec6da61db98e0..ad2bf315109b80 100644 --- a/drivers/clk/spacemit/Makefile +++ b/drivers/clk/spacemit/Makefile @@ -1,5 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_SPACEMIT_K1_CCU) = spacemit-ccu-k1.o -spacemit-ccu-k1-y = ccu_pll.o ccu_mix.o ccu_ddn.o +obj-$(CONFIG_SPACEMIT_CCU) += spacemit-ccu.o +spacemit-ccu-y += ccu_common.o +spacemit-ccu-y += ccu_pll.o +spacemit-ccu-y += ccu_mix.o +spacemit-ccu-y += ccu_ddn.o + +obj-$(CONFIG_SPACEMIT_K1_CCU) += spacemit-ccu-k1.o spacemit-ccu-k1-y += ccu-k1.o diff --git a/drivers/clk/spacemit/ccu-k1.c b/drivers/clk/spacemit/ccu-k1.c index f5a9fe6ba18591..01d9485b615d32 100644 --- a/drivers/clk/spacemit/ccu-k1.c +++ b/drivers/clk/spacemit/ccu-k1.c @@ -1018,6 +1018,8 @@ static int spacemit_ccu_register(struct device *dev, if (!clk_data) return -ENOMEM; + clk_data->num = data->num; + for (i = 0; i < data->num; i++) { struct clk_hw *hw = data->hws[i]; struct ccu_common *common; @@ -1044,8 +1046,6 @@ static int spacemit_ccu_register(struct device *dev, clk_data->hws[i] = hw; } - clk_data->num = data->num; - ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, clk_data); if (ret) dev_err(dev, "failed to add clock hardware provider (%d)\n", ret); @@ -1204,6 +1204,7 @@ static struct platform_driver k1_ccu_driver = { }; module_platform_driver(k1_ccu_driver); +MODULE_IMPORT_NS("CLK_SPACEMIT"); MODULE_DESCRIPTION("SpacemiT K1 CCU driver"); MODULE_AUTHOR("Haylen Chu "); MODULE_LICENSE("GPL"); diff --git a/drivers/clk/spacemit/ccu_common.c b/drivers/clk/spacemit/ccu_common.c new file mode 100644 index 00000000000000..4412c4104dabb3 --- /dev/null +++ b/drivers/clk/spacemit/ccu_common.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include + +MODULE_DESCRIPTION("SpacemiT CCU common clock driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/spacemit/ccu_ddn.c b/drivers/clk/spacemit/ccu_ddn.c index 5b16e273bee5b1..b5540e0781ffa3 100644 --- a/drivers/clk/spacemit/ccu_ddn.c +++ b/drivers/clk/spacemit/ccu_ddn.c @@ -84,3 +84,4 @@ const struct clk_ops spacemit_ccu_ddn_ops = { .determine_rate = ccu_ddn_determine_rate, .set_rate = ccu_ddn_set_rate, }; +EXPORT_SYMBOL_NS_GPL(spacemit_ccu_ddn_ops, "CLK_SPACEMIT"); diff --git a/drivers/clk/spacemit/ccu_mix.c b/drivers/clk/spacemit/ccu_mix.c index 7b799087537231..67f8b12b4f5b7d 100644 --- a/drivers/clk/spacemit/ccu_mix.c +++ b/drivers/clk/spacemit/ccu_mix.c @@ -198,24 +198,28 @@ const struct clk_ops spacemit_ccu_gate_ops = { .enable = ccu_gate_enable, .is_enabled = ccu_gate_is_enabled, }; +EXPORT_SYMBOL_NS_GPL(spacemit_ccu_gate_ops, "CLK_SPACEMIT"); const struct clk_ops spacemit_ccu_factor_ops = { .determine_rate = ccu_factor_determine_rate, .recalc_rate = ccu_factor_recalc_rate, .set_rate = ccu_factor_set_rate, }; +EXPORT_SYMBOL_NS_GPL(spacemit_ccu_factor_ops, "CLK_SPACEMIT"); const struct clk_ops spacemit_ccu_mux_ops = { .determine_rate = ccu_mix_determine_rate, .get_parent = ccu_mux_get_parent, .set_parent = ccu_mux_set_parent, }; +EXPORT_SYMBOL_NS_GPL(spacemit_ccu_mux_ops, "CLK_SPACEMIT"); const struct clk_ops spacemit_ccu_div_ops = { .determine_rate = ccu_mix_determine_rate, .recalc_rate = ccu_div_recalc_rate, .set_rate = ccu_mix_set_rate, }; +EXPORT_SYMBOL_NS_GPL(spacemit_ccu_div_ops, "CLK_SPACEMIT"); const struct clk_ops spacemit_ccu_factor_gate_ops = { .disable = ccu_gate_disable, @@ -226,6 +230,7 @@ const struct clk_ops spacemit_ccu_factor_gate_ops = { .recalc_rate = ccu_factor_recalc_rate, .set_rate = ccu_factor_set_rate, }; +EXPORT_SYMBOL_NS_GPL(spacemit_ccu_factor_gate_ops, "CLK_SPACEMIT"); const struct clk_ops spacemit_ccu_mux_gate_ops = { .disable = ccu_gate_disable, @@ -236,6 +241,7 @@ const struct clk_ops spacemit_ccu_mux_gate_ops = { .get_parent = ccu_mux_get_parent, .set_parent = ccu_mux_set_parent, }; +EXPORT_SYMBOL_NS_GPL(spacemit_ccu_mux_gate_ops, "CLK_SPACEMIT"); const struct clk_ops spacemit_ccu_div_gate_ops = { .disable = ccu_gate_disable, @@ -246,6 +252,7 @@ const struct clk_ops spacemit_ccu_div_gate_ops = { .recalc_rate = ccu_div_recalc_rate, .set_rate = ccu_mix_set_rate, }; +EXPORT_SYMBOL_NS_GPL(spacemit_ccu_div_gate_ops, "CLK_SPACEMIT"); const struct clk_ops spacemit_ccu_mux_div_gate_ops = { .disable = ccu_gate_disable, @@ -259,6 +266,7 @@ const struct clk_ops spacemit_ccu_mux_div_gate_ops = { .recalc_rate = ccu_div_recalc_rate, .set_rate = ccu_mix_set_rate, }; +EXPORT_SYMBOL_NS_GPL(spacemit_ccu_mux_div_gate_ops, "CLK_SPACEMIT"); const struct clk_ops spacemit_ccu_mux_div_ops = { .get_parent = ccu_mux_get_parent, @@ -268,3 +276,4 @@ const struct clk_ops spacemit_ccu_mux_div_ops = { .recalc_rate = ccu_div_recalc_rate, .set_rate = ccu_mix_set_rate, }; +EXPORT_SYMBOL_NS_GPL(spacemit_ccu_mux_div_ops, "CLK_SPACEMIT"); diff --git a/drivers/clk/spacemit/ccu_pll.c b/drivers/clk/spacemit/ccu_pll.c index d92f0dae65a490..76d0244873d87c 100644 --- a/drivers/clk/spacemit/ccu_pll.c +++ b/drivers/clk/spacemit/ccu_pll.c @@ -157,3 +157,4 @@ const struct clk_ops spacemit_ccu_pll_ops = { .determine_rate = ccu_pll_determine_rate, .is_enabled = ccu_pll_is_enabled, }; +EXPORT_SYMBOL_NS_GPL(spacemit_ccu_pll_ops, "CLK_SPACEMIT"); diff --git a/drivers/clk/sprd/div.c b/drivers/clk/sprd/div.c index 01342388196800..cd57163a7204c0 100644 --- a/drivers/clk/sprd/div.c +++ b/drivers/clk/sprd/div.c @@ -14,11 +14,7 @@ static int sprd_div_determine_rate(struct clk_hw *hw, { struct sprd_div *cd = hw_to_sprd_div(hw); - req->rate = divider_round_rate(&cd->common.hw, req->rate, - &req->best_parent_rate, - NULL, cd->div.width, 0); - - return 0; + return divider_determine_rate(&cd->common.hw, req, NULL, cd->div.width, 0); } unsigned long sprd_div_helper_recalc_rate(struct sprd_clk_common *common, diff --git a/drivers/clk/stm32/clk-stm32-core.c b/drivers/clk/stm32/clk-stm32-core.c index 72825b9c36a4d3..e921c25a929c30 100644 --- a/drivers/clk/stm32/clk-stm32-core.c +++ b/drivers/clk/stm32/clk-stm32-core.c @@ -369,22 +369,14 @@ static int clk_stm32_divider_determine_rate(struct clk_hw *hw, val = readl(div->base + divider->offset) >> divider->shift; val &= clk_div_mask(divider->width); - req->rate = divider_ro_round_rate(hw, req->rate, - &req->best_parent_rate, - divider->table, - divider->width, - divider->flags, val); - - return 0; + return divider_ro_determine_rate(hw, req, + divider->table, + divider->width, + divider->flags, val); } - req->rate = divider_round_rate_parent(hw, clk_hw_get_parent(hw), - req->rate, - &req->best_parent_rate, - divider->table, - divider->width, divider->flags); - - return 0; + return divider_determine_rate(hw, req, divider->table, divider->width, + divider->flags); } static unsigned long clk_stm32_divider_recalc_rate(struct clk_hw *hw, @@ -441,7 +433,6 @@ static int clk_stm32_composite_determine_rate(struct clk_hw *hw, { struct clk_stm32_composite *composite = to_clk_stm32_composite(hw); const struct stm32_div_cfg *divider; - long rate; if (composite->div_id == NO_STM32_DIV) return 0; @@ -455,24 +446,13 @@ static int clk_stm32_composite_determine_rate(struct clk_hw *hw, val = readl(composite->base + divider->offset) >> divider->shift; val &= clk_div_mask(divider->width); - rate = divider_ro_round_rate(hw, req->rate, &req->best_parent_rate, - divider->table, divider->width, divider->flags, - val); - if (rate < 0) - return rate; - - req->rate = rate; - return 0; + return divider_ro_determine_rate(hw, req, divider->table, + divider->width, divider->flags, + val); } - rate = divider_round_rate_parent(hw, clk_hw_get_parent(hw), - req->rate, &req->best_parent_rate, - divider->table, divider->width, divider->flags); - if (rate < 0) - return rate; - - req->rate = rate; - return 0; + return divider_determine_rate(hw, req, divider->table, divider->width, + divider->flags); } static u8 clk_stm32_composite_get_parent(struct clk_hw *hw) diff --git a/drivers/clk/thead/clk-th1520-ap.c b/drivers/clk/thead/clk-th1520-ap.c index 71ad03a998e8e1..d870f0c665f8a4 100644 --- a/drivers/clk/thead/clk-th1520-ap.c +++ b/drivers/clk/thead/clk-th1520-ap.c @@ -8,11 +8,14 @@ #include #include #include +#include #include #include #include #include +#define TH1520_PLL_STS 0x80 + #define TH1520_PLL_POSTDIV2 GENMASK(26, 24) #define TH1520_PLL_POSTDIV1 GENMASK(22, 20) #define TH1520_PLL_FBDIV GENMASK(19, 8) @@ -23,6 +26,13 @@ #define TH1520_PLL_FRAC GENMASK(23, 0) #define TH1520_PLL_FRAC_BITS 24 +/* + * All PLLs in TH1520 take 21250ns at maximum to lock, let's take its double + * for safety. + */ +#define TH1520_PLL_LOCK_TIMEOUT_US 44 +#define TH1520_PLL_STABLE_DELAY_US 30 + struct ccu_internal { u8 shift; u8 width; @@ -64,6 +74,7 @@ struct ccu_div { struct ccu_pll { struct ccu_common common; + u32 lock_sts_mask; }; #define TH_CCU_ARG(_shift, _width) \ @@ -299,9 +310,21 @@ static void ccu_pll_disable(struct clk_hw *hw) static int ccu_pll_enable(struct clk_hw *hw) { struct ccu_pll *pll = hw_to_ccu_pll(hw); + u32 reg; + int ret; - return regmap_clear_bits(pll->common.map, pll->common.cfg1, - TH1520_PLL_VCO_RST); + regmap_clear_bits(pll->common.map, pll->common.cfg1, + TH1520_PLL_VCO_RST); + + ret = regmap_read_poll_timeout_atomic(pll->common.map, TH1520_PLL_STS, + reg, reg & pll->lock_sts_mask, + 5, TH1520_PLL_LOCK_TIMEOUT_US); + if (ret) + return ret; + + udelay(TH1520_PLL_STABLE_DELAY_US); + + return 0; } static int ccu_pll_is_enabled(struct clk_hw *hw) @@ -389,6 +412,7 @@ static struct ccu_pll cpu_pll0_clk = { &clk_pll_ops, CLK_IS_CRITICAL), }, + .lock_sts_mask = BIT(1), }; static struct ccu_pll cpu_pll1_clk = { @@ -401,6 +425,7 @@ static struct ccu_pll cpu_pll1_clk = { &clk_pll_ops, CLK_IS_CRITICAL), }, + .lock_sts_mask = BIT(4), }; static struct ccu_pll gmac_pll_clk = { @@ -413,6 +438,7 @@ static struct ccu_pll gmac_pll_clk = { &clk_pll_ops, CLK_IS_CRITICAL), }, + .lock_sts_mask = BIT(3), }; static const struct clk_hw *gmac_pll_clk_parent[] = { @@ -433,6 +459,7 @@ static struct ccu_pll video_pll_clk = { &clk_pll_ops, CLK_IS_CRITICAL), }, + .lock_sts_mask = BIT(7), }; static const struct clk_hw *video_pll_clk_parent[] = { @@ -453,6 +480,7 @@ static struct ccu_pll dpu0_pll_clk = { &clk_pll_ops, 0), }, + .lock_sts_mask = BIT(8), }; static const struct clk_hw *dpu0_pll_clk_parent[] = { @@ -469,6 +497,7 @@ static struct ccu_pll dpu1_pll_clk = { &clk_pll_ops, 0), }, + .lock_sts_mask = BIT(9), }; static const struct clk_hw *dpu1_pll_clk_parent[] = { @@ -485,6 +514,7 @@ static struct ccu_pll tee_pll_clk = { &clk_pll_ops, CLK_IS_CRITICAL), }, + .lock_sts_mask = BIT(10), }; static const struct clk_parent_data c910_i0_parents[] = { diff --git a/drivers/clk/x86/clk-cgu.c b/drivers/clk/x86/clk-cgu.c index d099667355f8d8..92ee05d75af2b2 100644 --- a/drivers/clk/x86/clk-cgu.c +++ b/drivers/clk/x86/clk-cgu.c @@ -137,10 +137,8 @@ static int lgm_clk_divider_determine_rate(struct clk_hw *hw, { struct lgm_clk_divider *divider = to_lgm_clk_divider(hw); - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, divider->table, - divider->width, divider->flags); - - return 0; + return divider_determine_rate(hw, req, divider->table, divider->width, + divider->flags); } static int diff --git a/drivers/clk/zynqmp/divider.c b/drivers/clk/zynqmp/divider.c index c824eeacd8ebd4..984e577ea67115 100644 --- a/drivers/clk/zynqmp/divider.c +++ b/drivers/clk/zynqmp/divider.c @@ -111,10 +111,9 @@ static unsigned long zynqmp_clk_divider_recalc_rate(struct clk_hw *hw, } /** - * zynqmp_clk_divider_round_rate() - Round rate of divider clock + * zynqmp_clk_divider_determine_rate() - Determine rate of divider clock * @hw: handle between common and hardware-specific interfaces - * @rate: rate of clock to be set - * @prate: rate of parent clock + * @req: rate of clock to be set * * Return: 0 on success else error+reason */ @@ -151,8 +150,9 @@ static int zynqmp_clk_divider_determine_rate(struct clk_hw *hw, width = fls(divider->max_div); - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, - NULL, width, divider->flags); + ret = divider_determine_rate(hw, req, NULL, width, divider->flags); + if (ret != 0) + return ret; if (divider->is_frac && (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) && (req->rate % req->best_parent_rate)) diff --git a/drivers/clk/zynqmp/pll.c b/drivers/clk/zynqmp/pll.c index 630a3936c97c34..6bc2c3934f564f 100644 --- a/drivers/clk/zynqmp/pll.c +++ b/drivers/clk/zynqmp/pll.c @@ -91,10 +91,9 @@ static inline void zynqmp_pll_set_mode(struct clk_hw *hw, bool on) } /** - * zynqmp_pll_round_rate() - Round a clock frequency + * zynqmp_pll_determine_rate() - Round a clock frequency * @hw: Handle between common and hardware-specific interfaces - * @rate: Desired clock frequency - * @prate: Clock frequency of parent clock + * @req: Desired clock frequency * * Return: Frequency closest to @rate the hardware can generate */ diff --git a/drivers/clocksource/arm_arch_timer_mmio.c b/drivers/clocksource/arm_arch_timer_mmio.c index ebe1987d651ebc..d10362692fdd32 100644 --- a/drivers/clocksource/arm_arch_timer_mmio.c +++ b/drivers/clocksource/arm_arch_timer_mmio.c @@ -426,6 +426,7 @@ static struct platform_driver arch_timer_mmio_drv = { .driver = { .name = "arch-timer-mmio", .of_match_table = arch_timer_mmio_of_table, + .suppress_bind_attrs = true, }, .probe = arch_timer_mmio_probe, }; @@ -434,6 +435,7 @@ builtin_platform_driver(arch_timer_mmio_drv); static struct platform_driver arch_timer_mmio_acpi_drv = { .driver = { .name = "gtdt-arm-mmio-timer", + .suppress_bind_attrs = true, }, .probe = arch_timer_mmio_probe, }; diff --git a/drivers/clocksource/timer-nxp-pit.c b/drivers/clocksource/timer-nxp-pit.c index 2d0a3554b6bf7d..d1740f18f71803 100644 --- a/drivers/clocksource/timer-nxp-pit.c +++ b/drivers/clocksource/timer-nxp-pit.c @@ -374,9 +374,10 @@ static struct platform_driver nxp_pit_driver = { .driver = { .name = "nxp-pit", .of_match_table = pit_timer_of_match, + .suppress_bind_attrs = true, }, .probe = pit_timer_probe, }; -module_platform_driver(nxp_pit_driver); +builtin_platform_driver(nxp_pit_driver); TIMER_OF_DECLARE(vf610, "fsl,vf610-pit", pit_timer_init); diff --git a/drivers/clocksource/timer-nxp-stm.c b/drivers/clocksource/timer-nxp-stm.c index bbc40623728fa5..1ab907233f4818 100644 --- a/drivers/clocksource/timer-nxp-stm.c +++ b/drivers/clocksource/timer-nxp-stm.c @@ -177,15 +177,15 @@ static void nxp_stm_clocksource_resume(struct clocksource *cs) nxp_stm_clocksource_enable(cs); } -static void __init devm_clocksource_unregister(void *data) +static void devm_clocksource_unregister(void *data) { struct stm_timer *stm_timer = data; clocksource_unregister(&stm_timer->cs); } -static int __init nxp_stm_clocksource_init(struct device *dev, struct stm_timer *stm_timer, - const char *name, void __iomem *base, struct clk *clk) +static int nxp_stm_clocksource_init(struct device *dev, struct stm_timer *stm_timer, + const char *name, void __iomem *base, struct clk *clk) { int ret; @@ -208,10 +208,8 @@ static int __init nxp_stm_clocksource_init(struct device *dev, struct stm_timer return ret; ret = devm_add_action_or_reset(dev, devm_clocksource_unregister, stm_timer); - if (ret) { - clocksource_unregister(&stm_timer->cs); + if (ret) return ret; - } stm_sched_clock = stm_timer; @@ -298,9 +296,9 @@ static void nxp_stm_clockevent_resume(struct clock_event_device *ced) nxp_stm_module_get(stm_timer); } -static int __init nxp_stm_clockevent_per_cpu_init(struct device *dev, struct stm_timer *stm_timer, - const char *name, void __iomem *base, int irq, - struct clk *clk, int cpu) +static int nxp_stm_clockevent_per_cpu_init(struct device *dev, struct stm_timer *stm_timer, + const char *name, void __iomem *base, int irq, + struct clk *clk, int cpu) { stm_timer->base = base; stm_timer->rate = clk_get_rate(clk); @@ -388,7 +386,7 @@ static irqreturn_t nxp_stm_module_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static int __init nxp_stm_timer_probe(struct platform_device *pdev) +static int nxp_stm_timer_probe(struct platform_device *pdev) { struct stm_timer *stm_timer; struct device *dev = &pdev->dev; @@ -484,14 +482,15 @@ static const struct of_device_id nxp_stm_of_match[] = { }; MODULE_DEVICE_TABLE(of, nxp_stm_of_match); -static struct platform_driver nxp_stm_probe = { +static struct platform_driver nxp_stm_driver = { .probe = nxp_stm_timer_probe, .driver = { .name = "nxp-stm", .of_match_table = nxp_stm_of_match, + .suppress_bind_attrs = true, }, }; -module_platform_driver(nxp_stm_probe); +builtin_platform_driver(nxp_stm_driver); MODULE_DESCRIPTION("NXP System Timer Module driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/clocksource/timer-ralink.c b/drivers/clocksource/timer-ralink.c index 6ecdb4228f7637..68434d9ed91070 100644 --- a/drivers/clocksource/timer-ralink.c +++ b/drivers/clocksource/timer-ralink.c @@ -130,14 +130,15 @@ static int __init ralink_systick_init(struct device_node *np) systick.dev.irq = irq_of_parse_and_map(np, 0); if (!systick.dev.irq) { pr_err("%pOFn: request_irq failed", np); - return -EINVAL; + ret = -EINVAL; + goto err_iounmap; } ret = clocksource_mmio_init(systick.membase + SYSTICK_COUNT, np->name, SYSTICK_FREQ, 301, 16, clocksource_mmio_readl_up); if (ret) - return ret; + goto err_free_irq; clockevents_register_device(&systick.dev); @@ -145,6 +146,12 @@ static int __init ralink_systick_init(struct device_node *np) np, systick.dev.mult, systick.dev.shift); return 0; + +err_free_irq: + irq_dispose_mapping(systick.dev.irq); +err_iounmap: + iounmap(systick.membase); + return ret; } TIMER_OF_DECLARE(systick, "ralink,cevt-systick", ralink_systick_init); diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c index 4d7cf338824a3b..cfc4d83c42c039 100644 --- a/drivers/clocksource/timer-riscv.c +++ b/drivers/clocksource/timer-riscv.c @@ -50,8 +50,9 @@ static int riscv_clock_next_event(unsigned long delta, if (static_branch_likely(&riscv_sstc_available)) { #if defined(CONFIG_32BIT) - csr_write(CSR_STIMECMP, next_tval & 0xFFFFFFFF); + csr_write(CSR_STIMECMP, ULONG_MAX); csr_write(CSR_STIMECMPH, next_tval >> 32); + csr_write(CSR_STIMECMP, next_tval & 0xFFFFFFFF); #else csr_write(CSR_STIMECMP, next_tval); #endif diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c index 7e2f2b1a1c362e..8c5507d78914f7 100644 --- a/drivers/comedi/comedi_fops.c +++ b/drivers/comedi/comedi_fops.c @@ -1099,7 +1099,7 @@ static int do_chaninfo_ioctl(struct comedi_device *dev, for (i = 0; i < s->n_chan; i++) { int x; - x = (dev->minor << 28) | (it->subdev << 24) | (i << 16) | + x = (it->subdev << 24) | (i << 16) | (s->range_table_list[i]->length); if (put_user(x, it->rangelist + i)) return -EFAULT; @@ -3023,7 +3023,12 @@ static int compat_chaninfo(struct file *file, unsigned long arg) chaninfo.rangelist = compat_ptr(chaninfo32.rangelist); mutex_lock(&dev->mutex); - err = do_chaninfo_ioctl(dev, &chaninfo); + if (!dev->attached) { + dev_dbg(dev->class_dev, "no driver attached\n"); + err = -ENODEV; + } else { + err = do_chaninfo_ioctl(dev, &chaninfo); + } mutex_unlock(&dev->mutex); return err; } @@ -3044,7 +3049,12 @@ static int compat_rangeinfo(struct file *file, unsigned long arg) rangeinfo.range_ptr = compat_ptr(rangeinfo32.range_ptr); mutex_lock(&dev->mutex); - err = do_rangeinfo_ioctl(dev, &rangeinfo); + if (!dev->attached) { + dev_dbg(dev->class_dev, "no driver attached\n"); + err = -ENODEV; + } else { + err = do_rangeinfo_ioctl(dev, &rangeinfo); + } mutex_unlock(&dev->mutex); return err; } @@ -3120,7 +3130,12 @@ static int compat_cmd(struct file *file, unsigned long arg) return rc; mutex_lock(&dev->mutex); - rc = do_cmd_ioctl(dev, &cmd, ©, file); + if (!dev->attached) { + dev_dbg(dev->class_dev, "no driver attached\n"); + rc = -ENODEV; + } else { + rc = do_cmd_ioctl(dev, &cmd, ©, file); + } mutex_unlock(&dev->mutex); if (copy) { /* Special case: copy cmd back to user. */ @@ -3145,7 +3160,12 @@ static int compat_cmdtest(struct file *file, unsigned long arg) return rc; mutex_lock(&dev->mutex); - rc = do_cmdtest_ioctl(dev, &cmd, ©, file); + if (!dev->attached) { + dev_dbg(dev->class_dev, "no driver attached\n"); + rc = -ENODEV; + } else { + rc = do_cmdtest_ioctl(dev, &cmd, ©, file); + } mutex_unlock(&dev->mutex); if (copy) { err = put_compat_cmd(compat_ptr(arg), &cmd); @@ -3205,7 +3225,12 @@ static int compat_insnlist(struct file *file, unsigned long arg) } mutex_lock(&dev->mutex); - rc = do_insnlist_ioctl(dev, insns, insnlist32.n_insns, file); + if (!dev->attached) { + dev_dbg(dev->class_dev, "no driver attached\n"); + rc = -ENODEV; + } else { + rc = do_insnlist_ioctl(dev, insns, insnlist32.n_insns, file); + } mutex_unlock(&dev->mutex); kfree(insns); return rc; @@ -3224,7 +3249,12 @@ static int compat_insn(struct file *file, unsigned long arg) return rc; mutex_lock(&dev->mutex); - rc = do_insn_ioctl(dev, &insn, file); + if (!dev->attached) { + dev_dbg(dev->class_dev, "no driver attached\n"); + rc = -ENODEV; + } else { + rc = do_insn_ioctl(dev, &insn, file); + } mutex_unlock(&dev->mutex); return rc; } diff --git a/drivers/comedi/drivers/c6xdigio.c b/drivers/comedi/drivers/c6xdigio.c index 14b90d1c64dc1c..8a38d97d463b2e 100644 --- a/drivers/comedi/drivers/c6xdigio.c +++ b/drivers/comedi/drivers/c6xdigio.c @@ -249,9 +249,6 @@ static int c6xdigio_attach(struct comedi_device *dev, if (ret) return ret; - /* Make sure that PnP ports get activated */ - pnp_register_driver(&c6xdigio_pnp_driver); - s = &dev->subdevices[0]; /* pwm output subdevice */ s->type = COMEDI_SUBD_PWM; @@ -278,19 +275,46 @@ static int c6xdigio_attach(struct comedi_device *dev, return 0; } -static void c6xdigio_detach(struct comedi_device *dev) -{ - comedi_legacy_detach(dev); - pnp_unregister_driver(&c6xdigio_pnp_driver); -} - static struct comedi_driver c6xdigio_driver = { .driver_name = "c6xdigio", .module = THIS_MODULE, .attach = c6xdigio_attach, - .detach = c6xdigio_detach, + .detach = comedi_legacy_detach, }; -module_comedi_driver(c6xdigio_driver); + +static bool c6xdigio_pnp_registered = false; + +static int __init c6xdigio_module_init(void) +{ + int ret; + + ret = comedi_driver_register(&c6xdigio_driver); + if (ret) + return ret; + + if (IS_ENABLED(CONFIG_PNP)) { + /* Try to activate the PnP ports */ + ret = pnp_register_driver(&c6xdigio_pnp_driver); + if (ret) { + pr_warn("failed to register pnp driver - err %d\n", + ret); + ret = 0; /* ignore the error. */ + } else { + c6xdigio_pnp_registered = true; + } + } + + return 0; +} +module_init(c6xdigio_module_init); + +static void __exit c6xdigio_module_exit(void) +{ + if (c6xdigio_pnp_registered) + pnp_unregister_driver(&c6xdigio_pnp_driver); + comedi_driver_unregister(&c6xdigio_driver); +} +module_exit(c6xdigio_module_exit); MODULE_AUTHOR("Comedi https://www.comedi.org"); MODULE_DESCRIPTION("Comedi driver for the C6x_DIGIO DSP daughter card"); diff --git a/drivers/comedi/drivers/dmm32at.c b/drivers/comedi/drivers/dmm32at.c index 644e3b643c7965..910cd24b1bed57 100644 --- a/drivers/comedi/drivers/dmm32at.c +++ b/drivers/comedi/drivers/dmm32at.c @@ -330,6 +330,7 @@ static int dmm32at_ai_cmdtest(struct comedi_device *dev, static void dmm32at_setaitimer(struct comedi_device *dev, unsigned int nansec) { + unsigned long irq_flags; unsigned char lo1, lo2, hi2; unsigned short both2; @@ -342,6 +343,9 @@ static void dmm32at_setaitimer(struct comedi_device *dev, unsigned int nansec) /* set counter clocks to 10MHz, disable all aux dio */ outb(0, dev->iobase + DMM32AT_CTRDIO_CFG_REG); + /* serialize access to control register and paged registers */ + spin_lock_irqsave(&dev->spinlock, irq_flags); + /* get access to the clock regs */ outb(DMM32AT_CTRL_PAGE_8254, dev->iobase + DMM32AT_CTRL_REG); @@ -354,6 +358,8 @@ static void dmm32at_setaitimer(struct comedi_device *dev, unsigned int nansec) outb(lo2, dev->iobase + DMM32AT_CLK2); outb(hi2, dev->iobase + DMM32AT_CLK2); + spin_unlock_irqrestore(&dev->spinlock, irq_flags); + /* enable the ai conversion interrupt and the clock to start scans */ outb(DMM32AT_INTCLK_ADINT | DMM32AT_INTCLK_CLKEN | DMM32AT_INTCLK_CLKSEL, @@ -363,13 +369,19 @@ static void dmm32at_setaitimer(struct comedi_device *dev, unsigned int nansec) static int dmm32at_ai_cmd(struct comedi_device *dev, struct comedi_subdevice *s) { struct comedi_cmd *cmd = &s->async->cmd; + unsigned long irq_flags; int ret; dmm32at_ai_set_chanspec(dev, s, cmd->chanlist[0], cmd->chanlist_len); + /* serialize access to control register and paged registers */ + spin_lock_irqsave(&dev->spinlock, irq_flags); + /* reset the interrupt just in case */ outb(DMM32AT_CTRL_INTRST, dev->iobase + DMM32AT_CTRL_REG); + spin_unlock_irqrestore(&dev->spinlock, irq_flags); + /* * wait for circuit to settle * we don't have the 'insn' here but it's not needed @@ -429,8 +441,13 @@ static irqreturn_t dmm32at_isr(int irq, void *d) comedi_handle_events(dev, s); } + /* serialize access to control register and paged registers */ + spin_lock(&dev->spinlock); + /* reset the interrupt */ outb(DMM32AT_CTRL_INTRST, dev->iobase + DMM32AT_CTRL_REG); + + spin_unlock(&dev->spinlock); return IRQ_HANDLED; } @@ -481,14 +498,25 @@ static int dmm32at_ao_insn_write(struct comedi_device *dev, static int dmm32at_8255_io(struct comedi_device *dev, int dir, int port, int data, unsigned long regbase) { + unsigned long irq_flags; + int ret; + + /* serialize access to control register and paged registers */ + spin_lock_irqsave(&dev->spinlock, irq_flags); + /* get access to the DIO regs */ outb(DMM32AT_CTRL_PAGE_8255, dev->iobase + DMM32AT_CTRL_REG); if (dir) { outb(data, dev->iobase + regbase + port); - return 0; + ret = 0; + } else { + ret = inb(dev->iobase + regbase + port); } - return inb(dev->iobase + regbase + port); + + spin_unlock_irqrestore(&dev->spinlock, irq_flags); + + return ret; } /* Make sure the board is there and put it to a known state */ diff --git a/drivers/comedi/drivers/multiq3.c b/drivers/comedi/drivers/multiq3.c index 07ff5383da9976..ac369e9a262d72 100644 --- a/drivers/comedi/drivers/multiq3.c +++ b/drivers/comedi/drivers/multiq3.c @@ -67,6 +67,11 @@ #define MULTIQ3_TRSFRCNTR_OL 0x10 /* xfer CNTR to OL (x and y) */ #define MULTIQ3_EFLAG_RESET 0x06 /* reset E bit of flag reg */ +/* + * Limit on the number of optional encoder channels + */ +#define MULTIQ3_MAX_ENC_CHANS 8 + static void multiq3_set_ctrl(struct comedi_device *dev, unsigned int bits) { /* @@ -312,6 +317,10 @@ static int multiq3_attach(struct comedi_device *dev, s->insn_read = multiq3_encoder_insn_read; s->insn_config = multiq3_encoder_insn_config; + /* sanity check for number of encoder channels */ + if (s->n_chan > MULTIQ3_MAX_ENC_CHANS) + s->n_chan = MULTIQ3_MAX_ENC_CHANS; + for (i = 0; i < s->n_chan; i++) multiq3_encoder_reset(dev, i); diff --git a/drivers/comedi/drivers/pcl818.c b/drivers/comedi/drivers/pcl818.c index 4127adcfb22955..06fe06396f23ab 100644 --- a/drivers/comedi/drivers/pcl818.c +++ b/drivers/comedi/drivers/pcl818.c @@ -1111,10 +1111,9 @@ static void pcl818_detach(struct comedi_device *dev) { struct pcl818_private *devpriv = dev->private; - if (devpriv) { - pcl818_ai_cancel(dev, dev->read_subdev); + if (devpriv) pcl818_reset(dev); - } + pcl818_free_dma(dev); comedi_legacy_detach(dev); } diff --git a/drivers/comedi/range.c b/drivers/comedi/range.c index 8f43cf88d784bf..5b8f662365e356 100644 --- a/drivers/comedi/range.c +++ b/drivers/comedi/range.c @@ -52,7 +52,7 @@ int do_rangeinfo_ioctl(struct comedi_device *dev, const struct comedi_lrange *lr; struct comedi_subdevice *s; - subd = (it->range_type >> 24) & 0xf; + subd = (it->range_type >> 24) & 0xff; chan = (it->range_type >> 16) & 0xff; if (!dev->attached) diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c index ce81fc4e1ae763..573b2fe93253e5 100644 --- a/drivers/counter/104-quad-8.c +++ b/drivers/counter/104-quad-8.c @@ -1192,6 +1192,7 @@ static irqreturn_t quad8_irq_handler(int irq, void *private) { struct counter_device *counter = private; struct quad8 *const priv = counter_priv(counter); + struct device *dev = counter->parent; unsigned int status; unsigned long irq_status; unsigned long channel; @@ -1200,8 +1201,11 @@ static irqreturn_t quad8_irq_handler(int irq, void *private) int ret; ret = regmap_read(priv->map, QUAD8_INTERRUPT_STATUS, &status); - if (ret) - return ret; + if (ret) { + dev_WARN_ONCE(dev, true, + "Attempt to read Interrupt Status Register failed: %d\n", ret); + return IRQ_NONE; + } if (!status) return IRQ_NONE; @@ -1223,8 +1227,9 @@ static irqreturn_t quad8_irq_handler(int irq, void *private) break; default: /* should never reach this path */ - WARN_ONCE(true, "invalid interrupt trigger function %u configured for channel %lu\n", - flg_pins, channel); + dev_WARN_ONCE(dev, true, + "invalid interrupt trigger function %u configured for channel %lu\n", + flg_pins, channel); continue; } @@ -1232,8 +1237,11 @@ static irqreturn_t quad8_irq_handler(int irq, void *private) } ret = regmap_write(priv->map, QUAD8_CHANNEL_OPERATION, CLEAR_PENDING_INTERRUPTS); - if (ret) - return ret; + if (ret) { + dev_WARN_ONCE(dev, true, + "Attempt to clear pending interrupts by writing to Channel Operation Register failed: %d\n", ret); + return IRQ_HANDLED; + } return IRQ_HANDLED; } diff --git a/drivers/counter/interrupt-cnt.c b/drivers/counter/interrupt-cnt.c index 6c0c1d2d7027d5..e6100b5fb082e0 100644 --- a/drivers/counter/interrupt-cnt.c +++ b/drivers/counter/interrupt-cnt.c @@ -229,8 +229,7 @@ static int interrupt_cnt_probe(struct platform_device *pdev) irq_set_status_flags(priv->irq, IRQ_NOAUTOEN); ret = devm_request_irq(dev, priv->irq, interrupt_cnt_isr, - IRQF_TRIGGER_RISING | IRQF_NO_THREAD, - dev_name(dev), counter); + IRQF_TRIGGER_RISING, dev_name(dev), counter); if (ret) return ret; diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index b44f0f7a5ba1c7..602e4fa81d6c5e 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -1282,7 +1282,7 @@ static int amd_pstate_change_mode_without_dvr_change(int mode) if (cpu_feature_enabled(X86_FEATURE_CPPC) || cppc_state == AMD_PSTATE_ACTIVE) return 0; - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { cppc_set_auto_sel(cpu, (cppc_state == AMD_PSTATE_PASSIVE) ? 0 : 1); } diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index cd1816a12bb996..dc11b62399ad5b 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -87,6 +87,7 @@ static const struct of_device_id allowlist[] __initconst = { { .compatible = "st-ericsson,u9540", }, { .compatible = "starfive,jh7110", }, + { .compatible = "starfive,jh7110s", }, { .compatible = "ti,omap2", }, { .compatible = "ti,omap4", }, diff --git a/drivers/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c index fedad1081973fd..fbbbe501cf2dc1 100644 --- a/drivers/cpufreq/cpufreq-nforce2.c +++ b/drivers/cpufreq/cpufreq-nforce2.c @@ -145,6 +145,8 @@ static unsigned int nforce2_fsb_read(int bootfsb) pci_read_config_dword(nforce2_sub5, NFORCE2_BOOTFSB, &fsb); fsb /= 1000000; + pci_dev_put(nforce2_sub5); + /* Check if PLL register is already set */ pci_read_config_byte(nforce2_dev, NFORCE2_PLLENABLE, (u8 *)&temp); @@ -426,6 +428,7 @@ static int __init nforce2_init(void) static void __exit nforce2_exit(void) { cpufreq_unregister_driver(&nforce2_driver); + pci_dev_put(nforce2_dev); } module_init(nforce2_init); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 492a10f1bdbfa3..38333f7da40db4 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1152,7 +1152,7 @@ static void hybrid_init_cpu_capacity_scaling(bool refresh) * the capacity of SMT threads is not deterministic even approximately, * do not do that when SMT is in use. */ - if (hwp_is_hybrid && !sched_smt_active() && arch_enable_hybrid_capacity_scale()) { + if (hwp_is_hybrid && !cpu_smt_possible() && arch_enable_hybrid_capacity_scale()) { hybrid_refresh_cpu_capacity_scaling(); /* * Disabling ITMT causes sched domains to be rebuilt to disable asym diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c index 4215621deb3fe8..ba8a1c96427a10 100644 --- a/drivers/cpufreq/s5pv210-cpufreq.c +++ b/drivers/cpufreq/s5pv210-cpufreq.c @@ -518,7 +518,7 @@ static int s5pv210_cpu_init(struct cpufreq_policy *policy) if (policy->cpu != 0) { ret = -EINVAL; - goto out_dmc1; + goto out; } /* @@ -530,7 +530,7 @@ static int s5pv210_cpu_init(struct cpufreq_policy *policy) if ((mem_type != LPDDR) && (mem_type != LPDDR2)) { pr_err("CPUFreq doesn't support this memory type\n"); ret = -EINVAL; - goto out_dmc1; + goto out; } /* Find current refresh counter and frequency each DMC */ @@ -544,6 +544,8 @@ static int s5pv210_cpu_init(struct cpufreq_policy *policy) cpufreq_generic_init(policy, s5pv210_freq_table, 40000); return 0; +out: + clk_put(dmc1_clk); out_dmc1: clk_put(dmc0_clk); out_dmc0: diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index d2a110079f5fd5..c450cf9c881d49 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -101,6 +101,7 @@ static int scmi_cpu_domain_id(struct device *cpu_dev) return -EINVAL; } + of_node_put(domain_id.np); return domain_id.args[0]; } diff --git a/drivers/cpuidle/Kconfig.arm b/drivers/cpuidle/Kconfig.arm index a1ee475d180dac..c6870f08457632 100644 --- a/drivers/cpuidle/Kconfig.arm +++ b/drivers/cpuidle/Kconfig.arm @@ -130,3 +130,11 @@ config ARM_QCOM_SPM_CPUIDLE The Subsystem Power Manager (SPM) controls low power modes for the CPU and L2 cores. It interface with various system drivers to put the cores in low power modes. + +config ARM_APPLE_CPUIDLE + bool "Apple SoC CPU idle driver" + depends on ARM64 + default ARCH_APPLE + select CPU_IDLE_MULTIPLE_DRIVERS + help + Select this to enable cpuidle on Apple SoCs. diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile index 1de9e92c5b0fc9..f9e7a71d52c13f 100644 --- a/drivers/cpuidle/Makefile +++ b/drivers/cpuidle/Makefile @@ -29,6 +29,7 @@ obj-$(CONFIG_ARM_PSCI_CPUIDLE) += cpuidle-psci.o obj-$(CONFIG_ARM_PSCI_CPUIDLE_DOMAIN) += cpuidle-psci-domain.o obj-$(CONFIG_ARM_TEGRA_CPUIDLE) += cpuidle-tegra.o obj-$(CONFIG_ARM_QCOM_SPM_CPUIDLE) += cpuidle-qcom-spm.o +obj-$(CONFIG_ARM_APPLE_CPUIDLE) += cpuidle-apple.o ############################################################################### # MIPS drivers diff --git a/drivers/cpuidle/cpuidle-apple.c b/drivers/cpuidle/cpuidle-apple.c new file mode 100644 index 00000000000000..b7504066d75aa8 --- /dev/null +++ b/drivers/cpuidle/cpuidle-apple.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Copyright The Asahi Linux Contributors + * + * CPU idle support for Apple SoCs + */ + +#include +#include +#include +#include +#include +#include + +enum idle_state { + STATE_WFI, + STATE_PWRDOWN, + STATE_COUNT +}; + +asm( + ".pushsection .cpuidle.text, \"ax\"\n" + ".type apple_cpu_deep_wfi, @function\n" + "apple_cpu_deep_wfi:\n" + "str x30, [sp, #-16]!\n" + "stp x28, x29, [sp, #-16]!\n" + "stp x26, x27, [sp, #-16]!\n" + "stp x24, x25, [sp, #-16]!\n" + "stp x22, x23, [sp, #-16]!\n" + "stp x20, x21, [sp, #-16]!\n" + "stp x18, x19, [sp, #-16]!\n" + + "mrs x0, s3_5_c15_c5_0\n" + "orr x0, x0, #(3L << 24)\n" + "msr s3_5_c15_c5_0, x0\n" + + "1:\n" + "dsb sy\n" + "wfi\n" + + "mrs x0, ISR_EL1\n" + "cbz x0, 1b\n" + + "mrs x0, s3_5_c15_c5_0\n" + "bic x0, x0, #(1L << 24)\n" + "msr s3_5_c15_c5_0, x0\n" + + "ldp x18, x19, [sp], #16\n" + "ldp x20, x21, [sp], #16\n" + "ldp x22, x23, [sp], #16\n" + "ldp x24, x25, [sp], #16\n" + "ldp x26, x27, [sp], #16\n" + "ldp x28, x29, [sp], #16\n" + "ldr x30, [sp], #16\n" + + "ret\n" + ".popsection\n" +); + +void apple_cpu_deep_wfi(void); + +static __cpuidle int apple_enter_wfi(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) +{ + cpu_do_idle(); + return index; +} + +static __cpuidle int apple_enter_idle(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) +{ + /* + * Deep WFI will clobber FP state, among other things. + * The CPU PM notifier will take care of saving that and anything else + * that needs to be notified of the CPU powering down. + */ + if (cpu_pm_enter()) + return -1; + + ct_cpuidle_enter(); + + switch(index) { + case STATE_PWRDOWN: + apple_cpu_deep_wfi(); + break; + default: + WARN_ON(1); + break; + } + + ct_cpuidle_exit(); + + cpu_pm_exit(); + + return index; +} + +static struct cpuidle_driver apple_idle_driver = { + .name = "apple_idle", + .owner = THIS_MODULE, + .states = { + [STATE_WFI] = { + .enter = apple_enter_wfi, + .enter_s2idle = apple_enter_wfi, + .exit_latency = 1, + .target_residency = 1, + .power_usage = UINT_MAX, + .name = "WFI", + .desc = "CPU clock-gated", + .flags = 0, + }, + [STATE_PWRDOWN] = { + .enter = apple_enter_idle, + .enter_s2idle = apple_enter_idle, + .exit_latency = 10, + .target_residency = 10000, + .power_usage = 0, + .name = "CPU PD", + .desc = "CPU/cluster powered down", + .flags = CPUIDLE_FLAG_RCU_IDLE, + }, + }, + .safe_state_index = STATE_WFI, + .state_count = STATE_COUNT, +}; + +static int apple_cpuidle_probe(struct platform_device *pdev) +{ + return cpuidle_register(&apple_idle_driver, NULL); +} + +static struct platform_driver apple_cpuidle_driver = { + .driver = { + .name = "cpuidle-apple", + }, + .probe = apple_cpuidle_probe, +}; + +static int __init apple_cpuidle_init(void) +{ + struct platform_device *pdev; + int ret; + + ret = platform_driver_register(&apple_cpuidle_driver); + if (ret) + return ret; + + if (!of_machine_is_compatible("apple,arm-platform")) + return 0; + + if (!(of_machine_is_compatible("apple,t8103") || + of_machine_is_compatible("apple,t8112") || + of_machine_is_compatible("apple,t6000") || + of_machine_is_compatible("apple,t6001") || + of_machine_is_compatible("apple,t6002") || + of_machine_is_compatible("apple,t6020") || + of_machine_is_compatible("apple,t6021") || + of_machine_is_compatible("apple,t6022"))) + return 0; + + pdev = platform_device_register_simple("cpuidle-apple", -1, NULL, 0); + if (IS_ERR(pdev)) { + platform_driver_unregister(&apple_cpuidle_driver); + return PTR_ERR(pdev); + } + + return 0; +} +device_initcall(apple_cpuidle_init); diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 56132e843c9919..8950796a493deb 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -357,6 +357,16 @@ noinstr int cpuidle_enter_state(struct cpuidle_device *dev, int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, bool *stop_tick) { + /* + * If there is only a single idle state (or none), there is nothing + * meaningful for the governor to choose. Skip the governor and + * always use state 0 with the tick running. + */ + if (drv->state_count <= 1) { + *stop_tick = false; + return 0; + } + return cpuidle_curr_governor->select(drv, dev, stop_tick); } diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 23239b0c04f95b..ca863ba03d4544 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -239,7 +239,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, /* Find the shortest expected idle interval. */ predicted_ns = get_typical_interval(data) * NSEC_PER_USEC; - if (predicted_ns > RESIDENCY_THRESHOLD_NS) { + if (predicted_ns > RESIDENCY_THRESHOLD_NS || tick_nohz_tick_stopped()) { unsigned int timer_us; /* Determine the time till the closest timer. */ @@ -259,6 +259,16 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, RESOLUTION * DECAY * NSEC_PER_USEC); /* Use the lowest expected idle interval to pick the idle state. */ predicted_ns = min((u64)timer_us * NSEC_PER_USEC, predicted_ns); + /* + * If the tick is already stopped, the cost of possible short + * idle duration misprediction is much higher, because the CPU + * may be stuck in a shallow idle state for a long time as a + * result of it. In that case, say we might mispredict and use + * the known time till the closest timer event for the idle + * state selection. + */ + if (tick_nohz_tick_stopped() && predicted_ns < TICK_NSEC) + predicted_ns = data->next_timer_ns; } else { /* * Because the next timer event is not going to be determined @@ -284,16 +294,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, return 0; } - /* - * If the tick is already stopped, the cost of possible short idle - * duration misprediction is much higher, because the CPU may be stuck - * in a shallow idle state for a long time as a result of it. In that - * case, say we might mispredict and use the known time till the closest - * timer event for the idle state selection. - */ - if (tick_nohz_tick_stopped() && predicted_ns < TICK_NSEC) - predicted_ns = data->next_timer_ns; - /* * Find the idle state with the lowest power while satisfying * our constraints. @@ -317,12 +317,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, } /* - * Use a physical idle state, not busy polling, unless a timer - * is going to trigger soon enough or the exit latency of the - * idle state in question is greater than the predicted idle - * duration. + * Use a physical idle state instead of busy polling so long as + * its target residency is below the residency threshold, its + * exit latency is not greater than the predicted idle duration, + * and the next timer doesn't expire soon. */ if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) && + s->target_residency_ns < RESIDENCY_THRESHOLD_NS && s->target_residency_ns <= data->next_timer_ns && s->exit_latency_ns <= predicted_ns) { predicted_ns = s->target_residency_ns; diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index bfa55c1eab5bcd..8078eca72ca536 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/drivers/cpuidle/governors/teo.c @@ -458,11 +458,8 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * If the closest expected timer is before the target residency of the * candidate state, a shallower one needs to be found. */ - if (drv->states[idx].target_residency_ns > duration_ns) { - i = teo_find_shallower_state(drv, dev, idx, duration_ns, false); - if (teo_state_ok(i, drv)) - idx = i; - } + if (drv->states[idx].target_residency_ns > duration_ns) + idx = teo_find_shallower_state(drv, dev, idx, duration_ns, false); /* * If the selected state's target residency is below the tick length diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c index 107ccb2ade4205..c6117c23eb25b0 100644 --- a/drivers/crypto/caam/caamalg_qi2.c +++ b/drivers/crypto/caam/caamalg_qi2.c @@ -4814,7 +4814,8 @@ static void dpaa2_dpseci_free(struct dpaa2_caam_priv *priv) { struct device *dev = priv->dev; struct fsl_mc_device *ls_dev = to_fsl_mc_device(dev); - int err; + struct dpaa2_caam_priv_per_cpu *ppriv; + int i, err; if (DPSECI_VER(priv->major_ver, priv->minor_ver) > DPSECI_VER(5, 3)) { err = dpseci_reset(priv->mc_io, 0, ls_dev->mc_handle); @@ -4822,6 +4823,12 @@ static void dpaa2_dpseci_free(struct dpaa2_caam_priv *priv) dev_err(dev, "dpseci_reset() failed\n"); } + for_each_cpu(i, priv->clean_mask) { + ppriv = per_cpu_ptr(priv->ppriv, i); + free_netdev(ppriv->net_dev); + } + free_cpumask_var(priv->clean_mask); + dpaa2_dpseci_congestion_free(priv); dpseci_close(priv->mc_io, 0, ls_dev->mc_handle); } @@ -5007,16 +5014,15 @@ static int __cold dpaa2_dpseci_setup(struct fsl_mc_device *ls_dev) struct device *dev = &ls_dev->dev; struct dpaa2_caam_priv *priv; struct dpaa2_caam_priv_per_cpu *ppriv; - cpumask_var_t clean_mask; int err, cpu; u8 i; err = -ENOMEM; - if (!zalloc_cpumask_var(&clean_mask, GFP_KERNEL)) - goto err_cpumask; - priv = dev_get_drvdata(dev); + if (!zalloc_cpumask_var(&priv->clean_mask, GFP_KERNEL)) + goto err_cpumask; + priv->dev = dev; priv->dpsec_id = ls_dev->obj_desc.id; @@ -5118,7 +5124,7 @@ static int __cold dpaa2_dpseci_setup(struct fsl_mc_device *ls_dev) err = -ENOMEM; goto err_alloc_netdev; } - cpumask_set_cpu(cpu, clean_mask); + cpumask_set_cpu(cpu, priv->clean_mask); ppriv->net_dev->dev = *dev; netif_napi_add_tx_weight(ppriv->net_dev, &ppriv->napi, @@ -5126,18 +5132,16 @@ static int __cold dpaa2_dpseci_setup(struct fsl_mc_device *ls_dev) DPAA2_CAAM_NAPI_WEIGHT); } - err = 0; - goto free_cpumask; + return 0; err_alloc_netdev: - free_dpaa2_pcpu_netdev(priv, clean_mask); + free_dpaa2_pcpu_netdev(priv, priv->clean_mask); err_get_rx_queue: dpaa2_dpseci_congestion_free(priv); err_get_vers: dpseci_close(priv->mc_io, 0, ls_dev->mc_handle); err_open: -free_cpumask: - free_cpumask_var(clean_mask); + free_cpumask_var(priv->clean_mask); err_cpumask: return err; } @@ -5182,7 +5186,6 @@ static int __cold dpaa2_dpseci_disable(struct dpaa2_caam_priv *priv) ppriv = per_cpu_ptr(priv->ppriv, i); napi_disable(&ppriv->napi); netif_napi_del(&ppriv->napi); - free_netdev(ppriv->net_dev); } return 0; diff --git a/drivers/crypto/caam/caamalg_qi2.h b/drivers/crypto/caam/caamalg_qi2.h index 61d1219a202fcb..8e65b4b28c7bab 100644 --- a/drivers/crypto/caam/caamalg_qi2.h +++ b/drivers/crypto/caam/caamalg_qi2.h @@ -42,6 +42,7 @@ * @mc_io: pointer to MC portal's I/O object * @domain: IOMMU domain * @ppriv: per CPU pointers to privata data + * @clean_mask: CPU mask of CPUs that have allocated netdevs */ struct dpaa2_caam_priv { int dpsec_id; @@ -65,6 +66,7 @@ struct dpaa2_caam_priv { struct dpaa2_caam_priv_per_cpu __percpu *ppriv; struct dentry *dfs_root; + cpumask_var_t clean_mask; }; /** diff --git a/drivers/crypto/caam/caamrng.c b/drivers/crypto/caam/caamrng.c index b3d14a7f4dd147..0eb43c8625164f 100644 --- a/drivers/crypto/caam/caamrng.c +++ b/drivers/crypto/caam/caamrng.c @@ -181,7 +181,9 @@ static inline void test_len(struct hwrng *rng, size_t len, bool wait) struct device *dev = ctx->ctrldev; buf = kcalloc(CAAM_RNG_MAX_FIFO_STORE_SIZE, sizeof(u8), GFP_KERNEL); - + if (!buf) { + return; + } while (len > 0) { read_len = rng->read(rng, buf, len, wait); diff --git a/drivers/crypto/cavium/cpt/cptvf_main.c b/drivers/crypto/cavium/cpt/cptvf_main.c index c246920e6f540c..bccd680c7f7ee4 100644 --- a/drivers/crypto/cavium/cpt/cptvf_main.c +++ b/drivers/crypto/cavium/cpt/cptvf_main.c @@ -180,7 +180,8 @@ static void free_command_queues(struct cpt_vf *cptvf, hlist_for_each_entry_safe(chunk, node, &cqinfo->queue[i].chead, nextchunk) { - dma_free_coherent(&pdev->dev, chunk->size, + dma_free_coherent(&pdev->dev, + chunk->size + CPT_NEXT_CHUNK_PTR_SIZE, chunk->head, chunk->dma_addr); chunk->head = NULL; diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c index d78865d9d5f09c..d0412e58476253 100644 --- a/drivers/crypto/ccp/ccp-ops.c +++ b/drivers/crypto/ccp/ccp-ops.c @@ -642,7 +642,7 @@ ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd) struct ccp_data dst; struct ccp_data aad; struct ccp_op op; - } *wa __cleanup(kfree) = kzalloc(sizeof *wa, GFP_KERNEL); + } *wa __free(kfree) = kzalloc(sizeof(*wa), GFP_KERNEL); unsigned int dm_offset; unsigned int authsize; unsigned int jobid; diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c index 9e21da0e298ad7..5c7f7e02a7d8ab 100644 --- a/drivers/crypto/ccp/psp-dev.c +++ b/drivers/crypto/ccp/psp-dev.c @@ -351,6 +351,17 @@ struct psp_device *psp_get_master_device(void) return sp ? sp->psp_data : NULL; } +int psp_restore(struct sp_device *sp) +{ + struct psp_device *psp = sp->psp_data; + int ret = 0; + + if (psp->tee_data) + ret = tee_restore(psp); + + return ret; +} + void psp_pci_init(void) { psp_master = psp_get_master_device(); diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 0d13d47c164bb7..5fdba0fe4accea 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -119,13 +119,6 @@ static size_t sev_es_tmr_size = SEV_TMR_SIZE; #define NV_LENGTH (32 * 1024) static void *sev_init_ex_buffer; -/* - * SEV_DATA_RANGE_LIST: - * Array containing range of pages that firmware transitions to HV-fixed - * page state. - */ -static struct sev_data_range_list *snp_range_list; - static void __sev_firmware_shutdown(struct sev_device *sev, bool panic); static int snp_shutdown_on_panic(struct notifier_block *nb, @@ -1365,6 +1358,7 @@ static int snp_filter_reserved_mem_regions(struct resource *rs, void *arg) static int __sev_snp_init_locked(int *error, unsigned int max_snp_asid) { + struct sev_data_range_list *snp_range_list __free(kfree) = NULL; struct psp_device *psp = psp_master; struct sev_data_snp_init_ex data; struct sev_device *sev; @@ -2351,11 +2345,10 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable) static int sev_ioctl_do_snp_platform_status(struct sev_issue_cmd *argp) { struct sev_device *sev = psp_master->sev_data; - bool shutdown_required = false; struct sev_data_snp_addr buf; struct page *status_page; - int ret, error; void *data; + int ret; if (!argp->data) return -EINVAL; @@ -2366,31 +2359,35 @@ static int sev_ioctl_do_snp_platform_status(struct sev_issue_cmd *argp) data = page_address(status_page); - if (!sev->snp_initialized) { - ret = snp_move_to_init_state(argp, &shutdown_required); - if (ret) - goto cleanup; - } - /* - * Firmware expects status page to be in firmware-owned state, otherwise - * it will report firmware error code INVALID_PAGE_STATE (0x1A). + * SNP_PLATFORM_STATUS can be executed in any SNP state. But if executed + * when SNP has been initialized, the status page must be firmware-owned. */ - if (rmp_mark_pages_firmware(__pa(data), 1, true)) { - ret = -EFAULT; - goto cleanup; + if (sev->snp_initialized) { + /* + * Firmware expects the status page to be in Firmware state, + * otherwise it will report an error INVALID_PAGE_STATE. + */ + if (rmp_mark_pages_firmware(__pa(data), 1, true)) { + ret = -EFAULT; + goto cleanup; + } } buf.address = __psp_pa(data); ret = __sev_do_cmd_locked(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &argp->error); - /* - * Status page will be transitioned to Reclaim state upon success, or - * left in Firmware state in failure. Use snp_reclaim_pages() to - * transition either case back to Hypervisor-owned state. - */ - if (snp_reclaim_pages(__pa(data), 1, true)) - return -EFAULT; + if (sev->snp_initialized) { + /* + * The status page will be in Reclaim state on success, or left + * in Firmware state on failure. Use snp_reclaim_pages() to + * transition either case back to Hypervisor-owned state. + */ + if (snp_reclaim_pages(__pa(data), 1, true)) { + snp_leak_pages(__page_to_pfn(status_page), 1); + return -EFAULT; + } + } if (ret) goto cleanup; @@ -2400,9 +2397,6 @@ static int sev_ioctl_do_snp_platform_status(struct sev_issue_cmd *argp) ret = -EFAULT; cleanup: - if (shutdown_required) - __sev_snp_shutdown_locked(&error, false); - __free_pages(status_page, 0); return ret; } @@ -2753,11 +2747,6 @@ static void __sev_firmware_shutdown(struct sev_device *sev, bool panic) sev_init_ex_buffer = NULL; } - if (snp_range_list) { - kfree(snp_range_list); - snp_range_list = NULL; - } - __sev_snp_shutdown_locked(&error, panic); } diff --git a/drivers/crypto/ccp/sp-dev.c b/drivers/crypto/ccp/sp-dev.c index 3467f6db4f505a..f204aa5df96e24 100644 --- a/drivers/crypto/ccp/sp-dev.c +++ b/drivers/crypto/ccp/sp-dev.c @@ -230,6 +230,18 @@ int sp_resume(struct sp_device *sp) return 0; } +int sp_restore(struct sp_device *sp) +{ + if (sp->psp_data) { + int ret = psp_restore(sp); + + if (ret) + return ret; + } + + return sp_resume(sp); +} + struct sp_device *sp_get_psp_master_device(void) { struct sp_device *i, *ret = NULL; diff --git a/drivers/crypto/ccp/sp-dev.h b/drivers/crypto/ccp/sp-dev.h index 6f9d7063257d70..c8a611ef275b5f 100644 --- a/drivers/crypto/ccp/sp-dev.h +++ b/drivers/crypto/ccp/sp-dev.h @@ -141,6 +141,7 @@ void sp_destroy(struct sp_device *sp); int sp_suspend(struct sp_device *sp); int sp_resume(struct sp_device *sp); +int sp_restore(struct sp_device *sp); int sp_request_ccp_irq(struct sp_device *sp, irq_handler_t handler, const char *name, void *data); void sp_free_ccp_irq(struct sp_device *sp, void *data); @@ -174,6 +175,7 @@ int psp_dev_init(struct sp_device *sp); void psp_pci_init(void); void psp_dev_destroy(struct sp_device *sp); void psp_pci_exit(void); +int psp_restore(struct sp_device *sp); #else /* !CONFIG_CRYPTO_DEV_SP_PSP */ @@ -181,6 +183,7 @@ static inline int psp_dev_init(struct sp_device *sp) { return 0; } static inline void psp_pci_init(void) { } static inline void psp_dev_destroy(struct sp_device *sp) { } static inline void psp_pci_exit(void) { } +static inline int psp_restore(struct sp_device *sp) { return 0; } #endif /* CONFIG_CRYPTO_DEV_SP_PSP */ diff --git a/drivers/crypto/ccp/sp-pci.c b/drivers/crypto/ccp/sp-pci.c index e7bb803912a6d3..6ac805d99ccb30 100644 --- a/drivers/crypto/ccp/sp-pci.c +++ b/drivers/crypto/ccp/sp-pci.c @@ -353,6 +353,13 @@ static int __maybe_unused sp_pci_resume(struct device *dev) return sp_resume(sp); } +static int __maybe_unused sp_pci_restore(struct device *dev) +{ + struct sp_device *sp = dev_get_drvdata(dev); + + return sp_restore(sp); +} + #ifdef CONFIG_CRYPTO_DEV_SP_PSP static const struct sev_vdata sevv1 = { .cmdresp_reg = 0x10580, /* C2PMSG_32 */ @@ -459,6 +466,17 @@ static const struct psp_vdata pspv6 = { .intsts_reg = 0x10514, /* P2CMSG_INTSTS */ }; +static const struct psp_vdata pspv7 = { + .tee = &teev2, + .cmdresp_reg = 0x10944, /* C2PMSG_17 */ + .cmdbuff_addr_lo_reg = 0x10948, /* C2PMSG_18 */ + .cmdbuff_addr_hi_reg = 0x1094c, /* C2PMSG_19 */ + .bootloader_info_reg = 0x109ec, /* C2PMSG_59 */ + .feature_reg = 0x109fc, /* C2PMSG_63 */ + .inten_reg = 0x10510, /* P2CMSG_INTEN */ + .intsts_reg = 0x10514, /* P2CMSG_INTSTS */ +}; + #endif static const struct sp_dev_vdata dev_vdata[] = { @@ -525,6 +543,13 @@ static const struct sp_dev_vdata dev_vdata[] = { .psp_vdata = &pspv6, #endif }, + { /* 9 */ + .bar = 2, +#ifdef CONFIG_CRYPTO_DEV_SP_PSP + .psp_vdata = &pspv7, +#endif + }, + }; static const struct pci_device_id sp_pci_table[] = { { PCI_VDEVICE(AMD, 0x1537), (kernel_ulong_t)&dev_vdata[0] }, @@ -539,12 +564,20 @@ static const struct pci_device_id sp_pci_table[] = { { PCI_VDEVICE(AMD, 0x17E0), (kernel_ulong_t)&dev_vdata[7] }, { PCI_VDEVICE(AMD, 0x156E), (kernel_ulong_t)&dev_vdata[8] }, { PCI_VDEVICE(AMD, 0x17D8), (kernel_ulong_t)&dev_vdata[8] }, + { PCI_VDEVICE(AMD, 0x115A), (kernel_ulong_t)&dev_vdata[9] }, /* Last entry must be zero */ { 0, } }; MODULE_DEVICE_TABLE(pci, sp_pci_table); -static SIMPLE_DEV_PM_OPS(sp_pci_pm_ops, sp_pci_suspend, sp_pci_resume); +static const struct dev_pm_ops sp_pci_pm_ops = { + .suspend = pm_sleep_ptr(sp_pci_suspend), + .resume = pm_sleep_ptr(sp_pci_resume), + .freeze = pm_sleep_ptr(sp_pci_suspend), + .thaw = pm_sleep_ptr(sp_pci_resume), + .poweroff = pm_sleep_ptr(sp_pci_suspend), + .restore_early = pm_sleep_ptr(sp_pci_restore), +}; static struct pci_driver sp_pci_driver = { .name = "ccp", diff --git a/drivers/crypto/ccp/tee-dev.c b/drivers/crypto/ccp/tee-dev.c index 5e1d80724678d0..92ffa412622a24 100644 --- a/drivers/crypto/ccp/tee-dev.c +++ b/drivers/crypto/ccp/tee-dev.c @@ -86,10 +86,34 @@ static inline void tee_free_cmd_buffer(struct tee_init_ring_cmd *cmd) kfree(cmd); } +static bool tee_send_destroy_cmd(struct psp_tee_device *tee) +{ + unsigned int reg; + int ret; + + ret = psp_mailbox_command(tee->psp, PSP_CMD_TEE_RING_DESTROY, NULL, + TEE_DEFAULT_CMD_TIMEOUT, ®); + if (ret) { + dev_err(tee->dev, "tee: ring destroy command timed out, disabling TEE support\n"); + psp_dead = true; + return false; + } + + if (FIELD_GET(PSP_CMDRESP_STS, reg)) { + dev_err(tee->dev, "tee: ring destroy command failed (%#010lx)\n", + FIELD_GET(PSP_CMDRESP_STS, reg)); + psp_dead = true; + return false; + } + + return true; +} + static int tee_init_ring(struct psp_tee_device *tee) { int ring_size = MAX_RING_BUFFER_ENTRIES * sizeof(struct tee_ring_cmd); struct tee_init_ring_cmd *cmd; + bool retry = false; unsigned int reg; int ret; @@ -112,6 +136,7 @@ static int tee_init_ring(struct psp_tee_device *tee) /* Send command buffer details to Trusted OS by writing to * CPU-PSP message registers */ +retry_init: ret = psp_mailbox_command(tee->psp, PSP_CMD_TEE_RING_INIT, cmd, TEE_DEFAULT_CMD_TIMEOUT, ®); if (ret) { @@ -122,9 +147,22 @@ static int tee_init_ring(struct psp_tee_device *tee) } if (FIELD_GET(PSP_CMDRESP_STS, reg)) { + /* + * During the hibernate resume sequence driver may have gotten loaded + * but the ring not properly destroyed. If the ring doesn't work, try + * to destroy and re-init once. + */ + if (!retry && FIELD_GET(PSP_CMDRESP_STS, reg) == PSP_TEE_STS_RING_BUSY) { + dev_info(tee->dev, "tee: ring init command failed with busy status, retrying\n"); + if (tee_send_destroy_cmd(tee)) { + retry = true; + goto retry_init; + } + } dev_err(tee->dev, "tee: ring init command failed (%#010lx)\n", FIELD_GET(PSP_CMDRESP_STS, reg)); tee_free_ring(tee); + psp_dead = true; ret = -EIO; } @@ -136,24 +174,13 @@ static int tee_init_ring(struct psp_tee_device *tee) static void tee_destroy_ring(struct psp_tee_device *tee) { - unsigned int reg; - int ret; - if (!tee->rb_mgr.ring_start) return; if (psp_dead) goto free_ring; - ret = psp_mailbox_command(tee->psp, PSP_CMD_TEE_RING_DESTROY, NULL, - TEE_DEFAULT_CMD_TIMEOUT, ®); - if (ret) { - dev_err(tee->dev, "tee: ring destroy command timed out, disabling TEE support\n"); - psp_dead = true; - } else if (FIELD_GET(PSP_CMDRESP_STS, reg)) { - dev_err(tee->dev, "tee: ring destroy command failed (%#010lx)\n", - FIELD_GET(PSP_CMDRESP_STS, reg)); - } + tee_send_destroy_cmd(tee); free_ring: tee_free_ring(tee); @@ -365,3 +392,8 @@ int psp_check_tee_status(void) return 0; } EXPORT_SYMBOL(psp_check_tee_status); + +int tee_restore(struct psp_device *psp) +{ + return tee_init_ring(psp->tee_data); +} diff --git a/drivers/crypto/ccp/tee-dev.h b/drivers/crypto/ccp/tee-dev.h index ea9a2b7c05f577..c23416cb7bb37f 100644 --- a/drivers/crypto/ccp/tee-dev.h +++ b/drivers/crypto/ccp/tee-dev.h @@ -111,5 +111,6 @@ struct tee_ring_cmd { int tee_dev_init(struct psp_device *psp); void tee_dev_destroy(struct psp_device *psp); +int tee_restore(struct psp_device *psp); #endif /* __TEE_DEV_H__ */ diff --git a/drivers/crypto/ccree/cc_buffer_mgr.c b/drivers/crypto/ccree/cc_buffer_mgr.c index 3963bb91321fc1..dc7e0cd51c2596 100644 --- a/drivers/crypto/ccree/cc_buffer_mgr.c +++ b/drivers/crypto/ccree/cc_buffer_mgr.c @@ -1235,6 +1235,7 @@ int cc_map_hash_request_update(struct cc_drvdata *drvdata, void *ctx, int rc = 0; u32 dummy = 0; u32 mapped_nents = 0; + int sg_nents; dev_dbg(dev, " update params : curr_buff=%p curr_buff_cnt=0x%X nbytes=0x%X src=%p curr_index=%u\n", curr_buff, *curr_buff_cnt, nbytes, src, areq_ctx->buff_index); @@ -1248,7 +1249,10 @@ int cc_map_hash_request_update(struct cc_drvdata *drvdata, void *ctx, if (total_in_len < block_size) { dev_dbg(dev, " less than one block: curr_buff=%p *curr_buff_cnt=0x%X copy_to=%p\n", curr_buff, *curr_buff_cnt, &curr_buff[*curr_buff_cnt]); - areq_ctx->in_nents = sg_nents_for_len(src, nbytes); + sg_nents = sg_nents_for_len(src, nbytes); + if (sg_nents < 0) + return sg_nents; + areq_ctx->in_nents = sg_nents; sg_copy_to_buffer(src, areq_ctx->in_nents, &curr_buff[*curr_buff_cnt], nbytes); *curr_buff_cnt += nbytes; diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig index 4835bdebdbb381..a0cb1a8186ac9d 100644 --- a/drivers/crypto/hisilicon/Kconfig +++ b/drivers/crypto/hisilicon/Kconfig @@ -57,6 +57,7 @@ config CRYPTO_DEV_HISI_ZIP depends on UACCE || UACCE=n depends on ACPI select CRYPTO_DEV_HISI_QM + select CRYPTO_DEFLATE help Support for HiSilicon ZIP Driver diff --git a/drivers/crypto/hisilicon/hpre/hpre.h b/drivers/crypto/hisilicon/hpre/hpre.h index 0f3ddbadbcf991..021dbd9a1d48fb 100644 --- a/drivers/crypto/hisilicon/hpre/hpre.h +++ b/drivers/crypto/hisilicon/hpre/hpre.h @@ -94,9 +94,8 @@ struct hpre_sqe { __le64 key; __le64 in; __le64 out; - __le16 tag; - __le16 resv2; -#define _HPRE_SQE_ALIGN_EXT 7 + __le64 tag; +#define _HPRE_SQE_ALIGN_EXT 6 __le32 rsvd1[_HPRE_SQE_ALIGN_EXT]; }; diff --git a/drivers/crypto/hisilicon/hpre/hpre_crypto.c b/drivers/crypto/hisilicon/hpre/hpre_crypto.c index 21ccf879f70c55..839c1f67714369 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_crypto.c +++ b/drivers/crypto/hisilicon/hpre/hpre_crypto.c @@ -93,6 +93,7 @@ struct hpre_dh_ctx { char *g; /* m */ dma_addr_t dma_g; + struct crypto_kpp *soft_tfm; }; struct hpre_ecdh_ctx { @@ -103,17 +104,15 @@ struct hpre_ecdh_ctx { /* low address: x->y */ unsigned char *g; dma_addr_t dma_g; + struct crypto_kpp *soft_tfm; }; struct hpre_ctx { struct hisi_qp *qp; struct device *dev; - struct hpre_asym_request **req_list; struct hpre *hpre; - spinlock_t req_lock; unsigned int key_sz; bool crt_g2_mode; - struct idr req_idr; union { struct hpre_rsa_ctx rsa; struct hpre_dh_ctx dh; @@ -123,6 +122,7 @@ struct hpre_ctx { unsigned int curve_id; /* for high performance core */ u8 enable_hpcore; + bool fallback; }; struct hpre_asym_request { @@ -136,7 +136,6 @@ struct hpre_asym_request { struct kpp_request *ecdh; } areq; int err; - int req_id; hpre_cb cb; struct timespec64 req_time; }; @@ -151,79 +150,13 @@ static inline unsigned int hpre_align_pd(void) return (hpre_align_sz() - 1) & ~(crypto_tfm_ctx_alignment() - 1); } -static int hpre_alloc_req_id(struct hpre_ctx *ctx) +static void hpre_dfx_add_req_time(struct hpre_asym_request *hpre_req) { - unsigned long flags; - int id; - - spin_lock_irqsave(&ctx->req_lock, flags); - id = idr_alloc(&ctx->req_idr, NULL, 0, ctx->qp->sq_depth, GFP_ATOMIC); - spin_unlock_irqrestore(&ctx->req_lock, flags); - - return id; -} - -static void hpre_free_req_id(struct hpre_ctx *ctx, int req_id) -{ - unsigned long flags; - - spin_lock_irqsave(&ctx->req_lock, flags); - idr_remove(&ctx->req_idr, req_id); - spin_unlock_irqrestore(&ctx->req_lock, flags); -} - -static int hpre_add_req_to_ctx(struct hpre_asym_request *hpre_req) -{ - struct hpre_ctx *ctx; - struct hpre_dfx *dfx; - int id; - - ctx = hpre_req->ctx; - id = hpre_alloc_req_id(ctx); - if (unlikely(id < 0)) - return -EINVAL; - - ctx->req_list[id] = hpre_req; - hpre_req->req_id = id; + struct hpre_ctx *ctx = hpre_req->ctx; + struct hpre_dfx *dfx = ctx->hpre->debug.dfx; - dfx = ctx->hpre->debug.dfx; if (atomic64_read(&dfx[HPRE_OVERTIME_THRHLD].value)) ktime_get_ts64(&hpre_req->req_time); - - return id; -} - -static void hpre_rm_req_from_ctx(struct hpre_asym_request *hpre_req) -{ - struct hpre_ctx *ctx = hpre_req->ctx; - int id = hpre_req->req_id; - - if (hpre_req->req_id >= 0) { - hpre_req->req_id = HPRE_INVLD_REQ_ID; - ctx->req_list[id] = NULL; - hpre_free_req_id(ctx, id); - } -} - -static struct hisi_qp *hpre_get_qp_and_start(u8 type) -{ - struct hisi_qp *qp; - int ret; - - qp = hpre_create_qp(type); - if (!qp) { - pr_err("Can not create hpre qp!\n"); - return ERR_PTR(-ENODEV); - } - - ret = hisi_qm_start_qp(qp, 0); - if (ret < 0) { - hisi_qm_free_qps(&qp, 1); - pci_err(qp->qm->pdev, "Can not start qp!\n"); - return ERR_PTR(-EINVAL); - } - - return qp; } static int hpre_get_data_dma_addr(struct hpre_asym_request *hpre_req, @@ -340,26 +273,19 @@ static void hpre_hw_data_clr_all(struct hpre_ctx *ctx, static int hpre_alg_res_post_hf(struct hpre_ctx *ctx, struct hpre_sqe *sqe, void **kreq) { - struct hpre_asym_request *req; unsigned int err, done, alg; - int id; #define HPRE_NO_HW_ERR 0 #define HPRE_HW_TASK_DONE 3 #define HREE_HW_ERR_MASK GENMASK(10, 0) #define HREE_SQE_DONE_MASK GENMASK(1, 0) #define HREE_ALG_TYPE_MASK GENMASK(4, 0) - id = (int)le16_to_cpu(sqe->tag); - req = ctx->req_list[id]; - hpre_rm_req_from_ctx(req); - *kreq = req; + *kreq = (void *)le64_to_cpu(sqe->tag); err = (le32_to_cpu(sqe->dw0) >> HPRE_SQE_ALG_BITS) & HREE_HW_ERR_MASK; - done = (le32_to_cpu(sqe->dw0) >> HPRE_SQE_DONE_SHIFT) & HREE_SQE_DONE_MASK; - if (likely(err == HPRE_NO_HW_ERR && done == HPRE_HW_TASK_DONE)) return 0; @@ -370,36 +296,10 @@ static int hpre_alg_res_post_hf(struct hpre_ctx *ctx, struct hpre_sqe *sqe, return -EINVAL; } -static int hpre_ctx_set(struct hpre_ctx *ctx, struct hisi_qp *qp, int qlen) -{ - struct hpre *hpre; - - if (!ctx || !qp || qlen < 0) - return -EINVAL; - - spin_lock_init(&ctx->req_lock); - ctx->qp = qp; - ctx->dev = &qp->qm->pdev->dev; - - hpre = container_of(ctx->qp->qm, struct hpre, qm); - ctx->hpre = hpre; - ctx->req_list = kcalloc(qlen, sizeof(void *), GFP_KERNEL); - if (!ctx->req_list) - return -ENOMEM; - ctx->key_sz = 0; - ctx->crt_g2_mode = false; - idr_init(&ctx->req_idr); - - return 0; -} - static void hpre_ctx_clear(struct hpre_ctx *ctx, bool is_clear_all) { - if (is_clear_all) { - idr_destroy(&ctx->req_idr); - kfree(ctx->req_list); + if (is_clear_all) hisi_qm_free_qps(&ctx->qp, 1); - } ctx->crt_g2_mode = false; ctx->key_sz = 0; @@ -467,49 +367,44 @@ static void hpre_rsa_cb(struct hpre_ctx *ctx, void *resp) static void hpre_alg_cb(struct hisi_qp *qp, void *resp) { - struct hpre_ctx *ctx = qp->qp_ctx; - struct hpre_dfx *dfx = ctx->hpre->debug.dfx; + struct hpre_asym_request *h_req; struct hpre_sqe *sqe = resp; - struct hpre_asym_request *req = ctx->req_list[le16_to_cpu(sqe->tag)]; - if (unlikely(!req)) { - atomic64_inc(&dfx[HPRE_INVALID_REQ_CNT].value); + h_req = (struct hpre_asym_request *)le64_to_cpu(sqe->tag); + if (unlikely(!h_req)) { + pr_err("Failed to get request, and qp_id is %u\n", qp->qp_id); return; } - req->cb(ctx, resp); -} - -static void hpre_stop_qp_and_put(struct hisi_qp *qp) -{ - hisi_qm_stop_qp(qp); - hisi_qm_free_qps(&qp, 1); + h_req->cb(h_req->ctx, resp); } static int hpre_ctx_init(struct hpre_ctx *ctx, u8 type) { struct hisi_qp *qp; - int ret; + struct hpre *hpre; - qp = hpre_get_qp_and_start(type); - if (IS_ERR(qp)) - return PTR_ERR(qp); + qp = hpre_create_qp(type); + if (!qp) { + ctx->qp = NULL; + return -ENODEV; + } - qp->qp_ctx = ctx; qp->req_cb = hpre_alg_cb; + ctx->qp = qp; + ctx->dev = &qp->qm->pdev->dev; + hpre = container_of(ctx->qp->qm, struct hpre, qm); + ctx->hpre = hpre; + ctx->key_sz = 0; + ctx->crt_g2_mode = false; - ret = hpre_ctx_set(ctx, qp, qp->sq_depth); - if (ret) - hpre_stop_qp_and_put(qp); - - return ret; + return 0; } static int hpre_msg_request_set(struct hpre_ctx *ctx, void *req, bool is_rsa) { struct hpre_asym_request *h_req; struct hpre_sqe *msg; - int req_id; void *tmp; if (is_rsa) { @@ -549,11 +444,8 @@ static int hpre_msg_request_set(struct hpre_ctx *ctx, void *req, bool is_rsa) msg->task_len1 = (ctx->key_sz >> HPRE_BITS_2_BYTES_SHIFT) - 1; h_req->ctx = ctx; - req_id = hpre_add_req_to_ctx(h_req); - if (req_id < 0) - return -EBUSY; - - msg->tag = cpu_to_le16((u16)req_id); + hpre_dfx_add_req_time(h_req); + msg->tag = cpu_to_le64((uintptr_t)h_req); return 0; } @@ -566,9 +458,7 @@ static int hpre_send(struct hpre_ctx *ctx, struct hpre_sqe *msg) do { atomic64_inc(&dfx[HPRE_SEND_CNT].value); - spin_lock_bh(&ctx->req_lock); ret = hisi_qp_send(ctx->qp, msg); - spin_unlock_bh(&ctx->req_lock); if (ret != -EBUSY) break; atomic64_inc(&dfx[HPRE_SEND_BUSY_CNT].value); @@ -619,12 +509,53 @@ static int hpre_dh_compute_value(struct kpp_request *req) return -EINPROGRESS; clear_all: - hpre_rm_req_from_ctx(hpre_req); hpre_hw_data_clr_all(ctx, hpre_req, req->dst, req->src); return ret; } +static struct kpp_request *hpre_dh_prepare_fb_req(struct kpp_request *req) +{ + struct kpp_request *fb_req = kpp_request_ctx(req); + struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + + kpp_request_set_tfm(fb_req, ctx->dh.soft_tfm); + kpp_request_set_callback(fb_req, req->base.flags, req->base.complete, req->base.data); + kpp_request_set_input(fb_req, req->src, req->src_len); + kpp_request_set_output(fb_req, req->dst, req->dst_len); + + return fb_req; +} + +static int hpre_dh_generate_public_key(struct kpp_request *req) +{ + struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + struct kpp_request *fb_req; + + if (ctx->fallback) { + fb_req = hpre_dh_prepare_fb_req(req); + return crypto_kpp_generate_public_key(fb_req); + } + + return hpre_dh_compute_value(req); +} + +static int hpre_dh_compute_shared_secret(struct kpp_request *req) +{ + struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + struct kpp_request *fb_req; + + if (ctx->fallback) { + fb_req = hpre_dh_prepare_fb_req(req); + return crypto_kpp_compute_shared_secret(fb_req); + } + + return hpre_dh_compute_value(req); +} + static int hpre_is_dh_params_length_valid(unsigned int key_sz) { #define _HPRE_DH_GRP1 768 @@ -651,13 +582,6 @@ static int hpre_dh_set_params(struct hpre_ctx *ctx, struct dh *params) struct device *dev = ctx->dev; unsigned int sz; - if (params->p_size > HPRE_DH_MAX_P_SZ) - return -EINVAL; - - if (hpre_is_dh_params_length_valid(params->p_size << - HPRE_BITS_2_BYTES_SHIFT)) - return -EINVAL; - sz = ctx->key_sz = params->p_size; ctx->dh.xa_p = dma_alloc_coherent(dev, sz << 1, &ctx->dh.dma_xa_p, GFP_KERNEL); @@ -690,8 +614,8 @@ static void hpre_dh_clear_ctx(struct hpre_ctx *ctx, bool is_clear_all) struct device *dev = ctx->dev; unsigned int sz = ctx->key_sz; - if (is_clear_all) - hisi_qm_stop_qp(ctx->qp); + if (!ctx->qp) + return; if (ctx->dh.g) { dma_free_coherent(dev, sz, ctx->dh.g, ctx->dh.dma_g); @@ -718,6 +642,13 @@ static int hpre_dh_set_secret(struct crypto_kpp *tfm, const void *buf, if (crypto_dh_decode_key(buf, len, ¶ms) < 0) return -EINVAL; + if (!ctx->qp) + goto set_soft_secret; + + if (hpre_is_dh_params_length_valid(params.p_size << + HPRE_BITS_2_BYTES_SHIFT)) + goto set_soft_secret; + /* Free old secret if any */ hpre_dh_clear_ctx(ctx, false); @@ -728,27 +659,55 @@ static int hpre_dh_set_secret(struct crypto_kpp *tfm, const void *buf, memcpy(ctx->dh.xa_p + (ctx->key_sz - params.key_size), params.key, params.key_size); + ctx->fallback = false; return 0; err_clear_ctx: hpre_dh_clear_ctx(ctx, false); return ret; +set_soft_secret: + ctx->fallback = true; + return crypto_kpp_set_secret(ctx->dh.soft_tfm, buf, len); } static unsigned int hpre_dh_max_size(struct crypto_kpp *tfm) { struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + if (ctx->fallback) + return crypto_kpp_maxsize(ctx->dh.soft_tfm); + return ctx->key_sz; } static int hpre_dh_init_tfm(struct crypto_kpp *tfm) { struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + const char *alg = kpp_alg_name(tfm); + unsigned int reqsize; + int ret; + + ctx->dh.soft_tfm = crypto_alloc_kpp(alg, 0, CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(ctx->dh.soft_tfm)) { + pr_err("Failed to alloc dh tfm!\n"); + return PTR_ERR(ctx->dh.soft_tfm); + } - kpp_set_reqsize(tfm, sizeof(struct hpre_asym_request) + hpre_align_pd()); + crypto_kpp_set_flags(ctx->dh.soft_tfm, crypto_kpp_get_flags(tfm)); - return hpre_ctx_init(ctx, HPRE_V2_ALG_TYPE); + reqsize = max(sizeof(struct hpre_asym_request) + hpre_align_pd(), + sizeof(struct kpp_request) + crypto_kpp_reqsize(ctx->dh.soft_tfm)); + kpp_set_reqsize(tfm, reqsize); + + ret = hpre_ctx_init(ctx, HPRE_V2_ALG_TYPE); + if (ret && ret != -ENODEV) { + crypto_free_kpp(ctx->dh.soft_tfm); + return ret; + } else if (ret == -ENODEV) { + ctx->fallback = true; + } + + return 0; } static void hpre_dh_exit_tfm(struct crypto_kpp *tfm) @@ -756,6 +715,7 @@ static void hpre_dh_exit_tfm(struct crypto_kpp *tfm) struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); hpre_dh_clear_ctx(ctx, true); + crypto_free_kpp(ctx->dh.soft_tfm); } static void hpre_rsa_drop_leading_zeros(const char **ptr, size_t *len) @@ -795,9 +755,8 @@ static int hpre_rsa_enc(struct akcipher_request *req) struct hpre_sqe *msg = &hpre_req->req; int ret; - /* For 512 and 1536 bits key size, use soft tfm instead */ - if (ctx->key_sz == HPRE_RSA_512BITS_KSZ || - ctx->key_sz == HPRE_RSA_1536BITS_KSZ) { + /* For unsupported key size and unavailable devices, use soft tfm instead */ + if (ctx->fallback) { akcipher_request_set_tfm(req, ctx->rsa.soft_tfm); ret = crypto_akcipher_encrypt(req); akcipher_request_set_tfm(req, tfm); @@ -828,7 +787,6 @@ static int hpre_rsa_enc(struct akcipher_request *req) return -EINPROGRESS; clear_all: - hpre_rm_req_from_ctx(hpre_req); hpre_hw_data_clr_all(ctx, hpre_req, req->dst, req->src); return ret; @@ -843,9 +801,8 @@ static int hpre_rsa_dec(struct akcipher_request *req) struct hpre_sqe *msg = &hpre_req->req; int ret; - /* For 512 and 1536 bits key size, use soft tfm instead */ - if (ctx->key_sz == HPRE_RSA_512BITS_KSZ || - ctx->key_sz == HPRE_RSA_1536BITS_KSZ) { + /* For unsupported key size and unavailable devices, use soft tfm instead */ + if (ctx->fallback) { akcipher_request_set_tfm(req, ctx->rsa.soft_tfm); ret = crypto_akcipher_decrypt(req); akcipher_request_set_tfm(req, tfm); @@ -883,7 +840,6 @@ static int hpre_rsa_dec(struct akcipher_request *req) return -EINPROGRESS; clear_all: - hpre_rm_req_from_ctx(hpre_req); hpre_hw_data_clr_all(ctx, hpre_req, req->dst, req->src); return ret; @@ -899,8 +855,10 @@ static int hpre_rsa_set_n(struct hpre_ctx *ctx, const char *value, ctx->key_sz = vlen; /* if invalid key size provided, we use software tfm */ - if (!hpre_rsa_key_size_is_support(ctx->key_sz)) + if (!hpre_rsa_key_size_is_support(ctx->key_sz)) { + ctx->fallback = true; return 0; + } ctx->rsa.pubkey = dma_alloc_coherent(ctx->dev, vlen << 1, &ctx->rsa.dma_pubkey, @@ -1035,8 +993,8 @@ static void hpre_rsa_clear_ctx(struct hpre_ctx *ctx, bool is_clear_all) unsigned int half_key_sz = ctx->key_sz >> 1; struct device *dev = ctx->dev; - if (is_clear_all) - hisi_qm_stop_qp(ctx->qp); + if (!ctx->qp) + return; if (ctx->rsa.pubkey) { dma_free_coherent(dev, ctx->key_sz << 1, @@ -1117,6 +1075,7 @@ static int hpre_rsa_setkey(struct hpre_ctx *ctx, const void *key, goto free; } + ctx->fallback = false; return 0; free: @@ -1134,6 +1093,9 @@ static int hpre_rsa_setpubkey(struct crypto_akcipher *tfm, const void *key, if (ret) return ret; + if (!ctx->qp) + return 0; + return hpre_rsa_setkey(ctx, key, keylen, false); } @@ -1147,6 +1109,9 @@ static int hpre_rsa_setprivkey(struct crypto_akcipher *tfm, const void *key, if (ret) return ret; + if (!ctx->qp) + return 0; + return hpre_rsa_setkey(ctx, key, keylen, true); } @@ -1154,9 +1119,8 @@ static unsigned int hpre_rsa_max_size(struct crypto_akcipher *tfm) { struct hpre_ctx *ctx = akcipher_tfm_ctx(tfm); - /* For 512 and 1536 bits key size, use soft tfm instead */ - if (ctx->key_sz == HPRE_RSA_512BITS_KSZ || - ctx->key_sz == HPRE_RSA_1536BITS_KSZ) + /* For unsupported key size and unavailable devices, use soft tfm instead */ + if (ctx->fallback) return crypto_akcipher_maxsize(ctx->rsa.soft_tfm); return ctx->key_sz; @@ -1177,10 +1141,14 @@ static int hpre_rsa_init_tfm(struct crypto_akcipher *tfm) hpre_align_pd()); ret = hpre_ctx_init(ctx, HPRE_V2_ALG_TYPE); - if (ret) + if (ret && ret != -ENODEV) { crypto_free_akcipher(ctx->rsa.soft_tfm); + return ret; + } else if (ret == -ENODEV) { + ctx->fallback = true; + } - return ret; + return 0; } static void hpre_rsa_exit_tfm(struct crypto_akcipher *tfm) @@ -1207,9 +1175,6 @@ static void hpre_ecc_clear_ctx(struct hpre_ctx *ctx, bool is_clear_all) unsigned int sz = ctx->key_sz; unsigned int shift = sz << 1; - if (is_clear_all) - hisi_qm_stop_qp(ctx->qp); - if (ctx->ecdh.p) { /* ecdh: p->a->k->b */ memzero_explicit(ctx->ecdh.p + shift, sz); @@ -1346,7 +1311,7 @@ static int hpre_ecdh_set_param(struct hpre_ctx *ctx, struct ecdh *params) return 0; } -static bool hpre_key_is_zero(char *key, unsigned short key_sz) +static bool hpre_key_is_zero(const char *key, unsigned short key_sz) { int i; @@ -1387,6 +1352,9 @@ static int hpre_ecdh_set_secret(struct crypto_kpp *tfm, const void *buf, struct ecdh params; int ret; + if (ctx->fallback) + return crypto_kpp_set_secret(ctx->ecdh.soft_tfm, buf, len); + if (crypto_ecdh_decode_key(buf, len, ¶ms) < 0) { dev_err(dev, "failed to decode ecdh key!\n"); return -EINVAL; @@ -1488,7 +1456,6 @@ static int hpre_ecdh_msg_request_set(struct hpre_ctx *ctx, { struct hpre_asym_request *h_req; struct hpre_sqe *msg; - int req_id; void *tmp; if (req->dst_len < ctx->key_sz << 1) { @@ -1510,11 +1477,8 @@ static int hpre_ecdh_msg_request_set(struct hpre_ctx *ctx, msg->task_len1 = (ctx->key_sz >> HPRE_BITS_2_BYTES_SHIFT) - 1; h_req->ctx = ctx; - req_id = hpre_add_req_to_ctx(h_req); - if (req_id < 0) - return -EBUSY; - - msg->tag = cpu_to_le16((u16)req_id); + hpre_dfx_add_req_time(h_req); + msg->tag = cpu_to_le64((uintptr_t)h_req); return 0; } @@ -1612,28 +1576,86 @@ static int hpre_ecdh_compute_value(struct kpp_request *req) return -EINPROGRESS; clear_all: - hpre_rm_req_from_ctx(hpre_req); hpre_ecdh_hw_data_clr_all(ctx, hpre_req, req->dst, req->src); return ret; } +static int hpre_ecdh_generate_public_key(struct kpp_request *req) +{ + struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + int ret; + + if (ctx->fallback) { + kpp_request_set_tfm(req, ctx->ecdh.soft_tfm); + ret = crypto_kpp_generate_public_key(req); + kpp_request_set_tfm(req, tfm); + return ret; + } + + return hpre_ecdh_compute_value(req); +} + +static int hpre_ecdh_compute_shared_secret(struct kpp_request *req) +{ + struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + int ret; + + if (ctx->fallback) { + kpp_request_set_tfm(req, ctx->ecdh.soft_tfm); + ret = crypto_kpp_compute_shared_secret(req); + kpp_request_set_tfm(req, tfm); + return ret; + } + + return hpre_ecdh_compute_value(req); +} + static unsigned int hpre_ecdh_max_size(struct crypto_kpp *tfm) { struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + if (ctx->fallback) + return crypto_kpp_maxsize(ctx->ecdh.soft_tfm); + /* max size is the pub_key_size, include x and y */ return ctx->key_sz << 1; } +static int hpre_ecdh_init_tfm(struct crypto_kpp *tfm) +{ + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + const char *alg = kpp_alg_name(tfm); + int ret; + + ret = hpre_ctx_init(ctx, HPRE_V3_ECC_ALG_TYPE); + if (!ret) { + kpp_set_reqsize(tfm, sizeof(struct hpre_asym_request) + hpre_align_pd()); + return 0; + } else if (ret && ret != -ENODEV) { + return ret; + } + + ctx->ecdh.soft_tfm = crypto_alloc_kpp(alg, 0, CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(ctx->ecdh.soft_tfm)) { + pr_err("Failed to alloc %s tfm!\n", alg); + return PTR_ERR(ctx->ecdh.soft_tfm); + } + + crypto_kpp_set_flags(ctx->ecdh.soft_tfm, crypto_kpp_get_flags(tfm)); + ctx->fallback = true; + + return 0; +} + static int hpre_ecdh_nist_p192_init_tfm(struct crypto_kpp *tfm) { struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); ctx->curve_id = ECC_CURVE_NIST_P192; - kpp_set_reqsize(tfm, sizeof(struct hpre_asym_request) + hpre_align_pd()); - - return hpre_ctx_init(ctx, HPRE_V3_ECC_ALG_TYPE); + return hpre_ecdh_init_tfm(tfm); } static int hpre_ecdh_nist_p256_init_tfm(struct crypto_kpp *tfm) @@ -1643,9 +1665,7 @@ static int hpre_ecdh_nist_p256_init_tfm(struct crypto_kpp *tfm) ctx->curve_id = ECC_CURVE_NIST_P256; ctx->enable_hpcore = 1; - kpp_set_reqsize(tfm, sizeof(struct hpre_asym_request) + hpre_align_pd()); - - return hpre_ctx_init(ctx, HPRE_V3_ECC_ALG_TYPE); + return hpre_ecdh_init_tfm(tfm); } static int hpre_ecdh_nist_p384_init_tfm(struct crypto_kpp *tfm) @@ -1654,15 +1674,18 @@ static int hpre_ecdh_nist_p384_init_tfm(struct crypto_kpp *tfm) ctx->curve_id = ECC_CURVE_NIST_P384; - kpp_set_reqsize(tfm, sizeof(struct hpre_asym_request) + hpre_align_pd()); - - return hpre_ctx_init(ctx, HPRE_V3_ECC_ALG_TYPE); + return hpre_ecdh_init_tfm(tfm); } static void hpre_ecdh_exit_tfm(struct crypto_kpp *tfm) { struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + if (ctx->fallback) { + crypto_free_kpp(ctx->ecdh.soft_tfm); + return; + } + hpre_ecc_clear_ctx(ctx, true); } @@ -1680,13 +1703,14 @@ static struct akcipher_alg rsa = { .cra_name = "rsa", .cra_driver_name = "hpre-rsa", .cra_module = THIS_MODULE, + .cra_flags = CRYPTO_ALG_NEED_FALLBACK, }, }; static struct kpp_alg dh = { .set_secret = hpre_dh_set_secret, - .generate_public_key = hpre_dh_compute_value, - .compute_shared_secret = hpre_dh_compute_value, + .generate_public_key = hpre_dh_generate_public_key, + .compute_shared_secret = hpre_dh_compute_shared_secret, .max_size = hpre_dh_max_size, .init = hpre_dh_init_tfm, .exit = hpre_dh_exit_tfm, @@ -1696,14 +1720,15 @@ static struct kpp_alg dh = { .cra_name = "dh", .cra_driver_name = "hpre-dh", .cra_module = THIS_MODULE, + .cra_flags = CRYPTO_ALG_NEED_FALLBACK, }, }; static struct kpp_alg ecdh_curves[] = { { .set_secret = hpre_ecdh_set_secret, - .generate_public_key = hpre_ecdh_compute_value, - .compute_shared_secret = hpre_ecdh_compute_value, + .generate_public_key = hpre_ecdh_generate_public_key, + .compute_shared_secret = hpre_ecdh_compute_shared_secret, .max_size = hpre_ecdh_max_size, .init = hpre_ecdh_nist_p192_init_tfm, .exit = hpre_ecdh_exit_tfm, @@ -1713,11 +1738,12 @@ static struct kpp_alg ecdh_curves[] = { .cra_name = "ecdh-nist-p192", .cra_driver_name = "hpre-ecdh-nist-p192", .cra_module = THIS_MODULE, + .cra_flags = CRYPTO_ALG_NEED_FALLBACK, }, }, { .set_secret = hpre_ecdh_set_secret, - .generate_public_key = hpre_ecdh_compute_value, - .compute_shared_secret = hpre_ecdh_compute_value, + .generate_public_key = hpre_ecdh_generate_public_key, + .compute_shared_secret = hpre_ecdh_compute_shared_secret, .max_size = hpre_ecdh_max_size, .init = hpre_ecdh_nist_p256_init_tfm, .exit = hpre_ecdh_exit_tfm, @@ -1727,11 +1753,12 @@ static struct kpp_alg ecdh_curves[] = { .cra_name = "ecdh-nist-p256", .cra_driver_name = "hpre-ecdh-nist-p256", .cra_module = THIS_MODULE, + .cra_flags = CRYPTO_ALG_NEED_FALLBACK, }, }, { .set_secret = hpre_ecdh_set_secret, - .generate_public_key = hpre_ecdh_compute_value, - .compute_shared_secret = hpre_ecdh_compute_value, + .generate_public_key = hpre_ecdh_generate_public_key, + .compute_shared_secret = hpre_ecdh_compute_shared_secret, .max_size = hpre_ecdh_max_size, .init = hpre_ecdh_nist_p384_init_tfm, .exit = hpre_ecdh_exit_tfm, @@ -1741,6 +1768,7 @@ static struct kpp_alg ecdh_curves[] = { .cra_name = "ecdh-nist-p384", .cra_driver_name = "hpre-ecdh-nist-p384", .cra_module = THIS_MODULE, + .cra_flags = CRYPTO_ALG_NEED_FALLBACK, }, } }; diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c index b94fecd765eebd..884d5d0afaf41f 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_main.c +++ b/drivers/crypto/hisilicon/hpre/hpre_main.c @@ -465,7 +465,7 @@ struct hisi_qp *hpre_create_qp(u8 type) * type: 0 - RSA/DH. algorithm supported in V2, * 1 - ECC algorithm in V3. */ - ret = hisi_qm_alloc_qps_node(&hpre_devices, 1, type, node, &qp); + ret = hisi_qm_alloc_qps_node(&hpre_devices, 1, &type, node, &qp); if (!ret) return qp; diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 3b391a1466353d..a7c8839180ee72 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -2210,6 +2210,7 @@ static void qp_stop_fail_cb(struct hisi_qp *qp) for (i = 0; i < qp_used; i++) { pos = (i + cur_head) % sq_depth; qp->req_cb(qp, qp->sqe + (u32)(qm->sqe_size * pos)); + qm_cq_head_update(qp); atomic_dec(&qp->qp_status.used); } } @@ -2359,25 +2360,33 @@ EXPORT_SYMBOL_GPL(hisi_qm_stop_qp); int hisi_qp_send(struct hisi_qp *qp, const void *msg) { struct hisi_qp_status *qp_status = &qp->qp_status; - u16 sq_tail = qp_status->sq_tail; - u16 sq_tail_next = (sq_tail + 1) % qp->sq_depth; - void *sqe = qm_get_avail_sqe(qp); + u16 sq_tail, sq_tail_next; + void *sqe; + spin_lock_bh(&qp->qp_lock); if (unlikely(atomic_read(&qp->qp_status.flags) == QP_STOP || atomic_read(&qp->qm->status.flags) == QM_STOP || qp->is_resetting)) { + spin_unlock_bh(&qp->qp_lock); dev_info_ratelimited(&qp->qm->pdev->dev, "QP is stopped or resetting\n"); return -EAGAIN; } - if (!sqe) + sqe = qm_get_avail_sqe(qp); + if (!sqe) { + spin_unlock_bh(&qp->qp_lock); return -EBUSY; + } + sq_tail = qp_status->sq_tail; + sq_tail_next = (sq_tail + 1) % qp->sq_depth; memcpy(sqe, msg, qp->qm->sqe_size); + qp->msg[sq_tail] = msg; qm_db(qp->qm, qp->qp_id, QM_DOORBELL_CMD_SQ, sq_tail_next, 0); atomic_inc(&qp->qp_status.used); qp_status->sq_tail = sq_tail_next; + spin_unlock_bh(&qp->qp_lock); return 0; } @@ -2907,12 +2916,13 @@ EXPORT_SYMBOL_GPL(hisi_qm_wait_task_finish); static void hisi_qp_memory_uninit(struct hisi_qm *qm, int num) { struct device *dev = &qm->pdev->dev; - struct qm_dma *qdma; + struct hisi_qp *qp; int i; for (i = num - 1; i >= 0; i--) { - qdma = &qm->qp_array[i].qdma; - dma_free_coherent(dev, qdma->size, qdma->va, qdma->dma); + qp = &qm->qp_array[i]; + dma_free_coherent(dev, qp->qdma.size, qp->qdma.va, qp->qdma.dma); + kfree(qp->msg); kfree(qm->poll_data[i].qp_finish_id); } @@ -2934,10 +2944,14 @@ static int hisi_qp_memory_init(struct hisi_qm *qm, size_t dma_size, int id, return -ENOMEM; qp = &qm->qp_array[id]; + qp->msg = kmalloc_array(sq_depth, sizeof(void *), GFP_KERNEL); + if (!qp->msg) + goto err_free_qp_finish_id; + qp->qdma.va = dma_alloc_coherent(dev, dma_size, &qp->qdma.dma, GFP_KERNEL); if (!qp->qdma.va) - goto err_free_qp_finish_id; + goto err_free_qp_msg; qp->sqe = qp->qdma.va; qp->sqe_dma = qp->qdma.dma; @@ -2949,8 +2963,14 @@ static int hisi_qp_memory_init(struct hisi_qm *qm, size_t dma_size, int id, qp->qm = qm; qp->qp_id = id; + spin_lock_init(&qp->qp_lock); + spin_lock_init(&qp->backlog.lock); + INIT_LIST_HEAD(&qp->backlog.list); + return 0; +err_free_qp_msg: + kfree(qp->msg); err_free_qp_finish_id: kfree(qm->poll_data[id].qp_finish_id); return ret; @@ -3496,6 +3516,14 @@ void hisi_qm_dev_err_uninit(struct hisi_qm *qm) } EXPORT_SYMBOL_GPL(hisi_qm_dev_err_uninit); +static void qm_release_qp_nolock(struct hisi_qp *qp) +{ + struct hisi_qm *qm = qp->qm; + + qm->qp_in_used--; + idr_remove(&qm->qp_idr, qp->qp_id); +} + /** * hisi_qm_free_qps() - free multiple queue pairs. * @qps: The queue pairs need to be freed. @@ -3508,8 +3536,15 @@ void hisi_qm_free_qps(struct hisi_qp **qps, int qp_num) if (!qps || qp_num <= 0) return; - for (i = qp_num - 1; i >= 0; i--) - hisi_qm_release_qp(qps[i]); + down_write(&qps[0]->qm->qps_lock); + + for (i = qp_num - 1; i >= 0; i--) { + qm_stop_qp_nolock(qps[i]); + qm_release_qp_nolock(qps[i]); + } + + up_write(&qps[0]->qm->qps_lock); + qm_pm_put_sync(qps[0]->qm); } EXPORT_SYMBOL_GPL(hisi_qm_free_qps); @@ -3523,6 +3558,43 @@ static void free_list(struct list_head *head) } } +static int qm_get_and_start_qp(struct hisi_qm *qm, int qp_num, struct hisi_qp **qps, u8 *alg_type) +{ + int i, ret; + + ret = qm_pm_get_sync(qm); + if (ret) + return ret; + + down_write(&qm->qps_lock); + for (i = 0; i < qp_num; i++) { + qps[i] = qm_create_qp_nolock(qm, alg_type[i]); + if (IS_ERR(qps[i])) { + ret = -ENODEV; + goto stop_and_free; + } + + ret = qm_start_qp_nolock(qps[i], 0); + if (ret) { + qm_release_qp_nolock(qps[i]); + goto stop_and_free; + } + } + up_write(&qm->qps_lock); + + return 0; + +stop_and_free: + for (i--; i >= 0; i--) { + qm_stop_qp_nolock(qps[i]); + qm_release_qp_nolock(qps[i]); + } + up_write(&qm->qps_lock); + qm_pm_put_sync(qm); + + return ret; +} + static int hisi_qm_sort_devices(int node, struct list_head *head, struct hisi_qm_list *qm_list) { @@ -3571,12 +3643,11 @@ static int hisi_qm_sort_devices(int node, struct list_head *head, * not meet the requirements will return error. */ int hisi_qm_alloc_qps_node(struct hisi_qm_list *qm_list, int qp_num, - u8 alg_type, int node, struct hisi_qp **qps) + u8 *alg_type, int node, struct hisi_qp **qps) { struct hisi_qm_resource *tmp; int ret = -ENODEV; LIST_HEAD(head); - int i; if (!qps || !qm_list || qp_num <= 0) return -EINVAL; @@ -3588,24 +3659,15 @@ int hisi_qm_alloc_qps_node(struct hisi_qm_list *qm_list, int qp_num, } list_for_each_entry(tmp, &head, list) { - for (i = 0; i < qp_num; i++) { - qps[i] = hisi_qm_create_qp(tmp->qm, alg_type); - if (IS_ERR(qps[i])) { - hisi_qm_free_qps(qps, i); - break; - } - } - - if (i == qp_num) { - ret = 0; + ret = qm_get_and_start_qp(tmp->qm, qp_num, qps, alg_type); + if (!ret) break; - } } mutex_unlock(&qm_list->lock); if (ret) - pr_info("Failed to create qps, node[%d], alg[%u], qp[%d]!\n", - node, alg_type, qp_num); + pr_info("Failed to create qps, node[%d], qp[%d]!\n", + node, qp_num); err: free_list(&head); @@ -3678,6 +3740,7 @@ static void qm_clear_vft_config(struct hisi_qm *qm) static int qm_func_shaper_enable(struct hisi_qm *qm, u32 fun_index, u32 qos) { struct device *dev = &qm->pdev->dev; + struct qm_shaper_factor t_factor; u32 ir = qos * QM_QOS_RATE; int ret, total_vfs, i; @@ -3685,6 +3748,7 @@ static int qm_func_shaper_enable(struct hisi_qm *qm, u32 fun_index, u32 qos) if (fun_index > total_vfs) return -EINVAL; + memcpy(&t_factor, &qm->factor[fun_index], sizeof(t_factor)); qm->factor[fun_index].func_qos = qos; ret = qm_get_shaper_para(ir, &qm->factor[fun_index]); @@ -3698,11 +3762,21 @@ static int qm_func_shaper_enable(struct hisi_qm *qm, u32 fun_index, u32 qos) ret = qm_set_vft_common(qm, SHAPER_VFT, fun_index, i, 1); if (ret) { dev_err(dev, "type: %d, failed to set shaper vft!\n", i); - return -EINVAL; + goto back_func_qos; } } return 0; + +back_func_qos: + memcpy(&qm->factor[fun_index], &t_factor, sizeof(t_factor)); + for (i--; i >= ALG_TYPE_0; i--) { + ret = qm_set_vft_common(qm, SHAPER_VFT, fun_index, i, 1); + if (ret) + dev_err(dev, "failed to restore shaper vft during rollback!\n"); + } + + return -EINVAL; } static u32 qm_get_shaper_vft_qos(struct hisi_qm *qm, u32 fun_index) diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h index 81d0beda93b2bb..0710977861f323 100644 --- a/drivers/crypto/hisilicon/sec2/sec.h +++ b/drivers/crypto/hisilicon/sec2/sec.h @@ -82,11 +82,6 @@ struct sec_aead_req { __u8 out_mac_buf[SEC_MAX_MAC_LEN]; }; -struct sec_instance_backlog { - struct list_head list; - spinlock_t lock; -}; - /* SEC request of Crypto */ struct sec_req { union { @@ -112,7 +107,6 @@ struct sec_req { bool use_pbuf; struct list_head list; - struct sec_instance_backlog *backlog; struct sec_request_buf buf; }; @@ -172,7 +166,6 @@ struct sec_qp_ctx { spinlock_t id_lock; struct hisi_acc_sgl_pool *c_in_pool; struct hisi_acc_sgl_pool *c_out_pool; - struct sec_instance_backlog backlog; u16 send_head; }; diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c index 31590d01139a37..c462b58d303435 100644 --- a/drivers/crypto/hisilicon/sec2/sec_crypto.c +++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c @@ -54,7 +54,6 @@ #define SEC_AUTH_CIPHER_V3 0x40 #define SEC_FLAG_OFFSET 7 #define SEC_FLAG_MASK 0x0780 -#define SEC_TYPE_MASK 0x0F #define SEC_DONE_MASK 0x0001 #define SEC_ICV_MASK 0x000E @@ -148,7 +147,7 @@ static void sec_free_req_id(struct sec_req *req) spin_unlock_bh(&qp_ctx->id_lock); } -static u8 pre_parse_finished_bd(struct bd_status *status, void *resp) +static void pre_parse_finished_bd(struct bd_status *status, void *resp) { struct sec_sqe *bd = resp; @@ -158,11 +157,9 @@ static u8 pre_parse_finished_bd(struct bd_status *status, void *resp) SEC_FLAG_MASK) >> SEC_FLAG_OFFSET; status->tag = le16_to_cpu(bd->type2.tag); status->err_type = bd->type2.error_type; - - return bd->type_cipher_auth & SEC_TYPE_MASK; } -static u8 pre_parse_finished_bd3(struct bd_status *status, void *resp) +static void pre_parse_finished_bd3(struct bd_status *status, void *resp) { struct sec_sqe3 *bd3 = resp; @@ -172,8 +169,6 @@ static u8 pre_parse_finished_bd3(struct bd_status *status, void *resp) SEC_FLAG_MASK) >> SEC_FLAG_OFFSET; status->tag = le64_to_cpu(bd3->tag); status->err_type = bd3->error_type; - - return le32_to_cpu(bd3->bd_param) & SEC_TYPE_MASK; } static int sec_cb_status_check(struct sec_req *req, @@ -244,7 +239,7 @@ static void sec_alg_send_backlog_soft(struct sec_ctx *ctx, struct sec_qp_ctx *qp struct sec_req *req, *tmp; int ret; - list_for_each_entry_safe(req, tmp, &qp_ctx->backlog.list, list) { + list_for_each_entry_safe(req, tmp, &qp_ctx->qp->backlog.list, list) { list_del(&req->list); ctx->req_op->buf_unmap(ctx, req); if (req->req_id >= 0) @@ -265,11 +260,12 @@ static void sec_alg_send_backlog_soft(struct sec_ctx *ctx, struct sec_qp_ctx *qp static void sec_alg_send_backlog(struct sec_ctx *ctx, struct sec_qp_ctx *qp_ctx) { + struct hisi_qp *qp = qp_ctx->qp; struct sec_req *req, *tmp; int ret; - spin_lock_bh(&qp_ctx->backlog.lock); - list_for_each_entry_safe(req, tmp, &qp_ctx->backlog.list, list) { + spin_lock_bh(&qp->backlog.lock); + list_for_each_entry_safe(req, tmp, &qp->backlog.list, list) { ret = qp_send_message(req); switch (ret) { case -EINPROGRESS: @@ -287,42 +283,46 @@ static void sec_alg_send_backlog(struct sec_ctx *ctx, struct sec_qp_ctx *qp_ctx) } unlock: - spin_unlock_bh(&qp_ctx->backlog.lock); + spin_unlock_bh(&qp->backlog.lock); } static void sec_req_cb(struct hisi_qp *qp, void *resp) { - struct sec_qp_ctx *qp_ctx = qp->qp_ctx; - struct sec_dfx *dfx = &qp_ctx->ctx->sec->debug.dfx; - u8 type_supported = qp_ctx->ctx->type_supported; + const struct sec_sqe *sqe = qp->msg[qp->qp_status.cq_head]; + struct sec_req *req = container_of(sqe, struct sec_req, sec_sqe); + struct sec_ctx *ctx = req->ctx; + struct sec_dfx *dfx = &ctx->sec->debug.dfx; struct bd_status status; - struct sec_ctx *ctx; - struct sec_req *req; int err; - u8 type; - if (type_supported == SEC_BD_TYPE2) { - type = pre_parse_finished_bd(&status, resp); - req = qp_ctx->req_list[status.tag]; - } else { - type = pre_parse_finished_bd3(&status, resp); - req = (void *)(uintptr_t)status.tag; - } + pre_parse_finished_bd(&status, resp); - if (unlikely(type != type_supported)) { - atomic64_inc(&dfx->err_bd_cnt); - pr_err("err bd type [%u]\n", type); - return; - } + req->err_type = status.err_type; + err = sec_cb_status_check(req, &status); + if (err) + atomic64_inc(&dfx->done_flag_cnt); - if (unlikely(!req)) { - atomic64_inc(&dfx->invalid_req_cnt); - atomic_inc(&qp->qp_status.used); - return; - } + atomic64_inc(&dfx->recv_cnt); + ctx->req_op->buf_unmap(ctx, req); + ctx->req_op->callback(ctx, req, err); +} + +static void sec_req_cb3(struct hisi_qp *qp, void *resp) +{ + struct bd_status status; + struct sec_ctx *ctx; + struct sec_dfx *dfx; + struct sec_req *req; + int err; + + pre_parse_finished_bd3(&status, resp); + + req = (void *)(uintptr_t)status.tag; req->err_type = status.err_type; ctx = req->ctx; + dfx = &ctx->sec->debug.dfx; + err = sec_cb_status_check(req, &status); if (err) atomic64_inc(&dfx->done_flag_cnt); @@ -330,7 +330,6 @@ static void sec_req_cb(struct hisi_qp *qp, void *resp) atomic64_inc(&dfx->recv_cnt); ctx->req_op->buf_unmap(ctx, req); - ctx->req_op->callback(ctx, req, err); } @@ -348,8 +347,10 @@ static int sec_alg_send_message_retry(struct sec_req *req) static int sec_alg_try_enqueue(struct sec_req *req) { + struct hisi_qp *qp = req->qp_ctx->qp; + /* Check if any request is already backlogged */ - if (!list_empty(&req->backlog->list)) + if (!list_empty(&qp->backlog.list)) return -EBUSY; /* Try to enqueue to HW ring */ @@ -359,17 +360,18 @@ static int sec_alg_try_enqueue(struct sec_req *req) static int sec_alg_send_message_maybacklog(struct sec_req *req) { + struct hisi_qp *qp = req->qp_ctx->qp; int ret; ret = sec_alg_try_enqueue(req); if (ret != -EBUSY) return ret; - spin_lock_bh(&req->backlog->lock); + spin_lock_bh(&qp->backlog.lock); ret = sec_alg_try_enqueue(req); if (ret == -EBUSY) - list_add_tail(&req->list, &req->backlog->list); - spin_unlock_bh(&req->backlog->lock); + list_add_tail(&req->list, &qp->backlog.list); + spin_unlock_bh(&qp->backlog.lock); return ret; } @@ -624,32 +626,25 @@ static int sec_create_qp_ctx(struct sec_ctx *ctx, int qp_ctx_id) qp_ctx = &ctx->qp_ctx[qp_ctx_id]; qp = ctx->qps[qp_ctx_id]; - qp->req_type = 0; - qp->qp_ctx = qp_ctx; qp_ctx->qp = qp; qp_ctx->ctx = ctx; - qp->req_cb = sec_req_cb; + if (ctx->type_supported == SEC_BD_TYPE3) + qp->req_cb = sec_req_cb3; + else + qp->req_cb = sec_req_cb; spin_lock_init(&qp_ctx->req_lock); idr_init(&qp_ctx->req_idr); - spin_lock_init(&qp_ctx->backlog.lock); spin_lock_init(&qp_ctx->id_lock); - INIT_LIST_HEAD(&qp_ctx->backlog.list); qp_ctx->send_head = 0; ret = sec_alloc_qp_ctx_resource(ctx, qp_ctx); if (ret) goto err_destroy_idr; - ret = hisi_qm_start_qp(qp, 0); - if (ret < 0) - goto err_resource_free; - return 0; -err_resource_free: - sec_free_qp_ctx_resource(ctx, qp_ctx); err_destroy_idr: idr_destroy(&qp_ctx->req_idr); return ret; @@ -658,7 +653,6 @@ static int sec_create_qp_ctx(struct sec_ctx *ctx, int qp_ctx_id) static void sec_release_qp_ctx(struct sec_ctx *ctx, struct sec_qp_ctx *qp_ctx) { - hisi_qm_stop_qp(qp_ctx->qp); sec_free_qp_ctx_resource(ctx, qp_ctx); idr_destroy(&qp_ctx->req_idr); } @@ -669,10 +663,8 @@ static int sec_ctx_base_init(struct sec_ctx *ctx) int i, ret; ctx->qps = sec_create_qps(); - if (!ctx->qps) { - pr_err("Can not create sec qps!\n"); + if (!ctx->qps) return -ENODEV; - } sec = container_of(ctx->qps[0]->qm, struct sec_dev, qm); ctx->sec = sec; @@ -708,6 +700,9 @@ static void sec_ctx_base_uninit(struct sec_ctx *ctx) { int i; + if (!ctx->qps) + return; + for (i = 0; i < ctx->sec->ctx_q_num; i++) sec_release_qp_ctx(ctx, &ctx->qp_ctx[i]); @@ -719,6 +714,9 @@ static int sec_cipher_init(struct sec_ctx *ctx) { struct sec_cipher_ctx *c_ctx = &ctx->c_ctx; + if (!ctx->qps) + return 0; + c_ctx->c_key = dma_alloc_coherent(ctx->dev, SEC_MAX_KEY_SIZE, &c_ctx->c_key_dma, GFP_KERNEL); if (!c_ctx->c_key) @@ -731,6 +729,9 @@ static void sec_cipher_uninit(struct sec_ctx *ctx) { struct sec_cipher_ctx *c_ctx = &ctx->c_ctx; + if (!ctx->qps) + return; + memzero_explicit(c_ctx->c_key, SEC_MAX_KEY_SIZE); dma_free_coherent(ctx->dev, SEC_MAX_KEY_SIZE, c_ctx->c_key, c_ctx->c_key_dma); @@ -752,6 +753,9 @@ static void sec_auth_uninit(struct sec_ctx *ctx) { struct sec_auth_ctx *a_ctx = &ctx->a_ctx; + if (!ctx->qps) + return; + memzero_explicit(a_ctx->a_key, SEC_MAX_AKEY_SIZE); dma_free_coherent(ctx->dev, SEC_MAX_AKEY_SIZE, a_ctx->a_key, a_ctx->a_key_dma); @@ -789,7 +793,7 @@ static int sec_skcipher_init(struct crypto_skcipher *tfm) } ret = sec_ctx_base_init(ctx); - if (ret) + if (ret && ret != -ENODEV) return ret; ret = sec_cipher_init(ctx); @@ -898,6 +902,9 @@ static int sec_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, struct device *dev = ctx->dev; int ret; + if (!ctx->qps) + goto set_soft_key; + if (c_mode == SEC_CMODE_XTS) { ret = xts_verify_key(tfm, key, keylen); if (ret) { @@ -928,13 +935,14 @@ static int sec_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, } memcpy(c_ctx->c_key, key, keylen); - if (c_ctx->fbtfm) { - ret = crypto_sync_skcipher_setkey(c_ctx->fbtfm, key, keylen); - if (ret) { - dev_err(dev, "failed to set fallback skcipher key!\n"); - return ret; - } + +set_soft_key: + ret = crypto_sync_skcipher_setkey(c_ctx->fbtfm, key, keylen); + if (ret) { + dev_err(dev, "failed to set fallback skcipher key!\n"); + return ret; } + return 0; } @@ -1398,6 +1406,9 @@ static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key, struct crypto_authenc_keys keys; int ret; + if (!ctx->qps) + return sec_aead_fallback_setkey(a_ctx, tfm, key, keylen); + ctx->a_ctx.a_alg = a_alg; ctx->c_ctx.c_alg = c_alg; c_ctx->c_mode = c_mode; @@ -1952,7 +1963,6 @@ static int sec_request_init(struct sec_ctx *ctx, struct sec_req *req) } while (req->req_id < 0 && ++i < ctx->sec->ctx_q_num); req->qp_ctx = qp_ctx; - req->backlog = &qp_ctx->backlog; return 0; } @@ -2055,6 +2065,9 @@ static int sec_skcipher_ctx_init(struct crypto_skcipher *tfm) if (ret) return ret; + if (!ctx->qps) + return 0; + if (ctx->sec->qm.ver < QM_HW_V3) { ctx->type_supported = SEC_BD_TYPE2; ctx->req_op = &sec_skcipher_req_ops; @@ -2063,7 +2076,7 @@ static int sec_skcipher_ctx_init(struct crypto_skcipher *tfm) ctx->req_op = &sec_skcipher_req_ops_v3; } - return ret; + return 0; } static void sec_skcipher_ctx_exit(struct crypto_skcipher *tfm) @@ -2131,7 +2144,7 @@ static int sec_aead_ctx_init(struct crypto_aead *tfm, const char *hash_name) int ret; ret = sec_aead_init(tfm); - if (ret) { + if (ret && ret != -ENODEV) { pr_err("hisi_sec2: aead init error!\n"); return ret; } @@ -2173,7 +2186,7 @@ static int sec_aead_xcm_ctx_init(struct crypto_aead *tfm) int ret; ret = sec_aead_init(tfm); - if (ret) { + if (ret && ret != -ENODEV) { dev_err(ctx->dev, "hisi_sec2: aead xcm init error!\n"); return ret; } @@ -2318,6 +2331,9 @@ static int sec_skcipher_crypto(struct skcipher_request *sk_req, bool encrypt) bool need_fallback = false; int ret; + if (!ctx->qps) + goto soft_crypto; + if (!sk_req->cryptlen) { if (ctx->c_ctx.c_mode == SEC_CMODE_XTS) return -EINVAL; @@ -2335,9 +2351,12 @@ static int sec_skcipher_crypto(struct skcipher_request *sk_req, bool encrypt) return -EINVAL; if (unlikely(ctx->c_ctx.fallback || need_fallback)) - return sec_skcipher_soft_crypto(ctx, sk_req, encrypt); + goto soft_crypto; return ctx->req_op->process(ctx, req); + +soft_crypto: + return sec_skcipher_soft_crypto(ctx, sk_req, encrypt); } static int sec_skcipher_encrypt(struct skcipher_request *sk_req) @@ -2545,6 +2564,9 @@ static int sec_aead_crypto(struct aead_request *a_req, bool encrypt) bool need_fallback = false; int ret; + if (!ctx->qps) + goto soft_crypto; + req->flag = a_req->base.flags; req->aead_req.aead_req = a_req; req->c_req.encrypt = encrypt; @@ -2555,11 +2577,14 @@ static int sec_aead_crypto(struct aead_request *a_req, bool encrypt) ret = sec_aead_param_check(ctx, req, &need_fallback); if (unlikely(ret)) { if (need_fallback) - return sec_aead_soft_crypto(ctx, a_req, encrypt); + goto soft_crypto; return -EINVAL; } return ctx->req_op->process(ctx, req); + +soft_crypto: + return sec_aead_soft_crypto(ctx, a_req, encrypt); } static int sec_aead_encrypt(struct aead_request *a_req) diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index 5eb2d68207426e..7dd125f5f511fa 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -417,18 +417,29 @@ struct hisi_qp **sec_create_qps(void) int node = cpu_to_node(raw_smp_processor_id()); u32 ctx_num = ctx_q_num; struct hisi_qp **qps; + u8 *type; int ret; qps = kcalloc(ctx_num, sizeof(struct hisi_qp *), GFP_KERNEL); if (!qps) return NULL; - ret = hisi_qm_alloc_qps_node(&sec_devices, ctx_num, 0, node, qps); - if (!ret) - return qps; + /* The type of SEC is all 0, so just allocated by kcalloc */ + type = kcalloc(ctx_num, sizeof(u8), GFP_KERNEL); + if (!type) { + kfree(qps); + return NULL; + } - kfree(qps); - return NULL; + ret = hisi_qm_alloc_qps_node(&sec_devices, ctx_num, type, node, qps); + if (ret) { + kfree(type); + kfree(qps); + return NULL; + } + + kfree(type); + return qps; } u64 sec_get_alg_bitmap(struct hisi_qm *qm, u32 high, u32 low) diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c index 7a9ef2a9972a22..848ad7b101d939 100644 --- a/drivers/crypto/hisilicon/sgl.c +++ b/drivers/crypto/hisilicon/sgl.c @@ -265,7 +265,7 @@ hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, struct scatterlist *sgl, return curr_hw_sgl; err_unmap: - dma_unmap_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL); + dma_unmap_sg(dev, sgl, sg_n, dir); return ERR_PTR(ret); } diff --git a/drivers/crypto/hisilicon/trng/trng.c b/drivers/crypto/hisilicon/trng/trng.c index ac74df4a947126..5ca0b90859a81e 100644 --- a/drivers/crypto/hisilicon/trng/trng.c +++ b/drivers/crypto/hisilicon/trng/trng.c @@ -40,6 +40,7 @@ #define SEED_SHIFT_24 24 #define SEED_SHIFT_16 16 #define SEED_SHIFT_8 8 +#define SW_MAX_RANDOM_BYTES 65520 struct hisi_trng_list { struct mutex lock; @@ -53,8 +54,10 @@ struct hisi_trng { struct list_head list; struct hwrng rng; u32 ver; - bool is_used; - struct mutex mutex; + u32 ctx_num; + /* The bytes of the random number generated since the last seeding. */ + u32 random_bytes; + struct mutex lock; }; struct hisi_trng_ctx { @@ -63,10 +66,14 @@ struct hisi_trng_ctx { static atomic_t trng_active_devs; static struct hisi_trng_list trng_devices; +static int hisi_trng_read(struct hwrng *rng, void *buf, size_t max, bool wait); -static void hisi_trng_set_seed(struct hisi_trng *trng, const u8 *seed) +static int hisi_trng_set_seed(struct hisi_trng *trng, const u8 *seed) { u32 val, seed_reg, i; + int ret; + + writel(0x0, trng->base + SW_DRBG_BLOCKS); for (i = 0; i < SW_DRBG_SEED_SIZE; i += SW_DRBG_SEED_SIZE / SW_DRBG_SEED_REGS_NUM) { @@ -78,6 +85,20 @@ static void hisi_trng_set_seed(struct hisi_trng *trng, const u8 *seed) seed_reg = (i >> SW_DRBG_NUM_SHIFT) % SW_DRBG_SEED_REGS_NUM; writel(val, trng->base + SW_DRBG_SEED(seed_reg)); } + + writel(SW_DRBG_BLOCKS_NUM | (0x1 << SW_DRBG_ENABLE_SHIFT), + trng->base + SW_DRBG_BLOCKS); + writel(0x1, trng->base + SW_DRBG_INIT); + ret = readl_relaxed_poll_timeout(trng->base + SW_DRBG_STATUS, + val, val & BIT(0), SLEEP_US, TIMEOUT_US); + if (ret) { + pr_err("failed to init trng(%d)\n", ret); + return -EIO; + } + + trng->random_bytes = 0; + + return 0; } static int hisi_trng_seed(struct crypto_rng *tfm, const u8 *seed, @@ -85,8 +106,7 @@ static int hisi_trng_seed(struct crypto_rng *tfm, const u8 *seed, { struct hisi_trng_ctx *ctx = crypto_rng_ctx(tfm); struct hisi_trng *trng = ctx->trng; - u32 val = 0; - int ret = 0; + int ret; if (slen < SW_DRBG_SEED_SIZE) { pr_err("slen(%u) is not matched with trng(%d)\n", slen, @@ -94,43 +114,45 @@ static int hisi_trng_seed(struct crypto_rng *tfm, const u8 *seed, return -EINVAL; } - writel(0x0, trng->base + SW_DRBG_BLOCKS); - hisi_trng_set_seed(trng, seed); + mutex_lock(&trng->lock); + ret = hisi_trng_set_seed(trng, seed); + mutex_unlock(&trng->lock); - writel(SW_DRBG_BLOCKS_NUM | (0x1 << SW_DRBG_ENABLE_SHIFT), - trng->base + SW_DRBG_BLOCKS); - writel(0x1, trng->base + SW_DRBG_INIT); + return ret; +} - ret = readl_relaxed_poll_timeout(trng->base + SW_DRBG_STATUS, - val, val & BIT(0), SLEEP_US, TIMEOUT_US); - if (ret) - pr_err("fail to init trng(%d)\n", ret); +static int hisi_trng_reseed(struct hisi_trng *trng) +{ + u8 seed[SW_DRBG_SEED_SIZE]; + int size; - return ret; + if (!trng->random_bytes) + return 0; + + size = hisi_trng_read(&trng->rng, seed, SW_DRBG_SEED_SIZE, false); + if (size != SW_DRBG_SEED_SIZE) + return -EIO; + + return hisi_trng_set_seed(trng, seed); } -static int hisi_trng_generate(struct crypto_rng *tfm, const u8 *src, - unsigned int slen, u8 *dstn, unsigned int dlen) +static int hisi_trng_get_bytes(struct hisi_trng *trng, u8 *dstn, unsigned int dlen) { - struct hisi_trng_ctx *ctx = crypto_rng_ctx(tfm); - struct hisi_trng *trng = ctx->trng; u32 data[SW_DRBG_DATA_NUM]; u32 currsize = 0; u32 val = 0; int ret; u32 i; - if (dlen > SW_DRBG_BLOCKS_NUM * SW_DRBG_BYTES || dlen == 0) { - pr_err("dlen(%u) exceeds limit(%d)!\n", dlen, - SW_DRBG_BLOCKS_NUM * SW_DRBG_BYTES); - return -EINVAL; - } + ret = hisi_trng_reseed(trng); + if (ret) + return ret; do { ret = readl_relaxed_poll_timeout(trng->base + SW_DRBG_STATUS, - val, val & BIT(1), SLEEP_US, TIMEOUT_US); + val, val & BIT(1), SLEEP_US, TIMEOUT_US); if (ret) { - pr_err("fail to generate random number(%d)!\n", ret); + pr_err("failed to generate random number(%d)!\n", ret); break; } @@ -145,30 +167,57 @@ static int hisi_trng_generate(struct crypto_rng *tfm, const u8 *src, currsize = dlen; } + trng->random_bytes += SW_DRBG_BYTES; writel(0x1, trng->base + SW_DRBG_GEN); } while (currsize < dlen); return ret; } +static int hisi_trng_generate(struct crypto_rng *tfm, const u8 *src, + unsigned int slen, u8 *dstn, unsigned int dlen) +{ + struct hisi_trng_ctx *ctx = crypto_rng_ctx(tfm); + struct hisi_trng *trng = ctx->trng; + unsigned int currsize = 0; + unsigned int block_size; + int ret; + + if (!dstn || !dlen) { + pr_err("output is error, dlen %u!\n", dlen); + return -EINVAL; + } + + do { + block_size = min_t(unsigned int, dlen - currsize, SW_MAX_RANDOM_BYTES); + mutex_lock(&trng->lock); + ret = hisi_trng_get_bytes(trng, dstn + currsize, block_size); + mutex_unlock(&trng->lock); + if (ret) + return ret; + currsize += block_size; + } while (currsize < dlen); + + return 0; +} + static int hisi_trng_init(struct crypto_tfm *tfm) { struct hisi_trng_ctx *ctx = crypto_tfm_ctx(tfm); struct hisi_trng *trng; - int ret = -EBUSY; + u32 ctx_num = ~0; mutex_lock(&trng_devices.lock); list_for_each_entry(trng, &trng_devices.list, list) { - if (!trng->is_used) { - trng->is_used = true; + if (trng->ctx_num < ctx_num) { + ctx_num = trng->ctx_num; ctx->trng = trng; - ret = 0; - break; } } + ctx->trng->ctx_num++; mutex_unlock(&trng_devices.lock); - return ret; + return 0; } static void hisi_trng_exit(struct crypto_tfm *tfm) @@ -176,7 +225,7 @@ static void hisi_trng_exit(struct crypto_tfm *tfm) struct hisi_trng_ctx *ctx = crypto_tfm_ctx(tfm); mutex_lock(&trng_devices.lock); - ctx->trng->is_used = false; + ctx->trng->ctx_num--; mutex_unlock(&trng_devices.lock); } @@ -238,7 +287,7 @@ static int hisi_trng_del_from_list(struct hisi_trng *trng) int ret = -EBUSY; mutex_lock(&trng_devices.lock); - if (!trng->is_used) { + if (!trng->ctx_num) { list_del(&trng->list); ret = 0; } @@ -262,7 +311,9 @@ static int hisi_trng_probe(struct platform_device *pdev) if (IS_ERR(trng->base)) return PTR_ERR(trng->base); - trng->is_used = false; + trng->ctx_num = 0; + trng->random_bytes = SW_MAX_RANDOM_BYTES; + mutex_init(&trng->lock); trng->ver = readl(trng->base + HISI_TRNG_VERSION); if (!trng_devices.is_init) { INIT_LIST_HEAD(&trng_devices.list); diff --git a/drivers/crypto/hisilicon/zip/zip.h b/drivers/crypto/hisilicon/zip/zip.h index 9fb2a9c01132b4..b83f228281ab1e 100644 --- a/drivers/crypto/hisilicon/zip/zip.h +++ b/drivers/crypto/hisilicon/zip/zip.h @@ -99,7 +99,7 @@ enum zip_cap_table_type { ZIP_CORE5_BITMAP, }; -int zip_create_qps(struct hisi_qp **qps, int qp_num, int node); +int zip_create_qps(struct hisi_qp **qps, int qp_num, int node, u8 *alg_type); int hisi_zip_register_to_crypto(struct hisi_qm *qm); void hisi_zip_unregister_from_crypto(struct hisi_qm *qm); bool hisi_zip_alg_support(struct hisi_qm *qm, u32 alg); diff --git a/drivers/crypto/hisilicon/zip/zip_crypto.c b/drivers/crypto/hisilicon/zip/zip_crypto.c index b97513981a3b79..e140d4f8afe0e8 100644 --- a/drivers/crypto/hisilicon/zip/zip_crypto.c +++ b/drivers/crypto/hisilicon/zip/zip_crypto.c @@ -39,6 +39,7 @@ enum { HZIP_CTX_Q_NUM }; +#define GET_REQ_FROM_SQE(sqe) ((u64)(sqe)->dw26 | (u64)(sqe)->dw27 << 32) #define COMP_NAME_TO_TYPE(alg_name) \ (!strcmp((alg_name), "deflate") ? HZIP_ALG_TYPE_DEFLATE : 0) @@ -48,6 +49,7 @@ struct hisi_zip_req { struct hisi_acc_hw_sgl *hw_dst; dma_addr_t dma_src; dma_addr_t dma_dst; + struct hisi_zip_qp_ctx *qp_ctx; u16 req_id; }; @@ -64,6 +66,7 @@ struct hisi_zip_qp_ctx { struct hisi_acc_sgl_pool *sgl_pool; struct hisi_zip *zip_dev; struct hisi_zip_ctx *ctx; + u8 req_type; }; struct hisi_zip_sqe_ops { @@ -74,7 +77,6 @@ struct hisi_zip_sqe_ops { void (*fill_req_type)(struct hisi_zip_sqe *sqe, u8 req_type); void (*fill_tag)(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req); void (*fill_sqe_type)(struct hisi_zip_sqe *sqe, u8 sqe_type); - u32 (*get_tag)(struct hisi_zip_sqe *sqe); u32 (*get_status)(struct hisi_zip_sqe *sqe); u32 (*get_dstlen)(struct hisi_zip_sqe *sqe); }; @@ -82,6 +84,7 @@ struct hisi_zip_sqe_ops { struct hisi_zip_ctx { struct hisi_zip_qp_ctx qp_ctx[HZIP_CTX_Q_NUM]; const struct hisi_zip_sqe_ops *ops; + bool fallback; }; static int sgl_sge_nr_set(const char *val, const struct kernel_param *kp) @@ -108,6 +111,24 @@ static u16 sgl_sge_nr = HZIP_SGL_SGE_NR; module_param_cb(sgl_sge_nr, &sgl_sge_nr_ops, &sgl_sge_nr, 0444); MODULE_PARM_DESC(sgl_sge_nr, "Number of sge in sgl(1-255)"); +static int hisi_zip_fallback_do_work(struct acomp_req *acomp_req, bool is_decompress) +{ + ACOMP_FBREQ_ON_STACK(fbreq, acomp_req); + int ret; + + if (!is_decompress) + ret = crypto_acomp_compress(fbreq); + else + ret = crypto_acomp_decompress(fbreq); + if (ret) { + pr_err("failed to do fallback work, ret=%d\n", ret); + return ret; + } + + acomp_req->dlen = fbreq->dlen; + return ret; +} + static struct hisi_zip_req *hisi_zip_create_req(struct hisi_zip_qp_ctx *qp_ctx, struct acomp_req *req) { @@ -131,6 +152,7 @@ static struct hisi_zip_req *hisi_zip_create_req(struct hisi_zip_qp_ctx *qp_ctx, req_cache = q + req_id; req_cache->req_id = req_id; req_cache->req = req; + req_cache->qp_ctx = qp_ctx; return req_cache; } @@ -181,7 +203,8 @@ static void hisi_zip_fill_req_type(struct hisi_zip_sqe *sqe, u8 req_type) static void hisi_zip_fill_tag(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req) { - sqe->dw26 = req->req_id; + sqe->dw26 = lower_32_bits((u64)req); + sqe->dw27 = upper_32_bits((u64)req); } static void hisi_zip_fill_sqe_type(struct hisi_zip_sqe *sqe, u8 sqe_type) @@ -213,7 +236,6 @@ static int hisi_zip_do_work(struct hisi_zip_qp_ctx *qp_ctx, { struct hisi_acc_sgl_pool *pool = qp_ctx->sgl_pool; struct hisi_zip_dfx *dfx = &qp_ctx->zip_dev->dfx; - struct hisi_zip_req_q *req_q = &qp_ctx->req_q; struct acomp_req *a_req = req->req; struct hisi_qp *qp = qp_ctx->qp; struct device *dev = &qp->qm->pdev->dev; @@ -237,18 +259,16 @@ static int hisi_zip_do_work(struct hisi_zip_qp_ctx *qp_ctx, &req->dma_dst, DMA_FROM_DEVICE); if (IS_ERR(req->hw_dst)) { ret = PTR_ERR(req->hw_dst); - dev_err(dev, "failed to map the dst buffer to hw slg (%d)!\n", + dev_err(dev, "failed to map the dst buffer to hw sgl (%d)!\n", ret); goto err_unmap_input; } - hisi_zip_fill_sqe(qp_ctx->ctx, &zip_sqe, qp->req_type, req); + hisi_zip_fill_sqe(qp_ctx->ctx, &zip_sqe, qp_ctx->req_type, req); /* send command to start a task */ atomic64_inc(&dfx->send_cnt); - spin_lock_bh(&req_q->req_lock); ret = hisi_qp_send(qp, &zip_sqe); - spin_unlock_bh(&req_q->req_lock); if (unlikely(ret < 0)) { atomic64_inc(&dfx->send_busy_cnt); ret = -EAGAIN; @@ -265,11 +285,6 @@ static int hisi_zip_do_work(struct hisi_zip_qp_ctx *qp_ctx, return ret; } -static u32 hisi_zip_get_tag(struct hisi_zip_sqe *sqe) -{ - return sqe->dw26; -} - static u32 hisi_zip_get_status(struct hisi_zip_sqe *sqe) { return sqe->dw3 & HZIP_BD_STATUS_M; @@ -282,14 +297,12 @@ static u32 hisi_zip_get_dstlen(struct hisi_zip_sqe *sqe) static void hisi_zip_acomp_cb(struct hisi_qp *qp, void *data) { - struct hisi_zip_qp_ctx *qp_ctx = qp->qp_ctx; + struct hisi_zip_sqe *sqe = data; + struct hisi_zip_req *req = (struct hisi_zip_req *)GET_REQ_FROM_SQE(sqe); + struct hisi_zip_qp_ctx *qp_ctx = req->qp_ctx; const struct hisi_zip_sqe_ops *ops = qp_ctx->ctx->ops; struct hisi_zip_dfx *dfx = &qp_ctx->zip_dev->dfx; - struct hisi_zip_req_q *req_q = &qp_ctx->req_q; struct device *dev = &qp->qm->pdev->dev; - struct hisi_zip_sqe *sqe = data; - u32 tag = ops->get_tag(sqe); - struct hisi_zip_req *req = req_q->q + tag; struct acomp_req *acomp_req = req->req; int err = 0; u32 status; @@ -319,10 +332,15 @@ static int hisi_zip_acompress(struct acomp_req *acomp_req) { struct hisi_zip_ctx *ctx = crypto_tfm_ctx(acomp_req->base.tfm); struct hisi_zip_qp_ctx *qp_ctx = &ctx->qp_ctx[HZIP_QPC_COMP]; - struct device *dev = &qp_ctx->qp->qm->pdev->dev; struct hisi_zip_req *req; + struct device *dev; int ret; + if (ctx->fallback) + return hisi_zip_fallback_do_work(acomp_req, 0); + + dev = &qp_ctx->qp->qm->pdev->dev; + req = hisi_zip_create_req(qp_ctx, acomp_req); if (IS_ERR(req)) return PTR_ERR(req); @@ -340,10 +358,15 @@ static int hisi_zip_adecompress(struct acomp_req *acomp_req) { struct hisi_zip_ctx *ctx = crypto_tfm_ctx(acomp_req->base.tfm); struct hisi_zip_qp_ctx *qp_ctx = &ctx->qp_ctx[HZIP_QPC_DECOMP]; - struct device *dev = &qp_ctx->qp->qm->pdev->dev; struct hisi_zip_req *req; + struct device *dev; int ret; + if (ctx->fallback) + return hisi_zip_fallback_do_work(acomp_req, 1); + + dev = &qp_ctx->qp->qm->pdev->dev; + req = hisi_zip_create_req(qp_ctx, acomp_req); if (IS_ERR(req)) return PTR_ERR(req); @@ -358,33 +381,6 @@ static int hisi_zip_adecompress(struct acomp_req *acomp_req) return ret; } -static int hisi_zip_start_qp(struct hisi_qp *qp, struct hisi_zip_qp_ctx *qp_ctx, - int alg_type, int req_type) -{ - struct device *dev = &qp->qm->pdev->dev; - int ret; - - qp->req_type = req_type; - qp->alg_type = alg_type; - qp->qp_ctx = qp_ctx; - - ret = hisi_qm_start_qp(qp, 0); - if (ret < 0) { - dev_err(dev, "failed to start qp (%d)!\n", ret); - return ret; - } - - qp_ctx->qp = qp; - - return 0; -} - -static void hisi_zip_release_qp(struct hisi_zip_qp_ctx *qp_ctx) -{ - hisi_qm_stop_qp(qp_ctx->qp); - hisi_qm_free_qps(&qp_ctx->qp, 1); -} - static const struct hisi_zip_sqe_ops hisi_zip_ops = { .sqe_type = 0x3, .fill_addr = hisi_zip_fill_addr, @@ -393,7 +389,6 @@ static const struct hisi_zip_sqe_ops hisi_zip_ops = { .fill_req_type = hisi_zip_fill_req_type, .fill_tag = hisi_zip_fill_tag, .fill_sqe_type = hisi_zip_fill_sqe_type, - .get_tag = hisi_zip_get_tag, .get_status = hisi_zip_get_status, .get_dstlen = hisi_zip_get_dstlen, }; @@ -402,10 +397,15 @@ static int hisi_zip_ctx_init(struct hisi_zip_ctx *hisi_zip_ctx, u8 req_type, int { struct hisi_qp *qps[HZIP_CTX_Q_NUM] = { NULL }; struct hisi_zip_qp_ctx *qp_ctx; + u8 alg_type[HZIP_CTX_Q_NUM]; struct hisi_zip *hisi_zip; - int ret, i, j; + int ret, i; - ret = zip_create_qps(qps, HZIP_CTX_Q_NUM, node); + /* alg_type = 0 for compress, 1 for decompress in hw sqe */ + for (i = 0; i < HZIP_CTX_Q_NUM; i++) + alg_type[i] = i; + + ret = zip_create_qps(qps, HZIP_CTX_Q_NUM, node, alg_type); if (ret) { pr_err("failed to create zip qps (%d)!\n", ret); return -ENODEV; @@ -414,19 +414,11 @@ static int hisi_zip_ctx_init(struct hisi_zip_ctx *hisi_zip_ctx, u8 req_type, int hisi_zip = container_of(qps[0]->qm, struct hisi_zip, qm); for (i = 0; i < HZIP_CTX_Q_NUM; i++) { - /* alg_type = 0 for compress, 1 for decompress in hw sqe */ qp_ctx = &hisi_zip_ctx->qp_ctx[i]; qp_ctx->ctx = hisi_zip_ctx; - ret = hisi_zip_start_qp(qps[i], qp_ctx, i, req_type); - if (ret) { - for (j = i - 1; j >= 0; j--) - hisi_qm_stop_qp(hisi_zip_ctx->qp_ctx[j].qp); - - hisi_qm_free_qps(qps, HZIP_CTX_Q_NUM); - return ret; - } - qp_ctx->zip_dev = hisi_zip; + qp_ctx->req_type = req_type; + qp_ctx->qp = qps[i]; } hisi_zip_ctx->ops = &hisi_zip_ops; @@ -436,10 +428,13 @@ static int hisi_zip_ctx_init(struct hisi_zip_ctx *hisi_zip_ctx, u8 req_type, int static void hisi_zip_ctx_exit(struct hisi_zip_ctx *hisi_zip_ctx) { + struct hisi_qp *qps[HZIP_CTX_Q_NUM] = { NULL }; int i; for (i = 0; i < HZIP_CTX_Q_NUM; i++) - hisi_zip_release_qp(&hisi_zip_ctx->qp_ctx[i]); + qps[i] = hisi_zip_ctx->qp_ctx[i].qp; + + hisi_qm_free_qps(qps, HZIP_CTX_Q_NUM); } static int hisi_zip_create_req_q(struct hisi_zip_ctx *ctx) @@ -549,7 +544,7 @@ static int hisi_zip_acomp_init(struct crypto_acomp *tfm) ret = hisi_zip_ctx_init(ctx, COMP_NAME_TO_TYPE(alg_name), tfm->base.node); if (ret) { pr_err("failed to init ctx (%d)!\n", ret); - return ret; + goto switch_to_soft; } dev = &ctx->qp_ctx[0].qp->qm->pdev->dev; @@ -574,17 +569,20 @@ static int hisi_zip_acomp_init(struct crypto_acomp *tfm) hisi_zip_release_req_q(ctx); err_ctx_exit: hisi_zip_ctx_exit(ctx); - return ret; +switch_to_soft: + ctx->fallback = true; + return 0; } static void hisi_zip_acomp_exit(struct crypto_acomp *tfm) { struct hisi_zip_ctx *ctx = crypto_tfm_ctx(&tfm->base); - hisi_zip_set_acomp_cb(ctx, NULL); - hisi_zip_release_sgl_pool(ctx); - hisi_zip_release_req_q(ctx); - hisi_zip_ctx_exit(ctx); + if (!ctx->fallback) { + hisi_zip_release_sgl_pool(ctx); + hisi_zip_release_req_q(ctx); + hisi_zip_ctx_exit(ctx); + } } static struct acomp_alg hisi_zip_acomp_deflate = { @@ -595,7 +593,8 @@ static struct acomp_alg hisi_zip_acomp_deflate = { .base = { .cra_name = "deflate", .cra_driver_name = "hisi-deflate-acomp", - .cra_flags = CRYPTO_ALG_ASYNC, + .cra_flags = CRYPTO_ALG_ASYNC | + CRYPTO_ALG_NEED_FALLBACK, .cra_module = THIS_MODULE, .cra_priority = HZIP_ALG_PRIORITY, .cra_ctxsize = sizeof(struct hisi_zip_ctx), diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index 4fcbe6bada0663..85b26ef1754855 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -446,12 +446,12 @@ static const struct pci_device_id hisi_zip_dev_ids[] = { }; MODULE_DEVICE_TABLE(pci, hisi_zip_dev_ids); -int zip_create_qps(struct hisi_qp **qps, int qp_num, int node) +int zip_create_qps(struct hisi_qp **qps, int qp_num, int node, u8 *alg_type) { if (node == NUMA_NO_NODE) node = cpu_to_node(raw_smp_processor_id()); - return hisi_qm_alloc_qps_node(&zip_devices, qp_num, 0, node, qps); + return hisi_qm_alloc_qps_node(&zip_devices, qp_num, alg_type, node, qps); } bool hisi_zip_alg_support(struct hisi_qm *qm, u32 alg) diff --git a/drivers/crypto/inside-secure/eip93/eip93-main.c b/drivers/crypto/inside-secure/eip93/eip93-main.c index 0b38a567da0e01..b7fd9795062d4c 100644 --- a/drivers/crypto/inside-secure/eip93/eip93-main.c +++ b/drivers/crypto/inside-secure/eip93/eip93-main.c @@ -77,11 +77,44 @@ inline void eip93_irq_clear(struct eip93_device *eip93, u32 mask) __raw_writel(mask, eip93->base + EIP93_REG_INT_CLR); } -static void eip93_unregister_algs(unsigned int i) +static int eip93_algo_is_supported(u32 alg_flags, u32 supported_algo_flags) +{ + if ((IS_DES(alg_flags) || IS_3DES(alg_flags)) && + !(supported_algo_flags & EIP93_PE_OPTION_TDES)) + return 0; + + if (IS_AES(alg_flags) && + !(supported_algo_flags & EIP93_PE_OPTION_AES)) + return 0; + + if (IS_HASH_MD5(alg_flags) && + !(supported_algo_flags & EIP93_PE_OPTION_MD5)) + return 0; + + if (IS_HASH_SHA1(alg_flags) && + !(supported_algo_flags & EIP93_PE_OPTION_SHA_1)) + return 0; + + if (IS_HASH_SHA224(alg_flags) && + !(supported_algo_flags & EIP93_PE_OPTION_SHA_224)) + return 0; + + if (IS_HASH_SHA256(alg_flags) && + !(supported_algo_flags & EIP93_PE_OPTION_SHA_256)) + return 0; + + return 1; +} + +static void eip93_unregister_algs(u32 supported_algo_flags, unsigned int i) { unsigned int j; for (j = 0; j < i; j++) { + if (!eip93_algo_is_supported(eip93_algs[j]->flags, + supported_algo_flags)) + continue; + switch (eip93_algs[j]->type) { case EIP93_ALG_TYPE_SKCIPHER: crypto_unregister_skcipher(&eip93_algs[j]->alg.skcipher); @@ -90,7 +123,7 @@ static void eip93_unregister_algs(unsigned int i) crypto_unregister_aead(&eip93_algs[j]->alg.aead); break; case EIP93_ALG_TYPE_HASH: - crypto_unregister_ahash(&eip93_algs[i]->alg.ahash); + crypto_unregister_ahash(&eip93_algs[j]->alg.ahash); break; } } @@ -106,49 +139,27 @@ static int eip93_register_algs(struct eip93_device *eip93, u32 supported_algo_fl eip93_algs[i]->eip93 = eip93; - if ((IS_DES(alg_flags) || IS_3DES(alg_flags)) && - !(supported_algo_flags & EIP93_PE_OPTION_TDES)) + if (!eip93_algo_is_supported(alg_flags, supported_algo_flags)) continue; - if (IS_AES(alg_flags)) { - if (!(supported_algo_flags & EIP93_PE_OPTION_AES)) - continue; + if (IS_AES(alg_flags) && !IS_HMAC(alg_flags)) { + if (supported_algo_flags & EIP93_PE_OPTION_AES_KEY128) + eip93_algs[i]->alg.skcipher.max_keysize = + AES_KEYSIZE_128; - if (!IS_HMAC(alg_flags)) { - if (supported_algo_flags & EIP93_PE_OPTION_AES_KEY128) - eip93_algs[i]->alg.skcipher.max_keysize = - AES_KEYSIZE_128; + if (supported_algo_flags & EIP93_PE_OPTION_AES_KEY192) + eip93_algs[i]->alg.skcipher.max_keysize = + AES_KEYSIZE_192; - if (supported_algo_flags & EIP93_PE_OPTION_AES_KEY192) - eip93_algs[i]->alg.skcipher.max_keysize = - AES_KEYSIZE_192; + if (supported_algo_flags & EIP93_PE_OPTION_AES_KEY256) + eip93_algs[i]->alg.skcipher.max_keysize = + AES_KEYSIZE_256; - if (supported_algo_flags & EIP93_PE_OPTION_AES_KEY256) - eip93_algs[i]->alg.skcipher.max_keysize = - AES_KEYSIZE_256; - - if (IS_RFC3686(alg_flags)) - eip93_algs[i]->alg.skcipher.max_keysize += - CTR_RFC3686_NONCE_SIZE; - } + if (IS_RFC3686(alg_flags)) + eip93_algs[i]->alg.skcipher.max_keysize += + CTR_RFC3686_NONCE_SIZE; } - if (IS_HASH_MD5(alg_flags) && - !(supported_algo_flags & EIP93_PE_OPTION_MD5)) - continue; - - if (IS_HASH_SHA1(alg_flags) && - !(supported_algo_flags & EIP93_PE_OPTION_SHA_1)) - continue; - - if (IS_HASH_SHA224(alg_flags) && - !(supported_algo_flags & EIP93_PE_OPTION_SHA_224)) - continue; - - if (IS_HASH_SHA256(alg_flags) && - !(supported_algo_flags & EIP93_PE_OPTION_SHA_256)) - continue; - switch (eip93_algs[i]->type) { case EIP93_ALG_TYPE_SKCIPHER: ret = crypto_register_skcipher(&eip93_algs[i]->alg.skcipher); @@ -167,7 +178,7 @@ static int eip93_register_algs(struct eip93_device *eip93, u32 supported_algo_fl return 0; fail: - eip93_unregister_algs(i); + eip93_unregister_algs(supported_algo_flags, i); return ret; } @@ -469,8 +480,11 @@ static int eip93_crypto_probe(struct platform_device *pdev) static void eip93_crypto_remove(struct platform_device *pdev) { struct eip93_device *eip93 = platform_get_drvdata(pdev); + u32 algo_flags; + + algo_flags = readl(eip93->base + EIP93_REG_PE_OPTION_1); - eip93_unregister_algs(ARRAY_SIZE(eip93_algs)); + eip93_unregister_algs(algo_flags, ARRAY_SIZE(eip93_algs)); eip93_cleanup(eip93); } diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c index 23f585219fb4b2..da9b2bc515194f 100644 --- a/drivers/crypto/intel/iaa/iaa_crypto_main.c +++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c @@ -221,15 +221,13 @@ static struct iaa_compression_mode *iaa_compression_modes[IAA_COMP_MODES_MAX]; static int find_empty_iaa_compression_mode(void) { - int i = -EINVAL; + int i; - for (i = 0; i < IAA_COMP_MODES_MAX; i++) { - if (iaa_compression_modes[i]) - continue; - break; - } + for (i = 0; i < IAA_COMP_MODES_MAX; i++) + if (!iaa_compression_modes[i]) + return i; - return i; + return -EINVAL; } static struct iaa_compression_mode *find_iaa_compression_mode(const char *name, int *idx) @@ -805,7 +803,7 @@ static int save_iaa_wq(struct idxd_wq *wq) if (!cpus_per_iaa) cpus_per_iaa = 1; out: - return 0; + return ret; } static void remove_iaa_wq(struct idxd_wq *wq) diff --git a/drivers/crypto/intel/qat/qat_common/adf_aer.c b/drivers/crypto/intel/qat/qat_common/adf_aer.c index 35679b21ff63bb..f63e78724c7a73 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_aer.c +++ b/drivers/crypto/intel/qat/qat_common/adf_aer.c @@ -41,8 +41,6 @@ static pci_ers_result_t adf_error_detected(struct pci_dev *pdev, adf_error_notifier(accel_dev); adf_pf2vf_notify_fatal_error(accel_dev); adf_dev_restarting_notify(accel_dev); - adf_pf2vf_notify_restarting(accel_dev); - adf_pf2vf_wait_for_restarting_complete(accel_dev); pci_clear_master(pdev); adf_dev_down(accel_dev); @@ -105,7 +103,6 @@ void adf_dev_restore(struct adf_accel_dev *accel_dev) accel_dev->accel_id); hw_device->reset_device(accel_dev); pci_restore_state(pdev); - pci_save_state(pdev); } } @@ -204,7 +201,6 @@ static pci_ers_result_t adf_slot_reset(struct pci_dev *pdev) if (!pdev->is_busmaster) pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); res = adf_dev_up(accel_dev, false); if (res && res != -EALREADY) return PCI_ERS_RESULT_DISCONNECT; diff --git a/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_proto.c b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_proto.c index b9b5e744a3f163..af8dbc7517cf82 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_proto.c +++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_proto.c @@ -148,6 +148,16 @@ static struct pfvf_message handle_blkmsg_req(struct adf_accel_vf_info *vf_info, blk_byte = FIELD_GET(ADF_VF2PF_SMALL_BLOCK_BYTE_MASK, req.data); byte_max = ADF_VF2PF_SMALL_BLOCK_BYTE_MAX; break; + default: + dev_err(&GET_DEV(vf_info->accel_dev), + "Invalid BlockMsg type 0x%.4x received from VF%u\n", + req.type, vf_info->vf_nr); + resp.type = ADF_PF2VF_MSGTYPE_BLKMSG_RESP; + resp.data = FIELD_PREP(ADF_PF2VF_BLKMSG_RESP_TYPE_MASK, + ADF_PF2VF_BLKMSG_RESP_TYPE_ERROR) | + FIELD_PREP(ADF_PF2VF_BLKMSG_RESP_DATA_MASK, + ADF_PF2VF_UNSPECIFIED_ERROR); + return resp; } /* Is this a request for CRC or data? */ diff --git a/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c b/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c index 9f5601c0280bf1..417a48f4135053 100644 --- a/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c +++ b/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c @@ -1326,7 +1326,7 @@ static ssize_t ucode_load_store(struct device *dev, int del_grp_idx = -1; int ucode_idx = 0; - if (strlen(buf) > OTX_CPT_UCODE_NAME_LENGTH) + if (count >= OTX_CPT_UCODE_NAME_LENGTH) return -EINVAL; eng_grps = container_of(attr, struct otx_cpt_eng_grps, ucode_load_attr); diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_main.c b/drivers/crypto/marvell/octeontx/otx_cptvf_main.c index 88a41d1ca5f644..6c0bfb3ea1c9f2 100644 --- a/drivers/crypto/marvell/octeontx/otx_cptvf_main.c +++ b/drivers/crypto/marvell/octeontx/otx_cptvf_main.c @@ -168,7 +168,8 @@ static void free_command_queues(struct otx_cptvf *cptvf, chunk = list_first_entry(&cqinfo->queue[i].chead, struct otx_cpt_cmd_chunk, nextchunk); - dma_free_coherent(&pdev->dev, chunk->size, + dma_free_coherent(&pdev->dev, + chunk->size + OTX_CPT_NEXT_CHUNK_PTR_SIZE, chunk->head, chunk->dma_addr); chunk->head = NULL; diff --git a/drivers/crypto/omap-crypto.c b/drivers/crypto/omap-crypto.c index a4cc6bf146ec09..0345c9383d5097 100644 --- a/drivers/crypto/omap-crypto.c +++ b/drivers/crypto/omap-crypto.c @@ -21,7 +21,7 @@ static int omap_crypto_copy_sg_lists(int total, int bs, struct scatterlist *tmp; if (!(flags & OMAP_CRYPTO_FORCE_SINGLE_ENTRY)) { - new_sg = kmalloc_array(n, sizeof(*sg), GFP_KERNEL); + new_sg = kmalloc_array(n, sizeof(*new_sg), GFP_KERNEL); if (!new_sg) return -ENOMEM; diff --git a/drivers/crypto/starfive/jh7110-aes.c b/drivers/crypto/starfive/jh7110-aes.c index 426b24889af853..01195664cc7cd9 100644 --- a/drivers/crypto/starfive/jh7110-aes.c +++ b/drivers/crypto/starfive/jh7110-aes.c @@ -669,8 +669,10 @@ static int starfive_aes_aead_do_one_req(struct crypto_engine *engine, void *areq return -ENOMEM; if (sg_copy_to_buffer(req->src, sg_nents_for_len(req->src, cryp->assoclen), - rctx->adata, cryp->assoclen) != cryp->assoclen) + rctx->adata, cryp->assoclen) != cryp->assoclen) { + kfree(rctx->adata); return -EINVAL; + } } if (cryp->total_in) @@ -681,8 +683,11 @@ static int starfive_aes_aead_do_one_req(struct crypto_engine *engine, void *areq ctx->rctx = rctx; ret = starfive_aes_hw_init(ctx); - if (ret) + if (ret) { + if (cryp->assoclen) + kfree(rctx->adata); return ret; + } if (!cryp->assoclen) goto write_text; diff --git a/drivers/crypto/starfive/jh7110-hash.c b/drivers/crypto/starfive/jh7110-hash.c index e6839c7bfb73ac..54b7af4a7aee82 100644 --- a/drivers/crypto/starfive/jh7110-hash.c +++ b/drivers/crypto/starfive/jh7110-hash.c @@ -325,6 +325,7 @@ static int starfive_hash_digest(struct ahash_request *req) struct starfive_cryp_ctx *ctx = crypto_ahash_ctx(tfm); struct starfive_cryp_request_ctx *rctx = ahash_request_ctx(req); struct starfive_cryp_dev *cryp = ctx->cryp; + int sg_len; memset(rctx, 0, sizeof(struct starfive_cryp_request_ctx)); @@ -333,7 +334,10 @@ static int starfive_hash_digest(struct ahash_request *req) rctx->in_sg = req->src; rctx->blksize = crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm)); rctx->digsize = crypto_ahash_digestsize(tfm); - rctx->in_sg_len = sg_nents_for_len(rctx->in_sg, rctx->total); + sg_len = sg_nents_for_len(rctx->in_sg, rctx->total); + if (sg_len < 0) + return sg_len; + rctx->in_sg_len = sg_len; ctx->rctx = rctx; return crypto_transfer_hash_request_to_engine(cryp->engine, req); diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c index 3d241446099cc9..ccc6b5c1b24b37 100644 --- a/drivers/crypto/virtio/virtio_crypto_core.c +++ b/drivers/crypto/virtio/virtio_crypto_core.c @@ -75,15 +75,20 @@ static void virtcrypto_done_task(unsigned long data) struct data_queue *data_vq = (struct data_queue *)data; struct virtqueue *vq = data_vq->vq; struct virtio_crypto_request *vc_req; + unsigned long flags; unsigned int len; + spin_lock_irqsave(&data_vq->lock, flags); do { virtqueue_disable_cb(vq); while ((vc_req = virtqueue_get_buf(vq, &len)) != NULL) { + spin_unlock_irqrestore(&data_vq->lock, flags); if (vc_req->alg_cb) vc_req->alg_cb(vc_req, len); + spin_lock_irqsave(&data_vq->lock, flags); } } while (!virtqueue_enable_cb(vq)); + spin_unlock_irqrestore(&data_vq->lock, flags); } static void virtcrypto_dataq_callback(struct virtqueue *vq) diff --git a/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c index 1b3fb21a2a7de2..11053d1786d4d2 100644 --- a/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c @@ -541,8 +541,6 @@ int virtio_crypto_skcipher_crypt_req( if (ret < 0) return ret; - virtqueue_kick(data_vq->vq); - return 0; } diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c index 79994ca9bc9f37..81160260e26b7e 100644 --- a/drivers/cxl/core/edac.c +++ b/drivers/cxl/core/edac.c @@ -1988,6 +1988,40 @@ static int cxl_memdev_soft_ppr_init(struct cxl_memdev *cxlmd, return 0; } +static void err_rec_free(void *_cxlmd) +{ + struct cxl_memdev *cxlmd = _cxlmd; + struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array; + struct cxl_event_gen_media *rec_gen_media; + struct cxl_event_dram *rec_dram; + unsigned long index; + + cxlmd->err_rec_array = NULL; + xa_for_each(&array_rec->rec_dram, index, rec_dram) + kfree(rec_dram); + xa_destroy(&array_rec->rec_dram); + + xa_for_each(&array_rec->rec_gen_media, index, rec_gen_media) + kfree(rec_gen_media); + xa_destroy(&array_rec->rec_gen_media); + kfree(array_rec); +} + +static int devm_cxl_memdev_setup_err_rec(struct cxl_memdev *cxlmd) +{ + struct cxl_mem_err_rec *array_rec = + kzalloc(sizeof(*array_rec), GFP_KERNEL); + + if (!array_rec) + return -ENOMEM; + + xa_init(&array_rec->rec_gen_media); + xa_init(&array_rec->rec_dram); + cxlmd->err_rec_array = array_rec; + + return devm_add_action_or_reset(&cxlmd->dev, err_rec_free, cxlmd); +} + int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd) { struct edac_dev_feature ras_features[CXL_NR_EDAC_DEV_FEATURES]; @@ -2038,15 +2072,9 @@ int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd) } if (repair_inst) { - struct cxl_mem_err_rec *array_rec = - devm_kzalloc(&cxlmd->dev, sizeof(*array_rec), - GFP_KERNEL); - if (!array_rec) - return -ENOMEM; - - xa_init(&array_rec->rec_gen_media); - xa_init(&array_rec->rec_dram); - cxlmd->err_rec_array = array_rec; + rc = devm_cxl_memdev_setup_err_rec(cxlmd); + if (rc) + return rc; } } @@ -2088,22 +2116,4 @@ int devm_cxl_region_edac_register(struct cxl_region *cxlr) } EXPORT_SYMBOL_NS_GPL(devm_cxl_region_edac_register, "CXL"); -void devm_cxl_memdev_edac_release(struct cxl_memdev *cxlmd) -{ - struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array; - struct cxl_event_gen_media *rec_gen_media; - struct cxl_event_dram *rec_dram; - unsigned long index; - - if (!IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR) || !array_rec) - return; - - xa_for_each(&array_rec->rec_dram, index, rec_dram) - kfree(rec_dram); - xa_destroy(&array_rec->rec_dram); - xa_for_each(&array_rec->rec_gen_media, index, rec_gen_media) - kfree(rec_gen_media); - xa_destroy(&array_rec->rec_gen_media); -} -EXPORT_SYMBOL_NS_GPL(devm_cxl_memdev_edac_release, "CXL"); diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index d3a094ca01ad9e..13dafac7c6d56d 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -403,7 +403,7 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, * is not set. */ if (cxled->part < 0) - for (int i = 0; cxlds->nr_partitions; i++) + for (int i = 0; i < cxlds->nr_partitions; i++) if (resource_contains(&cxlds->part[i].res, res)) { cxled->part = i; break; @@ -844,14 +844,13 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld) scoped_guard(rwsem_read, &cxl_rwsem.dpa) setup_hw_decoder(cxld, hdm); - port->commit_end++; rc = cxld_await_commit(hdm, cxld->id); if (rc) { dev_dbg(&port->dev, "%s: error %d committing decoder\n", dev_name(&cxld->dev), rc); - cxld->reset(cxld); return rc; } + port->commit_end++; cxld->flags |= CXL_DECODER_F_ENABLE; return 0; diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index e370d733e44001..4dff7f44d908e0 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -27,7 +27,6 @@ static void cxl_memdev_release(struct device *dev) struct cxl_memdev *cxlmd = to_cxl_memdev(dev); ida_free(&cxl_memdev_ida, cxlmd->id); - devm_cxl_memdev_edac_release(cxlmd); kfree(cxlmd); } diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 8128fd2b5b317f..85131872d7f6e0 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -823,16 +823,18 @@ DEFINE_DEBUGFS_ATTRIBUTE(cxl_einj_inject_fops, NULL, cxl_einj_inject, static void cxl_debugfs_create_dport_dir(struct cxl_dport *dport) { + struct cxl_port *parent = parent_port_of(dport->port); struct dentry *dir; if (!einj_cxl_is_initialized()) return; /* - * dport_dev needs to be a PCIe port for CXL 2.0+ ports because - * EINJ expects a dport SBDF to be specified for 2.0 error injection. + * Protocol error injection is only available for CXL 2.0+ root ports + * and CXL 1.1 downstream ports */ - if (!dport->rch && !dev_is_pci(dport->dport_dev)) + if (!dport->rch && + !(dev_is_pci(dport->dport_dev) && parent && is_cxl_root(parent))) return; dir = cxl_debugfs_create_dir(dev_name(dport->dport_dev)); @@ -1591,7 +1593,7 @@ static int update_decoder_targets(struct device *dev, void *data) cxlsd->target[i] = dport; dev_dbg(dev, "dport%d found in target list, index %d\n", dport->port_id, i); - return 1; + return 0; } } diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 434031a0c1f74a..c12ab4fc951238 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -63,7 +63,7 @@ struct cxl_memdev { int depth; u8 scrub_cycle; int scrub_region_id; - void *err_rec_array; + struct cxl_mem_err_rec *err_rec_array; }; static inline struct cxl_memdev *to_cxl_memdev(struct device *dev) @@ -877,7 +877,6 @@ int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd); int devm_cxl_region_edac_register(struct cxl_region *cxlr); int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt); int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt); -void devm_cxl_memdev_edac_release(struct cxl_memdev *cxlmd); #else static inline int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd) { return 0; } @@ -889,8 +888,6 @@ static inline int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, static inline int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt) { return 0; } -static inline void devm_cxl_memdev_edac_release(struct cxl_memdev *cxlmd) -{ return; } #endif #ifdef CONFIG_CXL_SUSPEND diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h index 0867115aeef2e1..c6ae27c982f439 100644 --- a/drivers/dax/dax-private.h +++ b/drivers/dax/dax-private.h @@ -67,14 +67,16 @@ struct dev_dax_range { /** * struct dev_dax - instance data for a subdivision of a dax region, and * data while the device is activated in the driver. - * @region - parent region - * @dax_dev - core dax functionality + * @region: parent region + * @dax_dev: core dax functionality + * @align: alignment of this instance * @target_node: effective numa node if dev_dax memory range is onlined * @dyn_id: is this a dynamic or statically created instance * @id: ida allocated id when the dax_region is not static * @ida: mapping id allocator - * @dev - device core - * @pgmap - pgmap for memmap setup / lifetime (driver owned) + * @dev: device core + * @pgmap: pgmap for memmap setup / lifetime (driver owned) + * @memmap_on_memory: allow kmem to put the memmap in the memory * @nr_range: size of @ranges * @ranges: range tuples of memory used */ diff --git a/drivers/devfreq/hisi_uncore_freq.c b/drivers/devfreq/hisi_uncore_freq.c index 96d1815059e32c..c1ed70fa0a4004 100644 --- a/drivers/devfreq/hisi_uncore_freq.c +++ b/drivers/devfreq/hisi_uncore_freq.c @@ -265,10 +265,11 @@ static int hisi_uncore_target(struct device *dev, unsigned long *freq, dev_err(dev, "Failed to get opp for freq %lu hz\n", *freq); return PTR_ERR(opp); } - dev_pm_opp_put(opp); data = (u32)(dev_pm_opp_get_freq(opp) / HZ_PER_MHZ); + dev_pm_opp_put(opp); + return hisi_uncore_cmd_send(uncore, HUCF_PCC_CMD_SET_FREQ, &data); } diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index b8a74b1798ba1d..3c96c57d02634a 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -89,9 +89,20 @@ config APPLE_ADMAC tristate "Apple ADMAC support" depends on ARCH_APPLE || COMPILE_TEST select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS help Enable support for Audio DMA Controller found on Apple Silicon SoCs. +config APPLE_SIO + tristate "Apple SIO support" + depends on ARCH_APPLE || COMPILE_TEST + depends on APPLE_RTKIT + depends on OF_ADDRESS + select DMA_ENGINE + help + Enable support for the SIO coprocessor found on Apple Silicon SoCs + where it provides DMA services. + config ARM_DMA350 tristate "Arm DMA-350 support" depends on ARM || ARM64 || COMPILE_TEST diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index a54d7688392b1a..1c11fdc02692cc 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_ALTERA_MSGDMA) += altera-msgdma.o obj-$(CONFIG_AMBA_PL08X) += amba-pl08x.o obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/ obj-$(CONFIG_APPLE_ADMAC) += apple-admac.o +obj-$(CONFIG_APPLE_SIO) += apple-sio.o obj-$(CONFIG_ARM_DMA350) += arm-dma350.o obj-$(CONFIG_AT_HDMAC) += at_hdmac.o obj-$(CONFIG_AT_XDMAC) += at_xdmac.o diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c index bd49f037429121..04bbd774b3b444 100644 --- a/drivers/dma/apple-admac.c +++ b/drivers/dma/apple-admac.c @@ -936,6 +936,7 @@ static void admac_remove(struct platform_device *pdev) } static const struct of_device_id admac_of_match[] = { + { .compatible = "apple,t8103-admac", }, { .compatible = "apple,admac", }, { } }; diff --git a/drivers/dma/apple-sio.c b/drivers/dma/apple-sio.c new file mode 100644 index 00000000000000..511f91999ed3de --- /dev/null +++ b/drivers/dma/apple-sio.c @@ -0,0 +1,942 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Driver for SIO coprocessor on t8103 (M1) and other Apple SoCs + * + * Copyright (C) The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "dmaengine.h" +#include "virt-dma.h" + +#define NCHANNELS_MAX 0x80 + +#define REG_CPU_CONTROL 0x44 +#define CPU_CONTROL_RUN BIT(4) + +#define SIOMSG_DATA GENMASK(63, 32) +#define SIOMSG_TYPE GENMASK(23, 16) +#define SIOMSG_PARAM GENMASK(31, 24) +#define SIOMSG_TAG GENMASK(13, 8) +#define SIOMSG_EP GENMASK(7, 0) + +#define EP_SIO 0x20 + +#define MSG_START 0x2 +#define MSG_SETUP 0x3 +#define MSG_CONFIGURE 0x5 +#define MSG_ISSUE 0x6 +#define MSG_TERMINATE 0x8 +#define MSG_ACK 0x65 +#define MSG_NACK 0x66 +#define MSG_STARTED 0x67 +#define MSG_REPORT 0x68 + +#define SIO_CALL_TIMEOUT_MS 100 +#define SIO_SHMEM_SIZE 0x1000 +#define SIO_NO_DESC_SLOTS 64 + +/* + * There are two kinds of 'transaction descriptors' in play here. + * + * There's the struct sio_tx, and the struct dma_async_tx_descriptor embedded + * inside, which jointly represent a transaction to the dmaengine subsystem. + * At this time we only support those transactions to be cyclic. + * + * Then there are the coprocessor descriptors, which is what the coprocessor + * knows and understands. These don't seem to have a cyclic regime, so we can't + * map the dmaengine transaction on an exact coprocessor counterpart. Instead + * we continually queue up many coprocessor descriptors to implement a cyclic + * transaction. + * + * The number below is the maximum of how far ahead (how many) coprocessor + * descriptors we should be queuing up, per channel, for a cyclic transaction. + * Basically it's a made-up number. + */ +#define SIO_MAX_NINFLIGHT 4 + +struct sio_coproc_desc { + u32 pad1; + u32 flag; + u64 unk; + u64 iova; + u64 size; + u64 pad2; + u64 pad3; +} __packed; +static_assert(sizeof(struct sio_coproc_desc) == 48); + +struct sio_shmem_chan_config { + u32 datashape; + u32 timeout; + u32 fifo; + u32 threshold; + u32 limit; +} __packed; + +struct sio_data; +struct sio_tx; + +struct sio_chan { + unsigned int no; + struct sio_data *host; + struct virt_dma_chan vc; + struct work_struct terminate_wq; + + bool configured; + struct sio_shmem_chan_config cfg; + + struct sio_tx *current_tx; +}; + +#define SIO_NTAGS 16 + +typedef void (*sio_ack_callback)(struct sio_chan *, void *, bool); + +struct sio_data { + void __iomem *base; + struct dma_device dma; + struct device *dev; + struct apple_rtkit *rtk; + void *shmem; + struct sio_coproc_desc *shmem_desc_base; + unsigned long *desc_allocated; + + struct sio_tagdata { + DECLARE_BITMAP(allocated, SIO_NTAGS); + int last_tag; + + struct completion completions[SIO_NTAGS]; + bool atomic[SIO_NTAGS]; + bool acked[SIO_NTAGS]; + + sio_ack_callback ack_callback[SIO_NTAGS]; + void *cookie[SIO_NTAGS]; + } tags; + + int nchannels; + struct sio_chan channels[]; +}; + +struct sio_tx { + struct virt_dma_desc vd; + struct completion done; + + bool terminated; + size_t period_len; + int nperiods; + int ninflight; + int next; + + struct sio_coproc_desc *siodesc[]; +}; + +static int sio_send_siomsg(struct sio_data *sio, u64 msg); +static int sio_send_siomsg_atomic(struct sio_data *sio, u64 msg, + sio_ack_callback ack_callback, + void *cookie); +static int sio_call(struct sio_data *sio, u64 msg); + +static struct sio_chan *to_sio_chan(struct dma_chan *chan) +{ + return container_of(chan, struct sio_chan, vc.chan); +} + +static struct sio_tx *to_sio_tx(struct dma_async_tx_descriptor *tx) +{ + return container_of(tx, struct sio_tx, vd.tx); +} + +static int sio_alloc_tag(struct sio_data *sio) +{ + struct sio_tagdata *tags = &sio->tags; + int tag, i; + + /* + * Because tag number 0 is special, the usable tag range + * is 1...(SIO_NTAGS - 1). So, to pick the next usable tag, + * we do modulo (SIO_NTAGS - 1) *then* plus one. + */ + +#define SIO_USABLE_TAGS (SIO_NTAGS - 1) + tag = (READ_ONCE(tags->last_tag) % SIO_USABLE_TAGS) + 1; + + for (i = 0; i < SIO_USABLE_TAGS; i++) { + if (!test_and_set_bit(tag, tags->allocated)) + break; + + tag = (tag % SIO_USABLE_TAGS) + 1; + } + + WRITE_ONCE(tags->last_tag, tag); + + if (i < SIO_USABLE_TAGS) + return tag; + else + return -EBUSY; +#undef SIO_USABLE_TAGS +} + +static void sio_free_tag(struct sio_data *sio, int tag) +{ + struct sio_tagdata *tags = &sio->tags; + + if (WARN_ON(tag >= SIO_NTAGS)) + return; + + tags->atomic[tag] = false; + tags->ack_callback[tag] = NULL; + + WARN_ON(!test_and_clear_bit(tag, tags->allocated)); +} + +static void sio_set_tag_atomic(struct sio_data *sio, int tag, + sio_ack_callback ack_callback, + void *cookie) +{ + struct sio_tagdata *tags = &sio->tags; + + tags->atomic[tag] = true; + tags->ack_callback[tag] = ack_callback; + tags->cookie[tag] = cookie; +} + +static struct sio_coproc_desc *sio_alloc_desc(struct sio_data *sio) +{ + int i; + + for (i = 0; i < SIO_NO_DESC_SLOTS; i++) + if (!test_and_set_bit(i, sio->desc_allocated)) + return sio->shmem_desc_base + i; + + return NULL; +} + +static void sio_free_desc(struct sio_data *sio, struct sio_coproc_desc *desc) +{ + clear_bit(desc - sio->shmem_desc_base, sio->desc_allocated); +} + +static int sio_coproc_desc_slot(struct sio_data *sio, struct sio_coproc_desc *desc) +{ + return (desc - sio->shmem_desc_base) * 4; +} + +static enum dma_transfer_direction sio_chan_direction(int channo) +{ + /* Channel directions are fixed based on channel number */ + return (channo & 1) ? DMA_DEV_TO_MEM : DMA_MEM_TO_DEV; +} + +static void sio_tx_free(struct virt_dma_desc *vd) +{ + struct sio_data *sio = to_sio_chan(vd->tx.chan)->host; + struct sio_tx *siotx = to_sio_tx(&vd->tx); + int i; + + for (i = 0; i < siotx->nperiods; i++) + if (siotx->siodesc[i]) + sio_free_desc(sio, siotx->siodesc[i]); + kfree(siotx); +} + +static struct dma_async_tx_descriptor *sio_prep_dma_cyclic( + struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len, + size_t period_len, enum dma_transfer_direction direction, + unsigned long flags) +{ + struct sio_chan *siochan = to_sio_chan(chan); + struct sio_tx *siotx = NULL; + int i, nperiods = buf_len / period_len; + + if (direction != sio_chan_direction(siochan->no)) + return NULL; + + siotx = kzalloc(struct_size(siotx, siodesc, nperiods), GFP_NOWAIT); + if (!siotx) + return NULL; + + init_completion(&siotx->done); + siotx->period_len = period_len; + siotx->nperiods = nperiods; + + for (i = 0; i < nperiods; i++) { + struct sio_coproc_desc *d; + + siotx->siodesc[i] = d = sio_alloc_desc(siochan->host); + if (!d) { + siotx->vd.tx.chan = &siochan->vc.chan; + sio_tx_free(&siotx->vd); + return NULL; + } + + d->flag = 1; /* not sure what's up with this */ + d->iova = buf_addr + period_len * i; + d->size = period_len; + } + dma_wmb(); + + return vchan_tx_prep(&siochan->vc, &siotx->vd, flags); +} + +static enum dma_status sio_tx_status(struct dma_chan *chan, dma_cookie_t cookie, + struct dma_tx_state *txstate) +{ + struct sio_chan *siochan = to_sio_chan(chan); + struct virt_dma_desc *vd; + struct sio_tx *siotx; + enum dma_status ret; + unsigned long flags; + int periods_residue; + size_t residue; + + ret = dma_cookie_status(chan, cookie, txstate); + if (ret == DMA_COMPLETE || !txstate) + return ret; + + spin_lock_irqsave(&siochan->vc.lock, flags); + siotx = siochan->current_tx; + + if (siotx && siotx->vd.tx.cookie == cookie) { + ret = DMA_IN_PROGRESS; + periods_residue = siotx->next - siotx->ninflight; + while (periods_residue < 0) + periods_residue += siotx->nperiods; + residue = (siotx->nperiods - periods_residue) * siotx->period_len; + } else { + ret = DMA_IN_PROGRESS; + residue = 0; + vd = vchan_find_desc(&siochan->vc, cookie); + if (vd) { + siotx = to_sio_tx(&vd->tx); + residue = siotx->period_len * siotx->nperiods; + } + } + spin_unlock_irqrestore(&siochan->vc.lock, flags); + dma_set_residue(txstate, residue); + + return ret; +} + +static bool sio_fill_in_locked(struct sio_chan *siochan); + +static void sio_handle_issue_ack(struct sio_chan *siochan, void *cookie, bool ok) +{ + dma_cookie_t tx_cookie = (unsigned long) cookie; + unsigned long flags; + struct sio_tx *tx; + + if (!ok) { + dev_err(siochan->host->dev, "nacked issue on chan %d\n", siochan->no); + return; + } + + spin_lock_irqsave(&siochan->vc.lock, flags); + if (!siochan->current_tx || tx_cookie != siochan->current_tx->vd.tx.cookie || + siochan->current_tx->terminated) + goto out; + + tx = siochan->current_tx; + tx->next = (tx->next + 1) % tx->nperiods; + tx->ninflight++; + sio_fill_in_locked(siochan); + +out: + spin_unlock_irqrestore(&siochan->vc.lock, flags); +} + +static bool sio_fill_in_locked(struct sio_chan *siochan) +{ + struct sio_data *sio = siochan->host; + struct sio_tx *tx = siochan->current_tx; + struct sio_coproc_desc *d = tx->siodesc[tx->next]; + int ret; + + if (tx->ninflight >= SIO_MAX_NINFLIGHT || tx->terminated) + return false; + + static_assert(sizeof(dma_cookie_t) <= sizeof(void *)); + ret = sio_send_siomsg_atomic(sio, FIELD_PREP(SIOMSG_EP, siochan->no) | + FIELD_PREP(SIOMSG_TYPE, MSG_ISSUE) | + FIELD_PREP(SIOMSG_DATA, sio_coproc_desc_slot(sio, d)), + sio_handle_issue_ack, (void *) (uintptr_t) tx->vd.tx.cookie); + if (ret < 0) + dev_err_ratelimited(sio->dev, "can't issue on chan %d ninflight %d: %d\n", + siochan->no, tx->ninflight, ret); + return true; +} + +static void sio_update_current_tx_locked(struct sio_chan *siochan) +{ + struct virt_dma_desc *vd = vchan_next_desc(&siochan->vc); + + if (vd && !siochan->current_tx) { + list_del(&vd->node); + siochan->current_tx = to_sio_tx(&vd->tx); + sio_fill_in_locked(siochan); + } +} + +static void sio_issue_pending(struct dma_chan *chan) +{ + struct sio_chan *siochan = to_sio_chan(chan); + unsigned long flags; + + spin_lock_irqsave(&siochan->vc.lock, flags); + vchan_issue_pending(&siochan->vc); + sio_update_current_tx_locked(siochan); + spin_unlock_irqrestore(&siochan->vc.lock, flags); +} + +static int sio_terminate_all(struct dma_chan *chan) +{ + struct sio_chan *siochan = to_sio_chan(chan); + unsigned long flags; + LIST_HEAD(to_free); + + spin_lock_irqsave(&siochan->vc.lock, flags); + if (siochan->current_tx && !siochan->current_tx->terminated) { + dma_cookie_complete(&siochan->current_tx->vd.tx); + siochan->current_tx->terminated = true; + schedule_work(&siochan->terminate_wq); + } + vchan_get_all_descriptors(&siochan->vc, &to_free); + spin_unlock_irqrestore(&siochan->vc.lock, flags); + + vchan_dma_desc_free_list(&siochan->vc, &to_free); + + return 0; +} + +static void sio_terminate_work(struct work_struct *wq) +{ + struct sio_chan *siochan = container_of(wq, struct sio_chan, terminate_wq); + struct sio_tx *tx; + unsigned long flags; + int ret; + + spin_lock_irqsave(&siochan->vc.lock, flags); + tx = siochan->current_tx; + spin_unlock_irqrestore(&siochan->vc.lock, flags); + + if (WARN_ON(!tx)) + return; + + ret = sio_call(siochan->host, FIELD_PREP(SIOMSG_EP, siochan->no) | + FIELD_PREP(SIOMSG_TYPE, MSG_TERMINATE)); + if (ret < 0) + dev_err(siochan->host->dev, "terminate call on chan %d failed: %d\n", + siochan->no, ret); + + ret = wait_for_completion_timeout(&tx->done, msecs_to_jiffies(500)); + if (!ret) + dev_err(siochan->host->dev, "terminate descriptor wait timed out\n"); + + tasklet_kill(&siochan->vc.task); + + spin_lock_irqsave(&siochan->vc.lock, flags); + WARN_ON(siochan->current_tx != tx); + siochan->current_tx = NULL; + sio_update_current_tx_locked(siochan); + spin_unlock_irqrestore(&siochan->vc.lock, flags); + + sio_tx_free(&tx->vd); +} + +static void sio_synchronize(struct dma_chan *chan) +{ + struct sio_chan *siochan = to_sio_chan(chan); + + flush_work(&siochan->terminate_wq); +} + +static void sio_free_chan_resources(struct dma_chan *chan) +{ + sio_terminate_all(chan); + sio_synchronize(chan); + vchan_free_chan_resources(&to_sio_chan(chan)->vc); +} + +static struct dma_chan *sio_dma_of_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct sio_data *sio = (struct sio_data *) ofdma->of_dma_data; + unsigned int index = dma_spec->args[0]; + + if (dma_spec->args_count != 1 || index >= sio->nchannels) + return ERR_PTR(-EINVAL); + + return dma_get_slave_channel(&sio->channels[index].vc.chan); +} + +static void sio_rtk_crashed(void *cookie, const void *crashlog, size_t crashlog_size) +{ + struct sio_data *sio = cookie; + + dev_err(sio->dev, "SIO down (crashed)"); +} + +static void sio_process_report(struct sio_chan *siochan) +{ + unsigned long flags; + + spin_lock_irqsave(&siochan->vc.lock, flags); + if (siochan->current_tx) { + struct sio_tx *tx = siochan->current_tx; + + if (tx->ninflight) + tx->ninflight--; + vchan_cyclic_callback(&tx->vd); + if (!sio_fill_in_locked(siochan) && !tx->ninflight) + complete(&tx->done); + } + spin_unlock_irqrestore(&siochan->vc.lock, flags); +} + +static void sio_recv_msg(void *cookie, u8 ep, u64 msg) +{ + struct sio_data *sio = cookie; + struct sio_tagdata *tags = &sio->tags; + u32 data; + u8 type, tag, sioep; + + if (ep != EP_SIO) + goto unknown; + + data = FIELD_GET(SIOMSG_DATA, msg); + // param = FIELD_GET(SIOMSG_PARAM, msg); + type = FIELD_GET(SIOMSG_TYPE, msg); + tag = FIELD_GET(SIOMSG_TAG, msg); + sioep = FIELD_GET(SIOMSG_EP, msg); + + switch (type) { + case MSG_STARTED: + dev_info(sio->dev, "SIO protocol v%u\n", data); + type = MSG_ACK; /* Pretend this is an ACK */ + fallthrough; + case MSG_ACK: + case MSG_NACK: + if (WARN_ON(tag >= SIO_NTAGS)) + break; + + if (tags->atomic[tag]) { + sio_ack_callback callback = tags->ack_callback[tag]; + + if (callback && !WARN_ON(sioep >= sio->nchannels)) + callback(&sio->channels[sioep], + tags->cookie[tag], type == MSG_ACK); + if (type == MSG_NACK) + dev_err(sio->dev, "got a NACK on channel %d\n", sioep); + sio_free_tag(sio, tag); + } else { + tags->acked[tag] = (type == MSG_ACK); + complete(&tags->completions[tag]); + } + break; + + case MSG_REPORT: + if (WARN_ON(sioep >= sio->nchannels)) + break; + + sio_process_report(&sio->channels[sioep]); + break; + + default: + goto unknown; + } + return; + +unknown: + dev_warn(sio->dev, "received unknown message: ep %x data %016llx\n", + ep, msg); +} + +static int _sio_send_siomsg(struct sio_data *sio, u64 msg, bool atomic, + sio_ack_callback ack_callback, void *cookie) +{ + int tag, ret; + + tag = sio_alloc_tag(sio); + if (tag < 0) + return tag; + + if (atomic) + sio_set_tag_atomic(sio, tag, ack_callback, cookie); + else + reinit_completion(&sio->tags.completions[tag]); + + msg &= ~SIOMSG_TAG; + msg |= FIELD_PREP(SIOMSG_TAG, tag); + ret = apple_rtkit_send_message(sio->rtk, EP_SIO, msg, NULL, + atomic); + if (ret < 0) { + sio_free_tag(sio, tag); + return ret; + } + + return tag; +} + +static int sio_send_siomsg(struct sio_data *sio, u64 msg) +{ + return _sio_send_siomsg(sio, msg, false, NULL, NULL); +} + +static int sio_send_siomsg_atomic(struct sio_data *sio, u64 msg, + sio_ack_callback ack_callback, + void *cookie) +{ + return _sio_send_siomsg(sio, msg, true, ack_callback, cookie); +} + +static int sio_call(struct sio_data *sio, u64 msg) +{ + int tag, ret; + + tag = sio_send_siomsg(sio, msg); + if (tag < 0) + return tag; + + ret = wait_for_completion_timeout(&sio->tags.completions[tag], + msecs_to_jiffies(SIO_CALL_TIMEOUT_MS)); + if (!ret) { + dev_warn(sio->dev, "call %8llx timed out\n", msg); + sio_free_tag(sio, tag); + return -ETIME; + } + + ret = sio->tags.acked[tag]; + sio_free_tag(sio, tag); + + return ret; +} + +static const struct apple_rtkit_ops sio_rtkit_ops = { + .crashed = sio_rtk_crashed, + .recv_message = sio_recv_msg, +}; + +static int sio_device_config(struct dma_chan *chan, + struct dma_slave_config *config) +{ + struct sio_chan *siochan = to_sio_chan(chan); + struct sio_data *sio = siochan->host; + bool is_tx = sio_chan_direction(siochan->no) == DMA_MEM_TO_DEV; + struct sio_shmem_chan_config *cfg_shmem = sio->shmem; + struct sio_shmem_chan_config cfg; + int ret; + + switch (is_tx ? config->dst_addr_width : config->src_addr_width) { + case DMA_SLAVE_BUSWIDTH_1_BYTE: + cfg.datashape = 0; + break; + case DMA_SLAVE_BUSWIDTH_2_BYTES: + cfg.datashape = 1; + break; + case DMA_SLAVE_BUSWIDTH_4_BYTES: + cfg.datashape = 2; + break; + default: + return -EINVAL; + } + + cfg.timeout = 0; + cfg.fifo = 0x800; + cfg.limit = 0x800; + cfg.threshold = 0x800; + + /* + * Dmaengine prescribes we ought to apply the new configuration only + * to newly-queued descriptors. + * + * To comply with dmaengine's interface we take the lazy path here: + * we apply the configuration right away, we only allow the channel + * to be configured once, which means subsequent calls to `device_config` + * either return -EBUSY if the configuration differs, or they are + * a no-op if the configuration is the same as the starting one. + * + * This is the reasonable thing to do given that these sio channels + * are tied to fixed peripherals, and what's more given that the + * only planned consumer of this dmaengine driver in the kernel is + * diplayport audio support, where the DMA configuration is fixed, + * and no more than a single descriptor (a cyclic one) gets ever issued + * at the same time. + * + * The code complexity cost of tracking to which descriptor + * the configuration relates would be significant here, especially + * since we need to do a non-atomic operation to apply it (a call to + * the coprocessor) and dmaengine has its bunch of atomicity + * restrictions. And this complexity would be for naught since it + * doesn't even get exercised by the only planned consumer. + */ + if (siochan->configured && memcmp(&siochan->cfg, &cfg, sizeof(cfg))) + return -EBUSY; + + *cfg_shmem = cfg; + dma_wmb(); + + ret = sio_call(sio, FIELD_PREP(SIOMSG_TYPE, MSG_CONFIGURE) | + FIELD_PREP(SIOMSG_EP, siochan->no)); + + if (ret == 1) + ret = 0; + else if (ret == 0) + ret = -EINVAL; + + if (ret == 0) { + siochan->configured = true; + siochan->cfg = cfg; + } + + return ret; +} + +static int sio_alloc_shmem(struct sio_data *sio) +{ + dma_addr_t iova; + int err; + + sio->shmem = dma_alloc_coherent(sio->dev, SIO_SHMEM_SIZE, + &iova, GFP_KERNEL | __GFP_ZERO); + if (!sio->shmem) + return -ENOMEM; + + sio->shmem_desc_base = (struct sio_coproc_desc *) (sio->shmem + 56); + sio->desc_allocated = devm_kzalloc(sio->dev, SIO_NO_DESC_SLOTS / 32, + GFP_KERNEL); + if (!sio->desc_allocated) + return -ENOMEM; + + err = sio_call(sio, FIELD_PREP(SIOMSG_TYPE, MSG_SETUP) | + FIELD_PREP(SIOMSG_PARAM, 1) | + FIELD_PREP(SIOMSG_DATA, iova >> 12)); + if (err != 1) { + if (err == 0) + err = -EINVAL; + return err; + } + + err = sio_call(sio, FIELD_PREP(SIOMSG_TYPE, MSG_SETUP) | + FIELD_PREP(SIOMSG_PARAM, 2) | + FIELD_PREP(SIOMSG_DATA, SIO_SHMEM_SIZE)); + if (err != 1) { + if (err == 0) + err = -EINVAL; + return err; + } + + return 0; +} + +static int sio_send_dt_params(struct sio_data *sio) +{ + struct device_node *np = sio->dev->of_node; + const char *propname = "apple,sio-firmware-params"; + int nparams, err, i; + + nparams = of_property_count_u32_elems(np, propname); + if (nparams < 0) { + err = nparams; + goto badprop; + } + + for (i = 0; i < nparams / 2; i++) { + u32 key, val; + + err = of_property_read_u32_index(np, propname, 2 * i, &key); + if (err) + goto badprop; + err = of_property_read_u32_index(np, propname, 2 * i + 1, &val); + if (err) + goto badprop; + + err = sio_call(sio, FIELD_PREP(SIOMSG_TYPE, MSG_SETUP) | + FIELD_PREP(SIOMSG_PARAM, key & 0xff) | + FIELD_PREP(SIOMSG_EP, key >> 8) | + FIELD_PREP(SIOMSG_DATA, val)); + if (err < 1) { + if (err == 0) + err = -ENXIO; + return dev_err_probe(sio->dev, err, "sending SIO parameter %#x value %#x\n", + key, val); + } + } + + return 0; + +badprop: + return dev_err_probe(sio->dev, err, "failed to read '%s'\n", propname); +} + +static int sio_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct sio_data *sio; + struct dma_device *dma; + int nchannels; + int err, i; + + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(42)); + if (err) + return dev_err_probe(&pdev->dev, err, "Failed to set DMA mask\n"); + + err = of_property_read_u32(np, "dma-channels", &nchannels); + if (err || nchannels > NCHANNELS_MAX) + return dev_err_probe(&pdev->dev, -EINVAL, + "missing or invalid dma-channels property\n"); + + sio = devm_kzalloc(&pdev->dev, struct_size(sio, channels, nchannels), GFP_KERNEL); + if (!sio) + return -ENOMEM; + + platform_set_drvdata(pdev, sio); + sio->dev = &pdev->dev; + sio->nchannels = nchannels; + + sio->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(sio->base)) + return PTR_ERR(sio->base); + + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + err = devm_pm_runtime_enable(&pdev->dev); + if (err < 0) + return dev_err_probe(&pdev->dev, err, + "pm_runtime_enable failed: %d\n", err); + + sio->rtk = devm_apple_rtkit_init(&pdev->dev, sio, NULL, 0, &sio_rtkit_ops); + if (IS_ERR(sio->rtk)) { + err = PTR_ERR(sio->rtk); + dev_err(&pdev->dev, "couldn't initialize rtkit\n"); + goto rpm_put; + } + for (i = 1; i < SIO_NTAGS; i++) + init_completion(&sio->tags.completions[i]); + + dma = &sio->dma; + dma_cap_set(DMA_PRIVATE, dma->cap_mask); + dma_cap_set(DMA_CYCLIC, dma->cap_mask); + + dma->dev = &pdev->dev; + dma->device_free_chan_resources = sio_free_chan_resources; + dma->device_tx_status = sio_tx_status; + dma->device_issue_pending = sio_issue_pending; + dma->device_terminate_all = sio_terminate_all; + dma->device_synchronize = sio_synchronize; + dma->device_prep_dma_cyclic = sio_prep_dma_cyclic; + dma->device_config = sio_device_config; + + dma->directions = BIT(DMA_MEM_TO_DEV); + dma->residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT; + dma->dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | + BIT(DMA_SLAVE_BUSWIDTH_4_BYTES); + + INIT_LIST_HEAD(&dma->channels); + for (i = 0; i < nchannels; i++) { + struct sio_chan *siochan = &sio->channels[i]; + + siochan->host = sio; + siochan->no = i; + siochan->vc.desc_free = sio_tx_free; + INIT_WORK(&siochan->terminate_wq, sio_terminate_work); + vchan_init(&siochan->vc, dma); + } + + writel(CPU_CONTROL_RUN, sio->base + REG_CPU_CONTROL); + + err = apple_rtkit_boot(sio->rtk); + if (err) + return dev_err_probe(&pdev->dev, err, "SIO did not boot\n"); + + err = apple_rtkit_start_ep(sio->rtk, EP_SIO); + if (err) + return dev_err_probe(&pdev->dev, err, "starting SIO endpoint\n"); + + err = sio_call(sio, FIELD_PREP(SIOMSG_TYPE, MSG_START)); + if (err < 1) { + if (err == 0) + err = -ENXIO; + return dev_err_probe(&pdev->dev, err, "starting SIO service\n"); + } + + err = sio_send_dt_params(sio); + if (err < 0) + return dev_err_probe(&pdev->dev, err, "failed to send boot-up parameters\n"); + + err = sio_alloc_shmem(sio); + if (err < 0) + return err; + + err = dma_async_device_register(&sio->dma); + if (err) + return dev_err_probe(&pdev->dev, err, "failed to register DMA device\n"); + + err = of_dma_controller_register(pdev->dev.of_node, sio_dma_of_xlate, sio); + if (err) { + dma_async_device_unregister(&sio->dma); + return dev_err_probe(&pdev->dev, err, "failed to register with OF\n"); + } + +rpm_put: + pm_runtime_put(&pdev->dev); + + return err; +} + +static void sio_remove(struct platform_device *pdev) +{ + struct sio_data *sio = platform_get_drvdata(pdev); + + of_dma_controller_free(pdev->dev.of_node); + dma_async_device_unregister(&sio->dma); +} + +static const struct of_device_id sio_of_match[] = { + { .compatible = "apple,sio", }, + { } +}; +MODULE_DEVICE_TABLE(of, sio_of_match); + +static __maybe_unused int sio_suspend(struct device *dev) +{ + /* + * TODO: SIO coproc sleep state + */ + return 0; +} + +static __maybe_unused int sio_resume(struct device *dev) +{ + return 0; +} + +static DEFINE_RUNTIME_DEV_PM_OPS(sio_pm_ops, sio_suspend, sio_resume, NULL); + +static struct platform_driver apple_sio_driver = { + .driver = { + .name = "apple-sio", + .of_match_table = sio_of_match, + .pm = pm_ptr(&sio_pm_ops), + }, + .probe = sio_probe, + .remove = sio_remove, +}; +module_platform_driver(apple_sio_driver); + +MODULE_AUTHOR("Martin Povišer "); +MODULE_DESCRIPTION("Driver for SIO coprocessor on Apple SoCs"); +MODULE_LICENSE("Dual MIT/GPL"); diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 2d147712cbc69b..dffe5becd6c3cd 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -1765,6 +1765,7 @@ static int atc_alloc_chan_resources(struct dma_chan *chan) static void atc_free_chan_resources(struct dma_chan *chan) { struct at_dma_chan *atchan = to_at_dma_chan(chan); + struct at_dma_slave *atslave; BUG_ON(atc_chan_is_enabled(atchan)); @@ -1774,8 +1775,12 @@ static void atc_free_chan_resources(struct dma_chan *chan) /* * Free atslave allocated in at_dma_xlate() */ - kfree(chan->private); - chan->private = NULL; + atslave = chan->private; + if (atslave) { + put_device(atslave->dma_dev); + kfree(atslave); + chan->private = NULL; + } dev_vdbg(chan2dev(chan), "free_chan_resources: done\n"); } diff --git a/drivers/dma/bcm-sba-raid.c b/drivers/dma/bcm-sba-raid.c index 7f0e76439ce58e..ed037fa883f6f9 100644 --- a/drivers/dma/bcm-sba-raid.c +++ b/drivers/dma/bcm-sba-raid.c @@ -1699,7 +1699,7 @@ static int sba_probe(struct platform_device *pdev) /* Prealloc channel resource */ ret = sba_prealloc_channel_resources(sba); if (ret) - goto fail_free_mchan; + goto fail_put_mbox; /* Check availability of debugfs */ if (!debugfs_initialized()) @@ -1729,6 +1729,8 @@ static int sba_probe(struct platform_device *pdev) fail_free_resources: debugfs_remove_recursive(sba->root); sba_freeup_channel_resources(sba); +fail_put_mbox: + put_device(sba->mbox_dev); fail_free_mchan: mbox_free_channel(sba->mchan); return ret; @@ -1744,6 +1746,8 @@ static void sba_remove(struct platform_device *pdev) sba_freeup_channel_resources(sba); + put_device(sba->mbox_dev); + mbox_free_channel(sba->mchan); } diff --git a/drivers/dma/cv1800b-dmamux.c b/drivers/dma/cv1800b-dmamux.c index e900d65956171f..f7a952fcbc7d76 100644 --- a/drivers/dma/cv1800b-dmamux.c +++ b/drivers/dma/cv1800b-dmamux.c @@ -102,11 +102,11 @@ static void *cv1800_dmamux_route_allocate(struct of_phandle_args *dma_spec, struct llist_node *node; unsigned long flags; unsigned int chid, devid, cpuid; - int ret; + int ret = -EINVAL; if (dma_spec->args_count != DMAMUX_NCELLS) { dev_err(&pdev->dev, "invalid number of dma mux args\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } devid = dma_spec->args[0]; @@ -115,18 +115,18 @@ static void *cv1800_dmamux_route_allocate(struct of_phandle_args *dma_spec, if (devid > MAX_DMA_MAPPING_ID) { dev_err(&pdev->dev, "invalid device id: %u\n", devid); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } if (cpuid > MAX_DMA_CPU_ID) { dev_err(&pdev->dev, "invalid cpu id: %u\n", cpuid); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", 0); if (!dma_spec->np) { dev_err(&pdev->dev, "can't get dma master\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } spin_lock_irqsave(&dmamux->lock, flags); @@ -136,8 +136,6 @@ static void *cv1800_dmamux_route_allocate(struct of_phandle_args *dma_spec, if (map->peripheral == devid && map->cpu == cpuid) goto found; } - - ret = -EINVAL; goto failed; } else { node = llist_del_first(&dmamux->free_maps); @@ -171,12 +169,17 @@ static void *cv1800_dmamux_route_allocate(struct of_phandle_args *dma_spec, dev_dbg(&pdev->dev, "register channel %u for req %u (cpu %u)\n", chid, devid, cpuid); + put_device(&pdev->dev); + return map; failed: spin_unlock_irqrestore(&dmamux->lock, flags); of_node_put(dma_spec->np); dev_err(&pdev->dev, "errno %d\n", ret); +err_put_pdev: + put_device(&pdev->dev); + return ERR_PTR(ret); } diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c index 5b06b0dc67ee12..0f25f6d8ae71fa 100644 --- a/drivers/dma/dma-axi-dmac.c +++ b/drivers/dma/dma-axi-dmac.c @@ -233,11 +233,9 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan) unsigned int flags = 0; unsigned int val; - if (!chan->hw_sg) { - val = axi_dmac_read(dmac, AXI_DMAC_REG_START_TRANSFER); - if (val) /* Queue is full, wait for the next SOT IRQ */ - return; - } + val = axi_dmac_read(dmac, AXI_DMAC_REG_START_TRANSFER); + if (val) /* Queue is full, wait for the next SOT IRQ */ + return; desc = chan->next_desc; @@ -247,6 +245,7 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan) return; list_move_tail(&vdesc->node, &chan->active_descs); desc = to_axi_dmac_desc(vdesc); + chan->next_desc = desc; } sg = &desc->sg[desc->num_submitted]; @@ -265,8 +264,6 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan) else chan->next_desc = NULL; flags |= AXI_DMAC_FLAG_LAST; - } else { - chan->next_desc = desc; } sg->hw->id = axi_dmac_read(dmac, AXI_DMAC_REG_TRANSFER_ID); diff --git a/drivers/dma/dw/rzn1-dmamux.c b/drivers/dma/dw/rzn1-dmamux.c index deadf135681b67..cbec277af4dd36 100644 --- a/drivers/dma/dw/rzn1-dmamux.c +++ b/drivers/dma/dw/rzn1-dmamux.c @@ -90,7 +90,7 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec, if (test_and_set_bit(map->req_idx, dmamux->used_chans)) { ret = -EBUSY; - goto free_map; + goto put_dma_spec_np; } mask = BIT(map->req_idx); @@ -103,6 +103,8 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec, clear_bitmap: clear_bit(map->req_idx, dmamux->used_chans); +put_dma_spec_np: + of_node_put(dma_spec->np); free_map: kfree(map); put_device: diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index 4976d7dde08090..11655dcc4d6c15 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -852,6 +852,7 @@ int fsl_edma_alloc_chan_resources(struct dma_chan *chan) free_irq(fsl_chan->txirq, fsl_chan); err_txirq: dma_pool_destroy(fsl_chan->tcd_pool); + clk_disable_unprepare(fsl_chan->clk); return ret; } diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index 97583c7d51a2e8..093185768ad8ef 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -915,7 +915,6 @@ static void fsl_edma_remove(struct platform_device *pdev) of_dma_controller_free(np); dma_async_device_unregister(&fsl_edma->dma_dev); fsl_edma_cleanup_vchan(&fsl_edma->dma_dev); - fsl_disable_clocks(fsl_edma, fsl_edma->drvdata->dmamuxs); } static int fsl_edma_suspend_late(struct device *dev) diff --git a/drivers/dma/idxd/compat.c b/drivers/dma/idxd/compat.c index eff9943f1a42e2..95b8ef95863386 100644 --- a/drivers/dma/idxd/compat.c +++ b/drivers/dma/idxd/compat.c @@ -20,11 +20,16 @@ static ssize_t unbind_store(struct device_driver *drv, const char *buf, size_t c int rc = -ENODEV; dev = bus_find_device_by_name(bus, NULL, buf); - if (dev && dev->driver) { + if (!dev) + return -ENODEV; + + if (dev->driver) { device_driver_detach(dev); rc = count; } + put_device(dev); + return rc; } static DRIVER_ATTR_IGNORE_LOCKDEP(unbind, 0200, NULL, unbind_store); @@ -38,9 +43,12 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf, size_t cou struct idxd_dev *idxd_dev; dev = bus_find_device_by_name(bus, NULL, buf); - if (!dev || dev->driver || drv != &dsa_drv.drv) + if (!dev) return -ENODEV; + if (dev->driver || drv != &dsa_drv.drv) + goto err_put_dev; + idxd_dev = confdev_to_idxd_dev(dev); if (is_idxd_dev(idxd_dev)) { alt_drv = driver_find("idxd", bus); @@ -53,13 +61,20 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf, size_t cou alt_drv = driver_find("user", bus); } if (!alt_drv) - return -ENODEV; + goto err_put_dev; rc = device_driver_attach(alt_drv, dev); if (rc < 0) - return rc; + goto err_put_dev; + + put_device(dev); return count; + +err_put_dev: + put_device(dev); + + return rc; } static DRIVER_ATTR_IGNORE_LOCKDEP(bind, 0200, NULL, bind_store); diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c index 02f68b32851121..227398673b731d 100644 --- a/drivers/dma/ioat/init.c +++ b/drivers/dma/ioat/init.c @@ -1286,7 +1286,6 @@ static pci_ers_result_t ioat_pcie_error_slot_reset(struct pci_dev *pdev) } else { pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); pci_wake_from_d3(pdev, false); } diff --git a/drivers/dma/lpc18xx-dmamux.c b/drivers/dma/lpc18xx-dmamux.c index 2b6436f4b19374..d3ff521951b835 100644 --- a/drivers/dma/lpc18xx-dmamux.c +++ b/drivers/dma/lpc18xx-dmamux.c @@ -57,30 +57,31 @@ static void *lpc18xx_dmamux_reserve(struct of_phandle_args *dma_spec, struct lpc18xx_dmamux_data *dmamux = platform_get_drvdata(pdev); unsigned long flags; unsigned mux; + int ret = -EINVAL; if (dma_spec->args_count != 3) { dev_err(&pdev->dev, "invalid number of dma mux args\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } mux = dma_spec->args[0]; if (mux >= dmamux->dma_master_requests) { dev_err(&pdev->dev, "invalid mux number: %d\n", dma_spec->args[0]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } if (dma_spec->args[1] > LPC18XX_DMAMUX_MAX_VAL) { dev_err(&pdev->dev, "invalid dma mux value: %d\n", dma_spec->args[1]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } /* The of_node_put() will be done in the core for the node */ dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", 0); if (!dma_spec->np) { dev_err(&pdev->dev, "can't get dma master\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } spin_lock_irqsave(&dmamux->lock, flags); @@ -89,7 +90,8 @@ static void *lpc18xx_dmamux_reserve(struct of_phandle_args *dma_spec, dev_err(&pdev->dev, "dma request %u busy with %u.%u\n", mux, mux, dmamux->muxes[mux].value); of_node_put(dma_spec->np); - return ERR_PTR(-EBUSY); + ret = -EBUSY; + goto err_put_pdev; } dmamux->muxes[mux].busy = true; @@ -106,7 +108,14 @@ static void *lpc18xx_dmamux_reserve(struct of_phandle_args *dma_spec, dev_dbg(&pdev->dev, "mapping dmamux %u.%u to dma request %u\n", mux, dmamux->muxes[mux].value, mux); + put_device(&pdev->dev); + return &dmamux->muxes[mux]; + +err_put_pdev: + put_device(&pdev->dev); + + return ERR_PTR(ret); } static int lpc18xx_dmamux_probe(struct platform_device *pdev) diff --git a/drivers/dma/lpc32xx-dmamux.c b/drivers/dma/lpc32xx-dmamux.c index 351d7e23e6156e..33be714740ddfb 100644 --- a/drivers/dma/lpc32xx-dmamux.c +++ b/drivers/dma/lpc32xx-dmamux.c @@ -95,11 +95,12 @@ static void *lpc32xx_dmamux_reserve(struct of_phandle_args *dma_spec, struct lpc32xx_dmamux_data *dmamux = platform_get_drvdata(pdev); unsigned long flags; struct lpc32xx_dmamux *mux = NULL; + int ret = -EINVAL; int i; if (dma_spec->args_count != 3) { dev_err(&pdev->dev, "invalid number of dma mux args\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } for (i = 0; i < ARRAY_SIZE(lpc32xx_muxes); i++) { @@ -111,20 +112,20 @@ static void *lpc32xx_dmamux_reserve(struct of_phandle_args *dma_spec, if (!mux) { dev_err(&pdev->dev, "invalid mux request number: %d\n", dma_spec->args[0]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } if (dma_spec->args[2] > 1) { dev_err(&pdev->dev, "invalid dma mux value: %d\n", dma_spec->args[1]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } /* The of_node_put() will be done in the core for the node */ dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", 0); if (!dma_spec->np) { dev_err(&pdev->dev, "can't get dma master\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } spin_lock_irqsave(&dmamux->lock, flags); @@ -133,7 +134,8 @@ static void *lpc32xx_dmamux_reserve(struct of_phandle_args *dma_spec, dev_err(dev, "dma request signal %d busy, routed to %s\n", mux->signal, mux->muxval ? mux->name_sel1 : mux->name_sel1); of_node_put(dma_spec->np); - return ERR_PTR(-EBUSY); + ret = -EBUSY; + goto err_put_pdev; } mux->busy = true; @@ -148,7 +150,14 @@ static void *lpc32xx_dmamux_reserve(struct of_phandle_args *dma_spec, dev_dbg(dev, "dma request signal %d routed to %s\n", mux->signal, mux->muxval ? mux->name_sel1 : mux->name_sel1); + put_device(&pdev->dev); + return mux; + +err_put_pdev: + put_device(&pdev->dev); + + return ERR_PTR(ret); } static int lpc32xx_dmamux_probe(struct platform_device *pdev) diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c index 08e15177427b94..96c18c815f1df6 100644 --- a/drivers/dma/mediatek/mtk-uart-apdma.c +++ b/drivers/dma/mediatek/mtk-uart-apdma.c @@ -41,7 +41,7 @@ #define VFF_STOP_CLR_B 0 #define VFF_EN_CLR_B 0 #define VFF_INT_EN_CLR_B 0 -#define VFF_4G_SUPPORT_CLR_B 0 +#define VFF_ADDR2_CLR_B 0 /* * interrupt trigger level for tx @@ -72,7 +72,7 @@ /* TX: the buffer size SW can write. RX: the buffer size HW can write. */ #define VFF_LEFT_SIZE 0x40 #define VFF_DEBUG_STATUS 0x50 -#define VFF_4G_SUPPORT 0x54 +#define VFF_ADDR2 0x54 struct mtk_uart_apdmadev { struct dma_device ddev; @@ -149,7 +149,7 @@ static void mtk_uart_apdma_start_tx(struct mtk_chan *c) mtk_uart_apdma_write(c, VFF_INT_FLAG, VFF_TX_INT_CLR_B); if (mtkd->support_33bits) - mtk_uart_apdma_write(c, VFF_4G_SUPPORT, VFF_4G_EN_B); + mtk_uart_apdma_write(c, VFF_ADDR2, upper_32_bits(d->addr)); } mtk_uart_apdma_write(c, VFF_EN, VFF_EN_B); @@ -192,7 +192,7 @@ static void mtk_uart_apdma_start_rx(struct mtk_chan *c) mtk_uart_apdma_write(c, VFF_INT_FLAG, VFF_RX_INT_CLR_B); if (mtkd->support_33bits) - mtk_uart_apdma_write(c, VFF_4G_SUPPORT, VFF_4G_EN_B); + mtk_uart_apdma_write(c, VFF_ADDR2, upper_32_bits(d->addr)); } mtk_uart_apdma_write(c, VFF_INT_EN, VFF_RX_INT_EN_B); @@ -298,7 +298,7 @@ static int mtk_uart_apdma_alloc_chan_resources(struct dma_chan *chan) } if (mtkd->support_33bits) - mtk_uart_apdma_write(c, VFF_4G_SUPPORT, VFF_4G_SUPPORT_CLR_B); + mtk_uart_apdma_write(c, VFF_ADDR2, VFF_ADDR2_CLR_B); err_pm: pm_runtime_put_noidle(mtkd->ddev.dev); diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c index d07229a748868b..d12e729ee12c56 100644 --- a/drivers/dma/mmp_pdma.c +++ b/drivers/dma/mmp_pdma.c @@ -152,8 +152,8 @@ struct mmp_pdma_phy { * * Controller Configuration: * @run_bits: Control bits in DCSR register for channel start/stop - * @dma_mask: DMA addressing capability of controller. 0 to use OF/platform - * settings, or explicit mask like DMA_BIT_MASK(32/64) + * @dma_width: DMA addressing width in bits (32 or 64). Determines the + * DMA mask capability of the controller hardware. */ struct mmp_pdma_ops { /* Hardware Register Operations */ @@ -173,7 +173,7 @@ struct mmp_pdma_ops { /* Controller Configuration */ u32 run_bits; - u64 dma_mask; + u32 dma_width; }; struct mmp_pdma_device { @@ -928,6 +928,7 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, { struct mmp_pdma_desc_sw *sw; struct mmp_pdma_device *pdev = to_mmp_pdma_dev(chan->chan.device); + unsigned long flags; u64 curr; u32 residue = 0; bool passed = false; @@ -945,6 +946,8 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, else curr = pdev->ops->read_src_addr(chan->phy); + spin_lock_irqsave(&chan->desc_lock, flags); + list_for_each_entry(sw, &chan->chain_running, node) { u64 start, end; u32 len; @@ -989,6 +992,7 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, continue; if (sw->async_tx.cookie == cookie) { + spin_unlock_irqrestore(&chan->desc_lock, flags); return residue; } else { residue = 0; @@ -996,6 +1000,8 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, } } + spin_unlock_irqrestore(&chan->desc_lock, flags); + /* We should only get here in case of cyclic transactions */ return residue; } @@ -1172,7 +1178,7 @@ static const struct mmp_pdma_ops marvell_pdma_v1_ops = { .get_desc_src_addr = get_desc_src_addr_32, .get_desc_dst_addr = get_desc_dst_addr_32, .run_bits = (DCSR_RUN), - .dma_mask = 0, /* let OF/platform set DMA mask */ + .dma_width = 32, }; static const struct mmp_pdma_ops spacemit_k1_pdma_ops = { @@ -1185,7 +1191,7 @@ static const struct mmp_pdma_ops spacemit_k1_pdma_ops = { .get_desc_src_addr = get_desc_src_addr_64, .get_desc_dst_addr = get_desc_dst_addr_64, .run_bits = (DCSR_RUN | DCSR_LPAEEN), - .dma_mask = DMA_BIT_MASK(64), /* force 64-bit DMA addr capability */ + .dma_width = 64, }; static const struct of_device_id mmp_pdma_dt_ids[] = { @@ -1314,13 +1320,9 @@ static int mmp_pdma_probe(struct platform_device *op) pdev->device.directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM); pdev->device.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR; - /* Set DMA mask based on ops->dma_mask, or OF/platform */ - if (pdev->ops->dma_mask) - dma_set_mask(pdev->dev, pdev->ops->dma_mask); - else if (pdev->dev->coherent_dma_mask) - dma_set_mask(pdev->dev, pdev->dev->coherent_dma_mask); - else - dma_set_mask(pdev->dev, DMA_BIT_MASK(64)); + /* Set DMA mask based on controller hardware capabilities */ + dma_set_mask_and_coherent(pdev->dev, + DMA_BIT_MASK(pdev->ops->dma_width)); ret = dma_async_device_register(&pdev->device); if (ret) { diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c index 8e87738086b25a..8908b7c7190074 100644 --- a/drivers/dma/qcom/gpi.c +++ b/drivers/dma/qcom/gpi.c @@ -1605,14 +1605,16 @@ static int gpi_peripheral_config(struct dma_chan *chan, struct dma_slave_config *config) { struct gchan *gchan = to_gchan(chan); + void *new_config; if (!config->peripheral_config) return -EINVAL; - gchan->config = krealloc(gchan->config, config->peripheral_size, GFP_NOWAIT); - if (!gchan->config) + new_config = krealloc(gchan->config, config->peripheral_size, GFP_NOWAIT); + if (!new_config) return -ENOMEM; + gchan->config = new_config; memcpy(gchan->config, config->peripheral_config, config->peripheral_size); return 0; diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c index 1f687b08d6b867..9e5f088355e226 100644 --- a/drivers/dma/sh/rz-dmac.c +++ b/drivers/dma/sh/rz-dmac.c @@ -557,11 +557,16 @@ rz_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, static int rz_dmac_terminate_all(struct dma_chan *chan) { struct rz_dmac_chan *channel = to_rz_dmac_chan(chan); + struct rz_lmdesc *lmdesc = channel->lmdesc.base; unsigned long flags; + unsigned int i; LIST_HEAD(head); rz_dmac_disable_hw(channel); spin_lock_irqsave(&channel->vc.lock, flags); + for (i = 0; i < DMAC_NR_LMDESC; i++) + lmdesc[i].header = 0; + list_splice_tail_init(&channel->ld_active, &channel->ld_free); list_splice_tail_init(&channel->ld_queue, &channel->ld_free); vchan_get_all_descriptors(&channel->vc, &head); @@ -854,6 +859,13 @@ static int rz_dmac_chan_probe(struct rz_dmac *dmac, return 0; } +static void rz_dmac_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int rz_dmac_parse_of_icu(struct device *dev, struct rz_dmac *dmac) { struct device_node *np = dev->of_node; @@ -876,6 +888,10 @@ static int rz_dmac_parse_of_icu(struct device *dev, struct rz_dmac *dmac) return -ENODEV; } + ret = devm_add_action_or_reset(dev, rz_dmac_put_device, &dmac->icu.pdev->dev); + if (ret) + return ret; + dmac_index = args.args[0]; if (dmac_index > RZV2H_MAX_DMAC_INDEX) { dev_err(dev, "DMAC index %u invalid.\n", dmac_index); @@ -1055,8 +1071,6 @@ static void rz_dmac_remove(struct platform_device *pdev) reset_control_assert(dmac->rstc); pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); - - platform_device_put(dmac->icu.pdev); } static const struct of_device_id of_rz_dmac_match[] = { diff --git a/drivers/dma/stm32/stm32-dmamux.c b/drivers/dma/stm32/stm32-dmamux.c index 8d77e2a7939a0d..2bd218dbabbb15 100644 --- a/drivers/dma/stm32/stm32-dmamux.c +++ b/drivers/dma/stm32/stm32-dmamux.c @@ -90,23 +90,25 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, struct stm32_dmamux_data *dmamux = platform_get_drvdata(pdev); struct stm32_dmamux *mux; u32 i, min, max; - int ret; + int ret = -EINVAL; unsigned long flags; if (dma_spec->args_count != 3) { dev_err(&pdev->dev, "invalid number of dma mux args\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } if (dma_spec->args[0] > dmamux->dmamux_requests) { dev_err(&pdev->dev, "invalid mux request number: %d\n", dma_spec->args[0]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } mux = kzalloc(sizeof(*mux), GFP_KERNEL); - if (!mux) - return ERR_PTR(-ENOMEM); + if (!mux) { + ret = -ENOMEM; + goto err_put_pdev; + } spin_lock_irqsave(&dmamux->lock, flags); mux->chan_id = find_first_zero_bit(dmamux->dma_inuse, @@ -133,7 +135,6 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", i - 1); if (!dma_spec->np) { dev_err(&pdev->dev, "can't get dma master\n"); - ret = -EINVAL; goto error; } @@ -142,7 +143,7 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) { spin_unlock_irqrestore(&dmamux->lock, flags); - goto error; + goto err_put_dma_spec_np; } spin_unlock_irqrestore(&dmamux->lock, flags); @@ -160,13 +161,20 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, dev_dbg(&pdev->dev, "Mapping DMAMUX(%u) to DMA%u(%u)\n", mux->request, mux->master, mux->chan_id); + put_device(&pdev->dev); + return mux; +err_put_dma_spec_np: + of_node_put(dma_spec->np); error: clear_bit(mux->chan_id, dmamux->dma_inuse); error_chan_id: kfree(mux); +err_put_pdev: + put_device(&pdev->dev); + return ERR_PTR(ret); } diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index fad896ff29a2d3..812f64569e6d88 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -429,10 +429,17 @@ static void tegra_adma_stop(struct tegra_adma_chan *tdc) return; } - kfree(tdc->desc); + vchan_terminate_vdesc(&tdc->desc->vd); tdc->desc = NULL; } +static void tegra_adma_synchronize(struct dma_chan *dc) +{ + struct tegra_adma_chan *tdc = to_tegra_adma_chan(dc); + + vchan_synchronize(&tdc->vc); +} + static void tegra_adma_start(struct tegra_adma_chan *tdc) { struct virt_dma_desc *vd = vchan_next_desc(&tdc->vc); @@ -1155,6 +1162,7 @@ static int tegra_adma_probe(struct platform_device *pdev) tdma->dma_dev.device_config = tegra_adma_slave_config; tdma->dma_dev.device_tx_status = tegra_adma_tx_status; tdma->dma_dev.device_terminate_all = tegra_adma_terminate_all; + tdma->dma_dev.device_synchronize = tegra_adma_synchronize; tdma->dma_dev.src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES); tdma->dma_dev.dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES); tdma->dma_dev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); diff --git a/drivers/dma/ti/dma-crossbar.c b/drivers/dma/ti/dma-crossbar.c index 7f17ee87a6dce3..ff05b150ad3723 100644 --- a/drivers/dma/ti/dma-crossbar.c +++ b/drivers/dma/ti/dma-crossbar.c @@ -79,34 +79,35 @@ static void *ti_am335x_xbar_route_allocate(struct of_phandle_args *dma_spec, { struct platform_device *pdev = of_find_device_by_node(ofdma->of_node); struct ti_am335x_xbar_data *xbar = platform_get_drvdata(pdev); - struct ti_am335x_xbar_map *map; + struct ti_am335x_xbar_map *map = ERR_PTR(-EINVAL); if (dma_spec->args_count != 3) - return ERR_PTR(-EINVAL); + goto out_put_pdev; if (dma_spec->args[2] >= xbar->xbar_events) { dev_err(&pdev->dev, "Invalid XBAR event number: %d\n", dma_spec->args[2]); - return ERR_PTR(-EINVAL); + goto out_put_pdev; } if (dma_spec->args[0] >= xbar->dma_requests) { dev_err(&pdev->dev, "Invalid DMA request line number: %d\n", dma_spec->args[0]); - return ERR_PTR(-EINVAL); + goto out_put_pdev; } /* The of_node_put() will be done in the core for the node */ dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", 0); if (!dma_spec->np) { dev_err(&pdev->dev, "Can't get DMA master\n"); - return ERR_PTR(-EINVAL); + goto out_put_pdev; } map = kzalloc(sizeof(*map), GFP_KERNEL); if (!map) { of_node_put(dma_spec->np); - return ERR_PTR(-ENOMEM); + map = ERR_PTR(-ENOMEM); + goto out_put_pdev; } map->dma_line = (u16)dma_spec->args[0]; @@ -120,6 +121,9 @@ static void *ti_am335x_xbar_route_allocate(struct of_phandle_args *dma_spec, ti_am335x_xbar_write(xbar->iomem, map->dma_line, map->mux_val); +out_put_pdev: + put_device(&pdev->dev); + return map; } @@ -288,6 +292,8 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec, ti_dra7_xbar_write(xbar->iomem, map->xbar_out, map->xbar_in); + put_device(&pdev->dev); + return map; } diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c index 05228bf0003332..624360423ef170 100644 --- a/drivers/dma/ti/k3-udma-private.c +++ b/drivers/dma/ti/k3-udma-private.c @@ -42,9 +42,9 @@ struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property) } ud = platform_get_drvdata(pdev); + put_device(&pdev->dev); if (!ud) { pr_debug("UDMA has not been probed\n"); - put_device(&pdev->dev); return ERR_PTR(-EPROBE_DEFER); } diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c index 8c023c6e623a5a..73ed4b79463047 100644 --- a/drivers/dma/ti/omap-dma.c +++ b/drivers/dma/ti/omap-dma.c @@ -1808,6 +1808,8 @@ static int omap_dma_probe(struct platform_device *pdev) if (rc) { pr_warn("OMAP-DMA: failed to register slave DMA engine device: %d\n", rc); + if (od->ll123_supported) + dma_pool_destroy(od->desc_pool); omap_dma_free(od); return rc; } @@ -1823,6 +1825,8 @@ static int omap_dma_probe(struct platform_device *pdev) if (rc) { pr_warn("OMAP-DMA: failed to register DMA controller\n"); dma_async_device_unregister(&od->ddev); + if (od->ll123_supported) + dma_pool_destroy(od->desc_pool); omap_dma_free(od); } } diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h index 6ad08878e93862..70bca92621aa41 100644 --- a/drivers/dma/xilinx/xdma-regs.h +++ b/drivers/dma/xilinx/xdma-regs.h @@ -9,6 +9,7 @@ /* The length of register space exposed to host */ #define XDMA_REG_SPACE_LEN 65536 +#define XDMA_MAX_REG_OFFSET (XDMA_REG_SPACE_LEN - 4) /* * maximum number of DMA channels for each direction: diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c index 0d88b1a670e142..5ecf8223c112e4 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -38,7 +38,7 @@ static const struct regmap_config xdma_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, - .max_register = XDMA_REG_SPACE_LEN, + .max_register = XDMA_MAX_REG_OFFSET, }; /** diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index fabff602065f6c..89a8254d9cdc62 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -131,6 +131,7 @@ #define XILINX_MCDMA_MAX_CHANS_PER_DEVICE 0x20 #define XILINX_DMA_MAX_CHANS_PER_DEVICE 0x2 #define XILINX_CDMA_MAX_CHANS_PER_DEVICE 0x1 +#define XILINX_DMA_DFAULT_ADDRWIDTH 0x20 #define XILINX_DMA_DMAXR_ALL_IRQ_MASK \ (XILINX_DMA_DMASR_FRM_CNT_IRQ | \ @@ -3159,7 +3160,7 @@ static int xilinx_dma_probe(struct platform_device *pdev) struct device_node *node = pdev->dev.of_node; struct xilinx_dma_device *xdev; struct device_node *child, *np = pdev->dev.of_node; - u32 num_frames, addr_width, len_width; + u32 num_frames, addr_width = XILINX_DMA_DFAULT_ADDRWIDTH, len_width; int i, err; /* Allocate and initialize the DMA engine structure */ @@ -3235,7 +3236,9 @@ static int xilinx_dma_probe(struct platform_device *pdev) err = of_property_read_u32(node, "xlnx,addrwidth", &addr_width); if (err < 0) - dev_warn(xdev->dev, "missing xlnx,addrwidth property\n"); + dev_warn(xdev->dev, + "missing xlnx,addrwidth property, using default value %d\n", + XILINX_DMA_DFAULT_ADDRWIDTH); if (addr_width > 32) xdev->ext_addr = true; diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c index a461095efd8ac7..8879a72351561b 100644 --- a/drivers/dpll/dpll_core.c +++ b/drivers/dpll/dpll_core.c @@ -83,10 +83,8 @@ dpll_xa_ref_pin_add(struct xarray *xa_pins, struct dpll_pin *pin, if (ref->pin != pin) continue; reg = dpll_pin_registration_find(ref, ops, priv, cookie); - if (reg) { - refcount_inc(&ref->refcount); - return 0; - } + if (reg) + return -EEXIST; ref_exists = true; break; } @@ -164,10 +162,8 @@ dpll_xa_ref_dpll_add(struct xarray *xa_dplls, struct dpll_device *dpll, if (ref->dpll != dpll) continue; reg = dpll_pin_registration_find(ref, ops, priv, cookie); - if (reg) { - refcount_inc(&ref->refcount); - return 0; - } + if (reg) + return -EEXIST; ref_exists = true; break; } diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index a4153bcb6dcfe1..64944f601ee5aa 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -637,6 +637,10 @@ dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin, ret = dpll_msg_add_pin_freq(msg, pin, ref, extack); if (ret) return ret; + if (prop->phase_gran && + nla_put_u32(msg, DPLL_A_PIN_PHASE_ADJUST_GRAN, + prop->phase_gran)) + return -EMSGSIZE; if (nla_put_s32(msg, DPLL_A_PIN_PHASE_ADJUST_MIN, prop->phase_range.min)) return -EMSGSIZE; @@ -1261,7 +1265,13 @@ dpll_pin_phase_adj_set(struct dpll_pin *pin, struct nlattr *phase_adj_attr, if (phase_adj > pin->prop.phase_range.max || phase_adj < pin->prop.phase_range.min) { NL_SET_ERR_MSG_ATTR(extack, phase_adj_attr, - "phase adjust value not supported"); + "phase adjust value of out range"); + return -EINVAL; + } + if (pin->prop.phase_gran && phase_adj % (s32)pin->prop.phase_gran) { + NL_SET_ERR_MSG_ATTR_FMT(extack, phase_adj_attr, + "phase adjust value not multiple of %u", + pin->prop.phase_gran); return -EINVAL; } diff --git a/drivers/dpll/zl3073x/Makefile b/drivers/dpll/zl3073x/Makefile index 84e22aae57e5f7..bd324c7fe7101d 100644 --- a/drivers/dpll/zl3073x/Makefile +++ b/drivers/dpll/zl3073x/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ZL3073X) += zl3073x.o -zl3073x-objs := core.o devlink.o dpll.o flash.o fw.o prop.o +zl3073x-objs := core.o devlink.o dpll.o flash.o fw.o \ + out.o prop.o ref.o synth.o obj-$(CONFIG_ZL3073X_I2C) += zl3073x_i2c.o zl3073x_i2c-objs := i2c.o diff --git a/drivers/dpll/zl3073x/core.c b/drivers/dpll/zl3073x/core.c index e42e527813cf8b..2f340f7eb9ec31 100644 --- a/drivers/dpll/zl3073x/core.c +++ b/drivers/dpll/zl3073x/core.c @@ -129,47 +129,6 @@ const struct regmap_config zl3073x_regmap_config = { }; EXPORT_SYMBOL_NS_GPL(zl3073x_regmap_config, "ZL3073X"); -/** - * zl3073x_ref_freq_factorize - factorize given frequency - * @freq: input frequency - * @base: base frequency - * @mult: multiplier - * - * Checks if the given frequency can be factorized using one of the - * supported base frequencies. If so the base frequency and multiplier - * are stored into appropriate parameters if they are not NULL. - * - * Return: 0 on success, -EINVAL if the frequency cannot be factorized - */ -int -zl3073x_ref_freq_factorize(u32 freq, u16 *base, u16 *mult) -{ - static const u16 base_freqs[] = { - 1, 2, 4, 5, 8, 10, 16, 20, 25, 32, 40, 50, 64, 80, 100, 125, - 128, 160, 200, 250, 256, 320, 400, 500, 625, 640, 800, 1000, - 1250, 1280, 1600, 2000, 2500, 3125, 3200, 4000, 5000, 6250, - 6400, 8000, 10000, 12500, 15625, 16000, 20000, 25000, 31250, - 32000, 40000, 50000, 62500, - }; - u32 div; - int i; - - for (i = 0; i < ARRAY_SIZE(base_freqs); i++) { - div = freq / base_freqs[i]; - - if (div <= U16_MAX && (freq % base_freqs[i]) == 0) { - if (base) - *base = base_freqs[i]; - if (mult) - *mult = div; - - return 0; - } - } - - return -EINVAL; -} - static bool zl3073x_check_reg(struct zl3073x_dev *zldev, unsigned int reg, size_t size) { @@ -593,190 +552,6 @@ int zl3073x_write_hwreg_seq(struct zl3073x_dev *zldev, return rc; } -/** - * zl3073x_ref_state_fetch - get input reference state - * @zldev: pointer to zl3073x_dev structure - * @index: input reference index to fetch state for - * - * Function fetches information for the given input reference that are - * invariant and stores them for later use. - * - * Return: 0 on success, <0 on error - */ -static int -zl3073x_ref_state_fetch(struct zl3073x_dev *zldev, u8 index) -{ - struct zl3073x_ref *input = &zldev->ref[index]; - u8 ref_config; - int rc; - - /* If the input is differential then the configuration for N-pin - * reference is ignored and P-pin config is used for both. - */ - if (zl3073x_is_n_pin(index) && - zl3073x_ref_is_diff(zldev, index - 1)) { - input->enabled = zl3073x_ref_is_enabled(zldev, index - 1); - input->diff = true; - - return 0; - } - - guard(mutex)(&zldev->multiop_lock); - - /* Read reference configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(index)); - if (rc) - return rc; - - /* Read ref_config register */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_CONFIG, &ref_config); - if (rc) - return rc; - - input->enabled = FIELD_GET(ZL_REF_CONFIG_ENABLE, ref_config); - input->diff = FIELD_GET(ZL_REF_CONFIG_DIFF_EN, ref_config); - - dev_dbg(zldev->dev, "REF%u is %s and configured as %s\n", index, - str_enabled_disabled(input->enabled), - input->diff ? "differential" : "single-ended"); - - return rc; -} - -/** - * zl3073x_out_state_fetch - get output state - * @zldev: pointer to zl3073x_dev structure - * @index: output index to fetch state for - * - * Function fetches information for the given output (not output pin) - * that are invariant and stores them for later use. - * - * Return: 0 on success, <0 on error - */ -static int -zl3073x_out_state_fetch(struct zl3073x_dev *zldev, u8 index) -{ - struct zl3073x_out *out = &zldev->out[index]; - u8 output_ctrl, output_mode; - int rc; - - /* Read output configuration */ - rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_CTRL(index), &output_ctrl); - if (rc) - return rc; - - /* Store info about output enablement and synthesizer the output - * is connected to. - */ - out->enabled = FIELD_GET(ZL_OUTPUT_CTRL_EN, output_ctrl); - out->synth = FIELD_GET(ZL_OUTPUT_CTRL_SYNTH_SEL, output_ctrl); - - dev_dbg(zldev->dev, "OUT%u is %s and connected to SYNTH%u\n", index, - str_enabled_disabled(out->enabled), out->synth); - - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(index)); - if (rc) - return rc; - - /* Read output_mode */ - rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_MODE, &output_mode); - if (rc) - return rc; - - /* Extract and store output signal format */ - out->signal_format = FIELD_GET(ZL_OUTPUT_MODE_SIGNAL_FORMAT, - output_mode); - - dev_dbg(zldev->dev, "OUT%u has signal format 0x%02x\n", index, - out->signal_format); - - return rc; -} - -/** - * zl3073x_synth_state_fetch - get synth state - * @zldev: pointer to zl3073x_dev structure - * @index: synth index to fetch state for - * - * Function fetches information for the given synthesizer that are - * invariant and stores them for later use. - * - * Return: 0 on success, <0 on error - */ -static int -zl3073x_synth_state_fetch(struct zl3073x_dev *zldev, u8 index) -{ - struct zl3073x_synth *synth = &zldev->synth[index]; - u16 base, m, n; - u8 synth_ctrl; - u32 mult; - int rc; - - /* Read synth control register */ - rc = zl3073x_read_u8(zldev, ZL_REG_SYNTH_CTRL(index), &synth_ctrl); - if (rc) - return rc; - - /* Store info about synth enablement and DPLL channel the synth is - * driven by. - */ - synth->enabled = FIELD_GET(ZL_SYNTH_CTRL_EN, synth_ctrl); - synth->dpll = FIELD_GET(ZL_SYNTH_CTRL_DPLL_SEL, synth_ctrl); - - dev_dbg(zldev->dev, "SYNTH%u is %s and driven by DPLL%u\n", index, - str_enabled_disabled(synth->enabled), synth->dpll); - - guard(mutex)(&zldev->multiop_lock); - - /* Read synth configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_SYNTH_MB_SEM, ZL_SYNTH_MB_SEM_RD, - ZL_REG_SYNTH_MB_MASK, BIT(index)); - if (rc) - return rc; - - /* The output frequency is determined by the following formula: - * base * multiplier * numerator / denominator - * - * Read registers with these values - */ - rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_BASE, &base); - if (rc) - return rc; - - rc = zl3073x_read_u32(zldev, ZL_REG_SYNTH_FREQ_MULT, &mult); - if (rc) - return rc; - - rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_M, &m); - if (rc) - return rc; - - rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_N, &n); - if (rc) - return rc; - - /* Check denominator for zero to avoid div by 0 */ - if (!n) { - dev_err(zldev->dev, - "Zero divisor for SYNTH%u retrieved from device\n", - index); - return -EINVAL; - } - - /* Compute and store synth frequency */ - zldev->synth[index].freq = div_u64(mul_u32_u32(base * m, mult), n); - - dev_dbg(zldev->dev, "SYNTH%u frequency: %u Hz\n", index, - zldev->synth[index].freq); - - return rc; -} - static int zl3073x_dev_state_fetch(struct zl3073x_dev *zldev) { diff --git a/drivers/dpll/zl3073x/core.h b/drivers/dpll/zl3073x/core.h index 1dca4ddcf2350c..fe779fc77dd09d 100644 --- a/drivers/dpll/zl3073x/core.h +++ b/drivers/dpll/zl3073x/core.h @@ -9,7 +9,10 @@ #include #include +#include "out.h" +#include "ref.h" #include "regs.h" +#include "synth.h" struct device; struct regmap; @@ -27,42 +30,6 @@ struct zl3073x_dpll; #define ZL3073X_NUM_PINS (ZL3073X_NUM_INPUT_PINS + \ ZL3073X_NUM_OUTPUT_PINS) -/** - * struct zl3073x_ref - input reference invariant info - * @enabled: input reference is enabled or disabled - * @diff: true if input reference is differential - * @ffo: current fractional frequency offset - */ -struct zl3073x_ref { - bool enabled; - bool diff; - s64 ffo; -}; - -/** - * struct zl3073x_out - output invariant info - * @enabled: out is enabled or disabled - * @synth: synthesizer the out is connected to - * @signal_format: out signal format - */ -struct zl3073x_out { - bool enabled; - u8 synth; - u8 signal_format; -}; - -/** - * struct zl3073x_synth - synthesizer invariant info - * @freq: synthesizer frequency - * @dpll: ID of DPLL the synthesizer is driven by - * @enabled: synth is enabled or disabled - */ -struct zl3073x_synth { - u32 freq; - u8 dpll; - bool enabled; -}; - /** * struct zl3073x_dev - zl3073x device * @dev: pointer to device @@ -175,7 +142,6 @@ int zl3073x_write_hwreg_seq(struct zl3073x_dev *zldev, * Misc operations *****************/ -int zl3073x_ref_freq_factorize(u32 freq, u16 *base, u16 *mult); int zl3073x_ref_phase_offsets_update(struct zl3073x_dev *zldev, int channel); static inline bool @@ -217,172 +183,188 @@ zl3073x_output_pin_out_get(u8 id) } /** - * zl3073x_ref_ffo_get - get current fractional frequency offset + * zl3073x_dev_ref_ffo_get - get current fractional frequency offset * @zldev: pointer to zl3073x device * @index: input reference index * * Return: the latest measured fractional frequency offset */ static inline s64 -zl3073x_ref_ffo_get(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_ref_ffo_get(struct zl3073x_dev *zldev, u8 index) { - return zldev->ref[index].ffo; + const struct zl3073x_ref *ref = zl3073x_ref_state_get(zldev, index); + + return zl3073x_ref_ffo_get(ref); } /** - * zl3073x_ref_is_diff - check if the given input reference is differential + * zl3073x_dev_ref_is_diff - check if the given input reference is differential * @zldev: pointer to zl3073x device * @index: input reference index * * Return: true if reference is differential, false if reference is single-ended */ static inline bool -zl3073x_ref_is_diff(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_ref_is_diff(struct zl3073x_dev *zldev, u8 index) { - return zldev->ref[index].diff; + const struct zl3073x_ref *ref = zl3073x_ref_state_get(zldev, index); + + return zl3073x_ref_is_diff(ref); } /** - * zl3073x_ref_is_enabled - check if the given input reference is enabled + * zl3073x_dev_ref_is_enabled - check if the given input reference is enabled * @zldev: pointer to zl3073x device * @index: input reference index * * Return: true if input refernce is enabled, false otherwise */ static inline bool -zl3073x_ref_is_enabled(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_ref_is_enabled(struct zl3073x_dev *zldev, u8 index) { - return zldev->ref[index].enabled; + const struct zl3073x_ref *ref = zl3073x_ref_state_get(zldev, index); + + return zl3073x_ref_is_enabled(ref); } /** - * zl3073x_synth_dpll_get - get DPLL ID the synth is driven by + * zl3073x_dev_synth_dpll_get - get DPLL ID the synth is driven by * @zldev: pointer to zl3073x device * @index: synth index * * Return: ID of DPLL the given synthetizer is driven by */ static inline u8 -zl3073x_synth_dpll_get(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_synth_dpll_get(struct zl3073x_dev *zldev, u8 index) { - return zldev->synth[index].dpll; + const struct zl3073x_synth *synth; + + synth = zl3073x_synth_state_get(zldev, index); + return zl3073x_synth_dpll_get(synth); } /** - * zl3073x_synth_freq_get - get synth current freq + * zl3073x_dev_synth_freq_get - get synth current freq * @zldev: pointer to zl3073x device * @index: synth index * * Return: frequency of given synthetizer */ static inline u32 -zl3073x_synth_freq_get(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_synth_freq_get(struct zl3073x_dev *zldev, u8 index) { - return zldev->synth[index].freq; + const struct zl3073x_synth *synth; + + synth = zl3073x_synth_state_get(zldev, index); + return zl3073x_synth_freq_get(synth); } /** - * zl3073x_synth_is_enabled - check if the given synth is enabled + * zl3073x_dev_synth_is_enabled - check if the given synth is enabled * @zldev: pointer to zl3073x device * @index: synth index * * Return: true if synth is enabled, false otherwise */ static inline bool -zl3073x_synth_is_enabled(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_synth_is_enabled(struct zl3073x_dev *zldev, u8 index) { - return zldev->synth[index].enabled; + const struct zl3073x_synth *synth; + + synth = zl3073x_synth_state_get(zldev, index); + return zl3073x_synth_is_enabled(synth); } /** - * zl3073x_out_synth_get - get synth connected to given output + * zl3073x_dev_out_synth_get - get synth connected to given output * @zldev: pointer to zl3073x device * @index: output index * * Return: index of synth connected to given output. */ static inline u8 -zl3073x_out_synth_get(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_out_synth_get(struct zl3073x_dev *zldev, u8 index) { - return zldev->out[index].synth; + const struct zl3073x_out *out = zl3073x_out_state_get(zldev, index); + + return zl3073x_out_synth_get(out); } /** - * zl3073x_out_is_enabled - check if the given output is enabled + * zl3073x_dev_out_is_enabled - check if the given output is enabled * @zldev: pointer to zl3073x device * @index: output index * * Return: true if the output is enabled, false otherwise */ static inline bool -zl3073x_out_is_enabled(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_out_is_enabled(struct zl3073x_dev *zldev, u8 index) { - u8 synth; + const struct zl3073x_out *out = zl3073x_out_state_get(zldev, index); + const struct zl3073x_synth *synth; + u8 synth_id; /* Output is enabled only if associated synth is enabled */ - synth = zl3073x_out_synth_get(zldev, index); - if (zl3073x_synth_is_enabled(zldev, synth)) - return zldev->out[index].enabled; + synth_id = zl3073x_out_synth_get(out); + synth = zl3073x_synth_state_get(zldev, synth_id); - return false; + return zl3073x_synth_is_enabled(synth) && zl3073x_out_is_enabled(out); } /** - * zl3073x_out_signal_format_get - get output signal format + * zl3073x_dev_out_signal_format_get - get output signal format * @zldev: pointer to zl3073x device * @index: output index * * Return: signal format of given output */ static inline u8 -zl3073x_out_signal_format_get(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_out_signal_format_get(struct zl3073x_dev *zldev, u8 index) { - return zldev->out[index].signal_format; + const struct zl3073x_out *out = zl3073x_out_state_get(zldev, index); + + return zl3073x_out_signal_format_get(out); } /** - * zl3073x_out_dpll_get - get DPLL ID the output is driven by + * zl3073x_dev_out_dpll_get - get DPLL ID the output is driven by * @zldev: pointer to zl3073x device * @index: output index * * Return: ID of DPLL the given output is driven by */ static inline -u8 zl3073x_out_dpll_get(struct zl3073x_dev *zldev, u8 index) +u8 zl3073x_dev_out_dpll_get(struct zl3073x_dev *zldev, u8 index) { - u8 synth; + const struct zl3073x_out *out = zl3073x_out_state_get(zldev, index); + const struct zl3073x_synth *synth; + u8 synth_id; /* Get synthesizer connected to given output */ - synth = zl3073x_out_synth_get(zldev, index); + synth_id = zl3073x_out_synth_get(out); + synth = zl3073x_synth_state_get(zldev, synth_id); /* Return DPLL that drives the synth */ - return zl3073x_synth_dpll_get(zldev, synth); + return zl3073x_synth_dpll_get(synth); } /** - * zl3073x_out_is_diff - check if the given output is differential + * zl3073x_dev_out_is_diff - check if the given output is differential * @zldev: pointer to zl3073x device * @index: output index * * Return: true if output is differential, false if output is single-ended */ static inline bool -zl3073x_out_is_diff(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_out_is_diff(struct zl3073x_dev *zldev, u8 index) { - switch (zl3073x_out_signal_format_get(zldev, index)) { - case ZL_OUTPUT_MODE_SIGNAL_FORMAT_LVDS: - case ZL_OUTPUT_MODE_SIGNAL_FORMAT_DIFF: - case ZL_OUTPUT_MODE_SIGNAL_FORMAT_LOWVCM: - return true; - default: - break; - } + const struct zl3073x_out *out = zl3073x_out_state_get(zldev, index); - return false; + return zl3073x_out_is_diff(out); } /** - * zl3073x_output_pin_is_enabled - check if the given output pin is enabled + * zl3073x_dev_output_pin_is_enabled - check if the given output pin is enabled * @zldev: pointer to zl3073x device * @id: output pin id * @@ -392,16 +374,21 @@ zl3073x_out_is_diff(struct zl3073x_dev *zldev, u8 index) * Return: true if output pin is enabled, false if output pin is disabled */ static inline bool -zl3073x_output_pin_is_enabled(struct zl3073x_dev *zldev, u8 id) +zl3073x_dev_output_pin_is_enabled(struct zl3073x_dev *zldev, u8 id) { - u8 output = zl3073x_output_pin_out_get(id); + u8 out_id = zl3073x_output_pin_out_get(id); + const struct zl3073x_out *out; + + out = zl3073x_out_state_get(zldev, out_id); - /* Check if the whole output is enabled */ - if (!zl3073x_out_is_enabled(zldev, output)) + /* Check if the output is enabled - call _dev_ helper that + * additionally checks for attached synth enablement. + */ + if (!zl3073x_dev_out_is_enabled(zldev, out_id)) return false; /* Check signal format */ - switch (zl3073x_out_signal_format_get(zldev, output)) { + switch (zl3073x_out_signal_format_get(out)) { case ZL_OUTPUT_MODE_SIGNAL_FORMAT_DISABLED: /* Both output pins are disabled by signal format */ return false; diff --git a/drivers/dpll/zl3073x/dpll.c b/drivers/dpll/zl3073x/dpll.c index f93f9a45832432..11ca32e1bb8292 100644 --- a/drivers/dpll/zl3073x/dpll.c +++ b/drivers/dpll/zl3073x/dpll.c @@ -35,6 +35,7 @@ * @prio: pin priority <0, 14> * @selectable: pin is selectable in automatic mode * @esync_control: embedded sync is controllable + * @phase_gran: phase adjustment granularity * @pin_state: last saved pin state * @phase_offset: last saved pin phase offset * @freq_offset: last saved fractional frequency offset @@ -49,6 +50,7 @@ struct zl3073x_dpll_pin { u8 prio; bool selectable; bool esync_control; + s32 phase_gran; enum dpll_pin_state pin_state; s64 phase_offset; s64 freq_offset; @@ -951,21 +953,19 @@ zl3073x_dpll_output_pin_esync_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - struct device *dev = zldev->dev; - u32 esync_period, esync_width; - u8 clock_type, synth; - u8 out, output_mode; - u32 output_div; + const struct zl3073x_synth *synth; + const struct zl3073x_out *out; + u8 clock_type, out_id; u32 synth_freq; - int rc; - out = zl3073x_output_pin_out_get(pin->id); + out_id = zl3073x_output_pin_out_get(pin->id); + out = zl3073x_out_state_get(zldev, out_id); /* If N-division is enabled, esync is not supported. The register used * for N-division is also used for the esync divider so both cannot * be used. */ - switch (zl3073x_out_signal_format_get(zldev, out)) { + switch (zl3073x_out_signal_format_get(out)) { case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV: case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV_INV: return -EOPNOTSUPP; @@ -973,38 +973,11 @@ zl3073x_dpll_output_pin_esync_get(const struct dpll_pin *dpll_pin, break; } - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration into mailbox */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; - - /* Read output mode */ - rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_MODE, &output_mode); - if (rc) - return rc; + /* Get attached synth frequency */ + synth = zl3073x_synth_state_get(zldev, zl3073x_out_synth_get(out)); + synth_freq = zl3073x_synth_freq_get(synth); - /* Read output divisor */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &output_div); - if (rc) - return rc; - - /* Check output divisor for zero */ - if (!output_div) { - dev_err(dev, "Zero divisor for OUTPUT%u got from device\n", - out); - return -EINVAL; - } - - /* Get synth attached to output pin */ - synth = zl3073x_out_synth_get(zldev, out); - - /* Get synth frequency */ - synth_freq = zl3073x_synth_freq_get(zldev, synth); - - clock_type = FIELD_GET(ZL_OUTPUT_MODE_CLOCK_TYPE, output_mode); + clock_type = FIELD_GET(ZL_OUTPUT_MODE_CLOCK_TYPE, out->mode); if (clock_type != ZL_OUTPUT_MODE_CLOCK_TYPE_ESYNC) { /* No need to read esync data if it is not enabled */ esync->freq = 0; @@ -1013,38 +986,21 @@ zl3073x_dpll_output_pin_esync_get(const struct dpll_pin *dpll_pin, goto finish; } - /* Read esync period */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, &esync_period); - if (rc) - return rc; - - /* Check esync divisor for zero */ - if (!esync_period) { - dev_err(dev, "Zero esync divisor for OUTPUT%u got from device\n", - out); - return -EINVAL; - } - - /* Get esync pulse width in units of half synth cycles */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, &esync_width); - if (rc) - return rc; - /* Compute esync frequency */ - esync->freq = synth_freq / output_div / esync_period; + esync->freq = synth_freq / out->div / out->esync_n_period; /* By comparing the esync_pulse_width to the half of the pulse width * the esync pulse percentage can be determined. * Note that half pulse width is in units of half synth cycles, which * is why it reduces down to be output_div. */ - esync->pulse = (50 * esync_width) / output_div; + esync->pulse = (50 * out->esync_n_width) / out->div; finish: /* Set supported esync ranges if the pin supports esync control and * if the output frequency is > 1 Hz. */ - if (pin->esync_control && (synth_freq / output_div) > 1) { + if (pin->esync_control && (synth_freq / out->div) > 1) { esync->range = esync_freq_ranges; esync->range_num = ARRAY_SIZE(esync_freq_ranges); } else { @@ -1062,21 +1018,22 @@ zl3073x_dpll_output_pin_esync_set(const struct dpll_pin *dpll_pin, void *dpll_priv, u64 freq, struct netlink_ext_ack *extack) { - u32 esync_period, esync_width, output_div; struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u8 clock_type, out, output_mode, synth; + const struct zl3073x_synth *synth; + struct zl3073x_out out; + u8 clock_type, out_id; u32 synth_freq; - int rc; - out = zl3073x_output_pin_out_get(pin->id); + out_id = zl3073x_output_pin_out_get(pin->id); + out = *zl3073x_out_state_get(zldev, out_id); /* If N-division is enabled, esync is not supported. The register used * for N-division is also used for the esync divider so both cannot * be used. */ - switch (zl3073x_out_signal_format_get(zldev, out)) { + switch (zl3073x_out_signal_format_get(&out)) { case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV: case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV_INV: return -EOPNOTSUPP; @@ -1084,19 +1041,6 @@ zl3073x_dpll_output_pin_esync_set(const struct dpll_pin *dpll_pin, break; } - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration into mailbox */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; - - /* Read output mode */ - rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_MODE, &output_mode); - if (rc) - return rc; - /* Select clock type */ if (freq) clock_type = ZL_OUTPUT_MODE_CLOCK_TYPE_ESYNC; @@ -1104,38 +1048,19 @@ zl3073x_dpll_output_pin_esync_set(const struct dpll_pin *dpll_pin, clock_type = ZL_OUTPUT_MODE_CLOCK_TYPE_NORMAL; /* Update clock type in output mode */ - output_mode &= ~ZL_OUTPUT_MODE_CLOCK_TYPE; - output_mode |= FIELD_PREP(ZL_OUTPUT_MODE_CLOCK_TYPE, clock_type); - rc = zl3073x_write_u8(zldev, ZL_REG_OUTPUT_MODE, output_mode); - if (rc) - return rc; + out.mode &= ~ZL_OUTPUT_MODE_CLOCK_TYPE; + out.mode |= FIELD_PREP(ZL_OUTPUT_MODE_CLOCK_TYPE, clock_type); /* If esync is being disabled just write mailbox and finish */ if (!freq) goto write_mailbox; - /* Get synth attached to output pin */ - synth = zl3073x_out_synth_get(zldev, out); - - /* Get synth frequency */ - synth_freq = zl3073x_synth_freq_get(zldev, synth); - - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &output_div); - if (rc) - return rc; - - /* Check output divisor for zero */ - if (!output_div) { - dev_err(zldev->dev, - "Zero divisor for OUTPUT%u got from device\n", out); - return -EINVAL; - } + /* Get attached synth frequency */ + synth = zl3073x_synth_state_get(zldev, zl3073x_out_synth_get(&out)); + synth_freq = zl3073x_synth_freq_get(synth); /* Compute and update esync period */ - esync_period = synth_freq / (u32)freq / output_div; - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, esync_period); - if (rc) - return rc; + out.esync_n_period = synth_freq / (u32)freq / out.div; /* Half of the period in units of 1/2 synth cycle can be represented by * the output_div. To get the supported esync pulse width of 25% of the @@ -1143,15 +1068,11 @@ zl3073x_dpll_output_pin_esync_set(const struct dpll_pin *dpll_pin, * assumes that output_div is even, otherwise some resolution will be * lost. */ - esync_width = output_div / 2; - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, esync_width); - if (rc) - return rc; + out.esync_n_width = out.div / 2; write_mailbox: /* Commit output configuration */ - return zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); + return zl3073x_out_state_set(zldev, out_id, &out); } static int @@ -1164,83 +1085,46 @@ zl3073x_dpll_output_pin_frequency_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - struct device *dev = zldev->dev; - u8 out, signal_format, synth; - u32 output_div, synth_freq; - int rc; - - out = zl3073x_output_pin_out_get(pin->id); - synth = zl3073x_out_synth_get(zldev, out); - synth_freq = zl3073x_synth_freq_get(zldev, synth); - - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration into mailbox */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; + const struct zl3073x_synth *synth; + const struct zl3073x_out *out; + u32 synth_freq; + u8 out_id; - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &output_div); - if (rc) - return rc; + out_id = zl3073x_output_pin_out_get(pin->id); + out = zl3073x_out_state_get(zldev, out_id); - /* Check output divisor for zero */ - if (!output_div) { - dev_err(dev, "Zero divisor for output %u got from device\n", - out); - return -EINVAL; - } + /* Get attached synth frequency */ + synth = zl3073x_synth_state_get(zldev, zl3073x_out_synth_get(out)); + synth_freq = zl3073x_synth_freq_get(synth); - /* Read used signal format for the given output */ - signal_format = zl3073x_out_signal_format_get(zldev, out); - - switch (signal_format) { + switch (zl3073x_out_signal_format_get(out)) { case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV: case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV_INV: /* In case of divided format we have to distiguish between * given output pin type. + * + * For P-pin the resulting frequency is computed as simple + * division of synth frequency and output divisor. + * + * For N-pin we have to divide additionally by divisor stored + * in esync_n_period output mailbox register that is used as + * N-pin divisor for these modes. */ - if (zl3073x_dpll_is_p_pin(pin)) { - /* For P-pin the resulting frequency is computed as - * simple division of synth frequency and output - * divisor. - */ - *frequency = synth_freq / output_div; - } else { - /* For N-pin we have to divide additionally by - * divisor stored in esync_period output mailbox - * register that is used as N-pin divisor for these - * modes. - */ - u32 ndiv; - - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, - &ndiv); - if (rc) - return rc; + *frequency = synth_freq / out->div; - /* Check N-pin divisor for zero */ - if (!ndiv) { - dev_err(dev, - "Zero N-pin divisor for output %u got from device\n", - out); - return -EINVAL; - } + if (!zl3073x_dpll_is_p_pin(pin)) + *frequency = (u32)*frequency / out->esync_n_period; - /* Compute final divisor for N-pin */ - *frequency = synth_freq / output_div / ndiv; - } break; default: /* In other modes the resulting frequency is computed as * division of synth frequency and output divisor. */ - *frequency = synth_freq / output_div; + *frequency = synth_freq / out->div; break; } - return rc; + return 0; } static int @@ -1253,28 +1137,21 @@ zl3073x_dpll_output_pin_frequency_set(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - struct device *dev = zldev->dev; - u32 output_n_freq, output_p_freq; - u8 out, signal_format, synth; - u32 cur_div, new_div, ndiv; - u32 synth_freq; - int rc; + const struct zl3073x_synth *synth; + u8 out_id, signal_format; + u32 new_div, synth_freq; + struct zl3073x_out out; + + out_id = zl3073x_output_pin_out_get(pin->id); + out = *zl3073x_out_state_get(zldev, out_id); - out = zl3073x_output_pin_out_get(pin->id); - synth = zl3073x_out_synth_get(zldev, out); - synth_freq = zl3073x_synth_freq_get(zldev, synth); + /* Get attached synth frequency and compute new divisor */ + synth = zl3073x_synth_state_get(zldev, zl3073x_out_synth_get(&out)); + synth_freq = zl3073x_synth_freq_get(synth); new_div = synth_freq / (u32)frequency; /* Get used signal format for the given output */ - signal_format = zl3073x_out_signal_format_get(zldev, out); - - guard(mutex)(&zldev->multiop_lock); - - /* Load output configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; + signal_format = zl3073x_out_signal_format_get(&out); /* Check signal format */ if (signal_format != ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV && @@ -1282,99 +1159,50 @@ zl3073x_dpll_output_pin_frequency_set(const struct dpll_pin *dpll_pin, /* For non N-divided signal formats the frequency is computed * as division of synth frequency and output divisor. */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_DIV, new_div); - if (rc) - return rc; + out.div = new_div; /* For 50/50 duty cycle the divisor is equal to width */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_WIDTH, new_div); - if (rc) - return rc; + out.width = new_div; /* Commit output configuration */ - return zl3073x_mb_op(zldev, - ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); + return zl3073x_out_state_set(zldev, out_id, &out); } - /* For N-divided signal format get current divisor */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &cur_div); - if (rc) - return rc; - - /* Check output divisor for zero */ - if (!cur_div) { - dev_err(dev, "Zero divisor for output %u got from device\n", - out); - return -EINVAL; - } - - /* Get N-pin divisor (shares the same register with esync */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, &ndiv); - if (rc) - return rc; - - /* Check N-pin divisor for zero */ - if (!ndiv) { - dev_err(dev, - "Zero N-pin divisor for output %u got from device\n", - out); - return -EINVAL; - } - - /* Compute current output frequency for P-pin */ - output_p_freq = synth_freq / cur_div; - - /* Compute current N-pin frequency */ - output_n_freq = output_p_freq / ndiv; - if (zl3073x_dpll_is_p_pin(pin)) { /* We are going to change output frequency for P-pin but * if the requested frequency is less than current N-pin * frequency then indicate a failure as we are not able * to compute N-pin divisor to keep its frequency unchanged. + * + * Update divisor for N-pin to keep N-pin frequency. */ - if (frequency <= output_n_freq) + out.esync_n_period = (out.esync_n_period * out.div) / new_div; + if (!out.esync_n_period) return -EINVAL; /* Update the output divisor */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_DIV, new_div); - if (rc) - return rc; + out.div = new_div; /* For 50/50 duty cycle the divisor is equal to width */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_WIDTH, new_div); - if (rc) - return rc; - - /* Compute new divisor for N-pin */ - ndiv = (u32)frequency / output_n_freq; + out.width = out.div; } else { /* We are going to change frequency of N-pin but if * the requested freq is greater or equal than freq of P-pin * in the output pair we cannot compute divisor for the N-pin. * In this case indicate a failure. + * + * Update divisor for N-pin */ - if (output_p_freq <= frequency) + out.esync_n_period = div64_u64(synth_freq, frequency * out.div); + if (!out.esync_n_period) return -EINVAL; - - /* Compute new divisor for N-pin */ - ndiv = output_p_freq / (u32)frequency; } - /* Update divisor for the N-pin */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, ndiv); - if (rc) - return rc; - /* For 50/50 duty cycle the divisor is equal to width */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, ndiv); - if (rc) - return rc; + out.esync_n_width = out.esync_n_period; /* Commit output configuration */ - return zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); + return zl3073x_out_state_set(zldev, out_id, &out); } static int @@ -1388,42 +1216,16 @@ zl3073x_dpll_output_pin_phase_adjust_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u32 synth_freq; - s32 phase_comp; - u8 out, synth; - int rc; - - out = zl3073x_output_pin_out_get(pin->id); - synth = zl3073x_out_synth_get(zldev, out); - synth_freq = zl3073x_synth_freq_get(zldev, synth); + const struct zl3073x_out *out; + u8 out_id; - /* Check synth freq for zero */ - if (!synth_freq) { - dev_err(zldev->dev, "Got zero synth frequency for output %u\n", - out); - return -EINVAL; - } - - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; - - /* Read current output phase compensation */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_PHASE_COMP, &phase_comp); - if (rc) - return rc; + out_id = zl3073x_output_pin_out_get(pin->id); + out = zl3073x_out_state_get(zldev, out_id); - /* Value in register is expressed in half synth clock cycles */ - phase_comp *= (int)div_u64(PSEC_PER_SEC, 2 * synth_freq); + /* The value in the register is expressed in half synth clock cycles. */ + *phase_adjust = out->phase_comp * pin->phase_gran; - /* Reverse two's complement negation applied during 'set' */ - *phase_adjust = -phase_comp; - - return rc; + return 0; } static int @@ -1437,52 +1239,17 @@ zl3073x_dpll_output_pin_phase_adjust_set(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - int half_synth_cycle; - u32 synth_freq; - u8 out, synth; - int rc; + struct zl3073x_out out; + u8 out_id; - /* Get attached synth */ - out = zl3073x_output_pin_out_get(pin->id); - synth = zl3073x_out_synth_get(zldev, out); + out_id = zl3073x_output_pin_out_get(pin->id); + out = *zl3073x_out_state_get(zldev, out_id); - /* Get synth's frequency */ - synth_freq = zl3073x_synth_freq_get(zldev, synth); - - /* Value in register is expressed in half synth clock cycles so - * the given phase adjustment a multiple of half synth clock. - */ - half_synth_cycle = (int)div_u64(PSEC_PER_SEC, 2 * synth_freq); - - if ((phase_adjust % half_synth_cycle) != 0) { - NL_SET_ERR_MSG_FMT(extack, - "Phase adjustment value has to be multiple of %d", - half_synth_cycle); - return -EINVAL; - } - phase_adjust /= half_synth_cycle; - - /* The value in the register is stored as two's complement negation - * of requested value. - */ - phase_adjust = -phase_adjust; - - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; - - /* Write the requested value into the compensation register */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_PHASE_COMP, phase_adjust); - if (rc) - return rc; + /* The value in the register is expressed in half synth clock cycles. */ + out.phase_comp = phase_adjust / pin->phase_gran; /* Update output configuration from mailbox */ - return zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); + return zl3073x_out_state_set(zldev, out_id, &out); } static int @@ -1758,9 +1525,10 @@ zl3073x_dpll_pin_register(struct zl3073x_dpll_pin *pin, u32 index) if (IS_ERR(props)) return PTR_ERR(props); - /* Save package label & esync capability */ + /* Save package label, esync capability and phase adjust granularity */ strscpy(pin->label, props->package_label); pin->esync_control = props->esync_control; + pin->phase_gran = props->dpll_props.phase_gran; if (zl3073x_dpll_is_input_pin(pin)) { rc = zl3073x_dpll_ref_prio_get(pin, &pin->prio); @@ -1886,25 +1654,23 @@ zl3073x_dpll_pin_is_registrable(struct zl3073x_dpll *zldpll, if (zldpll->refsel_mode == ZL_DPLL_MODE_REFSEL_MODE_NCO) return false; - is_diff = zl3073x_ref_is_diff(zldev, ref); - is_enabled = zl3073x_ref_is_enabled(zldev, ref); + is_diff = zl3073x_dev_ref_is_diff(zldev, ref); + is_enabled = zl3073x_dev_ref_is_enabled(zldev, ref); } else { /* Output P&N pair shares single HW output */ u8 out = zl3073x_output_pin_out_get(index); - name = "OUT"; - /* Skip the pin if it is connected to different DPLL channel */ - if (zl3073x_out_dpll_get(zldev, out) != zldpll->id) { + if (zl3073x_dev_out_dpll_get(zldev, out) != zldpll->id) { dev_dbg(zldev->dev, - "%s%u is driven by different DPLL\n", name, - out); + "OUT%u is driven by different DPLL\n", out); return false; } - is_diff = zl3073x_out_is_diff(zldev, out); - is_enabled = zl3073x_output_pin_is_enabled(zldev, index); + name = "OUT"; + is_diff = zl3073x_dev_out_is_diff(zldev, out); + is_enabled = zl3073x_dev_output_pin_is_enabled(zldev, index); } /* Skip N-pin if the corresponding input/output is differential */ @@ -2154,7 +1920,7 @@ zl3073x_dpll_pin_ffo_check(struct zl3073x_dpll_pin *pin) return false; /* Get the latest measured ref's ffo */ - ffo = zl3073x_ref_ffo_get(zldev, ref); + ffo = zl3073x_dev_ref_ffo_get(zldev, ref); /* Compare with previous value */ if (pin->freq_offset != ffo) { diff --git a/drivers/dpll/zl3073x/out.c b/drivers/dpll/zl3073x/out.c new file mode 100644 index 00000000000000..86829a0c1c022f --- /dev/null +++ b/drivers/dpll/zl3073x/out.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include +#include + +#include "core.h" +#include "out.h" + +/** + * zl3073x_out_state_fetch - fetch output state from hardware + * @zldev: pointer to zl3073x_dev structure + * @index: output index to fetch state for + * + * Function fetches state of the given output from hardware and stores it + * for later use. + * + * Return: 0 on success, <0 on error + */ +int zl3073x_out_state_fetch(struct zl3073x_dev *zldev, u8 index) +{ + struct zl3073x_out *out = &zldev->out[index]; + int rc; + + /* Read output configuration */ + rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_CTRL(index), &out->ctrl); + if (rc) + return rc; + + dev_dbg(zldev->dev, "OUT%u is %s and connected to SYNTH%u\n", index, + str_enabled_disabled(zl3073x_out_is_enabled(out)), + zl3073x_out_synth_get(out)); + + guard(mutex)(&zldev->multiop_lock); + + /* Read output configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, + ZL_REG_OUTPUT_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* Read output mode */ + rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_MODE, &out->mode); + if (rc) + return rc; + + dev_dbg(zldev->dev, "OUT%u has signal format 0x%02x\n", index, + zl3073x_out_signal_format_get(out)); + + /* Read output divisor */ + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &out->div); + if (rc) + return rc; + + if (!out->div) { + dev_err(zldev->dev, "Zero divisor for OUT%u got from device\n", + index); + return -EINVAL; + } + + dev_dbg(zldev->dev, "OUT%u divisor: %u\n", index, out->div); + + /* Read output width */ + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_WIDTH, &out->width); + if (rc) + return rc; + + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, + &out->esync_n_period); + if (rc) + return rc; + + if (!out->esync_n_period) { + dev_err(zldev->dev, + "Zero esync divisor for OUT%u got from device\n", + index); + return -EINVAL; + } + + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, + &out->esync_n_width); + if (rc) + return rc; + + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_PHASE_COMP, + &out->phase_comp); + if (rc) + return rc; + + return rc; +} + +/** + * zl3073x_out_state_get - get current output state + * @zldev: pointer to zl3073x_dev structure + * @index: output index to get state for + * + * Return: pointer to given output state + */ +const struct zl3073x_out *zl3073x_out_state_get(struct zl3073x_dev *zldev, + u8 index) +{ + return &zldev->out[index]; +} + +int zl3073x_out_state_set(struct zl3073x_dev *zldev, u8 index, + const struct zl3073x_out *out) +{ + struct zl3073x_out *dout = &zldev->out[index]; + int rc; + + guard(mutex)(&zldev->multiop_lock); + + /* Read output configuration into mailbox */ + rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, + ZL_REG_OUTPUT_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* Update mailbox with changed values */ + if (dout->div != out->div) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_DIV, out->div); + if (!rc && dout->width != out->width) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_WIDTH, out->width); + if (!rc && dout->esync_n_period != out->esync_n_period) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, + out->esync_n_period); + if (!rc && dout->esync_n_width != out->esync_n_width) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, + out->esync_n_width); + if (!rc && dout->mode != out->mode) + rc = zl3073x_write_u8(zldev, ZL_REG_OUTPUT_MODE, out->mode); + if (!rc && dout->phase_comp != out->phase_comp) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_PHASE_COMP, + out->phase_comp); + if (rc) + return rc; + + /* Commit output configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, + ZL_REG_OUTPUT_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* After successful commit store new state */ + dout->div = out->div; + dout->width = out->width; + dout->esync_n_period = out->esync_n_period; + dout->esync_n_width = out->esync_n_width; + dout->mode = out->mode; + dout->phase_comp = out->phase_comp; + + return 0; +} diff --git a/drivers/dpll/zl3073x/out.h b/drivers/dpll/zl3073x/out.h new file mode 100644 index 00000000000000..e8ea7a0e0f071c --- /dev/null +++ b/drivers/dpll/zl3073x/out.h @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ZL3073X_OUT_H +#define _ZL3073X_OUT_H + +#include +#include + +#include "regs.h" + +struct zl3073x_dev; + +/** + * struct zl3073x_out - output state + * @div: output divisor + * @width: output pulse width + * @esync_n_period: embedded sync or n-pin period (for n-div formats) + * @esync_n_width: embedded sync or n-pin pulse width + * @phase_comp: phase compensation + * @ctrl: output control + * @mode: output mode + */ +struct zl3073x_out { + u32 div; + u32 width; + u32 esync_n_period; + u32 esync_n_width; + s32 phase_comp; + u8 ctrl; + u8 mode; +}; + +int zl3073x_out_state_fetch(struct zl3073x_dev *zldev, u8 index); +const struct zl3073x_out *zl3073x_out_state_get(struct zl3073x_dev *zldev, + u8 index); + +int zl3073x_out_state_set(struct zl3073x_dev *zldev, u8 index, + const struct zl3073x_out *out); + +/** + * zl3073x_out_signal_format_get - get output signal format + * @out: pointer to out state + * + * Return: signal format of given output + */ +static inline u8 zl3073x_out_signal_format_get(const struct zl3073x_out *out) +{ + return FIELD_GET(ZL_OUTPUT_MODE_SIGNAL_FORMAT, out->mode); +} + +/** + * zl3073x_out_is_diff - check if the given output is differential + * @out: pointer to out state + * + * Return: true if output is differential, false if output is single-ended + */ +static inline bool zl3073x_out_is_diff(const struct zl3073x_out *out) +{ + switch (zl3073x_out_signal_format_get(out)) { + case ZL_OUTPUT_MODE_SIGNAL_FORMAT_LVDS: + case ZL_OUTPUT_MODE_SIGNAL_FORMAT_DIFF: + case ZL_OUTPUT_MODE_SIGNAL_FORMAT_LOWVCM: + return true; + default: + break; + } + + return false; +} + +/** + * zl3073x_out_is_enabled - check if the given output is enabled + * @out: pointer to out state + * + * Return: true if output is enabled, false if output is disabled + */ +static inline bool zl3073x_out_is_enabled(const struct zl3073x_out *out) +{ + return !!FIELD_GET(ZL_OUTPUT_CTRL_EN, out->ctrl); +} + +/** + * zl3073x_out_synth_get - get synth connected to given output + * @out: pointer to out state + * + * Return: index of synth connected to given output. + */ +static inline u8 zl3073x_out_synth_get(const struct zl3073x_out *out) +{ + return FIELD_GET(ZL_OUTPUT_CTRL_SYNTH_SEL, out->ctrl); +} + +#endif /* _ZL3073X_OUT_H */ diff --git a/drivers/dpll/zl3073x/prop.c b/drivers/dpll/zl3073x/prop.c index 4cf7e8aefcb373..4ed153087570b4 100644 --- a/drivers/dpll/zl3073x/prop.c +++ b/drivers/dpll/zl3073x/prop.c @@ -46,10 +46,10 @@ zl3073x_pin_check_freq(struct zl3073x_dev *zldev, enum dpll_pin_direction dir, /* Get output pin synthesizer */ out = zl3073x_output_pin_out_get(id); - synth = zl3073x_out_synth_get(zldev, out); + synth = zl3073x_dev_out_synth_get(zldev, out); /* Get synth frequency */ - synth_freq = zl3073x_synth_freq_get(zldev, synth); + synth_freq = zl3073x_dev_synth_freq_get(zldev, synth); /* Check the frequency divides synth frequency */ if (synth_freq % (u32)freq) @@ -93,13 +93,13 @@ zl3073x_prop_pin_package_label_set(struct zl3073x_dev *zldev, prefix = "REF"; ref = zl3073x_input_pin_ref_get(id); - is_diff = zl3073x_ref_is_diff(zldev, ref); + is_diff = zl3073x_dev_ref_is_diff(zldev, ref); } else { u8 out; prefix = "OUT"; out = zl3073x_output_pin_out_get(id); - is_diff = zl3073x_out_is_diff(zldev, out); + is_diff = zl3073x_dev_out_is_diff(zldev, out); } if (!is_diff) @@ -208,7 +208,18 @@ struct zl3073x_pin_props *zl3073x_pin_props_get(struct zl3073x_dev *zldev, DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE | DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; } else { + u8 out, synth; + u32 f; + props->dpll_props.type = DPLL_PIN_TYPE_GNSS; + + /* The output pin phase adjustment granularity equals half of + * the synth frequency count. + */ + out = zl3073x_output_pin_out_get(index); + synth = zl3073x_dev_out_synth_get(zldev, out); + f = 2 * zl3073x_dev_synth_freq_get(zldev, synth); + props->dpll_props.phase_gran = f ? div_u64(PSEC_PER_SEC, f) : 1; } props->dpll_props.phase_range.min = S32_MIN; diff --git a/drivers/dpll/zl3073x/ref.c b/drivers/dpll/zl3073x/ref.c new file mode 100644 index 00000000000000..6abd6288a02ad9 --- /dev/null +++ b/drivers/dpll/zl3073x/ref.c @@ -0,0 +1,112 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include +#include + +#include "core.h" +#include "ref.h" + +/** + * zl3073x_ref_freq_factorize - factorize given frequency + * @freq: input frequency + * @base: base frequency + * @mult: multiplier + * + * Checks if the given frequency can be factorized using one of the + * supported base frequencies. If so the base frequency and multiplier + * are stored into appropriate parameters if they are not NULL. + * + * Return: 0 on success, -EINVAL if the frequency cannot be factorized + */ +int +zl3073x_ref_freq_factorize(u32 freq, u16 *base, u16 *mult) +{ + static const u16 base_freqs[] = { + 1, 2, 4, 5, 8, 10, 16, 20, 25, 32, 40, 50, 64, 80, 100, 125, + 128, 160, 200, 250, 256, 320, 400, 500, 625, 640, 800, 1000, + 1250, 1280, 1600, 2000, 2500, 3125, 3200, 4000, 5000, 6250, + 6400, 8000, 10000, 12500, 15625, 16000, 20000, 25000, 31250, + 32000, 40000, 50000, 62500, + }; + u32 div; + int i; + + for (i = 0; i < ARRAY_SIZE(base_freqs); i++) { + div = freq / base_freqs[i]; + + if (div <= U16_MAX && (freq % base_freqs[i]) == 0) { + if (base) + *base = base_freqs[i]; + if (mult) + *mult = div; + + return 0; + } + } + + return -EINVAL; +} + +/** + * zl3073x_ref_state_fetch - fetch input reference state from hardware + * @zldev: pointer to zl3073x_dev structure + * @index: input reference index to fetch state for + * + * Function fetches state for the given input reference from hardware and + * stores it for later use. + * + * Return: 0 on success, <0 on error + */ +int zl3073x_ref_state_fetch(struct zl3073x_dev *zldev, u8 index) +{ + struct zl3073x_ref *ref = &zldev->ref[index]; + int rc; + + /* For differential type inputs the N-pin reference shares + * part of the configuration with the P-pin counterpart. + */ + if (zl3073x_is_n_pin(index) && zl3073x_ref_is_diff(ref - 1)) { + struct zl3073x_ref *p_ref = &zldev->ref[index - 1]; + + /* Copy the shared items from the P-pin */ + ref->config = p_ref->config; + + return 0; /* Finish - no non-shared items for now */ + } + + guard(mutex)(&zldev->multiop_lock); + + /* Read reference configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, + ZL_REG_REF_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* Read ref_config register */ + rc = zl3073x_read_u8(zldev, ZL_REG_REF_CONFIG, &ref->config); + if (rc) + return rc; + + dev_dbg(zldev->dev, "REF%u is %s and configured as %s\n", index, + str_enabled_disabled(zl3073x_ref_is_enabled(ref)), + zl3073x_ref_is_diff(ref) ? "differential" : "single-ended"); + + return rc; +} + +/** + * zl3073x_ref_state_get - get current input reference state + * @zldev: pointer to zl3073x_dev structure + * @index: input reference index to get state for + * + * Return: pointer to given input reference state + */ +const struct zl3073x_ref * +zl3073x_ref_state_get(struct zl3073x_dev *zldev, u8 index) +{ + return &zldev->ref[index]; +} diff --git a/drivers/dpll/zl3073x/ref.h b/drivers/dpll/zl3073x/ref.h new file mode 100644 index 00000000000000..e72f2c87508760 --- /dev/null +++ b/drivers/dpll/zl3073x/ref.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ZL3073X_REF_H +#define _ZL3073X_REF_H + +#include +#include + +#include "regs.h" + +struct zl3073x_dev; + +/** + * struct zl3073x_ref - input reference state + * @ffo: current fractional frequency offset + * @config: reference config + */ +struct zl3073x_ref { + s64 ffo; + u8 config; +}; + +int zl3073x_ref_state_fetch(struct zl3073x_dev *zldev, u8 index); + +const struct zl3073x_ref *zl3073x_ref_state_get(struct zl3073x_dev *zldev, + u8 index); + +int zl3073x_ref_freq_factorize(u32 freq, u16 *base, u16 *mult); + +/** + * zl3073x_ref_ffo_get - get current fractional frequency offset + * @ref: pointer to ref state + * + * Return: the latest measured fractional frequency offset + */ +static inline s64 +zl3073x_ref_ffo_get(const struct zl3073x_ref *ref) +{ + return ref->ffo; +} + +/** + * zl3073x_ref_is_diff - check if the given input reference is differential + * @ref: pointer to ref state + * + * Return: true if reference is differential, false if reference is single-ended + */ +static inline bool +zl3073x_ref_is_diff(const struct zl3073x_ref *ref) +{ + return !!FIELD_GET(ZL_REF_CONFIG_DIFF_EN, ref->config); +} + +/** + * zl3073x_ref_is_enabled - check if the given input reference is enabled + * @ref: pointer to ref state + * + * Return: true if input refernce is enabled, false otherwise + */ +static inline bool +zl3073x_ref_is_enabled(const struct zl3073x_ref *ref) +{ + return !!FIELD_GET(ZL_REF_CONFIG_ENABLE, ref->config); +} + +#endif /* _ZL3073X_REF_H */ diff --git a/drivers/dpll/zl3073x/synth.c b/drivers/dpll/zl3073x/synth.c new file mode 100644 index 00000000000000..da839572dab26f --- /dev/null +++ b/drivers/dpll/zl3073x/synth.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include +#include + +#include "core.h" +#include "synth.h" + +/** + * zl3073x_synth_state_fetch - fetch synth state from hardware + * @zldev: pointer to zl3073x_dev structure + * @index: synth index to fetch state for + * + * Function fetches state of the given synthesizer from the hardware and + * stores it for later use. + * + * Return: 0 on success, <0 on error + */ +int zl3073x_synth_state_fetch(struct zl3073x_dev *zldev, u8 index) +{ + struct zl3073x_synth *synth = &zldev->synth[index]; + int rc; + + /* Read synth control register */ + rc = zl3073x_read_u8(zldev, ZL_REG_SYNTH_CTRL(index), &synth->ctrl); + if (rc) + return rc; + + guard(mutex)(&zldev->multiop_lock); + + /* Read synth configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_SYNTH_MB_SEM, ZL_SYNTH_MB_SEM_RD, + ZL_REG_SYNTH_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* The output frequency is determined by the following formula: + * base * multiplier * numerator / denominator + * + * Read registers with these values + */ + rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_BASE, &synth->freq_base); + if (rc) + return rc; + + rc = zl3073x_read_u32(zldev, ZL_REG_SYNTH_FREQ_MULT, &synth->freq_mult); + if (rc) + return rc; + + rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_M, &synth->freq_m); + if (rc) + return rc; + + rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_N, &synth->freq_n); + if (rc) + return rc; + + /* Check denominator for zero to avoid div by 0 */ + if (!synth->freq_n) { + dev_err(zldev->dev, + "Zero divisor for SYNTH%u retrieved from device\n", + index); + return -EINVAL; + } + + dev_dbg(zldev->dev, "SYNTH%u frequency: %u Hz\n", index, + zl3073x_synth_freq_get(synth)); + + return rc; +} + +/** + * zl3073x_synth_state_get - get current synth state + * @zldev: pointer to zl3073x_dev structure + * @index: synth index to get state for + * + * Return: pointer to given synth state + */ +const struct zl3073x_synth *zl3073x_synth_state_get(struct zl3073x_dev *zldev, + u8 index) +{ + return &zldev->synth[index]; +} diff --git a/drivers/dpll/zl3073x/synth.h b/drivers/dpll/zl3073x/synth.h new file mode 100644 index 00000000000000..6c55eb8a888c2c --- /dev/null +++ b/drivers/dpll/zl3073x/synth.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ZL3073X_SYNTH_H +#define _ZL3073X_SYNTH_H + +#include +#include +#include + +#include "regs.h" + +struct zl3073x_dev; + +/** + * struct zl3073x_synth - synthesizer state + * @freq_mult: frequency multiplier + * @freq_base: frequency base + * @freq_m: frequency numerator + * @freq_n: frequency denominator + * @ctrl: synth control + */ +struct zl3073x_synth { + u32 freq_mult; + u16 freq_base; + u16 freq_m; + u16 freq_n; + u8 ctrl; +}; + +int zl3073x_synth_state_fetch(struct zl3073x_dev *zldev, u8 synth_id); + +const struct zl3073x_synth *zl3073x_synth_state_get(struct zl3073x_dev *zldev, + u8 synth_id); + +int zl3073x_synth_state_set(struct zl3073x_dev *zldev, u8 synth_id, + const struct zl3073x_synth *synth); + +/** + * zl3073x_synth_dpll_get - get DPLL ID the synth is driven by + * @synth: pointer to synth state + * + * Return: ID of DPLL the given synthetizer is driven by + */ +static inline u8 zl3073x_synth_dpll_get(const struct zl3073x_synth *synth) +{ + return FIELD_GET(ZL_SYNTH_CTRL_DPLL_SEL, synth->ctrl); +} + +/** + * zl3073x_synth_freq_get - get synth current freq + * @synth: pointer to synth state + * + * Return: frequency of given synthetizer + */ +static inline u32 zl3073x_synth_freq_get(const struct zl3073x_synth *synth) +{ + return mul_u64_u32_div(synth->freq_base * synth->freq_m, + synth->freq_mult, synth->freq_n); +} + +/** + * zl3073x_synth_is_enabled - check if the given synth is enabled + * @synth: pointer to synth state + * + * Return: true if synth is enabled, false otherwise + */ +static inline bool zl3073x_synth_is_enabled(const struct zl3073x_synth *synth) +{ + return FIELD_GET(ZL_SYNTH_CTRL_EN, synth->ctrl); +} + +#endif /* _ZL3073X_SYNTH_H */ diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 0c5b94e64ea157..4edd2088c2db6f 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -1563,8 +1563,7 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) goto err_release_group_1; } rc = devm_request_irq(&altdev->ddev, altdev->sb_irq, - prv->ecc_irq_handler, - IRQF_ONESHOT | IRQF_TRIGGER_HIGH, + prv->ecc_irq_handler, IRQF_TRIGGER_HIGH, ecc_name, altdev); if (rc) { edac_printk(KERN_ERR, EDAC_DEVICE, "PortB SBERR IRQ error\n"); @@ -1587,8 +1586,7 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) goto err_release_group_1; } rc = devm_request_irq(&altdev->ddev, altdev->db_irq, - prv->ecc_irq_handler, - IRQF_ONESHOT | IRQF_TRIGGER_HIGH, + prv->ecc_irq_handler, IRQF_TRIGGER_HIGH, ecc_name, altdev); if (rc) { edac_printk(KERN_ERR, EDAC_DEVICE, "PortB DBERR IRQ error\n"); @@ -1970,8 +1968,7 @@ static int altr_edac_a10_device_add(struct altr_arria10_edac *edac, goto err_release_group1; } rc = devm_request_irq(edac->dev, altdev->sb_irq, prv->ecc_irq_handler, - IRQF_ONESHOT | IRQF_TRIGGER_HIGH, - ecc_name, altdev); + IRQF_TRIGGER_HIGH, ecc_name, altdev); if (rc) { edac_printk(KERN_ERR, EDAC_DEVICE, "No SBERR IRQ resource\n"); goto err_release_group1; @@ -1993,7 +1990,7 @@ static int altr_edac_a10_device_add(struct altr_arria10_edac *edac, goto err_release_group1; } rc = devm_request_irq(edac->dev, altdev->db_irq, prv->ecc_irq_handler, - IRQF_ONESHOT | IRQF_TRIGGER_HIGH, + IRQF_TRIGGER_HIGH, ecc_name, altdev); if (rc) { edac_printk(KERN_ERR, EDAC_DEVICE, "No DBERR IRQ resource\n"); diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c index afccdebf5ac1eb..6cade6d7ceff62 100644 --- a/drivers/edac/i3200_edac.c +++ b/drivers/edac/i3200_edac.c @@ -358,10 +358,11 @@ static int i3200_probe1(struct pci_dev *pdev, int dev_idx) layers[1].type = EDAC_MC_LAYER_CHANNEL; layers[1].size = nr_channels; layers[1].is_virt_csrow = false; - mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, - sizeof(struct i3200_priv)); + + rc = -ENOMEM; + mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(struct i3200_priv)); if (!mci) - return -ENOMEM; + goto unmap; edac_dbg(3, "MC: init mci\n"); @@ -421,9 +422,9 @@ static int i3200_probe1(struct pci_dev *pdev, int dev_idx) return 0; fail: + edac_mc_free(mci); +unmap: iounmap(window); - if (mci) - edac_mc_free(mci); return rc; } diff --git a/drivers/edac/i5000_edac.c b/drivers/edac/i5000_edac.c index 4a1bebc1ff14d4..471b8540d18b0f 100644 --- a/drivers/edac/i5000_edac.c +++ b/drivers/edac/i5000_edac.c @@ -1111,6 +1111,7 @@ static void calculate_dimm_size(struct i5000_pvt *pvt) n = snprintf(p, space, " "); p += n; + space -= n; for (branch = 0; branch < MAX_BRANCHES; branch++) { n = snprintf(p, space, " branch %d | ", branch); p += n; diff --git a/drivers/edac/i5400_edac.c b/drivers/edac/i5400_edac.c index b5cf25905b059d..fb49a1d1df1120 100644 --- a/drivers/edac/i5400_edac.c +++ b/drivers/edac/i5400_edac.c @@ -1026,13 +1026,13 @@ static void calculate_dimm_size(struct i5400_pvt *pvt) space -= n; } - space -= n; edac_dbg(2, "%s\n", mem_buffer); p = mem_buffer; space = PAGE_SIZE; n = snprintf(p, space, " "); p += n; + space -= n; for (branch = 0; branch < MAX_BRANCHES; branch++) { n = snprintf(p, space, " branch %d | ", branch); p += n; diff --git a/drivers/edac/x38_edac.c b/drivers/edac/x38_edac.c index 49ab5721aab25c..292dda754c2366 100644 --- a/drivers/edac/x38_edac.c +++ b/drivers/edac/x38_edac.c @@ -341,9 +341,12 @@ static int x38_probe1(struct pci_dev *pdev, int dev_idx) layers[1].type = EDAC_MC_LAYER_CHANNEL; layers[1].size = x38_channel_num; layers[1].is_virt_csrow = false; + + + rc = -ENOMEM; mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, 0); if (!mci) - return -ENOMEM; + goto unmap; edac_dbg(3, "MC: init mci\n"); @@ -403,9 +406,9 @@ static int x38_probe1(struct pci_dev *pdev, int dev_idx) return 0; fail: + edac_mc_free(mci); +unmap: iounmap(window); - if (mci) - edac_mc_free(mci); return rc; } diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index c65f491c54d063..2e797430332c07 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -134,20 +134,14 @@ static void split_transaction_timeout_callback(struct timer_list *timer) } } -static void start_split_transaction_timeout(struct fw_transaction *t, - struct fw_card *card) +// card->transactions.lock should be acquired in advance for the linked list. +static void start_split_transaction_timeout(struct fw_transaction *t, unsigned int delta) { - unsigned long delta; - if (list_empty(&t->link) || WARN_ON(t->is_split_transaction)) return; t->is_split_transaction = true; - // NOTE: This can be without irqsave when we can guarantee that __fw_send_request() for - // local destination never runs in any type of IRQ context. - scoped_guard(spinlock_irqsave, &card->split_timeout.lock) - delta = card->split_timeout.jiffies; mod_timer(&t->split_timeout_timer, jiffies + delta); } @@ -168,13 +162,20 @@ static void transmit_complete_callback(struct fw_packet *packet, break; case ACK_PENDING: { + unsigned int delta; + // NOTE: This can be without irqsave when we can guarantee that __fw_send_request() for // local destination never runs in any type of IRQ context. scoped_guard(spinlock_irqsave, &card->split_timeout.lock) { t->split_timeout_cycle = compute_split_timeout_timestamp(card, packet->timestamp) & 0xffff; + delta = card->split_timeout.jiffies; } - start_split_transaction_timeout(t, card); + + // NOTE: This can be without irqsave when we can guarantee that __fw_send_request() for + // local destination never runs in any type of IRQ context. + scoped_guard(spinlock_irqsave, &card->transactions.lock) + start_split_transaction_timeout(t, delta); break; } case ACK_BUSY_X: diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c index ea31ac7ac1ca93..e59053738a432a 100644 --- a/drivers/firewire/nosy.c +++ b/drivers/firewire/nosy.c @@ -36,6 +36,8 @@ static char driver_name[] = KBUILD_MODNAME; +#define RCV_BUFFER_SIZE (16 * 1024) + /* this is the physical layout of a PCL, its size is 128 bytes */ struct pcl { __le32 next; @@ -517,16 +519,14 @@ remove_card(struct pci_dev *dev) lynx->rcv_start_pcl, lynx->rcv_start_pcl_bus); dma_free_coherent(&lynx->pci_device->dev, sizeof(struct pcl), lynx->rcv_pcl, lynx->rcv_pcl_bus); - dma_free_coherent(&lynx->pci_device->dev, PAGE_SIZE, lynx->rcv_buffer, - lynx->rcv_buffer_bus); + dma_free_coherent(&lynx->pci_device->dev, RCV_BUFFER_SIZE, + lynx->rcv_buffer, lynx->rcv_buffer_bus); iounmap(lynx->registers); pci_disable_device(dev); lynx_put(lynx); } -#define RCV_BUFFER_SIZE (16 * 1024) - static int add_card(struct pci_dev *dev, const struct pci_device_id *unused) { @@ -680,7 +680,7 @@ add_card(struct pci_dev *dev, const struct pci_device_id *unused) dma_free_coherent(&lynx->pci_device->dev, sizeof(struct pcl), lynx->rcv_pcl, lynx->rcv_pcl_bus); if (lynx->rcv_buffer) - dma_free_coherent(&lynx->pci_device->dev, PAGE_SIZE, + dma_free_coherent(&lynx->pci_device->dev, RCV_BUFFER_SIZE, lynx->rcv_buffer, lynx->rcv_buffer_bus); iounmap(lynx->registers); diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index c72ee475658569..c501c3104b3a4f 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -981,10 +981,27 @@ static void __do_sched_recv_cb(u16 part_id, u16 vcpu, bool is_per_vcpu) } } +/* + * Map logical ID index to the u16 index within the packed ID list. + * + * For native responses (FF-A width == kernel word size), IDs are + * tightly packed: idx -> idx. + * + * For 32-bit responses on a 64-bit kernel, each 64-bit register + * contributes 4 x u16 values but only the lower 2 are defined; the + * upper 2 are garbage. This mapping skips those upper halves: + * 0,1,2,3,4,5,... -> 0,1,4,5,8,9,... + */ +static int list_idx_to_u16_idx(int idx, bool is_native_resp) +{ + return is_native_resp ? idx : idx + 2 * (idx >> 1); +} + static void ffa_notification_info_get(void) { - int idx, list, max_ids, lists_cnt, ids_processed, ids_count[MAX_IDS_64]; - bool is_64b_resp; + int ids_processed, ids_count[MAX_IDS_64]; + int idx, list, max_ids, lists_cnt; + bool is_64b_resp, is_native_resp; ffa_value_t ret; u64 id_list; @@ -1001,6 +1018,7 @@ static void ffa_notification_info_get(void) } is_64b_resp = (ret.a0 == FFA_FN64_SUCCESS); + is_native_resp = (ret.a0 == FFA_FN_NATIVE(SUCCESS)); ids_processed = 0; lists_cnt = FIELD_GET(NOTIFICATION_INFO_GET_ID_COUNT, ret.a2); @@ -1017,12 +1035,16 @@ static void ffa_notification_info_get(void) /* Process IDs */ for (list = 0; list < lists_cnt; list++) { + int u16_idx; u16 vcpu_id, part_id, *packed_id_list = (u16 *)&ret.a3; if (ids_processed >= max_ids - 1) break; - part_id = packed_id_list[ids_processed++]; + u16_idx = list_idx_to_u16_idx(ids_processed, + is_native_resp); + part_id = packed_id_list[u16_idx]; + ids_processed++; if (ids_count[list] == 1) { /* Global Notification */ __do_sched_recv_cb(part_id, 0, false); @@ -1034,7 +1056,10 @@ static void ffa_notification_info_get(void) if (ids_processed >= max_ids - 1) break; - vcpu_id = packed_id_list[ids_processed++]; + u16_idx = list_idx_to_u16_idx(ids_processed, + is_native_resp); + vcpu_id = packed_id_list[u16_idx]; + ids_processed++; __do_sched_recv_cb(part_id, vcpu_id, true); } diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index f51047d8ea64f5..7ca56777a1da5b 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -9,6 +9,8 @@ * Cirrus Logic International Semiconductor Ltd. */ +#include +#include #include #include #include @@ -22,6 +24,41 @@ #include #include +#include "cs_dsp.h" + +/* + * When the KUnit test is running the error-case tests will cause a lot + * of messages. Rate-limit to prevent overflowing the kernel log buffer + * during KUnit test runs. + */ +#if IS_ENABLED(CONFIG_FW_CS_DSP_KUNIT_TEST) +bool cs_dsp_suppress_err_messages; +EXPORT_SYMBOL_IF_KUNIT(cs_dsp_suppress_err_messages); + +bool cs_dsp_suppress_warn_messages; +EXPORT_SYMBOL_IF_KUNIT(cs_dsp_suppress_warn_messages); + +bool cs_dsp_suppress_info_messages; +EXPORT_SYMBOL_IF_KUNIT(cs_dsp_suppress_info_messages); + +#define cs_dsp_err(_dsp, fmt, ...) \ + do { \ + if (!cs_dsp_suppress_err_messages) \ + dev_err_ratelimited(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__); \ + } while (false) +#define cs_dsp_warn(_dsp, fmt, ...) \ + do { \ + if (!cs_dsp_suppress_warn_messages) \ + dev_warn_ratelimited(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__); \ + } while (false) +#define cs_dsp_info(_dsp, fmt, ...) \ + do { \ + if (!cs_dsp_suppress_info_messages) \ + dev_info_ratelimited(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__); \ + } while (false) +#define cs_dsp_dbg(_dsp, fmt, ...) \ + dev_dbg_ratelimited(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__) +#else #define cs_dsp_err(_dsp, fmt, ...) \ dev_err(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__) #define cs_dsp_warn(_dsp, fmt, ...) \ @@ -30,6 +67,7 @@ dev_info(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__) #define cs_dsp_dbg(_dsp, fmt, ...) \ dev_dbg(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__) +#endif #define ADSP1_CONTROL_1 0x00 #define ADSP1_CONTROL_2 0x02 @@ -410,24 +448,30 @@ static void cs_dsp_debugfs_clear(struct cs_dsp *dsp) dsp->bin_file_name = NULL; } +static ssize_t cs_dsp_debugfs_string_read(struct cs_dsp *dsp, + char __user *user_buf, + size_t count, loff_t *ppos, + const char **pstr) +{ + const char *str; + + scoped_guard(mutex, &dsp->pwr_lock) { + str = *pstr; + if (!str) + return 0; + + return simple_read_from_buffer(user_buf, count, ppos, str, strlen(str)); + } +} + static ssize_t cs_dsp_debugfs_wmfw_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct cs_dsp *dsp = file->private_data; - ssize_t ret; - - mutex_lock(&dsp->pwr_lock); - - if (!dsp->wmfw_file_name || !dsp->booted) - ret = 0; - else - ret = simple_read_from_buffer(user_buf, count, ppos, - dsp->wmfw_file_name, - strlen(dsp->wmfw_file_name)); - mutex_unlock(&dsp->pwr_lock); - return ret; + return cs_dsp_debugfs_string_read(dsp, user_buf, count, ppos, + &dsp->wmfw_file_name); } static ssize_t cs_dsp_debugfs_bin_read(struct file *file, @@ -435,19 +479,9 @@ static ssize_t cs_dsp_debugfs_bin_read(struct file *file, size_t count, loff_t *ppos) { struct cs_dsp *dsp = file->private_data; - ssize_t ret; - - mutex_lock(&dsp->pwr_lock); - if (!dsp->bin_file_name || !dsp->booted) - ret = 0; - else - ret = simple_read_from_buffer(user_buf, count, ppos, - dsp->bin_file_name, - strlen(dsp->bin_file_name)); - - mutex_unlock(&dsp->pwr_lock); - return ret; + return cs_dsp_debugfs_string_read(dsp, user_buf, count, ppos, + &dsp->bin_file_name); } static const struct { diff --git a/drivers/firmware/cirrus/cs_dsp.h b/drivers/firmware/cirrus/cs_dsp.h new file mode 100644 index 00000000000000..adf543004aea31 --- /dev/null +++ b/drivers/firmware/cirrus/cs_dsp.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * cs_dsp.h -- Private header for cs_dsp driver. + * + * Copyright (C) 2026 Cirrus Logic, Inc. and + * Cirrus Logic International Semiconductor Ltd. + */ + +#ifndef FW_CS_DSP_H +#define FW_CS_DSP_H + +#if IS_ENABLED(CONFIG_KUNIT) +extern bool cs_dsp_suppress_err_messages; +extern bool cs_dsp_suppress_warn_messages; +extern bool cs_dsp_suppress_info_messages; +#endif + +#endif /* ifndef FW_CS_DSP_H */ diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_bin.c b/drivers/firmware/cirrus/test/cs_dsp_test_bin.c index 163b7faecff466..2c6486fa95758d 100644 --- a/drivers/firmware/cirrus/test/cs_dsp_test_bin.c +++ b/drivers/firmware/cirrus/test/cs_dsp_test_bin.c @@ -17,6 +17,8 @@ #include #include +#include "../cs_dsp.h" + /* * Test method is: * @@ -2224,7 +2226,22 @@ static int cs_dsp_bin_test_common_init(struct kunit *test, struct cs_dsp *dsp) return ret; /* Automatically call cs_dsp_remove() when test case ends */ - return kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); + ret = kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); + if (ret) + return ret; + + /* + * The large number of test cases will cause an unusually large amount + * of dev_info() messages from cs_dsp, so suppress these. + */ + cs_dsp_suppress_info_messages = true; + + return 0; +} + +static void cs_dsp_bin_test_exit(struct kunit *test) +{ + cs_dsp_suppress_info_messages = false; } static int cs_dsp_bin_test_halo_init(struct kunit *test) @@ -2536,18 +2553,21 @@ static struct kunit_case cs_dsp_bin_test_cases_adsp2[] = { static struct kunit_suite cs_dsp_bin_test_halo = { .name = "cs_dsp_bin_halo", .init = cs_dsp_bin_test_halo_init, + .exit = cs_dsp_bin_test_exit, .test_cases = cs_dsp_bin_test_cases_halo, }; static struct kunit_suite cs_dsp_bin_test_adsp2_32bit = { .name = "cs_dsp_bin_adsp2_32bit", .init = cs_dsp_bin_test_adsp2_32bit_init, + .exit = cs_dsp_bin_test_exit, .test_cases = cs_dsp_bin_test_cases_adsp2, }; static struct kunit_suite cs_dsp_bin_test_adsp2_16bit = { .name = "cs_dsp_bin_adsp2_16bit", .init = cs_dsp_bin_test_adsp2_16bit_init, + .exit = cs_dsp_bin_test_exit, .test_cases = cs_dsp_bin_test_cases_adsp2, }; diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c b/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c index a7ec956d27249e..631b9cb9eb2508 100644 --- a/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c +++ b/drivers/firmware/cirrus/test/cs_dsp_test_bin_error.c @@ -18,6 +18,8 @@ #include #include +#include "../cs_dsp.h" + KUNIT_DEFINE_ACTION_WRAPPER(_put_device_wrapper, put_device, struct device *); KUNIT_DEFINE_ACTION_WRAPPER(_cs_dsp_remove_wrapper, cs_dsp_remove, struct cs_dsp *); @@ -380,11 +382,9 @@ static void bin_block_payload_len_garbage(struct kunit *test) static void cs_dsp_bin_err_test_exit(struct kunit *test) { - /* - * Testing error conditions can produce a lot of log output - * from cs_dsp error messages, so rate limit the test cases. - */ - usleep_range(200, 500); + cs_dsp_suppress_err_messages = false; + cs_dsp_suppress_warn_messages = false; + cs_dsp_suppress_info_messages = false; } static int cs_dsp_bin_err_test_common_init(struct kunit *test, struct cs_dsp *dsp, @@ -474,7 +474,19 @@ static int cs_dsp_bin_err_test_common_init(struct kunit *test, struct cs_dsp *ds return ret; /* Automatically call cs_dsp_remove() when test case ends */ - return kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); + ret = kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); + if (ret) + return ret; + + /* + * Testing error conditions can produce a lot of log output + * from cs_dsp error messages, so suppress messages. + */ + cs_dsp_suppress_err_messages = true; + cs_dsp_suppress_warn_messages = true; + cs_dsp_suppress_info_messages = true; + + return 0; } static int cs_dsp_bin_err_test_halo_init(struct kunit *test) diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_wmfw.c b/drivers/firmware/cirrus/test/cs_dsp_test_wmfw.c index 9e997c4ee2d67c..f02cb6cf763868 100644 --- a/drivers/firmware/cirrus/test/cs_dsp_test_wmfw.c +++ b/drivers/firmware/cirrus/test/cs_dsp_test_wmfw.c @@ -18,6 +18,8 @@ #include #include +#include "../cs_dsp.h" + /* * Test method is: * @@ -1853,7 +1855,22 @@ static int cs_dsp_wmfw_test_common_init(struct kunit *test, struct cs_dsp *dsp, return ret; /* Automatically call cs_dsp_remove() when test case ends */ - return kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); + ret = kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); + if (ret) + return ret; + + /* + * The large number of test cases will cause an unusually large amount + * of dev_info() messages from cs_dsp, so suppress these. + */ + cs_dsp_suppress_info_messages = true; + + return 0; +} + +static void cs_dsp_wmfw_test_exit(struct kunit *test) +{ + cs_dsp_suppress_info_messages = false; } static int cs_dsp_wmfw_test_halo_init(struct kunit *test) @@ -2163,42 +2180,49 @@ static struct kunit_case cs_dsp_wmfw_test_cases_adsp2[] = { static struct kunit_suite cs_dsp_wmfw_test_halo = { .name = "cs_dsp_wmfwV3_halo", .init = cs_dsp_wmfw_test_halo_init, + .exit = cs_dsp_wmfw_test_exit, .test_cases = cs_dsp_wmfw_test_cases_halo, }; static struct kunit_suite cs_dsp_wmfw_test_adsp2_32bit_wmfw0 = { .name = "cs_dsp_wmfwV0_adsp2_32bit", .init = cs_dsp_wmfw_test_adsp2_32bit_wmfw0_init, + .exit = cs_dsp_wmfw_test_exit, .test_cases = cs_dsp_wmfw_test_cases_adsp2, }; static struct kunit_suite cs_dsp_wmfw_test_adsp2_32bit_wmfw1 = { .name = "cs_dsp_wmfwV1_adsp2_32bit", .init = cs_dsp_wmfw_test_adsp2_32bit_wmfw1_init, + .exit = cs_dsp_wmfw_test_exit, .test_cases = cs_dsp_wmfw_test_cases_adsp2, }; static struct kunit_suite cs_dsp_wmfw_test_adsp2_32bit_wmfw2 = { .name = "cs_dsp_wmfwV2_adsp2_32bit", .init = cs_dsp_wmfw_test_adsp2_32bit_wmfw2_init, + .exit = cs_dsp_wmfw_test_exit, .test_cases = cs_dsp_wmfw_test_cases_adsp2, }; static struct kunit_suite cs_dsp_wmfw_test_adsp2_16bit_wmfw0 = { .name = "cs_dsp_wmfwV0_adsp2_16bit", .init = cs_dsp_wmfw_test_adsp2_16bit_wmfw0_init, + .exit = cs_dsp_wmfw_test_exit, .test_cases = cs_dsp_wmfw_test_cases_adsp2, }; static struct kunit_suite cs_dsp_wmfw_test_adsp2_16bit_wmfw1 = { .name = "cs_dsp_wmfwV1_adsp2_16bit", .init = cs_dsp_wmfw_test_adsp2_16bit_wmfw1_init, + .exit = cs_dsp_wmfw_test_exit, .test_cases = cs_dsp_wmfw_test_cases_adsp2, }; static struct kunit_suite cs_dsp_wmfw_test_adsp2_16bit_wmfw2 = { .name = "cs_dsp_wmfwV2_adsp2_16bit", .init = cs_dsp_wmfw_test_adsp2_16bit_wmfw2_init, + .exit = cs_dsp_wmfw_test_exit, .test_cases = cs_dsp_wmfw_test_cases_adsp2, }; diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_wmfw_error.c b/drivers/firmware/cirrus/test/cs_dsp_test_wmfw_error.c index c309843261d724..37162d12e2fa78 100644 --- a/drivers/firmware/cirrus/test/cs_dsp_test_wmfw_error.c +++ b/drivers/firmware/cirrus/test/cs_dsp_test_wmfw_error.c @@ -18,6 +18,8 @@ #include #include +#include "../cs_dsp.h" + KUNIT_DEFINE_ACTION_WRAPPER(_put_device_wrapper, put_device, struct device *); KUNIT_DEFINE_ACTION_WRAPPER(_cs_dsp_remove_wrapper, cs_dsp_remove, struct cs_dsp *); @@ -989,11 +991,9 @@ static void wmfw_v2_coeff_description_exceeds_block(struct kunit *test) static void cs_dsp_wmfw_err_test_exit(struct kunit *test) { - /* - * Testing error conditions can produce a lot of log output - * from cs_dsp error messages, so rate limit the test cases. - */ - usleep_range(200, 500); + cs_dsp_suppress_err_messages = false; + cs_dsp_suppress_warn_messages = false; + cs_dsp_suppress_info_messages = false; } static int cs_dsp_wmfw_err_test_common_init(struct kunit *test, struct cs_dsp *dsp, @@ -1072,7 +1072,19 @@ static int cs_dsp_wmfw_err_test_common_init(struct kunit *test, struct cs_dsp *d return ret; /* Automatically call cs_dsp_remove() when test case ends */ - return kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); + ret = kunit_add_action_or_reset(priv->test, _cs_dsp_remove_wrapper, dsp); + if (ret) + return ret; + + /* + * Testing error conditions can produce a lot of log output + * from cs_dsp error messages, so suppress messages. + */ + cs_dsp_suppress_err_messages = true; + cs_dsp_suppress_warn_messages = true; + cs_dsp_suppress_info_messages = true; + + return 0; } static int cs_dsp_wmfw_err_test_halo_init(struct kunit *test) diff --git a/drivers/firmware/cirrus/test/cs_dsp_tests.c b/drivers/firmware/cirrus/test/cs_dsp_tests.c index 7b829a03ca5291..288675fdbdc534 100644 --- a/drivers/firmware/cirrus/test/cs_dsp_tests.c +++ b/drivers/firmware/cirrus/test/cs_dsp_tests.c @@ -12,3 +12,4 @@ MODULE_AUTHOR("Richard Fitzgerald "); MODULE_LICENSE("GPL"); MODULE_IMPORT_NS("FW_CS_DSP"); MODULE_IMPORT_NS("FW_CS_DSP_KUNIT_TEST_UTILS"); +MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING"); diff --git a/drivers/firmware/efi/cper-arm.c b/drivers/firmware/efi/cper-arm.c index f0a63d09d3c499..76542a53e20275 100644 --- a/drivers/firmware/efi/cper-arm.c +++ b/drivers/firmware/efi/cper-arm.c @@ -93,15 +93,11 @@ static void cper_print_arm_err_info(const char *pfx, u32 type, bool proc_context_corrupt, corrected, precise_pc, restartable_pc; bool time_out, access_mode; - /* If the type is unknown, bail. */ - if (type > CPER_ARM_MAX_TYPE) - return; - /* * Vendor type errors have error information values that are vendor * specific. */ - if (type == CPER_ARM_VENDOR_ERROR) + if (type & CPER_ARM_VENDOR_ERROR) return; if (error_info & CPER_ARM_ERR_VALID_TRANSACTION_TYPE) { @@ -116,43 +112,38 @@ static void cper_print_arm_err_info(const char *pfx, u32 type, if (error_info & CPER_ARM_ERR_VALID_OPERATION_TYPE) { op_type = ((error_info >> CPER_ARM_ERR_OPERATION_SHIFT) & CPER_ARM_ERR_OPERATION_MASK); - switch (type) { - case CPER_ARM_CACHE_ERROR: + if (type & CPER_ARM_CACHE_ERROR) { if (op_type < ARRAY_SIZE(arm_cache_err_op_strs)) { - printk("%soperation type: %s\n", pfx, + printk("%scache error, operation type: %s\n", pfx, arm_cache_err_op_strs[op_type]); } - break; - case CPER_ARM_TLB_ERROR: + } + if (type & CPER_ARM_TLB_ERROR) { if (op_type < ARRAY_SIZE(arm_tlb_err_op_strs)) { - printk("%soperation type: %s\n", pfx, + printk("%sTLB error, operation type: %s\n", pfx, arm_tlb_err_op_strs[op_type]); } - break; - case CPER_ARM_BUS_ERROR: + } + if (type & CPER_ARM_BUS_ERROR) { if (op_type < ARRAY_SIZE(arm_bus_err_op_strs)) { - printk("%soperation type: %s\n", pfx, + printk("%sbus error, operation type: %s\n", pfx, arm_bus_err_op_strs[op_type]); } - break; } } if (error_info & CPER_ARM_ERR_VALID_LEVEL) { level = ((error_info >> CPER_ARM_ERR_LEVEL_SHIFT) & CPER_ARM_ERR_LEVEL_MASK); - switch (type) { - case CPER_ARM_CACHE_ERROR: + if (type & CPER_ARM_CACHE_ERROR) printk("%scache level: %d\n", pfx, level); - break; - case CPER_ARM_TLB_ERROR: + + if (type & CPER_ARM_TLB_ERROR) printk("%sTLB level: %d\n", pfx, level); - break; - case CPER_ARM_BUS_ERROR: + + if (type & CPER_ARM_BUS_ERROR) printk("%saffinity level at which the bus error occurred: %d\n", pfx, level); - break; - } } if (error_info & CPER_ARM_ERR_VALID_PROC_CONTEXT_CORRUPT) { @@ -240,7 +231,8 @@ void cper_print_proc_arm(const char *pfx, int i, len, max_ctx_type; struct cper_arm_err_info *err_info; struct cper_arm_ctx_info *ctx_info; - char newpfx[64], infopfx[64]; + char newpfx[64], infopfx[ARRAY_SIZE(newpfx) + 1]; + char error_type[120]; printk("%sMIDR: 0x%016llx\n", pfx, proc->midr); @@ -289,9 +281,15 @@ void cper_print_proc_arm(const char *pfx, newpfx); } - printk("%serror_type: %d, %s\n", newpfx, err_info->type, - err_info->type < ARRAY_SIZE(cper_proc_error_type_strs) ? - cper_proc_error_type_strs[err_info->type] : "unknown"); + cper_bits_to_str(error_type, sizeof(error_type), + FIELD_GET(CPER_ARM_ERR_TYPE_MASK, err_info->type), + cper_proc_error_type_strs, + ARRAY_SIZE(cper_proc_error_type_strs)); + + printk("%serror_type: 0x%02x: %s%s\n", newpfx, err_info->type, + error_type, + (err_info->type & ~CPER_ARM_ERR_TYPE_MASK) ? " with reserved bit(s)" : ""); + if (err_info->validation_bits & CPER_ARM_INFO_VALID_ERR_INFO) { printk("%serror_info: 0x%016llx\n", newpfx, err_info->error_info); diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 928409199a1a40..322c6bdefb6110 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -12,6 +12,7 @@ * Specification version 2.4. */ +#include #include #include #include @@ -106,6 +107,65 @@ void cper_print_bits(const char *pfx, unsigned int bits, printk("%s\n", buf); } +/** + * cper_bits_to_str - return a string for set bits + * @buf: buffer to store the output string + * @buf_size: size of the output string buffer + * @bits: bit mask + * @strs: string array, indexed by bit position + * @strs_size: size of the string array: @strs + * + * Add to @buf the bitmask in hexadecimal. Then, for each set bit in @bits, + * add the corresponding string describing the bit in @strs to @buf. + * + * A typical example is:: + * + * const char * const bits[] = { + * "bit 3 name", + * "bit 4 name", + * "bit 5 name", + * }; + * char str[120]; + * unsigned int bitmask = BIT(3) | BIT(5); + * #define MASK GENMASK(5,3) + * + * cper_bits_to_str(str, sizeof(str), FIELD_GET(MASK, bitmask), + * bits, ARRAY_SIZE(bits)); + * + * The above code fills the string ``str`` with ``bit 3 name|bit 5 name``. + * + * Return: number of bytes stored or an error code if lower than zero. + */ +int cper_bits_to_str(char *buf, int buf_size, unsigned long bits, + const char * const strs[], unsigned int strs_size) +{ + int len = buf_size; + char *str = buf; + int i, size; + + *buf = '\0'; + + for_each_set_bit(i, &bits, strs_size) { + if (!(bits & BIT_ULL(i))) + continue; + + if (*buf && len > 0) { + *str = '|'; + len--; + str++; + } + + size = strscpy(str, strs[i], len); + if (size < 0) + return size; + + len -= size; + str += size; + } + return buf_size - len; +} +EXPORT_SYMBOL_GPL(cper_bits_to_str); + static const char * const proc_type_strs[] = { "IA32/X64", "IA64", diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 1ce428e2ac8a0e..c3cf5541ed682f 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -74,6 +74,9 @@ struct mm_struct efi_mm = { .page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock), .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), .cpu_bitmap = { [BITS_TO_LONGS(NR_CPUS)] = 0}, +#ifdef CONFIG_SCHED_MM_CID + .cpus_allowed_lock = __RAW_SPIN_LOCK_UNLOCKED(efi_mm.cpus_allowed_lock), +#endif }; struct workqueue_struct *efi_rts_wq; @@ -688,13 +691,13 @@ static __init int match_config_table(const efi_guid_t *guid, static __init void reserve_unaccepted(struct efi_unaccepted_memory *unaccepted) { - phys_addr_t start, size; + phys_addr_t start, end; start = PAGE_ALIGN_DOWN(efi.unaccepted); - size = PAGE_ALIGN(sizeof(*unaccepted) + unaccepted->size); + end = PAGE_ALIGN(efi.unaccepted + sizeof(*unaccepted) + unaccepted->size); - memblock_add(start, size); - memblock_reserve(start, size); + memblock_add(start, end - start); + memblock_reserve(start, end - start); } int __init efi_config_parse_tables(const efi_config_table_t *config_tables, diff --git a/drivers/firmware/efi/libstub/x86-5lvl.c b/drivers/firmware/efi/libstub/x86-5lvl.c index f1c5fb45d5f7cf..c00d0ae7ed5d5a 100644 --- a/drivers/firmware/efi/libstub/x86-5lvl.c +++ b/drivers/firmware/efi/libstub/x86-5lvl.c @@ -66,7 +66,7 @@ void efi_5level_switch(void) bool have_la57 = native_read_cr4() & X86_CR4_LA57; bool need_toggle = want_la57 ^ have_la57; u64 *pgt = (void *)la57_toggle + PAGE_SIZE; - u64 *cr3 = (u64 *)__native_read_cr3(); + pgd_t *cr3 = (pgd_t *)native_read_cr3_pa(); u64 *new_cr3; if (!la57_toggle || !need_toggle) @@ -82,7 +82,7 @@ void efi_5level_switch(void) new_cr3[0] = (u64)cr3 | _PAGE_TABLE_NOENC; } else { /* take the new root table pointer from the current entry #0 */ - new_cr3 = (u64 *)(cr3[0] & PAGE_MASK); + new_cr3 = (u64 *)(native_pgd_val(cr3[0]) & PTE_PFN_MASK); /* copy the new root table if it is not 32-bit addressable */ if ((u64)new_cr3 > U32_MAX) diff --git a/drivers/firmware/imx/imx-scu-irq.c b/drivers/firmware/imx/imx-scu-irq.c index 6125cccc9ba79c..f587abcd7ca3aa 100644 --- a/drivers/firmware/imx/imx-scu-irq.c +++ b/drivers/firmware/imx/imx-scu-irq.c @@ -203,6 +203,18 @@ int imx_scu_enable_general_irq_channel(struct device *dev) struct mbox_chan *ch; int ret = 0, i = 0; + if (!of_parse_phandle_with_args(dev->of_node, "mboxes", + "#mbox-cells", 0, &spec)) { + i = of_alias_get_id(spec.np, "mu"); + of_node_put(spec.np); + } + + /* use mu1 as general mu irq channel if failed */ + if (i < 0) + i = 1; + + mu_resource_id = IMX_SC_R_MU_0A + i; + ret = imx_scu_get_handle(&imx_sc_irq_ipc_handle); if (ret) return ret; @@ -214,6 +226,8 @@ int imx_scu_enable_general_irq_channel(struct device *dev) cl->dev = dev; cl->rx_callback = imx_scu_irq_callback; + INIT_WORK(&imx_sc_irq_work, imx_scu_irq_work_handler); + /* SCU general IRQ uses general interrupt channel 3 */ ch = mbox_request_channel_byname(cl, "gip3"); if (IS_ERR(ch)) { @@ -223,18 +237,6 @@ int imx_scu_enable_general_irq_channel(struct device *dev) return ret; } - INIT_WORK(&imx_sc_irq_work, imx_scu_irq_work_handler); - - if (!of_parse_phandle_with_args(dev->of_node, "mboxes", - "#mbox-cells", 0, &spec)) - i = of_alias_get_id(spec.np, "mu"); - - /* use mu1 as general mu irq channel if failed */ - if (i < 0) - i = 1; - - mu_resource_id = IMX_SC_R_MU_0A + i; - /* Create directory under /sysfs/firmware */ wakeup_obj = kobject_create_and_add("scu_wakeup_source", firmware_kobj); if (!wakeup_obj) { diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c index 00f58e27f6de53..1d24e82f3d09d8 100644 --- a/drivers/firmware/stratix10-svc.c +++ b/drivers/firmware/stratix10-svc.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2017-2018, Intel Corporation + * Copyright (C) 2025, Altera Corporation */ #include @@ -52,6 +53,7 @@ struct stratix10_svc_chan; /** * struct stratix10_svc - svc private data * @stratix10_svc_rsu: pointer to stratix10 RSU device + * @intel_svc_fcs: pointer to the FCS device */ struct stratix10_svc { struct platform_device *stratix10_svc_rsu; @@ -174,6 +176,12 @@ struct stratix10_svc_chan { static LIST_HEAD(svc_ctrl); static LIST_HEAD(svc_data_mem); +/** + * svc_mem_lock protects access to the svc_data_mem list for + * concurrent multi-client operations + */ +static DEFINE_MUTEX(svc_mem_lock); + /** * svc_pa_to_va() - translate physical address to virtual address * @addr: to be translated physical address @@ -186,6 +194,7 @@ static void *svc_pa_to_va(unsigned long addr) struct stratix10_svc_data_mem *pmem; pr_debug("claim back P-addr=0x%016x\n", (unsigned int)addr); + guard(mutex)(&svc_mem_lock); list_for_each_entry(pmem, &svc_data_mem, node) if (pmem->paddr == addr) return pmem->vaddr; @@ -992,6 +1001,7 @@ int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg) p_data->flag = ct->flags; } } else { + guard(mutex)(&svc_mem_lock); list_for_each_entry(p_mem, &svc_data_mem, node) if (p_mem->vaddr == p_msg->payload) { p_data->paddr = p_mem->paddr; @@ -1074,6 +1084,7 @@ void *stratix10_svc_allocate_memory(struct stratix10_svc_chan *chan, if (!pmem) return ERR_PTR(-ENOMEM); + guard(mutex)(&svc_mem_lock); va = gen_pool_alloc(genpool, s); if (!va) return ERR_PTR(-ENOMEM); @@ -1102,6 +1113,7 @@ EXPORT_SYMBOL_GPL(stratix10_svc_allocate_memory); void stratix10_svc_free_memory(struct stratix10_svc_chan *chan, void *kaddr) { struct stratix10_svc_data_mem *pmem; + guard(mutex)(&svc_mem_lock); list_for_each_entry(pmem, &svc_data_mem, node) if (pmem->vaddr == kaddr) { diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c index 49fd2ae01055d0..8d96a3c12b36a9 100644 --- a/drivers/firmware/ti_sci.c +++ b/drivers/firmware/ti_sci.c @@ -3751,9 +3751,11 @@ static int __maybe_unused ti_sci_suspend_noirq(struct device *dev) struct ti_sci_info *info = dev_get_drvdata(dev); int ret = 0; - ret = ti_sci_cmd_set_io_isolation(&info->handle, TISCI_MSG_VALUE_IO_ENABLE); - if (ret) - return ret; + if (info->fw_caps & MSG_FLAG_CAPS_IO_ISOLATION) { + ret = ti_sci_cmd_set_io_isolation(&info->handle, TISCI_MSG_VALUE_IO_ENABLE); + if (ret) + return ret; + } return 0; } @@ -3767,9 +3769,11 @@ static int __maybe_unused ti_sci_resume_noirq(struct device *dev) u8 pin; u8 mode; - ret = ti_sci_cmd_set_io_isolation(&info->handle, TISCI_MSG_VALUE_IO_DISABLE); - if (ret) - return ret; + if (info->fw_caps & MSG_FLAG_CAPS_IO_ISOLATION) { + ret = ti_sci_cmd_set_io_isolation(&info->handle, TISCI_MSG_VALUE_IO_DISABLE); + if (ret) + return ret; + } ret = ti_sci_msg_cmd_lpm_wake_reason(&info->handle, &source, &time, &pin, &mode); /* Do not fail to resume on error as the wake reason is not critical */ @@ -3928,11 +3932,12 @@ static int ti_sci_probe(struct platform_device *pdev) } ti_sci_msg_cmd_query_fw_caps(&info->handle, &info->fw_caps); - dev_dbg(dev, "Detected firmware capabilities: %s%s%s%s\n", + dev_dbg(dev, "Detected firmware capabilities: %s%s%s%s%s\n", info->fw_caps & MSG_FLAG_CAPS_GENERIC ? "Generic" : "", info->fw_caps & MSG_FLAG_CAPS_LPM_PARTIAL_IO ? " Partial-IO" : "", info->fw_caps & MSG_FLAG_CAPS_LPM_DM_MANAGED ? " DM-Managed" : "", - info->fw_caps & MSG_FLAG_CAPS_LPM_ABORT ? " LPM-Abort" : "" + info->fw_caps & MSG_FLAG_CAPS_LPM_ABORT ? " LPM-Abort" : "", + info->fw_caps & MSG_FLAG_CAPS_IO_ISOLATION ? " IO-Isolation" : "" ); ti_sci_setup_ops(info); diff --git a/drivers/firmware/ti_sci.h b/drivers/firmware/ti_sci.h index 701c416b2e78f8..7559cde17b6ccf 100644 --- a/drivers/firmware/ti_sci.h +++ b/drivers/firmware/ti_sci.h @@ -149,6 +149,7 @@ struct ti_sci_msg_req_reboot { * MSG_FLAG_CAPS_LPM_PARTIAL_IO: Partial IO in LPM * MSG_FLAG_CAPS_LPM_DM_MANAGED: LPM can be managed by DM * MSG_FLAG_CAPS_LPM_ABORT: Abort entry to LPM + * MSG_FLAG_CAPS_IO_ISOLATION: IO Isolation support * * Response to a generic message with message type TI_SCI_MSG_QUERY_FW_CAPS * providing currently available SOC/firmware capabilities. SoC that don't @@ -160,6 +161,7 @@ struct ti_sci_msg_resp_query_fw_caps { #define MSG_FLAG_CAPS_LPM_PARTIAL_IO TI_SCI_MSG_FLAG(4) #define MSG_FLAG_CAPS_LPM_DM_MANAGED TI_SCI_MSG_FLAG(5) #define MSG_FLAG_CAPS_LPM_ABORT TI_SCI_MSG_FLAG(9) +#define MSG_FLAG_CAPS_IO_ISOLATION TI_SCI_MSG_FLAG(7) #define MSG_MASK_CAPS_LPM GENMASK_ULL(4, 1) u64 fw_caps; } __packed; diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 7ee3afbc2b05da..e053524c5e35f1 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -738,7 +738,6 @@ config GPIO_TB10X depends on ARC_PLAT_TB10X || COMPILE_TEST select GPIO_GENERIC select GENERIC_IRQ_CHIP - select OF_GPIO config GPIO_TEGRA tristate "NVIDIA Tegra GPIO support" diff --git a/drivers/gpio/gpio-amd-fch.c b/drivers/gpio/gpio-amd-fch.c index e6c6c3ec7656e9..9f329938202bff 100644 --- a/drivers/gpio/gpio-amd-fch.c +++ b/drivers/gpio/gpio-amd-fch.c @@ -8,6 +8,7 @@ * */ +#include #include #include #include @@ -120,15 +121,15 @@ static int amd_fch_gpio_get(struct gpio_chip *gc, unsigned int offset) { unsigned long flags; - int ret; + u32 val; struct amd_fch_gpio_priv *priv = gpiochip_get_data(gc); void __iomem *ptr = amd_fch_gpio_addr(priv, offset); spin_lock_irqsave(&priv->lock, flags); - ret = (readl_relaxed(ptr) & AMD_FCH_GPIO_FLAG_READ); + val = readl_relaxed(ptr); spin_unlock_irqrestore(&priv->lock, flags); - return ret; + return FIELD_GET(AMD_FCH_GPIO_FLAG_READ, val); } static int amd_fch_gpio_request(struct gpio_chip *chip, diff --git a/drivers/gpio/gpio-brcmstb.c b/drivers/gpio/gpio-brcmstb.c index f40c9472588bc7..f0cb1991b326cd 100644 --- a/drivers/gpio/gpio-brcmstb.c +++ b/drivers/gpio/gpio-brcmstb.c @@ -301,12 +301,10 @@ static struct brcmstb_gpio_bank *brcmstb_gpio_hwirq_to_bank( struct brcmstb_gpio_priv *priv, irq_hw_number_t hwirq) { struct brcmstb_gpio_bank *bank; - int i = 0; - /* banks are in descending order */ - list_for_each_entry_reverse(bank, &priv->bank_list, node) { - i += bank->chip.gc.ngpio; - if (hwirq < i) + list_for_each_entry(bank, &priv->bank_list, node) { + if (hwirq >= bank->chip.gc.offset && + hwirq < (bank->chip.gc.offset + bank->chip.gc.ngpio)) return bank; } return NULL; diff --git a/drivers/gpio/gpio-it87.c b/drivers/gpio/gpio-it87.c index 5d677bcfccf26f..2ad3c239367bcc 100644 --- a/drivers/gpio/gpio-it87.c +++ b/drivers/gpio/gpio-it87.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -241,23 +242,17 @@ static int it87_gpio_direction_out(struct gpio_chip *chip, mask = 1 << (gpio_num % 8); group = (gpio_num / 8); - spin_lock(&it87_gpio->lock); + guard(spinlock)(&it87_gpio->lock); rc = superio_enter(); if (rc) - goto exit; + return rc; /* set the output enable bit */ superio_set_mask(mask, group + it87_gpio->output_base); rc = it87_gpio_set(chip, gpio_num, val); - if (rc) - goto exit; - superio_exit(); - -exit: - spin_unlock(&it87_gpio->lock); return rc; } diff --git a/drivers/gpio/gpio-loongson-64bit.c b/drivers/gpio/gpio-loongson-64bit.c index 02f181cb219e99..d5573fb0616ce6 100644 --- a/drivers/gpio/gpio-loongson-64bit.c +++ b/drivers/gpio/gpio-loongson-64bit.c @@ -263,7 +263,7 @@ static int loongson_gpio_init_irqchip(struct platform_device *pdev, chip->irq.num_parents = data->intr_num; chip->irq.parents = devm_kcalloc(&pdev->dev, data->intr_num, sizeof(*chip->irq.parents), GFP_KERNEL); - if (!chip->parent) + if (!chip->irq.parents) return -ENOMEM; for (i = 0; i < data->intr_num; i++) { @@ -407,11 +407,11 @@ static const struct loongson_gpio_chip_data loongson_gpio_ls2k2000_data0 = { static const struct loongson_gpio_chip_data loongson_gpio_ls2k2000_data1 = { .label = "ls2k2000_gpio", - .mode = BIT_CTRL_MODE, - .conf_offset = 0x0, - .in_offset = 0x20, - .out_offset = 0x10, - .inten_offset = 0x30, + .mode = BYTE_CTRL_MODE, + .conf_offset = 0x800, + .in_offset = 0xa00, + .out_offset = 0x900, + .inten_offset = 0xb00, }; static const struct loongson_gpio_chip_data loongson_gpio_ls2k2000_data2 = { diff --git a/drivers/gpio/gpio-mpsse.c b/drivers/gpio/gpio-mpsse.c index 9f42bb30b4ec7c..120b27183b1d9e 100644 --- a/drivers/gpio/gpio-mpsse.c +++ b/drivers/gpio/gpio-mpsse.c @@ -10,6 +10,7 @@ #include #include #include +#include #include struct mpsse_priv { @@ -17,8 +18,10 @@ struct mpsse_priv { struct usb_device *udev; /* USB device encompassing all MPSSEs */ struct usb_interface *intf; /* USB interface for this MPSSE */ u8 intf_id; /* USB interface number for this MPSSE */ - struct work_struct irq_work; /* polling work thread */ + struct list_head workers; /* polling work threads */ struct mutex irq_mutex; /* lock over irq_data */ + struct mutex irq_race; /* race for polling worker teardown */ + raw_spinlock_t irq_spin; /* protects worker list */ atomic_t irq_type[16]; /* pin -> edge detection type */ atomic_t irq_enabled; int id; @@ -26,6 +29,9 @@ struct mpsse_priv { u8 gpio_outputs[2]; /* Output states for GPIOs [L, H] */ u8 gpio_dir[2]; /* Directions for GPIOs [L, H] */ + unsigned long dir_in; /* Bitmask of valid input pins */ + unsigned long dir_out; /* Bitmask of valid output pins */ + u8 *bulk_in_buf; /* Extra recv buffer to grab status bytes */ struct usb_endpoint_descriptor *bulk_in; @@ -34,6 +40,14 @@ struct mpsse_priv { struct mutex io_mutex; /* sync I/O with disconnect */ }; +struct mpsse_worker { + struct mpsse_priv *priv; + struct work_struct work; + atomic_t cancelled; + struct list_head list; /* linked list */ + struct list_head destroy; /* teardown linked list */ +}; + struct bulk_desc { bool tx; /* direction of bulk transfer */ u8 *data; /* input (tx) or output (rx) */ @@ -43,6 +57,14 @@ struct bulk_desc { int timeout; }; +#define MPSSE_NGPIO 16 + +struct mpsse_quirk { + const char *names[MPSSE_NGPIO]; /* Pin names, if applicable */ + unsigned long dir_in; /* Bitmask of valid input pins */ + unsigned long dir_out; /* Bitmask of valid output pins */ +}; + static const struct usb_device_id gpio_mpsse_table[] = { { USB_DEVICE(0x0c52, 0xa064) }, /* SeaLevel Systems, Inc. */ { } /* Terminating entry */ @@ -160,6 +182,32 @@ static int gpio_mpsse_get_bank(struct mpsse_priv *priv, u8 bank) return buf; } +static int mpsse_ensure_supported(struct gpio_chip *chip, + unsigned long mask, int direction) +{ + unsigned long supported, unsupported; + char *type = "input"; + struct mpsse_priv *priv = gpiochip_get_data(chip); + + supported = priv->dir_in; + if (direction == GPIO_LINE_DIRECTION_OUT) { + supported = priv->dir_out; + type = "output"; + } + + /* An invalid bit was in the provided mask */ + unsupported = mask & ~supported; + if (unsupported) { + dev_err(&priv->udev->dev, + "mpsse: GPIO %lu doesn't support %s\n", + find_first_bit(&unsupported, sizeof(unsupported) * 8), + type); + return -EOPNOTSUPP; + } + + return 0; +} + static int gpio_mpsse_set_multiple(struct gpio_chip *chip, unsigned long *mask, unsigned long *bits) { @@ -167,6 +215,10 @@ static int gpio_mpsse_set_multiple(struct gpio_chip *chip, unsigned long *mask, int ret; struct mpsse_priv *priv = gpiochip_get_data(chip); + ret = mpsse_ensure_supported(chip, *mask, GPIO_LINE_DIRECTION_OUT); + if (ret) + return ret; + guard(mutex)(&priv->io_mutex); for_each_set_clump8(i, bank_mask, mask, chip->ngpio) { bank = i / 8; @@ -194,6 +246,10 @@ static int gpio_mpsse_get_multiple(struct gpio_chip *chip, unsigned long *mask, int ret; struct mpsse_priv *priv = gpiochip_get_data(chip); + ret = mpsse_ensure_supported(chip, *mask, GPIO_LINE_DIRECTION_IN); + if (ret) + return ret; + guard(mutex)(&priv->io_mutex); for_each_set_clump8(i, bank_mask, mask, chip->ngpio) { bank = i / 8; @@ -242,10 +298,15 @@ static int gpio_mpsse_gpio_set(struct gpio_chip *chip, unsigned int offset, static int gpio_mpsse_direction_output(struct gpio_chip *chip, unsigned int offset, int value) { + int ret; struct mpsse_priv *priv = gpiochip_get_data(chip); int bank = (offset & 8) >> 3; int bank_offset = offset & 7; + ret = mpsse_ensure_supported(chip, BIT(offset), GPIO_LINE_DIRECTION_OUT); + if (ret) + return ret; + scoped_guard(mutex, &priv->io_mutex) priv->gpio_dir[bank] |= BIT(bank_offset); @@ -255,10 +316,15 @@ static int gpio_mpsse_direction_output(struct gpio_chip *chip, static int gpio_mpsse_direction_input(struct gpio_chip *chip, unsigned int offset) { + int ret; struct mpsse_priv *priv = gpiochip_get_data(chip); int bank = (offset & 8) >> 3; int bank_offset = offset & 7; + ret = mpsse_ensure_supported(chip, BIT(offset), GPIO_LINE_DIRECTION_IN); + if (ret) + return ret; + guard(mutex)(&priv->io_mutex); priv->gpio_dir[bank] &= ~BIT(bank_offset); gpio_mpsse_set_bank(priv, bank); @@ -284,18 +350,62 @@ static int gpio_mpsse_get_direction(struct gpio_chip *chip, return ret; } -static void gpio_mpsse_poll(struct work_struct *work) +/* + * Stops all workers except `my_worker`. + * Safe to call only when `irq_race` is held. + */ +static void gpio_mpsse_stop_all_except(struct mpsse_priv *priv, + struct mpsse_worker *my_worker) +{ + struct mpsse_worker *worker, *worker_tmp; + struct list_head destructors = LIST_HEAD_INIT(destructors); + + scoped_guard(raw_spinlock_irqsave, &priv->irq_spin) { + list_for_each_entry_safe(worker, worker_tmp, + &priv->workers, list) { + /* Don't stop ourselves */ + if (worker == my_worker) + continue; + + list_del(&worker->list); + + /* Give worker a chance to terminate itself */ + atomic_set(&worker->cancelled, 1); + /* Keep track of stuff to cancel */ + INIT_LIST_HEAD(&worker->destroy); + list_add(&worker->destroy, &destructors); + } + } + + list_for_each_entry_safe(worker, worker_tmp, + &destructors, destroy) { + list_del(&worker->destroy); + cancel_work_sync(&worker->work); + kfree(worker); + } +} + +static void gpio_mpsse_poll(struct work_struct *my_work) { unsigned long pin_mask, pin_states, flags; int irq_enabled, offset, err, value, fire_irq, irq, old_value[16], irq_type[16]; - struct mpsse_priv *priv = container_of(work, struct mpsse_priv, - irq_work); + struct mpsse_worker *my_worker = container_of(my_work, struct mpsse_worker, work); + struct mpsse_priv *priv = my_worker->priv; for (offset = 0; offset < priv->gpio.ngpio; ++offset) old_value[offset] = -1; - while ((irq_enabled = atomic_read(&priv->irq_enabled))) { + /* + * We only want one worker. Workers race to acquire irq_race and tear + * down all other workers. This is a cond guard so that we don't deadlock + * trying to cancel a worker. + */ + scoped_cond_guard(mutex_try, return, &priv->irq_race) + gpio_mpsse_stop_all_except(priv, my_worker); + + while ((irq_enabled = atomic_read(&priv->irq_enabled)) && + !atomic_read(&my_worker->cancelled)) { usleep_range(MPSSE_POLL_INTERVAL, MPSSE_POLL_INTERVAL + 1000); /* Cleanup will trigger at the end of the loop */ guard(mutex)(&priv->irq_mutex); @@ -370,21 +480,45 @@ static int gpio_mpsse_set_irq_type(struct irq_data *irqd, unsigned int type) static void gpio_mpsse_irq_disable(struct irq_data *irqd) { + struct mpsse_worker *worker; struct mpsse_priv *priv = irq_data_get_irq_chip_data(irqd); atomic_and(~BIT(irqd->hwirq), &priv->irq_enabled); gpiochip_disable_irq(&priv->gpio, irqd->hwirq); + + /* + * Can't actually do teardown in IRQ context (it blocks). + * As a result, these workers will stick around until irq is reenabled + * or device gets disconnected + */ + scoped_guard(raw_spinlock_irqsave, &priv->irq_spin) + list_for_each_entry(worker, &priv->workers, list) + atomic_set(&worker->cancelled, 1); } static void gpio_mpsse_irq_enable(struct irq_data *irqd) { + struct mpsse_worker *worker; struct mpsse_priv *priv = irq_data_get_irq_chip_data(irqd); gpiochip_enable_irq(&priv->gpio, irqd->hwirq); /* If no-one else was using the IRQ, enable it */ if (!atomic_fetch_or(BIT(irqd->hwirq), &priv->irq_enabled)) { - INIT_WORK(&priv->irq_work, gpio_mpsse_poll); - schedule_work(&priv->irq_work); + /* + * Can't be devm because it uses a non-raw spinlock (illegal in + * this context, where a raw spinlock is held by our caller) + */ + worker = kzalloc(sizeof(*worker), GFP_NOWAIT); + if (!worker) + return; + + worker->priv = priv; + INIT_LIST_HEAD(&worker->list); + INIT_WORK(&worker->work, gpio_mpsse_poll); + schedule_work(&worker->work); + + scoped_guard(raw_spinlock_irqsave, &priv->irq_spin) + list_add(&worker->list, &priv->workers); } } @@ -404,19 +538,61 @@ static void gpio_mpsse_ida_remove(void *data) ida_free(&gpio_mpsse_ida, priv->id); } +static void gpio_mpsse_usb_put_dev(void *data) +{ + struct mpsse_priv *priv = data; + + usb_put_dev(priv->udev); +} + +static int mpsse_init_valid_mask(struct gpio_chip *chip, + unsigned long *valid_mask, + unsigned int ngpios) +{ + struct mpsse_priv *priv = gpiochip_get_data(chip); + + if (WARN_ON(priv == NULL)) + return -ENODEV; + + *valid_mask = priv->dir_in | priv->dir_out; + + return 0; +} + +static void mpsse_irq_init_valid_mask(struct gpio_chip *chip, + unsigned long *valid_mask, + unsigned int ngpios) +{ + struct mpsse_priv *priv = gpiochip_get_data(chip); + + if (WARN_ON(priv == NULL)) + return; + + /* Can only use IRQ on input capable pins */ + *valid_mask = priv->dir_in; +} + static int gpio_mpsse_probe(struct usb_interface *interface, const struct usb_device_id *id) { struct mpsse_priv *priv; struct device *dev; + char *serial; int err; + struct mpsse_quirk *quirk = (void *)id->driver_info; dev = &interface->dev; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; + INIT_LIST_HEAD(&priv->workers); + priv->udev = usb_get_dev(interface_to_usbdev(interface)); + err = devm_add_action_or_reset(dev, gpio_mpsse_usb_put_dev, priv); + if (err) + return err; + priv->intf = interface; priv->intf_id = interface->cur_altsetting->desc.bInterfaceNumber; @@ -436,9 +612,21 @@ static int gpio_mpsse_probe(struct usb_interface *interface, if (err) return err; + err = devm_mutex_init(dev, &priv->irq_race); + if (err) + return err; + + raw_spin_lock_init(&priv->irq_spin); + + serial = priv->udev->serial; + if (!serial) + serial = "NONE"; + priv->gpio.label = devm_kasprintf(dev, GFP_KERNEL, - "gpio-mpsse.%d.%d", - priv->id, priv->intf_id); + "MPSSE%04x:%04x.%d.%d.%s", + id->idVendor, id->idProduct, + priv->intf_id, priv->id, + serial); if (!priv->gpio.label) return -ENOMEM; @@ -452,10 +640,20 @@ static int gpio_mpsse_probe(struct usb_interface *interface, priv->gpio.get_multiple = gpio_mpsse_get_multiple; priv->gpio.set_multiple = gpio_mpsse_set_multiple; priv->gpio.base = -1; - priv->gpio.ngpio = 16; + priv->gpio.ngpio = MPSSE_NGPIO; priv->gpio.offset = priv->intf_id * priv->gpio.ngpio; priv->gpio.can_sleep = 1; + if (quirk) { + priv->dir_out = quirk->dir_out; + priv->dir_in = quirk->dir_in; + priv->gpio.names = quirk->names; + priv->gpio.init_valid_mask = mpsse_init_valid_mask; + } else { + priv->dir_in = U16_MAX; + priv->dir_out = U16_MAX; + } + err = usb_find_common_endpoints(interface->cur_altsetting, &priv->bulk_in, &priv->bulk_out, NULL, NULL); @@ -494,6 +692,7 @@ static int gpio_mpsse_probe(struct usb_interface *interface, priv->gpio.irq.parents = NULL; priv->gpio.irq.default_type = IRQ_TYPE_NONE; priv->gpio.irq.handler = handle_simple_irq; + priv->gpio.irq.init_valid_mask = mpsse_irq_init_valid_mask; err = devm_gpiochip_add_data(dev, &priv->gpio, priv); if (err) @@ -506,9 +705,15 @@ static void gpio_mpsse_disconnect(struct usb_interface *intf) { struct mpsse_priv *priv = usb_get_intfdata(intf); + /* + * Lock prevents double-free of worker from here and the teardown + * step at the beginning of gpio_mpsse_poll + */ + scoped_guard(mutex, &priv->irq_race) + gpio_mpsse_stop_all_except(priv, NULL); + priv->intf = NULL; usb_set_intfdata(intf, NULL); - usb_put_dev(priv->udev); } static struct usb_driver gpio_mpsse_driver = { diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index a268c76bdca62d..8693544304fa8f 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -799,10 +799,13 @@ static struct platform_device omap_mpuio_device = { static inline void omap_mpuio_init(struct gpio_bank *bank) { - platform_set_drvdata(&omap_mpuio_device, bank); + static bool registered; - if (platform_driver_register(&omap_mpuio_driver) == 0) - (void) platform_device_register(&omap_mpuio_device); + platform_set_drvdata(&omap_mpuio_device, bank); + if (!registered) { + (void)platform_device_register(&omap_mpuio_device); + registered = true; + } } /*---------------------------------------------------------------------*/ @@ -1576,13 +1579,24 @@ static struct platform_driver omap_gpio_driver = { */ static int __init omap_gpio_drv_reg(void) { - return platform_driver_register(&omap_gpio_driver); + int ret; + + ret = platform_driver_register(&omap_mpuio_driver); + if (ret) + return ret; + + ret = platform_driver_register(&omap_gpio_driver); + if (ret) + platform_driver_unregister(&omap_mpuio_driver); + + return ret; } postcore_initcall(omap_gpio_drv_reg); static void __exit omap_gpio_exit(void) { platform_driver_unregister(&omap_gpio_driver); + platform_driver_unregister(&omap_mpuio_driver); } module_exit(omap_gpio_exit); diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index b46927f550389a..34cadce9b31017 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -911,6 +911,8 @@ static void pca953x_irq_shutdown(struct irq_data *d) clear_bit(hwirq, chip->irq_trig_fall); clear_bit(hwirq, chip->irq_trig_level_low); clear_bit(hwirq, chip->irq_trig_level_high); + + pca953x_irq_mask(d); } static void pca953x_irq_print_chip(struct irq_data *data, struct seq_file *p) @@ -940,14 +942,35 @@ static bool pca953x_irq_pending(struct pca953x_chip *chip, unsigned long *pendin DECLARE_BITMAP(old_stat, MAX_LINE); DECLARE_BITMAP(cur_stat, MAX_LINE); DECLARE_BITMAP(new_stat, MAX_LINE); + DECLARE_BITMAP(int_stat, MAX_LINE); DECLARE_BITMAP(trigger, MAX_LINE); DECLARE_BITMAP(edges, MAX_LINE); int ret; + if (chip->driver_data & PCA_PCAL) { + /* Read INT_STAT before it is cleared by the input-port read. */ + ret = pca953x_read_regs(chip, PCAL953X_INT_STAT, int_stat); + if (ret) + return false; + } + ret = pca953x_read_regs(chip, chip->regs->input, cur_stat); if (ret) return false; + if (chip->driver_data & PCA_PCAL) { + /* Detect short pulses via INT_STAT. */ + bitmap_and(trigger, int_stat, chip->irq_mask, gc->ngpio); + + /* Apply filter for rising/falling edge selection. */ + bitmap_replace(new_stat, chip->irq_trig_fall, chip->irq_trig_raise, + cur_stat, gc->ngpio); + + bitmap_and(int_stat, new_stat, trigger, gc->ngpio); + } else { + bitmap_zero(int_stat, gc->ngpio); + } + /* Remove output pins from the equation */ pca953x_read_regs(chip, chip->regs->direction, reg_direction); @@ -961,7 +984,8 @@ static bool pca953x_irq_pending(struct pca953x_chip *chip, unsigned long *pendin if (bitmap_empty(chip->irq_trig_level_high, gc->ngpio) && bitmap_empty(chip->irq_trig_level_low, gc->ngpio)) { - if (bitmap_empty(trigger, gc->ngpio)) + if (bitmap_empty(trigger, gc->ngpio) && + bitmap_empty(int_stat, gc->ngpio)) return false; } @@ -969,6 +993,7 @@ static bool pca953x_irq_pending(struct pca953x_chip *chip, unsigned long *pendin bitmap_and(old_stat, chip->irq_trig_raise, new_stat, gc->ngpio); bitmap_or(edges, old_stat, cur_stat, gc->ngpio); bitmap_and(pending, edges, trigger, gc->ngpio); + bitmap_or(pending, pending, int_stat, gc->ngpio); bitmap_and(cur_stat, new_stat, chip->irq_trig_level_high, gc->ngpio); bitmap_and(cur_stat, cur_stat, chip->irq_mask, gc->ngpio); diff --git a/drivers/gpio/gpio-regmap.c b/drivers/gpio/gpio-regmap.c index f4267af00027e2..c64805dcb9f885 100644 --- a/drivers/gpio/gpio-regmap.c +++ b/drivers/gpio/gpio-regmap.c @@ -328,7 +328,7 @@ struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config config->regmap_irq_line, config->regmap_irq_flags, 0, config->regmap_irq_chip, &gpio->irq_chip_data); if (ret) - goto err_free_bitmap; + goto err_remove_gpiochip; irq_domain = regmap_irq_get_domain(gpio->irq_chip_data); } else diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index 47174eb3ba76fb..0fff4a699f12d1 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -164,12 +163,6 @@ static int rockchip_gpio_set_direction(struct gpio_chip *chip, unsigned long flags; u32 data = input ? 0 : 1; - - if (input) - pinctrl_gpio_direction_input(chip, offset); - else - pinctrl_gpio_direction_output(chip, offset); - raw_spin_lock_irqsave(&bank->slock, flags); rockchip_gpio_writel_bit(bank, offset, data, bank->gpio_regs->port_ddr); raw_spin_unlock_irqrestore(&bank->slock, flags); diff --git a/drivers/gpio/gpio-sprd.c b/drivers/gpio/gpio-sprd.c index 413bcd0a424050..2cc8abe705cdb7 100644 --- a/drivers/gpio/gpio-sprd.c +++ b/drivers/gpio/gpio-sprd.c @@ -35,7 +35,7 @@ struct sprd_gpio { struct gpio_chip chip; void __iomem *base; - spinlock_t lock; + raw_spinlock_t lock; int irq; }; @@ -54,7 +54,7 @@ static void sprd_gpio_update(struct gpio_chip *chip, unsigned int offset, unsigned long flags; u32 tmp; - spin_lock_irqsave(&sprd_gpio->lock, flags); + raw_spin_lock_irqsave(&sprd_gpio->lock, flags); tmp = readl_relaxed(base + reg); if (val) @@ -63,7 +63,7 @@ static void sprd_gpio_update(struct gpio_chip *chip, unsigned int offset, tmp &= ~BIT(SPRD_GPIO_BIT(offset)); writel_relaxed(tmp, base + reg); - spin_unlock_irqrestore(&sprd_gpio->lock, flags); + raw_spin_unlock_irqrestore(&sprd_gpio->lock, flags); } static int sprd_gpio_read(struct gpio_chip *chip, unsigned int offset, u16 reg) @@ -236,7 +236,7 @@ static int sprd_gpio_probe(struct platform_device *pdev) if (IS_ERR(sprd_gpio->base)) return PTR_ERR(sprd_gpio->base); - spin_lock_init(&sprd_gpio->lock); + raw_spin_lock_init(&sprd_gpio->lock); sprd_gpio->chip.label = dev_name(&pdev->dev); sprd_gpio->chip.ngpio = SPRD_GPIO_NR; diff --git a/drivers/gpio/gpio-virtuser.c b/drivers/gpio/gpio-virtuser.c index a10eab7d2617e4..252fec5ea38354 100644 --- a/drivers/gpio/gpio-virtuser.c +++ b/drivers/gpio/gpio-virtuser.c @@ -1684,10 +1684,10 @@ static void gpio_virtuser_device_config_group_release(struct config_item *item) { struct gpio_virtuser_device *dev = to_gpio_virtuser_device(item); - guard(mutex)(&dev->lock); - - if (gpio_virtuser_device_is_live(dev)) - gpio_virtuser_device_deactivate(dev); + scoped_guard(mutex, &dev->lock) { + if (gpio_virtuser_device_is_live(dev)) + gpio_virtuser_device_deactivate(dev); + } mutex_destroy(&dev->lock); ida_free(&gpio_virtuser_ida, dev->id); diff --git a/drivers/gpio/gpiolib-acpi-core.c b/drivers/gpio/gpiolib-acpi-core.c index d441c1236d8ca1..8110690ea69d0b 100644 --- a/drivers/gpio/gpiolib-acpi-core.c +++ b/drivers/gpio/gpiolib-acpi-core.c @@ -1104,6 +1104,7 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address, unsigned int pin = agpio->pin_table[i]; struct acpi_gpio_connection *conn; struct gpio_desc *desc; + u16 word, shift; bool found; mutex_lock(&achip->conn_lock); @@ -1158,10 +1159,22 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address, mutex_unlock(&achip->conn_lock); - if (function == ACPI_WRITE) - gpiod_set_raw_value_cansleep(desc, !!(*value & BIT(i))); - else - *value |= (u64)gpiod_get_raw_value_cansleep(desc) << i; + /* + * For the cases when OperationRegion() consists of more than + * 64 bits calculate the word and bit shift to use that one to + * access the value. + */ + word = i / 64; + shift = i % 64; + + if (function == ACPI_WRITE) { + gpiod_set_raw_value_cansleep(desc, value[word] & BIT_ULL(shift)); + } else { + if (gpiod_get_raw_value_cansleep(desc)) + value[word] |= BIT_ULL(shift); + else + value[word] &= ~BIT_ULL(shift); + } } out: @@ -1346,6 +1359,7 @@ static int acpi_gpio_package_count(const union acpi_object *obj) while (element < end) { switch (element->type) { case ACPI_TYPE_LOCAL_REFERENCE: + case ACPI_TYPE_STRING: element += 3; fallthrough; case ACPI_TYPE_INTEGER: diff --git a/drivers/gpio/gpiolib-acpi-quirks.c b/drivers/gpio/gpiolib-acpi-quirks.c index 7b95d1b0336149..a0116f004975ae 100644 --- a/drivers/gpio/gpiolib-acpi-quirks.c +++ b/drivers/gpio/gpiolib-acpi-quirks.c @@ -370,6 +370,28 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = { .ignore_wake = "ASCP1A00:00@8", }, }, + { + /* + * Spurious wakeups, likely from touchpad controller + * Dell Precision 7780 + * Found in BIOS 1.24.1 + * + * Found in touchpad firmware, installed by Dell Touchpad Firmware Update Utility version 1160.4196.9, A01 + * ( Dell-Touchpad-Firmware-Update-Utility_VYGNN_WIN64_1160.4196.9_A00.EXE ), + * released on 11 Jul 2024 + * + * https://lore.kernel.org/linux-i2c/197ae95ffd8.dc819e60457077.7692120488609091556@zohomail.com/ + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_FAMILY, "Precision"), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision 7780"), + DMI_MATCH(DMI_BOARD_NAME, "0C6JVW"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_wake = "VEN_0488:00@355", + }, + }, {} /* Terminating entry */ }; diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index d8d93059ac04c8..e76bcbd647539b 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -2573,6 +2573,7 @@ static int lineinfo_changed_notify(struct notifier_block *nb, ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); if (!ctx) { pr_err("Failed to allocate memory for line info notification\n"); + fput(fp); return NOTIFY_DONE; } @@ -2720,7 +2721,7 @@ static int gpio_chrdev_open(struct inode *inode, struct file *file) cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); if (!cdev) - return -ENODEV; + return -ENOMEM; cdev->watched_lines = bitmap_zalloc(gdev->ngpio, GFP_KERNEL); if (!cdev->watched_lines) @@ -2820,15 +2821,20 @@ int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt) return -ENOMEM; ret = cdev_device_add(&gdev->chrdev, &gdev->dev); - if (ret) + if (ret) { + destroy_workqueue(gdev->line_state_wq); return ret; + } guard(srcu)(&gdev->srcu); gc = srcu_dereference(gdev->chip, &gdev->srcu); - if (!gc) + if (!gc) { + cdev_device_del(&gdev->chrdev, &gdev->dev); + destroy_workqueue(gdev->line_state_wq); return -ENODEV; + } - chip_dbg(gc, "added GPIO chardev (%d:%d)\n", MAJOR(devt), gdev->id); + gpiochip_dbg(gc, "added GPIO chardev (%d:%d)\n", MAJOR(devt), gdev->id); return 0; } diff --git a/drivers/gpio/gpiolib-swnode.c b/drivers/gpio/gpiolib-swnode.c index e3806db1c0e077..f21dbc28cf2c8c 100644 --- a/drivers/gpio/gpiolib-swnode.c +++ b/drivers/gpio/gpiolib-swnode.c @@ -41,7 +41,7 @@ static struct gpio_device *swnode_get_gpio_device(struct fwnode_handle *fwnode) !strcmp(gdev_node->name, GPIOLIB_SWNODE_UNDEFINED_NAME)) return ERR_PTR(-ENOENT); - gdev = gpio_device_find_by_fwnode(fwnode); + gdev = gpio_device_find_by_label(gdev_node->name); return gdev ?: ERR_PTR(-EPROBE_DEFER); } diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c index 9a849245b35880..7d5fc1ea2aa54f 100644 --- a/drivers/gpio/gpiolib-sysfs.c +++ b/drivers/gpio/gpiolib-sysfs.c @@ -1091,7 +1091,7 @@ static int gpiofind_sysfs_register(struct gpio_chip *gc, const void *data) ret = gpiochip_sysfs_register(gdev); if (ret) - chip_err(gc, "failed to register the sysfs entry: %d\n", ret); + gpiochip_err(gc, "failed to register the sysfs entry: %d\n", ret); return 0; } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index cd8800ba5825ff..9aa6ddf6389ccd 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -921,8 +921,8 @@ static void gpiochip_machine_hog(struct gpio_chip *gc, struct gpiod_hog *hog) desc = gpiochip_get_desc(gc, hog->chip_hwnum); if (IS_ERR(desc)) { - chip_err(gc, "%s: unable to get GPIO desc: %ld\n", __func__, - PTR_ERR(desc)); + gpiochip_err(gc, "%s: unable to get GPIO desc: %ld\n", + __func__, PTR_ERR(desc)); return; } @@ -1091,6 +1091,18 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, gdev->ngpio = gc->ngpio; gdev->can_sleep = gc->can_sleep; + rwlock_init(&gdev->line_state_lock); + RAW_INIT_NOTIFIER_HEAD(&gdev->line_state_notifier); + BLOCKING_INIT_NOTIFIER_HEAD(&gdev->device_notifier); + + ret = init_srcu_struct(&gdev->srcu); + if (ret) + goto err_free_label; + + ret = init_srcu_struct(&gdev->desc_srcu); + if (ret) + goto err_cleanup_gdev_srcu; + scoped_guard(mutex, &gpio_devices_lock) { /* * TODO: this allocates a Linux GPIO number base in the global @@ -1105,7 +1117,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, if (base < 0) { ret = base; base = 0; - goto err_free_label; + goto err_cleanup_desc_srcu; } /* @@ -1124,23 +1136,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, ret = gpiodev_add_to_list_unlocked(gdev); if (ret) { - chip_err(gc, "GPIO integer space overlap, cannot add chip\n"); - goto err_free_label; + gpiochip_err(gc, "GPIO integer space overlap, cannot add chip\n"); + goto err_cleanup_desc_srcu; } } - rwlock_init(&gdev->line_state_lock); - RAW_INIT_NOTIFIER_HEAD(&gdev->line_state_notifier); - BLOCKING_INIT_NOTIFIER_HEAD(&gdev->device_notifier); - - ret = init_srcu_struct(&gdev->srcu); - if (ret) - goto err_remove_from_list; - - ret = init_srcu_struct(&gdev->desc_srcu); - if (ret) - goto err_cleanup_gdev_srcu; - #ifdef CONFIG_PINCTRL INIT_LIST_HEAD(&gdev->pin_ranges); #endif @@ -1150,11 +1150,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, ret = gpiochip_set_names(gc); if (ret) - goto err_cleanup_desc_srcu; + goto err_remove_from_list; ret = gpiochip_init_valid_mask(gc); if (ret) - goto err_cleanup_desc_srcu; + goto err_remove_from_list; for (desc_index = 0; desc_index < gc->ngpio; desc_index++) { struct gpio_desc *desc = &gdev->descs[desc_index]; @@ -1227,10 +1227,6 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, of_gpiochip_remove(gc); err_free_valid_mask: gpiochip_free_valid_mask(gc); -err_cleanup_desc_srcu: - cleanup_srcu_struct(&gdev->desc_srcu); -err_cleanup_gdev_srcu: - cleanup_srcu_struct(&gdev->srcu); err_remove_from_list: scoped_guard(mutex, &gpio_devices_lock) list_del_rcu(&gdev->list); @@ -1240,6 +1236,10 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, gpio_device_put(gdev); goto err_print_message; } +err_cleanup_desc_srcu: + cleanup_srcu_struct(&gdev->desc_srcu); +err_cleanup_gdev_srcu: + cleanup_srcu_struct(&gdev->srcu); err_free_label: kfree_const(gdev->label); err_free_descs: @@ -1528,8 +1528,7 @@ static void gpiochip_set_hierarchical_irqchip(struct gpio_chip *gc, &parent_hwirq, &parent_type); if (ret) { - chip_err(gc, "skip set-up on hwirq %d\n", - i); + gpiochip_err(gc, "skip set-up on hwirq %d\n", i); continue; } @@ -1542,15 +1541,14 @@ static void gpiochip_set_hierarchical_irqchip(struct gpio_chip *gc, ret = irq_domain_alloc_irqs(gc->irq.domain, 1, NUMA_NO_NODE, &fwspec); if (ret < 0) { - chip_err(gc, - "can not allocate irq for GPIO line %d parent hwirq %d in hierarchy domain: %d\n", - i, parent_hwirq, - ret); + gpiochip_err(gc, + "can not allocate irq for GPIO line %d parent hwirq %d in hierarchy domain: %d\n", + i, parent_hwirq, ret); } } } - chip_err(gc, "%s unknown fwnode type proceed anyway\n", __func__); + gpiochip_err(gc, "%s unknown fwnode type proceed anyway\n", __func__); return; } @@ -1602,15 +1600,15 @@ static int gpiochip_hierarchy_irq_domain_alloc(struct irq_domain *d, if (ret) return ret; - chip_dbg(gc, "allocate IRQ %d, hwirq %lu\n", irq, hwirq); + gpiochip_dbg(gc, "allocate IRQ %d, hwirq %lu\n", irq, hwirq); ret = girq->child_to_parent_hwirq(gc, hwirq, type, &parent_hwirq, &parent_type); if (ret) { - chip_err(gc, "can't look up hwirq %lu\n", hwirq); + gpiochip_err(gc, "can't look up hwirq %lu\n", hwirq); return ret; } - chip_dbg(gc, "found parent hwirq %u\n", parent_hwirq); + gpiochip_dbg(gc, "found parent hwirq %u\n", parent_hwirq); /* * We set handle_bad_irq because the .set_type() should @@ -1631,8 +1629,8 @@ static int gpiochip_hierarchy_irq_domain_alloc(struct irq_domain *d, if (ret) return ret; - chip_dbg(gc, "alloc_irqs_parent for %d parent hwirq %d\n", - irq, parent_hwirq); + gpiochip_dbg(gc, "alloc_irqs_parent for %d parent hwirq %d\n", + irq, parent_hwirq); irq_set_lockdep_class(irq, gc->irq.lock_key, gc->irq.request_key); ret = irq_domain_alloc_irqs_parent(d, irq, 1, &gpio_parent_fwspec); /* @@ -1642,9 +1640,9 @@ static int gpiochip_hierarchy_irq_domain_alloc(struct irq_domain *d, if (irq_domain_is_msi(d->parent) && (ret == -EEXIST)) ret = 0; if (ret) - chip_err(gc, - "failed to allocate parent hwirq %d for hwirq %lu\n", - parent_hwirq, hwirq); + gpiochip_err(gc, + "failed to allocate parent hwirq %d for hwirq %lu\n", + parent_hwirq, hwirq); return ret; } @@ -1720,7 +1718,7 @@ static struct irq_domain *gpiochip_hierarchy_create_domain(struct gpio_chip *gc) if (!gc->irq.child_to_parent_hwirq || !gc->irq.fwnode) { - chip_err(gc, "missing irqdomain vital data\n"); + gpiochip_err(gc, "missing irqdomain vital data\n"); return ERR_PTR(-EINVAL); } @@ -1993,7 +1991,7 @@ static void gpiochip_set_irq_hooks(struct gpio_chip *gc) if (irqchip->flags & IRQCHIP_IMMUTABLE) return; - chip_warn(gc, "not an immutable chip, please consider fixing it!\n"); + gpiochip_warn(gc, "not an immutable chip, please consider fixing it!\n"); if (!irqchip->irq_request_resources && !irqchip->irq_release_resources) { @@ -2009,8 +2007,8 @@ static void gpiochip_set_irq_hooks(struct gpio_chip *gc) * ...and if so, give a gentle warning that this is bad * practice. */ - chip_info(gc, - "detected irqchip that is shared with multiple gpiochips: please fix the driver.\n"); + gpiochip_info(gc, + "detected irqchip that is shared with multiple gpiochips: please fix the driver.\n"); return; } @@ -2039,7 +2037,8 @@ static int gpiochip_irqchip_add_allocated_domain(struct gpio_chip *gc, return -EINVAL; if (gc->to_irq) - chip_warn(gc, "to_irq is redefined in %s and you shouldn't rely on it\n", __func__); + gpiochip_warn(gc, "to_irq is redefined in %s and you shouldn't rely on it\n", + __func__); gc->to_irq = gpiochip_to_irq; gc->irq.domain = domain; @@ -2080,7 +2079,7 @@ static int gpiochip_add_irqchip(struct gpio_chip *gc, return 0; if (gc->irq.parent_handler && gc->can_sleep) { - chip_err(gc, "you cannot have chained interrupts on a chip that may sleep\n"); + gpiochip_err(gc, "you cannot have chained interrupts on a chip that may sleep\n"); return -EINVAL; } @@ -2316,10 +2315,8 @@ int gpiochip_add_pingroup_range(struct gpio_chip *gc, int ret; pin_range = kzalloc(sizeof(*pin_range), GFP_KERNEL); - if (!pin_range) { - chip_err(gc, "failed to allocate pin ranges\n"); + if (!pin_range) return -ENOMEM; - } /* Use local offset as range ID */ pin_range->range.id = gpio_offset; @@ -2338,7 +2335,7 @@ int gpiochip_add_pingroup_range(struct gpio_chip *gc, pinctrl_add_gpio_range(pctldev, &pin_range->range); - chip_dbg(gc, "created GPIO range %d->%d ==> %s PINGRP %s\n", + gpiochip_dbg(gc, "created GPIO range %d->%d ==> %s PINGRP %s\n", gpio_offset, gpio_offset + pin_range->range.npins - 1, pinctrl_dev_get_devname(pctldev), pin_group); @@ -2379,10 +2376,8 @@ int gpiochip_add_pin_range_with_pins(struct gpio_chip *gc, int ret; pin_range = kzalloc(sizeof(*pin_range), GFP_KERNEL); - if (!pin_range) { - chip_err(gc, "failed to allocate pin ranges\n"); + if (!pin_range) return -ENOMEM; - } /* Use local offset as range ID */ pin_range->range.id = gpio_offset; @@ -2396,19 +2391,18 @@ int gpiochip_add_pin_range_with_pins(struct gpio_chip *gc, &pin_range->range); if (IS_ERR(pin_range->pctldev)) { ret = PTR_ERR(pin_range->pctldev); - chip_err(gc, "could not create pin range\n"); + gpiochip_err(gc, "could not create pin range\n"); kfree(pin_range); return ret; } if (pin_range->range.pins) - chip_dbg(gc, "created GPIO range %d->%d ==> %s %d sparse PIN range { %d, ... }", - gpio_offset, gpio_offset + npins - 1, - pinctl_name, npins, pins[0]); + gpiochip_dbg(gc, "created GPIO range %d->%d ==> %s %d sparse PIN range { %d, ... }", + gpio_offset, gpio_offset + npins - 1, + pinctl_name, npins, pins[0]); else - chip_dbg(gc, "created GPIO range %d->%d ==> %s PIN %d->%d\n", - gpio_offset, gpio_offset + npins - 1, - pinctl_name, - pin_offset, pin_offset + npins - 1); + gpiochip_dbg(gc, "created GPIO range %d->%d ==> %s PIN %d->%d\n", + gpio_offset, gpio_offset + npins - 1, pinctl_name, + pin_offset, pin_offset + npins - 1); list_add_tail(&pin_range->node, &gdev->pin_ranges); @@ -2618,7 +2612,7 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc, int ret; if (IS_ERR(desc)) { - chip_err(gc, "failed to get GPIO %s descriptor\n", name); + gpiochip_err(gc, "failed to get GPIO %s descriptor\n", name); return desc; } @@ -2629,7 +2623,7 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc, ret = gpiod_configure_flags(desc, label, lflags, dflags); if (ret) { gpiod_free_commit(desc); - chip_err(gc, "setup of own GPIO %s failed\n", name); + gpiochip_err(gc, "setup of own GPIO %s failed\n", name); return ERR_PTR(ret); } @@ -4056,8 +4050,8 @@ int gpiochip_lock_as_irq(struct gpio_chip *gc, unsigned int offset) int dir = gpiod_get_direction(desc); if (dir < 0) { - chip_err(gc, "%s: cannot get GPIO direction\n", - __func__); + gpiochip_err(gc, "%s: cannot get GPIO direction\n", + __func__); return dir; } } @@ -4065,9 +4059,9 @@ int gpiochip_lock_as_irq(struct gpio_chip *gc, unsigned int offset) /* To be valid for IRQ the line needs to be input or open drain */ if (test_bit(GPIOD_FLAG_IS_OUT, &desc->flags) && !test_bit(GPIOD_FLAG_OPEN_DRAIN, &desc->flags)) { - chip_err(gc, - "%s: tried to flag a GPIO set as output for IRQ\n", - __func__); + gpiochip_err(gc, + "%s: tried to flag a GPIO set as output for IRQ\n", + __func__); return -EIO; } @@ -4144,7 +4138,7 @@ int gpiochip_reqres_irq(struct gpio_chip *gc, unsigned int offset) ret = gpiochip_lock_as_irq(gc, offset); if (ret) { - chip_err(gc, "unable to lock HW IRQ %u for IRQ\n", offset); + gpiochip_err(gc, "unable to lock HW IRQ %u for IRQ\n", offset); module_put(gc->gpiodev->owner); return ret; } diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h index 2a003a7311e7ac..6ee29d0222393d 100644 --- a/drivers/gpio/gpiolib.h +++ b/drivers/gpio/gpiolib.h @@ -309,13 +309,13 @@ do { \ /* With chip prefix */ -#define chip_err(gc, fmt, ...) \ +#define gpiochip_err(gc, fmt, ...) \ dev_err(&gc->gpiodev->dev, "(%s): " fmt, gc->label, ##__VA_ARGS__) -#define chip_warn(gc, fmt, ...) \ +#define gpiochip_warn(gc, fmt, ...) \ dev_warn(&gc->gpiodev->dev, "(%s): " fmt, gc->label, ##__VA_ARGS__) -#define chip_info(gc, fmt, ...) \ +#define gpiochip_info(gc, fmt, ...) \ dev_info(&gc->gpiodev->dev, "(%s): " fmt, gc->label, ##__VA_ARGS__) -#define chip_dbg(gc, fmt, ...) \ +#define gpiochip_dbg(gc, fmt, ...) \ dev_dbg(&gc->gpiodev->dev, "(%s): " fmt, gc->label, ##__VA_ARGS__) #endif /* GPIOLIB_H */ diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 7e6bc0b3a589ce..77190fc4fbd690 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -210,7 +210,7 @@ config DRM_GPUVM config DRM_GPUSVM tristate - depends on DRM && DEVICE_PRIVATE + depends on DRM select HMM_MIRROR select MMU_NOTIFIER help @@ -294,6 +294,8 @@ config DRM_VGEM source "drivers/gpu/drm/vkms/Kconfig" +source "drivers/gpu/drm/asahi/Kconfig" + source "drivers/gpu/drm/exynos/Kconfig" source "drivers/gpu/drm/rockchip/Kconfig" @@ -394,6 +396,8 @@ source "drivers/gpu/drm/solomon/Kconfig" source "drivers/gpu/drm/sprd/Kconfig" +source "drivers/gpu/drm/apple/Kconfig" + source "drivers/gpu/drm/imagination/Kconfig" source "drivers/gpu/drm/tyr/Kconfig" diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index da2565e6de71d8..1b232242909363 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -106,8 +106,10 @@ obj-$(CONFIG_DRM_EXEC) += drm_exec.o obj-$(CONFIG_DRM_GPUVM) += drm_gpuvm.o drm_gpusvm_helper-y := \ - drm_gpusvm.o\ + drm_gpusvm.o +drm_gpusvm_helper-$(CONFIG_ZONE_DEVICE) += \ drm_pagemap.o + obj-$(CONFIG_DRM_GPUSVM) += drm_gpusvm_helper.o obj-$(CONFIG_DRM_BUDDY) += drm_buddy.o @@ -215,12 +217,14 @@ obj-y += tiny/ obj-$(CONFIG_DRM_PL111) += pl111/ obj-$(CONFIG_DRM_TVE200) += tve200/ obj-$(CONFIG_DRM_ADP) += adp/ +obj-$(CONFIG_DRM_ASAHI) += asahi/ obj-$(CONFIG_DRM_XEN) += xen/ obj-$(CONFIG_DRM_VBOXVIDEO) += vboxvideo/ obj-$(CONFIG_DRM_LIMA) += lima/ obj-$(CONFIG_DRM_PANFROST) += panfrost/ obj-$(CONFIG_DRM_PANTHOR) += panthor/ obj-$(CONFIG_DRM_TYR) += tyr/ +obj-$(CONFIG_DRM_APPLE) += apple/ obj-$(CONFIG_DRM_ASPEED_GFX) += aspeed/ obj-$(CONFIG_DRM_MCDE) += mcde/ obj-$(CONFIG_DRM_TIDSS) += tidss/ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 6f5b4a0e0a343f..803b6fc360a07b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -274,6 +274,8 @@ extern int amdgpu_rebar; extern int amdgpu_wbrf; extern int amdgpu_user_queue; +extern uint amdgpu_hdmi_hpd_debounce_delay_ms; + #define AMDGPU_VM_MAX_NUM_CTX 4096 #define AMDGPU_SG_THRESHOLD (256*1024*1024) #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS 3000 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 6c62e27b980023..67db986eda3f64 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -1136,8 +1136,10 @@ static int amdgpu_acpi_enumerate_xcc(void) if (!dev_info) ret = amdgpu_acpi_dev_init(&dev_info, xcc_info, sbdf); - if (ret == -ENOMEM) + if (ret == -ENOMEM) { + kfree(xcc_info); return ret; + } if (!dev_info) { kfree(xcc_info); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 96b6738e625265..53b33a636971a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3416,11 +3416,10 @@ int amdgpu_device_set_pg_state(struct amdgpu_device *adev, (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX || adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SDMA)) continue; - /* skip CG for VCE/UVD/VPE, it's handled specially */ + /* skip CG for VCE/UVD, it's handled specially */ if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCN && - adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VPE && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_JPEG && adev->ip_blocks[i].version->funcs->set_powergating_state) { /* enable powergating to save power */ @@ -4986,6 +4985,14 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) amdgpu_ttm_set_buffer_funcs_status(adev, false); + /* + * device went through surprise hotplug; we need to destroy topology + * before ip_fini_early to prevent kfd locking refcount issues by calling + * amdgpu_amdkfd_suspend() + */ + if (drm_dev_is_unplugged(adev_to_drm(adev))) + amdgpu_amdkfd_device_fini_sw(adev); + amdgpu_device_ip_fini_early(adev); amdgpu_irq_fini_hw(adev); @@ -5732,6 +5739,9 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev) if (ret) goto mode1_reset_failed; + /* enable mmio access after mode 1 reset completed */ + adev->no_hw_access = false; + amdgpu_device_load_pci_state(adev->pdev); ret = amdgpu_psp_wait_for_bootloader(adev); if (ret) @@ -6476,6 +6486,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, struct amdgpu_hive_info *hive = NULL; int r = 0; bool need_emergency_restart = false; + /* save the pasid here as the job may be freed before the end of the reset */ + int pasid = job ? job->pasid : -EINVAL; /* * If it reaches here because of hang/timeout and a RAS error is @@ -6572,8 +6584,12 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, if (!r) { struct amdgpu_task_info *ti = NULL; - if (job) - ti = amdgpu_vm_get_task_info_pasid(adev, job->pasid); + /* + * The job may already be freed at this point via the sched tdr workqueue so + * use the cached pasid. + */ + if (pasid >= 0) + ti = amdgpu_vm_get_task_info_pasid(adev, pasid); drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, ti ? &ti->task : NULL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 51bab32fd8c6fc..2f416d12e2e7ee 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -1824,7 +1824,12 @@ int amdgpu_display_get_scanout_buffer(struct drm_plane *plane, struct drm_scanout_buffer *sb) { struct amdgpu_bo *abo; - struct drm_framebuffer *fb = plane->state->fb; + struct drm_framebuffer *fb; + + if (drm_drv_uses_atomic_modeset(plane->dev)) + fb = plane->state->fb; + else + fb = plane->fb; if (!fb) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 7333e19291cf93..335f7e2f4ce557 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -246,6 +246,7 @@ int amdgpu_damage_clips = -1; /* auto */ int amdgpu_umsch_mm_fwlog; int amdgpu_rebar = -1; /* auto */ int amdgpu_user_queue = -1; +uint amdgpu_hdmi_hpd_debounce_delay_ms; DECLARE_DYNDBG_CLASSMAP(drm_debug_classes, DD_CLASS_TYPE_DISJOINT_BITS, 0, "DRM_UT_CORE", @@ -1128,6 +1129,16 @@ module_param_named(rebar, amdgpu_rebar, int, 0444); MODULE_PARM_DESC(user_queue, "Enable user queues (-1 = auto (default), 0 = disable, 1 = enable, 2 = enable UQs and disable KQs)"); module_param_named(user_queue, amdgpu_user_queue, int, 0444); +/* + * DOC: hdmi_hpd_debounce_delay_ms (uint) + * HDMI HPD disconnect debounce delay in milliseconds. + * + * Used to filter short disconnect->reconnect HPD toggles some HDMI sinks + * generate while entering/leaving power save. Set to 0 to disable by default. + */ +MODULE_PARM_DESC(hdmi_hpd_debounce_delay_ms, "HDMI HPD disconnect debounce delay in milliseconds (0 to disable (by default), 1500 is common)"); +module_param_named(hdmi_hpd_debounce_delay_ms, amdgpu_hdmi_hpd_debounce_delay_ms, uint, 0644); + /* These devices are not supported by amdgpu. * They are supported by the mach64, r128, radeon drivers */ @@ -2334,9 +2345,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, return -ENODEV; } - if (amdgpu_aspm == -1 && !pcie_aspm_enabled(pdev)) - amdgpu_aspm = 0; - if (amdgpu_virtual_display || amdgpu_device_asic_has_dc_support(pdev, flags & AMD_ASIC_MASK)) supports_atomic = true; @@ -3158,7 +3166,6 @@ static int __init amdgpu_init(void) if (r) goto error_fence; - DRM_INFO("amdgpu kernel modesetting enabled.\n"); amdgpu_register_atpx_handler(); amdgpu_acpi_detect(); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 18a7829122d246..89a639044d5203 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -804,7 +804,7 @@ void amdgpu_fence_save_wptr(struct dma_fence *fence) } static void amdgpu_ring_backup_unprocessed_command(struct amdgpu_ring *ring, - u64 start_wptr, u32 end_wptr) + u64 start_wptr, u64 end_wptr) { unsigned int first_idx = start_wptr & ring->buf_mask; unsigned int last_idx = end_wptr & ring->buf_mask; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 869bceb0fe2c6d..01ad5cc008a965 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -498,8 +498,13 @@ void amdgpu_gmc_filter_faults_remove(struct amdgpu_device *adev, uint64_t addr, if (adev->irq.retry_cam_enabled) return; + else if (adev->irq.ih1.ring_size) + ih = &adev->irq.ih1; + else if (adev->irq.ih_soft.enabled) + ih = &adev->irq.ih_soft; + else + return; - ih = &adev->irq.ih1; /* Get the WPTR of the last entry in IH ring */ last_wptr = amdgpu_ih_get_wptr(adev, ih); /* Order wptr with ring data. */ @@ -1376,7 +1381,7 @@ int amdgpu_gmc_get_nps_memranges(struct amdgpu_device *adev, if (!*exp_ranges) *exp_ranges = range_cnt; err: - kfree(ranges); + kvfree(ranges); return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index 7d9bcb72e8dd3c..9581643dbb7262 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -228,7 +228,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs, amdgpu_ring_ib_begin(ring); - if (ring->funcs->emit_gfx_shadow) + if (ring->funcs->emit_gfx_shadow && adev->gfx.cp_gfx_shadow) amdgpu_ring_emit_gfx_shadow(ring, shadow_va, csa_va, gds_va, init_shadow, vmid); @@ -284,7 +284,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs, fence_flags | AMDGPU_FENCE_FLAG_64BIT); } - if (ring->funcs->emit_gfx_shadow && ring->funcs->init_cond_exec) { + if (ring->funcs->emit_gfx_shadow && ring->funcs->init_cond_exec && + adev->gfx.cp_gfx_shadow) { amdgpu_ring_emit_gfx_shadow(ring, 0, 0, 0, false, 0); amdgpu_ring_init_cond_exec(ring, ring->cond_exe_gpu_addr); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index d020a890a0ea42..630af847f29ff3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -130,11 +130,9 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) } /* attempt a per ring reset */ - if (unlikely(adev->debug_disable_gpu_ring_reset)) { - dev_err(adev->dev, "Ring reset disabled by debug mask\n"); - } else if (amdgpu_gpu_recovery && - amdgpu_ring_is_reset_type_supported(ring, AMDGPU_RESET_TYPE_PER_QUEUE) && - ring->funcs->reset) { + if (amdgpu_gpu_recovery && + amdgpu_ring_is_reset_type_supported(ring, AMDGPU_RESET_TYPE_PER_QUEUE) && + ring->funcs->reset) { dev_err(adev->dev, "Starting %s ring reset\n", s_job->sched->name); r = amdgpu_ring_reset(ring, job->vmid, &job->hw_fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index b3e6b3fcdf2cb1..a8b507fd856739 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -201,6 +201,9 @@ static enum amd_ip_block_type type = (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_JPEG)) ? AMD_IP_BLOCK_TYPE_JPEG : AMD_IP_BLOCK_TYPE_VCN; break; + case AMDGPU_HW_IP_VPE: + type = AMD_IP_BLOCK_TYPE_VPE; + break; default: type = AMD_IP_BLOCK_TYPE_NUM; break; @@ -721,6 +724,9 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) case AMD_IP_BLOCK_TYPE_UVD: count = adev->uvd.num_uvd_inst; break; + case AMD_IP_BLOCK_TYPE_VPE: + count = adev->vpe.num_instances; + break; /* For all other IP block types not listed in the switch statement * the ip status is valid here and the instance count is one. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 656b8a931dae85..52c2d1731aabf6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -96,6 +96,7 @@ struct amdgpu_bo_va { * if non-zero, cannot unmap from GPU because user queues may still access it */ unsigned int queue_refcount; + atomic_t userq_va_mapped; }; struct amdgpu_bo { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index e0ee211508607e..3fd19859055a57 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -4137,7 +4137,7 @@ int amdgpu_ras_init(struct amdgpu_device *adev) * to handle fatal error */ r = amdgpu_nbio_ras_sw_init(adev); if (r) - return r; + goto release_con; if (adev->nbio.ras && adev->nbio.ras->init_ras_controller_interrupt) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 5ec5c3ff22bb07..304564ec2f59a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -460,9 +460,6 @@ bool amdgpu_ring_soft_recovery(struct amdgpu_ring *ring, unsigned int vmid, ktime_t deadline; bool ret; - if (unlikely(ring->adev->debug_disable_soft_recovery)) - return false; - deadline = ktime_add_us(ktime_get(), 10000); if (amdgpu_sriov_vf(ring->adev) || !ring->funcs->soft_recovery || !fence) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 9d568c16beb1e2..4183e5301cffc0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1529,6 +1529,7 @@ static int amdgpu_ttm_access_memory_sdma(struct ttm_buffer_object *bo, if (r) goto out; + mutex_lock(&adev->mman.gtt_window_lock); amdgpu_res_first(abo->tbo.resource, offset, len, &src_mm); src_addr = amdgpu_ttm_domain_start(adev, bo->resource->mem_type) + src_mm.start; @@ -1543,6 +1544,7 @@ static int amdgpu_ttm_access_memory_sdma(struct ttm_buffer_object *bo, WARN_ON(job->ibs[0].length_dw > num_dw); fence = amdgpu_job_submit(job); + mutex_unlock(&adev->mman.gtt_window_lock); if (!dma_fence_wait_timeout(fence, false, adev->sdma_timeout)) r = -ETIMEDOUT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index 1add21160d2187..8c41951feb437a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -44,10 +44,29 @@ u32 amdgpu_userq_get_supported_ip_mask(struct amdgpu_device *adev) return userq_ip_mask; } -int amdgpu_userq_input_va_validate(struct amdgpu_vm *vm, u64 addr, - u64 expected_size) +static int amdgpu_userq_buffer_va_list_add(struct amdgpu_usermode_queue *queue, + struct amdgpu_bo_va_mapping *va_map, u64 addr) +{ + struct amdgpu_userq_va_cursor *va_cursor; + struct userq_va_list; + + va_cursor = kzalloc(sizeof(*va_cursor), GFP_KERNEL); + if (!va_cursor) + return -ENOMEM; + + INIT_LIST_HEAD(&va_cursor->list); + va_cursor->gpu_addr = addr; + atomic_set(&va_map->bo_va->userq_va_mapped, 1); + list_add(&va_cursor->list, &queue->userq_va_list); + + return 0; +} + +int amdgpu_userq_input_va_validate(struct amdgpu_usermode_queue *queue, + u64 addr, u64 expected_size) { struct amdgpu_bo_va_mapping *va_map; + struct amdgpu_vm *vm = queue->vm; u64 user_addr; u64 size; int r = 0; @@ -67,6 +86,7 @@ int amdgpu_userq_input_va_validate(struct amdgpu_vm *vm, u64 addr, /* Only validate the userq whether resident in the VM mapping range */ if (user_addr >= va_map->start && va_map->last - user_addr + 1 >= size) { + amdgpu_userq_buffer_va_list_add(queue, va_map, user_addr); amdgpu_bo_unreserve(vm->root.bo); return 0; } @@ -185,6 +205,7 @@ amdgpu_userq_cleanup(struct amdgpu_userq_mgr *uq_mgr, uq_funcs->mqd_destroy(uq_mgr, queue); amdgpu_userq_fence_driver_free(queue); idr_remove(&uq_mgr->userq_idr, queue_id); + list_del(&queue->userq_va_list); kfree(queue); } @@ -505,14 +526,7 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args) goto unlock; } - /* Validate the userq virtual address.*/ - if (amdgpu_userq_input_va_validate(&fpriv->vm, args->in.queue_va, args->in.queue_size) || - amdgpu_userq_input_va_validate(&fpriv->vm, args->in.rptr_va, AMDGPU_GPU_PAGE_SIZE) || - amdgpu_userq_input_va_validate(&fpriv->vm, args->in.wptr_va, AMDGPU_GPU_PAGE_SIZE)) { - r = -EINVAL; - kfree(queue); - goto unlock; - } + INIT_LIST_HEAD(&queue->userq_va_list); queue->doorbell_handle = args->in.doorbell_handle; queue->queue_type = args->in.ip_type; queue->vm = &fpriv->vm; @@ -523,6 +537,15 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args) db_info.db_obj = &queue->db_obj; db_info.doorbell_offset = args->in.doorbell_offset; + /* Validate the userq virtual address.*/ + if (amdgpu_userq_input_va_validate(queue, args->in.queue_va, args->in.queue_size) || + amdgpu_userq_input_va_validate(queue, args->in.rptr_va, AMDGPU_GPU_PAGE_SIZE) || + amdgpu_userq_input_va_validate(queue, args->in.wptr_va, AMDGPU_GPU_PAGE_SIZE)) { + r = -EINVAL; + kfree(queue); + goto unlock; + } + /* Convert relative doorbell offset into absolute doorbell index */ index = amdgpu_userq_get_doorbell_index(uq_mgr, &db_info, filp); if (index == (uint64_t)-EINVAL) { @@ -548,7 +571,6 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args) goto unlock; } - qid = idr_alloc(&uq_mgr->userq_idr, queue, 1, AMDGPU_MAX_USERQ_COUNT, GFP_KERNEL); if (qid < 0) { drm_file_err(uq_mgr->file, "Failed to allocate a queue id\n"); @@ -659,12 +681,28 @@ static int amdgpu_userq_input_args_validate(struct drm_device *dev, return 0; } +bool amdgpu_userq_enabled(struct drm_device *dev) +{ + struct amdgpu_device *adev = drm_to_adev(dev); + int i; + + for (i = 0; i < AMDGPU_HW_IP_NUM; i++) { + if (adev->userq_funcs[i]) + return true; + } + + return false; +} + int amdgpu_userq_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { union drm_amdgpu_userq *args = data; int r; + if (!amdgpu_userq_enabled(dev)) + return -ENOTSUPP; + if (amdgpu_userq_input_args_validate(dev, args, filp) < 0) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h index c027dd9166727f..d78532f9d507b9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h @@ -47,6 +47,11 @@ struct amdgpu_userq_obj { struct amdgpu_bo *obj; }; +struct amdgpu_userq_va_cursor { + u64 gpu_addr; + struct list_head list; +}; + struct amdgpu_usermode_queue { int queue_type; enum amdgpu_userq_state state; @@ -66,6 +71,8 @@ struct amdgpu_usermode_queue { u32 xcp_id; int priority; struct dentry *debugfs_queue; + + struct list_head userq_va_list; }; struct amdgpu_userq_funcs { @@ -128,6 +135,7 @@ uint64_t amdgpu_userq_get_doorbell_index(struct amdgpu_userq_mgr *uq_mgr, struct drm_file *filp); u32 amdgpu_userq_get_supported_ip_mask(struct amdgpu_device *adev); +bool amdgpu_userq_enabled(struct drm_device *dev); int amdgpu_userq_suspend(struct amdgpu_device *adev); int amdgpu_userq_resume(struct amdgpu_device *adev); @@ -136,7 +144,6 @@ int amdgpu_userq_stop_sched_for_enforce_isolation(struct amdgpu_device *adev, u32 idx); int amdgpu_userq_start_sched_for_enforce_isolation(struct amdgpu_device *adev, u32 idx); - -int amdgpu_userq_input_va_validate(struct amdgpu_vm *vm, u64 addr, - u64 expected_size); +int amdgpu_userq_input_va_validate(struct amdgpu_usermode_queue *queue, + u64 addr, u64 expected_size); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c index 4d0096d0baa9d0..5c181ac75d548f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c @@ -141,6 +141,8 @@ static void amdgpu_userq_walk_and_drop_fence_drv(struct xarray *xa) void amdgpu_userq_fence_driver_free(struct amdgpu_usermode_queue *userq) { + dma_fence_put(userq->last_fence); + amdgpu_userq_walk_and_drop_fence_drv(&userq->fence_drv_xa); xa_destroy(&userq->fence_drv_xa); /* Drop the fence_drv reference held by user queue */ @@ -470,6 +472,9 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data, struct drm_exec exec; u64 wptr; + if (!amdgpu_userq_enabled(dev)) + return -ENOTSUPP; + num_syncobj_handles = args->num_syncobj_handles; syncobj_handles = memdup_user(u64_to_user_ptr(args->syncobj_handles), size_mul(sizeof(u32), num_syncobj_handles)); @@ -652,6 +657,9 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data, int r, i, rentry, wentry, cnt; struct drm_exec exec; + if (!amdgpu_userq_enabled(dev)) + return -ENOTSUPP; + num_read_bo_handles = wait_info->num_bo_read_handles; bo_handles_read = memdup_user(u64_to_user_ptr(wait_info->bo_read_handles), size_mul(sizeof(u32), num_read_bo_handles)); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 676e24fb886474..3d2f9d0e2d2397 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1066,7 +1066,9 @@ amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params, } /* Prepare a TLB flush fence to be attached to PTs */ - if (!params->unlocked) { + if (!params->unlocked && + /* SI doesn't support pasid or KIQ/MES */ + params->adev->family > AMDGPU_FAMILY_SI) { amdgpu_vm_tlb_fence_create(params->adev, vm, fence); /* Makes sure no PD/PT is freed before the flush */ @@ -2908,8 +2910,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) switch (args->in.op) { case AMDGPU_VM_OP_RESERVE_VMID: /* We only have requirement to reserve vmid from gfxhub */ - amdgpu_vmid_alloc_reserved(adev, vm, AMDGPU_GFXHUB(0)); - break; + return amdgpu_vmid_alloc_reserved(adev, vm, AMDGPU_GFXHUB(0)); case AMDGPU_VM_OP_UNRESERVE_VMID: amdgpu_vmid_free_reserved(adev, vm, AMDGPU_GFXHUB(0)); break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 8841d7213de456..003bcece715eb6 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -4956,7 +4956,8 @@ static int gfx_v10_0_sw_init(struct amdgpu_ip_block *ip_block) amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]); adev->gfx.compute_supported_reset = amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]); - if (!amdgpu_sriov_vf(adev)) { + if (!amdgpu_sriov_vf(adev) && + !adev->debug_disable_gpu_ring_reset) { adev->gfx.compute_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; adev->gfx.gfx_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; } @@ -6878,7 +6879,7 @@ static int gfx_v10_0_kgq_init_queue(struct amdgpu_ring *ring, bool reset) memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset the ring */ ring->wptr = 0; - *ring->wptr_cpu_addr = 0; + atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0); amdgpu_ring_clear_ring(ring); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index f2be16e700c41a..1dd9fd486eecfb 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -1821,13 +1821,15 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block) case IP_VERSION(11, 0, 3): if ((adev->gfx.me_fw_version >= 2280) && (adev->gfx.mec_fw_version >= 2410) && - !amdgpu_sriov_vf(adev)) { + !amdgpu_sriov_vf(adev) && + !adev->debug_disable_gpu_ring_reset) { adev->gfx.compute_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; adev->gfx.gfx_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; } break; default: - if (!amdgpu_sriov_vf(adev)) { + if (!amdgpu_sriov_vf(adev) && + !adev->debug_disable_gpu_ring_reset) { adev->gfx.compute_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; adev->gfx.gfx_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; } @@ -4199,7 +4201,7 @@ static int gfx_v11_0_kgq_init_queue(struct amdgpu_ring *ring, bool reset) memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset the ring */ ring->wptr = 0; - *ring->wptr_cpu_addr = 0; + atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0); amdgpu_ring_clear_ring(ring); } @@ -6821,11 +6823,12 @@ static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring, struct amdgpu_fence *timedout_fence) { struct amdgpu_device *adev = ring->adev; + bool use_mmio = false; int r; amdgpu_ring_reset_helper_begin(ring, timedout_fence); - r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, false); + r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, use_mmio); if (r) { dev_warn(adev->dev, "reset via MES failed and try pipe reset %d\n", r); @@ -6834,16 +6837,18 @@ static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring, return r; } - r = gfx_v11_0_kgq_init_queue(ring, true); - if (r) { - dev_err(adev->dev, "failed to init kgq\n"); - return r; - } + if (use_mmio) { + r = gfx_v11_0_kgq_init_queue(ring, true); + if (r) { + dev_err(adev->dev, "failed to init kgq\n"); + return r; + } - r = amdgpu_mes_map_legacy_queue(adev, ring); - if (r) { - dev_err(adev->dev, "failed to remap kgq\n"); - return r; + r = amdgpu_mes_map_legacy_queue(adev, ring); + if (r) { + dev_err(adev->dev, "failed to remap kgq\n"); + return r; + } } return amdgpu_ring_reset_helper_end(ring, timedout_fence); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index 93fde0f9af87f8..50e39b9d9df6f8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -278,7 +278,6 @@ static void gfx_v12_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num, u32 instance, int xcc_id); static u32 gfx_v12_0_get_wgp_active_bitmap_per_sh(struct amdgpu_device *adev); -static void gfx_v12_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, bool start, bool secure); static void gfx_v12_0_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val); static int gfx_v12_0_wait_for_rlc_autoload_complete(struct amdgpu_device *adev); @@ -1548,7 +1547,8 @@ static int gfx_v12_0_sw_init(struct amdgpu_ip_block *ip_block) case IP_VERSION(12, 0, 1): if ((adev->gfx.me_fw_version >= 2660) && (adev->gfx.mec_fw_version >= 2920) && - !amdgpu_sriov_vf(adev)) { + !amdgpu_sriov_vf(adev) && + !adev->debug_disable_gpu_ring_reset) { adev->gfx.compute_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; adev->gfx.gfx_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; } @@ -3079,7 +3079,7 @@ static int gfx_v12_0_kgq_init_queue(struct amdgpu_ring *ring, bool reset) memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset the ring */ ring->wptr = 0; - *ring->wptr_cpu_addr = 0; + atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0); amdgpu_ring_clear_ring(ring); } @@ -4633,16 +4633,6 @@ static int gfx_v12_0_ring_preempt_ib(struct amdgpu_ring *ring) return r; } -static void gfx_v12_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, - bool start, - bool secure) -{ - uint32_t v = secure ? FRAME_TMZ : 0; - - amdgpu_ring_write(ring, PACKET3(PACKET3_FRAME_CONTROL, 0)); - amdgpu_ring_write(ring, v | FRAME_CMD(start ? 0 : 1)); -} - static void gfx_v12_0_ring_emit_rreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t reg_val_offs) { @@ -5307,11 +5297,12 @@ static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring, struct amdgpu_fence *timedout_fence) { struct amdgpu_device *adev = ring->adev; + bool use_mmio = false; int r; amdgpu_ring_reset_helper_begin(ring, timedout_fence); - r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, false); + r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, use_mmio); if (r) { dev_warn(adev->dev, "reset via MES failed and try pipe reset %d\n", r); r = gfx_v12_reset_gfx_pipe(ring); @@ -5319,16 +5310,18 @@ static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring, return r; } - r = gfx_v12_0_kgq_init_queue(ring, true); - if (r) { - dev_err(adev->dev, "failed to init kgq\n"); - return r; - } + if (use_mmio) { + r = gfx_v12_0_kgq_init_queue(ring, true); + if (r) { + dev_err(adev->dev, "failed to init kgq\n"); + return r; + } - r = amdgpu_mes_map_legacy_queue(adev, ring); - if (r) { - dev_err(adev->dev, "failed to remap kgq\n"); - return r; + r = amdgpu_mes_map_legacy_queue(adev, ring); + if (r) { + dev_err(adev->dev, "failed to remap kgq\n"); + return r; + } } return amdgpu_ring_reset_helper_end(ring, timedout_fence); @@ -5519,7 +5512,6 @@ static const struct amdgpu_ring_funcs gfx_v12_0_ring_funcs_gfx = { .emit_cntxcntl = gfx_v12_0_ring_emit_cntxcntl, .init_cond_exec = gfx_v12_0_ring_emit_init_cond_exec, .preempt_ib = gfx_v12_0_ring_preempt_ib, - .emit_frame_cntl = gfx_v12_0_ring_emit_frame_cntl, .emit_wreg = gfx_v12_0_ring_emit_wreg, .emit_reg_wait = gfx_v12_0_ring_emit_reg_wait, .emit_reg_write_reg_wait = gfx_v12_0_ring_emit_reg_write_reg_wait, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index dd19a97436db95..7d0a2d239b78dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2409,7 +2409,7 @@ static int gfx_v9_0_sw_init(struct amdgpu_ip_block *ip_block) amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]); adev->gfx.compute_supported_reset = amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]); - if (!amdgpu_sriov_vf(adev)) + if (!amdgpu_sriov_vf(adev) && !adev->debug_disable_gpu_ring_reset) adev->gfx.compute_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; r = amdgpu_gfx_kiq_init(adev, GFX9_MEC_HPD_SIZE, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index c90cbe053ef37b..a4ebb6c5af5574 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -1149,14 +1149,16 @@ static int gfx_v9_4_3_sw_init(struct amdgpu_ip_block *ip_block) case IP_VERSION(9, 4, 3): case IP_VERSION(9, 4, 4): if ((adev->gfx.mec_fw_version >= 155) && - !amdgpu_sriov_vf(adev)) { + !amdgpu_sriov_vf(adev) && + !adev->debug_disable_gpu_ring_reset) { adev->gfx.compute_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; adev->gfx.compute_supported_reset |= AMDGPU_RESET_TYPE_PER_PIPE; } break; case IP_VERSION(9, 5, 0): if ((adev->gfx.mec_fw_version >= 21) && - !amdgpu_sriov_vf(adev)) { + !amdgpu_sriov_vf(adev) && + !adev->debug_disable_gpu_ring_reset) { adev->gfx.compute_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; adev->gfx.compute_supported_reset |= AMDGPU_RESET_TYPE_PER_PIPE; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index 7bc389d9f5c487..8acc912e7e4cb3 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -103,12 +103,39 @@ static int gmc_v11_0_process_interrupt(struct amdgpu_device *adev, uint32_t vmhub_index = entry->client_id == SOC21_IH_CLIENTID_VMC ? AMDGPU_MMHUB0(0) : AMDGPU_GFXHUB(0); struct amdgpu_vmhub *hub = &adev->vmhub[vmhub_index]; + bool retry_fault = !!(entry->src_data[1] & 0x80); + bool write_fault = !!(entry->src_data[1] & 0x20); uint32_t status = 0; u64 addr; addr = (u64)entry->src_data[0] << 12; addr |= ((u64)entry->src_data[1] & 0xf) << 44; + if (retry_fault) { + /* Returning 1 here also prevents sending the IV to the KFD */ + + /* Process it only if it's the first fault for this address */ + if (entry->ih != &adev->irq.ih_soft && + amdgpu_gmc_filter_faults(adev, entry->ih, addr, entry->pasid, + entry->timestamp)) + return 1; + + /* Delegate it to a different ring if the hardware hasn't + * already done it. + */ + if (entry->ih == &adev->irq.ih) { + amdgpu_irq_delegate(adev, entry, 8); + return 1; + } + + /* Try to handle the recoverable page faults by filling page + * tables + */ + if (amdgpu_vm_handle_fault(adev, entry->pasid, 0, 0, addr, + entry->timestamp, write_fault)) + return 1; + } + if (!amdgpu_sriov_vf(adev)) { /* * Issue a dummy read to wait for the status register to diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c index f4a19357ccbc65..3746d39182707f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c @@ -91,6 +91,8 @@ static int gmc_v12_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_iv_entry *entry) { struct amdgpu_vmhub *hub; + bool retry_fault = !!(entry->src_data[1] & 0x80); + bool write_fault = !!(entry->src_data[1] & 0x20); uint32_t status = 0; u64 addr; @@ -102,6 +104,31 @@ static int gmc_v12_0_process_interrupt(struct amdgpu_device *adev, else hub = &adev->vmhub[AMDGPU_GFXHUB(0)]; + if (retry_fault) { + /* Returning 1 here also prevents sending the IV to the KFD */ + + /* Process it only if it's the first fault for this address */ + if (entry->ih != &adev->irq.ih_soft && + amdgpu_gmc_filter_faults(adev, entry->ih, addr, entry->pasid, + entry->timestamp)) + return 1; + + /* Delegate it to a different ring if the hardware hasn't + * already done it. + */ + if (entry->ih == &adev->irq.ih) { + amdgpu_irq_delegate(adev, entry, 8); + return 1; + } + + /* Try to handle the recoverable page faults by filling page + * tables + */ + if (amdgpu_vm_handle_fault(adev, entry->pasid, 0, 0, addr, + entry->timestamp, write_fault)) + return 1; + } + if (!amdgpu_sriov_vf(adev)) { /* * Issue a dummy read to wait for the status register to diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 0d1dd587db5f49..fd9485e9dd1931 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1233,16 +1233,16 @@ static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev, *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_NC); break; case AMDGPU_VM_MTYPE_WC: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_WC); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_WC); break; case AMDGPU_VM_MTYPE_RW: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_RW); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_RW); break; case AMDGPU_VM_MTYPE_CC: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_CC); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_CC); break; case AMDGPU_VM_MTYPE_UC: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_UC); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_UC); break; } diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c index 1cd9eaeef38f97..f5aa83ff57f351 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c @@ -254,7 +254,6 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_mqd *mqd_hw_default = &adev->mqds[queue->queue_type]; struct drm_amdgpu_userq_in *mqd_user = args_in; struct amdgpu_mqd_prop *userq_props; - struct amdgpu_gfx_shadow_info shadow_info; int r; /* Structure to initialize MQD for userqueue using generic MQD init function */ @@ -280,8 +279,6 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr, userq_props->doorbell_index = queue->doorbell_index; userq_props->fence_address = queue->fence_drv->gpu_addr; - if (adev->gfx.funcs->get_gfx_shadow_info) - adev->gfx.funcs->get_gfx_shadow_info(adev, &shadow_info, true); if (queue->queue_type == AMDGPU_HW_IP_COMPUTE) { struct drm_amdgpu_userq_mqd_compute_gfx11 *compute_mqd; @@ -298,8 +295,9 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr, goto free_mqd; } - if (amdgpu_userq_input_va_validate(queue->vm, compute_mqd->eop_va, - max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE))) + r = amdgpu_userq_input_va_validate(queue, compute_mqd->eop_va, + 2048); + if (r) goto free_mqd; userq_props->eop_gpu_addr = compute_mqd->eop_va; @@ -311,6 +309,14 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr, kfree(compute_mqd); } else if (queue->queue_type == AMDGPU_HW_IP_GFX) { struct drm_amdgpu_userq_mqd_gfx11 *mqd_gfx_v11; + struct amdgpu_gfx_shadow_info shadow_info; + + if (adev->gfx.funcs->get_gfx_shadow_info) { + adev->gfx.funcs->get_gfx_shadow_info(adev, &shadow_info, true); + } else { + r = -EINVAL; + goto free_mqd; + } if (mqd_user->mqd_size != sizeof(*mqd_gfx_v11) || !mqd_user->mqd) { DRM_ERROR("Invalid GFX MQD\n"); @@ -330,8 +336,13 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr, userq_props->tmz_queue = mqd_user->flags & AMDGPU_USERQ_CREATE_FLAGS_QUEUE_SECURE; - if (amdgpu_userq_input_va_validate(queue->vm, mqd_gfx_v11->shadow_va, - shadow_info.shadow_size)) + r = amdgpu_userq_input_va_validate(queue, mqd_gfx_v11->shadow_va, + shadow_info.shadow_size); + if (r) + goto free_mqd; + r = amdgpu_userq_input_va_validate(queue, mqd_gfx_v11->csa_va, + shadow_info.csa_size); + if (r) goto free_mqd; kfree(mqd_gfx_v11); @@ -350,9 +361,9 @@ static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr, r = -ENOMEM; goto free_mqd; } - - if (amdgpu_userq_input_va_validate(queue->vm, mqd_sdma_v11->csa_va, - shadow_info.csa_size)) + r = amdgpu_userq_input_va_validate(queue, mqd_sdma_v11->csa_va, + 32); + if (r) goto free_mqd; userq_props->csa_addr = mqd_sdma_v11->csa_va; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index da575bb1377f14..05546a6e80aeca 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -1667,7 +1667,7 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block) if (r) goto failure; - if ((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x50) { + if ((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x52) { r = mes_v11_0_set_hw_resources_1(&adev->mes); if (r) { DRM_ERROR("failed mes_v11_0_set_hw_resources_1, r=%d\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c index 36b1ca73c2ed32..a1443990d5c60d 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c @@ -2361,11 +2361,15 @@ static void sdma_v4_4_2_update_reset_mask(struct amdgpu_device *adev) switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { case IP_VERSION(9, 4, 3): case IP_VERSION(9, 4, 4): - if ((adev->gfx.mec_fw_version >= 0xb0) && amdgpu_dpm_reset_sdma_is_supported(adev)) + if ((adev->gfx.mec_fw_version >= 0xb0) && + amdgpu_dpm_reset_sdma_is_supported(adev) && + !adev->debug_disable_gpu_ring_reset) adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; break; case IP_VERSION(9, 5, 0): - if ((adev->gfx.mec_fw_version >= 0xf) && amdgpu_dpm_reset_sdma_is_supported(adev)) + if ((adev->gfx.mec_fw_version >= 0xf) && + amdgpu_dpm_reset_sdma_is_supported(adev) && + !adev->debug_disable_gpu_ring_reset) adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index 7dc67a22a7a01d..45e2933214a802 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -1424,17 +1424,9 @@ static int sdma_v5_0_sw_init(struct amdgpu_ip_block *ip_block) adev->sdma.supported_reset = amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring); - switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) { - case IP_VERSION(5, 0, 0): - case IP_VERSION(5, 0, 2): - case IP_VERSION(5, 0, 5): - if ((adev->sdma.instance[0].fw_version >= 35) && - !amdgpu_sriov_vf(adev)) - adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; - break; - default: - break; - } + if (!amdgpu_sriov_vf(adev) && + !adev->debug_disable_gpu_ring_reset) + adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; /* Allocate memory for SDMA IP Dump buffer */ ptr = kcalloc(adev->sdma.num_instances * reg_count, sizeof(uint32_t), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 3bd44c24f692db..5b982cc91af391 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -1342,23 +1342,9 @@ static int sdma_v5_2_sw_init(struct amdgpu_ip_block *ip_block) adev->sdma.supported_reset = amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring); - switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) { - case IP_VERSION(5, 2, 0): - case IP_VERSION(5, 2, 2): - case IP_VERSION(5, 2, 3): - case IP_VERSION(5, 2, 4): - if ((adev->sdma.instance[0].fw_version >= 76) && - !amdgpu_sriov_vf(adev)) - adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; - break; - case IP_VERSION(5, 2, 5): - if ((adev->sdma.instance[0].fw_version >= 34) && - !amdgpu_sriov_vf(adev)) - adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; - break; - default: - break; - } + if (!amdgpu_sriov_vf(adev) && + !adev->debug_disable_gpu_ring_reset) + adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; /* Allocate memory for SDMA IP Dump buffer */ ptr = kcalloc(adev->sdma.num_instances * reg_count, sizeof(uint32_t), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index db6e41967f126b..6809c6d4be5b1b 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -1351,17 +1351,9 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block) adev->sdma.supported_reset = amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring); - switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) { - case IP_VERSION(6, 0, 0): - case IP_VERSION(6, 0, 2): - case IP_VERSION(6, 0, 3): - if ((adev->sdma.instance[0].fw_version >= 21) && - !amdgpu_sriov_vf(adev)) - adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; - break; - default: - break; - } + if (!amdgpu_sriov_vf(adev) && + !adev->debug_disable_gpu_ring_reset) + adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; if (amdgpu_sdma_ras_sw_init(adev)) { dev_err(adev->dev, "Failed to initialize sdma ras block!\n"); @@ -1389,7 +1381,7 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block) adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; break; case IP_VERSION(6, 0, 3): - if ((adev->sdma.instance[0].fw_version >= 27) && !adev->sdma.disable_uq) + if (adev->sdma.instance[0].fw_version >= 29 && !adev->sdma.disable_uq) adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; break; case IP_VERSION(6, 1, 0): diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c index 326ecc8d37d21d..2b81344dcd668a 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c @@ -1337,7 +1337,8 @@ static int sdma_v7_0_sw_init(struct amdgpu_ip_block *ip_block) adev->sdma.supported_reset = amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring); - if (!amdgpu_sriov_vf(adev)) + if (!amdgpu_sriov_vf(adev) && + !adev->debug_disable_gpu_ring_reset) adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; r = amdgpu_sdma_sysfs_reset_mask_init(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index ad36c96478a826..25536d89635d35 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -225,7 +225,13 @@ static u32 soc21_get_config_memsize(struct amdgpu_device *adev) static u32 soc21_get_xclk(struct amdgpu_device *adev) { - return adev->clock.spll.reference_freq; + u32 reference_clock = adev->clock.spll.reference_freq; + + /* reference clock is actually 99.81 Mhz rather than 100 Mhz */ + if ((adev->flags & AMD_IS_APU) && reference_clock == 10000) + return 9981; + + return reference_clock; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index 8897dcc9c1a0a9..e35fae9cdaf66e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -1964,7 +1964,8 @@ static int vcn_v2_0_start_sriov(struct amdgpu_device *adev) struct mmsch_v2_0_cmd_end end = { {0} }; struct mmsch_v2_0_init_header *header; uint32_t *init_table = adev->virt.mm_table.cpu_addr; - uint8_t i = 0; + + /* This path only programs VCN instance 0. */ header = (struct mmsch_v2_0_init_header *)init_table; direct_wt.cmd_header.command_type = MMSCH_COMMAND__DIRECT_REG_WRITE; @@ -1983,93 +1984,93 @@ static int vcn_v2_0_start_sriov(struct amdgpu_device *adev) size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[0].fw->size + 4); MMSCH_V2_0_INSERT_DIRECT_RD_MOD_WT( - SOC15_REG_OFFSET(UVD, i, mmUVD_STATUS), + SOC15_REG_OFFSET(UVD, 0, mmUVD_STATUS), 0xFFFFFFFF, 0x00000004); /* mc resume*/ if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, + SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW), adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_lo); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, + SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH), adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_hi); offset = 0; } else { MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, + SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW), lower_32_bits(adev->vcn.inst->gpu_addr)); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, + SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH), upper_32_bits(adev->vcn.inst->gpu_addr)); offset = size; } MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET0), + SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0), 0); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE0), + SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_SIZE0), size); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, + SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW), lower_32_bits(adev->vcn.inst->gpu_addr + offset)); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, + SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH), upper_32_bits(adev->vcn.inst->gpu_addr + offset)); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET1), + SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_OFFSET1), 0); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE1), + SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_SIZE1), AMDGPU_VCN_STACK_SIZE); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, + SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW), lower_32_bits(adev->vcn.inst->gpu_addr + offset + AMDGPU_VCN_STACK_SIZE)); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, + SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH), upper_32_bits(adev->vcn.inst->gpu_addr + offset + AMDGPU_VCN_STACK_SIZE)); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET2), + SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_OFFSET2), 0); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE2), + SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_SIZE2), AMDGPU_VCN_CONTEXT_SIZE); for (r = 0; r < adev->vcn.inst[0].num_enc_rings; ++r) { ring = &adev->vcn.inst->ring_enc[r]; ring->wptr = 0; MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, mmUVD_RB_BASE_LO), + SOC15_REG_OFFSET(UVD, 0, mmUVD_RB_BASE_LO), lower_32_bits(ring->gpu_addr)); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, mmUVD_RB_BASE_HI), + SOC15_REG_OFFSET(UVD, 0, mmUVD_RB_BASE_HI), upper_32_bits(ring->gpu_addr)); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, mmUVD_RB_SIZE), + SOC15_REG_OFFSET(UVD, 0, mmUVD_RB_SIZE), ring->ring_size / 4); } ring = &adev->vcn.inst->ring_dec; ring->wptr = 0; MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, + SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW), lower_32_bits(ring->gpu_addr)); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, + SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH), upper_32_bits(ring->gpu_addr)); /* force RBC into idle state */ @@ -2080,7 +2081,7 @@ static int vcn_v2_0_start_sriov(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1); tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1); MMSCH_V2_0_INSERT_DIRECT_WT( - SOC15_REG_OFFSET(UVD, i, mmUVD_RBC_RB_CNTL), tmp); + SOC15_REG_OFFSET(UVD, 0, mmUVD_RBC_RB_CNTL), tmp); /* add end packet */ tmp = sizeof(struct mmsch_v2_0_cmd_end); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c index b107ee80e4728a..1f6a22983c0dd5 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c @@ -265,6 +265,8 @@ static int vcn_v4_0_5_sw_fini(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev)) amdgpu_virt_free_mm_table(adev); + amdgpu_vcn_sysfs_reset_mask_fini(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { r = amdgpu_vcn_suspend(adev, i); if (r) diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h index 0320163b6e740f..f98c735b2905f3 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h @@ -3644,14 +3644,18 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = { }; static const uint32_t cwsr_trap_gfx12_hex[] = { - 0xbfa00001, 0xbfa002a2, - 0xb0804009, 0xb8f8f804, + 0xbfa00001, 0xbfa002b2, + 0xb0804009, 0xb8eef81a, + 0xbf880000, 0xb980081a, + 0x00000000, 0xb8f8f804, + 0x9177ff77, 0x0c000000, + 0x846e9a6e, 0x8c776e77, 0x9178ff78, 0x00008c00, 0xb8fbf811, 0x8b6eff78, 0x00004000, 0xbfa10008, 0x8b6eff7b, 0x00000080, 0xbfa20018, 0x8b6ea07b, - 0xbfa20042, 0xbf830010, + 0xbfa2004a, 0xbf830010, 0xb8fbf811, 0xbfa0fffb, 0x8b6eff7b, 0x00000bd0, 0xbfa20010, 0xb8eef812, @@ -3662,28 +3666,32 @@ static const uint32_t cwsr_trap_gfx12_hex[] = { 0xf0000000, 0xbfa20005, 0x8b6fff6f, 0x00000200, 0xbfa20002, 0x8b6ea07b, - 0xbfa2002c, 0xbefa4d82, + 0xbfa20034, 0xbefa4d82, 0xbf8a0000, 0x84fa887a, 0xbf0d8f7b, 0xbfa10002, 0x8c7bff7b, 0xffff0000, - 0xf4601bbd, 0xf8000010, - 0xbf8a0000, 0x846e976e, - 0x9177ff77, 0x00800000, - 0x8c776e77, 0xf4603bbd, - 0xf8000000, 0xbf8a0000, - 0xf4603ebd, 0xf8000008, - 0xbf8a0000, 0x8bee6e6e, - 0xbfa10001, 0xbe80486e, - 0x8b6eff6d, 0xf0000000, - 0xbfa20009, 0xb8eef811, - 0x8b6eff6e, 0x00000080, - 0xbfa20007, 0x8c78ff78, - 0x00004000, 0x80ec886c, - 0x82ed806d, 0xbfa00002, - 0x806c846c, 0x826d806d, - 0x8b6dff6d, 0x0000ffff, - 0x8bfe7e7e, 0x8bea6a6a, - 0x85788978, 0xb9783244, + 0x8b6eff77, 0x0c000000, + 0x916dff6d, 0x0c000000, + 0x8c6d6e6d, 0xf4601bbd, + 0xf8000010, 0xbf8a0000, + 0x846e976e, 0x9177ff77, + 0x00800000, 0x8c776e77, + 0xf4603bbd, 0xf8000000, + 0xbf8a0000, 0xf4603ebd, + 0xf8000008, 0xbf8a0000, + 0x8bee6e6e, 0xbfa10001, + 0xbe80486e, 0x8b6eff6d, + 0xf0000000, 0xbfa20009, + 0xb8eef811, 0x8b6eff6e, + 0x00000080, 0xbfa20007, + 0x8c78ff78, 0x00004000, + 0x80ec886c, 0x82ed806d, + 0xbfa00002, 0x806c846c, + 0x826d806d, 0x8b6dff6d, + 0x0000ffff, 0x8bfe7e7e, + 0x8bea6a6a, 0x85788978, + 0x936eff77, 0x0002001a, + 0xb96ef81a, 0xb9783244, 0xbe804a6c, 0xb8faf802, 0xbf0d987a, 0xbfa10001, 0xbfb00000, 0x8b6dff6d, @@ -3981,7 +3989,7 @@ static const uint32_t cwsr_trap_gfx12_hex[] = { 0x008ce800, 0x00000000, 0x807d817d, 0x8070ff70, 0x00000080, 0xbf0a7b7d, - 0xbfa2fff7, 0xbfa0016e, + 0xbfa2fff7, 0xbfa00171, 0xbef4007e, 0x8b75ff7f, 0x0000ffff, 0x8c75ff75, 0x00040000, 0xbef60080, @@ -4163,12 +4171,14 @@ static const uint32_t cwsr_trap_gfx12_hex[] = { 0xf8000074, 0xbf8a0000, 0x8b6dff6d, 0x0000ffff, 0x8bfe7e7e, 0x8bea6a6a, - 0xb97af804, 0xbe804ec2, - 0xbf94fffe, 0xbe804a6c, + 0x936eff77, 0x0002001a, + 0xb96ef81a, 0xb97af804, 0xbe804ec2, 0xbf94fffe, - 0xbfb10000, 0xbf9f0000, + 0xbe804a6c, 0xbe804ec2, + 0xbf94fffe, 0xbfb10000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, + 0xbf9f0000, 0x00000000, }; static const uint32_t cwsr_trap_gfx9_5_0_hex[] = { diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm index 5a1a1b1f897fe3..07999b4649ded0 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm @@ -78,9 +78,16 @@ var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SHIFT = SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SIZE = SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_SHIFT - SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT = SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_SHIFT var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SIZE = 32 - SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT + +var SQ_WAVE_SCHED_MODE_DEP_MODE_SHIFT = 0 +var SQ_WAVE_SCHED_MODE_DEP_MODE_SIZE = 2 + var BARRIER_STATE_SIGNAL_OFFSET = 16 var BARRIER_STATE_VALID_OFFSET = 0 +var TTMP11_SCHED_MODE_SHIFT = 26 +var TTMP11_SCHED_MODE_SIZE = 2 +var TTMP11_SCHED_MODE_MASK = 0xC000000 var TTMP11_DEBUG_TRAP_ENABLED_SHIFT = 23 var TTMP11_DEBUG_TRAP_ENABLED_MASK = 0x800000 @@ -160,8 +167,19 @@ L_JUMP_TO_RESTORE: s_branch L_RESTORE L_SKIP_RESTORE: + // Assume most relaxed scheduling mode is set. Save and revert to normal mode. + s_getreg_b32 ttmp2, hwreg(HW_REG_WAVE_SCHED_MODE) + s_wait_alu 0 + s_setreg_imm32_b32 hwreg(HW_REG_WAVE_SCHED_MODE, \ + SQ_WAVE_SCHED_MODE_DEP_MODE_SHIFT, SQ_WAVE_SCHED_MODE_DEP_MODE_SIZE), 0 + s_getreg_b32 s_save_state_priv, hwreg(HW_REG_WAVE_STATE_PRIV) //save STATUS since we will change SCC + // Save SCHED_MODE[1:0] into ttmp11[27:26]. + s_andn2_b32 ttmp11, ttmp11, TTMP11_SCHED_MODE_MASK + s_lshl_b32 ttmp2, ttmp2, TTMP11_SCHED_MODE_SHIFT + s_or_b32 ttmp11, ttmp11, ttmp2 + // Clear SPI_PRIO: do not save with elevated priority. // Clear ECC_ERR: prevents SQC store and triggers FATAL_HALT if setreg'd. s_andn2_b32 s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_ALWAYS_CLEAR_MASK @@ -238,6 +256,13 @@ L_FETCH_2ND_TRAP: s_cbranch_scc0 L_NO_SIGN_EXTEND_TMA s_or_b32 ttmp15, ttmp15, 0xFFFF0000 L_NO_SIGN_EXTEND_TMA: +#if ASIC_FAMILY == CHIP_GFX12 + // Move SCHED_MODE[1:0] from ttmp11 to unused bits in ttmp1[27:26] (return PC_HI). + // The second-level trap will restore from ttmp1 for backwards compatibility. + s_and_b32 ttmp2, ttmp11, TTMP11_SCHED_MODE_MASK + s_andn2_b32 ttmp1, ttmp1, TTMP11_SCHED_MODE_MASK + s_or_b32 ttmp1, ttmp1, ttmp2 +#endif s_load_dword ttmp2, [ttmp14, ttmp15], 0x10 scope:SCOPE_SYS // debug trap enabled flag s_wait_idle @@ -287,6 +312,10 @@ L_EXIT_TRAP: // STATE_PRIV.BARRIER_COMPLETE may have changed since we read it. // Only restore fields which the trap handler changes. s_lshr_b32 s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_SCC_SHIFT + + // Assume relaxed scheduling mode after this point. + restore_sched_mode(ttmp2) + s_setreg_b32 hwreg(HW_REG_WAVE_STATE_PRIV, SQ_WAVE_STATE_PRIV_SCC_SHIFT, \ SQ_WAVE_STATE_PRIV_POISON_ERR_SHIFT - SQ_WAVE_STATE_PRIV_SCC_SHIFT + 1), s_save_state_priv @@ -1043,6 +1072,9 @@ L_SKIP_BARRIER_RESTORE: s_and_b64 exec, exec, exec // Restore STATUS.EXECZ, not writable by s_setreg_b32 s_and_b64 vcc, vcc, vcc // Restore STATUS.VCCZ, not writable by s_setreg_b32 + // Assume relaxed scheduling mode after this point. + restore_sched_mode(s_restore_tmp) + s_setreg_b32 hwreg(HW_REG_WAVE_STATE_PRIV), s_restore_state_priv // SCC is included, which is changed by previous salu // Make barrier and LDS state visible to all waves in the group. @@ -1134,3 +1166,8 @@ function valu_sgpr_hazard end #endif end + +function restore_sched_mode(s_tmp) + s_bfe_u32 s_tmp, ttmp11, (TTMP11_SCHED_MODE_SHIFT | (TTMP11_SCHED_MODE_SIZE << 0x10)) + s_setreg_b32 hwreg(HW_REG_WAVE_SCHED_MODE), s_tmp +end diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c index ba99e0f258aee2..986cb297de8f83 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c @@ -401,27 +401,25 @@ static int kfd_dbg_get_dev_watch_id(struct kfd_process_device *pdd, int *watch_i return -ENOMEM; } -static void kfd_dbg_clear_dev_watch_id(struct kfd_process_device *pdd, int watch_id) +static void kfd_dbg_clear_dev_watch_id(struct kfd_process_device *pdd, u32 watch_id) { spin_lock(&pdd->dev->watch_points_lock); /* process owns device watch point so safe to clear */ - if ((pdd->alloc_watch_ids >> watch_id) & 0x1) { - pdd->alloc_watch_ids &= ~(0x1 << watch_id); - pdd->dev->alloc_watch_ids &= ~(0x1 << watch_id); + if (pdd->alloc_watch_ids & BIT(watch_id)) { + pdd->alloc_watch_ids &= ~BIT(watch_id); + pdd->dev->alloc_watch_ids &= ~BIT(watch_id); } spin_unlock(&pdd->dev->watch_points_lock); } -static bool kfd_dbg_owns_dev_watch_id(struct kfd_process_device *pdd, int watch_id) +static bool kfd_dbg_owns_dev_watch_id(struct kfd_process_device *pdd, u32 watch_id) { bool owns_watch_id = false; spin_lock(&pdd->dev->watch_points_lock); - owns_watch_id = watch_id < MAX_WATCH_ADDRESSES && - ((pdd->alloc_watch_ids >> watch_id) & 0x1); - + owns_watch_id = pdd->alloc_watch_ids & BIT(watch_id); spin_unlock(&pdd->dev->watch_points_lock); return owns_watch_id; @@ -432,6 +430,9 @@ int kfd_dbg_trap_clear_dev_address_watch(struct kfd_process_device *pdd, { int r; + if (watch_id >= MAX_WATCH_ADDRESSES) + return -EINVAL; + if (!kfd_dbg_owns_dev_watch_id(pdd, watch_id)) return -EINVAL; @@ -469,6 +470,9 @@ int kfd_dbg_trap_set_dev_address_watch(struct kfd_process_device *pdd, if (r) return r; + if (*watch_id >= MAX_WATCH_ADDRESSES) + return -EINVAL; + if (!pdd->dev->kfd->shared_resources.enable_mes) { r = debug_lock_and_unmap(pdd->dev->dqm); if (r) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 6e7bc983fc0b68..58c5acf50a2204 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1209,14 +1209,8 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, pr_debug_ratelimited("Evicting process pid %d queues\n", pdd->process->lead_thread->pid); - if (dqm->dev->kfd->shared_resources.enable_mes) { + if (dqm->dev->kfd->shared_resources.enable_mes) pdd->last_evict_timestamp = get_jiffies_64(); - retval = suspend_all_queues_mes(dqm); - if (retval) { - dev_err(dev, "Suspending all queues failed"); - goto out; - } - } /* Mark all queues as evicted. Deactivate all active queues on * the qpd. @@ -1246,10 +1240,6 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES : KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0, USE_DEFAULT_GRACE_PERIOD); - } else { - retval = resume_all_queues_mes(dqm); - if (retval) - dev_err(dev, "Resuming all queues failed"); } out: @@ -2915,6 +2905,14 @@ static int allocate_hiq_sdma_mqd(struct device_queue_manager *dqm) return retval; } +static void deallocate_hiq_sdma_mqd(struct kfd_node *dev, + struct kfd_mem_obj *mqd) +{ + WARN(!mqd, "No hiq sdma mqd trunk to free"); + + amdgpu_amdkfd_free_gtt_mem(dev->adev, &mqd->gtt_mem); +} + struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) { struct device_queue_manager *dqm; @@ -3038,19 +3036,14 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) return dqm; } + if (!dev->kfd->shared_resources.enable_mes) + deallocate_hiq_sdma_mqd(dev, &dqm->hiq_sdma_mqd); + out_free: kfree(dqm); return NULL; } -static void deallocate_hiq_sdma_mqd(struct kfd_node *dev, - struct kfd_mem_obj *mqd) -{ - WARN(!mqd, "No hiq sdma mqd trunk to free"); - - amdgpu_amdkfd_free_gtt_mem(dev->adev, &mqd->gtt_mem); -} - void device_queue_manager_uninit(struct device_queue_manager *dqm) { dqm->ops.stop(dqm); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index ddfe30c13e9d6e..8ed513a77d38f0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1992,7 +1992,7 @@ static int signal_eviction_fence(struct kfd_process *p) ef = dma_fence_get_rcu_safe(&p->ef); rcu_read_unlock(); if (!ef) - return -EINVAL; + return true; ret = dma_fence_signal(ef); dma_fence_put(ef); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c index f1e7583650c416..80c4fa2b0975dc 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c @@ -409,6 +409,7 @@ static u32 kfd_get_vgpr_size_per_cu(u32 gfxv) vgpr_size = 0x80000; else if (gfxv == 110000 || /* GFX_VERSION_PLUM_BONITO */ gfxv == 110001 || /* GFX_VERSION_WHEAT_NAS */ + gfxv == 110501 || /* GFX_VERSION_GFX1151 */ gfxv == 120000 || /* GFX_VERSION_GFX1200 */ gfxv == 120001) /* GFX_VERSION_GFX1201 */ vgpr_size = 0x60000; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index a499449fcb068a..d2bc169e84b0b6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -312,7 +312,7 @@ void kfd_smi_event_queue_restore(struct kfd_node *node, pid_t pid) { kfd_smi_event_add(pid, node, KFD_SMI_EVENT_QUEUE_RESTORE, KFD_EVENT_FMT_QUEUE_RESTORE(ktime_get_boottime_ns(), pid, - node->id, 0)); + node->id, '0')); } void kfd_smi_event_queue_restore_rescheduled(struct mm_struct *mm) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 74a1d3e1d52bee..49dd0a81114e4c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1144,30 +1144,48 @@ static int svm_range_split_tail(struct svm_range *prange, uint64_t new_last, struct list_head *insert_list, struct list_head *remap_list) { + unsigned long last_align_down = ALIGN_DOWN(prange->last, 512); + unsigned long start_align = ALIGN(prange->start, 512); + bool huge_page_mapping = last_align_down > start_align; struct svm_range *tail = NULL; - int r = svm_range_split(prange, prange->start, new_last, &tail); + int r; - if (!r) { - list_add(&tail->list, insert_list); - if (!IS_ALIGNED(new_last + 1, 1UL << prange->granularity)) - list_add(&tail->update_list, remap_list); - } - return r; + r = svm_range_split(prange, prange->start, new_last, &tail); + + if (r) + return r; + + list_add(&tail->list, insert_list); + + if (huge_page_mapping && tail->start > start_align && + tail->start < last_align_down && (!IS_ALIGNED(tail->start, 512))) + list_add(&tail->update_list, remap_list); + + return 0; } static int svm_range_split_head(struct svm_range *prange, uint64_t new_start, struct list_head *insert_list, struct list_head *remap_list) { + unsigned long last_align_down = ALIGN_DOWN(prange->last, 512); + unsigned long start_align = ALIGN(prange->start, 512); + bool huge_page_mapping = last_align_down > start_align; struct svm_range *head = NULL; - int r = svm_range_split(prange, new_start, prange->last, &head); + int r; - if (!r) { - list_add(&head->list, insert_list); - if (!IS_ALIGNED(new_start, 1UL << prange->granularity)) - list_add(&head->update_list, remap_list); - } - return r; + r = svm_range_split(prange, new_start, prange->last, &head); + + if (r) + return r; + + list_add(&head->list, insert_list); + + if (huge_page_mapping && head->last + 1 > start_align && + head->last + 1 < last_align_down && (!IS_ALIGNED(head->last, 512))) + list_add(&head->update_list, remap_list); + + return 0; } static void diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 5c98746eb72dfc..3eb32d58a12007 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -491,6 +491,10 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr, dev->node_props.num_sdma_queues_per_engine); sysfs_show_32bit_prop(buffer, offs, "num_cp_queues", dev->node_props.num_cp_queues); + sysfs_show_32bit_prop(buffer, offs, "cwsr_size", + dev->node_props.cwsr_size); + sysfs_show_32bit_prop(buffer, offs, "ctl_stack_size", + dev->node_props.ctl_stack_size); if (dev->gpu) { log_max_watch_addr = @@ -530,7 +534,9 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr, sysfs_show_32bit_prop(buffer, offs, "sdma_fw_version", dev->gpu->kfd->sdma_fw_version); sysfs_show_64bit_prop(buffer, offs, "unique_id", - dev->gpu->xcp ? + dev->gpu->xcp && + (dev->gpu->xcp->xcp_mgr->mode != + AMDGPU_SPX_PARTITION_MODE) ? dev->gpu->xcp->unique_id : dev->gpu->adev->unique_id); sysfs_show_32bit_prop(buffer, offs, "num_xcc", diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 7fe40bbba26588..a0077fe79ed269 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5193,6 +5193,8 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) struct amdgpu_dm_backlight_caps *caps; char bl_name[16]; int min, max; + int real_brightness; + int init_brightness; if (aconnector->bl_idx == -1) return; @@ -5217,6 +5219,8 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) } else props.brightness = props.max_brightness = MAX_BACKLIGHT_LEVEL; + init_brightness = props.brightness; + if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)) { drm_info(drm, "Using custom brightness curve\n"); props.scale = BACKLIGHT_SCALE_NON_LINEAR; @@ -5235,8 +5239,20 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) if (IS_ERR(dm->backlight_dev[aconnector->bl_idx])) { drm_err(drm, "DM: Backlight registration failed!\n"); dm->backlight_dev[aconnector->bl_idx] = NULL; - } else + } else { + /* + * dm->brightness[x] can be inconsistent just after startup until + * ops.get_brightness is called. + */ + real_brightness = + amdgpu_dm_backlight_ops.get_brightness(dm->backlight_dev[aconnector->bl_idx]); + + if (real_brightness != init_brightness) { + dm->actual_brightness[aconnector->bl_idx] = real_brightness; + dm->brightness[aconnector->bl_idx] = real_brightness; + } drm_dbg_driver(drm, "DM: Registered Backlight device: %s\n", bl_name); + } } static int initialize_plane(struct amdgpu_display_manager *dm, @@ -5545,7 +5561,8 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) if (psr_feature_enabled) { amdgpu_dm_set_psr_caps(link); - drm_info(adev_to_drm(adev), "PSR support %d, DC PSR ver %d, sink PSR ver %d DPCD caps 0x%x su_y_granularity %d\n", + drm_info(adev_to_drm(adev), "%s: PSR support %d, DC PSR ver %d, sink PSR ver %d DPCD caps 0x%x su_y_granularity %d\n", + aconnector->base.name, link->psr_settings.psr_feature_enabled, link->psr_settings.psr_version, link->dpcd_caps.psr_info.psr_version, @@ -7531,10 +7548,12 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector) drm_dp_mst_topology_mgr_destroy(&aconnector->mst_mgr); /* Cancel and flush any pending HDMI HPD debounce work */ - cancel_delayed_work_sync(&aconnector->hdmi_hpd_debounce_work); - if (aconnector->hdmi_prev_sink) { - dc_sink_release(aconnector->hdmi_prev_sink); - aconnector->hdmi_prev_sink = NULL; + if (aconnector->hdmi_hpd_debounce_delay_ms) { + cancel_delayed_work_sync(&aconnector->hdmi_hpd_debounce_work); + if (aconnector->hdmi_prev_sink) { + dc_sink_release(aconnector->hdmi_prev_sink); + aconnector->hdmi_prev_sink = NULL; + } } if (aconnector->bl_idx != -1) { @@ -8698,9 +8717,18 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, mutex_init(&aconnector->hpd_lock); mutex_init(&aconnector->handle_mst_msg_ready); - aconnector->hdmi_hpd_debounce_delay_ms = AMDGPU_DM_HDMI_HPD_DEBOUNCE_MS; - INIT_DELAYED_WORK(&aconnector->hdmi_hpd_debounce_work, hdmi_hpd_debounce_work); - aconnector->hdmi_prev_sink = NULL; + /* + * If HDMI HPD debounce delay is set, use the minimum between selected + * value and AMDGPU_DM_MAX_HDMI_HPD_DEBOUNCE_MS + */ + if (amdgpu_hdmi_hpd_debounce_delay_ms) { + aconnector->hdmi_hpd_debounce_delay_ms = min(amdgpu_hdmi_hpd_debounce_delay_ms, + AMDGPU_DM_MAX_HDMI_HPD_DEBOUNCE_MS); + INIT_DELAYED_WORK(&aconnector->hdmi_hpd_debounce_work, hdmi_hpd_debounce_work); + aconnector->hdmi_prev_sink = NULL; + } else { + aconnector->hdmi_hpd_debounce_delay_ms = 0; + } /* * configure support HPD hot plug connector_>polled default value is 0 @@ -12010,10 +12038,9 @@ static int dm_crtc_get_cursor_mode(struct amdgpu_device *adev, /* Overlay cursor not supported on HW before DCN * DCN401 does not have the cursor-on-scaled-plane or cursor-on-yuv-plane restrictions - * as previous DCN generations, so enable native mode on DCN401 in addition to DCE + * as previous DCN generations, so enable native mode on DCN401 */ - if (amdgpu_ip_version(adev, DCE_HWIP, 0) == 0 || - amdgpu_ip_version(adev, DCE_HWIP, 0) == IP_VERSION(4, 0, 1)) { + if (amdgpu_ip_version(adev, DCE_HWIP, 0) == IP_VERSION(4, 0, 1)) { *cursor_mode = DM_CURSOR_NATIVE_MODE; return 0; } @@ -12333,6 +12360,12 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, * need to be added for DC to not disable a plane by mistake */ if (dm_new_crtc_state->cursor_mode == DM_CURSOR_OVERLAY_MODE) { + if (amdgpu_ip_version(adev, DCE_HWIP, 0) == 0) { + drm_dbg(dev, "Overlay cursor not supported on DCE\n"); + ret = -EINVAL; + goto fail; + } + ret = drm_atomic_add_affected_planes(state, crtc); if (ret) goto fail; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 8ca73895759893..adcd7ea696719a 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -59,7 +59,10 @@ #define AMDGPU_HDR_MULT_DEFAULT (0x100000000LL) -#define AMDGPU_DM_HDMI_HPD_DEBOUNCE_MS 1500 +/* + * Maximum HDMI HPD debounce delay in milliseconds + */ +#define AMDGPU_DM_MAX_HDMI_HPD_DEBOUNCE_MS 5000 /* #include "include/amdgpu_dal_power_if.h" #include "amdgpu_dm_irq.h" diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index 38f9ea313dcbb5..2e7ee77c010e18 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -248,8 +248,6 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work) struct vblank_control_work *vblank_work = container_of(work, struct vblank_control_work, work); struct amdgpu_display_manager *dm = vblank_work->dm; - struct amdgpu_device *adev = drm_to_adev(dm->ddev); - int r; mutex_lock(&dm->dc_lock); @@ -279,16 +277,7 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work) if (dm->active_vblank_irq_count == 0) { dc_post_update_surfaces_to_stream(dm->dc); - - r = amdgpu_dpm_pause_power_profile(adev, true); - if (r) - dev_warn(adev->dev, "failed to set default power profile mode\n"); - dc_allow_idle_optimizations(dm->dc, true); - - r = amdgpu_dpm_pause_power_profile(adev, false); - if (r) - dev_warn(adev->dev, "failed to restore the power profile mode\n"); } mutex_unlock(&dm->dc_lock); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index dbd1da4d85d323..5e92eaa67aa33d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -884,28 +884,26 @@ struct dsc_mst_fairness_params { }; #if defined(CONFIG_DRM_AMD_DC_FP) -static uint64_t kbps_to_pbn(int kbps, bool is_peak_pbn) +static uint16_t get_fec_overhead_multiplier(struct dc_link *dc_link) { - uint64_t effective_kbps = (uint64_t)kbps; + u8 link_coding_cap; + uint16_t fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_8B_10B; - if (is_peak_pbn) { // add 0.6% (1006/1000) overhead into effective kbps - effective_kbps *= 1006; - effective_kbps = div_u64(effective_kbps, 1000); - } + link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(dc_link); + if (link_coding_cap == DP_128b_132b_ENCODING) + fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_128B_132B; - return (uint64_t) DIV64_U64_ROUND_UP(effective_kbps * 64, (54 * 8 * 1000)); + return fec_overhead_multiplier_x1000; } -static uint32_t pbn_to_kbps(unsigned int pbn, bool with_margin) +static int kbps_to_peak_pbn(int kbps, uint16_t fec_overhead_multiplier_x1000) { - uint64_t pbn_effective = (uint64_t)pbn; - - if (with_margin) // deduct 0.6% (994/1000) overhead from effective pbn - pbn_effective *= (1000000 / PEAK_FACTOR_X1000); - else - pbn_effective *= 1000; + u64 peak_kbps = kbps; - return DIV_U64_ROUND_UP(pbn_effective * 8 * 54, 64); + peak_kbps *= 1006; + peak_kbps *= fec_overhead_multiplier_x1000; + peak_kbps = div_u64(peak_kbps, 1000 * 1000); + return (int) DIV64_U64_ROUND_UP(peak_kbps * 64, (54 * 8 * 1000)); } static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *params, @@ -976,7 +974,7 @@ static int bpp_x16_from_pbn(struct dsc_mst_fairness_params param, int pbn) dc_dsc_get_default_config_option(param.sink->ctx->dc, &dsc_options); dsc_options.max_target_bpp_limit_override_x16 = drm_connector->display_info.max_dsc_bpp * 16; - kbps = pbn_to_kbps(pbn, false); + kbps = div_u64((u64)pbn * 994 * 8 * 54, 64); dc_dsc_compute_config( param.sink->ctx->dc->res_pool->dscs[0], ¶m.sink->dsc_caps.dsc_dec_caps, @@ -1005,11 +1003,12 @@ static int increase_dsc_bpp(struct drm_atomic_state *state, int link_timeslots_used; int fair_pbn_alloc; int ret = 0; + uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); for (i = 0; i < count; i++) { if (vars[i + k].dsc_enabled) { initial_slack[i] = - kbps_to_pbn(params[i].bw_range.max_kbps, false) - vars[i + k].pbn; + kbps_to_peak_pbn(params[i].bw_range.max_kbps, fec_overhead_multiplier_x1000) - vars[i + k].pbn; bpp_increased[i] = false; remaining_to_increase += 1; } else { @@ -1105,6 +1104,7 @@ static int try_disable_dsc(struct drm_atomic_state *state, int next_index; int remaining_to_try = 0; int ret; + uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); int var_pbn; for (i = 0; i < count; i++) { @@ -1137,7 +1137,7 @@ static int try_disable_dsc(struct drm_atomic_state *state, DRM_DEBUG_DRIVER("MST_DSC index #%d, try no compression\n", next_index); var_pbn = vars[next_index].pbn; - vars[next_index].pbn = kbps_to_pbn(params[next_index].bw_range.stream_kbps, true); + vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps, fec_overhead_multiplier_x1000); ret = drm_dp_atomic_find_time_slots(state, params[next_index].port->mgr, params[next_index].port, @@ -1197,6 +1197,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, int count = 0; int i, k, ret; bool debugfs_overwrite = false; + uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); struct drm_connector_state *new_conn_state; memset(params, 0, sizeof(params)); @@ -1277,7 +1278,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, DRM_DEBUG_DRIVER("MST_DSC Try no compression\n"); for (i = 0; i < count; i++) { vars[i + k].aconnector = params[i].aconnector; - vars[i + k].pbn = kbps_to_pbn(params[i].bw_range.stream_kbps, false); + vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, params[i].port, @@ -1299,7 +1300,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, DRM_DEBUG_DRIVER("MST_DSC Try max compression\n"); for (i = 0; i < count; i++) { if (params[i].compression_possible && params[i].clock_force_enable != DSC_CLK_FORCE_DISABLE) { - vars[i + k].pbn = kbps_to_pbn(params[i].bw_range.min_kbps, false); + vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps, fec_overhead_multiplier_x1000); vars[i + k].dsc_enabled = true; vars[i + k].bpp_x16 = params[i].bw_range.min_target_bpp_x16; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, @@ -1307,7 +1308,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, if (ret < 0) return ret; } else { - vars[i + k].pbn = kbps_to_pbn(params[i].bw_range.stream_kbps, false); + vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, @@ -1762,6 +1763,18 @@ int pre_validate_dsc(struct drm_atomic_state *state, return ret; } +static uint32_t kbps_from_pbn(unsigned int pbn) +{ + uint64_t kbps = (uint64_t)pbn; + + kbps *= (1000000 / PEAK_FACTOR_X1000); + kbps *= 8; + kbps *= 54; + kbps /= 64; + + return (uint32_t)kbps; +} + static bool is_dsc_common_config_possible(struct dc_stream_state *stream, struct dc_dsc_bw_range *bw_range) { @@ -1860,7 +1873,7 @@ enum dc_status dm_dp_mst_is_port_support_mode( dc_link_get_highest_encoding_format(stream->link)); cur_link_settings = stream->link->verified_link_cap; root_link_bw_in_kbps = dc_link_bandwidth_kbps(aconnector->dc_link, &cur_link_settings); - virtual_channel_bw_in_kbps = pbn_to_kbps(aconnector->mst_output_port->full_pbn, true); + virtual_channel_bw_in_kbps = kbps_from_pbn(aconnector->mst_output_port->full_pbn); /* pick the end to end bw bottleneck */ end_to_end_bw_in_kbps = min(root_link_bw_in_kbps, virtual_channel_bw_in_kbps); @@ -1913,7 +1926,7 @@ enum dc_status dm_dp_mst_is_port_support_mode( immediate_upstream_port = aconnector->mst_output_port->parent->port_parent; if (immediate_upstream_port) { - virtual_channel_bw_in_kbps = pbn_to_kbps(immediate_upstream_port->full_pbn, true); + virtual_channel_bw_in_kbps = kbps_from_pbn(immediate_upstream_port->full_pbn); virtual_channel_bw_in_kbps = min(root_link_bw_in_kbps, virtual_channel_bw_in_kbps); } else { /* For topology LCT 1 case - only one mstb*/ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index e027798ece0322..9bb7475e80bad6 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -1059,10 +1059,15 @@ static void amdgpu_dm_plane_get_min_max_dc_plane_scaling(struct drm_device *dev, *min_downscale = plane_cap->max_downscale_factor.nv12; break; + /* All 64 bpp formats have the same fp16 scaling limits */ case DRM_FORMAT_XRGB16161616F: case DRM_FORMAT_ARGB16161616F: case DRM_FORMAT_XBGR16161616F: case DRM_FORMAT_ABGR16161616F: + case DRM_FORMAT_XRGB16161616: + case DRM_FORMAT_ARGB16161616: + case DRM_FORMAT_XBGR16161616: + case DRM_FORMAT_ABGR16161616: *max_upscale = plane_cap->max_upscale_factor.fp16; *min_downscale = plane_cap->max_downscale_factor.fp16; break; diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 04eb647acc4e1a..550a9f1d03f82d 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -1480,10 +1480,10 @@ static enum bp_result get_embedded_panel_info_v2_1( /* not provided by VBIOS */ info->lcd_timing.misc_info.HORIZONTAL_CUT_OFF = 0; - info->lcd_timing.misc_info.H_SYNC_POLARITY = ~(uint32_t) (lvds->lcd_timing.miscinfo - & ATOM_HSYNC_POLARITY); - info->lcd_timing.misc_info.V_SYNC_POLARITY = ~(uint32_t) (lvds->lcd_timing.miscinfo - & ATOM_VSYNC_POLARITY); + info->lcd_timing.misc_info.H_SYNC_POLARITY = !(lvds->lcd_timing.miscinfo & + ATOM_HSYNC_POLARITY); + info->lcd_timing.misc_info.V_SYNC_POLARITY = !(lvds->lcd_timing.miscinfo & + ATOM_VSYNC_POLARITY); /* not provided by VBIOS */ info->lcd_timing.misc_info.VERTICAL_CUT_OFF = 0; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c index 922f23557f5d9e..0971dfa258454e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c @@ -86,7 +86,7 @@ uint8_t dc_plane_get_pipe_mask(struct dc_state *dc_state, const struct dc_plane struct dc_plane_state *dc_create_plane_state(const struct dc *dc) { struct dc_plane_state *plane_state = kvzalloc(sizeof(*plane_state), - GFP_KERNEL); + GFP_ATOMIC); if (NULL == plane_state) return NULL; diff --git a/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h b/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h index b015e80672ec9b..fcd3ab4b004594 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h @@ -41,7 +41,7 @@ /* kHZ*/ #define DP_ADAPTOR_DVI_MAX_TMDS_CLK 165000 /* kHZ*/ -#define DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK 165000 +#define DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK 340000 struct dp_hdmi_dongle_signature_data { int8_t id[15];/* "DP-HDMI ADAPTOR"*/ diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c index 0690c346f2c521..227aa8672d17ba 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c @@ -105,9 +105,12 @@ void cm_helper_program_gamcor_xfer_func( #define NUMBER_REGIONS 32 #define NUMBER_SW_SEGMENTS 16 -bool cm3_helper_translate_curve_to_hw_format( - const struct dc_transfer_func *output_tf, - struct pwl_params *lut_params, bool fixpoint) +#define DC_LOGGER \ + ctx->logger + +bool cm3_helper_translate_curve_to_hw_format(struct dc_context *ctx, + const struct dc_transfer_func *output_tf, + struct pwl_params *lut_params, bool fixpoint) { struct curve_points3 *corner_points; struct pwl_result_data *rgb_resulted; @@ -163,6 +166,11 @@ bool cm3_helper_translate_curve_to_hw_format( hw_points += (1 << seg_distr[k]); } + // DCN3+ have 257 pts in lieu of no separate slope registers + // Prior HW had 256 base+slope pairs + // Shaper LUT (i.e. fixpoint == true) is still 256 bases and 256 deltas + hw_points = fixpoint ? (hw_points - 1) : hw_points; + j = 0; for (k = 0; k < (region_end - region_start); k++) { increment = NUMBER_SW_SEGMENTS / (1 << seg_distr[k]); @@ -223,8 +231,6 @@ bool cm3_helper_translate_curve_to_hw_format( corner_points[1].green.slope = dc_fixpt_zero; corner_points[1].blue.slope = dc_fixpt_zero; - // DCN3+ have 257 pts in lieu of no separate slope registers - // Prior HW had 256 base+slope pairs lut_params->hw_points_num = hw_points + 1; k = 0; @@ -248,6 +254,10 @@ bool cm3_helper_translate_curve_to_hw_format( if (fixpoint == true) { i = 1; while (i != hw_points + 2) { + uint32_t red_clamp; + uint32_t green_clamp; + uint32_t blue_clamp; + if (i >= hw_points) { if (dc_fixpt_lt(rgb_plus_1->red, rgb->red)) rgb_plus_1->red = dc_fixpt_add(rgb->red, @@ -260,9 +270,20 @@ bool cm3_helper_translate_curve_to_hw_format( rgb_minus_1->delta_blue); } - rgb->delta_red_reg = dc_fixpt_clamp_u0d10(rgb->delta_red); - rgb->delta_green_reg = dc_fixpt_clamp_u0d10(rgb->delta_green); - rgb->delta_blue_reg = dc_fixpt_clamp_u0d10(rgb->delta_blue); + rgb->delta_red = dc_fixpt_sub(rgb_plus_1->red, rgb->red); + rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green); + rgb->delta_blue = dc_fixpt_sub(rgb_plus_1->blue, rgb->blue); + + red_clamp = dc_fixpt_clamp_u0d14(rgb->delta_red); + green_clamp = dc_fixpt_clamp_u0d14(rgb->delta_green); + blue_clamp = dc_fixpt_clamp_u0d14(rgb->delta_blue); + + if (red_clamp >> 10 || green_clamp >> 10 || blue_clamp >> 10) + DC_LOG_ERROR("Losing delta precision while programming shaper LUT."); + + rgb->delta_red_reg = red_clamp & 0x3ff; + rgb->delta_green_reg = green_clamp & 0x3ff; + rgb->delta_blue_reg = blue_clamp & 0x3ff; rgb->red_reg = dc_fixpt_clamp_u0d14(rgb->red); rgb->green_reg = dc_fixpt_clamp_u0d14(rgb->green); rgb->blue_reg = dc_fixpt_clamp_u0d14(rgb->blue); diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index b357683b4255af..268b5fbdb48bd5 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -30,7 +30,11 @@ dml_rcflags := $(CC_FLAGS_NO_FPU) ifneq ($(CONFIG_FRAME_WARN),0) ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) - frame_warn_limit := 3072 + ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_COMPILE_TEST),yy) + frame_warn_limit := 4096 + else + frame_warn_limit := 3072 + endif else frame_warn_limit := 2048 endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c index 8d24763938ea6d..2d19bb8de59c84 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c @@ -77,32 +77,14 @@ static unsigned int dscceComputeDelay( static unsigned int dscComputeDelay( enum output_format_class pixelFormat, enum output_encoder_class Output); -// Super monster function with some 45 argument static bool CalculatePrefetchSchedule( struct display_mode_lib *mode_lib, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + unsigned int k, Pipe *myPipe, unsigned int DSCDelay, - double DPPCLKDelaySubtotalPlusCNVCFormater, - double DPPCLKDelaySCL, - double DPPCLKDelaySCLLBOnly, - double DPPCLKDelayCNVCCursor, - double DISPCLKDelaySubtotal, unsigned int DPP_RECOUT_WIDTH, - enum output_format_class OutputFormat, - unsigned int MaxInterDCNTileRepeaters, unsigned int VStartup, unsigned int MaxVStartup, - unsigned int GPUVMPageTableLevels, - bool GPUVMEnable, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - double HostVMMinPageSize, - bool DynamicMetadataEnable, - bool DynamicMetadataVMEnabled, - int DynamicMetadataLinesBeforeActiveRequired, - unsigned int DynamicMetadataTransmittedBytes, double UrgentLatency, double UrgentExtraLatency, double TCalc, @@ -116,7 +98,6 @@ static bool CalculatePrefetchSchedule( unsigned int MaxNumSwathY, double PrefetchSourceLinesC, unsigned int SwathWidthC, - int BytePerPixelC, double VInitPreFillC, unsigned int MaxNumSwathC, long swath_width_luma_ub, @@ -124,9 +105,6 @@ static bool CalculatePrefetchSchedule( unsigned int SwathHeightY, unsigned int SwathHeightC, double TWait, - bool ProgressiveToInterlaceUnitInOPP, - double *DSTXAfterScaler, - double *DSTYAfterScaler, double *DestinationLinesForPrefetch, double *PrefetchBandwidth, double *DestinationLinesToRequestVMInVBlank, @@ -135,14 +113,7 @@ static bool CalculatePrefetchSchedule( double *VRatioPrefetchC, double *RequiredPrefetchPixDataBWLuma, double *RequiredPrefetchPixDataBWChroma, - bool *NotEnoughTimeForDynamicMetadata, - double *Tno_bw, - double *prefetch_vmrow_bw, - double *Tdmdl_vm, - double *Tdmdl, - unsigned int *VUpdateOffsetPix, - double *VUpdateWidthPix, - double *VReadyOffsetPix); + bool *NotEnoughTimeForDynamicMetadata); static double RoundToDFSGranularityUp(double Clock, double VCOSpeed); static double RoundToDFSGranularityDown(double Clock, double VCOSpeed); static void CalculateDCCConfiguration( @@ -810,29 +781,12 @@ static unsigned int dscComputeDelay(enum output_format_class pixelFormat, enum o static bool CalculatePrefetchSchedule( struct display_mode_lib *mode_lib, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + unsigned int k, Pipe *myPipe, unsigned int DSCDelay, - double DPPCLKDelaySubtotalPlusCNVCFormater, - double DPPCLKDelaySCL, - double DPPCLKDelaySCLLBOnly, - double DPPCLKDelayCNVCCursor, - double DISPCLKDelaySubtotal, unsigned int DPP_RECOUT_WIDTH, - enum output_format_class OutputFormat, - unsigned int MaxInterDCNTileRepeaters, unsigned int VStartup, unsigned int MaxVStartup, - unsigned int GPUVMPageTableLevels, - bool GPUVMEnable, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - double HostVMMinPageSize, - bool DynamicMetadataEnable, - bool DynamicMetadataVMEnabled, - int DynamicMetadataLinesBeforeActiveRequired, - unsigned int DynamicMetadataTransmittedBytes, double UrgentLatency, double UrgentExtraLatency, double TCalc, @@ -846,7 +800,6 @@ static bool CalculatePrefetchSchedule( unsigned int MaxNumSwathY, double PrefetchSourceLinesC, unsigned int SwathWidthC, - int BytePerPixelC, double VInitPreFillC, unsigned int MaxNumSwathC, long swath_width_luma_ub, @@ -854,9 +807,6 @@ static bool CalculatePrefetchSchedule( unsigned int SwathHeightY, unsigned int SwathHeightC, double TWait, - bool ProgressiveToInterlaceUnitInOPP, - double *DSTXAfterScaler, - double *DSTYAfterScaler, double *DestinationLinesForPrefetch, double *PrefetchBandwidth, double *DestinationLinesToRequestVMInVBlank, @@ -865,15 +815,10 @@ static bool CalculatePrefetchSchedule( double *VRatioPrefetchC, double *RequiredPrefetchPixDataBWLuma, double *RequiredPrefetchPixDataBWChroma, - bool *NotEnoughTimeForDynamicMetadata, - double *Tno_bw, - double *prefetch_vmrow_bw, - double *Tdmdl_vm, - double *Tdmdl, - unsigned int *VUpdateOffsetPix, - double *VUpdateWidthPix, - double *VReadyOffsetPix) + bool *NotEnoughTimeForDynamicMetadata) { + struct vba_vars_st *v = &mode_lib->vba; + double DPPCLKDelaySubtotalPlusCNVCFormater = v->DPPCLKDelaySubtotal + v->DPPCLKDelayCNVCFormater; bool MyError = false; unsigned int DPPCycles = 0, DISPCLKCycles = 0; double DSTTotalPixelsAfterScaler = 0; @@ -905,26 +850,26 @@ static bool CalculatePrefetchSchedule( double Tdmec = 0; double Tdmsks = 0; - if (GPUVMEnable == true && HostVMEnable == true) { - HostVMInefficiencyFactor = PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData / PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly; - HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels; + if (v->GPUVMEnable == true && v->HostVMEnable == true) { + HostVMInefficiencyFactor = v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData / v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly; + HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels; } else { HostVMInefficiencyFactor = 1; HostVMDynamicLevelsTrips = 0; } CalculateDynamicMetadataParameters( - MaxInterDCNTileRepeaters, + v->MaxInterDCNTileRepeaters, myPipe->DPPCLK, myPipe->DISPCLK, myPipe->DCFCLKDeepSleep, myPipe->PixelClock, myPipe->HTotal, myPipe->VBlank, - DynamicMetadataTransmittedBytes, - DynamicMetadataLinesBeforeActiveRequired, + v->DynamicMetadataTransmittedBytes[k], + v->DynamicMetadataLinesBeforeActiveRequired[k], myPipe->InterlaceEnable, - ProgressiveToInterlaceUnitInOPP, + v->ProgressiveToInterlaceUnitInOPP, &Tsetup, &Tdmbf, &Tdmec, @@ -932,16 +877,16 @@ static bool CalculatePrefetchSchedule( LineTime = myPipe->HTotal / myPipe->PixelClock; trip_to_mem = UrgentLatency; - Tvm_trips = UrgentExtraLatency + trip_to_mem * (GPUVMPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1); + Tvm_trips = UrgentExtraLatency + trip_to_mem * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1); - if (DynamicMetadataVMEnabled == true && GPUVMEnable == true) { - *Tdmdl = TWait + Tvm_trips + trip_to_mem; + if (v->DynamicMetadataVMEnabled == true && v->GPUVMEnable == true) { + v->Tdmdl[k] = TWait + Tvm_trips + trip_to_mem; } else { - *Tdmdl = TWait + UrgentExtraLatency; + v->Tdmdl[k] = TWait + UrgentExtraLatency; } - if (DynamicMetadataEnable == true) { - if (VStartup * LineTime < Tsetup + *Tdmdl + Tdmbf + Tdmec + Tdmsks) { + if (v->DynamicMetadataEnable[k] == true) { + if (VStartup * LineTime < Tsetup + v->Tdmdl[k] + Tdmbf + Tdmec + Tdmsks) { *NotEnoughTimeForDynamicMetadata = true; } else { *NotEnoughTimeForDynamicMetadata = false; @@ -949,39 +894,39 @@ static bool CalculatePrefetchSchedule( dml_print("DML: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n", Tdmbf); dml_print("DML: Tdmec: %fus - time dio takes to transfer dmd\n", Tdmec); dml_print("DML: Tdmsks: %fus - time before active dmd must complete transmission at dio\n", Tdmsks); - dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", *Tdmdl); + dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", v->Tdmdl[k]); } } else { *NotEnoughTimeForDynamicMetadata = false; } - *Tdmdl_vm = (DynamicMetadataEnable == true && DynamicMetadataVMEnabled == true && GPUVMEnable == true ? TWait + Tvm_trips : 0); + v->Tdmdl_vm[k] = (v->DynamicMetadataEnable[k] == true && v->DynamicMetadataVMEnabled == true && v->GPUVMEnable == true ? TWait + Tvm_trips : 0); if (myPipe->ScalerEnabled) - DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCL; + DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCL; else - DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCLLBOnly; + DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCLLBOnly; - DPPCycles = DPPCycles + myPipe->NumberOfCursors * DPPCLKDelayCNVCCursor; + DPPCycles = DPPCycles + myPipe->NumberOfCursors * v->DPPCLKDelayCNVCCursor; - DISPCLKCycles = DISPCLKDelaySubtotal; + DISPCLKCycles = v->DISPCLKDelaySubtotal; if (myPipe->DPPCLK == 0.0 || myPipe->DISPCLK == 0.0) return true; - *DSTXAfterScaler = DPPCycles * myPipe->PixelClock / myPipe->DPPCLK + DISPCLKCycles * myPipe->PixelClock / myPipe->DISPCLK + v->DSTXAfterScaler[k] = DPPCycles * myPipe->PixelClock / myPipe->DPPCLK + DISPCLKCycles * myPipe->PixelClock / myPipe->DISPCLK + DSCDelay; - *DSTXAfterScaler = *DSTXAfterScaler + ((myPipe->ODMCombineEnabled)?18:0) + (myPipe->DPPPerPlane - 1) * DPP_RECOUT_WIDTH; + v->DSTXAfterScaler[k] = v->DSTXAfterScaler[k] + ((myPipe->ODMCombineEnabled)?18:0) + (myPipe->DPPPerPlane - 1) * DPP_RECOUT_WIDTH; - if (OutputFormat == dm_420 || (myPipe->InterlaceEnable && ProgressiveToInterlaceUnitInOPP)) - *DSTYAfterScaler = 1; + if (v->OutputFormat[k] == dm_420 || (myPipe->InterlaceEnable && v->ProgressiveToInterlaceUnitInOPP)) + v->DSTYAfterScaler[k] = 1; else - *DSTYAfterScaler = 0; + v->DSTYAfterScaler[k] = 0; - DSTTotalPixelsAfterScaler = *DSTYAfterScaler * myPipe->HTotal + *DSTXAfterScaler; - *DSTYAfterScaler = dml_floor(DSTTotalPixelsAfterScaler / myPipe->HTotal, 1); - *DSTXAfterScaler = DSTTotalPixelsAfterScaler - ((double) (*DSTYAfterScaler * myPipe->HTotal)); + DSTTotalPixelsAfterScaler = v->DSTYAfterScaler[k] * myPipe->HTotal + v->DSTXAfterScaler[k]; + v->DSTYAfterScaler[k] = dml_floor(DSTTotalPixelsAfterScaler / myPipe->HTotal, 1); + v->DSTXAfterScaler[k] = DSTTotalPixelsAfterScaler - ((double) (v->DSTYAfterScaler[k] * myPipe->HTotal)); MyError = false; @@ -990,33 +935,33 @@ static bool CalculatePrefetchSchedule( Tvm_trips_rounded = dml_ceil(4.0 * Tvm_trips / LineTime, 1) / 4 * LineTime; Tr0_trips_rounded = dml_ceil(4.0 * Tr0_trips / LineTime, 1) / 4 * LineTime; - if (GPUVMEnable) { - if (GPUVMPageTableLevels >= 3) { - *Tno_bw = UrgentExtraLatency + trip_to_mem * ((GPUVMPageTableLevels - 2) - 1); + if (v->GPUVMEnable) { + if (v->GPUVMMaxPageTableLevels >= 3) { + v->Tno_bw[k] = UrgentExtraLatency + trip_to_mem * ((v->GPUVMMaxPageTableLevels - 2) - 1); } else - *Tno_bw = 0; + v->Tno_bw[k] = 0; } else if (!myPipe->DCCEnable) - *Tno_bw = LineTime; + v->Tno_bw[k] = LineTime; else - *Tno_bw = LineTime / 4; + v->Tno_bw[k] = LineTime / 4; - dst_y_prefetch_equ = VStartup - (Tsetup + dml_max(TWait + TCalc, *Tdmdl)) / LineTime - - (*DSTYAfterScaler + *DSTXAfterScaler / myPipe->HTotal); + dst_y_prefetch_equ = VStartup - (Tsetup + dml_max(TWait + TCalc, v->Tdmdl[k])) / LineTime + - (v->DSTYAfterScaler[k] + v->DSTXAfterScaler[k] / myPipe->HTotal); dst_y_prefetch_equ = dml_min(dst_y_prefetch_equ, 63.75); // limit to the reg limit of U6.2 for DST_Y_PREFETCH Lsw_oto = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC); Tsw_oto = Lsw_oto * LineTime; - prefetch_bw_oto = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * BytePerPixelC) / Tsw_oto; + prefetch_bw_oto = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * v->BytePerPixelC[k]) / Tsw_oto; - if (GPUVMEnable == true) { - Tvm_oto = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_oto, + if (v->GPUVMEnable == true) { + Tvm_oto = dml_max3(v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_oto, Tvm_trips, LineTime / 4.0); } else Tvm_oto = LineTime / 4.0; - if ((GPUVMEnable == true || myPipe->DCCEnable == true)) { + if ((v->GPUVMEnable == true || myPipe->DCCEnable == true)) { Tr0_oto = dml_max3( (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_oto, LineTime - Tvm_oto, LineTime / 4); @@ -1042,10 +987,10 @@ static bool CalculatePrefetchSchedule( dml_print("DML: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n", Tdmbf); dml_print("DML: Tdmec: %fus - time dio takes to transfer dmd\n", Tdmec); dml_print("DML: Tdmsks: %fus - time before active dmd must complete transmission at dio\n", Tdmsks); - dml_print("DML: Tdmdl_vm: %fus - time for vm stages of dmd \n", *Tdmdl_vm); - dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", *Tdmdl); - dml_print("DML: dst_x_after_scl: %f pixels - number of pixel clocks pipeline and buffer delay after scaler \n", *DSTXAfterScaler); - dml_print("DML: dst_y_after_scl: %d lines - number of lines of pipeline and buffer delay after scaler \n", (int)*DSTYAfterScaler); + dml_print("DML: Tdmdl_vm: %fus - time for vm stages of dmd \n", v->Tdmdl_vm[k]); + dml_print("DML: Tdmdl: %fus - time for fabric to become ready and fetch dmd \n", v->Tdmdl[k]); + dml_print("DML: dst_x_after_scl: %f pixels - number of pixel clocks pipeline and buffer delay after scaler \n", v->DSTXAfterScaler[k]); + dml_print("DML: dst_y_after_scl: %d lines - number of lines of pipeline and buffer delay after scaler \n", (int)v->DSTYAfterScaler[k]); *PrefetchBandwidth = 0; *DestinationLinesToRequestVMInVBlank = 0; @@ -1059,26 +1004,26 @@ static bool CalculatePrefetchSchedule( double PrefetchBandwidth3 = 0; double PrefetchBandwidth4 = 0; - if (Tpre_rounded - *Tno_bw > 0) + if (Tpre_rounded - v->Tno_bw[k] > 0) PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor + PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY - + PrefetchSourceLinesC * swath_width_chroma_ub * BytePerPixelC) - / (Tpre_rounded - *Tno_bw); + + PrefetchSourceLinesC * swath_width_chroma_ub * v->BytePerPixelC[k]) + / (Tpre_rounded - v->Tno_bw[k]); else PrefetchBandwidth1 = 0; - if (VStartup == MaxVStartup && (PrefetchBandwidth1 > 4 * prefetch_bw_oto) && (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - *Tno_bw) > 0) { - PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor) / (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - *Tno_bw); + if (VStartup == MaxVStartup && (PrefetchBandwidth1 > 4 * prefetch_bw_oto) && (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - v->Tno_bw[k]) > 0) { + PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor) / (Tpre_rounded - Tsw_oto / 4 - 0.75 * LineTime - v->Tno_bw[k]); } - if (Tpre_rounded - *Tno_bw - 2 * Tr0_trips_rounded > 0) + if (Tpre_rounded - v->Tno_bw[k] - 2 * Tr0_trips_rounded > 0) PrefetchBandwidth2 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * - BytePerPixelC) / - (Tpre_rounded - *Tno_bw - 2 * Tr0_trips_rounded); + v->BytePerPixelC[k]) / + (Tpre_rounded - v->Tno_bw[k] - 2 * Tr0_trips_rounded); else PrefetchBandwidth2 = 0; @@ -1086,7 +1031,7 @@ static bool CalculatePrefetchSchedule( PrefetchBandwidth3 = (2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor + PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * - swath_width_chroma_ub * BytePerPixelC) / (Tpre_rounded - + swath_width_chroma_ub * v->BytePerPixelC[k]) / (Tpre_rounded - Tvm_trips_rounded); else PrefetchBandwidth3 = 0; @@ -1096,7 +1041,7 @@ static bool CalculatePrefetchSchedule( } if (Tpre_rounded - Tvm_trips_rounded - 2 * Tr0_trips_rounded > 0) - PrefetchBandwidth4 = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * BytePerPixelC) + PrefetchBandwidth4 = (PrefetchSourceLinesY * swath_width_luma_ub * BytePerPixelY + PrefetchSourceLinesC * swath_width_chroma_ub * v->BytePerPixelC[k]) / (Tpre_rounded - Tvm_trips_rounded - 2 * Tr0_trips_rounded); else PrefetchBandwidth4 = 0; @@ -1107,7 +1052,7 @@ static bool CalculatePrefetchSchedule( bool Case3OK; if (PrefetchBandwidth1 > 0) { - if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth1 + if (v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth1 >= Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / PrefetchBandwidth1 >= Tr0_trips_rounded) { Case1OK = true; } else { @@ -1118,7 +1063,7 @@ static bool CalculatePrefetchSchedule( } if (PrefetchBandwidth2 > 0) { - if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth2 + if (v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth2 >= Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / PrefetchBandwidth2 < Tr0_trips_rounded) { Case2OK = true; } else { @@ -1129,7 +1074,7 @@ static bool CalculatePrefetchSchedule( } if (PrefetchBandwidth3 > 0) { - if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth3 + if (v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth3 < Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / PrefetchBandwidth3 >= Tr0_trips_rounded) { Case3OK = true; } else { @@ -1152,13 +1097,13 @@ static bool CalculatePrefetchSchedule( dml_print("DML: prefetch_bw_equ: %f\n", prefetch_bw_equ); if (prefetch_bw_equ > 0) { - if (GPUVMEnable) { - Tvm_equ = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_equ, Tvm_trips, LineTime / 4); + if (v->GPUVMEnable) { + Tvm_equ = dml_max3(v->Tno_bw[k] + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_equ, Tvm_trips, LineTime / 4); } else { Tvm_equ = LineTime / 4; } - if ((GPUVMEnable || myPipe->DCCEnable)) { + if ((v->GPUVMEnable || myPipe->DCCEnable)) { Tr0_equ = dml_max4( (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_equ, Tr0_trips, @@ -1227,7 +1172,7 @@ static bool CalculatePrefetchSchedule( } *RequiredPrefetchPixDataBWLuma = (double) PrefetchSourceLinesY / LinesToRequestPrefetchPixelData * BytePerPixelY * swath_width_luma_ub / LineTime; - *RequiredPrefetchPixDataBWChroma = (double) PrefetchSourceLinesC / LinesToRequestPrefetchPixelData * BytePerPixelC * swath_width_chroma_ub / LineTime; + *RequiredPrefetchPixDataBWChroma = (double) PrefetchSourceLinesC / LinesToRequestPrefetchPixelData * v->BytePerPixelC[k] * swath_width_chroma_ub / LineTime; } else { MyError = true; dml_print("DML: MyErr set %s:%d\n", __FILE__, __LINE__); @@ -1243,9 +1188,9 @@ static bool CalculatePrefetchSchedule( dml_print("DML: Tr0: %fus - time to fetch first row of data pagetables and first row of meta data (done in parallel)\n", TimeForFetchingRowInVBlank); dml_print("DML: Tr1: %fus - time to fetch second row of data pagetables and second row of meta data (done in parallel)\n", TimeForFetchingRowInVBlank); dml_print("DML: Tsw: %fus = time to fetch enough pixel data and cursor data to feed the scalers init position and detile\n", (double)LinesToRequestPrefetchPixelData * LineTime); - dml_print("DML: To: %fus - time for propagation from scaler to optc\n", (*DSTYAfterScaler + ((*DSTXAfterScaler) / (double) myPipe->HTotal)) * LineTime); + dml_print("DML: To: %fus - time for propagation from scaler to optc\n", (v->DSTYAfterScaler[k] + ((v->DSTXAfterScaler[k]) / (double) myPipe->HTotal)) * LineTime); dml_print("DML: Tvstartup - Tsetup - Tcalc - Twait - Tpre - To > 0\n"); - dml_print("DML: Tslack(pre): %fus - time left over in schedule\n", VStartup * LineTime - TimeForFetchingMetaPTE - 2 * TimeForFetchingRowInVBlank - (*DSTYAfterScaler + ((*DSTXAfterScaler) / (double) myPipe->HTotal)) * LineTime - TWait - TCalc - Tsetup); + dml_print("DML: Tslack(pre): %fus - time left over in schedule\n", VStartup * LineTime - TimeForFetchingMetaPTE - 2 * TimeForFetchingRowInVBlank - (v->DSTYAfterScaler[k] + ((v->DSTXAfterScaler[k]) / (double) myPipe->HTotal)) * LineTime - TWait - TCalc - Tsetup); dml_print("DML: row_bytes = dpte_row_bytes (per_pipe) = PixelPTEBytesPerRow = : %d\n", PixelPTEBytesPerRow); } else { @@ -1276,7 +1221,7 @@ static bool CalculatePrefetchSchedule( dml_print("DML: MyErr set %s:%d\n", __FILE__, __LINE__); } - *prefetch_vmrow_bw = dml_max(prefetch_vm_bw, prefetch_row_bw); + v->prefetch_vmrow_bw[k] = dml_max(prefetch_vm_bw, prefetch_row_bw); } if (MyError) { @@ -2437,30 +2382,12 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->ErrorResult[k] = CalculatePrefetchSchedule( mode_lib, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + k, &myPipe, v->DSCDelay[k], - v->DPPCLKDelaySubtotal - + v->DPPCLKDelayCNVCFormater, - v->DPPCLKDelaySCL, - v->DPPCLKDelaySCLLBOnly, - v->DPPCLKDelayCNVCCursor, - v->DISPCLKDelaySubtotal, (unsigned int) (v->SwathWidthY[k] / v->HRatio[k]), - v->OutputFormat[k], - v->MaxInterDCNTileRepeaters, dml_min(v->VStartupLines, v->MaxVStartupLines[k]), v->MaxVStartupLines[k], - v->GPUVMMaxPageTableLevels, - v->GPUVMEnable, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->HostVMMinPageSize, - v->DynamicMetadataEnable[k], - v->DynamicMetadataVMEnabled, - v->DynamicMetadataLinesBeforeActiveRequired[k], - v->DynamicMetadataTransmittedBytes[k], v->UrgentLatency, v->UrgentExtraLatency, v->TCalc, @@ -2474,7 +2401,6 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->MaxNumSwathY[k], v->PrefetchSourceLinesC[k], v->SwathWidthC[k], - v->BytePerPixelC[k], v->VInitPreFillC[k], v->MaxNumSwathC[k], v->swath_width_luma_ub[k], @@ -2482,9 +2408,6 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->SwathHeightY[k], v->SwathHeightC[k], TWait, - v->ProgressiveToInterlaceUnitInOPP, - &v->DSTXAfterScaler[k], - &v->DSTYAfterScaler[k], &v->DestinationLinesForPrefetch[k], &v->PrefetchBandwidth[k], &v->DestinationLinesToRequestVMInVBlank[k], @@ -2493,14 +2416,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman &v->VRatioPrefetchC[k], &v->RequiredPrefetchPixDataBWLuma[k], &v->RequiredPrefetchPixDataBWChroma[k], - &v->NotEnoughTimeForDynamicMetadata[k], - &v->Tno_bw[k], - &v->prefetch_vmrow_bw[k], - &v->Tdmdl_vm[k], - &v->Tdmdl[k], - &v->VUpdateOffsetPix[k], - &v->VUpdateWidthPix[k], - &v->VReadyOffsetPix[k]); + &v->NotEnoughTimeForDynamicMetadata[k]); if (v->BlendingAndTiming[k] == k) { double TotalRepeaterDelayTime = v->MaxInterDCNTileRepeaters * (2 / v->DPPCLK[k] + 3 / v->DISPCLK); v->VUpdateWidthPix[k] = (14 / v->DCFCLKDeepSleep + 12 / v->DPPCLK[k] + TotalRepeaterDelayTime) * v->PixelClock[k]; @@ -4770,29 +4686,12 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->NoTimeForPrefetch[i][j][k] = CalculatePrefetchSchedule( mode_lib, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData, - v->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly, + k, &myPipe, v->DSCDelayPerState[i][k], - v->DPPCLKDelaySubtotal + v->DPPCLKDelayCNVCFormater, - v->DPPCLKDelaySCL, - v->DPPCLKDelaySCLLBOnly, - v->DPPCLKDelayCNVCCursor, - v->DISPCLKDelaySubtotal, v->SwathWidthYThisState[k] / v->HRatio[k], - v->OutputFormat[k], - v->MaxInterDCNTileRepeaters, dml_min(v->MaxVStartup, v->MaximumVStartup[i][j][k]), v->MaximumVStartup[i][j][k], - v->GPUVMMaxPageTableLevels, - v->GPUVMEnable, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->HostVMMinPageSize, - v->DynamicMetadataEnable[k], - v->DynamicMetadataVMEnabled, - v->DynamicMetadataLinesBeforeActiveRequired[k], - v->DynamicMetadataTransmittedBytes[k], v->UrgLatency[i], v->ExtraLatency, v->TimeCalc, @@ -4806,7 +4705,6 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->MaxNumSwY[k], v->PrefetchLinesC[i][j][k], v->SwathWidthCThisState[k], - v->BytePerPixelC[k], v->PrefillC[k], v->MaxNumSwC[k], v->swath_width_luma_ub_this_state[k], @@ -4814,9 +4712,6 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->SwathHeightYThisState[k], v->SwathHeightCThisState[k], v->TWait, - v->ProgressiveToInterlaceUnitInOPP, - &v->DSTXAfterScaler[k], - &v->DSTYAfterScaler[k], &v->LineTimesForPrefetch[k], &v->PrefetchBW[k], &v->LinesForMetaPTE[k], @@ -4825,14 +4720,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l &v->VRatioPreC[i][j][k], &v->RequiredPrefetchPixelDataBWLuma[i][j][k], &v->RequiredPrefetchPixelDataBWChroma[i][j][k], - &v->NoTimeForDynamicMetadata[i][j][k], - &v->Tno_bw[k], - &v->prefetch_vmrow_bw[k], - &v->Tdmdl_vm[k], - &v->Tdmdl[k], - &v->VUpdateOffsetPix[k], - &v->VUpdateWidthPix[k], - &v->VReadyOffsetPix[k]); + &v->NoTimeForDynamicMetadata[i][j][k]); } for (k = 0; k <= v->NumberOfActivePlanes - 1; k++) { diff --git a/drivers/gpu/drm/amd/display/dc/dwb/dcn30/dcn30_cm_common.h b/drivers/gpu/drm/amd/display/dc/dwb/dcn30/dcn30_cm_common.h index b86347c9b0389d..95f9318a54efce 100644 --- a/drivers/gpu/drm/amd/display/dc/dwb/dcn30/dcn30_cm_common.h +++ b/drivers/gpu/drm/amd/display/dc/dwb/dcn30/dcn30_cm_common.h @@ -59,7 +59,7 @@ void cm_helper_program_gamcor_xfer_func( const struct pwl_params *params, const struct dcn3_xfer_func_reg *reg); -bool cm3_helper_translate_curve_to_hw_format( +bool cm3_helper_translate_curve_to_hw_format(struct dc_context *ctx, const struct dc_transfer_func *output_tf, struct pwl_params *lut_params, bool fixpoint); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index ebc220b29d1427..39be5a58f837a5 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -1098,13 +1098,13 @@ void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx) if (dc->current_state->res_ctx.pipe_ctx[i].stream_res.audio != NULL) num_audio++; } + if (num_audio >= 1 && clk_mgr->funcs->enable_pme_wa) { + /*wake AZ from D3 first before access az endpoint*/ + clk_mgr->funcs->enable_pme_wa(clk_mgr); + } pipe_ctx->stream_res.audio->funcs->az_enable(pipe_ctx->stream_res.audio); - if (num_audio >= 1 && clk_mgr->funcs->enable_pme_wa) - /*this is the first audio. apply the PME w/a in order to wake AZ from D3*/ - clk_mgr->funcs->enable_pme_wa(clk_mgr); - link_hwss->enable_audio_packet(pipe_ctx); if (pipe_ctx->stream_res.audio) @@ -1458,9 +1458,6 @@ void build_audio_output( state->clk_mgr); } - audio_output->pll_info.feed_back_divider = - pipe_ctx->pll_settings.feedback_divider; - audio_output->pll_info.dto_source = translate_to_dto_source( pipe_ctx->stream_res.tg->inst + 1); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c index e47ed5571dfdd8..731645a2ab9aa7 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c @@ -238,7 +238,7 @@ bool dcn30_set_blend_lut( if (plane_state->blend_tf.type == TF_TYPE_HWPWL) blend_lut = &plane_state->blend_tf.pwl; else if (plane_state->blend_tf.type == TF_TYPE_DISTRIBUTED_POINTS) { - result = cm3_helper_translate_curve_to_hw_format( + result = cm3_helper_translate_curve_to_hw_format(plane_state->ctx, &plane_state->blend_tf, &dpp_base->regamma_params, false); if (!result) return result; @@ -333,8 +333,9 @@ bool dcn30_set_input_transfer_func(struct dc *dc, if (plane_state->in_transfer_func.type == TF_TYPE_HWPWL) params = &plane_state->in_transfer_func.pwl; else if (plane_state->in_transfer_func.type == TF_TYPE_DISTRIBUTED_POINTS && - cm3_helper_translate_curve_to_hw_format(&plane_state->in_transfer_func, - &dpp_base->degamma_params, false)) + cm3_helper_translate_curve_to_hw_format(plane_state->ctx, + &plane_state->in_transfer_func, + &dpp_base->degamma_params, false)) params = &dpp_base->degamma_params; result = dpp_base->funcs->dpp_program_gamcor_lut(dpp_base, params); @@ -405,7 +406,7 @@ bool dcn30_set_output_transfer_func(struct dc *dc, params = &stream->out_transfer_func.pwl; else if (pipe_ctx->stream->out_transfer_func.type == TF_TYPE_DISTRIBUTED_POINTS && - cm3_helper_translate_curve_to_hw_format( + cm3_helper_translate_curve_to_hw_format(stream->ctx, &stream->out_transfer_func, &mpc->blender_params, false)) params = &mpc->blender_params; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c index f39292952702fa..c6fde355ac8235 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c @@ -486,8 +486,9 @@ bool dcn32_set_mcm_luts( if (plane_state->blend_tf.type == TF_TYPE_HWPWL) lut_params = &plane_state->blend_tf.pwl; else if (plane_state->blend_tf.type == TF_TYPE_DISTRIBUTED_POINTS) { - result = cm3_helper_translate_curve_to_hw_format(&plane_state->blend_tf, - &dpp_base->regamma_params, false); + result = cm3_helper_translate_curve_to_hw_format(plane_state->ctx, + &plane_state->blend_tf, + &dpp_base->regamma_params, false); if (!result) return result; @@ -501,9 +502,9 @@ bool dcn32_set_mcm_luts( lut_params = &plane_state->in_shaper_func.pwl; else if (plane_state->in_shaper_func.type == TF_TYPE_DISTRIBUTED_POINTS) { // TODO: dpp_base replace - ASSERT(false); - cm3_helper_translate_curve_to_hw_format(&plane_state->in_shaper_func, - &dpp_base->shaper_params, true); + cm3_helper_translate_curve_to_hw_format(plane_state->ctx, + &plane_state->in_shaper_func, + &dpp_base->shaper_params, true); lut_params = &dpp_base->shaper_params; } @@ -543,8 +544,9 @@ bool dcn32_set_input_transfer_func(struct dc *dc, if (plane_state->in_transfer_func.type == TF_TYPE_HWPWL) params = &plane_state->in_transfer_func.pwl; else if (plane_state->in_transfer_func.type == TF_TYPE_DISTRIBUTED_POINTS && - cm3_helper_translate_curve_to_hw_format(&plane_state->in_transfer_func, - &dpp_base->degamma_params, false)) + cm3_helper_translate_curve_to_hw_format(plane_state->ctx, + &plane_state->in_transfer_func, + &dpp_base->degamma_params, false)) params = &dpp_base->degamma_params; dpp_base->funcs->dpp_program_gamcor_lut(dpp_base, params); @@ -575,7 +577,7 @@ bool dcn32_set_output_transfer_func(struct dc *dc, params = &stream->out_transfer_func.pwl; else if (pipe_ctx->stream->out_transfer_func.type == TF_TYPE_DISTRIBUTED_POINTS && - cm3_helper_translate_curve_to_hw_format( + cm3_helper_translate_curve_to_hw_format(stream->ctx, &stream->out_transfer_func, &mpc->blender_params, false)) params = &mpc->blender_params; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c index 68e48a2492c9ee..77cdd02a41bdd0 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c @@ -427,7 +427,7 @@ void dcn401_populate_mcm_luts(struct dc *dc, if (mcm_luts.lut1d_func->type == TF_TYPE_HWPWL) m_lut_params.pwl = &mcm_luts.lut1d_func->pwl; else if (mcm_luts.lut1d_func->type == TF_TYPE_DISTRIBUTED_POINTS) { - rval = cm3_helper_translate_curve_to_hw_format( + rval = cm3_helper_translate_curve_to_hw_format(mpc->ctx, mcm_luts.lut1d_func, &dpp_base->regamma_params, false); m_lut_params.pwl = rval ? &dpp_base->regamma_params : NULL; @@ -447,7 +447,7 @@ void dcn401_populate_mcm_luts(struct dc *dc, m_lut_params.pwl = &mcm_luts.shaper->pwl; else if (mcm_luts.shaper->type == TF_TYPE_DISTRIBUTED_POINTS) { ASSERT(false); - rval = cm3_helper_translate_curve_to_hw_format( + rval = cm3_helper_translate_curve_to_hw_format(mpc->ctx, mcm_luts.shaper, &dpp_base->regamma_params, true); m_lut_params.pwl = rval ? &dpp_base->regamma_params : NULL; @@ -624,8 +624,9 @@ bool dcn401_set_mcm_luts(struct pipe_ctx *pipe_ctx, if (plane_state->blend_tf.type == TF_TYPE_HWPWL) lut_params = &plane_state->blend_tf.pwl; else if (plane_state->blend_tf.type == TF_TYPE_DISTRIBUTED_POINTS) { - rval = cm3_helper_translate_curve_to_hw_format(&plane_state->blend_tf, - &dpp_base->regamma_params, false); + rval = cm3_helper_translate_curve_to_hw_format(plane_state->ctx, + &plane_state->blend_tf, + &dpp_base->regamma_params, false); lut_params = rval ? &dpp_base->regamma_params : NULL; } result = mpc->funcs->program_1dlut(mpc, lut_params, mpcc_id); @@ -636,8 +637,9 @@ bool dcn401_set_mcm_luts(struct pipe_ctx *pipe_ctx, lut_params = &plane_state->in_shaper_func.pwl; else if (plane_state->in_shaper_func.type == TF_TYPE_DISTRIBUTED_POINTS) { // TODO: dpp_base replace - rval = cm3_helper_translate_curve_to_hw_format(&plane_state->in_shaper_func, - &dpp_base->shaper_params, true); + rval = cm3_helper_translate_curve_to_hw_format(plane_state->ctx, + &plane_state->in_shaper_func, + &dpp_base->shaper_params, true); lut_params = rval ? &dpp_base->shaper_params : NULL; } result &= mpc->funcs->program_shaper(mpc, lut_params, mpcc_id); @@ -671,7 +673,7 @@ bool dcn401_set_output_transfer_func(struct dc *dc, params = &stream->out_transfer_func.pwl; else if (pipe_ctx->stream->out_transfer_func.type == TF_TYPE_DISTRIBUTED_POINTS && - cm3_helper_translate_curve_to_hw_format( + cm3_helper_translate_curve_to_hw_format(stream->ctx, &stream->out_transfer_func, &mpc->blender_params, false)) params = &mpc->blender_params; diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index 1173c53359b009..31b404e9b9ae07 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -332,7 +332,7 @@ static void query_dp_dual_mode_adaptor( /* Assume we have no valid DP passive dongle connected */ *dongle = DISPLAY_DONGLE_NONE; - sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK; + sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK; /* Read DP-HDMI dongle I2c (no response interpreted as DP-DVI dongle)*/ if (!i2c_read( @@ -388,6 +388,8 @@ static void query_dp_dual_mode_adaptor( } } + if (is_valid_hdmi_signature) + sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK; if (is_type2_dongle) { uint32_t max_tmds_clk = diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c index 82cc78c291d824..12c2a0d9fb2a34 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c @@ -1226,12 +1226,12 @@ static struct stream_encoder *dcn315_stream_encoder_create( /*PHYB is wired off in HW, allow front end to remapping, otherwise needs more changes*/ /* Mapping of VPG, AFMT, DME register blocks to DIO block instance */ - if (eng_id <= ENGINE_ID_DIGF) { - vpg_inst = eng_id; - afmt_inst = eng_id; - } else + if (eng_id < 0 || eng_id >= ARRAY_SIZE(stream_enc_regs)) return NULL; + vpg_inst = eng_id; + afmt_inst = eng_id; + enc1 = kzalloc(sizeof(struct dcn10_stream_encoder), GFP_KERNEL); vpg = dcn31_vpg_create(ctx, vpg_inst); afmt = dcn31_afmt_create(ctx, afmt_inst); diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c index 636110e48d01b6..3c77c14c5a5ed0 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c @@ -1220,12 +1220,12 @@ static struct stream_encoder *dcn316_stream_encoder_create( int afmt_inst; /* Mapping of VPG, AFMT, DME register blocks to DIO block instance */ - if (eng_id <= ENGINE_ID_DIGF) { - vpg_inst = eng_id; - afmt_inst = eng_id; - } else + if (eng_id < 0 || eng_id >= ARRAY_SIZE(stream_enc_regs)) return NULL; + vpg_inst = eng_id; + afmt_inst = eng_id; + enc1 = kzalloc(sizeof(struct dcn10_stream_encoder), GFP_KERNEL); vpg = dcn31_vpg_create(ctx, vpg_inst); afmt = dcn31_afmt_create(ctx, afmt_inst); diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c index 3965a7f1b64b7d..9cace432ce3642 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c @@ -1208,12 +1208,12 @@ static struct stream_encoder *dcn32_stream_encoder_create( int afmt_inst; /* Mapping of VPG, AFMT, DME register blocks to DIO block instance */ - if (eng_id <= ENGINE_ID_DIGF) { - vpg_inst = eng_id; - afmt_inst = eng_id; - } else + if (eng_id < 0 || eng_id >= ARRAY_SIZE(stream_enc_regs)) return NULL; + vpg_inst = eng_id; + afmt_inst = eng_id; + enc1 = kzalloc(sizeof(struct dcn10_stream_encoder), GFP_KERNEL); vpg = dcn32_vpg_create(ctx, vpg_inst); afmt = dcn32_afmt_create(ctx, afmt_inst); diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c index ad214986f7ac71..26fd5c03c01475 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c @@ -1189,12 +1189,12 @@ static struct stream_encoder *dcn321_stream_encoder_create( int afmt_inst; /* Mapping of VPG, AFMT, DME register blocks to DIO block instance */ - if (eng_id <= ENGINE_ID_DIGF) { - vpg_inst = eng_id; - afmt_inst = eng_id; - } else + if (eng_id < 0 || eng_id >= ARRAY_SIZE(stream_enc_regs)) return NULL; + vpg_inst = eng_id; + afmt_inst = eng_id; + enc1 = kzalloc(sizeof(struct dcn10_stream_encoder), GFP_KERNEL); vpg = dcn321_vpg_create(ctx, vpg_inst); afmt = dcn321_afmt_create(ctx, afmt_inst); diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c index fff57f23f4f7ab..e8d74ceb9dc290 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c @@ -203,12 +203,12 @@ enum dcn35_clk_src_array_id { NBIO_BASE_INNER(seg) #define NBIO_SR(reg_name)\ - REG_STRUCT.reg_name = NBIO_BASE(regBIF_BX2_ ## reg_name ## _BASE_IDX) + \ - regBIF_BX2_ ## reg_name + REG_STRUCT.reg_name = NBIO_BASE(regBIF_BX1_ ## reg_name ## _BASE_IDX) + \ + regBIF_BX1_ ## reg_name #define NBIO_SR_ARR(reg_name, id)\ - REG_STRUCT[id].reg_name = NBIO_BASE(regBIF_BX2_ ## reg_name ## _BASE_IDX) + \ - regBIF_BX2_ ## reg_name + REG_STRUCT[id].reg_name = NBIO_BASE(regBIF_BX1_ ## reg_name ## _BASE_IDX) + \ + regBIF_BX1_ ## reg_name #define bios_regs_init() \ ( \ @@ -1271,12 +1271,12 @@ static struct stream_encoder *dcn35_stream_encoder_create( int afmt_inst; /* Mapping of VPG, AFMT, DME register blocks to DIO block instance */ - if (eng_id <= ENGINE_ID_DIGF) { - vpg_inst = eng_id; - afmt_inst = eng_id; - } else + if (eng_id < 0 || eng_id >= ARRAY_SIZE(stream_enc_regs)) return NULL; + vpg_inst = eng_id; + afmt_inst = eng_id; + enc1 = kzalloc(sizeof(struct dcn10_stream_encoder), GFP_KERNEL); vpg = dcn31_vpg_create(ctx, vpg_inst); afmt = dcn31_afmt_create(ctx, afmt_inst); diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c index 0abd163b425e53..532e5d9bc43378 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c @@ -183,12 +183,12 @@ enum dcn351_clk_src_array_id { NBIO_BASE_INNER(seg) #define NBIO_SR(reg_name)\ - REG_STRUCT.reg_name = NBIO_BASE(regBIF_BX2_ ## reg_name ## _BASE_IDX) + \ - regBIF_BX2_ ## reg_name + REG_STRUCT.reg_name = NBIO_BASE(regBIF_BX1_ ## reg_name ## _BASE_IDX) + \ + regBIF_BX1_ ## reg_name #define NBIO_SR_ARR(reg_name, id)\ - REG_STRUCT[id].reg_name = NBIO_BASE(regBIF_BX2_ ## reg_name ## _BASE_IDX) + \ - regBIF_BX2_ ## reg_name + REG_STRUCT[id].reg_name = NBIO_BASE(regBIF_BX1_ ## reg_name ## _BASE_IDX) + \ + regBIF_BX1_ ## reg_name #define bios_regs_init() \ ( \ @@ -1251,12 +1251,12 @@ static struct stream_encoder *dcn35_stream_encoder_create( int afmt_inst; /* Mapping of VPG, AFMT, DME register blocks to DIO block instance */ - if (eng_id <= ENGINE_ID_DIGF) { - vpg_inst = eng_id; - afmt_inst = eng_id; - } else + if (eng_id < 0 || eng_id >= ARRAY_SIZE(stream_enc_regs)) return NULL; + vpg_inst = eng_id; + afmt_inst = eng_id; + enc1 = kzalloc(sizeof(struct dcn10_stream_encoder), GFP_KERNEL); vpg = dcn31_vpg_create(ctx, vpg_inst); afmt = dcn31_afmt_create(ctx, afmt_inst); diff --git a/drivers/gpu/drm/amd/display/include/audio_types.h b/drivers/gpu/drm/amd/display/include/audio_types.h index e4a26143f14c94..6699ad4fa825e3 100644 --- a/drivers/gpu/drm/amd/display/include/audio_types.h +++ b/drivers/gpu/drm/amd/display/include/audio_types.h @@ -47,15 +47,15 @@ struct audio_crtc_info { uint32_t h_total; uint32_t h_active; uint32_t v_active; - uint32_t pixel_repetition; uint32_t requested_pixel_clock_100Hz; /* in 100Hz */ uint32_t calculated_pixel_clock_100Hz; /* in 100Hz */ - uint32_t refresh_rate; + uint32_t dsc_bits_per_pixel; + uint32_t dsc_num_slices; enum dc_color_depth color_depth; enum dc_pixel_encoding pixel_encoding; + uint16_t refresh_rate; + uint8_t pixel_repetition; bool interlaced; - uint32_t dsc_bits_per_pixel; - uint32_t dsc_num_slices; }; struct azalia_clock_info { uint32_t pixel_clock_in_10khz; @@ -78,11 +78,9 @@ enum audio_dto_source { struct audio_pll_info { uint32_t audio_dto_source_clock_in_khz; - uint32_t feed_back_divider; + uint32_t ss_percentage; enum audio_dto_source dto_source; bool ss_enabled; - uint32_t ss_percentage; - uint32_t ss_percentage_divider; }; struct audio_channel_associate_info { diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index bc29a923fa6e53..8253d2977408db 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -80,15 +80,15 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, enum ip_power_state pwr_state = gate ? POWER_STATE_OFF : POWER_STATE_ON; bool is_vcn = block_type == AMD_IP_BLOCK_TYPE_VCN; + mutex_lock(&adev->pm.mutex); + if (atomic_read(&adev->pm.pwr_state[block_type]) == pwr_state && (!is_vcn || adev->vcn.num_vcn_inst == 1)) { dev_dbg(adev->dev, "IP block%d already in the target %s state!", block_type, gate ? "gate" : "ungate"); - return 0; + goto out_unlock; } - mutex_lock(&adev->pm.mutex); - switch (block_type) { case AMD_IP_BLOCK_TYPE_UVD: case AMD_IP_BLOCK_TYPE_VCE: @@ -115,6 +115,7 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, if (!ret) atomic_set(&adev->pm.pwr_state[block_type], pwr_state); +out_unlock: mutex_unlock(&adev->pm.mutex); return ret; diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index 3a9522c17fee30..a1da3e5812ce3c 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -2273,8 +2273,6 @@ static int si_populate_smc_tdp_limits(struct amdgpu_device *adev, if (scaling_factor == 0) return -EINVAL; - memset(smc_table, 0, sizeof(SISLANDS_SMC_STATETABLE)); - ret = si_calculate_adjusted_tdp_limits(adev, false, /* ??? */ adev->pm.dpm.tdp_adjustment, @@ -2283,6 +2281,12 @@ static int si_populate_smc_tdp_limits(struct amdgpu_device *adev, if (ret) return ret; + if (adev->pdev->device == 0x6611 && adev->pdev->revision == 0x87) { + /* Workaround buggy powertune on Radeon 430 and 520. */ + tdp_limit = 32; + near_tdp_limit = 28; + } + smc_table->dpm2Params.TDPLimit = cpu_to_be32(si_scale_power_for_smc(tdp_limit, scaling_factor) * 1000); smc_table->dpm2Params.NearTDPLimit = @@ -2328,16 +2332,8 @@ static int si_populate_smc_tdp_limits_2(struct amdgpu_device *adev, if (ni_pi->enable_power_containment) { SISLANDS_SMC_STATETABLE *smc_table = &si_pi->smc_statetable; - u32 scaling_factor = si_get_smc_power_scaling_factor(adev); int ret; - memset(smc_table, 0, sizeof(SISLANDS_SMC_STATETABLE)); - - smc_table->dpm2Params.NearTDPLimit = - cpu_to_be32(si_scale_power_for_smc(adev->pm.dpm.near_tdp_limit_adjusted, scaling_factor) * 1000); - smc_table->dpm2Params.SafePowerLimit = - cpu_to_be32(si_scale_power_for_smc((adev->pm.dpm.near_tdp_limit_adjusted * SISLANDS_DPM2_TDP_SAFE_LIMIT_PERCENT) / 100, scaling_factor) * 1000); - ret = amdgpu_si_copy_bytes_to_smc(adev, (si_pi->state_table_start + offsetof(SISLANDS_SMC_STATETABLE, dpm2Params) + @@ -3478,10 +3474,15 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev, (adev->pdev->revision == 0x80) || (adev->pdev->revision == 0x81) || (adev->pdev->revision == 0x83) || - (adev->pdev->revision == 0x87) || + (adev->pdev->revision == 0x87 && + adev->pdev->device != 0x6611) || (adev->pdev->device == 0x6604) || (adev->pdev->device == 0x6605)) { max_sclk = 75000; + } else if (adev->pdev->revision == 0x87 && + adev->pdev->device == 0x6611) { + /* Radeon 430 and 520 */ + max_sclk = 78000; } } @@ -7600,12 +7601,12 @@ static int si_dpm_set_interrupt_state(struct amdgpu_device *adev, case AMDGPU_IRQ_STATE_DISABLE: cg_thermal_int = RREG32_SMC(mmCG_THERMAL_INT); cg_thermal_int |= CG_THERMAL_INT__THERM_INT_MASK_HIGH_MASK; - WREG32_SMC(mmCG_THERMAL_INT, cg_thermal_int); + WREG32(mmCG_THERMAL_INT, cg_thermal_int); break; case AMDGPU_IRQ_STATE_ENABLE: cg_thermal_int = RREG32_SMC(mmCG_THERMAL_INT); cg_thermal_int &= ~CG_THERMAL_INT__THERM_INT_MASK_HIGH_MASK; - WREG32_SMC(mmCG_THERMAL_INT, cg_thermal_int); + WREG32(mmCG_THERMAL_INT, cg_thermal_int); break; default: break; @@ -7617,12 +7618,12 @@ static int si_dpm_set_interrupt_state(struct amdgpu_device *adev, case AMDGPU_IRQ_STATE_DISABLE: cg_thermal_int = RREG32_SMC(mmCG_THERMAL_INT); cg_thermal_int |= CG_THERMAL_INT__THERM_INT_MASK_LOW_MASK; - WREG32_SMC(mmCG_THERMAL_INT, cg_thermal_int); + WREG32(mmCG_THERMAL_INT, cg_thermal_int); break; case AMDGPU_IRQ_STATE_ENABLE: cg_thermal_int = RREG32_SMC(mmCG_THERMAL_INT); cg_thermal_int &= ~CG_THERMAL_INT__THERM_INT_MASK_LOW_MASK; - WREG32_SMC(mmCG_THERMAL_INT, cg_thermal_int); + WREG32(mmCG_THERMAL_INT, cg_thermal_int); break; default: break; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index 4263798d716b76..8e592a477c33a1 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -56,6 +56,7 @@ #define SMUQ10_TO_UINT(x) ((x) >> 10) #define SMUQ10_FRAC(x) ((x) & 0x3ff) #define SMUQ10_ROUND(x) ((SMUQ10_TO_UINT(x)) + ((SMUQ10_FRAC(x)) >= 0x200)) +#define SMU_V13_SOFT_FREQ_ROUND(x) ((x) + 1) extern const int pmfw_decoded_link_speed[5]; extern const int pmfw_decoded_link_width[7]; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h index 29a4583db8734b..0b1e6f25e61129 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h @@ -57,6 +57,7 @@ extern const int decoded_link_width[8]; #define DECODE_GEN_SPEED(gen_speed_idx) (decoded_link_speed[gen_speed_idx]) #define DECODE_LANE_WIDTH(lane_width_idx) (decoded_link_width[lane_width_idx]) +#define SMU_V14_SOFT_FREQ_ROUND(x) ((x) + 1) struct smu_14_0_max_sustainable_clocks { uint32_t display_clock; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 0028f10ead4237..a2fcf678182b4e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -2454,24 +2454,21 @@ static int navi10_update_pcie_parameters(struct smu_context *smu, } for (i = 0; i < NUM_LINK_LEVELS; i++) { - if (pptable->PcieGenSpeed[i] > pcie_gen_cap || - pptable->PcieLaneCount[i] > pcie_width_cap) { - dpm_context->dpm_tables.pcie_table.pcie_gen[i] = - pptable->PcieGenSpeed[i] > pcie_gen_cap ? - pcie_gen_cap : pptable->PcieGenSpeed[i]; - dpm_context->dpm_tables.pcie_table.pcie_lane[i] = - pptable->PcieLaneCount[i] > pcie_width_cap ? - pcie_width_cap : pptable->PcieLaneCount[i]; - smu_pcie_arg = i << 16; - smu_pcie_arg |= pcie_gen_cap << 8; - smu_pcie_arg |= pcie_width_cap; - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_OverridePcieParameters, - smu_pcie_arg, - NULL); - if (ret) - break; - } + dpm_context->dpm_tables.pcie_table.pcie_gen[i] = + pptable->PcieGenSpeed[i] > pcie_gen_cap ? + pcie_gen_cap : pptable->PcieGenSpeed[i]; + dpm_context->dpm_tables.pcie_table.pcie_lane[i] = + pptable->PcieLaneCount[i] > pcie_width_cap ? + pcie_width_cap : pptable->PcieLaneCount[i]; + smu_pcie_arg = i << 16; + smu_pcie_arg |= dpm_context->dpm_tables.pcie_table.pcie_gen[i] << 8; + smu_pcie_arg |= dpm_context->dpm_tables.pcie_table.pcie_lane[i]; + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_OverridePcieParameters, + smu_pcie_arg, + NULL); + if (ret) + return ret; } return ret; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index a89075e257174a..2efd914d81e5b8 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -1555,6 +1555,7 @@ int smu_v13_0_set_soft_freq_limited_range(struct smu_context *smu, return clk_id; if (max > 0) { + max = SMU_V13_SOFT_FREQ_ROUND(max); if (automatic) param = (uint32_t)((clk_id << 16) | 0xffff); else diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index c1062e5f039367..8d070a9ea2c101 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2922,8 +2922,13 @@ static int smu_v13_0_0_mode1_reset(struct smu_context *smu) break; } - if (!ret) + if (!ret) { + /* disable mmio access while doing mode 1 reset*/ + smu->adev->no_hw_access = true; + /* ensure no_hw_access is globally visible before any MMIO */ + smp_mb(); msleep(SMU13_MODE1_RESET_WAIT_TIME_IN_MS); + } return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c index f9b0938c57ea71..e042f40c987f2c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c @@ -1178,6 +1178,7 @@ int smu_v14_0_set_soft_freq_limited_range(struct smu_context *smu, return clk_id; if (max > 0) { + max = SMU_V14_SOFT_FREQ_ROUND(max); if (automatic) param = (uint32_t)((clk_id << 16) | 0xffff); else diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 086501cc5213be..bad8dd786bff2f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -1701,8 +1701,9 @@ static int smu_v14_0_2_get_power_limit(struct smu_context *smu, table_context->power_play_table; PPTable_t *pptable = table_context->driver_pptable; CustomSkuTable_t *skutable = &pptable->CustomSkuTable; - uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0; + int16_t od_percent_upper = 0, od_percent_lower = 0; uint32_t msg_limit = pptable->SkuTable.MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC]; + uint32_t power_limit; if (smu_v14_0_get_current_power_limit(smu, &power_limit)) power_limit = smu->adev->pm.ac_power ? @@ -2142,10 +2143,15 @@ static int smu_v14_0_2_mode1_reset(struct smu_context *smu) ret = smu_cmn_send_debug_smc_msg(smu, DEBUGSMC_MSG_Mode1Reset); if (!ret) { - if (amdgpu_emu_mode == 1) + if (amdgpu_emu_mode == 1) { msleep(50000); - else + } else { + /* disable mmio access while doing mode 1 reset*/ + smu->adev->no_hw_access = true; + /* ensure no_hw_access is globally visible before any MMIO */ + smp_mb(); msleep(1000); + } } return ret; diff --git a/drivers/gpu/drm/apple/.gitignore b/drivers/gpu/drm/apple/.gitignore new file mode 100644 index 00000000000000..d9a77f3b59b21a --- /dev/null +++ b/drivers/gpu/drm/apple/.gitignore @@ -0,0 +1 @@ +*.hdrtest diff --git a/drivers/gpu/drm/apple/Kconfig b/drivers/gpu/drm/apple/Kconfig new file mode 100644 index 00000000000000..df247b6ed77deb --- /dev/null +++ b/drivers/gpu/drm/apple/Kconfig @@ -0,0 +1,29 @@ +# SPDX-License-Identifier: GPL-2.0-only OR MIT +config DRM_APPLE + tristate "DRM Support for Apple display controllers" + depends on DRM && OF && ARM64 + depends on ARCH_APPLE || COMPILE_TEST + depends on APPLE_RTKIT + depends on OF_ADDRESS + select DRM_CLIENT_SELECTION + select DRM_KMS_HELPER + select DRM_KMS_DMA_HELPER + select DRM_GEM_DMA_HELPER + select VIDEOMODE_HELPERS + select BACKLIGHT_CLASS_DEVICE + select MULTIPLEXER + help + Say Y if you have an Apple Silicon chipset. + +config DRM_APPLE_AUDIO + bool "DisplayPort/HDMI Audio support" + default y + depends on DRM_APPLE + depends on SND + select SND_PCM + select SND_DMAENGINE_PCM + +config DRM_APPLE_DEBUG + bool "Enable additional driver debugging" + depends on DRM_APPLE + depends on EXPERT # only for developers diff --git a/drivers/gpu/drm/apple/Makefile b/drivers/gpu/drm/apple/Makefile new file mode 100644 index 00000000000000..2bb2fd107daed3 --- /dev/null +++ b/drivers/gpu/drm/apple/Makefile @@ -0,0 +1,35 @@ +# SPDX-License-Identifier: GPL-2.0-only OR MIT + +CFLAGS_trace.o = -I$(src) + +appledrm-y := apple_drv.o +appledrm-y += afk.o dcp.o dcp_backlight.o dptxep.o iomfb.o parser.o systemep.o +appledrm-$(CONFIG_DRM_APPLE_AUDIO) += audio.o +appledrm-$(CONFIG_DRM_APPLE_AUDIO) += av.o +appledrm-y += connector.o +appledrm-y += ibootep.o +appledrm-y += iomfb_v12_3.o +appledrm-y += iomfb_v13_3.o +appledrm-y += epic/dpavservep.o +appledrm-y += plane.o + + +appledrm-$(CONFIG_TRACING) += trace.o + +obj-$(CONFIG_DRM_APPLE) += appledrm.o + +# header test + +# exclude some broken headers from the test coverage +no-header-test := \ + hdmi-codec-chmap.h + +always-y += \ + $(patsubst %.h,%.hdrtest, $(filter-out $(no-header-test), \ + $(shell cd $(src) && find * -name '*.h'))) + +quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@) + cmd_hdrtest = $(CC) $(filter-out $(CFLAGS_GCOV), $(c_flags)) -S -o /dev/null -x c /dev/null -include $<; touch $@ + +$(obj)/%.hdrtest: $(src)/%.h FORCE + $(call if_changed_dep,hdrtest) diff --git a/drivers/gpu/drm/apple/afk.c b/drivers/gpu/drm/apple/afk.c new file mode 100644 index 00000000000000..d0de72072877b8 --- /dev/null +++ b/drivers/gpu/drm/apple/afk.c @@ -0,0 +1,1181 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2022 Sven Peter */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "afk.h" +#include "trace.h" + +struct afk_receive_message_work { + struct apple_dcp_afkep *ep; + u64 message; + struct work_struct work; +}; + +#define RBEP_TYPE GENMASK(63, 48) + +enum rbep_msg_type { + RBEP_INIT = 0x80, + RBEP_INIT_ACK = 0xa0, + RBEP_GETBUF = 0x89, + RBEP_GETBUF_ACK = 0xa1, + RBEP_INIT_TX = 0x8a, + RBEP_INIT_RX = 0x8b, + RBEP_START = 0xa3, + RBEP_START_ACK = 0x86, + RBEP_SEND = 0xa2, + RBEP_RECV = 0x85, + RBEP_SHUTDOWN = 0xc0, + RBEP_SHUTDOWN_ACK = 0xc1, +}; + +#define BLOCK_SHIFT 6 + +#define GETBUF_SIZE GENMASK(31, 16) +#define GETBUF_TAG GENMASK(15, 0) +#define GETBUF_ACK_DVA GENMASK(47, 0) + +#define INITRB_OFFSET GENMASK(47, 32) +#define INITRB_SIZE GENMASK(31, 16) +#define INITRB_TAG GENMASK(15, 0) + +#define SEND_WPTR GENMASK(31, 0) + +static void afk_send(struct apple_dcp_afkep *ep, u64 message) +{ + dcp_send_message(ep->dcp, ep->endpoint, message); +} + +struct apple_dcp_afkep *afk_init(struct apple_dcp *dcp, u32 endpoint, + const struct apple_epic_service_ops *ops) +{ + struct apple_dcp_afkep *afkep; + int ret; + + afkep = devm_kzalloc(dcp->dev, sizeof(*afkep), GFP_KERNEL); + if (!afkep) + return ERR_PTR(-ENOMEM); + + afkep->ops = ops; + afkep->dcp = dcp; + afkep->endpoint = endpoint; + afkep->wq = alloc_ordered_workqueue("apple-dcp-afkep%02x", + WQ_MEM_RECLAIM, endpoint); + if (!afkep->wq) { + ret = -ENOMEM; + goto out_free_afkep; + } + + // TODO: devm_ for wq + + init_completion(&afkep->started); + init_completion(&afkep->stopped); + spin_lock_init(&afkep->lock); + + return afkep; + +out_free_afkep: + devm_kfree(dcp->dev, afkep); + return ERR_PTR(ret); +} + +void afk_shutdown(struct apple_dcp_afkep *afkep) +{ + afk_send(afkep, FIELD_PREP(RBEP_TYPE, RBEP_SHUTDOWN)); + int ret; + + ret = wait_for_completion_timeout(&afkep->stopped, msecs_to_jiffies(1000)); + if (ret <= 0) { + dev_err(afkep->dcp->dev, "Timed out shutting down AFK endpoint %02x", afkep->endpoint); + } + + destroy_workqueue(afkep->wq); +} + +int afk_start(struct apple_dcp_afkep *ep) +{ + int ret; + + reinit_completion(&ep->started); + apple_rtkit_start_ep(ep->dcp->rtk, ep->endpoint); + afk_send(ep, FIELD_PREP(RBEP_TYPE, RBEP_INIT)); + + ret = wait_for_completion_timeout(&ep->started, msecs_to_jiffies(1000)); + if (ret <= 0) + return -ETIMEDOUT; + else + return 0; +} + +static void afk_getbuf(struct apple_dcp_afkep *ep, u64 message) +{ + u16 size = FIELD_GET(GETBUF_SIZE, message) << BLOCK_SHIFT; + u16 tag = FIELD_GET(GETBUF_TAG, message); + u64 reply; + + trace_afk_getbuf(ep, size, tag); + + if (ep->bfr) { + dev_err(ep->dcp->dev, + "Got GETBUF message but buffer already exists\n"); + return; + } + + ep->bfr = dmam_alloc_coherent(ep->dcp->dev, size, &ep->bfr_dma, + GFP_KERNEL); + if (!ep->bfr) { + dev_err(ep->dcp->dev, "Failed to allocate %d bytes buffer\n", + size); + return; + } + + ep->bfr_size = size; + ep->bfr_tag = tag; + + reply = FIELD_PREP(RBEP_TYPE, RBEP_GETBUF_ACK); + reply |= FIELD_PREP(GETBUF_ACK_DVA, ep->bfr_dma); + afk_send(ep, reply); +} + +static void afk_init_rxtx(struct apple_dcp_afkep *ep, u64 message, + struct afk_ringbuffer *bfr) +{ + u16 base = FIELD_GET(INITRB_OFFSET, message) << BLOCK_SHIFT; + u16 size = FIELD_GET(INITRB_SIZE, message) << BLOCK_SHIFT; + u16 tag = FIELD_GET(INITRB_TAG, message); + u32 bufsz, end; + + if (tag != ep->bfr_tag) { + dev_err(ep->dcp->dev, "AFK[ep:%02x]: expected tag 0x%x but got 0x%x\n", + ep->endpoint, ep->bfr_tag, tag); + return; + } + + if (bfr->ready) { + dev_err(ep->dcp->dev, "AFK[ep:%02x]: buffer is already initialized\n", + ep->endpoint); + return; + } + + if (base >= ep->bfr_size) { + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: requested base 0x%x >= max size 0x%lx\n", + ep->endpoint, base, ep->bfr_size); + return; + } + + end = base + size; + if (end > ep->bfr_size) { + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: requested end 0x%x > max size 0x%lx\n", + ep->endpoint, end, ep->bfr_size); + return; + } + + bfr->hdr = ep->bfr + base; + bufsz = le32_to_cpu(bfr->hdr->bufsz); + if (bufsz + sizeof(*bfr->hdr) != size) { + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: ring buffer size 0x%x != expected 0x%lx\n", + ep->endpoint, bufsz, sizeof(*bfr->hdr)); + return; + } + + bfr->buf = bfr->hdr + 1; + bfr->bufsz = bufsz; + bfr->ready = true; + + if (ep->rxbfr.ready && ep->txbfr.ready) + afk_send(ep, FIELD_PREP(RBEP_TYPE, RBEP_START)); +} + +#if IS_ENABLED(CONFIG_DRM_APPLE_DEBUG) +static void afk_populate_service_debugfs(struct apple_epic_service *srv); +static void afk_remove_service_debugfs(struct apple_epic_service *srv); +#else +static void afk_populate_service_debugfs(struct apple_epic_service *srv) +{ +} +static void afk_remove_service_debugfs(struct apple_epic_service *srv) +{ +} +#endif + +static const struct apple_epic_service_ops * +afk_match_service(struct apple_dcp_afkep *ep, const char *name) +{ + const struct apple_epic_service_ops *ops; + + if (!name[0]) + return NULL; + if (!ep->ops) + return NULL; + + for (ops = ep->ops; ops->name[0]; ops++) { + if (strcmp(ops->name, name)) + continue; + + return ops; + } + + return NULL; +} + +static struct apple_epic_service *afk_epic_find_service(struct apple_dcp_afkep *ep, + u32 channel) +{ + for (u32 i = 0; i < ep->num_channels; i++) + if (ep->services[i].enabled && ep->services[i].channel == channel) + return &ep->services[i]; + + return NULL; +} + +static void afk_recv_handle_init(struct apple_dcp_afkep *ep, u32 channel, + u8 *payload, size_t payload_size) +{ + char name[32]; + s64 epic_unit = -1; + u32 ch_idx; + const char *service_name = name; + const char *epic_name = NULL, *epic_class = NULL; + const struct apple_epic_service_ops *ops; + struct dcp_parse_ctx ctx; + u8 *props = payload + sizeof(name); + size_t props_size = payload_size - sizeof(name); + + WARN_ON(afk_epic_find_service(ep, channel)); + + if (payload_size < sizeof(name)) { + dev_err(ep->dcp->dev, "AFK[ep:%02x]: payload too small: %lx\n", + ep->endpoint, payload_size); + return; + } + + if (ep->num_channels >= AFK_MAX_CHANNEL) { + dev_err(ep->dcp->dev, "AFK[ep:%02x]: too many enabled services!\n", + ep->endpoint); + return; + } + + strscpy(name, payload, sizeof(name)); + + /* + * in DCP firmware 13.2 DCP reports interface-name as name which starts + * with "dispext%d" using -1 s ID for "dcp". In the 12.3 firmware + * EPICProviderClass was used. If the init call has props parse them and + * use EPICProviderClass to match the service. + */ + if (props_size > 36) { + int ret = parse(props, props_size, &ctx); + if (ret) { + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: Failed to parse service init props for %s\n", + ep->endpoint, name); + return; + } + ret = parse_epic_service_init(&ctx, &epic_name, &epic_class, &epic_unit); + if (ret) { + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: failed to extract init props: %d\n", + ep->endpoint, ret); + return; + } + service_name = epic_class; + } else { + service_name = name; + } + + if (ep->match_epic_name) + ops = afk_match_service(ep, epic_name); + else + ops = afk_match_service(ep, service_name); + + if (!ops) { + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: unable to match service %s on channel %d\n", + ep->endpoint, service_name, channel); + goto free; + } + + ch_idx = ep->num_channels++; + spin_lock_init(&ep->services[ch_idx].lock); + ep->services[ch_idx].enabled = true; + ep->services[ch_idx].torndown = false; + ep->services[ch_idx].ops = ops; + ep->services[ch_idx].ep = ep; + ep->services[ch_idx].channel = channel; + ep->services[ch_idx].cmd_tag = 0; + ops->init(&ep->services[ch_idx], epic_name, epic_class, epic_unit); + dev_info(ep->dcp->dev, "AFK[ep:%02x]: new service %s on channel %d\n", + ep->endpoint, service_name, channel); + + afk_populate_service_debugfs(&ep->services[ch_idx]); + +free: + kfree(epic_name); + kfree(epic_class); +} + +static void afk_recv_handle_teardown(struct apple_dcp_afkep *ep, u32 channel) +{ + struct apple_epic_service *service; + const struct apple_epic_service_ops *ops; + unsigned long flags; + + service = afk_epic_find_service(ep, channel); + if (!service) { + dev_warn(ep->dcp->dev, "AFK[ep:%02x]: teardown for disabled channel %u\n", + ep->endpoint, channel); + return; + } + + afk_remove_service_debugfs(service); + + // TODO: think through what locking is necessary + spin_lock_irqsave(&service->lock, flags); + /* + * teardown must not disable the service since since it may be sent as + * side effect of a COMMAND which for which a reply is expected. + * Seen with DCP's "av" endpoint during the close afk_service_call. + */ + service->torndown = true; + ops = service->ops; + spin_unlock_irqrestore(&service->lock, flags); + + if (ops->teardown) + ops->teardown(service); +} + +static void afk_recv_handle_reply(struct apple_dcp_afkep *ep, u32 channel, + u16 tag, void *payload, size_t payload_size) +{ + struct epic_cmd *cmd = payload; + struct apple_epic_service *service; + unsigned long flags; + u8 idx = tag & 0xff; + void *rxbuf, *txbuf; + dma_addr_t rxbuf_dma, txbuf_dma; + size_t rxlen, txlen; + + service = afk_epic_find_service(ep, channel); + if (!service) { + dev_warn(ep->dcp->dev, "AFK[ep:%02x]: command reply on disabled channel %u\n", + ep->endpoint, channel); + return; + } + + if (payload_size < sizeof(*cmd)) { + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: command reply on channel %d too small: %ld\n", + ep->endpoint, channel, payload_size); + return; + } + + if (idx >= MAX_PENDING_CMDS) { + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: command reply on channel %d out of range: %d\n", + ep->endpoint, channel, idx); + return; + } + + spin_lock_irqsave(&service->lock, flags); + if (service->cmds[idx].done) { + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: command reply on channel %d already handled\n", + ep->endpoint, channel); + spin_unlock_irqrestore(&service->lock, flags); + return; + } + + if (tag != service->cmds[idx].tag) { + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: command reply on channel %d has invalid tag: expected 0x%04x != 0x%04x\n", + ep->endpoint, channel, tag, service->cmds[idx].tag); + spin_unlock_irqrestore(&service->lock, flags); + return; + } + + service->cmds[idx].done = true; + service->cmds[idx].retcode = le32_to_cpu(cmd->retcode); + if (service->cmds[idx].free_on_ack) { + /* defer freeing until we're no longer in atomic context */ + rxbuf = service->cmds[idx].rxbuf; + txbuf = service->cmds[idx].txbuf; + rxlen = service->cmds[idx].rxlen; + txlen = service->cmds[idx].txlen; + rxbuf_dma = service->cmds[idx].rxbuf_dma; + txbuf_dma = service->cmds[idx].txbuf_dma; + bitmap_release_region(service->cmd_map, idx, 0); + } else { + rxbuf = txbuf = NULL; + rxlen = txlen = 0; + } + if (service->cmds[idx].completion) + complete(service->cmds[idx].completion); + + spin_unlock_irqrestore(&service->lock, flags); + + if (rxbuf && rxlen) + dma_free_coherent(ep->dcp->dev, rxlen, rxbuf, rxbuf_dma); + if (txbuf && txlen) + dma_free_coherent(ep->dcp->dev, txlen, txbuf, txbuf_dma); +} + +struct epic_std_service_ap_call { + __le32 unk0; + __le32 unk1; + __le32 type; + __le32 len; + __le32 magic; + u8 _unk[48]; +} __attribute__((packed)); + +static void afk_recv_handle_std_service(struct apple_dcp_afkep *ep, u32 channel, + u32 type, struct epic_hdr *ehdr, + struct epic_sub_hdr *eshdr, + void *payload, size_t payload_size) +{ + struct apple_epic_service *service = afk_epic_find_service(ep, channel); + + if (!service) { + dev_warn(ep->dcp->dev, + "AFK[ep:%02x]: std service notify on disabled channel %u\n", + ep->endpoint, channel); + return; + } + if (service->torndown) { + dev_warn(ep->dcp->dev, + "AFK[ep:%02x]: std service notify on torn down service " + "(chan:%u)\n", ep->endpoint, channel); + return; + } + + if (type == EPIC_TYPE_NOTIFY && eshdr->category == EPIC_CAT_NOTIFY) { + struct epic_std_service_ap_call *call = payload; + size_t call_size; + void *reply; + int ret; + + if (payload_size < sizeof(*call)) + return; + + call_size = le32_to_cpu(call->len); + if (payload_size < sizeof(*call) + call_size) + return; + + if (!service->ops->call) + return; + reply = kzalloc(payload_size, GFP_KERNEL); + if (!reply) + return; + + ret = service->ops->call(service, le32_to_cpu(call->type), + payload + sizeof(*call), call_size, + reply + sizeof(*call), call_size); + if (ret) { + kfree(reply); + return; + } + + memcpy(reply, call, sizeof(*call)); + afk_send_epic(ep, channel, le16_to_cpu(eshdr->tag), + EPIC_TYPE_NOTIFY_ACK, EPIC_CAT_REPLY, + EPIC_SUBTYPE_STD_SERVICE, reply, payload_size); + kfree(reply); + + return; + } + + if (type == EPIC_TYPE_NOTIFY && eshdr->category == EPIC_CAT_REPORT) { + if (service->ops->report) + service->ops->report(service, le16_to_cpu(eshdr->type), + payload, payload_size); + return; + } + + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: channel %d received unhandled standard service message: %x / %x\n", + ep->endpoint, channel, type, eshdr->category); + print_hex_dump(KERN_INFO, "AFK: ", DUMP_PREFIX_NONE, 16, 1, payload, + payload_size, true); +} + +static void afk_recv_handle(struct apple_dcp_afkep *ep, u32 channel, u32 type, + u8 *data, size_t data_size) +{ + struct apple_epic_service *service; + struct epic_hdr *ehdr = (struct epic_hdr *)data; + struct epic_sub_hdr *eshdr = + (struct epic_sub_hdr *)(data + sizeof(*ehdr)); + u16 subtype = le16_to_cpu(eshdr->type); + u8 *payload = data + sizeof(*ehdr) + sizeof(*eshdr); + size_t payload_size; + + if (data_size < sizeof(*ehdr) + sizeof(*eshdr)) { + dev_err(ep->dcp->dev, "AFK[ep:%02x]: payload too small: %lx\n", + ep->endpoint, data_size); + return; + } + payload_size = data_size - sizeof(*ehdr) - sizeof(*eshdr); + + trace_afk_recv_handle(ep, channel, type, data_size, ehdr, eshdr); + + service = afk_epic_find_service(ep, channel); + + if (!service) { + if (type != EPIC_TYPE_NOTIFY && type != EPIC_TYPE_REPLY) { + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: expected notify but got 0x%x on channel %d\n", + ep->endpoint, type, channel); + return; + } + if (eshdr->category != EPIC_CAT_REPORT) { + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: expected report but got 0x%x on channel %d\n", + ep->endpoint, eshdr->category, channel); + return; + } + if (subtype == EPIC_SUBTYPE_TEARDOWN) { + dev_dbg(ep->dcp->dev, + "AFK[ep:%02x]: teardown without service on channel %d\n", + ep->endpoint, channel); + return; + } + if (subtype != EPIC_SUBTYPE_ANNOUNCE) { + dev_err(ep->dcp->dev, + "AFK[ep:%02x]: expected announce but got 0x%x on channel %d\n", + ep->endpoint, subtype, channel); + return; + } + + return afk_recv_handle_init(ep, channel, payload, payload_size); + } + + if (!service) { + dev_err(ep->dcp->dev, "AFK[ep:%02x]: channel %d has no service\n", + ep->endpoint, channel); + return; + } + + if (type == EPIC_TYPE_NOTIFY && eshdr->category == EPIC_CAT_REPORT && + subtype == EPIC_SUBTYPE_TEARDOWN) + return afk_recv_handle_teardown(ep, channel); + + if (type == EPIC_TYPE_REPLY && eshdr->category == EPIC_CAT_REPLY) + return afk_recv_handle_reply(ep, channel, + le16_to_cpu(eshdr->tag), payload, + payload_size); + + if (subtype == EPIC_SUBTYPE_STD_SERVICE) + return afk_recv_handle_std_service( + ep, channel, type, ehdr, eshdr, payload, payload_size); + + dev_err(ep->dcp->dev, "AFK[ep:%02x]: channel %d received unhandled message " + "(type %x subtype %x)\n", ep->endpoint, channel, type, subtype); + print_hex_dump(KERN_INFO, "AFK: ", DUMP_PREFIX_NONE, 16, 1, payload, + payload_size, true); +} + +static bool afk_recv(struct apple_dcp_afkep *ep) +{ + struct afk_qe *hdr; + u32 rptr, wptr; + u32 magic, size, channel, type; + + if (!ep->rxbfr.ready) { + dev_err(ep->dcp->dev, "AFK[ep:%02x]: got RECV but not ready\n", + ep->endpoint); + return false; + } + + rptr = le32_to_cpu(ep->rxbfr.hdr->rptr); + wptr = le32_to_cpu(ep->rxbfr.hdr->wptr); + trace_afk_recv_rwptr_pre(ep, rptr, wptr); + + if (rptr == wptr) + return false; + + if (rptr > (ep->rxbfr.bufsz - sizeof(*hdr))) { + dev_warn(ep->dcp->dev, + "AFK[ep:%02x]: rptr out of bounds: 0x%x > 0x%lx\n", + ep->endpoint, rptr, ep->rxbfr.bufsz - sizeof(*hdr)); + return false; + } + + dma_rmb(); + + hdr = ep->rxbfr.buf + rptr; + magic = le32_to_cpu(hdr->magic); + size = le32_to_cpu(hdr->size); + trace_afk_recv_qe(ep, rptr, magic, size); + + if (magic != QE_MAGIC) { + dev_warn(ep->dcp->dev, "AFK[ep:%02x]: invalid queue entry magic: 0x%x\n", + ep->endpoint, magic); + return false; + } + + /* + * If there's not enough space for the payload the co-processor inserted + * the current dummy queue entry and we have to advance to the next one + * which will contain the real data. + */ + if (rptr + size + sizeof(*hdr) > ep->rxbfr.bufsz) { + rptr = 0; + hdr = ep->rxbfr.buf + rptr; + magic = le32_to_cpu(hdr->magic); + size = le32_to_cpu(hdr->size); + trace_afk_recv_qe(ep, rptr, magic, size); + + if (magic != QE_MAGIC) { + dev_warn(ep->dcp->dev, + "AFK[ep:%02x]: invalid next queue entry magic: 0x%x\n", + ep->endpoint, magic); + return false; + } + + ep->rxbfr.hdr->rptr = cpu_to_le32(rptr); + } + + if (rptr + size + sizeof(*hdr) > ep->rxbfr.bufsz) { + dev_warn(ep->dcp->dev, + "AFK[ep:%02x]: queue entry out of bounds: 0x%lx > 0x%lx\n", + ep->endpoint, rptr + size + sizeof(*hdr), ep->rxbfr.bufsz); + return false; + } + + channel = le32_to_cpu(hdr->channel); + type = le32_to_cpu(hdr->type); + + rptr = ALIGN(rptr + sizeof(*hdr) + size, 1 << BLOCK_SHIFT); + if (WARN_ON(rptr > ep->rxbfr.bufsz)) + rptr = 0; + if (rptr == ep->rxbfr.bufsz) + rptr = 0; + + dma_mb(); + + ep->rxbfr.hdr->rptr = cpu_to_le32(rptr); + trace_afk_recv_rwptr_post(ep, rptr, wptr); + + /* + * TODO: this is theoretically unsafe since DCP could overwrite data + * after the read pointer was updated above. Do it anyway since + * it avoids 2 problems in the DCP tracer: + * 1. the tracer sees replies before the notifies from dcp + * 2. the tracer tries to read buffers after they are unmapped. + */ + afk_recv_handle(ep, channel, type, hdr->data, size); + + return true; +} + +static void afk_receive_message_worker(struct work_struct *work_) +{ + struct afk_receive_message_work *work; + u16 type; + + work = container_of(work_, struct afk_receive_message_work, work); + + type = FIELD_GET(RBEP_TYPE, work->message); + switch (type) { + case RBEP_INIT_ACK: + break; + + case RBEP_START_ACK: + complete_all(&work->ep->started); + break; + + case RBEP_SHUTDOWN_ACK: + complete_all(&work->ep->stopped); + break; + + case RBEP_GETBUF: + afk_getbuf(work->ep, work->message); + break; + + case RBEP_INIT_TX: + afk_init_rxtx(work->ep, work->message, &work->ep->txbfr); + break; + + case RBEP_INIT_RX: + afk_init_rxtx(work->ep, work->message, &work->ep->rxbfr); + break; + + case RBEP_RECV: + while (afk_recv(work->ep)) + ; + break; + + default: + dev_err(work->ep->dcp->dev, + "Received unknown AFK message type: 0x%x\n", type); + } + + kfree(work); +} + +int afk_receive_message(struct apple_dcp_afkep *ep, u64 message) +{ + struct afk_receive_message_work *work; + + // TODO: comment why decoupling from rtkit thread is required here + work = kzalloc(sizeof(*work), GFP_KERNEL); + if (!work) + return -ENOMEM; + + work->ep = ep; + work->message = message; + INIT_WORK(&work->work, afk_receive_message_worker); + queue_work(ep->wq, &work->work); + + return 0; +} + +int afk_send_epic(struct apple_dcp_afkep *ep, u32 channel, u16 tag, + enum epic_type etype, enum epic_category ecat, u8 stype, + const void *payload, size_t payload_len) +{ + u32 rptr, wptr; + struct afk_qe *hdr, *hdr2; + struct epic_hdr *ehdr; + struct epic_sub_hdr *eshdr; + unsigned long flags; + size_t total_epic_size, total_size; + int ret; + + spin_lock_irqsave(&ep->lock, flags); + + dma_rmb(); + rptr = le32_to_cpu(ep->txbfr.hdr->rptr); + wptr = le32_to_cpu(ep->txbfr.hdr->wptr); + trace_afk_send_rwptr_pre(ep, rptr, wptr); + total_epic_size = sizeof(*ehdr) + sizeof(*eshdr) + payload_len; + total_size = sizeof(*hdr) + total_epic_size; + + hdr = hdr2 = NULL; + + /* + * We need to figure out how to place the entire headers and payload + * into the ring buffer: + * - If the write pointer is in front of the read pointer we just need + * enough space inbetween to store everything. + * - If the read pointer has already wrapper around the end of the + * buffer we can + * a) either store the entire payload at the writer pointer if + * there's enough space until the end, + * b) or just store the queue entry at the write pointer to indicate + * that we need to wrap to the start and then store the headers + * and the payload at the beginning of the buffer. The queue + * header has to be store twice in this case. + * In either case we have to ensure that there's always enough space + * so that we don't accidentally overwrite other buffers. + */ + if (wptr < rptr) { + /* + * If wptr < rptr we can't wrap around and only have to make + * sure that there's enough space for the entire payload. + */ + if (wptr + total_size > rptr) { + ret = -ENOMEM; + goto out; + } + + hdr = ep->txbfr.buf + wptr; + wptr += sizeof(*hdr); + } else { + /* We need enough space to place at least a queue entry */ + if (wptr + sizeof(*hdr) > ep->txbfr.bufsz) { + ret = -ENOMEM; + goto out; + } + + /* + * If we can place a single queue entry but not the full payload + * we need to place one queue entry at the end of the ring + * buffer and then another one together with the entire + * payload at the beginning. + */ + if (wptr + total_size > ep->txbfr.bufsz) { + /* + * Ensure there's space for the queue entry at the + * beginning + */ + if (sizeof(*hdr) > rptr) { + ret = -ENOMEM; + goto out; + } + + /* + * Place two queue entries to indicate we want to wrap + * around to the firmware. + */ + hdr = ep->txbfr.buf + wptr; + hdr2 = ep->txbfr.buf; + wptr = sizeof(*hdr); + + /* Ensure there's enough space for the entire payload */ + if (wptr + total_epic_size > rptr) { + ret = -ENOMEM; + goto out; + } + } else { + /* We have enough space to place the entire payload */ + hdr = ep->txbfr.buf + wptr; + wptr += sizeof(*hdr); + } + } + /* + * At this point we're guaranteed that hdr (and possibly hdr2) point + * to a buffer large enough to fit the queue entry and that we have + * enough space at wptr to store the payload. + */ + + hdr->magic = cpu_to_le32(QE_MAGIC); + hdr->size = cpu_to_le32(total_epic_size); + hdr->channel = cpu_to_le32(channel); + hdr->type = cpu_to_le32(etype); + if (hdr2) + memcpy(hdr2, hdr, sizeof(*hdr)); + + ehdr = ep->txbfr.buf + wptr; + memset(ehdr, 0, sizeof(*ehdr)); + ehdr->version = 2; + ehdr->seq = cpu_to_le16(ep->qe_seq++); + ehdr->timestamp = cpu_to_le64(0); + wptr += sizeof(*ehdr); + + eshdr = ep->txbfr.buf + wptr; + memset(eshdr, 0, sizeof(*eshdr)); + eshdr->length = cpu_to_le32(payload_len); + eshdr->version = 4; + eshdr->category = ecat; + eshdr->type = cpu_to_le16(stype); + eshdr->timestamp = cpu_to_le64(0); + eshdr->tag = cpu_to_le16(tag); + if (ecat == EPIC_CAT_REPLY) + eshdr->inline_len = cpu_to_le16(payload_len - 4); + else + eshdr->inline_len = cpu_to_le16(0); + wptr += sizeof(*eshdr); + + memcpy(ep->txbfr.buf + wptr, payload, payload_len); + wptr += payload_len; + wptr = ALIGN(wptr, 1 << BLOCK_SHIFT); + if (wptr == ep->txbfr.bufsz) + wptr = 0; + trace_afk_send_rwptr_post(ep, rptr, wptr); + + ep->txbfr.hdr->wptr = cpu_to_le32(wptr); + afk_send(ep, FIELD_PREP(RBEP_TYPE, RBEP_SEND) | + FIELD_PREP(SEND_WPTR, wptr)); + ret = 0; + +out: + spin_unlock_irqrestore(&ep->lock, flags); + return ret; +} + +int afk_send_command(struct apple_epic_service *service, u8 type, + const void *payload, size_t payload_len, void *output, + size_t output_len, u32 *retcode) +{ + struct epic_cmd cmd; + void *rxbuf, *txbuf; + dma_addr_t rxbuf_dma, txbuf_dma; + unsigned long flags; + int ret, idx; + u16 tag; + struct apple_dcp_afkep *ep = service->ep; + DECLARE_COMPLETION_ONSTACK(completion); + + rxbuf = dma_alloc_coherent(ep->dcp->dev, output_len, &rxbuf_dma, + GFP_KERNEL); + if (!rxbuf) + return -ENOMEM; + txbuf = dma_alloc_coherent(ep->dcp->dev, payload_len, &txbuf_dma, + GFP_KERNEL); + if (!txbuf) { + ret = -ENOMEM; + goto err_free_rxbuf; + } + + memcpy(txbuf, payload, payload_len); + + memset(&cmd, 0, sizeof(cmd)); + cmd.retcode = cpu_to_le32(0); + cmd.rxbuf = cpu_to_le64(rxbuf_dma); + cmd.rxlen = cpu_to_le32(output_len); + cmd.txbuf = cpu_to_le64(txbuf_dma); + cmd.txlen = cpu_to_le32(payload_len); + + spin_lock_irqsave(&service->lock, flags); + idx = bitmap_find_free_region(service->cmd_map, MAX_PENDING_CMDS, 0); + if (idx < 0) { + ret = -ENOSPC; + goto err_unlock; + } + + tag = (service->cmd_tag & 0xff) << 8; + tag |= idx & 0xff; + service->cmd_tag++; + + service->cmds[idx].tag = tag; + service->cmds[idx].rxbuf = rxbuf; + service->cmds[idx].txbuf = txbuf; + service->cmds[idx].rxbuf_dma = rxbuf_dma; + service->cmds[idx].txbuf_dma = txbuf_dma; + service->cmds[idx].rxlen = output_len; + service->cmds[idx].txlen = payload_len; + service->cmds[idx].free_on_ack = false; + service->cmds[idx].done = false; + service->cmds[idx].completion = &completion; + init_completion(&completion); + + spin_unlock_irqrestore(&service->lock, flags); + + ret = afk_send_epic(service->ep, service->channel, tag, + EPIC_TYPE_COMMAND, EPIC_CAT_COMMAND, type, &cmd, + sizeof(cmd)); + if (ret) + goto err_free_cmd; + + ret = wait_for_completion_timeout(&completion, + msecs_to_jiffies(MSEC_PER_SEC)); + + if (ret <= 0) { + spin_lock_irqsave(&service->lock, flags); + /* + * Check again while we're inside the lock to make sure + * the command wasn't completed just after + * wait_for_completion_timeout returned. + */ + if (!service->cmds[idx].done) { + service->cmds[idx].completion = NULL; + service->cmds[idx].free_on_ack = true; + spin_unlock_irqrestore(&service->lock, flags); + return -ETIMEDOUT; + } + spin_unlock_irqrestore(&service->lock, flags); + } + + ret = 0; + if (retcode) + *retcode = service->cmds[idx].retcode; + if (output && output_len) + memcpy(output, rxbuf, output_len); + +err_free_cmd: + spin_lock_irqsave(&service->lock, flags); + bitmap_release_region(service->cmd_map, idx, 0); +err_unlock: + spin_unlock_irqrestore(&service->lock, flags); + dma_free_coherent(ep->dcp->dev, payload_len, txbuf, txbuf_dma); +err_free_rxbuf: + dma_free_coherent(ep->dcp->dev, output_len, rxbuf, rxbuf_dma); + return ret; +} + +int afk_service_call(struct apple_epic_service *service, u16 group, u32 command, + const void *data, size_t data_len, size_t data_pad, + void *output, size_t output_len, size_t output_pad) +{ + struct epic_service_call *call; + void *bfr; + size_t bfr_len = max(data_len + data_pad, output_len + output_pad) + + sizeof(*call); + int ret; + u32 retcode; + u32 retlen; + + bfr = kzalloc(bfr_len, GFP_KERNEL); + if (!bfr) + return -ENOMEM; + + call = bfr; + + memset(call, 0, sizeof(*call)); + call->group = cpu_to_le16(group); + call->command = cpu_to_le32(command); + call->data_len = cpu_to_le32(data_len + data_pad); + call->magic = cpu_to_le32(EPIC_SERVICE_CALL_MAGIC); + + memcpy(bfr + sizeof(*call), data, data_len); + + ret = afk_send_command(service, EPIC_SUBTYPE_STD_SERVICE, bfr, bfr_len, + bfr, bfr_len, &retcode); + if (ret) + goto out; + if (retcode) { + ret = -EINVAL; + goto out; + } + if (le32_to_cpu(call->magic) != EPIC_SERVICE_CALL_MAGIC || + le16_to_cpu(call->group) != group || + le32_to_cpu(call->command) != command) { + ret = -EINVAL; + goto out; + } + + retlen = le32_to_cpu(call->data_len); + if (output_len < retlen) + retlen = output_len; + if (output && output_len) { + memset(output, 0, output_len); + memcpy(output, bfr + sizeof(*call), retlen); + } + +out: + kfree(bfr); + return ret; +} + +#if IS_ENABLED(CONFIG_DRM_APPLE_DEBUG) + +#define AFK_DEBUGFS_MAX_REPLY 8192 + +static ssize_t service_call_write_file(struct file *file, const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct apple_epic_service *srv = file->private_data; + void *buf; + int ret; + struct { + u32 group; + u32 command; + } call_info; + + if (count < sizeof(call_info)) + return -EINVAL; + if (!srv->debugfs.scratch) { + srv->debugfs.scratch = \ + devm_kzalloc(srv->ep->dcp->dev, AFK_DEBUGFS_MAX_REPLY, GFP_KERNEL); + if (!srv->debugfs.scratch) + return -ENOMEM; + } + + ret = copy_from_user(&call_info, user_buf, sizeof(call_info)); + if (ret == sizeof(call_info)) + return -EFAULT; + user_buf += sizeof(call_info); + count -= sizeof(call_info); + + buf = kmalloc(count, GFP_KERNEL); + if (!buf) + return -ENOMEM; + ret = copy_from_user(buf, user_buf, count); + if (ret == count) { + kfree(buf); + return -EFAULT; + } + + memset(srv->debugfs.scratch, 0, AFK_DEBUGFS_MAX_REPLY); + dma_mb(); + + ret = afk_service_call(srv, call_info.group, call_info.command, buf, count, 0, + srv->debugfs.scratch, AFK_DEBUGFS_MAX_REPLY, 0); + kfree(buf); + + if (ret < 0) + return ret; + + return count + sizeof(call_info); +} + +static ssize_t service_call_read_file(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct apple_epic_service *srv = file->private_data; + + if (!srv->debugfs.scratch) + return -EINVAL; + + return simple_read_from_buffer(user_buf, count, ppos, + srv->debugfs.scratch, AFK_DEBUGFS_MAX_REPLY); +} + +static const struct file_operations service_call_fops = { + .open = simple_open, + .write = service_call_write_file, + .read = service_call_read_file, +}; + +static ssize_t service_raw_call_write_file(struct file *file, const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct apple_epic_service *srv = file->private_data; + u32 retcode; + int ret; + + if (!srv->debugfs.scratch) { + srv->debugfs.scratch = \ + devm_kzalloc(srv->ep->dcp->dev, AFK_DEBUGFS_MAX_REPLY, GFP_KERNEL); + if (!srv->debugfs.scratch) + return -ENOMEM; + } + + memset(srv->debugfs.scratch, 0, AFK_DEBUGFS_MAX_REPLY); + ret = copy_from_user(srv->debugfs.scratch, user_buf, count); + if (ret == count) + return -EFAULT; + + ret = afk_send_command(srv, EPIC_SUBTYPE_STD_SERVICE, srv->debugfs.scratch, count, + srv->debugfs.scratch, AFK_DEBUGFS_MAX_REPLY, &retcode); + if (ret < 0) + return ret; + if (retcode) + return -EINVAL; + + return count; +} + +static ssize_t service_raw_call_read_file(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct apple_epic_service *srv = file->private_data; + + if (!srv->debugfs.scratch) + return -EINVAL; + + return simple_read_from_buffer(user_buf, count, ppos, + srv->debugfs.scratch, AFK_DEBUGFS_MAX_REPLY); +} + +static const struct file_operations service_raw_call_fops = { + .open = simple_open, + .write = service_raw_call_write_file, + .read = service_raw_call_read_file, +}; + +static void afk_populate_service_debugfs(struct apple_epic_service *srv) +{ + if (!srv->ep->debugfs_entry || !srv->ops) + return; + + if (strcmp(srv->ops->name, "DCPAVAudioInterface") == 0) { + srv->debugfs.entry = debugfs_create_dir(srv->ops->name, + srv->ep->debugfs_entry); + debugfs_create_file("call", 0600, srv->debugfs.entry, srv, + &service_call_fops); + debugfs_create_file("raw_call", 0600, srv->debugfs.entry, srv, + &service_raw_call_fops); + } +} + +static void afk_remove_service_debugfs(struct apple_epic_service *srv) +{ + if (srv->debugfs.entry) { + debugfs_remove_recursive(srv->debugfs.entry); + srv->debugfs.entry = NULL; + } +} + +#endif diff --git a/drivers/gpu/drm/apple/afk.h b/drivers/gpu/drm/apple/afk.h new file mode 100644 index 00000000000000..a339c00a2a0138 --- /dev/null +++ b/drivers/gpu/drm/apple/afk.h @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * AFK (Apple Firmware Kit) EPIC (EndPoint Interface Client) support + */ +/* Copyright 2022 Sven Peter */ + +#ifndef _DRM_APPLE_DCP_AFK_H +#define _DRM_APPLE_DCP_AFK_H + +#include +#include +#include + +#include "dcp.h" + +#define AFK_MAX_CHANNEL 16 +#define MAX_PENDING_CMDS 16 + +struct apple_epic_service_ops; +struct apple_dcp_afkep; + +struct epic_cmd_info { + u16 tag; + + void *rxbuf; + void *txbuf; + dma_addr_t rxbuf_dma; + dma_addr_t txbuf_dma; + size_t rxlen; + size_t txlen; + + u32 retcode; + bool done; + bool free_on_ack; + struct completion *completion; +}; + +struct apple_epic_service { + const struct apple_epic_service_ops *ops; + struct apple_dcp_afkep *ep; + + struct epic_cmd_info cmds[MAX_PENDING_CMDS]; + DECLARE_BITMAP(cmd_map, MAX_PENDING_CMDS); + u8 cmd_tag; + spinlock_t lock; + + u32 channel; + bool enabled; + bool torndown; + + void *cookie; + + struct { + struct dentry *entry; + u8 *scratch; + } debugfs; +}; + +enum epic_subtype; + +struct apple_epic_service_ops { + const char name[32]; + + void (*init)(struct apple_epic_service *service, const char *name, + const char *class, s64 unit); + int (*call)(struct apple_epic_service *service, u32 idx, + const void *data, size_t data_size, void *reply, + size_t reply_size); + int (*report)(struct apple_epic_service *service, enum epic_subtype type, + const void *data, size_t data_size); + void (*teardown)(struct apple_epic_service *service); +}; + +struct afk_ringbuffer_header { + __le32 bufsz; + u32 unk; + u32 _pad1[14]; + __le32 rptr; + u32 _pad2[15]; + __le32 wptr; + u32 _pad3[15]; +}; + +struct afk_qe { +#define QE_MAGIC 0x20504f49 // ' POI' + __le32 magic; + __le32 size; + __le32 channel; + __le32 type; + u8 data[]; +}; + +struct epic_hdr { + u8 version; + __le16 seq; + u8 _pad; + __le32 unk; + __le64 timestamp; +} __attribute__((packed)); + +struct epic_sub_hdr { + __le32 length; + u8 version; + u8 category; + __le16 type; + __le64 timestamp; + __le16 tag; + __le16 unk; + __le32 inline_len; +} __attribute__((packed)); + +struct epic_cmd { + __le32 retcode; + __le64 rxbuf; + __le64 txbuf; + __le32 rxlen; + __le32 txlen; + u8 rxcookie; + u8 txcookie; +} __attribute__((packed)); + +struct epic_service_call { + u8 _pad0[2]; + __le16 group; + __le32 command; + __le32 data_len; +#define EPIC_SERVICE_CALL_MAGIC 0x69706378 + __le32 magic; + u8 _pad1[48]; +} __attribute__((packed)); +static_assert(sizeof(struct epic_service_call) == 64); + +enum epic_type { + EPIC_TYPE_NOTIFY = 0, + EPIC_TYPE_COMMAND = 3, + EPIC_TYPE_REPLY = 4, + EPIC_TYPE_NOTIFY_ACK = 8, +}; + +enum epic_category { + EPIC_CAT_REPORT = 0x00, + EPIC_CAT_NOTIFY = 0x10, + EPIC_CAT_REPLY = 0x20, + EPIC_CAT_COMMAND = 0x30, +}; + +enum epic_subtype { + EPIC_SUBTYPE_ANNOUNCE = 0x30, + EPIC_SUBTYPE_TEARDOWN = 0x32, + EPIC_SUBTYPE_STD_SERVICE = 0xc0, +}; + +struct afk_ringbuffer { + bool ready; + struct afk_ringbuffer_header *hdr; + u32 rptr; + void *buf; + size_t bufsz; +}; + +struct apple_dcp_afkep { + struct apple_dcp *dcp; + + u32 endpoint; + struct workqueue_struct *wq; + + struct completion started; + struct completion stopped; + + void *bfr; + u16 bfr_tag; + size_t bfr_size; + dma_addr_t bfr_dma; + + struct afk_ringbuffer txbfr; + struct afk_ringbuffer rxbfr; + + spinlock_t lock; + u16 qe_seq; + + const struct apple_epic_service_ops *ops; + struct apple_epic_service services[AFK_MAX_CHANNEL]; + u32 num_channels; + + struct dentry *debugfs_entry; + + bool match_epic_name; +}; + +struct apple_dcp_afkep *afk_init(struct apple_dcp *dcp, u32 endpoint, + const struct apple_epic_service_ops *ops); +int afk_start(struct apple_dcp_afkep *ep); +void afk_shutdown(struct apple_dcp_afkep *ep); +int afk_receive_message(struct apple_dcp_afkep *ep, u64 message); +int afk_send_epic(struct apple_dcp_afkep *ep, u32 channel, u16 tag, + enum epic_type etype, enum epic_category ecat, u8 stype, + const void *payload, size_t payload_len); +int afk_send_command(struct apple_epic_service *service, u8 type, + const void *payload, size_t payload_len, void *output, + size_t output_len, u32 *retcode); +int afk_service_call(struct apple_epic_service *service, u16 group, u32 command, + const void *data, size_t data_len, size_t data_pad, + void *output, size_t output_len, size_t output_pad); +#endif diff --git a/drivers/gpu/drm/apple/apple_drv.c b/drivers/gpu/drm/apple/apple_drv.c new file mode 100644 index 00000000000000..4c1a4a7f5e2001 --- /dev/null +++ b/drivers/gpu/drm/apple/apple_drv.c @@ -0,0 +1,693 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2021 Alyssa Rosenzweig */ +/* Based on meson driver which is + * Copyright (C) 2016 BayLibre, SAS + * Author: Neil Armstrong + * Copyright (C) 2015 Amlogic, Inc. All rights reserved. + * Copyright (C) 2014 Endless Mobile + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "dcp.h" +#include "plane.h" + +#define DRIVER_NAME "apple" +#define DRIVER_DESC "Apple display controller DRM driver" + +#define MAX_COPROCESSORS 3 + +struct apple_drm_private { + struct drm_device drm; +}; + +DEFINE_DRM_GEM_DMA_FOPS(apple_fops); + +#define DART_PAGE_SIZE 16384 + +static int apple_drm_gem_dumb_create(struct drm_file *file_priv, + struct drm_device *drm, + struct drm_mode_create_dumb *args) +{ + args->pitch = ALIGN(DIV_ROUND_UP(args->width * args->bpp, 8), 64); + args->size = round_up(args->pitch * args->height, DART_PAGE_SIZE); + + return drm_gem_dma_dumb_create_internal(file_priv, drm, args); +} + +static const struct drm_driver apple_drm_driver = { + DRM_GEM_DMA_DRIVER_OPS_WITH_DUMB_CREATE(apple_drm_gem_dumb_create), + DRM_FBDEV_DMA_DRIVER_OPS, + .name = DRIVER_NAME, + .desc = DRIVER_DESC, + .major = 1, + .minor = 0, + .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_ATOMIC | DRIVER_SYNCOBJ | DRIVER_SYNCOBJ_TIMELINE, + .fops = &apple_fops, +}; + +static enum drm_connector_status +apple_connector_detect(struct drm_connector *connector, bool force) +{ + struct apple_connector *apple_connector = to_apple_connector(connector); + + return apple_connector->connected ? connector_status_connected : + connector_status_disconnected; +} + +static void apple_connector_oob_hotplug(struct drm_connector *connector, + enum drm_connector_status status) +{ + struct apple_connector *apple_connector = to_apple_connector(connector); + + printk("#### oob_hotplug status:0x%x ####\n", (u32)status); + + if (status == connector_status_connected) + dcp_dptx_connect_oob(apple_connector->dcp, 0); + else if (status == connector_status_disconnected) + dcp_dptx_disconnect_oob(apple_connector->dcp, 0); + else + dev_err(&apple_connector->dcp->dev, "unexpected connector status" + ":0x%x in oob_hotplug event\n", (u32)status); +} + +static void apple_crtc_atomic_enable(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct drm_crtc_state *crtc_state; + crtc_state = drm_atomic_get_new_crtc_state(state, crtc); + + if (crtc_state->active_changed && crtc_state->active) { + struct apple_crtc *apple_crtc = to_apple_crtc(crtc); + dcp_poweron(apple_crtc->dcp); + } + + if (crtc_state->active) + dcp_crtc_atomic_modeset(crtc, state); +} + +static void apple_crtc_atomic_disable(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct drm_crtc_state *crtc_state; + crtc_state = drm_atomic_get_new_crtc_state(state, crtc); + + if (crtc_state->active_changed && !crtc_state->active) { + struct apple_crtc *apple_crtc = to_apple_crtc(crtc); + dcp_poweroff(apple_crtc->dcp); + } + + if (crtc->state->event && !crtc->state->active) { + spin_lock_irq(&crtc->dev->event_lock); + drm_crtc_send_vblank_event(crtc, crtc->state->event); + spin_unlock_irq(&crtc->dev->event_lock); + + crtc->state->event = NULL; + } +} + +static void apple_crtc_atomic_begin(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct apple_crtc *apple_crtc = to_apple_crtc(crtc); + unsigned long flags; + + if (crtc->state->event) { + spin_lock_irqsave(&crtc->dev->event_lock, flags); + apple_crtc->event = crtc->state->event; + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + crtc->state->event = NULL; + } +} + +static void apple_crtc_cleanup(struct drm_crtc *crtc) +{ + drm_crtc_cleanup(crtc); + kfree(to_apple_crtc(crtc)); +} + +static int apple_crtc_parse_crc_source(const char *source, bool *enabled) +{ + int ret = 0; + + if (!source) { + *enabled = false; + } else if (strcmp(source, "auto") == 0) { + *enabled = true; + } else { + *enabled = false; + ret = -EINVAL; + } + + return ret; +} + +static int apple_crtc_set_crc_source(struct drm_crtc *crtc, const char *source) +{ + bool enabled = false; + + int ret = apple_crtc_parse_crc_source(source, &enabled); + + if (!ret) + dcp_set_crc(crtc, enabled); + + return ret; +} + +static int apple_crtc_verify_crc_source(struct drm_crtc *crtc, + const char *source, + size_t *values_cnt) +{ + bool enabled; + + if (apple_crtc_parse_crc_source(source, &enabled) < 0) { + pr_warn("dcp: Invalid CRC source name %s\n", source); + return -EINVAL; + } + + *values_cnt = 1; + + return 0; +} + +static const char * const apple_crtc_crc_sources[] = {"auto"}; + +static const char *const * apple_crtc_get_crc_sources(struct drm_crtc *crtc, + size_t *count) +{ + *count = ARRAY_SIZE(apple_crtc_crc_sources); + return apple_crtc_crc_sources; +} + +static const struct drm_crtc_funcs apple_crtc_funcs = { + .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, + .atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state, + .destroy = apple_crtc_cleanup, + .page_flip = drm_atomic_helper_page_flip, + .reset = drm_atomic_helper_crtc_reset, + .set_config = drm_atomic_helper_set_config, + .set_crc_source = apple_crtc_set_crc_source, + .verify_crc_source = apple_crtc_verify_crc_source, + .get_crc_sources = apple_crtc_get_crc_sources, + +}; + +static const struct drm_mode_config_funcs apple_mode_config_funcs = { + .atomic_check = drm_atomic_helper_check, + .atomic_commit = drm_atomic_helper_commit, + .fb_create = drm_gem_fb_create, +}; + +static const struct drm_mode_config_helper_funcs apple_mode_config_helpers = { + .atomic_commit_tail = drm_atomic_helper_commit_tail_rpm, +}; + +static void appledrm_connector_cleanup(struct drm_connector *connector) +{ + drm_connector_cleanup(connector); + kfree(to_apple_connector(connector)); +} + +static const struct drm_connector_funcs apple_connector_funcs = { + .fill_modes = drm_helper_probe_single_connector_modes, + .destroy = appledrm_connector_cleanup, + .reset = drm_atomic_helper_connector_reset, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, + .detect = apple_connector_detect, + .debugfs_init = apple_connector_debugfs_init, + .oob_hotplug_event = apple_connector_oob_hotplug, +}; + +static const struct drm_connector_helper_funcs apple_connector_helper_funcs = { + .get_modes = dcp_get_modes, + .mode_valid = dcp_mode_valid, +}; + +static const struct drm_crtc_helper_funcs apple_crtc_helper_funcs = { + .atomic_begin = apple_crtc_atomic_begin, + .atomic_check = dcp_crtc_atomic_check, + .atomic_flush = dcp_flush, + .atomic_enable = apple_crtc_atomic_enable, + .atomic_disable = apple_crtc_atomic_disable, + .mode_fixup = dcp_crtc_mode_fixup, +}; + +static int apple_probe_per_dcp(struct device *dev, + struct drm_device *drm, + struct platform_device *dcp, + int num, bool dcp_ext) +{ + struct apple_crtc *crtc; + struct apple_connector *connector; + struct apple_encoder *enc; + struct drm_plane *planes[DCP_MAX_PLANES]; + int ret, i; + int immutable_zpos = 0; + bool supports_l10r = !dcp_fw_compat_is_12_x(dcp); + + planes[0] = apple_plane_init(drm, 1U << num, supports_l10r, + DRM_PLANE_TYPE_PRIMARY); + if (IS_ERR(planes[0])) + return PTR_ERR(planes[0]); + ret = drm_plane_create_zpos_immutable_property(planes[0], immutable_zpos); + if (ret) { + return ret; + } + + + /* Set up our other planes */ + for (i = 1; i < DCP_MAX_PLANES; i++) { + planes[i] = apple_plane_init(drm, 1U << num, supports_l10r, + DRM_PLANE_TYPE_OVERLAY); + if (IS_ERR(planes[i])) + return PTR_ERR(planes[i]); + immutable_zpos++; + ret = drm_plane_create_zpos_immutable_property(planes[i], immutable_zpos); + if (ret) { + return ret; + } + } + + /* + * Even though we have an overlay plane, we cannot expose it to legacy + * userspace for cursors as we cannot make the same guarantees as ye olde + * hardware cursor planes such userspace would expect us to. Modern userspace + * knows what to do with overlays. + */ + crtc = kzalloc(sizeof(*crtc), GFP_KERNEL); + ret = drm_crtc_init_with_planes(drm, &crtc->base, planes[0], NULL, + &apple_crtc_funcs, NULL); + if (ret) + return ret; + + drm_crtc_helper_add(&crtc->base, &apple_crtc_helper_funcs); + drm_crtc_enable_color_mgmt(&crtc->base, 0, true, 0); + + enc = drmm_simple_encoder_alloc(drm, struct apple_encoder, base, + DRM_MODE_ENCODER_TMDS); + if (IS_ERR(enc)) + return PTR_ERR(enc); + enc->base.possible_crtcs = drm_crtc_mask(&crtc->base); + + connector = kzalloc(sizeof(*connector), GFP_KERNEL); + mutex_init(&connector->chunk_lock); + drm_connector_helper_add(&connector->base, + &apple_connector_helper_funcs); + + // HACK: + if (dcp_ext) + connector->base.fwnode = fwnode_handle_get(dcp->dev.fwnode); + + ret = drm_connector_init(drm, &connector->base, &apple_connector_funcs, + dcp_get_connector_type(dcp)); + if (ret) + return ret; + + connector->base.polled = DRM_CONNECTOR_POLL_HPD; + connector->connected = false; + connector->dcp = dcp; + + INIT_WORK(&connector->hotplug_wq, dcp_hotplug); + + crtc->dcp = dcp; + dcp_link(dcp, crtc, connector); + + return drm_connector_attach_encoder(&connector->base, &enc->base); +} + +static int apple_get_fb_resource(struct device *dev, const char *name, + struct resource *fb_r) +{ + int idx, ret = -ENODEV; + struct device_node *node; + + idx = of_property_match_string(dev->of_node, "memory-region-names", name); + + node = of_parse_phandle(dev->of_node, "memory-region", idx); + if (!node) { + dev_err(dev, "reserved-memory node '%s' not found\n", name); + return -ENODEV; + } + + if (!of_device_is_available(node)) { + dev_err(dev, "reserved-memory node '%s' is unavailable\n", name); + goto err; + } + + if (!of_device_is_compatible(node, "framebuffer")) { + dev_err(dev, "reserved-memory node '%s' is incompatible\n", + node->full_name); + goto err; + } + + ret = of_address_to_resource(node, 0, fb_r); + +err: + of_node_put(node); + return ret; +} + +static const struct of_device_id apple_dcp_id_tbl[] = { + { .compatible = "apple,dcp" }, + { .compatible = "apple,dcpext" }, + {}, +}; + +static int apple_drm_init_dcp(struct device *dev) +{ + struct apple_drm_private *apple = dev_get_drvdata(dev); + struct platform_device *dcp[MAX_COPROCESSORS]; + struct device_node *np; + u64 timeout; + int i, ret, num_dcp = 0; + + for_each_matching_node(np, apple_dcp_id_tbl) { + bool dcp_ext; + if (!of_device_is_available(np)) { + of_node_put(np); + continue; + } + dcp_ext = of_device_is_compatible(np, "apple,dcpext") || + of_property_present(np, "phys"); + + dcp[num_dcp] = of_find_device_by_node(np); + of_node_put(np); + if (!dcp[num_dcp]) + continue; + + device_link_add(dev, &dcp[num_dcp]->dev, DL_FLAG_AUTOREMOVE_SUPPLIER); + + ret = apple_probe_per_dcp(dev, &apple->drm, dcp[num_dcp], + num_dcp, dcp_ext); + if (ret) + continue; + + ret = dcp_start(dcp[num_dcp]); + if (ret) + continue; + + num_dcp++; + } + + if (num_dcp < 1) + return -ENODEV; + + /* + * Starting DPTX might take some time. + */ + timeout = get_jiffies_64() + msecs_to_jiffies(3000); + + for (i = 0; i < num_dcp; ++i) { + u64 jiffies = get_jiffies_64(); + u64 wait = time_after_eq64(jiffies, timeout) ? + 0 : + timeout - jiffies; + ret = dcp_wait_ready(dcp[i], wait); + /* There is nothing we can do if a dcp/dcpext does not boot + * (successfully). Ignoring it should not do any harm now. + * Needs to reevaluated when adding dcpext support. + */ + if (ret) + dev_warn(dev, "DCP[%d] not ready: %d\n", i, ret); + } + /* HACK: Wait for dcp* to settle before a modeset */ + msleep(100); + + return 0; +} + +static int apple_drm_init(struct device *dev) +{ + struct apple_drm_private *apple; + struct resource fb_r; + resource_size_t fb_size; + int ret; + + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(42)); + if (ret) + return ret; + + ret = apple_get_fb_resource(dev, "framebuffer", &fb_r); + if (ret) + return ret; + + apple = devm_drm_dev_alloc(dev, &apple_drm_driver, + struct apple_drm_private, drm); + if (IS_ERR(apple)) + return PTR_ERR(apple); + + dev_set_drvdata(dev, apple); + + ret = component_bind_all(dev, apple); + if (ret) + return ret; + + ret = drmm_mode_config_init(&apple->drm); + if (ret) + goto err_unbind; + + /* + * IOMFB::UPPipeDCP_H13P::verify_surfaces produces the error "plane + * requires a minimum of 32x32 for the source buffer" if smaller + */ + apple->drm.mode_config.min_width = 32; + apple->drm.mode_config.min_height = 32; + + /* + * TODO: this is the max framebuffer size not the maximal supported + * output resolution. DCP reports the maximal framebuffer size take it + * from there. + * Hardcode it for now to the M1 Max DCP reported 'MaxSrcBufferWidth' + * and 'MaxSrcBufferHeight' of 16384. + */ + apple->drm.mode_config.max_width = 16384; + apple->drm.mode_config.max_height = 16384; + + apple->drm.mode_config.funcs = &apple_mode_config_funcs; + apple->drm.mode_config.helper_private = &apple_mode_config_helpers; + + ret = apple_drm_init_dcp(dev); + if (ret) + goto err_unbind; + + drm_mode_config_reset(&apple->drm); + + fb_size = fb_r.end - fb_r.start + 1; + ret = aperture_remove_conflicting_devices(fb_r.start, fb_size, + apple_drm_driver.name); + if (ret) { + dev_err(dev, "Failed remove fb: %d\n", ret); + goto err_unbind; + } + + ret = drm_dev_register(&apple->drm, 0); + if (ret) + goto err_unbind; + + drm_client_setup_with_fourcc(&apple->drm, DRM_FORMAT_XRGB8888); + + return 0; + +err_unbind: + component_unbind_all(dev, NULL); + return ret; +} + +static void apple_drm_uninit(struct device *dev) +{ + struct apple_drm_private *apple = dev_get_drvdata(dev); + + drm_dev_unregister(&apple->drm); + drm_atomic_helper_shutdown(&apple->drm); + + component_unbind_all(dev, NULL); + + dev_set_drvdata(dev, NULL); +} + +static int apple_drm_bind(struct device *dev) +{ + return apple_drm_init(dev); +} + +static void apple_drm_unbind(struct device *dev) +{ + apple_drm_uninit(dev); +} + +const struct component_master_ops apple_drm_ops = { + .bind = apple_drm_bind, + .unbind = apple_drm_unbind, +}; + +static int add_dcp_components(struct device *dev, + struct component_match **matchptr) +{ + struct device_node *np, *endpoint, *port; + int num = 0; + + for_each_matching_node(np, apple_dcp_id_tbl) { + if (of_device_is_available(np)) { + drm_of_component_match_add(dev, matchptr, + component_compare_of, np); + num++; + for_each_endpoint_of_node(np, endpoint) { + port = of_graph_get_remote_port_parent(endpoint); + if (!port) + continue; + +#if !IS_ENABLED(CONFIG_DRM_APPLE_AUDIO) + if (of_device_is_compatible(port, "apple,dpaudio")) { + of_node_put(port); + continue; + } +#endif + + /* + * The ATC phy driver is not part of the component + * collection for the Apple display-subsystem so + * ignore it here. + */ + if (of_device_is_compatible(port, "apple,t8103-atcphy")) { + of_node_put(port); + continue; + } + + if (of_device_is_available(port)) + drm_of_component_match_add(dev, matchptr, + component_compare_of, + port); + of_node_put(port); + } + } + of_node_put(np); + } + + return num; +} + +static int apple_platform_probe(struct platform_device *pdev) +{ + struct device *mdev = &pdev->dev; + struct component_match *match = NULL; + int num_dcp; + + /* add DCP components, handle less than 1 as probe error */ + num_dcp = add_dcp_components(mdev, &match); + if (num_dcp < 1) + return -ENODEV; + + return component_master_add_with_match(mdev, &apple_drm_ops, match); +} + +static void apple_platform_remove(struct platform_device *pdev) +{ + component_master_del(&pdev->dev, &apple_drm_ops); +} + +static const struct of_device_id of_match[] = { + { .compatible = "apple,display-subsystem" }, + {} +}; +MODULE_DEVICE_TABLE(of, of_match); + +#ifdef CONFIG_PM_SLEEP +static int apple_platform_suspend(struct device *dev) +{ + struct apple_drm_private *apple = dev_get_drvdata(dev); + + if (apple) + return drm_mode_config_helper_suspend(&apple->drm); + + return 0; +} + +static int apple_platform_resume(struct device *dev) +{ + struct apple_drm_private *apple = dev_get_drvdata(dev); + + if (apple) + drm_mode_config_helper_resume(&apple->drm); + + return 0; +} + +static const struct dev_pm_ops apple_platform_pm_ops = { + .suspend = apple_platform_suspend, + .resume = apple_platform_resume, +}; +#endif + +static struct platform_driver apple_platform_driver = { + .driver = { + .name = "apple-drm", + .of_match_table = of_match, +#ifdef CONFIG_PM_SLEEP + .pm = &apple_platform_pm_ops, +#endif + }, + .probe = apple_platform_probe, + .remove = apple_platform_remove, +}; + + + +static int __init appledrm_register(void) +{ + if (drm_firmware_drivers_only()) + return -ENODEV; + +#if IS_ENABLED(CONFIG_DRM_APPLE_AUDIO) + dcp_audio_register(); +#endif + dcp_register(); + platform_driver_register(&apple_platform_driver); + + return 0; +} + +static void __exit appledrm_unregister(void) +{ +#if IS_ENABLED(CONFIG_DRM_APPLE_AUDIO) + dcp_audio_unregister(); +#endif + dcp_unregister(); + platform_driver_unregister(&apple_platform_driver); +} + +module_init(appledrm_register); +module_exit(appledrm_unregister); + +MODULE_AUTHOR("Alyssa Rosenzweig "); +MODULE_DESCRIPTION(DRIVER_DESC); +MODULE_LICENSE("Dual MIT/GPL"); diff --git a/drivers/gpu/drm/apple/audio.c b/drivers/gpu/drm/apple/audio.c new file mode 100644 index 00000000000000..38718e2f56117b --- /dev/null +++ b/drivers/gpu/drm/apple/audio.c @@ -0,0 +1,776 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * DCP Audio Bits + * + * Copyright (C) The Asahi Linux Contributors + * + * TODO: + * - figure some nice identification of the sound card (in case + * there's many DCP instances) + */ + +#define DEBUG + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "av.h" +#include "dcp.h" +#include "audio.h" +#include "parser.h" + +#define DCPAUD_ELEMENTS_MAXSIZE 16384 +#define DCPAUD_PRODUCTATTRS_MAXSIZE 1024 + +struct dcp_audio { + struct device *dev; + struct device *dcp_dev; + struct device *dma_dev; + struct device_link *dma_link; + struct dma_chan *chan; + struct snd_card *card; + struct snd_jack *jack; + struct snd_pcm_substream *substream; + unsigned int open_cookie; + + struct mutex data_lock; + bool dcp_connected; /// dcp status keep for delayed initialization + bool connected; + unsigned int connection_cookie; + + struct snd_pcm_chmap_elem selected_chmap; + struct dcp_sound_cookie selected_cookie; + void *elements; + void *productattrs; + + struct snd_pcm_chmap *chmap_info; +}; + +static const struct snd_pcm_hardware dcp_pcm_hw = { + .info = SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_MMAP_VALID | + SNDRV_PCM_INFO_INTERLEAVED, + .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_LE | + SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S32_LE, + .rates = SNDRV_PCM_RATE_CONTINUOUS, + .rate_min = 0, + .rate_max = UINT_MAX, + .channels_min = 1, + .channels_max = 16, + .buffer_bytes_max = SIZE_MAX, + .period_bytes_min = 4096, /* TODO */ + .period_bytes_max = SIZE_MAX, + .periods_min = 2, + .periods_max = UINT_MAX, +}; + +static int dcpaud_read_remote_info(struct dcp_audio *dcpaud) +{ + int ret; + + ret = dcp_audiosrv_get_elements(dcpaud->dcp_dev, dcpaud->elements, + DCPAUD_ELEMENTS_MAXSIZE); + if (ret < 0) + return ret; + + ret = dcp_audiosrv_get_product_attrs(dcpaud->dcp_dev, dcpaud->productattrs, + DCPAUD_PRODUCTATTRS_MAXSIZE); + if (ret < 0) + return ret; + + return 0; +} + +static int dcpaud_interval_bitmask(struct snd_interval *i, + unsigned int mask) +{ + struct snd_interval range; + if (!mask) + return -EINVAL; + + snd_interval_any(&range); + range.min = __ffs(mask); + range.max = __fls(mask); + return snd_interval_refine(i, &range); +} + +extern const struct snd_pcm_hw_constraint_list snd_pcm_known_rates; + +static void dcpaud_fill_fmt_sieve(struct snd_pcm_hw_params *params, + struct dcp_sound_format_mask *sieve) +{ + struct snd_interval *c = hw_param_interval(params, + SNDRV_PCM_HW_PARAM_CHANNELS); + struct snd_interval *r = hw_param_interval(params, + SNDRV_PCM_HW_PARAM_RATE); + struct snd_mask *f = hw_param_mask(params, + SNDRV_PCM_HW_PARAM_FORMAT); + int i; + + sieve->nchans = GENMASK(c->max, c->min); + sieve->formats = f->bits[0] | ((u64) f->bits[1]) << 32; /* TODO: don't open-code */ + + for (i = 0; i < snd_pcm_known_rates.count; i++) { + unsigned int rate = snd_pcm_known_rates.list[i]; + + if (snd_interval_test(r, rate)) + sieve->rates |= 1u << i; + } +} + +static void dcpaud_consult_elements(struct dcp_audio *dcpaud, + struct snd_pcm_hw_params *params, + struct dcp_sound_format_mask *hits) +{ + struct dcp_sound_format_mask sieve; + struct dcp_parse_ctx elements = { + .dcp = dev_get_drvdata(dcpaud->dcp_dev), + .blob = dcpaud->elements + 4, + .len = DCPAUD_ELEMENTS_MAXSIZE - 4, + .pos = 0, + }; + + dcpaud_fill_fmt_sieve(params, &sieve); + dev_dbg(dcpaud->dev, "elements in: %llx %x %x\n", sieve.formats, sieve.nchans, sieve.rates); + parse_sound_constraints(&elements, &sieve, hits); + dev_dbg(dcpaud->dev, "elements out: %llx %x %x\n", hits->formats, hits->nchans, hits->rates); +} + +static int dcpaud_select_cookie(struct dcp_audio *dcpaud, + struct snd_pcm_hw_params *params) +{ + struct dcp_sound_format_mask sieve; + struct dcp_parse_ctx elements = { + .dcp = dev_get_drvdata(dcpaud->dcp_dev), + .blob = dcpaud->elements + 4, + .len = DCPAUD_ELEMENTS_MAXSIZE - 4, + .pos = 0, + }; + + dcpaud_fill_fmt_sieve(params, &sieve); + return parse_sound_mode(&elements, &sieve, &dcpaud->selected_chmap, + &dcpaud->selected_cookie); +} + +static int dcpaud_rule_channels(struct snd_pcm_hw_params *params, + struct snd_pcm_hw_rule *rule) +{ + struct dcp_audio *dcpaud = rule->private; + struct snd_interval *c = hw_param_interval(params, + SNDRV_PCM_HW_PARAM_CHANNELS); + struct dcp_sound_format_mask hits = {0, 0, 0}; + + dcpaud_consult_elements(dcpaud, params, &hits); + + return dcpaud_interval_bitmask(c, hits.nchans); +} + +static int dcpaud_refine_fmt_mask(struct snd_mask *m, u64 mask) +{ + struct snd_mask mask_mask; + + if (!mask) + return -EINVAL; + mask_mask.bits[0] = mask; + mask_mask.bits[1] = mask >> 32; + + return snd_mask_refine(m, &mask_mask); +} + +static int dcpaud_rule_format(struct snd_pcm_hw_params *params, + struct snd_pcm_hw_rule *rule) +{ + struct dcp_audio *dcpaud = rule->private; + struct snd_mask *f = hw_param_mask(params, + SNDRV_PCM_HW_PARAM_FORMAT); + struct dcp_sound_format_mask hits; + + dcpaud_consult_elements(dcpaud, params, &hits); + + return dcpaud_refine_fmt_mask(f, hits.formats); +} + +static int dcpaud_rule_rate(struct snd_pcm_hw_params *params, + struct snd_pcm_hw_rule *rule) +{ + struct dcp_audio *dcpaud = rule->private; + struct snd_interval *r = hw_param_interval(params, + SNDRV_PCM_HW_PARAM_RATE); + struct dcp_sound_format_mask hits; + + dcpaud_consult_elements(dcpaud, params, &hits); + + return snd_interval_rate_bits(r, hits.rates); +} + +static int dcpaud_init_dma(struct dcp_audio *dcpaud) +{ + struct dma_chan *chan; + if (dcpaud->chan) + return 0; + + chan = of_dma_request_slave_channel(dcpaud->dev->of_node, "tx"); + /* squelch dma channel request errors, the driver will try again alter */ + if (!chan) { + dev_warn(dcpaud->dev, "audio TX DMA channel request failed\n"); + return -ENXIO; + } else if (chan == ERR_PTR(-EPROBE_DEFER)) { + dev_info(dcpaud->dev, "audio TX DMA channel is not ready yet\n"); + return -ENXIO; + } else if (IS_ERR(chan)) { + dev_warn(dcpaud->dev, "audio TX DMA channel request failed: %ld\n", PTR_ERR(chan)); + return PTR_ERR(chan); + } + dcpaud->chan = chan; + + snd_pcm_set_managed_buffer(dcpaud->substream, SNDRV_DMA_TYPE_DEV_IRAM, + dcpaud->chan->device->dev, 1024 * 1024, + SIZE_MAX); + + return 0; +} + +static int dcp_pcm_open(struct snd_pcm_substream *substream) +{ + struct dcp_audio *dcpaud = substream->pcm->private_data; + struct snd_dmaengine_dai_dma_data dma_data = { + .flags = SND_DMAENGINE_PCM_DAI_FLAG_PACK, + }; + struct snd_pcm_hardware hw; + int ret; + + mutex_lock(&dcpaud->data_lock); + ret = dcpaud_init_dma(dcpaud); + if (ret < 0) + return ret; + + if (!dcpaud->connected) { + mutex_unlock(&dcpaud->data_lock); + return -ENXIO; + } + dcpaud->open_cookie = dcpaud->connection_cookie; + mutex_unlock(&dcpaud->data_lock); + + ret = dcpaud_read_remote_info(dcpaud); + if (ret < 0) + return ret; + + snd_pcm_hw_rule_add(substream->runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT, + dcpaud_rule_format, dcpaud, + SNDRV_PCM_HW_PARAM_CHANNELS, SNDRV_PCM_HW_PARAM_RATE, -1); + snd_pcm_hw_rule_add(substream->runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS, + dcpaud_rule_channels, dcpaud, + SNDRV_PCM_HW_PARAM_FORMAT, SNDRV_PCM_HW_PARAM_RATE, -1); + snd_pcm_hw_rule_add(substream->runtime, 0, SNDRV_PCM_HW_PARAM_RATE, + dcpaud_rule_rate, dcpaud, + SNDRV_PCM_HW_PARAM_FORMAT, SNDRV_PCM_HW_PARAM_CHANNELS, -1); + + hw = dcp_pcm_hw; + hw.info = SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_MMAP_VALID | + SNDRV_PCM_INFO_INTERLEAVED; + hw.periods_min = 2; + hw.periods_max = UINT_MAX; + hw.period_bytes_min = 256; + hw.period_bytes_max = SIZE_MAX; // TODO dma_get_max_seg_size(dma_dev); + hw.buffer_bytes_max = SIZE_MAX; + hw.fifo_size = 16; + ret = snd_dmaengine_pcm_refine_runtime_hwparams(substream, &dma_data, + &hw, dcpaud->chan); + if (ret) + return ret; + substream->runtime->hw = hw; + + return snd_dmaengine_pcm_open(substream, dcpaud->chan); +} + +static int dcp_pcm_close(struct snd_pcm_substream *substream) +{ + struct dcp_audio *dcpaud = substream->pcm->private_data; + dcpaud->selected_chmap.channels = 0; + + return snd_dmaengine_pcm_close(substream); +} + +static int dcpaud_connection_up(struct dcp_audio *dcpaud) +{ + bool ret; + mutex_lock(&dcpaud->data_lock); + ret = dcpaud->connected && + dcpaud->open_cookie == dcpaud->connection_cookie; + mutex_unlock(&dcpaud->data_lock); + return ret; +} + +static int dcp_pcm_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params) +{ + struct dcp_audio *dcpaud = substream->pcm->private_data; + struct dma_slave_config slave_config; + struct dma_chan *chan = snd_dmaengine_pcm_get_chan(substream); + int ret; + + if (!dcpaud_connection_up(dcpaud)) + return -ENXIO; + + ret = dcpaud_select_cookie(dcpaud, params); + if (ret < 0) + return ret; + if (!ret) + return -EINVAL; + + memset(&slave_config, 0, sizeof(slave_config)); + ret = snd_hwparams_to_dma_slave_config(substream, params, &slave_config); + dev_info(dcpaud->dev, "snd_hwparams_to_dma_slave_config: %d\n", ret); + if (ret < 0) + return ret; + + slave_config.direction = DMA_MEM_TO_DEV; + /* + * The data entry from the DMA controller to the DPA peripheral + * is 32-bit wide no matter the actual sample size. + */ + slave_config.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; + + ret = dmaengine_slave_config(chan, &slave_config); + dev_info(dcpaud->dev, "dmaengine_slave_config: %d\n", ret); + return ret; +} + +static int dcp_pcm_hw_free(struct snd_pcm_substream *substream) +{ + struct dcp_audio *dcpaud = substream->pcm->private_data; + + if (!dcpaud_connection_up(dcpaud)) + return 0; + + return dcp_audiosrv_unprepare(dcpaud->dcp_dev); +} + +static int dcp_pcm_prepare(struct snd_pcm_substream *substream) +{ + struct dcp_audio *dcpaud = substream->pcm->private_data; + + if (!dcpaud_connection_up(dcpaud)) + return -ENXIO; + + return dcp_audiosrv_prepare(dcpaud->dcp_dev, + &dcpaud->selected_cookie); +} + +static int dcp_pcm_trigger(struct snd_pcm_substream *substream, int cmd) +{ + struct dcp_audio *dcpaud = substream->pcm->private_data; + int ret; + + switch (cmd) { + case SNDRV_PCM_TRIGGER_START: + case SNDRV_PCM_TRIGGER_RESUME: + if (!dcpaud_connection_up(dcpaud)) + return -ENXIO; + + WARN_ON(pm_runtime_get_sync(dcpaud->dev) < 0); + ret = dcp_audiosrv_startlink(dcpaud->dcp_dev, + &dcpaud->selected_cookie); + if (ret < 0) + return ret; + break; + + case SNDRV_PCM_TRIGGER_STOP: + case SNDRV_PCM_TRIGGER_SUSPEND: + break; + + default: + return -EINVAL; + } + + ret = snd_dmaengine_pcm_trigger(substream, cmd); + if (ret < 0) + return ret; + + switch (cmd) { + case SNDRV_PCM_TRIGGER_START: + case SNDRV_PCM_TRIGGER_RESUME: + break; + + case SNDRV_PCM_TRIGGER_STOP: + case SNDRV_PCM_TRIGGER_SUSPEND: + ret = dcp_audiosrv_stoplink(dcpaud->dcp_dev); + pm_runtime_mark_last_busy(dcpaud->dev); + __pm_runtime_put_autosuspend(dcpaud->dev); + if (ret < 0) + return ret; + break; + } + + return 0; +} + +struct snd_pcm_ops dcp_playback_ops = { + .open = dcp_pcm_open, + .close = dcp_pcm_close, + .hw_params = dcp_pcm_hw_params, + .hw_free = dcp_pcm_hw_free, + .prepare = dcp_pcm_prepare, + .trigger = dcp_pcm_trigger, + .pointer = snd_dmaengine_pcm_pointer, +}; + +// Transitional workaround: for the chmap control TLV, advertise options +// copied from hdmi-codec.c +#include "hdmi-codec-chmap.h" + +static int dcpaud_chmap_ctl_get(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_pcm_chmap *info = snd_kcontrol_chip(kcontrol); + struct dcp_audio *dcpaud = info->private_data; + unsigned int i; + + for (i = 0; i < info->max_channels; i++) + ucontrol->value.integer.value[i] = \ + (i < dcpaud->selected_chmap.channels) ? + dcpaud->selected_chmap.map[i] : SNDRV_CHMAP_UNKNOWN; + + return 0; +} + + +static int dcpaud_create_chmap_ctl(struct dcp_audio *dcpaud) +{ + struct snd_pcm *pcm = dcpaud->substream->pcm; + struct snd_pcm_chmap *chmap_info; + int ret; + + ret = snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK, NULL, + dcp_pcm_hw.channels_max, 0, &chmap_info); + if (ret < 0) + return ret; + + chmap_info->kctl->get = dcpaud_chmap_ctl_get; + chmap_info->chmap = hdmi_codec_8ch_chmaps; + chmap_info->private_data = dcpaud; + + return 0; +} + +static int dcpaud_create_pcm(struct dcp_audio *dcpaud) +{ + struct snd_card *card = dcpaud->card; + struct snd_pcm *pcm; + int ret; + +#define NUM_PLAYBACK 1 +#define NUM_CAPTURE 0 + + ret = snd_pcm_new(card, card->shortname, 0, NUM_PLAYBACK, NUM_CAPTURE, &pcm); + if (ret) + return ret; + + snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &dcp_playback_ops); + dcpaud->substream = pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream; + pcm->nonatomic = true; + pcm->private_data = dcpaud; + strscpy(pcm->name, card->shortname, sizeof(pcm->name)); + + return 0; +} + +/* expects to be called with data_lock locked and unlocks it */ +static void dcpaud_report_hotplug(struct dcp_audio *dcpaud, bool connected) +{ + struct snd_pcm_substream *substream = dcpaud->substream; + + if (!dcpaud->card || dcpaud->connected == connected) { + mutex_unlock(&dcpaud->data_lock); + return; + } + + dcpaud->connected = connected; + if (connected) + dcpaud->connection_cookie++; + mutex_unlock(&dcpaud->data_lock); + + snd_jack_report(dcpaud->jack, connected ? SND_JACK_AVOUT : 0); + + if (!connected) { + snd_pcm_stream_lock(substream); + if (substream->runtime) + snd_pcm_stop(substream, SNDRV_PCM_STATE_DISCONNECTED); + snd_pcm_stream_unlock(substream); + } +} + +static int dcpaud_create_jack(struct dcp_audio *dcpaud) +{ + struct snd_card *card = dcpaud->card; + + return snd_jack_new(card, "HDMI/DP", SND_JACK_AVOUT, + &dcpaud->jack, true, false); +} + +static void dcpaud_set_card_names(struct dcp_audio *dcpaud) +{ + struct snd_card *card = dcpaud->card; + + strscpy(card->driver, "apple_dcp", sizeof(card->driver)); + strscpy(card->longname, "Apple DisplayPort", sizeof(card->longname)); + strscpy(card->shortname, "Apple DisplayPort", sizeof(card->shortname)); +} + +#ifdef CONFIG_SND_DEBUG +static void dcpaud_expose_debugfs_blob(struct dcp_audio *dcpaud, const char *name, void *base, size_t size) +{ + struct debugfs_blob_wrapper *wrapper; + wrapper = devm_kzalloc(dcpaud->dev, sizeof(*wrapper), GFP_KERNEL); + if (!wrapper) + return; + wrapper->data = base; + wrapper->size = size; + debugfs_create_blob(name, 0600, dcpaud->card->debugfs_root, wrapper); +} +#else +static void dcpaud_expose_debugfs_blob(struct dcp_audio *dcpaud, const char *name, void *base, size_t size) {} +#endif + +extern bool hdmi_audio; + +static int dcpaud_init_snd_card(struct dcp_audio *dcpaud) +{ + int ret; + if (!hdmi_audio) + return -ENODEV; + + + ret = snd_card_new(dcpaud->dev, SNDRV_DEFAULT_IDX1, SNDRV_DEFAULT_STR1, + THIS_MODULE, 0, &dcpaud->card); + if (ret) + return ret; + + dcpaud_set_card_names(dcpaud); + + ret = dcpaud_create_pcm(dcpaud); + if (ret) + goto err_free_card; + + ret = dcpaud_create_chmap_ctl(dcpaud); + if (ret) + goto err_free_card; + + ret = dcpaud_create_jack(dcpaud); + if (ret) + goto err_free_card; + + ret = snd_card_register(dcpaud->card); + if (ret) + goto err_free_card; + + return 0; +err_free_card: + dev_warn(dcpaud->dev, "Failed to initialize sound card: %d\n", ret); + snd_card_free(dcpaud->card); + dcpaud->card = NULL; + return ret; +} + +void dcpaud_connect(struct platform_device *pdev, bool connected) +{ + struct dcp_audio *dcpaud = platform_get_drvdata(pdev); + + mutex_lock(&dcpaud->data_lock); + + dcpaud_report_hotplug(dcpaud, connected); +} + +void dcpaud_disconnect(struct platform_device *pdev) +{ + struct dcp_audio *dcpaud = platform_get_drvdata(pdev); + + mutex_lock(&dcpaud->data_lock); + + dcpaud_report_hotplug(dcpaud, false); +} + +static int dcpaud_comp_bind(struct device *dev, struct device *main, void *data) +{ + struct dcp_audio *dcpaud = dev_get_drvdata(dev); + struct device_node *endpoint, *dcp_node = NULL; + struct platform_device *dcp_pdev, *dma_pdev; + struct of_phandle_args dma_spec; + int index; + int ret; + + pm_runtime_get_noresume(dev); + pm_runtime_set_active(dev); + + ret = devm_pm_runtime_enable(dev); + if (ret) + return dev_err_probe(dev, ret, "Failed to enable runtime PM: %d\n", ret); + + /* find linked DCP instance */ + endpoint = of_graph_get_endpoint_by_regs(dev->of_node, 0, 0); + if (endpoint) { + dcp_node = of_graph_get_remote_port_parent(endpoint); + of_node_put(endpoint); + } + if (!dcp_node || !of_device_is_available(dcp_node)) { + of_node_put(dcp_node); + dev_info(dev, "No audio support\n"); + goto rpm_put; + } + + index = of_property_match_string(dev->of_node, "dma-names", "tx"); + if (index < 0) { + dev_err(dev, "No dma-names property\n"); + goto rpm_put; + } + + if (of_parse_phandle_with_args(dev->of_node, "dmas", "#dma-cells", index, + &dma_spec) || !dma_spec.np) { + dev_err(dev, "Failed to parse dmas property\n"); + goto rpm_put; + } + + dcp_pdev = of_find_device_by_node(dcp_node); + of_node_put(dcp_node); + if (!dcp_pdev) { + dev_info(dev, "No DP/HDMI audio device, dcp not ready\n"); + goto rpm_put; + } + dcpaud->dcp_dev = &dcp_pdev->dev; + + dma_pdev = of_find_device_by_node(dma_spec.np); + of_node_put(dma_spec.np); + if (!dma_pdev) { + dev_info(dev, "No DMA device\n"); + goto rpm_put; + } + dcpaud->dma_dev = &dma_pdev->dev; + + dcpaud->dma_link = device_link_add(dev, dcpaud->dma_dev, + DL_FLAG_PM_RUNTIME | + DL_FLAG_RPM_ACTIVE | + DL_FLAG_STATELESS); + + /* ignore errors to prevent audio issues affecting the display side */ + ret = dcpaud_init_snd_card(dcpaud); + + if (!ret) { + dcpaud_expose_debugfs_blob(dcpaud, "selected_cookie", &dcpaud->selected_cookie, + sizeof(dcpaud->selected_cookie)); + dcpaud_expose_debugfs_blob(dcpaud, "elements", dcpaud->elements, + DCPAUD_ELEMENTS_MAXSIZE); + dcpaud_expose_debugfs_blob(dcpaud, "product_attrs", dcpaud->productattrs, + DCPAUD_PRODUCTATTRS_MAXSIZE); + } + +rpm_put: + pm_runtime_put(dev); + + return 0; +} + +static void dcpaud_comp_unbind(struct device *dev, struct device *main, + void *data) +{ + struct dcp_audio *dcpaud = dev_get_drvdata(dev); + + /* snd_card_free_when_closed() checks for NULL */ + snd_card_free_when_closed(dcpaud->card); + + if (dcpaud->dma_link) + device_link_del(dcpaud->dma_link); +} + +static const struct component_ops dcpaud_comp_ops = { + .bind = dcpaud_comp_bind, + .unbind = dcpaud_comp_unbind, +}; + +static int dcpaud_probe(struct platform_device *pdev) +{ + struct dcp_audio *dcpaud; + + dcpaud = devm_kzalloc(&pdev->dev, sizeof(*dcpaud), GFP_KERNEL); + if (!dcpaud) + return -ENOMEM; + + dcpaud->elements = devm_kzalloc(&pdev->dev, DCPAUD_ELEMENTS_MAXSIZE, + GFP_KERNEL); + if (!dcpaud->elements) + return -ENOMEM; + + dcpaud->productattrs = devm_kzalloc(&pdev->dev, DCPAUD_PRODUCTATTRS_MAXSIZE, + GFP_KERNEL); + if (!dcpaud->productattrs) + return -ENOMEM; + + dcpaud->dev = &pdev->dev; + mutex_init(&dcpaud->data_lock); + platform_set_drvdata(pdev, dcpaud); + + return component_add(&pdev->dev, &dcpaud_comp_ops); +} + +static void dcpaud_remove(struct platform_device *pdev) +{ + component_del(&pdev->dev, &dcpaud_comp_ops); +} + +static void dcpaud_shutdown(struct platform_device *pdev) +{ + component_del(&pdev->dev, &dcpaud_comp_ops); +} + +static __maybe_unused int dcpaud_suspend(struct device *dev) +{ + /* + * Using snd_power_change_state() does not work since the sound card + * is what resumes runtime PM. + */ + + return 0; +} + +static __maybe_unused int dcpaud_resume(struct device *dev) +{ + return 0; +} + +static DEFINE_RUNTIME_DEV_PM_OPS(dcpaud_pm_ops, dcpaud_suspend, dcpaud_resume, NULL); + +static const struct of_device_id dcpaud_of_match[] = { + { .compatible = "apple,dpaudio" }, + {} +}; + +static struct platform_driver dcpaud_driver = { + .driver = { + .name = "dcp-dp-audio", + .of_match_table = dcpaud_of_match, + .pm = pm_ptr(&dcpaud_pm_ops), + }, + .probe = dcpaud_probe, + .remove = dcpaud_remove, + .shutdown = dcpaud_shutdown, +}; + +void __init dcp_audio_register(void) +{ + platform_driver_register(&dcpaud_driver); +} + +void __exit dcp_audio_unregister(void) +{ + platform_driver_unregister(&dcpaud_driver); +} + diff --git a/drivers/gpu/drm/apple/audio.h b/drivers/gpu/drm/apple/audio.h new file mode 100644 index 00000000000000..83b990dc6c343f --- /dev/null +++ b/drivers/gpu/drm/apple/audio.h @@ -0,0 +1,20 @@ +#ifndef __AUDIO_H__ +#define __AUDIO_H__ + +#include + +struct device; +struct platform_device; +struct dcp_sound_cookie; + +int dcp_audiosrv_prepare(struct device *dev, struct dcp_sound_cookie *cookie); +int dcp_audiosrv_startlink(struct device *dev, struct dcp_sound_cookie *cookie); +int dcp_audiosrv_stoplink(struct device *dev); +int dcp_audiosrv_unprepare(struct device *dev); +int dcp_audiosrv_get_elements(struct device *dev, void *elements, size_t maxsize); +int dcp_audiosrv_get_product_attrs(struct device *dev, void *attrs, size_t maxsize); + +void dcpaud_connect(struct platform_device *pdev, bool connected); +void dcpaud_disconnect(struct platform_device *pdev); + +#endif /* __AUDIO_H__ */ diff --git a/drivers/gpu/drm/apple/av.c b/drivers/gpu/drm/apple/av.c new file mode 100644 index 00000000000000..0d3c752f62d5f5 --- /dev/null +++ b/drivers/gpu/drm/apple/av.c @@ -0,0 +1,433 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2023 Martin Povišer */ + +// #define DEBUG + +#include +#include +#include +#include +#include +#include +#include + +#include "audio.h" +#include "afk.h" +#include "av.h" +#include "dcp.h" +#include "dcp-internal.h" + +struct dcp_av_audio_cmds { + /* commands in group 0*/ + u32 open; + u32 close; + u32 prepare; + u32 start_link; + u32 stop_link; + u32 unprepare; + /* commands in group 1*/ + u32 get_elements; + u32 get_product_attrs; +}; + +static const struct dcp_av_audio_cmds dcp_av_audio_cmds_v12_3 = { + .open = 6, + .close = 7, + .prepare = 8, + .start_link = 9, + .stop_link = 12, + .unprepare = 13, + .get_elements = 18, + .get_product_attrs = 20, +}; + +static const struct dcp_av_audio_cmds dcp_av_audio_cmds_v13_5 = { + .open = 4, + .close = 5, + .prepare = 6, + .start_link = 7, + .stop_link = 10, + .unprepare = 11, + .get_elements = 16, + .get_product_attrs = 18, +}; + +struct audiosrv_data { + struct platform_device *audio_dev; + bool plugged; + struct mutex plug_lock; + + struct apple_epic_service *srv; + struct rw_semaphore srv_rwsem; + /* Workqueue for starting the audio service */ + struct work_struct start_av_service_wq; + + struct dcp_av_audio_cmds cmds; + + bool warned_get_elements; + bool warned_get_product_attrs; + bool is_open; +}; + +static void av_interface_init(struct apple_epic_service *service, const char *name, + const char *class, s64 unit) +{ +} + +static void av_interface_teardown(struct apple_epic_service *service) +{ + struct apple_dcp *dcp = service->ep->dcp; + struct audiosrv_data *asrv = dcp->audiosrv; + + service->enabled = false; + + mutex_lock(&asrv->plug_lock); + + asrv->plugged = false; + if (asrv->audio_dev) + dcpaud_disconnect(asrv->audio_dev); + + mutex_unlock(&asrv->plug_lock); +} + +static void av_audiosrv_init(struct apple_epic_service *service, const char *name, + const char *class, s64 unit) +{ + struct apple_dcp *dcp = service->ep->dcp; + struct audiosrv_data *asrv = dcp->audiosrv; + + mutex_lock(&asrv->plug_lock); + + down_write(&asrv->srv_rwsem); + asrv->srv = service; + up_write(&asrv->srv_rwsem); + + asrv->plugged = true; + mutex_unlock(&asrv->plug_lock); + schedule_work(&asrv->start_av_service_wq); +} + +static void av_audiosrv_teardown(struct apple_epic_service *service) +{ + struct apple_dcp *dcp = service->ep->dcp; + struct audiosrv_data *asrv = dcp->audiosrv; + + mutex_lock(&asrv->plug_lock); + + down_write(&asrv->srv_rwsem); + asrv->srv = NULL; + up_write(&asrv->srv_rwsem); + + asrv->plugged = false; + if (asrv->audio_dev) + dcpaud_disconnect(asrv->audio_dev); + + mutex_unlock(&asrv->plug_lock); +} + +int dcp_audiosrv_prepare(struct device *dev, struct dcp_sound_cookie *cookie) +{ + struct apple_dcp *dcp = dev_get_drvdata(dev); + struct audiosrv_data *asrv = dcp->audiosrv; + int ret; + + down_write(&asrv->srv_rwsem); + ret = afk_service_call(asrv->srv, 0, asrv->cmds.prepare, cookie, + sizeof(*cookie), 64 - sizeof(*cookie), NULL, 0, + 64); + up_write(&asrv->srv_rwsem); + + return ret; +} + +int dcp_audiosrv_startlink(struct device *dev, struct dcp_sound_cookie *cookie) +{ + struct apple_dcp *dcp = dev_get_drvdata(dev); + struct audiosrv_data *asrv = dcp->audiosrv; + int ret; + + down_write(&asrv->srv_rwsem); + ret = afk_service_call(asrv->srv, 0, asrv->cmds.start_link, cookie, + sizeof(*cookie), 64 - sizeof(*cookie), NULL, 0, + 64); + up_write(&asrv->srv_rwsem); + + return ret; +} + +int dcp_audiosrv_stoplink(struct device *dev) +{ + struct apple_dcp *dcp = dev_get_drvdata(dev); + struct audiosrv_data *asrv = dcp->audiosrv; + int ret; + + down_write(&asrv->srv_rwsem); + ret = afk_service_call(asrv->srv, 0, asrv->cmds.stop_link, NULL, 0, 64, + NULL, 0, 64); + up_write(&asrv->srv_rwsem); + + return ret; +} + +int dcp_audiosrv_unprepare(struct device *dev) +{ + struct apple_dcp *dcp = dev_get_drvdata(dev); + struct audiosrv_data *asrv = dcp->audiosrv; + int ret; + + down_write(&asrv->srv_rwsem); + ret = afk_service_call(asrv->srv, 0, asrv->cmds.unprepare, NULL, 0, 64, + NULL, 0, 64); + up_write(&asrv->srv_rwsem); + + return ret; +} + +static int +dcp_audiosrv_osobject_call(struct apple_epic_service *service, u16 group, + u32 command, void *output, size_t output_maxsize, + size_t *output_size) +{ + struct { + __le64 max_size; + u8 _pad1[24]; + __le64 used_size; + u8 _pad2[8]; + } __attribute__((packed)) *hdr; + static_assert(sizeof(*hdr) == 48); + size_t bfr_len = output_maxsize + sizeof(*hdr); + void *bfr; + int ret; + + bfr = kzalloc(bfr_len, GFP_KERNEL); + if (!bfr) + return -ENOMEM; + + hdr = bfr; + hdr->max_size = cpu_to_le64(output_maxsize); + ret = afk_service_call(service, group, command, hdr, sizeof(*hdr), output_maxsize, + bfr, sizeof(*hdr) + output_maxsize, 0); + if (ret) + return ret; + + if (output) + memcpy(output, bfr + sizeof(*hdr), output_maxsize); + + if (output_size) + *output_size = le64_to_cpu(hdr->used_size); + + return 0; +} + +int dcp_audiosrv_get_elements(struct device *dev, void *elements, size_t maxsize) +{ + struct apple_dcp *dcp = dev_get_drvdata(dev); + struct audiosrv_data *asrv = dcp->audiosrv; + size_t size; + int ret; + + down_write(&asrv->srv_rwsem); + ret = dcp_audiosrv_osobject_call(asrv->srv, 1, asrv->cmds.get_elements, + elements, maxsize, &size); + up_write(&asrv->srv_rwsem); + + if (ret && asrv->warned_get_elements) { + dev_err(dev, "audiosrv: error getting elements: %d\n", ret); + asrv->warned_get_elements = true; + } else { + dev_dbg(dev, "audiosrv: got %zd bytes worth of elements\n", size); + } + + return ret; +} + +int dcp_audiosrv_get_product_attrs(struct device *dev, void *attrs, size_t maxsize) +{ + struct apple_dcp *dcp = dev_get_drvdata(dev); + struct audiosrv_data *asrv = dcp->audiosrv; + size_t size; + int ret; + + down_write(&asrv->srv_rwsem); + ret = dcp_audiosrv_osobject_call(asrv->srv, 1, + asrv->cmds.get_product_attrs, attrs, + maxsize, &size); + up_write(&asrv->srv_rwsem); + + if (ret && asrv->warned_get_product_attrs) { + dev_err(dev, "audiosrv: error getting product attributes: %d\n", ret); + asrv->warned_get_product_attrs = true; + } else { + dev_dbg(dev, "audiosrv: got %zd bytes worth of product attributes\n", size); + } + + return ret; +} + +static int av_audiosrv_report(struct apple_epic_service *service, u32 idx, + const void *data, size_t data_size) +{ + dev_dbg(service->ep->dcp->dev, "got audio report %d size %zx\n", idx, data_size); +#ifdef DEBUG + print_hex_dump(KERN_DEBUG, "audio report: ", DUMP_PREFIX_NONE, 16, 1, data, data_size, true); +#endif + + return 0; +} + +static const struct apple_epic_service_ops avep_ops[] = { + { + .name = "DCPAVSimpleVideoInterface", + .init = av_interface_init, + .teardown = av_interface_teardown, + }, + { + .name = "DCPAVAudioInterface", + .init = av_audiosrv_init, + .report = av_audiosrv_report, + .teardown = av_audiosrv_teardown, + }, + {} +}; + +void av_service_connect(struct apple_dcp *dcp) +{ + struct apple_epic_service *service; + struct audiosrv_data *asrv = dcp->audiosrv; + int ret; + + scoped_guard(rwsem_write, &asrv->srv_rwsem) { + if (!asrv->srv) + return; + service = asrv->srv; + } + + /* open AV audio service */ + dev_info(dcp->dev, "%s: starting audio service, plugged:%d\n", __func__, asrv->plugged); + if (asrv->is_open) + return; + + ret = afk_service_call(service, 0, asrv->cmds.open, NULL, 0, 32, + NULL, 0, 32); + if (ret) { + dev_err(dcp->dev, "error opening audio service: %d\n", ret); + return; + } + mutex_lock(&asrv->plug_lock); + asrv->is_open = true; + + if (asrv->audio_dev) + dcpaud_connect(asrv->audio_dev, asrv->plugged); + mutex_unlock(&asrv->plug_lock); +} + +void av_service_disconnect(struct apple_dcp *dcp) +{ + struct apple_epic_service *service; + struct audiosrv_data *asrv = dcp->audiosrv; + int ret; + + scoped_guard(rwsem_write, &asrv->srv_rwsem) { + if (!asrv->srv) + return; + service = asrv->srv; + } + + /* close AV audio service */ + dev_info(dcp->dev, "%s: stopping audio service\n", __func__); + if (!asrv->is_open) + return; + + mutex_lock(&asrv->plug_lock); + + if (asrv->audio_dev) + dcpaud_disconnect(asrv->audio_dev); + + mutex_unlock(&asrv->plug_lock); + + ret = afk_service_call(service, 0, asrv->cmds.close, NULL, 0, 16, + NULL, 0, 16); + if (ret) { + dev_err(dcp->dev, "error closing audio service: %d\n", ret); + } + if (service->torndown) + service->enabled = false; + asrv->is_open = false; +} + +static void av_work_service_start(struct work_struct *work) +{ + struct audiosrv_data *audiosrv_data; + struct apple_dcp *dcp; + + audiosrv_data = container_of(work, struct audiosrv_data, start_av_service_wq); + + scoped_guard(rwsem_read, &audiosrv_data->srv_rwsem) { + if (!audiosrv_data->srv || + !audiosrv_data->srv->ep || + !audiosrv_data->srv->ep->dcp) { + pr_err("%s: dcp: av: NULL ptr during startup\n", __func__); + return; + } + dcp = audiosrv_data->srv->ep->dcp; + } + + av_service_connect(dcp); +} + +int avep_init(struct apple_dcp *dcp) +{ + struct audiosrv_data *audiosrv_data; + struct platform_device *audio_pdev; + struct device *dev = dcp->dev; + struct device_node *endpoint, *audio_node = NULL; + + audiosrv_data = devm_kzalloc(dcp->dev, sizeof(*audiosrv_data), GFP_KERNEL); + if (!audiosrv_data) + return -ENOMEM; + init_rwsem(&audiosrv_data->srv_rwsem); + mutex_init(&audiosrv_data->plug_lock); + + switch (dcp->fw_compat) { + case DCP_FIRMWARE_V_12_3: + audiosrv_data->cmds = dcp_av_audio_cmds_v12_3; + break; + case DCP_FIRMWARE_V_13_5: + audiosrv_data->cmds = dcp_av_audio_cmds_v13_5; + break; + default: + dev_err(dcp->dev, "Audio not supported for firmware\n"); + return -ENODEV; + } + + dcp->audiosrv = audiosrv_data; + INIT_WORK(&audiosrv_data->start_av_service_wq, av_work_service_start); + + endpoint = of_graph_get_endpoint_by_regs(dev->of_node, 0, 0); + if (endpoint) { + audio_node = of_graph_get_remote_port_parent(endpoint); + of_node_put(endpoint); + } + if (!audio_node || !of_device_is_available(audio_node)) { + of_node_put(audio_node); + dev_info(dev, "No audio support\n"); + return 0; + } + + audio_pdev = of_find_device_by_node(audio_node); + of_node_put(audio_node); + if (!audio_pdev) { + dev_info(dev, "No DP/HDMI audio device not ready\n"); + return 0; + } + dcp->audiosrv->audio_dev = audio_pdev; + + device_link_add(&audio_pdev->dev, dev, + DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME); + + dcp->avep = afk_init(dcp, AV_ENDPOINT, avep_ops); + if (IS_ERR(dcp->avep)) + return PTR_ERR(dcp->avep); + dcp->avep->debugfs_entry = dcp->ep_debugfs[AV_ENDPOINT - 0x20]; + return afk_start(dcp->avep); +} diff --git a/drivers/gpu/drm/apple/av.h b/drivers/gpu/drm/apple/av.h new file mode 100644 index 00000000000000..c00cbef549fd2e --- /dev/null +++ b/drivers/gpu/drm/apple/av.h @@ -0,0 +1,17 @@ +#ifndef __AV_H__ +#define __AV_H__ + +#include "parser.h" + +//int avep_audiosrv_startlink(struct apple_dcp *dcp, struct dcp_sound_cookie *cookie); +//int avep_audiosrv_stoplink(struct apple_dcp *dcp); + +#if IS_ENABLED(CONFIG_DRM_APPLE_AUDIO) +void av_service_connect(struct apple_dcp *dcp); +void av_service_disconnect(struct apple_dcp *dcp); +#else +static inline void av_service_connect(struct apple_dcp *dcp) { } +static inline void av_service_disconnect(struct apple_dcp *dcp) { } +#endif + +#endif /* __AV_H__ */ diff --git a/drivers/gpu/drm/apple/connector.c b/drivers/gpu/drm/apple/connector.c new file mode 100644 index 00000000000000..15b3664d85631e --- /dev/null +++ b/drivers/gpu/drm/apple/connector.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * Copyright (C) The Asahi Linux Contributors + */ + +#include "connector.h" + +#include "linux/err.h" +#include +#include +#include +#include +#include + +#include + +#include "dcp-internal.h" + +enum dcp_chunk_type { + DCP_CHUNK_COLOR_ELEMENTS, + DCP_CHUNK_TIMING_ELELMENTS, + DCP_CHUNK_DISPLAY_ATTRIBUTES, + DCP_CHUNK_TRANSPORT, + DCP_CHUNK_NUM_TYPES, +}; + +static int chunk_show(struct seq_file *m, + enum dcp_chunk_type chunk_type) +{ + struct apple_connector *apple_con = m->private; + struct dcp_chunks *chunk = NULL; + + mutex_lock(&apple_con->chunk_lock); + + switch (chunk_type) { + case DCP_CHUNK_COLOR_ELEMENTS: + chunk = &apple_con->color_elements; + break; + case DCP_CHUNK_TIMING_ELELMENTS: + chunk = &apple_con->timing_elements; + break; + case DCP_CHUNK_DISPLAY_ATTRIBUTES: + chunk = &apple_con->display_attributes; + break; + case DCP_CHUNK_TRANSPORT: + chunk = &apple_con->transport; + break; + default: + break; + } + + if (chunk) + seq_write(m, chunk->data, chunk->length); + + mutex_unlock(&apple_con->chunk_lock); + + return 0; +} + +#define CONNECTOR_DEBUGFS_ENTRY(name, type) \ +static int chunk_ ## name ## _show(struct seq_file *m, void *data) \ +{ \ + return chunk_show(m, type); \ +} \ +static int chunk_ ## name ## _open(struct inode *inode, struct file *file) \ +{ \ + return single_open(file, chunk_ ## name ## _show, inode->i_private); \ +} \ +static const struct file_operations chunk_ ## name ## _fops = { \ + .owner = THIS_MODULE, \ + .open = chunk_ ## name ## _open, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ +} + +CONNECTOR_DEBUGFS_ENTRY(color, DCP_CHUNK_COLOR_ELEMENTS); +CONNECTOR_DEBUGFS_ENTRY(timing, DCP_CHUNK_TIMING_ELELMENTS); +CONNECTOR_DEBUGFS_ENTRY(display_attribs, DCP_CHUNK_DISPLAY_ATTRIBUTES); +CONNECTOR_DEBUGFS_ENTRY(transport, DCP_CHUNK_TRANSPORT); + +static void dcp_afk_debugfs_root(struct platform_device *pdev, int ep, struct dentry *root) +{ +#if IS_ENABLED(CONFIG_DRM_APPLE_DEBUG) + struct dentry *entry = NULL; + struct apple_dcp *dcp = platform_get_drvdata(pdev); + + switch (ep) { + case AV_ENDPOINT: + entry = debugfs_create_dir("avep", root); + break; + default: + break; + } + + if (!IS_ERR_OR_NULL(entry)) + dcp->ep_debugfs[ep - 0x20] = entry; +#endif +} + +void apple_connector_debugfs_init(struct drm_connector *connector, struct dentry *root) +{ + struct apple_connector *apple_con = to_apple_connector(connector); + + debugfs_create_file("ColorElements", 0444, root, apple_con, + &chunk_color_fops); + debugfs_create_file("TimingElements", 0444, root, apple_con, + &chunk_timing_fops); + debugfs_create_file("DisplayAttributes", 0444, root, apple_con, + &chunk_display_attribs_fops); + debugfs_create_file("Transport", 0444, root, apple_con, + &chunk_transport_fops); + + switch (connector->connector_type) { + case DRM_MODE_CONNECTOR_DisplayPort: + case DRM_MODE_CONNECTOR_HDMIA: + dcp_afk_debugfs_root(apple_con->dcp, AV_ENDPOINT, root); + break; + default: + break; + } +} + +static void dcp_connector_set_dict(struct apple_connector *connector, + struct dcp_chunks *dict, + struct dcp_chunks *chunks) +{ + if (dict->data) + devm_kfree(&connector->dcp->dev, dict->data); + + *dict = *chunks; +} + +void dcp_connector_update_dict(struct apple_connector *connector, const char *key, + struct dcp_chunks *chunks) +{ + mutex_lock(&connector->chunk_lock); + if (!strcmp(key, "ColorElements")) + dcp_connector_set_dict(connector, &connector->color_elements, chunks); + else if (!strcmp(key, "TimingElements")) + dcp_connector_set_dict(connector, &connector->timing_elements, chunks); + else if (!strcmp(key, "DisplayAttributes")) + dcp_connector_set_dict(connector, &connector->display_attributes, chunks); + else if (!strcmp(key, "Transport")) + dcp_connector_set_dict(connector, &connector->transport, chunks); + + chunks->data = NULL; + chunks->length = 0; + + mutex_unlock(&connector->chunk_lock); +} diff --git a/drivers/gpu/drm/apple/connector.h b/drivers/gpu/drm/apple/connector.h new file mode 100644 index 00000000000000..ff643552c77d4c --- /dev/null +++ b/drivers/gpu/drm/apple/connector.h @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* "Copyright" 2021 Alyssa Rosenzweig */ + +#ifndef __APPLE_CONNECTOR_H__ +#define __APPLE_CONNECTOR_H__ + +#include + +#include +#include "drm/drm_connector.h" +#include "drm/drm_edid.h" + +struct apple_connector; + +#include "dcp-internal.h" + +void dcp_hotplug(struct work_struct *work); + +struct apple_connector { + struct drm_connector base; + bool connected; + + struct platform_device *dcp; + + const struct drm_edid *drm_edid; + + /* Workqueue for sending hotplug events to the associated device */ + struct work_struct hotplug_wq; + + struct mutex chunk_lock; + + struct dcp_chunks color_elements; + struct dcp_chunks timing_elements; + struct dcp_chunks display_attributes; + struct dcp_chunks transport; +}; + +#define to_apple_connector(x) container_of(x, struct apple_connector, base) + +void apple_connector_debugfs_init(struct drm_connector *connector, struct dentry *root); + +void dcp_connector_update_dict(struct apple_connector *connector, const char *key, + struct dcp_chunks *chunks); +#endif diff --git a/drivers/gpu/drm/apple/dcp-internal.h b/drivers/gpu/drm/apple/dcp-internal.h new file mode 100644 index 00000000000000..083d044f4f5791 --- /dev/null +++ b/drivers/gpu/drm/apple/dcp-internal.h @@ -0,0 +1,277 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2021 Alyssa Rosenzweig */ + +#ifndef __APPLE_DCP_INTERNAL_H__ +#define __APPLE_DCP_INTERNAL_H__ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "dptxep.h" +#include "iomfb.h" +#include "iomfb_v12_3.h" +#include "iomfb_v13_3.h" +#include "epic/dpavservep.h" + +#define DCP_MAX_PLANES 2 + +struct apple_dcp; +struct apple_dcp_afkep; + +struct dcpav_service_epic; + +enum dcp_firmware_version { + DCP_FIRMWARE_UNKNOWN, + DCP_FIRMWARE_V_12_3, + DCP_FIRMWARE_V_13_5, +}; + +enum { + SYSTEM_ENDPOINT = 0x20, + TEST_ENDPOINT = 0x21, + DCP_EXPERT_ENDPOINT = 0x22, + DISP0_ENDPOINT = 0x23, + DPAVSERV_ENDPOINT = 0x28, + AV_ENDPOINT = 0x29, + DPTX_ENDPOINT = 0x2a, + HDCP_ENDPOINT = 0x2b, + REMOTE_ALLOC_ENDPOINT = 0x2d, + IOMFB_ENDPOINT = 0x37, +}; + +/* Temporary backing for a chunked transfer via setDCPAVPropStart/Chunk/End */ +struct dcp_chunks { + size_t length; + void *data; +}; + +#define DCP_MAX_MAPPINGS (128) /* should be enough */ +#define MAX_DISP_REGISTERS (7) + +struct dcp_mem_descriptor { + size_t size; + void *buf; + dma_addr_t dva; + struct sg_table map; + u64 reg; +}; + +/* Limit on call stack depth (arbitrary). Some nesting is required */ +#define DCP_MAX_CALL_DEPTH 8 + +typedef void (*dcp_callback_t)(struct apple_dcp *, void *, void *); + +struct dcp_channel { + dcp_callback_t callbacks[DCP_MAX_CALL_DEPTH]; + void *cookies[DCP_MAX_CALL_DEPTH]; + void *output[DCP_MAX_CALL_DEPTH]; + u16 end[DCP_MAX_CALL_DEPTH]; + + /* Current depth of the call stack. Less than DCP_MAX_CALL_DEPTH */ + u8 depth; + /* Already warned about busy channel */ + bool warned_busy; +}; + +struct dcp_fb_reference { + struct list_head head; + struct drm_framebuffer *fb; + u32 swap_id; +}; + +#define MAX_NOTCH_HEIGHT 160 + +struct dcp_brightness { + struct backlight_device *bl_dev; + u32 maximum; + u32 dac; + int nits; + int scale; + bool update; +}; + +struct audiosrv_data; + +/** laptop/AiO integrated panel parameters from DT */ +struct dcp_panel { + /// panel width in millimeter + int width_mm; + /// panel height in millimeter + int height_mm; + /// panel has a mini-LED backlight + bool has_mini_led; +}; + +struct apple_dcp_hw_data { + u32 num_dptx_ports; +}; + +/* TODO: move IOMFB members to its own struct */ +struct apple_dcp { + struct device *dev; + struct platform_device *piodma; + struct iommu_domain *iommu_dom; + struct apple_rtkit *rtk; + struct apple_crtc *crtc; + struct apple_connector *connector; + + struct apple_dcp_hw_data hw; + + /* firmware version and compatible firmware version */ + enum dcp_firmware_version fw_compat; + + /* Coprocessor control register */ + void __iomem *coproc_reg; + + /* DCP has crashed */ + bool crashed; + + /************* IOMFB ************************************************** + * everything below is mostly used inside IOMFB but it could make * + * sense to keep some of the members in apple_dcp. * + **********************************************************************/ + + /* clock rate request by dcp in */ + struct clk *clk; + + /* DCP shared memory */ + void *shmem; + + /* Display registers mappable to the DCP */ + struct resource *disp_registers[MAX_DISP_REGISTERS]; + unsigned int nr_disp_registers; + + struct resource disp_bw_scratch_res; + struct resource disp_bw_doorbell_res; + u32 disp_bw_scratch_index; + u32 disp_bw_scratch_offset; + u32 disp_bw_doorbell_index; + u32 disp_bw_doorbell_offset; + + u32 index; + + /* Bitmap of memory descriptors used for mappings made by the DCP */ + DECLARE_BITMAP(memdesc_map, DCP_MAX_MAPPINGS); + + /* Indexed table of memory descriptors */ + struct dcp_mem_descriptor memdesc[DCP_MAX_MAPPINGS]; + + struct dcp_channel ch_cmd, ch_oobcmd; + struct dcp_channel ch_cb, ch_oobcb, ch_async, ch_oobasync; + + /* iomfb EP callback handlers */ + const iomfb_cb_handler *cb_handlers; + + /* Active chunked transfer. There can only be one at a time. */ + struct dcp_chunks chunks; + + /* Queued swap. Owned by the DCP to avoid per-swap memory allocation */ + union { + struct dcp_swap_submit_req_v12_3 v12_3; + struct dcp_swap_submit_req_v13_3 v13_3; + } swap; + + /* swap id of the last completed swap */ + u32 last_swap_id; + ktime_t swap_start; + + /* Current display mode */ + bool during_modeset; + bool valid_mode; + bool use_timestamps; + struct dcp_set_digital_out_mode_req mode; + + /* completion for active turning true */ + struct completion start_done; + + /* Is the DCP booted? */ + bool active; + + /* eDP display without DP-HDMI conversion */ + bool main_display; + + /* clear all surfaces on init */ + bool surfaces_cleared; + + /* enable CRC calculation */ + bool crc_enabled; + + /* Modes valid for the connected display */ + struct dcp_display_mode *modes; + unsigned int nr_modes; + + /* Attributes of the connector */ + int connector_type; + + /* Attributes of the connected display */ + int width_mm, height_mm; + + unsigned notch_height; + + /* Workqueue for sending vblank events when a dcp swap is not possible */ + struct work_struct vblank_wq; + + /* List of referenced drm_framebuffers which can be unreferenced + * on the next successfully completed swap. + */ + struct list_head swapped_out_fbs; + + struct dcp_brightness brightness; + /* Workqueue for updating the initial brightness */ + struct work_struct bl_register_wq; + struct mutex bl_register_mutex; + /* Workqueue for updating the brightness */ + struct work_struct bl_update_wq; + + /* integrated panel if present */ + struct dcp_panel panel; + + struct apple_dcp_afkep *systemep; + struct completion systemep_done; + + struct apple_dcp_afkep *ibootep; + struct apple_dcp_afkep *dcpavservep; + struct dcpavserv dcpavserv; + + struct apple_dcp_afkep *avep; + struct audiosrv_data *audiosrv; + + struct apple_dcp_afkep *dptxep; + + struct dptx_port dptxport[2]; + + /* debugfs entries */ + struct dentry *ep_debugfs[0x20]; + + /* these fields are output port specific */ + struct phy *phy; + struct mux_control *xbar; + struct typec_mux *typec_mux; + + struct gpio_desc *hdmi_hpd; + struct gpio_desc *hdmi_pwren; + struct gpio_desc *dp2hdmi_pwren; + + struct mutex hpd_mutex; + + u32 dptx_phy; + u32 dptx_die; + int hdmi_hpd_irq; +}; + +void dcp_drm_crtc_page_flip(struct apple_dcp *dcp, ktime_t now); + +int dcp_backlight_register(struct apple_dcp *dcp); +int dcp_backlight_update(struct apple_dcp *dcp); +bool dcp_has_panel(struct apple_dcp *dcp); + +#define DCP_AUDIO_MAX_CHANS 15 + +#endif /* __APPLE_DCP_INTERNAL_H__ */ diff --git a/drivers/gpu/drm/apple/dcp.c b/drivers/gpu/drm/apple/dcp.c new file mode 100644 index 00000000000000..ff1b59eef989c4 --- /dev/null +++ b/drivers/gpu/drm/apple/dcp.c @@ -0,0 +1,1367 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2021 Alyssa Rosenzweig */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +#include "afk.h" +#include "av.h" +#include "dcp.h" +#include "dcp-internal.h" +#include "iomfb.h" +#include "parser.h" +#include "trace.h" + +#define APPLE_DCP_COPROC_CPU_CONTROL 0x44 +#define APPLE_DCP_COPROC_CPU_CONTROL_RUN BIT(4) + +#define DCP_BOOT_TIMEOUT msecs_to_jiffies(1000) + +static bool show_notch; +module_param(show_notch, bool, 0644); +MODULE_PARM_DESC(show_notch, "Use the full display height and shows the notch"); + +bool hdmi_audio; +module_param(hdmi_audio, bool, 0644); +MODULE_PARM_DESC(hdmi_audio, "Enable unstable HDMI audio support"); + +static bool unstable_edid = true; +module_param(unstable_edid, bool, 0644); +MODULE_PARM_DESC(unstable_edid, "Enable unstable EDID retrival support"); + +/* copied and simplified from drm_vblank.c */ +static void send_vblank_event(struct drm_device *dev, + struct drm_pending_vblank_event *e, + u64 seq, ktime_t now) +{ + struct timespec64 tv; + + if (e->event.base.type != DRM_EVENT_FLIP_COMPLETE) + return; + + tv = ktime_to_timespec64(now); + e->event.vbl.sequence = seq; + /* + * e->event is a user space structure, with hardcoded unsigned + * 32-bit seconds/microseconds. This is safe as we always use + * monotonic timestamps since linux-4.15 + */ + e->event.vbl.tv_sec = tv.tv_sec; + e->event.vbl.tv_usec = tv.tv_nsec / 1000; + + /* + * Use the same timestamp for any associated fence signal to avoid + * mismatch in timestamps for vsync & fence events triggered by the + * same HW event. Frameworks like SurfaceFlinger in Android expects the + * retire-fence timestamp to match exactly with HW vsync as it uses it + * for its software vsync modeling. + */ + drm_send_event_timestamp_locked(dev, &e->base, now); +} + +/** + * dcp_crtc_send_page_flip_event - helper to send vblank event after pageflip + * + * Compensate for unknown slack between page flip and arrival of the + * swap_complete callback. Minimal observed duration on DCP with HDMI output + * was around 2.3 ms. If the fb swap was submitted closer to the expected + * swap_complete it gets a penalty of one frame duration. This is on the border + * of unreasonable considering that Apple advertises support for 240 Hz (frame + * duration of 4.167 ms). + * It is unreasonable considering kwin's kms commit scheduling. Kwin commits + * 1.5 ms + the mode's vblank time before the expected next page flip + * completion. This results in presenting at half the display's rate for HDMI + * outputs. + * This might be a difference between dcp and dcpext. + */ +static void dcp_crtc_send_page_flip_event(struct apple_crtc *crtc, + struct drm_pending_vblank_event *e, + ktime_t now, ktime_t start) +{ + struct drm_device *dev = crtc->base.dev; + u64 seq; + unsigned int pipe = drm_crtc_index(&crtc->base); + ktime_t flip; + + seq = 0; + if (start != KTIME_MIN) { + s64 delta = ktime_us_delta(now, start); + if (delta <= 500) + flip = now; + else if (delta >= 2500) + flip = ktime_sub_us(now, 1000); + else + flip = ktime_sub_us(now, (delta - 500) / 2); + } else { + flip = now; + } + e->pipe = pipe; + send_vblank_event(dev, e, seq, flip); +} + +/* HACK: moved here to avoid circular dependency between apple_drv and dcp */ +void dcp_drm_crtc_vblank(struct apple_crtc *crtc) +{ + unsigned long flags; + + spin_lock_irqsave(&crtc->base.dev->event_lock, flags); + if (crtc->event) { + drm_crtc_send_vblank_event(&crtc->base, crtc->event); + crtc->event = NULL; + } + spin_unlock_irqrestore(&crtc->base.dev->event_lock, flags); +} + +void dcp_drm_crtc_page_flip(struct apple_dcp *dcp, ktime_t now) +{ + unsigned long flags; + struct apple_crtc *crtc = dcp->crtc; + + spin_lock_irqsave(&crtc->base.dev->event_lock, flags); + if (crtc->event) { + if (crtc->event->event.base.type == DRM_EVENT_FLIP_COMPLETE) + dcp_crtc_send_page_flip_event(crtc, crtc->event, now, dcp->swap_start); + else + drm_crtc_send_vblank_event(&crtc->base, crtc->event); + crtc->event = NULL; + dcp->swap_start = KTIME_MIN; + } + spin_unlock_irqrestore(&crtc->base.dev->event_lock, flags); +} + +void dcp_set_dimensions(struct apple_dcp *dcp) +{ + int i; + int width_mm = dcp->width_mm; + int height_mm = dcp->height_mm; + + if (width_mm == 0 || height_mm == 0) { + width_mm = dcp->panel.width_mm; + height_mm = dcp->panel.height_mm; + } + + /* Set the connector info */ + if (dcp->connector) { + struct drm_connector *connector = &dcp->connector->base; + + mutex_lock(&connector->dev->mode_config.mutex); + connector->display_info.width_mm = width_mm; + connector->display_info.height_mm = height_mm; + mutex_unlock(&connector->dev->mode_config.mutex); + } + + /* + * Fix up any probed modes. Modes are created when parsing + * TimingElements, dimensions are calculated when parsing + * DisplayAttributes, and TimingElements may be sent first + */ + for (i = 0; i < dcp->nr_modes; ++i) { + dcp->modes[i].mode.width_mm = width_mm; + dcp->modes[i].mode.height_mm = height_mm; + } +} + +bool dcp_has_panel(struct apple_dcp *dcp) +{ + return dcp->panel.width_mm > 0; +} + +int dcp_set_crc(struct drm_crtc *crtc, bool enabled) +{ + struct apple_crtc *ac = to_apple_crtc(crtc); + struct apple_dcp *dcp = platform_get_drvdata(ac->dcp); + + dcp->crc_enabled = enabled; + + return 0; +} + +/* + * Helper to send a DRM vblank event. We do not know how call swap_submit_dcp + * without surfaces. To avoid timeouts in drm_atomic_helper_wait_for_vblanks + * send a vblank event via a workqueue. + */ +static void dcp_delayed_vblank(struct work_struct *work) +{ + struct apple_dcp *dcp; + + dcp = container_of(work, struct apple_dcp, vblank_wq); + mdelay(5); + dcp_drm_crtc_vblank(dcp->crtc); +} + +static void dcp_recv_msg(void *cookie, u8 endpoint, u64 message) +{ + struct apple_dcp *dcp = cookie; + + trace_dcp_recv_msg(dcp, endpoint, message); + + switch (endpoint) { + case IOMFB_ENDPOINT: + return iomfb_recv_msg(dcp, message); + case AV_ENDPOINT: + afk_receive_message(dcp->avep, message); + return; + case SYSTEM_ENDPOINT: + afk_receive_message(dcp->systemep, message); + return; + case DISP0_ENDPOINT: + afk_receive_message(dcp->ibootep, message); + return; + case DPAVSERV_ENDPOINT: + afk_receive_message(dcp->dcpavservep, message); + return; + case DPTX_ENDPOINT: + afk_receive_message(dcp->dptxep, message); + return; + default: + WARN(endpoint, "unknown DCP endpoint %hhu\n", endpoint); + } +} + +static void dcp_rtk_crashed(void *cookie, const void *crashlog, size_t crashlog_size) +{ + struct apple_dcp *dcp = cookie; + + dcp->crashed = true; + dev_err(dcp->dev, "DCP has crashed\n"); + if (dcp->connector) { + dcp->connector->connected = 0; + drm_edid_free(dcp->connector->drm_edid); + dcp->connector->drm_edid = NULL; + schedule_work(&dcp->connector->hotplug_wq); + } + complete(&dcp->start_done); +} + +static int dcp_rtk_shmem_setup(void *cookie, struct apple_rtkit_shmem *bfr) +{ + struct apple_dcp *dcp = cookie; + + if (bfr->iova) { + struct iommu_domain *domain = + iommu_get_domain_for_dev(dcp->dev); + phys_addr_t phy_addr; + + if (!domain) + return -ENOMEM; + + // TODO: get map from device-tree + phy_addr = iommu_iova_to_phys(domain, bfr->iova); + if (!phy_addr) + return -ENOMEM; + + // TODO: verify phy_addr, cache attribute + bfr->buffer = memremap(phy_addr, bfr->size, MEMREMAP_WB); + if (!bfr->buffer) + return -ENOMEM; + + bfr->is_mapped = true; + dev_info(dcp->dev, + "shmem_setup: iova: %lx -> pa: %lx -> iomem: %lx\n", + (uintptr_t)bfr->iova, (uintptr_t)phy_addr, + (uintptr_t)bfr->buffer); + } else { + bfr->buffer = dma_alloc_coherent(dcp->dev, bfr->size, + &bfr->iova, GFP_KERNEL); + if (!bfr->buffer) + return -ENOMEM; + + dev_info(dcp->dev, "shmem_setup: iova: %lx, buffer: %lx\n", + (uintptr_t)bfr->iova, (uintptr_t)bfr->buffer); + } + + return 0; +} + +static void dcp_rtk_shmem_destroy(void *cookie, struct apple_rtkit_shmem *bfr) +{ + struct apple_dcp *dcp = cookie; + + if (bfr->is_mapped) + memunmap(bfr->buffer); + else + dma_free_coherent(dcp->dev, bfr->size, bfr->buffer, bfr->iova); +} + +static struct apple_rtkit_ops rtkit_ops = { + .crashed = dcp_rtk_crashed, + .recv_message = dcp_recv_msg, + .shmem_setup = dcp_rtk_shmem_setup, + .shmem_destroy = dcp_rtk_shmem_destroy, +}; + +void dcp_send_message(struct apple_dcp *dcp, u8 endpoint, u64 message) +{ + trace_dcp_send_msg(dcp, endpoint, message); + apple_rtkit_send_message(dcp->rtk, endpoint, message, NULL, + true); +} + +int dcp_crtc_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state) +{ + struct platform_device *pdev = to_apple_crtc(crtc)->dcp; + struct apple_dcp *dcp = platform_get_drvdata(pdev); + struct drm_plane_state *new_state; + struct drm_plane *plane; + struct drm_crtc_state *crtc_state; + int plane_idx, plane_count = 0; + bool needs_modeset; + + if (dcp->crashed) + return -EINVAL; + + crtc_state = drm_atomic_get_new_crtc_state(state, crtc); + + needs_modeset = drm_atomic_crtc_needs_modeset(crtc_state) || !dcp->valid_mode; + if (!needs_modeset && !dcp->connector->connected) { + dev_err(dcp->dev, "crtc_atomic_check: disconnected but no modeset\n"); + return -EINVAL; + } + + for_each_new_plane_in_state(state, plane, new_state, plane_idx) { + /* skip planes not for this crtc */ + if (new_state->crtc != crtc) + continue; + + plane_count += 1; + } + + if (plane_count > DCP_MAX_PLANES) { + dev_err(dcp->dev, "crtc_atomic_check: Blend supports only 2 layers!\n"); + return -EINVAL; + } + + return 0; +} + +int dcp_get_connector_type(struct platform_device *pdev) +{ + struct apple_dcp *dcp = platform_get_drvdata(pdev); + + return (dcp->connector_type); +} + +#define DPTX_CONNECT_TIMEOUT msecs_to_jiffies(2000) + +static int dcp_dptx_connect(struct apple_dcp *dcp, u32 port) +{ + int ret = 0; + + if (!dcp->phy) { + dev_warn(dcp->dev, "dcp_dptx_connect: missing phy\n"); + return -ENODEV; + } + dev_info(dcp->dev, "%s(port=%d)\n", __func__, port); + + mutex_lock(&dcp->hpd_mutex); + if (!dcp->dptxport[port].enabled) { + dev_warn(dcp->dev, "dcp_dptx_connect: dptx service for port %d not enabled\n", port); + ret = -ENODEV; + goto out_unlock; + } + + if (dcp->dptxport[port].connected) + goto out_unlock; + + reinit_completion(&dcp->dptxport[port].linkcfg_completion); + dcp->dptxport[port].atcphy = dcp->phy; + dptxport_connect(dcp->dptxport[port].service, 0, dcp->dptx_phy, dcp->dptx_die); + dptxport_request_display(dcp->dptxport[port].service); + dcp->dptxport[port].connected = true; + + mutex_unlock(&dcp->hpd_mutex); + ret = wait_for_completion_timeout(&dcp->dptxport[port].linkcfg_completion, + DPTX_CONNECT_TIMEOUT); + if (ret < 0) + dev_warn(dcp->dev, "dcp_dptx_connect: port %d link complete failed:%d\n", + port, ret); + else + dev_dbg(dcp->dev, "dcp_dptx_connect: waited %d ms for link\n", + jiffies_to_msecs(DPTX_CONNECT_TIMEOUT - ret)); + + usleep_range(5, 10); + + if (dcp->connector_type == DRM_MODE_CONNECTOR_DisplayPort) + dptxport_set_hpd(dcp->dptxport[port].service, true); + + if (dcp->avep) + av_service_connect(dcp); + + return 0; + +out_unlock: + mutex_unlock(&dcp->hpd_mutex); + return ret; +} + +static void disconnected_hpd_event(struct apple_connector *con) +{ + if (con && con->connected) { + con->connected = 0; + drm_kms_helper_connector_hotplug_event(&con->base); + } +} + +static int dcp_dptx_disconnect(struct apple_dcp *dcp, u32 port) +{ + dev_info(dcp->dev, "%s(port=%d)\n", __func__, port); + + mutex_lock(&dcp->hpd_mutex); + if (dcp->dptxport[port].enabled && dcp->dptxport[port].connected) { + dptxport_release_display(dcp->dptxport[port].service); + dcp->dptxport[port].connected = false; + } + mutex_unlock(&dcp->hpd_mutex); + + return 0; +} + +int dcp_dptx_connect_oob(struct platform_device *pdev, u32 port) +{ + struct apple_dcp *dcp = platform_get_drvdata(pdev); + return dcp_dptx_connect(dcp, port); +} + +int dcp_dptx_disconnect_oob(struct platform_device *pdev, u32 port) +{ + struct apple_dcp *dcp = platform_get_drvdata(pdev); + + disconnected_hpd_event(dcp->connector); + + if (dcp->avep) + av_service_disconnect(dcp); + + if (dcp->dptxport[port].enabled) + dptxport_set_hpd(dcp->dptxport[port].service, false); + + return dcp_dptx_disconnect(dcp, port); +} + +static irqreturn_t dcp_dp2hdmi_hpd(int irq, void *data) +{ + struct apple_dcp *dcp = data; + bool connected = gpiod_get_value_cansleep(dcp->hdmi_hpd); + + /* do nothing on disconnect and trust that dcp detects it itself. + * Parallel disconnect HPDs result drm disabling the CRTC even when it + * should not. + * The interrupt should be changed to rising but for now the disconnect + * IRQs might be helpful for debugging. + */ + dev_info(dcp->dev, "DP2HDMI HPD irq, connected:%d\n", connected); + + if (connected) { + msleep(500); + connected = gpiod_get_value_cansleep(dcp->hdmi_hpd); + dev_info(dcp->dev, "DP2HDMI HPD irq, 500ms debounce: connected:%d\n", connected); + } + + if (connected) + dcp_dptx_connect(dcp, 0); + + return IRQ_HANDLED; +} + +void dcp_link(struct platform_device *pdev, struct apple_crtc *crtc, + struct apple_connector *connector) +{ + struct apple_dcp *dcp = platform_get_drvdata(pdev); + + dcp->crtc = crtc; + dcp->connector = connector; +} + + +bool dcp_fw_compat_is_12_x(struct platform_device *pdev) +{ + struct apple_dcp *dcp = platform_get_drvdata(pdev); + + return dcp->fw_compat == DCP_FIRMWARE_V_12_3; +} + +int dcp_start(struct platform_device *pdev) +{ + struct apple_dcp *dcp = platform_get_drvdata(pdev); + int ret; + + init_completion(&dcp->start_done); + + /* start RTKit endpoints */ + ret = systemep_init(dcp); + if (ret) + dev_warn(dcp->dev, "Failed to start system endpoint: %d\n", ret); + + if (unstable_edid && !dcp_has_panel(dcp)) { + ret = dpavservep_init(dcp); + if (ret) + dev_warn(dcp->dev, "Failed to start DPAVSERV endpoint: %d", + ret); + } + + if (dcp->phy && dcp->fw_compat >= DCP_FIRMWARE_V_13_5) { + ret = ibootep_init(dcp); + if (ret) + dev_warn(dcp->dev, "Failed to start IBOOT endpoint: %d\n", + ret); + + ret = dptxep_init(dcp); + if (ret) { + dev_warn(dcp->dev, "Failed to start DPTX endpoint: %d\n", + ret); +#ifdef DCP_DPTX_DISCONNECT_ON_INIT + /* + * This disconnect / connect cycle on init is only necessary + * when using dcp0 on j473, j474s and presumedly j475c. + * Since dcp0 is not used at the moment let's avoid this + * since it is possibly the cause for startup issues. + */ + } else if (dcp->dptxport[0].enabled) { + bool connected; + /* force disconnect on start - necessary if the display + * is already up from m1n1 + */ + dptxport_set_hpd(dcp->dptxport[0].service, false); + dptxport_release_display(dcp->dptxport[0].service); + usleep_range(10 * USEC_PER_MSEC, 25 * USEC_PER_MSEC); + + connected = gpiod_get_value_cansleep(dcp->hdmi_hpd); + dev_info(dcp->dev, "%s: DP2HDMI HPD connected:%d\n", __func__, connected); + + // necessary on j473/j474 but not on j314c + if (connected) + dcp_dptx_connect(dcp, 0); +#endif + } + } else if (dcp->phy) { + dev_warn(dcp->dev, "OS firmware incompatible with dptxport EP\n"); + } + ret = iomfb_start_rtkit(dcp); + if (ret) + dev_err(dcp->dev, "Failed to start IOMFB endpoint: %d\n", ret); + +#if IS_ENABLED(CONFIG_DRM_APPLE_AUDIO) + if (hdmi_audio) { + ret = avep_init(dcp); + if (ret) + dev_warn(dcp->dev, "Failed to start AV endpoint: %d", ret); + ret = 0; + } +#endif + + return ret; +} + +static int dcp_enable_dp2hdmi_hpd(struct apple_dcp *dcp) +{ + // check HPD state before enabling the edge triggered IRQ + if (dcp->hdmi_hpd) { + bool connected = gpiod_get_value_cansleep(dcp->hdmi_hpd); + dev_info(dcp->dev, "%s: DP2HDMI HPD connected:%d\n", __func__, connected); + + if (connected) + dcp_dptx_connect(dcp, 0); + } + + if (dcp->hdmi_hpd_irq) + enable_irq(dcp->hdmi_hpd_irq); + + return 0; +} + +int dcp_wait_ready(struct platform_device *pdev, u64 timeout) +{ + struct apple_dcp *dcp = platform_get_drvdata(pdev); + int ret; + + if (dcp->crashed) + return -ENODEV; + if (dcp->active) + return dcp_enable_dp2hdmi_hpd(dcp); + if (timeout <= 0) + return -ETIMEDOUT; + + ret = wait_for_completion_timeout(&dcp->start_done, timeout); + if (ret < 0) + return ret; + + if (dcp->crashed) + return -ENODEV; + + if (dcp->active) + dcp_enable_dp2hdmi_hpd(dcp); + + return dcp->active ? 0 : -ETIMEDOUT; +} + +static void __maybe_unused dcp_sleep(struct apple_dcp *dcp) +{ + switch (dcp->fw_compat) { + case DCP_FIRMWARE_V_12_3: + iomfb_sleep_v12_3(dcp); + break; + case DCP_FIRMWARE_V_13_5: + iomfb_sleep_v13_3(dcp); + break; + default: + WARN_ONCE(true, "Unexpected firmware version: %u\n", dcp->fw_compat); + break; + } +} + +void dcp_poweron(struct platform_device *pdev) +{ + struct apple_dcp *dcp = platform_get_drvdata(pdev); + + if (dcp->hdmi_hpd) { + bool connected = gpiod_get_value_cansleep(dcp->hdmi_hpd); + dev_info(dcp->dev, "%s: DP2HDMI HPD connected:%d\n", __func__, connected); + + if (connected) + dcp_dptx_connect(dcp, 0); + } + + switch (dcp->fw_compat) { + case DCP_FIRMWARE_V_12_3: + iomfb_poweron_v12_3(dcp); + break; + case DCP_FIRMWARE_V_13_5: + iomfb_poweron_v13_3(dcp); + break; + default: + WARN_ONCE(true, "Unexpected firmware version: %u\n", dcp->fw_compat); + break; + } + + if (dcp->avep) + av_service_connect(dcp); +} + +void dcp_poweroff(struct platform_device *pdev) +{ + struct apple_dcp *dcp = platform_get_drvdata(pdev); + + if (dcp->avep) + av_service_disconnect(dcp); + + switch (dcp->fw_compat) { + case DCP_FIRMWARE_V_12_3: + iomfb_poweroff_v12_3(dcp); + break; + case DCP_FIRMWARE_V_13_5: + iomfb_poweroff_v13_3(dcp); + break; + default: + WARN_ONCE(true, "Unexpected firmware version: %u\n", dcp->fw_compat); + break; + } + + if (dcp->hdmi_hpd) { + bool connected = gpiod_get_value_cansleep(dcp->hdmi_hpd); + if (!connected) { + disconnected_hpd_event(dcp->connector); + dcp_dptx_disconnect(dcp, 0); + } + } +} + +static void dcp_work_register_backlight(struct work_struct *work) +{ + int ret; + struct apple_dcp *dcp; + + dcp = container_of(work, struct apple_dcp, bl_register_wq); + + mutex_lock(&dcp->bl_register_mutex); + if (dcp->brightness.bl_dev) + goto out_unlock; + + /* try to register backlight device, */ + ret = dcp_backlight_register(dcp); + if (ret) { + dev_err(dcp->dev, "Unable to register backlight device\n"); + dcp->brightness.maximum = 0; + } + +out_unlock: + mutex_unlock(&dcp->bl_register_mutex); +} + +static void dcp_work_update_backlight(struct work_struct *work) +{ + struct apple_dcp *dcp; + + dcp = container_of(work, struct apple_dcp, bl_update_wq); + + dcp_backlight_update(dcp); +} + +static int dcp_create_piodma_iommu_dev(struct apple_dcp *dcp) +{ + int ret; + struct device_node *node = of_get_child_by_name(dcp->dev->of_node, "piodma"); + + if (!node) + return dev_err_probe(dcp->dev, -ENODEV, + "Failed to get piodma child DT node\n"); + + dcp->piodma = of_platform_device_create(node, NULL, dcp->dev); + if (!dcp->piodma) { + of_node_put(node); + return dev_err_probe(dcp->dev, -ENODEV, "Failed to create piodma pdev for %pOF\n", node); + } + + ret = dma_set_mask_and_coherent(&dcp->piodma->dev, DMA_BIT_MASK(42)); + if (ret) + goto err_destroy_pdev; + + ret = of_dma_configure(&dcp->piodma->dev, node, true); + if (ret) { + ret = dev_err_probe(dcp->dev, ret, + "Failed to configure IOMMU child DMA\n"); + goto err_destroy_pdev; + } + of_node_put(node); + + dcp->iommu_dom = iommu_get_domain_for_dev(&dcp->piodma->dev); + if (IS_ERR(dcp->iommu_dom)) { + ret = dev_err_probe(dcp->dev, PTR_ERR(dcp->iommu_dom), + "Failed to get default iommu domain for " + "piodma device\n"); + dcp->iommu_dom = NULL; + goto err_destroy_pdev; + } + + return 0; +err_destroy_pdev: + of_node_put(node); + of_platform_device_destroy(&dcp->piodma->dev, NULL); + return ret; +} + +static int dcp_get_bw_scratch_reg(struct apple_dcp *dcp, u32 expected) +{ + struct of_phandle_args ph_args; + u32 addr_idx, disp_idx, offset; + int ret; + + ret = of_parse_phandle_with_args(dcp->dev->of_node, "apple,bw-scratch", + "#apple,bw-scratch-cells", 0, &ph_args); + if (ret < 0) { + dev_err(dcp->dev, "Failed to read 'apple,bw-scratch': %d\n", ret); + return ret; + } + + if (ph_args.args_count != 3) { + dev_err(dcp->dev, "Unexpected 'apple,bw-scratch' arg count %d\n", + ph_args.args_count); + ret = -EINVAL; + goto err_of_node_put; + } + + addr_idx = ph_args.args[0]; + disp_idx = ph_args.args[1]; + offset = ph_args.args[2]; + + if (disp_idx != expected || disp_idx >= MAX_DISP_REGISTERS) { + dev_err(dcp->dev, "Unexpected disp_reg value in 'apple,bw-scratch': %d\n", + disp_idx); + ret = -EINVAL; + goto err_of_node_put; + } + + ret = of_address_to_resource(ph_args.np, addr_idx, &dcp->disp_bw_scratch_res); + if (ret < 0) { + dev_err(dcp->dev, "Failed to get 'apple,bw-scratch' resource %d from %pOF\n", + addr_idx, ph_args.np); + goto err_of_node_put; + } + if (offset > resource_size(&dcp->disp_bw_scratch_res) - 4) { + ret = -EINVAL; + goto err_of_node_put; + } + + dcp->disp_registers[disp_idx] = &dcp->disp_bw_scratch_res; + dcp->disp_bw_scratch_index = disp_idx; + dcp->disp_bw_scratch_offset = offset; + ret = 0; + +err_of_node_put: + of_node_put(ph_args.np); + return ret; +} + +static int dcp_get_bw_doorbell_reg(struct apple_dcp *dcp, u32 expected) +{ + struct of_phandle_args ph_args; + u32 addr_idx, disp_idx; + int ret; + + ret = of_parse_phandle_with_args(dcp->dev->of_node, "apple,bw-doorbell", + "#apple,bw-doorbell-cells", 0, &ph_args); + if (ret < 0) { + dev_err(dcp->dev, "Failed to read 'apple,bw-doorbell': %d\n", ret); + return ret; + } + + if (ph_args.args_count != 2) { + dev_err(dcp->dev, "Unexpected 'apple,bw-doorbell' arg count %d\n", + ph_args.args_count); + ret = -EINVAL; + goto err_of_node_put; + } + + addr_idx = ph_args.args[0]; + disp_idx = ph_args.args[1]; + + if (disp_idx != expected || disp_idx >= MAX_DISP_REGISTERS) { + dev_err(dcp->dev, "Unexpected disp_reg value in 'apple,bw-doorbell': %d\n", + disp_idx); + ret = -EINVAL; + goto err_of_node_put; + } + + ret = of_address_to_resource(ph_args.np, addr_idx, &dcp->disp_bw_doorbell_res); + if (ret < 0) { + dev_err(dcp->dev, "Failed to get 'apple,bw-doorbell' resource %d from %pOF\n", + addr_idx, ph_args.np); + goto err_of_node_put; + } + dcp->disp_bw_doorbell_index = disp_idx; + dcp->disp_registers[disp_idx] = &dcp->disp_bw_doorbell_res; + ret = 0; + +err_of_node_put: + of_node_put(ph_args.np); + return ret; +} + +static int dcp_get_disp_regs(struct apple_dcp *dcp) +{ + struct platform_device *pdev = to_platform_device(dcp->dev); + int count = pdev->num_resources - 1; + int i, ret; + + if (count <= 0 || count > MAX_DISP_REGISTERS) + return -EINVAL; + + for (i = 0; i < count; ++i) { + dcp->disp_registers[i] = + platform_get_resource(pdev, IORESOURCE_MEM, 1 + i); + } + + /* load pmgr bandwidth scratch resource and offset */ + ret = dcp_get_bw_scratch_reg(dcp, count); + if (ret < 0) + return ret; + count += 1; + + /* load pmgr bandwidth doorbell resource if present (only on t8103) */ + if (of_property_present(dcp->dev->of_node, "apple,bw-doorbell")) { + ret = dcp_get_bw_doorbell_reg(dcp, count); + if (ret < 0) + return ret; + count += 1; + } + + dcp->nr_disp_registers = count; + return 0; +} + +#define DCP_FW_VERSION_MIN_LEN 3 +#define DCP_FW_VERSION_MAX_LEN 5 +#define DCP_FW_VERSION_STR_LEN (DCP_FW_VERSION_MAX_LEN * 4) + +static int dcp_read_fw_version(struct device *dev, const char *name, + char *version_str) +{ + u32 ver[DCP_FW_VERSION_MAX_LEN]; + int len_str; + int len; + + len = of_property_read_variable_u32_array(dev->of_node, name, ver, + DCP_FW_VERSION_MIN_LEN, + DCP_FW_VERSION_MAX_LEN); + + switch (len) { + case 3: + len_str = scnprintf(version_str, DCP_FW_VERSION_STR_LEN, + "%d.%d.%d", ver[0], ver[1], ver[2]); + break; + case 4: + len_str = scnprintf(version_str, DCP_FW_VERSION_STR_LEN, + "%d.%d.%d.%d", ver[0], ver[1], ver[2], + ver[3]); + break; + case 5: + len_str = scnprintf(version_str, DCP_FW_VERSION_STR_LEN, + "%d.%d.%d.%d.%d", ver[0], ver[1], ver[2], + ver[3], ver[4]); + break; + default: + len_str = strscpy(version_str, "UNKNOWN", + DCP_FW_VERSION_STR_LEN); + if (len >= 0) + len = -EOVERFLOW; + break; + } + + if (len_str >= DCP_FW_VERSION_STR_LEN) + dev_warn(dev, "'%s' truncated: '%s'\n", name, version_str); + + return len; +} + +static enum dcp_firmware_version dcp_check_firmware_version(struct device *dev) +{ + char compat_str[DCP_FW_VERSION_STR_LEN]; + char fw_str[DCP_FW_VERSION_STR_LEN]; + int ret; + + /* firmware version is just informative */ + dcp_read_fw_version(dev, "apple,firmware-version", fw_str); + + ret = dcp_read_fw_version(dev, "apple,firmware-compat", compat_str); + if (ret < 0) { + dev_err(dev, "Could not read 'apple,firmware-compat': %d\n", ret); + return DCP_FIRMWARE_UNKNOWN; + } + + if (strncmp(compat_str, "12.3.0", sizeof(compat_str)) == 0) + return DCP_FIRMWARE_V_12_3; + /* + * m1n1 reports firmware version 13.5 as compatible with 13.3. This is + * only true for the iomfb endpoint. The interface for the dptx-port + * endpoint changed between 13.3 and 13.5. The driver will only support + * firmware 13.5. Check the actual firmware version for compat version + * 13.3 until m1n1 reports 13.5 as "firmware-compat". + */ + else if ((strncmp(compat_str, "13.3.0", sizeof(compat_str)) == 0) && + (strncmp(fw_str, "13.5.0", sizeof(compat_str)) == 0)) + return DCP_FIRMWARE_V_13_5; + else if (strncmp(compat_str, "13.5.0", sizeof(compat_str)) == 0) + return DCP_FIRMWARE_V_13_5; + + dev_err(dev, "DCP firmware-compat %s (FW: %s) is not supported\n", + compat_str, fw_str); + + return DCP_FIRMWARE_UNKNOWN; +} + +static int dcp_comp_bind(struct device *dev, struct device *main, void *data) +{ + struct device_node *panel_np; + struct apple_dcp *dcp = dev_get_drvdata(dev); + u32 cpu_ctrl; + int ret; + + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(42)); + if (ret) + return ret; + + dcp->coproc_reg = devm_platform_ioremap_resource_byname(to_platform_device(dev), "coproc"); + if (IS_ERR(dcp->coproc_reg)) + return PTR_ERR(dcp->coproc_reg); + + of_property_read_u32(dev->of_node, "apple,dcp-index", + &dcp->index); + of_property_read_u32(dev->of_node, "apple,dptx-phy", + &dcp->dptx_phy); + of_property_read_u32(dev->of_node, "apple,dptx-die", + &dcp->dptx_die); + if (dcp->index || dcp->dptx_phy || dcp->dptx_die) + dev_info(dev, "DCP index:%u dptx target phy: %u dptx die: %u\n", + dcp->index, dcp->dptx_phy, dcp->dptx_die); + mutex_init(&dcp->hpd_mutex); + + if (!show_notch) + ret = of_property_read_u32(dev->of_node, "apple,notch-height", + &dcp->notch_height); + + if (dcp->notch_height > MAX_NOTCH_HEIGHT) + dcp->notch_height = MAX_NOTCH_HEIGHT; + if (dcp->notch_height > 0) + dev_info(dev, "Detected display with notch of %u pixel\n", dcp->notch_height); + + /* initialize brightness scale to a sensible default to avoid divide by 0*/ + dcp->brightness.scale = 65536; + panel_np = of_get_compatible_child(dev->of_node, "apple,panel-mini-led"); + if (panel_np) + dcp->panel.has_mini_led = true; + else + panel_np = of_get_compatible_child(dev->of_node, "apple,panel"); + + if (panel_np) { + const char height_prop[2][16] = { "adj-height-mm", "height-mm" }; + + if (of_device_is_available(panel_np)) { + ret = of_property_read_u32(panel_np, "apple,max-brightness", + &dcp->brightness.maximum); + if (ret) + dev_err(dev, "Missing property 'apple,max-brightness'\n"); + } + + of_property_read_u32(panel_np, "width-mm", &dcp->panel.width_mm); + /* use adjusted height as long as the notch is hidden */ + of_property_read_u32(panel_np, height_prop[!dcp->notch_height], + &dcp->panel.height_mm); + + of_node_put(panel_np); + dcp->connector_type = DRM_MODE_CONNECTOR_eDP; + INIT_WORK(&dcp->bl_register_wq, dcp_work_register_backlight); + mutex_init(&dcp->bl_register_mutex); + INIT_WORK(&dcp->bl_update_wq, dcp_work_update_backlight); + } else if (of_property_match_string(dev->of_node, "apple,connector-type", "HDMI-A") >= 0) + dcp->connector_type = DRM_MODE_CONNECTOR_HDMIA; + else if (of_property_match_string(dev->of_node, "apple,connector-type", "DP") >= 0) + dcp->connector_type = DRM_MODE_CONNECTOR_DisplayPort; + else if (of_property_match_string(dev->of_node, "apple,connector-type", "USB-C") >= 0) + dcp->connector_type = DRM_MODE_CONNECTOR_USB; + else + dcp->connector_type = DRM_MODE_CONNECTOR_Unknown; + + ret = dcp_create_piodma_iommu_dev(dcp); + if (ret) + return dev_err_probe(dev, ret, + "Failed to created PIODMA iommu child device"); + + ret = dcp_get_disp_regs(dcp); + if (ret) { + dev_err(dev, "failed to find display registers\n"); + return ret; + } + + dcp->clk = devm_clk_get(dev, NULL); + if (IS_ERR(dcp->clk)) + return dev_err_probe(dev, PTR_ERR(dcp->clk), + "Unable to find clock\n"); + + bitmap_zero(dcp->memdesc_map, DCP_MAX_MAPPINGS); + // TDOD: mem_desc IDs start at 1, for simplicity just skip '0' entry + set_bit(0, dcp->memdesc_map); + + INIT_WORK(&dcp->vblank_wq, dcp_delayed_vblank); + + dcp->swapped_out_fbs = + (struct list_head)LIST_HEAD_INIT(dcp->swapped_out_fbs); + + cpu_ctrl = + readl_relaxed(dcp->coproc_reg + APPLE_DCP_COPROC_CPU_CONTROL); + writel_relaxed(cpu_ctrl | APPLE_DCP_COPROC_CPU_CONTROL_RUN, + dcp->coproc_reg + APPLE_DCP_COPROC_CPU_CONTROL); + + dcp->rtk = devm_apple_rtkit_init(dev, dcp, "mbox", 0, &rtkit_ops); + if (IS_ERR(dcp->rtk)) + return dev_err_probe(dev, PTR_ERR(dcp->rtk), + "Failed to initialize RTKit\n"); + + ret = apple_rtkit_wake(dcp->rtk); + if (ret) + return dev_err_probe(dev, ret, + "Failed to boot RTKit: %d\n", ret); + return ret; +} + +/* + * We need to shutdown DCP before tearing down the display subsystem. Otherwise + * the DCP will crash and briefly flash a green screen of death. + */ +static void dcp_comp_unbind(struct device *dev, struct device *main, void *data) +{ + struct apple_dcp *dcp = dev_get_drvdata(dev); + + if (!dcp) + return; + + if (dcp->hdmi_hpd_irq) + disable_irq(dcp->hdmi_hpd_irq); + + typec_mux_put(dcp->typec_mux); + + if (dcp->avep) { + av_service_disconnect(dcp); + afk_shutdown(dcp->avep); + dcp->avep = NULL; + } + + if (dcp->dptxep) { + afk_shutdown(dcp->dptxep); + dcp->dptxep = NULL; + } + + if (dcp->ibootep) { + afk_shutdown(dcp->ibootep); + dcp->ibootep = NULL; + } + + if (dcp->systemep) { + afk_shutdown(dcp->systemep); + dcp->systemep = NULL; + } + + if (dcp->dcpavservep) { + afk_shutdown(dcp->dcpavservep); + dcp->dcpavservep = NULL; + } + + if (dcp->shmem) + iomfb_shutdown(dcp); + + if (dcp->piodma) { + dcp->iommu_dom = NULL; + of_platform_device_destroy(&dcp->piodma->dev, NULL); + dcp->piodma = NULL; + } + + if (dcp->connector_type == DRM_MODE_CONNECTOR_eDP) { + cancel_work_sync(&dcp->bl_register_wq); + cancel_work_sync(&dcp->bl_update_wq); + } + cancel_work_sync(&dcp->vblank_wq); + + devm_clk_put(dev, dcp->clk); + dcp->clk = NULL; +} + +static const struct component_ops dcp_comp_ops = { + .bind = dcp_comp_bind, + .unbind = dcp_comp_unbind, +}; + +static int dcp_platform_probe(struct platform_device *pdev) +{ + enum dcp_firmware_version fw_compat; + struct device *dev = &pdev->dev; + struct apple_dcp *dcp; + u32 mux_index; + + fw_compat = dcp_check_firmware_version(dev); + if (fw_compat == DCP_FIRMWARE_UNKNOWN) + return -ENODEV; + + /* Check for "apple,bw-scratch" to avoid probing appledrm with outdated + * device trees. This prevents replacing simpledrm and ending up without + * display. + */ + if (!of_property_present(dev->of_node, "apple,bw-scratch")) + return dev_err_probe(dev, -ENODEV, "Incompatible devicetree! " + "Use devicetree matching this kernel.\n"); + + dcp = devm_kzalloc(dev, sizeof(*dcp), GFP_KERNEL); + if (!dcp) + return -ENOMEM; + + dcp->fw_compat = fw_compat; + dcp->dev = dev; + dcp->hw = *(struct apple_dcp_hw_data *)of_device_get_match_data(dev); + + platform_set_drvdata(pdev, dcp); + + dcp->phy = devm_phy_optional_get(dev, "dp-phy"); + if (IS_ERR(dcp->phy)) { + dev_err(dev, "Failed to get dp-phy: %ld\n", PTR_ERR(dcp->phy)); + return PTR_ERR(dcp->phy); + } + if (dcp->phy) { + int ret; + /* + * Request DP2HDMI related GPIOs as optional for DP-altmode + * compatibility. J180D misses a dp2hdmi-pwren GPIO in the + * template ADT. TODO: check device ADT + */ + dcp->hdmi_hpd = devm_gpiod_get_optional(dev, "hdmi-hpd", GPIOD_IN); + if (IS_ERR(dcp->hdmi_hpd)) + return PTR_ERR(dcp->hdmi_hpd); + if (dcp->hdmi_hpd) { + int irq = gpiod_to_irq(dcp->hdmi_hpd); + if (irq < 0) { + dev_err(dev, "failed to translate HDMI hpd GPIO to IRQ\n"); + return irq; + } + dcp->hdmi_hpd_irq = irq; + + ret = devm_request_threaded_irq(dev, dcp->hdmi_hpd_irq, + NULL, dcp_dp2hdmi_hpd, + IRQF_ONESHOT | IRQF_NO_AUTOEN | + IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING, + "dp2hdmi-hpd-irq", dcp); + if (ret < 0) { + dev_err(dev, "failed to request HDMI hpd irq %d: %d\n", + irq, ret); + return ret; + } + } + + /* + * Power DP2HDMI on as it is required for the HPD irq. + * TODO: check if one is sufficient for the hpd to save power + * on battery powered Macbooks. + */ + dcp->hdmi_pwren = devm_gpiod_get_optional(dev, "hdmi-pwren", GPIOD_OUT_HIGH); + if (IS_ERR(dcp->hdmi_pwren)) + return PTR_ERR(dcp->hdmi_pwren); + + dcp->dp2hdmi_pwren = devm_gpiod_get_optional(dev, "dp2hdmi-pwren", GPIOD_OUT_HIGH); + if (IS_ERR(dcp->dp2hdmi_pwren)) + return PTR_ERR(dcp->dp2hdmi_pwren); + + ret = of_property_read_u32(dev->of_node, "mux-index", &mux_index); + if (!ret) { + dcp->xbar = devm_mux_control_get(dev, "dp-xbar"); + if (IS_ERR(dcp->xbar)) { + dev_err(dev, "Failed to get dp-xbar: %ld\n", PTR_ERR(dcp->xbar)); + return PTR_ERR(dcp->xbar); + } + ret = mux_control_select(dcp->xbar, mux_index); + if (ret) + dev_warn(dev, "mux_control_select failed: %d\n", ret); + + /* + * Switch atcphy to DP-only. should move to a Macbook Pro + * 14-/16-inch specific DP-to-HDMI drm_bridge. + */ + dcp->typec_mux = fwnode_typec_mux_get(dev_fwnode(dcp->dev)); + if (!IS_ERR_OR_NULL(dcp->typec_mux)) { + struct typec_altmode alt = { + .svid = USB_TYPEC_DP_SID, + }; + struct typec_mux_state state = { + .alt = &alt, + .mode = TYPEC_DP_STATE_C, + }; + int ret = typec_mux_set(dcp->typec_mux, &state); + dev_info(dev, "typec_mux_set() returned: %d\n", ret); + } else { + dev_info(dev, "fwnode_typec_mux_get() returned: %ld\n", + IS_ERR(dcp->typec_mux) ? PTR_ERR(dcp->typec_mux) : 0); + dcp->typec_mux = NULL; + } + } + } + + return component_add(&pdev->dev, &dcp_comp_ops); +} + +static void dcp_platform_remove(struct platform_device *pdev) +{ + component_del(&pdev->dev, &dcp_comp_ops); +} + +static void dcp_platform_shutdown(struct platform_device *pdev) +{ + component_del(&pdev->dev, &dcp_comp_ops); +} + +static int dcp_platform_suspend(struct device *dev) +{ + struct apple_dcp *dcp = dev_get_drvdata(dev); + + if (dcp->avep) + av_service_disconnect(dcp); + + if (dcp->hdmi_hpd_irq) { + disable_irq(dcp->hdmi_hpd_irq); + disconnected_hpd_event(dcp->connector); + dcp_dptx_disconnect(dcp, 0); + } + /* + * Set the device as a wakeup device, which forces its power + * domains to stay on. We need this as we do not support full + * shutdown properly yet. + */ + device_set_wakeup_path(dev); + + return 0; +} + +static int dcp_platform_resume(struct device *dev) +{ + struct apple_dcp *dcp = dev_get_drvdata(dev); + + if (dcp->hdmi_hpd_irq) + enable_irq(dcp->hdmi_hpd_irq); + + if (dcp->avep) + av_service_connect(dcp); + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(dcp_platform_pm_ops, + dcp_platform_suspend, dcp_platform_resume); + + +static const struct apple_dcp_hw_data apple_dcp_hw_t6020 = { + .num_dptx_ports = 1, +}; + +static const struct apple_dcp_hw_data apple_dcp_hw_t8112 = { + .num_dptx_ports = 2, +}; + +static const struct apple_dcp_hw_data apple_dcp_hw_dcp = { + .num_dptx_ports = 0, +}; + +static const struct apple_dcp_hw_data apple_dcp_hw_dcpext = { + .num_dptx_ports = 2, +}; + +static const struct of_device_id of_match[] = { + { .compatible = "apple,t6020-dcp", .data = &apple_dcp_hw_t6020, }, + { .compatible = "apple,t8112-dcp", .data = &apple_dcp_hw_t8112, }, + { .compatible = "apple,dcp", .data = &apple_dcp_hw_dcp, }, + { .compatible = "apple,dcpext", .data = &apple_dcp_hw_dcpext, }, + {} +}; +MODULE_DEVICE_TABLE(of, of_match); + +static struct platform_driver apple_platform_driver = { + .probe = dcp_platform_probe, + .remove = dcp_platform_remove, + .shutdown = dcp_platform_shutdown, + .driver = { + .name = "apple-dcp", + .of_match_table = of_match, + .pm = pm_sleep_ptr(&dcp_platform_pm_ops), + }, +}; + +void __init dcp_register(void) +{ + platform_driver_register(&apple_platform_driver); +} + +void __exit dcp_unregister(void) +{ + platform_driver_unregister(&apple_platform_driver); +} diff --git a/drivers/gpu/drm/apple/dcp.h b/drivers/gpu/drm/apple/dcp.h new file mode 100644 index 00000000000000..f3301fc9129cfc --- /dev/null +++ b/drivers/gpu/drm/apple/dcp.h @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2021 Alyssa Rosenzweig */ + +#ifndef __APPLE_DCP_H__ +#define __APPLE_DCP_H__ + +#include +#include +#include + +#include "connector.h" +#include "dcp-internal.h" +#include "parser.h" + +struct apple_crtc { + struct drm_crtc base; + struct drm_pending_vblank_event *event; + bool vsync_disabled; + + /* Reference to the DCP device owning this CRTC */ + struct platform_device *dcp; +}; + +#define to_apple_crtc(x) container_of(x, struct apple_crtc, base) + +struct apple_encoder { + struct drm_encoder base; +}; + +#define to_apple_encoder(x) container_of(x, struct apple_encoder, base) + +void dcp_poweroff(struct platform_device *pdev); +void dcp_poweron(struct platform_device *pdev); +int dcp_set_crc(struct drm_crtc *crtc, bool enabled); +int dcp_crtc_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state); +int dcp_get_connector_type(struct platform_device *pdev); +bool dcp_fw_compat_is_12_x(struct platform_device *pdev); +void dcp_link(struct platform_device *pdev, struct apple_crtc *apple, + struct apple_connector *connector); +int dcp_start(struct platform_device *pdev); +int dcp_wait_ready(struct platform_device *pdev, u64 timeout); +void dcp_flush(struct drm_crtc *crtc, struct drm_atomic_state *state); +bool dcp_is_initialized(struct platform_device *pdev); +void apple_crtc_vblank(struct apple_crtc *apple); +void dcp_drm_crtc_vblank(struct apple_crtc *crtc); +int dcp_get_modes(struct drm_connector *connector); +enum drm_mode_status dcp_mode_valid(struct drm_connector *connector, + const struct drm_display_mode *mode); +int dcp_crtc_atomic_modeset(struct drm_crtc *crtc, + struct drm_atomic_state *state); +bool dcp_crtc_mode_fixup(struct drm_crtc *crtc, + const struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode); +void dcp_set_dimensions(struct apple_dcp *dcp); +void dcp_send_message(struct apple_dcp *dcp, u8 endpoint, u64 message); + +int dcp_dptx_connect_oob(struct platform_device *pdev, u32 port); +int dcp_dptx_disconnect_oob(struct platform_device *pdev, u32 port); + +int iomfb_start_rtkit(struct apple_dcp *dcp); +void iomfb_shutdown(struct apple_dcp *dcp); +/* rtkit message handler for IOMFB messages */ +void iomfb_recv_msg(struct apple_dcp *dcp, u64 message); + +int systemep_init(struct apple_dcp *dcp); +int dptxep_init(struct apple_dcp *dcp); +int ibootep_init(struct apple_dcp *dcp); +int dpavservep_init(struct apple_dcp *dcp); +int avep_init(struct apple_dcp *dcp); + + +void __init dcp_register(void); +void __exit dcp_unregister(void); + +void __init dcp_audio_register(void); +void __exit dcp_audio_unregister(void); + +#endif diff --git a/drivers/gpu/drm/apple/dcp_backlight.c b/drivers/gpu/drm/apple/dcp_backlight.c new file mode 100644 index 00000000000000..9eb0c7d4eb5345 --- /dev/null +++ b/drivers/gpu/drm/apple/dcp_backlight.c @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright (C) The Asahi Linux Contributors */ + +#include +#include +#include +#include + +#include +#include +#include +#include "linux/jiffies.h" + +#include "dcp.h" +#include "dcp-internal.h" + +#define MIN_BRIGHTNESS_PART1 2U +#define MAX_BRIGHTNESS_PART1 99U +#define MIN_BRIGHTNESS_PART2 103U +#define MAX_BRIGHTNESS_PART2 510U + +/* + * lookup for display brightness 2 to 99 nits + * */ +static u32 brightness_part1[] = { + 0x0000000, 0x0810038, 0x0f000bd, 0x143011c, + 0x1850165, 0x1bc01a1, 0x1eb01d4, 0x2140200, + 0x2380227, 0x2590249, 0x2770269, 0x2930285, + 0x2ac02a0, 0x2c402b8, 0x2d902cf, 0x2ee02e4, + 0x30102f8, 0x314030b, 0x325031c, 0x335032d, + 0x345033d, 0x354034d, 0x362035b, 0x3700369, + 0x37d0377, 0x38a0384, 0x3960390, 0x3a2039c, + 0x3ad03a7, 0x3b803b3, 0x3c303bd, 0x3cd03c8, + 0x3d703d2, 0x3e103dc, 0x3ea03e5, 0x3f303ef, + 0x3fc03f8, 0x4050400, 0x40d0409, 0x4150411, + 0x41d0419, 0x4250421, 0x42d0429, 0x4340431, + 0x43c0438, 0x443043f, 0x44a0446, 0x451044d, + 0x4570454, 0x45e045b, 0x4640461, 0x46b0468, + 0x471046e, 0x4770474, 0x47d047a, 0x4830480, + 0x4890486, 0x48e048b, 0x4940491, 0x4990497, + 0x49f049c, 0x4a404a1, 0x4a904a7, 0x4ae04ac, + 0x4b304b1, 0x4b804b6, 0x4bd04bb, 0x4c204c0, + 0x4c704c5, 0x4cc04c9, 0x4d004ce, 0x4d504d3, + 0x4d904d7, 0x4de04dc, 0x4e204e0, 0x4e704e4, + 0x4eb04e9, 0x4ef04ed, 0x4f304f1, 0x4f704f5, + 0x4fb04f9, 0x4ff04fd, 0x5030501, 0x5070505, + 0x50b0509, 0x50f050d, 0x5130511, 0x5160515, + 0x51a0518, 0x51e051c, 0x5210520, 0x5250523, + 0x5290527, 0x52c052a, 0x52f052e, 0x5330531, + 0x5360535, 0x53a0538, 0x53d053b, 0x540053f, + 0x5440542, 0x5470545, 0x54a0548, 0x54d054c, + 0x550054f, 0x5530552, 0x5560555, 0x5590558, + 0x55c055b, 0x55f055e, 0x5620561, 0x5650564, + 0x5680567, 0x56b056a, 0x56e056d, 0x571056f, + 0x5740572, 0x5760575, 0x5790578, 0x57c057b, + 0x57f057d, 0x5810580, 0x5840583, 0x5870585, + 0x5890588, 0x58c058b, 0x58f058d +}; + +static u32 brightness_part12[] = { 0x58f058d, 0x59d058f }; + +/* + * lookup table for display brightness 103.3 to 510 nits + * */ +static u32 brightness_part2[] = { + 0x59d058f, 0x5b805ab, 0x5d105c5, 0x5e805dd, + 0x5fe05f3, 0x6120608, 0x625061c, 0x637062e, + 0x6480640, 0x6580650, 0x6680660, 0x677066f, + 0x685067e, 0x693068c, 0x6a00699, 0x6ac06a6, + 0x6b806b2, 0x6c406be, 0x6cf06ca, 0x6da06d5, + 0x6e506df, 0x6ef06ea, 0x6f906f4, 0x70206fe, + 0x70c0707, 0x7150710, 0x71e0719, 0x7260722, + 0x72f072a, 0x7370733, 0x73f073b, 0x7470743, + 0x74e074a, 0x7560752, 0x75d0759, 0x7640760, + 0x76b0768, 0x772076e, 0x7780775, 0x77f077c, + 0x7850782, 0x78c0789, 0x792078f, 0x7980795, + 0x79e079b, 0x7a407a1, 0x7aa07a7, 0x7af07ac, + 0x7b507b2, 0x7ba07b8, 0x7c007bd, 0x7c507c2, + 0x7ca07c8, 0x7cf07cd, 0x7d407d2, 0x7d907d7, + 0x7de07dc, 0x7e307e1, 0x7e807e5, 0x7ec07ea, + 0x7f107ef, 0x7f607f3, 0x7fa07f8, 0x7fe07fc +}; + + +static int dcp_get_brightness(struct backlight_device *bd) +{ + struct apple_dcp *dcp = bl_get_data(bd); + + return dcp->brightness.nits; +} + +#define SCALE_FACTOR (1 << 10) + +static u32 interpolate(int val, int min, int max, u32 *tbl, size_t tbl_size) +{ + u32 frac; + u64 low, high; + u32 interpolated = (tbl_size - 1) * ((val - min) * SCALE_FACTOR) / (max - min); + + size_t index = interpolated / SCALE_FACTOR; + + if (WARN(index + 1 >= tbl_size, "invalid index %zu for brightness %u\n", index, val)) + return tbl[tbl_size / 2]; + + frac = interpolated & (SCALE_FACTOR - 1); + low = tbl[index]; + high = tbl[index + 1]; + + return ((frac * high) + ((SCALE_FACTOR - frac) * low)) / SCALE_FACTOR; +} + +static u32 calculate_dac(struct apple_dcp *dcp, int val) +{ + u32 dac; + + if (val <= MIN_BRIGHTNESS_PART1) + return 16 * brightness_part1[0]; + else if (val == MAX_BRIGHTNESS_PART1) + return 16 * brightness_part1[ARRAY_SIZE(brightness_part1) - 1]; + else if (val == MIN_BRIGHTNESS_PART2) + return 16 * brightness_part2[0]; + else if (val >= MAX_BRIGHTNESS_PART2) + return brightness_part2[ARRAY_SIZE(brightness_part2) - 1]; + + if (val < MAX_BRIGHTNESS_PART1) { + dac = interpolate(val, MIN_BRIGHTNESS_PART1, MAX_BRIGHTNESS_PART1, + brightness_part1, ARRAY_SIZE(brightness_part1)); + } else if (val > MIN_BRIGHTNESS_PART2) { + dac = interpolate(val, MIN_BRIGHTNESS_PART2, MAX_BRIGHTNESS_PART2, + brightness_part2, ARRAY_SIZE(brightness_part2)); + } else { + dac = interpolate(val, MAX_BRIGHTNESS_PART1, MIN_BRIGHTNESS_PART2, + brightness_part12, ARRAY_SIZE(brightness_part12)); + } + + return 16 * dac; +} + +static int drm_crtc_set_brightness(struct apple_dcp *dcp) +{ + struct drm_atomic_state *state; + struct drm_crtc_state *crtc_state; + struct drm_modeset_acquire_ctx ctx; + struct drm_crtc *crtc = &dcp->crtc->base; + int ret = 0; + + drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE); + ret = drm_modeset_lock(&crtc->mutex, &ctx); + if (ret == -EDEADLK) { + drm_modeset_backoff(&ctx); + return -EDEADLK; + } else if (ret == -ERESTARTSYS) { + return -ERESTARTSYS; + } + + if (!dcp->brightness.update) + goto done; + + state = drm_atomic_state_alloc(crtc->dev); + if (!state) { + ret = -ENOMEM; + goto done; + } + + state->acquire_ctx = &ctx; + crtc_state = drm_atomic_get_crtc_state(state, crtc); + if (IS_ERR(crtc_state)) { + ret = PTR_ERR(crtc_state); + goto fail; + } + + crtc_state->color_mgmt_changed |= true; + + ret = drm_atomic_commit(state); + +fail: + drm_atomic_state_put(state); +done: + drm_modeset_drop_locks(&ctx); + + return ret; +} + +int dcp_backlight_update(struct apple_dcp *dcp) +{ + /* + * Do not actively try to change brightness if no mode is set. + * TODO: should this be reflected the in backlight's power property? + * defer this hopefully until it becomes irrelevant due to proper + * drm integrated backlight handling + */ + if (!dcp->valid_mode) + return 0; + + /* Wait 1 vblank cycle in the hope an atomic swap has already updated + * the brightness */ + msleep((1001 + 23) / 24); // 42ms for 23.976 fps + + return drm_crtc_set_brightness(dcp); +} + +static int dcp_set_brightness(struct backlight_device *bd) +{ + int ret = 0; + struct apple_dcp *dcp = bl_get_data(bd); + struct drm_modeset_acquire_ctx ctx; + int brightness = backlight_get_brightness(bd); + + drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE); + ret = drm_modeset_lock(&dcp->crtc->base.mutex, &ctx); + if (ret == -EDEADLK) { + drm_modeset_backoff(&ctx); + return -EDEADLK; + } else if (ret == -ERESTARTSYS) { + return -ERESTARTSYS; + } + + dcp->brightness.dac = calculate_dac(dcp, brightness); + dcp->brightness.update = true; + + drm_modeset_drop_locks(&ctx); + + return dcp_backlight_update(dcp); +} + +static const struct backlight_ops dcp_backlight_ops = { + .options = BL_CORE_SUSPENDRESUME, + .get_brightness = dcp_get_brightness, + .update_status = dcp_set_brightness, +}; + +int dcp_backlight_register(struct apple_dcp *dcp) +{ + struct device *dev = dcp->dev; + struct backlight_device *bl_dev; + struct backlight_properties props = { + .type = BACKLIGHT_PLATFORM, + .brightness = dcp->brightness.nits, + .scale = BACKLIGHT_SCALE_LINEAR, + }; + props.max_brightness = min(dcp->brightness.maximum, MAX_BRIGHTNESS_PART2 - 1); + + bl_dev = devm_backlight_device_register(dev, "apple-panel-bl", dev, dcp, + &dcp_backlight_ops, &props); + if (IS_ERR(bl_dev)) + return PTR_ERR(bl_dev); + + dcp->brightness.bl_dev = bl_dev; + dcp->brightness.dac = calculate_dac(dcp, dcp->brightness.nits); + + return 0; +} diff --git a/drivers/gpu/drm/apple/dcp_trace.c b/drivers/gpu/drm/apple/dcp_trace.c new file mode 100644 index 00000000000000..d18e71af73a74d --- /dev/null +++ b/drivers/gpu/drm/apple/dcp_trace.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define CREATE_TRACE_POINTS +#include "dcp_trace.h" \ No newline at end of file diff --git a/drivers/gpu/drm/apple/dptxep.c b/drivers/gpu/drm/apple/dptxep.c new file mode 100644 index 00000000000000..e21299e0124035 --- /dev/null +++ b/drivers/gpu/drm/apple/dptxep.c @@ -0,0 +1,640 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2022 Sven Peter */ + +#include +#include +#include +#include + +#include "afk.h" +#include "dcp.h" +#include "dptxep.h" +#include "parser.h" +#include "trace.h" + +struct dcpdptx_connection_cmd { + __le32 unk; + __le32 target; +} __attribute__((packed)); + +struct dcpdptx_hotplug_cmd { + u8 _pad0[16]; + __le32 unk; +} __attribute__((packed)); + +struct dptxport_apcall_link_rate { + __le32 retcode; + u8 _unk0[12]; + __le32 link_rate; + u8 _unk1[12]; +} __attribute__((packed)); + +struct dptxport_apcall_lane_count { + __le32 retcode; + u8 _unk0[12]; + __le64 lane_count; + u8 _unk1[8]; +} __attribute__((packed)); + +struct dptxport_apcall_set_active_lane_count { + __le32 retcode; + u8 _unk0[12]; + __le64 lane_count; + u8 _unk1[8]; +} __packed; + +struct dptxport_apcall_get_support { + __le32 retcode; + u8 _unk0[12]; + __le32 supported; + u8 _unk1[12]; +} __attribute__((packed)); + +struct dptxport_apcall_max_drive_settings { + __le32 retcode; + u8 _unk0[12]; + __le32 max_drive_settings[2]; + u8 _unk1[8]; +}; + +struct dptxport_apcall_drive_settings { + __le32 retcode; + u8 _unk0[12]; + __le32 unk1; + __le32 unk2; + __le32 unk3; + __le32 unk4; + __le32 unk5; + __le32 unk6; + __le32 unk7; +}; + +int dptxport_validate_connection(struct apple_epic_service *service, u8 core, + u8 atc, u8 die) +{ + struct dptx_port *dptx = service->cookie; + struct dcpdptx_connection_cmd cmd, resp; + int ret; + u32 target = FIELD_PREP(DCPDPTX_REMOTE_PORT_CORE, core) | + FIELD_PREP(DCPDPTX_REMOTE_PORT_ATC, atc) | + FIELD_PREP(DCPDPTX_REMOTE_PORT_DIE, die) | + DCPDPTX_REMOTE_PORT_CONNECTED; + + trace_dptxport_validate_connection(dptx, core, atc, die); + + cmd.target = cpu_to_le32(target); + cmd.unk = cpu_to_le32(0x100); + ret = afk_service_call(service, 0, 12, &cmd, sizeof(cmd), 40, &resp, + sizeof(resp), 40); + if (ret) + return ret; + + if (le32_to_cpu(resp.target) != target) + return -EINVAL; + if (le32_to_cpu(resp.unk) != 0x100) + return -EINVAL; + + return 0; +} + +int dptxport_connect(struct apple_epic_service *service, u8 core, u8 atc, + u8 die) +{ + struct dptx_port *dptx = service->cookie; + struct dcpdptx_connection_cmd cmd, resp; + u32 unk_field = 0x0; // seen as 0x100 under some conditions + int ret; + u32 target = FIELD_PREP(DCPDPTX_REMOTE_PORT_CORE, core) | + FIELD_PREP(DCPDPTX_REMOTE_PORT_ATC, atc) | + FIELD_PREP(DCPDPTX_REMOTE_PORT_DIE, die) | + DCPDPTX_REMOTE_PORT_CONNECTED; + + trace_dptxport_connect(dptx, core, atc, die); + + cmd.target = cpu_to_le32(target); + cmd.unk = cpu_to_le32(unk_field); + ret = afk_service_call(service, 0, 11, &cmd, sizeof(cmd), 24, &resp, + sizeof(resp), 24); + if (ret) + return ret; + + if (le32_to_cpu(resp.target) != target) + return -EINVAL; + if (le32_to_cpu(resp.unk) != unk_field) + dev_notice(service->ep->dcp->dev, "unexpected unk field in reply: 0x%x (0x%x)\n", + le32_to_cpu(resp.unk), unk_field); + + return 0; +} + +int dptxport_request_display(struct apple_epic_service *service) +{ + return afk_service_call(service, 0, 6, NULL, 0, 16, NULL, 0, 16); +} + +int dptxport_release_display(struct apple_epic_service *service) +{ + return afk_service_call(service, 0, 7, NULL, 0, 16, NULL, 0, 16); +} + +int dptxport_set_hpd(struct apple_epic_service *service, bool hpd) +{ + struct dcpdptx_hotplug_cmd cmd, resp; + int ret; + + memset(&cmd, 0, sizeof(cmd)); + + if (hpd) + cmd.unk = cpu_to_le32(1); + + ret = afk_service_call(service, 8, 8, &cmd, sizeof(cmd), 12, &resp, + sizeof(resp), 12); + if (ret) + return ret; + if (le32_to_cpu(resp.unk) != 1) + return -EINVAL; + return 0; +} + +static int +dptxport_call_get_max_drive_settings(struct apple_epic_service *service, + void *reply_, size_t reply_size) +{ + struct dptxport_apcall_max_drive_settings *reply = reply_; + + if (reply_size < sizeof(*reply)) + return -EINVAL; + + reply->retcode = cpu_to_le32(0); + reply->max_drive_settings[0] = cpu_to_le32(0x3); + reply->max_drive_settings[1] = cpu_to_le32(0x3); + + return 0; +} + +static int +dptxport_call_get_drive_settings(struct apple_epic_service *service, + const void *request_, size_t request_size, + void *reply_, size_t reply_size) +{ + struct dptx_port *dptx = service->cookie; + const struct dptxport_apcall_drive_settings *request = request_; + struct dptxport_apcall_drive_settings *reply = reply_; + + if (reply_size < sizeof(*reply) || request_size < sizeof(*request)) + return -EINVAL; + + *reply = *request; + + /* Clear the rest of the buffer */ + memset(reply_ + sizeof(*reply), 0, reply_size - sizeof(*reply)); + + /* + * retcode appears to be lane count, seeing 2 for USB-C dp alt mode + * with lanes splitted for DP/USB3. + */ + if (reply->retcode != dptx->lane_count) + dev_err(service->ep->dcp->dev, + "get_drive_settings: unexpected retcode %d\n", + reply->retcode); + + reply->retcode = dptx->lane_count; + reply->unk5 = dptx->drive_settings[0]; + reply->unk6 = 0; + reply->unk7 = dptx->drive_settings[1]; + + return 0; +} + +static int +dptxport_call_set_drive_settings(struct apple_epic_service *service, + const void *request_, size_t request_size, + void *reply_, size_t reply_size) +{ + struct dptx_port *dptx = service->cookie; + const struct dptxport_apcall_drive_settings *request = request_; + struct dptxport_apcall_drive_settings *reply = reply_; + + if (reply_size < sizeof(*reply) || request_size < sizeof(*request)) + return -EINVAL; + + *reply = *request; + reply->retcode = cpu_to_le32(0); + + dev_info(service->ep->dcp->dev, "set_drive_settings: %d:%d:%d:%d:%d:%d:%d\n", + request->unk1, request->unk2, request->unk3, request->unk4, + request->unk5, request->unk6, request->unk7); + + dptx->drive_settings[0] = reply->unk5; + dptx->drive_settings[1] = reply->unk7; + + return 0; +} + +static int dptxport_call_get_max_link_rate(struct apple_epic_service *service, + void *reply_, size_t reply_size) +{ + struct dptxport_apcall_link_rate *reply = reply_; + + if (reply_size < sizeof(*reply)) + return -EINVAL; + + reply->retcode = cpu_to_le32(0); + reply->link_rate = cpu_to_le32(LINK_RATE_HBR3); + + return 0; +} + +static int dptxport_call_get_max_lane_count(struct apple_epic_service *service, + void *reply_, size_t reply_size) +{ + struct dptxport_apcall_lane_count *reply = reply_; + struct dptx_port *dptx = service->cookie; + struct apple_dcp *dcp = service->ep->dcp; + union phy_configure_opts phy_ops; + int ret; + + if (reply_size < sizeof(*reply)) + return -EINVAL; + + ret = phy_validate(dptx->atcphy, PHY_MODE_DP, 0, &phy_ops); + if (ret < 0) { + dev_err(dcp->dev, "phy_validate failed: %d\n", ret); + reply->retcode = cpu_to_le32(1); + reply->lane_count = cpu_to_le64(0); + } else { + if (phy_ops.dp.lanes < 2) { + // phy_validate might return 0 lanes if atc phy is not + // yet switched to DP mode + dev_dbg(dcp->dev, "get_max_lane_count: phy lanes: %d\n", + phy_ops.dp.lanes); + // default to 4 lanes + dptx->lane_count = 4; + } else { + dptx->lane_count = phy_ops.dp.lanes; + } + reply->retcode = cpu_to_le32(0); + reply->lane_count = cpu_to_le64(dptx->lane_count); + } + + return 0; +} + +static int dptxport_call_set_active_lane_count(struct apple_epic_service *service, + const void *data, size_t data_size, + void *reply_, size_t reply_size) +{ + struct dptx_port *dptx = service->cookie; + struct apple_dcp *dcp = service->ep->dcp; + const struct dptxport_apcall_set_active_lane_count *request = data; + struct dptxport_apcall_set_active_lane_count *reply = reply_; + int ret = 0; + int retcode = 0; + + if (reply_size < sizeof(*reply)) + return -1; + if (data_size < sizeof(*request)) + return -1; + + u64 lane_count = cpu_to_le64(request->lane_count); + + if (dptx->lane_count < lane_count) + dev_err(dcp->dev, "set_active_lane_count: unexpected lane " + "count:%llu phy: %d\n", lane_count, dptx->lane_count); + + switch (lane_count) { + case 0 ... 2: + case 4: + dptx->phy_ops.dp.lanes = lane_count; + // Use dptx phy index > 3 as indication for dptx-phy or + // lpdptx-phy and configure the number of lanes for those + dptx->phy_ops.dp.set_lanes = (dcp->dptx_phy > 3); + break; + default: + dev_err(dcp->dev, "set_active_lane_count: invalid lane count:%llu\n", lane_count); + retcode = 1; + lane_count = 0; + break; + } + + if (dptx->phy_ops.dp.set_lanes) { + if (dptx->atcphy) { + ret = phy_configure(dptx->atcphy, &dptx->phy_ops); + if (ret) + return ret; + } + dptx->phy_ops.dp.set_lanes = 0; + dptx->lane_count = lane_count; + } + + reply->retcode = cpu_to_le32(retcode); + reply->lane_count = cpu_to_le64(lane_count); + + if (lane_count > 0) + complete(&dptx->linkcfg_completion); + + return ret; +} + +static int dptxport_call_get_link_rate(struct apple_epic_service *service, + void *reply_, size_t reply_size) +{ + struct dptx_port *dptx = service->cookie; + struct dptxport_apcall_link_rate *reply = reply_; + + if (reply_size < sizeof(*reply)) + return -EINVAL; + + reply->retcode = cpu_to_le32(0); + reply->link_rate = cpu_to_le32(dptx->link_rate); + + return 0; +} + +static int +dptxport_call_will_change_link_config(struct apple_epic_service *service) +{ + struct dptx_port *dptx = service->cookie; + + dptx->phy_ops.dp.set_lanes = 0; + dptx->phy_ops.dp.set_rate = 0; + dptx->phy_ops.dp.set_voltages = 0; + + return 0; +} + +static int +dptxport_call_did_change_link_config(struct apple_epic_service *service) +{ + /* assume the link config did change and wait a little bit */ + mdelay(10); + + return 0; +} + +static int dptxport_call_set_link_rate(struct apple_epic_service *service, + const void *data, size_t data_size, + void *reply_, size_t reply_size) +{ + struct dptx_port *dptx = service->cookie; + const struct dptxport_apcall_link_rate *request = data; + struct dptxport_apcall_link_rate *reply = reply_; + u32 link_rate, phy_link_rate; + bool phy_set_rate = false; + int ret; + + if (reply_size < sizeof(*reply)) + return -EINVAL; + if (data_size < sizeof(*request)) + return -EINVAL; + + link_rate = le32_to_cpu(request->link_rate); + trace_dptxport_call_set_link_rate(dptx, link_rate); + + switch (link_rate) { + case LINK_RATE_RBR: + phy_link_rate = 1620; + phy_set_rate = true; + break; + case LINK_RATE_HBR: + phy_link_rate = 2700; + phy_set_rate = true; + break; + case LINK_RATE_HBR2: + phy_link_rate = 5400; + phy_set_rate = true; + break; + case LINK_RATE_HBR3: + phy_link_rate = 8100; + phy_set_rate = true; + break; + case 0: + phy_link_rate = 0; + phy_set_rate = true; + break; + default: + dev_err(service->ep->dcp->dev, + "DPTXPort: Unsupported link rate 0x%x requested\n", + link_rate); + link_rate = 0; + phy_set_rate = false; + break; + } + + if (phy_set_rate) { + dptx->phy_ops.dp.link_rate = phy_link_rate; + dptx->phy_ops.dp.set_rate = 1; + + if (dptx->atcphy) { + ret = phy_configure(dptx->atcphy, &dptx->phy_ops); + if (ret) + return ret; + } + + //if (dptx->phy_ops.dp.set_rate) + dptx->link_rate = dptx->pending_link_rate = link_rate; + + } + + //dptx->pending_link_rate = link_rate; + reply->retcode = cpu_to_le32(0); + reply->link_rate = cpu_to_le32(link_rate); + + return 0; +} + +static int dptxport_call_get_supports_hpd(struct apple_epic_service *service, + void *reply_, size_t reply_size) +{ + struct dptxport_apcall_get_support *reply = reply_; + + if (reply_size < sizeof(*reply)) + return -EINVAL; + + reply->retcode = cpu_to_le32(0); + reply->supported = cpu_to_le32(0); + return 0; +} + +static int +dptxport_call_get_supports_downspread(struct apple_epic_service *service, + void *reply_, size_t reply_size) +{ + struct dptxport_apcall_get_support *reply = reply_; + + if (reply_size < sizeof(*reply)) + return -EINVAL; + + reply->retcode = cpu_to_le32(0); + reply->supported = cpu_to_le32(0); + return 0; +} + +static int +dptxport_call_activate(struct apple_epic_service *service, + const void *data, size_t data_size, + void *reply, size_t reply_size) +{ + struct dptx_port *dptx = service->cookie; + const struct apple_dcp *dcp = service->ep->dcp; + + // TODO: hack, use phy_set_mode to select the correct DCP(EXT) input + // for standalone phy (i.e. not atc phy). + if (!dcp->typec_mux) + phy_set_mode_ext(dptx->atcphy, PHY_MODE_DP, dcp->index); + + memcpy(reply, data, min(reply_size, data_size)); + if (reply_size >= 4) + memset(reply, 0, 4); + + return 0; +} + +static int +dptxport_call_deactivate(struct apple_epic_service *service, + const void *data, size_t data_size, + void *reply, size_t reply_size) +{ + struct dptx_port *dptx = service->cookie; + + /* deactivate phy */ + phy_set_mode_ext(dptx->atcphy, PHY_MODE_INVALID, 0); + + memcpy(reply, data, min(reply_size, data_size)); + if (reply_size >= 4) + memset(reply, 0, 4); + + return 0; +} + +static int dptxport_call(struct apple_epic_service *service, u32 idx, + const void *data, size_t data_size, void *reply, + size_t reply_size) +{ + struct dptx_port *dptx = service->cookie; + trace_dptxport_apcall(dptx, idx, data_size); + + switch (idx) { + case DPTX_APCALL_WILL_CHANGE_LINKG_CONFIG: + return dptxport_call_will_change_link_config(service); + case DPTX_APCALL_DID_CHANGE_LINK_CONFIG: + return dptxport_call_did_change_link_config(service); + case DPTX_APCALL_GET_MAX_LINK_RATE: + return dptxport_call_get_max_link_rate(service, reply, + reply_size); + case DPTX_APCALL_GET_LINK_RATE: + return dptxport_call_get_link_rate(service, reply, reply_size); + case DPTX_APCALL_SET_LINK_RATE: + return dptxport_call_set_link_rate(service, data, data_size, + reply, reply_size); + case DPTX_APCALL_GET_MAX_LANE_COUNT: + return dptxport_call_get_max_lane_count(service, reply, reply_size); + case DPTX_APCALL_SET_ACTIVE_LANE_COUNT: + return dptxport_call_set_active_lane_count(service, data, data_size, + reply, reply_size); + case DPTX_APCALL_GET_SUPPORTS_HPD: + return dptxport_call_get_supports_hpd(service, reply, + reply_size); + case DPTX_APCALL_GET_SUPPORTS_DOWN_SPREAD: + return dptxport_call_get_supports_downspread(service, reply, + reply_size); + case DPTX_APCALL_GET_MAX_DRIVE_SETTINGS: + return dptxport_call_get_max_drive_settings(service, reply, + reply_size); + case DPTX_APCALL_GET_DRIVE_SETTINGS: + return dptxport_call_get_drive_settings(service, data, data_size, + reply, reply_size); + case DPTX_APCALL_SET_DRIVE_SETTINGS: + return dptxport_call_set_drive_settings(service, data, data_size, + reply, reply_size); + case DPTX_APCALL_ACTIVATE: + return dptxport_call_activate(service, data, data_size, + reply, reply_size); + case DPTX_APCALL_DEACTIVATE: + return dptxport_call_deactivate(service, data, data_size, + reply, reply_size); + default: + /* just try to ACK and hope for the best... */ + dev_info(service->ep->dcp->dev, "DPTXPort: acking unhandled call %u\n", + idx); + fallthrough; + case DPTX_APCALL_GET_DOWN_SPREAD: + case DPTX_APCALL_SET_DOWN_SPREAD: + memcpy(reply, data, min(reply_size, data_size)); + if (reply_size >= 4) + memset(reply, 0, 4); + return 0; + } +} + +static void dptxport_init(struct apple_epic_service *service, const char *name, + const char *class, s64 unit) +{ + + if (strcmp(name, "dcpdptx-port-epic")) + return; + if (strcmp(class, "AppleDCPDPTXRemotePort")) + return; + + trace_dptxport_init(service->ep->dcp, unit); + + switch (unit) { + case 0: + case 1: + if (service->ep->dcp->dptxport[unit].enabled) { + dev_err(service->ep->dcp->dev, + "DPTXPort: unit %lld already exists\n", unit); + return; + } + service->ep->dcp->dptxport[unit].unit = unit; + service->ep->dcp->dptxport[unit].service = service; + service->ep->dcp->dptxport[unit].enabled = true; + service->cookie = (void *)&service->ep->dcp->dptxport[unit]; + complete(&service->ep->dcp->dptxport[unit].enable_completion); + break; + default: + dev_err(service->ep->dcp->dev, "DPTXPort: invalid unit %lld\n", + unit); + } +} + +static const struct apple_epic_service_ops dptxep_ops[] = { + { + .name = "AppleDCPDPTXRemotePort", + .init = dptxport_init, + .call = dptxport_call, + }, + {} +}; + +int dptxep_init(struct apple_dcp *dcp) +{ + int ret; + u32 port; + unsigned long timeout = msecs_to_jiffies(1000); + + init_completion(&dcp->dptxport[0].enable_completion); + init_completion(&dcp->dptxport[1].enable_completion); + init_completion(&dcp->dptxport[0].linkcfg_completion); + init_completion(&dcp->dptxport[1].linkcfg_completion); + + dcp->dptxep = afk_init(dcp, DPTX_ENDPOINT, dptxep_ops); + if (IS_ERR(dcp->dptxep)) + return PTR_ERR(dcp->dptxep); + + ret = afk_start(dcp->dptxep); + if (ret) + return ret; + + for (port = 0; port < dcp->hw.num_dptx_ports; port++) { + ret = wait_for_completion_timeout(&dcp->dptxport[port].enable_completion, + timeout); + if (!ret) + return -ETIMEDOUT; + else if (ret < 0) + return ret; + timeout = ret; + } + + return 0; +} diff --git a/drivers/gpu/drm/apple/dptxep.h b/drivers/gpu/drm/apple/dptxep.h new file mode 100644 index 00000000000000..0bf2534054fd7b --- /dev/null +++ b/drivers/gpu/drm/apple/dptxep.h @@ -0,0 +1,70 @@ +#ifndef __APPLE_DCP_DPTXEP_H__ +#define __APPLE_DCP_DPTXEP_H__ + +#include +#include + +enum dptx_apcall { + DPTX_APCALL_ACTIVATE = 0, + DPTX_APCALL_DEACTIVATE = 1, + DPTX_APCALL_GET_MAX_DRIVE_SETTINGS = 2, + DPTX_APCALL_SET_DRIVE_SETTINGS = 3, + DPTX_APCALL_GET_DRIVE_SETTINGS = 4, + DPTX_APCALL_WILL_CHANGE_LINKG_CONFIG = 5, + DPTX_APCALL_DID_CHANGE_LINK_CONFIG = 6, + DPTX_APCALL_GET_MAX_LINK_RATE = 7, + DPTX_APCALL_GET_LINK_RATE = 8, + DPTX_APCALL_SET_LINK_RATE = 9, + DPTX_APCALL_GET_MAX_LANE_COUNT = 10, + DPTX_APCALL_GET_ACTIVE_LANE_COUNT = 11, + DPTX_APCALL_SET_ACTIVE_LANE_COUNT = 12, + DPTX_APCALL_GET_SUPPORTS_DOWN_SPREAD = 13, + DPTX_APCALL_GET_DOWN_SPREAD = 14, + DPTX_APCALL_SET_DOWN_SPREAD = 15, + DPTX_APCALL_GET_SUPPORTS_LANE_MAPPING = 16, + DPTX_APCALL_SET_LANE_MAP = 17, + DPTX_APCALL_GET_SUPPORTS_HPD = 18, + DPTX_APCALL_FORCE_HOTPLUG_DETECT = 19, + DPTX_APCALL_INACTIVE_SINK_DETECTED = 20, + DPTX_APCALL_SET_TILED_DISPLAY_HINTS = 21, + DPTX_APCALL_DEVICE_NOT_RESPONDING = 22, + DPTX_APCALL_DEVICE_BUSY_TIMEOUT = 23, + DPTX_APCALL_DEVICE_NOT_STARTED = 24, +}; + +#define DCPDPTX_REMOTE_PORT_CORE GENMASK(3, 0) +#define DCPDPTX_REMOTE_PORT_ATC GENMASK(7, 4) +#define DCPDPTX_REMOTE_PORT_DIE GENMASK(11, 8) +#define DCPDPTX_REMOTE_PORT_CONNECTED BIT(15) + +enum dptx_link_rate { + LINK_RATE_RBR = 0x06, + LINK_RATE_HBR = 0x0a, + LINK_RATE_HBR2 = 0x14, + LINK_RATE_HBR3 = 0x1e, +}; + +struct apple_epic_service; + +struct dptx_port { + bool enabled, connected; + struct completion enable_completion; + struct completion linkcfg_completion; + u32 unit; + struct apple_epic_service *service; + union phy_configure_opts phy_ops; + struct phy *atcphy; + struct mux_control *mux; + u32 lane_count; + u32 link_rate, pending_link_rate; + u32 drive_settings[2]; +}; + +int dptxport_validate_connection(struct apple_epic_service *service, u8 core, + u8 atc, u8 die); +int dptxport_connect(struct apple_epic_service *service, u8 core, u8 atc, + u8 die); +int dptxport_request_display(struct apple_epic_service *service); +int dptxport_release_display(struct apple_epic_service *service); +int dptxport_set_hpd(struct apple_epic_service *service, bool hpd); +#endif diff --git a/drivers/gpu/drm/apple/epic/dpavservep.c b/drivers/gpu/drm/apple/epic/dpavservep.c new file mode 100644 index 00000000000000..2de9d2fe4c24a3 --- /dev/null +++ b/drivers/gpu/drm/apple/epic/dpavservep.c @@ -0,0 +1,233 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright The Asahi Linux Contributors */ + +#include "dpavservep.h" + +#include + +#include +#include +#include + +#include "../afk.h" +#include "../dcp.h" +#include "../dcp-internal.h" +#include "../trace.h" + +static void dcpavserv_init(struct apple_epic_service *service, const char *name, + const char *class, s64 unit) +{ + struct apple_dcp *dcp = service->ep->dcp; + trace_dcpavserv_init(dcp, unit); + + if (unit == 0 && name && !strcmp(name, "dcpav-service-epic")) { + if (dcp->dcpavserv.enabled) { + dev_err(dcp->dev, + "DCPAVSERV: unit %lld already exists\n", unit); + return; + } + dcp->dcpavserv.service = service; + dcp->dcpavserv.enabled = true; + service->cookie = &dcp->dcpavserv; + complete(&dcp->dcpavserv.enable_completion); + } +} + +static void dcpavserv_teardown(struct apple_epic_service *service) +{ + struct apple_dcp *dcp = service->ep->dcp; + service->enabled = false; + + if (dcp->dcpavserv.enabled) { + dcp->dcpavserv.enabled = false; + dcp->dcpavserv.service = NULL; + service->cookie = NULL; + reinit_completion(&dcp->dcpavserv.enable_completion); + } +} + +static void dcpdpserv_init(struct apple_epic_service *service, const char *name, + const char *class, s64 unit) +{ +} + +static void dcpdpserv_teardown(struct apple_epic_service *service) +{ + service->enabled = false; +} + +struct dcpavserv_status_report { + u32 unk00[4]; + u8 flag0; + u8 flag1; + u8 flag2; + u8 flag3; + u32 unk14[3]; + u32 status; + u32 unk24[3]; +} __packed; + +struct dpavserv_copy_edid_cmd { + __le64 max_size; + u8 _pad1[24]; + __le64 used_size; + u8 _pad2[8]; +} __packed; + +#define EDID_LEADING_DATA_SIZE 8 +#define EDID_BLOCK_SIZE 128 +#define EDID_EXT_BLOCK_COUNT_OFFSET 0x7E +#define EDID_MAX_SIZE SZ_32K +#define EDID_BUF_SIZE (EDID_LEADING_DATA_SIZE + EDID_MAX_SIZE) + +struct dpavserv_copy_edid_resp { + __le64 max_size; + u8 _pad1[24]; + __le64 used_size; + u8 _pad2[8]; + u8 data[]; +} __packed; + +static int parse_report(struct apple_epic_service *service, enum epic_subtype type, + const void *data, size_t data_size) +{ +#if defined(DEBUG) + struct apple_dcp *dcp = service->ep->dcp; + const struct epic_service_call *call; + const void *payload; + size_t payload_size; + + dev_dbg(dcp->dev, "dcpavserv[ch:%u]: report type:%02x len:%zu\n", + service->channel, type, data_size); + + if (type != EPIC_SUBTYPE_STD_SERVICE) + return 0; + + if (data_size < sizeof(*call)) + return 0; + + call = data; + + if (le32_to_cpu(call->magic) != EPIC_SERVICE_CALL_MAGIC) { + dev_warn(dcp->dev, "dcpavserv[ch:%u]: report magic 0x%08x != 0x%08x\n", + service->channel, le32_to_cpu(call->magic), EPIC_SERVICE_CALL_MAGIC); + return 0; + } + + payload_size = data_size - sizeof(*call); + if (payload_size < le32_to_cpu(call->data_len)) { + dev_warn(dcp->dev, "dcpavserv[ch:%u]: report payload size %zu call len %u\n", + service->channel, payload_size, le32_to_cpu(call->data_len)); + return 0; + } + payload_size = le32_to_cpu(call->data_len); + payload = data + sizeof(*call); + + if (le16_to_cpu(call->group) == 2 && le16_to_cpu(call->command) == 0) { + if (payload_size == sizeof(struct dcpavserv_status_report)) { + const struct dcpavserv_status_report *stat = payload; + dev_info(dcp->dev, "dcpavserv[ch:%u]: flags: 0x%02x,0x%02x,0x%02x,0x%02x status:%u\n", + service->channel, stat->flag0, stat->flag1, + stat->flag2, stat->flag3, stat->status); + } else { + dev_dbg(dcp->dev, "dcpavserv[ch:%u]: report payload size %zu\n", service->channel, payload_size); + } + } else { + print_hex_dump(KERN_DEBUG, "dcpavserv report: ", DUMP_PREFIX_NONE, + 16, 1, payload, payload_size, true); + } +#endif + + return 0; +} + +static int dcpavserv_report(struct apple_epic_service *service, + enum epic_subtype type, const void *data, + size_t data_size) +{ + return parse_report(service, type, data, data_size); +} + +static int dcpdpserv_report(struct apple_epic_service *service, + enum epic_subtype type, const void *data, + size_t data_size) +{ + return parse_report(service, type, data, data_size); +} + +const struct drm_edid *dcpavserv_copy_edid(struct apple_epic_service *service) +{ + struct dpavserv_copy_edid_cmd cmd; + struct dpavserv_copy_edid_resp *resp __free(kfree) = NULL; + int num_blocks; + u64 data_size; + int ret; + + memset(&cmd, 0, sizeof(cmd)); + cmd.max_size = cpu_to_le64(EDID_BUF_SIZE); + resp = kzalloc(sizeof(*resp) + EDID_BUF_SIZE, GFP_KERNEL); + if (!resp) + return ERR_PTR(-ENOMEM); + + ret = afk_service_call(service, 1, 7, &cmd, sizeof(cmd), EDID_BUF_SIZE, resp, + sizeof(resp) + EDID_BUF_SIZE, 0); + if (ret < 0) + return ERR_PTR(ret); + + if (le64_to_cpu(resp->max_size) != EDID_BUF_SIZE) + return ERR_PTR(-EIO); + + // print_hex_dump(KERN_DEBUG, "dpavserv EDID cmd: ", DUMP_PREFIX_NONE, + // 16, 1, resp, 192, true); + + data_size = le64_to_cpu(resp->used_size); + if (data_size < EDID_LEADING_DATA_SIZE + EDID_BLOCK_SIZE) + return ERR_PTR(-EIO); + + num_blocks = resp->data[EDID_LEADING_DATA_SIZE + EDID_EXT_BLOCK_COUNT_OFFSET]; + if ((1 + num_blocks) * EDID_BLOCK_SIZE != data_size - EDID_LEADING_DATA_SIZE) + return ERR_PTR(-EIO); + + return drm_edid_alloc(resp->data + EDID_LEADING_DATA_SIZE, + data_size - EDID_LEADING_DATA_SIZE); +} + +static const struct apple_epic_service_ops dpavservep_ops[] = { + { + .name = "dcpav-service-epic", + .init = dcpavserv_init, + .teardown = dcpavserv_teardown, + .report = dcpavserv_report, + }, + { + .name = "dcpdp-service-epic", + .init = dcpdpserv_init, + .teardown = dcpdpserv_teardown, + .report = dcpdpserv_report, + }, + {}, +}; + +int dpavservep_init(struct apple_dcp *dcp) +{ + int ret; + + init_completion(&dcp->dcpavserv.enable_completion); + + dcp->dcpavservep = afk_init(dcp, DPAVSERV_ENDPOINT, dpavservep_ops); + if (IS_ERR(dcp->dcpavservep)) + return PTR_ERR(dcp->dcpavservep); + + dcp->dcpavservep->match_epic_name = true; + + ret = afk_start(dcp->dcpavservep); + if (ret) + return ret; + + ret = wait_for_completion_timeout(&dcp->dcpavserv.enable_completion, + msecs_to_jiffies(1000)); + if (ret >= 0) + return 0; + + return ret; +} diff --git a/drivers/gpu/drm/apple/epic/dpavservep.h b/drivers/gpu/drm/apple/epic/dpavservep.h new file mode 100644 index 00000000000000..858ff14b0bd7be --- /dev/null +++ b/drivers/gpu/drm/apple/epic/dpavservep.h @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright The Asahi Linux Contributors */ + +#ifndef _DRM_APPLE_EPIC_DPAVSERV_H +#define _DRM_APPLE_EPIC_DPAVSERV_H + +#include +#include + +struct drm_edid; +struct apple_epic_service; + +struct dcpavserv { + bool enabled; + struct completion enable_completion; + u32 unit; + struct apple_epic_service *service; +}; + +const struct drm_edid *dcpavserv_copy_edid(struct apple_epic_service *service); + +#endif /* _DRM_APPLE_EPIC_DPAVSERV_H */ diff --git a/drivers/gpu/drm/apple/hdmi-codec-chmap.h b/drivers/gpu/drm/apple/hdmi-codec-chmap.h new file mode 100644 index 00000000000000..f98e1e86b89602 --- /dev/null +++ b/drivers/gpu/drm/apple/hdmi-codec-chmap.h @@ -0,0 +1,123 @@ +// copied from sound/soc/codecs/hdmi-codec.c + +#include + +/* Channel maps for multi-channel playbacks, up to 8 n_ch */ +static const struct snd_pcm_chmap_elem hdmi_codec_8ch_chmaps[] = { + { .channels = 2, /* CA_ID 0x00 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR } }, + { .channels = 4, /* CA_ID 0x01 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_NA } }, + { .channels = 4, /* CA_ID 0x02 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FC } }, + { .channels = 4, /* CA_ID 0x03 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_FC } }, + { .channels = 6, /* CA_ID 0x04 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_NA, SNDRV_CHMAP_RC, SNDRV_CHMAP_NA } }, + { .channels = 6, /* CA_ID 0x05 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_NA, SNDRV_CHMAP_RC, SNDRV_CHMAP_NA } }, + { .channels = 6, /* CA_ID 0x06 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FC, SNDRV_CHMAP_RC, SNDRV_CHMAP_NA } }, + { .channels = 6, /* CA_ID 0x07 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_FC, SNDRV_CHMAP_RC, SNDRV_CHMAP_NA } }, + { .channels = 6, /* CA_ID 0x08 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_NA, SNDRV_CHMAP_RL, SNDRV_CHMAP_RR } }, + { .channels = 6, /* CA_ID 0x09 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_NA, SNDRV_CHMAP_RL, SNDRV_CHMAP_RR } }, + { .channels = 6, /* CA_ID 0x0A */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FC, SNDRV_CHMAP_RL, SNDRV_CHMAP_RR } }, + { .channels = 6, /* CA_ID 0x0B */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_FC, SNDRV_CHMAP_RL, SNDRV_CHMAP_RR } }, + { .channels = 8, /* CA_ID 0x0C */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_NA, SNDRV_CHMAP_RL, SNDRV_CHMAP_RR, + SNDRV_CHMAP_RC, SNDRV_CHMAP_NA } }, + { .channels = 8, /* CA_ID 0x0D */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_NA, SNDRV_CHMAP_RL, SNDRV_CHMAP_RR, + SNDRV_CHMAP_RC, SNDRV_CHMAP_NA } }, + { .channels = 8, /* CA_ID 0x0E */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FC, SNDRV_CHMAP_RL, SNDRV_CHMAP_RR, + SNDRV_CHMAP_RC, SNDRV_CHMAP_NA } }, + { .channels = 8, /* CA_ID 0x0F */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_FC, SNDRV_CHMAP_RL, SNDRV_CHMAP_RR, + SNDRV_CHMAP_RC, SNDRV_CHMAP_NA } }, + { .channels = 8, /* CA_ID 0x10 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_NA, SNDRV_CHMAP_RL, SNDRV_CHMAP_RR, + SNDRV_CHMAP_RLC, SNDRV_CHMAP_RRC } }, + { .channels = 8, /* CA_ID 0x11 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_NA, SNDRV_CHMAP_RL, SNDRV_CHMAP_RR, + SNDRV_CHMAP_RLC, SNDRV_CHMAP_RRC } }, + { .channels = 8, /* CA_ID 0x12 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FC, SNDRV_CHMAP_RL, SNDRV_CHMAP_RR, + SNDRV_CHMAP_RLC, SNDRV_CHMAP_RRC } }, + { .channels = 8, /* CA_ID 0x13 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_FC, SNDRV_CHMAP_RL, SNDRV_CHMAP_RR, + SNDRV_CHMAP_RLC, SNDRV_CHMAP_RRC } }, + { .channels = 8, /* CA_ID 0x14 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FLC, SNDRV_CHMAP_FRC } }, + { .channels = 8, /* CA_ID 0x15 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FLC, SNDRV_CHMAP_FRC } }, + { .channels = 8, /* CA_ID 0x16 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FC, SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FLC, SNDRV_CHMAP_FRC } }, + { .channels = 8, /* CA_ID 0x17 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_FC, SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FLC, SNDRV_CHMAP_FRC } }, + { .channels = 8, /* CA_ID 0x18 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FLC, SNDRV_CHMAP_FRC } }, + { .channels = 8, /* CA_ID 0x19 */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FLC, SNDRV_CHMAP_FRC } }, + { .channels = 8, /* CA_ID 0x1A */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FC, SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FLC, SNDRV_CHMAP_FRC } }, + { .channels = 8, /* CA_ID 0x1B */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_FC, SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FLC, SNDRV_CHMAP_FRC } }, + { .channels = 8, /* CA_ID 0x1C */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FLC, SNDRV_CHMAP_FRC } }, + { .channels = 8, /* CA_ID 0x1D */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FLC, SNDRV_CHMAP_FRC } }, + { .channels = 8, /* CA_ID 0x1E */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FC, SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FLC, SNDRV_CHMAP_FRC } }, + { .channels = 8, /* CA_ID 0x1F */ + .map = { SNDRV_CHMAP_FL, SNDRV_CHMAP_FR, SNDRV_CHMAP_LFE, + SNDRV_CHMAP_FC, SNDRV_CHMAP_NA, SNDRV_CHMAP_NA, + SNDRV_CHMAP_FLC, SNDRV_CHMAP_FRC } }, + { } +}; diff --git a/drivers/gpu/drm/apple/ibootep.c b/drivers/gpu/drm/apple/ibootep.c new file mode 100644 index 00000000000000..ae4bc8a69f2a8d --- /dev/null +++ b/drivers/gpu/drm/apple/ibootep.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2023 */ + +#include + +#include "afk.h" +#include "dcp.h" + +static void disp_service_init(struct apple_epic_service *service, const char *name, + const char *class, s64 unit) +{ +} + + +static const struct apple_epic_service_ops ibootep_ops[] = { + { + .name = "disp0-service", + .init = disp_service_init, + }, + {} +}; + +int ibootep_init(struct apple_dcp *dcp) +{ + dcp->ibootep = afk_init(dcp, DISP0_ENDPOINT, ibootep_ops); + afk_start(dcp->ibootep); + + return 0; +} diff --git a/drivers/gpu/drm/apple/iomfb.c b/drivers/gpu/drm/apple/iomfb.c new file mode 100644 index 00000000000000..421ff925e0ecb2 --- /dev/null +++ b/drivers/gpu/drm/apple/iomfb.c @@ -0,0 +1,558 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2021 Alyssa Rosenzweig */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#include "dcp.h" +#include "dcp-internal.h" +#include "iomfb.h" +#include "iomfb_internal.h" +#include "parser.h" +#include "trace.h" + +static int dcp_tx_offset(enum dcp_context_id id) +{ + switch (id) { + case DCP_CONTEXT_CB: + case DCP_CONTEXT_CMD: + return 0x00000; + case DCP_CONTEXT_OOBCB: + case DCP_CONTEXT_OOBCMD: + return 0x08000; + default: + return -EINVAL; + } +} + +static int dcp_channel_offset(enum dcp_context_id id) +{ + switch (id) { + case DCP_CONTEXT_ASYNC: + return 0x40000; + case DCP_CONTEXT_OOBASYNC: + return 0x48000; + case DCP_CONTEXT_CB: + return 0x60000; + case DCP_CONTEXT_OOBCB: + return 0x68000; + default: + return dcp_tx_offset(id); + } +} + +static inline u64 dcpep_set_shmem(u64 dart_va) +{ + return FIELD_PREP(IOMFB_MESSAGE_TYPE, IOMFB_MESSAGE_TYPE_SET_SHMEM) | + FIELD_PREP(IOMFB_SHMEM_FLAG, IOMFB_SHMEM_FLAG_VALUE) | + FIELD_PREP(IOMFB_SHMEM_DVA, dart_va); +} + +static inline u64 dcpep_msg(enum dcp_context_id id, u32 length, u16 offset) +{ + return FIELD_PREP(IOMFB_MESSAGE_TYPE, IOMFB_MESSAGE_TYPE_MSG) | + FIELD_PREP(IOMFB_MSG_CONTEXT, id) | + FIELD_PREP(IOMFB_MSG_OFFSET, offset) | + FIELD_PREP(IOMFB_MSG_LENGTH, length); +} + +static inline u64 dcpep_ack(enum dcp_context_id id) +{ + return dcpep_msg(id, 0, 0) | IOMFB_MSG_ACK; +} + +/* + * A channel is busy if we have sent a message that has yet to be + * acked. The driver must not sent a message to a busy channel. + */ +static bool dcp_channel_busy(struct dcp_channel *ch) +{ + return (ch->depth != 0); +} + +/* + * Get the context ID passed to the DCP for a command we push. The rule is + * simple: callback contexts are used when replying to the DCP, command + * contexts are used otherwise. That corresponds to a non/zero call stack + * depth. This rule frees the caller from tracking the call context manually. + */ +static enum dcp_context_id dcp_call_context(struct apple_dcp *dcp, bool oob) +{ + u8 depth = oob ? dcp->ch_oobcmd.depth : dcp->ch_cmd.depth; + + if (depth) + return oob ? DCP_CONTEXT_OOBCB : DCP_CONTEXT_CB; + else + return oob ? DCP_CONTEXT_OOBCMD : DCP_CONTEXT_CMD; +} + +/* Get a channel for a context */ +static struct dcp_channel *dcp_get_channel(struct apple_dcp *dcp, + enum dcp_context_id context) +{ + switch (context) { + case DCP_CONTEXT_CB: + return &dcp->ch_cb; + case DCP_CONTEXT_CMD: + return &dcp->ch_cmd; + case DCP_CONTEXT_OOBCB: + return &dcp->ch_oobcb; + case DCP_CONTEXT_OOBCMD: + return &dcp->ch_oobcmd; + case DCP_CONTEXT_ASYNC: + return &dcp->ch_async; + case DCP_CONTEXT_OOBASYNC: + return &dcp->ch_oobasync; + default: + return NULL; + } +} + +/* Get the start of a packet: after the end of the previous packet */ +static u16 dcp_packet_start(struct dcp_channel *ch, u8 depth) +{ + if (depth > 0) + return ch->end[depth - 1]; + else + return 0; +} + +/* Pushes and pops the depth of the call stack with safety checks */ +static u8 dcp_push_depth(u8 *depth) +{ + u8 ret = (*depth)++; + + WARN_ON(ret >= DCP_MAX_CALL_DEPTH); + return ret; +} + +static u8 dcp_pop_depth(u8 *depth) +{ + WARN_ON((*depth) == 0); + + return --(*depth); +} + +/* Call a DCP function given by a tag */ +void dcp_push(struct apple_dcp *dcp, bool oob, const struct dcp_method_entry *call, + u32 in_len, u32 out_len, void *data, dcp_callback_t cb, + void *cookie) +{ + enum dcp_context_id context = dcp_call_context(dcp, oob); + struct dcp_channel *ch = dcp_get_channel(dcp, context); + + struct dcp_packet_header header = { + .in_len = in_len, + .out_len = out_len, + + /* Tag is reversed due to endianness of the fourcc */ + .tag[0] = call->tag[3], + .tag[1] = call->tag[2], + .tag[2] = call->tag[1], + .tag[3] = call->tag[0], + }; + + u8 depth = dcp_push_depth(&ch->depth); + u16 offset = dcp_packet_start(ch, depth); + + void *out = dcp->shmem + dcp_tx_offset(context) + offset; + void *out_data = out + sizeof(header); + size_t data_len = sizeof(header) + in_len + out_len; + + memcpy(out, &header, sizeof(header)); + + if (in_len > 0) + memcpy(out_data, data, in_len); + + trace_iomfb_push(dcp, call, context, offset, depth); + + ch->callbacks[depth] = cb; + ch->cookies[depth] = cookie; + ch->output[depth] = out + sizeof(header) + in_len; + ch->end[depth] = offset + ALIGN(data_len, DCP_PACKET_ALIGNMENT); + + dcp_send_message(dcp, IOMFB_ENDPOINT, + dcpep_msg(context, data_len, offset)); +} + +/* Parse a callback tag "D123" into the ID 123. Returns -EINVAL on failure. */ +int dcp_parse_tag(char tag[4]) +{ + u32 d[3]; + int i; + + if (tag[3] != 'D') + return -EINVAL; + + for (i = 0; i < 3; ++i) { + d[i] = (u32)(tag[i] - '0'); + + if (d[i] > 9) + return -EINVAL; + } + + return d[0] + (d[1] * 10) + (d[2] * 100); +} + +/* Ack a callback from the DCP */ +void dcp_ack(struct apple_dcp *dcp, enum dcp_context_id context) +{ + struct dcp_channel *ch = dcp_get_channel(dcp, context); + + dcp_pop_depth(&ch->depth); + dcp_send_message(dcp, IOMFB_ENDPOINT, + dcpep_ack(context)); +} + +/* + * Helper to send a DRM hotplug event. The DCP is accessed from a single + * (RTKit) thread. To handle hotplug callbacks, we need to call + * drm_kms_helper_hotplug_event, which does an atomic commit (via DCP) and + * waits for vblank (a DCP callback). That means we deadlock if we call from + * the RTKit thread! Instead, move the call to another thread via a workqueue. + */ +void dcp_hotplug(struct work_struct *work) +{ + struct apple_connector *connector; + struct apple_dcp *dcp; + + connector = container_of(work, struct apple_connector, hotplug_wq); + + dcp = platform_get_drvdata(connector->dcp); + dev_info(dcp->dev, "%s() connected:%d valid_mode:%d nr_modes:%u\n", __func__, + connector->connected, dcp->valid_mode, dcp->nr_modes); + + if (!connector->connected) { + drm_edid_free(connector->drm_edid); + connector->drm_edid = NULL; + } + + /* + * DCP defers link training until we set a display mode. But we set + * display modes from atomic_flush, so userspace needs to trigger a + * flush, or the CRTC gets no signal. + */ + if (connector->base.state && !dcp->valid_mode && connector->connected) + drm_connector_set_link_status_property(&connector->base, + DRM_MODE_LINK_STATUS_BAD); + + drm_kms_helper_connector_hotplug_event(&connector->base); +} + +static void dcpep_handle_cb(struct apple_dcp *dcp, enum dcp_context_id context, + void *data, u32 length, u16 offset) +{ + struct device *dev = dcp->dev; + struct dcp_packet_header *hdr = data; + void *in, *out; + int tag = dcp_parse_tag(hdr->tag); + struct dcp_channel *ch = dcp_get_channel(dcp, context); + u8 depth; + + if (tag < 0 || tag >= IOMFB_MAX_CB || !dcp->cb_handlers || !dcp->cb_handlers[tag]) { + dev_warn(dev, "received unknown callback %c%c%c%c\n", + hdr->tag[3], hdr->tag[2], hdr->tag[1], hdr->tag[0]); + return; + } + + in = data + sizeof(*hdr); + out = in + hdr->in_len; + + // TODO: verify that in_len and out_len match our prototypes + // for now just clear the out data to have at least consistent results + if (hdr->out_len) + memset(out, 0, hdr->out_len); + + depth = dcp_push_depth(&ch->depth); + ch->output[depth] = out; + ch->end[depth] = offset + ALIGN(length, DCP_PACKET_ALIGNMENT); + + if (dcp->cb_handlers[tag](dcp, tag, out, in)) + dcp_ack(dcp, context); +} + +static void dcpep_handle_ack(struct apple_dcp *dcp, enum dcp_context_id context, + void *data, u32 length) +{ + struct dcp_packet_header *header = data; + struct dcp_channel *ch = dcp_get_channel(dcp, context); + void *cookie; + dcp_callback_t cb; + + if (!ch) { + dev_warn(dcp->dev, "ignoring ack on context %X\n", context); + return; + } + + dcp_pop_depth(&ch->depth); + + cb = ch->callbacks[ch->depth]; + cookie = ch->cookies[ch->depth]; + + ch->callbacks[ch->depth] = NULL; + ch->cookies[ch->depth] = NULL; + + if (cb) + cb(dcp, data + sizeof(*header) + header->in_len, cookie); +} + +static void dcpep_got_msg(struct apple_dcp *dcp, u64 message) +{ + enum dcp_context_id ctx_id; + u16 offset; + u32 length; + int channel_offset; + void *data; + + ctx_id = FIELD_GET(IOMFB_MSG_CONTEXT, message); + offset = FIELD_GET(IOMFB_MSG_OFFSET, message); + length = FIELD_GET(IOMFB_MSG_LENGTH, message); + + channel_offset = dcp_channel_offset(ctx_id); + + if (channel_offset < 0) { + dev_warn(dcp->dev, "invalid context received %u\n", ctx_id); + return; + } + + data = dcp->shmem + channel_offset + offset; + + if (FIELD_GET(IOMFB_MSG_ACK, message)) + dcpep_handle_ack(dcp, ctx_id, data, length); + else + dcpep_handle_cb(dcp, ctx_id, data, length, offset); +} + +int dcp_get_modes(struct drm_connector *connector) +{ + struct apple_connector *apple_connector = to_apple_connector(connector); + struct platform_device *pdev = apple_connector->dcp; + struct apple_dcp *dcp = platform_get_drvdata(pdev); + + struct drm_device *dev = connector->dev; + struct drm_display_mode *mode; + int i; + + for (i = 0; i < dcp->nr_modes; ++i) { + mode = drm_mode_duplicate(dev, &dcp->modes[i].mode); + + if (!mode) { + dev_err(dev->dev, "Failed to duplicate display mode\n"); + return 0; + } + + drm_mode_probed_add(connector, mode); + } + + if (dcp->nr_modes && dcp->dcpavserv.enabled && + !apple_connector->drm_edid) { + const struct drm_edid *edid; + edid = dcpavserv_copy_edid(dcp->dcpavserv.service); + if (IS_ERR_OR_NULL(edid)) { + dev_info(dcp->dev, "copy_edid failed: %pe\n", edid); + } else { + drm_edid_free(apple_connector->drm_edid); + apple_connector->drm_edid = edid; + } + } + if (dcp->nr_modes && apple_connector->drm_edid) + drm_edid_connector_update(connector, apple_connector->drm_edid); + + return dcp->nr_modes; +} + +/* The user may own drm_display_mode, so we need to search for our copy */ +struct dcp_display_mode *lookup_mode(struct apple_dcp *dcp, + const struct drm_display_mode *mode) +{ + int i; + + for (i = 0; i < dcp->nr_modes; ++i) { + if (drm_mode_match(mode, &dcp->modes[i].mode, + DRM_MODE_MATCH_TIMINGS | + DRM_MODE_MATCH_CLOCK)) + return &dcp->modes[i]; + } + + return NULL; +} + +enum drm_mode_status dcp_mode_valid(struct drm_connector *connector, + const struct drm_display_mode *mode) +{ + struct apple_connector *apple_connector = to_apple_connector(connector); + struct platform_device *pdev = apple_connector->dcp; + struct apple_dcp *dcp = platform_get_drvdata(pdev); + + return lookup_mode(dcp, mode) ? MODE_OK : MODE_BAD; +} + +int dcp_crtc_atomic_modeset(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct apple_crtc *apple_crtc = to_apple_crtc(crtc); + struct apple_dcp *dcp = platform_get_drvdata(apple_crtc->dcp); + struct drm_crtc_state *crtc_state; + int ret = -EIO; + bool modeset; + + crtc_state = drm_atomic_get_new_crtc_state(state, crtc); + if (!crtc_state) + return 0; + + modeset = drm_atomic_crtc_needs_modeset(crtc_state) || !dcp->valid_mode; + + if (!modeset) + return 0; + + /* ignore no mode, poweroff is handled elsewhere */ + if (crtc_state->mode.hdisplay == 0 && crtc_state->mode.vdisplay == 0) + return 0; + + switch (dcp->fw_compat) { + case DCP_FIRMWARE_V_12_3: + ret = iomfb_modeset_v12_3(dcp, crtc_state); + break; + case DCP_FIRMWARE_V_13_5: + ret = iomfb_modeset_v13_3(dcp, crtc_state); + break; + default: + WARN_ONCE(true, "Unexpected firmware version: %u\n", + dcp->fw_compat); + break; + } + + return ret; +} + +bool dcp_crtc_mode_fixup(struct drm_crtc *crtc, + const struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ + struct apple_crtc *apple_crtc = to_apple_crtc(crtc); + struct platform_device *pdev = apple_crtc->dcp; + struct apple_dcp *dcp = platform_get_drvdata(pdev); + + /* TODO: support synthesized modes through scaling */ + return lookup_mode(dcp, mode) != NULL; +} + + +void dcp_flush(struct drm_crtc *crtc, struct drm_atomic_state *state) +{ + struct platform_device *pdev = to_apple_crtc(crtc)->dcp; + struct apple_dcp *dcp = platform_get_drvdata(pdev); + + if (dcp_channel_busy(&dcp->ch_cmd)) + { + if (!dcp->ch_cmd.warned_busy) { + dev_err(dcp->dev, "unexpected busy command channel\n"); + dcp->ch_cmd.warned_busy = true; + } + /* HACK: issue a delayed vblank event to avoid timeouts in + * drm_atomic_helper_wait_for_vblanks(). + */ + schedule_work(&dcp->vblank_wq); + return; + } else if (dcp->ch_cmd.warned_busy) { + dcp->ch_cmd.warned_busy = false; + } + + switch (dcp->fw_compat) { + case DCP_FIRMWARE_V_12_3: + iomfb_flush_v12_3(dcp, crtc, state); + break; + case DCP_FIRMWARE_V_13_5: + iomfb_flush_v13_3(dcp, crtc, state); + break; + default: + WARN_ONCE(true, "Unexpected firmware version: %u\n", dcp->fw_compat); + break; + } +} + +static void iomfb_start(struct apple_dcp *dcp) +{ + switch (dcp->fw_compat) { + case DCP_FIRMWARE_V_12_3: + iomfb_start_v12_3(dcp); + break; + case DCP_FIRMWARE_V_13_5: + iomfb_start_v13_3(dcp); + break; + default: + WARN_ONCE(true, "Unexpected firmware version: %u\n", dcp->fw_compat); + break; + } +} + +bool dcp_is_initialized(struct platform_device *pdev) +{ + struct apple_dcp *dcp = platform_get_drvdata(pdev); + + return dcp->active; +} + +void iomfb_recv_msg(struct apple_dcp *dcp, u64 message) +{ + enum dcpep_type type = FIELD_GET(IOMFB_MESSAGE_TYPE, message); + + if (type == IOMFB_MESSAGE_TYPE_INITIALIZED) + iomfb_start(dcp); + else if (type == IOMFB_MESSAGE_TYPE_MSG) + dcpep_got_msg(dcp, message); + else + dev_warn(dcp->dev, "Ignoring unknown message %llx\n", message); +} + +int iomfb_start_rtkit(struct apple_dcp *dcp) +{ + dma_addr_t shmem_iova; + apple_rtkit_start_ep(dcp->rtk, IOMFB_ENDPOINT); + + dcp->shmem = dma_alloc_coherent(dcp->dev, DCP_SHMEM_SIZE, &shmem_iova, + GFP_KERNEL); + + dcp_send_message(dcp, IOMFB_ENDPOINT, dcpep_set_shmem(shmem_iova)); + + return 0; +} + +void iomfb_shutdown(struct apple_dcp *dcp) +{ + /* We're going down */ + dcp->active = false; + dcp->valid_mode = false; + + switch (dcp->fw_compat) { + case DCP_FIRMWARE_V_12_3: + iomfb_shutdown_v12_3(dcp); + break; + case DCP_FIRMWARE_V_13_5: + iomfb_shutdown_v13_3(dcp); + break; + default: + WARN_ONCE(true, "Unexpected firmware version: %u\n", dcp->fw_compat); + break; + } +} diff --git a/drivers/gpu/drm/apple/iomfb.h b/drivers/gpu/drm/apple/iomfb.h new file mode 100644 index 00000000000000..d40870c8103a25 --- /dev/null +++ b/drivers/gpu/drm/apple/iomfb.h @@ -0,0 +1,396 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2021 Alyssa Rosenzweig */ + +#ifndef __APPLE_DCPEP_H__ +#define __APPLE_DCPEP_H__ + +#include + +#include "version_utils.h" + +/* Fixed size of shared memory between DCP and AP */ +#define DCP_SHMEM_SIZE 0x100000 + +/* DCP message contexts */ +enum dcp_context_id { + /* Callback */ + DCP_CONTEXT_CB = 0, + + /* Command */ + DCP_CONTEXT_CMD = 2, + + /* Asynchronous */ + DCP_CONTEXT_ASYNC = 3, + + /* Out-of-band callback */ + DCP_CONTEXT_OOBCB = 4, + + /* Out-of-band command */ + DCP_CONTEXT_OOBCMD = 6, + + /* Out-of-band Asynchronous */ + DCP_CONTEXT_OOBASYNC = 7, + + DCP_NUM_CONTEXTS +}; + +/* RTKit endpoint message types */ +enum dcpep_type { + /* Set shared memory */ + IOMFB_MESSAGE_TYPE_SET_SHMEM = 0, + + /* DCP is initialized */ + IOMFB_MESSAGE_TYPE_INITIALIZED = 1, + + /* Remote procedure call */ + IOMFB_MESSAGE_TYPE_MSG = 2, +}; + +#define IOMFB_MESSAGE_TYPE GENMASK_ULL( 3, 0) + +/* Message */ +#define IOMFB_MSG_LENGTH GENMASK_ULL(63, 32) +#define IOMFB_MSG_OFFSET GENMASK_ULL(31, 16) +#define IOMFB_MSG_CONTEXT GENMASK_ULL(11, 8) +#define IOMFB_MSG_ACK BIT_ULL(6) + +/* Set shmem */ +#define IOMFB_SHMEM_DVA GENMASK_ULL(63, 16) +#define IOMFB_SHMEM_FLAG GENMASK_ULL( 7, 4) +#define IOMFB_SHMEM_FLAG_VALUE 4 + +struct dcp_packet_header { + char tag[4]; + u32 in_len; + u32 out_len; +} __packed; + +#define DCP_IS_NULL(ptr) ((ptr) ? 1 : 0) +#define DCP_PACKET_ALIGNMENT (0x40) + +enum iomfb_property_id { + IOMFB_PROPERTY_NITS = 15, // divide by Brightness_Scale +}; + +#define IOMFB_BRIGHTNESS_MIN 0x10000000 + +/* Structures used in v12.0 firmware */ + +#define SWAP_SURFACES 4 +/* We have 4 surfaces, but we can only ever blend two */ +#define MAX_BLEND_SURFACES 2 + +struct dcp_iouserclient { + /* Handle for the IOUserClient. macOS sets this to a kernel VA. */ + u64 handle; + u32 unk; + u8 flag1; + u8 flag2; + u8 padding[2]; +} __packed; + +/* + * Update background color to struct dcp_swap.bg_color + */ +#define IOMFB_SET_BACKGROUND BIT(31) + +struct dcp_allocate_bandwidth_req { + u64 unk1; + u64 unk2; + u64 unk3; + u8 unk1_null; + u8 unk2_null; + u8 padding[8]; +} __packed; + +struct dcp_allocate_bandwidth_resp { + u64 unk1; + u64 unk2; + u32 ret; +} __packed; + +struct dcp_rt_bandwidth { + u64 unk1; + u64 reg_scratch; + u64 reg_doorbell; + u32 unk2; + u32 doorbell_bit; + u32 padding[7]; +} __packed; + +struct frame_sync_props { + u8 unk[28]; +}; + +struct dcp_set_frame_sync_props_req { + struct frame_sync_props props; + u8 frame_sync_props_null; + u8 padding[3]; +} __packed; + +struct dcp_set_frame_sync_props_resp { + struct frame_sync_props props; +} __packed; + +/* Method calls */ + +enum dcpep_method { + dcpep_late_init_signal, + dcpep_setup_video_limits, + dcpep_set_create_dfb, + dcpep_start_signal, + dcpep_swap_start, + dcpep_swap_submit, + dcpep_set_display_device, + dcpep_set_digital_out_mode, + dcpep_create_default_fb, + dcpep_set_display_refresh_properties, + dcpep_flush_supports_power, + dcpep_set_power_state, + dcpep_first_client_open, + dcpep_set_parameter_dcp, + dcpep_enable_disable_video_power_savings, + dcpep_is_main_display, + iomfbep_a131_pmu_service_matched, + iomfbep_a132_backlight_service_matched, + iomfbep_a358_vi_set_temperature_hint, + iomfbep_get_color_remap_mode, + iomfbep_last_client_close, + iomfbep_abort_swaps_dcp, + iomfbep_set_matrix, + dcpep_num_methods +}; + +#define IOMFB_METHOD(tag, name) [name] = { #name, { tag[0], tag[1], tag[2], tag[3] } } + +struct dcp_method_entry { + const char *name; + char tag[4]; +}; + +#define IOMFB_MAX_CB (1000) +struct apple_dcp; + +typedef bool (*iomfb_cb_handler)(struct apple_dcp *, int, void *, void *); + +/* Prototypes */ + +struct dcp_set_digital_out_mode_req { + u32 color_mode_id; + u32 timing_mode_id; +} __packed; + +struct dcp_map_buf_req { + u64 buffer; + u8 unk; + u8 buf_null; + u8 vaddr_null; + u8 dva_null; +} __packed; + +struct dcp_map_buf_resp { + u64 vaddr; + u64 dva; + u32 ret; +} __packed; + +struct dcp_unmap_buf_resp { + u64 buffer; + u64 vaddr; + u64 dva; + u8 unk; + u8 buf_null; +} __packed; + +struct dcp_allocate_buffer_req { + u32 unk0; + u64 size; + u32 unk2; + u8 paddr_null; + u8 dva_null; + u8 dva_size_null; + u8 padding; +} __packed; + +struct dcp_allocate_buffer_resp { + u64 paddr; + u64 dva; + u64 dva_size; + u32 mem_desc_id; +} __packed; + +struct dcp_map_physical_req { + u64 paddr; + u64 size; + u32 flags; + u8 dva_null; + u8 dva_size_null; + u8 padding[2]; +} __packed; + +struct dcp_map_physical_resp { + u64 dva; + u64 dva_size; + u32 mem_desc_id; +} __packed; + +struct dcp_swap_start_req { + u32 swap_id; + struct dcp_iouserclient client; + u8 swap_id_null; + u8 client_null; + u8 padding[2]; +} __packed; + +struct dcp_swap_start_resp { + u32 swap_id; + struct dcp_iouserclient client; + u32 ret; +} __packed; + +struct dcp_get_uint_prop_req { + char obj[4]; + char key[0x40]; + u64 value; + u8 value_null; + u8 padding[3]; +} __packed; + +struct dcp_get_uint_prop_resp { + u64 value; + u8 ret; + u8 padding[3]; +} __packed; + +struct iomfb_sr_set_property_int_req { + char obj[4]; + char key[0x40]; + u64 value; + u8 value_null; + u8 padding[3]; +} __packed; + +struct iomfb_set_fx_prop_req { + char obj[4]; + char key[0x40]; + u32 value; +} __packed; + +struct dcp_set_power_state_req { + u64 unklong; + u8 unkbool; + u8 unkint_null; + u8 padding[2]; +} __packed; + +struct dcp_set_power_state_resp { + u32 unkint; + u32 ret; +} __packed; + +struct dcp_set_dcpav_prop_chunk_req { + char data[0x1000]; + u32 offset; + u32 length; +} __packed; + +struct dcp_set_dcpav_prop_end_req { + char key[0x40]; +} __packed; + +struct dcp_set_parameter_dcp { + u32 param; + u32 value[8]; + u32 count; +} __packed; + +struct dcp_swap_complete_intent_gated { + u32 swap_id; + u8 unkBool; + u32 unkInt; + u32 width; + u32 height; +} __packed; + +struct dcp_read_edt_data_req { + char key[0x40]; + u32 count; + u32 value[8]; +} __packed; + +struct dcp_read_edt_data_resp { + u32 value[8]; + u8 ret; +} __packed; + +struct iomfb_property { + u32 id; + u32 value; +} __packed; + +struct iomfb_get_color_remap_mode_req { + u32 mode; + u8 mode_null; + u8 padding[3]; +} __packed; + +struct iomfb_get_color_remap_mode_resp { + u32 mode; + u32 ret; +} __packed; + +struct iomfb_last_client_close_req { + u8 unkint_null; + u8 padding[3]; +} __packed; + +struct iomfb_last_client_close_resp { + u32 unkint; +} __packed; + +struct io_user_client { + u64 addr; + u32 unk; + u8 flag1; + u8 flag2; + u8 pad[2]; +} __packed; + +struct iomfb_abort_swaps_dcp_req { + struct io_user_client client; + u8 client_null; + u8 pad[3]; +} __packed; + +struct iomfb_abort_swaps_dcp_resp { + struct io_user_client client; + u32 ret; +} __packed; + +struct iomfb_set_matrix_req { + u32 unk_u32; // maybe length? + u64 r[3]; + u64 g[3]; + u64 b[3]; + u8 matrix_null; + u8 padding[3]; +} __packed; + +struct iomfb_set_matrix_resp { + u32 ret; +} __packed; + +struct dcpep_get_tiling_state_req { + u32 event; + u32 param; + u32 value; + u8 value_null; + u8 padding[3]; +} __packed; + +struct dcpep_get_tiling_state_resp { + u32 value; + u32 ret; +} __packed; + +#endif diff --git a/drivers/gpu/drm/apple/iomfb_internal.h b/drivers/gpu/drm/apple/iomfb_internal.h new file mode 100644 index 00000000000000..75e9d7b0e8cc84 --- /dev/null +++ b/drivers/gpu/drm/apple/iomfb_internal.h @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright The Asahi Linux Contributors */ + +#include +#include + +#include "dcp-internal.h" + +struct apple_dcp; + +typedef void (*dcp_callback_t)(struct apple_dcp *, void *, void *); + + +#define DCP_THUNK_VOID(func, handle) \ + static void func(struct apple_dcp *dcp, bool oob, dcp_callback_t cb, \ + void *cookie) \ + { \ + dcp_push(dcp, oob, &dcp_methods[handle], 0, 0, NULL, cb, cookie); \ + } + +#define DCP_THUNK_OUT(func, handle, T) \ + static void func(struct apple_dcp *dcp, bool oob, dcp_callback_t cb, \ + void *cookie) \ + { \ + dcp_push(dcp, oob, &dcp_methods[handle], 0, sizeof(T), NULL, cb, cookie); \ + } + +#define DCP_THUNK_IN(func, handle, T) \ + static void func(struct apple_dcp *dcp, bool oob, T *data, \ + dcp_callback_t cb, void *cookie) \ + { \ + dcp_push(dcp, oob, &dcp_methods[handle], sizeof(T), 0, data, cb, cookie); \ + } + +#define DCP_THUNK_INOUT(func, handle, T_in, T_out) \ + static void func(struct apple_dcp *dcp, bool oob, T_in *data, \ + dcp_callback_t cb, void *cookie) \ + { \ + dcp_push(dcp, oob, &dcp_methods[handle], sizeof(T_in), sizeof(T_out), data, \ + cb, cookie); \ + } + +#define IOMFB_THUNK_INOUT(name) \ + static void iomfb_ ## name(struct apple_dcp *dcp, bool oob, \ + struct iomfb_ ## name ## _req *data, \ + dcp_callback_t cb, void *cookie) \ + { \ + dcp_push(dcp, oob, &dcp_methods[iomfbep_ ## name], \ + sizeof(struct iomfb_ ## name ## _req), \ + sizeof(struct iomfb_ ## name ## _resp), \ + data, cb, cookie); \ + } + +/* + * Define type-safe trampolines. Define typedefs to enforce type-safety on the + * input data (so if the types don't match, gcc errors out). + */ + +#define TRAMPOLINE_VOID(func, handler) \ + static bool __maybe_unused func(struct apple_dcp *dcp, int tag, void *out, void *in) \ + { \ + trace_iomfb_callback(dcp, tag, #handler); \ + handler(dcp); \ + return true; \ + } + +#define TRAMPOLINE_IN(func, handler, T_in) \ + typedef void (*callback_##handler)(struct apple_dcp *, T_in *); \ + \ + static bool __maybe_unused func(struct apple_dcp *dcp, int tag, void *out, void *in) \ + { \ + callback_##handler cb = handler; \ + \ + trace_iomfb_callback(dcp, tag, #handler); \ + cb(dcp, in); \ + return true; \ + } + +#define TRAMPOLINE_INOUT(func, handler, T_in, T_out) \ + typedef T_out (*callback_##handler)(struct apple_dcp *, T_in *); \ + \ + static bool __maybe_unused func(struct apple_dcp *dcp, int tag, void *out, void *in) \ + { \ + T_out *typed_out = out; \ + callback_##handler cb = handler; \ + \ + trace_iomfb_callback(dcp, tag, #handler); \ + *typed_out = cb(dcp, in); \ + return true; \ + } + +#define TRAMPOLINE_OUT(func, handler, T_out) \ + static bool __maybe_unused func(struct apple_dcp *dcp, int tag, void *out, void *in) \ + { \ + T_out *typed_out = out; \ + \ + trace_iomfb_callback(dcp, tag, #handler); \ + *typed_out = handler(dcp); \ + return true; \ + } + +/* Call a DCP function given by a tag */ +void dcp_push(struct apple_dcp *dcp, bool oob, const struct dcp_method_entry *call, + u32 in_len, u32 out_len, void *data, dcp_callback_t cb, + void *cookie); + +/* Parse a callback tag "D123" into the ID 123. Returns -EINVAL on failure. */ +int dcp_parse_tag(char tag[4]); + +void dcp_ack(struct apple_dcp *dcp, enum dcp_context_id context); + +/* The user may own drm_display_mode, so we need to search for our copy */ +struct dcp_display_mode *lookup_mode(struct apple_dcp *dcp, + const struct drm_display_mode *mode); diff --git a/drivers/gpu/drm/apple/iomfb_plane.h b/drivers/gpu/drm/apple/iomfb_plane.h new file mode 100644 index 00000000000000..46eb7ab3fed4c7 --- /dev/null +++ b/drivers/gpu/drm/apple/iomfb_plane.h @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Copyright (C) The Asahi Linux Contributors + */ + + +#ifndef __APPLE_IOMFB_PLANE_H__ +#define __APPLE_IOMFB_PLANE_H__ + +#include + +#include + +#define DCP_SURF_MAX_PLANES 3 + +#define DCP_FORMAT_BGRA fourcc_code('A', 'R', 'G', 'B') +#define DCP_FORMAT_RGBA fourcc_code('A', 'B', 'G', 'R') + +#define DCP_FORMAT_W30R fourcc_code('r', '0', '3', 'w') // wide gamut packed 10-bit RGB without alpha +#define DCP_FORMAT_L10R fourcc_code('r', '0', '1', 'l') // full range packed 10-bit RGB with alpha + +#define DCP_FORMAT_420V fourcc_code('v', '0', '2', '4') // NV12 video range 2 plane 8-bit YCbCr +#define DCP_FORMAT_420F fourcc_code('f', '0', '2', '4') // NV12 full range 2 plane 8-bit YCbCr +#define DCP_FORMAT_422V fourcc_code('v', '2', '2', '4') // NV16 video range 2 plane 8-bit YCbCr +#define DCP_FORMAT_422F fourcc_code('f', '2', '2', '4') // NV16 full range 2 plane 8-bit YCbCr +#define DCP_FORMAT_444V fourcc_code('v', '4', '4', '4') // NV24 video range 2 plane 8-bit YCbCr +#define DCP_FORMAT_444F fourcc_code('f', '4', '4', '4') // NV24 full range 2 plane 8-bit YCbCr + +#define DCP_FORMAT_X420 fourcc_code('0', '2', '4', 'x') // P010 video range 2 plane 10-bit YCbCR +#define DCP_FORMAT_X422 fourcc_code('2', '2', '4', 'x') // P210 video range 2 plane 10-bit YCbCR +#define DCP_FORMAT_X444 fourcc_code('4', '4', '4', 'x') // P410 video range 2 plane 10-bit YCbCR + +#define DCP_FORMAT_XF20 fourcc_code('0', '2', 'f', 'x') // P010 full range 2 plane 10-bit YCbCR +#define DCP_FORMAT_XF22 fourcc_code('2', '2', 'f', 'x') // P210 full range 2 plane 10-bit YCbCR +#define DCP_FORMAT_XF44 fourcc_code('4', '4', 'f', 'x') // P410 full range 2 plane 10-bit YCbCR + +enum dcp_colorspace { + DCP_COLORSPACE_BG_SRGB = 0, + DCP_COLORSPACE_BT601 = 1, + DCP_COLORSPACE_BT709 = 2, + DCP_COLORSPACE_BG_BT2020 = 9, + DCP_COLORSPACE_NATIVE = 12, +}; + +enum dcp_xfer_func { + DCP_XFER_FUNC_BT601 = 1, + DCP_XFER_FUNC_BT1886 = 2, + DCP_XFER_FUNC_SDR = 13, + DCP_XFER_FUNC_HDR = 16, +}; + +enum dcp_address_format { + DCP_ADDRESS_FORMAT_INTERCHANGE_TILED = 5, +}; + +enum dcp_compression_type { + DCP_COMPRESSION_TYPE_INTERCHANGE_TILED = 3, +}; + +struct dcp_rect { + u32 x; + u32 y; + u32 w; + u32 h; +} __packed; + +/* Information describing a plane of a planar compressed surface */ +struct dcp_plane_info { + u32 width; + u32 height; + u32 base; + u32 offset; + u32 stride; + u32 size; + u16 tile_size; + u8 tile_w; + u8 tile_h; + u8 unk1[0xd]; + u8 address_format; + u8 unk2[0x26]; +} __packed; + +struct dcp_compression_info { + u32 tile_w; + u32 tile_h; + u32 meta_offset; + u32 data_offset; + u32 tile_meta_bytes; + u32 tiles_w; + u32 tiles_h; + u32 unk1; + u32 compresson_type; + u32 unk3; + u8 _pad1[3]; + u32 tile_bytes; + u32 row_stride; + u8 pad2; +} __packed; + +struct dcp_component_types { + u8 count; + u8 types[7]; +} __packed; + +/* Information describing a surface */ +struct dcp_surface { + u8 is_tiled; + u8 is_tearing_allowed; + u8 is_premultiplied; + u32 plane_cnt; + u32 plane_cnt2; + u32 format; /* DCP fourcc */ + u32 ycbcr_matrix; + u8 xfer_func; + u8 colorspace; + u32 stride; + u16 pix_size; + u8 pel_w; + u8 pel_h; + u32 offset; + u32 width; + u32 height; + u32 buf_size; + u64 protection_opts; + u32 surface_id; + struct dcp_component_types comp_types[DCP_SURF_MAX_PLANES]; + u64 has_comp; + struct dcp_plane_info planes[DCP_SURF_MAX_PLANES]; + u64 has_planes; + struct dcp_compression_info compression_info[DCP_SURF_MAX_PLANES]; + u64 has_compr_info; + u32 unk_num; + u32 unk_denom; +} __packed; + +#endif /* __APPLE_IOMFB_PLANE_H__ */ diff --git a/drivers/gpu/drm/apple/iomfb_template.c b/drivers/gpu/drm/apple/iomfb_template.c new file mode 100644 index 00000000000000..113a55b4a8a2b7 --- /dev/null +++ b/drivers/gpu/drm/apple/iomfb_template.c @@ -0,0 +1,1482 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Copyright 2021 Alyssa Rosenzweig + * Copyright The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include "dcp.h" +#include "dcp-internal.h" +#include "iomfb.h" +#include "iomfb_internal.h" +#include "parser.h" +#include "trace.h" +#include "version_utils.h" + +/* Register defines used in bandwidth setup structure */ +#define REG_DOORBELL_BIT(idx) (2 + (idx)) + +struct dcp_wait_cookie { + struct kref refcount; + struct completion done; +}; + +static void release_wait_cookie(struct kref *ref) +{ + struct dcp_wait_cookie *cookie; + cookie = container_of(ref, struct dcp_wait_cookie, refcount); + + kfree(cookie); +} + +DCP_THUNK_OUT(iomfb_a131_pmu_service_matched, iomfbep_a131_pmu_service_matched, u32); +DCP_THUNK_OUT(iomfb_a132_backlight_service_matched, iomfbep_a132_backlight_service_matched, u32); +DCP_THUNK_OUT(iomfb_a358_vi_set_temperature_hint, iomfbep_a358_vi_set_temperature_hint, u32); + +IOMFB_THUNK_INOUT(set_matrix); +IOMFB_THUNK_INOUT(get_color_remap_mode); +IOMFB_THUNK_INOUT(last_client_close); +IOMFB_THUNK_INOUT(abort_swaps_dcp); + +DCP_THUNK_INOUT(dcp_swap_submit, dcpep_swap_submit, + struct DCP_FW_NAME(dcp_swap_submit_req), + struct DCP_FW_NAME(dcp_swap_submit_resp)); + +DCP_THUNK_INOUT(dcp_swap_start, dcpep_swap_start, struct dcp_swap_start_req, + struct dcp_swap_start_resp); + +DCP_THUNK_INOUT(dcp_set_power_state, dcpep_set_power_state, + struct dcp_set_power_state_req, + struct dcp_set_power_state_resp); + +DCP_THUNK_INOUT(dcp_set_digital_out_mode, dcpep_set_digital_out_mode, + struct dcp_set_digital_out_mode_req, u32); + +DCP_THUNK_INOUT(dcp_set_display_device, dcpep_set_display_device, u32, u32); + +DCP_THUNK_OUT(dcp_set_display_refresh_properties, + dcpep_set_display_refresh_properties, u32); + +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) +DCP_THUNK_INOUT(dcp_late_init_signal, dcpep_late_init_signal, u32, u32); +#else +DCP_THUNK_OUT(dcp_late_init_signal, dcpep_late_init_signal, u32); +#endif +DCP_THUNK_IN(dcp_flush_supports_power, dcpep_flush_supports_power, u32); +DCP_THUNK_OUT(dcp_create_default_fb, dcpep_create_default_fb, u32); +DCP_THUNK_OUT(dcp_start_signal, dcpep_start_signal, u32); +DCP_THUNK_VOID(dcp_setup_video_limits, dcpep_setup_video_limits); +DCP_THUNK_VOID(dcp_set_create_dfb, dcpep_set_create_dfb); +DCP_THUNK_VOID(dcp_first_client_open, dcpep_first_client_open); + +DCP_THUNK_INOUT(dcp_set_parameter_dcp, dcpep_set_parameter_dcp, + struct dcp_set_parameter_dcp, u32); + +DCP_THUNK_INOUT(dcp_enable_disable_video_power_savings, + dcpep_enable_disable_video_power_savings, u32, int); + +DCP_THUNK_OUT(dcp_is_main_display, dcpep_is_main_display, u32); + +/* DCP callback handlers */ +static void dcpep_cb_nop(struct apple_dcp *dcp) +{ + /* No operation */ +} + +static u8 dcpep_cb_true(struct apple_dcp *dcp) +{ + return true; +} + +static u8 dcpep_cb_false(struct apple_dcp *dcp) +{ + return false; +} + +static u32 dcpep_cb_zero(struct apple_dcp *dcp) +{ + return 0; +} + +static void dcpep_cb_swap_complete(struct apple_dcp *dcp, + struct DCP_FW_NAME(dc_swap_complete_resp) *resp) +{ + ktime_t now = ktime_get(); + trace_iomfb_swap_complete(dcp, resp->swap_id); + dcp->last_swap_id = resp->swap_id; + + dcp_drm_crtc_page_flip(dcp, now); + if (dcp->crc_enabled) { + u32 crc32 = 0; + drm_crtc_add_crc_entry(&dcp->crtc->base, true, resp->swap_id, &crc32); + } +} + +/* special */ +static void complete_vi_set_temperature_hint(struct apple_dcp *dcp, void *out, void *cookie) +{ + // ack D100 cb_match_pmu_service + dcp_ack(dcp, DCP_CONTEXT_CB); +} + +static bool iomfbep_cb_match_pmu_service(struct apple_dcp *dcp, int tag, void *out, void *in) +{ + trace_iomfb_callback(dcp, tag, __func__); + iomfb_a358_vi_set_temperature_hint(dcp, false, + complete_vi_set_temperature_hint, + NULL); + + // return false for deferred ACK + return false; +} + +static void complete_pmu_service_matched(struct apple_dcp *dcp, void *out, void *cookie) +{ + struct dcp_channel *ch = &dcp->ch_cb; + u8 *succ = ch->output[ch->depth - 1]; + + *succ = true; + + // ack D206 cb_match_pmu_service_2 + dcp_ack(dcp, DCP_CONTEXT_CB); +} + +static bool iomfbep_cb_match_pmu_service_2(struct apple_dcp *dcp, int tag, void *out, void *in) +{ + trace_iomfb_callback(dcp, tag, __func__); + + iomfb_a131_pmu_service_matched(dcp, false, complete_pmu_service_matched, + out); + + // return false for deferred ACK + return false; +} + +static void complete_backlight_service_matched(struct apple_dcp *dcp, void *out, void *cookie) +{ + struct dcp_channel *ch = &dcp->ch_cb; + u8 *succ = ch->output[ch->depth - 1]; + + *succ = true; + + // ack D206 cb_match_backlight_service + dcp_ack(dcp, DCP_CONTEXT_CB); +} + +static bool iomfbep_cb_match_backlight_service(struct apple_dcp *dcp, int tag, void *out, void *in) +{ + trace_iomfb_callback(dcp, tag, __func__); + + if (!dcp_has_panel(dcp)) { + u8 *succ = out; + *succ = true; + return true; + } + + iomfb_a132_backlight_service_matched(dcp, false, complete_backlight_service_matched, out); + + // return false for deferred ACK + return false; +} + +static void iomfb_cb_pr_publish(struct apple_dcp *dcp, struct iomfb_property *prop) +{ + switch (prop->id) { + case IOMFB_PROPERTY_NITS: + { + if (dcp_has_panel(dcp)) { + dcp->brightness.nits = prop->value / dcp->brightness.scale; + /* notify backlight device of the initial brightness */ + if (!dcp->brightness.bl_dev && dcp->brightness.maximum > 0) + schedule_work(&dcp->bl_register_wq); + trace_iomfb_brightness(dcp, prop->value); + } + break; + } + default: + dev_dbg(dcp->dev, "pr_publish: id: %d = %u\n", prop->id, prop->value); + } +} + +static struct dcp_get_uint_prop_resp +dcpep_cb_get_uint_prop(struct apple_dcp *dcp, struct dcp_get_uint_prop_req *req) +{ + struct dcp_get_uint_prop_resp resp = (struct dcp_get_uint_prop_resp){ + .value = 0 + }; + + if (dcp->panel.has_mini_led && + memcmp(req->obj, "SUMP", sizeof(req->obj)) == 0) { /* "PMUS */ + if (strncmp(req->key, "Temperature", sizeof(req->key)) == 0) { + /* + * TODO: value from j314c, find out if it is temperature in + * centigrade C and which temperature sensor reports it + */ + resp.value = 3029; + resp.ret = true; + } + } + + return resp; +} + +static u8 iomfbep_cb_sr_set_property_int(struct apple_dcp *dcp, + struct iomfb_sr_set_property_int_req *req) +{ + if (memcmp(req->obj, "FMOI", sizeof(req->obj)) == 0) { /* "IOMF */ + if (strncmp(req->key, "Brightness_Scale", sizeof(req->key)) == 0) { + if (!req->value_null) + dcp->brightness.scale = req->value; + } + } + + return 1; +} + +static void iomfbep_cb_set_fx_prop(struct apple_dcp *dcp, struct iomfb_set_fx_prop_req *req) +{ + // TODO: trace this, see if there properties which needs to used later +} + +/* + * Callback to map a buffer allocated with allocate_buf for PIODMA usage. + * PIODMA is separate from the main DCP and uses own IOVA space on a dedicated + * stream of the display DART, rather than the expected DCP DART. + */ +static struct dcp_map_buf_resp dcpep_cb_map_piodma(struct apple_dcp *dcp, + struct dcp_map_buf_req *req) +{ + struct dcp_mem_descriptor *memdesc; + struct sg_table *map; + ssize_t ret; + + if (req->buffer >= ARRAY_SIZE(dcp->memdesc)) + goto reject; + + memdesc = &dcp->memdesc[req->buffer]; + map = &memdesc->map; + + if (!map->sgl) + goto reject; + + /* use the piodma iommu domain to map against the right IOMMU */ + ret = iommu_map_sgtable(dcp->iommu_dom, memdesc->dva, map, + IOMMU_READ | IOMMU_WRITE); + + /* HACK: expect size to be 16K aligned since the iommu API only maps + * full pages + */ + if (ret < 0 || ret != ALIGN(memdesc->size, SZ_16K)) { + dev_err(dcp->dev, "iommu_map_sgtable() returned %zd instead of expected buffer size of %zu\n", ret, memdesc->size); + goto reject; + } + + return (struct dcp_map_buf_resp){ .dva = memdesc->dva }; + +reject: + dev_err(dcp->dev, "denying map of invalid buffer %llx for piodma\n", + req->buffer); + return (struct dcp_map_buf_resp){ .ret = EINVAL }; +} + +static void dcpep_cb_unmap_piodma(struct apple_dcp *dcp, + struct dcp_unmap_buf_resp *resp) +{ + struct dcp_mem_descriptor *memdesc; + + if (resp->buffer >= ARRAY_SIZE(dcp->memdesc)) { + dev_warn(dcp->dev, "unmap request for out of range buffer %llu\n", + resp->buffer); + return; + } + + memdesc = &dcp->memdesc[resp->buffer]; + + if (!memdesc->buf) { + dev_warn(dcp->dev, + "unmap for non-mapped buffer %llu iova:0x%08llx\n", + resp->buffer, resp->dva); + return; + } + + if (memdesc->dva != resp->dva) { + dev_warn(dcp->dev, "unmap buffer %llu address mismatch " + "memdesc.dva:%llx dva:%llx\n", resp->buffer, + memdesc->dva, resp->dva); + return; + } + + /* use the piodma iommu domain to unmap from the right IOMMU */ + /* HACK: expect size to be 16K aligned since the iommu API only maps + * full pages + */ + iommu_unmap(dcp->iommu_dom, memdesc->dva, ALIGN(memdesc->size, SZ_16K)); +} + +/* + * Allocate an IOVA contiguous buffer mapped to the DCP. The buffer need not be + * physically contiguous, however we should save the sgtable in case the + * buffer needs to be later mapped for PIODMA. + */ +static struct dcp_allocate_buffer_resp +dcpep_cb_allocate_buffer(struct apple_dcp *dcp, + struct dcp_allocate_buffer_req *req) +{ + struct dcp_allocate_buffer_resp resp = { 0 }; + struct dcp_mem_descriptor *memdesc; + size_t size; + u32 id; + + resp.dva_size = ALIGN(req->size, 4096); + resp.mem_desc_id = + find_first_zero_bit(dcp->memdesc_map, DCP_MAX_MAPPINGS); + + if (resp.mem_desc_id >= DCP_MAX_MAPPINGS) { + dev_warn(dcp->dev, "DCP overflowed mapping table, ignoring\n"); + resp.dva_size = 0; + resp.mem_desc_id = 0; + return resp; + } + id = resp.mem_desc_id; + set_bit(id, dcp->memdesc_map); + + memdesc = &dcp->memdesc[id]; + + memdesc->size = resp.dva_size; + /* HACK: align size to 16K since the iommu API only maps full pages */ + size = ALIGN(resp.dva_size, SZ_16K); + memdesc->buf = dma_alloc_coherent(dcp->dev, size, + &memdesc->dva, GFP_KERNEL); + + dma_get_sgtable(dcp->dev, &memdesc->map, memdesc->buf, memdesc->dva, + size); + resp.dva = memdesc->dva; + + return resp; +} + +static u8 dcpep_cb_release_mem_desc(struct apple_dcp *dcp, u32 *mem_desc_id) +{ + struct dcp_mem_descriptor *memdesc; + size_t size; + u32 id = *mem_desc_id; + + if (id >= DCP_MAX_MAPPINGS) { + dev_warn(dcp->dev, + "unmap request for out of range mem_desc_id %u", id); + return 0; + } + + if (!test_and_clear_bit(id, dcp->memdesc_map)) { + dev_warn(dcp->dev, "unmap request for unused mem_desc_id %u\n", + id); + return 0; + } + + memdesc = &dcp->memdesc[id]; + size = ALIGN(memdesc->size, SZ_16K); + if (memdesc->buf) { + dma_free_coherent(dcp->dev, size, memdesc->buf, memdesc->dva); + memdesc->buf = NULL; + memset(&memdesc->map, 0, sizeof(memdesc->map)); + } else { + memdesc->reg = 0; + } + + memdesc->size = 0; + + return 1; +} + +/* Validate that the specified region is a display register */ +static bool is_disp_register(struct apple_dcp *dcp, u64 start, u64 end) +{ + int i; + + for (i = 0; i < dcp->nr_disp_registers; ++i) { + struct resource *r = dcp->disp_registers[i]; + + if ((start >= r->start) && (end <= r->end)) + return true; + } + + return false; +} + +/* + * Map contiguous physical memory into the DCP's address space. The firmware + * uses this to map the display registers we advertise in + * sr_map_device_memory_with_index, so we bounds check against that to guard + * safe against malicious coprocessors. + */ +static struct dcp_map_physical_resp +dcpep_cb_map_physical(struct apple_dcp *dcp, struct dcp_map_physical_req *req) +{ + int size = ALIGN(req->size, 4096); + dma_addr_t dva; + u32 id; + + if (!is_disp_register(dcp, req->paddr, req->paddr + size - 1)) { + dev_err(dcp->dev, "refusing to map phys address %llx size %llx\n", + req->paddr, req->size); + return (struct dcp_map_physical_resp){}; + } + + id = find_first_zero_bit(dcp->memdesc_map, DCP_MAX_MAPPINGS); + set_bit(id, dcp->memdesc_map); + dcp->memdesc[id].size = size; + dcp->memdesc[id].reg = req->paddr; + + dva = dma_map_resource(dcp->dev, req->paddr, size, DMA_BIDIRECTIONAL, 0); + WARN_ON(dva == DMA_MAPPING_ERROR); + + return (struct dcp_map_physical_resp){ + .dva_size = size, + .mem_desc_id = id, + .dva = dva, + }; +} + +static u64 dcpep_cb_get_frequency(struct apple_dcp *dcp) +{ + return clk_get_rate(dcp->clk); +} + +static struct DCP_FW_NAME(dcp_map_reg_resp) dcpep_cb_map_reg(struct apple_dcp *dcp, + struct DCP_FW_NAME(dcp_map_reg_req) *req) +{ + if (req->index >= dcp->nr_disp_registers) { + dev_warn(dcp->dev, "attempted to read invalid reg index %u\n", + req->index); + + return (struct DCP_FW_NAME(dcp_map_reg_resp)){ .ret = 1 }; + } else { + struct resource *rsrc = dcp->disp_registers[req->index]; +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + dma_addr_t dva = dma_map_resource(dcp->dev, rsrc->start, resource_size(rsrc), + DMA_BIDIRECTIONAL, 0); + WARN_ON(dva == DMA_MAPPING_ERROR); +#endif + + return (struct DCP_FW_NAME(dcp_map_reg_resp)){ + .addr = rsrc->start, + .length = resource_size(rsrc), +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + .dva = dva, +#endif + }; + } +} + +static struct dcp_read_edt_data_resp +dcpep_cb_read_edt_data(struct apple_dcp *dcp, struct dcp_read_edt_data_req *req) +{ + return (struct dcp_read_edt_data_resp){ + .value[0] = req->value[0], + .ret = 0, + }; +} + +static void iomfbep_cb_enable_backlight_message_ap_gated(struct apple_dcp *dcp, + u8 *enabled) +{ + /* + * update backlight brightness on next swap, on non mini-LED displays + * DCP seems to set an invalid iDAC value after coming out of DPMS. + * syslog: "[BrightnessLCD.cpp:743][AFK]nitsToDBV: iDAC out of range" + */ + dcp->brightness.update = true; + schedule_work(&dcp->bl_update_wq); +} + +/* Chunked data transfer for property dictionaries */ +static u8 dcpep_cb_prop_start(struct apple_dcp *dcp, u32 *length) +{ + if (dcp->chunks.data != NULL) { + dev_warn(dcp->dev, "ignoring spurious transfer start\n"); + return false; + } + + dcp->chunks.length = *length; + dcp->chunks.data = devm_kzalloc(dcp->dev, *length, GFP_KERNEL); + + if (!dcp->chunks.data) { + dev_warn(dcp->dev, "failed to allocate chunks\n"); + return false; + } + + return true; +} + +static u8 dcpep_cb_prop_chunk(struct apple_dcp *dcp, + struct dcp_set_dcpav_prop_chunk_req *req) +{ + if (!dcp->chunks.data) { + dev_warn(dcp->dev, "ignoring spurious chunk\n"); + return false; + } + + if (req->offset + req->length > dcp->chunks.length) { + dev_warn(dcp->dev, "ignoring overflowing chunk\n"); + return false; + } + + memcpy(dcp->chunks.data + req->offset, req->data, req->length); + return true; +} + +static bool dcpep_process_chunks(struct apple_dcp *dcp, + struct dcp_set_dcpav_prop_end_req *req) +{ + struct dcp_parse_ctx ctx; + int ret; + + if (!dcp->chunks.data) { + dev_warn(dcp->dev, "ignoring spurious end\n"); + return false; + } + + /* used just as opaque pointer for tracing */ + ctx.dcp = dcp; + + ret = parse(dcp->chunks.data, dcp->chunks.length, &ctx); + + if (ret) { + dev_warn(dcp->dev, "bad header on dcpav props\n"); + return false; + } + + if (!strcmp(req->key, "TimingElements")) { + dcp->modes = enumerate_modes(&ctx, &dcp->nr_modes, + dcp->width_mm, dcp->height_mm, + dcp->notch_height); + + if (IS_ERR(dcp->modes)) { + dev_warn(dcp->dev, "failed to parse modes\n"); + dcp->modes = NULL; + dcp->nr_modes = 0; + return false; + } + if (dcp->nr_modes == 0) + dev_warn(dcp->dev, "TimingElements without valid modes!\n"); + } else if (!strcmp(req->key, "DisplayAttributes")) { + ret = parse_display_attributes(&ctx, &dcp->width_mm, + &dcp->height_mm); + + if (ret) { + dev_warn(dcp->dev, "failed to parse display attribs\n"); + return false; + } + + dcp_set_dimensions(dcp); + } + + return true; +} + +static u8 dcpep_cb_prop_end(struct apple_dcp *dcp, + struct dcp_set_dcpav_prop_end_req *req) +{ + u8 resp = dcpep_process_chunks(dcp, req); + + /* move chunked data to connector to provide it via debugfs */ + dcp_connector_update_dict(dcp->connector, req->key, &dcp->chunks); + dcp->chunks.data = NULL; + dcp->chunks.length = 0; + + return resp; +} + +/* Boot sequence */ +static void boot_done(struct apple_dcp *dcp, void *out, void *cookie) +{ + struct dcp_channel *ch = &dcp->ch_cb; + u8 *succ = ch->output[ch->depth - 1]; + dev_dbg(dcp->dev, "boot done\n"); + + *succ = true; + dcp_ack(dcp, DCP_CONTEXT_CB); +} + +static void boot_5(struct apple_dcp *dcp, void *out, void *cookie) +{ + dcp_set_display_refresh_properties(dcp, false, boot_done, NULL); +} + +static void boot_4(struct apple_dcp *dcp, void *out, void *cookie) +{ +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + u32 v_true = 1; + dcp_late_init_signal(dcp, false, &v_true, boot_5, NULL); +#else + dcp_late_init_signal(dcp, false, boot_5, NULL); +#endif +} + +static void boot_3(struct apple_dcp *dcp, void *out, void *cookie) +{ + u32 v_true = true; + + dcp_flush_supports_power(dcp, false, &v_true, boot_4, NULL); +} + +static void boot_2(struct apple_dcp *dcp, void *out, void *cookie) +{ + dcp_setup_video_limits(dcp, false, boot_3, NULL); +} + +static void boot_1_5(struct apple_dcp *dcp, void *out, void *cookie) +{ + dcp_create_default_fb(dcp, false, boot_2, NULL); +} + +/* Use special function signature to defer the ACK */ +static bool dcpep_cb_boot_1(struct apple_dcp *dcp, int tag, void *out, void *in) +{ + trace_iomfb_callback(dcp, tag, __func__); + dcp_set_create_dfb(dcp, false, boot_1_5, NULL); + return false; +} + +static struct dcp_allocate_bandwidth_resp dcpep_cb_allocate_bandwidth(struct apple_dcp *dcp, + struct dcp_allocate_bandwidth_req *req) +{ + return (struct dcp_allocate_bandwidth_resp){ + .unk1 = req->unk1, + .unk2 = req->unk2, + .ret = 1, + }; +} + +static struct dcp_rt_bandwidth dcpep_cb_rt_bandwidth(struct apple_dcp *dcp) +{ + struct dcp_rt_bandwidth rt_bw = (struct dcp_rt_bandwidth){ + .reg_scratch = 0, + .reg_doorbell = 0, + .doorbell_bit = 0, + }; + + if (dcp->disp_bw_scratch_index) { + u32 offset = dcp->disp_bw_scratch_offset; + u32 index = dcp->disp_bw_scratch_index; + rt_bw.reg_scratch = dcp->disp_registers[index]->start + offset; + } + + if (dcp->disp_bw_doorbell_index) { + u32 index = dcp->disp_bw_doorbell_index; + rt_bw.reg_doorbell = dcp->disp_registers[index]->start; + rt_bw.doorbell_bit = REG_DOORBELL_BIT(dcp->index); + /* + * This is most certainly not padding. t8103-dcp crashes without + * setting this immediately during modeset on 12.3 and 13.5 + * firmware. + */ + rt_bw.padding[3] = 0x4; + } + + return rt_bw; +} + +static struct dcp_set_frame_sync_props_resp +dcpep_cb_set_frame_sync_props(struct apple_dcp *dcp, + struct dcp_set_frame_sync_props_req *req) +{ + return (struct dcp_set_frame_sync_props_resp){}; +} + +/* Callback to get the current time as milliseconds since the UNIX epoch */ +static u64 dcpep_cb_get_time(struct apple_dcp *dcp) +{ + return ktime_to_ms(ktime_get_real()); +} + +struct dcp_swap_cookie { + struct kref refcount; + struct completion done; + u32 swap_id; +}; + +static void release_swap_cookie(struct kref *ref) +{ + struct dcp_swap_cookie *cookie; + cookie = container_of(ref, struct dcp_swap_cookie, refcount); + + kfree(cookie); +} + +static void dcp_swap_cleared(struct apple_dcp *dcp, void *data, void *cookie) +{ + struct DCP_FW_NAME(dcp_swap_submit_resp) *resp = data; + + if (cookie) { + struct dcp_swap_cookie *info = cookie; + complete(&info->done); + kref_put(&info->refcount, release_swap_cookie); + } + + if (resp->ret) { + dev_err(dcp->dev, "swap_clear failed! status %u\n", resp->ret); + dcp_drm_crtc_vblank(dcp->crtc); + return; + } + + while (!list_empty(&dcp->swapped_out_fbs)) { + struct dcp_fb_reference *entry; + entry = list_first_entry(&dcp->swapped_out_fbs, + struct dcp_fb_reference, head); + if (entry->swap_id == dcp->last_swap_id) + break; + if (entry->fb) + drm_framebuffer_put(entry->fb); + list_del(&entry->head); + kfree(entry); + } +} + +static void dcp_swap_clear_started(struct apple_dcp *dcp, void *data, + void *cookie) +{ + struct dcp_swap_start_resp *resp = data; + DCP_FW_UNION(dcp->swap).swap.swap_id = resp->swap_id; + + if (cookie) { + struct dcp_swap_cookie *info = cookie; + info->swap_id = resp->swap_id; + } + + dcp_swap_submit(dcp, false, &DCP_FW_UNION(dcp->swap), dcp_swap_cleared, cookie); +} + +static void dcp_on_final(struct apple_dcp *dcp, void *out, void *cookie) +{ + struct dcp_wait_cookie *wait = cookie; + + if (wait) { + complete(&wait->done); + kref_put(&wait->refcount, release_wait_cookie); + } +} + +static void dcp_on_set_power_state(struct apple_dcp *dcp, void *out, void *cookie) +{ + struct dcp_set_power_state_req req = { + .unklong = 1, + }; + + dcp_set_power_state(dcp, false, &req, dcp_on_final, cookie); +} + +static void dcp_on_set_parameter(struct apple_dcp *dcp, void *out, void *cookie) +{ + struct dcp_set_parameter_dcp param = { + .param = 14, + .value = { 0 }, +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + .count = 3, +#else + .count = 1, +#endif + }; + + dcp_set_parameter_dcp(dcp, false, ¶m, dcp_on_set_power_state, cookie); +} + +void DCP_FW_NAME(iomfb_poweron)(struct apple_dcp *dcp) +{ + struct dcp_wait_cookie *cookie; + int ret; + u32 handle; + dev_info(dcp->dev, "dcp_poweron() starting\n"); + + cookie = kzalloc(sizeof(*cookie), GFP_KERNEL); + if (!cookie) + return; + + init_completion(&cookie->done); + kref_init(&cookie->refcount); + /* increase refcount to ensure the receiver has a reference */ + kref_get(&cookie->refcount); + + if (dcp->main_display) { + handle = 0; + dcp_set_display_device(dcp, false, &handle, dcp_on_set_power_state, + cookie); + } else { + handle = 2; + dcp_set_display_device(dcp, false, &handle, + dcp_on_set_parameter, cookie); + } + ret = wait_for_completion_timeout(&cookie->done, msecs_to_jiffies(5000)); + + if (ret == 0) + dev_warn(dcp->dev, "wait for power timed out\n"); + else if (ret > 0) + dev_info(dcp->dev, "dcp_set_power_state_req returned, %d ms remaining\n", jiffies_to_msecs(ret)); + if (ret <= 0) + drm_connector_set_link_status_property(&dcp->connector->base, + DRM_MODE_LINK_STATUS_BAD); + + kref_put(&cookie->refcount, release_wait_cookie);; + + /* Force a brightness update after poweron, to restore the brightness */ + dcp->brightness.update = true; +} + +static void complete_set_powerstate(struct apple_dcp *dcp, void *out, + void *cookie) +{ + struct dcp_wait_cookie *wait = cookie; + + if (wait) { + complete(&wait->done); + kref_put(&wait->refcount, release_wait_cookie); + } +} + +static void last_client_closed_poff(struct apple_dcp *dcp, void *out, void *cookie) +{ + struct dcp_set_power_state_req power_req = { + .unklong = 0, + }; + dcp_set_power_state(dcp, false, &power_req, complete_set_powerstate, + cookie); +} + +static void aborted_swaps_dcp_poff(struct apple_dcp *dcp, void *out, void *cookie) +{ + struct iomfb_last_client_close_req last_client_req = {}; + iomfb_last_client_close(dcp, false, &last_client_req, + last_client_closed_poff, cookie); +} + +void DCP_FW_NAME(iomfb_poweroff)(struct apple_dcp *dcp) +{ + int ret, swap_id; + struct iomfb_abort_swaps_dcp_req abort_req = { + .client = { + .flag2 = 1, + }, + }; + struct dcp_swap_cookie *cookie; + struct dcp_wait_cookie *poff_cookie; + struct dcp_swap_start_req swap_req = { 0 }; + struct DCP_FW_NAME(dcp_swap_submit_req) *swap = &DCP_FW_UNION(dcp->swap); + + cookie = kzalloc(sizeof(*cookie), GFP_KERNEL); + if (!cookie) + return; + init_completion(&cookie->done); + kref_init(&cookie->refcount); + /* increase refcount to ensure the receiver has a reference */ + kref_get(&cookie->refcount); + + // clear surfaces + memset(swap, 0, sizeof(*swap)); + + swap->swap.swap_enabled = + swap->swap.swap_completed = IOMFB_SET_BACKGROUND | 0x7; + swap->swap.bg_color = 0xFF000000; + + /* + * Turn off the backlight. This matters because the DCP's idea of + * backlight brightness gets desynced after a power change, and it + * needs to be told it's going to turn off so it will consider the + * subsequent update on poweron an actual change and restore the + * brightness. + */ + if (dcp_has_panel(dcp)) { + swap->swap.bl_unk = 1; + swap->swap.bl_value = 0; + swap->swap.bl_power = 0; + } + + /* Null all surfaces */ + for (int l = 0; l < SWAP_SURFACES; l++) + swap->surf_null[l] = true; +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + for (int l = 0; l < 5; l++) + swap->surf2_null[l] = true; + swap->unkU32Ptr_null = true; + swap->unkU32out_null = true; +#endif + + dcp_swap_start(dcp, false, &swap_req, dcp_swap_clear_started, cookie); + + ret = wait_for_completion_timeout(&cookie->done, msecs_to_jiffies(50)); + swap_id = cookie->swap_id; + kref_put(&cookie->refcount, release_swap_cookie); + if (ret <= 0) { + dcp->crashed = true; + return; + } + + dev_dbg(dcp->dev, "%s: clear swap submitted: %u\n", __func__, swap_id); + + poff_cookie = kzalloc(sizeof(*poff_cookie), GFP_KERNEL); + if (!poff_cookie) + return; + init_completion(&poff_cookie->done); + kref_init(&poff_cookie->refcount); + /* increase refcount to ensure the receiver has a reference */ + kref_get(&poff_cookie->refcount); + + iomfb_abort_swaps_dcp(dcp, false, &abort_req, + aborted_swaps_dcp_poff, poff_cookie); + ret = wait_for_completion_timeout(&poff_cookie->done, + msecs_to_jiffies(1000)); + + if (ret == 0) + dev_warn(dcp->dev, "setPowerState(0) timeout %u ms\n", 1000); + else if (ret > 0) + dev_dbg(dcp->dev, + "setPowerState(0) finished with %d ms to spare", + jiffies_to_msecs(ret)); + + kref_put(&poff_cookie->refcount, release_wait_cookie); + + dev_info(dcp->dev, "dcp_poweroff() done\n"); +} + +static void last_client_closed_sleep(struct apple_dcp *dcp, void *out, void *cookie) +{ + struct dcp_set_power_state_req power_req = { + .unklong = 0, + }; + dcp_set_power_state(dcp, false, &power_req, complete_set_powerstate, cookie); +} + +static void aborted_swaps_dcp_sleep(struct apple_dcp *dcp, void *out, void *cookie) +{ + struct iomfb_last_client_close_req req = { 0 }; + iomfb_last_client_close(dcp, false, &req, last_client_closed_sleep, cookie); +} + +void DCP_FW_NAME(iomfb_sleep)(struct apple_dcp *dcp) +{ + int ret; + struct iomfb_abort_swaps_dcp_req req = { + .client = { + .flag2 = 1, + }, + }; + + struct dcp_wait_cookie *cookie; + + cookie = kzalloc(sizeof(*cookie), GFP_KERNEL); + if (!cookie) + return; + init_completion(&cookie->done); + kref_init(&cookie->refcount); + /* increase refcount to ensure the receiver has a reference */ + kref_get(&cookie->refcount); + + iomfb_abort_swaps_dcp(dcp, false, &req, aborted_swaps_dcp_sleep, + cookie); + ret = wait_for_completion_timeout(&cookie->done, + msecs_to_jiffies(1000)); + + if (ret == 0) + dev_warn(dcp->dev, "setDCPPower(0) timeout %u ms\n", 1000); + + kref_put(&cookie->refcount, release_wait_cookie); + dev_info(dcp->dev, "dcp_sleep() done\n"); +} + +static void dcpep_cb_hotplug(struct apple_dcp *dcp, u64 *connected) +{ + struct apple_connector *connector = dcp->connector; + + /* DCP issues hotplug_gated callbacks after SetPowerState() calls on + * devices with display (macbooks, imacs). This must not result in + * connector state changes on DRM side. Some applications won't enable + * a CRTC with a connector in disconnected state. Weston after DPMS off + * is one example. dcp_is_main_display() returns true on devices with + * integrated display. Ignore the hotplug_gated() callbacks there. + */ + if (dcp->main_display) + return; + + if (dcp->during_modeset) { + dev_info(dcp->dev, + "cb_hotplug() ignored during modeset connected:%llu\n", + *connected); + return; + } + + dev_info(dcp->dev, "cb_hotplug() connected:%llu, valid_mode:%d\n", + *connected, dcp->valid_mode); + + /* Hotplug invalidates mode. DRM doesn't always handle this. */ + if (!(*connected)) { + dcp->valid_mode = false; + /* after unplug swap will not complete until the next + * set_digital_out_mode */ + schedule_work(&dcp->vblank_wq); + } + + if (connector && connector->connected != !!(*connected)) { + connector->connected = !!(*connected); + dcp->valid_mode = false; + schedule_work(&connector->hotplug_wq); + } +} + +static void +dcpep_cb_swap_complete_intent_gated(struct apple_dcp *dcp, + struct dcp_swap_complete_intent_gated *info) +{ + trace_iomfb_swap_complete_intent_gated(dcp, info->swap_id, + info->width, info->height); +} + +static void +dcpep_cb_abort_swap_ap_gated(struct apple_dcp *dcp, u32 *swap_id) +{ + trace_iomfb_abort_swap_ap_gated(dcp, *swap_id); +} + +static struct dcpep_get_tiling_state_resp +dcpep_cb_get_tiling_state(struct apple_dcp *dcp, + struct dcpep_get_tiling_state_req *req) +{ + return (struct dcpep_get_tiling_state_resp){ + .value = 0, + .ret = 1, + }; +} + +static u8 dcpep_cb_create_backlight_service(struct apple_dcp *dcp) +{ + return dcp_has_panel(dcp); +} + +TRAMPOLINE_VOID(trampoline_nop, dcpep_cb_nop); +TRAMPOLINE_OUT(trampoline_true, dcpep_cb_true, u8); +TRAMPOLINE_OUT(trampoline_false, dcpep_cb_false, u8); +TRAMPOLINE_OUT(trampoline_zero, dcpep_cb_zero, u32); +TRAMPOLINE_IN(trampoline_swap_complete, dcpep_cb_swap_complete, + struct DCP_FW_NAME(dc_swap_complete_resp)); +TRAMPOLINE_INOUT(trampoline_get_uint_prop, dcpep_cb_get_uint_prop, + struct dcp_get_uint_prop_req, struct dcp_get_uint_prop_resp); +TRAMPOLINE_IN(trampoline_set_fx_prop, iomfbep_cb_set_fx_prop, + struct iomfb_set_fx_prop_req) +TRAMPOLINE_INOUT(trampoline_map_piodma, dcpep_cb_map_piodma, + struct dcp_map_buf_req, struct dcp_map_buf_resp); +TRAMPOLINE_IN(trampoline_unmap_piodma, dcpep_cb_unmap_piodma, + struct dcp_unmap_buf_resp); +TRAMPOLINE_INOUT(trampoline_sr_set_property_int, iomfbep_cb_sr_set_property_int, + struct iomfb_sr_set_property_int_req, u8); +TRAMPOLINE_INOUT(trampoline_allocate_buffer, dcpep_cb_allocate_buffer, + struct dcp_allocate_buffer_req, + struct dcp_allocate_buffer_resp); +TRAMPOLINE_INOUT(trampoline_map_physical, dcpep_cb_map_physical, + struct dcp_map_physical_req, struct dcp_map_physical_resp); +TRAMPOLINE_INOUT(trampoline_release_mem_desc, dcpep_cb_release_mem_desc, u32, + u8); +TRAMPOLINE_INOUT(trampoline_map_reg, dcpep_cb_map_reg, + struct DCP_FW_NAME(dcp_map_reg_req), + struct DCP_FW_NAME(dcp_map_reg_resp)); +TRAMPOLINE_INOUT(trampoline_read_edt_data, dcpep_cb_read_edt_data, + struct dcp_read_edt_data_req, struct dcp_read_edt_data_resp); +TRAMPOLINE_INOUT(trampoline_prop_start, dcpep_cb_prop_start, u32, u8); +TRAMPOLINE_INOUT(trampoline_prop_chunk, dcpep_cb_prop_chunk, + struct dcp_set_dcpav_prop_chunk_req, u8); +TRAMPOLINE_INOUT(trampoline_prop_end, dcpep_cb_prop_end, + struct dcp_set_dcpav_prop_end_req, u8); +TRAMPOLINE_INOUT(trampoline_allocate_bandwidth, dcpep_cb_allocate_bandwidth, + struct dcp_allocate_bandwidth_req, struct dcp_allocate_bandwidth_resp); +TRAMPOLINE_OUT(trampoline_rt_bandwidth, dcpep_cb_rt_bandwidth, + struct dcp_rt_bandwidth); +TRAMPOLINE_INOUT(trampoline_set_frame_sync_props, dcpep_cb_set_frame_sync_props, + struct dcp_set_frame_sync_props_req, + struct dcp_set_frame_sync_props_resp); +TRAMPOLINE_OUT(trampoline_get_frequency, dcpep_cb_get_frequency, u64); +TRAMPOLINE_OUT(trampoline_get_time, dcpep_cb_get_time, u64); +TRAMPOLINE_IN(trampoline_hotplug, dcpep_cb_hotplug, u64); +TRAMPOLINE_IN(trampoline_swap_complete_intent_gated, + dcpep_cb_swap_complete_intent_gated, + struct dcp_swap_complete_intent_gated); +TRAMPOLINE_IN(trampoline_abort_swap_ap_gated, dcpep_cb_abort_swap_ap_gated, u32); +TRAMPOLINE_IN(trampoline_enable_backlight_message_ap_gated, + iomfbep_cb_enable_backlight_message_ap_gated, u8); +TRAMPOLINE_IN(trampoline_pr_publish, iomfb_cb_pr_publish, + struct iomfb_property); +TRAMPOLINE_INOUT(trampoline_get_tiling_state, dcpep_cb_get_tiling_state, + struct dcpep_get_tiling_state_req, struct dcpep_get_tiling_state_resp); +TRAMPOLINE_OUT(trampoline_create_backlight_service, dcpep_cb_create_backlight_service, u8); + +/* + * Callback for swap requests. If a swap failed, we'll never get a swap + * complete event so we need to fake a vblank event early to avoid a hang. + */ + +static void dcp_swapped(struct apple_dcp *dcp, void *data, void *cookie) +{ + struct DCP_FW_NAME(dcp_swap_submit_resp) *resp = data; + + if (resp->ret) { + dev_err(dcp->dev, "swap failed! status %u\n", resp->ret); + dcp_drm_crtc_vblank(dcp->crtc); + return; + } + dcp->swap_start = ktime_get(); + + while (!list_empty(&dcp->swapped_out_fbs)) { + struct dcp_fb_reference *entry; + entry = list_first_entry(&dcp->swapped_out_fbs, + struct dcp_fb_reference, head); + if (entry->swap_id == dcp->last_swap_id) + break; + if (entry->fb) + drm_framebuffer_put(entry->fb); + list_del(&entry->head); + kfree(entry); + } +} + +static void dcp_swap_started(struct apple_dcp *dcp, void *data, void *cookie) +{ + struct dcp_swap_start_resp *resp = data; + + DCP_FW_UNION(dcp->swap).swap.swap_id = resp->swap_id; + + trace_iomfb_swap_submit(dcp, resp->swap_id); + dcp_swap_submit(dcp, false, &DCP_FW_UNION(dcp->swap), dcp_swapped, NULL); +} + +/* Helpers to modeset and swap, used to flush */ +static void do_swap(struct apple_dcp *dcp, void *data, void *cookie) +{ + struct dcp_swap_start_req start_req = { 0 }; + + if (dcp->connector && dcp->connector->connected) + dcp_swap_start(dcp, false, &start_req, dcp_swap_started, NULL); + else + dcp_drm_crtc_vblank(dcp->crtc); +} + +static void complete_set_digital_out_mode(struct apple_dcp *dcp, void *data, + void *cookie) +{ + struct dcp_wait_cookie *wait = cookie; + + if (wait) { + complete(&wait->done); + kref_put(&wait->refcount, release_wait_cookie); + } +} + +int DCP_FW_NAME(iomfb_modeset)(struct apple_dcp *dcp, + struct drm_crtc_state *crtc_state) +{ + struct dcp_display_mode *mode; + struct dcp_wait_cookie *cookie; + struct dcp_color_mode *cmode = NULL; + int ret; + + mode = lookup_mode(dcp, &crtc_state->mode); + if (!mode) { + dev_err(dcp->dev, "no match for " DRM_MODE_FMT "\n", + DRM_MODE_ARG(&crtc_state->mode)); + return -EIO; + } + + dev_info(dcp->dev, + "set_digital_out_mode(color:%d timing:%d) " DRM_MODE_FMT "\n", + mode->color_mode_id, mode->timing_mode_id, + DRM_MODE_ARG(&crtc_state->mode)); + if (mode->color_mode_id == mode->sdr_rgb.id) + cmode = &mode->sdr_rgb; + else if (mode->color_mode_id == mode->sdr_444.id) + cmode = &mode->sdr_444; + else if (mode->color_mode_id == mode->sdr.id) + cmode = &mode->sdr; + else if (mode->color_mode_id == mode->best.id) + cmode = &mode->best; + if (cmode) + dev_info(dcp->dev, + "set_digital_out_mode() color mode depth:%hhu format:%u " + "colorimetry:%u eotf:%u range:%u vrr:%u\n", cmode->depth, + cmode->format, cmode->colorimetry, cmode->eotf, + cmode->range, mode->vrr); + + dcp->mode = (struct dcp_set_digital_out_mode_req){ + .color_mode_id = mode->color_mode_id, + .timing_mode_id = mode->timing_mode_id + }; + + /* Keep track of suspected vrr modes */ + dcp->use_timestamps = mode->vrr; + + cookie = kzalloc(sizeof(*cookie), GFP_KERNEL); + if (!cookie) { + return -ENOMEM; + } + + init_completion(&cookie->done); + kref_init(&cookie->refcount); + /* increase refcount to ensure the receiver has a reference */ + kref_get(&cookie->refcount); + + dcp->during_modeset = true; + + dcp_set_digital_out_mode(dcp, false, &dcp->mode, + complete_set_digital_out_mode, cookie); + + /* + * The DCP firmware has an internal timeout of ~8 seconds for + * modesets. Add an extra 500ms to safe side that the modeset + * call has returned. + */ + ret = wait_for_completion_timeout(&cookie->done, + msecs_to_jiffies(8500)); + + kref_put(&cookie->refcount, release_wait_cookie); + dcp->during_modeset = false; + dev_info(dcp->dev, "set_digital_out_mode finished:%d\n", ret); + + if (ret == 0) { + dev_info(dcp->dev, "set_digital_out_mode timed out\n"); + return -EIO; + } else if (ret < 0) { + dev_info(dcp->dev, + "waiting on set_digital_out_mode failed:%d\n", ret); + return -EIO; + + } else if (ret > 0) { + dev_dbg(dcp->dev, + "set_digital_out_mode finished with %d to spare\n", + jiffies_to_msecs(ret)); + } + dcp->valid_mode = true; + + return 0; +} + +void DCP_FW_NAME(iomfb_flush)(struct apple_dcp *dcp, struct drm_crtc *crtc, struct drm_atomic_state *state) +{ + struct drm_plane *plane; + struct drm_plane_state *new_state, *old_state; + struct drm_crtc_state *crtc_state; + struct DCP_FW_NAME(dcp_swap_submit_req) *req = &DCP_FW_UNION(dcp->swap); + int plane_idx, l; + int has_surface = 0; + + crtc_state = drm_atomic_get_new_crtc_state(state, crtc); + + /* Reset all surfaces to defaults */ + memset(req, 0, sizeof(*req)); + for (l = 0; l < SWAP_SURFACES; l++) + req->surf_null[l] = true; +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + for (l = 0; l < 5; l++) + req->surf2_null[l] = true; + req->unkU32Ptr_null = true; + req->unkU32out_null = true; +#endif + + /* + * Clear all surfaces on startup. The boot framebuffer in surface 0 + * sticks around. + */ + if (!dcp->surfaces_cleared) { + req->swap.swap_enabled = IOMFB_SET_BACKGROUND | 0x7; + req->swap.bg_color = 0xFF000000; + dcp->surfaces_cleared = true; + } + + for_each_oldnew_plane_in_state(state, plane, old_state, new_state, plane_idx) { + struct apple_plane_state *apple_state = to_apple_plane_state(new_state); + + /* skip planes not for this crtc */ + if (old_state->crtc != crtc && new_state->crtc != crtc) + continue; + + /* + * Plane order is nondeterministic for this iterator. DCP will + * almost always crash at some point if the z order of planes + * flip-flops around. Make sure we are always blending them + * in the correct order. + * + * Despite having 4 surfaces, we can only blend two. Surface 0 is + * also unusable on some machines, so ignore it. + */ + + l = MAX_BLEND_SURFACES - new_state->normalized_zpos; + + WARN_ON(l > MAX_BLEND_SURFACES); + + req->swap.swap_enabled |= BIT(l); + + if (old_state->fb && new_state->fb != old_state->fb) { + /* + * Race condition between a framebuffer unbind getting + * swapped out and GEM unreferencing a framebuffer. If + * we lose the race, the display gets IOVA faults and + * the DCP crashes. We need to extend the lifetime of + * the drm_framebuffer (and hence the GEM object) until + * after we get a swap complete for the swap unbinding + * it. + */ + struct dcp_fb_reference *entry = + kzalloc(sizeof(*entry), GFP_KERNEL); + if (entry) { + entry->fb = old_state->fb; + entry->swap_id = dcp->last_swap_id; + list_add_tail(&entry->head, + &dcp->swapped_out_fbs); + } + drm_framebuffer_get(old_state->fb); + } + + if (!new_state->fb || !new_state->visible) { + continue; + } + req->surf_null[l] = false; + has_surface = 1; + + req->swap.src_rect[l] = apple_state->src_rect; + req->swap.dst_rect[l] = apple_state->dst_rect; + + if (dcp->notch_height > 0) + req->swap.dst_rect[l].y += dcp->notch_height; + + req->surf_iova[l] = apple_state->iova; + req->surf[l].base = apple_state->surf; + + /* Use sRGB colorspace only for internal panels. External + * displays are expected to have EDID and user space can use + * the contained colorimetry information to provide native + * colors. + */ + if (dcp->connector_type == DRM_MODE_CONNECTOR_eDP && + req->surf[l].base.colorspace == DCP_COLORSPACE_BG_SRGB) + req->surf[l].base.colorspace = DCP_COLORSPACE_NATIVE; + } + + if (!has_surface && !crtc_state->color_mgmt_changed) { + if (crtc_state->enable && crtc_state->active && + !crtc_state->planes_changed) { + schedule_work(&dcp->vblank_wq); + return; + } + + /* Set black background */ + req->swap.swap_enabled |= IOMFB_SET_BACKGROUND; + req->swap.bg_color = 0xFF000000; + req->clear = 1; + } + + if (has_surface && dcp->use_timestamps) { + /* + * Fake timstamps to get 120hz refresh rate. It looks + * like the actual value does not matter, as long as it is non zero. + */ + req->swap.ts1 = 120; + req->swap.ts2 = 120; + req->swap.ts3 = 120; + } + + /* These fields should be set together */ + req->swap.swap_completed = req->swap.swap_enabled; + + /* update brightness if changed */ + if (dcp_has_panel(dcp) && dcp->brightness.update) { + req->swap.bl_unk = 1; + req->swap.bl_value = dcp->brightness.dac; + req->swap.bl_power = 0x40; + dcp->brightness.update = false; + } + + if (crtc_state->color_mgmt_changed && crtc_state->ctm) { + struct iomfb_set_matrix_req mat; + struct drm_color_ctm *ctm = (struct drm_color_ctm *)crtc_state->ctm->data; + + mat.unk_u32 = 9; + mat.r[0] = ctm->matrix[0]; + mat.r[1] = ctm->matrix[1]; + mat.r[2] = ctm->matrix[2]; + mat.g[0] = ctm->matrix[3]; + mat.g[1] = ctm->matrix[4]; + mat.g[2] = ctm->matrix[5]; + mat.b[0] = ctm->matrix[6]; + mat.b[1] = ctm->matrix[7]; + mat.b[2] = ctm->matrix[8]; + + iomfb_set_matrix(dcp, false, &mat, do_swap, NULL); + } else + do_swap(dcp, NULL, NULL); +} + +static void res_is_main_display(struct apple_dcp *dcp, void *out, void *cookie) +{ + struct apple_connector *connector; + int result = *(int *)out; + dev_info(dcp->dev, "DCP is_main_display: %d\n", result); + + dcp->main_display = result != 0; + + connector = dcp->connector; + if (connector) { + connector->connected = dcp->nr_modes > 0; + schedule_work(&connector->hotplug_wq); + } + + dcp->active = true; + complete(&dcp->start_done); +} + +static void init_3(struct apple_dcp *dcp, void *out, void *cookie) +{ + dcp_is_main_display(dcp, false, res_is_main_display, NULL); +} + +static void init_2(struct apple_dcp *dcp, void *out, void *cookie) +{ + dcp_first_client_open(dcp, false, init_3, NULL); +} + +static void init_1(struct apple_dcp *dcp, void *out, void *cookie) +{ + u32 val = 0; + dcp_enable_disable_video_power_savings(dcp, false, &val, init_2, NULL); +} + +static void dcp_started(struct apple_dcp *dcp, void *data, void *cookie) +{ + struct iomfb_get_color_remap_mode_req color_remap = + (struct iomfb_get_color_remap_mode_req){ + .mode = 6, + }; + + dev_info(dcp->dev, "DCP booted\n"); + + iomfb_get_color_remap_mode(dcp, false, &color_remap, init_1, cookie); +} + +void DCP_FW_NAME(iomfb_shutdown)(struct apple_dcp *dcp) +{ + struct dcp_set_power_state_req req = { + /* defaults are ok */ + }; + + dcp_set_power_state(dcp, false, &req, NULL, NULL); +} diff --git a/drivers/gpu/drm/apple/iomfb_template.h b/drivers/gpu/drm/apple/iomfb_template.h new file mode 100644 index 00000000000000..c208e1e8e6c1f9 --- /dev/null +++ b/drivers/gpu/drm/apple/iomfb_template.h @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2021 Alyssa Rosenzweig */ + +/* + * This file is intended to be included multiple times with IOMFB_VER + * defined to declare DCP firmware version dependent structs. + */ + +#ifdef DCP_FW_VER + +#include + +#include + +#include "iomfb.h" +#include "iomfb_plane.h" +#include "plane.h" +#include "version_utils.h" + +struct DCP_FW_NAME(dcp_swap) { + u64 ts1; + u64 ts2; + + u64 unk_10; + u64 unk_18; + u64 ts64_unk; + u64 unk_28; + u64 ts3; + u64 unk_38; + + u64 flags1; + u64 flags2; + + u32 swap_id; + + u32 surf_ids[SWAP_SURFACES]; + struct dcp_rect src_rect[SWAP_SURFACES]; + u32 surf_flags[SWAP_SURFACES]; + u32 surf_unk[SWAP_SURFACES]; + struct dcp_rect dst_rect[SWAP_SURFACES]; + u32 swap_enabled; + u32 swap_completed; + + u32 bg_color; + u8 unk_110[0x1b8]; + u32 unk_2c8; + u8 unk_2cc[0x14]; + u32 unk_2e0; +#if DCP_FW_VER < DCP_FW_VERSION(13, 2, 0) + u16 unk_2e2; +#else + u8 unk_2e2[3]; +#endif + u64 bl_unk; + u32 bl_value; // min value is 0x10000000 + u8 bl_power; // constant 0x40 for on + u8 unk_2f3[0x2d]; +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + u8 unk_320[0x13f]; + u64 unk_1; +#endif +} __packed; + +/* Information describing a surface */ +struct DCP_FW_NAME(dcp_surface) { + struct dcp_surface base; +#if DCP_FW_VER < DCP_FW_VERSION(13, 2, 0) + u8 padding[7]; +#else + u8 padding[47]; +#endif +} __packed; + +/* Prototypes */ + +struct DCP_FW_NAME(dcp_swap_submit_req) { + struct DCP_FW_NAME(dcp_swap) swap; + struct DCP_FW_NAME(dcp_surface) surf[SWAP_SURFACES]; + u64 surf_iova[SWAP_SURFACES]; +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + u64 unk_u64_a[SWAP_SURFACES]; + struct DCP_FW_NAME(dcp_surface) surf2[5]; + u64 surf2_iova[5]; +#endif + u8 unkbool; + u64 unkdouble; +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + u64 unkU64; + u8 unkbool2; +#endif + u32 clear; // or maybe switch to default fb? +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + u32 unkU32Ptr; +#endif + u8 swap_null; + u8 surf_null[SWAP_SURFACES]; +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + u8 surf2_null[5]; +#endif + u8 unkoutbool_null; +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + u8 unkU32Ptr_null; + u8 unkU32out_null; +#endif + u8 padding[1]; +} __packed; + +struct DCP_FW_NAME(dcp_swap_submit_resp) { + u8 unkoutbool; +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + u32 unkU32out; +#endif + u32 ret; + u8 padding[3]; +} __packed; + +struct DCP_FW_NAME(dc_swap_complete_resp) { + u32 swap_id; + u8 unkbool; + u64 swap_data; +#if DCP_FW_VER < DCP_FW_VERSION(13, 2, 0) + u8 swap_info[0x6c4]; +#else + u8 swap_info[0x6c5]; +#endif + u32 unkint; + u8 swap_info_null; +} __packed; + +struct DCP_FW_NAME(dcp_map_reg_req) { + char obj[4]; + u32 index; + u32 flags; +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + u8 unk_u64_null; +#endif + u8 addr_null; + u8 length_null; +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + u8 padding[1]; +#else + u8 padding[2]; +#endif +} __packed; + +struct DCP_FW_NAME(dcp_map_reg_resp) { +#if DCP_FW_VER >= DCP_FW_VERSION(13, 2, 0) + u64 dva; +#endif + u64 addr; + u64 length; + u32 ret; +} __packed; + + +struct apple_dcp; + +int DCP_FW_NAME(iomfb_modeset)(struct apple_dcp *dcp, + struct drm_crtc_state *crtc_state); +void DCP_FW_NAME(iomfb_flush)(struct apple_dcp *dcp, struct drm_crtc *crtc, struct drm_atomic_state *state); +void DCP_FW_NAME(iomfb_poweron)(struct apple_dcp *dcp); +void DCP_FW_NAME(iomfb_poweroff)(struct apple_dcp *dcp); +void DCP_FW_NAME(iomfb_sleep)(struct apple_dcp *dcp); +void DCP_FW_NAME(iomfb_start)(struct apple_dcp *dcp); +void DCP_FW_NAME(iomfb_shutdown)(struct apple_dcp *dcp); + +#endif diff --git a/drivers/gpu/drm/apple/iomfb_v12_3.c b/drivers/gpu/drm/apple/iomfb_v12_3.c new file mode 100644 index 00000000000000..0fe08c42d64659 --- /dev/null +++ b/drivers/gpu/drm/apple/iomfb_v12_3.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright The Asahi Linux Contributors */ + +#include "iomfb_v12_3.h" +#include "iomfb_v13_3.h" +#include "version_utils.h" + +static const struct dcp_method_entry dcp_methods[dcpep_num_methods] = { + IOMFB_METHOD("A000", dcpep_late_init_signal), + IOMFB_METHOD("A029", dcpep_setup_video_limits), + IOMFB_METHOD("A131", iomfbep_a131_pmu_service_matched), + IOMFB_METHOD("A132", iomfbep_a132_backlight_service_matched), + IOMFB_METHOD("A357", dcpep_set_create_dfb), + IOMFB_METHOD("A358", iomfbep_a358_vi_set_temperature_hint), + IOMFB_METHOD("A401", dcpep_start_signal), + IOMFB_METHOD("A407", dcpep_swap_start), + IOMFB_METHOD("A408", dcpep_swap_submit), + IOMFB_METHOD("A410", dcpep_set_display_device), + IOMFB_METHOD("A411", dcpep_is_main_display), + IOMFB_METHOD("A412", dcpep_set_digital_out_mode), + IOMFB_METHOD("A422", iomfbep_set_matrix), + IOMFB_METHOD("A426", iomfbep_get_color_remap_mode), + IOMFB_METHOD("A439", dcpep_set_parameter_dcp), + IOMFB_METHOD("A443", dcpep_create_default_fb), + IOMFB_METHOD("A447", dcpep_enable_disable_video_power_savings), + IOMFB_METHOD("A454", dcpep_first_client_open), + IOMFB_METHOD("A455", iomfbep_last_client_close), + IOMFB_METHOD("A460", dcpep_set_display_refresh_properties), + IOMFB_METHOD("A463", dcpep_flush_supports_power), + IOMFB_METHOD("A464", iomfbep_abort_swaps_dcp), + IOMFB_METHOD("A468", dcpep_set_power_state), +}; + +#define DCP_FW v12_3 +#define DCP_FW_VER DCP_FW_VERSION(12, 3, 0) + +#include "iomfb_template.c" + +static const iomfb_cb_handler cb_handlers[IOMFB_MAX_CB] = { + [0] = trampoline_true, /* did_boot_signal */ + [1] = trampoline_true, /* did_power_on_signal */ + [2] = trampoline_nop, /* will_power_off_signal */ + [3] = trampoline_rt_bandwidth, + [100] = iomfbep_cb_match_pmu_service, + [101] = trampoline_zero, /* get_display_default_stride */ + [102] = trampoline_nop, /* set_number_property */ + [103] = trampoline_nop, /* set_boolean_property */ + [106] = trampoline_nop, /* remove_property */ + [107] = trampoline_true, /* create_provider_service */ + [108] = trampoline_true, /* create_product_service */ + [109] = trampoline_true, /* create_pmu_service */ + [110] = trampoline_true, /* create_iomfb_service */ + [111] = trampoline_create_backlight_service, + [116] = dcpep_cb_boot_1, + [117] = trampoline_false, /* is_dark_boot */ + [118] = trampoline_false, /* is_dark_boot / is_waking_from_hibernate*/ + [120] = trampoline_read_edt_data, + [122] = trampoline_prop_start, + [123] = trampoline_prop_chunk, + [124] = trampoline_prop_end, + [201] = trampoline_map_piodma, + [202] = trampoline_unmap_piodma, + [206] = iomfbep_cb_match_pmu_service_2, + [207] = iomfbep_cb_match_backlight_service, + [208] = trampoline_get_time, + [211] = trampoline_nop, /* update_backlight_factor_prop */ + [300] = trampoline_pr_publish, + [401] = trampoline_get_uint_prop, + [404] = trampoline_nop, /* sr_set_uint_prop */ + [406] = trampoline_set_fx_prop, + [408] = trampoline_get_frequency, + [411] = trampoline_map_reg, + [413] = trampoline_true, /* sr_set_property_dict */ + [414] = trampoline_sr_set_property_int, + [415] = trampoline_true, /* sr_set_property_bool */ + [451] = trampoline_allocate_buffer, + [452] = trampoline_map_physical, + [456] = trampoline_release_mem_desc, + [552] = trampoline_true, /* set_property_dict_0 */ + [561] = trampoline_true, /* set_property_dict */ + [563] = trampoline_true, /* set_property_int */ + [565] = trampoline_true, /* set_property_bool */ + [567] = trampoline_true, /* set_property_str */ + [574] = trampoline_zero, /* power_up_dart */ + [576] = trampoline_hotplug, + [577] = trampoline_nop, /* powerstate_notify */ + [582] = trampoline_true, /* create_default_fb_surface */ + [584] = trampoline_nop, /* IOMobileFramebufferAP::clear_default_surface */ + [588] = trampoline_nop, /* resize_default_fb_surface_gated */ + [589] = trampoline_swap_complete, + [591] = trampoline_swap_complete_intent_gated, + [592] = trampoline_abort_swap_ap_gated, + [593] = trampoline_enable_backlight_message_ap_gated, + [594] = trampoline_nop, /* IOMobileFramebufferAP::setSystemConsoleMode */ + [596] = trampoline_false, /* IOMobileFramebufferAP::isDFBAllocated */ + [597] = trampoline_false, /* IOMobileFramebufferAP::preserveContents */ + [598] = trampoline_nop, /* find_swap_function_gated */ +}; + +void DCP_FW_NAME(iomfb_start)(struct apple_dcp *dcp) +{ + dcp->cb_handlers = cb_handlers; + + dcp_start_signal(dcp, false, dcp_started, NULL); +} + +#undef DCP_FW_VER +#undef DCP_FW diff --git a/drivers/gpu/drm/apple/iomfb_v12_3.h b/drivers/gpu/drm/apple/iomfb_v12_3.h new file mode 100644 index 00000000000000..7359685d981fe5 --- /dev/null +++ b/drivers/gpu/drm/apple/iomfb_v12_3.h @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright The Asahi Linux Contributors */ + +#ifndef __APPLE_IOMFB_V12_3_H__ +#define __APPLE_IOMFB_V12_3_H__ + +#include "version_utils.h" + +#define DCP_FW v12_3 +#define DCP_FW_VER DCP_FW_VERSION(12, 3, 0) + +#include "iomfb_template.h" + +#undef DCP_FW_VER +#undef DCP_FW + +#endif /* __APPLE_IOMFB_V12_3_H__ */ diff --git a/drivers/gpu/drm/apple/iomfb_v13_3.c b/drivers/gpu/drm/apple/iomfb_v13_3.c new file mode 100644 index 00000000000000..0ac869d24eb01b --- /dev/null +++ b/drivers/gpu/drm/apple/iomfb_v13_3.c @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright The Asahi Linux Contributors */ + +#include "iomfb_v12_3.h" +#include "iomfb_v13_3.h" +#include "version_utils.h" + +static const struct dcp_method_entry dcp_methods[dcpep_num_methods] = { + IOMFB_METHOD("A000", dcpep_late_init_signal), + IOMFB_METHOD("A029", dcpep_setup_video_limits), + IOMFB_METHOD("A131", iomfbep_a131_pmu_service_matched), + IOMFB_METHOD("A132", iomfbep_a132_backlight_service_matched), + IOMFB_METHOD("A373", dcpep_set_create_dfb), + IOMFB_METHOD("A374", iomfbep_a358_vi_set_temperature_hint), + IOMFB_METHOD("A401", dcpep_start_signal), + IOMFB_METHOD("A407", dcpep_swap_start), + IOMFB_METHOD("A408", dcpep_swap_submit), + IOMFB_METHOD("A410", dcpep_set_display_device), + IOMFB_METHOD("A411", dcpep_is_main_display), + IOMFB_METHOD("A412", dcpep_set_digital_out_mode), + IOMFB_METHOD("A422", iomfbep_set_matrix), + IOMFB_METHOD("A426", iomfbep_get_color_remap_mode), + IOMFB_METHOD("A441", dcpep_set_parameter_dcp), + IOMFB_METHOD("A445", dcpep_create_default_fb), + IOMFB_METHOD("A449", dcpep_enable_disable_video_power_savings), + IOMFB_METHOD("A456", dcpep_first_client_open), + IOMFB_METHOD("A457", iomfbep_last_client_close), + IOMFB_METHOD("A463", dcpep_set_display_refresh_properties), + IOMFB_METHOD("A466", dcpep_flush_supports_power), + IOMFB_METHOD("A467", iomfbep_abort_swaps_dcp), + IOMFB_METHOD("A472", dcpep_set_power_state), +}; + +#define DCP_FW v13_3 +#define DCP_FW_VER DCP_FW_VERSION(13, 3, 0) + +#include "iomfb_template.c" + +static const iomfb_cb_handler cb_handlers[IOMFB_MAX_CB] = { + [0] = trampoline_true, /* did_boot_signal */ + [1] = trampoline_true, /* did_power_on_signal */ + [2] = trampoline_nop, /* will_power_off_signal */ + [3] = trampoline_rt_bandwidth, + [6] = trampoline_set_frame_sync_props, + [100] = iomfbep_cb_match_pmu_service, + [101] = trampoline_zero, /* get_display_default_stride */ + [102] = trampoline_nop, /* set_number_property */ + [103] = trampoline_nop, /* trigger_user_cal_loader */ + [104] = trampoline_nop, /* set_boolean_property */ + [107] = trampoline_nop, /* remove_property */ + [108] = trampoline_true, /* create_provider_service */ + [109] = trampoline_true, /* create_product_service */ + [110] = trampoline_true, /* create_pmu_service */ + [111] = trampoline_true, /* create_iomfb_service */ + [112] = trampoline_create_backlight_service, + [113] = trampoline_true, /* create_nvram_service? */ + [114] = trampoline_get_tiling_state, + [115] = trampoline_false, /* set_tiling_state */ + [120] = dcpep_cb_boot_1, + [121] = trampoline_false, /* is_dark_boot */ + [122] = trampoline_false, /* is_dark_boot / is_waking_from_hibernate*/ + [124] = trampoline_read_edt_data, + [126] = trampoline_prop_start, + [127] = trampoline_prop_chunk, + [128] = trampoline_prop_end, + [129] = trampoline_allocate_bandwidth, + [201] = trampoline_map_piodma, + [202] = trampoline_unmap_piodma, + [206] = iomfbep_cb_match_pmu_service_2, + [207] = iomfbep_cb_match_backlight_service, + [208] = trampoline_nop, /* update_backlight_factor_prop */ + [209] = trampoline_get_time, + [300] = trampoline_pr_publish, + [401] = trampoline_get_uint_prop, + [404] = trampoline_nop, /* sr_set_uint_prop */ + [406] = trampoline_set_fx_prop, + [408] = trampoline_get_frequency, + [411] = trampoline_map_reg, + [413] = trampoline_true, /* sr_set_property_dict */ + [414] = trampoline_sr_set_property_int, + [415] = trampoline_true, /* sr_set_property_bool */ + [451] = trampoline_allocate_buffer, + [452] = trampoline_map_physical, + [454] = trampoline_release_mem_desc, + [552] = trampoline_true, /* set_property_dict_0 */ + [561] = trampoline_true, /* set_property_dict */ + [563] = trampoline_true, /* set_property_int */ + [565] = trampoline_true, /* set_property_bool */ + [567] = trampoline_true, /* set_property_str */ + [574] = trampoline_zero, /* power_up_dart */ + [576] = trampoline_hotplug, + [577] = trampoline_nop, /* powerstate_notify */ + [582] = trampoline_true, /* create_default_fb_surface */ + [584] = trampoline_nop, /* IOMobileFramebufferAP::clear_default_surface */ + [588] = trampoline_nop, /* resize_default_fb_surface_gated */ + [589] = trampoline_swap_complete, + [591] = trampoline_swap_complete_intent_gated, + [592] = trampoline_abort_swap_ap_gated, + [593] = trampoline_enable_backlight_message_ap_gated, + [594] = trampoline_nop, /* IOMobileFramebufferAP::setSystemConsoleMode */ + [596] = trampoline_false, /* IOMobileFramebufferAP::isDFBAllocated */ + [597] = trampoline_false, /* IOMobileFramebufferAP::preserveContents */ + [598] = trampoline_nop, /* find_swap_function_gated */ +}; +void DCP_FW_NAME(iomfb_start)(struct apple_dcp *dcp) +{ + dcp->cb_handlers = cb_handlers; + + dcp_start_signal(dcp, false, dcp_started, NULL); +} + +#undef DCP_FW_VER +#undef DCP_FW diff --git a/drivers/gpu/drm/apple/iomfb_v13_3.h b/drivers/gpu/drm/apple/iomfb_v13_3.h new file mode 100644 index 00000000000000..bbb3156b40f893 --- /dev/null +++ b/drivers/gpu/drm/apple/iomfb_v13_3.h @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright The Asahi Linux Contributors */ + +#ifndef __APPLE_IOMFB_V13_3_H__ +#define __APPLE_IOMFB_V13_3_H__ + +#include "version_utils.h" + +#define DCP_FW v13_3 +#define DCP_FW_VER DCP_FW_VERSION(13, 3, 0) + +#include "iomfb_template.h" + +#undef DCP_FW_VER +#undef DCP_FW + +#endif /* __APPLE_IOMFB_V13_3_H__ */ diff --git a/drivers/gpu/drm/apple/parser.c b/drivers/gpu/drm/apple/parser.c new file mode 100644 index 00000000000000..8e69f639ddde5a --- /dev/null +++ b/drivers/gpu/drm/apple/parser.c @@ -0,0 +1,1039 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2021 Alyssa Rosenzweig */ + +#include +#include +#include +#include +#include + +#if IS_ENABLED(CONFIG_DRM_APPLE_AUDIO) +#include // for sound format masks +#endif + +#include "parser.h" +#include "trace.h" + +#define DCP_PARSE_HEADER 0xd3 + +enum dcp_parse_type { + DCP_TYPE_DICTIONARY = 1, + DCP_TYPE_ARRAY = 2, + DCP_TYPE_INT64 = 4, + DCP_TYPE_STRING = 9, + DCP_TYPE_BLOB = 10, + DCP_TYPE_BOOL = 11 +}; + +struct dcp_parse_tag { + unsigned int size : 24; + enum dcp_parse_type type : 5; + unsigned int padding : 2; + bool last : 1; +} __packed; + +static const void *parse_bytes(struct dcp_parse_ctx *ctx, size_t count) +{ + const void *ptr = ctx->blob + ctx->pos; + + if (ctx->pos + count > ctx->len) + return ERR_PTR(-EINVAL); + + ctx->pos += count; + return ptr; +} + +static const u32 *parse_u32(struct dcp_parse_ctx *ctx) +{ + return parse_bytes(ctx, sizeof(u32)); +} + +static const struct dcp_parse_tag *parse_tag(struct dcp_parse_ctx *ctx) +{ + const struct dcp_parse_tag *tag; + + /* Align to 32-bits */ + ctx->pos = round_up(ctx->pos, 4); + + tag = parse_bytes(ctx, sizeof(struct dcp_parse_tag)); + + if (IS_ERR(tag)) + return tag; + + if (tag->padding) + return ERR_PTR(-EINVAL); + + return tag; +} + +static const struct dcp_parse_tag *parse_tag_of_type(struct dcp_parse_ctx *ctx, + enum dcp_parse_type type) +{ + const struct dcp_parse_tag *tag = parse_tag(ctx); + + if (IS_ERR(tag)) + return tag; + + if (tag->type != type) + return ERR_PTR(-EINVAL); + + return tag; +} + +static int skip(struct dcp_parse_ctx *handle) +{ + const struct dcp_parse_tag *tag = parse_tag(handle); + int ret = 0; + int i; + + if (IS_ERR(tag)) + return PTR_ERR(tag); + + switch (tag->type) { + case DCP_TYPE_DICTIONARY: + for (i = 0; i < tag->size; ++i) { + ret |= skip(handle); /* key */ + ret |= skip(handle); /* value */ + } + + return ret; + + case DCP_TYPE_ARRAY: + for (i = 0; i < tag->size; ++i) + ret |= skip(handle); + + return ret; + + case DCP_TYPE_INT64: + handle->pos += sizeof(s64); + return 0; + + case DCP_TYPE_STRING: + case DCP_TYPE_BLOB: + handle->pos += tag->size; + return 0; + + case DCP_TYPE_BOOL: + return 0; + + default: + return -EINVAL; + } +} + +#if IS_ENABLED(CONFIG_DRM_APPLE_AUDIO) +static int skip_pair(struct dcp_parse_ctx *handle) +{ + int ret; + + ret = skip(handle); + if (ret) + return ret; + + return skip(handle); +} + +static bool consume_string(struct dcp_parse_ctx *ctx, const char *specimen) +{ + const struct dcp_parse_tag *tag; + const char *key; + ctx->pos = round_up(ctx->pos, 4); + + if (ctx->pos + sizeof(*tag) + strlen(specimen) - 1 > ctx->len) + return false; + tag = ctx->blob + ctx->pos; + key = ctx->blob + ctx->pos + sizeof(*tag); + if (tag->padding) + return false; + + if (tag->type != DCP_TYPE_STRING || + tag->size != strlen(specimen) || + strncmp(key, specimen, tag->size)) + return false; + + skip(ctx); + return true; +} +#endif + +/* Caller must free the result */ +static char *parse_string(struct dcp_parse_ctx *handle) +{ + const struct dcp_parse_tag *tag = parse_tag_of_type(handle, DCP_TYPE_STRING); + const char *in; + char *out; + + if (IS_ERR(tag)) + return (void *)tag; + + in = parse_bytes(handle, tag->size); + if (IS_ERR(in)) + return (void *)in; + + out = kmalloc(tag->size + 1, GFP_KERNEL); + + memcpy(out, in, tag->size); + out[tag->size] = '\0'; + return out; +} + +static int parse_int(struct dcp_parse_ctx *handle, s64 *value) +{ + const void *tag = parse_tag_of_type(handle, DCP_TYPE_INT64); + const s64 *in; + + if (IS_ERR(tag)) + return PTR_ERR(tag); + + in = parse_bytes(handle, sizeof(s64)); + + if (IS_ERR(in)) + return PTR_ERR(in); + + memcpy(value, in, sizeof(*value)); + return 0; +} + +static int parse_bool(struct dcp_parse_ctx *handle, bool *b) +{ + const struct dcp_parse_tag *tag = parse_tag_of_type(handle, DCP_TYPE_BOOL); + + if (IS_ERR(tag)) + return PTR_ERR(tag); + + *b = !!tag->size; + return 0; +} + +#if IS_ENABLED(CONFIG_DRM_APPLE_AUDIO) +static int parse_blob(struct dcp_parse_ctx *handle, size_t size, u8 const **blob) +{ + const struct dcp_parse_tag *tag = parse_tag_of_type(handle, DCP_TYPE_BLOB); + const u8 *out; + + if (IS_ERR(tag)) + return PTR_ERR(tag); + + if (tag->size < size) + return -EINVAL; + + out = parse_bytes(handle, tag->size); + + if (IS_ERR(out)) + return PTR_ERR(out); + + *blob = out; + return 0; +} +#endif + +struct iterator { + struct dcp_parse_ctx *handle; + u32 idx, len; +}; + +static int iterator_begin(struct dcp_parse_ctx *handle, struct iterator *it, + bool dict) +{ + const struct dcp_parse_tag *tag; + enum dcp_parse_type type = dict ? DCP_TYPE_DICTIONARY : DCP_TYPE_ARRAY; + + *it = (struct iterator) { + .handle = handle, + .idx = 0 + }; + + tag = parse_tag_of_type(it->handle, type); + if (IS_ERR(tag)) + return PTR_ERR(tag); + + it->len = tag->size; + return 0; +} + +#define dcp_parse_foreach_in_array(handle, it) \ + for (iterator_begin(handle, &it, false); it.idx < it.len; ++it.idx) +#define dcp_parse_foreach_in_dict(handle, it) \ + for (iterator_begin(handle, &it, true); it.idx < it.len; ++it.idx) + +int parse(const void *blob, size_t size, struct dcp_parse_ctx *ctx) +{ + const u32 *header; + + *ctx = (struct dcp_parse_ctx) { + .blob = blob, + .len = size, + .pos = 0, + }; + + header = parse_u32(ctx); + if (IS_ERR(header)) + return PTR_ERR(header); + + if (*header != DCP_PARSE_HEADER) + return -EINVAL; + + return 0; +} + +static int parse_dimension(struct dcp_parse_ctx *handle, struct dimension *dim) +{ + struct iterator it; + int ret = 0; + + dcp_parse_foreach_in_dict(handle, it) { + char *key = parse_string(it.handle); + + if (IS_ERR(key)) + ret = PTR_ERR(key); + else if (!strcmp(key, "Active")) + ret = parse_int(it.handle, &dim->active); + else if (!strcmp(key, "Total")) + ret = parse_int(it.handle, &dim->total); + else if (!strcmp(key, "FrontPorch")) + ret = parse_int(it.handle, &dim->front_porch); + else if (!strcmp(key, "SyncWidth")) + ret = parse_int(it.handle, &dim->sync_width); + else if (!strcmp(key, "PreciseSyncRate")) + ret = parse_int(it.handle, &dim->precise_sync_rate); + else + skip(it.handle); + + if (!IS_ERR_OR_NULL(key)) + kfree(key); + + if (ret) + return ret; + } + + return 0; +} + +struct color_mode { + s64 colorimetry; + s64 depth; + s64 dynamic_range; + s64 eotf; + s64 id; + s64 pixel_encoding; + s64 score; +}; + +static int fill_color_mode(struct dcp_color_mode *color, + struct color_mode *cmode) +{ + if (color->score >= cmode->score) + return 0; + + if (cmode->colorimetry < 0 || cmode->colorimetry >= DCP_COLORIMETRY_COUNT) + return -EINVAL; + if (cmode->depth < 8 || cmode->depth > 12) + return -EINVAL; + if (cmode->dynamic_range < 0 || cmode->dynamic_range >= DCP_COLOR_YCBCR_RANGE_COUNT) + return -EINVAL; + if (cmode->eotf < 0 || cmode->eotf >= DCP_EOTF_COUNT) + return -EINVAL; + if (cmode->pixel_encoding < 0 || cmode->pixel_encoding >= DCP_COLOR_FORMAT_COUNT) + return -EINVAL; + + color->score = cmode->score; + color->id = cmode->id; + color->eotf = cmode->eotf; + color->format = cmode->pixel_encoding; + color->colorimetry = cmode->colorimetry; + color->range = cmode->dynamic_range; + color->depth = cmode->depth; + + return 0; +} + +static int parse_color_modes(struct dcp_parse_ctx *handle, + struct dcp_display_mode *out) +{ + struct iterator outer_it; + int ret = 0; + out->sdr_444.score = -1; + out->sdr_rgb.score = -1; + out->sdr.score = -1; + out->best.score = -1; + + dcp_parse_foreach_in_array(handle, outer_it) { + struct iterator it; + bool is_virtual = true; + struct color_mode cmode; + + dcp_parse_foreach_in_dict(handle, it) { + char *key = parse_string(it.handle); + + if (IS_ERR(key)) + ret = PTR_ERR(key); + else if (!strcmp(key, "Colorimetry")) + ret = parse_int(it.handle, &cmode.colorimetry); + else if (!strcmp(key, "Depth")) + ret = parse_int(it.handle, &cmode.depth); + else if (!strcmp(key, "DynamicRange")) + ret = parse_int(it.handle, &cmode.dynamic_range); + else if (!strcmp(key, "EOTF")) + ret = parse_int(it.handle, &cmode.eotf); + else if (!strcmp(key, "ID")) + ret = parse_int(it.handle, &cmode.id); + else if (!strcmp(key, "IsVirtual")) + ret = parse_bool(it.handle, &is_virtual); + else if (!strcmp(key, "PixelEncoding")) + ret = parse_int(it.handle, &cmode.pixel_encoding); + else if (!strcmp(key, "Score")) + ret = parse_int(it.handle, &cmode.score); + else + skip(it.handle); + + if (!IS_ERR_OR_NULL(key)) + kfree(key); + + if (ret) + return ret; + } + + /* Skip virtual or partial entries */ + if (is_virtual || cmode.score < 0 || cmode.id < 0) + continue; + + trace_iomfb_color_mode(handle->dcp, cmode.id, cmode.score, + cmode.depth, cmode.colorimetry, + cmode.eotf, cmode.dynamic_range, + cmode.pixel_encoding); + + if (cmode.eotf == DCP_EOTF_SDR_GAMMA) { + if (cmode.pixel_encoding == DCP_COLOR_FORMAT_RGB && + cmode.depth <= 10) + fill_color_mode(&out->sdr_rgb, &cmode); + else if (cmode.pixel_encoding == DCP_COLOR_FORMAT_YCBCR444 && + cmode.depth <= 10) + fill_color_mode(&out->sdr_444, &cmode); + fill_color_mode(&out->sdr, &cmode); + } + fill_color_mode(&out->best, &cmode); + } + + return 0; +} + +/* + * Calculate the pixel clock for a mode given the 16:16 fixed-point refresh + * rate. The pixel clock is the refresh rate times the pixel count. DRM + * specifies the clock in kHz. The intermediate result may overflow a u32, so + * use a u64 where required. + */ +static u32 calculate_clock(struct dimension *horiz, struct dimension *vert) +{ + u32 pixels = horiz->total * vert->total; + u64 clock = mul_u32_u32(pixels, vert->precise_sync_rate); + + return DIV_ROUND_CLOSEST_ULL(clock >> 16, 1000); +} + +static int parse_mode(struct dcp_parse_ctx *handle, + struct dcp_display_mode *out, s64 *score, int width_mm, + int height_mm, unsigned notch_height) +{ + int ret = 0; + struct iterator it; + struct dimension horiz, vert; + s64 id = -1; + s64 best_color_mode = -1; + bool is_virtual = false; + struct drm_display_mode *mode = &out->mode; + + dcp_parse_foreach_in_dict(handle, it) { + char *key = parse_string(it.handle); + + if (IS_ERR(key)) + ret = PTR_ERR(key); + else if (is_virtual) + skip(it.handle); + else if (!strcmp(key, "HorizontalAttributes")) + ret = parse_dimension(it.handle, &horiz); + else if (!strcmp(key, "VerticalAttributes")) + ret = parse_dimension(it.handle, &vert); + else if (!strcmp(key, "ColorModes")) + ret = parse_color_modes(it.handle, out); + else if (!strcmp(key, "ID")) + ret = parse_int(it.handle, &id); + else if (!strcmp(key, "IsVirtual")) + ret = parse_bool(it.handle, &is_virtual); + else if (!strcmp(key, "Score")) + ret = parse_int(it.handle, score); + else + skip(it.handle); + + if (!IS_ERR_OR_NULL(key)) + kfree(key); + + if (ret) { + trace_iomfb_parse_mode_fail(id, &horiz, &vert, best_color_mode, is_virtual, *score); + return ret; + } + } + if (out->sdr_rgb.score >= 0) + best_color_mode = out->sdr_rgb.id; + else if (out->sdr_444.score >= 0) + best_color_mode = out->sdr_444.id; + else if (out->sdr.score >= 0) + best_color_mode = out->sdr.id; + else if (out->best.score >= 0) + best_color_mode = out->best.id; + + trace_iomfb_parse_mode_success(id, &horiz, &vert, best_color_mode, + is_virtual, *score); + + /* + * Reject modes without valid color mode. + */ + if (best_color_mode < 0) + return -EINVAL; + + /* + * We need to skip virtual modes. In some cases, virtual modes are "too + * big" for the monitor and can cause breakage. It is unclear why the + * DCP reports these modes at all. Treat as a recoverable error. + */ + if (is_virtual) + return -EINVAL; + + /* + * HACK: + * Mark the 120 Hz mode on j314/j316 (identified by resolution) as vrr. + * We still do not know how to drive VRR but at least seetinng timestamps + * in the the swap_surface message to non-zero values drives the display + * at 120 fps. + */ + if (vert.precise_sync_rate >> 16 == 120 && + ((horiz.active == 3024 && vert.active == 1964) || + (horiz.active == 3456 && vert.active == 2234))) + out->vrr = true; + + vert.active -= notch_height; + vert.sync_width += notch_height; + + /* From here we must succeed. Start filling out the mode. */ + *mode = (struct drm_display_mode) { + .type = DRM_MODE_TYPE_DRIVER, + .clock = calculate_clock(&horiz, &vert), + + .vdisplay = vert.active, + .vsync_start = vert.active + vert.front_porch, + .vsync_end = vert.active + vert.front_porch + vert.sync_width, + .vtotal = vert.total, + + .hdisplay = horiz.active, + .hsync_start = horiz.active + horiz.front_porch, + .hsync_end = horiz.active + horiz.front_porch + + horiz.sync_width, + .htotal = horiz.total, + + .width_mm = width_mm, + .height_mm = height_mm, + }; + + drm_mode_set_name(mode); + + out->timing_mode_id = id; + out->color_mode_id = best_color_mode; + + trace_iomfb_timing_mode(handle->dcp, id, *score, horiz.active, + vert.active, vert.precise_sync_rate, + best_color_mode); + + return 0; +} + +struct dcp_display_mode *enumerate_modes(struct dcp_parse_ctx *handle, + unsigned int *count, int width_mm, + int height_mm, unsigned notch_height) +{ + struct iterator it; + int ret; + struct dcp_display_mode *mode, *modes; + struct dcp_display_mode *best_mode = NULL; + s64 score, best_score = -1; + + ret = iterator_begin(handle, &it, false); + + if (ret) + return ERR_PTR(ret); + + /* Start with a worst case allocation */ + modes = kmalloc_array(it.len, sizeof(*modes), GFP_KERNEL); + *count = 0; + + if (!modes) + return ERR_PTR(-ENOMEM); + + for (; it.idx < it.len; ++it.idx) { + mode = &modes[*count]; + ret = parse_mode(it.handle, mode, &score, width_mm, height_mm, notch_height); + + /* Errors for a single mode are recoverable -- just skip it. */ + if (ret) + continue; + + /* Process a successful mode */ + (*count)++; + + if (score > best_score) { + best_score = score; + best_mode = mode; + } + } + + if (best_mode != NULL) + best_mode->mode.type |= DRM_MODE_TYPE_PREFERRED; + + return modes; +} + +int parse_display_attributes(struct dcp_parse_ctx *handle, int *width_mm, + int *height_mm) +{ + int ret = 0; + struct iterator it; + s64 width_cm = 0, height_cm = 0; + + dcp_parse_foreach_in_dict(handle, it) { + char *key = parse_string(it.handle); + + if (IS_ERR(key)) + ret = PTR_ERR(key); + else if (!strcmp(key, "MaxHorizontalImageSize")) + ret = parse_int(it.handle, &width_cm); + else if (!strcmp(key, "MaxVerticalImageSize")) + ret = parse_int(it.handle, &height_cm); + else + skip(it.handle); + + if (!IS_ERR_OR_NULL(key)) + kfree(key); + + if (ret) + return ret; + } + + /* 1cm = 10mm */ + *width_mm = 10 * width_cm; + *height_mm = 10 * height_cm; + + return 0; +} + +int parse_epic_service_init(struct dcp_parse_ctx *handle, const char **name, + const char **class, s64 *unit) +{ + int ret = 0; + struct iterator it; + bool parsed_unit = false; + bool parsed_name = false; + bool parsed_class = false; + + *name = ERR_PTR(-ENOENT); + *class = ERR_PTR(-ENOENT); + + dcp_parse_foreach_in_dict(handle, it) { + char *key = parse_string(it.handle); + + if (IS_ERR(key)) { + ret = PTR_ERR(key); + break; + } + + if (!strcmp(key, "EPICName")) { + *name = parse_string(it.handle); + if (IS_ERR(*name)) + ret = PTR_ERR(*name); + else + parsed_name = true; + } else if (!strcmp(key, "EPICProviderClass")) { + *class = parse_string(it.handle); + if (IS_ERR(*class)) + ret = PTR_ERR(*class); + else + parsed_class = true; + } else if (!strcmp(key, "EPICUnit")) { + ret = parse_int(it.handle, unit); + if (!ret) + parsed_unit = true; + } else { + skip(it.handle); + } + + kfree(key); + if (ret) + break; + } + + if (!parsed_unit || !parsed_name || !parsed_class) + ret = -ENOENT; + + if (ret) { + if (!IS_ERR(*name)) { + kfree(*name); + *name = ERR_PTR(ret); + } + if (!IS_ERR(*class)) { + kfree(*class); + *class = ERR_PTR(ret); + } + } + + return ret; +} + +#if IS_ENABLED(CONFIG_DRM_APPLE_AUDIO) +static int parse_sample_rate_bit(struct dcp_parse_ctx *handle, unsigned int *ratebit) +{ + s64 rate; + int ret = parse_int(handle, &rate); + + if (ret) + return ret; + + *ratebit = snd_pcm_rate_to_rate_bit(rate); + if (*ratebit == SNDRV_PCM_RATE_KNOT) { + /* + * The rate wasn't recognized, and unless we supply + * a supplementary constraint, the SNDRV_PCM_RATE_KNOT bit + * will allow any rate. So clear it. + */ + *ratebit = 0; + } + + return 0; +} + +static int parse_sample_fmtbit(struct dcp_parse_ctx *handle, u64 *fmtbit) +{ + s64 sample_size; + int ret = parse_int(handle, &sample_size); + + if (ret) + return ret; + + switch (sample_size) { + case 16: + *fmtbit = SNDRV_PCM_FMTBIT_S16; + break; + case 20: + *fmtbit = SNDRV_PCM_FMTBIT_S20; + break; + case 24: + *fmtbit = SNDRV_PCM_FMTBIT_S24; + break; + case 32: + *fmtbit = SNDRV_PCM_FMTBIT_S32; + break; + default: + *fmtbit = 0; + break; + } + + return 0; +} + +static struct { + const char *label; + u8 type; +} chan_position_names[] = { + { "Front Left", SNDRV_CHMAP_FL }, + { "Front Right", SNDRV_CHMAP_FR }, + { "Rear Left", SNDRV_CHMAP_RL }, + { "Rear Right", SNDRV_CHMAP_RR }, + { "Front Center", SNDRV_CHMAP_FC }, + { "Low Frequency Effects", SNDRV_CHMAP_LFE }, + { "Rear Center", SNDRV_CHMAP_RC }, + { "Front Left Center", SNDRV_CHMAP_FLC }, + { "Front Right Center", SNDRV_CHMAP_FRC }, + { "Rear Left Center", SNDRV_CHMAP_RLC }, + { "Rear Right Center", SNDRV_CHMAP_RRC }, + { "Front Left Wide", SNDRV_CHMAP_FLW }, + { "Front Right Wide", SNDRV_CHMAP_FRW }, + { "Front Left High", SNDRV_CHMAP_FLH }, + { "Front Center High", SNDRV_CHMAP_FCH }, + { "Front Right High", SNDRV_CHMAP_FRH }, + { "Top Center", SNDRV_CHMAP_TC }, +}; + +static void append_chmap(struct snd_pcm_chmap_elem *chmap, u8 type) +{ + if (!chmap || chmap->channels >= ARRAY_SIZE(chmap->map)) + return; + + chmap->map[chmap->channels] = type; + chmap->channels++; +} + +static int parse_chmap(struct dcp_parse_ctx *handle, struct snd_pcm_chmap_elem *chmap) +{ + struct iterator it; + int i, ret; + + if (!chmap) { + skip(handle); + return 0; + } + + chmap->channels = 0; + + dcp_parse_foreach_in_array(handle, it) { + for (i = 0; i < ARRAY_SIZE(chan_position_names); i++) + if (consume_string(it.handle, chan_position_names[i].label)) + break; + + if (i == ARRAY_SIZE(chan_position_names)) { + ret = skip(it.handle); + if (ret) + return ret; + + append_chmap(chmap, SNDRV_CHMAP_UNKNOWN); + continue; + } + + append_chmap(chmap, chan_position_names[i].type); + } + + return 0; +} + +static int parse_chan_layout_element(struct dcp_parse_ctx *handle, + unsigned int *nchans_out, + struct snd_pcm_chmap_elem *chmap) +{ + struct iterator it; + int ret; + s64 nchans = 0; + + dcp_parse_foreach_in_dict(handle, it) { + if (consume_string(it.handle, "ActiveChannelCount")) + ret = parse_int(it.handle, &nchans); + else if (consume_string(it.handle, "ChannelLayout")) + ret = parse_chmap(it.handle, chmap); + else + ret = skip_pair(it.handle); + + if (ret) + return ret; + } + + if (nchans_out) + *nchans_out = nchans; + + return 0; +} + +static int parse_nchans_mask(struct dcp_parse_ctx *handle, unsigned int *mask) +{ + struct iterator it; + int ret; + + *mask = 0; + + dcp_parse_foreach_in_array(handle, it) { + int nchans; + + ret = parse_chan_layout_element(it.handle, &nchans, NULL); + if (ret) + return ret; + *mask |= 1 << nchans; + } + + return 0; +} + +static int parse_avep_element(struct dcp_parse_ctx *handle, + struct dcp_sound_format_mask *sieve, + struct dcp_sound_format_mask *hits) +{ + struct dcp_sound_format_mask mask = {0, 0, 0}; + struct iterator it; + int ret; + + dcp_parse_foreach_in_dict(handle, it) { + if (consume_string(handle, "StreamSampleRate")) + ret = parse_sample_rate_bit(it.handle, &mask.rates); + else if (consume_string(handle, "SampleSize")) + ret = parse_sample_fmtbit(it.handle, &mask.formats); + else if (consume_string(handle, "AudioChannelLayoutElements")) + ret = parse_nchans_mask(it.handle, &mask.nchans); + else + ret = skip_pair(it.handle); + + if (ret) + return ret; + } + + trace_avep_sound_mode(handle->dcp, mask.rates, mask.formats, mask.nchans); + + if (!(mask.rates & sieve->rates) || !(mask.formats & sieve->formats) || + !(mask.nchans & sieve->nchans)) + return 0; + + if (hits) { + hits->rates |= mask.rates; + hits->formats |= mask.formats; + hits->nchans |= mask.nchans; + } + + return 1; +} + +static int parse_mode_in_avep_element(struct dcp_parse_ctx *handle, + unsigned int selected_nchans, + struct snd_pcm_chmap_elem *chmap, + struct dcp_sound_cookie *cookie) +{ + struct iterator it; + struct dcp_parse_ctx save_handle; + int ret; + + dcp_parse_foreach_in_dict(handle, it) { + if (consume_string(it.handle, "AudioChannelLayoutElements")) { + struct iterator inner_it; + int nchans; + + dcp_parse_foreach_in_array(it.handle, inner_it) { + save_handle = *it.handle; + ret = parse_chan_layout_element(inner_it.handle, + &nchans, NULL); + if (ret) + return ret; + + if (nchans != selected_nchans) + continue; + + /* + * Now that we know this layout matches the + * selected channel number, reread the element + * and fill in the channel map. + */ + *inner_it.handle = save_handle; + ret = parse_chan_layout_element(inner_it.handle, + NULL, chmap); + if (ret) + return ret; + } + } else if (consume_string(it.handle, "ElementData")) { + const u8 *blob; + + ret = parse_blob(it.handle, sizeof(*cookie), &blob); + if (ret) + return ret; + + if (cookie) + memcpy(cookie, blob, sizeof(*cookie)); + } else { + ret = skip_pair(it.handle); + if (ret) + return ret; + } + } + + return 0; +} + +int parse_sound_constraints(struct dcp_parse_ctx *handle, + struct dcp_sound_format_mask *sieve, + struct dcp_sound_format_mask *hits) +{ + int ret; + struct iterator it; + + if (hits) { + hits->rates = 0; + hits->formats = 0; + hits->nchans = 0; + } + + dcp_parse_foreach_in_array(handle, it) { + ret = parse_avep_element(it.handle, sieve, hits); + + if (ret < 0) + return ret; + } + + return 0; +} + +int parse_sound_mode(struct dcp_parse_ctx *handle, + struct dcp_sound_format_mask *sieve, + struct snd_pcm_chmap_elem *chmap, + struct dcp_sound_cookie *cookie) +{ + struct dcp_parse_ctx save_handle; + struct iterator it; + int ret; + + dcp_parse_foreach_in_array(handle, it) { + save_handle = *it.handle; + ret = parse_avep_element(it.handle, sieve, NULL); + + if (!ret) + continue; + + if (ret < 0) + return ret; + + ret = parse_mode_in_avep_element(&save_handle, __ffs(sieve->nchans), + chmap, cookie); + if (ret < 0) + return ret; + return 1; + } + + return 0; +} +#endif + +int parse_system_log_mnits(struct dcp_parse_ctx *handle, struct dcp_system_ev_mnits *entry) +{ + struct iterator it; + int ret; + s64 mnits = -1; + s64 idac = -1; + s64 timestamp = -1; + bool type_match = false; + + dcp_parse_foreach_in_dict(handle, it) { + char *key = parse_string(it.handle); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + } else if (!strcmp(key, "mNits")) { + ret = parse_int(it.handle, &mnits); + } else if (!strcmp(key, "iDAC")) { + ret = parse_int(it.handle, &idac); + } else if (!strcmp(key, "logEvent")) { + const char * value = parse_string(it.handle); + if (!IS_ERR_OR_NULL(value)) { + type_match = strcmp(value, "Display (Event Forward)") == 0; + kfree(value); + } + } else if (!strcmp(key, "timestamp")) { + ret = parse_int(it.handle, ×tamp); + } else { + skip(it.handle); + } + + if (!IS_ERR_OR_NULL(key)) + kfree(key); + + if (ret) { + pr_err("dcp parser: failed to parse mNits sys event\n"); + return ret; + } + } + + if (!type_match || mnits < 0 || idac < 0 || timestamp < 0) + return -EINVAL; + + entry->millinits = mnits; + entry->idac = idac; + entry->timestamp = timestamp; + + return 0; +} diff --git a/drivers/gpu/drm/apple/parser.h b/drivers/gpu/drm/apple/parser.h new file mode 100644 index 00000000000000..f3cb661de9ce5e --- /dev/null +++ b/drivers/gpu/drm/apple/parser.h @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2021 Alyssa Rosenzweig */ + +#ifndef __APPLE_DCP_PARSER_H__ +#define __APPLE_DCP_PARSER_H__ + +/* For mode parsing */ +#include + +struct apple_dcp; + +struct dcp_parse_ctx { + struct apple_dcp *dcp; + const void *blob; + u32 pos, len; +}; + +enum dcp_color_eotf { + DCP_EOTF_SDR_GAMMA = 0, // "SDR gamma" + DCP_EOTF_HDR_GAMMA = 1, // "HDR gamma" + DCP_EOTF_ST_2084 = 2, // "ST 2084 (PQ)" + DCP_EOTF_BT_2100 = 3, // "BT.2100 (HLG)" + DCP_EOTF_COUNT +}; + +enum dcp_color_format { + DCP_COLOR_FORMAT_RGB = 0, // "RGB" + DCP_COLOR_FORMAT_YCBCR420 = 1, // "YUV 4:2:0" + DCP_COLOR_FORMAT_YCBCR422 = 3, // "YUV 4:2:2" + DCP_COLOR_FORMAT_YCBCR444 = 2, // "YUV 4:4:4" + DCP_COLOR_FORMAT_DV_NATIVE = 4, // "DolbyVision (native)" + DCP_COLOR_FORMAT_DV_HDMI = 5, // "DolbyVision (HDMI)" + DCP_COLOR_FORMAT_YCBCR422_DP = 6, // "YCbCr 4:2:2 (DP tunnel)" + DCP_COLOR_FORMAT_YCBCR422_HDMI = 7, // "YCbCr 4:2:2 (HDMI tunnel)" + DCP_COLOR_FORMAT_DV_LL_YCBCR422 = 8, // "DolbyVision LL YCbCr 4:2:2" + DCP_COLOR_FORMAT_DV_LL_YCBCR422_DP = 9, // "DolbyVision LL YCbCr 4:2:2 (DP)" + DCP_COLOR_FORMAT_DV_LL_YCBCR422_HDMI = 10, // "DolbyVision LL YCbCr 4:2:2 (HDMI)" + DCP_COLOR_FORMAT_DV_LL_YCBCR444 = 11, // "DolbyVision LL YCbCr 4:4:4" + DCP_COLOR_FORMAT_DV_LL_RGB422 = 12, // "DolbyVision LL RGB 4:2:2" + DCP_COLOR_FORMAT_GRGB_BLUE_422 = 13, // "GRGB as YCbCr422 (Even line blue)" + DCP_COLOR_FORMAT_GRGB_RED_422 = 14, // "GRGB as YCbCr422 (Even line red)" + DCP_COLOR_FORMAT_COUNT +}; + +enum dcp_colorimetry { + DCP_COLORIMETRY_BT601 = 0, // "SMPTE 170M/BT.601" + DCP_COLORIMETRY_BT709 = 1, // "BT.701" + DCP_COLORIMETRY_XVYCC_601 = 2, // "xvYCC601" + DCP_COLORIMETRY_XVYCC_709 = 3, // "xvYCC709" + DCP_COLORIMETRY_SYCC_601 = 4, // "sYCC601" + DCP_COLORIMETRY_ADOBE_YCC_601 = 5, // "AdobeYCC601" + DCP_COLORIMETRY_BT2020_CYCC = 6, // "BT.2020 (c)" + DCP_COLORIMETRY_BT2020_YCC = 7, // "BT.2020 (nc)" + DCP_COLORIMETRY_VSVDB = 8, // "DolbyVision VSVDB" + DCP_COLORIMETRY_BT2020_RGB = 9, // "BT.2020 (RGB)" + DCP_COLORIMETRY_SRGB = 10, // "sRGB" + DCP_COLORIMETRY_SCRGB = 11, // "scRGB" + DCP_COLORIMETRY_SCRGB_FIXED = 12, // "scRGBfixed" + DCP_COLORIMETRY_ADOBE_RGB = 13, // "AdobeRGB" + DCP_COLORIMETRY_DCI_P3_RGB_D65 = 14, // "DCI-P3 (D65)" + DCP_COLORIMETRY_DCI_P3_RGB_THEATER = 15, // "DCI-P3 (Theater)" + DCP_COLORIMETRY_RGB = 16, // "Default RGB" + DCP_COLORIMETRY_COUNT +}; + +enum dcp_color_range { + DCP_COLOR_YCBCR_RANGE_FULL = 0, + DCP_COLOR_YCBCR_RANGE_LIMITED = 1, + DCP_COLOR_YCBCR_RANGE_COUNT +}; + +struct dcp_color_mode { + s64 score; + u32 id; + enum dcp_color_eotf eotf; + enum dcp_color_format format; + enum dcp_colorimetry colorimetry; + enum dcp_color_range range; + u8 depth; +}; + +/* + * Represents a single display mode. These mode objects are populated at + * runtime based on the TimingElements dictionary sent by the DCP. + */ +struct dcp_display_mode { + struct drm_display_mode mode; + u32 color_mode_id; + u32 timing_mode_id; + struct dcp_color_mode sdr_rgb; + struct dcp_color_mode sdr_444; + struct dcp_color_mode sdr; + struct dcp_color_mode best; + bool vrr; +}; + +struct dimension { + s64 total, front_porch, sync_width, active; + s64 precise_sync_rate; +}; + +int parse(const void *blob, size_t size, struct dcp_parse_ctx *ctx); +struct dcp_display_mode *enumerate_modes(struct dcp_parse_ctx *handle, + unsigned int *count, int width_mm, + int height_mm, unsigned notch_height); +int parse_display_attributes(struct dcp_parse_ctx *handle, int *width_mm, + int *height_mm); +int parse_epic_service_init(struct dcp_parse_ctx *handle, const char **name, + const char **class, s64 *unit); + +struct dcp_sound_format_mask { + u64 formats; /* SNDRV_PCM_FMTBIT_* */ + unsigned int rates; /* SNDRV_PCM_RATE_* */ + unsigned int nchans; +}; + +struct dcp_sound_cookie { + u8 data[24]; +}; + +struct snd_pcm_chmap_elem; +int parse_sound_constraints(struct dcp_parse_ctx *handle, + struct dcp_sound_format_mask *sieve, + struct dcp_sound_format_mask *hits); +int parse_sound_mode(struct dcp_parse_ctx *handle, + struct dcp_sound_format_mask *sieve, + struct snd_pcm_chmap_elem *chmap, + struct dcp_sound_cookie *cookie); + +struct dcp_system_ev_mnits { + u32 timestamp; + u32 millinits; + u32 idac; +}; + +int parse_system_log_mnits(struct dcp_parse_ctx *handle, + struct dcp_system_ev_mnits *entry); + +#endif diff --git a/drivers/gpu/drm/apple/plane.c b/drivers/gpu/drm/apple/plane.c new file mode 100644 index 00000000000000..a401bc92289166 --- /dev/null +++ b/drivers/gpu/drm/apple/plane.c @@ -0,0 +1,620 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Copyright (C) The Asahi Linux Contributors + */ + +#include "plane.h" + +#include "iomfb_internal.h" + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#ifndef DRM_FORMAT_MOD_APPLE_INTERCHANGE_COMPRESSED +#define DRM_FORMAT_MOD_APPLE_INTERCHANGE_COMPRESSED fourcc_mod_code(APPLE, 3) +#endif + +#define FRAC_16_16(mult, div) (((mult) << 16) / (div)) + +#define APPLE_GPU_CACHELINE 16 + +struct apple_interchange_layout { + u32 tiles_width; + u32 tiles_height; + u32 tile_size_B; + u32 meta_offset; + u32 meta_size; +}; + +static struct apple_interchange_layout +get_apple_interchange_layout(u32 width, u32 height, u32 bpp) +{ + u32 tw = DIV_ROUND_UP(width, 16); + u32 th = DIV_ROUND_UP(height, 16); + u32 tsize_B = 16 * 16 * (bpp / 8); + + u32 meta_offset = ALIGN(tw * th * tsize_B, APPLE_GPU_CACHELINE); + + /* + * The metadata buffer contains 8 bytes per 16x16 compression tile. + * Addressing is fully twiddled, so both width and height are padded to + * powers-of-two. + */ + u32 w_tl = roundup_pow_of_two(tw); + u32 h_tl = roundup_pow_of_two(th); + u32 B_per_tl = 8; + + u32 meta_size = ALIGN(w_tl * h_tl * B_per_tl, APPLE_GPU_CACHELINE); + + return (struct apple_interchange_layout){ + .tiles_width = tw, + .tiles_height = th, + .tile_size_B = tsize_B, + .meta_offset = meta_offset, + .meta_size = meta_size, + }; +} + +static int apple_plane_atomic_check(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct drm_plane_state *new_plane_state; + struct drm_crtc_state *crtc_state; + struct drm_rect *dst; + int ret; + + new_plane_state = drm_atomic_get_new_plane_state(state, plane); + + if (!new_plane_state->crtc) + return 0; + + crtc_state = drm_atomic_get_crtc_state(state, new_plane_state->crtc); + if (IS_ERR(crtc_state)) + return PTR_ERR(crtc_state); + + /* + * DCP limits downscaling to 2x and upscaling to 4x. Attempting to + * scale outside these bounds errors out when swapping. + * + * This function also takes care of clipping the src/dest rectangles, + * which is required for correct operation. Partially off-screen + * surfaces may appear corrupted. + * + * DCP does not distinguish plane types in the hardware, so we set + * can_position. If the primary plane does not fill the screen, the + * hardware will fill in zeroes (black). + */ + ret = drm_atomic_helper_check_plane_state(new_plane_state, crtc_state, + FRAC_16_16(1, 2), + FRAC_16_16(4, 1), + true, true); + if (ret < 0) + return ret; + + if (!new_plane_state->visible) + return 0; + + /* + * DCP does not allow a surface to clip off the screen, and will crash + * if any blended surface is smaller than 32x32. Reject the atomic op + * if the plane will crash DCP. + * + * This is most pertinent to cursors. Userspace should fall back to + * software cursors if the plane check is rejected. + */ + dst = &new_plane_state->dst; + if (drm_rect_width(dst) < 32 || drm_rect_height(dst) < 32) { + dev_err_once(state->dev->dev, + "Plane operation would have crashed DCP! Rejected!\n\ + DCP requires 32x32 of every plane to be within screen space.\n\ + Your compositor asked to overlay [%dx%d, %dx%d] on %dx%d.\n\ + This is not supported, and your compositor should have\n\ + switched to software compositing when this operation failed.\n\ + You should not have noticed this at all. If your screen\n\ + froze/hitched, or your compositor crashed, please report\n\ + this to the your compositor's developers. We will not\n\ + throw this error again until you next reboot.\n", + dst->x1, dst->y1, dst->x2, dst->y2, + crtc_state->mode.hdisplay, crtc_state->mode.vdisplay); + return -EINVAL; + } + + if (new_plane_state->fb->modifier != DRM_FORMAT_MOD_APPLE_INTERCHANGE_COMPRESSED) { + /* + * Pitches have to be 64-byte aligned for non-tiled modifiers. + */ + for (u32 i = 0; i < new_plane_state->fb->format->num_planes; i++) + if (new_plane_state->fb->pitches[i] & 63) + return -EINVAL; + } + + /* + * FIXME: dcp can currently only use multi-planar buffers using the same + * object for all planes. It has a mandatory iommu so it should + * be no problem to map multiple objects "linearly" into DCP + * virtual address space and calculate the offsets accordingly. + * Or maybe it can accept multiple BOs via the per plane field + * `base`. + */ + if (new_plane_state->fb->format->num_planes > 1) { + const struct drm_gem_object *first = new_plane_state->fb->obj[0]; + for (u32 i = 1; i < new_plane_state->fb->format->num_planes; i++) + if (new_plane_state->fb->obj[i] != NULL && + new_plane_state->fb->obj[i] != first) + return -EINVAL; + } + + /* + * The calculated size of the compression meta data must fit into the size + * of the gem object + */ + for (u32 i = 0; i < new_plane_state->fb->format->num_planes; i++) { + struct drm_framebuffer *fb = new_plane_state->fb; + + if (fb->modifier != DRM_FORMAT_MOD_APPLE_INTERCHANGE_COMPRESSED) + continue; + + u32 width = + drm_format_info_plane_width(fb->format, fb->width, i); + u32 height = + drm_format_info_plane_height(fb->format, fb->height, i); + u32 bpp = drm_format_info_bpp(fb->format, i); + struct apple_interchange_layout l = + get_apple_interchange_layout(width, height, bpp); + + u32 required_size = + fb->offsets[0] + l.meta_offset + l.meta_size; + + struct drm_gem_dma_object *obj = drm_fb_dma_get_gem_obj(fb, i); + if (obj && required_size > obj->base.size) { + dev_err_ratelimited( + state->dev->dev, + "dcp: atomic_check, required size of %u bytes is more than gem size of %zu\n", + required_size, obj->base.size); + + return -EINVAL; + } + } + + return 0; +} + +/* + * DRM specifies rectangles as start and end coordinates. DCP specifies + * rectangles as a start coordinate and a width/height. Convert a DRM rectangle + * to a DCP rectangle. + */ +static struct dcp_rect drm_to_dcp_rect(const struct drm_rect *rect) +{ + return (struct dcp_rect){ .x = rect->x1, + .y = rect->y1, + .w = drm_rect_width(rect), + .h = drm_rect_height(rect), + }; +} + +static struct dcp_rect drm_to_dcp_rect_fp(const struct drm_rect *fp_rect) +{ + struct drm_rect rect; + drm_rect_fp_to_int(&rect, fp_rect); + return drm_to_dcp_rect(&rect); +} + +static u32 drm_format_to_dcp(u32 drm, enum drm_color_range range) +{ + bool fr = range == DRM_COLOR_YCBCR_FULL_RANGE; + switch (drm) { + case DRM_FORMAT_XRGB8888: + case DRM_FORMAT_ARGB8888: + return DCP_FORMAT_BGRA; + + case DRM_FORMAT_XBGR8888: + case DRM_FORMAT_ABGR8888: + return DCP_FORMAT_RGBA; + + case DRM_FORMAT_XRGB2101010: + case DRM_FORMAT_ARGB2101010: + return DCP_FORMAT_L10R; + + /* semi planar YCbCr formats, limited and full range */ + case DRM_FORMAT_NV12: + return fr ? DCP_FORMAT_420F : DCP_FORMAT_420V; + case DRM_FORMAT_NV16: + return fr ? DCP_FORMAT_422F : DCP_FORMAT_422V; + case DRM_FORMAT_NV24: + return fr ? DCP_FORMAT_444F : DCP_FORMAT_444V; + + /* semi planar 10-bit YCbCr formats, limited and full range */ + case DRM_FORMAT_P010: + return fr ? DCP_FORMAT_XF20 : DCP_FORMAT_X420; + case DRM_FORMAT_P210: + return fr ? DCP_FORMAT_XF22 : DCP_FORMAT_X422; + /* + * TODO: missing DRM fourcc for P410 + */ +#if defined(DRM_FORMAT_P410) + case DRM_FORMAT_P410: + return fr ? DCP_FORMAT_XF44 : DCP_FORMAT_X444; +#endif + } + + pr_warn("DRM format %X not supported in DCP\n", drm); + return 0; +} + +static enum dcp_xfer_func get_xfer_func(bool is_yuv, enum drm_color_encoding enc) +{ + if (!is_yuv) + return DCP_XFER_FUNC_SDR; + + switch (enc) { + case DRM_COLOR_YCBCR_BT601: + return DCP_XFER_FUNC_BT601; + case DRM_COLOR_YCBCR_BT709: + case DRM_COLOR_YCBCR_BT2020: + return DCP_XFER_FUNC_BT1886; + default: + return DCP_XFER_FUNC_SDR; + } +} + +static enum dcp_colorspace get_colorspace(bool is_yuv, + enum drm_color_encoding enc) +{ + if (!is_yuv) + return DCP_COLORSPACE_NATIVE; + + switch (enc) { + case DRM_COLOR_YCBCR_BT601: + return DCP_COLORSPACE_BT601; + case DRM_COLOR_YCBCR_BT709: + return DCP_COLORSPACE_BT709; + case DRM_COLOR_YCBCR_BT2020: + return DCP_COLORSPACE_BG_BT2020; + default: + return DCP_COLORSPACE_NATIVE; + } +} + +static void apple_plane_atomic_update(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct drm_plane_state *base = drm_atomic_get_new_plane_state(state, plane); + struct apple_plane_state *new_state; + struct drm_gem_dma_object *obj; + bool is_premultiplied = false; + + if (!base) + return; + + new_state = to_apple_plane_state(base); + + if (!base->fb) { + memset(&new_state->surf, 0, sizeof(new_state->surf)); + return; + } + + struct drm_framebuffer *fb = base->fb; + const struct drm_format_info *fmt = fb->format; + /* + * DCP doesn't support XBGR8 / XRGB8 / XBGR2101010 natively. Blending as + * pre-multiplied alpha with a black background can be used as + * workaround for the bottommost plane. + */ + if (fmt->format == DRM_FORMAT_XRGB8888 || + fmt->format == DRM_FORMAT_XBGR8888 || + fmt->format == DRM_FORMAT_XBGR2101010) + is_premultiplied = true; + + new_state->src_rect = drm_to_dcp_rect_fp(&base->src); + new_state->dst_rect = drm_to_dcp_rect(&base->dst); + + new_state->surf = (struct dcp_surface){ + .is_premultiplied = is_premultiplied, + .plane_cnt = fb->format->num_planes, + .plane_cnt2 = fb->format->num_planes, + .format = drm_format_to_dcp(fmt->format, base->color_range), + .xfer_func = get_xfer_func(fmt->is_yuv, base->color_encoding), + .colorspace = get_colorspace(fmt->is_yuv, base->color_encoding), + .stride = fb->pitches[0], + .width = fb->width, + .height = fb->height, + // .surface_id = req->swap.surf_ids[l], + + /* Only used for compressed or multiplanar surfaces */ + .pix_size = 1, + .pel_w = 1, + .pel_h = 1, + .has_comp = 1, + .has_planes = 1, + .has_compr_info = 1, + }; + + /* Populate plane information for planar formats */ + struct dcp_surface *surf = &new_state->surf; + for (int i = 0; fb->format->num_planes && i < fb->format->num_planes; i++) { + u32 width = drm_format_info_plane_width(fb->format, fb->width, i); + u32 height = drm_format_info_plane_height(fb->format, fb->height, i); + u32 bh = drm_format_info_block_height(fb->format, i); + u32 bw = drm_format_info_block_width(fb->format, i); + + surf->planes[i] = (struct dcp_plane_info){ + .width = width, + .height = height, + .base = fb->offsets[i] - fb->offsets[0], + .offset = fb->offsets[i] - fb->offsets[0], + .stride = fb->pitches[i], + .size = height * fb->pitches[i], + .tile_size = bw * bh, + .tile_w = bw, + .tile_h = bh, + }; + + if (fb->modifier == DRM_FORMAT_MOD_APPLE_INTERCHANGE_COMPRESSED) { + u32 bpp = drm_format_info_bpp(fmt, i); + struct apple_interchange_layout l = + get_apple_interchange_layout(width, height, bpp); + + surf->planes[i].tile_w = 16; + surf->planes[i].tile_h = 16; + surf->planes[i].stride = l.tiles_width * l.tile_size_B; + surf->planes[i].size = l.meta_offset + l.meta_size; + surf->planes[i].tile_size = l.tile_size_B; + surf->planes[i].address_format = DCP_ADDRESS_FORMAT_INTERCHANGE_TILED; + + surf->compression_info[i] = (struct dcp_compression_info){ + .tile_w = 16, + .tile_h = 16, + .data_offset = 0, + .meta_offset = l.meta_offset, + .tile_meta_bytes = 8, + .tiles_w = l.tiles_width, + .tiles_h = l.tiles_height, + .tile_bytes = l.tile_size_B, + .row_stride = l.tiles_width * l.tile_size_B, + .compresson_type = DCP_COMPRESSION_TYPE_INTERCHANGE_TILED, + }; + } + + surf->buf_size += surf->planes[i].size; + } + + /* the obvious helper call drm_fb_dma_get_gem_addr() adjusts + * the address for source x/y offsets. Since IOMFB has a direct + * support source position prefer that. + */ + obj = drm_fb_dma_get_gem_obj(base->fb, 0); + if (obj) + new_state->iova = obj->dma_addr + base->fb->offsets[0]; +} + +static const struct drm_plane_helper_funcs apple_primary_plane_helper_funcs = { + .atomic_check = apple_plane_atomic_check, + .atomic_update = apple_plane_atomic_update, + .get_scanout_buffer = drm_fb_dma_get_scanout_buffer, +}; + +static const struct drm_plane_helper_funcs apple_plane_helper_funcs = { + .atomic_check = apple_plane_atomic_check, + .atomic_update = apple_plane_atomic_update, +}; + +// Duplicate drm_atomic_helper_plane_reset but allocate struct apple_plane_state +static void apple_plane_reset(struct drm_plane *plane) +{ + struct apple_plane_state *state = to_apple_plane_state(plane->state); + if (state) + __drm_atomic_helper_plane_destroy_state(&state->base); + + kfree(state); + plane->state = NULL; + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (state) + __drm_atomic_helper_plane_reset(plane, &state->base); +} + +static struct drm_plane_state * +apple_plane_duplicate_state(struct drm_plane *plane) +{ + struct apple_plane_state *apple_plane_state, *old_apple_plane_state; + + if (!plane->state) + return NULL; + + old_apple_plane_state = to_apple_plane_state(plane->state); + apple_plane_state = kzalloc(sizeof(*apple_plane_state), GFP_KERNEL); + if (!apple_plane_state) + return NULL; + + __drm_atomic_helper_plane_duplicate_state(plane, &apple_plane_state->base); + + apple_plane_state->surf = old_apple_plane_state->surf; + + return &apple_plane_state->base; +} + +static bool apple_plane_format_mod_supported(struct drm_plane *plane, + uint32_t format, uint64_t modifier) +{ + if (modifier != DRM_FORMAT_MOD_APPLE_INTERCHANGE_COMPRESSED) { + return true; + } + + // interchange is only supported with rgba formats for now. + switch (format) { + case DRM_FORMAT_XRGB2101010: + case DRM_FORMAT_ARGB2101010: + case DRM_FORMAT_XRGB8888: + case DRM_FORMAT_ARGB8888: + case DRM_FORMAT_XBGR8888: + case DRM_FORMAT_ABGR8888: + return true; + + default: + return false; + } +} + +// void apple_plane_destroy_state(struct drm_plane *plane, +// struct drm_plane_state *state) +// { +// drm_atomic_helper_plane_destroy_state(plane, state); +// } + +static const struct drm_plane_funcs apple_plane_funcs = { + .update_plane = drm_atomic_helper_update_plane, + .disable_plane = drm_atomic_helper_disable_plane, + .reset = apple_plane_reset, + .atomic_duplicate_state = apple_plane_duplicate_state, + // .atomic_destroy_state = apple_plane_destroy_state, + .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, + .format_mod_supported = apple_plane_format_mod_supported, +}; + +/* + * Table of supported formats, mapping from DRM fourccs to DCP fourccs. + * + * For future work, DCP supports more formats not listed, including YUV + * formats, an extra RGBA format, and a biplanar RGB10_A8 format (fourcc b3a8) + * used for HDR. + * + * Note: we don't have non-alpha formats but userspace breaks without XRGB. It + * doesn't matter for the primary plane, but cursors/overlays must not + * advertise formats without alpha. + */ +static const u32 dcp_primary_formats[] = { + DRM_FORMAT_XRGB2101010, + DRM_FORMAT_ARGB2101010, + DRM_FORMAT_XRGB8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_XBGR8888, + DRM_FORMAT_ABGR8888, + DRM_FORMAT_NV12, + DRM_FORMAT_NV16, + DRM_FORMAT_NV24, + DRM_FORMAT_P010, + DRM_FORMAT_P210, +#if defined(DRM_FORMAT_P410) + DRM_FORMAT_P410, +#endif +}; + +static const u32 dcp_overlay_formats[] = { + DRM_FORMAT_ARGB2101010, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_ABGR8888, + DRM_FORMAT_NV12, + DRM_FORMAT_NV16, + DRM_FORMAT_NV24, + DRM_FORMAT_P010, + DRM_FORMAT_P210, +#if defined(DRM_FORMAT_P410) + DRM_FORMAT_P410, +#endif +}; + +/* + * Formats for the 12.x firmware which does not support "l10r" / ARGB2101010 + */ +static const u32 dcp_primary_formats_12_x[] = { + DRM_FORMAT_XRGB8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_XBGR8888, + DRM_FORMAT_ABGR8888, + DRM_FORMAT_NV12, + DRM_FORMAT_NV16, + DRM_FORMAT_NV24, + DRM_FORMAT_P010, + DRM_FORMAT_P210, +#if defined(DRM_FORMAT_P410) + DRM_FORMAT_P410, +#endif +}; + +static const u32 dcp_overlay_formats_12_x[] = { + DRM_FORMAT_ARGB8888, + DRM_FORMAT_ABGR8888, + DRM_FORMAT_NV12, + DRM_FORMAT_NV16, + DRM_FORMAT_NV24, + DRM_FORMAT_P010, + DRM_FORMAT_P210, +#if defined(DRM_FORMAT_P410) + DRM_FORMAT_P410, +#endif +}; + +u64 apple_format_modifiers[] = { + DRM_FORMAT_MOD_APPLE_INTERCHANGE_COMPRESSED, + DRM_FORMAT_MOD_LINEAR, + DRM_FORMAT_MOD_INVALID +}; + +struct apple_plane { + struct drm_plane base; +}; + +struct drm_plane *apple_plane_init(struct drm_device *dev, + unsigned long possible_crtcs, + bool supports_l10r, + enum drm_plane_type type) +{ + struct apple_plane *plane; + const u32 *fmts; + u32 num_fmts; + + switch (type) { + case DRM_PLANE_TYPE_PRIMARY: + if (supports_l10r) { + fmts = dcp_primary_formats; + num_fmts = ARRAY_SIZE(dcp_primary_formats); + } else { + fmts = dcp_primary_formats_12_x; + num_fmts = ARRAY_SIZE(dcp_primary_formats_12_x); + } + plane = drmm_universal_plane_alloc(dev, struct apple_plane, base, possible_crtcs, + &apple_plane_funcs, fmts, num_fmts, + apple_format_modifiers, type, NULL); + break; + case DRM_PLANE_TYPE_OVERLAY: + case DRM_PLANE_TYPE_CURSOR: + if (supports_l10r) { + fmts = dcp_overlay_formats; + num_fmts = ARRAY_SIZE(dcp_overlay_formats); + } else { + fmts = dcp_overlay_formats_12_x; + num_fmts = ARRAY_SIZE(dcp_overlay_formats_12_x); + } + plane = drmm_universal_plane_alloc(dev, struct apple_plane, base, possible_crtcs, + &apple_plane_funcs, fmts, num_fmts, + apple_format_modifiers, type, NULL); + break; + default: + return ERR_PTR(-EINVAL); + } + + if (IS_ERR(plane)) + return ERR_PTR(PTR_ERR(plane)); + + drm_plane_create_color_properties(&plane->base, + (1 << DRM_COLOR_ENCODING_MAX) - 1, + (1 << DRM_COLOR_RANGE_MAX) - 1, + DRM_COLOR_YCBCR_BT709, + DRM_COLOR_YCBCR_LIMITED_RANGE); + + if (type == DRM_PLANE_TYPE_PRIMARY) + drm_plane_helper_add(&plane->base, &apple_primary_plane_helper_funcs); + else + drm_plane_helper_add(&plane->base, &apple_plane_helper_funcs); + + return &plane->base; +} diff --git a/drivers/gpu/drm/apple/plane.h b/drivers/gpu/drm/apple/plane.h new file mode 100644 index 00000000000000..67d15938cf0dcb --- /dev/null +++ b/drivers/gpu/drm/apple/plane.h @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Copyright (C) The Asahi Linux Contributors + */ + +#ifndef __APPLE_PLANE_H__ +#define __APPLE_PLANE_H__ + +#include + +#include + +#include "iomfb_plane.h" + +struct apple_plane_state { + struct drm_plane_state base; + struct dcp_surface surf; + struct dcp_rect src_rect; + struct dcp_rect dst_rect; + u64 iova; +}; + +#define to_apple_plane_state(x) container_of(x, struct apple_plane_state, base) + +struct drm_plane *apple_plane_init(struct drm_device *dev, + unsigned long possible_crtcs, + bool supports_l10r, + enum drm_plane_type type); + +#endif /* __APPLE_PLANE_H__ */ diff --git a/drivers/gpu/drm/apple/systemep.c b/drivers/gpu/drm/apple/systemep.c new file mode 100644 index 00000000000000..9fe7a0ce495aab --- /dev/null +++ b/drivers/gpu/drm/apple/systemep.c @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2022 Sven Peter */ + +#include + +#include "afk.h" +#include "dcp.h" +#include "parser.h" + +static bool enable_verbose_logging; +module_param(enable_verbose_logging, bool, 0644); +MODULE_PARM_DESC(enable_verbose_logging, "Enable DCP firmware verbose logging"); + +/* + * Serialized setProperty("gAFKConfigLogMask", 0xffff) IPC call which + * will set the DCP firmware log level to the most verbose setting + */ +#define SYSTEM_SET_PROPERTY 0x43 +static const u8 setprop_gAFKConfigLogMask_ffff[] = { + 0x14, 0x00, 0x00, 0x00, 0x67, 0x41, 0x46, 0x4b, 0x43, 0x6f, + 0x6e, 0x66, 0x69, 0x67, 0x4c, 0x6f, 0x67, 0x4d, 0x61, 0x73, + 0x6b, 0x00, 0x00, 0x00, 0xd3, 0x00, 0x00, 0x00, 0x40, 0x00, + 0x00, 0x84, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 +}; + +struct systemep_work { + struct apple_epic_service *service; + struct work_struct work; +}; + +static void system_log_work(struct work_struct *work_) +{ + struct systemep_work *work = + container_of(work_, struct systemep_work, work); + + afk_send_command(work->service, SYSTEM_SET_PROPERTY, + setprop_gAFKConfigLogMask_ffff, + sizeof(setprop_gAFKConfigLogMask_ffff), NULL, + sizeof(setprop_gAFKConfigLogMask_ffff), NULL); + complete(&work->service->ep->dcp->systemep_done); + kfree(work); +} + +static void system_init(struct apple_epic_service *service, const char *name, + const char *class, s64 unit) +{ + struct systemep_work *work; + + if (!enable_verbose_logging) + return; + + /* + * We're called from the service message handler thread and can't + * dispatch blocking message from there. + */ + work = kzalloc(sizeof(*work), GFP_KERNEL); + if (!work) + return; + + work->service = service; + INIT_WORK(&work->work, system_log_work); + schedule_work(&work->work); +} + +static void powerlog_init(struct apple_epic_service *service, const char *name, + const char *class, s64 unit) +{ +} + +static int powerlog_report(struct apple_epic_service *service, enum epic_subtype type, + const void *data, size_t data_size) +{ + struct dcp_system_ev_mnits mnits; + struct dcp_parse_ctx parse_ctx; + struct apple_dcp *dcp = service->ep->dcp; + int ret; + + dev_dbg(dcp->dev, "systemep[ch:%u]: report type:%02x len:%zu\n", + service->channel, type, data_size); + + if (type != EPIC_SUBTYPE_STD_SERVICE) + return 0; + + ret = parse(data, data_size, &parse_ctx); + if (ret) { + dev_warn(service->ep->dcp->dev, "systemep: failed to parse report: %d\n", ret); + return ret; + } + + ret = parse_system_log_mnits(&parse_ctx, &mnits); + if (ret) { + /* ignore parse errors in the case dcp sends unknown log events */ + dev_dbg(dcp->dev, "systemep: failed to parse mNits event: %d\n", ret); + return 0; + } + + dev_dbg(dcp->dev, "systemep: mNits event: Nits: %u.%03u, iDAC: %u\n", + mnits.millinits / 1000, mnits.millinits % 1000, mnits.idac); + + dcp->brightness.nits = mnits.millinits / 1000; + + return 0; +} + +static const struct apple_epic_service_ops systemep_ops[] = { + { + .name = "system", + .init = system_init, + }, + { + .name = "powerlog-service", + .init = powerlog_init, + .report = powerlog_report, + }, + {} +}; + +int systemep_init(struct apple_dcp *dcp) +{ + init_completion(&dcp->systemep_done); + + dcp->systemep = afk_init(dcp, SYSTEM_ENDPOINT, systemep_ops); + afk_start(dcp->systemep); + + if (!enable_verbose_logging) + return 0; + + /* + * Timeouts aren't really fatal here: in the worst case we just weren't + * able to enable additional debug prints inside DCP + */ + if (!wait_for_completion_timeout(&dcp->systemep_done, + msecs_to_jiffies(MSEC_PER_SEC))) + dev_err(dcp->dev, "systemep: couldn't enable verbose logs\n"); + + return 0; +} diff --git a/drivers/gpu/drm/apple/trace.c b/drivers/gpu/drm/apple/trace.c new file mode 100644 index 00000000000000..6f40d5a583df01 --- /dev/null +++ b/drivers/gpu/drm/apple/trace.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ OR MIT +/* + * Tracepoints for Apple DCP driver + * + * Copyright (C) The Asahi Linux Contributors + */ + +#define CREATE_TRACE_POINTS +#include "trace.h" diff --git a/drivers/gpu/drm/apple/trace.h b/drivers/gpu/drm/apple/trace.h new file mode 100644 index 00000000000000..a13dd34fb7aab1 --- /dev/null +++ b/drivers/gpu/drm/apple/trace.h @@ -0,0 +1,608 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright (C) The Asahi Linux Contributors */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM dcp + +#if !defined(_TRACE_DCP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_DCP_H + +#include "afk.h" +#include "dptxep.h" +#include "dcp-internal.h" +#include "parser.h" + +#include +#include +#include + +#define show_dcp_endpoint(ep) \ + __print_symbolic(ep, { SYSTEM_ENDPOINT, "system" }, \ + { TEST_ENDPOINT, "test" }, \ + { DCP_EXPERT_ENDPOINT, "dcpexpert" }, \ + { DISP0_ENDPOINT, "disp0" }, \ + { DPTX_ENDPOINT, "dptxport" }, \ + { HDCP_ENDPOINT, "hdcp" }, \ + { REMOTE_ALLOC_ENDPOINT, "remotealloc" }, \ + { IOMFB_ENDPOINT, "iomfb" }) +#define print_epic_type(etype) \ + __print_symbolic(etype, { EPIC_TYPE_NOTIFY, "notify" }, \ + { EPIC_TYPE_COMMAND, "command" }, \ + { EPIC_TYPE_REPLY, "reply" }, \ + { EPIC_TYPE_NOTIFY_ACK, "notify-ack" }) + +#define print_epic_category(ecat) \ + __print_symbolic(ecat, { EPIC_CAT_REPORT, "report" }, \ + { EPIC_CAT_NOTIFY, "notify" }, \ + { EPIC_CAT_REPLY, "reply" }, \ + { EPIC_CAT_COMMAND, "command" }) + +#define show_dptxport_apcall(idx) \ + __print_symbolic( \ + idx, { DPTX_APCALL_ACTIVATE, "activate" }, \ + { DPTX_APCALL_DEACTIVATE, "deactivate" }, \ + { DPTX_APCALL_GET_MAX_DRIVE_SETTINGS, \ + "get_max_drive_settings" }, \ + { DPTX_APCALL_SET_DRIVE_SETTINGS, "set_drive_settings" }, \ + { DPTX_APCALL_GET_DRIVE_SETTINGS, "get_drive_settings" }, \ + { DPTX_APCALL_WILL_CHANGE_LINKG_CONFIG, \ + "will_change_link_config" }, \ + { DPTX_APCALL_DID_CHANGE_LINK_CONFIG, \ + "did_change_link_config" }, \ + { DPTX_APCALL_GET_MAX_LINK_RATE, "get_max_link_rate" }, \ + { DPTX_APCALL_GET_LINK_RATE, "get_link_rate" }, \ + { DPTX_APCALL_SET_LINK_RATE, "set_link_rate" }, \ + { DPTX_APCALL_GET_MAX_LANE_COUNT, \ + "get_max_lane_count" }, \ + { DPTX_APCALL_GET_ACTIVE_LANE_COUNT, \ + "get_active_lane_count" }, \ + { DPTX_APCALL_SET_ACTIVE_LANE_COUNT, \ + "set_active_lane_count" }, \ + { DPTX_APCALL_GET_SUPPORTS_DOWN_SPREAD, \ + "get_supports_downspread" }, \ + { DPTX_APCALL_GET_DOWN_SPREAD, "get_downspread" }, \ + { DPTX_APCALL_SET_DOWN_SPREAD, "set_downspread" }, \ + { DPTX_APCALL_GET_SUPPORTS_LANE_MAPPING, \ + "get_supports_lane_mapping" }, \ + { DPTX_APCALL_SET_LANE_MAP, "set_lane_map" }, \ + { DPTX_APCALL_GET_SUPPORTS_HPD, "get_supports_hpd" }, \ + { DPTX_APCALL_FORCE_HOTPLUG_DETECT, "force_hotplug_detect" }, \ + { DPTX_APCALL_INACTIVE_SINK_DETECTED, \ + "inactive_sink_detected" }, \ + { DPTX_APCALL_SET_TILED_DISPLAY_HINTS, \ + "set_tiled_display_hints" }, \ + { DPTX_APCALL_DEVICE_NOT_RESPONDING, \ + "device_not_responding" }, \ + { DPTX_APCALL_DEVICE_BUSY_TIMEOUT, "device_busy_timeout" }, \ + { DPTX_APCALL_DEVICE_NOT_STARTED, "device_not_started" }) + +TRACE_EVENT(dcp_recv_msg, + TP_PROTO(struct apple_dcp *dcp, u8 endpoint, u64 message), + TP_ARGS(dcp, endpoint, message), + + TP_STRUCT__entry(__string(devname, dev_name(dcp->dev)) + __field(u8, endpoint) + __field(u64, message)), + + TP_fast_assign(__assign_str(devname); + __entry->endpoint = endpoint; + __entry->message = message;), + + TP_printk("%s: endpoint 0x%x (%s): received message 0x%016llx", + __get_str(devname), __entry->endpoint, + show_dcp_endpoint(__entry->endpoint), __entry->message)); + +TRACE_EVENT(dcp_send_msg, + TP_PROTO(struct apple_dcp *dcp, u8 endpoint, u64 message), + TP_ARGS(dcp, endpoint, message), + + TP_STRUCT__entry(__string(devname, dev_name(dcp->dev)) + __field(u8, endpoint) + __field(u64, message)), + + TP_fast_assign(__assign_str(devname); + __entry->endpoint = endpoint; + __entry->message = message;), + + TP_printk("%s: endpoint 0x%x (%s): will send message 0x%016llx", + __get_str(devname), __entry->endpoint, + show_dcp_endpoint(__entry->endpoint), __entry->message)); + +TRACE_EVENT( + afk_getbuf, TP_PROTO(struct apple_dcp_afkep *ep, u16 size, u16 tag), + TP_ARGS(ep, size, tag), + + TP_STRUCT__entry(__string(devname, dev_name(ep->dcp->dev)) + __field(u8, endpoint) __field(u16, size) + __field(u16, tag)), + + TP_fast_assign(__assign_str(devname); + __entry->endpoint = ep->endpoint; __entry->size = size; + __entry->tag = tag;), + + TP_printk( + "%s: endpoint 0x%x (%s): get buffer with size 0x%x and tag 0x%x", + __get_str(devname), __entry->endpoint, + show_dcp_endpoint(__entry->endpoint), __entry->size, + __entry->tag)); + +DECLARE_EVENT_CLASS(afk_rwptr_template, + TP_PROTO(struct apple_dcp_afkep *ep, u32 rptr, u32 wptr), + TP_ARGS(ep, rptr, wptr), + + TP_STRUCT__entry(__string(devname, dev_name(ep->dcp->dev)) + __field(u8, endpoint) __field(u32, rptr) + __field(u32, wptr)), + + TP_fast_assign(__assign_str(devname); + __entry->endpoint = ep->endpoint; + __entry->rptr = rptr; __entry->wptr = wptr;), + + TP_printk("%s: endpoint 0x%x (%s): rptr 0x%x, wptr 0x%x", + __get_str(devname), __entry->endpoint, + show_dcp_endpoint(__entry->endpoint), __entry->rptr, + __entry->wptr)); + +DEFINE_EVENT(afk_rwptr_template, afk_recv_rwptr_pre, + TP_PROTO(struct apple_dcp_afkep *ep, u32 rptr, u32 wptr), + TP_ARGS(ep, rptr, wptr)); +DEFINE_EVENT(afk_rwptr_template, afk_recv_rwptr_post, + TP_PROTO(struct apple_dcp_afkep *ep, u32 rptr, u32 wptr), + TP_ARGS(ep, rptr, wptr)); +DEFINE_EVENT(afk_rwptr_template, afk_send_rwptr_pre, + TP_PROTO(struct apple_dcp_afkep *ep, u32 rptr, u32 wptr), + TP_ARGS(ep, rptr, wptr)); +DEFINE_EVENT(afk_rwptr_template, afk_send_rwptr_post, + TP_PROTO(struct apple_dcp_afkep *ep, u32 rptr, u32 wptr), + TP_ARGS(ep, rptr, wptr)); + +TRACE_EVENT( + afk_recv_qe, + TP_PROTO(struct apple_dcp_afkep *ep, u32 rptr, u32 magic, u32 size), + TP_ARGS(ep, rptr, magic, size), + + TP_STRUCT__entry(__string(devname, dev_name(ep->dcp->dev)) + __field(u8, endpoint) __field(u32, rptr) + __field(u32, magic) + __field(u32, size)), + + TP_fast_assign(__assign_str(devname); + __entry->endpoint = ep->endpoint; __entry->rptr = rptr; + __entry->magic = magic; __entry->size = size;), + + TP_printk("%s: endpoint 0x%x (%s): QE rptr 0x%x, magic 0x%x, size 0x%x", + __get_str(devname), __entry->endpoint, + show_dcp_endpoint(__entry->endpoint), __entry->rptr, + __entry->magic, __entry->size)); + +TRACE_EVENT( + afk_recv_handle, + TP_PROTO(struct apple_dcp_afkep *ep, u32 channel, u32 type, + u32 data_size, struct epic_hdr *ehdr, + struct epic_sub_hdr *eshdr), + TP_ARGS(ep, channel, type, data_size, ehdr, eshdr), + + TP_STRUCT__entry(__string(devname, dev_name(ep->dcp->dev)) __field( + u8, endpoint) __field(u32, channel) __field(u32, type) + __field(u32, data_size) __field(u8, category) + __field(u16, subtype) + __field(u16, tag)), + + TP_fast_assign(__assign_str(devname); + __entry->endpoint = ep->endpoint; + __entry->channel = channel; __entry->type = type; + __entry->data_size = data_size; + __entry->category = eshdr->category, + __entry->subtype = le16_to_cpu(eshdr->type), + __entry->tag = le16_to_cpu(eshdr->tag)), + + TP_printk( + "%s: endpoint 0x%x (%s): channel 0x%x, type 0x%x (%s), data_size 0x%x, category: 0x%x (%s), subtype: 0x%x, seq: 0x%x", + __get_str(devname), __entry->endpoint, + show_dcp_endpoint(__entry->endpoint), __entry->channel, + __entry->type, print_epic_type(__entry->type), + __entry->data_size, __entry->category, + print_epic_category(__entry->category), __entry->subtype, + __entry->tag)); + +TRACE_EVENT(iomfb_callback, + TP_PROTO(struct apple_dcp *dcp, int tag, const char *name), + TP_ARGS(dcp, tag, name), + + TP_STRUCT__entry( + __string(devname, dev_name(dcp->dev)) + __field(int, tag) + __field(const char *, name) + ), + + TP_fast_assign( + __assign_str(devname); + __entry->tag = tag; __entry->name = name; + ), + + TP_printk("%s: Callback D%03d %s", __get_str(devname), __entry->tag, + __entry->name)); + +TRACE_EVENT(iomfb_push, + TP_PROTO(struct apple_dcp *dcp, + const struct dcp_method_entry *method, int context, + int offset, int depth), + TP_ARGS(dcp, method, context, offset, depth), + + TP_STRUCT__entry( + __string(devname, dev_name(dcp->dev)) + __string(name, method->name) + __field(int, context) + __field(int, offset) + __field(int, depth)), + + TP_fast_assign( + __assign_str(devname); + __assign_str(name); + __entry->context = context; __entry->offset = offset; + __entry->depth = depth; + ), + + TP_printk("%s: Method %s: context %u, offset %u, depth %u", + __get_str(devname), __get_str(name), __entry->context, + __entry->offset, __entry->depth)); + +TRACE_EVENT(iomfb_swap_submit, + TP_PROTO(struct apple_dcp *dcp, u32 swap_id), + TP_ARGS(dcp, swap_id), + TP_STRUCT__entry( + __field(u64, dcp) + __field(u32, swap_id) + ), + TP_fast_assign( + __entry->dcp = (u64)dcp; + __entry->swap_id = swap_id; + ), + TP_printk("dcp=%llx, swap_id=%d", + __entry->dcp, + __entry->swap_id) +); + +TRACE_EVENT(iomfb_swap_complete, + TP_PROTO(struct apple_dcp *dcp, u32 swap_id), + TP_ARGS(dcp, swap_id), + TP_STRUCT__entry( + __field(u64, dcp) + __field(u32, swap_id) + ), + TP_fast_assign( + __entry->dcp = (u64)dcp; + __entry->swap_id = swap_id; + ), + TP_printk("dcp=%llx, swap_id=%d", + __entry->dcp, + __entry->swap_id + ) +); + +TRACE_EVENT(iomfb_swap_complete_intent_gated, + TP_PROTO(struct apple_dcp *dcp, u32 swap_id, u32 width, u32 height), + TP_ARGS(dcp, swap_id, width, height), + TP_STRUCT__entry( + __field(u64, dcp) + __field(u32, swap_id) + __field(u32, width) + __field(u32, height) + ), + TP_fast_assign( + __entry->dcp = (u64)dcp; + __entry->swap_id = swap_id; + __entry->height = height; + __entry->width = width; + ), + TP_printk("dcp=%llx, swap_id=%u %ux%u", + __entry->dcp, + __entry->swap_id, + __entry->width, + __entry->height + ) +); + +TRACE_EVENT(iomfb_abort_swap_ap_gated, + TP_PROTO(struct apple_dcp *dcp, u32 swap_id), + TP_ARGS(dcp, swap_id), + TP_STRUCT__entry( + __field(u64, dcp) + __field(u32, swap_id) + ), + TP_fast_assign( + __entry->dcp = (u64)dcp; + __entry->swap_id = swap_id; + ), + TP_printk("dcp=%llx, swap_id=%u", + __entry->dcp, + __entry->swap_id + ) +); + +DECLARE_EVENT_CLASS(iomfb_parse_mode_template, + TP_PROTO(s64 id, struct dimension *horiz, struct dimension *vert, s64 best_color_mode, bool is_virtual, s64 score), + TP_ARGS(id, horiz, vert, best_color_mode, is_virtual, score), + + TP_STRUCT__entry(__field(s64, id) + __field_struct(struct dimension, horiz) + __field_struct(struct dimension, vert) + __field(s64, best_color_mode) + __field(bool, is_virtual) + __field(s64, score)), + + TP_fast_assign(__entry->id = id; + __entry->horiz = *horiz; + __entry->vert = *vert; + __entry->best_color_mode = best_color_mode; + __entry->is_virtual = is_virtual; + __entry->score = score;), + + TP_printk("id: %lld, best_color_mode: %lld, resolution:%lldx%lld virtual: %d, score: %lld", + __entry->id, __entry->best_color_mode, + __entry->horiz.active, __entry->vert.active, + __entry->is_virtual, __entry->score)); + +DEFINE_EVENT(iomfb_parse_mode_template, iomfb_parse_mode_success, + TP_PROTO(s64 id, struct dimension *horiz, struct dimension *vert, s64 best_color_mode, bool is_virtual, s64 score), + TP_ARGS(id, horiz, vert, best_color_mode, is_virtual, score)); + +DEFINE_EVENT(iomfb_parse_mode_template, iomfb_parse_mode_fail, + TP_PROTO(s64 id, struct dimension *horiz, struct dimension *vert, s64 best_color_mode, bool is_virtual, s64 score), + TP_ARGS(id, horiz, vert, best_color_mode, is_virtual, score)); + +TRACE_EVENT(dcpavserv_init, TP_PROTO(struct apple_dcp *dcp, u64 unit), + TP_ARGS(dcp, unit), + + TP_STRUCT__entry(__string(devname, dev_name(dcp->dev)) + __field(u64, unit)), + + TP_fast_assign(__assign_str(devname); + __entry->unit = unit;), + + TP_printk("%s: dcpav-service unit %lld initialized", __get_str(devname), + __entry->unit)); + +TRACE_EVENT(dptxport_init, TP_PROTO(struct apple_dcp *dcp, u64 unit), + TP_ARGS(dcp, unit), + + TP_STRUCT__entry(__string(devname, dev_name(dcp->dev)) + __field(u64, unit)), + + TP_fast_assign(__assign_str(devname); + __entry->unit = unit;), + + TP_printk("%s: dptxport unit %lld initialized", __get_str(devname), + __entry->unit)); + +TRACE_EVENT( + dptxport_apcall, + TP_PROTO(struct dptx_port *dptx, int idx, size_t len), + TP_ARGS(dptx, idx, len), + + TP_STRUCT__entry(__string(devname, dev_name(dptx->service->ep->dcp->dev)) + __field(u32, unit) __field(int, idx) __field(size_t, len)), + + TP_fast_assign(__assign_str(devname); + __entry->unit = dptx->unit; __entry->idx = idx; __entry->len = len;), + + TP_printk("%s: dptx%d: AP Call %d (%s) with len %lu", __get_str(devname), + __entry->unit, + __entry->idx, show_dptxport_apcall(__entry->idx), __entry->len)); + +TRACE_EVENT( + dptxport_validate_connection, + TP_PROTO(struct dptx_port *dptx, u8 core, u8 atc, u8 die), + TP_ARGS(dptx, core, atc, die), + + TP_STRUCT__entry(__string(devname, dev_name(dptx->service->ep->dcp->dev)) + __field(u32, unit) __field(u8, core) __field(u8, atc) __field(u8, die)), + + TP_fast_assign(__assign_str(devname); + __entry->unit = dptx->unit; __entry->core = core; __entry->atc = atc; __entry->die = die;), + + TP_printk("%s: dptx%d: core %d, atc %d, die %d", __get_str(devname), + __entry->unit, __entry->core, __entry->atc, __entry->die)); + +TRACE_EVENT( + dptxport_connect, + TP_PROTO(struct dptx_port *dptx, u8 core, u8 atc, u8 die), + TP_ARGS(dptx, core, atc, die), + + TP_STRUCT__entry(__string(devname, dev_name(dptx->service->ep->dcp->dev)) + __field(u32, unit) __field(u8, core) __field(u8, atc) __field(u8, die)), + + TP_fast_assign(__assign_str(devname); + __entry->unit = dptx->unit; __entry->core = core; __entry->atc = atc; __entry->die = die;), + + TP_printk("%s: dptx%d: core %d, atc %d, die %d", __get_str(devname), + __entry->unit, __entry->core, __entry->atc, __entry->die)); + +TRACE_EVENT( + dptxport_call_set_link_rate, + TP_PROTO(struct dptx_port *dptx, u32 link_rate), + TP_ARGS(dptx, link_rate), + + TP_STRUCT__entry(__string(devname, dev_name(dptx->service->ep->dcp->dev)) + __field(u32, unit) + __field(u32, link_rate)), + + TP_fast_assign(__assign_str(devname); + __entry->unit = dptx->unit; + __entry->link_rate = link_rate;), + + TP_printk("%s: dptx%d: link rate 0x%x", __get_str(devname), __entry->unit, + __entry->link_rate)); + +TRACE_EVENT(iomfb_brightness, + TP_PROTO(struct apple_dcp *dcp, u32 nits), + TP_ARGS(dcp, nits), + TP_STRUCT__entry( + __field(u64, dcp) + __field(u32, nits) + ), + TP_fast_assign( + __entry->dcp = (u64)dcp; + __entry->nits = nits; + ), + TP_printk("dcp=%llx, nits=%u (raw=0x%05x)", + __entry->dcp, + __entry->nits >> 16, + __entry->nits + ) +); + +#define show_eotf(eotf) \ + __print_symbolic(eotf, { 0, "SDR gamma"}, \ + { 1, "HDR gamma"}, \ + { 2, "ST 2084 (PQ)"}, \ + { 3, "BT.2100 (HLG)"}, \ + { 4, "unexpected"}) + +#define show_encoding(enc) \ + __print_symbolic(enc, { 0, "RGB"}, \ + { 1, "YUV 4:2:0"}, \ + { 3, "YUV 4:2:2"}, \ + { 2, "YUV 4:4:4"}, \ + { 4, "DolbyVision (native)"}, \ + { 5, "DolbyVision (HDMI)"}, \ + { 6, "YCbCr 4:2:2 (DP tunnel)"}, \ + { 7, "YCbCr 4:2:2 (HDMI tunnel)"}, \ + { 8, "DolbyVision LL YCbCr 4:2:2"}, \ + { 9, "DolbyVision LL YCbCr 4:2:2 (DP)"}, \ + {10, "DolbyVision LL YCbCr 4:2:2 (HDMI)"}, \ + {11, "DolbyVision LL YCbCr 4:4:4"}, \ + {12, "DolbyVision LL RGB 4:2:2"}, \ + {13, "GRGB as YCbCr422 (Even line blue)"}, \ + {14, "GRGB as YCbCr422 (Even line red)"}, \ + {15, "unexpected"}) + +#define show_colorimetry(col) \ + __print_symbolic(col, { 0, "SMPTE 170M/BT.601"}, \ + { 1, "BT.701"}, \ + { 2, "xvYCC601"}, \ + { 3, "xvYCC709"}, \ + { 4, "sYCC601"}, \ + { 5, "AdobeYCC601"}, \ + { 6, "BT.2020 (c)"}, \ + { 7, "BT.2020 (nc)"}, \ + { 8, "DolbyVision VSVDB"}, \ + { 9, "BT.2020 (RGB)"}, \ + {10, "sRGB"}, \ + {11, "scRGB"}, \ + {12, "scRGBfixed"}, \ + {13, "AdobeRGB"}, \ + {14, "DCI-P3 (D65)"}, \ + {15, "DCI-P3 (Theater)"}, \ + {16, "Default RGB"}, \ + {17, "unexpected"}) + +#define show_range(range) \ + __print_symbolic(range, { 0, "Full"}, \ + { 1, "Limited"}, \ + { 2, "unexpected"}) + +TRACE_EVENT(iomfb_color_mode, + TP_PROTO(struct apple_dcp *dcp, u32 id, u32 score, u32 depth, + u32 colorimetry, u32 eotf, u32 range, u32 pixel_enc), + TP_ARGS(dcp, id, score, depth, colorimetry, eotf, range, pixel_enc), + TP_STRUCT__entry( + __field(u64, dcp) + __field(u32, id) + __field(u32, score) + __field(u32, depth) + __field(u32, colorimetry) + __field(u32, eotf) + __field(u32, range) + __field(u32, pixel_enc) + ), + TP_fast_assign( + __entry->dcp = (u64)dcp; + __entry->id = id; + __entry->score = score; + __entry->depth = depth; + __entry->colorimetry = min_t(u32, colorimetry, 17U); + __entry->eotf = min_t(u32, eotf, 4U); + __entry->range = min_t(u32, range, 2U); + __entry->pixel_enc = min_t(u32, pixel_enc, 15U); + ), + TP_printk("dcp=%llx, id=%u, score=%u, depth=%u, colorimetry=%s, eotf=%s, range=%s, pixel_enc=%s", + __entry->dcp, + __entry->id, + __entry->score, + __entry->depth, + show_colorimetry(__entry->colorimetry), + show_eotf(__entry->eotf), + show_range(__entry->range), + show_encoding(__entry->pixel_enc) + ) +); + +TRACE_EVENT(iomfb_timing_mode, + TP_PROTO(struct apple_dcp *dcp, u32 id, u32 score, u32 width, + u32 height, u32 clock, u32 color_mode), + TP_ARGS(dcp, id, score, width, height, clock, color_mode), + TP_STRUCT__entry( + __field(u64, dcp) + __field(u32, id) + __field(u32, score) + __field(u32, width) + __field(u32, height) + __field(u32, clock) + __field(u32, color_mode) + ), + TP_fast_assign( + __entry->dcp = (u64)dcp; + __entry->id = id; + __entry->score = score; + __entry->width = width; + __entry->height = height; + __entry->clock = clock; + __entry->color_mode = color_mode; + ), + TP_printk("dcp=%llx, id=%u, score=%u, %ux%u@%u.%u, color_mode=%u", + __entry->dcp, + __entry->id, + __entry->score, + __entry->width, + __entry->height, + __entry->clock >> 16, + ((__entry->clock & 0xffff) * 1000) >> 16, + __entry->color_mode + ) +); + +TRACE_EVENT(avep_sound_mode, + TP_PROTO(struct apple_dcp *dcp, u32 rates, u64 formats, unsigned int nchans), + TP_ARGS(dcp, rates, formats, nchans), + TP_STRUCT__entry( + __field(u64, dcp) + __field(u32, rates) + __field(u64, formats) + __field(unsigned int, nchans) + ), + TP_fast_assign( + __entry->dcp = (u64)dcp; + __entry->rates = rates; + __entry->formats = formats; + __entry->nchans = nchans; + ), + TP_printk("dcp=%llx, rates=%#x, formats=%#llx, nchans=%#x", + __entry->dcp, + __entry->rates, + __entry->formats, + __entry->nchans + ) +); + +#endif /* _TRACE_DCP_H */ + +/* This part must be outside protection */ + +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . + +#include diff --git a/drivers/gpu/drm/apple/version_utils.h b/drivers/gpu/drm/apple/version_utils.h new file mode 100644 index 00000000000000..5a33ce1db61c47 --- /dev/null +++ b/drivers/gpu/drm/apple/version_utils.h @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright The Asahi Linux Contributors */ + +#ifndef __APPLE_VERSION_UTILS_H__ +#define __APPLE_VERSION_UTILS_H__ + +#include +#include + +#define DCP_FW_UNION(u) (u).DCP_FW +#define DCP_FW_SUFFIX CONCATENATE(_, DCP_FW) +#define DCP_FW_NAME(name) CONCATENATE(name, DCP_FW_SUFFIX) +#define DCP_FW_VERSION(x, y, z) ( ((x) << 16) | ((y) << 8) | (z) ) + +#endif /*__APPLE_VERSION_UTILS_H__*/ diff --git a/drivers/gpu/drm/asahi/Kconfig b/drivers/gpu/drm/asahi/Kconfig new file mode 100644 index 00000000000000..ab98d29b6b4a84 --- /dev/null +++ b/drivers/gpu/drm/asahi/Kconfig @@ -0,0 +1,41 @@ +# SPDX-License-Identifier: GPL-2.0 + +config RUST_DRM_SCHED + bool + select DRM_SCHED + +config RUST_DRM_GEM_SHMEM_HELPER + bool + select DRM_GEM_SHMEM_HELPER + +config RUST_DRM_GPUVM + bool + select DRM_GPUVM + +config DRM_ASAHI + tristate "Asahi (DRM support for Apple AGX GPUs)" + depends on RUST + depends on DRM=y + depends on (ARM64 && ARCH_APPLE) || (COMPILE_TEST && !GENERIC_ATOMIC64) + depends on MMU + depends on IOMMU_SUPPORT + depends on PAGE_SIZE_16KB + select RUST_DRM_SCHED + select RUST_DRM_GEM_SHMEM_HELPER + select RUST_DRM_GPUVM + select RUST_APPLE_RTKIT + select WANT_DEV_COREDUMP + help + DRM driver for Apple AGX GPUs (G13x, found in the M1 SoC family) + +config DRM_ASAHI_DEBUG_ALLOCATOR + bool "Use debug allocator" + depends on DRM_ASAHI + help + Use an alternate, simpler allocator which significantly reduces + performance, but can help find firmware- or GPU-side memory safety + issues. However, it can also trigger firmware bugs more easily, + so expect GPU crashes. + + Say N unless you are debugging firmware structures or porting to a + new firmware version. diff --git a/drivers/gpu/drm/asahi/Makefile b/drivers/gpu/drm/asahi/Makefile new file mode 100644 index 00000000000000..e6724866798760 --- /dev/null +++ b/drivers/gpu/drm/asahi/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_DRM_ASAHI) += asahi.o diff --git a/drivers/gpu/drm/asahi/alloc.rs b/drivers/gpu/drm/asahi/alloc.rs new file mode 100644 index 00000000000000..2711b784843300 --- /dev/null +++ b/drivers/gpu/drm/asahi/alloc.rs @@ -0,0 +1,1087 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU kernel object allocator. +//! +//! This kernel driver needs to manage a large number of GPU objects, in both firmware/kernel +//! address space and user address space. This module implements a simple grow-only heap allocator +//! based on the DRM MM range allocator, and a debug allocator that allocates each object as a +//! separate GEM object. +//! +//! Allocations may optionally have debugging enabled, which adds preambles that store metadata +//! about the allocation. This is useful for live debugging using the hypervisor or postmortem +//! debugging with a GPU memory snapshot, since it makes it easier to identify use-after-free and +//! caching issues. + +use kernel::{ + drm::mm, + error::Result, + prelude::*, + str::CString, // +}; + +use crate::debug::*; +use crate::driver::{ + AsahiDevRef, + AsahiDevice, // +}; +use crate::fw::types::Zeroable; +use crate::mmu; +use crate::object::{ + GpuArray, + GpuObject, + GpuOnlyArray, + GpuStruct, + GpuWeakPointer, // +}; +use crate::util::RangeExt; + +use core::cmp::Ordering; +use core::fmt; +use core::fmt::{ + Debug, + Formatter, // +}; +use core::marker::PhantomData; +use core::mem; +use core::ops::Range; +use core::ptr::NonNull; + +const DEBUG_CLASS: DebugFlags = DebugFlags::Alloc; + +#[cfg(not(CONFIG_DRM_ASAHI_DEBUG_ALLOCATOR))] +/// The driver-global allocator type +pub(crate) type DefaultAllocator = HeapAllocator; + +#[cfg(not(CONFIG_DRM_ASAHI_DEBUG_ALLOCATOR))] +/// The driver-global allocation type +pub(crate) type DefaultAllocation = HeapAllocation; + +#[cfg(CONFIG_DRM_ASAHI_DEBUG_ALLOCATOR)] +/// The driver-global allocator type +pub(crate) type DefaultAllocator = SimpleAllocator; + +#[cfg(CONFIG_DRM_ASAHI_DEBUG_ALLOCATOR)] +/// The driver-global allocation type +pub(crate) type DefaultAllocation = SimpleAllocation; + +/// Represents a raw allocation (without any type information). +pub(crate) trait RawAllocation { + /// Returns the CPU-side pointer (if CPU mapping is enabled) as a byte non-null pointer. + fn ptr(&self) -> Option>; + /// Returns the GPU VA pointer as a u64. + fn gpu_ptr(&self) -> u64; + /// Returns the AsahiDevice that owns this allocation. + fn device(&self) -> &AsahiDevice; +} + +/// Represents a typed allocation. +pub(crate) trait Allocation: Debug { + /// Returns the typed CPU-side pointer (if CPU mapping is enabled). + fn ptr(&self) -> Option>; + /// Returns the GPU VA pointer as a u64. + fn gpu_ptr(&self) -> u64; + /// Returns the size of the allocation in bytes. + fn size(&self) -> usize; + /// Returns the AsahiDevice that owns this allocation. + fn device(&self) -> &AsahiDevice; +} + +/// A generic typed allocation wrapping a RawAllocation. +/// +/// This is currently the only Allocation implementation, since it is shared by all allocators. +/// +/// # Invariants +/// The alloaction at `alloc` must have a size equal or greater than `alloc_size` plus `debug_offset` plus `padding`. +pub(crate) struct GenericAlloc { + alloc: U, + alloc_size: usize, + debug_offset: usize, + padding: usize, + tag: u32, + pad_word: u32, + _p: PhantomData, +} + +impl Allocation for GenericAlloc { + /// Returns a pointer to the inner (usable) part of the allocation. + fn ptr(&self) -> Option> { + // SAFETY: self.debug_offset is always within the allocation per the invariant, so is safe to add + // to the base pointer. + unsafe { self.alloc.ptr().map(|p| p.add(self.debug_offset).cast()) } + } + /// Returns the GPU pointer to the inner (usable) part of the allocation. + fn gpu_ptr(&self) -> u64 { + self.alloc.gpu_ptr() + self.debug_offset as u64 + } + /// Returns the size of the inner (usable) part of the allocation. + fn size(&self) -> usize { + self.alloc_size + } + fn device(&self) -> &AsahiDevice { + self.alloc.device() + } +} + +impl Debug for GenericAlloc { + fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result { + f.debug_struct(core::any::type_name::>()) + .field("ptr", &format_args!("{:?}", self.ptr())) + .field("gpu_ptr", &format_args!("{:#X?}", self.gpu_ptr())) + .field("size", &format_args!("{:#X?}", self.size())) + .finish() + } +} + +/// Debugging data associated with an allocation, when debugging is enabled. +#[repr(C)] +struct AllocDebugData { + state: u32, + tag: u32, + size: u64, + base_gpuva: u64, + obj_gpuva: u64, + name: [u8; 0x20], +} + +/// Magic flag indicating a live allocation. +const STATE_LIVE: u32 = u32::from_le_bytes(*b"LIVE"); +/// Magic flag indicating a freed allocation. +const STATE_DEAD: u32 = u32::from_le_bytes(*b"DEAD"); + +/// Marker byte to identify when firmware/GPU write beyond the end of an allocation. +const GUARD_MARKER: u32 = 0x93939393; + +impl Drop for GenericAlloc { + fn drop(&mut self) { + let debug_len = mem::size_of::(); + if self.debug_offset >= debug_len { + if let Some(p) = self.alloc.ptr() { + // SAFETY: self.debug_offset is always greater than the alloc size per + // the invariant, and greater than debug_len as checked above. + unsafe { + let p = p.as_ptr().add(self.debug_offset - debug_len); + (p as *mut u32).write(STATE_DEAD); + } + } + } + if debug_enabled(DebugFlags::FillAllocations) { + if let Some(p) = self.ptr() { + // SAFETY: Writing to our inner base pointer with our known inner size is safe. + unsafe { (p.as_ptr() as *mut u8).write_bytes(0xde, self.size()) }; + } + } + if self.padding != 0 { + if let Some(p) = self.ptr() { + // SAFETY: Per the invariant, we have at least `self.padding` bytes trailing + // the inner base pointer, after `size()` bytes. + let guard = unsafe { + core::slice::from_raw_parts( + (p.as_ptr() as *mut u8 as *const u8).add(self.size()), + self.padding, + ) + }; + let mut first_err = None; + let mut last_err = 0; + for (i, p) in guard.iter().enumerate() { + if *p != (self.pad_word >> (8 * (i & 3))) as u8 { + if first_err.is_none() { + first_err = Some(i); + } + last_err = i; + } + } + if let Some(start) = first_err { + dev_warn!( + self.device().as_ref(), + "Allocator: Corruption after object of type {}/{:#x} at {:#x}:{:#x} + {:#x}..={:#x}\n", + core::any::type_name::(), + self.tag, + self.gpu_ptr(), + self.size(), + start, + last_err, + ); + } + } + } + } +} + +static_assert!(mem::size_of::() == 0x40); + +/// A trait representing an allocator. +pub(crate) trait Allocator { + /// The raw allocation type used by this allocator. + type Raw: RawAllocation; + // TODO: Needs associated_type_defaults + // type Allocation = GenericAlloc; + + /// Returns whether CPU-side mapping is enabled. + fn cpu_maps(&self) -> bool; + /// Returns the minimum alignment for allocations. + fn min_align(&self) -> usize; + /// Allocate an object of the given size in bytes with the given alignment. + fn alloc(&mut self, size: usize, align: usize) -> Result; + + /// Returns a tuple of (count, size) of how much garbage (freed but not yet reusable objects) + /// exists in this allocator. Optional. + fn garbage(&self) -> (usize, usize) { + (0, 0) + } + /// Collect garbage for this allocator, up to the given object count. Optional. + fn collect_garbage(&mut self, _count: usize) {} + + /// Allocate a new GpuStruct object. See [`GpuObject::new`]. + #[inline(never)] + fn new_object( + &mut self, + inner: T, + callback: impl for<'a> FnOnce(&'a T) -> T::Raw<'a>, + ) -> Result>> { + GpuObject::>::new(self.alloc_object()?, inner, callback) + } + + /// Allocate a new GpuStruct object. See [`GpuObject::new_default`]. + #[inline(never)] + fn new_default( + &mut self, + ) -> Result>> + where + for<'a> ::Raw<'a>: Default + Zeroable, + { + GpuObject::>::new_default(self.alloc_object()?) + } + + /// Allocate a new GpuStruct object. See [`GpuObject::new_init`]. + #[inline(never)] + fn new_init<'a, T: GpuStruct, R: PinInit, F>, E, F>( + &mut self, + inner_init: impl Init, + raw_init: impl FnOnce(&'a T, GpuWeakPointer) -> R, + ) -> Result>> + where + kernel::error::Error: core::convert::From, + kernel::error::Error: core::convert::From, + { + GpuObject::>::new_init_prealloc( + self.alloc_object()?, + |_p| inner_init, + raw_init, + ) + } + + /// Allocate a generic buffer of the given size and alignment, applying the debug features if + /// enabled to tag it and detect overflows. + fn alloc_generic( + &mut self, + size: usize, + align: usize, + tag: Option, + ) -> Result> { + let padding = if debug_enabled(DebugFlags::DetectOverflows) { + size + } else { + 0 + }; + + let ret: GenericAlloc = + if self.cpu_maps() && debug_enabled(debug::DebugFlags::DebugAllocations) { + let debug_align = self.min_align().max(align); + let debug_len = mem::size_of::(); + let debug_offset = (debug_len * 2 + debug_align - 1) & !(debug_align - 1); + + let alloc = self.alloc(size + debug_offset + padding, align)?; + + let mut debug = AllocDebugData { + state: STATE_LIVE, + tag: tag.unwrap_or(0), + size: size as u64, + base_gpuva: alloc.gpu_ptr(), + obj_gpuva: alloc.gpu_ptr() + debug_offset as u64, + name: [0; 0x20], + }; + + let name = core::any::type_name::().as_bytes(); + let len = name.len().min(debug.name.len() - 1); + debug.name[..len].copy_from_slice(&name[..len]); + + if let Some(p) = alloc.ptr() { + // SAFETY: Per the size calculations above, this pointer math and the + // writes never exceed the allocation size. + unsafe { + let p = p.as_ptr(); + p.write_bytes(0x42, debug_offset - 2 * debug_len); + let cur = p.add(debug_offset - debug_len) as *mut AllocDebugData; + let prev = p.add(debug_offset - 2 * debug_len) as *mut AllocDebugData; + prev.copy_from(cur, 1); + cur.copy_from(&debug, 1); + }; + } + + GenericAlloc { + alloc, + alloc_size: size, + debug_offset, + tag: tag.unwrap_or(0), + pad_word: tag.unwrap_or(GUARD_MARKER) | 0x81818181, + padding, + _p: PhantomData, + } + } else { + GenericAlloc { + alloc: self.alloc(size + padding, align)?, + alloc_size: size, + debug_offset: 0, + tag: tag.unwrap_or(0), + pad_word: tag.unwrap_or(GUARD_MARKER) | 0x81818181, + padding, + _p: PhantomData, + } + }; + + if debug_enabled(DebugFlags::FillAllocations) { + if let Some(p) = ret.ptr() { + // SAFETY: Writing to our inner base pointer with our known inner size is safe. + unsafe { (p.as_ptr() as *mut u8).write_bytes(0xaa, ret.size()) }; + } + } + + if padding != 0 { + if let Some(p) = ret.ptr() { + // SAFETY: Per the invariant, we have at least `self.padding` bytes trailing + // the inner base pointer, after `size()` bytes. + let guard = unsafe { + core::slice::from_raw_parts_mut( + (p.as_ptr() as *mut u8).add(ret.size()), + padding, + ) + }; + for (i, p) in guard.iter_mut().enumerate() { + *p = (ret.pad_word >> (8 * (i & 3))) as u8; + } + } + } + + Ok(ret) + } + + /// Allocate an object of a given type, without actually initializing the allocation. + /// + /// This is useful to directly call [`GpuObject::new_*`], without borrowing a reference to the + /// allocator for the entire duration (e.g. if further allocations need to happen inside the + /// callbacks). + fn alloc_object(&mut self) -> Result> { + let size = mem::size_of::>(); + let align = mem::align_of::>(); + + self.alloc_generic(size, align, None) + } + + /// Allocate an empty `GpuArray` of a given type and length. + fn array_empty( + &mut self, + count: usize, + ) -> Result>> { + let size = mem::size_of::() * count; + let align = mem::align_of::(); + + let alloc = self.alloc_generic(size, align, None)?; + GpuArray::>::empty(alloc, count) + } + + /// Allocate an empty `GpuArray` of a given type and length. + fn array_empty_tagged( + &mut self, + count: usize, + tag: &[u8; 4], + ) -> Result>> { + let size = mem::size_of::() * count; + let align = mem::align_of::(); + + let alloc = self.alloc_generic(size, align, Some(u32::from_le_bytes(*tag)))?; + GpuArray::>::empty(alloc, count) + } + + /// Allocate an empty `GpuOnlyArray` of a given type and length. + fn array_gpuonly( + &mut self, + count: usize, + ) -> Result>> { + let size = mem::size_of::() * count; + let align = mem::align_of::(); + + let alloc = self.alloc_generic(size, align, None)?; + GpuOnlyArray::>::new(alloc, count) + } +} + +/// A simple allocation backed by a separate GEM object. +/// +/// # Invariants +/// `ptr` is either None or a valid, non-null pointer to the CPU view of the object. +/// `gpu_ptr` is the GPU-side VA of the object. +pub(crate) struct SimpleAllocation { + dev: AsahiDevRef, + ptr: Option>, + gpu_ptr: u64, + _mapping: mmu::KernelMapping, + obj: crate::gem::ObjectRef, +} + +/// SAFETY: `SimpleAllocation` just points to raw memory and should be safe to send across threads. +unsafe impl Send for SimpleAllocation {} +/// SAFETY: `SimpleAllocation` just points to raw memory and should be safe to share across threads. +unsafe impl Sync for SimpleAllocation {} + +impl Drop for SimpleAllocation { + fn drop(&mut self) { + mod_dev_dbg!( + self.device(), + "SimpleAllocator: drop object @ {:#x}\n", + self.gpu_ptr() + ); + if debug_enabled(DebugFlags::FillAllocations) { + if let Ok(mut vmap) = self.obj.vmap() { + vmap.memset(0x42); + } + } + } +} + +impl RawAllocation for SimpleAllocation { + fn ptr(&self) -> Option> { + self.ptr + } + fn gpu_ptr(&self) -> u64 { + self.gpu_ptr + } + fn device(&self) -> &AsahiDevice { + &self.dev + } +} + +/// A simple allocator that allocates each object as its own GEM object, aligned to the end of a +/// page. +/// +/// This is very slow, but it has the advantage that over-reads by the firmware or GPU will fault on +/// the guard page after the allocation, which can be useful to validate that the firmware's or +/// GPU's idea of object size what we expect. +pub(crate) struct SimpleAllocator { + dev: AsahiDevRef, + range: Range, + prot: mmu::Prot, + vm: mmu::Vm, + min_align: usize, + cpu_maps: bool, +} + +impl SimpleAllocator { + /// Create a new `SimpleAllocator` for a given address range and `Vm`. + #[allow(dead_code)] + #[allow(clippy::too_many_arguments)] + pub(crate) fn new( + dev: &AsahiDevice, + vm: &mmu::Vm, + range: Range, + min_align: usize, + prot: mmu::Prot, + _block_size: usize, + mut cpu_maps: bool, + _name: fmt::Arguments<'_>, + _keep_garbage: bool, + ) -> Result { + if debug_enabled(DebugFlags::ForceCPUMaps) { + cpu_maps = true; + } + Ok(SimpleAllocator { + dev: dev.into(), + vm: vm.clone(), + range, + prot, + min_align, + cpu_maps, + }) + } +} + +impl Allocator for SimpleAllocator { + type Raw = SimpleAllocation; + + fn cpu_maps(&self) -> bool { + self.cpu_maps + } + + fn min_align(&self) -> usize { + self.min_align + } + + #[inline(never)] + fn alloc(&mut self, size: usize, align: usize) -> Result { + let size_aligned = (size + mmu::UAT_PGSZ - 1) & !mmu::UAT_PGMSK; + let align = self.min_align.max(align); + let offset = (size_aligned - size) & !(align - 1); + + mod_dev_dbg!( + &self.dev, + "SimpleAllocator::new: size={:#x} size_al={:#x} al={:#x} off={:#x}\n", + size, + size_aligned, + align, + offset + ); + + let mut obj = crate::gem::new_kernel_object(&self.dev, size_aligned)?; + let p = obj.vmap()?.as_mut_ptr() as *mut u8; + if debug_enabled(DebugFlags::FillAllocations) { + obj.vmap()?.memset(0xde); + } + let mapping = obj.map_into_range( + &self.vm, + self.range.clone(), + self.min_align.max(mmu::UAT_PGSZ) as u64, + self.prot, + true, + )?; + + let iova = mapping.iova(); + + // SAFETY: Per the math above to calculate `size_aligned`, this can never overflow. + let ptr = unsafe { p.add(offset) }; + let gpu_ptr = iova + offset as u64; + + mod_dev_dbg!( + &self.dev, + "SimpleAllocator::new -> {:#?} / {:#?} | {:#x} / {:#x}\n", + p, + ptr, + iova, + gpu_ptr + ); + + Ok(SimpleAllocation { + dev: self.dev.clone(), + ptr: NonNull::new(ptr), + gpu_ptr, + _mapping: mapping, + obj, + }) + } +} + +/// Inner data for an allocation from the heap allocator. +/// +/// This is wrapped in an `mm::Node`. +pub(crate) struct HeapAllocationInner { + dev: AsahiDevRef, + ptr: Option>, + real_size: usize, +} + +/// SAFETY: `HeapAllocationInner` just points to raw memory and should be safe to send across threads. +unsafe impl Send for HeapAllocationInner {} +/// SAFETY: `HeapAllocationInner` just points to raw memory and should be safe to share between threads. +unsafe impl Sync for HeapAllocationInner {} + +/// Outer view of a heap allocation. +/// +/// This uses an Option<> so we can move the internal `Node` into the garbage pool when it gets +/// dropped. +/// +/// # Invariants +/// The `Option` must always be `Some(...)` while this object is alive. +pub(crate) struct HeapAllocation(Option>); + +impl Drop for HeapAllocation { + fn drop(&mut self) { + let node = self.0.take().unwrap(); + let size = node.size(); + let alloc = node.alloc_ref(); + + alloc.with(|a| { + if let Some(garbage) = a.garbage.as_mut() { + if garbage.push(node, GFP_KERNEL).is_err() { + dev_err!( + &a.dev.as_ref(), + "HeapAllocation[{}]::drop: Failed to keep garbage\n", + &*a.name, + ); + } + a.total_garbage += size as usize; + None + } else { + // We need to ensure node survives this scope, since dropping it + // will try to take the mm lock and deadlock us + Some(node) + } + }); + } +} + +impl mm::AllocInner for HeapAllocatorInner { + fn drop_object( + &mut self, + start: u64, + _size: u64, + _color: usize, + obj: &mut HeapAllocationInner, + ) { + /* real_size == 0 means it's a guard node */ + if obj.real_size > 0 { + mod_dev_dbg!( + obj.dev, + "HeapAllocator[{}]: drop object @ {:#x} ({} bytes)\n", + &*self.name, + start, + obj.real_size, + ); + self.allocated -= obj.real_size; + } + } +} + +impl RawAllocation for HeapAllocation { + // SAFETY: This function must always return a valid pointer. + // Since the HeapAllocation contains a reference to the + // backing_objects array that contains the object backing this pointer, + // and objects are only ever added to it, this pointer is guaranteed to + // remain valid for the lifetime of the HeapAllocation. + fn ptr(&self) -> Option> { + self.0.as_ref().unwrap().ptr + } + // SAFETY: This function must always return a valid GPU pointer. + // See the explanation in ptr(). + fn gpu_ptr(&self) -> u64 { + self.0.as_ref().unwrap().start() + } + fn device(&self) -> &AsahiDevice { + &self.0.as_ref().unwrap().dev + } +} + +/// Inner data for a heap allocator which uses the DRM MM range allocator to manage the heap. +/// +/// This is wrapped by an `mm::Allocator`. +struct HeapAllocatorInner { + dev: AsahiDevRef, + allocated: usize, + backing_objects: KVec<(crate::gem::ObjectRef, mmu::KernelMapping, u64)>, + garbage: Option>>, + total_garbage: usize, + name: CString, +} + +/// A heap allocator which uses the DRM MM range allocator to manage its objects. +/// +/// The heap is composed of a series of GEM objects. This implementation only ever grows the heap, +/// never shrinks it. +pub(crate) struct HeapAllocator { + dev: AsahiDevRef, + range: Range, + top: u64, + prot: mmu::Prot, + vm: mmu::Vm, + min_align: usize, + block_size: usize, + cpu_maps: bool, + guard_nodes: KVec>, + mm: mm::Allocator, + name: CString, + garbage: Option>>, +} + +impl HeapAllocator { + /// Create a new HeapAllocator for a given `Vm` and address range. + #[allow(dead_code)] + #[allow(clippy::too_many_arguments)] + pub(crate) fn new( + dev: &AsahiDevice, + vm: &mmu::Vm, + range: Range, + min_align: usize, + prot: mmu::Prot, + block_size: usize, + mut cpu_maps: bool, + name: fmt::Arguments<'_>, + keep_garbage: bool, + ) -> Result { + if !min_align.is_power_of_two() { + return Err(EINVAL); + } + if debug_enabled(DebugFlags::ForceCPUMaps) { + cpu_maps = true; + } + + let name = CString::try_from_fmt(name)?; + + let inner = HeapAllocatorInner { + dev: dev.into(), + allocated: 0, + backing_objects: KVec::new(), + // TODO: This clearly needs a try_clone() or similar + name: CString::try_from_fmt(fmt!("{}", &*name))?, + garbage: if keep_garbage { + Some(KVec::new()) + } else { + None + }, + total_garbage: 0, + }; + + let mm = mm::Allocator::new(range.start, range.range(), inner)?; + + Ok(HeapAllocator { + dev: dev.into(), + vm: vm.clone(), + top: range.start, + range, + prot, + min_align, + block_size: block_size.max(min_align), + cpu_maps, + guard_nodes: KVec::new(), + mm, + name, + garbage: if keep_garbage { + Some({ + let mut v = KVec::new(); + v.reserve(128, GFP_KERNEL)?; + v + }) + } else { + None + }, + }) + } + + /// Add a new backing block of the given size to this heap. + /// + /// If CPU mapping is enabled, this also adds a guard node to the range allocator to ensure that + /// objects cannot straddle backing block boundaries, since we cannot easily create a contiguous + /// CPU VA mapping for them. This can create some fragmentation. If CPU mapping is disabled, we + /// skip the guard blocks, since the GPU view of the heap is always contiguous. + #[inline(never)] + fn add_block(&mut self, size: usize) -> Result { + let size_aligned = (size + mmu::UAT_PGSZ - 1) & !mmu::UAT_PGMSK; + + mod_dev_dbg!( + &self.dev, + "HeapAllocator[{}]::add_block: size={:#x} size_al={:#x}\n", + &*self.name, + size, + size_aligned, + ); + + if self.top.saturating_add(size_aligned as u64) > self.range.end { + dev_err!( + self.dev.as_ref(), + "HeapAllocator[{}]::add_block: Exhausted VA space\n", + &*self.name, + ); + } + + let mut obj = crate::gem::new_kernel_object(&self.dev, size_aligned)?; + if self.cpu_maps && debug_enabled(DebugFlags::FillAllocations) { + obj.vmap()?.memset(0xde); + } + + let gpu_ptr = self.top; + let mapping = obj + .map_at(&self.vm, gpu_ptr, self.prot, self.cpu_maps) + .inspect_err(|err| { + dev_err!( + self.dev.as_ref(), + "HeapAllocator[{}]::add_block: Failed to map at {:#x} ({:?})\n", + &*self.name, + gpu_ptr, + err + ); + })?; + + if self.cpu_maps { + // Create virtual mapping here ahead of time so that the vmap() in + // alloc_inner() does not take the the object's dma_resv lock while + // the mm lock is locked. mmu::Vm requires the opposite lock order. + obj.vmap()?; + } + + self.mm + .with_inner(|inner| inner.backing_objects.reserve(1, GFP_KERNEL))?; + + let mut new_top = self.top + size_aligned as u64; + if self.cpu_maps { + let guard = self.min_align.max(mmu::UAT_PGSZ); + mod_dev_dbg!( + self.dev, + "HeapAllocator[{}]::add_block: Adding guard node {:#x}:{:#x}\n", + &*self.name, + new_top, + guard + ); + + let inner = HeapAllocationInner { + dev: self.dev.clone(), + ptr: None, + real_size: 0, + }; + + let node = match self.mm.reserve_node(inner, new_top, guard as u64, 0) { + Ok(a) => a, + Err(a) => { + dev_err!( + self.dev.as_ref(), + "HeapAllocator[{}]::add_block: Failed to reserve guard node {:#x}:{:#x}: {:?}\n", + &*self.name, + guard, + new_top, + a + ); + return Err(EIO); + } + }; + + self.guard_nodes.push(node, GFP_KERNEL)?; + + new_top += guard as u64; + } + mod_dev_dbg!( + &self.dev, + "HeapAllocator[{}]::add_block: top={:#x}\n", + &*self.name, + new_top + ); + + self.mm.with_inner(|inner| { + inner + .backing_objects + .push((obj, mapping, gpu_ptr), GFP_KERNEL) + })?; + + self.top = new_top; + + cls_dev_dbg!( + MemStats, + &self.dev, + "{} Heap: grow to {} bytes\n", + &*self.name, + self.top - self.range.start + ); + + Ok(()) + } + + /// Find the backing object index that backs a given GPU address. + fn find_obj(&mut self, addr: u64) -> Result { + self.mm.with_inner(|inner| { + inner + .backing_objects + .binary_search_by(|obj| { + let start = obj.2; + let end = obj.2 + obj.0.size() as u64; + if start > addr { + Ordering::Greater + } else if end <= addr { + Ordering::Less + } else { + Ordering::Equal + } + }) + .or(Err(ENOENT)) + }) + } + + fn alloc_inner(&mut self, size: usize, align: usize) -> Result { + if align != 0 && !align.is_power_of_two() { + return Err(EINVAL); + } + let align = self.min_align.max(align); + let size_aligned = (size + align - 1) & !(align - 1); + + mod_dev_dbg!( + &self.dev, + "HeapAllocator[{}]::new: size={:#x} size_al={:#x}\n", + &*self.name, + size, + size_aligned, + ); + + let inner = HeapAllocationInner { + dev: self.dev.clone(), + ptr: None, + real_size: size, + }; + + let mut node = match self.mm.insert_node_generic( + inner, + size_aligned as u64, + align as u64, + 0, + mm::InsertMode::Best, + ) { + Ok(a) => a, + Err(a) => { + dev_err!( + &self.dev.as_ref(), + "HeapAllocator[{}]::new: Failed to insert node of size {:#x} / align {:#x}: {:?}\n", + &*self.name, size_aligned, align, a + ); + return Err(a); + } + }; + + self.mm.with_inner(|inner| inner.allocated += size); + + let mut new_object = false; + let start = node.start(); + let end = start + node.size(); + if end > self.top { + if start > self.top { + dev_warn!( + self.dev.as_ref(), + "HeapAllocator[{}]::alloc: top={:#x}, start={:#x}\n", + &*self.name, + self.top, + start + ); + } + let block_size = self.block_size.max((end - self.top) as usize); + self.add_block(block_size)?; + new_object = true; + } + assert!(end <= self.top); + + if self.cpu_maps { + mod_dev_dbg!( + self.dev, + "HeapAllocator[{}]::alloc: mapping to CPU\n", + &*self.name + ); + + let idx = if new_object { + None + } else { + Some(match self.find_obj(start) { + Ok(a) => a, + Err(_) => { + dev_warn!( + self.dev.as_ref(), + "HeapAllocator[{}]::alloc: Failed to find object at {:#x}\n", + &*self.name, + start + ); + return Err(EIO); + } + }) + }; + let (obj_start, obj_size, p) = self.mm.with_inner(|inner| -> Result<_> { + let idx = idx.unwrap_or(inner.backing_objects.len() - 1); + let obj = &mut inner.backing_objects[idx]; + let p = obj.0.vmap()?.as_mut_ptr() as *mut u8; + Ok((obj.2, obj.0.size(), p)) + })?; + assert!(obj_start <= start); + assert!(obj_start + obj_size as u64 >= end); + node.as_mut().inner_mut().ptr = + // SAFETY: Per the asserts above, this offset is always within the allocation. + NonNull::new(unsafe { p.add((start - obj_start) as usize) }); + mod_dev_dbg!( + self.dev, + "HeapAllocator[{}]::alloc: CPU pointer = {:?}\n", + &*self.name, + node.ptr + ); + } + + mod_dev_dbg!( + self.dev, + "HeapAllocator[{}]::alloc: Allocated {:#x} bytes @ {:#x}\n", + &*self.name, + end - start, + start + ); + + Ok(HeapAllocation(Some(node))) + } +} + +impl Allocator for HeapAllocator { + type Raw = HeapAllocation; + + fn cpu_maps(&self) -> bool { + self.cpu_maps + } + + fn min_align(&self) -> usize { + self.min_align + } + + fn alloc(&mut self, size: usize, align: usize) -> Result { + let ret = self.alloc_inner(size, align); + + if ret.is_err() { + dev_warn!( + self.dev.as_ref(), + "HeapAllocator[{}]::alloc: Allocation of {:#x}({:#x}) size object failed\n", + &*self.name, + size, + align + ); + } + ret + } + + fn garbage(&self) -> (usize, usize) { + self.mm.with_inner(|inner| { + if let Some(g) = inner.garbage.as_ref() { + (g.len(), inner.total_garbage) + } else { + (0, 0) + } + }) + } + + fn collect_garbage(&mut self, mut count: usize) { + if let Some(garbage) = self.garbage.as_mut() { + garbage.clear(); + + while count > 0 { + let block = count.min(garbage.capacity()); + assert!(block > 0); + + // Take the garbage out of the inner block, so we can safely drop it without deadlocking + self.mm.with_inner(|inner| { + if let Some(g) = inner.garbage.as_mut() { + for node in g.drain(0..block) { + inner.total_garbage -= node.size() as usize; + garbage + .push(node, GFP_KERNEL) + .expect("push() failed after reserve()"); + } + } + }); + + count -= block; + // Now drop it + garbage.clear(); + } + } + } +} + +impl Drop for HeapAllocatorInner { + fn drop(&mut self) { + mod_dev_dbg!( + self.dev, + "HeapAllocator[{}]: dropping allocator\n", + &*self.name + ); + if self.allocated > 0 { + // This should never happen + dev_crit!( + self.dev.as_ref(), + "HeapAllocator[{}]: dropping with {} bytes allocated\n", + &*self.name, + self.allocated + ); + } + } +} diff --git a/drivers/gpu/drm/asahi/asahi.rs b/drivers/gpu/drm/asahi/asahi.rs new file mode 100644 index 00000000000000..296091dced554d --- /dev/null +++ b/drivers/gpu/drm/asahi/asahi.rs @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +#![recursion_limit = "2048"] + +//! Driver for the Apple AGX GPUs found in Apple Silicon SoCs. + +mod alloc; +mod buffer; +mod channel; +#[cfg(CONFIG_DEV_COREDUMP)] +mod crashdump; +mod debug; +mod driver; +mod event; +mod file; +mod float; +mod fw; +mod gem; +mod gpu; +mod hw; +mod initdata; +mod mem; +mod microseq; +mod mmu; +mod object; +mod pgtable; +mod queue; +mod regs; +mod slotalloc; +mod util; +#[cfg(CONFIG_DRM_ASAHI_MAPLE_TREE)] +mod vm; +mod workqueue; + +kernel::module_platform_driver! { + type: driver::AsahiDriver, + name: "asahi", + description: "AGX GPU driver for Apple silicon SoCs", + license: "Dual MIT/GPL", + params: { + debug_flags: u64 { + default: 0, + // permissions: 0o644, + description: "Debug flags", + }, + fault_control: u32 { + default: 0xb, + // permissions: 0, + description: "Fault control (0x0: hard faults, 0xb: macOS default)", + }, + initial_tvb_size: usize { + default: 0x8, + // permissions: 0o644, + description: "Initial TVB size in blocks", + }, + robust_isolation: u32 { + default: 0, + // permissions: 0o644, + description: "Fully isolate GPU contexts (limits performance)", + }, + }, +} diff --git a/drivers/gpu/drm/asahi/buffer.rs b/drivers/gpu/drm/asahi/buffer.rs new file mode 100644 index 00000000000000..309482441062d9 --- /dev/null +++ b/drivers/gpu/drm/asahi/buffer.rs @@ -0,0 +1,809 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Tiled Vertex Buffer management +//! +//! This module manages the Tiled Vertex Buffer, also known as the Parameter Buffer (in imgtec +//! parlance) or the tiler heap (on other architectures). This buffer holds transformed primitive +//! data between the vertex/tiling stage and the fragment stage. +//! +//! On AGX, the buffer is a heap of 128K blocks split into 32K pages (which must be aligned to a +//! multiple of 32K in VA space). The buffer can be shared between multiple render jobs, and each +//! will allocate pages from it during vertex processing and return them during fragment processing. +//! +//! If the buffer runs out of free pages, the vertex pass stops and a partial fragment pass occurs, +//! spilling the intermediate render target state to RAM (a partial render). This is all managed +//! transparently by the firmware. Since partial renders are less efficient, the kernel must grow +//! the heap in response to feedback from the firmware to avoid partial renders in the future. +//! Currently, we only ever grow the heap, and never shrink it. +//! +//! AGX also supports memoryless render targets, which can be used for intermediate results within +//! a render pass. To support partial renders, it seems the GPU/firmware has the ability to borrow +//! pages from the TVB buffer as a temporary render target buffer. Since this happens during a +//! partial render itself, if the buffer runs out of space, it requires synchronous growth in +//! response to a firmware interrupt. This is not currently supported, but may be in the future, +//! though it is unclear whether it is worth the effort. +//! +//! This module is also in charge of managing the temporary objects associated with a single render +//! pass, which includes the top-level tile array, the tail pointer cache, preemption buffers, and +//! other miscellaneous structures collectively managed as a "scene". +//! +//! To avoid runaway memory usage, there is a maximum size for buffers (at that point it's unlikely +//! that partial renders will incur much overhead over the buffer data access itself). This is +//! different depending on whether memoryless render targets are in use, and is currently hardcoded. +//! to the most common value used by macOS. + +use crate::debug::*; +use crate::fw::buffer; +use crate::fw::types::*; +use crate::util::*; +use crate::{ + alloc, + fw, + gpu, + hw, + mmu, + slotalloc, // +}; +use core::sync::atomic::Ordering; +use kernel::new_mutex; +use kernel::prelude::*; +use kernel::sync::{ + Arc, + Mutex, // +}; +use kernel::{ + c_str, + static_lock_class, // +}; + +const DEBUG_CLASS: DebugFlags = DebugFlags::Buffer; + +/// There are 127 GPU/firmware-side buffer manager slots (yes, 127, not 128). +const NUM_BUFFERS: u32 = 127; + +/// Page size bits for buffer pages (32K). VAs must be aligned to this size. +pub(crate) const PAGE_SHIFT: usize = 15; +/// Page size for buffer pages. +pub(crate) const PAGE_SIZE: usize = 1 << PAGE_SHIFT; +/// Number of pages in a buffer block, which should be contiguous in VA space. +pub(crate) const PAGES_PER_BLOCK: usize = 4; +/// Size of a buffer block. +pub(crate) const BLOCK_SIZE: usize = PAGE_SIZE * PAGES_PER_BLOCK; + +/// Metadata about the tiling configuration for a scene. This is computed in the `render` module. +/// based on dimensions, tile size, and other info. +pub(crate) struct TileInfo { + /// Tile count in the X dimension. Tiles are always 32x32. + pub(crate) tiles_x: u32, + /// Tile count in the Y dimension. Tiles are always 32x32. + pub(crate) tiles_y: u32, + /// Total tile count. + pub(crate) tiles: u32, + /// Micro-tile width (16 or 32). + pub(crate) utile_width: u32, + /// Micro-tile height (16 or 32). + pub(crate) utile_height: u32, + // Macro-tiles in the X dimension. Always 4. + //pub(crate) mtiles_x: u32, + // Macro-tiles in the Y dimension. Always 4. + //pub(crate) mtiles_y: u32, + /// Tiles per macro-tile in the X dimension. + pub(crate) tiles_per_mtile_x: u32, + /// Tiles per macro-tile in the Y dimension. + pub(crate) tiles_per_mtile_y: u32, + // Total tiles per macro-tile. + //pub(crate) tiles_per_mtile: u32, + /// Micro-tiles per macro-tile in the X dimension. + pub(crate) utiles_per_mtile_x: u32, + /// Micro-tiles per macro-tile in the Y dimension. + pub(crate) utiles_per_mtile_y: u32, + // Total micro-tiles per macro-tile. + //pub(crate) utiles_per_mtile: u32, + /// Size of the top-level tilemap, in bytes (for all layers, one cluster). + pub(crate) tilemap_size: usize, + /// Size of the Tail Pointer Cache, in bytes (for all layers * clusters). + pub(crate) tpc_size: usize, + /// Number of blocks in the clustering meta buffer (for clustering) per layer. + pub(crate) meta1_layer_stride: u32, + /// Number of blocks in the clustering meta buffer (for clustering). + pub(crate) meta1_blocks: u32, + /// Layering metadata size. + pub(crate) layermeta_size: usize, + /// Minimum number of TVB blocks for this render. + pub(crate) min_tvb_blocks: usize, + /// Tiling parameter structure passed to firmware. + pub(crate) params: fw::vertex::raw::TilingParameters, +} + +/// A single scene, representing a render pass and its required buffers. +#[versions(AGX)] +#[derive(Debug)] +pub(crate) struct Scene { + object: GpuObject, + slot: u32, + rebind: bool, + preempt2_off: usize, + preempt3_off: usize, + // Note: these are dead code only on some version variants. + // It's easier to do this than to propagate the version conditionals everywhere. + #[allow(dead_code)] + meta1_off: usize, + #[allow(dead_code)] + meta2_off: usize, + #[allow(dead_code)] + meta3_off: usize, + #[allow(dead_code)] + meta4_off: usize, +} + +#[versions(AGX)] +impl Scene::ver { + /// Returns true if the buffer was bound to a fresh manager slot, and therefore needs an init + /// command before a render. + pub(crate) fn rebind(&self) -> bool { + self.rebind + } + + /// Returns the buffer manager slot this scene's buffer was bound to. + pub(crate) fn slot(&self) -> u32 { + self.slot + } + + /// Returns the GPU pointer to the [`buffer::Scene::ver`]. + pub(crate) fn gpu_pointer(&self) -> GpuPointer<'_, buffer::Scene::ver> { + self.object.gpu_pointer() + } + + /// Returns the GPU weak pointer to the [`buffer::Scene::ver`]. + pub(crate) fn weak_pointer(&self) -> GpuWeakPointer { + self.object.weak_pointer() + } + + /// Returns the GPU weak pointer to the kernel-side temp buffer. + /// (purpose unknown...) + pub(crate) fn kernel_buffer_pointer(&self) -> GpuWeakPointer<[u8]> { + self.object.buffer.inner.lock().kernel_buffer.weak_pointer() + } + + /// Returns the GPU pointer to the `buffer::Info::ver` object associated with this Scene. + pub(crate) fn buffer_pointer(&self) -> GpuPointer<'_, buffer::Info::ver> { + // SAFETY: We can't return the strong pointer directly since its lifetime crosses a lock, + // but we know its lifetime will be valid as long as &self since we hold a reference to the + // buffer, so just construct the strong pointer with the right lifetime here. + unsafe { self.weak_buffer_pointer().upgrade() } + } + + /// Returns the GPU weak pointer to the `buffer::Info::ver` object associated with this Scene. + pub(crate) fn weak_buffer_pointer(&self) -> GpuWeakPointer { + self.object.buffer.inner.lock().info.weak_pointer() + } + + /// Returns the GPU pointer to the TVB heap metadata buffer. + pub(crate) fn tvb_heapmeta_pointer(&self) -> GpuPointer<'_, &'_ [u8]> { + self.object.tvb_heapmeta.gpu_pointer() + } + + /// Returns the GPU pointer to the layer metadata buffer. + pub(crate) fn tvb_layermeta_pointer(&self) -> GpuPointer<'_, &'_ [u8]> { + self.object.tvb_heapmeta.gpu_offset_pointer(0x200) + } + + /// Returns the GPU pointer to the top-level TVB tilemap buffer. + pub(crate) fn tvb_tilemap_pointer(&self) -> GpuPointer<'_, &'_ [u8]> { + self.object.tvb_tilemap.gpu_pointer() + } + + /// Returns the GPU pointer to the Tail Pointer Cache buffer. + pub(crate) fn tpc_pointer(&self) -> GpuPointer<'_, &'_ [u8]> { + self.object.tpc.gpu_pointer() + } + + /// Returns the GPU pointer to the first preemption scratch buffer. + pub(crate) fn preempt_buf_1_pointer(&self) -> GpuPointer<'_, &'_ [u8]> { + self.object.preempt_buf.gpu_pointer() + } + + /// Returns the GPU pointer to the second preemption scratch buffer. + pub(crate) fn preempt_buf_2_pointer(&self) -> GpuPointer<'_, &'_ [u8]> { + self.object + .preempt_buf + .gpu_offset_pointer(self.preempt2_off) + } + + /// Returns the GPU pointer to the third preemption scratch buffer. + pub(crate) fn preempt_buf_3_pointer(&self) -> GpuPointer<'_, &'_ [u8]> { + self.object + .preempt_buf + .gpu_offset_pointer(self.preempt3_off) + } + + /// Returns the GPU pointer to the per-cluster tilemap buffer, if clustering is enabled. + #[allow(dead_code)] + pub(crate) fn cluster_tilemaps_pointer(&self) -> Option> { + self.object + .clustering + .as_ref() + .map(|c| c.tilemaps.gpu_pointer()) + } + + /// Returns the GPU pointer to the clustering layer metadata buffer, if clustering is enabled. + #[allow(dead_code)] + pub(crate) fn tvb_cluster_layermeta_pointer(&self) -> Option> { + self.object + .clustering + .as_ref() + .map(|c| c.meta.gpu_pointer()) + } + + /// Returns the GPU pointer to the clustering metadata 1 buffer, if clustering is enabled. + #[allow(dead_code)] + pub(crate) fn meta_1_pointer(&self) -> Option> { + self.object + .clustering + .as_ref() + .map(|c| c.meta.gpu_offset_pointer(self.meta1_off)) + } + + /// Returns the GPU pointer to the clustering metadata 2 buffer, if clustering is enabled. + #[allow(dead_code)] + pub(crate) fn meta_2_pointer(&self) -> Option> { + self.object + .clustering + .as_ref() + .map(|c| c.meta.gpu_offset_pointer(self.meta2_off)) + } + + /// Returns the GPU pointer to the clustering metadata 3 buffer, if clustering is enabled. + #[allow(dead_code)] + pub(crate) fn meta_3_pointer(&self) -> Option> { + self.object + .clustering + .as_ref() + .map(|c| c.meta.gpu_offset_pointer(self.meta3_off)) + } + + /// Returns the GPU pointer to the clustering metadata 4 buffer, if clustering is enabled. + #[allow(dead_code)] + pub(crate) fn meta_4_pointer(&self) -> Option> { + self.object + .clustering + .as_ref() + .map(|c| c.meta.gpu_offset_pointer(self.meta4_off)) + } +} + +#[versions(AGX)] +impl Drop for Scene::ver { + fn drop(&mut self) { + let mut inner = self.object.buffer.inner.lock(); + assert_ne!(inner.active_scenes, 0); + inner.active_scenes -= 1; + + if inner.active_scenes == 0 { + mod_pr_debug!( + "Buffer: no scenes left, dropping slot {}", + inner.active_slot.take().unwrap().slot() + ); + inner.active_slot = None; + } + } +} + +/// Inner data for a single TVB buffer object. +#[versions(AGX)] +struct BufferInner { + info: GpuObject, + ualloc: Arc>, + ualloc_priv: Arc>, + blocks: KVec>, + max_blocks: usize, + max_blocks_nomemless: usize, + mgr: BufferManager::ver, + active_scenes: usize, + active_slot: Option>, + last_token: Option, + tpc: Option>>, + kernel_buffer: GpuArray, + stats: GpuObject, + cfg: &'static hw::HwConfig, + preempt1_size: usize, + preempt2_size: usize, + preempt3_size: usize, + num_clusters: usize, +} + +/// Locked and reference counted TVB buffer. +#[versions(AGX)] +pub(crate) struct Buffer { + inner: Arc>, +} + +#[versions(AGX)] +impl Buffer::ver { + /// Create a new Buffer for a given VM, given the per-VM allocators. + pub(crate) fn new( + gpu: &dyn gpu::GpuManager, + alloc: &mut gpu::KernelAllocators, + ualloc: Arc>, + ualloc_priv: Arc>, + mgr: &BufferManager::ver, + ) -> Result { + // These are the typical max numbers on macOS. + // 8GB machines have this halved. + let max_size: usize = 862_322_688; // bytes + let max_size_nomemless = max_size / 3; + + let max_blocks = max_size / BLOCK_SIZE; + let max_blocks_nomemless = max_size_nomemless / BLOCK_SIZE; + let max_pages = max_blocks * PAGES_PER_BLOCK; + let max_pages_nomemless = max_blocks_nomemless * PAGES_PER_BLOCK; + + let num_clusters = gpu.get_dyncfg().id.num_clusters as usize; + let num_clusters_adj = if num_clusters > 1 { + num_clusters + 1 + } else { + 1 + }; + + let preempt1_size = num_clusters_adj * gpu.get_cfg().preempt1_size; + let preempt2_size = num_clusters_adj * gpu.get_cfg().preempt2_size; + let preempt3_size = num_clusters_adj * gpu.get_cfg().preempt3_size; + + let shared = &mut alloc.shared; + let info = alloc.private.new_init( + { + let ualloc_priv = &ualloc_priv; + try_init!(buffer::Info::ver { + block_ctl: shared.new_default::()?, + counter: shared.new_default::()?, + page_list: ualloc_priv.lock().array_empty_tagged(max_pages, b"PLST")?, + block_list: ualloc_priv + .lock() + .array_empty_tagged(max_blocks * 2, b"BLST")?, + }) + }, + |inner, _p| { + try_init!(buffer::raw::Info::ver { + gpu_counter: 0x0, + unk_4: 0, + last_id: 0x0, + cur_id: -1, + unk_10: 0x0, + gpu_counter2: 0x0, + unk_18: 0x0, + #[ver(V < V13_0B4 || G >= G14X)] + unk_1c: 0x0, + page_list: inner.page_list.gpu_pointer(), + page_list_size: (4 * max_pages).try_into()?, + page_count: AtomicU32::new(0), + max_blocks: max_blocks.try_into()?, + block_count: AtomicU32::new(0), + unk_38: 0x0, + block_list: inner.block_list.gpu_pointer(), + block_ctl: inner.block_ctl.gpu_pointer(), + last_page: AtomicU32::new(0), + gpu_page_ptr1: 0x0, + gpu_page_ptr2: 0x0, + unk_58: 0x0, + block_size: BLOCK_SIZE as u32, + unk_60: U64(0x0), + counter: inner.counter.gpu_pointer(), + unk_70: 0x0, + unk_74: 0x0, + unk_78: 0x0, + unk_7c: 0x0, + unk_80: 0x1, + max_pages: max_pages.try_into()?, + max_pages_nomemless: max_pages_nomemless.try_into()?, + unk_8c: 0x0, + unk_90: Default::default(), + }) + }, + )?; + + // Technically similar to Scene below, let's play it safe. + let kernel_buffer = alloc.shared.array_empty_tagged(0x40, b"KBUF")?; + let stats = alloc + .shared + .new_object(Default::default(), |_inner| buffer::raw::Stats { + reset: AtomicU32::from(1), + ..Default::default() + })?; + + Ok(Buffer::ver { + inner: Arc::pin_init( + new_mutex!(BufferInner::ver { + info, + ualloc, + ualloc_priv, + blocks: KVec::new(), + max_blocks, + max_blocks_nomemless, + mgr: mgr.clone(), + active_scenes: 0, + active_slot: None, + last_token: None, + tpc: None, + kernel_buffer, + stats, + cfg: gpu.get_cfg(), + preempt1_size, + preempt2_size, + preempt3_size, + num_clusters, + }), + GFP_KERNEL, + )?, + }) + } + + /// Returns the total block count allocated to this Buffer. + pub(crate) fn block_count(&self) -> u32 { + self.inner.lock().blocks.len() as u32 + } + + /// Automatically grow the Buffer based on feedback from the statistics. + pub(crate) fn auto_grow(&self) -> Result { + let inner = self.inner.lock(); + + let used_pages = inner.stats.with(|raw, _inner| { + let used = raw.max_pages.load(Ordering::Relaxed); + raw.reset.store(1, Ordering::Release); + used as usize + }); + + let need_blocks = (used_pages * 2) + .div_ceil(PAGES_PER_BLOCK) + .min(inner.max_blocks_nomemless); + let want_blocks = (used_pages * 3) + .div_ceil(PAGES_PER_BLOCK) + .min(inner.max_blocks_nomemless); + + let cur_count = inner.blocks.len(); + + if need_blocks <= cur_count { + Ok(false) + } else { + // Grow to 3x requested size (same logic as macOS) + core::mem::drop(inner); + self.ensure_blocks(want_blocks)?; + Ok(true) + } + } + + /// Synchronously grow the Buffer. + pub(crate) fn sync_grow(&self) { + let inner = self.inner.lock(); + + let cur_count = inner.blocks.len(); + core::mem::drop(inner); + if self.ensure_blocks(cur_count + 10).is_err() { + pr_err!("BufferManager: Failed to grow buffer synchronously\n"); + } + } + + /// Ensure that the buffer has at least a certain minimum size in blocks. + pub(crate) fn ensure_blocks(&self, min_blocks: usize) -> Result { + let mut inner = self.inner.lock(); + + let cur_count = inner.blocks.len(); + if cur_count >= min_blocks { + return Ok(false); + } + if min_blocks > inner.max_blocks { + return Err(ENOMEM); + } + + let add_blocks = min_blocks - cur_count; + let new_count = min_blocks; + + let mut new_blocks: KVec> = KVec::new(); + + // Allocate the new blocks first, so if it fails they will be dropped + let mut ualloc = inner.ualloc.lock(); + for _i in 0..add_blocks { + new_blocks.push(ualloc.array_gpuonly(BLOCK_SIZE)?, GFP_KERNEL)?; + } + core::mem::drop(ualloc); + + // Then actually commit them + inner.blocks.reserve(add_blocks, GFP_KERNEL)?; + + for (i, block) in new_blocks.into_iter().enumerate() { + let page_num = (block.gpu_va().get() >> PAGE_SHIFT) as u32; + + inner + .blocks + .push(block, GFP_KERNEL) + .expect("push() failed after reserve()"); + inner.info.block_list[2 * (cur_count + i)] = page_num; + for j in 0..PAGES_PER_BLOCK { + inner.info.page_list[(cur_count + i) * PAGES_PER_BLOCK + j] = page_num + j as u32; + } + } + + inner.info.block_ctl.with(|raw, _inner| { + raw.total.store(new_count as u32, Ordering::SeqCst); + raw.wptr.store(new_count as u32, Ordering::SeqCst); + }); + + /* Only do this update if the buffer manager is idle (which means we own it) */ + if inner.active_scenes == 0 { + let page_count = (new_count * PAGES_PER_BLOCK) as u32; + inner.info.with(|raw, _inner| { + raw.page_count.store(page_count, Ordering::Relaxed); + raw.block_count.store(new_count as u32, Ordering::Relaxed); + raw.last_page.store(page_count - 1, Ordering::Relaxed); + }); + } + + Ok(true) + } + + /// Create a new [`Scene::ver`] (render pass) using this buffer. + pub(crate) fn new_scene( + &self, + alloc: &mut gpu::KernelAllocators, + tile_info: &TileInfo, + ) -> Result { + let mut inner = self.inner.lock(); + + let tilemap_size = tile_info.tilemap_size; + let tpc_size = tile_info.tpc_size; + + // TODO: what is this exactly? + mod_pr_debug!("Buffer: Allocating TVB buffers\n"); + + // This seems to be a list, with 4x2 bytes of headers and 8 bytes per entry. + // On single-cluster devices, the used length always seems to be 1. + // On M1 Ultra, it can grow and usually doesn't exceed 64 entries. + // macOS allocates a whole 64K * 0x80 for this, so let's go with + // that to be safe... + let user_buffer = inner.ualloc.lock().array_empty_tagged( + if inner.num_clusters > 1 { + 0x10080 + } else { + 0x80 + }, + b"UBUF", + )?; + + let tvb_heapmeta = inner + .ualloc + .lock() + .array_empty_tagged(0x200 + tile_info.layermeta_size, b"HMTA")?; + let tvb_tilemap = inner + .ualloc + .lock() + .array_empty_tagged(tilemap_size, b"TMAP")?; + + mod_pr_debug!("Buffer: Allocating misc buffers\n"); + let preempt_buf = inner.ualloc.lock().array_empty_tagged( + inner.preempt1_size + inner.preempt2_size + inner.preempt3_size, + b"PRMT", + )?; + + let tpc = match inner.tpc.as_ref() { + Some(buf) if buf.len() >= tpc_size => buf.clone(), + _ => { + // MacOS allocates this as shared GPU+FW, but + // priv seems to work and might be faster? + // Needs to be FW-writable anyway, so ualloc + // won't work. + let buf = Arc::new( + inner.ualloc_priv.lock().array_empty_tagged( + (tpc_size + mmu::UAT_PGMSK) & !mmu::UAT_PGMSK, + b"TPC ", + )?, + GFP_KERNEL, + )?; + inner.tpc = Some(buf.clone()); + buf + } + }; + + let mut clmeta_size = 0; + let mut meta1_size = 0; + let mut meta2_size = 0; + let mut meta3_size = 0; + + let clustering = if inner.num_clusters > 1 { + let cfg = inner.cfg.clustering.as_ref().unwrap(); + + clmeta_size = tile_info.layermeta_size * cfg.max_splits; + // Maybe: (4x4 macro tiles + 1 global page)*n, 32bit each (17*4*n) + // Unused on t602x? + meta1_size = align(tile_info.meta1_blocks as usize * cfg.meta1_blocksize, 0x80); + meta2_size = align(cfg.meta2_size, 0x80); + meta3_size = align(cfg.meta3_size, 0x80); + let meta4_size = cfg.meta4_size; + + let meta_size = clmeta_size + meta1_size + meta2_size + meta3_size + meta4_size; + + mod_pr_debug!("Buffer: Allocating clustering buffers\n"); + let tilemaps = inner + .ualloc + .lock() + .array_empty_tagged(cfg.max_splits * tilemap_size, b"CTMP")?; + let meta = inner.ualloc.lock().array_empty_tagged(meta_size, b"CMTA")?; + Some(buffer::ClusterBuffers { tilemaps, meta }) + } else { + None + }; + + // Could be made strong, but we wind up with a deadlock if we try to grab the + // pointer through the inner.buffer path inside the closure. + let stats_pointer = inner.stats.weak_pointer(); + + let _gpu = &mut alloc.gpu; + + // macOS allocates this as private. However, the firmware does not + // DC CIVAC this before reading it (like it does most other things), + // which causes odd cache incoherency bugs when combined with + // speculation on the firmware side (maybe). This doesn't happen + // on macOS because these structs are a circular pool that is mapped + // already initialized. Just mark this shared for now. + let scene = alloc.shared.new_init( + try_init!(buffer::Scene::ver { + user_buffer: user_buffer, + buffer: self.clone(), + tvb_heapmeta: tvb_heapmeta, + tvb_tilemap: tvb_tilemap, + tpc: tpc, + clustering: clustering, + preempt_buf: preempt_buf, + #[ver(G >= G14X)] + control_word: _gpu.array_empty_tagged(1, b"CWRD")?, + }), + |inner, _p| { + try_init!(buffer::raw::Scene::ver { + #[ver(G >= G14X)] + control_word: inner.control_word.gpu_pointer(), + #[ver(G >= G14X)] + control_word2: inner.control_word.gpu_pointer(), + pass_page_count: AtomicU32::new(0), + unk_4: 0, + unk_8: U64(0), + unk_10: U64(0), + user_buffer: inner.user_buffer.gpu_pointer(), + unk_20: 0, + #[ver(V >= V13_3)] + unk_28: U64(0), + stats: stats_pointer, + total_page_count: AtomicU32::new(0), + #[ver(G < G14X)] + unk_30: U64(0), + #[ver(G < G14X)] + unk_38: U64(0), + }) + }, + )?; + + let mut rebind = false; + + if inner.active_slot.is_none() { + assert_eq!(inner.active_scenes, 0); + + let slot = inner.mgr.0.get_inner(inner.last_token, |inner, mgr| { + inner.owners[mgr.slot() as usize] = Some(self.clone()); + Ok(()) + })?; + rebind = slot.changed(); + + mod_pr_debug!("Buffer: assigning slot {} (rebind={})", slot.slot(), rebind); + + inner.last_token = Some(slot.token()); + inner.active_slot = Some(slot); + } + + inner.active_scenes += 1; + + Ok(Scene::ver { + object: scene, + slot: inner.active_slot.as_ref().unwrap().slot(), + rebind, + preempt2_off: inner.preempt1_size, + preempt3_off: inner.preempt1_size + inner.preempt2_size, + meta1_off: clmeta_size, + meta2_off: clmeta_size + meta1_size, + meta3_off: clmeta_size + meta1_size + meta2_size, + meta4_off: clmeta_size + meta1_size + meta2_size + meta3_size, + }) + } + + /// Increment the buffer manager usage count. Should we done once we know the Scene is ready + /// to be committed and used in commands submitted to the GPU. + pub(crate) fn increment(&self) { + let inner = self.inner.lock(); + inner.info.counter.with(|raw, _inner| { + // We could use fetch_add, but the non-LSE atomic + // sequence Rust produces confuses the hypervisor. + // We have inner locked anyway, so this is not racy. + let v = raw.count.load(Ordering::Relaxed); + raw.count.store(v + 1, Ordering::Relaxed); + }); + } + + pub(crate) fn any_ref(&self) -> Arc { + self.inner.clone() + } +} + +#[versions(AGX)] +impl Clone for Buffer::ver { + fn clone(&self) -> Self { + Buffer::ver { + inner: self.inner.clone(), + } + } +} + +#[versions(AGX)] +struct BufferSlotInner(); + +#[versions(AGX)] +impl slotalloc::SlotItem for BufferSlotInner::ver { + type Data = BufferManagerInner::ver; + + fn release(&mut self, data: &mut Self::Data, slot: u32) { + mod_pr_debug!("BufferManager: Released slot {}\n", slot); + data.owners[slot as usize] = None; + } +} + +/// Inner data for the buffer manager, to be protected by the SlotAllocator lock. +#[versions(AGX)] +pub(crate) struct BufferManagerInner { + owners: KVec>, +} + +/// The GPU-global buffer manager, used to allocate and release buffer slots from the pool. +#[versions(AGX)] +pub(crate) struct BufferManager(slotalloc::SlotAllocator); + +#[versions(AGX)] +impl BufferManager::ver { + pub(crate) fn new() -> Result { + let mut owners = KVec::new(); + for _i in 0..(NUM_BUFFERS as usize) { + owners.push(None, GFP_KERNEL)?; + } + Ok(BufferManager::ver(slotalloc::SlotAllocator::new( + NUM_BUFFERS, + BufferManagerInner::ver { owners }, + |_inner, _slot| Some(BufferSlotInner::ver()), + c_str!("BufferManager::SlotAllocator"), + static_lock_class!(), + static_lock_class!(), + )?)) + } + + /// Signals a Buffer to synchronously grow. + pub(crate) fn grow(&self, slot: u32) { + match self + .0 + .with_inner(|inner| inner.owners[slot as usize].as_ref().cloned()) + { + Some(owner) => { + pr_err!( + "BufferManager: Unexpected grow request for slot {}. This might deadlock. Please report this bug.\n", + slot + ); + owner.sync_grow(); + } + None => { + pr_err!( + "BufferManager: Received grow request for empty slot {}\n", + slot + ); + } + } + } +} + +#[versions(AGX)] +impl Clone for BufferManager::ver { + fn clone(&self) -> Self { + BufferManager::ver(self.0.clone()) + } +} diff --git a/drivers/gpu/drm/asahi/channel.rs b/drivers/gpu/drm/asahi/channel.rs new file mode 100644 index 00000000000000..30cc0efbf3ce22 --- /dev/null +++ b/drivers/gpu/drm/asahi/channel.rs @@ -0,0 +1,631 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU ring buffer channels +//! +//! The GPU firmware use a set of ring buffer channels to receive commands from the driver and send +//! it notifications and status messages. +//! +//! These ring buffers mostly follow uniform conventions, so they share the same base +//! implementation. + +use crate::debug::*; +use crate::driver::{ + AsahiDevRef, + AsahiDevice, // +}; +use crate::fw::channels::*; +use crate::fw::initdata::{ + raw, + ChannelRing, // +}; +use crate::fw::types::*; +use crate::{ + buffer, + event, + gpu, + mem, // +}; +use kernel::{ + c_str, + prelude::*, + sync::Arc, + time::{ + delay::fsleep, + Delta, + Instant, + Monotonic, // + }, +}; + +pub(crate) use crate::fw::channels::PipeType; + +/// A receive (FW->driver) channel. +pub(crate) struct RxChannel +where + for<'a> ::Raw<'a>: Debug + Default + Zeroable, +{ + ring: ChannelRing, + // FIXME: needs feature(generic_const_exprs) + //rptr: [u32; T::SUB_CHANNELS], + rptr: [u32; 6], + count: u32, +} + +impl RxChannel +where + for<'a> ::Raw<'a>: Debug + Default + Zeroable, +{ + /// Allocates a new receive channel with a given message count. + pub(crate) fn new(alloc: &mut gpu::KernelAllocators, count: usize) -> Result> { + Ok(RxChannel { + ring: ChannelRing { + state: alloc.shared.new_default()?, + ring: alloc.shared.array_empty(T::SUB_CHANNELS * count)?, + }, + rptr: Default::default(), + count: count as u32, + }) + } + + /// Receives a message on the specified sub-channel index, optionally leaving in the ring + /// buffer. + /// + /// Returns None if the channel is empty. + fn get_or_peek(&mut self, index: usize, peek: bool) -> Option { + self.ring.state.with(|raw, _inner| { + let wptr = T::wptr(raw, index); + let rptr = &mut self.rptr[index]; + if wptr == *rptr { + None + } else { + let off = self.count as usize * index; + let msg = self.ring.ring[off + *rptr as usize]; + if !peek { + *rptr = (*rptr + 1) % self.count; + T::set_rptr(raw, index, *rptr); + } + Some(msg) + } + }) + } + + /// Receives a message on the specified sub-channel index, and dequeues it from the ring buffer. + /// + /// Returns None if the channel is empty. + pub(crate) fn get(&mut self, index: usize) -> Option { + self.get_or_peek(index, false) + } + + /// Peeks a message on the specified sub-channel index, leaving it in the ring buffer. + /// + /// Returns None if the channel is empty. + pub(crate) fn peek(&mut self, index: usize) -> Option { + self.get_or_peek(index, true) + } +} + +/// A transmit (driver->FW) channel. +pub(crate) struct TxChannel +where + for<'a> ::Raw<'a>: Debug + Default + Zeroable, +{ + ring: ChannelRing, + wptr: u32, + count: u32, +} + +impl TxChannel +where + for<'a> ::Raw<'a>: Debug + Default + Zeroable, +{ + /// Allocates a new cached transmit channel with a given message count. + pub(crate) fn new(alloc: &mut gpu::KernelAllocators, count: usize) -> Result> { + Ok(TxChannel { + ring: ChannelRing { + state: alloc.shared.new_default()?, + ring: alloc.private.array_empty(count)?, + }, + wptr: 0, + count: count as u32, + }) + } + + /// Allocates a new uncached transmit channel with a given message count. + pub(crate) fn new_uncached( + alloc: &mut gpu::KernelAllocators, + count: usize, + ) -> Result> { + Ok(TxChannel { + ring: ChannelRing { + state: alloc.shared.new_default()?, + ring: alloc.shared.array_empty(count)?, + }, + wptr: 0, + count: count as u32, + }) + } + + /// Send a message to the ring, returning a cookie with the ring buffer position. + /// + /// This will poll/block if the ring is full, which we don't really expect to happen. + pub(crate) fn put(&mut self, msg: &U) -> u32 { + self.ring.state.with(|raw, _inner| { + let next_wptr = (self.wptr + 1) % self.count; + let mut rptr = T::rptr(raw); + if next_wptr == rptr { + pr_err!( + "TX ring buffer is full! Waiting... ({}, {})\n", + next_wptr, + rptr + ); + // TODO: block properly on incoming messages? + while next_wptr == rptr { + fsleep(Delta::from_millis(8)); + rptr = T::rptr(raw); + } + } + self.ring.ring[self.wptr as usize] = *msg; + mem::sync(); + T::set_wptr(raw, next_wptr); + self.wptr = next_wptr; + }); + self.wptr + } + + /// Wait for a previously submitted message to be popped off of the ring by the GPU firmware. + /// + /// This busy-loops, and is intended to be used for rare cases when we need to block for + /// completion of a cache management or invalidation operation synchronously (which + /// the firmware normally completes fast enough not to be worth sleeping for). + /// If the poll takes longer than 10ms, this switches to sleeping between polls. + pub(crate) fn wait_for(&mut self, wptr: u32, timeout_ms: i64) -> Result { + const MAX_FAST_POLL: i64 = 10; + let start = Instant::::now(); + let timeout_ms = timeout_ms.max(1); + let timeout_fast = Delta::from_millis(timeout_ms.min(MAX_FAST_POLL)); + let timeout_slow = Delta::from_millis(timeout_ms); + self.ring.state.with(|raw, _inner| { + while start.elapsed() < timeout_fast { + if T::rptr(raw) == wptr { + return Ok(()); + } + mem::sync(); + } + while start.elapsed() < timeout_slow { + if T::rptr(raw) == wptr { + return Ok(()); + } + fsleep(Delta::from_millis(5)); + mem::sync(); + } + Err(ETIMEDOUT) + }) + } +} + +/// Device Control channel for global device management commands. +#[versions(AGX)] +pub(crate) struct DeviceControlChannel { + dev: AsahiDevRef, + ch: TxChannel, +} + +#[versions(AGX)] +impl DeviceControlChannel::ver { + const COMMAND_TIMEOUT_MS: i64 = 1000; + + /// Allocate a new Device Control channel. + pub(crate) fn new( + dev: &AsahiDevice, + alloc: &mut gpu::KernelAllocators, + ) -> Result { + Ok(DeviceControlChannel::ver { + dev: dev.into(), + ch: TxChannel::::new(alloc, 0x100)?, + }) + } + + /// Returns the raw `ChannelRing` structure to pass to firmware. + pub(crate) fn to_raw(&self) -> raw::ChannelRing { + self.ch.ring.to_raw() + } + + /// Submits a Device Control command. + pub(crate) fn send(&mut self, msg: &DeviceControlMsg::ver) -> u32 { + cls_dev_dbg!(DeviceControlCh, self.dev, "DeviceControl: {:?}\n", msg); + self.ch.put(msg) + } + + /// Waits for a previously submitted Device Control command to complete. + pub(crate) fn wait_for(&mut self, wptr: u32) -> Result { + self.ch.wait_for(wptr, Self::COMMAND_TIMEOUT_MS) + } +} + +/// Pipe channel to submit WorkQueue execution requests. +#[versions(AGX)] +pub(crate) struct PipeChannel { + dev: AsahiDevRef, + ch: TxChannel, +} + +#[versions(AGX)] +impl PipeChannel::ver { + /// Allocate a new Pipe submission channel. + pub(crate) fn new( + dev: &AsahiDevice, + alloc: &mut gpu::KernelAllocators, + ) -> Result { + Ok(PipeChannel::ver { + dev: dev.into(), + ch: TxChannel::::new(alloc, 0x100)?, + }) + } + + /// Returns the raw `ChannelRing` structure to pass to firmware. + pub(crate) fn to_raw(&self) -> raw::ChannelRing { + self.ch.ring.to_raw() + } + + /// Submits a Pipe kick command to the firmware. + pub(crate) fn send(&mut self, msg: &PipeMsg::ver) { + cls_dev_dbg!(PipeCh, self.dev, "Pipe: {:?}\n", msg); + self.ch.put(msg); + } +} + +/// Firmware Control channel, used for secure cache flush requests. +pub(crate) struct FwCtlChannel { + dev: AsahiDevRef, + ch: TxChannel, +} + +impl FwCtlChannel { + const COMMAND_TIMEOUT_MS: i64 = 1000; + + /// Allocate a new Firmware Control channel. + pub(crate) fn new( + dev: &AsahiDevice, + alloc: &mut gpu::KernelAllocators, + ) -> Result { + Ok(FwCtlChannel { + dev: dev.into(), + ch: TxChannel::::new_uncached(alloc, 0x100)?, + }) + } + + /// Returns the raw `ChannelRing` structure to pass to firmware. + pub(crate) fn to_raw(&self) -> raw::ChannelRing { + self.ch.ring.to_raw() + } + + /// Submits a Firmware Control command to the firmware. + pub(crate) fn send(&mut self, msg: &FwCtlMsg) -> u32 { + cls_dev_dbg!(FwCtlCh, self.dev, "FwCtl: {:?}\n", msg); + self.ch.put(msg) + } + + /// Waits for a previously submitted Firmware Control command to complete. + pub(crate) fn wait_for(&mut self, wptr: u32) -> Result { + self.ch.wait_for(wptr, Self::COMMAND_TIMEOUT_MS) + } +} + +/// Event channel, used to notify the driver of command completions, GPU faults and errors, and +/// other events. +#[versions(AGX)] +pub(crate) struct EventChannel { + dev: AsahiDevRef, + ch: RxChannel, + ev_mgr: Arc, + buf_mgr: buffer::BufferManager::ver, + gpu: Option>, +} + +#[versions(AGX)] +impl EventChannel::ver { + /// Allocate a new Event channel. + pub(crate) fn new( + dev: &AsahiDevice, + alloc: &mut gpu::KernelAllocators, + ev_mgr: Arc, + buf_mgr: buffer::BufferManager::ver, + ) -> Result { + Ok(EventChannel::ver { + dev: dev.into(), + ch: RxChannel::::new(alloc, 0x100)?, + ev_mgr, + buf_mgr, + gpu: None, + }) + } + + /// Registers the managing `Gpu` instance that will handle events on this channel. + pub(crate) fn set_manager(&mut self, gpu: Arc) { + self.gpu = Some(gpu); + } + + /// Returns the raw `ChannelRing` structure to pass to firmware. + pub(crate) fn to_raw(&self) -> raw::ChannelRing { + self.ch.ring.to_raw() + } + + /// Polls for new Event messages on this ring. + pub(crate) fn poll(&mut self) { + while let Some(msg) = self.ch.get(0) { + // SAFETY: The raw view is always valid for all bit patterns. + let tag = unsafe { msg.raw.0 }; + match tag { + 0..=EVENT_MAX => { + // SAFETY: Since we have checked the tag to be in range, + // accessing the enum view is valid. + let msg = unsafe { msg.msg }; + + cls_dev_dbg!(EventCh, self.dev, "Event: {:?}\n", msg); + match msg { + EventMsg::Fault => match self.gpu.as_ref() { + Some(gpu) => gpu.handle_fault(), + None => { + dev_crit!( + self.dev.as_ref(), + "EventChannel: No GPU manager available!\n" + ) + } + }, + EventMsg::Timeout { + counter, + unk_8, + event_slot, + } => match self.gpu.as_ref() { + Some(gpu) => gpu.handle_timeout(counter, event_slot, unk_8), + None => { + dev_crit!( + self.dev.as_ref(), + "EventChannel: No GPU manager available!\n" + ) + } + }, + EventMsg::Flag { firing, .. } => { + for (i, flags) in firing.iter().enumerate() { + for j in 0..32 { + if flags & (1u32 << j) != 0 { + self.ev_mgr.signal((i * 32 + j) as u32); + } + } + } + } + EventMsg::GrowTVB { + vm_slot, + buffer_slot, + counter, + } => match self.gpu.as_ref() { + Some(gpu) => { + self.buf_mgr.grow(buffer_slot); + gpu.ack_grow(buffer_slot, vm_slot, counter); + } + None => { + dev_crit!( + self.dev.as_ref(), + "EventChannel: No GPU manager available!\n" + ) + } + }, + EventMsg::ChannelError { + error_type, + pipe_type, + event_slot, + event_value, + } => match self.gpu.as_ref() { + Some(gpu) => { + let error_type = match error_type { + 0 => ChannelErrorType::MemoryError, + 1 => ChannelErrorType::DMKill, + 2 => ChannelErrorType::Aborted, + 3 => ChannelErrorType::Unk3, + a => ChannelErrorType::Unknown(a), + }; + gpu.handle_channel_error( + error_type, + pipe_type, + event_slot, + event_value, + ); + } + None => { + dev_crit!( + self.dev.as_ref(), + "EventChannel: No GPU manager available!\n" + ) + } + }, + msg => { + dev_crit!(self.dev.as_ref(), "Unknown event message: {:?}\n", msg); + } + } + } + _ => { + // SAFETY: The raw view is always valid for all bit patterns. + dev_warn!(self.dev.as_ref(), "Unknown event message: {:?}\n", unsafe { + msg.raw + }); + } + } + } + } +} + +/// Firmware Log channel. This one is pretty special, since it has 6 sub-channels (for different log +/// levels), and it also uses a side buffer to actually hold the log messages, only passing around +/// pointers in the main buffer. +pub(crate) struct FwLogChannel { + dev: AsahiDevRef, + ch: RxChannel, + payload_buf: GpuArray, +} + +impl FwLogChannel { + const RING_SIZE: usize = 0x100; + const BUF_SIZE: usize = 0x100; + + /// Allocate a new Firmware Log channel. + pub(crate) fn new( + dev: &AsahiDevice, + alloc: &mut gpu::KernelAllocators, + ) -> Result { + Ok(FwLogChannel { + dev: dev.into(), + ch: RxChannel::::new(alloc, Self::RING_SIZE)?, + payload_buf: alloc + .shared + .array_empty(Self::BUF_SIZE * FwLogChannelState::SUB_CHANNELS)?, + }) + } + + /// Returns the raw `ChannelRing` structure to pass to firmware. + pub(crate) fn to_raw(&self) -> raw::ChannelRing { + self.ch.ring.to_raw() + } + + /// Returns the GPU pointers to the firmware log payload buffer. + pub(crate) fn get_buf(&self) -> GpuWeakPointer<[RawFwLogPayloadMsg]> { + self.payload_buf.weak_pointer() + } + + /// Polls for new log messages on all sub-rings. + pub(crate) fn poll(&mut self) { + for i in 0..=FwLogChannelState::SUB_CHANNELS - 1 { + while let Some(msg) = self.ch.peek(i) { + cls_dev_dbg!(FwLogCh, self.dev, "FwLog{}: {:?}\n", i, msg); + if msg.msg_type != 2 { + dev_warn!(self.dev.as_ref(), "Unknown FWLog{} message: {:?}\n", i, msg); + self.ch.get(i); + continue; + } + if msg.msg_index.0 as usize >= Self::BUF_SIZE { + dev_warn!( + self.dev.as_ref(), + "FWLog{} message index out of bounds: {:?}\n", + i, + msg + ); + self.ch.get(i); + continue; + } + let index = Self::BUF_SIZE * i + msg.msg_index.0 as usize; + let payload = &self.payload_buf.as_slice()[index]; + if payload.msg_type != 3 { + dev_warn!( + self.dev.as_ref(), + "Unknown FWLog{} payload: {:?}\n", + i, + payload + ); + self.ch.get(i); + continue; + } + let msg = if let Some(end) = payload.msg.iter().position(|&r| r == 0) { + CStr::from_bytes_with_nul(&(*payload.msg)[..end + 1]) + .unwrap_or(c_str!("cstr_err")) + } else { + dev_warn!( + self.dev.as_ref(), + "FWLog{} payload not NUL-terminated: {:?}\n", + i, + payload + ); + self.ch.get(i); + continue; + }; + match i { + 0 => dev_dbg!(self.dev.as_ref(), "FWLog: {}\n", msg), + 1 => dev_info!(self.dev.as_ref(), "FWLog: {}\n", msg), + 2 => dev_notice!(self.dev.as_ref(), "FWLog: {}\n", msg), + 3 => dev_warn!(self.dev.as_ref(), "FWLog: {}\n", msg), + 4 => dev_err!(self.dev.as_ref(), "FWLog: {}\n", msg), + 5 => dev_crit!(self.dev.as_ref(), "FWLog: {}\n", msg), + _ => (), + }; + self.ch.get(i); + } + } + } +} + +pub(crate) struct KTraceChannel { + dev: AsahiDevRef, + ch: RxChannel, +} + +/// KTrace channel, used to receive detailed execution trace markers from the firmware. +/// We currently disable this in initdata, so no messages are expected here at this time. +impl KTraceChannel { + /// Allocate a new KTrace channel. + pub(crate) fn new( + dev: &AsahiDevice, + alloc: &mut gpu::KernelAllocators, + ) -> Result { + Ok(KTraceChannel { + dev: dev.into(), + ch: RxChannel::::new(alloc, 0x200)?, + }) + } + + /// Returns the raw `ChannelRing` structure to pass to firmware. + pub(crate) fn to_raw(&self) -> raw::ChannelRing { + self.ch.ring.to_raw() + } + + /// Polls for new KTrace messages on this ring. + pub(crate) fn poll(&mut self) { + while let Some(msg) = self.ch.get(0) { + cls_dev_dbg!(KTraceCh, self.dev, "KTrace: {:?}\n", msg); + } + } +} + +/// Statistics channel, reporting power-related statistics to the driver. +/// Not really implemented other than debug logs yet... +#[versions(AGX)] +pub(crate) struct StatsChannel { + dev: AsahiDevRef, + ch: RxChannel, +} + +#[versions(AGX)] +impl StatsChannel::ver { + /// Allocate a new Statistics channel. + pub(crate) fn new( + dev: &AsahiDevice, + alloc: &mut gpu::KernelAllocators, + ) -> Result { + Ok(StatsChannel::ver { + dev: dev.into(), + ch: RxChannel::::new(alloc, 0x100)?, + }) + } + + /// Returns the raw `ChannelRing` structure to pass to firmware. + pub(crate) fn to_raw(&self) -> raw::ChannelRing { + self.ch.ring.to_raw() + } + + /// Polls for new statistics messages on this ring. + pub(crate) fn poll(&mut self) { + while let Some(msg) = self.ch.get(0) { + // SAFETY: The raw view is always valid for all bit patterns. + let tag = unsafe { msg.raw.0 }; + match tag { + 0..=STATS_MAX::ver => { + // SAFETY: Since we have checked the tag to be in range, + // accessing the enum view is valid. + let msg = unsafe { msg.msg }; + cls_dev_dbg!(StatsCh, self.dev, "Stats: {:?}\n", msg); + } + _ => { + // SAFETY: The raw view is always valid for all bit patterns. + pr_warn!("Unknown stats message: {:?}\n", unsafe { msg.raw }); + } + } + } + } +} diff --git a/drivers/gpu/drm/asahi/crashdump.rs b/drivers/gpu/drm/asahi/crashdump.rs new file mode 100644 index 00000000000000..bd9f2f1649584f --- /dev/null +++ b/drivers/gpu/drm/asahi/crashdump.rs @@ -0,0 +1,305 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU crash dump formatter +//! +//! Takes a raw dump of firmware/kernel mapped pages from `pgtable` and formats it into +//! an ELF core dump suitable for dumping into userspace. + +use core::mem::size_of; + +use kernel::{ + devcoredump::DevCoreDump, + error::Result, + page::{Page, PAGE_MASK, PAGE_SHIFT, PAGE_SIZE}, + prelude::*, + types::Owned, + uapi, +}; + +use crate::hw; +use crate::pgtable::{self, DumpedPage, Prot, UAT_PGSZ}; +use crate::util::align; + +pub(crate) struct CrashDump { + headers: KVVec, + pages: KVVec>, +} + +const NOTE_NAME_AGX: &str = "AGX"; +const NOTE_AGX_DUMP_INFO: u32 = 1; + +const NOTE_NAME_RTKIT: &str = "RTKIT"; +const NOTE_RTKIT_CRASHLOG: u32 = 1; + +#[repr(C)] +pub(crate) struct AGXDumpInfo { + initdata_address: u64, + chip_id: u32, + gpu_gen: hw::GpuGen, + gpu_variant: hw::GpuVariant, + gpu_rev: hw::GpuRevision, + total_active_cores: u32, + firmware_version: [u32; 6], +} + +struct ELFNote { + name: &'static str, + ty: u32, + data: KVVec, +} + +pub(crate) struct CrashDumpBuilder { + page_dump: KVVec, + notes: KVec, +} + +/// Helper to convert ELF headers into byte slices +/// TODO: Hook this up into kernel::AsBytes somehow +/// +/// # Safety +/// +/// Types implementing this trait must have no padding bytes. +unsafe trait AsBytes: Sized { + fn as_bytes(&self) -> &[u8] { + // SAFETY: This trait is only implemented for types with no padding bytes + unsafe { core::slice::from_raw_parts(self as *const _ as *const u8, size_of::()) } + } + fn slice_as_bytes(slice: &[Self]) -> &[u8] { + // SAFETY: This trait is only implemented for types with no padding bytes + unsafe { + core::slice::from_raw_parts(slice.as_ptr() as *const u8, core::mem::size_of_val(slice)) + } + } +} + +// SAFETY: This type has no padding +unsafe impl AsBytes for uapi::Elf64_Ehdr {} +// SAFETY: This type has no padding +unsafe impl AsBytes for uapi::Elf64_Phdr {} +// SAFETY: This type has no padding +unsafe impl AsBytes for uapi::Elf64_Nhdr {} +// SAFETY: This type has no padding +unsafe impl AsBytes for AGXDumpInfo {} + +const FIRMWARE_ENTRYPOINT: u64 = 0xFFFFFF8000000000u64; + +impl CrashDumpBuilder { + pub(crate) fn new(page_dump: KVVec) -> Result { + Ok(CrashDumpBuilder { + page_dump, + notes: KVec::new(), + }) + } + + pub(crate) fn add_agx_info( + &mut self, + cfg: &hw::HwConfig, + dyncfg: &hw::DynConfig, + initdata_address: u64, + ) -> Result { + let mut info = AGXDumpInfo { + chip_id: cfg.chip_id, + gpu_gen: dyncfg.id.gpu_gen, + gpu_variant: dyncfg.id.gpu_variant, + gpu_rev: dyncfg.id.gpu_rev, + total_active_cores: dyncfg.id.total_active_cores, + firmware_version: [0; 6], + initdata_address, + }; + info.firmware_version[..dyncfg.firmware_version.len().min(6)] + .copy_from_slice(&dyncfg.firmware_version); + + let mut data = KVVec::new(); + data.extend_from_slice(info.as_bytes(), GFP_KERNEL)?; + + self.notes.push( + ELFNote { + name: NOTE_NAME_AGX, + ty: NOTE_AGX_DUMP_INFO, + data, + }, + GFP_KERNEL, + )?; + Ok(()) + } + + pub(crate) fn add_crashlog(&mut self, crashlog: &[u8]) -> Result { + let mut data = KVVec::new(); + data.extend_from_slice(crashlog, GFP_KERNEL)?; + + self.notes.push( + ELFNote { + name: NOTE_NAME_RTKIT, + ty: NOTE_RTKIT_CRASHLOG, + data, + }, + GFP_KERNEL, + )?; + + Ok(()) + } + + pub(crate) fn finalize(self) -> Result { + let CrashDumpBuilder { page_dump, notes } = self; + + let mut ehdr: uapi::Elf64_Ehdr = Default::default(); + + ehdr.e_ident[uapi::EI_MAG0 as usize..=uapi::EI_MAG3 as usize].copy_from_slice(b"\x7fELF"); + ehdr.e_ident[uapi::EI_CLASS as usize] = uapi::ELFCLASS64 as u8; + ehdr.e_ident[uapi::EI_DATA as usize] = uapi::ELFDATA2LSB as u8; + ehdr.e_ident[uapi::EI_VERSION as usize] = uapi::EV_CURRENT as u8; + ehdr.e_type = uapi::ET_CORE as u16; + ehdr.e_machine = uapi::EM_AARCH64 as u16; + ehdr.e_version = uapi::EV_CURRENT; + ehdr.e_entry = FIRMWARE_ENTRYPOINT; + ehdr.e_ehsize = core::mem::size_of::() as u16; + ehdr.e_phentsize = core::mem::size_of::() as u16; + + let phdr_offset = core::mem::size_of::(); + + // PHDRs come after the ELF header + ehdr.e_phoff = phdr_offset as u64; + + let mut phdrs = KVVec::new(); + + // First PHDR is the NOTE section + phdrs.push( + uapi::Elf64_Phdr { + p_type: uapi::PT_NOTE, + p_flags: uapi::PF_R, + p_align: 1, + ..Default::default() + }, + GFP_KERNEL, + )?; + + // Generate the page phdrs. The offset will be fixed up later. + let mut off: usize = 0; + let mut next = None; + let mut pages: KVVec> = KVVec::new(); + + for mut page in page_dump { + let vaddr = page.iova; + let paddr = page.pte & pgtable::PTE_ADDR_BITS; + let flags = Prot::from_pte(page.pte).elf_flags(); + let valid = page.data.is_some(); + let cur = (vaddr, paddr, flags, valid); + if Some(cur) != next { + phdrs.push( + uapi::Elf64_Phdr { + p_type: uapi::PT_LOAD, + p_offset: if valid { off as u64 } else { 0 }, + p_vaddr: vaddr, + p_paddr: paddr, + p_filesz: if valid { UAT_PGSZ as u64 } else { 0 }, + p_memsz: UAT_PGSZ as u64, + p_flags: flags, + p_align: UAT_PGSZ as u64, + }, + GFP_KERNEL, + )?; + if valid { + off += UAT_PGSZ; + } + } else { + let ph = phdrs.last_mut().unwrap(); + ph.p_memsz += UAT_PGSZ as u64; + if valid { + ph.p_filesz += UAT_PGSZ as u64; + off += UAT_PGSZ; + } + } + if let Some(data_page) = page.data.take() { + pages.push(data_page, GFP_KERNEL)?; + } + next = Some(( + vaddr + UAT_PGSZ as u64, + paddr + UAT_PGSZ as u64, + flags, + valid, + )); + } + + ehdr.e_phnum = phdrs.len() as u16; + + let note_offset = phdr_offset + size_of::() * phdrs.len(); + + let mut note_data: KVVec = KVVec::new(); + + for note in notes { + let hdr = uapi::Elf64_Nhdr { + n_namesz: note.name.len() as u32 + 1, + n_descsz: note.data.len() as u32, + n_type: note.ty, + }; + note_data.extend_from_slice(hdr.as_bytes(), GFP_KERNEL)?; + note_data.extend_from_slice(note.name.as_bytes(), GFP_KERNEL)?; + note_data.push(0, GFP_KERNEL)?; + while note_data.len() & 3 != 0 { + note_data.push(0, GFP_KERNEL)?; + } + note_data.extend_from_slice(¬e.data, GFP_KERNEL)?; + while note_data.len() & 3 != 0 { + note_data.push(0, GFP_KERNEL)?; + } + } + + // NOTE section comes after the PHDRs + phdrs[0].p_offset = note_offset as u64; + phdrs[0].p_filesz = note_data.len() as u64; + + // Align data section to the page size + let data_offset = align(note_offset + note_data.len(), UAT_PGSZ); + + // Fix up data PHDR offsets + for phdr in &mut phdrs[1..] { + phdr.p_offset += data_offset as u64; + } + + // Build ELF header buffer + let mut headers: KVVec = KVVec::from_elem(0, data_offset, GFP_KERNEL)?; + + headers[0..size_of::()].copy_from_slice(ehdr.as_bytes()); + headers[phdr_offset..phdr_offset + phdrs.len() * size_of::()] + .copy_from_slice(AsBytes::slice_as_bytes(&phdrs)); + headers[note_offset..note_offset + note_data.len()].copy_from_slice(¬e_data); + + Ok(CrashDump { headers, pages }) + } +} + +impl DevCoreDump for CrashDump { + fn read(&self, buf: &mut [u8], mut offset: usize) -> Result { + let mut read = 0; + let mut left = buf.len(); + if offset < self.headers.len() { + let block = left.min(self.headers.len() - offset); + buf[..block].copy_from_slice(&self.headers[offset..offset + block]); + read += block; + offset += block; + left -= block; + } + if left == 0 { + return Ok(read); + } + offset -= self.headers.len(); // Offset from the page area + + while left > 0 { + let page_index = offset >> PAGE_SHIFT; + let page_offset = offset & !PAGE_MASK; + let block = left.min(PAGE_SIZE - page_offset); + let Some(page) = self.pages.get(page_index) else { + break; + }; + let slice = &mut buf[read..read + block]; + // SAFETY: We own the page, and the slice guarantees the + // dst length is sufficient. + unsafe { page.read_raw(slice.as_mut_ptr(), page_offset, slice.len())? }; + read += block; + offset += block; + left -= block; + } + + Ok(read) + } +} diff --git a/drivers/gpu/drm/asahi/debug.rs b/drivers/gpu/drm/asahi/debug.rs new file mode 100644 index 00000000000000..50628ade5ab8e4 --- /dev/null +++ b/drivers/gpu/drm/asahi/debug.rs @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +#![allow(dead_code)] + +//! Debug enable/disable flags and convenience macros + +#[allow(unused_imports)] +pub(crate) use super::{ + cls_dev_dbg, + cls_pr_debug, + debug, + mod_dev_dbg, + mod_pr_debug, // +}; +use crate::module_parameters; +use core::sync::atomic::{ + AtomicU64, + Ordering, // +}; + +static DEBUG_FLAGS: AtomicU64 = AtomicU64::new(0); + +/// Debug flag bit indices +pub(crate) enum DebugFlags { + // 0-4: Memory-related debug + Mmu = 0, + PgTable = 1, + Alloc = 2, + Gem = 3, + Object = 4, + + // 5-7: Firmware objects and resources + Event = 5, + Buffer = 6, + WorkQueue = 7, + + // 8-13: DRM interface, rendering, compute, GPU globals + Gpu = 8, + File = 9, + Queue = 10, + Render = 11, + Compute = 12, + Errors = 13, + + // 14-15: Misc stats + MemStats = 14, + TVBStats = 15, + + // 16-22: Channels + FwLogCh = 16, + KTraceCh = 17, + StatsCh = 18, + EventCh = 19, + PipeCh = 20, + DeviceControlCh = 21, + FwCtlCh = 22, + + // 32-35: Allocator debugging + FillAllocations = 32, + DebugAllocations = 33, + DetectOverflows = 34, + ForceCPUMaps = 35, + + // 36-: Behavior flags + ConservativeTlbi = 36, + KeepGpuPowered = 37, + WaitForPowerOff = 38, + NoGpuRecovery = 39, + DisableClustering = 40, + + // 48-: Misc + Debug0 = 48, + Debug1 = 49, + Debug2 = 50, + Debug3 = 51, + Debug4 = 52, + Debug5 = 53, + Debug6 = 54, + Debug7 = 55, + + VerboseFaults = 61, + AllowUnknownOverrides = 62, + OopsOnGpuCrash = 63, +} + +/// Update the cached global debug flags from the module parameter +pub(crate) fn update_debug_flags() { + let flags = *module_parameters::debug_flags.value(); + + DEBUG_FLAGS.store(flags, Ordering::Relaxed); +} + +/// Check whether debug is enabled for a given flag +#[inline(always)] +pub(crate) fn debug_enabled(flag: DebugFlags) -> bool { + DEBUG_FLAGS.load(Ordering::Relaxed) & 1 << (flag as usize) != 0 +} + +/// Run some code only if debug is enabled for the calling module +#[macro_export] +macro_rules! debug { + ($($arg:tt)*) => { + if $crate::debug::debug_enabled(DEBUG_CLASS) { + $($arg)* + } + }; +} + +/// pr_info!() if debug is enabled for the calling module +#[macro_export] +macro_rules! mod_pr_debug ( + ($($arg:tt)*) => ( + $crate::debug! { ::kernel::pr_info! ( $($arg)* ); } + ) +); + +/// dev_info!() if debug is enabled for the calling module +#[macro_export] +macro_rules! mod_dev_dbg ( + ($dev:expr, $($arg:tt)*) => ( + $crate::debug! { ::kernel::dev_info! ( $dev.as_ref(), $($arg)* ); } + ) +); + +/// pr_info!() if debug is enabled for a specific module +#[macro_export] +macro_rules! cls_pr_debug ( + ($cls:ident, $($arg:tt)*) => ( + if $crate::debug::debug_enabled($crate::debug::DebugFlags::$cls) { + ::kernel::pr_info! ( $($arg)* ); + } + ) +); + +/// dev_info!() if debug is enabled for a specific module +#[macro_export] +macro_rules! cls_dev_dbg ( + ($cls:ident, $dev:expr, $($arg:tt)*) => ( + if $crate::debug::debug_enabled($crate::debug::DebugFlags::$cls) { + ::kernel::dev_info! ( $dev.as_ref(), $($arg)* ); + } + ) +); diff --git a/drivers/gpu/drm/asahi/driver.rs b/drivers/gpu/drm/asahi/driver.rs new file mode 100644 index 00000000000000..7f407bfad44d24 --- /dev/null +++ b/drivers/gpu/drm/asahi/driver.rs @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Top-level GPU driver implementation. + +use kernel::{ + c_str, + device::Core, + dma::{ + Device, + DmaMask, // + }, + drm, + drm::ioctl, + error::Result, + of, + platform, + prelude::*, + sync::Arc, // +}; + +use crate::{ + debug, + file, + gem::AsahiObject, + gpu, + hw, + regs, // +}; + +use kernel::macros::vtable; +use kernel::types::ARef; + +/// Holds a reference to the top-level `GpuManager` object. +#[pin_data] +pub(crate) struct AsahiData { + #[pin] + pub(crate) gpu: Arc, + pub(crate) pdev: ARef, + pub(crate) resources: regs::Resources, +} + +unsafe impl Send for AsahiData {} +unsafe impl Sync for AsahiData {} + +pub(crate) struct AsahiDriver { + #[expect(unused)] + drm: ARef>, +} + +unsafe impl Send for AsahiDriver {} +unsafe impl Sync for AsahiDriver {} + +/// Convenience type alias for the DRM device type for this driver. +pub(crate) type AsahiDevice = drm::device::Device; +pub(crate) type AsahiDevRef = ARef; + +/// DRM Driver metadata +const INFO: drm::driver::DriverInfo = drm::driver::DriverInfo { + major: 0, + minor: 0, + patchlevel: 0, + name: c_str!("asahi"), + desc: c_str!("Apple AGX Graphics"), +}; + +/// DRM Driver implementation for `AsahiDriver`. +#[vtable] +impl drm::driver::Driver for AsahiDriver { + /// Our `DeviceData` type, reference-counted + type Data = AsahiData; + /// Our `File` type. + type File = file::File; + /// Our `Object` type. + type Object = drm::gem::shmem::Object; + + const INFO: drm::driver::DriverInfo = INFO; + const FEATURES: u32 = drm::driver::FEAT_GEM + | drm::driver::FEAT_RENDER + | drm::driver::FEAT_SYNCOBJ + | drm::driver::FEAT_SYNCOBJ_TIMELINE + | drm::driver::FEAT_GEM_GPUVA; + + kernel::declare_drm_ioctls! { + (ASAHI_GET_PARAMS, drm_asahi_get_params, + ioctl::RENDER_ALLOW, crate::file::File::get_params), + (ASAHI_GET_TIME, drm_asahi_get_time, + ioctl::AUTH | ioctl::RENDER_ALLOW, crate::file::File::get_time), + (ASAHI_VM_CREATE, drm_asahi_vm_create, + ioctl::AUTH | ioctl::RENDER_ALLOW, crate::file::File::vm_create), + (ASAHI_VM_DESTROY, drm_asahi_vm_destroy, + ioctl::AUTH | ioctl::RENDER_ALLOW, crate::file::File::vm_destroy), + (ASAHI_VM_BIND, drm_asahi_vm_bind, + ioctl::AUTH | ioctl::RENDER_ALLOW, crate::file::File::vm_bind), + (ASAHI_GEM_CREATE, drm_asahi_gem_create, + ioctl::AUTH | ioctl::RENDER_ALLOW, crate::file::File::gem_create), + (ASAHI_GEM_MMAP_OFFSET, drm_asahi_gem_mmap_offset, + ioctl::AUTH | ioctl::RENDER_ALLOW, crate::file::File::gem_mmap_offset), + (ASAHI_GEM_BIND_OBJECT, drm_asahi_gem_bind_object, + ioctl::AUTH | ioctl::RENDER_ALLOW, crate::file::File::gem_bind_object), + (ASAHI_QUEUE_CREATE, drm_asahi_queue_create, + ioctl::AUTH | ioctl::RENDER_ALLOW, crate::file::File::queue_create), + (ASAHI_QUEUE_DESTROY, drm_asahi_queue_destroy, + ioctl::AUTH | ioctl::RENDER_ALLOW, crate::file::File::queue_destroy), + (ASAHI_SUBMIT, drm_asahi_submit, + ioctl::AUTH | ioctl::RENDER_ALLOW, crate::file::File::submit), + } +} + +// OF Device ID table.s +kernel::of_device_table!( + OF_TABLE, + MODULE_OF_TABLE, + ::IdInfo, + [ + ( + of::DeviceId::new(c_str!("apple,agx-t8103")), + &hw::t8103::HWCONFIG + ), + ( + of::DeviceId::new(c_str!("apple,agx-t8112")), + &hw::t8112::HWCONFIG + ), + ( + of::DeviceId::new(c_str!("apple,agx-t6000")), + &hw::t600x::HWCONFIG_T6000 + ), + ( + of::DeviceId::new(c_str!("apple,agx-t6001")), + &hw::t600x::HWCONFIG_T6001 + ), + ( + of::DeviceId::new(c_str!("apple,agx-t6002")), + &hw::t600x::HWCONFIG_T6002 + ), + ( + of::DeviceId::new(c_str!("apple,agx-t6020")), + &hw::t602x::HWCONFIG_T6020 + ), + ( + of::DeviceId::new(c_str!("apple,agx-t6021")), + &hw::t602x::HWCONFIG_T6021 + ), + ( + of::DeviceId::new(c_str!("apple,agx-t6022")), + &hw::t602x::HWCONFIG_T6022 + ), + ] +); + +/// Platform Driver implementation for `AsahiDriver`. +impl platform::Driver for AsahiDriver { + type IdInfo = &'static hw::HwConfig; + const OF_ID_TABLE: Option> = Some(&OF_TABLE); + + /// Device probe function. + fn probe( + pdev: &platform::Device, + info: Option<&Self::IdInfo>, + ) -> Result>> { + debug::update_debug_flags(); + + dev_info!(pdev.as_ref(), "Probing...\n"); + + let cfg = info.ok_or(ENODEV)?; + + unsafe { pdev.dma_set_mask_and_coherent(DmaMask::try_new(cfg.uat_oas)?)? }; + + let res = regs::Resources::new(pdev)?; + + // Initialize misc MMIO + res.init_mmio()?; + + // Start the coprocessor CPU, so UAT can initialize the handoff + regs::Resources::start_cpu(pdev)?; + + let fwnode = pdev.as_ref().fwnode().ok_or(EIO)?; + let compat: KVec = fwnode + .property_read_array_vec(c_str!("apple,firmware-compat"), 3)? + .required_by(pdev.as_ref())?; + + // TODO: This is very temporary + // SAFETY: This should be safe as data is not touched by the driver + // untill it gets fully initialised. + // Additionally drm::device::Device::release() will not drop data and + // leaks instead. + let uninit = unsafe { + pin_init::pin_init_from_closure::(|_slot| Ok(())) + }; + let drm: ARef = drm::device::Device::new(pdev.as_ref(), uninit)?; + + let gpu = match (cfg.gpu_gen, cfg.gpu_variant, compat.as_slice()) { + (hw::GpuGen::G13, _, &[12, 3, 0]) => { + gpu::GpuManagerG13V12_3::new(&drm.clone(), &res, cfg)? as Arc + } + (hw::GpuGen::G14, hw::GpuVariant::G, &[12, 4, 0]) => { + gpu::GpuManagerG14V12_4::new(&drm.clone(), &res, cfg)? as Arc + } + (hw::GpuGen::G13, _, &[13, 5, 0]) => { + gpu::GpuManagerG13V13_5::new(&drm.clone(), &res, cfg)? as Arc + } + (hw::GpuGen::G14, hw::GpuVariant::G, &[13, 5, 0]) => { + gpu::GpuManagerG14V13_5::new(&drm.clone(), &res, cfg)? as Arc + } + (hw::GpuGen::G14, _, &[13, 5, 0]) => { + gpu::GpuManagerG14XV13_5::new(&drm.clone(), &res, cfg)? as Arc + } + _ => { + dev_info!( + pdev.as_ref(), + "Unsupported GPU/firmware combination ({:?}, {:?}, {:?})\n", + cfg.gpu_gen, + cfg.gpu_variant, + compat + ); + return Err(ENODEV); + } + }; + + let data = try_pin_init!(AsahiData { + gpu, + pdev: pdev.into(), + resources: res, + }); + + let ptr: *const AsahiData = &raw const **drm; + unsafe { data.__pinned_init(ptr as *mut AsahiData)?; } + + (*drm).gpu.init()?; + + drm::driver::Registration::new_foreign_owned(&drm, pdev.as_ref(), 0)?; + + Ok(KBox::new(Self { drm }, GFP_KERNEL)?.into()) + } +} diff --git a/drivers/gpu/drm/asahi/event.rs b/drivers/gpu/drm/asahi/event.rs new file mode 100644 index 00000000000000..edd7d701e665cd --- /dev/null +++ b/drivers/gpu/drm/asahi/event.rs @@ -0,0 +1,257 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU event manager +//! +//! The GPU firmware manages work completion by using event objects (Apple calls them "stamps"), +//! which are monotonically incrementing counters. There are a fixed number of objects, and +//! they are managed with a `SlotAllocator`. +//! +//! This module manages the set of available events and lets users compute expected values. +//! It also manages signaling owners when the GPU firmware reports that an event fired. + +use crate::debug::*; +use crate::fw::types::*; +use crate::{ + gpu, + slotalloc, + workqueue, // +}; +use core::cmp; +use core::sync::atomic::Ordering; +use kernel::prelude::*; +use kernel::sync::Arc; +use kernel::{ + c_str, + static_lock_class, // +}; + +const DEBUG_CLASS: DebugFlags = DebugFlags::Event; + +/// Number of events managed by the firmware. +const NUM_EVENTS: u32 = 128; + +/// Inner data associated with a given event slot. +pub(crate) struct EventInner { + /// CPU pointer to the driver notification event stamp + stamp: *const AtomicU32, + /// GPU pointer to the driver notification event stamp + gpu_stamp: GpuWeakPointer, + /// GPU pointer to the firmware-internal event stamp + gpu_fw_stamp: GpuWeakPointer, +} + +/// SAFETY: The event slots are safe to send across threads. +unsafe impl Send for EventInner {} + +/// Alias for an event token, which allows requesting the same event. +pub(crate) type Token = slotalloc::SlotToken; +/// Alias for an allocated `Event` that has a slot. +pub(crate) type Event = slotalloc::Guard; + +/// Represents a given stamp value for an event. +#[derive(Eq, PartialEq, Copy, Clone, Debug)] +#[repr(transparent)] +pub(crate) struct EventValue(u32); + +impl EventValue { + /// Returns the `EventValue` that succeeds this one. + pub(crate) fn next(&self) -> EventValue { + EventValue(self.0.wrapping_add(0x100)) + } + + /// Increments this `EventValue` in place. + pub(crate) fn increment(&mut self) { + self.0 = self.0.wrapping_add(0x100); + } + + /* Not used + /// Increments this `EventValue` in place by a certain count. + pub(crate) fn add(&mut self, val: u32) { + self.0 = self + .0 + .wrapping_add(val.checked_mul(0x100).expect("Adding too many events")); + } + */ + + /// Increments this `EventValue` in place by a certain count. + pub(crate) fn sub(&mut self, val: u32) { + self.0 = self + .0 + .wrapping_sub(val.checked_mul(0x100).expect("Subtracting too many events")); + } + + /// Computes the delta between this event and another event. + pub(crate) fn delta(&self, other: &EventValue) -> i32 { + (self.0.wrapping_sub(other.0) as i32) >> 8 + } +} + +impl PartialOrd for EventValue { + fn partial_cmp(&self, other: &Self) -> Option { + Some(self.cmp(other)) + } +} + +impl Ord for EventValue { + fn cmp(&self, other: &Self) -> cmp::Ordering { + self.delta(other).cmp(&0) + } +} + +impl EventInner { + /// Returns the GPU pointer to the driver notification stamp + pub(crate) fn stamp_pointer(&self) -> GpuWeakPointer { + self.gpu_stamp + } + + /// Returns the GPU pointer to the firmware internal stamp + pub(crate) fn fw_stamp_pointer(&self) -> GpuWeakPointer { + self.gpu_fw_stamp + } + + /// Fetches the current event value from shared memory + pub(crate) fn current(&self) -> EventValue { + // SAFETY: The pointer is always valid as constructed in + // EventManager below, and outside users cannot construct + // new EventInners, nor move or copy them, and Guards as + // returned by the SlotAllocator hold a reference to the + // SlotAllocator containing the EventManagerInner, which + // keeps the GpuObject the stamp is contained within alive. + EventValue(unsafe { &*self.stamp }.load(Ordering::Acquire)) + } +} + +impl slotalloc::SlotItem for EventInner { + type Data = EventManagerInner; + + fn release(&mut self, data: &mut Self::Data, slot: u32) { + mod_pr_debug!("EventManager: Released slot {}\n", slot); + data.owners[slot as usize] = None; + } +} + +/// Inner data for the event manager, to be protected by the SlotAllocator lock. +pub(crate) struct EventManagerInner { + stamps: GpuArray, + fw_stamps: GpuArray, + // Note: Use dyn to avoid having to version this entire module. + owners: KVec>>, +} + +/// Top-level EventManager object. +pub(crate) struct EventManager { + alloc: slotalloc::SlotAllocator, +} + +impl EventManager { + /// Create a new EventManager. + #[inline(never)] + pub(crate) fn new(alloc: &mut gpu::KernelAllocators) -> Result { + let mut owners = KVec::new(); + for _i in 0..(NUM_EVENTS as usize) { + owners.push(None, GFP_KERNEL)?; + } + let inner = EventManagerInner { + stamps: alloc.shared.array_empty(NUM_EVENTS as usize)?, + fw_stamps: alloc.private.array_empty(NUM_EVENTS as usize)?, + owners, + }; + + for slot in 0..NUM_EVENTS { + inner.stamps[slot as usize] + .0 + .store(slot << 24, Ordering::Relaxed); + } + + Ok(EventManager { + alloc: slotalloc::SlotAllocator::new( + NUM_EVENTS, + inner, + |inner: &mut EventManagerInner, slot| { + Some(EventInner { + stamp: &inner.stamps[slot as usize].0, + gpu_stamp: inner.stamps.weak_item_pointer(slot as usize), + gpu_fw_stamp: inner.fw_stamps.weak_item_pointer(slot as usize), + }) + }, + c_str!("EventManager::SlotAllocator"), + static_lock_class!(), + static_lock_class!(), + )?, + }) + } + + /// Gets a free `Event`, optionally trying to reuse the last one allocated by this caller. + pub(crate) fn get( + &self, + token: Option, + owner: Arc, + ) -> Result { + let ev = self.alloc.get_inner(token, |inner, ev| { + mod_pr_debug!( + "EventManager: Registered owner {:p} on slot {}\n", + &*owner, + ev.slot() + ); + inner.owners[ev.slot() as usize] = Some(owner); + Ok(()) + })?; + Ok(ev) + } + + /// Signals an event by slot, indicating completion (of one or more commands). + pub(crate) fn signal(&self, slot: u32) { + match self + .alloc + .with_inner(|inner| inner.owners[slot as usize].as_ref().cloned()) + { + Some(owner) => { + owner.signal(); + } + None => { + mod_pr_debug!("EventManager: Received event for empty slot {}\n", slot); + } + } + } + + /// Marks the owner of an event as having lost its work due to a GPU error. + pub(crate) fn mark_error(&self, slot: u32, wait_value: u32, error: workqueue::WorkError) { + match self + .alloc + .with_inner(|inner| inner.owners[slot as usize].as_ref().cloned()) + { + Some(owner) => { + owner.mark_error(EventValue(wait_value), error); + } + None => { + pr_err!("Received error for empty slot {}\n", slot); + } + } + } + + /// Returns a reference to the workqueue owning an event. + pub(crate) fn get_owner( + &self, + slot: u32, + ) -> Option> { + self.alloc + .with_inner(|inner| inner.owners[slot as usize].as_ref().cloned()) + } + + /// Fail all commands, used when the GPU crashes. + pub(crate) fn fail_all(&self, error: workqueue::WorkError) { + let mut owners: KVec> = KVec::new(); + + self.alloc.with_inner(|inner| { + for wq in inner.owners.iter().filter_map(|o| o.as_ref()).cloned() { + if owners.push(wq, GFP_KERNEL).is_err() { + pr_err!("Failed to signal failure to WorkQueue\n"); + } + } + }); + + for wq in owners { + wq.fail_all(error); + } + } +} diff --git a/drivers/gpu/drm/asahi/file.rs b/drivers/gpu/drm/asahi/file.rs new file mode 100644 index 00000000000000..02a4ce874a92c8 --- /dev/null +++ b/drivers/gpu/drm/asahi/file.rs @@ -0,0 +1,1092 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +#![allow(clippy::unusual_byte_groupings)] + +//! File implementation, which represents a single DRM client. +//! +//! This is in charge of managing the resources associated with one GPU client, including an +//! arbitrary number of submission queues and Vm objects, and reporting hardware/driver +//! information to userspace and accepting submissions. + +use crate::debug::*; +use crate::driver::AsahiDevice; +use crate::{ + alloc, + buffer, + driver, + gem, + mmu, + module_parameters, + queue, + util::{ + align, + align_down, + gcd, + AnyBitPattern, + RangeExt, + Reader, // + }, // +}; +use core::mem::MaybeUninit; +use core::ops::Deref; +use core::ops::Range; +use core::ptr::addr_of_mut; +use kernel::bindings; +use kernel::dma_fence::RawDmaFence; +use kernel::drm::gem::BaseObject; +use kernel::error::code::*; +use kernel::new_mutex; +use kernel::prelude::*; +use kernel::sync::{ + Arc, + Mutex, // +}; +use kernel::time::NSEC_PER_SEC; +use kernel::uaccess::{ + UserPtr, + UserSlice, // +}; +use kernel::{ + dma_fence, + drm, + uapi, + xarray, // +}; + +const DEBUG_CLASS: DebugFlags = DebugFlags::File; + +pub(crate) const MAX_COMMANDS_PER_SUBMISSION: u32 = 64; + +/// A client instance of an `mmu::Vm` address space. +struct Vm { + ualloc: Arc>, + ualloc_priv: Arc>, + vm: mmu::Vm, + kernel_range: Range, + _dummy_mapping: mmu::KernelMapping, +} + +impl Drop for Vm { + fn drop(&mut self) { + // When the user Vm is dropped, unmap everything in the user range + let left_range = VM_USER_RANGE.start..self.kernel_range.start; + let right_range = self.kernel_range.end..VM_USER_RANGE.end; + + if !left_range.is_empty() + && self + .vm + .unmap_range(left_range.start, left_range.range()) + .is_err() + { + pr_err!("Vm::Drop: vm.unmap_range() failed\n"); + } + if !right_range.is_empty() + && self + .vm + .unmap_range(right_range.start, right_range.range()) + .is_err() + { + pr_err!("Vm::Drop: vm.unmap_range() failed\n"); + } + } +} + +/// Sync object from userspace. +pub(crate) struct SyncItem { + pub(crate) syncobj: drm::syncobj::SyncObj, + pub(crate) fence: Option, + pub(crate) chain_fence: Option, + pub(crate) timeline_value: u64, +} + +impl SyncItem { + fn parse_one(file: &DrmFile, data: uapi::drm_asahi_sync, out: bool) -> Result { + match data.sync_type { + uapi::drm_asahi_sync_type_DRM_ASAHI_SYNC_SYNCOBJ => { + if data.timeline_value != 0 { + cls_pr_debug!(Errors, "Non-timeline sync object with a nonzero value\n"); + return Err(EINVAL); + } + let syncobj = drm::syncobj::SyncObj::lookup_handle(file, data.handle)?; + + Ok(SyncItem { + fence: if out { + None + } else { + Some(syncobj.fence_get().ok_or_else(|| { + cls_pr_debug!(Errors, "Failed to get fence from sync object\n"); + EINVAL + })?) + }, + syncobj, + chain_fence: None, + timeline_value: data.timeline_value, + }) + } + uapi::drm_asahi_sync_type_DRM_ASAHI_SYNC_TIMELINE_SYNCOBJ => { + let syncobj = drm::syncobj::SyncObj::lookup_handle(file, data.handle)?; + let fence = if out { + None + } else { + syncobj + .fence_get() + .ok_or_else(|| { + cls_pr_debug!( + Errors, + "Failed to get fence from timeline sync object\n" + ); + EINVAL + })? + .chain_find_seqno(data.timeline_value)? + }; + + Ok(SyncItem { + fence, + syncobj, + chain_fence: if out { + Some(dma_fence::FenceChain::new()?) + } else { + None + }, + timeline_value: data.timeline_value, + }) + } + _ => { + cls_pr_debug!(Errors, "Invalid sync type {}\n", data.sync_type); + Err(EINVAL) + } + } + } + + fn parse_array( + file: &DrmFile, + ptr: u64, + in_count: u32, + out_count: u32, + ) -> Result> { + let count = in_count + out_count; + let mut vec = KVec::with_capacity(count as usize, GFP_KERNEL)?; + + const STRIDE: usize = core::mem::size_of::(); + let size = STRIDE * count as usize; + + // SAFETY: We only read this once, so there are no TOCTOU issues. + let mut reader = UserSlice::new(UserPtr::from_addr(ptr as _), size).reader(); + + for i in 0..count { + let mut sync: MaybeUninit = MaybeUninit::uninit(); + + // SAFETY: The size of `sync` is STRIDE + reader.read_raw(unsafe { + core::slice::from_raw_parts_mut(sync.as_mut_ptr() as *mut MaybeUninit, STRIDE) + })?; + + // SAFETY: All bit patterns in the struct are valid + let sync = unsafe { sync.assume_init() }; + + vec.push(SyncItem::parse_one(file, sync, i >= in_count)?, GFP_KERNEL)?; + } + + Ok(vec) + } +} + +#[derive(Clone)] +pub(crate) enum Object { + TimestampBuffer(Arc), +} + +/// State associated with a client. +// #[pin_data] +pub(crate) struct File { + id: u64, + // #[pin] + vms: xarray::XArray>, + // #[pin] + queues: xarray::XArray>>>, + // #[pin] + objects: xarray::XArray>, +} + +/// Convenience type alias for our DRM `File` type. +pub(crate) type DrmFile = drm::File; + +/// Available VM range for the user +const VM_USER_RANGE: Range = mmu::IOVA_USER_USABLE_RANGE; + +/// Minimum reserved AS for kernel mappings +const VM_KERNEL_MIN_SIZE: u64 = 0x20000000; + +impl drm::file::DriverFile for File { + type Driver = driver::AsahiDriver; + + /// Create a new `File` instance for a fresh client. + fn open(device: &AsahiDevice) -> Result>> { + debug::update_debug_flags(); + + let gpu = &device.gpu; + let id = gpu.ids().file.next(); + + mod_dev_dbg!(device, "[File {}]: DRM device opened\n", id); + Ok(KBox::pin_init(File::new(id), GFP_KERNEL)?) + } + + fn as_raw(&self) -> *mut bindings::drm_file { + todo!() + } +} + +// SAFETY: All bit patterns are valid by construction. +unsafe impl AnyBitPattern for uapi::drm_asahi_gem_bind_op {} + +impl File { + fn new(id: u64) -> impl PinInit { + unsafe { + pin_init::pin_init_from_closure(move |slot: *mut Self| { + let raw_vms = addr_of_mut!((*slot).vms); + xarray::XArray::>::new(xarray::AllocKind::Alloc1) + .__pinned_init(raw_vms)?; + + let raw_queues = addr_of_mut!((*slot).queues); + xarray::XArray::>>>::new( + xarray::AllocKind::Alloc1, + ) + .__pinned_init(raw_queues)?; + + let raw_objects = addr_of_mut!((*slot).objects); + xarray::XArray::>::new(xarray::AllocKind::Alloc1) + .__pinned_init(raw_objects)?; + + (*slot).id = id; + Ok(()) + }) + } + } + + fn vms(self: Pin<&Self>) -> Pin<&xarray::XArray>> { + // SAFETY: Structural pinned projection for vms. + // We never move out of this field. + unsafe { self.map_unchecked(|s| &s.vms) } + } + + #[allow(clippy::type_complexity)] + fn queues(self: Pin<&Self>) -> Pin<&xarray::XArray>>>> { + // SAFETY: Structural pinned projection for queues. + // We never move out of this field. + unsafe { self.map_unchecked(|s| &s.queues) } + } + + fn objects(self: Pin<&Self>) -> Pin<&xarray::XArray>> { + // SAFETY: Structural pinned projection for objects. + // We never move out of this field. + unsafe { self.map_unchecked(|s| &s.objects) } + } + + /// IOCTL: get_param: Get a driver parameter value. + pub(crate) fn get_params( + device: &AsahiDevice, + data: &uapi::drm_asahi_get_params, + file: &DrmFile, + ) -> Result { + mod_dev_dbg!(device, "[File {}]: IOCTL: get_params\n", file.inner().id); + + let gpu = &device.gpu; + + if data.param_group != 0 || data.pad != 0 { + cls_pr_debug!(Errors, "get_params: Invalid arguments\n"); + return Err(EINVAL); + } + + if gpu.is_crashed() { + return Err(ENODEV); + } + + let mut params = uapi::drm_asahi_params_global { + features: 0, + + gpu_generation: gpu.get_dyncfg().id.gpu_gen as u32, + gpu_variant: gpu.get_dyncfg().id.gpu_variant as u32, + gpu_revision: gpu.get_dyncfg().id.gpu_rev as u32, + chip_id: gpu.get_cfg().chip_id, + + num_dies: gpu.get_cfg().num_dies, + num_clusters_total: gpu.get_dyncfg().id.num_clusters, + num_cores_per_cluster: gpu.get_dyncfg().id.num_cores, + core_masks: [0; uapi::DRM_ASAHI_MAX_CLUSTERS as usize], + + vm_start: VM_USER_RANGE.start, + vm_end: VM_USER_RANGE.end, + vm_kernel_min_size: VM_KERNEL_MIN_SIZE, + + max_commands_per_submission: MAX_COMMANDS_PER_SUBMISSION, + max_attachments: crate::microseq::MAX_ATTACHMENTS as u32, + max_frequency_khz: gpu.get_dyncfg().pwr.max_frequency_khz(), + + command_timestamp_frequency_hz: 1_000_000_000, // User timestamps always in nanoseconds + }; + + for (i, mask) in gpu.get_dyncfg().id.core_masks.iter().enumerate() { + *(params.core_masks.get_mut(i).ok_or(EIO)?) = (*mask).into(); + } + + if *module_parameters::fault_control.value() == 0xb { + params.features |= uapi::drm_asahi_feature_DRM_ASAHI_FEATURE_SOFT_FAULTS as u64; + } + + let size = core::mem::size_of::().min(data.size.try_into()?); + + // SAFETY: We only write to this userptr once, so there are no TOCTOU issues. + let mut params_writer = + UserSlice::new(UserPtr::from_addr(data.pointer as _), size).writer(); + + // SAFETY: `size` is at most the sizeof of `params` + params_writer.write_slice(unsafe { + core::slice::from_raw_parts(¶ms as *const _ as *const u8, size) + })?; + + Ok(0) + } + + /// IOCTL: vm_create: Create a new `Vm`. + pub(crate) fn vm_create( + device: &AsahiDevice, + data: &mut uapi::drm_asahi_vm_create, + file: &DrmFile, + ) -> Result { + let kernel_range = data.kernel_start..data.kernel_end; + + // Validate requested kernel range + if !VM_USER_RANGE.is_superset(kernel_range.clone()) + || kernel_range.range() < VM_KERNEL_MIN_SIZE + || kernel_range.start & (mmu::UAT_PGMSK as u64) != 0 + || kernel_range.end & (mmu::UAT_PGMSK as u64) != 0 + { + cls_pr_debug!(Errors, "vm_create: Invalid kernel range\n"); + return Err(EINVAL); + } + + // Align to buffer::PAGE_SIZE so the allocators are happy + let kernel_range = align(kernel_range.start, buffer::PAGE_SIZE as u64) + ..align_down(kernel_range.end, buffer::PAGE_SIZE as u64); + + let kernel_half_size = align_down(kernel_range.range() >> 1, buffer::PAGE_SIZE as u64); + let kernel_gpu_range = kernel_range.start..(kernel_range.start + kernel_half_size); + let kernel_gpufw_range = kernel_gpu_range.end..kernel_range.end; + + let gpu = &device.gpu; + let file_id = file.inner().id; + let vm = gpu.new_vm(kernel_range.clone())?; + + let vm_xa = file.inner().vms(); + let resv = vm_xa.lock().reserve_limit(1..=u32::MAX, GFP_KERNEL)?; + let id: u32 = resv.index().try_into()?; + + mod_dev_dbg!(device, "[File {} VM {}]: VM Create\n", file_id, id); + mod_dev_dbg!( + device, + "[File {} VM {}]: Creating allocators\n", + file_id, + id + ); + let ualloc = Arc::pin_init( + new_mutex!(alloc::DefaultAllocator::new( + device, + &vm, + kernel_gpu_range, + buffer::PAGE_SIZE, + mmu::PROT_GPU_SHARED_RW, + 512 * 1024, + true, + fmt!("File {} VM {} GPU Shared", file_id, id), + false, + )?), + GFP_KERNEL, + )?; + let ualloc_priv = Arc::pin_init( + new_mutex!(alloc::DefaultAllocator::new( + device, + &vm, + kernel_gpufw_range, + buffer::PAGE_SIZE, + mmu::PROT_GPU_FW_PRIV_RW, + 64 * 1024, + true, + fmt!("File {} VM {} GPU FW Private", file_id, id), + false, + )?), + GFP_KERNEL, + )?; + + mod_dev_dbg!( + device, + "[File {} VM {}]: Creating dummy object\n", + file_id, + id + ); + let mut dummy_obj = gem::new_kernel_object(device, 0x4000)?; + dummy_obj.vmap()?.memset(0); + let dummy_mapping = + dummy_obj.map_at(&vm, mmu::IOVA_UNK_PAGE, mmu::PROT_GPU_SHARED_RW, true)?; + + mod_dev_dbg!(device, "[File {} VM {}]: VM created\n", file_id, id); + resv.fill(KBox::new( + Vm { + ualloc, + ualloc_priv, + vm, + kernel_range, + _dummy_mapping: dummy_mapping, + }, + GFP_KERNEL, + )?)?; + + data.vm_id = id; + + Ok(0) + } + + /// IOCTL: vm_destroy: Destroy a `Vm`. + pub(crate) fn vm_destroy( + _device: &AsahiDevice, + data: &mut uapi::drm_asahi_vm_destroy, + file: &DrmFile, + ) -> Result { + let vm = file.inner().vms().remove(data.vm_id as usize); + if vm.is_none() { + Err(ENOENT) + } else { + Ok(0) + } + } + + /// IOCTL: gem_create: Create a new GEM object. + pub(crate) fn gem_create( + device: &AsahiDevice, + data: &mut uapi::drm_asahi_gem_create, + file: &DrmFile, + ) -> Result { + mod_dev_dbg!( + device, + "[File {}]: IOCTL: gem_create size={:#x?}\n", + file.inner().id, + data.size + ); + + if (data.flags + & !(uapi::drm_asahi_gem_flags_DRM_ASAHI_GEM_WRITEBACK + | uapi::drm_asahi_gem_flags_DRM_ASAHI_GEM_VM_PRIVATE)) + != 0 + || (data.flags & uapi::drm_asahi_gem_flags_DRM_ASAHI_GEM_VM_PRIVATE == 0 + && data.vm_id != 0) + { + cls_pr_debug!(Errors, "gem_create: Invalid arguments\n"); + return Err(EINVAL); + } + + let resv_gem; + let resv_obj = if data.flags & uapi::drm_asahi_gem_flags_DRM_ASAHI_GEM_VM_PRIVATE != 0 { + resv_gem = file + .inner() + .vms() + .lock() + .get(data.vm_id.try_into()?) + .ok_or(ENOENT)? + .vm + .get_resv_obj(); + Some(resv_gem.deref()) + } else { + None + }; + + let gem = gem::new_object(device, data.size.try_into()?, data.flags, resv_obj)?; + + let handle = gem.create_handle(file)?; + data.handle = handle; + + mod_dev_dbg!( + device, + "[File {}]: IOCTL: gem_create size={:#x} handle={:#x?}\n", + file.inner().id, + data.size, + data.handle + ); + + Ok(0) + } + + /// IOCTL: gem_mmap_offset: Assign an mmap offset to a GEM object. + pub(crate) fn gem_mmap_offset( + device: &AsahiDevice, + data: &mut uapi::drm_asahi_gem_mmap_offset, + file: &DrmFile, + ) -> Result { + mod_dev_dbg!( + device, + "[File {}]: IOCTL: gem_mmap_offset handle={:#x?}\n", + file.inner().id, + data.handle + ); + + if data.flags != 0 { + cls_pr_debug!(Errors, "gem_mmap_offset: Unexpected flags\n"); + return Err(EINVAL); + } + + let gem = gem::Object::lookup_handle(file, data.handle)?; + data.offset = gem.create_mmap_offset()?; + Ok(0) + } + + /// IOCTL: vm_bind: Map or unmap memory into a Vm. + pub(crate) fn vm_bind( + device: &AsahiDevice, + data: &uapi::drm_asahi_vm_bind, + file: &DrmFile, + ) -> Result { + mod_dev_dbg!( + device, + "[File {} VM {}]: IOCTL: vm_bind\n", + file.inner().id, + data.vm_id, + ); + + if data.stride == 0 || data.pad != 0 { + cls_pr_debug!(Errors, "vm_bind: Unexpected headers\n"); + return Err(EINVAL); + } + + let vm_id = data.vm_id.try_into()?; + + let mut vec = KVec::new(); + let size = (data.stride * data.num_binds) as usize; + let reader = UserSlice::new(UserPtr::from_addr(data.userptr as _), size).reader(); + reader.read_all(&mut vec, GFP_KERNEL)?; + let mut reader = Reader::new(&vec); + + for _i in 0..data.num_binds { + let bind: uapi::drm_asahi_gem_bind_op = reader.read_up_to(data.stride as usize)?; + Self::do_gem_bind_unbind(vm_id, &bind, file)?; + } + + Ok(0) + } + + pub(crate) fn do_gem_bind_unbind( + vm_id: usize, + data: &uapi::drm_asahi_gem_bind_op, + file: &DrmFile, + ) -> Result { + if (data.flags & uapi::drm_asahi_bind_flags_DRM_ASAHI_BIND_UNBIND) != 0 { + Self::do_gem_unbind(vm_id, data, file) + } else { + Self::do_gem_bind(vm_id, data, file) + } + } + + pub(crate) fn do_gem_bind( + vm_id: usize, + data: &uapi::drm_asahi_gem_bind_op, + file: &DrmFile, + ) -> Result { + if (data.addr | data.range | data.offset) as usize & mmu::UAT_PGMSK != 0 { + cls_pr_debug!( + Errors, + "gem_bind: Addr/range/offset not page aligned: {:#x} {:#x}\n", + data.addr, + data.range + ); + return Err(EINVAL); // Must be page aligned + } + + if (data.flags + & !(uapi::drm_asahi_bind_flags_DRM_ASAHI_BIND_READ + | uapi::drm_asahi_bind_flags_DRM_ASAHI_BIND_WRITE + | uapi::drm_asahi_bind_flags_DRM_ASAHI_BIND_SINGLE_PAGE)) + != 0 + { + cls_pr_debug!(Errors, "gem_bind: Invalid flags {:#x}\n", data.flags); + return Err(EINVAL); + } + + let single_page = data.flags & uapi::drm_asahi_bind_flags_DRM_ASAHI_BIND_SINGLE_PAGE != 0; + + let bo = gem::Object::lookup_handle(file, data.handle)?; + + let start = data.addr; + let end = data.addr.checked_add(data.range).ok_or(EINVAL)?; + let range = start..end; + + let bo_accessed_size = if single_page { + mmu::UAT_PGMSK as u64 + } else { + data.range + }; + let end_off = data.offset.checked_add(bo_accessed_size).ok_or(EINVAL)?; + if end_off as usize > bo.size() { + return Err(EINVAL); + } + + if !VM_USER_RANGE.is_superset(range.clone()) { + cls_pr_debug!( + Errors, + "gem_bind: Invalid map range {:#x}..{:#x} (not contained in user range)\n", + start, + end + ); + return Err(EINVAL); // Invalid map range + } + + let prot = if data.flags & uapi::drm_asahi_bind_flags_DRM_ASAHI_BIND_READ != 0 { + if data.flags & uapi::drm_asahi_bind_flags_DRM_ASAHI_BIND_WRITE != 0 { + mmu::PROT_GPU_SHARED_RW + } else { + mmu::PROT_GPU_SHARED_RO + } + } else if data.flags & uapi::drm_asahi_bind_flags_DRM_ASAHI_BIND_WRITE != 0 { + mmu::PROT_GPU_SHARED_WO + } else { + cls_pr_debug!( + Errors, + "gem_bind: Must specify read or write (flags: {:#x})\n", + data.flags + ); + return Err(EINVAL); // Must specify one of DRM_ASAHI_BIND_{READ,WRITE} + }; + + let vms_xa = file.inner().vms(); + let guard = vms_xa.lock(); + let guarded_vm = guard.get(vm_id).ok_or(ENOENT)?; + + // Clone it immediately so we aren't holding the XArray lock + let vm = guarded_vm.vm.clone(); + let kernel_range = guarded_vm.kernel_range.clone(); + let _ = guarded_vm; + core::mem::drop(guard); + + if kernel_range.overlaps(range) { + cls_pr_debug!( + Errors, + "gem_bind: Invalid map range {:#x}..{:#x} (intrudes in kernel range)\n", + start, + end + ); + return Err(EINVAL); + } + + vm.bind_object(&bo, data.addr, data.range, data.offset, prot, single_page)?; + + vm.bo_deferred_cleanup(); + + Ok(0) + } + + pub(crate) fn do_gem_unbind( + vm_id: usize, + data: &uapi::drm_asahi_gem_bind_op, + file: &DrmFile, + ) -> Result { + if data.offset != 0 + || data.flags != uapi::drm_asahi_bind_flags_DRM_ASAHI_BIND_UNBIND + || data.handle != 0 + { + cls_pr_debug!(Errors, "gem_unbind: offset/flags/handle not zero\n"); + return Err(EINVAL); + } + + if (data.addr | data.range) as usize & mmu::UAT_PGMSK != 0 { + cls_pr_debug!( + Errors, + "gem_bind: Addr/range/offset not page aligned: {:#x} {:#x}\n", + data.addr, + data.range + ); + return Err(EINVAL); // Must be page aligned + } + + let start = data.addr; + let end = data.addr.checked_add(data.range).ok_or(EINVAL)?; + let range = start..end; + + if !VM_USER_RANGE.is_superset(range.clone()) { + cls_pr_debug!( + Errors, + "gem_bind: Invalid unmap range {:#x}..{:#x} (not contained in user range)\n", + start, + end + ); + return Err(EINVAL); // Invalid map range + } + + let vms_xa = file.inner().vms(); + let guard = vms_xa.lock(); + let guarded_vm = guard.get(vm_id).ok_or(ENOENT)?; + + // Clone it immediately so we aren't holding the XArray lock + let vm = guarded_vm.vm.clone(); + let kernel_range = guarded_vm.kernel_range.clone(); + let _ = guarded_vm; + core::mem::drop(guard); + + if kernel_range.overlaps(range.clone()) { + cls_pr_debug!( + Errors, + "gem_bind: Invalid unmap range {:#x}..{:#x} (intrudes in kernel range)\n", + start, + end + ); + return Err(EINVAL); + } + + vm.unmap_range(range.start, range.range())?; + + vm.bo_deferred_cleanup(); + + Ok(0) + } + + pub(crate) fn unbind_gem_object(file: &DrmFile, bo: &gem::Object) -> Result { + // TODO: use iter() + let mut index = 0; + loop { + let vms = file.inner().vms(); + let item = vms.find(index, usize::MAX); + match item { + Some((idx, file_vm)) => { + // Clone since we can't hold the xarray spinlock while + // calling drop_mappings() + let vm = file_vm.borrow().vm.clone(); + core::mem::drop(file_vm); + vm.drop_mappings(bo)?; + if idx == usize::MAX { + break; + } + index = idx + 1; + } + None => break, + } + } + Ok(()) + } + + /// IOCTL: gem_bind_object: Map or unmap a GEM object as a special object. + pub(crate) fn gem_bind_object( + device: &AsahiDevice, + data: &mut uapi::drm_asahi_gem_bind_object, + file: &DrmFile, + ) -> Result { + mod_dev_dbg!( + device, + "[File {} VM {}]: IOCTL: gem_bind_object op={:?} handle={:#x?} flags={:#x?} {:#x?}:{:#x?} object_handle={:#x?}\n", + file.inner().id, + data.vm_id, + data.op, + data.handle, + data.flags, + data.offset, + data.range, + data.object_handle + ); + + if data.pad != 0 { + cls_pr_debug!(Errors, "gem_bind_object: Unexpected pad\n"); + return Err(EINVAL); + } + + if data.vm_id != 0 { + cls_pr_debug!(Errors, "gem_bind_object: Unexpected vm_id\n"); + return Err(EINVAL); + } + + match data.op { + uapi::drm_asahi_bind_object_op_DRM_ASAHI_BIND_OBJECT_OP_BIND => { + Self::do_gem_bind_object(device, data, file) + } + uapi::drm_asahi_bind_object_op_DRM_ASAHI_BIND_OBJECT_OP_UNBIND => { + Self::do_gem_unbind_object(device, data, file) + } + _ => { + cls_pr_debug!(Errors, "gem_bind_object: Invalid op {}\n", data.op); + Err(EINVAL) + } + } + } + + pub(crate) fn do_gem_bind_object( + device: &AsahiDevice, + data: &mut uapi::drm_asahi_gem_bind_object, + file: &DrmFile, + ) -> Result { + if (data.range | data.offset) as usize & mmu::UAT_PGMSK != 0 { + cls_pr_debug!( + Errors, + "gem_bind_object: Range/offset not page aligned: {:#x} {:#x}\n", + data.range, + data.offset + ); + return Err(EINVAL); // Must be page aligned + } + + if data.flags != uapi::drm_asahi_bind_object_flags_DRM_ASAHI_BIND_OBJECT_USAGE_TIMESTAMPS { + cls_pr_debug!(Errors, "gem_bind_object: Invalid flags {:#x}\n", data.flags); + return Err(EINVAL); + } + + let offset = data.offset.try_into()?; + let end_offset = data + .offset + .checked_add(data.range) + .ok_or(EINVAL)? + .try_into()?; + let bo = gem::ObjectRef::new(gem::Object::lookup_handle(file, data.handle)?); + + let mapping = Arc::new( + device.gpu.map_timestamp_buffer(bo, offset..end_offset)?, + GFP_KERNEL, + )?; + let obj = KBox::new(Object::TimestampBuffer(mapping), GFP_KERNEL)?; + let handle = file + .inner() + .objects() + .lock() + .insert_limit(1..=u32::MAX, obj, GFP_KERNEL)? as u64; + + data.object_handle = handle as u32; + Ok(0) + } + + pub(crate) fn do_gem_unbind_object( + _device: &AsahiDevice, + data: &mut uapi::drm_asahi_gem_bind_object, + file: &DrmFile, + ) -> Result { + if data.range != 0 || data.offset != 0 { + cls_pr_debug!( + Errors, + "gem_unbind_object: Range/offset not zero: {:#x} {:#x}\n", + data.range, + data.offset + ); + return Err(EINVAL); + } + + if data.flags != 0 { + cls_pr_debug!( + Errors, + "gem_unbind_object: Invalid flags {:#x}\n", + data.flags + ); + return Err(EINVAL); + } + + if data.handle != 0 { + cls_pr_debug!( + Errors, + "gem_unbind_object: Invalid handle {}\n", + data.handle + ); + return Err(EINVAL); + } + + let object = file.inner().objects().remove(data.object_handle as usize); + if object.is_none() { + Err(ENOENT) + } else { + Ok(0) + } + } + + /// IOCTL: queue_create: Create a new command submission queue of a given type. + pub(crate) fn queue_create( + device: &AsahiDevice, + data: &mut uapi::drm_asahi_queue_create, + file: &DrmFile, + ) -> Result { + let file_id = file.inner().id; + + mod_dev_dbg!( + device, + "[File {} VM {}]: Creating queue prio={:?} flags={:#x?}\n", + file_id, + data.vm_id, + data.priority, + data.flags, + ); + + if data.flags != 0 || data.priority > uapi::drm_asahi_priority_DRM_ASAHI_PRIORITY_REALTIME { + cls_pr_debug!(Errors, "queue_create: Invalid arguments\n"); + return Err(EINVAL); + } + + // TODO: Allow with CAP_SYS_NICE + if data.priority >= uapi::drm_asahi_priority_DRM_ASAHI_PRIORITY_HIGH { + cls_pr_debug!(Errors, "queue_create: Invalid priority\n"); + return Err(EINVAL); + } + + let queues_xa = file.inner().queues(); + let resv = queues_xa.lock().reserve_limit(1..=u32::MAX, GFP_KERNEL)?; + let vms_xa = file.inner().vms(); + let guard = vms_xa.lock(); + let file_vm = guard.get(data.vm_id.try_into()?).ok_or(ENOENT)?; + let vm = file_vm.vm.clone(); + let ualloc = file_vm.ualloc.clone(); + let ualloc_priv = file_vm.ualloc_priv.clone(); + // Drop the vms lock eagerly + let _ = file_vm; + core::mem::drop(guard); + + let queue = device.gpu.new_queue( + vm, + ualloc, + ualloc_priv, + // TODO: Plumb deeper the enum + uapi::drm_asahi_priority_DRM_ASAHI_PRIORITY_REALTIME - data.priority, + data.usc_exec_base, + )?; + + data.queue_id = resv.index().try_into()?; + resv.fill(Arc::pin_init(new_mutex!(queue), GFP_KERNEL)?)?; + + Ok(0) + } + + /// IOCTL: queue_destroy: Destroy a command submission queue. + pub(crate) fn queue_destroy( + _device: &AsahiDevice, + data: &mut uapi::drm_asahi_queue_destroy, + file: &DrmFile, + ) -> Result { + // grab the queue so the xarray spinlock is dropped first + let queue = file.inner().queues().remove(data.queue_id as usize); + if queue.is_none() { + Err(ENOENT) + } else { + Ok(0) + } + } + + /// IOCTL: submit: Submit GPU work to a command submission queue. + pub(crate) fn submit( + device: &AsahiDevice, + data: &mut uapi::drm_asahi_submit, + file: &DrmFile, + ) -> Result { + debug::update_debug_flags(); + + if data.flags != 0 || data.pad != 0 { + cls_pr_debug!(Errors, "submit: Invalid arguments\n"); + return Err(EINVAL); + } + + let gpu = &device.gpu; + gpu.update_globals(); + + // Upgrade to Arc to drop the XArray lock early + let queue: Arc>> = file + .inner() + .queues() + .lock() + .get(data.queue_id.try_into()?) + .ok_or(ENOENT)? + .into(); + + let id = gpu.ids().submission.next(); + mod_dev_dbg!( + device, + "[File {} Queue {}]: IOCTL: submit (submission ID: {})\n", + file.inner().id, + data.queue_id, + id + ); + + mod_dev_dbg!( + device, + "[File {} Queue {}]: IOCTL: submit({}): Parsing syncs\n", + file.inner().id, + data.queue_id, + id + ); + let syncs = + SyncItem::parse_array(file, data.syncs, data.in_sync_count, data.out_sync_count)?; + + mod_dev_dbg!( + device, + "[File {} Queue {}]: IOCTL: submit({}): Parsing commands\n", + file.inner().id, + data.queue_id, + id + ); + + let mut vec = KVec::new(); + + // Copy the command buffer into the kernel. Because we need to iterate + // the command buffer twice, we do this in one big copy_from_user to + // avoid TOCTOU issues. + let reader = UserSlice::new( + UserPtr::from_addr(data.cmdbuf as _), + data.cmdbuf_size as usize, + ) + .reader(); + reader.read_all(&mut vec, GFP_KERNEL)?; + + let objects = file.inner().objects(); + let ret = queue + .lock() + .submit(id, syncs, data.in_sync_count as usize, &vec, objects); + + match ret { + Err(ERESTARTSYS) => Err(ERESTARTSYS), + Err(e) => { + dev_info!( + device.as_ref(), + "[File {} Queue {}]: IOCTL: submit failed! (submission ID: {} err: {:?})\n", + file.inner().id, + data.queue_id, + id, + e + ); + Err(e) + } + Ok(()) => Ok(0), + } + } + + /// IOCTL: get_time: Get the current GPU timer value. + pub(crate) fn get_time( + device: &AsahiDevice, + data: &mut uapi::drm_asahi_get_time, + _file: &DrmFile, + ) -> Result { + if data.flags != 0 { + cls_pr_debug!(Errors, "get_time: Unexpected flags\n"); + return Err(EINVAL); + } + + // TODO: Do this on device-init for perf. + let gpu = &device.gpu; + let frequency_hz = gpu.get_cfg().base_clock_hz as u64; + let ts_gcd = gcd(frequency_hz, NSEC_PER_SEC as u64); + + let num = (NSEC_PER_SEC as u64) / ts_gcd; + let den = frequency_hz / ts_gcd; + + let raw: u64; + + // SAFETY: Assembly only loads the timer + unsafe { + core::arch::asm!( + "mrs {x}, CNTPCT_EL0", + x = out(reg) raw + ); + } + + data.gpu_timestamp = (raw * num) / den; + + Ok(0) + } +} + +impl Drop for File { + fn drop(&mut self) { + mod_pr_debug!("[File {}]: Closing...\n", self.id); + } +} diff --git a/drivers/gpu/drm/asahi/float.rs b/drivers/gpu/drm/asahi/float.rs new file mode 100644 index 00000000000000..d58a3d284da124 --- /dev/null +++ b/drivers/gpu/drm/asahi/float.rs @@ -0,0 +1,392 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Basic soft floating-point support +//! +//! The GPU firmware requires a large number of power-related configuration values, many of which +//! are IEEE 754 32-bit floating point values. These values change not only between GPU/SoC +//! variants, but also between specific hardware platforms using these SoCs, so they must be +//! derived from device tree properties. There are many redundant values computed from the same +//! inputs with simple add/sub/mul/div calculations, plus a few values that are actually specific +//! to each individual device depending on its binning and fused voltage configuration, so it +//! doesn't make sense to store the final values to be passed to the firmware in the device tree. +//! +//! Therefore, we need a way to perform floating-point calculations in the kernel. +//! +//! Using the actual FPU from kernel mode is asking for trouble, since there is no way to bound +//! the execution of FPU instructions to a controlled section of code without outright putting it +//! in its own compilation unit, which is quite painful for Rust. Since these calculations only +//! have to happen at initialization time and there is no need for performance, let's use a simple +//! software float implementation instead. +//! +//! This implementation makes no attempt to be fully IEEE754 compliant, but it's good enough and +//! gives bit-identical results to macOS in the vast majority of cases, with one or two exceptions +//! related to slightly non-compliant rounding. + +use core::ops; +use kernel::{ + of, + prelude::*, // +}; + +/// An IEEE754-compatible floating point number implemented in software. +#[derive(Default, Debug, Copy, Clone)] +#[repr(transparent)] +pub(crate) struct F32(u32); + +// SAFETY: F32 is a transparent repr of `u32` and therefore zeroable +unsafe impl Zeroable for F32 {} + +#[derive(Default, Debug, Copy, Clone)] +struct F32U { + sign: bool, + exp: i32, + frac: i64, +} + +impl F32 { + /// Convert a raw 32-bit representation into an F32 + pub(crate) const fn from_bits(u: u32) -> F32 { + F32(u) + } + + // Convert a `f32` value into an F32 + // + // This must ONLY be used in const context. Use the `f32!{}` macro to do it safely. + #[doc(hidden)] + pub(crate) const fn from_f32(v: f32) -> F32 { + // Replace with to_bits() after kernel Rust minreq is >= 1.83.0 + #[allow(clippy::transmute_float_to_int)] + #[allow(unnecessary_transmutes)] + // SAFETY: Transmuting f32 to u32 is always safe + F32(unsafe { core::mem::transmute::(v) }) + } + + // Convert an F32 into a `f32` value + // + // For testing only. + #[doc(hidden)] + #[cfg(test)] + pub(crate) fn to_f32(self) -> f32 { + f32::from_bits(self.0) + } + + const fn unpack(&self) -> F32U { + F32U { + sign: self.0 & (1 << 31) != 0, + exp: ((self.0 >> 23) & 0xff) as i32 - 127, + frac: (((self.0 & 0x7fffff) | 0x800000) as i64) << 9, + } + .norm() + } +} + +/// Safely construct an `F32` out of a constant floating-point value. +/// +/// This ensures that the conversion happens in const context, so no floating point operations are +/// emitted. +#[macro_export] +macro_rules! f32 { + ([$($val:expr),*]) => {{ + [$(f32!($val)),*] + }}; + ($val:expr) => {{ + const _K: $crate::float::F32 = $crate::float::F32::from_f32($val); + _K + }}; +} + +impl ops::Neg for F32 { + type Output = F32; + + fn neg(self) -> F32 { + F32(self.0 ^ (1 << 31)) + } +} + +impl ops::Add for F32 { + type Output = F32; + + fn add(self, rhs: F32) -> F32 { + self.unpack().add(rhs.unpack()).pack() + } +} + +impl ops::Sub for F32 { + type Output = F32; + + fn sub(self, rhs: F32) -> F32 { + self.unpack().add((-rhs).unpack()).pack() + } +} + +impl ops::Mul for F32 { + type Output = F32; + + fn mul(self, rhs: F32) -> F32 { + self.unpack().mul(rhs.unpack()).pack() + } +} + +impl ops::Div for F32 { + type Output = F32; + + fn div(self, rhs: F32) -> F32 { + self.unpack().div(rhs.unpack()).pack() + } +} + +macro_rules! from_ints { + ($u:ty, $i:ty) => { + impl From<$i> for F32 { + fn from(v: $i) -> F32 { + F32U::from_i64(v as i64).pack() + } + } + impl From<$u> for F32 { + fn from(v: $u) -> F32 { + F32U::from_u64(v as u64).pack() + } + } + }; +} + +from_ints!(u8, i8); +from_ints!(u16, i16); +from_ints!(u32, i32); +from_ints!(u64, i64); + +impl F32U { + const INFINITY: F32U = f32!(f32::INFINITY).unpack(); + const NEG_INFINITY: F32U = f32!(f32::NEG_INFINITY).unpack(); + + fn from_i64(v: i64) -> F32U { + F32U { + sign: v < 0, + exp: 32, + frac: v.abs(), + } + .norm() + } + + fn from_u64(mut v: u64) -> F32U { + let mut exp = 32; + if v >= (1 << 63) { + exp = 31; + v >>= 1; + } + F32U { + sign: false, + exp, + frac: v as i64, + } + .norm() + } + + fn shr(&mut self, shift: i32) { + if shift > 63 { + self.exp = 0; + self.frac = 0; + } else { + self.frac >>= shift; + } + } + + fn align(a: &mut F32U, b: &mut F32U) { + if a.exp > b.exp { + b.shr(a.exp - b.exp); + b.exp = a.exp; + } else { + a.shr(b.exp - a.exp); + a.exp = b.exp; + } + } + + fn mul(self, other: F32U) -> F32U { + F32U { + sign: self.sign != other.sign, + exp: self.exp + other.exp, + frac: ((self.frac >> 8) * (other.frac >> 8)) >> 16, + } + } + + fn div(self, other: F32U) -> F32U { + if other.frac == 0 || self.is_inf() { + if self.sign { + F32U::NEG_INFINITY + } else { + F32U::INFINITY + } + } else { + F32U { + sign: self.sign != other.sign, + exp: self.exp - other.exp, + frac: ((self.frac << 24) / (other.frac >> 8)), + } + } + } + + fn add(mut self, mut other: F32U) -> F32U { + F32U::align(&mut self, &mut other); + if self.sign == other.sign { + self.frac += other.frac; + } else { + self.frac -= other.frac; + } + if self.frac < 0 { + self.sign = !self.sign; + self.frac = -self.frac; + } + self + } + + const fn norm(mut self) -> F32U { + let lz = self.frac.leading_zeros() as i32; + if lz > 31 { + self.frac <<= lz - 31; + self.exp -= lz - 31; + } else if lz < 31 { + self.frac >>= 31 - lz; + self.exp += 31 - lz; + } + + if self.is_zero() { + return F32U { + sign: self.sign, + frac: 0, + exp: 0, + }; + } + self + } + + const fn is_zero(&self) -> bool { + self.frac == 0 || self.exp < -126 + } + + const fn is_inf(&self) -> bool { + self.exp > 127 + } + + const fn pack(mut self) -> F32 { + self = self.norm(); + if !self.is_zero() { + self.frac += 0x100; + self = self.norm(); + } + + if self.is_inf() { + if self.sign { + return f32!(f32::NEG_INFINITY); + } else { + return f32!(f32::INFINITY); + } + } else if self.is_zero() { + if self.sign { + return f32!(-0.0); + } else { + return f32!(0.0); + } + } + + F32(if self.sign { 1u32 << 31 } else { 0u32 } + | ((self.exp + 127) as u32) << 23 + | ((self.frac >> 9) & 0x7fffff) as u32) + } +} + +impl<'a> TryFrom> for F32 { + type Error = Error; + + fn try_from(p: of::Property<'_>) -> core::result::Result { + let bits: u32 = p.try_into()?; + Ok(F32::from_bits(bits)) + } +} + +impl of::PropertyUnit for F32 { + const UNIT_SIZE: usize = 4; + + fn from_bytes(data: &[u8]) -> Result { + Ok(F32::from_bits(::from_bytes(data)?)) + } +} + +// TODO: Make this an actual test and figure out how to make it run. +#[cfg(test)] +mod tests { + #[test] + fn test_all() { + fn add(a: f32, b: f32) { + println!( + "{} + {} = {} {}", + a, + b, + (F32::from_f32(a) + F32::from_f32(b)).to_f32(), + a + b + ); + } + fn sub(a: f32, b: f32) { + println!( + "{} - {} = {} {}", + a, + b, + (F32::from_f32(a) - F32::from_f32(b)).to_f32(), + a - b + ); + } + fn mul(a: f32, b: f32) { + println!( + "{} * {} = {} {}", + a, + b, + (F32::from_f32(a) * F32::from_f32(b)).to_f32(), + a * b + ); + } + fn div(a: f32, b: f32) { + println!( + "{} / {} = {} {}", + a, + b, + (F32::from_f32(a) / F32::from_f32(b)).to_f32(), + a / b + ); + } + + fn test(a: f32, b: f32) { + add(a, b); + sub(a, b); + mul(a, b); + div(a, b); + } + + test(1.123, 7.567); + test(1.123, 1.456); + test(7.567, 1.123); + test(1.123, -7.567); + test(1.123, -1.456); + test(7.567, -1.123); + test(-1.123, -7.567); + test(-1.123, -1.456); + test(-7.567, -1.123); + test(1000.123, 0.001); + test(1000.123, 0.0000001); + test(0.0012, 1000.123); + test(0.0000001, 1000.123); + test(0., 0.); + test(0., 1.); + test(1., 0.); + test(1., 1.); + test(2., f32::INFINITY); + test(2., f32::NEG_INFINITY); + test(f32::INFINITY, 2.); + test(f32::NEG_INFINITY, 2.); + test(f32::NEG_INFINITY, 2.); + test(f32::MAX, 2.); + test(f32::MIN, 2.); + test(f32::MIN_POSITIVE, 2.); + test(2., f32::MAX); + test(2., f32::MIN); + test(2., f32::MIN_POSITIVE); + } +} diff --git a/drivers/gpu/drm/asahi/fw/buffer.rs b/drivers/gpu/drm/asahi/fw/buffer.rs new file mode 100644 index 00000000000000..b1f4974fd02902 --- /dev/null +++ b/drivers/gpu/drm/asahi/fw/buffer.rs @@ -0,0 +1,184 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU tiled vertex buffer control firmware structures + +use super::types::*; +use super::workqueue; +use crate::{ + default_zeroed, + no_debug, + trivial_gpustruct, // +}; +use kernel::sync::Arc; + +pub(crate) mod raw { + use super::*; + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct BlockControl { + pub(crate) total: AtomicU32, + pub(crate) wptr: AtomicU32, + pub(crate) unk: AtomicU32, + pub(crate) pad: Pad<0x34>, + } + default_zeroed!(BlockControl); + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct Counter { + pub(crate) count: AtomicU32, + __pad: Pad<0x3c>, + } + default_zeroed!(Counter); + + #[derive(Debug, Default)] + #[repr(C)] + pub(crate) struct Stats { + pub(crate) max_pages: AtomicU32, + pub(crate) max_b: AtomicU32, + pub(crate) overflow_count: AtomicU32, + pub(crate) gpu_c: AtomicU32, + pub(crate) __pad0: Pad<0x10>, + pub(crate) reset: AtomicU32, + pub(crate) __pad1: Pad<0x1c>, + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct Info<'a> { + pub(crate) gpu_counter: u32, + pub(crate) unk_4: u32, + pub(crate) last_id: i32, + pub(crate) cur_id: i32, + pub(crate) unk_10: u32, + pub(crate) gpu_counter2: u32, + pub(crate) unk_18: u32, + + #[ver(V < V13_0B4 || G >= G14X)] + pub(crate) unk_1c: u32, + + pub(crate) page_list: GpuPointer<'a, &'a [u32]>, + pub(crate) page_list_size: u32, + pub(crate) page_count: AtomicU32, + pub(crate) max_blocks: u32, + pub(crate) block_count: AtomicU32, + pub(crate) unk_38: u32, + pub(crate) block_list: GpuPointer<'a, &'a [u32]>, + pub(crate) block_ctl: GpuPointer<'a, super::BlockControl>, + pub(crate) last_page: AtomicU32, + pub(crate) gpu_page_ptr1: u32, + pub(crate) gpu_page_ptr2: u32, + pub(crate) unk_58: u32, + pub(crate) block_size: u32, + pub(crate) unk_60: U64, + pub(crate) counter: GpuPointer<'a, super::Counter>, + pub(crate) unk_70: u32, + pub(crate) unk_74: u32, + pub(crate) unk_78: u32, + pub(crate) unk_7c: u32, + pub(crate) unk_80: u32, + pub(crate) max_pages: u32, + pub(crate) max_pages_nomemless: u32, + pub(crate) unk_8c: u32, + pub(crate) unk_90: Array<0x30, u8>, + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct Scene<'a> { + #[ver(G >= G14X)] + pub(crate) control_word: GpuPointer<'a, &'a [u32]>, + #[ver(G >= G14X)] + pub(crate) control_word2: GpuPointer<'a, &'a [u32]>, + pub(crate) pass_page_count: AtomicU32, + pub(crate) unk_4: u32, + pub(crate) unk_8: U64, + pub(crate) unk_10: U64, + pub(crate) user_buffer: GpuPointer<'a, &'a [u8]>, + pub(crate) unk_20: u32, + #[ver(V >= V13_3)] + pub(crate) unk_28: U64, + pub(crate) stats: GpuWeakPointer, + pub(crate) total_page_count: AtomicU32, + #[ver(G < G14X)] + pub(crate) unk_30: U64, // pad + #[ver(G < G14X)] + pub(crate) unk_38: U64, // pad + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct InitBuffer<'a> { + pub(crate) tag: workqueue::CommandType, + pub(crate) vm_slot: u32, + pub(crate) buffer_slot: u32, + pub(crate) unk_c: u32, + pub(crate) block_count: u32, + pub(crate) buffer: GpuPointer<'a, super::Info::ver>, + pub(crate) stamp_value: EventValue, + } +} + +trivial_gpustruct!(BlockControl); +trivial_gpustruct!(Counter); +trivial_gpustruct!(Stats); + +#[versions(AGX)] +#[derive(Debug)] +pub(crate) struct Info { + pub(crate) block_ctl: GpuObject, + pub(crate) counter: GpuObject, + pub(crate) page_list: GpuArray, + pub(crate) block_list: GpuArray, +} + +#[versions(AGX)] +impl GpuStruct for Info::ver { + type Raw<'a> = raw::Info::ver<'a>; +} + +pub(crate) struct ClusterBuffers { + pub(crate) tilemaps: GpuArray, + pub(crate) meta: GpuArray, +} + +#[versions(AGX)] +pub(crate) struct Scene { + pub(crate) user_buffer: GpuArray, + pub(crate) buffer: crate::buffer::Buffer::ver, + pub(crate) tvb_heapmeta: GpuArray, + pub(crate) tvb_tilemap: GpuArray, + pub(crate) tpc: Arc>, + pub(crate) clustering: Option, + pub(crate) preempt_buf: GpuArray, + #[ver(G >= G14X)] + pub(crate) control_word: GpuArray, +} + +#[versions(AGX)] +no_debug!(Scene::ver); + +#[versions(AGX)] +impl GpuStruct for Scene::ver { + type Raw<'a> = raw::Scene::ver<'a>; +} + +#[versions(AGX)] +pub(crate) struct InitBuffer { + pub(crate) scene: Arc, +} + +#[versions(AGX)] +no_debug!(InitBuffer::ver); + +#[versions(AGX)] +impl workqueue::Command for InitBuffer::ver {} + +#[versions(AGX)] +impl GpuStruct for InitBuffer::ver { + type Raw<'a> = raw::InitBuffer::ver<'a>; +} diff --git a/drivers/gpu/drm/asahi/fw/channels.rs b/drivers/gpu/drm/asahi/fw/channels.rs new file mode 100644 index 00000000000000..c1a7ec82aad1e2 --- /dev/null +++ b/drivers/gpu/drm/asahi/fw/channels.rs @@ -0,0 +1,443 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU communication channel firmware structures (ring buffers) + +use super::types::*; +use crate::default_zeroed; +use core::sync::atomic::Ordering; +use kernel::static_assert; + +pub(crate) mod raw { + use super::*; + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct ChannelState<'a> { + pub(crate) read_ptr: AtomicU32, + __pad0: Pad<0x1c>, + pub(crate) write_ptr: AtomicU32, + __pad1: Pad<0xc>, + _p: PhantomData<&'a ()>, + } + default_zeroed!(<'a>, ChannelState<'a>); + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct FwCtlChannelState<'a> { + pub(crate) read_ptr: AtomicU32, + __pad0: Pad<0xc>, + pub(crate) write_ptr: AtomicU32, + __pad1: Pad<0xc>, + _p: PhantomData<&'a ()>, + } + default_zeroed!(<'a>, FwCtlChannelState<'a>); +} + +pub(crate) trait RxChannelState: GpuStruct + Debug + Default +where + for<'a> ::Raw<'a>: Default + Zeroable, +{ + const SUB_CHANNELS: usize; + + fn wptr(raw: &Self::Raw<'_>, index: usize) -> u32; + fn set_rptr(raw: &Self::Raw<'_>, index: usize, rptr: u32); +} + +#[derive(Debug, Default)] +pub(crate) struct ChannelState {} + +impl GpuStruct for ChannelState { + type Raw<'a> = raw::ChannelState<'a>; +} + +impl RxChannelState for ChannelState { + const SUB_CHANNELS: usize = 1; + + fn wptr(raw: &Self::Raw<'_>, _index: usize) -> u32 { + raw.write_ptr.load(Ordering::Acquire) + } + + fn set_rptr(raw: &Self::Raw<'_>, _index: usize, rptr: u32) { + raw.read_ptr.store(rptr, Ordering::Release); + } +} + +#[derive(Debug, Default)] +pub(crate) struct FwLogChannelState {} + +impl GpuStruct for FwLogChannelState { + type Raw<'a> = Array<6, raw::ChannelState<'a>>; +} + +impl RxChannelState for FwLogChannelState { + const SUB_CHANNELS: usize = 6; + + fn wptr(raw: &Self::Raw<'_>, index: usize) -> u32 { + raw[index].write_ptr.load(Ordering::Acquire) + } + + fn set_rptr(raw: &Self::Raw<'_>, index: usize, rptr: u32) { + raw[index].read_ptr.store(rptr, Ordering::Release); + } +} + +#[derive(Debug, Default)] +pub(crate) struct FwCtlChannelState {} + +impl GpuStruct for FwCtlChannelState { + type Raw<'a> = raw::FwCtlChannelState<'a>; +} + +pub(crate) trait TxChannelState: GpuStruct + Debug + Default { + fn rptr(raw: &Self::Raw<'_>) -> u32; + fn set_wptr(raw: &Self::Raw<'_>, wptr: u32); +} + +impl TxChannelState for ChannelState { + fn rptr(raw: &Self::Raw<'_>) -> u32 { + raw.read_ptr.load(Ordering::Acquire) + } + + fn set_wptr(raw: &Self::Raw<'_>, wptr: u32) { + raw.write_ptr.store(wptr, Ordering::Release); + } +} + +impl TxChannelState for FwCtlChannelState { + fn rptr(raw: &Self::Raw<'_>) -> u32 { + raw.read_ptr.load(Ordering::Acquire) + } + + fn set_wptr(raw: &Self::Raw<'_>, wptr: u32) { + raw.write_ptr.store(wptr, Ordering::Release); + } +} + +#[derive(Debug, Copy, Clone, Default, PartialEq, Eq)] +#[repr(u32)] +pub(crate) enum PipeType { + #[default] + Vertex = 0, + Fragment = 1, + Compute = 2, +} + +#[versions(AGX)] +#[derive(Debug, Copy, Clone, Default)] +#[repr(C)] +pub(crate) struct RunWorkQueueMsg { + pub(crate) pipe_type: PipeType, + pub(crate) work_queue: Option>, + pub(crate) wptr: u32, + pub(crate) event_slot: u32, + pub(crate) is_new: bool, + #[ver(V >= V13_2 && G == G14)] + pub(crate) __pad: Pad<0x2b>, + #[ver(V < V13_2 || G != G14)] + pub(crate) __pad: Pad<0x1b>, +} + +#[versions(AGX)] +pub(crate) type PipeMsg = RunWorkQueueMsg::ver; + +#[versions(AGX)] +pub(crate) const DEVICECONTROL_SZ: usize = { + #[ver(V < V13_2 || G != G14)] + { + 0x2c + } + #[ver(V >= V13_2 && G == G14)] + { + 0x3c + } +}; + +// TODO: clean up when arbitrary_enum_discriminant is stable +// https://github.com/rust-lang/rust/issues/60553 + +#[versions(AGX)] +#[derive(Debug, Copy, Clone)] +#[repr(C, u32)] +#[allow(dead_code)] +pub(crate) enum DeviceControlMsg { + Unk00(Array), + Unk01(Array), + Unk02(Array), + Unk03(Array), + Unk04(Array), + Unk05(Array), + Unk06(Array), + Unk07(Array), + Unk08(Array), + Unk09(Array), + Unk0a(Array), + Unk0b(Array), + Unk0c(Array), + #[ver(V >= V13_3)] + Unk0d(Array), + GrowTVBAck { + unk_4: u32, + buffer_slot: u32, + vm_slot: u32, + counter: u32, + subpipe: u32, + halt_count: U64, + __pad: Pad<{ DEVICECONTROL_SZ::ver - 0x1c }>, + }, + RecoverChannel { + pipe_type: u32, + work_queue: GpuWeakPointer, + event_value: u32, + __pad: Pad<{ DEVICECONTROL_SZ::ver - 0x10 }>, + }, + IdlePowerOff { + val: u32, + __pad: Pad<{ DEVICECONTROL_SZ::ver - 0x4 }>, + }, + Unk10(Array), + Unk11(Array), + Unk12(Array), + Unk13(Array), + Unk14(Array), // Init? + Unk15(Array), // Enable something + Unk16(Array), // Disable something + DestroyContext { + unk_4: u32, + ctx_23: u8, + #[ver(V < V13_3)] + __pad0: Pad<3>, + unk_c: U32, + unk_10: U32, + ctx_0: u8, + ctx_1: u8, + ctx_4: u8, + #[ver(V < V13_3)] + __pad1: Pad<1>, + #[ver(V < V13_3)] + unk_18: u32, + gpu_context: Option>, + #[ver(V < V13_3)] + __pad2: Pad<{ DEVICECONTROL_SZ::ver - 0x20 }>, + #[ver(V >= V13_3)] + __pad2: Pad<{ DEVICECONTROL_SZ::ver - 0x18 }>, + }, + Unk18(Array), + Initialize(Pad), // Update RegionC +} + +#[versions(AGX)] +static_assert!(core::mem::size_of::() == 4 + DEVICECONTROL_SZ::ver); + +#[versions(AGX)] +default_zeroed!(DeviceControlMsg::ver); + +#[derive(Copy, Clone, Default, Debug)] +#[repr(C)] +#[allow(dead_code)] +pub(crate) struct FwCtlMsg { + pub(crate) addr: U64, + pub(crate) unk_8: u32, + pub(crate) slot: u32, + pub(crate) page_count: u16, + pub(crate) unk_12: u16, +} + +pub(crate) const EVENT_SZ: usize = 0x34; + +#[derive(Debug, Copy, Clone, PartialEq, Eq)] +#[repr(C, u32)] +#[allow(dead_code)] +pub(crate) enum ChannelErrorType { + MemoryError, + DMKill, + Aborted, + Unk3, + Unknown(u32), +} + +#[derive(Debug, Copy, Clone)] +#[repr(C, u32)] +#[allow(dead_code)] +pub(crate) enum EventMsg { + Fault, + Flag { + firing: [u32; 4], + unk_14: u16, + }, + Unk2(Array), + Unk3(Array), + Timeout { + counter: u32, + unk_8: u32, + event_slot: i32, + }, + Unk5(Array), + Unk6(Array), + GrowTVB { + vm_slot: u32, + buffer_slot: u32, + counter: u32, + }, + ChannelError { + error_type: u32, + pipe_type: u32, + event_slot: u32, + event_value: u32, + }, + // Max discriminant: 0x8 +} + +static_assert!(core::mem::size_of::() == 4 + EVENT_SZ); + +pub(crate) const EVENT_MAX: u32 = 0x8; + +#[derive(Copy, Clone)] +#[repr(C)] +pub(crate) union RawEventMsg { + pub(crate) raw: (u32, Array), + pub(crate) msg: EventMsg, +} + +default_zeroed!(RawEventMsg); + +#[derive(Debug, Copy, Clone, Default)] +#[repr(C)] +pub(crate) struct RawFwLogMsg { + pub(crate) msg_type: u32, + __pad0: u32, + pub(crate) msg_index: U64, + __pad1: Pad<0x28>, +} + +#[derive(Debug, Copy, Clone, Default)] +#[repr(C)] +pub(crate) struct RawFwLogPayloadMsg { + pub(crate) msg_type: u32, + pub(crate) seq_no: u32, + pub(crate) timestamp: U64, + pub(crate) msg: Array<0xc8, u8>, +} + +#[derive(Debug, Copy, Clone, Default)] +#[repr(C)] +pub(crate) struct RawKTraceMsg { + pub(crate) msg_type: u32, + pub(crate) timestamp: U64, + pub(crate) args: Array<4, U64>, + pub(crate) code: u8, + pub(crate) channel: u8, + __pad: Pad<1>, + pub(crate) thread: u8, + pub(crate) unk_flag: U64, +} + +#[versions(AGX)] +pub(crate) const STATS_SZ: usize = { + #[ver(V < V13_0B4)] + { + 0x2c + } + #[ver(V >= V13_0B4)] + { + 0x3c + } +}; + +#[versions(AGX)] +#[derive(Debug, Copy, Clone)] +#[repr(C, u32)] +#[allow(dead_code)] +pub(crate) enum StatsMsg { + Power { + // 0x00 + __pad: Pad<0x18>, + power: U64, + }, + Unk1(Array<{ STATS_SZ::ver }, u8>), + PowerOn { + // 0x02 + off_time: U64, + }, + PowerOff { + // 0x03 + on_time: U64, + }, + Utilization { + // 0x04 + timestamp: U64, + util1: u32, + util2: u32, + util3: u32, + util4: u32, + }, + Unk5(Array<{ STATS_SZ::ver }, u8>), + Unk6(Array<{ STATS_SZ::ver }, u8>), + Unk7(Array<{ STATS_SZ::ver }, u8>), + Unk8(Array<{ STATS_SZ::ver }, u8>), + AvgPower { + // 0x09 + active_cs: U64, + unk2: u32, + unk3: u32, + unk4: u32, + avg_power: u32, + }, + Temperature { + // 0x0a + __pad: Pad<0x8>, + raw_value: u32, + scale: u32, + tmin: u32, + tmax: u32, + }, + PowerState { + // 0x0b + timestamp: U64, + last_busy_ts: U64, + active: u32, + poweroff: u32, + unk1: u32, + pstate: u32, + unk2: u32, + unk3: u32, + }, + FwBusy { + // 0x0c + timestamp: U64, + busy: u32, + }, + PState { + // 0x0d + __pad: Pad<0x8>, + ps_min: u32, + unk1: u32, + ps_max: u32, + unk2: u32, + }, + TempSensor { + // 0x0e + __pad: Pad<0x4>, + sensor_id: u32, + raw_value: u32, + scale: u32, + tmin: u32, + tmax: u32, + }, // Max discriminant: 0xe +} + +#[versions(AGX)] +static_assert!(core::mem::size_of::() == 4 + STATS_SZ::ver); + +#[versions(AGX)] +pub(crate) const STATS_MAX: u32 = 0xe; + +#[versions(AGX)] +#[derive(Copy, Clone)] +#[repr(C)] +pub(crate) union RawStatsMsg { + pub(crate) raw: (u32, Array<{ STATS_SZ::ver }, u8>), + pub(crate) msg: StatsMsg::ver, +} + +#[versions(AGX)] +default_zeroed!(RawStatsMsg::ver); diff --git a/drivers/gpu/drm/asahi/fw/compute.rs b/drivers/gpu/drm/asahi/fw/compute.rs new file mode 100644 index 00000000000000..f5f6ffa9d8d0d8 --- /dev/null +++ b/drivers/gpu/drm/asahi/fw/compute.rs @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU compute job firmware structures + +use super::types::*; +use super::{ + event, + job, + workqueue, // +}; +use crate::{ + microseq, + mmu, // +}; +use kernel::sync::Arc; + +pub(crate) mod raw { + use super::*; + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct JobParameters1<'a> { + pub(crate) preempt_buf1: GpuPointer<'a, &'a [u8]>, + pub(crate) cdm_ctrl_stream_base: U64, + pub(crate) preempt_buf2: GpuPointer<'a, &'a [u8]>, + pub(crate) preempt_buf3: GpuPointer<'a, &'a [u8]>, + pub(crate) preempt_buf4: GpuPointer<'a, &'a [u8]>, + pub(crate) preempt_buf5: GpuPointer<'a, &'a [u8]>, + pub(crate) usc_exec_base_cp: U64, + pub(crate) unk_38: U64, + pub(crate) helper_program: u32, + pub(crate) unk_44: u32, + pub(crate) helper_arg: U64, + pub(crate) helper_cfg: u32, + pub(crate) unk_54: u32, + pub(crate) unk_58: u32, + pub(crate) unk_5c: u32, + pub(crate) iogpu_unk_40: u32, + pub(crate) __pad: Pad<0xfc>, + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct JobParameters2<'a> { + #[ver(V >= V13_0B4)] + pub(crate) unk_0_0: u32, + pub(crate) unk_0: Array<0x24, u8>, + pub(crate) preempt_buf1: GpuPointer<'a, &'a [u8]>, + pub(crate) cdm_ctrl_stream_end: U64, + pub(crate) unk_34: Array<0x20, u8>, + pub(crate) unk_g14x: u32, + pub(crate) unk_58: u32, + #[ver(V < V13_0B4)] + pub(crate) unk_5c: u32, + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct RunCompute<'a> { + pub(crate) tag: workqueue::CommandType, + + #[ver(V >= V13_0B4)] + pub(crate) counter: U64, + + pub(crate) unk_4: u32, + pub(crate) vm_slot: u32, + pub(crate) notifier: GpuPointer<'a, event::Notifier::ver>, + pub(crate) unk_pointee: u32, + #[ver(G < G14X)] + pub(crate) __pad0: Array<0x50, u8>, + #[ver(G < G14X)] + pub(crate) job_params1: JobParameters1<'a>, + #[ver(G >= G14X)] + pub(crate) registers: job::raw::RegisterArray, + pub(crate) __pad1: Array<0x20, u8>, + pub(crate) microsequence: GpuPointer<'a, &'a [u8]>, + pub(crate) microsequence_size: u32, + pub(crate) job_params2: JobParameters2::ver<'a>, + pub(crate) encoder_params: job::raw::EncoderParams, + pub(crate) meta: job::raw::JobMeta, + pub(crate) command_time: U64, + pub(crate) timestamp_pointers: job::raw::TimestampPointers<'a>, + pub(crate) user_timestamp_pointers: job::raw::TimestampPointers<'a>, + pub(crate) client_sequence: u8, + pub(crate) pad_2d1: Array<3, u8>, + pub(crate) unk_2d4: u32, + pub(crate) unk_2d8: u8, + #[ver(V >= V13_0B4)] + pub(crate) context_store_req: U64, + #[ver(V >= V13_0B4)] + pub(crate) context_store_compl: U64, + #[ver(V >= V13_0B4)] + pub(crate) unk_2e9: Array<0x14, u8>, + #[ver(V >= V13_0B4)] + pub(crate) unk_flag: U32, + #[ver(V >= V13_0B4)] + pub(crate) unk_pad: Array<0x10, u8>, + } +} + +#[versions(AGX)] +#[derive(Debug)] +pub(crate) struct RunCompute { + pub(crate) notifier: Arc>, + pub(crate) preempt_buf: GpuArray, + pub(crate) micro_seq: microseq::MicroSequence, + pub(crate) vm_bind: mmu::VmBind, + pub(crate) timestamps: Arc>, + pub(crate) user_timestamps: job::UserTimestamps, +} + +#[versions(AGX)] +impl GpuStruct for RunCompute::ver { + type Raw<'a> = raw::RunCompute::ver<'a>; +} + +#[versions(AGX)] +impl workqueue::Command for RunCompute::ver {} diff --git a/drivers/gpu/drm/asahi/fw/event.rs b/drivers/gpu/drm/asahi/fw/event.rs new file mode 100644 index 00000000000000..52bc456f58707d --- /dev/null +++ b/drivers/gpu/drm/asahi/fw/event.rs @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU events control structures & stamps + +use super::types::*; +use crate::{ + default_zeroed, + trivial_gpustruct, // +}; +use core::sync::atomic::Ordering; + +pub(crate) mod raw { + use super::*; + + #[derive(Debug, Clone, Copy, Default)] + #[repr(C)] + pub(crate) struct LinkedListHead { + pub(crate) prev: Option>, + pub(crate) next: Option>, + } + + #[derive(Debug, Clone, Copy)] + #[repr(C)] + pub(crate) struct NotifierList { + pub(crate) list_head: LinkedListHead, + pub(crate) unkptr_10: U64, + } + default_zeroed!(NotifierList); + + #[versions(AGX)] + #[derive(Debug, Clone, Copy)] + #[repr(C)] + pub(crate) struct NotifierState { + unk_14: u32, + unk_18: U64, + unk_20: u32, + vm_slot: u32, + has_vtx: u32, + pstamp_vtx: Array<4, U64>, + has_frag: u32, + pstamp_frag: Array<4, U64>, + has_comp: u32, + pstamp_comp: Array<4, U64>, + #[ver(G >= G14 && V < V13_0B4)] + unk_98_g14_0: Array<0x14, u8>, + in_list: u32, + list_head: LinkedListHead, + #[ver(G >= G14 && V < V13_0B4)] + unk_a8_g14_0: Pad<4>, + #[ver(V >= V13_0B4)] + pub(crate) unk_buf: Array<0x8, u8>, // Init to all-ff + } + + #[versions(AGX)] + impl Default for NotifierState::ver { + fn default() -> Self { + #[allow(unused_mut)] + // SAFETY: All bit patterns are valid for this type. + let mut s: Self = unsafe { core::mem::zeroed() }; + #[ver(V >= V13_0B4)] + s.unk_buf = Array::new([0xff; 0x8]); + s + } + } + + #[derive(Debug)] + #[repr(transparent)] + pub(crate) struct Threshold(AtomicU64); + default_zeroed!(Threshold); + + impl Threshold { + pub(crate) fn increase(&self, amount: u32) { + // We could use fetch_add, but the non-LSE atomic + // sequence Rust produces confuses the hypervisor. + let v = self.0.load(Ordering::Relaxed); + self.0.store(v + (amount as u64), Ordering::Relaxed); + } + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct Notifier<'a> { + pub(crate) threshold: GpuPointer<'a, super::Threshold>, + pub(crate) generation: AtomicU32, + pub(crate) cur_count: AtomicU32, + pub(crate) unk_10: AtomicU32, + pub(crate) state: NotifierState::ver, + } +} + +trivial_gpustruct!(Threshold); +trivial_gpustruct!(NotifierList); + +#[versions(AGX)] +#[derive(Debug)] +pub(crate) struct Notifier { + pub(crate) threshold: GpuObject, +} + +#[versions(AGX)] +impl GpuStruct for Notifier::ver { + type Raw<'a> = raw::Notifier::ver<'a>; +} diff --git a/drivers/gpu/drm/asahi/fw/fragment.rs b/drivers/gpu/drm/asahi/fw/fragment.rs new file mode 100644 index 00000000000000..3daad1ae4db671 --- /dev/null +++ b/drivers/gpu/drm/asahi/fw/fragment.rs @@ -0,0 +1,296 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU fragment job firmware structures + +use super::types::*; +use super::{ + event, + job, + workqueue, // +}; +use crate::{ + buffer, + fw, + microseq, + mmu, // +}; +use kernel::sync::Arc; + +pub(crate) mod raw { + use super::*; + + #[derive(Debug, Clone, Copy)] + #[repr(C)] + pub(crate) struct BackgroundProgram { + pub(crate) rsrc_spec: U64, + pub(crate) address: U64, + } + + #[derive(Debug, Clone, Copy, Default)] + #[repr(C)] + pub(crate) struct EotProgram { + pub(crate) unk_0: U64, + pub(crate) unk_8: u32, + pub(crate) rsrc_spec: u32, + pub(crate) unk_10: u32, + pub(crate) address: u32, + pub(crate) unk_18: u32, + pub(crate) unk_1c_padding: u32, + } + + impl EotProgram { + pub(crate) fn new(rsrc_spec: u32, address: u32) -> EotProgram { + EotProgram { + rsrc_spec, + address, + ..Default::default() + } + } + } + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct ArrayAddr { + pub(crate) ptr: U64, + pub(crate) unk_padding: U64, + } + + #[versions(AGX)] + #[derive(Debug, Clone, Copy)] + #[repr(C)] + pub(crate) struct AuxFBInfo { + pub(crate) isp_ctl: u32, + pub(crate) unk2: u32, + pub(crate) width: u32, + pub(crate) height: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk3: U64, + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct JobParameters1<'a> { + pub(crate) utile_config: u32, + pub(crate) unk_4: u32, + pub(crate) bg: BackgroundProgram, + pub(crate) ppp_multisamplectl: U64, + pub(crate) isp_scissor_base: U64, + pub(crate) isp_dbias_base: U64, + pub(crate) aux_fb_info: AuxFBInfo::ver, + pub(crate) isp_zls_pixels: U64, + pub(crate) isp_oclqry_base: U64, + pub(crate) zls_ctrl: U64, + + #[ver(G >= G14)] + pub(crate) unk_58_g14_0: U64, + #[ver(G >= G14)] + pub(crate) unk_58_g14_8: U64, + + pub(crate) z_load: U64, + pub(crate) z_store: U64, + pub(crate) s_load: U64, + pub(crate) s_store: U64, + + #[ver(G >= G14)] + pub(crate) unk_68_g14_0: Array<0x20, u8>, + + pub(crate) z_load_stride: U64, + pub(crate) z_store_stride: U64, + pub(crate) s_load_stride: U64, + pub(crate) s_store_stride: U64, + pub(crate) z_load_comp: U64, + pub(crate) z_load_comp_stride: U64, + pub(crate) z_store_comp: U64, + pub(crate) z_store_comp_stride: U64, + pub(crate) s_load_comp: U64, + pub(crate) s_load_comp_stride: U64, + pub(crate) s_store_comp: U64, + pub(crate) s_store_comp_stride: U64, + pub(crate) tvb_tilemap: GpuPointer<'a, &'a [u8]>, + pub(crate) tvb_layermeta: GpuPointer<'a, &'a [u8]>, + pub(crate) mtile_stride_dwords: U64, + pub(crate) tvb_heapmeta: GpuPointer<'a, &'a [u8]>, + pub(crate) tile_config: U64, + pub(crate) aux_fb: GpuPointer<'a, &'a [u8]>, + pub(crate) unk_108: Array<0x6, U64>, + pub(crate) usc_exec_base_isp: U64, + pub(crate) unk_140: U64, + pub(crate) helper_program: u32, + pub(crate) unk_14c: u32, + pub(crate) helper_arg: U64, + pub(crate) unk_158: U64, + pub(crate) unk_160: U64, + + #[ver(G < G14)] + pub(crate) __pad: Pad<0x1d8>, + #[ver(G >= G14)] + pub(crate) __pad: Pad<0x1a8>, + #[ver(V < V13_0B4)] + pub(crate) __pad1: Pad<0x8>, + } + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct JobParameters2 { + pub(crate) eot_rsrc_spec: u32, + pub(crate) eot_usc: u32, + pub(crate) unk_8: u32, + pub(crate) unk_c: u32, + pub(crate) isp_merge_upper_x: F32, + pub(crate) isp_merge_upper_y: F32, + pub(crate) unk_18: U64, + pub(crate) utiles_per_mtile_y: u16, + pub(crate) utiles_per_mtile_x: u16, + pub(crate) unk_24: u32, + pub(crate) tile_counts: u32, + pub(crate) tib_blocks: u32, + pub(crate) isp_bgobjdepth: u32, + pub(crate) isp_bgobjvals: u32, + pub(crate) unk_38: u32, + pub(crate) unk_3c: u32, + pub(crate) helper_cfg: u32, + pub(crate) __pad: Pad<0xac>, + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct JobParameters3 { + pub(crate) isp_dbias_base: ArrayAddr, + pub(crate) isp_scissor_base: ArrayAddr, + pub(crate) isp_oclqry_base: U64, + pub(crate) unk_118: U64, + pub(crate) unk_120: Array<0x25, U64>, + pub(crate) unk_partial_bg: BackgroundProgram, + pub(crate) unk_258: U64, + pub(crate) unk_260: U64, + pub(crate) unk_268: U64, + pub(crate) unk_270: U64, + pub(crate) partial_bg: BackgroundProgram, + pub(crate) zls_ctrl: U64, + pub(crate) unk_290: U64, + pub(crate) z_load: U64, + pub(crate) z_partial_stride: U64, + pub(crate) z_partial_comp_stride: U64, + pub(crate) z_store: U64, + pub(crate) z_partial: U64, + pub(crate) z_partial_comp: U64, + pub(crate) s_load: U64, + pub(crate) s_partial_stride: U64, + pub(crate) s_partial_comp_stride: U64, + pub(crate) s_store: U64, + pub(crate) s_partial: U64, + pub(crate) s_partial_comp: U64, + pub(crate) unk_2f8: Array<2, U64>, + pub(crate) tib_blocks: u32, + pub(crate) unk_30c: u32, + pub(crate) aux_fb_info: AuxFBInfo::ver, + pub(crate) tile_config: U64, + pub(crate) unk_328_padding: Array<0x8, u8>, + pub(crate) unk_partial_eot: EotProgram, + pub(crate) partial_eot: EotProgram, + pub(crate) isp_bgobjdepth: u32, + pub(crate) isp_bgobjvals: u32, + pub(crate) sample_size: u32, + pub(crate) unk_37c: u32, + pub(crate) unk_380: U64, + pub(crate) unk_388: U64, + + #[ver(V >= V13_0B4)] + pub(crate) unk_390_0: U64, + + pub(crate) isp_zls_pixels: U64, + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct RunFragment<'a> { + pub(crate) tag: workqueue::CommandType, + + #[ver(V >= V13_0B4)] + pub(crate) counter: U64, + + pub(crate) vm_slot: u32, + pub(crate) unk_8: u32, + pub(crate) microsequence: GpuPointer<'a, &'a [u8]>, + pub(crate) microsequence_size: u32, + pub(crate) notifier: GpuPointer<'a, event::Notifier::ver>, + pub(crate) buffer: GpuPointer<'a, fw::buffer::Info::ver>, + pub(crate) scene: GpuPointer<'a, fw::buffer::Scene::ver>, + pub(crate) unk_buffer_buf: GpuWeakPointer<[u8]>, + pub(crate) tvb_tilemap: GpuPointer<'a, &'a [u8]>, + pub(crate) ppp_multisamplectl: U64, + pub(crate) samples: u32, + pub(crate) tiles_per_mtile_y: u16, + pub(crate) tiles_per_mtile_x: u16, + pub(crate) unk_50: U64, + pub(crate) unk_58: U64, + pub(crate) isp_merge_upper_x: F32, + pub(crate) isp_merge_upper_y: F32, + pub(crate) unk_68: U64, + pub(crate) tile_count: U64, + + #[ver(G < G14X)] + pub(crate) job_params1: JobParameters1::ver<'a>, + #[ver(G < G14X)] + pub(crate) job_params2: JobParameters2, + #[ver(G >= G14X)] + pub(crate) registers: job::raw::RegisterArray, + + pub(crate) job_params3: JobParameters3::ver, + pub(crate) unk_758_flag: u32, + pub(crate) unk_75c_flag: u32, + pub(crate) unk_buf: Array<0x110, u8>, + pub(crate) busy_flag: u32, + pub(crate) tvb_overflow_count: u32, + pub(crate) unk_878: u32, + pub(crate) encoder_params: job::raw::EncoderParams, + pub(crate) process_empty_tiles: u32, + pub(crate) no_clear_pipeline_textures: u32, + pub(crate) msaa_zs: u32, + pub(crate) unk_pointee: u32, + #[ver(V >= V13_3)] + pub(crate) unk_v13_3: u32, + pub(crate) meta: job::raw::JobMeta, + pub(crate) unk_after_meta: u32, + pub(crate) unk_buf_0: U64, + pub(crate) unk_buf_8: U64, + pub(crate) unk_buf_10: U64, + pub(crate) command_time: U64, + pub(crate) timestamp_pointers: job::raw::TimestampPointers<'a>, + pub(crate) user_timestamp_pointers: job::raw::TimestampPointers<'a>, + pub(crate) client_sequence: u8, + pub(crate) pad_925: Array<3, u8>, + pub(crate) unk_928: u32, + pub(crate) unk_92c: u8, + + #[ver(V >= V13_0B4)] + pub(crate) unk_ts: U64, + + #[ver(V >= V13_0B4)] + pub(crate) unk_92d_8: Array<0x1b, u8>, + } +} + +#[versions(AGX)] +#[derive(Debug)] +pub(crate) struct RunFragment { + pub(crate) notifier: Arc>, + pub(crate) scene: Arc, + pub(crate) micro_seq: microseq::MicroSequence, + pub(crate) vm_bind: mmu::VmBind, + pub(crate) aux_fb: GpuArray, + pub(crate) timestamps: Arc>, + pub(crate) user_timestamps: job::UserTimestamps, +} + +#[versions(AGX)] +impl GpuStruct for RunFragment::ver { + type Raw<'a> = raw::RunFragment::ver<'a>; +} + +#[versions(AGX)] +impl workqueue::Command for RunFragment::ver {} diff --git a/drivers/gpu/drm/asahi/fw/initdata.rs b/drivers/gpu/drm/asahi/fw/initdata.rs new file mode 100644 index 00000000000000..7c7488e950acef --- /dev/null +++ b/drivers/gpu/drm/asahi/fw/initdata.rs @@ -0,0 +1,1352 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU initialization / global structures + +use super::channels; +use super::types::*; +use crate::{ + default_zeroed, + gem, + mmu, + no_debug, + trivial_gpustruct, // +}; + +pub(crate) mod raw { + use super::*; + + #[derive(Debug, Default)] + #[repr(C)] + pub(crate) struct ChannelRing { + pub(crate) state: Option>, + pub(crate) ring: Option>, + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct PipeChannels { + pub(crate) vtx: ChannelRing, + pub(crate) frag: ChannelRing, + pub(crate) comp: ChannelRing, + } + #[versions(AGX)] + default_zeroed!(PipeChannels::ver); + + #[derive(Debug, Default)] + #[repr(C)] + pub(crate) struct FwStatusFlags { + pub(crate) halt_count: AtomicU64, + __pad0: Pad<0x8>, + pub(crate) halted: AtomicU32, + __pad1: Pad<0xc>, + pub(crate) resume: AtomicU32, + __pad2: Pad<0xc>, + pub(crate) unk_40: u32, + __pad3: Pad<0xc>, + pub(crate) unk_ctr: u32, + __pad4: Pad<0xc>, + pub(crate) unk_60: u32, + __pad5: Pad<0xc>, + pub(crate) unk_70: u32, + __pad6: Pad<0xc>, + } + + #[derive(Debug, Default)] + #[repr(C)] + pub(crate) struct FwStatus { + pub(crate) fwctl_channel: ChannelRing, + pub(crate) flags: FwStatusFlags, + } + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct HwDataShared1 { + pub(crate) table: Array<16, i32>, + pub(crate) unk_44: Array<0x60, u8>, + pub(crate) unk_a4: u32, + pub(crate) unk_a8: u32, + } + default_zeroed!(HwDataShared1); + + #[derive(Debug, Default)] + #[repr(C)] + pub(crate) struct HwDataShared2Curve { + pub(crate) unk_0: u32, + pub(crate) unk_4: u32, + pub(crate) t1: Array<16, u16>, + pub(crate) t2: Array<16, i16>, + pub(crate) t3: Array<8, Array<16, i32>>, + } + + #[derive(Debug, Default)] + #[repr(C)] + pub(crate) struct HwDataShared2G14 { + pub(crate) unk_0: Array<5, u32>, + pub(crate) unk_14: u32, + pub(crate) unk_18: Array<8, u32>, + pub(crate) curve1: HwDataShared2Curve, + pub(crate) curve2: HwDataShared2Curve, + } + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct HwDataShared2 { + pub(crate) table: Array<10, i32>, + pub(crate) unk_28: Array<0x10, u8>, + pub(crate) g14: HwDataShared2G14, + pub(crate) unk_500: u32, + pub(crate) unk_504: u32, + pub(crate) unk_508: u32, + pub(crate) unk_50c: u32, + } + default_zeroed!(HwDataShared2); + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct HwDataShared3 { + pub(crate) unk_0: u32, + pub(crate) unk_4: u32, + pub(crate) unk_8: u32, + pub(crate) table: Array<16, u32>, + pub(crate) unk_4c: u32, + } + default_zeroed!(HwDataShared3); + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct HwDataA130Extra { + pub(crate) unk_0: Array<0x38, u8>, + pub(crate) unk_38: u32, + pub(crate) unk_3c: u32, + pub(crate) gpu_se_inactive_threshold: u32, + pub(crate) unk_44: u32, + pub(crate) gpu_se_engagement_criteria: i32, + pub(crate) gpu_se_reset_criteria: u32, + pub(crate) unk_50: u32, + pub(crate) unk_54: u32, + pub(crate) unk_58: u32, + pub(crate) unk_5c: u32, + pub(crate) gpu_se_filter_a_neg: F32, + pub(crate) gpu_se_filter_1_a_neg: F32, + pub(crate) gpu_se_filter_a: F32, + pub(crate) gpu_se_filter_1_a: F32, + pub(crate) gpu_se_ki_dt: F32, + pub(crate) gpu_se_ki_1_dt: F32, + pub(crate) unk_78: F32, + pub(crate) unk_7c: F32, + pub(crate) gpu_se_kp: F32, + pub(crate) gpu_se_kp_1: F32, + pub(crate) unk_88: u32, + pub(crate) unk_8c: u32, + pub(crate) max_pstate_scaled_1: u32, + pub(crate) unk_94: u32, + pub(crate) unk_98: u32, + pub(crate) unk_9c: F32, + pub(crate) unk_a0: u32, + pub(crate) unk_a4: u32, + pub(crate) gpu_se_filter_time_constant_ms: u32, + pub(crate) gpu_se_filter_time_constant_1_ms: u32, + pub(crate) gpu_se_filter_time_constant_clks: U64, + pub(crate) gpu_se_filter_time_constant_1_clks: U64, + pub(crate) unk_c0: u32, + pub(crate) unk_c4: F32, + pub(crate) unk_c8: Array<0x4c, u8>, + pub(crate) unk_114: F32, + pub(crate) unk_118: u32, + pub(crate) unk_11c: u32, + pub(crate) unk_120: u32, + pub(crate) unk_124: u32, + pub(crate) max_pstate_scaled_2: u32, + pub(crate) unk_12c: Array<0x8c, u8>, + } + default_zeroed!(HwDataA130Extra); + + #[repr(C)] + pub(crate) struct T81xxData { + pub(crate) unk_d8c: u32, + pub(crate) unk_d90: u32, + pub(crate) unk_d94: u32, + pub(crate) unk_d98: u32, + pub(crate) unk_d9c: F32, + pub(crate) unk_da0: u32, + pub(crate) unk_da4: F32, + pub(crate) unk_da8: u32, + pub(crate) unk_dac: F32, + pub(crate) unk_db0: u32, + pub(crate) unk_db4: u32, + pub(crate) unk_db8: F32, + pub(crate) unk_dbc: F32, + pub(crate) unk_dc0: u32, + pub(crate) unk_dc4: u32, + pub(crate) unk_dc8: u32, + pub(crate) max_pstate_scaled: u32, + } + default_zeroed!(T81xxData); + + #[versions(AGX)] + #[derive(Default, Copy, Clone)] + #[repr(C)] + pub(crate) struct PowerZone { + pub(crate) val: F32, + pub(crate) target: u32, + pub(crate) target_off: u32, + pub(crate) filter_tc_x4: u32, + pub(crate) filter_tc_xperiod: u32, + #[ver(V >= V13_0B4)] + pub(crate) unk_10: u32, + #[ver(V >= V13_0B4)] + pub(crate) unk_14: u32, + pub(crate) filter_a_neg: F32, + pub(crate) filter_a: F32, + pub(crate) pad: u32, + } + + #[versions(AGX)] + const MAX_CORES_PER_CLUSTER: usize = { + #[ver(G >= G14X)] + { + 16 + } + #[ver(G < G14X)] + { + 8 + } + }; + + #[derive(Debug, Default)] + #[repr(C)] + pub(crate) struct AuxLeakCoef { + pub(crate) afr_1: Array<2, F32>, + pub(crate) cs_1: Array<2, F32>, + pub(crate) afr_2: Array<2, F32>, + pub(crate) cs_2: Array<2, F32>, + } + + #[versions(AGX)] + #[repr(C)] + pub(crate) struct HwDataA { + pub(crate) unk_0: u32, + pub(crate) clocks_per_period: u32, + + #[ver(V >= V13_0B4)] + pub(crate) clocks_per_period_2: u32, + + pub(crate) unk_8: u32, + pub(crate) pwr_status: AtomicU32, + pub(crate) unk_10: F32, + pub(crate) unk_14: u32, + pub(crate) unk_18: u32, + pub(crate) unk_1c: u32, + pub(crate) unk_20: u32, + pub(crate) unk_24: u32, + pub(crate) actual_pstate: u32, + pub(crate) tgt_pstate: u32, + pub(crate) unk_30: u32, + pub(crate) cur_pstate: u32, + pub(crate) unk_38: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_3c_0: u32, + + pub(crate) base_pstate_scaled: u32, + pub(crate) unk_40: u32, + pub(crate) max_pstate_scaled: u32, + pub(crate) unk_48: u32, + pub(crate) min_pstate_scaled: u32, + pub(crate) freq_mhz: F32, + pub(crate) unk_54: Array<0x20, u8>, + + #[ver(V >= V13_0B4)] + pub(crate) unk_74_0: u32, + + pub(crate) sram_k: Array<0x10, F32>, + pub(crate) unk_b4: Array<0x100, u8>, + pub(crate) unk_1b4: u32, + pub(crate) temp_c: u32, + pub(crate) avg_power_mw: u32, + pub(crate) update_ts: U64, + pub(crate) unk_1c8: u32, + pub(crate) unk_1cc: Array<0x478, u8>, + pub(crate) pad_644: Pad<0x8>, + pub(crate) unk_64c: u32, + pub(crate) unk_650: u32, + pub(crate) pad_654: u32, + pub(crate) pwr_filter_a_neg: F32, + pub(crate) pad_65c: u32, + pub(crate) pwr_filter_a: F32, + pub(crate) pad_664: u32, + pub(crate) pwr_integral_gain: F32, + pub(crate) pad_66c: u32, + pub(crate) pwr_integral_min_clamp: F32, + pub(crate) max_power_1: F32, + pub(crate) pwr_proportional_gain: F32, + pub(crate) pad_67c: u32, + pub(crate) pwr_pstate_related_k: F32, + pub(crate) pwr_pstate_max_dc_offset: i32, + pub(crate) unk_688: u32, + pub(crate) max_pstate_scaled_2: u32, + pub(crate) pad_690: u32, + pub(crate) unk_694: u32, + pub(crate) max_power_2: u32, + pub(crate) pad_69c: Pad<0x18>, + pub(crate) unk_6b4: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_6b8_0: Array<0x10, u8>, + + pub(crate) max_pstate_scaled_3: u32, + pub(crate) unk_6bc: u32, + pub(crate) pad_6c0: Pad<0x14>, + pub(crate) ppm_filter_tc_periods_x4: u32, + pub(crate) unk_6d8: u32, + pub(crate) pad_6dc: u32, + pub(crate) ppm_filter_a_neg: F32, + pub(crate) pad_6e4: u32, + pub(crate) ppm_filter_a: F32, + pub(crate) pad_6ec: u32, + pub(crate) ppm_ki_dt: F32, + pub(crate) pad_6f4: u32, + pub(crate) pwr_integral_min_clamp_2: u32, + pub(crate) unk_6fc: F32, + pub(crate) ppm_kp: F32, + pub(crate) pad_704: u32, + pub(crate) unk_708: u32, + pub(crate) pwr_min_duty_cycle: u32, + pub(crate) max_pstate_scaled_4: u32, + pub(crate) unk_714: u32, + pub(crate) pad_718: u32, + pub(crate) unk_71c: F32, + pub(crate) max_power_3: u32, + pub(crate) cur_power_mw_2: u32, + pub(crate) ppm_filter_tc_ms: u32, + pub(crate) unk_72c: u32, + + #[ver(V >= V13_0B4)] + pub(crate) ppm_filter_tc_clks: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_730_4: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_730_8: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_730_c: u32, + + pub(crate) unk_730: F32, + pub(crate) unk_734: u32, + pub(crate) unk_738: u32, + pub(crate) unk_73c: u32, + pub(crate) unk_740: u32, + pub(crate) unk_744: u32, + pub(crate) unk_748: Array<0x4, F32>, + pub(crate) unk_758: u32, + pub(crate) perf_tgt_utilization: u32, + pub(crate) pad_760: u32, + pub(crate) perf_boost_min_util: u32, + pub(crate) perf_boost_ce_step: u32, + pub(crate) perf_reset_iters: u32, + pub(crate) pad_770: u32, + pub(crate) unk_774: u32, + pub(crate) unk_778: u32, + pub(crate) perf_filter_drop_threshold: u32, + pub(crate) perf_filter_a_neg: F32, + pub(crate) perf_filter_a2_neg: F32, + pub(crate) perf_filter_a: F32, + pub(crate) perf_filter_a2: F32, + pub(crate) perf_ki: F32, + pub(crate) perf_ki2: F32, + pub(crate) perf_integral_min_clamp: F32, + pub(crate) unk_79c: F32, + pub(crate) perf_kp: F32, + pub(crate) perf_kp2: F32, + pub(crate) boost_state_unk_k: F32, + pub(crate) base_pstate_scaled_2: u32, + pub(crate) max_pstate_scaled_5: u32, + pub(crate) base_pstate_scaled_3: u32, + pub(crate) pad_7b8: u32, + pub(crate) perf_cur_utilization: F32, + pub(crate) perf_tgt_utilization_2: u32, + pub(crate) pad_7c4: Pad<0x18>, + pub(crate) unk_7dc: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_7e0_0: Array<0x10, u8>, + + pub(crate) base_pstate_scaled_4: u32, + pub(crate) pad_7e4: u32, + pub(crate) unk_7e8: Array<0x14, u8>, + pub(crate) unk_7fc: F32, + pub(crate) pwr_min_duty_cycle_2: F32, + pub(crate) max_pstate_scaled_6: F32, + pub(crate) max_freq_mhz: u32, + pub(crate) pad_80c: u32, + pub(crate) unk_810: u32, + pub(crate) pad_814: u32, + pub(crate) pwr_min_duty_cycle_3: u32, + pub(crate) unk_81c: u32, + pub(crate) pad_820: u32, + pub(crate) min_pstate_scaled_4: F32, + pub(crate) max_pstate_scaled_7: u32, + pub(crate) unk_82c: u32, + pub(crate) unk_alpha_neg: F32, + pub(crate) unk_alpha: F32, + pub(crate) unk_838: u32, + pub(crate) unk_83c: u32, + pub(crate) pad_840: Pad<0x2c>, + pub(crate) unk_86c: u32, + pub(crate) fast_die0_sensor_mask: U64, + #[ver(G >= G14X)] + pub(crate) fast_die1_sensor_mask: U64, + pub(crate) fast_die0_release_temp_cc: u32, + pub(crate) unk_87c: i32, + pub(crate) unk_880: u32, + pub(crate) unk_884: u32, + pub(crate) pad_888: u32, + pub(crate) unk_88c: u32, + pub(crate) pad_890: u32, + pub(crate) unk_894: F32, + pub(crate) pad_898: u32, + pub(crate) fast_die0_ki_dt: F32, + pub(crate) pad_8a0: u32, + pub(crate) unk_8a4: u32, + pub(crate) unk_8a8: F32, + pub(crate) fast_die0_kp: F32, + pub(crate) pad_8b0: u32, + pub(crate) unk_8b4: u32, + pub(crate) pwr_min_duty_cycle_4: u32, + pub(crate) max_pstate_scaled_8: u32, + pub(crate) max_pstate_scaled_9: u32, + pub(crate) fast_die0_prop_tgt_delta: u32, + pub(crate) unk_8c8: u32, + pub(crate) unk_8cc: u32, + pub(crate) pad_8d0: Pad<0x14>, + + #[ver(V >= V13_0B4)] + pub(crate) unk_8e4_0: Array<0x10, u8>, + + pub(crate) unk_8e4: u32, + pub(crate) unk_8e8: u32, + pub(crate) max_pstate_scaled_10: u32, + pub(crate) unk_8f0: u32, + pub(crate) unk_8f4: u32, + pub(crate) pad_8f8: u32, + pub(crate) pad_8fc: u32, + pub(crate) unk_900: Array<0x24, u8>, + + pub(crate) unk_coef_a1: Array<8, Array>, + pub(crate) unk_coef_a2: Array<8, Array>, + + pub(crate) pad_b24: Pad<0x70>, + pub(crate) max_pstate_scaled_11: u32, + pub(crate) freq_with_off: u32, + pub(crate) unk_b9c: u32, + pub(crate) unk_ba0: U64, + pub(crate) unk_ba8: U64, + pub(crate) unk_bb0: u32, + pub(crate) unk_bb4: u32, + + #[ver(V >= V13_3)] + pub(crate) pad_bb8_0: Pad<0x200>, + #[ver(V >= V13_5)] + pub(crate) pad_bb8_200: Pad<0x8>, + + pub(crate) pad_bb8: Pad<0x74>, + pub(crate) unk_c2c: u32, + pub(crate) power_zone_count: u32, + pub(crate) max_power_4: u32, + pub(crate) max_power_5: u32, + pub(crate) max_power_6: u32, + pub(crate) unk_c40: u32, + pub(crate) unk_c44: F32, + pub(crate) avg_power_target_filter_a_neg: F32, + pub(crate) avg_power_target_filter_a: F32, + pub(crate) avg_power_target_filter_tc_x4: u32, + pub(crate) avg_power_target_filter_tc_xperiod: u32, + + #[ver(V >= V13_0B4)] + pub(crate) avg_power_target_filter_tc_clks: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_c58_4: u32, + + pub(crate) power_zones: Array<5, PowerZone::ver>, + pub(crate) avg_power_filter_tc_periods_x4: u32, + pub(crate) unk_cfc: u32, + pub(crate) unk_d00: u32, + pub(crate) avg_power_filter_a_neg: F32, + pub(crate) unk_d08: u32, + pub(crate) avg_power_filter_a: F32, + pub(crate) unk_d10: u32, + pub(crate) avg_power_ki_dt: F32, + pub(crate) unk_d18: u32, + pub(crate) unk_d1c: u32, + pub(crate) unk_d20: F32, + pub(crate) avg_power_kp: F32, + pub(crate) unk_d28: u32, + pub(crate) unk_d2c: u32, + pub(crate) avg_power_min_duty_cycle: u32, + pub(crate) max_pstate_scaled_12: u32, + pub(crate) max_pstate_scaled_13: u32, + pub(crate) unk_d3c: u32, + pub(crate) max_power_7: F32, + pub(crate) max_power_8: u32, + pub(crate) unk_d48: u32, + pub(crate) avg_power_filter_tc_ms: u32, + pub(crate) unk_d50: u32, + + #[ver(V >= V13_0B4)] + pub(crate) avg_power_filter_tc_clks: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_d54_4: Array<0xc, u8>, + + pub(crate) unk_d54: Array<0x10, u8>, + pub(crate) max_pstate_scaled_14: u32, + pub(crate) unk_d68: Array<0x24, u8>, + + pub(crate) t81xx_data: T81xxData, + + pub(crate) unk_dd0: Array<0x40, u8>, + + #[ver(V >= V13_2)] + pub(crate) unk_e10_pad: Array<0x10, u8>, + + #[ver(V >= V13_0B4)] + pub(crate) unk_e10_0: HwDataA130Extra, + + pub(crate) unk_e10: Array<0xc, u8>, + + pub(crate) fast_die0_sensor_mask_2: U64, + #[ver(G >= G14X)] + pub(crate) fast_die1_sensor_mask_2: U64, + + pub(crate) unk_e24: u32, + pub(crate) unk_e28: u32, + pub(crate) unk_e2c: Pad<0x1c>, + pub(crate) unk_coef_b1: Array<8, Array>, + pub(crate) unk_coef_b2: Array<8, Array>, + + #[ver(G >= G14X)] + pub(crate) pad_1048_0: Pad<0x600>, + + pub(crate) pad_1048: Pad<0x5e4>, + + pub(crate) fast_die0_sensor_mask_alt: U64, + #[ver(G >= G14X)] + pub(crate) fast_die1_sensor_mask_alt: U64, + #[ver(V < V13_0B4)] + pub(crate) fast_die0_sensor_present: U64, + + pub(crate) unk_163c: u32, + + pub(crate) unk_1640: Array<0x2000, u8>, + + #[ver(G >= G14X)] + pub(crate) unk_3640_0: Array<0x2000, u8>, + + pub(crate) unk_3640: u32, + pub(crate) unk_3644: u32, + pub(crate) hws1: HwDataShared1, + + #[ver(V >= V13_0B4)] + pub(crate) unk_hws2: Array<16, u16>, + + pub(crate) hws2: HwDataShared2, + pub(crate) unk_3c00: u32, + pub(crate) unk_3c04: u32, + pub(crate) hws3: HwDataShared3, + pub(crate) unk_3c58: Array<0x3c, u8>, + pub(crate) unk_3c94: u32, + pub(crate) unk_3c98: U64, + pub(crate) unk_3ca0: U64, + pub(crate) unk_3ca8: U64, + pub(crate) unk_3cb0: U64, + pub(crate) ts_last_idle: U64, + pub(crate) ts_last_poweron: U64, + pub(crate) ts_last_poweroff: U64, + pub(crate) unk_3cd0: U64, + pub(crate) unk_3cd8: U64, + + #[ver(V >= V13_0B4)] + pub(crate) unk_3ce0_0: u32, + + pub(crate) unk_3ce0: u32, + pub(crate) unk_3ce4: u32, + pub(crate) unk_3ce8: u32, + pub(crate) unk_3cec: u32, + pub(crate) unk_3cf0: u32, + pub(crate) core_leak_coef: Array<8, F32>, + pub(crate) sram_leak_coef: Array<8, F32>, + + #[ver(V >= V13_0B4)] + pub(crate) aux_leak_coef: AuxLeakCoef, + #[ver(V >= V13_0B4)] + pub(crate) unk_3d34_0: Array<0x18, u8>, + + pub(crate) unk_3d34: Array<0x38, u8>, + } + #[versions(AGX)] + default_zeroed!(HwDataA::ver); + #[versions(AGX)] + no_debug!(HwDataA::ver); + + #[derive(Debug, Default, Clone, Copy)] + #[repr(C)] + pub(crate) struct IOMapping { + pub(crate) phys_addr: U64, + pub(crate) virt_addr: U64, + pub(crate) total_size: u32, + pub(crate) element_size: u32, + pub(crate) readwrite: U64, + } + + #[versions(AGX)] + const IO_MAPPING_COUNT: usize = { + #[ver(V < V13_0B4)] + { + 0x14 + } + #[ver(V >= V13_0B4 && V < V13_3)] + { + 0x17 + } + #[ver(V >= V13_3 && V < V13_5)] + { + 0x18 + } + #[ver(V >= V13_5)] + { + 0x19 + } + }; + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct HwDataBAuxPStates { + pub(crate) cs_max_pstate: u32, + pub(crate) cs_frequencies: Array<0x10, u32>, + pub(crate) cs_voltages: Array<0x10, Array<0x2, u32>>, + pub(crate) cs_voltages_sram: Array<0x10, Array<0x2, u32>>, + pub(crate) cs_unkpad: u32, + pub(crate) afr_max_pstate: u32, + pub(crate) afr_frequencies: Array<0x8, u32>, + pub(crate) afr_voltages: Array<0x8, Array<0x2, u32>>, + pub(crate) afr_voltages_sram: Array<0x8, Array<0x2, u32>>, + pub(crate) afr_unkpad: u32, + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct HwDataB { + #[ver(V < V13_0B4)] + pub(crate) unk_0: U64, + + pub(crate) unk_8: U64, + + #[ver(V < V13_0B4)] + pub(crate) unk_10: U64, + + pub(crate) unk_18: U64, + pub(crate) unk_20: U64, + pub(crate) unk_28: U64, + pub(crate) unk_30: U64, + pub(crate) timestamp_area_base: U64, + pub(crate) pad_40: Pad<0x20>, + + #[ver(V < V13_0B4)] + pub(crate) yuv_matrices: Array<0xf, Array<3, Array<4, i16>>>, + + #[ver(V >= V13_0B4)] + pub(crate) yuv_matrices: Array<0x3f, Array<3, Array<4, i16>>>, + + pub(crate) pad_1c8: Pad<0x8>, + pub(crate) io_mappings: Array, + + #[ver(V >= V13_0B4)] + pub(crate) sgx_sram_ptr: U64, + + pub(crate) chip_id: u32, + pub(crate) unk_454: u32, + pub(crate) unk_458: u32, + pub(crate) unk_45c: u32, + pub(crate) unk_460: u32, + pub(crate) unk_464: u32, + pub(crate) unk_468: u32, + pub(crate) unk_46c: u32, + pub(crate) unk_470: u32, + pub(crate) unk_474: u32, + pub(crate) unk_478: u32, + pub(crate) unk_47c: u32, + pub(crate) unk_480: u32, + pub(crate) unk_484: u32, + pub(crate) unk_488: u32, + pub(crate) unk_48c: u32, + pub(crate) base_clock_khz: u32, + pub(crate) power_sample_period: u32, + pub(crate) pad_498: Pad<0x4>, + pub(crate) unk_49c: u32, + pub(crate) unk_4a0: u32, + pub(crate) unk_4a4: u32, + pub(crate) pad_4a8: Pad<0x4>, + pub(crate) unk_4ac: u32, + pub(crate) pad_4b0: Pad<0x8>, + pub(crate) unk_4b8: u32, + pub(crate) unk_4bc: Array<0x4, u8>, + pub(crate) unk_4c0: u32, + pub(crate) unk_4c4: u32, + pub(crate) unk_4c8: u32, + pub(crate) unk_4cc: u32, + pub(crate) unk_4d0: u32, + pub(crate) unk_4d4: u32, + pub(crate) unk_4d8: Array<0x4, u8>, + pub(crate) unk_4dc: u32, + pub(crate) unk_4e0: U64, + pub(crate) unk_4e8: u32, + pub(crate) unk_4ec: u32, + pub(crate) unk_4f0: u32, + pub(crate) unk_4f4: u32, + pub(crate) unk_4f8: u32, + pub(crate) unk_4fc: u32, + pub(crate) unk_500: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_504_0: u32, + + pub(crate) unk_504: u32, + pub(crate) unk_508: u32, + pub(crate) unk_50c: u32, + pub(crate) unk_510: u32, + pub(crate) unk_514: u32, + pub(crate) unk_518: u32, + pub(crate) unk_51c: u32, + pub(crate) unk_520: u32, + pub(crate) unk_524: u32, + pub(crate) unk_528: u32, + pub(crate) unk_52c: u32, + pub(crate) unk_530: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_534_0: u32, + + pub(crate) unk_534: u32, + pub(crate) unk_538: u32, + + pub(crate) num_frags: u32, + pub(crate) unk_540: u32, + pub(crate) unk_544: u32, + pub(crate) unk_548: u32, + pub(crate) unk_54c: u32, + pub(crate) unk_550: u32, + pub(crate) unk_554: u32, + pub(crate) uat_ttb_base: U64, + pub(crate) gpu_core_id: u32, + pub(crate) gpu_rev_id: u32, + pub(crate) num_cores: u32, + pub(crate) max_pstate: u32, + + #[ver(V < V13_0B4)] + pub(crate) num_pstates: u32, + + pub(crate) frequencies: Array<0x10, u32>, + pub(crate) voltages: Array<0x10, [u32; 0x8]>, + pub(crate) voltages_sram: Array<0x10, [u32; 0x8]>, + + #[ver(V >= V13_3)] + pub(crate) unk_9f4_0: Pad<64>, + + pub(crate) sram_k: Array<0x10, F32>, + pub(crate) unk_9f4: Array<0x10, u32>, + pub(crate) rel_max_powers: Array<0x10, u32>, + pub(crate) rel_boost_freqs: Array<0x10, u32>, + + #[ver(V >= V13_3)] + pub(crate) unk_arr_0: Array<32, u32>, + + #[ver(V < V13_0B4)] + pub(crate) min_sram_volt: u32, + + #[ver(V < V13_0B4)] + pub(crate) unk_ab8: u32, + + #[ver(V < V13_0B4)] + pub(crate) unk_abc: u32, + + #[ver(V < V13_0B4)] + pub(crate) unk_ac0: u32, + + #[ver(V >= V13_0B4)] + pub(crate) aux_ps: HwDataBAuxPStates, + + #[ver(V >= V13_3)] + pub(crate) pad_ac4_0: Array<0x44c, u8>, + + pub(crate) pad_ac4: Pad<0x8>, + pub(crate) unk_acc: u32, + pub(crate) unk_ad0: u32, + pub(crate) pad_ad4: Pad<0x10>, + pub(crate) unk_ae4: Array<0x4, u32>, + pub(crate) pad_af4: Pad<0x4>, + pub(crate) unk_af8: u32, + pub(crate) pad_afc: Pad<0x8>, + pub(crate) unk_b04: u32, + pub(crate) unk_b08: u32, + pub(crate) unk_b0c: u32, + + #[ver(G >= G14X)] + pub(crate) pad_b10_0: Array<0x8, u8>, + + pub(crate) unk_b10: u32, + pub(crate) timer_offset: U64, + pub(crate) unk_b1c: u32, + pub(crate) unk_b20: u32, + pub(crate) unk_b24: u32, + pub(crate) unk_b28: u32, + pub(crate) unk_b2c: u32, + pub(crate) unk_b30: u32, + pub(crate) unk_b34: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_b38_0: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_b38_4: u32, + + #[ver(V >= V13_3)] + pub(crate) unk_b38_8: u32, + + pub(crate) unk_b38: Array<0xc, u32>, + pub(crate) unk_b68: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_b6c: Array<0xd0, u8>, + + #[ver(G >= G14X)] + pub(crate) unk_c3c_0: Array<0x8, u8>, + + #[ver(G < G14X && V >= V13_5)] + pub(crate) unk_c3c_8: Array<0x10, u8>, + + #[ver(V >= V13_5)] + pub(crate) unk_c3c_18: Array<0x20, u8>, + + #[ver(V >= V13_0B4)] + pub(crate) unk_c3c: u32, + } + #[versions(AGX)] + default_zeroed!(HwDataB::ver); + + #[derive(Debug)] + #[repr(C, packed)] + pub(crate) struct GpuStatsVtx { + // This changes all the time and we don't use it, let's just make it a big buffer + pub(crate) opaque: Array<0x3000, u8>, + } + default_zeroed!(GpuStatsVtx); + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct GpuStatsFrag { + // This changes all the time and we don't use it, let's just make it a big buffer + // except for these two fields which may need init. + #[ver(G >= G14X)] + pub(crate) unk1_0: Array<0x910, u8>, + pub(crate) unk1: Array<0x100, u8>, + pub(crate) cur_stamp_id: i32, + pub(crate) unk2: Array<0x14, u8>, + pub(crate) unk_id: i32, + pub(crate) unk3: Array<0x1000, u8>, + } + + #[versions(AGX)] + impl Default for GpuStatsFrag::ver { + fn default() -> Self { + Self { + #[ver(G >= G14X)] + unk1_0: Default::default(), + unk1: Default::default(), + cur_stamp_id: -1, + unk2: Default::default(), + unk_id: -1, + unk3: Default::default(), + } + } + } + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct GpuGlobalStatsVtx { + pub(crate) total_cmds: u32, + pub(crate) stats: GpuStatsVtx, + } + default_zeroed!(GpuGlobalStatsVtx); + + #[versions(AGX)] + #[derive(Debug, Default)] + #[repr(C)] + pub(crate) struct GpuGlobalStatsFrag { + pub(crate) total_cmds: u32, + pub(crate) unk_4: u32, + pub(crate) stats: GpuStatsFrag::ver, + } + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct GpuStatsComp { + // This changes all the time and we don't use it, let's just make it a big buffer + pub(crate) opaque: Array<0x3000, u8>, + } + default_zeroed!(GpuStatsComp); + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct RuntimeScratch { + pub(crate) unk_280: Array<0x6800, u8>, + pub(crate) unk_6a80: u32, + pub(crate) gpu_idle: u32, + pub(crate) unkpad_6a88: Pad<0x14>, + pub(crate) unk_6a9c: u32, + pub(crate) unk_ctr0: u32, + pub(crate) unk_ctr1: u32, + pub(crate) unk_6aa8: u32, + pub(crate) unk_6aac: u32, + pub(crate) unk_ctr2: u32, + pub(crate) unk_6ab4: u32, + pub(crate) unk_6ab8: u32, + pub(crate) unk_6abc: u32, + pub(crate) unk_6ac0: u32, + pub(crate) unk_6ac4: u32, + pub(crate) unk_ctr3: u32, + pub(crate) unk_6acc: u32, + pub(crate) unk_6ad0: u32, + pub(crate) unk_6ad4: u32, + pub(crate) unk_6ad8: u32, + pub(crate) unk_6adc: u32, + pub(crate) unk_6ae0: u32, + pub(crate) unk_6ae4: u32, + pub(crate) unk_6ae8: u32, + pub(crate) unk_6aec: u32, + pub(crate) unk_6af0: u32, + pub(crate) unk_ctr4: u32, + pub(crate) unk_ctr5: u32, + pub(crate) unk_6afc: u32, + pub(crate) pad_6b00: Pad<0x38>, + + #[ver(G >= G14X)] + pub(crate) pad_6b00_extra: Array<0x4800, u8>, + + pub(crate) unk_6b38: u32, + pub(crate) pad_6b3c: Pad<0x84>, + } + #[versions(AGX)] + default_zeroed!(RuntimeScratch::ver); + + #[versions(AGX)] + #[repr(C)] + pub(crate) struct RuntimePointers<'a> { + pub(crate) pipes: Array<4, PipeChannels::ver>, + + pub(crate) device_control: + ChannelRing, + pub(crate) event: ChannelRing, + pub(crate) fw_log: ChannelRing, + pub(crate) ktrace: ChannelRing, + pub(crate) stats: ChannelRing, + + pub(crate) __pad0: Pad<0x50>, + pub(crate) unk_160: U64, + pub(crate) unk_168: U64, + pub(crate) stats_vtx: GpuPointer<'a, super::GpuGlobalStatsVtx>, + pub(crate) stats_frag: GpuPointer<'a, super::GpuGlobalStatsFrag::ver>, + pub(crate) stats_comp: GpuPointer<'a, super::GpuStatsComp>, + pub(crate) hwdata_a: GpuPointer<'a, super::HwDataA::ver>, + pub(crate) unkptr_190: GpuPointer<'a, &'a [u8]>, + pub(crate) unkptr_198: GpuPointer<'a, &'a [u8]>, + pub(crate) hwdata_b: GpuPointer<'a, super::HwDataB::ver>, + pub(crate) hwdata_b_2: GpuPointer<'a, super::HwDataB::ver>, + pub(crate) fwlog_buf: Option>, + pub(crate) unkptr_1b8: GpuPointer<'a, &'a [u8]>, + + #[ver(G < G14X)] + pub(crate) unkptr_1c0: GpuPointer<'a, &'a [u8]>, + #[ver(G < G14X)] + pub(crate) unkptr_1c8: GpuPointer<'a, &'a [u8]>, + + pub(crate) unk_1d0: u32, + pub(crate) unk_1d4: u32, + pub(crate) unk_1d8: Array<0x3c, u8>, + pub(crate) buffer_mgr_ctl_gpu_addr: U64, + pub(crate) buffer_mgr_ctl_fw_addr: U64, + pub(crate) __pad1: Pad<0x5c>, + pub(crate) gpu_scratch: RuntimeScratch::ver, + } + #[versions(AGX)] + no_debug!(RuntimePointers::ver<'_>); + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct PendingStamp { + pub(crate) info: AtomicU32, + pub(crate) wait_value: AtomicU32, + } + default_zeroed!(PendingStamp); + + #[derive(Debug, Clone, Copy)] + #[repr(C, packed)] + pub(crate) struct FaultInfo { + pub(crate) unk_0: u32, + pub(crate) unk_4: u32, + pub(crate) queue_uuid: u32, + pub(crate) unk_c: u32, + pub(crate) unk_10: u32, + pub(crate) unk_14: u32, + } + default_zeroed!(FaultInfo); + + #[derive(Debug, Clone, Copy)] + #[repr(C)] + pub(crate) struct PowerZoneGlobal { + pub(crate) target: u32, + pub(crate) target_off: u32, + pub(crate) filter_tc: u32, + } + default_zeroed!(PowerZoneGlobal); + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct Globals { + pub(crate) ktrace_enable: u32, + pub(crate) unk_4: Array<0x20, u8>, + + #[ver(V >= V13_2)] + pub(crate) unk_24_0: u32, + + pub(crate) unk_24: u32, + + #[ver(V >= V13_0B4)] + pub(crate) debug: u32, + + #[ver(V >= V13_3)] + pub(crate) unk_28_4: u32, + + pub(crate) unk_28: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_2c_0: u32, + + pub(crate) unk_2c: u32, + pub(crate) unk_30: u32, + pub(crate) unk_34: u32, + pub(crate) unk_38: Array<0x1c, u8>, + + // pub(crate) sub: GlobalsSub::ver, + pub(crate) unk_54: u16, + pub(crate) unk_56: u16, + pub(crate) unk_58: u16, + pub(crate) unk_5a: U32, + pub(crate) unk_5e: U32, + pub(crate) unk_62: U32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_66_0: Array<0xc, u8>, + + pub(crate) unk_66: U32, + pub(crate) unk_6a: Array<0x16, u8>, + // end GlobalsSub::ver + + pub(crate) unk_80: Array<0xf80, u8>, + pub(crate) unk_1000: Array<0x7000, u8>, + pub(crate) unk_8000: Array<0x900, u8>, + + #[ver(G >= G14X)] + pub(crate) unk_8900_pad: Array<0x484c, u8>, + + #[ver(V >= V13_3)] + pub(crate) unk_8900_pad2: Array<0x54, u8>, + + pub(crate) unk_8900: u32, + pub(crate) pending_submissions: AtomicU32, + pub(crate) max_power: u32, + pub(crate) max_pstate_scaled: u32, + pub(crate) max_pstate_scaled_2: u32, + pub(crate) unk_8914: u32, + pub(crate) unk_8918: u32, + pub(crate) max_pstate_scaled_3: u32, + pub(crate) unk_8920: u32, + pub(crate) power_zone_count: u32, + pub(crate) avg_power_filter_tc_periods: u32, + pub(crate) avg_power_ki_dt: F32, + pub(crate) avg_power_kp: F32, + pub(crate) avg_power_min_duty_cycle: u32, + pub(crate) avg_power_target_filter_tc: u32, + pub(crate) power_zones: Array<5, PowerZoneGlobal>, + pub(crate) unk_8978: Array<0x44, u8>, + + #[ver(V >= V13_0B4)] + pub(crate) unk_89bc_0: Array<0x3c, u8>, + + pub(crate) unk_89bc: u32, + pub(crate) fast_die0_release_temp: u32, + pub(crate) unk_89c4: i32, + pub(crate) fast_die0_prop_tgt_delta: u32, + pub(crate) fast_die0_kp: F32, + pub(crate) fast_die0_ki_dt: F32, + pub(crate) unk_89d4: Array<0xc, u8>, + pub(crate) unk_89e0: u32, + pub(crate) max_power_2: u32, + pub(crate) ppm_kp: F32, + pub(crate) ppm_ki_dt: F32, + pub(crate) unk_89f0: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_89f4_0: Array<0x8, u8>, + + #[ver(V >= V13_0B4)] + pub(crate) unk_89f4_8: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_89f4_c: Array<0x50, u8>, + + #[ver(V >= V13_3)] + pub(crate) unk_89f4_5c: Array<0xc, u8>, + + pub(crate) unk_89f4: u32, + pub(crate) hws1: HwDataShared1, + pub(crate) hws2: HwDataShared2, + + #[ver(V >= V13_0B4)] + pub(crate) idle_off_standby_timer: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_hws2_4: Array<0x8, F32>, + + #[ver(V >= V13_0B4)] + pub(crate) unk_hws2_24: u32, + + pub(crate) unk_hws2_28: u32, + + pub(crate) hws3: HwDataShared3, + pub(crate) unk_9004: Array<8, u8>, + pub(crate) unk_900c: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_9010_0: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_9010_4: Array<0x14, u8>, + + pub(crate) unk_9010: Array<0x2c, u8>, + pub(crate) unk_903c: u32, + pub(crate) unk_9040: Array<0xc0, u8>, + pub(crate) unk_9100: Array<0x6f00, u8>, + pub(crate) unk_10000: Array<0xe50, u8>, + pub(crate) unk_10e50: u32, + pub(crate) unk_10e54: Array<0x2c, u8>, + + #[ver((G >= G14X && V < V13_3) || (G <= G14 && V >= V13_3))] + pub(crate) unk_x_pad: Array<0x4, u8>, + + // bit 0: sets sgx_reg 0x17620 + // bit 1: sets sgx_reg 0x17630 + pub(crate) fault_control: u32, + pub(crate) do_init: u32, + pub(crate) unk_10e88: Array<0x188, u8>, + pub(crate) idle_ts: U64, + pub(crate) idle_unk: U64, + pub(crate) progress_check_interval_3d: u32, + pub(crate) progress_check_interval_ta: u32, + pub(crate) progress_check_interval_cl: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_1102c_0: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_1102c_4: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_1102c_8: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_1102c_c: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_1102c_10: u32, + + pub(crate) unk_1102c: u32, + pub(crate) idle_off_delay_ms: AtomicU32, + pub(crate) fender_idle_off_delay_ms: u32, + pub(crate) fw_early_wake_timeout_ms: u32, + #[ver(V == V13_3)] + pub(crate) ps_pad_0: Pad<0x8>, + pub(crate) pending_stamps: Array<0x100, PendingStamp>, + #[ver(V != V13_3)] + pub(crate) ps_pad_0: Pad<0x8>, + pub(crate) unkpad_ps: Pad<0x78>, + pub(crate) unk_117bc: u32, + pub(crate) fault_info: FaultInfo, + pub(crate) counter: u32, + pub(crate) unk_118dc: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_118e0_0: Array<0x9c, u8>, + + #[ver(G >= G14X)] + pub(crate) unk_118e0_9c: Array<0x580, u8>, + + #[ver(V >= V13_3)] + pub(crate) unk_118e0_9c_x: Array<0x8, u8>, + + pub(crate) cl_context_switch_timeout_ms: u32, + + #[ver(V >= V13_0B4)] + pub(crate) cl_kill_timeout_ms: u32, + + pub(crate) cdm_context_store_latency_threshold: u32, + pub(crate) unk_118e8: u32, + pub(crate) unk_118ec: Array<0x400, u8>, + pub(crate) unk_11cec: Array<0x54, u8>, + + #[ver(V >= V13_0B4)] + pub(crate) unk_11d40: Array<0x19c, u8>, + + #[ver(V >= V13_0B4)] + pub(crate) unk_11edc: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_11ee0: Array<0x1c, u8>, + + #[ver(V >= V13_0B4)] + pub(crate) unk_11efc: u32, + + #[ver(V >= V13_3)] + pub(crate) unk_11f00: Array<0x280, u8>, + } + #[versions(AGX)] + default_zeroed!(Globals::ver); + + #[derive(Debug, Default, Clone, Copy)] + #[repr(C, packed)] + pub(crate) struct UatLevelInfo { + pub(crate) unk_3: u8, + pub(crate) unk_1: u8, + pub(crate) unk_2: u8, + pub(crate) index_shift: u8, + pub(crate) num_entries: u16, + pub(crate) unk_4: u16, + pub(crate) unk_8: U64, + pub(crate) unk_10: U64, + pub(crate) index_mask: U64, + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct InitData<'a> { + #[ver(V >= V13_0B4)] + pub(crate) ver_info: Array<0x4, u16>, + + pub(crate) unk_buf: GpuPointer<'a, &'a [u8]>, + pub(crate) unk_8: u32, + pub(crate) unk_c: u32, + pub(crate) runtime_pointers: GpuPointer<'a, super::RuntimePointers::ver>, + pub(crate) globals: GpuPointer<'a, super::Globals::ver>, + pub(crate) fw_status: GpuPointer<'a, super::FwStatus>, + pub(crate) uat_page_size: u16, + pub(crate) uat_page_bits: u8, + pub(crate) uat_num_levels: u8, + pub(crate) uat_level_info: Array<0x3, UatLevelInfo>, + pub(crate) __pad0: Pad<0x14>, + pub(crate) host_mapped_fw_allocations: u32, + pub(crate) unk_ac: u32, + pub(crate) unk_b0: u32, + pub(crate) unk_b4: u32, + pub(crate) unk_b8: u32, + } +} + +#[derive(Debug)] +pub(crate) struct ChannelRing +where + for<'a> ::Raw<'a>: Debug, +{ + pub(crate) state: GpuObject, + pub(crate) ring: GpuArray, +} + +impl ChannelRing +where + for<'a> ::Raw<'a>: Debug, +{ + pub(crate) fn to_raw(&self) -> raw::ChannelRing { + raw::ChannelRing { + state: Some(self.state.weak_pointer()), + ring: Some(self.ring.weak_pointer()), + } + } +} + +trivial_gpustruct!(FwStatus); +trivial_gpustruct!(GpuGlobalStatsVtx); +#[versions(AGX)] +trivial_gpustruct!(GpuGlobalStatsFrag::ver); +trivial_gpustruct!(GpuStatsComp); + +#[versions(AGX)] +trivial_gpustruct!(HwDataA::ver); + +#[versions(AGX)] +trivial_gpustruct!(HwDataB::ver); + +#[versions(AGX)] +#[derive(Debug)] +pub(crate) struct Stats { + pub(crate) vtx: GpuObject, + pub(crate) frag: GpuObject, + pub(crate) comp: GpuObject, +} + +#[versions(AGX)] +#[derive(Debug)] +pub(crate) struct RuntimePointers { + pub(crate) stats: Stats::ver, + + pub(crate) hwdata_a: GpuObject, + pub(crate) unkptr_190: GpuArray, + pub(crate) unkptr_198: GpuArray, + pub(crate) hwdata_b: GpuObject, + + pub(crate) unkptr_1b8: GpuArray, + pub(crate) unkptr_1c0: GpuArray, + pub(crate) unkptr_1c8: GpuArray, + + pub(crate) buffer_mgr_ctl: gem::ObjectRef, + pub(crate) buffer_mgr_ctl_low_mapping: Option, + pub(crate) buffer_mgr_ctl_high_mapping: Option, +} + +#[versions(AGX)] +impl GpuStruct for RuntimePointers::ver { + type Raw<'a> = raw::RuntimePointers::ver<'a>; +} + +#[versions(AGX)] +trivial_gpustruct!(Globals::ver); + +#[versions(AGX)] +#[derive(Debug)] +pub(crate) struct InitData { + pub(crate) unk_buf: GpuArray, + pub(crate) runtime_pointers: GpuObject, + pub(crate) globals: GpuObject, + pub(crate) fw_status: GpuObject, +} + +#[versions(AGX)] +impl GpuStruct for InitData::ver { + type Raw<'a> = raw::InitData::ver<'a>; +} diff --git a/drivers/gpu/drm/asahi/fw/job.rs b/drivers/gpu/drm/asahi/fw/job.rs new file mode 100644 index 00000000000000..e4f2f9225ea050 --- /dev/null +++ b/drivers/gpu/drm/asahi/fw/job.rs @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Common GPU job firmware structures + +use super::types::*; +use crate::{ + default_zeroed, + mmu, + trivial_gpustruct, // +}; +use kernel::prelude::Result; +use kernel::sync::Arc; + +pub(crate) mod raw { + use super::*; + + #[derive(Debug, Clone, Copy)] + #[repr(C)] + pub(crate) struct JobMeta { + pub(crate) unk_0: u16, + pub(crate) unk_2: u8, + pub(crate) no_preemption: u8, + pub(crate) stamp: GpuWeakPointer, + pub(crate) fw_stamp: GpuWeakPointer, + pub(crate) stamp_value: EventValue, + pub(crate) stamp_slot: u32, + pub(crate) evctl_index: u32, + pub(crate) flush_stamps: u32, + pub(crate) uuid: u32, + pub(crate) event_seq: u32, + } + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct EncoderParams { + pub(crate) unk_8: u32, + pub(crate) sync_grow: u32, + pub(crate) unk_10: u32, + pub(crate) encoder_id: u32, + pub(crate) unk_18: u32, + pub(crate) unk_mask: u32, + pub(crate) sampler_array: U64, + pub(crate) sampler_count: u32, + pub(crate) sampler_max: u32, + } + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct JobTimestamps { + pub(crate) start: AtomicU64, + pub(crate) end: AtomicU64, + } + default_zeroed!(JobTimestamps); + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct RenderTimestamps { + pub(crate) vtx: JobTimestamps, + pub(crate) frag: JobTimestamps, + } + default_zeroed!(RenderTimestamps); + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct Register { + pub(crate) number: u32, + pub(crate) value: U64, + } + default_zeroed!(Register); + + impl Register { + fn new(number: u32, value: u64) -> Register { + Register { + number, + value: U64(value), + } + } + } + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct RegisterArray { + pub(crate) registers: Array<128, Register>, + pub(crate) pad: Array<0x100, u8>, + + pub(crate) addr: GpuWeakPointer>, + pub(crate) count: u16, + pub(crate) length: u16, + pub(crate) unk_pad: u32, + } + + impl RegisterArray { + pub(crate) fn new( + self_ptr: GpuWeakPointer>, + cb: impl FnOnce(&mut RegisterArray), + ) -> RegisterArray { + let mut array = RegisterArray { + registers: Default::default(), + pad: Default::default(), + addr: self_ptr, + count: 0, + length: 0, + unk_pad: 0, + }; + + cb(&mut array); + + array + } + + pub(crate) fn add(&mut self, number: u32, value: u64) { + self.registers[self.count as usize] = Register::new(number, value); + self.count += 1; + self.length += core::mem::size_of::() as u16; + } + } + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct TimestampPointers<'a> { + pub(crate) start_addr: Option>, + pub(crate) end_addr: Option>, + } +} + +trivial_gpustruct!(JobTimestamps); +trivial_gpustruct!(RenderTimestamps); + +#[derive(Debug)] +pub(crate) struct UserTimestamp { + pub(crate) mapping: Arc, + pub(crate) offset: usize, +} + +#[derive(Debug, Default)] +pub(crate) struct UserTimestamps { + pub(crate) start: Option, + pub(crate) end: Option, +} + +impl UserTimestamps { + pub(crate) fn any(&self) -> bool { + self.start.is_some() || self.end.is_some() + } + + pub(crate) fn pointers(&self) -> Result> { + Ok(raw::TimestampPointers { + start_addr: self + .start + .as_ref() + .map(|a| GpuPointer::from_mapping(&a.mapping, a.offset)) + .transpose()?, + end_addr: self + .end + .as_ref() + .map(|a| GpuPointer::from_mapping(&a.mapping, a.offset)) + .transpose()?, + }) + } +} diff --git a/drivers/gpu/drm/asahi/fw/microseq.rs b/drivers/gpu/drm/asahi/fw/microseq.rs new file mode 100644 index 00000000000000..ff59deda6be615 --- /dev/null +++ b/drivers/gpu/drm/asahi/fw/microseq.rs @@ -0,0 +1,412 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU firmware microsequence operations + +use super::types::*; +use super::{ + buffer, + compute, + fragment, + initdata, + job, + vertex, + workqueue, // +}; +use crate::default_zeroed; + +pub(crate) trait Operation {} + +#[derive(Debug, Copy, Clone)] +#[repr(u32)] +enum OpCode { + WaitForIdle = 0x01, + WaitForIdle2 = 0x02, + RetireStamp = 0x18, + #[allow(dead_code)] + Timestamp = 0x19, + StartVertex = 0x22, + FinalizeVertex = 0x23, + StartFragment = 0x24, + FinalizeFragment = 0x25, + StartCompute = 0x29, + FinalizeCompute = 0x2a, +} + +#[derive(Debug, Copy, Clone)] +#[repr(u32)] +pub(crate) enum Pipe { + Vertex = 1 << 0, + Fragment = 1 << 8, + Compute = 1 << 15, +} + +pub(crate) const MAX_ATTACHMENTS: usize = 16; + +#[derive(Debug, Clone, Copy)] +#[repr(C)] +pub(crate) struct Attachment { + pub(crate) address: U64, + pub(crate) size: u32, + pub(crate) unk_c: u16, + pub(crate) unk_e: u16, +} +default_zeroed!(Attachment); + +#[derive(Debug, Clone, Copy, Default)] +#[repr(C)] +pub(crate) struct Attachments { + pub(crate) list: Array, + pub(crate) count: u32, +} + +#[derive(Debug, Copy, Clone)] +#[repr(transparent)] +pub(crate) struct OpHeader(u32); + +impl OpHeader { + const fn new(opcode: OpCode) -> OpHeader { + OpHeader(opcode as u32) + } + const fn with_args(opcode: OpCode, args: u32) -> OpHeader { + OpHeader(opcode as u32 | args) + } +} + +macro_rules! simple_op { + ($name:ident) => { + #[allow(dead_code)] + #[derive(Debug, Copy, Clone)] + pub(crate) struct $name(OpHeader); + + impl $name { + pub(crate) const HEADER: $name = $name(OpHeader::new(OpCode::$name)); + } + }; +} + +pub(crate) mod op { + use super::*; + + simple_op!(StartVertex); + simple_op!(FinalizeVertex); + simple_op!(StartFragment); + simple_op!(FinalizeFragment); + simple_op!(StartCompute); + simple_op!(FinalizeCompute); + simple_op!(WaitForIdle2); + + #[allow(dead_code)] + #[derive(Debug, Copy, Clone)] + pub(crate) struct RetireStamp(OpHeader); + impl RetireStamp { + pub(crate) const HEADER: RetireStamp = + RetireStamp(OpHeader::with_args(OpCode::RetireStamp, 0x40000000)); + } + + #[allow(dead_code)] + #[derive(Debug, Copy, Clone)] + pub(crate) struct WaitForIdle(OpHeader); + impl WaitForIdle { + pub(crate) const fn new(pipe: Pipe) -> WaitForIdle { + WaitForIdle(OpHeader::with_args(OpCode::WaitForIdle, (pipe as u32) << 8)) + } + } + + #[allow(dead_code)] + #[derive(Debug, Copy, Clone)] + pub(crate) struct Timestamp(OpHeader); + impl Timestamp { + #[allow(dead_code)] + pub(crate) const fn new(flag: bool) -> Timestamp { + Timestamp(OpHeader::with_args(OpCode::Timestamp, (flag as u32) << 31)) + } + } +} + +#[derive(Debug)] +#[repr(C)] +pub(crate) struct WaitForIdle { + pub(crate) header: op::WaitForIdle, +} + +impl Operation for WaitForIdle {} + +#[derive(Debug)] +#[repr(C)] +pub(crate) struct WaitForIdle2 { + pub(crate) header: op::WaitForIdle2, +} + +impl Operation for WaitForIdle2 {} + +#[derive(Debug)] +#[repr(C)] +pub(crate) struct RetireStamp { + pub(crate) header: op::RetireStamp, +} + +impl Operation for RetireStamp {} + +#[versions(AGX)] +#[derive(Debug)] +#[repr(C)] +pub(crate) struct Timestamp<'a> { + pub(crate) header: op::Timestamp, + pub(crate) command_time: GpuWeakPointer, + pub(crate) ts_pointers: GpuWeakPointer>, + // Unused? + pub(crate) update_ts: GpuWeakPointer>>, + pub(crate) work_queue: GpuWeakPointer, + pub(crate) user_ts_pointers: GpuWeakPointer>, + + #[ver(V >= V13_0B4)] + pub(crate) unk_ts: GpuWeakPointer, + + pub(crate) uuid: u32, + pub(crate) unk_30_padding: u32, +} + +#[versions(AGX)] +impl<'a> Operation for Timestamp::ver<'a> {} + +#[versions(AGX)] +#[derive(Debug)] +#[repr(C)] +pub(crate) struct StartVertex<'a> { + pub(crate) header: op::StartVertex, + pub(crate) tiling_params: Option>, + pub(crate) job_params1: Option>>, + #[ver(G >= G14X)] + pub(crate) registers: GpuWeakPointer, + pub(crate) buffer: GpuWeakPointer, + pub(crate) scene: GpuWeakPointer, + pub(crate) stats: GpuWeakPointer, + pub(crate) work_queue: GpuWeakPointer, + pub(crate) vm_slot: u32, + pub(crate) unk_38: u32, + pub(crate) event_generation: u32, + pub(crate) buffer_slot: u32, + pub(crate) unk_44: u32, + pub(crate) event_seq: U64, + pub(crate) unk_50: u32, + pub(crate) unk_pointer: GpuWeakPointer, + pub(crate) unk_job_buf: GpuWeakPointer, + pub(crate) unk_64: u32, + pub(crate) unk_68: u32, + pub(crate) uuid: u32, + pub(crate) attachments: Attachments, + pub(crate) padding: u32, + + #[ver(V >= V13_0B4)] + pub(crate) counter: U64, + + #[ver(V >= V13_0B4)] + pub(crate) notifier_buf: GpuWeakPointer>, + + pub(crate) unk_178: u32, +} + +#[versions(AGX)] +impl<'a> Operation for StartVertex::ver<'a> {} + +#[versions(AGX)] +#[derive(Debug)] +#[repr(C)] +pub(crate) struct FinalizeVertex { + pub(crate) header: op::FinalizeVertex, + pub(crate) scene: GpuWeakPointer, + pub(crate) buffer: GpuWeakPointer, + pub(crate) stats: GpuWeakPointer, + pub(crate) work_queue: GpuWeakPointer, + pub(crate) vm_slot: u32, + pub(crate) unk_28: u32, + pub(crate) unk_pointer: GpuWeakPointer, + pub(crate) unk_34: u32, + pub(crate) uuid: u32, + pub(crate) fw_stamp: GpuWeakPointer, + pub(crate) stamp_value: EventValue, + pub(crate) unk_48: U64, + pub(crate) unk_50: u32, + pub(crate) unk_54: u32, + pub(crate) unk_58: U64, + pub(crate) unk_60: u32, + pub(crate) unk_64: u32, + pub(crate) unk_68: u32, + + #[ver(G >= G14 && V < V13_0B4)] + pub(crate) unk_68_g14: U64, + + pub(crate) restart_branch_offset: i32, + pub(crate) has_attachments: u32, // Check DCMP errors bits 2,3 1=ktrace 2=log 3=panic + + #[ver(V >= V13_0B4)] + pub(crate) unk_74: Array<0x10, u8>, +} + +#[versions(AGX)] +impl Operation for FinalizeVertex::ver {} + +#[versions(AGX)] +#[derive(Debug)] +#[repr(C)] +pub(crate) struct StartFragment<'a> { + pub(crate) header: op::StartFragment, + pub(crate) job_params2: Option>, + pub(crate) job_params1: Option>>, + #[ver(G >= G14X)] + pub(crate) registers: GpuWeakPointer, + pub(crate) scene: GpuPointer<'a, buffer::Scene::ver>, + pub(crate) stats: GpuWeakPointer, + pub(crate) busy_flag: GpuWeakPointer, + pub(crate) tvb_overflow_count: GpuWeakPointer, + pub(crate) unk_pointer: GpuWeakPointer, + pub(crate) work_queue: GpuWeakPointer, + pub(crate) work_item: GpuWeakPointer, + pub(crate) vm_slot: u32, + pub(crate) unk_50: u32, + pub(crate) event_generation: u32, + pub(crate) buffer_slot: u32, + pub(crate) sync_grow: u32, + pub(crate) event_seq: U64, + pub(crate) unk_68: u32, + pub(crate) unk_758_flag: GpuWeakPointer, + pub(crate) unk_job_buf: GpuWeakPointer, + #[ver(V >= V13_3)] + pub(crate) unk_7c_0: U64, + pub(crate) unk_7c: u32, + pub(crate) unk_80: u32, + pub(crate) unk_84: u32, + pub(crate) uuid: u32, + pub(crate) attachments: Attachments, + pub(crate) padding: u32, + + #[ver(V >= V13_0B4)] + pub(crate) counter: U64, + + #[ver(V >= V13_0B4)] + pub(crate) notifier_buf: GpuWeakPointer>, +} + +#[versions(AGX)] +impl<'a> Operation for StartFragment::ver<'a> {} + +#[versions(AGX)] +#[derive(Debug)] +#[repr(C)] +pub(crate) struct FinalizeFragment { + pub(crate) header: op::FinalizeFragment, + pub(crate) uuid: u32, + pub(crate) unk_8: u32, + pub(crate) fw_stamp: GpuWeakPointer, + pub(crate) stamp_value: EventValue, + pub(crate) unk_18: u32, + pub(crate) scene: GpuWeakPointer, + pub(crate) buffer: GpuWeakPointer, + pub(crate) unk_2c: U64, + pub(crate) stats: GpuWeakPointer, + pub(crate) unk_pointer: GpuWeakPointer, + pub(crate) busy_flag: GpuWeakPointer, + pub(crate) work_queue: GpuWeakPointer, + pub(crate) work_item: GpuWeakPointer, + pub(crate) vm_slot: u32, + pub(crate) unk_60: u32, + pub(crate) unk_758_flag: GpuWeakPointer, + #[ver(V >= V13_3)] + pub(crate) unk_6c_0: U64, + pub(crate) unk_6c: U64, + pub(crate) unk_74: U64, + pub(crate) unk_7c: U64, + pub(crate) unk_84: U64, + pub(crate) unk_8c: U64, + + #[ver(G == G14 && V < V13_0B4)] + pub(crate) unk_8c_g14: U64, + + pub(crate) restart_branch_offset: i32, + pub(crate) has_attachments: u32, // Check DCMP errors bits 2,3 1=ktrace 2=log 3=panic + + #[ver(V >= V13_0B4)] + pub(crate) unk_9c: Array<0x10, u8>, +} + +#[versions(AGX)] +impl Operation for FinalizeFragment::ver {} + +#[versions(AGX)] +#[derive(Debug)] +#[repr(C)] +pub(crate) struct StartCompute<'a> { + pub(crate) header: op::StartCompute, + pub(crate) unk_pointer: GpuWeakPointer, + pub(crate) job_params1: Option>>, + #[ver(G >= G14X)] + pub(crate) registers: GpuWeakPointer, + pub(crate) stats: GpuWeakPointer, + pub(crate) work_queue: GpuWeakPointer, + pub(crate) vm_slot: u32, + pub(crate) unk_28: u32, + pub(crate) event_generation: u32, + pub(crate) event_seq: U64, + pub(crate) unk_38: u32, + pub(crate) job_params2: GpuWeakPointer>, + pub(crate) unk_44: u32, + pub(crate) uuid: u32, + pub(crate) attachments: Attachments, + pub(crate) padding: u32, + + #[ver(V >= V13_0B4)] + pub(crate) unk_flag: GpuWeakPointer, + + #[ver(V >= V13_0B4)] + pub(crate) counter: U64, + + #[ver(V >= V13_0B4)] + pub(crate) notifier_buf: GpuWeakPointer>, +} + +#[versions(AGX)] +impl<'a> Operation for StartCompute::ver<'a> {} + +#[versions(AGX)] +#[derive(Debug)] +#[repr(C)] +pub(crate) struct FinalizeCompute<'a> { + pub(crate) header: op::FinalizeCompute, + pub(crate) stats: GpuWeakPointer, + pub(crate) work_queue: GpuWeakPointer, + pub(crate) vm_slot: u32, + #[ver(V < V13_0B4)] + pub(crate) unk_18: u32, + pub(crate) job_params2: GpuWeakPointer>, + pub(crate) unk_24: u32, + pub(crate) uuid: u32, + pub(crate) fw_stamp: GpuWeakPointer, + pub(crate) stamp_value: EventValue, + pub(crate) unk_38: u32, + pub(crate) unk_3c: u32, + pub(crate) unk_40: u32, + pub(crate) unk_44: u32, + pub(crate) unk_48: u32, + pub(crate) unk_4c: u32, + pub(crate) unk_50: u32, + pub(crate) unk_54: u32, + pub(crate) unk_58: u32, + + #[ver(G == G14 && V < V13_0B4)] + pub(crate) unk_5c_g14: U64, + + pub(crate) restart_branch_offset: i32, + pub(crate) has_attachments: u32, // Check DCMP errors bits 2,3 1=ktrace 2=log 3=panic + + #[ver(V >= V13_0B4)] + pub(crate) unk_64: Array<0xd, u8>, + + #[ver(V >= V13_0B4)] + pub(crate) unk_flag: GpuWeakPointer, + + #[ver(V >= V13_0B4)] + pub(crate) unk_79: Array<0x7, u8>, +} + +#[versions(AGX)] +impl<'a> Operation for FinalizeCompute::ver<'a> {} diff --git a/drivers/gpu/drm/asahi/fw/mod.rs b/drivers/gpu/drm/asahi/fw/mod.rs new file mode 100644 index 00000000000000..a5649aa20d3a8e --- /dev/null +++ b/drivers/gpu/drm/asahi/fw/mod.rs @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Firmware structures for Apple AGX GPUs + +pub(crate) mod buffer; +pub(crate) mod channels; +pub(crate) mod compute; +pub(crate) mod event; +pub(crate) mod fragment; +pub(crate) mod initdata; +pub(crate) mod job; +pub(crate) mod microseq; +pub(crate) mod types; +pub(crate) mod vertex; +pub(crate) mod workqueue; diff --git a/drivers/gpu/drm/asahi/fw/types.rs b/drivers/gpu/drm/asahi/fw/types.rs new file mode 100644 index 00000000000000..f55d6cec6b8ca3 --- /dev/null +++ b/drivers/gpu/drm/asahi/fw/types.rs @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Common types for firmware structure definitions + +use crate::{alloc, object}; +use core::fmt; +use core::ops::{Deref, DerefMut, Index, IndexMut}; + +pub(crate) use crate::event::EventValue; +pub(crate) use crate::object::{ + GpuPointer, + GpuStruct, + GpuWeakPointer, // +}; +pub(crate) use crate::{ + f32, + float::F32, // +}; + +pub(crate) use core::fmt::Debug; +pub(crate) use core::marker::PhantomData; +pub(crate) use core::sync::atomic::{ + AtomicI32, + AtomicU32, + AtomicU64, // +}; +pub(crate) use kernel::macros::versions; +pub(crate) use kernel::prelude::Zeroable; + +// Make the trait visible +pub(crate) use crate::alloc::Allocator as _Allocator; + +/// General allocator type used for the driver +pub(crate) type Allocator = alloc::DefaultAllocator; + +/// General GpuObject type used for the driver +pub(crate) type GpuObject = + object::GpuObject>; + +/// General GpuArray type used for the driver +pub(crate) type GpuArray = object::GpuArray>; + +/// General GpuOnlyArray type used for the driver +pub(crate) type GpuOnlyArray = + object::GpuOnlyArray>; + +/// A stamp slot that is shared between firmware and the driver. +#[derive(Debug, Default)] +#[repr(transparent)] +pub(crate) struct Stamp(pub(crate) AtomicU32); + +/// A stamp slot that is for private firmware use. +/// +/// This is a separate type to guard against pointer type confusion. +#[derive(Debug, Default)] +#[repr(transparent)] +pub(crate) struct FwStamp(pub(crate) AtomicU32); + +/// An unaligned u64 type. +/// +/// This is useful to avoid having to pack firmware structures entirely, since that is incompatible +/// with `#[derive(Debug)]` and atomics. +#[derive(Copy, Clone, Default)] +#[repr(C, packed(1))] +pub(crate) struct U64(pub(crate) u64); + +// SAFETY: U64 is zeroable just like u64 +unsafe impl Zeroable for U64 {} + +impl fmt::Debug for U64 { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + let v = self.0; + f.write_fmt(format_args!("{:#x}", v)) + } +} + +/// An unaligned u32 type. +/// +/// This is useful to avoid having to pack firmware structures entirely, since that is incompatible +/// with `#[derive(Debug)]` and atomics. +#[derive(Copy, Clone, Default)] +#[repr(C, packed(1))] +pub(crate) struct U32(pub(crate) u32); + +// SAFETY: U32 is zeroable just like u32 +unsafe impl Zeroable for U32 {} + +impl fmt::Debug for U32 { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + let v = self.0; + f.write_fmt(format_args!("{:#x}", v)) + } +} + +/// Create a dummy `Debug` implementation, for when we need it but it's too painful to write by +/// hand or not very useful. +#[macro_export] +macro_rules! no_debug { + ($type:ty) => { + impl ::core::fmt::Debug for $type { + fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result { + write!(f, "...") + } + } + }; +} + +/// Implement Zeroable for a given type (and Default along with it). +/// +/// # Safety +/// +/// This macro must only be used if a type only contains primitive types which can be +/// zero-initialized, FFI structs intended to be zero-initialized, or other types which +/// impl Zeroable. +#[macro_export] +macro_rules! default_zeroed { + (<$($lt:lifetime),*>, $type:ty) => { + impl<$($lt),*> Default for $type { + fn default() -> $type { + unsafe { core::mem::zeroed() } + } + } + // SAFETY: The user is responsible for ensuring this is safe. + unsafe impl<$($lt),*> ::pin_init::Zeroable for $type {} + }; + ($type:ty) => { + impl Default for $type { + fn default() -> $type { + unsafe { core::mem::zeroed() } + } + } + // SAFETY: The user is responsible for ensuring this is safe. + unsafe impl ::pin_init::Zeroable for $type {} + }; +} + +/// A convenience type for a number of padding bytes. Hidden from Debug formatting. +#[derive(Copy, Clone)] +#[repr(C, packed)] +pub(crate) struct Pad([u8; N]); + +/// SAFETY: Primitive type, safe to zero-init. +unsafe impl Zeroable for Pad {} + +impl Default for Pad { + fn default() -> Self { + unsafe { core::mem::zeroed() } + } +} + +impl fmt::Debug for Pad { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + f.write_fmt(format_args!("")) + } +} + +/// A convenience type for a fixed-sized array with Default/Zeroable impls. +#[derive(Copy, Clone)] +#[repr(C)] +pub(crate) struct Array([T; N]); + +impl Array { + pub(crate) fn new(data: [T; N]) -> Self { + Self(data) + } +} + +// SAFETY: Arrays of Zeroable values can be safely Zeroable. +unsafe impl Zeroable for Array {} + +impl Default for Array { + fn default() -> Self { + unsafe { core::mem::zeroed() } + } +} + +impl Index for Array { + type Output = T; + + fn index(&self, index: usize) -> &Self::Output { + &self.0[index] + } +} + +impl IndexMut for Array { + fn index_mut(&mut self, index: usize) -> &mut Self::Output { + &mut self.0[index] + } +} + +impl Deref for Array { + type Target = [T; N]; + + fn deref(&self) -> &Self::Target { + &self.0 + } +} + +impl DerefMut for Array { + fn deref_mut(&mut self) -> &mut Self::Target { + &mut self.0 + } +} + +impl fmt::Debug for Array { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + self.0.fmt(f) + } +} + +/// Convenience macro to define an identically-named trivial GpuStruct with no inner fields for a +/// given raw type name. +#[macro_export] +macro_rules! trivial_gpustruct { + ($type:ident) => { + #[derive(Debug)] + pub(crate) struct $type {} + + impl GpuStruct for $type { + type Raw<'a> = raw::$type; + } + $crate::default_zeroed!($type); + }; +} diff --git a/drivers/gpu/drm/asahi/fw/vertex.rs b/drivers/gpu/drm/asahi/fw/vertex.rs new file mode 100644 index 00000000000000..07a0e05c72112c --- /dev/null +++ b/drivers/gpu/drm/asahi/fw/vertex.rs @@ -0,0 +1,193 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU vertex job firmware structures + +use super::types::*; +use super::{ + event, + job, + workqueue, // +}; +use crate::{ + buffer, + fw, + microseq, + mmu, // +}; +use kernel::sync::Arc; + +pub(crate) mod raw { + use super::*; + + #[derive(Debug, Default, Copy, Clone)] + #[repr(C)] + pub(crate) struct TilingParameters { + pub(crate) rgn_size: u32, + pub(crate) unk_4: u32, + pub(crate) ppp_ctrl: u32, + pub(crate) x_max: u16, + pub(crate) y_max: u16, + pub(crate) te_screen: u32, + pub(crate) te_mtile1: u32, + pub(crate) te_mtile2: u32, + pub(crate) tiles_per_mtile: u32, + pub(crate) tpc_stride: u32, + pub(crate) unk_24: u32, + pub(crate) unk_28: u32, + pub(crate) helper_cfg: u32, + pub(crate) __pad: Pad<0x70>, + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct JobParameters1<'a> { + pub(crate) unk_0: U64, + pub(crate) unk_8: F32, + pub(crate) unk_c: F32, + pub(crate) tvb_tilemap: GpuPointer<'a, &'a [u8]>, + #[ver(G < G14)] + pub(crate) tvb_cluster_tilemaps: Option>, + pub(crate) tpc: GpuPointer<'a, &'a [u8]>, + pub(crate) tvb_heapmeta: GpuPointer<'a, &'a [u8]>, + pub(crate) iogpu_unk_54: U64, + pub(crate) iogpu_unk_56: U64, + #[ver(G < G14)] + pub(crate) tvb_cluster_meta1: Option>, + pub(crate) utile_config: u32, + pub(crate) unk_4c: u32, + pub(crate) ppp_multisamplectl: U64, + pub(crate) tvb_layermeta: GpuPointer<'a, &'a [u8]>, + #[ver(G < G14)] + pub(crate) tvb_cluster_layermeta: Option>, + #[ver(G < G14)] + pub(crate) core_mask: Array<2, u32>, + pub(crate) preempt_buf1: GpuPointer<'a, &'a [u8]>, + pub(crate) preempt_buf2: GpuPointer<'a, &'a [u8]>, + pub(crate) unk_80: U64, + pub(crate) preempt_buf3: GpuPointer<'a, &'a [u8]>, + pub(crate) vdm_ctrl_stream_base: U64, + #[ver(G < G14)] + pub(crate) tvb_cluster_meta2: Option>, + #[ver(G < G14)] + pub(crate) tvb_cluster_meta3: Option>, + #[ver(G < G14)] + pub(crate) tiling_control: u32, + #[ver(G < G14)] + pub(crate) unk_ac: u32, + pub(crate) unk_b0: Array<6, U64>, + pub(crate) usc_exec_base_ta: U64, + #[ver(G < G14)] + pub(crate) tvb_cluster_meta4: Option>, + #[ver(G < G14)] + pub(crate) unk_f0: U64, + pub(crate) unk_f8: U64, + pub(crate) helper_program: u32, + pub(crate) unk_104: u32, + pub(crate) helper_arg: U64, + pub(crate) unk_110: U64, + pub(crate) unk_118: u32, + #[ver(G >= G14)] + pub(crate) __pad: Pad<{ 8 * 9 + 0x268 }>, + #[ver(G < G14)] + pub(crate) __pad: Pad<0x268>, + } + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct JobParameters2<'a> { + pub(crate) unk_480: Array<4, u32>, + pub(crate) unk_498: U64, + pub(crate) unk_4a0: u32, + pub(crate) preempt_buf1: GpuPointer<'a, &'a [u8]>, + pub(crate) unk_4ac: u32, + pub(crate) unk_4b0: U64, + pub(crate) unk_4b8: u32, + pub(crate) unk_4bc: U64, + pub(crate) unk_4c4_padding: Array<0x48, u8>, + pub(crate) unk_50c: u32, + pub(crate) unk_510: U64, + pub(crate) unk_518: U64, + pub(crate) unk_520: U64, + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct RunVertex<'a> { + pub(crate) tag: workqueue::CommandType, + + #[ver(V >= V13_0B4)] + pub(crate) counter: U64, + + pub(crate) vm_slot: u32, + pub(crate) unk_8: u32, + pub(crate) notifier: GpuPointer<'a, event::Notifier::ver>, + pub(crate) buffer_slot: u32, + pub(crate) unk_1c: u32, + pub(crate) buffer: GpuPointer<'a, fw::buffer::Info::ver>, + pub(crate) scene: GpuPointer<'a, fw::buffer::Scene::ver>, + pub(crate) unk_buffer_buf: GpuWeakPointer<[u8]>, + pub(crate) unk_34: u32, + + #[ver(G < G14X)] + pub(crate) job_params1: JobParameters1::ver<'a>, + #[ver(G < G14X)] + pub(crate) tiling_params: TilingParameters, + #[ver(G >= G14X)] + pub(crate) registers: job::raw::RegisterArray, + + pub(crate) tpc: GpuPointer<'a, &'a [u8]>, + pub(crate) tpc_size: U64, + pub(crate) microsequence: GpuPointer<'a, &'a [u8]>, + pub(crate) microsequence_size: u32, + pub(crate) fragment_stamp_slot: u32, + pub(crate) fragment_stamp_value: EventValue, + pub(crate) unk_pointee: u32, + pub(crate) unk_pad: u32, + pub(crate) job_params2: JobParameters2<'a>, + pub(crate) encoder_params: job::raw::EncoderParams, + pub(crate) unk_55c: u32, + pub(crate) unk_560: u32, + pub(crate) sync_grow: u32, + pub(crate) unk_568: u32, + pub(crate) uses_scratch: u32, + pub(crate) meta: job::raw::JobMeta, + pub(crate) unk_after_meta: u32, + pub(crate) unk_buf_0: U64, + pub(crate) unk_buf_8: U64, + pub(crate) unk_buf_10: U64, + pub(crate) command_time: U64, + pub(crate) timestamp_pointers: job::raw::TimestampPointers<'a>, + pub(crate) user_timestamp_pointers: job::raw::TimestampPointers<'a>, + pub(crate) client_sequence: u8, + pub(crate) pad_5d5: Array<3, u8>, + pub(crate) unk_5d8: u32, + pub(crate) unk_5dc: u8, + + #[ver(V >= V13_0B4)] + pub(crate) unk_ts: U64, + + #[ver(V >= V13_0B4)] + pub(crate) unk_5dd_8: Array<0x1b, u8>, + } +} + +#[versions(AGX)] +#[derive(Debug)] +pub(crate) struct RunVertex { + pub(crate) notifier: Arc>, + pub(crate) scene: Arc, + pub(crate) micro_seq: microseq::MicroSequence, + pub(crate) vm_bind: mmu::VmBind, + pub(crate) timestamps: Arc>, + pub(crate) user_timestamps: job::UserTimestamps, +} + +#[versions(AGX)] +impl GpuStruct for RunVertex::ver { + type Raw<'a> = raw::RunVertex::ver<'a>; +} + +#[versions(AGX)] +impl workqueue::Command for RunVertex::ver {} diff --git a/drivers/gpu/drm/asahi/fw/workqueue.rs b/drivers/gpu/drm/asahi/fw/workqueue.rs new file mode 100644 index 00000000000000..b86bd3ff3757af --- /dev/null +++ b/drivers/gpu/drm/asahi/fw/workqueue.rs @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU work queue firmware structes + +use super::event; +use super::types::*; +use crate::event::EventValue; +use crate::{ + default_zeroed, + trivial_gpustruct, // +}; +use kernel::sync::Arc; + +#[derive(Debug)] +#[repr(u32)] +pub(crate) enum CommandType { + RunVertex = 0, + RunFragment = 1, + #[allow(dead_code)] + RunBlitter = 2, + RunCompute = 3, + Barrier = 4, + InitBuffer = 6, +} + +pub(crate) trait Command: GpuStruct + Send + Sync {} + +pub(crate) mod raw { + use super::*; + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct Barrier { + pub(crate) tag: CommandType, + pub(crate) wait_stamp: GpuWeakPointer, + pub(crate) wait_value: EventValue, + pub(crate) wait_slot: u32, + pub(crate) stamp_self: EventValue, + pub(crate) uuid: u32, + pub(crate) external_barrier: u32, + // G14X addition + pub(crate) internal_barrier_type: u32, + pub(crate) padding: Pad<0x1c>, + } + + #[derive(Debug, Clone, Copy)] + #[repr(C)] + pub(crate) struct GpuContextData { + pub(crate) unk_0: u8, + pub(crate) unk_1: u8, + unk_2: Array<0x2, u8>, + pub(crate) unk_4: u8, + pub(crate) unk_5: u8, + unk_6: Array<0x18, u8>, + pub(crate) unk_1e: u8, + pub(crate) unk_1f: u8, + unk_20: Array<0x3, u8>, + pub(crate) unk_23: u8, + unk_24: Array<0x1c, u8>, + } + + impl Default for GpuContextData { + fn default() -> Self { + Self { + unk_0: 0xff, + unk_1: 0xff, + unk_2: Default::default(), + unk_4: 0, + unk_5: 1, + unk_6: Default::default(), + unk_1e: 0xff, + unk_1f: 0, + unk_20: Default::default(), + unk_23: 2, + unk_24: Default::default(), + } + } + } + + #[derive(Debug)] + #[repr(C)] + pub(crate) struct RingState { + pub(crate) gpu_doneptr: AtomicU32, + __pad0: Pad<0xc>, + pub(crate) unk_10: AtomicU32, + __pad1: Pad<0xc>, + pub(crate) unk_20: AtomicU32, + __pad2: Pad<0xc>, + pub(crate) gpu_rptr: AtomicU32, + __pad3: Pad<0xc>, + pub(crate) cpu_wptr: AtomicU32, + __pad4: Pad<0xc>, + pub(crate) rb_size: u32, + __pad5: Pad<0xc>, + // This isn't part of the structure, but it's here as a + // debugging hack so we can inspect what ring position + // the driver considered complete and freeable. + pub(crate) cpu_freeptr: AtomicU32, + __pad6: Pad<0xc>, + } + default_zeroed!(RingState); + + #[derive(Debug, Clone, Copy)] + #[repr(C)] + pub(crate) struct Priority( + pub(crate) u32, + pub(crate) u32, + pub(crate) U64, + pub(crate) u32, + pub(crate) u32, + pub(crate) u32, + ); + + pub(crate) const PRIORITY: [Priority; 4] = [ + Priority(0, 0, U64(0xffff_ffff_ffff_0000), 1, 0, 1), + Priority(1, 1, U64(0xffff_ffff_0000_0000), 0, 0, 0), + Priority(2, 2, U64(0xffff_0000_0000_0000), 0, 0, 2), + Priority(3, 3, U64(0x0000_0000_0000_0000), 0, 0, 3), + ]; + + impl Default for Priority { + fn default() -> Priority { + PRIORITY[2] + } + } + + #[versions(AGX)] + #[derive(Debug)] + #[repr(C)] + pub(crate) struct QueueInfo<'a> { + pub(crate) state: GpuPointer<'a, super::RingState>, + pub(crate) ring: GpuPointer<'a, &'a [u64]>, + pub(crate) notifier_list: GpuPointer<'a, event::NotifierList>, + pub(crate) gpu_buf: GpuPointer<'a, &'a [u8]>, + pub(crate) gpu_rptr1: AtomicU32, + pub(crate) gpu_rptr2: AtomicU32, + pub(crate) gpu_rptr3: AtomicU32, + pub(crate) event_id: AtomicI32, + pub(crate) priority: Priority, + pub(crate) unk_4c: i32, + pub(crate) uuid: u32, + pub(crate) unk_54: i32, + pub(crate) unk_58: U64, + pub(crate) busy: AtomicU32, + pub(crate) __pad: Pad<0x20>, + #[ver(V >= V13_2 && G < G14X)] + pub(crate) unk_84_0: u32, + pub(crate) unk_84_state: AtomicU32, + pub(crate) error_count: AtomicU32, + pub(crate) unk_8c: u32, + pub(crate) unk_90: u32, + pub(crate) unk_94: u32, + pub(crate) pending: AtomicU32, + pub(crate) unk_9c: u32, + pub(crate) gpu_context: GpuPointer<'a, super::GpuContextData>, + pub(crate) unk_a8: U64, + #[ver(V >= V13_2 && G < G14X)] + pub(crate) unk_b0: u32, + } +} + +trivial_gpustruct!(Barrier); +trivial_gpustruct!(RingState); + +impl Command for Barrier {} + +pub(crate) struct GpuContextData { + pub(crate) _buffer: Arc, +} +impl GpuStruct for GpuContextData { + type Raw<'a> = raw::GpuContextData; +} + +#[versions(AGX)] +#[derive(Debug)] +pub(crate) struct QueueInfo { + pub(crate) state: GpuObject, + pub(crate) ring: GpuArray, + pub(crate) gpu_buf: GpuArray, + pub(crate) notifier_list: Arc>, + pub(crate) gpu_context: Arc, +} + +#[versions(AGX)] +impl GpuStruct for QueueInfo::ver { + type Raw<'a> = raw::QueueInfo::ver<'a>; +} diff --git a/drivers/gpu/drm/asahi/gem.rs b/drivers/gpu/drm/asahi/gem.rs new file mode 100644 index 00000000000000..8affba257d956f --- /dev/null +++ b/drivers/gpu/drm/asahi/gem.rs @@ -0,0 +1,248 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Asahi driver GEM object implementation +//! +//! Basic wrappers and adaptations between generic GEM shmem objects and this driver's +//! view of what a GPU buffer object is. It is in charge of keeping track of all mappings for +//! each GEM object so we can remove them when a client (File) or a Vm are destroyed, as well as +//! implementing RTKit buffers on top of GEM objects for firmware use. + +use kernel::{ + drm, + drm::gem::{ + shmem, + shmem::VMap, + BaseObject, + DriverObject, // + }, + error::Result, + prelude::*, + types::ARef, + uapi, +}; + +use core::ops::Range; +use core::sync::atomic::{ + AtomicU64, + Ordering, // +}; + +use crate::{ + debug::*, + driver::{ + AsahiDevice, + AsahiDriver, // + }, + file, + mmu, + util::*, // +}; + +const DEBUG_CLASS: DebugFlags = DebugFlags::Gem; + +/// Represents the inner data of a GEM object for this driver. +#[pin_data] +pub(crate) struct AsahiObject { + /// ID for debug + id: u64, + /// Object creation flags. + flags: u32, + /// Whether this object can be exported. + exportable: bool, + /// Whether this is a kernel-created object. + kernel: bool, +} + +/// Type alias for the shmem GEM object type for this driver. +pub(crate) type Object = shmem::Object; + +unsafe impl Send for AsahiObject {} +unsafe impl Sync for AsahiObject {} + +// /// Type alias for the SGTable type for this driver. +// pub(crate) type SGTable = shmem::SGTable; + +/// A shared reference to a GEM object for this driver. +pub(crate) struct ObjectRef { + /// The underlying GEM object reference + pub(crate) gem: ARef, + /// The kernel-side VMap of this object, if needed + vmap: Option>, +} + +crate::no_debug!(ObjectRef); + +static GEM_ID: AtomicU64 = AtomicU64::new(0); + +impl ObjectRef { + /// Create a new wrapper for a raw GEM object reference. + pub(crate) fn new(gem: ARef) -> ObjectRef { + ObjectRef { gem, vmap: None } + } + + /// Return the `VMap` for this object, creating it if necessary. + pub(crate) fn vmap(&mut self) -> Result> { + if self.vmap.is_none() { + self.vmap = Some(self.gem.owned_vmap()?); + } + self.gem.vmap() + } + + /// Returns the size of an object in bytes + pub(crate) fn size(&self) -> usize { + self.gem.size() + } + + /// Maps an object into a given `Vm` at any free address within a given range. + pub(crate) fn map_into_range( + &mut self, + vm: &crate::mmu::Vm, + range: Range, + alignment: u64, + prot: mmu::Prot, + guard: bool, + ) -> Result { + // Only used for kernel objects now + if !self.gem.kernel { + return Err(EINVAL); + } + vm.map_in_range(&self.gem, 0..self.gem.size(), alignment, range, prot, guard) + } + + /// Maps a range within an object into a given `Vm` at any free address within a given range. + pub(crate) fn map_range_into_range( + &mut self, + vm: &crate::mmu::Vm, + obj_range: Range, + range: Range, + alignment: u64, + prot: mmu::Prot, + guard: bool, + ) -> Result { + if obj_range.end > self.gem.size() { + return Err(EINVAL); + } + if self.gem.flags & uapi::drm_asahi_gem_flags_DRM_ASAHI_GEM_VM_PRIVATE != 0 + && vm.is_extobj(&*self.gem) + { + return Err(EINVAL); + } + vm.map_in_range(&self.gem, obj_range, alignment, range, prot, guard) + } + + /// Maps an object into a given `Vm` at a specific address. + /// + /// Returns Err(ENOSPC) if the requested address is already busy. + pub(crate) fn map_at( + &mut self, + vm: &crate::mmu::Vm, + addr: u64, + prot: mmu::Prot, + guard: bool, + ) -> Result { + if self.gem.flags & uapi::drm_asahi_gem_flags_DRM_ASAHI_GEM_VM_PRIVATE != 0 + && vm.is_extobj(&*self.gem) + { + return Err(EINVAL); + } + + vm.map_at(addr, self.gem.size(), self.gem.clone(), prot, guard) + } +} + +pub(crate) struct AsahiObjConfig { + flags: u32, + exportable: bool, + kernel: bool, +} + +/// Create a new kernel-owned GEM object. +pub(crate) fn new_kernel_object(dev: &AsahiDevice, size: usize) -> Result { + let gem = shmem::Object::::new( + dev, + align(size, mmu::UAT_PGSZ), + shmem::ObjectConfig:: { + map_wc: false, + parent_resv_obj: None, + }, + AsahiObjConfig { + flags: 0, + exportable: false, + kernel: true, + }, + )?; + + mod_pr_debug!("AsahiObject new kernel object id={}\n", gem.id); + Ok(ObjectRef::new(gem)) +} + +/// Create a new user-owned GEM object with the given flags. +pub(crate) fn new_object( + dev: &AsahiDevice, + size: usize, + flags: u32, + parent_object: Option<&shmem::Object>, +) -> Result> { + if (flags & uapi::drm_asahi_gem_flags_DRM_ASAHI_GEM_VM_PRIVATE != 0) != parent_object.is_some() + { + return Err(EINVAL); + } + + let gem = shmem::Object::::new( + dev, + align(size, mmu::UAT_PGSZ), + shmem::ObjectConfig:: { + map_wc: flags & uapi::drm_asahi_gem_flags_DRM_ASAHI_GEM_WRITEBACK == 0, + parent_resv_obj: parent_object, + }, + AsahiObjConfig { + flags, + exportable: parent_object.is_none(), + kernel: false, + }, + )?; + + mod_pr_debug!("AsahiObject new user object: id={}\n", gem.id); + Ok(gem) +} + +#[vtable] +impl DriverObject for AsahiObject { + type Driver = AsahiDriver; + type Args = AsahiObjConfig; + + const HAS_EXPORT: bool = true; + + /// Callback to create the inner data of a GEM object + fn new(_dev: &AsahiDevice, _size: usize, args: Self::Args) -> impl PinInit { + let id = GEM_ID.fetch_add(1, Ordering::Relaxed); + mod_pr_debug!("AsahiObject::new id={}\n", id); + try_pin_init!(AsahiObject { + id, + flags: args.flags, + exportable: args.exportable, + kernel: args.kernel, + }) + } + + /// Callback to drop all mappings for a GEM object owned by a given `File` + fn close(obj: &::Object, file: &drm::gem::DriverFile) { + // fn close(obj: &Object, file: &DrmFile) { + mod_pr_debug!("AsahiObject::close id={}\n", obj.id); + if file::File::unbind_gem_object(file, obj).is_err() { + pr_err!("AsahiObject::close: Failed to unbind GEM object\n"); + } + } + + /// Optional handle for exporting a gem object. + fn export( + obj: &::Object, + flags: u32, + ) -> Result> { + if !obj.exportable { + return Err(EINVAL); + } + + obj.prime_export(flags) + } +} diff --git a/drivers/gpu/drm/asahi/gpu.rs b/drivers/gpu/drm/asahi/gpu.rs new file mode 100644 index 00000000000000..1d7bf094651d94 --- /dev/null +++ b/drivers/gpu/drm/asahi/gpu.rs @@ -0,0 +1,1637 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Top-level GPU manager +//! +//! This module is the root of all GPU firmware management for a given driver instance. It is +//! responsible for initialization, owning the top-level managers (events, UAT, etc.), and +//! communicating with the raw RtKit endpoints to send and receive messages to/from the GPU +//! firmware. +//! +//! It is also the point where diverging driver firmware/GPU variants (using the versions macro) +//! are unified, so that the top level of the driver itself (in `driver`) does not have to concern +//! itself with version dependence. + +use core::any::Any; +use core::ops::Range; +use core::slice; +use core::sync::atomic::{ + AtomicBool, + AtomicU64, + Ordering, // +}; + +use kernel::{ + c_str, + drm::gem::shmem, + error::code::*, + io::mem::{Mem, MemFlags}, + iosys_map::IoSysMapRef, + macros::versions, + new_mutex, + prelude::*, + soc::apple::rtkit, + sync::{ + lock::{ + mutex::MutexBackend, + Guard, // + }, + Arc, + Mutex, + UniqueArc, // + }, + time::{ + Delta, + Instant, + Monotonic, // + }, + types::ForeignOwnable, // +}; +#[cfg(CONFIG_DEV_COREDUMP)] +use kernel::{ + devcoredump, + time::msecs_to_jiffies, // +}; + +use crate::alloc::Allocator; +use crate::debug::*; +use crate::driver::{ + AsahiDevRef, + AsahiDevice, // +}; +use crate::fw::channels::{ + ChannelErrorType, + PipeType, // +}; +use crate::fw::types::{ + U32, + U64, // +}; +use crate::{ + alloc, + buffer, + channel, + event, + fw, + gem, + hw, + initdata, + mem, + mmu, + queue, + regs, + workqueue, // +}; + +const DEBUG_CLASS: DebugFlags = DebugFlags::Gpu; + +/// Firmware endpoint for init & incoming notifications. +const EP_FIRMWARE: u8 = 0x20; + +/// Doorbell endpoint for work/message submissions. +const EP_DOORBELL: u8 = 0x21; + +/// Initialize the GPU firmware. +const MSG_INIT: u64 = 0x81 << 48; +const INIT_DATA_MASK: u64 = (1 << 44) - 1; + +/// TX channel doorbell. +const MSG_TX_DOORBELL: u64 = 0x83 << 48; +/// Firmware control channel doorbell. +const MSG_FWCTL: u64 = 0x84 << 48; +// /// Halt the firmware (?). +// const MSG_HALT: u64 = 0x85 << 48; + +/// Receive channel doorbell notification. +const MSG_RX_DOORBELL: u64 = 0x42 << 48; + +/// Doorbell number for firmware kicks/wakeups. +const DOORBELL_KICKFW: u64 = 0x10; +/// Doorbell number for device control channel kicks. +const DOORBELL_DEVCTRL: u64 = 0x11; + +// Upper kernel half VA address ranges. +/// Private (cached) firmware structure VA range base. +const IOVA_KERN_PRIV_RANGE: Range = 0xffffffa000000000..0xffffffa600000000; +/// Private (cached) GPU-RO firmware structure VA range base. +const IOVA_KERN_GPU_RO_RANGE: Range = 0xffffffa600000000..0xffffffa800000000; +/// Shared (uncached) firmware structure VA range base. +const IOVA_KERN_SHARED_RANGE: Range = 0xffffffa800000000..0xffffffaa00000000; +/// Shared (uncached) read-only firmware structure VA range base. +const IOVA_KERN_SHARED_RO_RANGE: Range = 0xffffffaa00000000..0xffffffac00000000; +/// GPU/FW shared structure VA range base. +const IOVA_KERN_GPU_RANGE: Range = 0xffffffac00000000..0xffffffae00000000; +/// GPU/FW shared structure VA range base. +const IOVA_KERN_RTKIT_RANGE: Range = 0xffffffae00000000..0xffffffae10000000; +/// Shared (uncached) timestamp region. +pub(crate) const IOVA_KERN_TIMESTAMP_RANGE: Range = 0xffffffae10000000..0xffffffae14000000; +/// FW MMIO VA range base. +const IOVA_KERN_MMIO_RANGE: Range = 0xffffffaf00000000..0xffffffb000000000; + +/// GPU/FW buffer manager control address (context 0 low) +pub(crate) const IOVA_KERN_GPU_BUFMGR_LOW: u64 = 0x20_0000_0000; +/// GPU/FW buffer manager control address (context 0 high) +pub(crate) const IOVA_KERN_GPU_BUFMGR_HIGH: u64 = 0xffffffaeffff0000; + +/// Timeout for entering the halt state after a fault or request. +const HALT_ENTER_TIMEOUT: Delta = Delta::from_millis(100); + +/// Maximum amount of firmware-private memory garbage allowed before collection. +/// Collection flushes the FW cache and is expensive, so this needs to be +/// reasonably high. +const MAX_FW_ALLOC_GARBAGE_BYTES: usize = 16 * 1024 * 1024; +/// Maximum count of firmware-private memory garbage objects allowed before collection. +/// This works out to 16K of memory in the garbage list (8 bytes each), which keeps us +/// within the safe range for kmalloc (on 16K page systems). +const MAX_FW_ALLOC_GARBAGE_OBJECTS: usize = 2048; + +/// Global allocators used for kernel-half structures. +pub(crate) struct KernelAllocators { + pub(crate) private: alloc::DefaultAllocator, + pub(crate) shared: alloc::DefaultAllocator, + pub(crate) shared_ro: alloc::DefaultAllocator, + #[allow(dead_code)] + pub(crate) gpu: alloc::DefaultAllocator, + pub(crate) gpu_ro: alloc::DefaultAllocator, +} + +/// Receive (GPU->driver) ring buffer channels. +#[versions(AGX)] +#[pin_data] +struct RxChannels { + event: channel::EventChannel::ver, + fw_log: channel::FwLogChannel, + ktrace: channel::KTraceChannel, + stats: channel::StatsChannel::ver, +} + +/// GPU work submission pipe channels (driver->GPU). +#[versions(AGX)] +struct PipeChannels { + pub(crate) vtx: KVec>>>, + pub(crate) frag: KVec>>>, + pub(crate) comp: KVec>>>, +} + +/// Misc command transmit (driver->GPU) channels. +#[versions(AGX)] +#[pin_data] +struct TxChannels { + pub(crate) device_control: channel::DeviceControlChannel::ver, +} + +/// Number of work submission pipes per type, one for each priority level. +const NUM_PIPES: usize = 4; + +/// A generic monotonically incrementing ID used to uniquely identify object instances within the +/// driver. +pub(crate) struct ID(AtomicU64); + +impl ID { + /// Create a new ID counter with a given value. + fn new(val: u64) -> ID { + ID(AtomicU64::new(val)) + } + + /// Fetch the next unique ID. + pub(crate) fn next(&self) -> u64 { + self.0.fetch_add(1, Ordering::Relaxed) + } +} + +impl Default for ID { + /// IDs default to starting at 2, as 0/1 are considered reserved for the system. + fn default() -> Self { + Self::new(2) + } +} + +/// A guard representing one active submission on the GPU. When dropped, decrements the active +/// submission count. +pub(crate) struct OpGuard(Arc); + +impl Drop for OpGuard { + fn drop(&mut self) { + self.0.end_op(); + } +} + +/// Set of global sequence IDs used in the driver. +#[derive(Default)] +pub(crate) struct SequenceIDs { + /// `File` instance ID. + pub(crate) file: ID, + /// `Vm` instance ID. + pub(crate) vm: ID, + /// Submission instance ID. + pub(crate) submission: ID, + /// `Queue` instance ID. + pub(crate) queue: ID, +} + +/// Top-level GPU manager that owns all the global state relevant to the driver instance. +#[versions(AGX)] +#[pin_data] +pub(crate) struct GpuManager { + dev: AsahiDevRef, + cfg: &'static hw::HwConfig, + dyncfg: hw::DynConfig, + pub(crate) initdata: fw::types::GpuObject, + uat: mmu::Uat, + crashed: AtomicBool, + #[pin] + alloc: Mutex, + io_mappings: KVec, + next_mmio_iova: u64, + #[pin] + rtkit: Mutex>>, + #[pin] + rx_channels: Mutex, + #[pin] + tx_channels: Mutex, + #[pin] + fwctl_channel: Mutex, + pipes: PipeChannels::ver, + event_manager: Arc, + buffer_mgr: buffer::BufferManager::ver, + ids: SequenceIDs, + #[allow(clippy::vec_box)] + #[pin] + garbage_contexts: Mutex>>>, +} + +/// Trait used to abstract the firmware/GPU-dependent variants of the GpuManager. +pub(crate) trait GpuManager: Send + Sync { + /// Cast as an Any type. + fn as_any(&self) -> &dyn Any; + /// Cast Arc as an Any type. + fn arc_as_any(self: Arc) -> Arc; + /// Initialize the GPU. + fn init(&self) -> Result; + /// Update the GPU globals from global info + /// + /// TODO: Unclear what can and cannot be updated like this. + fn update_globals(&self); + /// Get a reference to the KernelAllocators. + fn alloc(&self) -> Guard<'_, KernelAllocators, MutexBackend>; + /// Create a new `Vm` given a unique `File` ID. + fn new_vm(&self, kernel_range: Range) -> Result; + /// Bind a `Vm` to an available slot and return the `VmBind`. + fn bind_vm(&self, vm: &mmu::Vm) -> Result; + /// Create a new user command queue. + fn new_queue( + &self, + vm: mmu::Vm, + ualloc: Arc>, + ualloc_priv: Arc>, + priority: u32, + usc_exec_base: u64, + ) -> Result>; + /// Return a reference to the global `SequenceIDs` instance. + fn ids(&self) -> &SequenceIDs; + /// Kick the firmware (wake it up if asleep). + /// + /// This should be useful to reduce latency on work submission, so we can ask the firmware to + /// wake up while we do some preparatory work for the work submission. + fn kick_firmware(&self) -> Result; + /// Flush the entire firmware cache. + /// + /// TODO: Does this actually work? + fn flush_fw_cache(&self) -> Result; + /// Handle a GPU work timeout event. + fn handle_timeout(&self, counter: u32, event_slot: i32, unk: u32); + /// Handle a GPU fault event. + fn handle_fault(&self); + /// Handle a channel error event. + fn handle_channel_error( + &self, + error_type: ChannelErrorType, + pipe_type: u32, + event_slot: u32, + event_value: u32, + ); + /// Acknowledge a Buffer grow op. + fn ack_grow(&self, buffer_slot: u32, vm_slot: u32, counter: u32); + /// Send a firmware control command (secure cache flush). + fn fwctl(&self, msg: fw::channels::FwCtlMsg) -> Result; + /// Get the static GPU configuration for this SoC. + fn get_cfg(&self) -> &'static hw::HwConfig; + /// Get the dynamic GPU configuration for this SoC. + fn get_dyncfg(&self) -> &hw::DynConfig; + /// Register an unused context as garbage + fn free_context(&self, data: KBox>); + /// Check whether the GPU is crashed + fn is_crashed(&self) -> bool; + /// Map a BO as a timestamp buffer + fn map_timestamp_buffer( + &self, + bo: gem::ObjectRef, + range: Range, + ) -> Result; +} + +/// Private generic trait for functions that don't need to escape this module. +trait GpuManagerPriv { + /// Decrement the pending submission counter. + fn end_op(&self); +} + +pub(crate) struct RtkitObject { + vmap: shmem::VMap, + mapping: mmu::KernelMapping, +} + +impl rtkit::Buffer for RtkitObject { + fn iova(&self) -> Result { + Ok(self.mapping.iova() as usize) + } + fn buf(&mut self) -> Result> { + Ok(self.vmap.get()) + } +} + +#[versions(AGX)] +#[vtable] +impl rtkit::Operations for GpuManager::ver { + type Data = Arc; + type Buffer = RtkitObject; + + fn recv_message(data: ::Borrowed<'_>, ep: u8, msg: u64) { + let dev = &data.dev; + //dev_info!(dev.as_ref(), "RtKit message: {:#x}:{:#x}\n", ep, msg); + + if ep != EP_FIRMWARE || msg != MSG_RX_DOORBELL { + dev_err!(dev.as_ref(), "Unknown message: {:#x}:{:#x}\n", ep, msg); + return; + } + + let mut ch = data.rx_channels.lock(); + + ch.fw_log.poll(); + ch.ktrace.poll(); + ch.stats.poll(); + ch.event.poll(); + } + + fn crashed(data: ::Borrowed<'_>, crashlog: Option<&[u8]>) { + let dev = &data.dev; + + data.crashed.store(true, Ordering::Relaxed); + + #[cfg(CONFIG_DEV_COREDUMP)] + if let Err(e) = data.generate_crashdump(crashlog) { + dev_err!(dev.as_ref(), "Could not generate crashdump: {:?}\n", e); + } + #[cfg(not(CONFIG_DEV_COREDUMP))] + let _ = crashlog; + + if debug_enabled(DebugFlags::OopsOnGpuCrash) { + panic!("GPU firmware crashed"); + } else { + dev_err!(dev.as_ref(), "GPU firmware crashed, failing all jobs\n"); + data.event_manager.fail_all(workqueue::WorkError::NoDevice); + } + } + + fn shmem_alloc( + data: ::Borrowed<'_>, + size: usize, + ) -> Result { + let dev = &data.dev; + mod_dev_dbg!(dev, "shmem_alloc() {:#x} bytes\n", size); + + let mut obj = gem::new_kernel_object(dev, size)?; + let vmap = obj.gem.owned_vmap()?; + let mapping = obj.map_into_range( + data.uat.kernel_vm(), + IOVA_KERN_RTKIT_RANGE, + mmu::UAT_PGSZ as u64, + mmu::PROT_FW_SHARED_RW, + true, + )?; + mod_dev_dbg!(dev, "shmem_alloc() -> VA {:#x}\n", mapping.iova()); + Ok(RtkitObject { vmap, mapping }) + } +} + +#[versions(AGX)] +impl GpuManager::ver { + /// Create a new GpuManager of this version/GPU combination. + #[inline(never)] + pub(crate) fn new( + dev: &AsahiDevice, + res: ®s::Resources, + cfg: &'static hw::HwConfig, + ) -> Result> { + let uat = Self::make_uat(dev, cfg)?; + let dyncfg = Self::make_dyncfg(dev, res, cfg, &uat)?; + + let mut alloc = KernelAllocators { + private: alloc::DefaultAllocator::new( + dev, + uat.kernel_vm(), + IOVA_KERN_PRIV_RANGE, + 0x80, + mmu::PROT_FW_PRIV_RW, + 1024 * 1024, + true, + fmt!("Kernel Private"), + true, + )?, + shared: alloc::DefaultAllocator::new( + dev, + uat.kernel_vm(), + IOVA_KERN_SHARED_RANGE, + 0x80, + mmu::PROT_FW_SHARED_RW, + 1024 * 1024, + true, + fmt!("Kernel Shared"), + false, + )?, + shared_ro: alloc::DefaultAllocator::new( + dev, + uat.kernel_vm(), + IOVA_KERN_SHARED_RO_RANGE, + 0x80, + mmu::PROT_FW_SHARED_RO, + 64 * 1024, + true, + fmt!("Kernel RO Shared"), + false, + )?, + gpu: alloc::DefaultAllocator::new( + dev, + uat.kernel_vm(), + IOVA_KERN_GPU_RANGE, + 0x80, + mmu::PROT_GPU_FW_SHARED_RW, + 64 * 1024, + true, + fmt!("Kernel GPU Shared"), + false, + )?, + gpu_ro: alloc::DefaultAllocator::new( + dev, + uat.kernel_vm(), + IOVA_KERN_GPU_RO_RANGE, + 0x80, + mmu::PROT_GPU_RO_FW_PRIV_RW, + 1024 * 1024, + true, + fmt!("Kernel GPU RO Shared"), + true, + )?, + }; + + let event_manager = Self::make_event_manager(&mut alloc)?; + let mut initdata = Self::make_initdata(dev, cfg, &dyncfg, &mut alloc)?; + + initdata.runtime_pointers.buffer_mgr_ctl_low_mapping = + Some(initdata.runtime_pointers.buffer_mgr_ctl.map_at( + uat.kernel_lower_vm(), + IOVA_KERN_GPU_BUFMGR_LOW, + mmu::PROT_GPU_SHARED_RW, + false, + )?); + initdata.runtime_pointers.buffer_mgr_ctl_high_mapping = + Some(initdata.runtime_pointers.buffer_mgr_ctl.map_at( + uat.kernel_vm(), + IOVA_KERN_GPU_BUFMGR_HIGH, + mmu::PROT_FW_SHARED_RW, + false, + )?); + + let mut mgr = Self::make_mgr(dev, cfg, dyncfg, uat, alloc, event_manager, initdata)?; + + { + let fwctl = mgr.fwctl_channel.lock(); + let p_fwctl = fwctl.to_raw(); + core::mem::drop(fwctl); + + mgr.as_mut() + .initdata_mut() + .fw_status + .with_mut(|raw, _inner| { + raw.fwctl_channel = p_fwctl; + }); + } + + { + let txc = mgr.tx_channels.lock(); + let p_device_control = txc.device_control.to_raw(); + core::mem::drop(txc); + + let rxc = mgr.rx_channels.lock(); + let p_event = rxc.event.to_raw(); + let p_fw_log = rxc.fw_log.to_raw(); + let p_ktrace = rxc.ktrace.to_raw(); + let p_stats = rxc.stats.to_raw(); + let p_fwlog_buf = rxc.fw_log.get_buf(); + core::mem::drop(rxc); + + mgr.as_mut() + .initdata_mut() + .runtime_pointers + .with_mut(|raw, _inner| { + raw.device_control = p_device_control; + raw.event = p_event; + raw.fw_log = p_fw_log; + raw.ktrace = p_ktrace; + raw.stats = p_stats; + raw.fwlog_buf = Some(p_fwlog_buf); + }); + } + + let mut p_pipes: KVec = KVec::new(); + + for ((v, f), c) in mgr + .pipes + .vtx + .iter() + .zip(&mgr.pipes.frag) + .zip(&mgr.pipes.comp) + { + p_pipes.push( + fw::initdata::raw::PipeChannels::ver { + vtx: v.lock().to_raw(), + frag: f.lock().to_raw(), + comp: c.lock().to_raw(), + }, + GFP_KERNEL, + )?; + } + + mgr.as_mut() + .initdata_mut() + .runtime_pointers + .with_mut(|raw, _inner| { + for (i, p) in p_pipes.into_iter().enumerate() { + raw.pipes[i].vtx = p.vtx; + raw.pipes[i].frag = p.frag; + raw.pipes[i].comp = p.comp; + } + }); + + for (i, map) in cfg.io_mappings.iter().enumerate() { + if let Some(map) = map.as_ref() { + Self::iomap(&mut mgr, cfg, i, map)?; + } + } + + #[ver(V >= V13_0B4)] + if let Some(base) = cfg.sram_base { + let size = cfg.sram_size.unwrap(); + let iova = mgr.as_mut().alloc_mmio_iova(size); + + let mapping = mgr + .uat + .kernel_vm() + .map_io(iova, base, size, mmu::PROT_FW_SHARED_RW)?; + + mgr.as_mut() + .initdata_mut() + .runtime_pointers + .hwdata_b + .with_mut(|raw, _| { + raw.sgx_sram_ptr = U64(mapping.iova()); + }); + + mgr.as_mut().io_mappings_mut().push(mapping, GFP_KERNEL)?; + } + + let mgr = Arc::from(mgr); + + let rtkit = rtkit::RtKit::::new(dev.as_ref(), None, 0, mgr.clone())?; + + *mgr.rtkit.lock() = Some(rtkit); + + { + let mut rxc = mgr.rx_channels.lock(); + rxc.event.set_manager(mgr.clone()); + } + + Ok(mgr) + } + + /// Return a mutable reference to the initdata member + fn initdata_mut( + self: Pin<&mut Self>, + ) -> &mut fw::types::GpuObject { + // SAFETY: initdata does not require structural pinning. + unsafe { &mut self.get_unchecked_mut().initdata } + } + + /// Return a mutable reference to the io_mappings member + fn io_mappings_mut(self: Pin<&mut Self>) -> &mut KVec { + // SAFETY: io_mappings does not require structural pinning. + unsafe { &mut self.get_unchecked_mut().io_mappings } + } + + /// Allocate an MMIO iova range + fn alloc_mmio_iova(self: Pin<&mut Self>, size: usize) -> u64 { + // SAFETY: next_mmio_iova does not require structural pinning. + let next_ref = unsafe { &mut self.get_unchecked_mut().next_mmio_iova }; + + let addr = *next_ref; + let next = addr + (size + mmu::UAT_PGSZ) as u64; + + assert!(next <= IOVA_KERN_MMIO_RANGE.end); + + *next_ref = next; + + addr + } + + /// Build the entire GPU InitData structure tree and return it as a boxed GpuObject. + fn make_initdata( + dev: &AsahiDevice, + cfg: &'static hw::HwConfig, + dyncfg: &hw::DynConfig, + alloc: &mut KernelAllocators, + ) -> Result>> { + let mut builder = initdata::InitDataBuilder::ver::new(dev, alloc, cfg, dyncfg); + builder.build() + } + + /// Create a fresh boxed Uat instance. + /// + /// Force disable inlining to avoid blowing up the stack. + #[inline(never)] + fn make_uat(dev: &AsahiDevice, cfg: &'static hw::HwConfig) -> Result> { + // G14X has a new thing in the Scene structure that unfortunately requires + // write access from user contexts. Hopefully it's not security-sensitive. + #[ver(G >= G14X)] + let map_kernel_to_user = true; + #[ver(G < G14X)] + let map_kernel_to_user = false; + + Ok(KBox::new( + mmu::Uat::new(dev, cfg, map_kernel_to_user)?, + GFP_KERNEL, + )?) + } + + /// Actually create the final GpuManager instance, as a UniqueArc. + /// + /// Force disable inlining to avoid blowing up the stack. + #[inline(never)] + fn make_mgr( + dev: &AsahiDevice, + cfg: &'static hw::HwConfig, + dyncfg: KBox, + uat: KBox, + mut alloc: KernelAllocators, + event_manager: Arc, + initdata: KBox>, + ) -> Result>> { + let mut pipes = PipeChannels::ver { + vtx: KVec::new(), + frag: KVec::new(), + comp: KVec::new(), + }; + + for _i in 0..=NUM_PIPES - 1 { + pipes.vtx.push( + KBox::pin_init( + new_mutex!(channel::PipeChannel::ver::new(dev, &mut alloc)?, "pipe_vtx",), + GFP_KERNEL, + )?, + GFP_KERNEL, + )?; + pipes.frag.push( + KBox::pin_init( + new_mutex!( + channel::PipeChannel::ver::new(dev, &mut alloc)?, + "pipe_frag", + ), + GFP_KERNEL, + )?, + GFP_KERNEL, + )?; + pipes.comp.push( + KBox::pin_init( + new_mutex!( + channel::PipeChannel::ver::new(dev, &mut alloc)?, + "pipe_comp", + ), + GFP_KERNEL, + )?, + GFP_KERNEL, + )?; + } + + let fwctl_channel = channel::FwCtlChannel::new(dev, &mut alloc)?; + + let buffer_mgr = buffer::BufferManager::ver::new()?; + let event_manager_clone = event_manager.clone(); + let buffer_mgr_clone = buffer_mgr.clone(); + let alloc_ref = &mut alloc; + let rx_channels = KBox::init( + try_init!(RxChannels::ver { + event: channel::EventChannel::ver::new( + dev, + alloc_ref, + event_manager_clone, + buffer_mgr_clone, + )?, + fw_log: channel::FwLogChannel::new(dev, alloc_ref)?, + ktrace: channel::KTraceChannel::new(dev, alloc_ref)?, + stats: channel::StatsChannel::ver::new(dev, alloc_ref)?, + }), + GFP_KERNEL, + )?; + + let alloc_ref = &mut alloc; + let tx_channels = KBox::init( + try_init!(TxChannels::ver { + device_control: channel::DeviceControlChannel::ver::new(dev, alloc_ref)?, + }), + GFP_KERNEL, + )?; + + let x = UniqueArc::pin_init( + try_pin_init!(GpuManager::ver { + dev: dev.into(), + cfg, + dyncfg: KBox::::into_inner(dyncfg), + initdata: KBox::>::into_inner(initdata), + uat: KBox::::into_inner(uat), + io_mappings: KVec::new(), + next_mmio_iova: IOVA_KERN_MMIO_RANGE.start, + rtkit <- new_mutex!(None, "rtkit"), + crashed: AtomicBool::new(false), + event_manager, + alloc <- new_mutex!(alloc, "alloc"), + fwctl_channel <- new_mutex!(fwctl_channel, "fwctl_channel"), + rx_channels <- new_mutex!(KBox::::into_inner(rx_channels), "rx_channels"), + tx_channels <- new_mutex!(KBox::::into_inner(tx_channels), "tx_channels"), + pipes, + buffer_mgr, + ids: Default::default(), + garbage_contexts <- new_mutex!(KVec::new(), "garbage_contexts"), + }), + GFP_KERNEL, + )?; + + Ok(x) + } + + fn load_hwdata_blob(dev: &AsahiDevice, name: &CStr, size_name: &CStr) -> Result> { + let of_node = dev.as_ref().of_node().ok_or(EINVAL)?; + let size: usize = dev + .as_ref() + .fwnode() + .ok_or(ENOENT)? + .property_read::(size_name) + .or(0) + .try_into()?; + let res = of_node.reserved_mem_region_to_resource_byname(name)?; + // SAFETY: No dma here, just loading init data. + let mem = unsafe { Mem::try_new(res, MemFlags::WB)? }; + if size > mem.size() { + return Err(ENOENT); + } + // SAFETY: trusting the bootloader to fill it out correctly + let blob_sl = unsafe { slice::from_raw_parts(mem.ptr(), size) }; + let mut blob = KVVec::new(); + blob.extend_from_slice(blob_sl, GFP_KERNEL)?; + Ok(blob) + } + + /// Fetch and validate the GPU dynamic configuration from the device tree and hardware. + /// + /// Force disable inlining to avoid blowing up the stack. + #[inline(never)] + fn make_dyncfg( + dev: &AsahiDevice, + res: ®s::Resources, + cfg: &'static hw::HwConfig, + uat: &mmu::Uat, + ) -> Result> { + let gpu_id = res.get_gpu_id()?; + + dev_info!(dev.as_ref(), "GPU Information:\n"); + dev_info!( + dev.as_ref(), + " Type: {:?}{:?}\n", + gpu_id.gpu_gen, + gpu_id.gpu_variant + ); + dev_info!(dev.as_ref(), " Clusters: {}\n", gpu_id.num_clusters); + dev_info!( + dev.as_ref(), + " Cores: {} ({})\n", + gpu_id.num_cores, + gpu_id.num_cores * gpu_id.num_clusters + ); + dev_info!( + dev.as_ref(), + " Frags: {} ({})\n", + gpu_id.num_frags, + gpu_id.num_frags * gpu_id.num_clusters + ); + dev_info!( + dev.as_ref(), + " GPs: {} ({})\n", + gpu_id.num_gps, + gpu_id.num_gps * gpu_id.num_clusters + ); + dev_info!(dev.as_ref(), " Core masks: {:#x?}\n", gpu_id.core_masks); + dev_info!( + dev.as_ref(), + " Active cores: {}\n", + gpu_id.total_active_cores + ); + + dev_info!(dev.as_ref(), "Getting configuration from device tree...\n"); + let pwr_cfg = hw::PwrConfig::load(dev, cfg)?; + dev_info!(dev.as_ref(), "Dynamic configuration fetched\n"); + + if gpu_id.gpu_gen != cfg.gpu_gen || gpu_id.gpu_variant != cfg.gpu_variant { + dev_err!( + dev.as_ref(), + "GPU type mismatch (expected {:?}{:?}, found {:?}{:?})\n", + cfg.gpu_gen, + cfg.gpu_variant, + gpu_id.gpu_gen, + gpu_id.gpu_variant + ); + return Err(EIO); + } + if gpu_id.num_clusters > cfg.max_num_clusters { + dev_err!( + dev.as_ref(), + "Too many clusters ({} > {})\n", + gpu_id.num_clusters, + cfg.max_num_clusters + ); + return Err(EIO); + } + if gpu_id.num_cores > cfg.max_num_cores { + dev_err!( + dev.as_ref(), + "Too many cores ({} > {})\n", + gpu_id.num_cores, + cfg.max_num_cores + ); + return Err(EIO); + } + if gpu_id.num_frags > cfg.max_num_frags { + dev_err!( + dev.as_ref(), + "Too many frags ({} > {})\n", + gpu_id.num_frags, + cfg.max_num_frags + ); + return Err(EIO); + } + if gpu_id.num_gps > cfg.max_num_gps { + dev_err!( + dev.as_ref(), + "Too many GPs ({} > {})\n", + gpu_id.num_gps, + cfg.max_num_gps + ); + return Err(EIO); + } + + let fwnode = dev.as_ref().fwnode().ok_or(ENOENT)?; + + Ok(KBox::new( + hw::DynConfig { + pwr: pwr_cfg, + uat_ttb_base: uat.ttb_base(), + id: gpu_id, + firmware_version: fwnode + .property_read_array_vec(c_str!("apple,firmware-version"), 3)? + .or(kernel::kvec![0; 3]?), + + hw_data_a: Self::load_hwdata_blob( + dev, + c_str!("hw-cal-a"), + c_str!("debug,hw-cal-a-size"), + ) + .unwrap_or(KVVec::new()), + hw_data_b: Self::load_hwdata_blob( + dev, + c_str!("hw-cal-b"), + c_str!("debug,hw-cal-b-size"), + ) + .unwrap_or(KVVec::new()), + hw_globals: Self::load_hwdata_blob( + dev, + c_str!("globals"), + c_str!("debug,globals-size"), + ) + .unwrap_or(KVVec::new()), + }, + GFP_KERNEL, + )?) + } + + /// Create the global GPU event manager, and return an `Arc<>` to it. + fn make_event_manager(alloc: &mut KernelAllocators) -> Result> { + Ok(Arc::new(event::EventManager::new(alloc)?, GFP_KERNEL)?) + } + + /// Create a new MMIO mapping and add it to the mappings list in initdata at the specified + /// index. + fn iomap( + this: &mut Pin>, + cfg: &'static hw::HwConfig, + index: usize, + map: &hw::IOMapping, + ) -> Result { + let dies = if map.per_die { + cfg.num_dies as usize + } else { + 1 + }; + + let off = map.base & mmu::UAT_PGMSK; + let base = map.base - off; + let end = (map.base + map.size + mmu::UAT_PGMSK) & !mmu::UAT_PGMSK; + let map_size = end - base; + + // Array mappings must be aligned + assert!((off == 0 && map_size == map.size) || (map.count == 1 && !map.per_die)); + assert!(map.count > 0); + + let iova = this.as_mut().alloc_mmio_iova(map_size * map.count * dies); + let mut cur_iova = iova; + + for die in 0..dies { + for i in 0..map.count { + let phys_off = die * 0x20_0000_0000 + i * map.stride; + + let mapping = this.uat.kernel_vm().map_io( + cur_iova, + base + phys_off, + map_size, + if map.writable { + mmu::PROT_FW_MMIO_RW + } else { + mmu::PROT_FW_MMIO_RO + }, + )?; + + this.as_mut().io_mappings_mut().push(mapping, GFP_KERNEL)?; + cur_iova += map_size as u64; + } + } + + this.as_mut() + .initdata_mut() + .runtime_pointers + .hwdata_b + .with_mut(|raw, _| { + raw.io_mappings[index] = fw::initdata::raw::IOMapping { + phys_addr: U64(map.base as u64), + virt_addr: U64(iova + off as u64), + total_size: (map.size * map.count * dies) as u32, + element_size: map.size as u32, + readwrite: U64(map.writable as u64), + }; + }); + + Ok(()) + } + + /// Mark work associated with currently in-progress event slots as failed, after a fault or + /// timeout. + fn mark_pending_events(&self, culprit_slot: Option, error: workqueue::WorkError) { + dev_err!(self.dev.as_ref(), " Pending events:\n"); + + self.initdata.globals.with(|raw, _inner| { + for (index, i) in raw.pending_stamps.iter().enumerate() { + let info = i.info.load(Ordering::Relaxed); + let wait_value = i.wait_value.load(Ordering::Relaxed); + + if info & 1 != 0 { + #[ver(V >= V13_5)] + let slot = (info >> 4) & 0x7f; + #[ver(V < V13_5)] + let slot = (info >> 3) & 0x7f; + #[ver(V >= V13_5)] + let flags = info & 0xf; + #[ver(V < V13_5)] + let flags = info & 0x7; + dev_err!( + self.dev.as_ref(), + " [{}:{}] flags={} value={:#x}\n", + index, + slot, + flags, + wait_value + ); + let error = if culprit_slot.is_some() && culprit_slot != Some(slot) { + workqueue::WorkError::Killed + } else { + error + }; + self.event_manager.mark_error(slot, wait_value, error); + i.info.store(0, Ordering::Relaxed); + i.wait_value.store(0, Ordering::Relaxed); + } + } + }); + } + + /// Fetch the GPU MMU fault information from the hardware registers. + fn get_fault_info(&self) -> Option { + let res = &(*self.dev).resources; + + let info = res.get_fault_info(self.cfg); + if info.is_some() { + dev_err!( + self.dev.as_ref(), + " Fault info: {:#x?}\n", + info.as_ref().unwrap() + ); + } + info + } + + /// Resume the GPU firmware after it halts (due to a timeout, fault, or request). + fn recover(&self) { + self.initdata.fw_status.with(|raw, _inner| { + let halt_count = raw.flags.halt_count.load(Ordering::Relaxed); + let mut halted = raw.flags.halted.load(Ordering::Relaxed); + dev_err!(self.dev.as_ref(), " Halt count: {}\n", halt_count); + dev_err!(self.dev.as_ref(), " Halted: {}\n", halted); + + if halted == 0 { + let start = Instant::::now(); + while start.elapsed() < HALT_ENTER_TIMEOUT { + halted = raw.flags.halted.load(Ordering::Relaxed); + if halted != 0 { + break; + } + mem::sync(); + } + halted = raw.flags.halted.load(Ordering::Relaxed); + } + + if debug_enabled(DebugFlags::NoGpuRecovery) { + dev_crit!( + self.dev.as_ref(), + " GPU recovery is disabled, wedging forever!\n" + ); + } else if halted != 0 { + dev_err!(self.dev.as_ref(), " Attempting recovery...\n"); + raw.flags.halted.store(0, Ordering::SeqCst); + raw.flags.resume.store(1, Ordering::SeqCst); + } else { + dev_err!(self.dev.as_ref(), " Cannot recover.\n"); + } + }); + } + + /// Return the packed GPU enabled core masks. + // Only used for some versions + #[allow(dead_code)] + pub(crate) fn core_masks_packed(&self) -> &[u32] { + self.dyncfg.id.core_masks_packed.as_slice() + } + + /// Kick a submission pipe for a submitted job to tell the firmware to start processing it. + pub(crate) fn run_job(&self, job: workqueue::JobSubmission::ver<'_>) -> Result { + mod_dev_dbg!(self.dev, "GPU: run_job\n"); + + let pipe_type = job.pipe_type(); + mod_dev_dbg!(self.dev, "GPU: run_job: pipe_type={:?}\n", pipe_type); + + let pipes = match pipe_type { + PipeType::Vertex => &self.pipes.vtx, + PipeType::Fragment => &self.pipes.frag, + PipeType::Compute => &self.pipes.comp, + }; + + let index: usize = job.priority() as usize; + let mut pipe = pipes.get(index).ok_or(EIO)?.lock(); + + mod_dev_dbg!(self.dev, "GPU: run_job: run()\n"); + job.run(&mut pipe); + mod_dev_dbg!(self.dev, "GPU: run_job: ring doorbell\n"); + + let mut guard = self.rtkit.lock(); + let rtk = guard.as_mut().unwrap(); + rtk.send_message( + EP_DOORBELL, + MSG_TX_DOORBELL | pipe_type as u64 | ((index as u64) << 2), + )?; + mod_dev_dbg!(self.dev, "GPU: run_job: done\n"); + + Ok(()) + } + + pub(crate) fn start_op(self: &Arc) -> Result { + if self.is_crashed() { + return Err(ENODEV); + } + + let val = self + .initdata + .globals + .with(|raw, _inner| raw.pending_submissions.fetch_add(1, Ordering::Acquire)); + + mod_dev_dbg!(self.dev, "OP start (pending: {})\n", val + 1); + self.kick_firmware()?; + Ok(OpGuard(self.clone())) + } + + fn invalidate_context( + &self, + context: &fw::types::GpuObject, + ) -> Result { + mod_dev_dbg!( + self.dev, + "Invalidating GPU context @ {:?}\n", + context.weak_pointer() + ); + + if self.is_crashed() { + return Err(ENODEV); + } + + let mut guard = self.alloc.lock(); + let (garbage_count, _) = guard.private.garbage(); + let (garbage_count_gpuro, _) = guard.gpu_ro.garbage(); + + let dc = context.with( + |raw, _inner| fw::channels::DeviceControlMsg::ver::DestroyContext { + unk_4: 0, + ctx_23: raw.unk_23, + #[ver(V < V13_3)] + __pad0: Default::default(), + unk_c: U32(0), + unk_10: U32(0), + ctx_0: raw.unk_0, + ctx_1: raw.unk_1, + ctx_4: raw.unk_4, + #[ver(V < V13_3)] + __pad1: Default::default(), + #[ver(V < V13_3)] + unk_18: 0, + gpu_context: Some(context.weak_pointer()), + __pad2: Default::default(), + }, + ); + + mod_dev_dbg!(self.dev, "Context invalidation command: {:?}\n", &dc); + + let mut txch = self.tx_channels.lock(); + + let token = txch.device_control.send(&dc); + + { + let mut guard = self.rtkit.lock(); + let rtk = guard.as_mut().unwrap(); + rtk.send_message(EP_DOORBELL, MSG_TX_DOORBELL | DOORBELL_DEVCTRL)?; + } + + txch.device_control.wait_for(token)?; + + mod_dev_dbg!( + self.dev, + "GPU context invalidated: {:?}\n", + context.weak_pointer() + ); + + // The invalidation does a cache flush, so it is okay to collect garbage + guard.private.collect_garbage(garbage_count); + guard.gpu_ro.collect_garbage(garbage_count_gpuro); + + Ok(()) + } + + #[cfg(CONFIG_DEV_COREDUMP)] + fn generate_crashdump(&self, crashlog: Option<&[u8]>) -> Result { + // Lock the allocators, to block kernel/FW memory mutations (mostly) + let kalloc = self.alloc(); + let pages = self.uat.dump_kernel_pages()?; + core::mem::drop(kalloc); + + let mut crashdump = crate::crashdump::CrashDumpBuilder::new(pages)?; + let initdata_addr = self.initdata.gpu_va().get(); + crashdump.add_agx_info(self.cfg, &self.dyncfg, initdata_addr)?; + if let Some(crashlog) = crashlog { + crashdump.add_crashlog(crashlog)?; + } + let crashdump = KBox::new(crashdump.finalize()?, GFP_KERNEL)?; + + devcoredump::dev_coredump( + self.dev.as_ref(), + &crate::THIS_MODULE, + crashdump, + GFP_KERNEL, + msecs_to_jiffies(60 * 60 * 1000), + ); + + Ok(()) + } +} + +#[versions(AGX)] +impl GpuManager for GpuManager::ver { + fn as_any(&self) -> &dyn Any { + self + } + + fn arc_as_any(self: Arc) -> Arc { + self as Arc + } + + fn init(&self) -> Result { + self.tx_channels.lock().device_control.send( + &fw::channels::DeviceControlMsg::ver::Initialize(Default::default()), + ); + + let initdata = self.initdata.gpu_va().get(); + let mut guard = self.rtkit.lock(); + let rtk = guard.as_mut().unwrap(); + + rtk.boot()?; + rtk.start_endpoint(EP_FIRMWARE)?; + rtk.start_endpoint(EP_DOORBELL)?; + rtk.send_message(EP_FIRMWARE, MSG_INIT | (initdata & INIT_DATA_MASK))?; + rtk.send_message(EP_DOORBELL, MSG_TX_DOORBELL | DOORBELL_DEVCTRL)?; + core::mem::drop(guard); + + self.kick_firmware()?; + Ok(()) + } + + fn update_globals(&self) { + let mut timeout: u32 = 2; + if debug_enabled(DebugFlags::WaitForPowerOff) { + timeout = 0; + } else if debug_enabled(DebugFlags::KeepGpuPowered) { + timeout = 5000; + } + + self.initdata.globals.with(|raw, _inner| { + raw.idle_off_delay_ms.store(timeout, Ordering::Relaxed); + }); + } + + fn alloc(&self) -> Guard<'_, KernelAllocators, MutexBackend> { + /* Clean up idle contexts */ + let mut garbage_ctx = KVec::new(); + core::mem::swap(&mut *self.garbage_contexts.lock(), &mut garbage_ctx); + + for ctx in garbage_ctx { + if self.invalidate_context(&ctx).is_err() { + dev_err!( + self.dev.as_ref(), + "GpuContext: Failed to invalidate GPU context!\n" + ); + if debug_enabled(DebugFlags::OopsOnGpuCrash) { + panic!("GPU firmware timed out"); + } + } + } + + let mut guard = self.alloc.lock(); + let (garbage_count, garbage_bytes) = guard.private.garbage(); + let (ro_garbage_count, ro_garbage_bytes) = guard.gpu_ro.garbage(); + + if garbage_bytes > MAX_FW_ALLOC_GARBAGE_BYTES + || ro_garbage_bytes > MAX_FW_ALLOC_GARBAGE_BYTES + || garbage_count > MAX_FW_ALLOC_GARBAGE_OBJECTS + || ro_garbage_count > MAX_FW_ALLOC_GARBAGE_OBJECTS + { + mod_dev_dbg!( + self.dev, + "Collecting kalloc garbage (private: {} objects, {} bytes, gpuro: {} objects, {} bytes)\n", + garbage_count, + garbage_bytes, + ro_garbage_count, + ro_garbage_bytes + ); + if self.flush_fw_cache().is_err() { + dev_err!(self.dev.as_ref(), "Failed to flush FW cache\n"); + } else { + guard.private.collect_garbage(garbage_count); + guard.gpu_ro.collect_garbage(ro_garbage_count); + } + } + + guard + } + + fn new_vm(&self, kernel_range: Range) -> Result { + self.uat.new_vm(self.ids.vm.next(), kernel_range) + } + + fn bind_vm(&self, vm: &mmu::Vm) -> Result { + self.uat.bind(vm) + } + + fn new_queue( + &self, + vm: mmu::Vm, + ualloc: Arc>, + ualloc_priv: Arc>, + priority: u32, + usc_exec_base: u64, + ) -> Result> { + let mut kalloc = self.alloc(); + let id = self.ids.queue.next(); + Ok(KBox::new( + queue::Queue::ver::new( + &self.dev, + vm, + &mut kalloc, + ualloc, + ualloc_priv, + self.event_manager.clone(), + &self.buffer_mgr, + id, + priority, + usc_exec_base, + )?, + GFP_KERNEL, + )?) + } + + fn kick_firmware(&self) -> Result { + if self.is_crashed() { + return Err(ENODEV); + } + + let mut guard = self.rtkit.lock(); + let rtk = guard.as_mut().unwrap(); + rtk.send_message(EP_DOORBELL, MSG_TX_DOORBELL | DOORBELL_KICKFW)?; + + Ok(()) + } + + fn flush_fw_cache(&self) -> Result { + mod_dev_dbg!(self.dev, "Flushing coprocessor data cache\n"); + + if self.is_crashed() { + return Err(ENODEV); + } + + // ctx_0 == 0xff or ctx_1 == 0xff cause no effect on context, + // but this command does a full cache flush too, so abuse it + // for that. + + let dc = fw::channels::DeviceControlMsg::ver::DestroyContext { + unk_4: 0, + + ctx_23: 0, + #[ver(V < V13_3)] + __pad0: Default::default(), + unk_c: U32(0), + unk_10: U32(0), + ctx_0: 0xff, + ctx_1: 0xff, + ctx_4: 0, + #[ver(V < V13_3)] + __pad1: Default::default(), + #[ver(V < V13_3)] + unk_18: 0, + gpu_context: None, + __pad2: Default::default(), + }; + + let mut txch = self.tx_channels.lock(); + + let token = txch.device_control.send(&dc); + { + let mut guard = self.rtkit.lock(); + let rtk = guard.as_mut().unwrap(); + rtk.send_message(EP_DOORBELL, MSG_TX_DOORBELL | DOORBELL_DEVCTRL)?; + } + + txch.device_control.wait_for(token)?; + Ok(()) + } + + fn ids(&self) -> &SequenceIDs { + &self.ids + } + + fn handle_timeout(&self, counter: u32, event_slot: i32, unk: u32) { + dev_err!(self.dev.as_ref(), " (\\________/) \n"); + dev_err!(self.dev.as_ref(), " | | \n"); + dev_err!(self.dev.as_ref(), "'.| \\ , / |.'\n"); + dev_err!(self.dev.as_ref(), "--| / (( \\ |--\n"); + dev_err!(self.dev.as_ref(), ".'| _-_- |'.\n"); + dev_err!(self.dev.as_ref(), " |________| \n"); + dev_err!(self.dev.as_ref(), "** GPU timeout nya~!!!!! **\n"); + dev_err!(self.dev.as_ref(), " Event slot: {}\n", event_slot); + dev_err!(self.dev.as_ref(), " Timeout count: {}\n", counter); + dev_err!(self.dev.as_ref(), " Unk: {}\n", unk); + + // If we have fault info, consider it a fault. + let error = match self.get_fault_info() { + Some(info) => workqueue::WorkError::Fault(info), + None => workqueue::WorkError::Timeout, + }; + self.mark_pending_events(event_slot.try_into().ok(), error); + self.recover(); + } + + fn handle_fault(&self) { + dev_err!(self.dev.as_ref(), " (\\________/) \n"); + dev_err!(self.dev.as_ref(), " | | \n"); + dev_err!(self.dev.as_ref(), "'.| \\ , / |.'\n"); + dev_err!(self.dev.as_ref(), "--| / (( \\ |--\n"); + dev_err!(self.dev.as_ref(), ".'| _-_- |'.\n"); + dev_err!(self.dev.as_ref(), " |________| \n"); + dev_err!(self.dev.as_ref(), "GPU fault nya~!!!!!\n"); + let error = match self.get_fault_info() { + Some(info) => workqueue::WorkError::Fault(info), + None => workqueue::WorkError::Unknown, + }; + self.mark_pending_events(None, error); + self.recover(); + } + + fn handle_channel_error( + &self, + error_type: ChannelErrorType, + pipe_type: u32, + event_slot: u32, + event_value: u32, + ) { + dev_err!(self.dev.as_ref(), " (\\________/) \n"); + dev_err!(self.dev.as_ref(), " | | \n"); + dev_err!(self.dev.as_ref(), "'.| \\ , / |.'\n"); + dev_err!(self.dev.as_ref(), "--| / (( \\ |--\n"); + dev_err!(self.dev.as_ref(), ".'| _-_- |'.\n"); + dev_err!(self.dev.as_ref(), " |________| \n"); + dev_err!(self.dev.as_ref(), "GPU channel error nya~!!!!!\n"); + dev_err!(self.dev.as_ref(), " Error type: {:?}\n", error_type); + dev_err!(self.dev.as_ref(), " Pipe type: {}\n", pipe_type); + dev_err!(self.dev.as_ref(), " Event slot: {}\n", event_slot); + dev_err!(self.dev.as_ref(), " Event value: {:#x?}\n", event_value); + + self.event_manager.mark_error( + event_slot, + event_value, + workqueue::WorkError::ChannelError(error_type), + ); + + let wq = match self.event_manager.get_owner(event_slot) { + Some(wq) => wq, + None => { + dev_err!( + self.dev.as_ref(), + "Workqueue not found for this event slot!\n" + ); + return; + } + }; + + let wq = match wq.as_any().downcast_ref::() { + Some(wq) => wq, + None => { + dev_crit!(self.dev.as_ref(), "GpuManager mismatched with WorkQueue!\n"); + return; + } + }; + + if debug_enabled(DebugFlags::VerboseFaults) { + wq.dump_info(); + } + + let dc = fw::channels::DeviceControlMsg::ver::RecoverChannel { + pipe_type, + work_queue: wq.info_pointer(), + event_value, + __pad: Default::default(), + }; + + mod_dev_dbg!(self.dev, "Recover Channel command: {:?}\n", &dc); + let mut txch = self.tx_channels.lock(); + + let token = txch.device_control.send(&dc); + { + let mut guard = self.rtkit.lock(); + let rtk = guard.as_mut().unwrap(); + if rtk + .send_message(EP_DOORBELL, MSG_TX_DOORBELL | DOORBELL_DEVCTRL) + .is_err() + { + dev_err!( + self.dev.as_ref(), + "Failed to send Recover Channel command\n" + ); + } + } + + if txch.device_control.wait_for(token).is_err() { + dev_err!( + self.dev.as_ref(), + "Timed out waiting for Recover Channel command\n" + ); + } + + if debug_enabled(DebugFlags::VerboseFaults) { + wq.dump_info(); + } + } + + fn ack_grow(&self, buffer_slot: u32, vm_slot: u32, counter: u32) { + let halt_count = self + .initdata + .fw_status + .with(|raw, _inner| raw.flags.halt_count.load(Ordering::Relaxed)); + + let dc = fw::channels::DeviceControlMsg::ver::GrowTVBAck { + unk_4: 1, + buffer_slot, + vm_slot, + counter, + subpipe: 0, // TODO + halt_count: U64(halt_count), + __pad: Default::default(), + }; + + mod_dev_dbg!(self.dev, "TVB Grow Ack command: {:?}\n", &dc); + + let mut txch = self.tx_channels.lock(); + + txch.device_control.send(&dc); + { + let mut guard = self.rtkit.lock(); + let rtk = guard.as_mut().unwrap(); + if rtk + .send_message(EP_DOORBELL, MSG_TX_DOORBELL | DOORBELL_DEVCTRL) + .is_err() + { + dev_err!(self.dev.as_ref(), "Failed to send TVB Grow Ack command\n"); + } + } + } + + fn fwctl(&self, msg: fw::channels::FwCtlMsg) -> Result { + if self.is_crashed() { + return Err(ENODEV); + } + + let mut fwctl = self.fwctl_channel.lock(); + let token = fwctl.send(&msg); + { + let mut guard = self.rtkit.lock(); + let rtk = guard.as_mut().unwrap(); + rtk.send_message(EP_DOORBELL, MSG_FWCTL)?; + } + fwctl.wait_for(token)?; + Ok(()) + } + + fn get_cfg(&self) -> &'static hw::HwConfig { + self.cfg + } + + fn get_dyncfg(&self) -> &hw::DynConfig { + &self.dyncfg + } + + fn free_context(&self, ctx: KBox>) { + let mut garbage = self.garbage_contexts.lock(); + + if garbage.push(ctx, GFP_KERNEL).is_err() { + dev_err!( + self.dev.as_ref(), + "Failed to reserve space for freed context, deadlock possible.\n" + ); + } + } + + fn is_crashed(&self) -> bool { + self.crashed.load(Ordering::Relaxed) + } + + fn map_timestamp_buffer( + &self, + mut bo: gem::ObjectRef, + range: Range, + ) -> Result { + bo.map_range_into_range( + self.uat.kernel_vm(), + range, + IOVA_KERN_TIMESTAMP_RANGE, + mmu::UAT_PGSZ as u64, + mmu::PROT_FW_SHARED_RW, + false, + ) + } +} + +#[versions(AGX)] +impl GpuManagerPriv for GpuManager::ver { + fn end_op(&self) { + let val = self + .initdata + .globals + .with(|raw, _inner| raw.pending_submissions.fetch_sub(1, Ordering::Release)); + + mod_dev_dbg!(self.dev, "OP end (pending: {})\n", val - 1); + } +} diff --git a/drivers/gpu/drm/asahi/hw/mod.rs b/drivers/gpu/drm/asahi/hw/mod.rs new file mode 100644 index 00000000000000..611764b5463b59 --- /dev/null +++ b/drivers/gpu/drm/asahi/hw/mod.rs @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Per-SoC hardware configuration structures +//! +//! This module contains the definitions used to store per-GPU and per-SoC configuration data. + +use crate::driver::AsahiDevice; +use crate::fw::types::*; +use kernel::c_str; +use kernel::prelude::*; + +const MAX_POWERZONES: usize = 5; + +pub(crate) mod t600x; +pub(crate) mod t602x; +pub(crate) mod t8103; +pub(crate) mod t8112; + +/// GPU generation enumeration. Note: Part of the UABI. +#[derive(Debug, PartialEq, Copy, Clone)] +#[repr(u32)] +pub(crate) enum GpuGen { + G13 = 13, + G14 = 14, +} + +/// GPU variant enumeration. Note: Part of the UABI. +#[derive(Debug, PartialEq, Copy, Clone)] +#[repr(u32)] +pub(crate) enum GpuVariant { + P = 'P' as u32, + G = 'G' as u32, + S = 'S' as u32, + C = 'C' as u32, + D = 'D' as u32, +} + +/// GPU revision enumeration. Note: Part of the UABI. +#[derive(Debug, PartialEq, Copy, Clone)] +#[repr(u32)] +pub(crate) enum GpuRevision { + A0 = 0x00, + A1 = 0x01, + B0 = 0x10, + B1 = 0x11, + C0 = 0x20, + C1 = 0x21, +} + +/// GPU core type enumeration. Note: Part of the firmware ABI. +#[derive(Debug, Copy, Clone)] +#[repr(u32)] +pub(crate) enum GpuCore { + // Unknown = 0, + // G5P = 1, + // G5G = 2, + // G9P = 3, + // G9G = 4, + // G10P = 5, + // G11P = 6, + // G11M = 7, + // G11G = 8, + // G12P = 9, + // G13P = 10, + G13G = 11, + G13S = 12, + G13C = 13, + // G14P = 14, + G14G = 15, + G14S = 16, + G14C = 17, + G14D = 18, // Split out, unlike G13D +} + +/// GPU revision ID. Note: Part of the firmware ABI. +#[derive(Debug, PartialEq, Copy, Clone)] +#[repr(u32)] +pub(crate) enum GpuRevisionID { + // Unknown = 0, + A0 = 1, + A1 = 2, + B0 = 3, + B1 = 4, + C0 = 5, + C1 = 6, +} + +/// A single performance state of the GPU. +#[derive(Debug)] +pub(crate) struct PState { + /// Voltage in millivolts, per GPU cluster. + pub(crate) volt_mv: KVec, + /// Frequency in hertz. + pub(crate) freq_hz: u32, + /// Maximum power consumption of the GPU at this pstate, in milliwatts. + pub(crate) pwr_mw: u32, +} + +impl PState { + pub(crate) fn max_volt_mv(&self) -> u32 { + *self.volt_mv.iter().max().expect("No voltages") + } +} + +/// A power zone definition (we have no idea what this is but Apple puts them in the DT). +#[allow(missing_docs)] +#[derive(Debug, Copy, Clone)] +pub(crate) struct PowerZone { + pub(crate) target: u32, + pub(crate) target_offset: u32, + pub(crate) filter_tc: u32, +} + +/// An MMIO mapping used by the firmware. +#[derive(Debug, Copy, Clone)] +pub(crate) struct IOMapping { + /// Base physical address of the mapping. + pub(crate) base: usize, + /// Whether this mapping should be replicated to all dies + pub(crate) per_die: bool, + /// Number of mappings. + pub(crate) count: usize, + /// Size of one mapping. + pub(crate) size: usize, + /// Stride between mappings. + pub(crate) stride: usize, + /// Whether the mapping should be writable. + pub(crate) writable: bool, +} + +impl IOMapping { + /// Convenience constructor for a new IOMapping. + pub(crate) const fn new( + base: usize, + per_die: bool, + count: usize, + size: usize, + stride: usize, + writable: bool, + ) -> IOMapping { + IOMapping { + base, + per_die, + count, + size, + stride, + writable, + } + } +} + +/// Unknown HwConfigA fields that vary from SoC to SoC. +#[allow(missing_docs)] +#[derive(Debug, Copy, Clone)] +pub(crate) struct HwConfigA { + pub(crate) unk_87c: i32, + pub(crate) unk_8cc: u32, + pub(crate) unk_e24: u32, +} + +/// Unknown HwConfigB fields that vary from SoC to SoC. +#[allow(missing_docs)] +#[derive(Debug, Copy, Clone)] +pub(crate) struct HwConfigB { + pub(crate) unk_454: u32, + pub(crate) unk_4e0: u64, + pub(crate) unk_534: u32, + pub(crate) unk_ab8: u32, + pub(crate) unk_abc: u32, + pub(crate) unk_b30: u32, +} + +/// Render command configs that vary from SoC to SoC. +#[derive(Debug, Copy, Clone)] +pub(crate) struct HwRenderConfig { + /// Vertex/tiling-related configuration register (lsb: disable clustering) + pub(crate) tiling_control: u32, +} + +#[derive(Debug)] +pub(crate) struct HwConfigShared2Curves { + pub(crate) t1_coef: u32, + pub(crate) t2: &'static [i16], + pub(crate) t3_coefs: &'static [u32], + pub(crate) t3_scales: &'static [u32], +} + +/// Static hardware clustering configuration for multi-cluster SoCs. +#[derive(Debug)] +pub(crate) struct HwClusteringConfig { + pub(crate) meta1_blocksize: usize, + pub(crate) meta2_size: usize, + pub(crate) meta3_size: usize, + pub(crate) meta4_size: usize, + pub(crate) max_splits: usize, +} + +/// Static hardware configuration for a given SoC model. +#[derive(Debug)] +pub(crate) struct HwConfig { + /// Chip ID in hex format (e.g. 0x8103 for t8103). + pub(crate) chip_id: u32, + /// GPU generation. + pub(crate) gpu_gen: GpuGen, + /// GPU variant type. + pub(crate) gpu_variant: GpuVariant, + /// GPU core type ID (as known by the firmware). + pub(crate) gpu_core: GpuCore, + + /// Base clock used used for timekeeping. + pub(crate) base_clock_hz: u32, + /// Output address space for the UAT on this SoC. + pub(crate) uat_oas: u32, + /// Number of dies on this SoC. + pub(crate) num_dies: u32, + /// Maximum number of clusters on this SoC. + pub(crate) max_num_clusters: u32, + /// Maximum number of cores per cluster for this GPU. + pub(crate) max_num_cores: u32, + /// Maximum number of frags per cluster for this GPU. + pub(crate) max_num_frags: u32, + /// Maximum number of GPs per cluster for this GPU. + pub(crate) max_num_gps: u32, + + /// Required size of the first preemption buffer. + pub(crate) preempt1_size: usize, + /// Required size of the second preemption buffer. + pub(crate) preempt2_size: usize, + /// Required size of the third preemption buffer. + pub(crate) preempt3_size: usize, + + /// Required size of the compute preemption buffer. + pub(crate) compute_preempt1_size: usize, + + pub(crate) clustering: Option, + + /// Rendering-relevant configuration. + pub(crate) render: HwRenderConfig, + + /// Misc HWDataA field values. + pub(crate) da: HwConfigA, + /// Misc HWDataB field values. + pub(crate) db: HwConfigB, + /// HwDataShared1.table. + pub(crate) shared1_tab: &'static [i32], + /// HwDataShared1.unk_a4. + pub(crate) shared1_a4: u32, + /// HwDataShared2.table. + pub(crate) shared2_tab: &'static [i32], + /// HwDataShared2.unk_508. + pub(crate) shared2_unk_508: u32, + /// HwDataShared2.unk_508. + pub(crate) shared2_curves: Option, + + /// HwDataShared3.unk_8. + pub(crate) shared3_unk: u32, + /// HwDataShared3.table. + pub(crate) shared3_tab: &'static [u32], + + /// Globals.idle_off_standby_timer. + pub(crate) idle_off_standby_timer_default: u32, + /// Globals.unk_hws2_4. + pub(crate) unk_hws2_4: Option<[F32; 8]>, + /// Globals.unk_hws2_24. + pub(crate) unk_hws2_24: u32, + /// Globals.unk_54 + pub(crate) global_unk_54: u16, + + /// Constant related to SRAM voltages. + pub(crate) sram_k: F32, + /// Unknown per-cluster coefficients 1. + pub(crate) unk_coef_a: &'static [&'static [F32]], + /// Unknown per-cluster coefficients 2. + pub(crate) unk_coef_b: &'static [&'static [F32]], + /// Unknown table in Global struct. + pub(crate) global_tab: Option<&'static [u8]>, + /// Whether this GPU has CS/AFR performance states + pub(crate) has_csafr: bool, + + /// Temperature sensor list (8 bits per sensor). + pub(crate) fast_sensor_mask: [u64; 2], + /// Temperature sensor list (alternate). + pub(crate) fast_sensor_mask_alt: [u64; 2], + /// Temperature sensor present bitmask. + pub(crate) fast_die0_sensor_present: u32, + /// Required MMIO mappings for this GPU/firmware. + pub(crate) io_mappings: &'static [Option], + /// SRAM base + pub(crate) sram_base: Option, + /// SRAM size + pub(crate) sram_size: Option, +} + +/// Dynamic (fetched from hardware/DT) configuration. +#[derive(Debug)] +pub(crate) struct DynConfig { + /// Base physical address of the UAT TTB (from DT reserved memory region). + pub(crate) uat_ttb_base: u64, + /// GPU ID configuration read from hardware. + pub(crate) id: GpuIdConfig, + /// Power calibration configuration for this specific chip/device. + pub(crate) pwr: PwrConfig, + /// Firmware version. + #[allow(dead_code)] + pub(crate) firmware_version: KVec, + + pub(crate) hw_data_a: KVVec, + pub(crate) hw_data_b: KVVec, + pub(crate) hw_globals: KVVec, +} + +/// Specific GPU ID configuration fetched from SGX MMIO registers. +#[derive(Debug)] +pub(crate) struct GpuIdConfig { + /// GPU generation (should match static config). + pub(crate) gpu_gen: GpuGen, + /// GPU variant type (should match static config). + pub(crate) gpu_variant: GpuVariant, + /// GPU silicon revision. + pub(crate) gpu_rev: GpuRevision, + /// GPU silicon revision ID (firmware enum). + pub(crate) gpu_rev_id: GpuRevisionID, + /// Total number of GPU clusters. + pub(crate) num_clusters: u32, + /// Maximum number of GPU cores per cluster. + pub(crate) num_cores: u32, + /// Number of frags per cluster. + pub(crate) num_frags: u32, + /// Number of GPs per cluster. + pub(crate) num_gps: u32, + /// Total number of active cores for the whole GPU. + pub(crate) total_active_cores: u32, + /// Mask of active cores per cluster. + pub(crate) core_masks: KVec, + /// Packed mask of all active cores. + pub(crate) core_masks_packed: KVec, +} + +/// Configurable CS/AFR GPU power settings from the device tree. +#[derive(Debug)] +pub(crate) struct CsAfrPwrConfig { + /// GPU CS performance state list. + pub(crate) perf_states_cs: KVec, + /// GPU AFR performance state list. + pub(crate) perf_states_afr: KVec, + + /// CS leakage coefficient per die. + pub(crate) leak_coef_cs: KVec, + /// AFR leakage coefficient per die. + pub(crate) leak_coef_afr: KVec, + + /// Minimum voltage for the CS/AFR SRAM power domain in microvolts. + pub(crate) min_sram_microvolt: u32, +} + +/// Configurable GPU power settings from the device tree. +#[derive(Debug)] +pub(crate) struct PwrConfig { + /// GPU performance state list. + pub(crate) perf_states: KVec, + /// GPU power zone list. + pub(crate) power_zones: KVec, + + /// Core leakage coefficient per cluster. + pub(crate) core_leak_coef: KVec, + /// SRAM leakage coefficient per cluster. + pub(crate) sram_leak_coef: KVec, + + pub(crate) csafr: Option, + + /// Maximum total power of the GPU in milliwatts. + pub(crate) max_power_mw: u32, + /// Maximum frequency of the GPU in megahertz. + pub(crate) max_freq_mhz: u32, + + /// Minimum performance state to start at. + pub(crate) perf_base_pstate: u32, + /// Maximum enabled performance state. + pub(crate) perf_max_pstate: u32, + + /// Minimum voltage for the SRAM power domain in microvolts. + pub(crate) min_sram_microvolt: u32, + + // Most of these fields are just named after Apple ADT property names and we don't fully + // understand them. They configure various power-related PID loops and filters. + /// Average power filter time constant in milliseconds. + pub(crate) avg_power_filter_tc_ms: u32, + /// Average power filter PID integral gain? + pub(crate) avg_power_ki_only: F32, + /// Average power filter PID proportional gain? + pub(crate) avg_power_kp: F32, + pub(crate) avg_power_min_duty_cycle: u32, + /// Average power target filter time constant in periods. + pub(crate) avg_power_target_filter_tc: u32, + /// "Fast die0" (temperature?) PID integral gain. + pub(crate) fast_die0_integral_gain: F32, + /// "Fast die0" (temperature?) PID proportional gain. + pub(crate) fast_die0_proportional_gain: F32, + pub(crate) fast_die0_prop_tgt_delta: u32, + pub(crate) fast_die0_release_temp: u32, + /// Delay from the fender (?) becoming idle to powerdown + pub(crate) fender_idle_off_delay_ms: u32, + /// Timeout from firmware early wake to sleep if no work was submitted (?) + pub(crate) fw_early_wake_timeout_ms: u32, + /// Delay from the GPU becoming idle to powerdown + pub(crate) idle_off_delay_ms: u32, + /// Related to the above? + pub(crate) idle_off_standby_timer: u32, + /// Percent? + pub(crate) perf_boost_ce_step: u32, + /// Minimum utilization before performance state is increased in %. + pub(crate) perf_boost_min_util: u32, + pub(crate) perf_filter_drop_threshold: u32, + /// Performance PID filter time constant? (periods?) + pub(crate) perf_filter_time_constant: u32, + /// Performance PID filter time constant 2? (periods?) + pub(crate) perf_filter_time_constant2: u32, + /// Performance PID integral gain. + pub(crate) perf_integral_gain: F32, + /// Performance PID integral gain 2 (?). + pub(crate) perf_integral_gain2: F32, + pub(crate) perf_integral_min_clamp: u32, + /// Performance PID proportional gain. + pub(crate) perf_proportional_gain: F32, + /// Performance PID proportional gain 2 (?). + pub(crate) perf_proportional_gain2: F32, + pub(crate) perf_reset_iters: u32, + /// Target GPU utilization for the performance controller in %. + pub(crate) perf_tgt_utilization: u32, + /// Power sampling period in milliseconds. + pub(crate) power_sample_period: u32, + /// PPM (?) filter time constant in milliseconds. + pub(crate) ppm_filter_time_constant_ms: u32, + /// PPM (?) filter PID integral gain. + pub(crate) ppm_ki: F32, + /// PPM (?) filter PID proportional gain. + pub(crate) ppm_kp: F32, + /// Power consumption filter time constant (periods?) + pub(crate) pwr_filter_time_constant: u32, + /// Power consumption filter PID integral gain. + pub(crate) pwr_integral_gain: F32, + pub(crate) pwr_integral_min_clamp: u32, + pub(crate) pwr_min_duty_cycle: u32, + pub(crate) pwr_proportional_gain: F32, + /// Power sample period in base clocks, used when not an integer number of ms + pub(crate) pwr_sample_period_aic_clks: u32, + + pub(crate) se_engagement_criteria: i32, + pub(crate) se_filter_time_constant: u32, + pub(crate) se_filter_time_constant_1: u32, + pub(crate) se_inactive_threshold: u32, + pub(crate) se_ki: F32, + pub(crate) se_ki_1: F32, + pub(crate) se_kp: F32, + pub(crate) se_kp_1: F32, + pub(crate) se_reset_criteria: u32, +} + +impl PwrConfig { + fn load_opp( + dev: &AsahiDevice, + name: &CStr, + cfg: &HwConfig, + is_main: bool, + ) -> Result> { + let mut perf_states = KVec::new(); + + let node = dev.as_ref().of_node().ok_or(EIO)?; + let opps = node.parse_phandle(name, 0).ok_or(EIO)?; + + for opp in opps.children() { + let freq_hz: u64 = opp.get_property(c_str!("opp-hz"))?; + let mut volt_uv: KVec = opp.get_property(c_str!("opp-microvolt"))?; + let pwr_uw: u32 = if is_main { + opp.get_property(c_str!("opp-microwatt"))? + } else { + 0 + }; + + let voltage_count = if is_main { + cfg.max_num_clusters + } else { + cfg.num_dies + }; + + if volt_uv.len() != voltage_count as usize { + dev_err!( + dev.as_ref(), + "Invalid opp-microvolt length (expected {}, got {})\n", + voltage_count, + volt_uv.len() + ); + return Err(EINVAL); + } + + volt_uv.iter_mut().for_each(|a| *a /= 1000); + let volt_mv = volt_uv; + + let pwr_mw = pwr_uw / 1000; + + perf_states.push( + PState { + freq_hz: freq_hz.try_into()?, + volt_mv, + pwr_mw, + }, + GFP_KERNEL, + )?; + } + + if perf_states.is_empty() { + Err(EINVAL) + } else { + Ok(perf_states) + } + } + + /// Load the GPU power configuration from the device tree. + pub(crate) fn load(dev: &AsahiDevice, cfg: &HwConfig) -> Result { + let perf_states = Self::load_opp(dev, c_str!("operating-points-v2"), cfg, true)?; + let node = dev.as_ref().of_node().ok_or(EIO)?; + + macro_rules! prop { + ($prop:expr, $default:expr) => {{ + node.get_opt_property(c_str!($prop)) + .map_err(|e| { + dev_err!(dev.as_ref(), "Error reading property {}: {:?}\n", $prop, e); + e + })? + .unwrap_or($default) + }}; + ($prop:expr) => {{ + node.get_property(c_str!($prop)).map_err(|e| { + dev_err!(dev.as_ref(), "Error reading property {}: {:?}\n", $prop, e); + e + })? + }}; + } + + let pz_data = prop!("apple,power-zones", KVec::new()); + + if pz_data.len() > 3 * MAX_POWERZONES || pz_data.len() % 3 != 0 { + dev_err!(dev.as_ref(), "Invalid apple,power-zones value\n"); + return Err(EINVAL); + } + + let pz_count = pz_data.len() / 3; + let mut power_zones = KVec::new(); + for i in (0..pz_count).step_by(3) { + power_zones.push( + PowerZone { + target: pz_data[i], + target_offset: pz_data[i + 1], + filter_tc: pz_data[i + 2], + }, + GFP_KERNEL, + )?; + } + + let core_leak_coef: KVec = prop!("apple,core-leak-coef"); + let sram_leak_coef: KVec = prop!("apple,sram-leak-coef"); + + if core_leak_coef.len() != cfg.max_num_clusters as usize { + dev_err!(dev.as_ref(), "Invalid apple,core-leak-coef\n"); + return Err(EINVAL); + } + if sram_leak_coef.len() != cfg.max_num_clusters as usize { + dev_err!(dev.as_ref(), "Invalid apple,sram_leak_coef\n"); + return Err(EINVAL); + } + + let csafr = if cfg.has_csafr { + Some(CsAfrPwrConfig { + perf_states_cs: Self::load_opp(dev, c_str!("apple,cs-opp"), cfg, false)?, + perf_states_afr: Self::load_opp(dev, c_str!("apple,afr-opp"), cfg, false)?, + leak_coef_cs: prop!("apple,cs-leak-coef"), + leak_coef_afr: prop!("apple,afr-leak-coef"), + min_sram_microvolt: prop!("apple,csafr-min-sram-microvolt"), + }) + } else { + None + }; + + let power_sample_period: u32 = prop!("apple,power-sample-period"); + + Ok(PwrConfig { + core_leak_coef, + sram_leak_coef, + + max_power_mw: perf_states.iter().map(|a| a.pwr_mw).max().unwrap(), + max_freq_mhz: perf_states.iter().map(|a| a.freq_hz).max().unwrap() / 1_000_000, + + perf_base_pstate: prop!("apple,perf-base-pstate", 1), + perf_max_pstate: perf_states.len() as u32 - 1, + min_sram_microvolt: prop!("apple,min-sram-microvolt"), + + avg_power_filter_tc_ms: prop!("apple,avg-power-filter-tc-ms"), + avg_power_ki_only: prop!("apple,avg-power-ki-only"), + avg_power_kp: prop!("apple,avg-power-kp"), + avg_power_min_duty_cycle: prop!("apple,avg-power-min-duty-cycle"), + avg_power_target_filter_tc: prop!("apple,avg-power-target-filter-tc"), + fast_die0_integral_gain: prop!("apple,fast-die0-integral-gain"), + fast_die0_proportional_gain: prop!("apple,fast-die0-proportional-gain"), + fast_die0_prop_tgt_delta: prop!("apple,fast-die0-prop-tgt-delta", 0), + fast_die0_release_temp: prop!("apple,fast-die0-release-temp", 80), + fender_idle_off_delay_ms: prop!("apple,fender-idle-off-delay-ms", 40), + fw_early_wake_timeout_ms: prop!("apple,fw-early-wake-timeout-ms", 5), + idle_off_delay_ms: prop!("apple,idle-off-delay-ms", 2), + idle_off_standby_timer: prop!( + "apple,idleoff-standby-timer", + cfg.idle_off_standby_timer_default + ), + perf_boost_ce_step: prop!("apple,perf-boost-ce-step", 25), + perf_boost_min_util: prop!("apple,perf-boost-min-util", 100), + perf_filter_drop_threshold: prop!("apple,perf-filter-drop-threshold"), + perf_filter_time_constant2: prop!("apple,perf-filter-time-constant2"), + perf_filter_time_constant: prop!("apple,perf-filter-time-constant"), + perf_integral_gain2: prop!("apple,perf-integral-gain2"), + perf_integral_gain: prop!("apple,perf-integral-gain", f32!(7.8956833)), + perf_integral_min_clamp: prop!("apple,perf-integral-min-clamp"), + perf_proportional_gain2: prop!("apple,perf-proportional-gain2"), + perf_proportional_gain: prop!("apple,perf-proportional-gain", f32!(14.707963)), + perf_reset_iters: prop!("apple,perf-reset-iters", 6), + perf_tgt_utilization: prop!("apple,perf-tgt-utilization"), + power_sample_period, + ppm_filter_time_constant_ms: prop!("apple,ppm-filter-time-constant-ms"), + ppm_ki: prop!("apple,ppm-ki"), + ppm_kp: prop!("apple,ppm-kp"), + pwr_filter_time_constant: prop!("apple,pwr-filter-time-constant", 313), + pwr_integral_gain: prop!("apple,pwr-integral-gain", f32!(0.0202129)), + pwr_integral_min_clamp: prop!("apple,pwr-integral-min-clamp", 0), + pwr_min_duty_cycle: prop!("apple,pwr-min-duty-cycle"), + pwr_proportional_gain: prop!("apple,pwr-proportional-gain", f32!(5.2831855)), + pwr_sample_period_aic_clks: prop!( + "apple,pwr-sample-period-aic-clks", + cfg.base_clock_hz / 1000 * power_sample_period + ), + se_engagement_criteria: prop!("apple,se-engagement-criteria", -1), + se_filter_time_constant: prop!("apple,se-filter-time-constant", 9), + se_filter_time_constant_1: prop!("apple,se-filter-time-constant-1", 3), + se_inactive_threshold: prop!("apple,se-inactive-threshold", 2500), + se_ki: prop!("apple,se-ki", f32!(-50.0)), + se_ki_1: prop!("apple,se-ki-1", f32!(-100.0)), + se_kp: prop!("apple,se-kp", f32!(-5.0)), + se_kp_1: prop!("apple,se-kp-1", f32!(-10.0)), + se_reset_criteria: prop!("apple,se-reset-criteria", 50), + + perf_states, + power_zones, + csafr, + }) + } + + pub(crate) fn max_frequency_khz(&self) -> u32 { + self.perf_states[self.perf_max_pstate as usize].freq_hz / 1000 + } +} diff --git a/drivers/gpu/drm/asahi/hw/t600x.rs b/drivers/gpu/drm/asahi/hw/t600x.rs new file mode 100644 index 00000000000000..58665f985ec38e --- /dev/null +++ b/drivers/gpu/drm/asahi/hw/t600x.rs @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Hardware configuration for t600x (M1 Pro/Max/Ultra) platforms. + +use crate::f32; + +use super::*; + +const fn iomaps(mcc_count: usize, has_die1: bool) -> [Option; 20] { + [ + Some(IOMapping::new(0x404d00000, false, 1, 0x1c000, 0, true)), // Fender + Some(IOMapping::new(0x20e100000, false, 1, 0x4000, 0, false)), // AICTimer + Some(IOMapping::new(0x28e104000, false, 1, 0x4000, 0, true)), // AICSWInt + Some(IOMapping::new(0x404000000, false, 1, 0x20000, 0, true)), // RGX + None, // UVD + None, // unused + None, // DisplayUnderrunWA + Some(IOMapping::new(0x28e494000, true, 1, 0x4000, 0, false)), // AnalogTempSensorControllerRegs + None, // PMPDoorbell + Some(IOMapping::new(0x404d80000, false, 1, 0x8000, 0, true)), // MetrologySensorRegs + Some(IOMapping::new(0x204d61000, false, 1, 0x1000, 0, true)), // GMGIFAFRegs + Some(IOMapping::new( + 0x200000000, + true, + mcc_count, + 0xd8000, + 0x1000000, + true, + )), // MCache registers + None, // AICBankedRegisters + None, // PMGRScratch + Some(IOMapping::new(0x2643c4000, false, 1, 0x1000, 0, true)), // NIA Special agent idle register die 0 + if has_die1 { + // NIA Special agent idle register die 1 + Some(IOMapping::new(0x22643c4000, false, 1, 0x1000, 0, true)) + } else { + None + }, + None, // CRE registers + None, // Streaming codec registers + Some(IOMapping::new(0x28e3d0000, false, 1, 0x1000, 0, true)), // ? + Some(IOMapping::new(0x28e3c0000, false, 1, 0x2000, 0, false)), // ? + ] +} + +pub(crate) const HWCONFIG_T6002: super::HwConfig = HwConfig { + chip_id: 0x6002, + gpu_gen: GpuGen::G13, + gpu_variant: GpuVariant::D, + gpu_core: GpuCore::G13C, + + base_clock_hz: 24_000_000, + uat_oas: 42, + num_dies: 2, + max_num_clusters: 8, + max_num_cores: 8, + max_num_frags: 8, + max_num_gps: 4, + + preempt1_size: 0x540, + preempt2_size: 0x280, + preempt3_size: 0x20, + compute_preempt1_size: 0x3bd00, + clustering: Some(HwClusteringConfig { + meta1_blocksize: 0x44, + meta2_size: 0xc0 * 8, + meta3_size: 0x280 * 8, + meta4_size: 0x30 * 16, + max_splits: 16, + }), + + render: HwRenderConfig { + tiling_control: 0xa540, + }, + + da: HwConfigA { + unk_87c: 900, + unk_8cc: 11000, + unk_e24: 125, + }, + db: HwConfigB { + unk_454: 1, + unk_4e0: 4, + unk_534: 1, + unk_ab8: 0x2084, + unk_abc: 0x80, + unk_b30: 0, + }, + shared1_tab: &[ + 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, + 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, + ], + shared1_a4: 0xffff, + shared2_tab: &[-1, -1, -1, -1, 0x2aa, 0xaaa, -1, -1, 0, 0], + shared2_unk_508: 0xcc00001, + shared2_curves: None, + shared3_unk: 0, + shared3_tab: &[], + idle_off_standby_timer_default: 0, + unk_hws2_4: None, + unk_hws2_24: 0, + global_unk_54: 0xffff, + sram_k: f32!(1.02), + unk_coef_a: &[ + &f32!([9.838]), + &f32!([9.819]), + &f32!([9.826]), + &f32!([9.799]), + &f32!([9.799]), + &f32!([9.826]), + &f32!([9.819]), + &f32!([9.838]), + ], + unk_coef_b: &[ + &f32!([13.0]), + &f32!([13.0]), + &f32!([13.0]), + &f32!([13.0]), + &f32!([13.0]), + &f32!([13.0]), + &f32!([13.0]), + &f32!([13.0]), + ], + global_tab: Some(&[ + 0, 1, 2, 1, 1, 90, 75, 1, 1, 1, 2, 90, 75, 1, 1, 1, 1, 90, 75, 1, 1, + ]), + has_csafr: false, + fast_sensor_mask: [0x8080808080808080, 0], + fast_sensor_mask_alt: [0x9090909090909090, 0], + fast_die0_sensor_present: 0xff, + io_mappings: &iomaps(8, true), + sram_base: None, + sram_size: None, +}; + +pub(crate) const HWCONFIG_T6001: super::HwConfig = HwConfig { + chip_id: 0x6001, + gpu_variant: GpuVariant::C, + gpu_core: GpuCore::G13C, + + num_dies: 1, + max_num_clusters: 4, + fast_sensor_mask: [0x80808080, 0], + fast_sensor_mask_alt: [0x90909090, 0], + fast_die0_sensor_present: 0x0f, + io_mappings: &iomaps(8, false), + ..HWCONFIG_T6002 +}; + +pub(crate) const HWCONFIG_T6000: super::HwConfig = HwConfig { + chip_id: 0x6000, + gpu_variant: GpuVariant::S, + gpu_core: GpuCore::G13S, + + max_num_clusters: 2, + fast_sensor_mask: [0x8080, 0], + fast_sensor_mask_alt: [0x9090, 0], + fast_die0_sensor_present: 0x03, + io_mappings: &iomaps(4, false), + ..HWCONFIG_T6001 +}; diff --git a/drivers/gpu/drm/asahi/hw/t602x.rs b/drivers/gpu/drm/asahi/hw/t602x.rs new file mode 100644 index 00000000000000..98a7ac2b76e571 --- /dev/null +++ b/drivers/gpu/drm/asahi/hw/t602x.rs @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Hardware configuration for t600x (M1 Pro/Max/Ultra) platforms. + +use crate::f32; + +use super::*; + +const fn iomaps(chip_id: u32, mcc_count: usize) -> [Option; 24] { + [ + Some(IOMapping::new(0x404d00000, false, 1, 0x144000, 0, true)), // Fender + Some(IOMapping::new(0x20e100000, false, 1, 0x4000, 0, false)), // AICTimer + Some(IOMapping::new(0x28e106000, false, 1, 0x4000, 0, true)), // AICSWInt + Some(IOMapping::new(0x404000000, false, 1, 0x20000, 0, true)), // RGX + None, // UVD + None, // unused + None, // DisplayUnderrunWA + Some(match chip_id { + 0x6020 => IOMapping::new(0x28e460000, true, 1, 0x4000, 0, false), + _ => IOMapping::new(0x28e478000, true, 1, 0x4000, 0, false), + }), // AnalogTempSensorControllerRegs + None, // PMPDoorbell + Some(IOMapping::new(0x404e08000, false, 1, 0x8000, 0, true)), // MetrologySensorRegs + None, // GMGIFAFRegs + Some(IOMapping::new( + 0x200000000, + true, + mcc_count, + 0xd8000, + 0x1000000, + true, + )), // MCache registers + Some(IOMapping::new(0x28e118000, false, 1, 0x4000, 0, false)), // AICBankedRegisters + None, // PMGRScratch + None, // NIA Special agent idle register die 0 + None, // NIA Special agent idle register die 1 + None, // CRE registers + None, // Streaming codec registers + Some(IOMapping::new(0x28e3d0000, false, 1, 0x4000, 0, true)), // ? + Some(IOMapping::new(0x28e3c0000, false, 1, 0x4000, 0, false)), // ? + Some(IOMapping::new(0x28e3d8000, false, 1, 0x4000, 0, true)), // ? + Some(IOMapping::new(0x404eac000, true, 1, 0x4000, 0, true)), // ? + None, + None, + ] +} + +// TODO: Tentative +pub(crate) const HWCONFIG_T6022: super::HwConfig = HwConfig { + chip_id: 0x6022, + gpu_gen: GpuGen::G14, + gpu_variant: GpuVariant::D, + gpu_core: GpuCore::G14D, + + base_clock_hz: 24_000_000, + uat_oas: 42, + num_dies: 2, + max_num_clusters: 8, + max_num_cores: 10, + max_num_frags: 10, + max_num_gps: 4, + + preempt1_size: 0x540, + preempt2_size: 0x280, + preempt3_size: 0x40, + compute_preempt1_size: 0x25980 * 2, // Conservative guess + clustering: Some(HwClusteringConfig { + meta1_blocksize: 0x44, + meta2_size: 0xc0 * 16, + meta3_size: 0x280 * 16, + meta4_size: 0x10 * 128, + max_splits: 64, + }), + + render: HwRenderConfig { + tiling_control: 0x180340, + }, + + da: HwConfigA { + unk_87c: 500, + unk_8cc: 11000, + unk_e24: 125, + }, + db: HwConfigB { + unk_454: 1, + unk_4e0: 4, + unk_534: 0, + unk_ab8: 0, // Unused + unk_abc: 0, // Unused + unk_b30: 0, + }, + shared1_tab: &[ + 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, + 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, + ], + shared1_a4: 0, + shared2_tab: &[0x800, 0x1555, -1, -1, -1, -1, -1, -1, 0xaaaaa, 0], + shared2_unk_508: 0xc00007, + shared2_curves: Some(HwConfigShared2Curves { + t1_coef: 11000, + t2: &[ + 0xf07, 0x4c0, 0x680, 0x8c0, 0xa80, 0xc40, 0xd80, 0xec0, 0xf40, + ], + t3_coefs: &[0, 20, 27, 36, 43, 50, 55, 60, 62], + t3_scales: &[9, 3209, 10400], + }), + shared3_unk: 8, + shared3_tab: &[ + 125, 125, 125, 125, 125, 125, 125, 125, 7500, 125, 125, 125, 125, 125, 125, 125, + ], + idle_off_standby_timer_default: 700, + unk_hws2_4: Some(f32!([1.0, 0.8, 0.2, 0.9, 0.1, 0.25, 0.5, 0.9])), + unk_hws2_24: 6, + global_unk_54: 4000, + sram_k: f32!(1.02), + unk_coef_a: &[ + &f32!([0.0, 8.2, 0.0, 6.9, 6.9]), + &f32!([0.0, 0.0, 0.0, 6.9, 6.9]), + &f32!([0.0, 8.2, 0.0, 6.9, 0.0]), + &f32!([0.0, 0.0, 0.0, 6.9, 0.0]), + &f32!([0.0, 0.0, 0.0, 6.9, 0.0]), + &f32!([0.0, 8.2, 0.0, 6.9, 0.0]), + &f32!([0.0, 0.0, 0.0, 6.9, 6.9]), + &f32!([0.0, 8.2, 0.0, 6.9, 6.9]), + ], + unk_coef_b: &[ + &f32!([0.0, 9.0, 0.0, 8.0, 8.0]), + &f32!([0.0, 0.0, 0.0, 8.0, 8.0]), + &f32!([0.0, 9.0, 0.0, 8.0, 0.0]), + &f32!([0.0, 0.0, 0.0, 8.0, 0.0]), + &f32!([0.0, 0.0, 0.0, 8.0, 0.0]), + &f32!([0.0, 9.0, 0.0, 8.0, 0.0]), + &f32!([0.0, 0.0, 0.0, 8.0, 8.0]), + &f32!([0.0, 9.0, 0.0, 8.0, 8.0]), + ], + global_tab: Some(&[ + 0, 2, 2, 1, 1, 90, 75, 1, 1, 1, 2, 90, 75, 1, 1, 1, 2, 90, 75, 1, 1, 1, 1, 90, 75, 1, 1, + ]), + has_csafr: true, + fast_sensor_mask: [0x40005000c000d00, 0xd000c0005000400], + // Apple typo? Should probably be 0x140015001c001d00 + fast_sensor_mask_alt: [0x140015001d001d00, 0x1d001c0015001400], + fast_die0_sensor_present: 0, // Unused + io_mappings: &iomaps(0x6022, 8), + sram_base: Some(0x404d60000), + sram_size: Some(0x20000), +}; + +pub(crate) const HWCONFIG_T6021: super::HwConfig = HwConfig { + chip_id: 0x6021, + gpu_variant: GpuVariant::C, + gpu_core: GpuCore::G14C, + + num_dies: 1, + max_num_clusters: 4, + compute_preempt1_size: 0x25980, + unk_hws2_4: Some(f32!([1.0, 0.8, 0.2, 0.9, 0.1, 0.25, 0.7, 0.9])), + fast_sensor_mask: [0x40005000c000d00, 0], + fast_sensor_mask_alt: [0x140015001d001d00, 0], + io_mappings: &iomaps(0x6021, 8), + ..HWCONFIG_T6022 +}; + +pub(crate) const HWCONFIG_T6020: super::HwConfig = HwConfig { + chip_id: 0x6020, + gpu_variant: GpuVariant::S, + gpu_core: GpuCore::G14S, + + db: HwConfigB { + unk_454: 0, + ..HWCONFIG_T6021.db + }, + + max_num_clusters: 2, + fast_sensor_mask: [0xc000d00, 0], + fast_sensor_mask_alt: [0x1d001d00, 0], + io_mappings: &iomaps(0x6020, 4), + ..HWCONFIG_T6021 +}; diff --git a/drivers/gpu/drm/asahi/hw/t8103.rs b/drivers/gpu/drm/asahi/hw/t8103.rs new file mode 100644 index 00000000000000..484bf6c3414f2f --- /dev/null +++ b/drivers/gpu/drm/asahi/hw/t8103.rs @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Hardware configuration for t8103 platforms (M1). + +use crate::f32; + +use super::*; + +pub(crate) const HWCONFIG: super::HwConfig = HwConfig { + chip_id: 0x8103, + gpu_gen: GpuGen::G13, + gpu_variant: GpuVariant::G, + gpu_core: GpuCore::G13G, + + base_clock_hz: 24_000_000, + uat_oas: 40, + num_dies: 1, + max_num_clusters: 1, + max_num_cores: 8, + max_num_frags: 8, + max_num_gps: 4, + + preempt1_size: 0x540, + preempt2_size: 0x280, + preempt3_size: 0x20, + compute_preempt1_size: 0x7f80, + clustering: None, + + render: HwRenderConfig { + // bit 0: disable clustering (always) + tiling_control: 0xa041, + }, + + da: HwConfigA { + unk_87c: -220, + unk_8cc: 9880, + unk_e24: 112, + }, + db: HwConfigB { + unk_454: 1, + unk_4e0: 0, + unk_534: 0, + unk_ab8: 0x48, + unk_abc: 0x8, + unk_b30: 0, + }, + shared1_tab: &[ + -1, 0x7282, 0x50ea, 0x370a, 0x25be, 0x1c1f, 0x16fb, -1, -1, -1, -1, -1, -1, -1, -1, -1, + ], + shared1_a4: 0xffff, + shared2_tab: &[0x800, 0x1555, -1, -1, -1, -1, -1, -1, 0, 0], + shared2_unk_508: 0xc00007, + shared2_curves: None, + shared3_unk: 0, + shared3_tab: &[], + idle_off_standby_timer_default: 0, + unk_hws2_4: None, + unk_hws2_24: 0, + global_unk_54: 0xffff, + sram_k: f32!(1.02), + unk_coef_a: &[], + unk_coef_b: &[], + global_tab: None, + has_csafr: false, + fast_sensor_mask: [0x12, 0], + fast_sensor_mask_alt: [0x12, 0], + fast_die0_sensor_present: 0x01, + io_mappings: &[ + Some(IOMapping::new(0x204d00000, false, 1, 0x1c000, 0, true)), // Fender + Some(IOMapping::new(0x20e100000, false, 1, 0x4000, 0, false)), // AICTimer + Some(IOMapping::new(0x23b104000, false, 1, 0x4000, 0, true)), // AICSWInt + Some(IOMapping::new(0x204000000, false, 1, 0x20000, 0, true)), // RGX + None, // UVD + None, // unused + None, // DisplayUnderrunWA + Some(IOMapping::new(0x23b2e8000, false, 1, 0x1000, 0, false)), // AnalogTempSensorControllerRegs + Some(IOMapping::new(0x23bc00000, false, 1, 0x1000, 0, true)), // PMPDoorbell + Some(IOMapping::new(0x204d80000, false, 1, 0x5000, 0, true)), // MetrologySensorRegs + Some(IOMapping::new(0x204d61000, false, 1, 0x1000, 0, true)), // GMGIFAFRegs + Some(IOMapping::new(0x200000000, false, 1, 0xd6400, 0, true)), // MCache registers + None, // AICBankedRegisters + Some(IOMapping::new(0x23b738000, false, 1, 0x1000, 0, true)), // PMGRScratch + None, // NIA Special agent idle register die 0 + None, // NIA Special agent idle register die 1 + None, // CRE registers + None, // Streaming codec registers + None, // + None, // + ], + sram_base: None, + sram_size: None, +}; diff --git a/drivers/gpu/drm/asahi/hw/t8112.rs b/drivers/gpu/drm/asahi/hw/t8112.rs new file mode 100644 index 00000000000000..3eba0457d76ac9 --- /dev/null +++ b/drivers/gpu/drm/asahi/hw/t8112.rs @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Hardware configuration for t8112 platforms (M2). + +use crate::f32; + +use super::*; + +pub(crate) const HWCONFIG: super::HwConfig = HwConfig { + chip_id: 0x8112, + gpu_gen: GpuGen::G14, + gpu_variant: GpuVariant::G, + gpu_core: GpuCore::G14G, + + base_clock_hz: 24_000_000, + uat_oas: 40, + num_dies: 1, + max_num_clusters: 1, + max_num_cores: 10, + max_num_frags: 10, + max_num_gps: 4, + + preempt1_size: 0x540, + preempt2_size: 0x280, + preempt3_size: 0x20, + compute_preempt1_size: 0x10000, // TODO: Check + clustering: None, + + render: HwRenderConfig { + // TODO: this is unused here, may be present in newer FW + tiling_control: 0xa041, + }, + + da: HwConfigA { + unk_87c: 900, + unk_8cc: 11000, + unk_e24: 125, + }, + db: HwConfigB { + unk_454: 1, + unk_4e0: 4, + unk_534: 0, + unk_ab8: 0x2048, + unk_abc: 0x4000, + unk_b30: 1, + }, + shared1_tab: &[ + 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, + 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, + ], + shared1_a4: 0, + shared2_tab: &[-1, -1, -1, -1, -1, -1, -1, -1, 0xaa5aa, 0], + shared2_unk_508: 0xc00000, + shared2_curves: Some(HwConfigShared2Curves { + t1_coef: 7200, + t2: &[ + 0xf07, 0x4c0, 0x6c0, 0x8c0, 0xac0, 0xc40, 0xdc0, 0xec0, 0xf80, + ], + t3_coefs: &[0, 20, 28, 36, 44, 50, 56, 60, 63], + t3_scales: &[9, 3209, 10400], + }), + shared3_unk: 5, + shared3_tab: &[ + 10700, 10700, 10700, 10700, 10700, 6000, 1000, 1000, 1000, 10700, 10700, 10700, 10700, + 10700, 10700, 10700, + ], + idle_off_standby_timer_default: 0, + unk_hws2_4: None, + unk_hws2_24: 0, + global_unk_54: 0xffff, + + sram_k: f32!(1.02), + // 13.2: last coef changed from 6.6 to 5.3, assuming that was a fix we can backport + unk_coef_a: &[&f32!([0.0, 0.0, 0.0, 0.0, 5.3, 0.0, 5.3, /*6.6*/ 5.3])], + unk_coef_b: &[&f32!([0.0, 0.0, 0.0, 0.0, 5.3, 0.0, 5.3, /*6.6*/ 5.3])], + global_tab: None, + has_csafr: false, + fast_sensor_mask: [0x6800, 0], + fast_sensor_mask_alt: [0x6800, 0], + fast_die0_sensor_present: 0x02, + io_mappings: &[ + Some(IOMapping::new(0x204d00000, false, 1, 0x14000, 0, true)), // Fender + Some(IOMapping::new(0x20e100000, false, 1, 0x4000, 0, false)), // AICTimer + Some(IOMapping::new(0x23b0c4000, false, 1, 0x4000, 0, true)), // AICSWInt + Some(IOMapping::new(0x204000000, false, 1, 0x20000, 0, true)), // RGX + None, // UVD + None, // unused + None, // DisplayUnderrunWA + Some(IOMapping::new(0x23b2c0000, false, 1, 0x1000, 0, false)), // AnalogTempSensorControllerRegs + None, // PMPDoorbell + Some(IOMapping::new(0x204d80000, false, 1, 0x8000, 0, true)), // MetrologySensorRegs + Some(IOMapping::new(0x204d61000, false, 1, 0x1000, 0, true)), // GMGIFAFRegs + Some(IOMapping::new(0x200000000, false, 1, 0xd6400, 0, true)), // MCache registers + None, // AICBankedRegisters + None, // PMGRScratch + None, // NIA Special agent idle register die 0 + None, // NIA Special agent idle register die 1 + Some(IOMapping::new(0x204e00000, false, 1, 0x10000, 0, true)), // CRE registers + Some(IOMapping::new(0x27d050000, false, 1, 0x4000, 0, true)), // Streaming codec registers + Some(IOMapping::new(0x23b3d0000, false, 1, 0x1000, 0, true)), // + Some(IOMapping::new(0x23b3c0000, false, 1, 0x1000, 0, false)), // + ], + sram_base: None, + sram_size: None, +}; diff --git a/drivers/gpu/drm/asahi/initdata.rs b/drivers/gpu/drm/asahi/initdata.rs new file mode 100644 index 00000000000000..b190a7da6fe85f --- /dev/null +++ b/drivers/gpu/drm/asahi/initdata.rs @@ -0,0 +1,1021 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +#![allow(clippy::unusual_byte_groupings)] + +//! GPU initialization data builder. +//! +//! The root of all interaction between the GPU firmware and the host driver is a complex set of +//! nested structures that we call InitData. This includes both GPU hardware/firmware configuration +//! and the pointers to the ring buffers and global data fields that are used for communication at +//! runtime. +//! +//! Many of these structures are poorly understood, so there are lots of hardcoded unknown values +//! derived from observing the InitData structures that macOS generates. + +use crate::f32; +use crate::fw::initdata::*; +use crate::fw::types::*; +use crate::module_parameters; +use crate::{ + driver::AsahiDevice, + gem, + gpu, + hw, + mmu, // +}; +use kernel::error::{ + Error, + Result, // +}; +use kernel::macros::versions; +use kernel::prelude::*; +use kernel::try_init; + +use ::pin_init; +use ::pin_init::Init; + +/// Builder helper for the global GPU InitData. +#[versions(AGX)] +pub(crate) struct InitDataBuilder<'a> { + dev: &'a AsahiDevice, + alloc: &'a mut gpu::KernelAllocators, + cfg: &'static hw::HwConfig, + dyncfg: &'a hw::DynConfig, +} + +#[versions(AGX)] +impl<'a> InitDataBuilder::ver<'a> { + /// Create a new InitData builder + pub(crate) fn new( + dev: &'a AsahiDevice, + alloc: &'a mut gpu::KernelAllocators, + cfg: &'static hw::HwConfig, + dyncfg: &'a hw::DynConfig, + ) -> InitDataBuilder::ver<'a> { + InitDataBuilder::ver { + dev, + alloc, + cfg, + dyncfg, + } + } + + /// Create the HwDataShared1 structure, which is used in two places in InitData. + fn hw_shared1(cfg: &'static hw::HwConfig) -> impl Init { + init!(raw::HwDataShared1 { + unk_a4: cfg.shared1_a4, + ..Zeroable::init_zeroed() + }) + .chain(|ret| { + for (i, val) in cfg.shared1_tab.iter().enumerate() { + ret.table[i] = *val; + } + Ok(()) + }) + } + + fn init_curve( + curve: &mut raw::HwDataShared2Curve, + unk_0: u32, + unk_4: u32, + t1: &[u16], + t2: &[i16], + t3: &[KVec], + ) { + curve.unk_0 = unk_0; + curve.unk_4 = unk_4; + (*curve.t1)[..t1.len()].copy_from_slice(t1); + (*curve.t1)[t1.len()..].fill(t1[0]); + (*curve.t2)[..t2.len()].copy_from_slice(t2); + (*curve.t2)[t2.len()..].fill(t2[0]); + for (i, a) in curve.t3.iter_mut().enumerate() { + a.fill(0x3ffffff); + if i < t3.len() { + let b = &t3[i]; + (**a)[..b.len()].copy_from_slice(b); + } + } + } + + /// Create the HwDataShared2 structure, which is used in two places in InitData. + fn hw_shared2( + cfg: &'static hw::HwConfig, + dyncfg: &'a hw::DynConfig, + ) -> impl Init + 'a { + try_init!(raw::HwDataShared2 { + unk_28: Array::new([0xff; 16]), + g14: Default::default(), + unk_508: cfg.shared2_unk_508, + ..Zeroable::init_zeroed() + }) + .chain(|ret| { + for (i, val) in cfg.shared2_tab.iter().enumerate() { + ret.table[i] = *val; + } + + let curve_cfg = match cfg.shared2_curves.as_ref() { + None => return Ok(()), + Some(a) => a, + }; + + let mut t1 = KVec::new(); + let mut t3 = KVec::new(); + + for _ in 0..curve_cfg.t3_scales.len() { + t3.push(KVec::new(), GFP_KERNEL)?; + } + + for (i, ps) in dyncfg.pwr.perf_states.iter().enumerate() { + let t3_coef = curve_cfg.t3_coefs[i]; + if t3_coef == 0 { + t1.push(0xffff, GFP_KERNEL)?; + for j in t3.iter_mut() { + j.push(0x3ffffff, GFP_KERNEL)?; + } + continue; + } + + let f_khz = (ps.freq_hz / 1000) as u64; + let v_max = ps.max_volt_mv() as u64; + + t1.push( + (1000000000 * (curve_cfg.t1_coef as u64) / (f_khz * v_max)) + .try_into() + .unwrap(), + GFP_KERNEL, + )?; + + for (j, scale) in curve_cfg.t3_scales.iter().enumerate() { + t3[j].push( + (t3_coef as u64 * 1000000100 * *scale as u64 / (f_khz * v_max * 6)) + .try_into() + .unwrap(), + GFP_KERNEL, + )?; + } + } + + ret.g14.unk_14 = 0x6000000; + Self::init_curve( + &mut ret.g14.curve1, + 0, + 0x20000000, + &[0xffff], + &[0x0f07], + &[], + ); + Self::init_curve(&mut ret.g14.curve2, 7, 0x80000000, &t1, curve_cfg.t2, &t3); + + Ok(()) + }) + } + + /// Create the HwDataShared3 structure, which is used in two places in InitData. + fn hw_shared3(cfg: &'static hw::HwConfig) -> impl Init { + pin_init::init_zeroed::().chain(|ret| { + if !cfg.shared3_tab.is_empty() { + ret.unk_0 = 1; + ret.unk_4 = 500; + ret.unk_8 = cfg.shared3_unk; + ret.table.copy_from_slice(cfg.shared3_tab); + ret.unk_4c = 1; + } + Ok(()) + }) + } + + /// Create an unknown T81xx-specific data structure. + fn t81xx_data( + cfg: &'static hw::HwConfig, + dyncfg: &'a hw::DynConfig, + ) -> impl Init { + let _perf_max_pstate = dyncfg.pwr.perf_max_pstate; + + pin_init::init_zeroed::().chain(move |_ret| { + match cfg.chip_id { + 0x8103 | 0x8112 => { + #[ver(V < V13_3)] + { + _ret.unk_d8c = 0x80000000; + _ret.unk_d90 = 4; + _ret.unk_d9c = f32!(0.6); + _ret.unk_da4 = f32!(0.4); + _ret.unk_dac = f32!(0.38552); + _ret.unk_db8 = f32!(65536.0); + _ret.unk_dbc = f32!(13.56); + _ret.max_pstate_scaled = 100 * _perf_max_pstate; + } + } + _ => (), + } + Ok(()) + }) + } + + /// Create the HwDataA structure. This mostly contains power-related configuration. + fn hwdata_a(&mut self) -> Result> { + let pwr = &self.dyncfg.pwr; + let period_ms = pwr.power_sample_period; + let period_s = F32::from(period_ms) / f32!(1000.0); + let ppm_filter_tc_periods = pwr.ppm_filter_time_constant_ms / period_ms; + #[ver(V >= V13_0B4)] + let ppm_filter_tc_ms_rounded = ppm_filter_tc_periods * period_ms; + let ppm_filter_a = f32!(1.0) / ppm_filter_tc_periods.into(); + let perf_filter_a = f32!(1.0) / pwr.perf_filter_time_constant.into(); + let perf_filter_a2 = f32!(1.0) / pwr.perf_filter_time_constant2.into(); + let avg_power_target_filter_a = f32!(1.0) / pwr.avg_power_target_filter_tc.into(); + let avg_power_filter_tc_periods = pwr.avg_power_filter_tc_ms / period_ms; + #[ver(V >= V13_0B4)] + let avg_power_filter_tc_ms_rounded = avg_power_filter_tc_periods * period_ms; + let avg_power_filter_a = f32!(1.0) / avg_power_filter_tc_periods.into(); + let pwr_filter_a = f32!(1.0) / pwr.pwr_filter_time_constant.into(); + + let base_ps = pwr.perf_base_pstate; + let base_ps_scaled = 100 * base_ps; + let max_ps = pwr.perf_max_pstate; + let max_ps_scaled = 100 * max_ps; + let boost_ps_count = max_ps - base_ps; + + #[allow(unused_variables)] + let base_clock_khz = self.cfg.base_clock_hz / 1000; + let v_clocks_per_period = pwr.pwr_sample_period_aic_clks; + + #[allow(unused_variables)] + let clocks_per_period_coarse = self.cfg.base_clock_hz / 1000 * pwr.power_sample_period; + + self.alloc + .private + .new_init(pin_init::init_zeroed(), |_inner, _ptr| { + let cfg = &self.cfg; + let dyncfg = &self.dyncfg; + try_init!(raw::HwDataA::ver { + clocks_per_period: v_clocks_per_period, + #[ver(V >= V13_0B4)] + clocks_per_period_2: v_clocks_per_period, + pwr_status: AtomicU32::new(4), + unk_10: f32!(1.0), + actual_pstate: 1, + tgt_pstate: 1, + base_pstate_scaled: base_ps_scaled, + unk_40: 1, + max_pstate_scaled: max_ps_scaled, + min_pstate_scaled: 100, + unk_64c: 625, + pwr_filter_a_neg: f32!(1.0) - pwr_filter_a, + pwr_filter_a: pwr_filter_a, + pwr_integral_gain: pwr.pwr_integral_gain, + pwr_integral_min_clamp: pwr.pwr_integral_min_clamp.into(), + max_power_1: pwr.max_power_mw.into(), + pwr_proportional_gain: pwr.pwr_proportional_gain, + pwr_pstate_related_k: -F32::from(max_ps_scaled) / pwr.max_power_mw.into(), + pwr_pstate_max_dc_offset: pwr.pwr_min_duty_cycle as i32 - max_ps_scaled as i32, + max_pstate_scaled_2: max_ps_scaled, + max_power_2: pwr.max_power_mw, + max_pstate_scaled_3: max_ps_scaled, + ppm_filter_tc_periods_x4: ppm_filter_tc_periods * 4, + ppm_filter_a_neg: f32!(1.0) - ppm_filter_a, + ppm_filter_a: ppm_filter_a, + ppm_ki_dt: pwr.ppm_ki * period_s, + unk_6fc: f32!(65536.0), + ppm_kp: pwr.ppm_kp, + pwr_min_duty_cycle: pwr.pwr_min_duty_cycle, + max_pstate_scaled_4: max_ps_scaled, + unk_71c: f32!(0.0), + max_power_3: pwr.max_power_mw, + cur_power_mw_2: 0x0, + ppm_filter_tc_ms: pwr.ppm_filter_time_constant_ms, + #[ver(V >= V13_0B4)] + ppm_filter_tc_clks: ppm_filter_tc_ms_rounded * base_clock_khz, + perf_tgt_utilization: pwr.perf_tgt_utilization, + perf_boost_min_util: pwr.perf_boost_min_util, + perf_boost_ce_step: pwr.perf_boost_ce_step, + perf_reset_iters: pwr.perf_reset_iters, + unk_774: 6, + unk_778: 1, + perf_filter_drop_threshold: pwr.perf_filter_drop_threshold, + perf_filter_a_neg: f32!(1.0) - perf_filter_a, + perf_filter_a2_neg: f32!(1.0) - perf_filter_a2, + perf_filter_a: perf_filter_a, + perf_filter_a2: perf_filter_a2, + perf_ki: pwr.perf_integral_gain, + perf_ki2: pwr.perf_integral_gain2, + perf_integral_min_clamp: pwr.perf_integral_min_clamp.into(), + unk_79c: f32!(95.0), + perf_kp: pwr.perf_proportional_gain, + perf_kp2: pwr.perf_proportional_gain2, + boost_state_unk_k: F32::from(boost_ps_count) / f32!(0.95), + base_pstate_scaled_2: base_ps_scaled, + max_pstate_scaled_5: max_ps_scaled, + base_pstate_scaled_3: base_ps_scaled, + perf_tgt_utilization_2: pwr.perf_tgt_utilization, + base_pstate_scaled_4: base_ps_scaled, + unk_7fc: f32!(65536.0), + pwr_min_duty_cycle_2: pwr.pwr_min_duty_cycle.into(), + max_pstate_scaled_6: max_ps_scaled.into(), + max_freq_mhz: pwr.max_freq_mhz, + pwr_min_duty_cycle_3: pwr.pwr_min_duty_cycle, + min_pstate_scaled_4: f32!(100.0), + max_pstate_scaled_7: max_ps_scaled, + unk_alpha_neg: f32!(0.8), + unk_alpha: f32!(0.2), + fast_die0_sensor_mask: U64(cfg.fast_sensor_mask[0]), + #[ver(G >= G14X)] + fast_die1_sensor_mask: U64(cfg.fast_sensor_mask[1]), + fast_die0_release_temp_cc: 100 * pwr.fast_die0_release_temp, + unk_87c: cfg.da.unk_87c, + unk_880: 0x4, + unk_894: f32!(1.0), + + fast_die0_ki_dt: pwr.fast_die0_integral_gain * period_s, + unk_8a8: f32!(65536.0), + fast_die0_kp: pwr.fast_die0_proportional_gain, + pwr_min_duty_cycle_4: pwr.pwr_min_duty_cycle, + max_pstate_scaled_8: max_ps_scaled, + max_pstate_scaled_9: max_ps_scaled, + fast_die0_prop_tgt_delta: 100 * pwr.fast_die0_prop_tgt_delta, + unk_8cc: cfg.da.unk_8cc, + max_pstate_scaled_10: max_ps_scaled, + max_pstate_scaled_11: max_ps_scaled, + unk_c2c: 1, + power_zone_count: pwr.power_zones.len() as u32, + max_power_4: pwr.max_power_mw, + max_power_5: pwr.max_power_mw, + max_power_6: pwr.max_power_mw, + avg_power_target_filter_a_neg: f32!(1.0) - avg_power_target_filter_a, + avg_power_target_filter_a: avg_power_target_filter_a, + avg_power_target_filter_tc_x4: 4 * pwr.avg_power_target_filter_tc, + avg_power_target_filter_tc_xperiod: period_ms * pwr.avg_power_target_filter_tc, + #[ver(V >= V13_0B4)] + avg_power_target_filter_tc_clks: period_ms + * pwr.avg_power_target_filter_tc + * base_clock_khz, + avg_power_filter_tc_periods_x4: 4 * avg_power_filter_tc_periods, + avg_power_filter_a_neg: f32!(1.0) - avg_power_filter_a, + avg_power_filter_a: avg_power_filter_a, + avg_power_ki_dt: pwr.avg_power_ki_only * period_s, + unk_d20: f32!(65536.0), + avg_power_kp: pwr.avg_power_kp, + avg_power_min_duty_cycle: pwr.avg_power_min_duty_cycle, + max_pstate_scaled_12: max_ps_scaled, + max_pstate_scaled_13: max_ps_scaled, + max_power_7: pwr.max_power_mw.into(), + max_power_8: pwr.max_power_mw, + avg_power_filter_tc_ms: pwr.avg_power_filter_tc_ms, + #[ver(V >= V13_0B4)] + avg_power_filter_tc_clks: avg_power_filter_tc_ms_rounded * base_clock_khz, + max_pstate_scaled_14: max_ps_scaled, + t81xx_data <- Self::t81xx_data(cfg, dyncfg), + #[ver(V >= V13_0B4)] + unk_e10_0 <- { + let filter_a = f32!(1.0) / pwr.se_filter_time_constant.into(); + let filter_1_a = f32!(1.0) / pwr.se_filter_time_constant_1.into(); + try_init!(raw::HwDataA130Extra { + unk_38: 4, + unk_3c: 8000, + gpu_se_inactive_threshold: pwr.se_inactive_threshold, + gpu_se_engagement_criteria: pwr.se_engagement_criteria, + gpu_se_reset_criteria: pwr.se_reset_criteria, + unk_54: 50, + unk_58: 0x1, + gpu_se_filter_a_neg: f32!(1.0) - filter_a, + gpu_se_filter_1_a_neg: f32!(1.0) - filter_1_a, + gpu_se_filter_a: filter_a, + gpu_se_filter_1_a: filter_1_a, + gpu_se_ki_dt: pwr.se_ki * period_s, + gpu_se_ki_1_dt: pwr.se_ki_1 * period_s, + unk_7c: f32!(65536.0), + gpu_se_kp: pwr.se_kp, + gpu_se_kp_1: pwr.se_kp_1, + + #[ver(V >= V13_3)] + unk_8c: 100, + #[ver(V < V13_3)] + unk_8c: 40, + + max_pstate_scaled_1: max_ps_scaled, + unk_9c: f32!(8000.0), + unk_a0: 1400, + gpu_se_filter_time_constant_ms: pwr.se_filter_time_constant * period_ms, + gpu_se_filter_time_constant_1_ms: pwr.se_filter_time_constant_1 + * period_ms, + gpu_se_filter_time_constant_clks: U64((pwr.se_filter_time_constant + * clocks_per_period_coarse) + .into()), + gpu_se_filter_time_constant_1_clks: U64((pwr + .se_filter_time_constant_1 + * clocks_per_period_coarse) + .into()), + unk_c4: f32!(65536.0), + unk_114: f32!(65536.0), + unk_124: 40, + max_pstate_scaled_2: max_ps_scaled, + ..Zeroable::init_zeroed() + }) + }, + fast_die0_sensor_mask_2: U64(cfg.fast_sensor_mask[0]), + #[ver(G >= G14X)] + fast_die1_sensor_mask_2: U64(cfg.fast_sensor_mask[1]), + unk_e24: cfg.da.unk_e24, + unk_e28: 1, + fast_die0_sensor_mask_alt: U64(cfg.fast_sensor_mask_alt[0]), + #[ver(G >= G14X)] + fast_die1_sensor_mask_alt: U64(cfg.fast_sensor_mask_alt[1]), + #[ver(V < V13_0B4)] + fast_die0_sensor_present: U64(cfg.fast_die0_sensor_present as u64), + unk_163c: 1, + unk_3644: 0, + hws1 <- Self::hw_shared1(cfg), + hws2 <- Self::hw_shared2(cfg, dyncfg), + hws3 <- Self::hw_shared3(cfg), + unk_3ce8: 1, + ..Zeroable::init_zeroed() + }) + .chain(|raw| { + for i in 0..self.dyncfg.pwr.perf_states.len() { + raw.sram_k[i] = self.cfg.sram_k; + } + + for (i, coef) in pwr.core_leak_coef.iter().enumerate() { + raw.core_leak_coef[i] = *coef; + } + + for (i, coef) in pwr.sram_leak_coef.iter().enumerate() { + raw.sram_leak_coef[i] = *coef; + } + + #[ver(V >= V13_0B4)] + if let Some(csafr) = pwr.csafr.as_ref() { + for (i, coef) in csafr.leak_coef_afr.iter().enumerate() { + raw.aux_leak_coef.cs_1[i] = *coef; + raw.aux_leak_coef.cs_2[i] = *coef; + } + + for (i, coef) in csafr.leak_coef_cs.iter().enumerate() { + raw.aux_leak_coef.afr_1[i] = *coef; + raw.aux_leak_coef.afr_2[i] = *coef; + } + } + + for i in 0..self.dyncfg.id.num_clusters as usize { + if let Some(coef_a) = self.cfg.unk_coef_a.get(i) { + (*raw.unk_coef_a1[i])[..coef_a.len()].copy_from_slice(coef_a); + (*raw.unk_coef_a2[i])[..coef_a.len()].copy_from_slice(coef_a); + } + if let Some(coef_b) = self.cfg.unk_coef_b.get(i) { + (*raw.unk_coef_b1[i])[..coef_b.len()].copy_from_slice(coef_b); + (*raw.unk_coef_b2[i])[..coef_b.len()].copy_from_slice(coef_b); + } + } + + for (i, pz) in pwr.power_zones.iter().enumerate() { + raw.power_zones[i].target = pz.target; + raw.power_zones[i].target_off = pz.target - pz.target_offset; + raw.power_zones[i].filter_tc_x4 = 4 * pz.filter_tc; + raw.power_zones[i].filter_tc_xperiod = period_ms * pz.filter_tc; + let filter_a = f32!(1.0) / pz.filter_tc.into(); + raw.power_zones[i].filter_a = filter_a; + raw.power_zones[i].filter_a_neg = f32!(1.0) - filter_a; + #[ver(V >= V13_0B4)] + raw.power_zones[i].unk_10 = 1320000000; + } + + #[ver(V >= V13_0B4 && G >= G14X)] + for (i, j) in raw.hws2.g14.curve2.t1.iter().enumerate() { + raw.unk_hws2[i] = if *j == 0xffff { 0 } else { j / 2 }; + } + + if !dyncfg.hw_data_b.is_empty() { + unsafe { + let mut matches: bool = true; + let sla = core::slice::from_raw_parts( + raw as *const raw::HwDataA::ver as *const u8, + core::mem::size_of::(), + ); + if sla.len() != dyncfg.hw_data_a.len() { + matches = false; + dev_err!( + self.dev.as_ref(), + "!!! Hwdata A size mismatch: {} {}", + sla.len(), + dyncfg.hw_data_a.len(), + ); + } + for i in 0..core::cmp::min(sla.len(), dyncfg.hw_data_a.len()) { + if sla[i] != dyncfg.hw_data_a[i] { + matches = false; + dev_err!(self.dev.as_ref(), "!!! Hwdata A first mismatch: {i}"); + break; + } + } + if matches { + dev_info!(self.dev.as_ref(), "!!! Hwdata A match"); + } + } + } + + Ok(()) + }) + }) + } + + /// Create the HwDataB structure. This mostly contains GPU-related configuration. + fn hwdata_b(&mut self) -> Result> { + self.alloc + .private + .new_init(pin_init::init_zeroed(), |_inner, _ptr| { + let cfg = &self.cfg; + let dyncfg = &self.dyncfg; + try_init!(raw::HwDataB::ver { + // Userspace VA map related + #[ver(V < V13_0B4)] + unk_0: U64(0x13_00000000), + unk_8: U64(0x14_00000000), + #[ver(V < V13_0B4)] + unk_10: U64(0x1_00000000), + unk_18: U64(0xffc00000), + // USC start + unk_20: U64(0), // U64(0x11_00000000), + unk_28: U64(0), // U64(0x11_00000000), + // Unknown page + //unk_30: U64(0x6f_ffff8000), + unk_30: U64(mmu::IOVA_UNK_PAGE), + timestamp_area_base: U64(gpu::IOVA_KERN_TIMESTAMP_RANGE.start), + // TODO: yuv matrices + chip_id: cfg.chip_id, + unk_454: cfg.db.unk_454, + unk_458: 0x1, + unk_460: 0x1, + unk_464: 0x1, + unk_468: 0x1, + unk_47c: 0x1, + unk_484: 0x1, + unk_48c: 0x1, + base_clock_khz: cfg.base_clock_hz / 1000, + power_sample_period: dyncfg.pwr.power_sample_period, + unk_49c: 0x1, + unk_4a0: 0x1, + unk_4a4: 0x1, + unk_4c0: 0x1f, + unk_4e0: U64(cfg.db.unk_4e0), + unk_4f0: 0x1, + unk_4f4: 0x1, + unk_504: 0x31, + unk_524: 0x1, // use_secure_cache_flush + unk_534: cfg.db.unk_534, + num_frags: dyncfg.id.num_frags * dyncfg.id.num_clusters, + unk_554: 0x1, + uat_ttb_base: U64(dyncfg.uat_ttb_base), + gpu_core_id: cfg.gpu_core as u32, + gpu_rev_id: dyncfg.id.gpu_rev_id as u32, + num_cores: dyncfg.id.num_cores * dyncfg.id.num_clusters, + max_pstate: dyncfg.pwr.perf_states.len() as u32 - 1, + #[ver(V < V13_0B4)] + num_pstates: dyncfg.pwr.perf_states.len() as u32, + #[ver(V < V13_0B4)] + min_sram_volt: dyncfg.pwr.min_sram_microvolt / 1000, + #[ver(V < V13_0B4)] + unk_ab8: cfg.db.unk_ab8, + #[ver(V < V13_0B4)] + unk_abc: cfg.db.unk_abc, + #[ver(V < V13_0B4)] + unk_ac0: 0x1020, + + #[ver(V >= V13_0B4)] + unk_ae4: Array::new([0x0, 0x3, 0x7, 0x7]), + #[ver(V < V13_0B4)] + unk_ae4: Array::new([0x0, 0xf, 0x3f, 0x3f]), + unk_b10: 0x1, + timer_offset: U64(0), + unk_b24: 0x1, + unk_b28: 0x1, + unk_b2c: 0x1, + unk_b30: cfg.db.unk_b30, + #[ver(V >= V13_0B4)] + unk_b38_0: 1, + #[ver(V >= V13_0B4)] + unk_b38_4: 1, + unk_b38: Array::new([0xffffffff; 12]), + #[ver(V >= V13_0B4 && V < V13_3)] + unk_c3c: 0x19, + #[ver(V >= V13_3)] + unk_c3c: 0x1a, + ..Zeroable::init_zeroed() + }) + .chain(|raw| { + #[ver(V >= V13_3)] + for i in 0..16 { + raw.unk_arr_0[i] = i as u32; + } + + let base_ps = self.dyncfg.pwr.perf_base_pstate as usize; + let max_ps = self.dyncfg.pwr.perf_max_pstate as usize; + let base_freq = self.dyncfg.pwr.perf_states[base_ps].freq_hz; + let max_freq = self.dyncfg.pwr.perf_states[max_ps].freq_hz; + + for (i, ps) in self.dyncfg.pwr.perf_states.iter().enumerate() { + raw.frequencies[i] = ps.freq_hz / 1000000; + for (j, mv) in ps.volt_mv.iter().enumerate() { + let sram_mv = (*mv).max(self.dyncfg.pwr.min_sram_microvolt / 1000); + raw.voltages[i][j] = *mv; + raw.voltages_sram[i][j] = sram_mv; + } + for j in ps.volt_mv.len()..raw.voltages[i].len() { + raw.voltages[i][j] = raw.voltages[i][0]; + raw.voltages_sram[i][j] = raw.voltages_sram[i][0]; + } + raw.sram_k[i] = self.cfg.sram_k; + raw.rel_max_powers[i] = ps.pwr_mw * 100 / self.dyncfg.pwr.max_power_mw; + raw.rel_boost_freqs[i] = if i > base_ps { + (ps.freq_hz - base_freq) / ((max_freq - base_freq) / 100) + } else { + 0 + }; + } + + #[ver(V >= V13_0B4)] + if let Some(csafr) = self.dyncfg.pwr.csafr.as_ref() { + let aux = &mut raw.aux_ps; + aux.cs_max_pstate = (csafr.perf_states_cs.len() - 1).try_into()?; + aux.afr_max_pstate = (csafr.perf_states_afr.len() - 1).try_into()?; + + for (i, ps) in csafr.perf_states_cs.iter().enumerate() { + aux.cs_frequencies[i] = ps.freq_hz / 1000000; + for (j, mv) in ps.volt_mv.iter().enumerate() { + let sram_mv = (*mv).max(csafr.min_sram_microvolt / 1000); + aux.cs_voltages[i][j] = *mv; + aux.cs_voltages_sram[i][j] = sram_mv; + } + } + + for (i, ps) in csafr.perf_states_afr.iter().enumerate() { + aux.afr_frequencies[i] = ps.freq_hz / 1000000; + for (j, mv) in ps.volt_mv.iter().enumerate() { + let sram_mv = (*mv).max(csafr.min_sram_microvolt / 1000); + aux.afr_voltages[i][j] = *mv; + aux.afr_voltages_sram[i][j] = sram_mv; + } + } + } + + // Special case override for T602x + #[ver(G == G14X)] + if dyncfg.id.gpu_rev_id == hw::GpuRevisionID::B1 { + raw.gpu_rev_id = hw::GpuRevisionID::B0 as u32; + } + + if !dyncfg.hw_data_b.is_empty() { + unsafe { + let mut matches: bool = true; + let sla = core::slice::from_raw_parts( + raw as *const raw::HwDataB::ver as *const u8, + core::mem::size_of::(), + ); + if sla.len() != dyncfg.hw_data_b.len() { + matches = false; + dev_err!( + self.dev.as_ref(), + "!!! Hwdata B size mismatch: {} {}", + sla.len(), + dyncfg.hw_data_b.len(), + ); + } + for i in 0..core::cmp::min(sla.len(), dyncfg.hw_data_b.len()) { + if sla[i] != dyncfg.hw_data_b[i] { + matches = false; + dev_err!(self.dev.as_ref(), "!!! Hwdata B first mismatch: {i}"); + break; + } + } + if matches { + dev_info!(self.dev.as_ref(), "!!! Hwdata B match"); + } + } + } + + Ok(()) + }) + }) + } + + /// Create the Globals structure, which contains global firmware config including more power + /// configuration data and globals used to exchange state between the firmware and driver. + fn globals(&mut self) -> Result> { + self.alloc + .private + .new_init(pin_init::init_zeroed(), |_inner, _ptr| { + let cfg = &self.cfg; + let dyncfg = &self.dyncfg; + let pwr = &dyncfg.pwr; + let period_ms = pwr.power_sample_period; + let period_s = F32::from(period_ms) / f32!(1000.0); + let avg_power_filter_tc_periods = pwr.avg_power_filter_tc_ms / period_ms; + + let max_ps = pwr.perf_max_pstate; + let max_ps_scaled = 100 * max_ps; + + try_init!(raw::Globals::ver { + //ktrace_enable: 0xffffffff, + ktrace_enable: 0, + #[ver(V >= V13_2)] + unk_24_0: 3000, + unk_24: 0, + #[ver(V >= V13_0B4)] + debug: 0, + unk_28: 1, + #[ver(G >= G14X)] + unk_2c_0: 1, + #[ver(V >= V13_0B4 && G < G14X)] + unk_2c_0: 0, + unk_2c: 1, + unk_30: 0, + unk_34: 120, + // sub <- try_init!(raw::GlobalsSub::ver { + unk_54: cfg.global_unk_54, + unk_56: 40, + unk_58: 0xffff, + unk_5e: U32(1), + unk_66: U32(1), + // ..Zeroable::init_zeroed() + // }), + unk_8900: 1, + pending_submissions: AtomicU32::new(0), + max_power: pwr.max_power_mw, + max_pstate_scaled: max_ps_scaled, + max_pstate_scaled_2: max_ps_scaled, + max_pstate_scaled_3: max_ps_scaled, + power_zone_count: pwr.power_zones.len() as u32, + avg_power_filter_tc_periods: avg_power_filter_tc_periods, + avg_power_ki_dt: pwr.avg_power_ki_only * period_s, + avg_power_kp: pwr.avg_power_kp, + avg_power_min_duty_cycle: pwr.avg_power_min_duty_cycle, + avg_power_target_filter_tc: pwr.avg_power_target_filter_tc, + unk_89bc: cfg.da.unk_8cc, + fast_die0_release_temp: 100 * pwr.fast_die0_release_temp, + unk_89c4: cfg.da.unk_87c, + fast_die0_prop_tgt_delta: 100 * pwr.fast_die0_prop_tgt_delta, + fast_die0_kp: pwr.fast_die0_proportional_gain, + fast_die0_ki_dt: pwr.fast_die0_integral_gain * period_s, + unk_89e0: 1, + max_power_2: pwr.max_power_mw, + ppm_kp: pwr.ppm_kp, + ppm_ki_dt: pwr.ppm_ki * period_s, + #[ver(V >= V13_0B4)] + unk_89f4_8: 1, + unk_89f4: 0, + hws1 <- Self::hw_shared1(cfg), + hws2 <- Self::hw_shared2(cfg, dyncfg), + hws3 <- Self::hw_shared3(cfg), + #[ver(V >= V13_0B4)] + idle_off_standby_timer: pwr.idle_off_standby_timer, + #[ver(V >= V13_0B4)] + unk_hws2_4: cfg.unk_hws2_4.map(Array::new).unwrap_or_default(), + #[ver(V >= V13_0B4)] + unk_hws2_24: cfg.unk_hws2_24, + unk_900c: 1, + #[ver(V >= V13_0B4)] + unk_9010_0: 1, + #[ver(V >= V13_0B4)] + unk_903c: 1, + #[ver(V < V13_0B4)] + unk_903c: 0, + fault_control: *module_parameters::fault_control.value(), + do_init: 1, + progress_check_interval_3d: 40, + progress_check_interval_ta: 10, + progress_check_interval_cl: 250, + #[ver(V >= V13_0B4)] + unk_1102c_0: 1, + #[ver(V >= V13_0B4)] + unk_1102c_4: 1, + #[ver(V >= V13_0B4)] + unk_1102c_8: 100, + #[ver(V >= V13_0B4)] + unk_1102c_c: 1, + idle_off_delay_ms: AtomicU32::new(pwr.idle_off_delay_ms), + fender_idle_off_delay_ms: pwr.fender_idle_off_delay_ms, + fw_early_wake_timeout_ms: pwr.fw_early_wake_timeout_ms, + cl_context_switch_timeout_ms: 40, + #[ver(V >= V13_0B4)] + cl_kill_timeout_ms: 50, + #[ver(V >= V13_0B4)] + unk_11edc: 0, + #[ver(V >= V13_0B4)] + unk_11efc: 0, + ..Zeroable::init_zeroed() + }) + .chain(|raw| { + for (i, pz) in self.dyncfg.pwr.power_zones.iter().enumerate() { + raw.power_zones[i].target = pz.target; + raw.power_zones[i].target_off = pz.target - pz.target_offset; + raw.power_zones[i].filter_tc = pz.filter_tc; + } + + if let Some(tab) = self.cfg.global_tab.as_ref() { + for (i, x) in tab.iter().enumerate() { + raw.unk_118ec[i] = *x; + } + raw.unk_118e8 = 1; + } + + if !dyncfg.hw_globals.is_empty() { + unsafe { + let mut matches: bool = true; + let sla = core::slice::from_raw_parts( + raw as *const raw::Globals::ver as *const u8, + core::mem::size_of::(), + ); + if sla.len() != dyncfg.hw_globals.len() { + matches = false; + dev_err!( + self.dev.as_ref(), + "!!! Globals size mismatch: {} {}", + sla.len(), + dyncfg.hw_globals.len(), + ); + } + for i in 0..core::cmp::min(sla.len(), dyncfg.hw_globals.len()) { + if sla[i] != dyncfg.hw_globals[i] { + matches = false; + dev_err!(self.dev.as_ref(), "!!! Globals first mismatch: {i}"); + break; + } + } + if matches { + dev_info!(self.dev.as_ref(), "!!! Globals match"); + } + } + } + + Ok(()) + }) + }) + } + + /// Create the RuntimePointers structure, which contains pointers to most of the other + /// structures including the ring buffer channels, statistics structures, and HwDataA/HwDataB. + fn runtime_pointers(&mut self) -> Result> { + let hwa = self.hwdata_a()?; + let hwb = self.hwdata_b()?; + + let mut buffer_mgr_ctl = gem::new_kernel_object(self.dev, 0x4000)?; + buffer_mgr_ctl.vmap()?.memset(0); + + GpuObject::new_init_prealloc( + self.alloc.private.alloc_object()?, + |_ptr| { + let alloc = &mut *self.alloc; + try_init!(RuntimePointers::ver { + stats <- { + let alloc = &mut *alloc; + try_init!(Stats::ver { + vtx: alloc.private.new_default::()?, + frag: alloc.private.new_init( + pin_init::init_zeroed::(), + |_inner, _ptr| { + try_init!(raw::GpuGlobalStatsFrag::ver { + total_cmds: 0, + unk_4: 0, + stats: Default::default(), + }) + } + )?, + comp: alloc.private.new_default::()?, + }) + }, + + hwdata_a: hwa, + unkptr_190: alloc.private.array_empty_tagged(0x80, b"I190")?, + unkptr_198: alloc.private.array_empty_tagged(0xc0, b"I198")?, + hwdata_b: hwb, + + unkptr_1b8: alloc.private.array_empty_tagged(0x1000, b"I1B8")?, + unkptr_1c0: alloc.private.array_empty_tagged(0x300, b"I1C0")?, + unkptr_1c8: alloc.private.array_empty_tagged(0x1000, b"I1C8")?, + + buffer_mgr_ctl, + buffer_mgr_ctl_low_mapping: None, + buffer_mgr_ctl_high_mapping: None, + }) + }, + |inner, _ptr| { + try_init!(raw::RuntimePointers::ver { + pipes: Default::default(), + device_control: Default::default(), + event: Default::default(), + fw_log: Default::default(), + ktrace: Default::default(), + stats: Default::default(), + + stats_vtx: inner.stats.vtx.gpu_pointer(), + stats_frag: inner.stats.frag.gpu_pointer(), + stats_comp: inner.stats.comp.gpu_pointer(), + + hwdata_a: inner.hwdata_a.gpu_pointer(), + unkptr_190: inner.unkptr_190.gpu_pointer(), + unkptr_198: inner.unkptr_198.gpu_pointer(), + hwdata_b: inner.hwdata_b.gpu_pointer(), + hwdata_b_2: inner.hwdata_b.gpu_pointer(), + + fwlog_buf: None, + + unkptr_1b8: inner.unkptr_1b8.gpu_pointer(), + + #[ver(G < G14X)] + unkptr_1c0: inner.unkptr_1c0.gpu_pointer(), + #[ver(G < G14X)] + unkptr_1c8: inner.unkptr_1c8.gpu_pointer(), + + buffer_mgr_ctl_gpu_addr: U64(gpu::IOVA_KERN_GPU_BUFMGR_LOW), + buffer_mgr_ctl_fw_addr: U64(gpu::IOVA_KERN_GPU_BUFMGR_HIGH), + + __pad0: Default::default(), + unk_160: U64(0), + unk_168: U64(0), + unk_1d0: 0, + unk_1d4: 0, + unk_1d8: Default::default(), + + __pad1: Default::default(), + gpu_scratch: raw::RuntimeScratch::ver { + unk_6b38: 0xff, + ..Default::default() + }, + }) + }, + ) + } + + /// Create the FwStatus structure, which is used to coordinate the firmware halt state between + /// the firmware and the driver. + fn fw_status(&mut self) -> Result> { + self.alloc + .shared + .new_object(Default::default(), |_inner| Default::default()) + } + + /// Create one UatLevelInfo structure, which describes one level of translation for the UAT MMU. + fn uat_level_info( + cfg: &'static hw::HwConfig, + index_shift: usize, + num_entries: usize, + ) -> raw::UatLevelInfo { + raw::UatLevelInfo { + index_shift: index_shift as _, + unk_1: 14, + unk_2: 14, + unk_3: 8, + unk_4: 0x4000, + num_entries: num_entries as _, + unk_8: U64(1), + unk_10: U64(((1u64 << cfg.uat_oas) - 1) & !(mmu::UAT_PGMSK as u64)), + index_mask: U64(((num_entries - 1) << index_shift) as u64), + } + } + + /// Build the top-level InitData object. + #[inline(never)] + pub(crate) fn build(&mut self) -> Result>> { + let runtime_pointers = self.runtime_pointers()?; + let globals = self.globals()?; + let fw_status = self.fw_status()?; + let shared_ro = &mut self.alloc.shared_ro; + + let obj = self.alloc.private.new_init( + try_init!(InitData::ver { + unk_buf: shared_ro.array_empty_tagged(0x4000, b"IDTA")?, + runtime_pointers, + globals, + fw_status, + }), + |inner, _ptr| { + let cfg = &self.cfg; + try_init!(raw::InitData::ver { + #[ver(V == V13_5 && G != G14X)] + ver_info: Array::new([0x6ba0, 0x1f28, 0x601, 0xb0]), + #[ver(V == V13_5 && G == G14X)] + ver_info: Array::new([0xb390, 0x70f8, 0x601, 0xb0]), + unk_buf: inner.unk_buf.gpu_pointer(), + unk_8: 0, + unk_c: 0, + runtime_pointers: inner.runtime_pointers.gpu_pointer(), + globals: inner.globals.gpu_pointer(), + fw_status: inner.fw_status.gpu_pointer(), + uat_page_size: 0x4000, + uat_page_bits: 14, + uat_num_levels: 3, + uat_level_info: Array::new([ + Self::uat_level_info(cfg, 36, 8), + Self::uat_level_info(cfg, 25, 2048), + Self::uat_level_info(cfg, 14, 2048), + ]), + __pad0: Default::default(), + host_mapped_fw_allocations: 1, + unk_ac: 0, + unk_b0: 0, + unk_b4: 0, + unk_b8: 0, + }) + }, + )?; + Ok(KBox::new(obj, GFP_KERNEL)?) + } +} diff --git a/drivers/gpu/drm/asahi/mem.rs b/drivers/gpu/drm/asahi/mem.rs new file mode 100644 index 00000000000000..60a64e23a161c5 --- /dev/null +++ b/drivers/gpu/drm/asahi/mem.rs @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! ARM64 low level memory operations. +//! +//! This GPU uses CPU-side `tlbi` outer-shareable instructions to manage its TLBs. +//! Yes, really. Even though the VA address spaces are unrelated. +//! +//! Right now we pick our own ASIDs and don't coordinate with the CPU. This might result +//! in needless TLB shootdowns on the CPU side... TODO: fix this. + +use core::arch::asm; +use core::cmp::min; + +use crate::debug::*; +use crate::mmu; + +type Asid = u8; + +/// Invalidate the entire GPU TLB. +#[inline(always)] +pub(crate) fn tlbi_all() { + // SAFETY: tlbi is always safe by definition + unsafe { + asm!(".arch armv8.4-a", "tlbi vmalle1os",); + } +} + +/// Invalidate all TLB entries for a given ASID. +#[inline(always)] +pub(crate) fn tlbi_asid(asid: Asid) { + if debug_enabled(DebugFlags::ConservativeTlbi) { + tlbi_all(); + sync(); + return; + } + + // SAFETY: tlbi is always safe by definition + unsafe { + asm!( + ".arch armv8.4-a", + "tlbi aside1os, {x}", + x = in(reg) ((asid as u64) << 48) + ); + } +} + +/// Invalidate a single page for a given ASID. +#[inline(always)] +pub(crate) fn tlbi_page(asid: Asid, va: usize) { + if debug_enabled(DebugFlags::ConservativeTlbi) { + tlbi_all(); + sync(); + return; + } + + let val: u64 = ((asid as u64) << 48) | ((va as u64 >> 12) & 0xffffffffffc); + // SAFETY: tlbi is always safe by definition + unsafe { + asm!( + ".arch armv8.4-a", + "tlbi vae1os, {x}", + x = in(reg) val + ); + } +} + +/// Invalidate a range of pages for a given ASID. +#[inline(always)] +pub(crate) fn tlbi_range(asid: Asid, va: usize, len: usize) { + if debug_enabled(DebugFlags::ConservativeTlbi) { + tlbi_all(); + sync(); + return; + } + + if len == 0 { + return; + } + + let start_pg = va >> mmu::UAT_PGBIT; + let end_pg = (va + len + mmu::UAT_PGMSK) >> mmu::UAT_PGBIT; + + let mut val: u64 = ((asid as u64) << 48) | (2 << 46) | (start_pg as u64 & 0x1fffffffff); + let pages = end_pg - start_pg; + + // Guess? It's possible that the page count is in terms of 4K pages + // when the CPU is in 4K mode... + #[cfg(CONFIG_ARM64_4K_PAGES)] + let pages = 4 * pages; + + if pages == 1 { + tlbi_page(asid, va); + return; + } + + // Page count is always in units of 2 + let num = ((pages + 1) >> 1) as u64; + // base: 5 bits + // exp: 2 bits + // pages = (base + 1) << (5 * exp + 1) + // 0:00000 -> 2 pages = 2 << 0 + // 0:11111 -> 32 * 2 pages = 2 << 5 + // 1:00000 -> 1 * 32 * 2 pages = 2 << 5 + // 1:11111 -> 32 * 32 * 2 pages = 2 << 10 + // 2:00000 -> 1 * 32 * 32 * 2 pages = 2 << 10 + // 2:11111 -> 32 * 32 * 32 * 2 pages = 2 << 15 + // 3:00000 -> 1 * 32 * 32 * 32 * 2 pages = 2 << 15 + // 3:11111 -> 32 * 32 * 32 * 32 * 2 pages = 2 << 20 + let exp = min(3, (64 - num.leading_zeros()) / 5); + let bits = 5 * exp; + let mut base = (num + (1 << bits) - 1) >> bits; + + val |= (exp as u64) << 44; + + while base > 32 { + // SAFETY: tlbi is always safe by definition + unsafe { + asm!( + ".arch armv8.4-a", + "tlbi rvae1os, {x}", + x = in(reg) val | (31 << 39) + ); + } + base -= 32; + } + + // SAFETY: tlbi is always safe by definition + unsafe { + asm!( + ".arch armv8.4-a", + "tlbi rvae1os, {x}", + x = in(reg) val | ((base - 1) << 39) + ); + } +} + +/// Issue a memory barrier (`dsb sy`). +#[inline(always)] +pub(crate) fn sync() { + // SAFETY: Barriers are always safe + unsafe { + asm!("dsb sy"); + } +} diff --git a/drivers/gpu/drm/asahi/microseq.rs b/drivers/gpu/drm/asahi/microseq.rs new file mode 100644 index 00000000000000..cbdb5de62e9218 --- /dev/null +++ b/drivers/gpu/drm/asahi/microseq.rs @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU Micro operation sequence builder +//! +//! As part of a single job submisssion to the GPU, the GPU firmware interprets a sequence of +//! commands that we call a "microsequence". These are responsible for setting up the job execution, +//! timestamping the process, waiting for completion, tearing up any resources, and signaling +//! completion to the driver via the event stamp mechanism. +//! +//! Although the microsequences used by the macOS driver are usually quite uniform and simple, the +//! firmware actually implements enough operations to make this interpreter Turing-complete (!). +//! Most of those aren't implemented yet, since we don't need them, but they could come in handy in +//! the future to do strange things or work around firmware bugs... +//! +//! This module simply implements a collection of microsequence operations that can be appended to +//! and later concatenated into one buffer, ready for firmware execution. + +use crate::fw::microseq; +pub(crate) use crate::fw::microseq::*; +use crate::fw::types::*; +use kernel::prelude::*; + +/// MicroSequence object type, which is just an opaque byte array. +pub(crate) type MicroSequence = GpuArray; + +/// MicroSequence builder. +pub(crate) struct Builder { + ops: KVec, +} + +impl Builder { + /// Create a new Builder object + pub(crate) fn new() -> Builder { + Builder { ops: KVec::new() } + } + + /// Get the relative offset from the current pointer to a given target offset. + /// + /// Used for relative jumps. + pub(crate) fn offset_to(&self, target: i32) -> i32 { + target - self.ops.len() as i32 + } + + /// Add an operation to the end of the sequence. + pub(crate) fn add(&mut self, op: T) -> Result { + let off = self.ops.len(); + let p: *const T = &op; + let p: *const u8 = p as *const u8; + // SAFETY: Microseq operations always have no padding bytes, so it is safe to + // access them as a byte slice. + let s: &[u8] = unsafe { core::slice::from_raw_parts(p, core::mem::size_of::()) }; + self.ops.extend_from_slice(s, GFP_KERNEL)?; + Ok(off as i32) + } + + /// Collect all submitted operations into a finalized GPU object. + pub(crate) fn build(self, alloc: &mut Allocator) -> Result { + let mut array = alloc.array_empty::(self.ops.len())?; + + array.as_mut_slice().clone_from_slice(self.ops.as_slice()); + Ok(array) + } +} diff --git a/drivers/gpu/drm/asahi/mmu.rs b/drivers/gpu/drm/asahi/mmu.rs new file mode 100644 index 00000000000000..e8f2bd48f11211 --- /dev/null +++ b/drivers/gpu/drm/asahi/mmu.rs @@ -0,0 +1,1602 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU UAT (MMU) management +//! +//! AGX GPUs use an MMU called the UAT, which is largely compatible with the ARM64 page table +//! format. This module manages the global MMU structures, including a shared handoff structure +//! that is used to coordinate VM management operations with the firmware, the TTBAT which points +//! to currently active GPU VM contexts, as well as the individual `Vm` operations to map and +//! unmap buffer objects into a single user or kernel address space. +//! +//! The actual page table management is in the `pt` module. + +use core::fmt::Debug; +use core::mem::size_of; +use core::num::NonZeroUsize; +use core::ops::Range; +use core::sync::atomic::{ + fence, + AtomicU32, + AtomicU64, + AtomicU8, + Ordering, // +}; + +use kernel::{ + addr::PhysicalAddr, + bindings::drm_gpuvm_flags_DRM_GPUVM_IMMEDIATE_MODE, + c_str, + device, + drm::{ + gem::shmem, + gpuvm, + mm, // + }, + error::Result, + io, + new_mutex, + prelude::*, + static_lock_class, + sync::{ + lock::{ + mutex::MutexBackend, + Guard, // + }, + Arc, Mutex, + }, + time::{ + delay::fsleep, + Delta, + Instant, + Monotonic, // + }, + types::ARef, // +}; + +use crate::debug::*; +use crate::module_parameters; +use crate::no_debug; +use crate::{ + driver, + fw, + gem, + hw, + mem, + pgtable, + slotalloc, + util::RangeExt, // +}; + +// KernelMapping protection types +pub(crate) use crate::pgtable::Prot; +pub(crate) use pgtable::prot::*; +pub(crate) use pgtable::{ + UatPageTable, + UAT_PGBIT, + UAT_PGMSK, + UAT_PGSZ, // +}; + +use pgtable::UAT_IAS; + +use pin_init; + +const DEBUG_CLASS: DebugFlags = DebugFlags::Mmu; + +/// PPL magic number for the handoff region +const PPL_MAGIC: u64 = 0x4b1d000000000002; + +/// Number of supported context entries in the TTBAT +const UAT_NUM_CTX: usize = 64; +/// First context available for users +const UAT_USER_CTX_START: usize = 1; +/// Number of available user contexts +const UAT_USER_CTX: usize = UAT_NUM_CTX - UAT_USER_CTX_START; + +/// Lower/user base VA +pub(crate) const IOVA_USER_BASE: u64 = UAT_PGSZ as u64; +/// Lower/user top VA +pub(crate) const IOVA_USER_TOP: u64 = 1 << (UAT_IAS as u64); +/// Lower/user VA range +pub(crate) const IOVA_USER_RANGE: Range = IOVA_USER_BASE..IOVA_USER_TOP; + +/// Upper/kernel base VA +#[cfg(CONFIG_DEV_COREDUMP)] +const IOVA_TTBR1_BASE: u64 = 0xffffff8000000000; +/// Driver-managed kernel base VA +const IOVA_KERN_BASE: u64 = 0xffffffa000000000; +/// Driver-managed kernel top VA +const IOVA_KERN_TOP: u64 = 0xffffffb000000000; +/// Driver-managed kernel VA range +const IOVA_KERN_RANGE: Range = IOVA_KERN_BASE..IOVA_KERN_TOP; +/// Full kernel VA range +#[cfg(CONFIG_DEV_COREDUMP)] +const IOVA_KERN_FULL_RANGE: Range = IOVA_TTBR1_BASE..(!UAT_PGMSK as u64); + +const TTBR_VALID: u64 = 0x1; // BIT(0) +const TTBR_ASID_SHIFT: usize = 48; + +/// Address of a special dummy page? +//const IOVA_UNK_PAGE: u64 = 0x6f_ffff8000; +pub(crate) const IOVA_UNK_PAGE: u64 = IOVA_USER_TOP - 2 * UAT_PGSZ as u64; +/// User VA range excluding the unk page +pub(crate) const IOVA_USER_USABLE_RANGE: Range = IOVA_USER_BASE..IOVA_UNK_PAGE; + +/// A pre-allocated memory region for UAT management +struct UatRegion { + base: PhysicalAddr, + map: io::mem::Mem, +} + +/// SAFETY: It's safe to share UAT region records across threads. +unsafe impl Send for UatRegion {} +/// SAFETY: It's safe to share UAT region records across threads. +unsafe impl Sync for UatRegion {} + +/// Handoff region flush info structure +#[repr(C)] +struct FlushInfo { + state: AtomicU64, + addr: AtomicU64, + size: AtomicU64, +} + +/// UAT Handoff region layout +#[repr(C)] +struct Handoff { + magic_ap: AtomicU64, + magic_fw: AtomicU64, + + lock_ap: AtomicU8, + lock_fw: AtomicU8, + // Implicit padding: 2 bytes + turn: AtomicU32, + cur_slot: AtomicU32, + // Implicit padding: 4 bytes + flush: [FlushInfo; UAT_NUM_CTX + 1], + + unk2: AtomicU8, + // Implicit padding: 7 bytes + unk3: AtomicU64, +} + +const HANDOFF_SIZE: usize = size_of::(); + +/// One VM slot in the TTBAT +#[repr(C)] +struct SlotTTBS { + ttb0: AtomicU64, + ttb1: AtomicU64, +} + +const SLOTS_SIZE: usize = UAT_NUM_CTX * size_of::(); + +// We need at least page 0 (ttb0) +const PAGETABLES_SIZE: usize = UAT_PGSZ; + +/// Inner data for a Vm instance. This is reference-counted by the outer Vm object. +struct VmInner { + dev: driver::AsahiDevRef, + is_kernel: bool, + va_range: Range, + page_table: UatPageTable, + mm: mm::Allocator<(), KernelMappingInner>, + uat_inner: Arc, + binding: Arc>, + id: u64, +} + +/// Slot binding-related inner data for a Vm instance. +struct VmBinding { + active_users: usize, + binding: Option>, + bind_token: Option, + ttb: u64, +} + +/// Data associated with a VM <=> BO pairing +#[pin_data] +struct VmBo { + #[pin] + sgt: Mutex>>, +} + +impl gpuvm::DriverGpuVmBo for VmBo { + fn new() -> impl PinInit { + pin_init!(VmBo { + sgt <- new_mutex!(None, "VmBinding"), + }) + } +} + +#[derive(Default)] +struct StepContext { + new_va: Option>>>, + prev_va: Option>>>, + next_va: Option>>>, + vm_bo: Option>>, + prot: Prot, +} + +impl gpuvm::DriverGpuVm for VmInner { + type Driver = driver::AsahiDriver; + type GpuVmBo = VmBo; + type StepContext = StepContext; + + fn step_map( + self: &mut gpuvm::UpdatingGpuVm<'_, Self>, + op: &mut gpuvm::OpMap, + ctx: &mut Self::StepContext, + ) -> Result { + let mut iova = op.addr(); + let mut left = op.range() as usize; + let mut offset = op.offset() as usize; + + let bo = ctx.vm_bo.as_ref().expect("step_map with no BO"); + + let one_page = op.flags().contains(gpuvm::GpuVaFlags::REPEAT); + + let guard = bo.inner().sgt.lock(); + for range in guard.as_ref().expect("step_map with no SGT").iter() { + // TODO: proper DMA address/length handling + let mut addr = range.dma_address() as usize; + let mut len: usize = range.dma_len() as usize; + + if left == 0 { + break; + } + + if offset > 0 { + let skip = len.min(offset); + addr += skip; + len -= skip; + offset -= skip; + } + + if len == 0 { + continue; + } + + assert!(offset == 0); + + if one_page { + len = left; + } else { + len = len.min(left); + } + + mod_dev_dbg!( + self.dev, + "MMU: map: {:#x}:{:#x} -> {:#x} [OP={}]\n", + addr, + len, + iova, + one_page + ); + + self.page_table.map_pages( + iova..(iova + len as u64), + addr as PhysicalAddr, + ctx.prot, + one_page, + )?; + + left -= len; + iova += len as u64; + } + + let gpuva = ctx.new_va.take().expect("Multiple step_map calls"); + + if op + .map_and_link_va( + self, + gpuva, + ctx.vm_bo.as_ref().expect("step_map with no BO"), + ) + .is_err() + { + dev_err!( + self.dev.as_ref(), + "map_and_link_va failed: {:#x} [{:#x}] -> {:#x}\n", + op.offset(), + op.range(), + op.addr() + ); + return Err(EINVAL); + } + Ok(()) + } + fn step_unmap( + self: &mut gpuvm::UpdatingGpuVm<'_, Self>, + op: &mut gpuvm::OpUnMap, + _ctx: &mut Self::StepContext, + ) -> Result { + let va = op.va().expect("step_unmap: missing VA"); + + mod_dev_dbg!(self.dev, "MMU: unmap: {:#x}:{:#x}\n", va.addr(), va.range()); + + self.page_table + .unmap_pages(va.addr()..(va.addr() + va.range()))?; + + if let Some(asid) = self.slot() { + fence(Ordering::SeqCst); + mem::tlbi_range(asid as u8, va.addr() as usize, va.range() as usize); + mod_dev_dbg!( + self.dev, + "MMU: flush range: asid={:#x} start={:#x} len={:#x}\n", + asid, + va.addr(), + va.range(), + ); + mem::sync(); + } + + if op.unmap_and_unlink_va_defer().is_none() { + dev_err!(self.dev.as_ref(), "step_unmap: could not unlink gpuva"); + } + Ok(()) + } + fn step_remap( + self: &mut gpuvm::UpdatingGpuVm<'_, Self>, + op: &mut gpuvm::OpReMap, + vm_bo: &gpuvm::GpuVmBo, + ctx: &mut Self::StepContext, + ) -> Result { + let va = op.unmap().va().expect("No previous VA"); + let orig_addr = va.addr(); + let orig_range = va.range(); + + // Only unmap the hole between prev/next, if they exist + let unmap_start = if let Some(op) = op.prev_map() { + op.addr() + op.range() + } else { + orig_addr + }; + + let unmap_end = if let Some(op) = op.next_map() { + op.addr() + } else { + orig_addr + orig_range + }; + + mod_dev_dbg!( + self.dev, + "MMU: unmap for remap: {:#x}..{:#x} (from {:#x}:{:#x})\n", + unmap_start, + unmap_end, + orig_addr, + orig_range + ); + + let unmap_range = unmap_end - unmap_start; + + self.page_table.unmap_pages(unmap_start..unmap_end)?; + + if let Some(asid) = self.slot() { + fence(Ordering::SeqCst); + mem::tlbi_range(asid as u8, unmap_start as usize, unmap_range as usize); + mod_dev_dbg!( + self.dev, + "MMU: flush range: asid={:#x} start={:#x} len={:#x}\n", + asid, + unmap_start, + unmap_range, + ); + mem::sync(); + } + + if op.unmap().unmap_and_unlink_va_defer().is_none() { + dev_err!(self.dev.as_ref(), "step_unmap: could not unlink gpuva"); + } + + if let Some(prev_op) = op.prev_map() { + let prev_gpuva = ctx + .prev_va + .take() + .expect("Multiple step_remap calls with prev_op"); + if prev_op.map_and_link_va(self, prev_gpuva, vm_bo).is_err() { + dev_err!(self.dev.as_ref(), "step_remap: could not relink prev gpuva"); + return Err(EINVAL); + } + } + + if let Some(next_op) = op.next_map() { + let next_gpuva = ctx + .next_va + .take() + .expect("Multiple step_remap calls with next_op"); + if next_op.map_and_link_va(self, next_gpuva, vm_bo).is_err() { + dev_err!(self.dev.as_ref(), "step_remap: could not relink next gpuva"); + return Err(EINVAL); + } + } + + Ok(()) + } +} + +impl VmInner { + /// Returns the slot index, if this VM is bound. + fn slot(&self) -> Option { + if self.is_kernel { + // The GFX ASC does not care about the ASID. Pick an arbitrary one. + // TODO: This needs to be a persistently reserved ASID once we integrate + // with the ARM64 kernel ASID machinery to avoid overlap. + Some(0) + } else { + // We don't check whether we lost the slot, which could cause unnecessary + // invalidations against another Vm. However, this situation should be very + // rare (e.g. a Vm lost its slot, which means 63 other Vms bound in the + // interim, and then it gets killed / drops its mappings without doing any + // final rendering). Anything doing active maps/unmaps is probably also + // rendering and therefore likely bound. + self.binding + .lock() + .bind_token + .as_ref() + .map(|token| token.last_slot() + UAT_USER_CTX_START as u32) + } + } + + /// Returns the translation table base for this Vm + fn ttb(&self) -> u64 { + self.page_table.ttb() + } + + /// Map an `mm::Node` representing an mapping in VA space. + fn map_node(&mut self, node: &mm::Node<(), KernelMappingInner>, prot: Prot) -> Result { + let mut iova = node.start(); + let guard = node.bo.as_ref().ok_or(EINVAL)?.inner().sgt.lock(); + let sgt = guard.as_ref().ok_or(EINVAL)?; + let mut offset = node.offset; + let mut left = node.mapped_size; + + for range in sgt.iter() { + if left == 0 { + break; + } + + // TODO: proper DMA address/length handling + let mut addr = range.dma_address() as usize; + let mut len: usize = range.dma_len() as usize; + + if (offset | addr | len | iova as usize) & UAT_PGMSK != 0 { + dev_err!( + self.dev.as_ref(), + "MMU: KernelMapping {:#x}:{:#x} -> {:#x} is not page-aligned\n", + addr, + len, + iova + ); + return Err(EINVAL); + } + + if offset > 0 { + let skip = len.min(offset); + addr += skip; + len -= skip; + offset -= skip; + } + + len = len.min(left); + + if len == 0 { + continue; + } + + mod_dev_dbg!( + self.dev, + "MMU: map: {:#x}:{:#x} -> {:#x}\n", + addr, + len, + iova + ); + + self.page_table.map_pages( + iova..(iova + len as u64), + addr as PhysicalAddr, + prot, + false, + )?; + + iova += len as u64; + left -= len; + } + Ok(()) + } +} + +/// Shared reference to a virtual memory address space ([`Vm`]). +#[derive(Clone)] +pub(crate) struct Vm { + id: u64, + inner: ARef>, + dummy_obj: ARef, + binding: Arc>, +} +no_debug!(Vm); + +/// Slot data for a [`Vm`] slot (nothing, we only care about the indices). +pub(crate) struct SlotInner(); + +impl slotalloc::SlotItem for SlotInner { + type Data = (); +} + +/// Represents a single user of a binding of a [`Vm`] to a slot. +/// +/// The number of users is counted, and the slot will be freed when it drops to 0. +#[derive(Debug)] +pub(crate) struct VmBind(Vm, u32); + +impl VmBind { + /// Returns the slot that this `Vm` is bound to. + pub(crate) fn slot(&self) -> u32 { + self.1 + } +} + +impl Drop for VmBind { + fn drop(&mut self) { + let mut binding = self.0.binding.lock(); + + assert_ne!(binding.active_users, 0); + binding.active_users -= 1; + mod_pr_debug!( + "MMU: slot {} active users {}\n", + self.1, + binding.active_users + ); + if binding.active_users == 0 { + binding.binding = None; + } + } +} + +impl Clone for VmBind { + fn clone(&self) -> VmBind { + let mut binding = self.0.binding.lock(); + + binding.active_users += 1; + mod_pr_debug!( + "MMU: slot {} active users {}\n", + self.1, + binding.active_users + ); + VmBind(self.0.clone(), self.1) + } +} + +/// Inner data required for an object mapping into a [`Vm`]. +pub(crate) struct KernelMappingInner { + // Drop order matters: + // - Drop the GpuVmBo first, which resv locks its BO and drops a GpuVm reference + // - Drop the GEM BO next, since BO free can take the resv lock itself + // - Drop the owner GpuVm last, since that again can take resv locks when the refcount drops to 0 + bo: Option>>, + _gem: Option>, + owner: ARef>, + uat_inner: Arc, + prot: Prot, + offset: usize, + mapped_size: usize, +} + +/// An object mapping into a [`Vm`], which reserves the address range from use by other mappings. +pub(crate) struct KernelMapping(mm::Node<(), KernelMappingInner>); + +impl KernelMapping { + /// Returns the IOVA base of this mapping + pub(crate) fn iova(&self) -> u64 { + self.0.start() + } + + /// Returns the size of this mapping in bytes + pub(crate) fn size(&self) -> usize { + self.0.mapped_size + } + + /// Returns the IOVA base of this mapping + pub(crate) fn iova_range(&self) -> Range { + self.0.start()..(self.0.start() + self.0.mapped_size as u64) + } + + /// Remap a cached mapping as uncached, then synchronously flush that range of VAs from the + /// coprocessor cache. This is required to safely unmap cached/private mappings. + fn remap_uncached_and_flush(&mut self) { + let mut owner = self + .0 + .owner + .exec_lock(None, false) + .expect("Failed to exec_lock in remap_uncached_and_flush"); + + mod_dev_dbg!( + owner.dev, + "MMU: remap as uncached {:#x}:{:#x}\n", + self.iova(), + self.size() + ); + + // Remap in-place as uncached. + // Do not try to unmap the guard page (-1) + let prot = self.0.prot.as_uncached(); + if owner + .page_table + .reprot_pages(self.iova_range(), prot) + .is_err() + { + dev_err!( + owner.dev.as_ref(), + "MMU: remap {:#x}:{:#x} failed\n", + self.iova(), + self.size() + ); + } + fence(Ordering::SeqCst); + + // If we don't have (and have never had) a VM slot, just return + let slot = match owner.slot() { + None => return, + Some(slot) => slot, + }; + + let flush_slot = if owner.is_kernel { + // If this is a kernel mapping, always flush on index 64 + UAT_NUM_CTX as u32 + } else { + // Otherwise, check if this slot is the active one, otherwise return + // Also check that we actually own this slot + let ttb = owner.ttb() | TTBR_VALID | (slot as u64) << TTBR_ASID_SHIFT; + + let uat_inner = self.0.uat_inner.lock(); + uat_inner.handoff().lock(); + let cur_slot = uat_inner.handoff().current_slot(); + let ttb_cur = uat_inner.ttbs()[slot as usize].ttb0.load(Ordering::Relaxed); + uat_inner.handoff().unlock(); + if cur_slot == Some(slot) && ttb_cur == ttb { + slot + } else { + return; + } + }; + + // FIXME: There is a race here, though it'll probably never happen in practice. + // In theory, it's possible for the ASC to finish using our slot, whatever command + // it was processing to complete, the slot to be lost to another context, and the ASC + // to begin using it again with a different page table, thus faulting when it gets a + // flush request here. In practice, the chance of this happening is probably vanishingly + // small, as all 62 other slots would have to be recycled or in use before that slot can + // be reused, and the ASC using user contexts at all is very rare. + + // Still, the locking around UAT/Handoff/TTBs should probably be redesigned to better + // model the interactions with the firmware and avoid these races. + // Possibly TTB changes should be tied to slot locks: + + // Flush: + // - Can early check handoff here (no need to lock). + // If user slot and it doesn't match the active ASC slot, + // we can elide the flush as the ASC guarantees it flushes + // TLBs/caches when it switches context. We just need a + // barrier to ensure ordering. + // - Lock TTB slot + // - If user ctx: + // - Lock handoff AP-side + // - Lock handoff dekker + // - Check TTB & handoff cur ctx + // - Perform flush if necessary + // - This implies taking the fwring lock + // + // TTB change: + // - lock TTB slot + // - lock handoff AP-side + // - lock handoff dekker + // change TTB + + // Lock this flush slot, and write the range to it + let flush = self.0.uat_inner.lock_flush(flush_slot); + let pages = self.size() >> UAT_PGBIT; + flush.begin_flush(self.iova(), self.size() as u64); + if pages >= 0x10000 { + dev_err!( + owner.dev.as_ref(), + "MMU: Flush too big ({:#x} pages))\n", + pages + ); + } + + let cmd = fw::channels::FwCtlMsg { + addr: fw::types::U64(self.iova()), + unk_8: 0, + slot: flush_slot, + page_count: pages as u16, + unk_12: 2, // ? + }; + + // Tell the firmware to do a cache flush + if let Err(e) = (*owner.dev).gpu.fwctl(cmd) { + dev_err!( + owner.dev.as_ref(), + "MMU: ASC cache flush {:#x}:{:#x} failed (err: {:?})\n", + self.iova(), + self.size(), + e + ); + } + + // Finish the flush + flush.end_flush(); + + // Slot is unlocked here + } +} +no_debug!(KernelMapping); + +impl Drop for KernelMapping { + fn drop(&mut self) { + // This is the main unmap function for UAT mappings. + // The sequence of operations here is finicky, due to the interaction + // between cached GFX ASC mappings and the page tables. These mappings + // always have to be flushed from the cache before being unmapped. + + // For uncached mappings, just unmapping and flushing the TLB is sufficient. + + // For cached mappings, this is the required sequence: + // 1. Remap it as uncached + // 2. Flush the TLB range + // 3. If kernel VA mapping OR user VA mapping and handoff.current_slot() == slot: + // a. Take a lock for this slot + // b. Write the flush range to the right context slot in handoff area + // c. Issue a cache invalidation request via FwCtl queue + // d. Poll for completion via queue + // e. Check for completion flag in the handoff area + // f. Drop the lock + // 4. Unmap + // 5. Flush the TLB range again + + if self.0.prot.is_cached_noncoherent() { + mod_pr_debug!( + "MMU: remap as uncached {:#x}:{:#x}\n", + self.iova(), + self.size() + ); + self.remap_uncached_and_flush(); + } + + let mut owner = self + .0 + .owner + .exec_lock(None, false) + .expect("exec_lock failed in KernelMapping::drop"); + mod_dev_dbg!( + owner.dev, + "MMU: unmap {:#x}:{:#x}\n", + self.iova(), + self.size() + ); + + if owner.page_table.unmap_pages(self.iova_range()).is_err() { + dev_err!( + owner.dev.as_ref(), + "MMU: unmap {:#x}:{:#x} failed\n", + self.iova(), + self.size() + ); + } + + if let Some(asid) = owner.slot() { + fence(Ordering::SeqCst); + mem::tlbi_range(asid as u8, self.iova() as usize, self.size()); + mod_dev_dbg!( + owner.dev, + "MMU: flush range: asid={:#x} start={:#x} len={:#x}\n", + asid, + self.iova(), + self.size() + ); + mem::sync(); + } + } +} + +/// Shared UAT global data structures +struct UatShared { + kernel_ttb1: u64, + map_kernel_to_user: bool, + handoff_rgn: UatRegion, + ttbs_rgn: UatRegion, +} + +impl UatShared { + /// Returns the handoff region area + fn handoff(&self) -> &Handoff { + // SAFETY: pointer is non-null per the type invariant + unsafe { (self.handoff_rgn.map.ptr() as *mut Handoff).as_ref() }.unwrap() + } + + /// Returns the TTBAT area + fn ttbs(&self) -> &[SlotTTBS; UAT_NUM_CTX] { + // SAFETY: pointer is non-null per the type invariant + unsafe { (self.ttbs_rgn.map.ptr() as *mut [SlotTTBS; UAT_NUM_CTX]).as_ref() }.unwrap() + } +} + +// SAFETY: Nothing here is unsafe to send across threads. +unsafe impl Send for UatShared {} + +/// Inner data for the top-level UAT instance. +#[pin_data] +struct UatInner { + #[pin] + shared: Mutex, + #[pin] + handoff_flush: [Mutex; UAT_NUM_CTX + 1], +} + +impl UatInner { + /// Take the lock on the shared data and return the guard. + fn lock(&self) -> Guard<'_, UatShared, MutexBackend> { + self.shared.lock() + } + + /// Take a lock on a handoff flush slot and return the guard. + fn lock_flush(&self, slot: u32) -> Guard<'_, HandoffFlush, MutexBackend> { + self.handoff_flush[slot as usize].lock() + } +} + +/// Top-level UAT manager object +pub(crate) struct Uat { + dev: driver::AsahiDevRef, + cfg: &'static hw::HwConfig, + + inner: Arc, + slots: slotalloc::SlotAllocator, + + kernel_vm: Vm, + kernel_lower_vm: Vm, +} + +impl Handoff { + /// Lock the handoff region from firmware access + fn lock(&self) { + self.lock_ap.store(1, Ordering::Relaxed); + fence(Ordering::SeqCst); + + while self.lock_fw.load(Ordering::Relaxed) != 0 { + if self.turn.load(Ordering::Relaxed) != 0 { + self.lock_ap.store(0, Ordering::Relaxed); + while self.turn.load(Ordering::Relaxed) != 0 {} + self.lock_ap.store(1, Ordering::Relaxed); + fence(Ordering::SeqCst); + } + } + fence(Ordering::Acquire); + } + + /// Unlock the handoff region, allowing firmware access + fn unlock(&self) { + self.turn.store(1, Ordering::Relaxed); + self.lock_ap.store(0, Ordering::Release); + } + + /// Returns the current Vm slot mapped by the firmware for lower/unprivileged access, if any. + fn current_slot(&self) -> Option { + let slot = self.cur_slot.load(Ordering::Relaxed); + if slot == 0 || slot == u32::MAX { + None + } else { + Some(slot) + } + } + + /// Initialize the handoff region + fn init(&self) -> Result { + self.magic_ap.store(PPL_MAGIC, Ordering::Relaxed); + self.cur_slot.store(0, Ordering::Relaxed); + self.unk3.store(0, Ordering::Relaxed); + fence(Ordering::SeqCst); + + let start = Instant::::now(); + const TIMEOUT: Delta = Delta::from_millis(1000); + + self.lock(); + while start.elapsed() < TIMEOUT { + if self.magic_fw.load(Ordering::Relaxed) == PPL_MAGIC { + break; + } else { + self.unlock(); + fsleep(Delta::from_millis(10)); + self.lock(); + } + } + + if self.magic_fw.load(Ordering::Relaxed) != PPL_MAGIC { + self.unlock(); + pr_err!("Handoff: Failed to initialize (firmware not running?)\n"); + return Err(EIO); + } + + self.unlock(); + + for i in 0..=UAT_NUM_CTX { + self.flush[i].state.store(0, Ordering::Relaxed); + self.flush[i].addr.store(0, Ordering::Relaxed); + self.flush[i].size.store(0, Ordering::Relaxed); + } + fence(Ordering::SeqCst); + Ok(()) + } +} + +/// Represents a single flush info slot in the handoff region. +/// +/// # Invariants +/// The pointer is valid and there is no aliasing HandoffFlush instance. +struct HandoffFlush(*const FlushInfo); + +// SAFETY: These pointers are safe to send across threads. +unsafe impl Send for HandoffFlush {} + +impl HandoffFlush { + /// Set up a flush operation for the coprocessor + fn begin_flush(&self, start: u64, size: u64) { + // SAFETY: Per the type invariant, this is safe + let flush = unsafe { self.0.as_ref().unwrap() }; + + let state = flush.state.load(Ordering::Relaxed); + if state != 0 { + pr_err!("Handoff: expected flush state 0, got {}\n", state); + } + flush.addr.store(start, Ordering::Relaxed); + flush.size.store(size, Ordering::Relaxed); + flush.state.store(1, Ordering::Relaxed); + } + + /// Complete a flush operation for the coprocessor + fn end_flush(&self) { + // SAFETY: Per the type invariant, this is safe + let flush = unsafe { self.0.as_ref().unwrap() }; + let state = flush.state.load(Ordering::Relaxed); + if state != 2 { + pr_err!("Handoff: expected flush state 2, got {}\n", state); + } + flush.state.store(0, Ordering::Relaxed); + } +} + +impl Vm { + /// Create a new virtual memory address space + fn new( + dev: &driver::AsahiDevice, + uat_inner: Arc, + kernel_range: Range, + cfg: &'static hw::HwConfig, + ttb: Option, + id: u64, + ) -> Result { + let dummy_obj = gem::new_kernel_object(dev, UAT_PGSZ)?; + let is_kernel = ttb.is_some(); + + let page_table = if let Some(ttb) = ttb { + UatPageTable::new_with_ttb(ttb, IOVA_KERN_RANGE, cfg.uat_oas)? + } else { + UatPageTable::new(cfg.uat_oas)? + }; + + let (va_range, gpuvm_range) = if is_kernel { + (IOVA_KERN_RANGE, kernel_range.clone()) + } else { + (IOVA_USER_RANGE, IOVA_USER_USABLE_RANGE) + }; + + let mm = mm::Allocator::new(va_range.start, va_range.range(), ())?; + + let binding = Arc::pin_init( + new_mutex!( + VmBinding { + binding: None, + bind_token: None, + active_users: 0, + ttb: page_table.ttb(), + }, + "VmBinding", + ), + GFP_KERNEL, + )?; + + let binding_clone = binding.clone(); + Ok(Vm { + id, + dummy_obj: dummy_obj.gem.clone(), + inner: gpuvm::GpuVm::new( + c_str!("Asahi::GpuVm"), + // TODO: should we using DRM_GPUVM_RESV_PROTECTED as well? + drm_gpuvm_flags_DRM_GPUVM_IMMEDIATE_MODE, + dev, + dummy_obj.gem.clone(), + gpuvm_range, + kernel_range, + init!(VmInner { + dev: dev.into(), + va_range, + is_kernel, + page_table, + mm, + uat_inner, + binding: binding_clone, + id, + }), + )?, + binding, + }) + } + + /// Get the translation table base for this Vm + fn ttb(&self) -> u64 { + self.binding.lock().ttb + } + + /// Map a GEM object (using its `SGTable`) into this Vm at a free address in a given range. + #[allow(clippy::too_many_arguments)] + pub(crate) fn map_in_range( + &self, + gem: &gem::Object, + object_range: Range, + alignment: u64, + range: Range, + prot: Prot, + guard: bool, + ) -> Result { + let size = object_range.range(); + let sgt = gem.owned_sg_table()?; + let mut inner = self.inner.exec_lock(Some(gem), false)?; + let vm_bo = self.inner.obtain_bo(gem)?; + + let mut vm_bo_guard = vm_bo.inner().sgt.lock(); + if vm_bo_guard.is_none() { + vm_bo_guard.replace(sgt); + } + core::mem::drop(vm_bo_guard); + + let uat_inner = inner.uat_inner.clone(); + let node = inner.mm.insert_node_in_range( + KernelMappingInner { + owner: self.inner.clone(), + uat_inner, + prot, + bo: Some(vm_bo), + _gem: Some(gem.into()), + offset: object_range.start, + mapped_size: size, + }, + (size + if guard { UAT_PGSZ } else { 0 }) as u64, // Add guard page + alignment, + 0, + range.start, + range.end, + mm::InsertMode::Best, + )?; + + let ret = inner.map_node(&node, prot); + // Drop the exec_lock first, so that if map_node failed the + // KernelMappingInner destructur does not deadlock. + core::mem::drop(inner); + ret?; + Ok(KernelMapping(node)) + } + + /// Map a GEM object into this Vm at a specific address. + #[allow(clippy::too_many_arguments)] + pub(crate) fn map_at( + &self, + addr: u64, + size: usize, + gem: ARef, + prot: Prot, + guard: bool, + ) -> Result { + let sgt = gem.owned_sg_table()?; + let mut inner = self.inner.exec_lock(Some(&gem), false)?; + + let vm_bo = self.inner.obtain_bo(&gem)?; + + let mut vm_bo_guard = vm_bo.inner().sgt.lock(); + if vm_bo_guard.is_none() { + vm_bo_guard.replace(sgt); + } + core::mem::drop(vm_bo_guard); + + let uat_inner = inner.uat_inner.clone(); + let node = inner.mm.reserve_node( + KernelMappingInner { + owner: self.inner.clone(), + uat_inner, + prot, + bo: Some(vm_bo), + _gem: Some(gem.clone()), + offset: 0, + mapped_size: size, + }, + addr, + (size + if guard { UAT_PGSZ } else { 0 }) as u64, // Add guard page + 0, + )?; + + let ret = inner.map_node(&node, prot); + // Drop the exec_lock first, so that if map_node failed the + // KernelMappingInner destructur does not deadlock. + core::mem::drop(inner); + ret?; + Ok(KernelMapping(node)) + } + + /// Map a range of a GEM object into this Vm using GPUVM. + #[allow(clippy::too_many_arguments)] + pub(crate) fn bind_object( + &self, + gem: &gem::Object, + addr: u64, + size: u64, + offset: u64, + prot: Prot, + single_page: bool, + ) -> Result { + // Mapping needs a complete context + let mut ctx = StepContext { + new_va: Some(gpuvm::GpuVa::::new(pin_init::default())?), + prev_va: Some(gpuvm::GpuVa::::new(pin_init::default())?), + next_va: Some(gpuvm::GpuVa::::new(pin_init::default())?), + prot, + ..Default::default() + }; + + let sgt = gem.owned_sg_table()?; + let mut inner = self.inner.exec_lock(Some(gem), true)?; + + // Preallocate the page tables, to fail early if we ENOMEM + inner.page_table.alloc_pages(addr..(addr + size))?; + + let vm_bo = self.inner.obtain_bo(gem)?; + + let mut vm_bo_guard = vm_bo.inner().sgt.lock(); + if vm_bo_guard.is_none() { + vm_bo_guard.replace(sgt); + } + core::mem::drop(vm_bo_guard); + + ctx.vm_bo = Some(vm_bo); + + if (addr | size | offset) & (UAT_PGMSK as u64) != 0 { + dev_err!( + inner.dev.as_ref(), + "MMU: Map step {:#x} [{:#x}] -> {:#x} is not page-aligned\n", + offset, + size, + addr + ); + return Err(EINVAL); + } + + let (flags, gem_range) = if single_page { + (gpuvm::GpuVaFlags::REPEAT, UAT_PGSZ as u32) + } else { + (gpuvm::GpuVaFlags::NONE, 0u32) + }; + + mod_dev_dbg!( + inner.dev, + "MMU: sm_map: {:#x} [{:#x}] -> {:#x}\n", + offset, + size, + addr + ); + inner.sm_map(&mut ctx, addr, size, offset, gem_range, flags) + } + + /// Add a direct MMIO mapping to this Vm at a free address. + pub(crate) fn map_io( + &self, + iova: u64, + phys: usize, + size: usize, + prot: Prot, + ) -> Result { + let mut inner = self.inner.exec_lock(None, false)?; + + if (iova as usize | phys | size) & UAT_PGMSK != 0 { + dev_err!( + inner.dev.as_ref(), + "MMU: KernelMapping {:#x}:{:#x} -> {:#x} is not page-aligned\n", + phys, + size, + iova + ); + return Err(EINVAL); + } + + dev_info!( + inner.dev.as_ref(), + "MMU: IO map: {:#x}:{:#x} -> {:#x}\n", + phys, + size, + iova + ); + + let uat_inner = inner.uat_inner.clone(); + let node = inner.mm.reserve_node( + KernelMappingInner { + owner: self.inner.clone(), + uat_inner, + prot, + bo: None, + _gem: None, + offset: 0, + mapped_size: size, + }, + iova, + size as u64, + 0, + )?; + + let ret = inner.page_table.map_pages( + iova..(iova + size as u64), + phys as PhysicalAddr, + prot, + false, + ); + // Drop the exec_lock first, so that if map_node failed the + // KernelMappingInner destructur does not deadlock. + core::mem::drop(inner); + ret?; + Ok(KernelMapping(node)) + } + + /// Unmap everything in an address range. + pub(crate) fn unmap_range(&self, iova: u64, size: u64) -> Result { + // Unmapping a range can only do a single split, so just preallocate + // the prev and next GpuVas + let mut ctx = StepContext { + prev_va: Some(gpuvm::GpuVa::::new(pin_init::default())?), + next_va: Some(gpuvm::GpuVa::::new(pin_init::default())?), + ..Default::default() + }; + + let mut inner = self.inner.exec_lock(None, false)?; + + mod_dev_dbg!(inner.dev, "MMU: sm_unmap: {:#x}:{:#x}\n", iova, size); + inner.sm_unmap(&mut ctx, iova, size) + } + + /// Drop mappings for a given bo. + pub(crate) fn drop_mappings(&self, gem: &gem::Object) -> Result { + // Removing whole mappings only does unmaps, so no preallocated VAs + let mut ctx = Default::default(); + + let inner = self.inner.exec_lock(Some(gem), false)?; + + if let Some(bo) = self.inner.find_bo(gem) { + mod_dev_dbg!(inner.dev, "MMU: bo_unmap\n"); + self.inner.bo_unmap(&mut ctx, &bo)?; + mod_dev_dbg!(inner.dev, "MMU: bo_unmap done\n"); + // We need to drop the exec_lock first, then the GpuVmBo since that will take the lock itself. + core::mem::drop(inner); + core::mem::drop(bo); + } + + Ok(()) + } + + /// Returns the dummy GEM object used to hold the shared DMA reservation locks + pub(crate) fn get_resv_obj(&self) -> ARef { + self.dummy_obj.clone() + } + + /// Check whether an object is external to this GpuVm + pub(crate) fn is_extobj(&self, gem: &gem::Object) -> bool { + self.inner.is_extobj(gem) + } + + /// Check whether an object is external to this GpuVm + pub(crate) fn bo_deferred_cleanup(&self) { + self.inner.bo_deferred_cleanup() + } +} + +impl Drop for VmInner { + fn drop(&mut self) { + let mut binding = self.binding.lock(); + assert_eq!(binding.active_users, 0); + + mod_pr_debug!( + "VmInner::Drop [{}]: bind_token={:?}\n", + self.id, + binding.bind_token + ); + + // Make sure this VM is not mapped to a TTB if it was + if let Some(token) = binding.bind_token.take() { + let idx = (token.last_slot() as usize) + UAT_USER_CTX_START; + let ttb = self.ttb() | TTBR_VALID | (idx as u64) << TTBR_ASID_SHIFT; + + let uat_inner = self.uat_inner.lock(); + uat_inner.handoff().lock(); + let handoff_cur = uat_inner.handoff().current_slot(); + let ttb_cur = uat_inner.ttbs()[idx].ttb0.load(Ordering::SeqCst); + let inval = ttb_cur == ttb; + if inval { + if handoff_cur == Some(idx as u32) { + pr_err!( + "VmInner::drop owning slot {}, but it is currently in use by the ASC?\n", + idx + ); + } + uat_inner.ttbs()[idx].ttb0.store(0, Ordering::SeqCst); + uat_inner.ttbs()[idx].ttb1.store(0, Ordering::SeqCst); + } + uat_inner.handoff().unlock(); + core::mem::drop(uat_inner); + + // In principle we dropped all the KernelMappings already, but we might as + // well play it safe and invalidate the whole ASID. + if inval { + mod_pr_debug!( + "VmInner::Drop [{}]: need inval for ASID {:#x}\n", + self.id, + idx + ); + mem::tlbi_asid(idx as u8); + mem::sync(); + } + } + } +} + +impl Uat { + /// Map a bootloader-preallocated memory region + fn map_region( + dev: &device::Device, + name: &CStr, + size: usize, + cached: bool, + ) -> Result { + let of_node = dev.of_node().ok_or(EINVAL)?; + let res = of_node.reserved_mem_region_to_resource_byname(name)?; + let base = res.start(); + let res_size = res.size().try_into()?; + + if size > res_size { + dev_err!( + dev, + "Region {} is too small (expected {}, got {})\n", + name, + size, + res_size + ); + return Err(ENOMEM); + } + + let flags = if cached { + io::mem::MemFlags::WB + } else { + io::mem::MemFlags::WC + }; + + // SAFETY: The safety of this operation hinges on the correctness of + // much of this file and also the `pgtable` module, so it is difficult + // to prove in a single safety comment. Such is life with raw GPU + // page table management... + let map = unsafe { io::mem::Mem::try_new(res, flags) }.inspect_err(|_| { + dev_err!(dev, "Failed to remap {} mem resource\n", name); + })?; + + Ok(UatRegion { base, map }) + } + + /// Returns a reference to the global kernel (upper half) `Vm` + pub(crate) fn kernel_vm(&self) -> &Vm { + &self.kernel_vm + } + + /// Returns a reference to the local kernel (lower half) `Vm` + pub(crate) fn kernel_lower_vm(&self) -> &Vm { + &self.kernel_lower_vm + } + + #[cfg(CONFIG_DEV_COREDUMP)] + pub(crate) fn dump_kernel_pages(&self) -> Result> { + let mut inner = self.kernel_vm.inner.exec_lock(None, false)?; + inner.page_table.dump_pages(IOVA_KERN_FULL_RANGE) + } + + /// Returns the base physical address of the TTBAT region. + pub(crate) fn ttb_base(&self) -> u64 { + let inner = self.inner.lock(); + + inner.ttbs_rgn.base + } + + /// Binds a `Vm` to a slot, preferring the last used one. + pub(crate) fn bind(&self, vm: &Vm) -> Result { + let mut binding = vm.binding.lock(); + + if binding.binding.is_none() { + assert_eq!(binding.active_users, 0); + + let isolation = *module_parameters::robust_isolation.value() != 0; + + self.slots.set_limit(if isolation { + NonZeroUsize::new(1) + } else { + None + }); + + let slot = self.slots.get(binding.bind_token)?; + if slot.changed() { + mod_pr_debug!("Vm Bind [{}]: bind_token={:?}\n", vm.id, slot.token(),); + let idx = (slot.slot() as usize) + UAT_USER_CTX_START; + let ttb = binding.ttb | TTBR_VALID | (idx as u64) << TTBR_ASID_SHIFT; + + let uat_inner = self.inner.lock(); + + let ttb1 = if uat_inner.map_kernel_to_user { + uat_inner.kernel_ttb1 | TTBR_VALID | (idx as u64) << TTBR_ASID_SHIFT + } else { + 0 + }; + + let ttbs = uat_inner.ttbs(); + uat_inner.handoff().lock(); + if uat_inner.handoff().current_slot() == Some(idx as u32) { + pr_err!( + "Vm::bind to slot {}, but it is currently in use by the ASC?\n", + idx + ); + } + ttbs[idx].ttb0.store(ttb, Ordering::Release); + ttbs[idx].ttb1.store(ttb1, Ordering::Release); + uat_inner.handoff().unlock(); + core::mem::drop(uat_inner); + + // Make sure all TLB entries from the previous owner of this ASID are gone + mem::tlbi_asid(idx as u8); + mem::sync(); + } + + binding.bind_token = Some(slot.token()); + binding.binding = Some(slot); + } + + binding.active_users += 1; + + let slot = binding.binding.as_ref().unwrap().slot() + UAT_USER_CTX_START as u32; + mod_pr_debug!("MMU: slot {} active users {}\n", slot, binding.active_users); + Ok(VmBind(vm.clone(), slot)) + } + + /// Creates a new `Vm` linked to this UAT. + pub(crate) fn new_vm(&self, id: u64, kernel_range: Range) -> Result { + Vm::new( + &self.dev, + self.inner.clone(), + kernel_range, + self.cfg, + None, + id, + ) + } + + /// Creates the reference-counted inner data for a new `Uat` instance. + #[inline(never)] + fn make_inner(dev: &driver::AsahiDevice) -> Result> { + let handoff_rgn = Self::map_region(dev.as_ref(), c_str!("handoff"), HANDOFF_SIZE, true)?; + let ttbs_rgn = Self::map_region(dev.as_ref(), c_str!("ttbs"), SLOTS_SIZE, true)?; + + // SAFETY: The Handoff struct layout matches the firmware's view of memory at this address, + // and the region is at least large enough per the size specified above. + let handoff = unsafe { &(handoff_rgn.map.ptr() as *mut Handoff).as_ref().unwrap() }; + + dev_info!(dev.as_ref(), "MMU: Initializing kernel page table\n"); + + Arc::pin_init( + try_pin_init!(UatInner { + handoff_flush <- pin_init::pin_init_array_from_fn(|i| { + new_mutex!(HandoffFlush(&handoff.flush[i]), "handoff_flush") + }), + shared <- new_mutex!( + UatShared { + kernel_ttb1: 0, + map_kernel_to_user: false, + handoff_rgn, + ttbs_rgn, + }, + "uat_shared" + ), + }), + GFP_KERNEL, + ) + } + + /// Creates a new `Uat` instance given the relevant hardware config. + #[inline(never)] + pub(crate) fn new( + dev: &driver::AsahiDevice, + cfg: &'static hw::HwConfig, + map_kernel_to_user: bool, + ) -> Result { + dev_info!(dev.as_ref(), "MMU: Initializing...\n"); + + let inner = Self::make_inner(dev)?; + + let of_node = dev.as_ref().of_node().ok_or(EINVAL)?; + let res = of_node.reserved_mem_region_to_resource_byname(c_str!("pagetables"))?; + let ttb1 = res.start(); + let ttb1size: usize = res.size().try_into()?; + + if ttb1size < PAGETABLES_SIZE { + dev_err!(dev.as_ref(), "MMU: Pagetables region is too small\n"); + return Err(ENOMEM); + } + + dev_info!(dev.as_ref(), "MMU: Creating kernel page tables\n"); + let kernel_lower_vm = Vm::new(dev, inner.clone(), IOVA_USER_RANGE, cfg, None, 1)?; + let kernel_vm = Vm::new(dev, inner.clone(), IOVA_KERN_RANGE, cfg, Some(ttb1), 0)?; + + dev_info!(dev.as_ref(), "MMU: Kernel page tables created\n"); + + let ttb0 = kernel_lower_vm.ttb(); + + let uat = Self { + dev: dev.into(), + cfg, + kernel_vm, + kernel_lower_vm, + inner, + slots: slotalloc::SlotAllocator::new( + UAT_USER_CTX as u32, + (), + |_inner, _slot| Some(SlotInner()), + c_str!("Uat::SlotAllocator"), + static_lock_class!(), + static_lock_class!(), + )?, + }; + + let mut inner = uat.inner.lock(); + + inner.map_kernel_to_user = map_kernel_to_user; + inner.kernel_ttb1 = ttb1; + + inner.handoff().init()?; + + dev_info!(dev.as_ref(), "MMU: Initializing TTBs\n"); + + inner.handoff().lock(); + + let ttbs = inner.ttbs(); + + ttbs[0].ttb0.store(ttb0 | TTBR_VALID, Ordering::SeqCst); + ttbs[0].ttb1.store(ttb1 | TTBR_VALID, Ordering::SeqCst); + + for ctx in &ttbs[1..] { + ctx.ttb0.store(0, Ordering::Relaxed); + ctx.ttb1.store(0, Ordering::Relaxed); + } + + inner.handoff().unlock(); + + core::mem::drop(inner); + + dev_info!(dev.as_ref(), "MMU: initialized\n"); + + Ok(uat) + } +} + +impl Drop for Uat { + fn drop(&mut self) { + // Make sure we flush the TLBs + fence(Ordering::SeqCst); + mem::tlbi_all(); + mem::sync(); + } +} diff --git a/drivers/gpu/drm/asahi/object.rs b/drivers/gpu/drm/asahi/object.rs new file mode 100644 index 00000000000000..38a2268137effb --- /dev/null +++ b/drivers/gpu/drm/asahi/object.rs @@ -0,0 +1,733 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Asahi GPU object model +//! +//! The AGX GPU includes a coprocessor that uses a large number of shared memory structures to +//! communicate with the driver. These structures contain GPU VA pointers to each other, which are +//! directly dereferenced by the firmware and are expected to always be valid for the usage +//! lifetime of the containing struct (which is an implicit contract, not explicitly managed). +//! Any faults cause an unrecoverable firmware crash, requiring a full system reboot. +//! +//! In order to manage this complexity safely, we implement a GPU object model using Rust's type +//! system to enforce GPU object lifetime relationships. GPU objects represent an allocated piece +//! of memory of a given type, mapped to the GPU (and usually also the CPU). On the CPU side, +//! these objects are associated with a pure Rust structure that contains the objects it depends +//! on (or references to them). This allows us to map Rust lifetimes into the GPU object model +//! system. Then, GPU VA pointers also inherit those lifetimes, which means the Rust borrow checker +//! can ensure that all pointers are assigned an address that is guaranteed to outlive the GPU +//! object it points to. +//! +//! Since the firmware object model does have self-referencing pointers (and there is of course no +//! underlying revocability mechanism to make it safe), we must have an escape hatch. GPU pointers +//! can be weak pointers, which do not enforce lifetimes. In those cases, it is the user's +//! responsibility to ensure that lifetime requirements are met. +//! +//! In other words, the model is necessarily leaky and there is no way to fully map Rust safety to +//! GPU firmware object safety. The goal of the model is to make it easy to model the lifetimes of +//! GPU objects and have the compiler help in avoiding mistakes, rather than to guarantee safety +//! 100% of the time as would be the case for CPU-side Rust code. + +// TODO: There is a fundamental soundness issue with sharing memory with the GPU (that even affects +// C code too). Since the GPU is free to mutate that memory at any time, normal reference invariants +// cannot be enforced on the CPU side. For example, the compiler could perform an optimization that +// assumes that a given memory location does not change between two reads, and causes UB otherwise, +// and then the GPU could mutate that memory out from under the CPU. +// +// For cases where we *expect* this to happen, we use atomic types, which avoid this issue. However, +// doing so for every single field of every type is a non-starter. Right now, there seems to be no +// good solution for this that does not come with significant performance or ergonomics downsides. +// +// In *practice* we are almost always only writing GPU memory, and only reading from atomics, so the +// chances of this actually triggering UB (e.g. a security issue that can be triggered from the GPU +// side) due to a compiler optimization are very slim. +// +// Further discussion: https://github.com/rust-lang/unsafe-code-guidelines/issues/152 + +use kernel::{ + error::code::*, + prelude::*, + sync::Arc, // +}; + +use core::fmt; +use core::fmt::Debug; +use core::fmt::Formatter; +use core::marker::PhantomData; +use core::mem::MaybeUninit; +use core::num::NonZeroU64; +use core::ops::{ + Deref, + DerefMut, + Index, + IndexMut, // +}; +use core::{mem, ptr, slice}; + +use crate::alloc::Allocation; +use crate::debug::*; +use crate::fw::types::Zeroable; +use crate::mmu; + +const DEBUG_CLASS: DebugFlags = DebugFlags::Object; + +/// A GPU-side strong pointer, which is a 64-bit non-zero VA with an associated lifetime. +/// +/// In rare cases these pointers are not aligned, so this is `packed(1)`. +#[repr(C, packed(1))] +pub(crate) struct GpuPointer<'a, T: ?Sized>(NonZeroU64, PhantomData<&'a T>); + +impl<'a, T: ?Sized> GpuPointer<'a, T> { + /// Logical OR the pointer with an arbitrary `u64`. This is used when GPU struct fields contain + /// misc flag fields in the upper bits. The lifetime is retained. This is GPU-unsafe in + /// principle, but we assert that only non-implemented address bits are touched, which is safe + /// for pointers used by the GPU (not by firmware). + pub(crate) fn or(&self, other: u64) -> GpuPointer<'a, T> { + // This will fail for kernel-half pointers, which should not be ORed. + assert_eq!(self.0.get() & other, 0); + // Assert that we only touch the high bits. + assert_eq!(other & 0xffffffffff, 0); + GpuPointer(self.0 | other, PhantomData) + } + + /// Add an arbitrary offset to the pointer. This is not safe (from the GPU perspective), and + /// should only be used via the `inner_ptr` macro to get pointers to inner fields, hence we mark + /// it `unsafe` to discourage direct use. + /// + /// # Safety + /// Do not use directly, only via `inner_ptr`. + // NOTE: The third argument is a type inference hack. + pub(crate) unsafe fn offset(&self, off: usize, _: *const U) -> GpuPointer<'a, U> { + GpuPointer::<'a, U>( + NonZeroU64::new(self.0.get() + (off as u64)).unwrap(), + PhantomData, + ) + } +} + +impl<'a, T> GpuPointer<'a, T> { + /// Create a GPU pointer from a KernelMapping and an offset. + /// TODO: Change all GPU pointers to point to the raw types so size_of here is GPU-sound. + pub(crate) fn from_mapping( + mapping: &'a Arc, + offset: usize, + ) -> Result> { + let addr = mapping.iova().checked_add(offset as u64).ok_or(EINVAL)?; + let end = offset + .checked_add(core::mem::size_of::()) + .ok_or(EINVAL)?; + if end > mapping.size() { + Err(ERANGE) + } else { + Ok(Self(addr.try_into().unwrap(), PhantomData)) + } + } +} + +impl<'a, T: ?Sized> Debug for GpuPointer<'a, T> { + fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result { + let val = self.0; + f.write_fmt(format_args!("{:#x} ({})", val, core::any::type_name::())) + } +} + +impl<'a, T: ?Sized> From> for u64 { + fn from(value: GpuPointer<'a, T>) -> Self { + value.0.get() + } +} + +/// Take a pointer to a sub-field within a structure pointed to by a GpuPointer, keeping the +/// lifetime. +#[macro_export] +macro_rules! inner_ptr { + ($gpuva:expr, $($f:tt)*) => ({ + // This mirrors kernel::offset_of(), except we use type inference to avoid having to know + // the type of the pointer explicitly. + fn uninit_from(_: GpuPointer<'_, T>) -> core::mem::MaybeUninit> { + core::mem::MaybeUninit::uninit() + } + let tmp = uninit_from($gpuva); + let outer = tmp.as_ptr(); + // SAFETY: The pointer is valid and aligned, just not initialised; `addr_of` ensures that + // we don't actually read from `outer` (which would be UB) nor create an intermediate + // reference. + let p: *const _ = unsafe { core::ptr::addr_of!((*outer).$($f)*) }; + let inner = p as *const u8; + // SAFETY: The two pointers are within the same allocation block. + let off = unsafe { inner.offset_from(outer as *const u8) }; + // SAFETY: The resulting pointer is guaranteed to point to valid memory within the outer + // object. + unsafe { $gpuva.offset(off.try_into().unwrap(), p) } + }) +} + +/// A GPU-side weak pointer, which is a 64-bit non-zero VA with no lifetime. +/// +/// In rare cases these pointers are not aligned, so this is `packed(1)`. +#[repr(C, packed(1))] +pub(crate) struct GpuWeakPointer(NonZeroU64, PhantomData<*const T>); + +/// SAFETY: GPU weak pointers are always safe to share between threads. +unsafe impl Send for GpuWeakPointer {} +/// SAFETY: GPU weak pointers are always safe to share between threads. +unsafe impl Sync for GpuWeakPointer {} + +// Weak pointers can be copied/cloned regardless of their target type. +impl Copy for GpuWeakPointer {} + +impl Clone for GpuWeakPointer { + fn clone(&self) -> Self { + *self + } +} + +impl GpuWeakPointer { + /// Add an arbitrary offset to the pointer. This is not safe (from the GPU perspective), and + /// should only be used via the `inner_weak_ptr` macro to get pointers to inner fields, hence we + /// mark it `unsafe` to discourage direct use. + /// + /// # Safety + /// Do not use directly, only via `inner_weak_ptr`. + // NOTE: The third argument is a type inference hack. + pub(crate) unsafe fn offset(&self, off: usize, _: *const U) -> GpuWeakPointer { + GpuWeakPointer::( + NonZeroU64::new(self.0.get() + (off as u64)).unwrap(), + PhantomData, + ) + } + + /// Upgrade a weak pointer into a strong pointer. This is not considered safe from the GPU + /// perspective. + /// + /// # Safety + /// The caller must ensure tht the data pointed to lives in the GPU at least as long as the + /// returned lifetime. + pub(crate) unsafe fn upgrade<'a>(&self) -> GpuPointer<'a, T> { + GpuPointer(self.0, PhantomData) + } +} + +impl From> for u64 { + fn from(value: GpuWeakPointer) -> Self { + value.0.get() + } +} + +impl Debug for GpuWeakPointer { + fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result { + let val = self.0; + f.write_fmt(format_args!("{:#x} ({})", val, core::any::type_name::())) + } +} + +/// Take a pointer to a sub-field within a structure pointed to by a GpuWeakPointer. +#[macro_export] +macro_rules! inner_weak_ptr { + ($gpuva:expr, $($f:tt)*) => ({ + // See inner_ptr() + fn uninit_from(_: GpuWeakPointer) -> core::mem::MaybeUninit> { + core::mem::MaybeUninit::uninit() + } + let tmp = uninit_from($gpuva); + let outer = tmp.as_ptr(); + // SAFETY: The pointer is valid and aligned, just not initialised; `addr_of` ensures that + // we don't actually read from `outer` (which would be UB) nor create an intermediate + // reference. + let p: *const _ = unsafe { core::ptr::addr_of!((*outer).$($f)*) }; + let inner = p as *const u8; + // SAFETY: The two pointers are within the same allocation block. + let off = unsafe { inner.offset_from(outer as *const u8) }; + // SAFETY: The resulting pointer is guaranteed to point to valid memory within the outer + // object. + unsafe { $gpuva.offset(off.try_into().unwrap(), p) } + }) +} + +/// Types that implement this trait represent a GPU structure from the CPU side. +/// +/// The `Raw` type represents the actual raw structure definition on the GPU side. +/// +/// Types implementing [`GpuStruct`] must have fields owning any objects (or strong references +/// to them) that GPU pointers in the `Raw` structure point to. This mechanism is used to enforce +/// lifetimes. +pub(crate) trait GpuStruct: 'static { + /// The type of the GPU-side structure definition representing the firmware struct layout. + type Raw<'a>; +} + +/// An instance of a GPU object in memory. +/// +/// # Invariants +/// `raw` must point to a valid mapping of the `T::Raw` type associated with the `alloc` allocation. +/// `gpu_ptr` must be the GPU address of the same object. +pub(crate) struct GpuObject> { + raw: *mut T::Raw<'static>, + alloc: U, + gpu_ptr: GpuWeakPointer, + inner: KBox, +} + +impl> GpuObject { + /// Create a new GpuObject given an allocator and the inner data (a type implementing + /// GpuStruct). + /// + /// The caller passes a closure that constructs the `T::Raw` type given a reference to the + /// `GpuStruct`. This is the mechanism used to enforce lifetimes. + pub(crate) fn new( + alloc: U, + inner: T, + callback: impl for<'a> FnOnce(&'a T) -> T::Raw<'a>, + ) -> Result { + let size = mem::size_of::>(); + if size > 0x1000 { + dev_crit!( + alloc.device().as_ref(), + "Allocating {} of size {:#x}, with new, please use new_boxed!\n", + core::any::type_name::(), + size + ); + } + if alloc.size() < size { + return Err(ENOMEM); + } + let gpu_ptr = + GpuWeakPointer::(NonZeroU64::new(alloc.gpu_ptr()).ok_or(EINVAL)?, PhantomData); + mod_dev_dbg!( + alloc.device(), + "Allocating {} @ {:#x}\n", + core::any::type_name::(), + alloc.gpu_ptr() + ); + let p = alloc.ptr().ok_or(EINVAL)?.as_ptr() as *mut T::Raw<'static>; + let mut raw = callback(&inner); + // SAFETY: `p` is guaranteed to be valid per the Allocation invariant, and the type is + // identical to the type of `raw` other than the lifetime. + unsafe { p.copy_from(&mut raw as *mut _ as *mut u8 as *mut _, 1) }; + mem::forget(raw); + Ok(Self { + raw: p, + gpu_ptr, + alloc, + inner: KBox::new(inner, GFP_KERNEL)?, + }) + } + + /// Create a new GpuObject given an allocator and the boxed inner data (a type implementing + /// GpuStruct). + /// + /// The caller passes a closure that initializes the `T::Raw` type given a reference to the + /// `GpuStruct` and a `MaybeUninit`. This is intended to be used with the place!() + /// macro to avoid constructing the whole `T::Raw` object on the stack. + pub(crate) fn new_boxed( + alloc: U, + inner: KBox, + callback: impl for<'a> FnOnce( + &'a T, + &'a mut MaybeUninit>, + ) -> Result<&'a mut T::Raw<'a>>, + ) -> Result { + if alloc.size() < mem::size_of::>() { + return Err(ENOMEM); + } + let gpu_ptr = + GpuWeakPointer::(NonZeroU64::new(alloc.gpu_ptr()).ok_or(EINVAL)?, PhantomData); + mod_dev_dbg!( + alloc.device(), + "Allocating {} @ {:#x}\n", + core::any::type_name::(), + alloc.gpu_ptr() + ); + let p = alloc.ptr().ok_or(EINVAL)?.as_ptr() as *mut MaybeUninit>; + // SAFETY: `p` is guaranteed to be valid per the Allocation invariant. + let raw = callback(&inner, unsafe { &mut *p })?; + if p as *mut T::Raw<'_> != raw as *mut _ { + dev_err!( + alloc.device().as_ref(), + "Allocation callback returned a mismatched reference ({})\n", + core::any::type_name::(), + ); + return Err(EINVAL); + } + Ok(Self { + raw: p as *mut u8 as *mut T::Raw<'static>, + gpu_ptr, + alloc, + inner, + }) + } + + /// Create a new GpuObject given an allocator and the inner data (a type implementing + /// GpuStruct). + /// + /// The caller passes a closure that initializes the `T::Raw` type given a reference to the + /// `GpuStruct` and a `MaybeUninit`. This is intended to be used with the place!() + /// macro to avoid constructing the whole `T::Raw` object on the stack. + pub(crate) fn new_inplace( + alloc: U, + inner: T, + callback: impl for<'a> FnOnce( + &'a T, + &'a mut MaybeUninit>, + ) -> Result<&'a mut T::Raw<'a>>, + ) -> Result { + GpuObject::::new_boxed(alloc, KBox::new(inner, GFP_KERNEL)?, callback) + } + + /// Create a new GpuObject given an allocator and the boxed inner data (a type implementing + /// GpuStruct). + /// + /// The caller passes a closure that initializes the `T::Raw` type given a reference to the + /// `GpuStruct` and a `MaybeUninit`. This is intended to be used with the place!() + /// macro to avoid constructing the whole `T::Raw` object on the stack. + pub(crate) fn new_init_prealloc<'a, I: Init, R: PinInit, F>, E, F>( + alloc: U, + inner_init: impl FnOnce(GpuWeakPointer) -> I, + raw_init: impl FnOnce(&'a T, GpuWeakPointer) -> R, + ) -> Result + where + kernel::error::Error: core::convert::From, + kernel::error::Error: core::convert::From, + { + if alloc.size() < mem::size_of::>() { + return Err(ENOMEM); + } + let gpu_ptr = + GpuWeakPointer::(NonZeroU64::new(alloc.gpu_ptr()).ok_or(EINVAL)?, PhantomData); + mod_dev_dbg!( + alloc.device(), + "Allocating {} @ {:#x}\n", + core::any::type_name::(), + alloc.gpu_ptr() + ); + let inner = inner_init(gpu_ptr); + let p = alloc.ptr().ok_or(EINVAL)?.as_ptr() as *mut T::Raw<'_>; + let ret = Self { + raw: p as *mut u8 as *mut T::Raw<'static>, + gpu_ptr, + alloc, + inner: KBox::init(inner, GFP_KERNEL)?, + }; + let q = &*ret.inner as *const T; + // SAFETY: `p` is guaranteed to be valid per the Allocation invariant. + unsafe { raw_init(&*q, gpu_ptr).__pinned_init(p) }?; + Ok(ret) + } + + /// Returns the GPU VA of this object (as a raw [`NonZeroU64`]) + pub(crate) fn gpu_va(&self) -> NonZeroU64 { + self.gpu_ptr.0 + } + + /// Returns a strong GPU pointer to this object, with a lifetime. + pub(crate) fn gpu_pointer(&self) -> GpuPointer<'_, T> { + GpuPointer(self.gpu_ptr.0, PhantomData) + } + + /// Returns a weak GPU pointer to this object, with no lifetime. + pub(crate) fn weak_pointer(&self) -> GpuWeakPointer { + GpuWeakPointer(self.gpu_ptr.0, PhantomData) + } + + /// Perform a mutation to the inner `Raw` data given a user-supplied callback. + /// + /// The callback gets a mutable reference to the `GpuStruct` type. + pub(crate) fn with_mut( + &mut self, + callback: impl for<'a> FnOnce(&'a mut ::Raw<'a>, &'a mut T) -> RetVal, + ) -> RetVal { + // SAFETY: `self.raw` is valid per the type invariant, and the second half is just + // converting lifetimes. + unsafe { callback(&mut *self.raw, &mut *(&mut *self.inner as *mut _)) } + } + + /// Access the inner `Raw` data given a user-supplied callback. + /// + /// The callback gets a reference to the `GpuStruct` type. + pub(crate) fn with( + &self, + callback: impl for<'a> FnOnce(&'a ::Raw<'a>, &'a T) -> RetVal, + ) -> RetVal { + // SAFETY: `self.raw` is valid per the type invariant, and the second half is just + // converting lifetimes. + unsafe { callback(&*self.raw, &*(&*self.inner as *const _)) } + } +} + +impl> Deref for GpuObject { + type Target = T; + + fn deref(&self) -> &Self::Target { + &self.inner + } +} + +impl> DerefMut for GpuObject { + fn deref_mut(&mut self) -> &mut Self::Target { + &mut self.inner + } +} + +impl> Debug for GpuObject +where + ::Raw<'static>: Debug, +{ + fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result { + f.debug_struct(core::any::type_name::()) + // SAFETY: `self.raw` is valid per the type invariant. + .field("raw", &format_args!("{:#X?}", unsafe { &*self.raw })) + .field("inner", &format_args!("{:#X?}", &self.inner)) + .field("alloc", &format_args!("{:?}", &self.alloc)) + .finish() + } +} + +impl> GpuObject +where + for<'a> ::Raw<'a>: Default + Zeroable, +{ + /// Create a new GpuObject with default data. `T` must implement `Default` and `T::Raw` must + /// implement `Zeroable`, since the GPU-side memory is initialized by zeroing. + pub(crate) fn new_default(alloc: U) -> Result { + GpuObject::::new_inplace(alloc, Default::default(), |_inner, raw| { + // SAFETY: `raw` is valid here, and `T::Raw` implements `Zeroable`. + Ok(unsafe { + ptr::write_bytes(raw, 0, 1); + (*raw).assume_init_mut() + }) + }) + } +} + +impl> Drop for GpuObject { + fn drop(&mut self) { + mod_dev_dbg!( + self.alloc.device(), + "Dropping {} @ {:?}\n", + core::any::type_name::(), + self.gpu_pointer() + ); + } +} + +// SAFETY: GpuObjects are Send as long as the GpuStruct itself is Send +unsafe impl> Send for GpuObject {} +// SAFETY: GpuObjects are Send as long as the GpuStruct itself is Send +unsafe impl> Sync for GpuObject {} + +/// Trait used to erase the type of a GpuObject, used when we need to keep a list of heterogenous +/// objects around. +pub(crate) trait OpaqueGpuObject: Send + Sync { + fn gpu_va(&self) -> NonZeroU64; +} + +impl> OpaqueGpuObject for GpuObject { + fn gpu_va(&self) -> NonZeroU64 { + Self::gpu_va(self) + } +} + +/// An array of raw GPU objects that is only accessible to the GPU (no CPU-side mapping required). +/// +/// This must necessarily be uninitialized as far as the GPU is concerned, so it cannot be used +/// when initialization is required. +/// +/// # Invariants +/// +/// `alloc` is valid and at least as large as `len` times the size of one `T`. +/// `gpu_ptr` is valid and points to the allocation start. +pub(crate) struct GpuOnlyArray> { + len: usize, + alloc: U, + gpu_ptr: NonZeroU64, + _p: PhantomData, +} + +impl> GpuOnlyArray { + /// Allocate a new GPU-only array with the given length. + pub(crate) fn new(alloc: U, count: usize) -> Result> { + let bytes = count * mem::size_of::(); + let gpu_ptr = NonZeroU64::new(alloc.gpu_ptr()).ok_or(EINVAL)?; + if alloc.size() < bytes { + return Err(ENOMEM); + } + Ok(Self { + len: count, + alloc, + gpu_ptr, + _p: PhantomData, + }) + } + + /// Returns the GPU VA of this arraw (as a raw [`NonZeroU64`]) + pub(crate) fn gpu_va(&self) -> NonZeroU64 { + self.gpu_ptr + } + + /// Returns a strong GPU pointer to this array, with a lifetime. + pub(crate) fn gpu_pointer(&self) -> GpuPointer<'_, &'_ [T]> { + GpuPointer(self.gpu_ptr, PhantomData) + } + + /// Returns a weak GPU pointer to this array, with no lifetime. + pub(crate) fn weak_pointer(&self) -> GpuWeakPointer<[T]> { + GpuWeakPointer(self.gpu_ptr, PhantomData) + } + + /// Returns a pointer to an offset within the array (as a subslice). + pub(crate) fn gpu_offset_pointer(&self, offset: usize) -> GpuPointer<'_, &'_ [T]> { + if offset > self.len { + panic!("Index {} out of bounds (len: {})", offset, self.len); + } + GpuPointer( + NonZeroU64::new(self.gpu_ptr.get() + (offset * mem::size_of::()) as u64).unwrap(), + PhantomData, + ) + } + + /* Not used yet + /// Returns a weak pointer to an offset within the array (as a subslice). + pub(crate) fn weak_offset_pointer(&self, offset: usize) -> GpuWeakPointer<[T]> { + if offset > self.len { + panic!("Index {} out of bounds (len: {})", offset, self.len); + } + GpuWeakPointer( + NonZeroU64::new(self.gpu_ptr.get() + (offset * mem::size_of::()) as u64).unwrap(), + PhantomData, + ) + } + + /// Returns a pointer to an element within the array. + pub(crate) fn gpu_item_pointer(&self, index: usize) -> GpuPointer<'_, &'_ T> { + if index >= self.len { + panic!("Index {} out of bounds (len: {})", index, self.len); + } + GpuPointer( + NonZeroU64::new(self.gpu_ptr.get() + (index * mem::size_of::()) as u64).unwrap(), + PhantomData, + ) + } + */ + + /// Returns a weak pointer to an element within the array. + pub(crate) fn weak_item_pointer(&self, index: usize) -> GpuWeakPointer { + if index >= self.len { + panic!("Index {} out of bounds (len: {})", index, self.len); + } + GpuWeakPointer( + NonZeroU64::new(self.gpu_ptr.get() + (index * mem::size_of::()) as u64).unwrap(), + PhantomData, + ) + } + + /// Returns the length of the array. + pub(crate) fn len(&self) -> usize { + self.len + } +} + +impl> Debug for GpuOnlyArray { + fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result { + f.debug_struct(core::any::type_name::()) + .field("len", &format_args!("{:#X?}", self.len())) + .finish() + } +} + +impl> Drop for GpuOnlyArray { + fn drop(&mut self) { + mod_dev_dbg!( + self.alloc.device(), + "Dropping {} @ {:?}\n", + core::any::type_name::(), + self.gpu_pointer() + ); + } +} + +/// An array of raw GPU objects that is also CPU-accessible. +/// +/// # Invariants +/// +/// `raw` is valid and points to the CPU-side view of the array (which must have one). +pub(crate) struct GpuArray> { + raw: *mut T, + array: GpuOnlyArray, +} + +impl> GpuArray { + /// Allocate a new GPU array, initializing each element to its default. + pub(crate) fn empty(alloc: U, count: usize) -> Result> { + let p = alloc.ptr().ok_or(EINVAL)?.as_ptr(); + let inner = GpuOnlyArray::new(alloc, count)?; + let mut pi = p; + for _i in 0..count { + // SAFETY: `pi` is valid per the Allocation type invariant, and GpuOnlyArray guarantees + // that it can never iterate beyond the buffer length. + unsafe { + pi.write(Default::default()); + pi = pi.add(1); + } + } + Ok(Self { + raw: p, + array: inner, + }) + } +} + +impl> GpuArray { + /// Get a slice view of the array contents. + pub(crate) fn as_slice(&self) -> &[T] { + // SAFETY: self.raw / self.len are valid per the type invariant + unsafe { slice::from_raw_parts(self.raw, self.len) } + } + + /// Get a mutable slice view of the array contents. + pub(crate) fn as_mut_slice(&mut self) -> &mut [T] { + // SAFETY: self.raw / self.len are valid per the type invariant + unsafe { slice::from_raw_parts_mut(self.raw, self.len) } + } +} + +impl> Deref for GpuArray { + type Target = GpuOnlyArray; + + fn deref(&self) -> &GpuOnlyArray { + &self.array + } +} + +impl> Index for GpuArray { + type Output = T; + + fn index(&self, index: usize) -> &T { + if index >= self.len { + panic!("Index {} out of bounds (len: {})", index, self.len); + } + // SAFETY: This is bounds checked above + unsafe { &*(self.raw.add(index)) } + } +} + +impl> IndexMut for GpuArray { + fn index_mut(&mut self, index: usize) -> &mut T { + if index >= self.len { + panic!("Index {} out of bounds (len: {})", index, self.len); + } + // SAFETY: This is bounds checked above + unsafe { &mut *(self.raw.add(index)) } + } +} + +// SAFETY: GpuArray are Send as long as the contained type itself is Send +unsafe impl> Send for GpuArray {} +// SAFETY: GpuArray are Sync as long as the contained type itself is Sync +unsafe impl> Sync for GpuArray {} + +impl> Debug for GpuArray { + fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result { + f.debug_struct(core::any::type_name::()) + .field("array", &format_args!("{:#X?}", self.as_slice())) + .finish() + } +} diff --git a/drivers/gpu/drm/asahi/pgtable.rs b/drivers/gpu/drm/asahi/pgtable.rs new file mode 100644 index 00000000000000..7c9b54c2242515 --- /dev/null +++ b/drivers/gpu/drm/asahi/pgtable.rs @@ -0,0 +1,690 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! UAT Page Table management +//! +//! AGX GPUs use an MMU called the UAT, which is largely compatible with the ARM64 page table +//! format. This module manages the actual page tables by allocating raw memory pages from +//! the kernel page allocator. + +use core::fmt::Debug; +use core::mem::size_of; +use core::ops::Range; +use core::sync::atomic::{ + AtomicU64, + Ordering, // +}; + +use kernel::{ + addr::PhysicalAddr, + error::Result, + page::Page, + prelude::*, // +}; +#[cfg(CONFIG_DEV_COREDUMP)] +use kernel::{ + types::Owned, + uapi::{ + PF_R, + PF_W, + PF_X, // + }, +}; + +use crate::debug::*; +use crate::util::align; + +const DEBUG_CLASS: DebugFlags = DebugFlags::PgTable; + +/// Number of bits in a page offset. +pub(crate) const UAT_PGBIT: usize = 14; +/// UAT page size. +pub(crate) const UAT_PGSZ: usize = 1 << UAT_PGBIT; +/// UAT page offset mask. +pub(crate) const UAT_PGMSK: usize = UAT_PGSZ - 1; + +type Pte = AtomicU64; + +const PTE_BIT: usize = 3; // log2(sizeof(Pte)) +const PTE_SIZE: usize = 1 << PTE_BIT; + +/// Number of PTEs per page. +const UAT_NPTE: usize = UAT_PGSZ / size_of::(); + +/// Number of address bits to address a level +const UAT_LVBIT: usize = UAT_PGBIT - PTE_BIT; +/// Number of entries per level +const UAT_LVSZ: usize = UAT_NPTE; +/// Mask of level bits +const UAT_LVMSK: u64 = (UAT_LVSZ - 1) as u64; + +const UAT_LEVELS: usize = 3; + +/// UAT input address space +pub(crate) const UAT_IAS: usize = 39; +const UAT_IASMSK: u64 = (1u64 << UAT_IAS) - 1; + +const PTE_TYPE_BITS: u64 = 3; +const PTE_TYPE_LEAF_TABLE: u64 = 3; + +const UAT_NON_GLOBAL: u64 = 1 << 11; +const UAT_AP_SHIFT: u32 = 6; +const UAT_AP_BITS: u64 = 3 << UAT_AP_SHIFT; +const UAT_HIGH_BITS_SHIFT: u32 = 52; +const UAT_HIGH_BITS: u64 = 0xfff << UAT_HIGH_BITS_SHIFT; +const UAT_MEMATTR_SHIFT: u32 = 2; +const UAT_MEMATTR_BITS: u64 = 7 << UAT_MEMATTR_SHIFT; + +const UAT_PROT_BITS: u64 = UAT_AP_BITS | UAT_MEMATTR_BITS | UAT_HIGH_BITS; + +const UAT_AF: u64 = 1 << 10; + +const MEMATTR_CACHED: u8 = 0; +const MEMATTR_DEV: u8 = 1; +const MEMATTR_UNCACHED: u8 = 2; + +const AP_FW_GPU: u8 = 0; +const AP_FW: u8 = 1; +const AP_GPU: u8 = 2; + +const HIGH_BITS_PXN: u16 = 1 << 1; +const HIGH_BITS_UXN: u16 = 1 << 2; +const HIGH_BITS_GPU_ACCESS: u16 = 1 << 3; + +#[cfg(CONFIG_DEV_COREDUMP)] +pub(crate) const PTE_ADDR_BITS: u64 = (!UAT_PGMSK as u64) & (!UAT_HIGH_BITS); + +#[derive(Debug, Copy, Clone)] +pub(crate) struct Prot { + memattr: u8, + ap: u8, + high_bits: u16, +} + +// Firmware + GPU access +const PROT_FW_GPU_NA: Prot = Prot::from_bits(AP_FW_GPU, 0, 0); +const _PROT_FW_GPU_RO: Prot = Prot::from_bits(AP_FW_GPU, 0, 1); +const _PROT_FW_GPU_WO: Prot = Prot::from_bits(AP_FW_GPU, 1, 0); +const PROT_FW_GPU_RW: Prot = Prot::from_bits(AP_FW_GPU, 1, 1); + +// Firmware only access +const PROT_FW_RO: Prot = Prot::from_bits(AP_FW, 0, 0); +const _PROT_FW_NA: Prot = Prot::from_bits(AP_FW, 0, 1); +const PROT_FW_RW: Prot = Prot::from_bits(AP_FW, 1, 0); +const PROT_FW_RW_GPU_RO: Prot = Prot::from_bits(AP_FW, 1, 1); + +// GPU only access +const PROT_GPU_RO: Prot = Prot::from_bits(AP_GPU, 0, 0); +const PROT_GPU_WO: Prot = Prot::from_bits(AP_GPU, 0, 1); +const PROT_GPU_RW: Prot = Prot::from_bits(AP_GPU, 1, 0); +const _PROT_GPU_NA: Prot = Prot::from_bits(AP_GPU, 1, 1); + +#[cfg(CONFIG_DEV_COREDUMP)] +const PF_RW: u32 = PF_R | PF_W; +#[cfg(CONFIG_DEV_COREDUMP)] +const PF_RX: u32 = PF_R | PF_X; + +// For crash dumps +#[cfg(CONFIG_DEV_COREDUMP)] +const PROT_TO_PERMS_FW: [[u32; 4]; 4] = [ + [0, 0, 0, PF_RW], + [0, PF_RW, 0, PF_RW], + [PF_RX, PF_RX, 0, PF_R], + [PF_RX, PF_RW, 0, PF_R], +]; +#[cfg(CONFIG_DEV_COREDUMP)] +const PROT_TO_PERMS_OS: [[u32; 4]; 4] = [ + [0, PF_R, PF_W, PF_RW], + [PF_R, 0, PF_RW, PF_RW], + [0, 0, 0, 0], + [0, 0, 0, 0], +]; + +pub(crate) mod prot { + pub(crate) use super::Prot; + use super::*; + + /// Firmware MMIO R/W + pub(crate) const PROT_FW_MMIO_RW: Prot = PROT_FW_RW.memattr(MEMATTR_DEV); + /// Firmware MMIO R/O + pub(crate) const PROT_FW_MMIO_RO: Prot = PROT_FW_RO.memattr(MEMATTR_DEV); + /// Firmware shared (uncached) RW + pub(crate) const PROT_FW_SHARED_RW: Prot = PROT_FW_RW.memattr(MEMATTR_UNCACHED); + /// Firmware shared (uncached) RO + pub(crate) const PROT_FW_SHARED_RO: Prot = PROT_FW_RO.memattr(MEMATTR_UNCACHED); + /// Firmware private (cached) RW + pub(crate) const PROT_FW_PRIV_RW: Prot = PROT_FW_RW.memattr(MEMATTR_CACHED); + /// Firmware/GPU shared (uncached) RW + pub(crate) const PROT_GPU_FW_SHARED_RW: Prot = PROT_FW_GPU_RW.memattr(MEMATTR_UNCACHED); + /// Firmware/GPU shared (private) RW + pub(crate) const PROT_GPU_FW_PRIV_RW: Prot = PROT_FW_GPU_RW.memattr(MEMATTR_CACHED); + /// Firmware-RW/GPU-RO shared (private) RW + pub(crate) const PROT_GPU_RO_FW_PRIV_RW: Prot = PROT_FW_RW_GPU_RO.memattr(MEMATTR_CACHED); + /// GPU shared/coherent RW + pub(crate) const PROT_GPU_SHARED_RW: Prot = PROT_GPU_RW.memattr(MEMATTR_UNCACHED); + /// GPU shared/coherent RO + pub(crate) const PROT_GPU_SHARED_RO: Prot = PROT_GPU_RO.memattr(MEMATTR_UNCACHED); + /// GPU shared/coherent WO + pub(crate) const PROT_GPU_SHARED_WO: Prot = PROT_GPU_WO.memattr(MEMATTR_UNCACHED); +} + +impl Prot { + const fn from_bits(ap: u8, uxn: u16, pxn: u16) -> Self { + assert!(uxn <= 1); + assert!(pxn <= 1); + assert!(ap <= 3); + + Prot { + high_bits: HIGH_BITS_GPU_ACCESS | (pxn * HIGH_BITS_PXN) | (uxn * HIGH_BITS_UXN), + memattr: 0, + ap, + } + } + + #[cfg(CONFIG_DEV_COREDUMP)] + pub(crate) const fn from_pte(pte: u64) -> Self { + Prot { + high_bits: (pte >> UAT_HIGH_BITS_SHIFT) as u16, + ap: ((pte & UAT_AP_BITS) >> UAT_AP_SHIFT) as u8, + memattr: ((pte & UAT_MEMATTR_BITS) >> UAT_MEMATTR_SHIFT) as u8, + } + } + + #[cfg(CONFIG_DEV_COREDUMP)] + pub(crate) const fn elf_flags(&self) -> u32 { + let ap = (self.ap & 3) as usize; + let uxn = if self.high_bits & HIGH_BITS_UXN != 0 { + 1 + } else { + 0 + }; + let pxn = if self.high_bits & HIGH_BITS_PXN != 0 { + 1 + } else { + 0 + }; + let gpu = self.high_bits & HIGH_BITS_GPU_ACCESS != 0; + + // Format: + // [12 top bits of PTE] [12 bottom bits of PTE] [5 bits pad] [ELF RWX] + let mut perms = if gpu { + PROT_TO_PERMS_OS[ap][(uxn << 1) | pxn] + } else { + PROT_TO_PERMS_FW[ap][(uxn << 1) | pxn] + }; + + perms |= ((self.as_pte() >> 52) << 20) as u32; + perms |= ((self.as_pte() & 0xfff) << 8) as u32; + + perms + } + + const fn memattr(&self, memattr: u8) -> Self { + Self { memattr, ..*self } + } + + const fn as_pte(&self) -> u64 { + (self.ap as u64) << UAT_AP_SHIFT + | (self.high_bits as u64) << UAT_HIGH_BITS_SHIFT + | (self.memattr as u64) << UAT_MEMATTR_SHIFT + | UAT_AF + } + + pub(crate) const fn is_cached_noncoherent(&self) -> bool { + self.ap != AP_GPU && self.memattr == MEMATTR_CACHED + } + + pub(crate) const fn as_uncached(&self) -> Self { + self.memattr(MEMATTR_UNCACHED) + } +} + +impl Default for Prot { + fn default() -> Self { + PROT_FW_GPU_NA + } +} + +#[cfg(CONFIG_DEV_COREDUMP)] +pub(crate) struct DumpedPage { + pub(crate) iova: u64, + pub(crate) pte: u64, + pub(crate) data: Option>, +} + +pub(crate) struct UatPageTable { + ttb: PhysicalAddr, + ttb_owned: bool, + va_range: Range, + oas_mask: u64, +} + +impl UatPageTable { + pub(crate) fn new(oas: u32) -> Result { + mod_pr_debug!("UATPageTable::new: oas={}\n", oas); + let ttb_page = Page::alloc_page(GFP_KERNEL | __GFP_ZERO)?; + let ttb = Page::into_phys(ttb_page); + Ok(UatPageTable { + ttb, + ttb_owned: true, + va_range: 0..(1u64 << UAT_IAS), + oas_mask: (1u64 << oas) - 1, + }) + } + + pub(crate) fn new_with_ttb(ttb: PhysicalAddr, va_range: Range, oas: u32) -> Result { + mod_pr_debug!( + "UATPageTable::new_with_ttb: ttb={:#x} range={:#x?} oas={}\n", + ttb, + va_range, + oas + ); + if ttb & (UAT_PGMSK as PhysicalAddr) != 0 { + return Err(EINVAL); + } + if (va_range.start | va_range.end) & (UAT_PGMSK as u64) != 0 { + return Err(EINVAL); + } + // SAFETY: The TTB is should remain valid (if properly mapped), as it is bootloader-managed. + if unsafe { Page::borrow_phys(&ttb) }.is_none() { + pr_err!( + "UATPageTable::new_with_ttb: ttb at {:#x} is not mapped (DT using no-map?)\n", + ttb + ); + return Err(EIO); + } + + Ok(UatPageTable { + ttb, + ttb_owned: false, + va_range, + oas_mask: (1u64 << oas) - 1, + }) + } + + pub(crate) fn ttb(&self) -> PhysicalAddr { + self.ttb + } + + fn with_pages( + &mut self, + iova_range: Range, + alloc: bool, + free: bool, + mut cb: F, + ) -> Result + where + F: FnMut(u64, &[Pte]) -> Result, + { + mod_pr_debug!( + "UATPageTable::with_pages: {:#x?} alloc={} free={}\n", + iova_range, + alloc, + free + ); + if (iova_range.start | iova_range.end) & (UAT_PGMSK as u64) != 0 { + pr_err!( + "UATPageTable::with_pages: iova range not aligned: {:#x?}\n", + iova_range + ); + return Err(EINVAL); + } + + if iova_range.is_empty() { + return Ok(()); + } + + let mut iova = iova_range.start & UAT_IASMSK; + let mut last_iova = iova; + // Handle the case where iova_range.end is just at the top boundary of the IAS + let end = ((iova_range.end - 1) & UAT_IASMSK) + 1; + + let mut pt_addr: [Option; UAT_LEVELS] = Default::default(); + pt_addr[UAT_LEVELS - 1] = Some(self.ttb); + + 'outer: while iova < end { + mod_pr_debug!("UATPageTable::with_pages: iova={:#x}\n", iova); + let addr_diff = last_iova ^ iova; + for level in (0..UAT_LEVELS - 1).rev() { + // If the iova has changed at this level or above, invalidate the physaddr + if addr_diff & !((1 << (UAT_PGBIT + (level + 1) * UAT_LVBIT)) - 1) != 0 { + if let Some(phys) = pt_addr[level].take() { + if free { + mod_pr_debug!( + "UATPageTable::with_pages: free level {} {:#x?}\n", + level, + phys + ); + // SAFETY: Page tables for our VA ranges always come from Page::into_phys(). + unsafe { Page::from_phys(phys) }; + } + mod_pr_debug!("UATPageTable::with_pages: invalidate level {}\n", level); + } + } + } + last_iova = iova; + for level in (0..UAT_LEVELS - 1).rev() { + // Fetch the page table base address for this level + if pt_addr[level].is_none() { + let phys = pt_addr[level + 1].unwrap(); + mod_pr_debug!( + "UATPageTable::with_pages: need level {}, parent phys {:#x}\n", + level, + phys + ); + let upidx = ((iova >> (UAT_PGBIT + (level + 1) * UAT_LVBIT) as u64) & UAT_LVMSK) + as usize; + // SAFETY: Page table addresses are either allocated by us, or + // firmware-managed and safe to borrow a struct page from. + let upt = unsafe { Page::borrow_phys_unchecked(&phys) }; + mod_pr_debug!("UATPageTable::with_pages: borrowed phys {:#x}\n", phys); + pt_addr[level] = + upt.with_pointer_into_page(upidx * PTE_SIZE, PTE_SIZE, |p| { + let uptep = p as *const _ as *const Pte; + // SAFETY: with_pointer_into_page() ensures the pointer is valid, + // and our index is aligned so it is safe to deref as an AtomicU64. + let upte = unsafe { &*uptep }; + let mut upte_val = upte.load(Ordering::Relaxed); + // Allocate if requested + if upte_val == 0 && alloc { + let pt_page = Page::alloc_page(GFP_KERNEL | __GFP_ZERO)?; + mod_pr_debug!("UATPageTable::with_pages: alloc PT at {:#x}\n", pt_page.phys()); + let pt_paddr = Page::into_phys(pt_page); + upte_val = pt_paddr | PTE_TYPE_LEAF_TABLE; + upte.store(upte_val, Ordering::Relaxed); + } + if upte_val & PTE_TYPE_BITS == PTE_TYPE_LEAF_TABLE { + Ok(Some(upte_val & self.oas_mask & (!UAT_PGMSK as u64))) + } else if upte_val == 0 || (!alloc && !free) { + mod_pr_debug!("UATPageTable::with_pages: no level {}\n", level); + Ok(None) + } else { + pr_err!("UATPageTable::with_pages: Unexpected Table PTE value {:#x} at iova {:#x} index {} phys {:#x}\n", upte_val, + iova, level + 1, phys + ((upidx * PTE_SIZE) as PhysicalAddr)); + Ok(None) + } + })?; + mod_pr_debug!( + "UATPageTable::with_pages: level {} PT {:#x?}\n", + level, + pt_addr[level] + ); + } + // If we don't have a page table, skip this entire level + if pt_addr[level].is_none() { + let block = 1 << (UAT_PGBIT + UAT_LVBIT * (level + 1)); + let old = iova; + iova = align(iova + 1, block); + mod_pr_debug!( + "UATPageTable::with_pages: skip {:#x} {:#x} -> {:#x}\n", + block, + old, + iova + ); + continue 'outer; + } + } + + let idx = ((iova >> UAT_PGBIT as u64) & UAT_LVMSK) as usize; + let max_count = UAT_NPTE - idx; + let count = (((end - iova) >> UAT_PGBIT) as usize).min(max_count); + let phys = pt_addr[0].unwrap(); + mod_pr_debug!( + "UATPageTable::with_pages: leaf PT at {:#x} idx {:#x} count {:#x} iova {:#x}\n", + phys, + idx, + count, + iova + ); + // SAFETY: Page table addresses are either allocated by us, or + // firmware-managed and safe to borrow a struct page from. + let pt = unsafe { Page::borrow_phys_unchecked(&phys) }; + pt.with_pointer_into_page(idx * PTE_SIZE, count * PTE_SIZE, |p| { + let ptep = p as *const _ as *const Pte; + // SAFETY: We know this is a valid pointer to PTEs and the range is valid and + // checked by with_pointer_into_page(). + let ptes = unsafe { core::slice::from_raw_parts(ptep, count) }; + cb(iova, ptes)?; + Ok(()) + })?; + + let block = 1 << (UAT_PGBIT + UAT_LVBIT); + iova = align(iova + 1, block); + } + + if free { + for level in (0..UAT_LEVELS - 1).rev() { + if let Some(phys) = pt_addr[level] { + mod_pr_debug!( + "UATPageTable::with_pages: free level {} {:#x?}\n", + level, + phys + ); + // SAFETY: Page tables for our VA ranges always come from Page::into_phys(). + unsafe { Page::from_phys(phys) }; + } + } + } + + Ok(()) + } + + pub(crate) fn alloc_pages(&mut self, iova_range: Range) -> Result { + mod_pr_debug!("UATPageTable::alloc_pages: {:#x?}\n", iova_range); + self.with_pages(iova_range, true, false, |_, _| Ok(())) + } + + fn pte_bits(&self) -> u64 { + if self.ttb_owned { + // Owned page tables are userspace, so non-global + PTE_TYPE_LEAF_TABLE | UAT_NON_GLOBAL + } else { + // The sole non-owned page table is kernelspace, so global + PTE_TYPE_LEAF_TABLE + } + } + + pub(crate) fn map_pages( + &mut self, + iova_range: Range, + mut phys: PhysicalAddr, + prot: Prot, + one_page: bool, + ) -> Result { + mod_pr_debug!( + "UATPageTable::map_pages: {:#x?} {:#x?} {:?}\n", + iova_range, + phys, + prot + ); + if phys & (UAT_PGMSK as PhysicalAddr) != 0 { + pr_err!("UATPageTable::map_pages: phys not aligned: {:#x?}\n", phys); + return Err(EINVAL); + } + + let pte_bits = self.pte_bits(); + + self.with_pages(iova_range, true, false, |iova, ptes| { + for (idx, pte) in ptes.iter().enumerate() { + let ptev = pte.load(Ordering::Relaxed); + if ptev != 0 { + pr_err!( + "UATPageTable::map_pages: Page at IOVA {:#x} is mapped (PTE: {:#x})\n", + iova + (idx * UAT_PGSZ) as u64, + ptev + ); + } + pte.store(phys | prot.as_pte() | pte_bits, Ordering::Relaxed); + if !one_page { + phys += UAT_PGSZ as PhysicalAddr; + } + } + Ok(()) + }) + } + + pub(crate) fn reprot_pages(&mut self, iova_range: Range, prot: Prot) -> Result { + mod_pr_debug!( + "UATPageTable::reprot_pages: {:#x?} {:?}\n", + iova_range, + prot + ); + self.with_pages(iova_range, true, false, |iova, ptes| { + for (idx, pte) in ptes.iter().enumerate() { + let ptev = pte.load(Ordering::Relaxed); + if ptev & PTE_TYPE_BITS != PTE_TYPE_LEAF_TABLE { + pr_err!( + "UATPageTable::reprot_pages: Page at IOVA {:#x} is unmapped (PTE: {:#x})\n", + iova + (idx * UAT_PGSZ) as u64, + ptev + ); + continue; + } + pte.store((ptev & !UAT_PROT_BITS) | prot.as_pte(), Ordering::Relaxed); + } + Ok(()) + }) + } + + pub(crate) fn unmap_pages(&mut self, iova_range: Range) -> Result { + mod_pr_debug!("UATPageTable::unmap_pages: {:#x?}\n", iova_range); + self.with_pages(iova_range, false, false, |iova, ptes| { + for (idx, pte) in ptes.iter().enumerate() { + if pte.load(Ordering::Relaxed) & PTE_TYPE_LEAF_TABLE == 0 { + pr_err!( + "UATPageTable::unmap_pages: Page at IOVA {:#x} already unmapped\n", + iova + (idx * UAT_PGSZ) as u64 + ); + } + pte.store(0, Ordering::Relaxed); + } + Ok(()) + }) + } + + #[cfg(CONFIG_DEV_COREDUMP)] + pub(crate) fn dump_pages(&mut self, iova_range: Range) -> Result> { + let mut pages = KVVec::new(); + let oas_mask = self.oas_mask; + let iova_base = self.va_range.start & !UAT_IASMSK; + self.with_pages(iova_range, false, false, |iova, ptes| { + let iova = iova | iova_base; + for (idx, ppte) in ptes.iter().enumerate() { + let pte = ppte.load(Ordering::Relaxed); + if (pte & PTE_TYPE_LEAF_TABLE) != PTE_TYPE_LEAF_TABLE { + continue; + } + let memattr = ((pte & UAT_MEMATTR_BITS) >> UAT_MEMATTR_SHIFT) as u8; + + if !(memattr == MEMATTR_CACHED || memattr == MEMATTR_UNCACHED) { + pages.push( + DumpedPage { + iova: iova + (idx * UAT_PGSZ) as u64, + pte, + data: None, + }, + GFP_KERNEL, + )?; + continue; + } + let phys = pte & oas_mask & (!UAT_PGMSK as u64); + // SAFETY: GPU pages are either firmware/preallocated pages + // (which the kernel isn't concerned with and are either in + // the page map or not, and if they aren't, borrow_phys() + // will fail), or GPU page table pages (which we own), + // or GEM buffer pages (which are locked while they are + // mapped in the page table), so they should be safe to + // borrow. + // + // This does trust the firmware not to have any weird + // mappings in its own internal page tables, but since + // those are managed by the uPPL which is privileged anyway, + // this trust does not actually extend any trust boundary. + let src_page = match unsafe { Page::borrow_phys(&phys) } { + Some(page) => page, + None => { + pages.push( + DumpedPage { + iova: iova + (idx * UAT_PGSZ) as u64, + pte, + data: None, + }, + GFP_KERNEL, + )?; + continue; + } + }; + let dst_page = Page::alloc_page(GFP_KERNEL)?; + src_page.with_page_mapped(|psrc| -> Result { + // SAFETY: This could technically still have a data race with the firmware + // or other driver code (or even userspace with timestamp buffers), but while + // the Rust language technically says this is UB, in the real world, using + // atomic reads for this is guaranteed to never cause any harmful effects + // other than possibly reading torn/unreliable data. At least on ARM64 anyway. + // + // (Yes, I checked with Rust people about this. ~~ Lina) + // + let src_items = unsafe { + core::slice::from_raw_parts( + psrc as *const AtomicU64, + UAT_PGSZ / core::mem::size_of::(), + ) + }; + dst_page.with_page_mapped(|pdst| -> Result { + // SAFETY: We own the destination page, so it is safe to view its contents + // as a u64 slice. + let dst_items = unsafe { + core::slice::from_raw_parts_mut( + pdst as *mut u64, + UAT_PGSZ / core::mem::size_of::(), + ) + }; + for (si, di) in src_items.iter().zip(dst_items.iter_mut()) { + *di = si.load(Ordering::Relaxed); + } + Ok(()) + })?; + Ok(()) + })?; + pages.push( + DumpedPage { + iova: iova + (idx * UAT_PGSZ) as u64, + pte, + data: Some(dst_page), + }, + GFP_KERNEL, + )?; + } + Ok(()) + })?; + Ok(pages) + } +} + +impl Drop for UatPageTable { + fn drop(&mut self) { + mod_pr_debug!("UATPageTable::drop range: {:#x?}\n", &self.va_range); + if self + .with_pages(self.va_range.clone(), false, true, |iova, ptes| { + for (idx, pte) in ptes.iter().enumerate() { + if pte.load(Ordering::Relaxed) != 0 { + pr_err!( + "UATPageTable::drop: Leaked page at IOVA {:#x}\n", + iova + (idx * UAT_PGSZ) as u64 + ); + } + } + Ok(()) + }) + .is_err() + { + pr_err!("UATPageTable::drop failed to free page tables\n",); + } + if self.ttb_owned { + mod_pr_debug!("UATPageTable::drop: Free TTB {:#x}\n", self.ttb); + // SAFETY: If we own the ttb, it was allocated with Page::into_phys(). + unsafe { + Page::from_phys(self.ttb); + } + } + } +} diff --git a/drivers/gpu/drm/asahi/queue/common.rs b/drivers/gpu/drm/asahi/queue/common.rs new file mode 100644 index 00000000000000..a68352828cfbc3 --- /dev/null +++ b/drivers/gpu/drm/asahi/queue/common.rs @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Common queue functionality. +//! +//! Shared helpers used by the submission logic for multiple command types. + +use crate::file; +use crate::fw::job::UserTimestamp; + +use kernel::prelude::*; +use kernel::uapi; +use kernel::xarray; + +pub(super) fn get_timestamp_object( + objects: Pin<&xarray::XArray>>, + timestamp: uapi::drm_asahi_timestamp, +) -> Result> { + if timestamp.handle == 0 { + return Ok(None); + } + + let guard = objects.lock(); + let object = guard + .get(timestamp.handle.try_into()?) + .ok_or(ENOENT)? + .clone(); + core::mem::drop(guard); + + #[allow(irrefutable_let_patterns)] + if let file::Object::TimestampBuffer(mapping) = object { + let offset = timestamp.offset; + if (offset.checked_add(8).ok_or(EINVAL)?) as usize > mapping.size() { + return Err(ERANGE); + } + Ok(Some(UserTimestamp { + mapping: mapping.clone(), + offset: offset as usize, + })) + } else { + Err(EINVAL) + } +} diff --git a/drivers/gpu/drm/asahi/queue/compute.rs b/drivers/gpu/drm/asahi/queue/compute.rs new file mode 100644 index 00000000000000..62afc561806703 --- /dev/null +++ b/drivers/gpu/drm/asahi/queue/compute.rs @@ -0,0 +1,385 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +#![allow(clippy::unusual_byte_groupings)] + +//! Compute work queue. +//! +//! A compute queue consists of one underlying WorkQueue. +//! This module is in charge of creating all of the firmware structures required to submit compute +//! work to the GPU, based on the userspace command buffer. + +use super::common; +use crate::alloc::Allocator; +use crate::debug::*; +use crate::fw::types::*; +use crate::gpu::GpuManager; +use crate::{ + file, + fw, + gpu, + microseq, // +}; +use crate::{ + inner_ptr, + inner_weak_ptr, // +}; +use core::sync::atomic::Ordering; +use kernel::dma_fence::RawDmaFence; +use kernel::drm::sched::Job; +use kernel::prelude::*; +use kernel::sync::Arc; +use kernel::uapi; +use kernel::xarray; + +const DEBUG_CLASS: DebugFlags = DebugFlags::Compute; + +#[versions(AGX)] +impl super::QueueInner::ver { + /// Submit work to a compute queue. + pub(super) fn submit_compute( + &self, + job: &mut Job, + cmdbuf: &uapi::drm_asahi_cmd_compute, + attachments: µseq::Attachments, + objects: Pin<&xarray::XArray>>, + id: u64, + flush_stamps: bool, + ) -> Result { + let gpu = match (*self.dev) + .gpu + .as_any() + .downcast_ref::() + { + Some(gpu) => gpu, + None => { + dev_crit!(self.dev.as_ref(), "GpuManager mismatched with Queue!\n"); + return Err(EIO); + } + }; + + let mut alloc = gpu.alloc(); + let kalloc = &mut *alloc; + + mod_dev_dbg!(self.dev, "[Submission {}] Compute!\n", id); + + if cmdbuf.flags != 0 { + return Err(EINVAL); + } + + let mut user_timestamps: fw::job::UserTimestamps = Default::default(); + user_timestamps.start = common::get_timestamp_object(objects, cmdbuf.ts.start)?; + user_timestamps.end = common::get_timestamp_object(objects, cmdbuf.ts.end)?; + + // This sequence number increases per new client/VM? assigned to some slot, + // but it's unclear *which* slot... + let slot_client_seq: u8 = (self.id & 0xff) as u8; + + let vm_bind = job.vm_bind.clone(); + + mod_dev_dbg!( + self.dev, + "[Submission {}] VM slot = {}\n", + id, + vm_bind.slot() + ); + + let notifier = self.notifier.clone(); + + let fence = job.fence.clone(); + let comp_job = job.get_comp()?; + let ev_comp = comp_job.event_info(); + + let preempt2_off = gpu.get_cfg().compute_preempt1_size; + let preempt3_off = preempt2_off + 8; + let preempt4_off = preempt3_off + 8; + let preempt5_off = preempt4_off + 8; + let preempt_size = preempt5_off + 8; + + let preempt_buf = self + .ualloc + .lock() + .array_empty_tagged(preempt_size, b"CPMT")?; + + mod_dev_dbg!( + self.dev, + "[Submission {}] Event #{} {:#x?} -> {:#x?}\n", + id, + ev_comp.slot, + ev_comp.value, + ev_comp.value.next(), + ); + + let timestamps = Arc::new( + kalloc.shared.new_default::()?, + GFP_KERNEL, + )?; + + let uuid = 0; + mod_dev_dbg!(self.dev, "[Submission {}] UUID = {:#x?}\n", id, uuid); + + // TODO: check + #[ver(V >= V13_0B4)] + let count = self.counter.fetch_add(1, Ordering::Relaxed); + + let comp = GpuObject::new_init_prealloc( + kalloc.gpu_ro.alloc_object()?, + |ptr: GpuWeakPointer| { + let notifier = notifier.clone(); + let vm_bind = vm_bind.clone(); + try_init!(fw::compute::RunCompute::ver { + preempt_buf: preempt_buf, + micro_seq: { + let mut builder = microseq::Builder::new(); + + let stats = gpu.initdata.runtime_pointers.stats.comp.weak_pointer(); + + let start_comp = builder.add(microseq::StartCompute::ver { + header: microseq::op::StartCompute::HEADER, + unk_pointer: inner_weak_ptr!(ptr, unk_pointee), + #[ver(G < G14X)] + job_params1: Some(inner_weak_ptr!(ptr, job_params1)), + #[ver(G >= G14X)] + job_params1: None, + #[ver(G >= G14X)] + registers: inner_weak_ptr!(ptr, registers), + stats, + work_queue: ev_comp.info_ptr, + vm_slot: vm_bind.slot(), + unk_28: 0x1, + event_generation: self.id as u32, + event_seq: U64(ev_comp.event_seq), + unk_38: 0x0, + job_params2: inner_weak_ptr!(ptr, job_params2), + unk_44: 0x0, + uuid, + attachments: *attachments, + padding: Default::default(), + #[ver(V >= V13_0B4)] + unk_flag: inner_weak_ptr!(ptr, unk_flag), + #[ver(V >= V13_0B4)] + counter: U64(count), + #[ver(V >= V13_0B4)] + notifier_buf: inner_weak_ptr!(notifier.weak_pointer(), state.unk_buf), + })?; + + if user_timestamps.any() { + builder.add(microseq::Timestamp::ver { + header: microseq::op::Timestamp::new(true), + command_time: inner_weak_ptr!(ptr, command_time), + ts_pointers: inner_weak_ptr!(ptr, timestamp_pointers), + update_ts: inner_weak_ptr!(ptr, timestamp_pointers.start_addr), + work_queue: ev_comp.info_ptr, + user_ts_pointers: inner_weak_ptr!(ptr, user_timestamp_pointers), + #[ver(V >= V13_0B4)] + unk_ts: inner_weak_ptr!(ptr, context_store_req), + uuid, + unk_30_padding: 0, + })?; + } + + #[ver(G < G14X)] + builder.add(microseq::WaitForIdle { + header: microseq::op::WaitForIdle::new(microseq::Pipe::Compute), + })?; + #[ver(G >= G14X)] + builder.add(microseq::WaitForIdle2 { + header: microseq::op::WaitForIdle2::HEADER, + })?; + + if user_timestamps.any() { + builder.add(microseq::Timestamp::ver { + header: microseq::op::Timestamp::new(false), + command_time: inner_weak_ptr!(ptr, command_time), + ts_pointers: inner_weak_ptr!(ptr, timestamp_pointers), + update_ts: inner_weak_ptr!(ptr, timestamp_pointers.end_addr), + work_queue: ev_comp.info_ptr, + user_ts_pointers: inner_weak_ptr!(ptr, user_timestamp_pointers), + #[ver(V >= V13_0B4)] + unk_ts: inner_weak_ptr!(ptr, context_store_req), + uuid, + unk_30_padding: 0, + })?; + } + + let off = builder.offset_to(start_comp); + builder.add(microseq::FinalizeCompute::ver { + header: microseq::op::FinalizeCompute::HEADER, + stats, + work_queue: ev_comp.info_ptr, + vm_slot: vm_bind.slot(), + #[ver(V < V13_0B4)] + unk_18: 0, + job_params2: inner_weak_ptr!(ptr, job_params2), + unk_24: 0, + uuid, + fw_stamp: ev_comp.fw_stamp_pointer, + stamp_value: ev_comp.value.next(), + unk_38: 0, + unk_3c: 0, + unk_40: 0, + unk_44: 0, + unk_48: 0, + unk_4c: 0, + unk_50: 0, + unk_54: 0, + unk_58: 0, + #[ver(G == G14 && V < V13_0B4)] + unk_5c_g14: U64(0), + restart_branch_offset: off, + has_attachments: (attachments.count > 0) as u32, + #[ver(V >= V13_0B4)] + unk_64: Default::default(), + #[ver(V >= V13_0B4)] + unk_flag: inner_weak_ptr!(ptr, unk_flag), + #[ver(V >= V13_0B4)] + unk_79: Default::default(), + })?; + + builder.add(microseq::RetireStamp { + header: microseq::op::RetireStamp::HEADER, + })?; + builder.build(&mut kalloc.private)? + }, + notifier, + vm_bind, + timestamps, + user_timestamps, + }) + }, + |inner, _ptr| { + let vm_slot = vm_bind.slot(); + try_init!(fw::compute::raw::RunCompute::ver { + tag: fw::workqueue::CommandType::RunCompute, + #[ver(V >= V13_0B4)] + counter: U64(count), + unk_4: 0, + vm_slot, + notifier: inner.notifier.gpu_pointer(), + unk_pointee: Default::default(), + #[ver(G < G14X)] + __pad0: Default::default(), + #[ver(G < G14X)] + job_params1 <- try_init!(fw::compute::raw::JobParameters1 { + preempt_buf1: inner.preempt_buf.gpu_pointer(), + cdm_ctrl_stream_base: U64(cmdbuf.cdm_ctrl_stream_base), + // buf2-5 Only if internal program is used + preempt_buf2: inner.preempt_buf.gpu_offset_pointer(preempt2_off), + preempt_buf3: inner.preempt_buf.gpu_offset_pointer(preempt3_off), + preempt_buf4: inner.preempt_buf.gpu_offset_pointer(preempt4_off), + preempt_buf5: inner.preempt_buf.gpu_offset_pointer(preempt5_off), + usc_exec_base_cp: U64(self.usc_exec_base), + unk_38: U64(0x8c60), + helper_program: cmdbuf.helper.binary, // Internal program addr | 1 + unk_44: 0, + helper_arg: U64(cmdbuf.helper.data), // Only if internal program used + helper_cfg: cmdbuf.helper.cfg, // 0x40 if internal program used + unk_54: 0, + unk_58: 1, + unk_5c: 0, + iogpu_unk_40: 0, // 0x1c if internal program used + __pad: Default::default(), + }), + #[ver(G >= G14X)] + registers: fw::job::raw::RegisterArray::new( + inner_weak_ptr!(_ptr, registers.registers), + |r| { + r.add(0x1a510, inner.preempt_buf.gpu_pointer().into()); + r.add(0x1a420, cmdbuf.cdm_ctrl_stream_base); + // buf2-5 Only if internal program is used + r.add(0x1a4d0, inner.preempt_buf.gpu_offset_pointer(preempt2_off).into()); + r.add(0x1a4d8, inner.preempt_buf.gpu_offset_pointer(preempt3_off).into()); + r.add(0x1a4e0, inner.preempt_buf.gpu_offset_pointer(preempt4_off).into()); + r.add(0x1a4e8, inner.preempt_buf.gpu_offset_pointer(preempt5_off).into()); + r.add(0x10071, self.usc_exec_base); // USC_EXEC_BASE_CP + r.add(0x11841, cmdbuf.helper.binary.into()); + r.add(0x11849, cmdbuf.helper.data); + r.add(0x11f81, cmdbuf.helper.cfg.into()); + r.add(0x1a440, 0x24201); + r.add(0x12091, 0 /* iogpu_unk_40 */); + /* + r.add(0x10201, 0x100); // Some kind of counter?? Does this matter? + r.add(0x10428, 0x100); // Some kind of counter?? Does this matter? + */ + } + ), + __pad1: Default::default(), + microsequence: inner.micro_seq.gpu_pointer(), + microsequence_size: inner.micro_seq.len() as u32, + job_params2 <- try_init!(fw::compute::raw::JobParameters2::ver { + #[ver(V >= V13_0B4)] + unk_0_0: 0, + unk_0: Default::default(), + preempt_buf1: inner.preempt_buf.gpu_pointer(), + cdm_ctrl_stream_end: U64(cmdbuf.cdm_ctrl_stream_end), + unk_34: Default::default(), + #[ver(G < G14X)] + unk_g14x: 0, + #[ver(G >= G14X)] + unk_g14x: 0x24201, + unk_58: 0, + #[ver(V < V13_0B4)] + unk_5c: 0, + }), + encoder_params <- try_init!(fw::job::raw::EncoderParams { + unk_8: 0x0, // fixed + sync_grow: 0x0, // check! + unk_10: 0x0, // fixed + encoder_id: 0, + unk_18: 0x0, // fixed + unk_mask: 0xffffffff, + sampler_array: U64(cmdbuf.sampler_heap), + sampler_count: cmdbuf.sampler_count as u32, + sampler_max: (cmdbuf.sampler_count as u32) + 1, + }), + meta <- try_init!(fw::job::raw::JobMeta { + unk_0: 0, + unk_2: 0, + no_preemption: 0, + stamp: ev_comp.stamp_pointer, + fw_stamp: ev_comp.fw_stamp_pointer, + stamp_value: ev_comp.value.next(), + stamp_slot: ev_comp.slot, + evctl_index: 0, // fixed + flush_stamps: flush_stamps as u32, + uuid, + event_seq: ev_comp.event_seq as u32, + }), + command_time: U64(0), + timestamp_pointers <- try_init!(fw::job::raw::TimestampPointers { + start_addr: Some(inner_ptr!(inner.timestamps.gpu_pointer(), start)), + end_addr: Some(inner_ptr!(inner.timestamps.gpu_pointer(), end)), + }), + user_timestamp_pointers: inner.user_timestamps.pointers()?, + client_sequence: slot_client_seq, + pad_2d1: Default::default(), + unk_2d4: 0, + unk_2d8: 0, + #[ver(V >= V13_0B4)] + context_store_req: U64(0), + #[ver(V >= V13_0B4)] + context_store_compl: U64(0), + #[ver(V >= V13_0B4)] + unk_2e9: Default::default(), + #[ver(V >= V13_0B4)] + unk_flag: U32(0), + #[ver(V >= V13_0B4)] + unk_pad: Default::default(), + }) + }, + )?; + + core::mem::drop(alloc); + + fence.add_command(); + comp_job.add_cb(comp, vm_bind.slot(), move |error| { + if let Some(err) = error { + fence.set_error(err.into()) + } + + fence.command_complete(); + })?; + + comp_job.next_seq(); + + Ok(()) + } +} diff --git a/drivers/gpu/drm/asahi/queue/mod.rs b/drivers/gpu/drm/asahi/queue/mod.rs new file mode 100644 index 00000000000000..caae3e19f994c6 --- /dev/null +++ b/drivers/gpu/drm/asahi/queue/mod.rs @@ -0,0 +1,937 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Submission queue management +//! +//! This module implements the userspace view of submission queues and the logic to map userspace +//! submissions to firmware queues. + +use kernel::dma_fence::*; +use kernel::prelude::*; +use kernel::{ + c_str, + dma_fence, + drm::sched, + macros::versions, + sync::{ + Arc, + LockClassKey, + Mutex, // + }, + uapi, + xarray, // +}; + +use crate::alloc::Allocator; +use crate::debug::*; +use crate::driver::{AsahiDevRef, AsahiDevice}; +use crate::file::MAX_COMMANDS_PER_SUBMISSION; +use crate::fw::types::*; +use crate::gpu::GpuManager; +use crate::inner_weak_ptr; +use crate::microseq; +use crate::module_parameters; +use crate::util::{ + AnyBitPattern, + Reader, // +}; +use crate::{ + alloc, + buffer, + channel, + event, + file, + fw, + gpu, + mmu, + workqueue, // +}; + +use core::sync::atomic::{ + AtomicU64, + Ordering, // +}; + +const DEBUG_CLASS: DebugFlags = DebugFlags::Queue; + +const WQ_SIZE: u32 = 0x500; + +mod common; +mod compute; +mod render; + +/// Trait implemented by all versioned queues. +pub(crate) trait Queue: Send + Sync { + fn submit( + &mut self, + id: u64, + syncs: KVec, + in_sync_count: usize, + cmdbuf_raw: &[u8], + objects: Pin<&xarray::XArray>>, + ) -> Result; +} + +#[versions(AGX)] +struct SubQueue { + wq: Arc, +} + +#[versions(AGX)] +impl SubQueue::ver { + fn new_job(&mut self, fence: dma_fence::Fence) -> SubQueueJob::ver { + SubQueueJob::ver { + wq: self.wq.clone(), + fence: Some(fence), + job: None, + } + } +} + +#[versions(AGX)] +struct SubQueueJob { + wq: Arc, + job: Option, + fence: Option, +} + +#[versions(AGX)] +impl SubQueueJob::ver { + fn get(&mut self) -> Result<&mut workqueue::Job::ver> { + if self.job.is_none() { + mod_pr_debug!("SubQueueJob: Creating {:?} job\n", self.wq.pipe_type()); + self.job + .replace(self.wq.new_job(self.fence.take().unwrap())?); + } + Ok(self.job.as_mut().expect("expected a Job")) + } + + fn commit(&mut self) -> Result { + match self.job.as_mut() { + Some(job) => job.commit(), + None => Ok(()), + } + } + + fn can_submit(&self) -> Option { + self.job.as_ref().and_then(|job| job.can_submit()) + } +} + +#[versions(AGX)] +pub(crate) struct Queue { + dev: AsahiDevRef, + _sched: sched::Scheduler, + entity: sched::Entity, + vm: mmu::Vm, + q_vtx: Option, + q_frag: Option, + q_comp: Option, + fence_ctx: FenceContexts, + inner: QueueInner::ver, +} + +#[versions(AGX)] +pub(crate) struct QueueInner { + dev: AsahiDevRef, + ualloc: Arc>, + buffer: buffer::Buffer::ver, + gpu_context: Arc, + notifier_list: Arc>, + notifier: Arc>, + usc_exec_base: u64, + id: u64, + #[ver(V >= V13_0B4)] + counter: AtomicU64, +} + +#[versions(AGX)] +#[derive(Default)] +pub(crate) struct JobFence { + id: u64, + pending: AtomicU64, +} + +#[versions(AGX)] +impl JobFence::ver { + fn add_command(self: &FenceObject) { + self.pending.fetch_add(1, Ordering::Relaxed); + } + + fn command_complete(self: &FenceObject) { + let remain = self.pending.fetch_sub(1, Ordering::Relaxed) - 1; + mod_pr_debug!( + "JobFence[{}]: Command complete (remain: {})\n", + self.id, + remain + ); + if remain == 0 { + mod_pr_debug!("JobFence[{}]: Signaling\n", self.id); + if self.signal().is_err() { + pr_err!("JobFence[{}]: Fence signal failed\n", self.id); + } + } + } +} + +#[versions(AGX)] +#[vtable] +impl dma_fence::FenceOps for JobFence::ver { + fn get_driver_name<'a>(self: &'a FenceObject) -> &'a CStr { + c_str!("asahi") + } + fn get_timeline_name<'a>(self: &'a FenceObject) -> &'a CStr { + c_str!("queue") + } +} + +#[versions(AGX)] +pub(crate) struct QueueJob { + dev: AsahiDevRef, + vm_bind: mmu::VmBind, + op_guard: Option, + sj_vtx: Option, + sj_frag: Option, + sj_comp: Option, + fence: UserFence, + notifier: Arc>, + notification_count: u32, + did_run: bool, + id: u64, +} + +#[versions(AGX)] +impl QueueJob::ver { + fn get_vtx(&mut self) -> Result<&mut workqueue::Job::ver> { + self.sj_vtx + .as_mut() + .ok_or_else(|| { + cls_pr_debug!(Errors, "No vertex queue\n"); + EINVAL + })? + .get() + } + fn get_frag(&mut self) -> Result<&mut workqueue::Job::ver> { + self.sj_frag + .as_mut() + .ok_or_else(|| { + cls_pr_debug!(Errors, "No fragment queue\n"); + EINVAL + })? + .get() + } + fn get_comp(&mut self) -> Result<&mut workqueue::Job::ver> { + self.sj_comp + .as_mut() + .ok_or_else(|| { + cls_pr_debug!(Errors, "No compute queue\n"); + EINVAL + })? + .get() + } + + fn commit(&mut self) -> Result { + mod_dev_dbg!(self.dev, "QueueJob {}: Committing\n", self.id); + + self.sj_vtx.as_mut().map(|a| a.commit()).unwrap_or(Ok(()))?; + self.sj_frag + .as_mut() + .map(|a| a.commit()) + .unwrap_or(Ok(()))?; + self.sj_comp.as_mut().map(|a| a.commit()).unwrap_or(Ok(())) + } +} + +#[versions(AGX)] +impl sched::JobImpl for QueueJob::ver { + fn prepare(job: &mut sched::Job) -> Option { + mod_dev_dbg!(job.dev, "QueueJob {}: Checking runnability\n", job.id); + + if let Some(sj) = job.sj_vtx.as_ref() { + if let Some(fence) = sj.can_submit() { + mod_dev_dbg!( + job.dev, + "QueueJob {}: Blocking due to vertex queue full\n", + job.id + ); + return Some(fence); + } + } + if let Some(sj) = job.sj_frag.as_ref() { + if let Some(fence) = sj.can_submit() { + mod_dev_dbg!( + job.dev, + "QueueJob {}: Blocking due to fragment queue full\n", + job.id + ); + return Some(fence); + } + } + if let Some(sj) = job.sj_comp.as_ref() { + if let Some(fence) = sj.can_submit() { + mod_dev_dbg!( + job.dev, + "QueueJob {}: Blocking due to compute queue full\n", + job.id + ); + return Some(fence); + } + } + None + } + + #[allow(unused_assignments)] + fn run(job: &mut sched::Job) -> Result> { + mod_dev_dbg!(job.dev, "QueueJob {}: Running Job\n", job.id); + + // We can only increase the notifier threshold here, now that we are + // actually running the job. We cannot increase it while queueing the + // job without introducing subtle race conditions. Suppose we did, as + // early versions of drm/asahi did: + // + // 1. When processing the ioctl submit, a job is queued to drm_sched. + // Incorrectly, the notifier threshold is increased, gating firmware + // events. + // 2. When DRM schedules an event, the hardware is kicked. + // 3. When the number of processed jobs equals the threshold, the + // firmware signals the complete event to the kernel + // 4. When the kernel gets a complete event, we signal the out-syncs. + // + // Does that work? There are a few scenarios. + // + // 1. There is nothing else ioctl submitted before the job completes. + // The job is scheduled, completes, and signals immediately. + // Everything works. + // 2. There is nontrivial sync across different queues. Since each queue + // has a separate own notifier threshold, submitting one does not + // block scheduling of the other. Everything works the way you'd + // expect. drm/sched handles the wait/signal ordering. + // 3. Two ioctls are submitted back-to-back. The first signals a fence + // that the second waits on. Due to the notifier threshold increment, + // the first job's completion event is deferred. But in good + // conditions, drm/sched will schedule the second submit anyway + // because it kills the pointless intra-queue sync. Then both + // commands execute and are signalled together. + // 4. Two ioctls are submitted back-to-back as above, but conditions are + // bad. Reporting completion of the first job is still masked by the + // notifier threshold, but the intra-queue fences are not optimized + // out in drm/sched... drm/sched doesn't schedule the second job + // until the first is signalled, but the first isn't signalled until + // the second is completed, but the second can't complete until it's + // scheduled. We hang! + // + // In good conditions, everything works properly and/or we win the race + // to mask the issue. So the issue here is challenging to hit. + // Nevertheless, we do need to get it right. + // + // The intention with drm/sched is that jobs that are not yet scheduled + // are "invisible" to the firmware. Incrementing the notifier threshold + // earlier than this violates that which leads to circles like the + // above. Deferring the increment to submit solves the race. + job.notifier.threshold.with(|raw, _inner| { + raw.increase(job.notification_count); + }); + + let gpu = match (*job.dev) + .gpu + .clone() + .arc_as_any() + .downcast::() + { + Ok(gpu) => gpu, + Err(_) => { + dev_crit!(job.dev.as_ref(), "GpuManager mismatched with QueueJob!\n"); + return Err(EIO); + } + }; + + if job.op_guard.is_none() { + job.op_guard = Some(gpu.start_op()?); + } + + // First submit all the commands for each queue. This can fail. + + let mut frag_job = None; + let mut frag_sub = None; + if let Some(sj) = job.sj_frag.as_mut() { + frag_job = sj.job.take(); + if let Some(wqjob) = frag_job.as_mut() { + mod_dev_dbg!(job.dev, "QueueJob {}: Submit fragment\n", job.id); + frag_sub = Some(wqjob.submit()?); + } + } + + let mut vtx_job = None; + let mut vtx_sub = None; + if let Some(sj) = job.sj_vtx.as_mut() { + vtx_job = sj.job.take(); + if let Some(wqjob) = vtx_job.as_mut() { + mod_dev_dbg!(job.dev, "QueueJob {}: Submit vertex\n", job.id); + vtx_sub = Some(wqjob.submit()?); + } + } + + let mut comp_job = None; + let mut comp_sub = None; + if let Some(sj) = job.sj_comp.as_mut() { + comp_job = sj.job.take(); + if let Some(wqjob) = comp_job.as_mut() { + mod_dev_dbg!(job.dev, "QueueJob {}: Submit compute\n", job.id); + comp_sub = Some(wqjob.submit()?); + } + } + + // Now we fully commit to running the job + mod_dev_dbg!(job.dev, "QueueJob {}: Run fragment\n", job.id); + frag_sub.map(|a| gpu.run_job(a)).transpose()?; + + mod_dev_dbg!(job.dev, "QueueJob {}: Run vertex\n", job.id); + vtx_sub.map(|a| gpu.run_job(a)).transpose()?; + + mod_dev_dbg!(job.dev, "QueueJob {}: Run compute\n", job.id); + comp_sub.map(|a| gpu.run_job(a)).transpose()?; + + mod_dev_dbg!(job.dev, "QueueJob {}: Drop compute job\n", job.id); + core::mem::drop(comp_job); + mod_dev_dbg!(job.dev, "QueueJob {}: Drop vertex job\n", job.id); + core::mem::drop(vtx_job); + mod_dev_dbg!(job.dev, "QueueJob {}: Drop fragment job\n", job.id); + core::mem::drop(frag_job); + + job.did_run = true; + + Ok(Some(Fence::from_fence(&job.fence))) + } + + fn timed_out(job: &mut sched::Job) -> sched::Status { + // FIXME: Handle timeouts properly + dev_err!( + job.dev.as_ref(), + "QueueJob {}: Job timed out on the DRM scheduler, things will probably break (ran: {})\n", + job.id, job.did_run + ); + sched::Status::NoDevice + } + + fn cancel(job: &mut sched::Job) { + dev_info!( + job.dev.as_ref(), + "QueueJob {}: Job canceled on DRM scheduler teardown\n", + job.id + ); + } +} + +#[versions(AGX)] +impl Drop for QueueJob::ver { + fn drop(&mut self) { + mod_dev_dbg!(self.dev, "QueueJob {}: Dropping\n", self.id); + } +} + +static QUEUE_NAME: &CStr = c_str!("asahi_fence"); +static QUEUE_CLASS_KEY: Pin<&LockClassKey> = kernel::static_lock_class!(); + +#[versions(AGX)] +impl Queue::ver { + /// Create a new user queue. + #[allow(clippy::too_many_arguments)] + pub(crate) fn new( + dev: &AsahiDevice, + vm: mmu::Vm, + alloc: &mut gpu::KernelAllocators, + ualloc: Arc>, + ualloc_priv: Arc>, + event_manager: Arc, + mgr: &buffer::BufferManager::ver, + id: u64, + priority: u32, + usc_exec_base: u64, + ) -> Result { + mod_dev_dbg!(dev, "[Queue {}] Creating queue\n", id); + + // Must be shared, no cache management on this one! + let mut notifier_list = alloc.shared.new_default::()?; + + let self_ptr = notifier_list.weak_pointer(); + notifier_list.with_mut(|raw, _inner| { + raw.list_head.next = Some(inner_weak_ptr!(self_ptr, list_head)); + }); + + let threshold = alloc.shared.new_default::()?; + + let notifier: Arc> = Arc::new( + alloc.private.new_init( + /*try_*/ init!(fw::event::Notifier::ver { threshold }), + |inner, _p| { + try_init!(fw::event::raw::Notifier::ver { + threshold: inner.threshold.gpu_pointer(), + generation: AtomicU32::new(id as u32), + cur_count: AtomicU32::new(0), + unk_10: AtomicU32::new(0x50), + state: Default::default() + }) + }, + )?, + GFP_KERNEL, + )?; + + // Priorities are handled by the AGX scheduler, there is no meaning within a + // per-queue scheduler. Use a single run queue wth Kernel priority. + let sched = + sched::Scheduler::new(dev.as_ref(), 1, WQ_SIZE, 0, 100000, c_str!("asahi_sched"))?; + let entity = sched::Entity::new(&sched, sched::Priority::Kernel)?; + + let buffer = + buffer::Buffer::ver::new(&*(*dev).gpu, alloc, ualloc.clone(), ualloc_priv, mgr)?; + + let mut ret = Queue::ver { + dev: dev.into(), + _sched: sched, + entity, + vm, + q_vtx: None, + q_frag: None, + q_comp: None, + fence_ctx: FenceContexts::new(1, QUEUE_NAME, QUEUE_CLASS_KEY)?, + inner: QueueInner::ver { + dev: dev.into(), + ualloc, + gpu_context: Arc::new( + workqueue::GpuContext::new(dev, alloc, buffer.any_ref())?, + GFP_KERNEL, + )?, + + buffer, + notifier_list: Arc::new(notifier_list, GFP_KERNEL)?, + notifier, + usc_exec_base, + id, + #[ver(V >= V13_0B4)] + counter: AtomicU64::new(0), + }, + }; + + // Rendering structures + let tvb_blocks = *module_parameters::initial_tvb_size.value(); + + ret.inner.buffer.ensure_blocks(tvb_blocks)?; + + ret.q_vtx = Some(SubQueue::ver { + wq: workqueue::WorkQueue::ver::new( + dev, + alloc, + event_manager.clone(), + ret.inner.gpu_context.clone(), + ret.inner.notifier_list.clone(), + channel::PipeType::Vertex, + id, + priority, + WQ_SIZE, + )?, + }); + + ret.q_frag = Some(SubQueue::ver { + wq: workqueue::WorkQueue::ver::new( + dev, + alloc, + event_manager.clone(), + ret.inner.gpu_context.clone(), + ret.inner.notifier_list.clone(), + channel::PipeType::Fragment, + id, + priority, + WQ_SIZE, + )?, + }); + + // Compute structures + ret.q_comp = Some(SubQueue::ver { + wq: workqueue::WorkQueue::ver::new( + dev, + alloc, + event_manager, + ret.inner.gpu_context.clone(), + ret.inner.notifier_list.clone(), + channel::PipeType::Compute, + id, + priority, + WQ_SIZE, + )?, + }); + + mod_dev_dbg!(dev, "[Queue {}] Queue created\n", id); + Ok(ret) + } +} + +const SQ_RENDER: usize = 0; +const SQ_COMPUTE: usize = 1; +const SQ_COUNT: usize = 2; + +// SAFETY: All bit patterns are valid by construction. +unsafe impl AnyBitPattern for uapi::drm_asahi_cmd_header {} +unsafe impl AnyBitPattern for uapi::drm_asahi_cmd_render {} +unsafe impl AnyBitPattern for uapi::drm_asahi_cmd_compute {} +unsafe impl AnyBitPattern for uapi::drm_asahi_attachment {} + +fn build_attachments(reader: &mut Reader<'_>, size: usize) -> Result { + const STRIDE: usize = core::mem::size_of::(); + let count = size / STRIDE; + + if count > microseq::MAX_ATTACHMENTS { + return Err(EINVAL); + } + + let mut attachments: microseq::Attachments = Default::default(); + attachments.count = count as u32; + + for i in 0..count { + let att: uapi::drm_asahi_attachment = reader.read()?; + + if att.flags != 0 || att.pad != 0 { + return Err(EINVAL); + } + + // Some kind of power-of-2 exponent related to attachment size, in + // bounds [1, 6]? We don't know what this is exactly yet. + let unk_e = 1; + + let cache_lines = (att.size + 127) >> 7; + attachments.list[i as usize] = microseq::Attachment { + address: U64(att.pointer), + size: cache_lines.try_into()?, + unk_c: 0x17, + unk_e: unk_e as u16, + }; + } + + Ok(attachments) +} + +#[versions(AGX)] +impl Queue for Queue::ver { + fn submit( + &mut self, + id: u64, + mut syncs: KVec, + in_sync_count: usize, + cmdbuf_raw: &[u8], + objects: Pin<&xarray::XArray>>, + ) -> Result { + let gpu = match (*self.dev) + .gpu + .clone() + .arc_as_any() + .downcast::() + { + Ok(gpu) => gpu, + Err(_) => { + dev_crit!(self.dev.as_ref(), "GpuManager mismatched with JobImpl!\n"); + return Err(EIO); + } + }; + + mod_dev_dbg!(self.dev, "[Submission {}] Submit job\n", id); + + if gpu.is_crashed() { + dev_err!( + self.dev.as_ref(), + "[Submission {}] GPU is crashed, cannot submit\n", + id + ); + return Err(ENODEV); + } + + let op_guard = if in_sync_count > 0 { + Some(gpu.start_op()?) + } else { + None + }; + + let mut events: [KVec>; SQ_COUNT] = + Default::default(); + + events[SQ_RENDER].push( + self.q_frag.as_ref().and_then(|a| a.wq.event_info()), + GFP_KERNEL, + )?; + events[SQ_COMPUTE].push( + self.q_comp.as_ref().and_then(|a| a.wq.event_info()), + GFP_KERNEL, + )?; + + let vm_bind = gpu.bind_vm(&self.vm)?; + let vm_slot = vm_bind.slot(); + + mod_dev_dbg!(self.dev, "[Submission {}] Creating job\n", id); + + // FIXME: I think this can violate the fence seqno ordering contract. + // If we have e.g. a render submission with no barriers and then a compute submission + // with no barriers, it's possible for the compute submission to complete first, and + // therefore its fence. Maybe we should have separate fence contexts for render + // and compute, and then do a ? (Vert+frag should be fine since there is no vert + // without frag, and frag always serializes.) + let fence: UserFence = self + .fence_ctx + .new_fence::( + 0, + JobFence::ver { + id, + pending: Default::default(), + }, + )? + .into(); + + let mut cmdbuf = Reader::new(cmdbuf_raw); + + // First, parse the headers to determine the number of compute/render + // commands. This will be used to determine when to flush stamps. + // + // We also use it to determine how many notifications the job will + // generate. We could calculate that in the second pass since we don't + // need until much later, but it's convenient to gather everything at + // the same time. + let mut nr_commands = 0; + let mut last_compute = 0; + let mut last_render = 0; + let mut nr_render = 0; + let mut nr_compute = 0; + + while !cmdbuf.is_empty() { + let header: uapi::drm_asahi_cmd_header = cmdbuf.read()?; + cmdbuf.skip(header.size as usize); + nr_commands += 1; + + match header.cmd_type as u32 { + uapi::drm_asahi_cmd_type_DRM_ASAHI_CMD_RENDER => { + last_compute = nr_commands; + nr_render += 1; + } + uapi::drm_asahi_cmd_type_DRM_ASAHI_CMD_COMPUTE => { + last_render = nr_commands; + nr_compute += 1; + } + _ => {} + } + } + + let mut job = self.entity.new_job( + 1, + QueueJob::ver { + dev: self.dev.clone(), + vm_bind, + op_guard, + sj_vtx: self + .q_vtx + .as_mut() + .map(|a| a.new_job(Fence::from_fence(&fence))), + sj_frag: self + .q_frag + .as_mut() + .map(|a| a.new_job(Fence::from_fence(&fence))), + sj_comp: self + .q_comp + .as_mut() + .map(|a| a.new_job(Fence::from_fence(&fence))), + fence, + notifier: self.inner.notifier.clone(), + + // Each render command generates 2 notifications: 1 for the + // vertex part, 1 for the fragment part. Each compute command + // generates 1 notification. Sum up to calculate the total + // notification count for the job. + notification_count: (2 * nr_render) + nr_compute, + + did_run: false, + id, + }, + )?; + + mod_dev_dbg!( + self.dev, + "[Submission {}] Adding {} in_syncs\n", + id, + in_sync_count + ); + for sync in syncs.drain(0..in_sync_count) { + if let Some(fence) = sync.fence { + job.add_dependency(fence)?; + } + } + + // Validate the number of hardware commands, ignoring software commands + let nr_hw_commands = nr_render + nr_compute; + if nr_hw_commands == 0 || nr_hw_commands > MAX_COMMANDS_PER_SUBMISSION { + cls_pr_debug!( + Errors, + "submit: Command count {} out of valid range [1, {}]\n", + nr_hw_commands, + MAX_COMMANDS_PER_SUBMISSION - 1 + ); + return Err(EINVAL); + } + + cmdbuf.rewind(); + + let mut command_index = 0; + let mut vertex_attachments: microseq::Attachments = Default::default(); + let mut fragment_attachments: microseq::Attachments = Default::default(); + let mut compute_attachments: microseq::Attachments = Default::default(); + + // Parse the full command buffer submitting as we go + while !cmdbuf.is_empty() { + let header: uapi::drm_asahi_cmd_header = cmdbuf.read()?; + let header_size = header.size as usize; + + // Pre-increment command index to match last_compute/last_render + command_index += 1; + + for (queue_idx, index) in [header.vdm_barrier, header.cdm_barrier].iter().enumerate() { + if *index == uapi::DRM_ASAHI_BARRIER_NONE as u16 { + continue; + } + if let Some(event) = events[queue_idx].get(*index as usize).ok_or_else(|| { + cls_pr_debug!(Errors, "Invalid barrier #{}: {}\n", queue_idx, index); + EINVAL + })? { + let mut alloc = gpu.alloc(); + let queue_job = match header.cmd_type as u32 { + uapi::drm_asahi_cmd_type_DRM_ASAHI_CMD_RENDER => job.get_vtx()?, + uapi::drm_asahi_cmd_type_DRM_ASAHI_CMD_COMPUTE => job.get_comp()?, + _ => return Err(EINVAL), + }; + mod_dev_dbg!(self.dev, "[Submission {}] Create Explicit Barrier\n", id); + let barrier = alloc.private.new_init( + pin_init::zeroed::(), + |_inner, _p| { + let queue_job = &queue_job; + try_init!(fw::workqueue::raw::Barrier { + tag: fw::workqueue::CommandType::Barrier, + wait_stamp: event.fw_stamp_pointer, + wait_value: event.value, + wait_slot: event.slot, + stamp_self: queue_job.event_info().value.next(), + uuid: 0xffffbbbb, + external_barrier: 0, + internal_barrier_type: 1, + padding: Default::default(), + }) + }, + )?; + mod_dev_dbg!(self.dev, "[Submission {}] Add Explicit Barrier\n", id); + queue_job.add(barrier, vm_slot)?; + } else { + assert!(*index == 0); + } + } + + match header.cmd_type as u32 { + uapi::drm_asahi_cmd_type_DRM_ASAHI_CMD_RENDER => { + let render: uapi::drm_asahi_cmd_render = cmdbuf.read_up_to(header_size)?; + + self.inner.submit_render( + &mut job, + &render, + &vertex_attachments, + &fragment_attachments, + objects, + id, + command_index == last_render, + )?; + events[SQ_RENDER].push( + Some( + job.sj_frag + .as_ref() + .expect("No frag queue?") + .job + .as_ref() + .expect("No frag job?") + .event_info(), + ), + GFP_KERNEL, + )?; + } + uapi::drm_asahi_cmd_type_DRM_ASAHI_CMD_COMPUTE => { + let compute: uapi::drm_asahi_cmd_compute = cmdbuf.read_up_to(header_size)?; + + self.inner.submit_compute( + &mut job, + &compute, + &compute_attachments, + objects, + id, + command_index == last_compute, + )?; + events[SQ_COMPUTE].push( + Some( + job.sj_comp + .as_ref() + .expect("No comp queue?") + .job + .as_ref() + .expect("No comp job?") + .event_info(), + ), + GFP_KERNEL, + )?; + } + uapi::drm_asahi_cmd_type_DRM_ASAHI_SET_VERTEX_ATTACHMENTS => { + vertex_attachments = build_attachments(&mut cmdbuf, header_size)?; + } + uapi::drm_asahi_cmd_type_DRM_ASAHI_SET_FRAGMENT_ATTACHMENTS => { + fragment_attachments = build_attachments(&mut cmdbuf, header_size)?; + } + uapi::drm_asahi_cmd_type_DRM_ASAHI_SET_COMPUTE_ATTACHMENTS => { + compute_attachments = build_attachments(&mut cmdbuf, header_size)?; + } + _ => { + cls_pr_debug!(Errors, "Unknown command type {}\n", header.cmd_type); + return Err(EINVAL); + } + } + } + + mod_dev_dbg!( + self.dev, + "Queue {}: Committing job {}\n", + self.inner.id, + job.id + ); + job.commit()?; + + mod_dev_dbg!(self.dev, "Queue {}: Arming job {}\n", self.inner.id, job.id); + let mut job = job.arm(); + let out_fence = job.fences().finished(); + mod_dev_dbg!( + self.dev, + "Queue {}: Pushing job {}\n", + self.inner.id, + job.id + ); + job.push(); + + mod_dev_dbg!( + self.dev, + "Queue {}: Adding {} out_syncs\n", + self.inner.id, + syncs.len() + ); + for mut sync in syncs { + if let Some(chain) = sync.chain_fence.take() { + sync.syncobj + .add_point(chain, &out_fence, sync.timeline_value); + } else { + sync.syncobj.replace_fence(Some(&out_fence)); + } + } + + Ok(()) + } +} + +#[versions(AGX)] +impl Drop for Queue::ver { + fn drop(&mut self) { + mod_dev_dbg!(self.dev, "[Queue {}] Dropping queue\n", self.inner.id); + } +} diff --git a/drivers/gpu/drm/asahi/queue/render.rs b/drivers/gpu/drm/asahi/queue/render.rs new file mode 100644 index 00000000000000..32273b2975b505 --- /dev/null +++ b/drivers/gpu/drm/asahi/queue/render.rs @@ -0,0 +1,1400 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +#![allow(clippy::unusual_byte_groupings)] + +//! Render work queue. +//! +//! A render queue consists of two underlying WorkQueues, one for vertex and one for fragment work. +//! This module is in charge of creating all of the firmware structures required to submit 3D +//! rendering work to the GPU, based on the userspace command buffer. + +use super::common; +use crate::alloc::Allocator; +use crate::debug::*; +use crate::fw::types::*; +use crate::gpu::GpuManager; +use crate::util::*; +use crate::{ + buffer, + file, + fw, + gpu, + microseq, // +}; +use crate::{ + inner_ptr, + inner_weak_ptr, // +}; +use core::sync::atomic::Ordering; +use kernel::dma_fence::RawDmaFence; +use kernel::drm::sched::Job; +use kernel::prelude::*; +use kernel::sync::Arc; +use kernel::uapi; +use kernel::xarray; + +const DEBUG_CLASS: DebugFlags = DebugFlags::Render; + +/// Tiling/Vertex control bit to disable using more than one GPU cluster. This results in decreased +/// throughput but also less latency, which is probably desirable for light vertex loads where the +/// overhead of clustering/merging would exceed the time it takes to just run the job on one +/// cluster. +const TILECTL_DISABLE_CLUSTERING: u32 = 1u32 << 0; + +#[versions(AGX)] +impl super::QueueInner::ver { + /// Get the appropriate tiling parameters for a given userspace command buffer. + fn get_tiling_params( + cmdbuf: &uapi::drm_asahi_cmd_render, + num_clusters: u32, + ) -> Result { + let width: u32 = cmdbuf.width_px as u32; + let height: u32 = cmdbuf.height_px as u32; + let layers: u32 = cmdbuf.layers as u32; + + if layers == 0 || layers > 2048 { + cls_pr_debug!(Errors, "Layer count invalid ({})\n", layers); + return Err(EINVAL); + } + + // This is overflow safe: all these calculations are done in u32. + // At 64Kx64K max dimensions above, this is 2**32 pixels max. + // In terms of tiles that are always larger than one pixel, + // this can never overflow. Note that real actual dimensions + // are limited to 16K * 16K below anyway. + // + // Once we multiply by the layer count, then we need to check + // for overflow or use u64. + + let tile_width = 32u32; + let tile_height = 32u32; + + let utile_width = cmdbuf.utile_width_px as u32; + let utile_height = cmdbuf.utile_height_px as u32; + + match (utile_width, utile_height) { + (32, 32) | (32, 16) | (16, 16) => (), + _ => { + cls_pr_debug!( + Errors, + "uTile size invalid ({} x {})\n", + utile_width, + utile_height + ); + return Err(EINVAL); + } + }; + + let utiles_per_tile_x = tile_width / utile_width; + let utiles_per_tile_y = tile_height / utile_height; + + let utiles_per_tile = utiles_per_tile_x * utiles_per_tile_y; + + let tiles_x = width.div_ceil(tile_width); + let tiles_y = height.div_ceil(tile_height); + let tiles = tiles_x * tiles_y; + + let mtiles_x = 4u32; + let mtiles_y = 4u32; + let mtiles = mtiles_x * mtiles_y; + + let tiles_per_mtile_x = align(tiles_x.div_ceil(mtiles_x), 4); + let tiles_per_mtile_y = align(tiles_y.div_ceil(mtiles_y), 4); + let tiles_per_mtile = tiles_per_mtile_x * tiles_per_mtile_y; + + let mtile_x1 = tiles_per_mtile_x; + let mtile_x2 = 2 * tiles_per_mtile_x; + let mtile_x3 = 3 * tiles_per_mtile_x; + + let mtile_y1 = tiles_per_mtile_y; + let mtile_y2 = 2 * tiles_per_mtile_y; + let mtile_y3 = 3 * tiles_per_mtile_y; + + let rgn_entry_size = 5; + // Macrotile stride in 32-bit words + let rgn_size = align(rgn_entry_size * tiles_per_mtile * utiles_per_tile, 4) / 4; + let tilemap_size = (4 * rgn_size * mtiles) as usize * layers as usize; + + let tpc_entry_size = 8; + // TPC stride in 32-bit words + let tpc_mtile_stride = tpc_entry_size * utiles_per_tile * tiles_per_mtile / 4; + let tpc_size = + (4 * tpc_mtile_stride * mtiles) as usize * layers as usize * num_clusters as usize; + + // No idea where this comes from, but it fits what macOS does... + // GUESS: Number of 32K heap blocks to fit a 5-byte region header/pointer per tile? + // That would make a ton of sense... + let meta1_layer_stride = if num_clusters > 1 { + (align(tiles_x, 2) * align(tiles_y, 4) * utiles_per_tile).div_ceil(0x1980) + } else { + 0 + }; + + let mut min_tvb_blocks = align((tiles_x * tiles_y).div_ceil(128), 8); + + if num_clusters > 1 { + min_tvb_blocks = min_tvb_blocks.max(7 + 2 * layers); + } + + Ok(buffer::TileInfo { + tiles_x, + tiles_y, + tiles, + utile_width, + utile_height, + //mtiles_x, + //mtiles_y, + tiles_per_mtile_x, + tiles_per_mtile_y, + //tiles_per_mtile, + utiles_per_mtile_x: tiles_per_mtile_x * utiles_per_tile_x, + utiles_per_mtile_y: tiles_per_mtile_y * utiles_per_tile_y, + //utiles_per_mtile: tiles_per_mtile * utiles_per_tile, + tilemap_size, + tpc_size, + meta1_layer_stride, + #[ver(G < G14X)] + meta1_blocks: meta1_layer_stride * (cmdbuf.layers as u32), + #[ver(G >= G14X)] + meta1_blocks: meta1_layer_stride, + layermeta_size: if layers > 1 { 0x100 } else { 0 }, + min_tvb_blocks: min_tvb_blocks as usize, + params: fw::vertex::raw::TilingParameters { + rgn_size, + unk_4: 0x88, + ppp_ctrl: cmdbuf.ppp_ctrl, + x_max: (width - 1) as u16, + y_max: (height - 1) as u16, + te_screen: ((tiles_y - 1) << 12) | (tiles_x - 1), + te_mtile1: mtile_x3 | (mtile_x2 << 9) | (mtile_x1 << 18), + te_mtile2: mtile_y3 | (mtile_y2 << 9) | (mtile_y1 << 18), + tiles_per_mtile, + tpc_stride: tpc_mtile_stride, + unk_24: 0x100, + unk_28: if layers > 1 { + 0xe000 | (layers - 1) + } else { + 0x8000 + }, + helper_cfg: cmdbuf.vertex_helper.cfg, + __pad: Default::default(), + }, + }) + } + + /// Submit work to a render queue. + pub(super) fn submit_render( + &self, + job: &mut Job, + cmdbuf: &uapi::drm_asahi_cmd_render, + vertex_attachments: µseq::Attachments, + fragment_attachments: µseq::Attachments, + objects: Pin<&xarray::XArray>>, + id: u64, + flush_stamps: bool, + ) -> Result { + mod_dev_dbg!(self.dev, "[Submission {}] Render!\n", id); + + if cmdbuf.flags + & !(uapi::drm_asahi_render_flags_DRM_ASAHI_RENDER_VERTEX_SCRATCH + | uapi::drm_asahi_render_flags_DRM_ASAHI_RENDER_PROCESS_EMPTY_TILES + | uapi::drm_asahi_render_flags_DRM_ASAHI_RENDER_NO_VERTEX_CLUSTERING + | uapi::drm_asahi_render_flags_DRM_ASAHI_RENDER_DBIAS_IS_INT) as u32 + != 0 + { + cls_pr_debug!(Errors, "Invalid flags ({:#x})\n", cmdbuf.flags); + return Err(EINVAL); + } + + if cmdbuf.width_px == 0 + || cmdbuf.height_px == 0 + || cmdbuf.width_px > 16384 + || cmdbuf.height_px > 16384 + { + cls_pr_debug!( + Errors, + "Invalid dimensions ({}x{})\n", + cmdbuf.width_px, + cmdbuf.height_px + ); + return Err(EINVAL); + } + + let mut vtx_user_timestamps: fw::job::UserTimestamps = Default::default(); + let mut frg_user_timestamps: fw::job::UserTimestamps = Default::default(); + + vtx_user_timestamps.start = common::get_timestamp_object(objects, cmdbuf.ts_vtx.start)?; + vtx_user_timestamps.end = common::get_timestamp_object(objects, cmdbuf.ts_vtx.end)?; + frg_user_timestamps.start = common::get_timestamp_object(objects, cmdbuf.ts_frag.start)?; + frg_user_timestamps.end = common::get_timestamp_object(objects, cmdbuf.ts_frag.end)?; + + let gpu = match (*self.dev) + .gpu + .as_any() + .downcast_ref::() + { + Some(gpu) => gpu, + None => { + dev_crit!(self.dev.as_ref(), "GpuManager mismatched with Queue!\n"); + return Err(EIO); + } + }; + + let nclusters = gpu.get_dyncfg().id.num_clusters; + + // Can be set to false to disable clustering (for simpler jobs), but then the + // core masks below should be adjusted to cover a single rolling cluster. + let mut clustering = nclusters > 1; + + if debug_enabled(debug::DebugFlags::DisableClustering) + || cmdbuf.flags + & uapi::drm_asahi_render_flags_DRM_ASAHI_RENDER_NO_VERTEX_CLUSTERING as u32 + != 0 + { + clustering = false; + } + + #[ver(G != G14)] + let tiling_control = { + let render_cfg = gpu.get_cfg().render; + let mut tiling_control = render_cfg.tiling_control; + + if !clustering { + tiling_control |= TILECTL_DISABLE_CLUSTERING; + } + tiling_control + }; + + let mut alloc = gpu.alloc(); + let kalloc = &mut *alloc; + + // This sequence number increases per new client/VM? assigned to some slot, + // but it's unclear *which* slot... + let slot_client_seq: u8 = (self.id & 0xff) as u8; + + let tile_info = Self::get_tiling_params(&cmdbuf, if clustering { nclusters } else { 1 })?; + + let buffer = &self.buffer; + let notifier = self.notifier.clone(); + + let tvb_autogrown = buffer.auto_grow()?; + if tvb_autogrown { + let new_size = buffer.block_count() as usize; + cls_dev_dbg!( + TVBStats, + &self.dev, + "[Submission {}] TVB grew to {} bytes ({} blocks) due to overflows\n", + id, + new_size * buffer::BLOCK_SIZE, + new_size, + ); + } + + let tvb_grown = buffer.ensure_blocks(tile_info.min_tvb_blocks)?; + if tvb_grown { + cls_dev_dbg!( + TVBStats, + &self.dev, + "[Submission {}] TVB grew to {} bytes ({} blocks) due to dimensions ({}x{})\n", + id, + tile_info.min_tvb_blocks * buffer::BLOCK_SIZE, + tile_info.min_tvb_blocks, + cmdbuf.width_px, + cmdbuf.height_px + ); + } + + let scene = Arc::new(buffer.new_scene(kalloc, &tile_info)?, GFP_KERNEL)?; + + let vm_bind = job.vm_bind.clone(); + + mod_dev_dbg!( + self.dev, + "[Submission {}] VM slot = {}\n", + id, + vm_bind.slot() + ); + + let ev_vtx = job.get_vtx()?.event_info(); + let ev_frag = job.get_frag()?.event_info(); + + mod_dev_dbg!( + self.dev, + "[Submission {}] Vert event #{} -> {:#x?}\n", + id, + ev_vtx.slot, + ev_vtx.value.next(), + ); + mod_dev_dbg!( + self.dev, + "[Submission {}] Frag event #{} -> {:#x?}\n", + id, + ev_frag.slot, + ev_frag.value.next(), + ); + + let uuid_3d = 0; + let uuid_ta = 0; + + mod_dev_dbg!( + self.dev, + "[Submission {}] Vert UUID = {:#x?}\n", + id, + uuid_ta + ); + mod_dev_dbg!( + self.dev, + "[Submission {}] Frag UUID = {:#x?}\n", + id, + uuid_3d + ); + + let fence = job.fence.clone(); + let frag_job = job.get_frag()?; + + mod_dev_dbg!(self.dev, "[Submission {}] Create Barrier\n", id); + let barrier = kalloc.private.new_init( + pin_init::zeroed::(), + |_inner, _p| { + try_init!(fw::workqueue::raw::Barrier { + tag: fw::workqueue::CommandType::Barrier, + wait_stamp: ev_vtx.fw_stamp_pointer, + wait_value: ev_vtx.value.next(), + wait_slot: ev_vtx.slot, + stamp_self: ev_frag.value.next(), + uuid: uuid_3d, + external_barrier: 0, + internal_barrier_type: 0, + padding: Default::default(), + }) + }, + )?; + + mod_dev_dbg!(self.dev, "[Submission {}] Add Barrier\n", id); + frag_job.add(barrier, vm_bind.slot())?; + + let timestamps = Arc::new( + kalloc.shared.new_default::()?, + GFP_KERNEL, + )?; + + let unk1 = false; + + let mut tile_config: u64 = 0; + if !unk1 { + tile_config |= 0x280; + } + if cmdbuf.layers > 1 { + tile_config |= 1; + } + if cmdbuf.flags & uapi::drm_asahi_render_flags_DRM_ASAHI_RENDER_PROCESS_EMPTY_TILES as u32 + != 0 + { + tile_config |= 0x10000; + } + + let samples_log2 = match cmdbuf.samples { + 1 => 0, + 2 => 1, + 4 => 2, + _ => { + cls_pr_debug!(Errors, "Invalid sample count {}\n", cmdbuf.samples); + return Err(EINVAL); + } + }; + + let utile_config = ((tile_info.utile_width / 16) << 12) + | ((tile_info.utile_height / 16) << 14) + | samples_log2; + + // Calculate the number of 2KiB blocks to allocate per utile. This is + // just a bit of dimensional analysis. + let pixels_per_utile: u32 = + (cmdbuf.utile_width_px as u32) * (cmdbuf.utile_height_px as u32); + let samples_per_utile: u32 = pixels_per_utile << samples_log2; + let utile_size_bytes: u32 = (cmdbuf.sample_size_B as u32) * samples_per_utile; + let block_size_bytes: u32 = 2048; + let blocks_per_utile: u32 = utile_size_bytes.div_ceil(block_size_bytes); + + #[ver(G >= G14X)] + let frg_tilecfg = 0x0000000_00036011 + | (((tile_info.tiles_x - 1) as u64) << 44) + | (((tile_info.tiles_y - 1) as u64) << 53) + | (if unk1 { 0 } else { 0x20_00000000 }) + | (if cmdbuf.layers > 1 { 0x1_00000000 } else { 0 }) + | ((utile_config as u64 & 0xf000) << 28); + + // TODO: check + #[ver(V >= V13_0B4)] + let count_frag = self.counter.fetch_add(2, Ordering::Relaxed); + #[ver(V >= V13_0B4)] + let count_vtx = count_frag + 1; + + // Unknowns handling + + #[ver(G >= G14)] + let g14_unk = 0x4040404; + #[ver(G < G14)] + let g14_unk = 0; + #[ver(G < G14X)] + let frg_unk_140 = 0x8c60; + let frg_unk_158 = 0x1c; + #[ver(G >= G14)] + let load_bgobjvals = cmdbuf.isp_bgobjvals as u64; + #[ver(G < G14)] + let load_bgobjvals = cmdbuf.isp_bgobjvals as u64 | 0x400; + let reload_zlsctrl = cmdbuf.zls_ctrl; + let iogpu_unk54 = 0x3a0012006b0003; + let iogpu_unk56 = 1; + #[ver(G < G14)] + let tiling_control_2 = 0; + #[ver(G >= G14X)] + let tiling_control_2 = 4; + #[ver(G >= G14X)] + let vtx_unk_f0 = 0x1c; + #[ver(G < G14)] + let vtx_unk_f0 = 0x1c + (align(tile_info.meta1_blocks, 4) as u64); + let vtx_unk_118 = 0x1c; + + // DRM_ASAHI_RENDER_DBIAS_IS_INT chosen to match hardware bit. + let isp_ctl = 0xc000u32 + | (cmdbuf.flags & uapi::drm_asahi_render_flags_DRM_ASAHI_RENDER_DBIAS_IS_INT as u32); + + // Always allow preemption at the UAPI level + let no_preemption = false; + + mod_dev_dbg!(self.dev, "[Submission {}] Create Frag\n", id); + let frag = GpuObject::new_init_prealloc( + kalloc.gpu_ro.alloc_object()?, + |ptr: GpuWeakPointer| { + let scene = scene.clone(); + let notifier = notifier.clone(); + let vm_bind = vm_bind.clone(); + let timestamps = timestamps.clone(); + let private = &mut kalloc.private; + try_init!(fw::fragment::RunFragment::ver { + micro_seq: { + let mut builder = microseq::Builder::new(); + + let stats = inner_weak_ptr!( + gpu.initdata.runtime_pointers.stats.frag.weak_pointer(), + stats + ); + + let start_frag = builder.add(microseq::StartFragment::ver { + header: microseq::op::StartFragment::HEADER, + #[ver(G < G14X)] + job_params2: Some(inner_weak_ptr!(ptr, job_params2)), + #[ver(G < G14X)] + job_params1: Some(inner_weak_ptr!(ptr, job_params1)), + #[ver(G >= G14X)] + job_params1: None, + #[ver(G >= G14X)] + job_params2: None, + #[ver(G >= G14X)] + registers: inner_weak_ptr!(ptr, registers), + scene: scene.gpu_pointer(), + stats, + busy_flag: inner_weak_ptr!(ptr, busy_flag), + tvb_overflow_count: inner_weak_ptr!(ptr, tvb_overflow_count), + unk_pointer: inner_weak_ptr!(ptr, unk_pointee), + work_queue: ev_frag.info_ptr, + work_item: ptr, + vm_slot: vm_bind.slot(), + unk_50: 0x1, // fixed + event_generation: self.id as u32, + buffer_slot: scene.slot(), + sync_grow: 0, + event_seq: U64(ev_frag.event_seq), + unk_68: 0, + unk_758_flag: inner_weak_ptr!(ptr, unk_758_flag), + unk_job_buf: inner_weak_ptr!(ptr, unk_buf_0), + #[ver(V >= V13_3)] + unk_7c_0: U64(0), + unk_7c: 0, + unk_80: 0, + unk_84: unk1.into(), + uuid: uuid_3d, + attachments: *fragment_attachments, + padding: 0, + #[ver(V >= V13_0B4)] + counter: U64(count_frag), + #[ver(V >= V13_0B4)] + notifier_buf: inner_weak_ptr!(notifier.weak_pointer(), state.unk_buf), + })?; + + if frg_user_timestamps.any() { + builder.add(microseq::Timestamp::ver { + header: microseq::op::Timestamp::new(true), + command_time: inner_weak_ptr!(ptr, command_time), + ts_pointers: inner_weak_ptr!(ptr, timestamp_pointers), + update_ts: inner_weak_ptr!(ptr, timestamp_pointers.start_addr), + work_queue: ev_frag.info_ptr, + user_ts_pointers: inner_weak_ptr!(ptr, user_timestamp_pointers), + #[ver(V >= V13_0B4)] + unk_ts: inner_weak_ptr!(ptr, unk_ts), + uuid: uuid_3d, + unk_30_padding: 0, + })?; + } + + #[ver(G < G14X)] + builder.add(microseq::WaitForIdle { + header: microseq::op::WaitForIdle::new(microseq::Pipe::Fragment), + })?; + #[ver(G >= G14X)] + builder.add(microseq::WaitForIdle2 { + header: microseq::op::WaitForIdle2::HEADER, + })?; + + if frg_user_timestamps.any() { + builder.add(microseq::Timestamp::ver { + header: microseq::op::Timestamp::new(false), + command_time: inner_weak_ptr!(ptr, command_time), + ts_pointers: inner_weak_ptr!(ptr, timestamp_pointers), + update_ts: inner_weak_ptr!(ptr, timestamp_pointers.end_addr), + work_queue: ev_frag.info_ptr, + user_ts_pointers: inner_weak_ptr!(ptr, user_timestamp_pointers), + #[ver(V >= V13_0B4)] + unk_ts: inner_weak_ptr!(ptr, unk_ts), + uuid: uuid_3d, + unk_30_padding: 0, + })?; + } + + let off = builder.offset_to(start_frag); + builder.add(microseq::FinalizeFragment::ver { + header: microseq::op::FinalizeFragment::HEADER, + uuid: uuid_3d, + unk_8: 0, + fw_stamp: ev_frag.fw_stamp_pointer, + stamp_value: ev_frag.value.next(), + unk_18: 0, + scene: scene.weak_pointer(), + buffer: scene.weak_buffer_pointer(), + unk_2c: U64(1), + stats, + unk_pointer: inner_weak_ptr!(ptr, unk_pointee), + busy_flag: inner_weak_ptr!(ptr, busy_flag), + work_queue: ev_frag.info_ptr, + work_item: ptr, + vm_slot: vm_bind.slot(), + unk_60: 0, + unk_758_flag: inner_weak_ptr!(ptr, unk_758_flag), + #[ver(V >= V13_3)] + unk_6c_0: U64(0), + unk_6c: U64(0), + unk_74: U64(0), + unk_7c: U64(0), + unk_84: U64(0), + unk_8c: U64(0), + #[ver(G == G14 && V < V13_0B4)] + unk_8c_g14: U64(0), + restart_branch_offset: off, + has_attachments: (fragment_attachments.count > 0) as u32, + #[ver(V >= V13_0B4)] + unk_9c: Default::default(), + })?; + + builder.add(microseq::RetireStamp { + header: microseq::op::RetireStamp::HEADER, + })?; + + builder.build(private)? + }, + notifier, + scene, + vm_bind, + aux_fb: self.ualloc.lock().array_empty_tagged(0x8000, b"AXFB")?, + timestamps, + user_timestamps: frg_user_timestamps, + }) + }, + |inner, _ptr| { + let vm_slot = vm_bind.slot(); + let aux_fb_info = fw::fragment::raw::AuxFBInfo::ver { + isp_ctl: isp_ctl, + unk2: 0, + width: cmdbuf.width_px as u32, + height: cmdbuf.height_px as u32, + #[ver(V >= V13_0B4)] + unk3: U64(0x100000), + }; + + try_init!(fw::fragment::raw::RunFragment::ver { + tag: fw::workqueue::CommandType::RunFragment, + #[ver(V >= V13_0B4)] + counter: U64(count_frag), + vm_slot, + unk_8: 0, + microsequence: inner.micro_seq.gpu_pointer(), + microsequence_size: inner.micro_seq.len() as u32, + notifier: inner.notifier.gpu_pointer(), + buffer: inner.scene.buffer_pointer(), + scene: inner.scene.gpu_pointer(), + unk_buffer_buf: inner.scene.kernel_buffer_pointer(), + tvb_tilemap: inner.scene.tvb_tilemap_pointer(), + ppp_multisamplectl: U64(cmdbuf.ppp_multisamplectl), + samples: cmdbuf.samples as u32, + tiles_per_mtile_y: tile_info.tiles_per_mtile_y as u16, + tiles_per_mtile_x: tile_info.tiles_per_mtile_x as u16, + unk_50: U64(0), + unk_58: U64(0), + isp_merge_upper_x: F32::from_bits(cmdbuf.isp_merge_upper_x), + isp_merge_upper_y: F32::from_bits(cmdbuf.isp_merge_upper_y), + unk_68: U64(0), + tile_count: U64(tile_info.tiles as u64), + #[ver(G < G14X)] + job_params1 <- try_init!(fw::fragment::raw::JobParameters1::ver { + utile_config, + unk_4: 0, + bg: fw::fragment::raw::BackgroundProgram { + rsrc_spec: U64(cmdbuf.bg.rsrc_spec as u64), + address: U64(cmdbuf.bg.usc as u64), + }, + ppp_multisamplectl: U64(cmdbuf.ppp_multisamplectl), + isp_scissor_base: U64(cmdbuf.isp_scissor_base), + isp_dbias_base: U64(cmdbuf.isp_dbias_base), + isp_oclqry_base: U64(cmdbuf.isp_oclqry_base), + aux_fb_info, + isp_zls_pixels: U64(cmdbuf.isp_zls_pixels as u64), + zls_ctrl: U64(cmdbuf.zls_ctrl), + #[ver(G >= G14)] + unk_58_g14_0: U64(g14_unk), + #[ver(G >= G14)] + unk_58_g14_8: U64(0), + z_load: U64(cmdbuf.depth.base), + z_store: U64(cmdbuf.depth.base), + s_load: U64(cmdbuf.stencil.base), + s_store: U64(cmdbuf.stencil.base), + #[ver(G >= G14)] + unk_68_g14_0: Default::default(), + z_load_stride: U64(cmdbuf.depth.stride as u64), + z_store_stride: U64(cmdbuf.depth.stride as u64), + s_load_stride: U64(cmdbuf.stencil.stride as u64), + s_store_stride: U64(cmdbuf.stencil.stride as u64), + z_load_comp: U64(cmdbuf.depth.comp_base), + z_load_comp_stride: U64(cmdbuf.depth.comp_stride as u64), + z_store_comp: U64(cmdbuf.depth.comp_base), + z_store_comp_stride: U64(cmdbuf.depth.comp_stride as u64), + s_load_comp: U64(cmdbuf.stencil.comp_base), + s_load_comp_stride: U64(cmdbuf.stencil.comp_stride as u64), + s_store_comp: U64(cmdbuf.stencil.comp_base), + s_store_comp_stride: U64(cmdbuf.stencil.comp_stride as u64), + tvb_tilemap: inner.scene.tvb_tilemap_pointer(), + tvb_layermeta: inner.scene.tvb_layermeta_pointer(), + mtile_stride_dwords: U64((4 * tile_info.params.rgn_size as u64) << 24), + tvb_heapmeta: inner.scene.tvb_heapmeta_pointer(), + tile_config: U64(tile_config), + aux_fb: inner.aux_fb.gpu_pointer(), + unk_108: Default::default(), + usc_exec_base_isp: U64(self.usc_exec_base), + unk_140: U64(frg_unk_140), + helper_program: cmdbuf.fragment_helper.binary, + unk_14c: 0, + helper_arg: U64(cmdbuf.fragment_helper.data), + unk_158: U64(frg_unk_158), + unk_160: U64(0), + __pad: Default::default(), + #[ver(V < V13_0B4)] + __pad1: Default::default(), + }), + #[ver(G < G14X)] + job_params2 <- try_init!(fw::fragment::raw::JobParameters2 { + eot_rsrc_spec: cmdbuf.eot.rsrc_spec, + eot_usc: cmdbuf.eot.usc, + unk_8: 0x0, + unk_c: 0x0, + isp_merge_upper_x: F32::from_bits(cmdbuf.isp_merge_upper_x), + isp_merge_upper_y: F32::from_bits(cmdbuf.isp_merge_upper_y), + unk_18: U64(0x0), + utiles_per_mtile_y: tile_info.utiles_per_mtile_y as u16, + utiles_per_mtile_x: tile_info.utiles_per_mtile_x as u16, + unk_24: 0x0, + tile_counts: ((tile_info.tiles_y - 1) << 12) | (tile_info.tiles_x - 1), + tib_blocks: blocks_per_utile, + isp_bgobjdepth: cmdbuf.isp_bgobjdepth, + // TODO: does this flag need to be exposed to userspace? + isp_bgobjvals: load_bgobjvals as u32, + unk_38: 0x0, + unk_3c: 0x1, + helper_cfg: cmdbuf.fragment_helper.cfg, + __pad: Default::default(), + }), + #[ver(G >= G14X)] + registers: fw::job::raw::RegisterArray::new( + inner_weak_ptr!(_ptr, registers.registers), + |r| { + r.add(0x1739, 1); + r.add(0x10009, utile_config.into()); + r.add(0x15379, cmdbuf.eot.rsrc_spec.into()); + r.add(0x15381, cmdbuf.eot.usc.into()); + r.add(0x15369, cmdbuf.bg.rsrc_spec.into()); + r.add(0x15371, cmdbuf.bg.usc.into()); + r.add(0x15131, cmdbuf.isp_merge_upper_x.into()); + r.add(0x15139, cmdbuf.isp_merge_upper_y.into()); + r.add(0x100a1, 0); + r.add(0x15069, 0); + r.add(0x15071, 0); // pointer + r.add(0x16058, 0); + r.add(0x10019, cmdbuf.ppp_multisamplectl); + let isp_mtile_size = (tile_info.utiles_per_mtile_y + | (tile_info.utiles_per_mtile_x << 16)) + .into(); + r.add(0x100b1, isp_mtile_size); // ISP_MTILE_SIZE + r.add(0x16030, isp_mtile_size); // ISP_MTILE_SIZE + r.add( + 0x100d9, + (((tile_info.tiles_y - 1) << 12) | (tile_info.tiles_x - 1)).into(), + ); // TE_SCREEN + r.add(0x16098, inner.scene.tvb_heapmeta_pointer().into()); + r.add(0x15109, cmdbuf.isp_scissor_base); // ISP_SCISSOR_BASE + r.add(0x15101, cmdbuf.isp_dbias_base); // ISP_DBIAS_BASE + r.add(0x15021, isp_ctl.into()); // aux_fb_info.unk_1 + r.add( + 0x15211, + ((cmdbuf.height_px as u64) << 32) | cmdbuf.width_px as u64, + ); // aux_fb_info.{width, heigh + r.add(0x15049, 0x100000); // s2.aux_fb_info.unk3 + r.add(0x10051, blocks_per_utile.into()); // s1.unk_2c + r.add(0x15321, cmdbuf.isp_zls_pixels.into()); // ISP_ZLS_PIXELS + r.add(0x15301, cmdbuf.isp_bgobjdepth.into()); // ISP_BGOBJDEPTH + r.add(0x15309, load_bgobjvals); // ISP_BGOBJVALS + r.add(0x15311, cmdbuf.isp_oclqry_base); // ISP_OCLQRY_BASE + r.add(0x15319, cmdbuf.zls_ctrl); // ISP_ZLSCTL + r.add(0x15349, g14_unk); // s2.unk_58_g14_0 + r.add(0x15351, 0); // s2.unk_58_g14_8 + r.add(0x15329, cmdbuf.depth.base); // ISP_ZLOAD_BASE + r.add(0x15331, cmdbuf.depth.base); // ISP_ZSTORE_BASE + r.add(0x15339, cmdbuf.stencil.base); // ISP_STENCIL_LOAD_BASE + r.add(0x15341, cmdbuf.stencil.base); // ISP_STENCIL_STORE_BASE + r.add(0x15231, 0); + r.add(0x15221, 0); + r.add(0x15239, 0); + r.add(0x15229, 0); + r.add(0x15401, cmdbuf.depth.stride as u64); // load + r.add(0x15421, cmdbuf.depth.stride as u64); // store + r.add(0x15409, cmdbuf.stencil.stride as u64); // load + r.add(0x15429, cmdbuf.stencil.stride as u64); + r.add(0x153c1, cmdbuf.depth.comp_base); // load + r.add(0x15411, cmdbuf.depth.comp_stride as u64); // load + r.add(0x153c9, cmdbuf.depth.comp_base); // store + r.add(0x15431, cmdbuf.depth.comp_stride as u64); // store + r.add(0x153d1, cmdbuf.stencil.comp_base); // load + r.add(0x15419, cmdbuf.stencil.comp_stride as u64); // load + r.add(0x153d9, cmdbuf.stencil.comp_base); // store + r.add(0x15439, cmdbuf.stencil.comp_stride as u64); // store + r.add(0x16429, inner.scene.tvb_tilemap_pointer().into()); + r.add(0x16060, inner.scene.tvb_layermeta_pointer().into()); + r.add(0x16431, (4 * tile_info.params.rgn_size as u64) << 24); // ISP_RGN? + r.add(0x10039, tile_config); // tile_config ISP_CTL? + r.add(0x16451, 0x0); // ISP_RENDER_ORIGIN + r.add(0x11821, cmdbuf.fragment_helper.binary.into()); + r.add(0x11829, cmdbuf.fragment_helper.data); + r.add(0x11f79, cmdbuf.fragment_helper.cfg.into()); + r.add(0x15359, 0); + r.add(0x10069, self.usc_exec_base); // frag; USC_EXEC_BASE_ISP + r.add(0x16020, 0); + r.add(0x16461, inner.aux_fb.gpu_pointer().into()); + r.add(0x16090, inner.aux_fb.gpu_pointer().into()); + r.add(0x120a1, frg_unk_158); + r.add(0x160a8, 0); + r.add(0x16068, frg_tilecfg); + r.add(0x160b8, 0x0); + /* + r.add(0x10201, 0x100); // Some kind of counter?? Does this matter? + r.add(0x10428, 0x100); // Some kind of counter?? Does this matter? + r.add(0x1c838, 1); // ? + r.add(0x1ca28, 0x1502960f00); // ?? + r.add(0x1731, 0x1); // ?? + */ + } + ), + job_params3 <- try_init!(fw::fragment::raw::JobParameters3::ver { + isp_dbias_base: fw::fragment::raw::ArrayAddr { + ptr: U64(cmdbuf.isp_dbias_base), + unk_padding: U64(0), + }, + isp_scissor_base: fw::fragment::raw::ArrayAddr { + ptr: U64(cmdbuf.isp_scissor_base), + unk_padding: U64(0), + }, + isp_oclqry_base: U64(cmdbuf.isp_oclqry_base), + unk_118: U64(0x0), + unk_120: Default::default(), + unk_partial_bg: fw::fragment::raw::BackgroundProgram { + rsrc_spec: U64(cmdbuf.partial_bg.rsrc_spec as u64), + address: U64(cmdbuf.partial_bg.usc as u64), + }, + unk_258: U64(0), + unk_260: U64(0), + unk_268: U64(0), + unk_270: U64(0), + partial_bg: fw::fragment::raw::BackgroundProgram { + rsrc_spec: U64(cmdbuf.partial_bg.rsrc_spec as u64), + address: U64(cmdbuf.partial_bg.usc as u64), + }, + zls_ctrl: U64(reload_zlsctrl), + unk_290: U64(g14_unk), + z_load: U64(cmdbuf.depth.base), + z_partial_stride: U64(cmdbuf.depth.stride as u64), + z_partial_comp_stride: U64(cmdbuf.depth.comp_stride as u64), + z_store: U64(cmdbuf.depth.base), + z_partial: U64(cmdbuf.depth.base), + z_partial_comp: U64(cmdbuf.depth.comp_base), + s_load: U64(cmdbuf.stencil.base), + s_partial_stride: U64(cmdbuf.stencil.stride as u64), + s_partial_comp_stride: U64(cmdbuf.stencil.comp_stride as u64), + s_store: U64(cmdbuf.stencil.base), + s_partial: U64(cmdbuf.stencil.base), + s_partial_comp: U64(cmdbuf.stencil.comp_base), + unk_2f8: Default::default(), + tib_blocks: blocks_per_utile, + unk_30c: 0x0, + aux_fb_info, + tile_config: U64(tile_config), + unk_328_padding: Default::default(), + unk_partial_eot: fw::fragment::raw::EotProgram::new( + cmdbuf.partial_eot.rsrc_spec, + cmdbuf.partial_eot.usc + ), + partial_eot: fw::fragment::raw::EotProgram::new( + cmdbuf.partial_eot.rsrc_spec, + cmdbuf.partial_eot.usc + ), + isp_bgobjdepth: cmdbuf.isp_bgobjdepth, + isp_bgobjvals: cmdbuf.isp_bgobjvals, + sample_size: cmdbuf.sample_size_B as u32, + unk_37c: 0x0, + unk_380: U64(0x0), + unk_388: U64(0x0), + #[ver(V >= V13_0B4)] + unk_390_0: U64(0x0), + isp_zls_pixels: U64(cmdbuf.isp_zls_pixels as u64), + }), + unk_758_flag: 0, + unk_75c_flag: 0, + unk_buf: Default::default(), + busy_flag: 0, + tvb_overflow_count: 0, + unk_878: 0, + encoder_params <- try_init!(fw::job::raw::EncoderParams { + // Maybe set when reloading z/s? + unk_8: 0, + sync_grow: 0, + unk_10: 0x0, // fixed + encoder_id: 0, + unk_18: 0x0, // fixed + unk_mask: 0xffffffffu32, + sampler_array: U64(cmdbuf.sampler_heap), + sampler_count: cmdbuf.sampler_count as u32, + sampler_max: (cmdbuf.sampler_count as u32) + 1, + }), + process_empty_tiles: (cmdbuf.flags + & uapi::drm_asahi_render_flags_DRM_ASAHI_RENDER_PROCESS_EMPTY_TILES as u32 + != 0) as u32, + // TODO: needs to be investigated + no_clear_pipeline_textures: 1, + // TODO: needs to be investigated + msaa_zs: 0, + unk_pointee: 0, + #[ver(V >= V13_3)] + unk_v13_3: 0, + meta <- try_init!(fw::job::raw::JobMeta { + unk_0: 0, + unk_2: 0, + no_preemption: no_preemption as u8, + stamp: ev_frag.stamp_pointer, + fw_stamp: ev_frag.fw_stamp_pointer, + stamp_value: ev_frag.value.next(), + stamp_slot: ev_frag.slot, + evctl_index: 0, // fixed + flush_stamps: flush_stamps as u32, + uuid: uuid_3d, + event_seq: ev_frag.event_seq as u32, + }), + unk_after_meta: unk1.into(), + unk_buf_0: U64(0), + unk_buf_8: U64(0), + #[ver(G < G14X)] + unk_buf_10: U64(1), + #[ver(G >= G14X)] + unk_buf_10: U64(0), + command_time: U64(0), + timestamp_pointers <- try_init!(fw::job::raw::TimestampPointers { + start_addr: Some(inner_ptr!(inner.timestamps.gpu_pointer(), frag.start)), + end_addr: Some(inner_ptr!(inner.timestamps.gpu_pointer(), frag.end)), + }), + user_timestamp_pointers: inner.user_timestamps.pointers()?, + client_sequence: slot_client_seq, + pad_925: Default::default(), + unk_928: 0, + unk_92c: 0, + #[ver(V >= V13_0B4)] + unk_ts: U64(0), + #[ver(V >= V13_0B4)] + unk_92d_8: Default::default(), + }) + }, + )?; + + mod_dev_dbg!(self.dev, "[Submission {}] Add Frag\n", id); + fence.add_command(); + + frag_job.add_cb(frag, vm_bind.slot(), move |error| { + if let Some(err) = error { + fence.set_error(err.into()); + } + + fence.command_complete(); + })?; + + let fence = job.fence.clone(); + let vtx_job = job.get_vtx()?; + + if scene.rebind() || tvb_grown || tvb_autogrown { + mod_dev_dbg!(self.dev, "[Submission {}] Create Bind Buffer\n", id); + let bind_buffer = kalloc.private.new_init( + { + let scene = scene.clone(); + try_init!(fw::buffer::InitBuffer::ver { scene }) + }, + |inner, _ptr| { + let vm_slot = vm_bind.slot(); + try_init!(fw::buffer::raw::InitBuffer::ver { + tag: fw::workqueue::CommandType::InitBuffer, + vm_slot, + buffer_slot: inner.scene.slot(), + unk_c: 0, + block_count: buffer.block_count(), + buffer: inner.scene.buffer_pointer(), + stamp_value: ev_vtx.value.next(), + }) + }, + )?; + + mod_dev_dbg!(self.dev, "[Submission {}] Add Bind Buffer\n", id); + vtx_job.add(bind_buffer, vm_bind.slot())?; + } + + mod_dev_dbg!(self.dev, "[Submission {}] Create Vertex\n", id); + let vtx = GpuObject::new_init_prealloc( + kalloc.gpu_ro.alloc_object()?, + |ptr: GpuWeakPointer| { + let scene = scene.clone(); + let vm_bind = vm_bind.clone(); + let timestamps = timestamps.clone(); + let private = &mut kalloc.private; + try_init!(fw::vertex::RunVertex::ver { + micro_seq: { + let mut builder = microseq::Builder::new(); + + let stats = inner_weak_ptr!( + gpu.initdata.runtime_pointers.stats.vtx.weak_pointer(), + stats + ); + + let start_vtx = builder.add(microseq::StartVertex::ver { + header: microseq::op::StartVertex::HEADER, + #[ver(G < G14X)] + tiling_params: Some(inner_weak_ptr!(ptr, tiling_params)), + #[ver(G < G14X)] + job_params1: Some(inner_weak_ptr!(ptr, job_params1)), + #[ver(G >= G14X)] + tiling_params: None, + #[ver(G >= G14X)] + job_params1: None, + #[ver(G >= G14X)] + registers: inner_weak_ptr!(ptr, registers), + buffer: scene.weak_buffer_pointer(), + scene: scene.weak_pointer(), + stats, + work_queue: ev_vtx.info_ptr, + vm_slot: vm_bind.slot(), + unk_38: 1, // fixed + event_generation: self.id as u32, + buffer_slot: scene.slot(), + unk_44: 0, + event_seq: U64(ev_vtx.event_seq), + unk_50: 0, + unk_pointer: inner_weak_ptr!(ptr, unk_pointee), + unk_job_buf: inner_weak_ptr!(ptr, unk_buf_0), + unk_64: 0x0, // fixed + unk_68: unk1.into(), + uuid: uuid_ta, + attachments: *vertex_attachments, + padding: 0, + #[ver(V >= V13_0B4)] + counter: U64(count_vtx), + #[ver(V >= V13_0B4)] + notifier_buf: inner_weak_ptr!(notifier.weak_pointer(), state.unk_buf), + #[ver(V < V13_0B4)] + unk_178: 0x0, // padding? + #[ver(V >= V13_0B4)] + unk_178: (!clustering) as u32, + })?; + + if vtx_user_timestamps.any() { + builder.add(microseq::Timestamp::ver { + header: microseq::op::Timestamp::new(true), + command_time: inner_weak_ptr!(ptr, command_time), + ts_pointers: inner_weak_ptr!(ptr, timestamp_pointers), + update_ts: inner_weak_ptr!(ptr, timestamp_pointers.start_addr), + work_queue: ev_vtx.info_ptr, + user_ts_pointers: inner_weak_ptr!(ptr, user_timestamp_pointers), + #[ver(V >= V13_0B4)] + unk_ts: inner_weak_ptr!(ptr, unk_ts), + uuid: uuid_ta, + unk_30_padding: 0, + })?; + } + + #[ver(G < G14X)] + builder.add(microseq::WaitForIdle { + header: microseq::op::WaitForIdle::new(microseq::Pipe::Vertex), + })?; + #[ver(G >= G14X)] + builder.add(microseq::WaitForIdle2 { + header: microseq::op::WaitForIdle2::HEADER, + })?; + + if vtx_user_timestamps.any() { + builder.add(microseq::Timestamp::ver { + header: microseq::op::Timestamp::new(false), + command_time: inner_weak_ptr!(ptr, command_time), + ts_pointers: inner_weak_ptr!(ptr, timestamp_pointers), + update_ts: inner_weak_ptr!(ptr, timestamp_pointers.end_addr), + work_queue: ev_vtx.info_ptr, + user_ts_pointers: inner_weak_ptr!(ptr, user_timestamp_pointers), + #[ver(V >= V13_0B4)] + unk_ts: inner_weak_ptr!(ptr, unk_ts), + uuid: uuid_ta, + unk_30_padding: 0, + })?; + } + + let off = builder.offset_to(start_vtx); + builder.add(microseq::FinalizeVertex::ver { + header: microseq::op::FinalizeVertex::HEADER, + scene: scene.weak_pointer(), + buffer: scene.weak_buffer_pointer(), + stats, + work_queue: ev_vtx.info_ptr, + vm_slot: vm_bind.slot(), + unk_28: 0x0, // fixed + unk_pointer: inner_weak_ptr!(ptr, unk_pointee), + unk_34: 0x0, // fixed + uuid: uuid_ta, + fw_stamp: ev_vtx.fw_stamp_pointer, + stamp_value: ev_vtx.value.next(), + unk_48: U64(0x0), // fixed + unk_50: 0x0, // fixed + unk_54: 0x0, // fixed + unk_58: U64(0x0), // fixed + unk_60: 0x0, // fixed + unk_64: 0x0, // fixed + unk_68: 0x0, // fixed + #[ver(G >= G14 && V < V13_0B4)] + unk_68_g14: U64(0), + restart_branch_offset: off, + has_attachments: (vertex_attachments.count > 0) as u32, + #[ver(V >= V13_0B4)] + unk_74: Default::default(), // Ventura + })?; + + builder.add(microseq::RetireStamp { + header: microseq::op::RetireStamp::HEADER, + })?; + builder.build(private)? + }, + notifier, + scene, + vm_bind, + timestamps, + user_timestamps: vtx_user_timestamps, + }) + }, + |inner, _ptr| { + let vm_slot = vm_bind.slot(); + #[ver(G < G14)] + let core_masks = gpu.core_masks_packed(); + + try_init!(fw::vertex::raw::RunVertex::ver { + tag: fw::workqueue::CommandType::RunVertex, + #[ver(V >= V13_0B4)] + counter: U64(count_vtx), + vm_slot, + unk_8: 0, + notifier: inner.notifier.gpu_pointer(), + buffer_slot: inner.scene.slot(), + unk_1c: 0, + buffer: inner.scene.buffer_pointer(), + scene: inner.scene.gpu_pointer(), + unk_buffer_buf: inner.scene.kernel_buffer_pointer(), + unk_34: 0, + #[ver(G < G14X)] + job_params1 <- try_init!(fw::vertex::raw::JobParameters1::ver { + unk_0: U64(if unk1 { 0 } else { 0x200 }), // sometimes 0 + unk_8: f32!(1e-20), // fixed + unk_c: f32!(1e-20), // fixed + tvb_tilemap: inner.scene.tvb_tilemap_pointer(), + #[ver(G < G14)] + tvb_cluster_tilemaps: inner.scene.cluster_tilemaps_pointer(), + tpc: inner.scene.tpc_pointer(), + tvb_heapmeta: inner.scene.tvb_heapmeta_pointer().or(0x8000_0000_0000_0000), + iogpu_unk_54: U64(iogpu_unk54), // fixed + iogpu_unk_56: U64(iogpu_unk56), // fixed + #[ver(G < G14)] + tvb_cluster_meta1: inner + .scene + .meta_1_pointer() + .map(|x| x.or((tile_info.meta1_layer_stride as u64) << 50)), + utile_config, + unk_4c: 0, + ppp_multisamplectl: U64(cmdbuf.ppp_multisamplectl), // fixed + tvb_layermeta: inner.scene.tvb_layermeta_pointer(), + #[ver(G < G14)] + tvb_cluster_layermeta: inner.scene.tvb_cluster_layermeta_pointer(), + #[ver(G < G14)] + core_mask: Array::new([ + *core_masks.first().unwrap_or(&0), + *core_masks.get(1).unwrap_or(&0), + ]), + preempt_buf1: inner.scene.preempt_buf_1_pointer(), + preempt_buf2: inner.scene.preempt_buf_2_pointer(), + unk_80: U64(0x1), // fixed + preempt_buf3: inner.scene.preempt_buf_3_pointer().or(0x4_0000_0000_0000), // check + vdm_ctrl_stream_base: U64(cmdbuf.vdm_ctrl_stream_base), + #[ver(G < G14)] + tvb_cluster_meta2: inner.scene.meta_2_pointer(), + #[ver(G < G14)] + tvb_cluster_meta3: inner.scene.meta_3_pointer(), + #[ver(G < G14)] + tiling_control, + #[ver(G < G14)] + unk_ac: tiling_control_2 as u32, // fixed + unk_b0: Default::default(), // fixed + usc_exec_base_ta: U64(self.usc_exec_base), + #[ver(G < G14)] + tvb_cluster_meta4: inner + .scene + .meta_4_pointer() + .map(|x| x.or(0x3000_0000_0000_0000)), + #[ver(G < G14)] + unk_f0: U64(vtx_unk_f0), + unk_f8: U64(0x8c60), // fixed + helper_program: cmdbuf.vertex_helper.binary, + unk_104: 0, + helper_arg: U64(cmdbuf.vertex_helper.data), + unk_110: Default::default(), // fixed + unk_118: vtx_unk_118 as u32, // fixed + __pad: Default::default(), + }), + #[ver(G < G14X)] + tiling_params: tile_info.params, + #[ver(G >= G14X)] + registers: fw::job::raw::RegisterArray::new( + inner_weak_ptr!(_ptr, registers.registers), + |r| { + r.add(0x10141, if unk1 { 0 } else { 0x200 }); // s2.unk_0 + r.add(0x1c039, inner.scene.tvb_tilemap_pointer().into()); + r.add(0x1c9c8, inner.scene.tvb_tilemap_pointer().into()); + + let cl_tilemaps_ptr = inner + .scene + .cluster_tilemaps_pointer() + .map_or(0, |a| a.into()); + r.add(0x1c041, cl_tilemaps_ptr); + r.add(0x1c9d0, cl_tilemaps_ptr); + r.add(0x1c0a1, inner.scene.tpc_pointer().into()); // TE_TPC_ADDR + + let tvb_heapmeta_ptr = inner + .scene + .tvb_heapmeta_pointer() + .or(0x8000_0000_0000_0000) + .into(); + r.add(0x1c031, tvb_heapmeta_ptr); + r.add(0x1c9c0, tvb_heapmeta_ptr); + r.add(0x1c051, iogpu_unk54); // iogpu_unk_54/55 + r.add(0x1c061, iogpu_unk56); // iogpu_unk_56 + r.add(0x10149, utile_config.into()); // s2.unk_48 utile_config + r.add(0x10139, cmdbuf.ppp_multisamplectl); // PPP_MULTISAMPLECTL + r.add(0x10111, inner.scene.preempt_buf_1_pointer().into()); + r.add(0x1c9b0, inner.scene.preempt_buf_1_pointer().into()); + r.add(0x10119, inner.scene.preempt_buf_2_pointer().into()); + r.add(0x1c9b8, inner.scene.preempt_buf_2_pointer().into()); + r.add(0x1c958, 1); // s2.unk_80 + r.add( + 0x1c950, + inner + .scene + .preempt_buf_3_pointer() + .or(0x4_0000_0000_0000) + .into(), + ); + r.add(0x1c930, 0); // VCE related addr, lsb to enable + r.add(0x1c880, cmdbuf.vdm_ctrl_stream_base); // VDM_CTRL_STREAM_BASE + r.add(0x1c898, 0x0); // if lsb set, faults in UL1C0, possibly missing addr. + r.add( + 0x1c948, + inner.scene.meta_2_pointer().map_or(0, |a| a.into()), + ); // tvb_cluster_meta2 + r.add( + 0x1c888, + inner.scene.meta_3_pointer().map_or(0, |a| a.into()), + ); // tvb_cluster_meta3 + r.add(0x1c890, tiling_control.into()); // tvb_tiling_control + r.add(0x1c918, tiling_control_2); + r.add(0x1c079, inner.scene.tvb_layermeta_pointer().into()); + r.add(0x1c9d8, inner.scene.tvb_layermeta_pointer().into()); + let cl_layermeta_pointer = + inner.scene.tvb_cluster_layermeta_pointer().map_or(0, |a| a.into()); + r.add(0x1c089, cl_layermeta_pointer); + r.add(0x1c9e0, cl_layermeta_pointer); + let cl_meta_4_pointer = + inner.scene.meta_4_pointer().map_or(0, |a| a.into()); + r.add(0x16c41, cl_meta_4_pointer); // tvb_cluster_meta4 + r.add(0x1ca40, cl_meta_4_pointer); // tvb_cluster_meta4 + r.add(0x1c9a8, vtx_unk_f0); // + meta1_blocks? min_free_tvb_pages? + r.add( + 0x1c920, + inner.scene.meta_1_pointer().map_or(0, |a| a.into()), + ); // ??? | meta1_blocks? + r.add(0x10151, 0); + r.add(0x1c199, 0); + r.add(0x1c1a1, 0); + r.add(0x1c1a9, 0); // 0x10151 bit 1 enables + r.add(0x1c1b1, 0); + r.add(0x1c1b9, 0); + r.add(0x10061, self.usc_exec_base); // USC_EXEC_BASE_TA + r.add(0x11801, cmdbuf.vertex_helper.binary.into()); + r.add(0x11809, cmdbuf.vertex_helper.data); + r.add(0x11f71, cmdbuf.vertex_helper.cfg.into()); + r.add(0x1c0b1, tile_info.params.rgn_size.into()); // TE_PSG + r.add(0x1c850, tile_info.params.rgn_size.into()); + r.add(0x10131, tile_info.params.unk_4.into()); + r.add(0x10121, tile_info.params.ppp_ctrl.into()); // PPP_CTRL + r.add( + 0x10129, + tile_info.params.x_max as u64 + | ((tile_info.params.y_max as u64) << 16), + ); // PPP_SCREEN + r.add(0x101b9, tile_info.params.te_screen.into()); // TE_SCREEN + r.add(0x1c069, tile_info.params.te_mtile1.into()); // TE_MTILE1 + r.add(0x1c071, tile_info.params.te_mtile2.into()); // TE_MTILE2 + r.add(0x1c081, tile_info.params.tiles_per_mtile.into()); // TE_MTILE + r.add(0x1c0a9, tile_info.params.tpc_stride.into()); // TE_TPC + r.add(0x10171, tile_info.params.unk_24.into()); + r.add(0x10169, tile_info.params.unk_28.into()); // TA_RENDER_TARGET_MAX + r.add(0x12099, vtx_unk_118); + r.add(0x1c9e8, (tile_info.params.unk_28 & 0x4fff).into()); + /* + r.add(0x10209, 0x100); // Some kind of counter?? Does this matter? + r.add(0x1c9f0, 0x100); // Some kind of counter?? Does this matter? + r.add(0x1c830, 1); // ? + r.add(0x1ca30, 0x1502960e60); // ? + r.add(0x16c39, 0x1502960e60); // ? + r.add(0x1c910, 0xa0000b011d); // ? + r.add(0x1c8e0, 0xff); // cluster mask + r.add(0x1c8e8, 0); // ? + */ + } + ), + tpc: inner.scene.tpc_pointer(), + tpc_size: U64(tile_info.tpc_size as u64), + microsequence: inner.micro_seq.gpu_pointer(), + microsequence_size: inner.micro_seq.len() as u32, + fragment_stamp_slot: ev_frag.slot, + fragment_stamp_value: ev_frag.value.next(), + unk_pointee: 0, + unk_pad: 0, + job_params2 <- try_init!(fw::vertex::raw::JobParameters2 { + unk_480: Default::default(), // fixed + unk_498: U64(0x0), // fixed + unk_4a0: 0x0, // fixed + preempt_buf1: inner.scene.preempt_buf_1_pointer(), + unk_4ac: 0x0, // fixed + unk_4b0: U64(0x0), // fixed + unk_4b8: 0x0, // fixed + unk_4bc: U64(0x0), // fixed + unk_4c4_padding: Default::default(), + unk_50c: 0x0, // fixed + unk_510: U64(0x0), // fixed + unk_518: U64(0x0), // fixed + unk_520: U64(0x0), // fixed + }), + encoder_params <- try_init!(fw::job::raw::EncoderParams { + unk_8: 0x0, // fixed + sync_grow: 0x0, // fixed + unk_10: 0x0, // fixed + encoder_id: 0, + unk_18: 0x0, // fixed + unk_mask: 0xffffffffu32, + sampler_array: U64(cmdbuf.sampler_heap), + sampler_count: cmdbuf.sampler_count as u32, + sampler_max: (cmdbuf.sampler_count as u32) + 1, + }), + unk_55c: 0, + unk_560: 0, + sync_grow: 0, + unk_568: 0, + uses_scratch: (cmdbuf.flags + & uapi::drm_asahi_render_flags_DRM_ASAHI_RENDER_VERTEX_SCRATCH as u32 + != 0) as u32, + meta <- try_init!(fw::job::raw::JobMeta { + unk_0: 0, + unk_2: 0, + no_preemption: no_preemption as u8, + stamp: ev_vtx.stamp_pointer, + fw_stamp: ev_vtx.fw_stamp_pointer, + stamp_value: ev_vtx.value.next(), + stamp_slot: ev_vtx.slot, + evctl_index: 0, // fixed + flush_stamps: flush_stamps as u32, + uuid: uuid_ta, + event_seq: ev_vtx.event_seq as u32, + }), + unk_after_meta: unk1.into(), + unk_buf_0: U64(0), + unk_buf_8: U64(0), + unk_buf_10: U64(0), + command_time: U64(0), + timestamp_pointers <- try_init!(fw::job::raw::TimestampPointers { + start_addr: Some(inner_ptr!(inner.timestamps.gpu_pointer(), vtx.start)), + end_addr: Some(inner_ptr!(inner.timestamps.gpu_pointer(), vtx.end)), + }), + user_timestamp_pointers: inner.user_timestamps.pointers()?, + client_sequence: slot_client_seq, + pad_5d5: Default::default(), + unk_5d8: 0, + unk_5dc: 0, + #[ver(V >= V13_0B4)] + unk_ts: U64(0), + #[ver(V >= V13_0B4)] + unk_5dd_8: Default::default(), + }) + }, + )?; + + core::mem::drop(alloc); + + mod_dev_dbg!(self.dev, "[Submission {}] Add Vertex\n", id); + fence.add_command(); + vtx_job.add_cb(vtx, vm_bind.slot(), move |error| { + if let Some(err) = error { + fence.set_error(err.into()) + } + + fence.command_complete(); + })?; + + mod_dev_dbg!(self.dev, "[Submission {}] Increment counters\n", id); + + // TODO: handle rollbacks, move to job submit? + buffer.increment(); + + job.get_vtx()?.next_seq(); + job.get_frag()?.next_seq(); + + Ok(()) + } +} diff --git a/drivers/gpu/drm/asahi/regs.rs b/drivers/gpu/drm/asahi/regs.rs new file mode 100644 index 00000000000000..6ebbaa56f48c81 --- /dev/null +++ b/drivers/gpu/drm/asahi/regs.rs @@ -0,0 +1,491 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU MMIO register abstraction +//! +//! Since the vast majority of the interactions with the GPU are brokered through the firmware, +//! there is very little need to interact directly with GPU MMIO register. This module abstracts +//! the few operations that require that, mainly reading the MMU fault status, reading GPU ID +//! information, and starting the GPU firmware coprocessor. + +use crate::hw; +use kernel::{ + c_str, + device::Core, + devres::Devres, + io::mem::IoMem, + platform, + prelude::*, + types::ARef, // +}; + +/// Size of the ASC control MMIO region. +pub(crate) const ASC_CTL_SIZE: usize = 0x4000; + +/// Size of the SGX MMIO region. +pub(crate) const SGX_SIZE: usize = 0x1000000; + +const CPU_CONTROL: usize = 0x44; +const CPU_RUN: u32 = 0x1 << 4; // BIT(4) + +const FAULT_INFO: usize = 0x17030; + +const ID_VERSION: usize = 0xd04000; +const ID_UNK08: usize = 0xd04008; +const ID_COUNTS_1: usize = 0xd04010; +const ID_COUNTS_2: usize = 0xd04014; +const ID_UNK18: usize = 0xd04018; +const ID_CLUSTERS: usize = 0xd0401c; + +const CORE_MASK_0: usize = 0xd01500; +const CORE_MASK_1: usize = 0xd01514; + +const CORE_MASKS_G14X: usize = 0xe01500; +const FAULT_INFO_G14X: usize = 0xd8c0; +const FAULT_ADDR_G14X: usize = 0xd8c8; + +/// Enum representing the unit that caused an MMU fault. +#[allow(non_camel_case_types)] +#[allow(clippy::upper_case_acronyms)] +#[derive(Copy, Clone, Debug, Eq, PartialEq)] +pub(crate) enum FaultUnit { + /// Decompress / pixel fetch + DCMP(u8), + /// USC L1 Cache (device loads/stores) + UL1C(u8), + /// Compress / pixel store + CMP(u8), + GSL1(u8), + IAP(u8), + VCE(u8), + /// Tiling Engine + TE(u8), + RAS(u8), + /// Vertex Data Master + VDM(u8), + PPP(u8), + /// ISP Parameter Fetch + IPF(u8), + IPF_CPF(u8), + VF(u8), + VF_CPF(u8), + /// Depth/Stencil load/store + ZLS(u8), + + /// Parameter Management + dPM, + /// Compute Data Master + dCDM_KS(u8), + dIPP, + dIPP_CS, + // Vertex Data Master + dVDM_CSD, + dVDM_SSD, + dVDM_ILF, + dVDM_ILD, + dRDE(u8), + FC, + GSL2, + + /// Graphics L2 Cache Control? + GL2CC_META(u8), + GL2CC_MB, + + /// Parameter Management + gPM_SP(u8), + /// Vertex Data Master - CSD + gVDM_CSD_SP(u8), + gVDM_SSD_SP(u8), + gVDM_ILF_SP(u8), + gVDM_TFP_SP(u8), + gVDM_MMB_SP(u8), + /// Compute Data Master + gCDM_CS_KS0_SP(u8), + gCDM_CS_KS1_SP(u8), + gCDM_CS_KS2_SP(u8), + gCDM_KS0_SP(u8), + gCDM_KS1_SP(u8), + gCDM_KS2_SP(u8), + gIPP_SP(u8), + gIPP_CS_SP(u8), + gRDE0_SP(u8), + gRDE1_SP(u8), + + gCDM_CS, + gCDM_ID, + gCDM_CSR, + gCDM_CSW, + gCDM_CTXR, + gCDM_CTXW, + gIPP, + gIPP_CS, + gKSM_RCE, + + Unknown(u8), +} + +/// Reason for an MMU fault. +#[derive(Copy, Clone, Debug, Eq, PartialEq)] +pub(crate) enum FaultReason { + Unmapped, + AfFault, + WriteOnly, + ReadOnly, + NoAccess, + Unknown(u8), +} + +/// Collection of information about an MMU fault. +#[derive(Copy, Clone, Debug, Eq, PartialEq)] +pub(crate) struct FaultInfo { + pub(crate) address: u64, + pub(crate) sideband: u8, + pub(crate) vm_slot: u32, + pub(crate) unit_code: u8, + pub(crate) unit: FaultUnit, + pub(crate) level: u8, + pub(crate) unk_5: u8, + pub(crate) read: bool, + pub(crate) reason: FaultReason, +} + +/// Device resources for this GPU instance. +pub(crate) struct Resources { + dev: ARef, + sgx: Pin>>>, +} + +impl Resources { + /// Map the required resources given our platform device. + pub(crate) fn new(pdev: &platform::Device) -> Result { + let sgx_req = pdev.io_request_by_name(c_str!("sgx")).ok_or(EINVAL)?; + let sgx_iomem = KBox::pin_init(sgx_req.iomap_sized::(), GFP_KERNEL)?; + + Ok(Resources { + // SAFETY: This device does DMA via the UAT IOMMU. + dev: pdev.into(), + sgx: sgx_iomem, + }) + } + + fn sgx_read32(&self) -> u32 { + if let Some(sgx) = self.sgx.try_access() { + sgx.read32_relaxed(OFF) + } else { + 0 + } + } + + /* Not yet used + fn sgx_write32(&self, val: u32) { + if let Some(sgx) = self.sgx.try_access() { + sgx.write32_relaxed(val, OFF) + } + } + */ + + fn sgx_read64(&self) -> u64 { + if let Some(sgx) = self.sgx.try_access() { + sgx.read64_relaxed(OFF) + } else { + 0 + } + } + + /* Not yet used + fn sgx_write64(&self, val: u64) { + if let Some(sgx) = self.sgx.try_access() { + sgx.write64_relaxed(val, OFF) + } + } + */ + + /// Initialize the MMIO registers for the GPU. + pub(crate) fn init_mmio(&self) -> Result { + // Nothing to do for now... + + Ok(()) + } + + /// Start the ASC coprocessor CPU. + pub(crate) fn start_cpu(pdev: &platform::Device) -> Result { + let asc_req = pdev.io_request_by_name(c_str!("asc")).ok_or(EINVAL)?; + let asc_iomem = KBox::pin_init(asc_req.iomap_sized::(), GFP_KERNEL)?; + let res = asc_iomem.access(pdev.as_ref())?; + + let val = res.read32_relaxed(CPU_CONTROL); + res.write32_relaxed(val | CPU_RUN, CPU_CONTROL); + Ok(()) + } + + /// Get the GPU identification info from registers. + /// + /// See [`hw::GpuIdConfig`] for the result. + pub(crate) fn get_gpu_id(&self) -> Result { + let id_version = self.sgx_read32::(); + let id_unk08 = self.sgx_read32::(); + let id_counts_1 = self.sgx_read32::(); + let id_counts_2 = self.sgx_read32::(); + let id_unk18 = self.sgx_read32::(); + let id_clusters = self.sgx_read32::(); + + dev_info!( + self.dev.as_ref(), + "GPU ID registers: {:#x} {:#x} {:#x} {:#x} {:#x} {:#x}\n", + id_version, + id_unk08, + id_counts_1, + id_counts_2, + id_unk18, + id_clusters + ); + + let gpu_gen = (id_version >> 24) & 0xff; + + let mut core_mask_regs = KVec::new(); + + let num_clusters = match gpu_gen { + 4 | 5 => { + // G13 | G14G + core_mask_regs.push(self.sgx_read32::(), GFP_KERNEL)?; + core_mask_regs.push(self.sgx_read32::(), GFP_KERNEL)?; + (id_clusters >> 12) & 0xff + } + 6 => { + // G14X + core_mask_regs.push(self.sgx_read32::(), GFP_KERNEL)?; + core_mask_regs.push(self.sgx_read32::<{ CORE_MASKS_G14X + 4 }>(), GFP_KERNEL)?; + core_mask_regs.push(self.sgx_read32::<{ CORE_MASKS_G14X + 8 }>(), GFP_KERNEL)?; + // Clusters per die * num dies + ((id_counts_1 >> 8) & 0xff) * ((id_counts_1 >> 16) & 0xf) + } + a => { + dev_err!(self.dev.as_ref(), "Unknown GPU generation {}\n", a); + return Err(ENODEV); + } + }; + + let mut core_masks_packed = KVec::new(); + core_masks_packed.extend_from_slice(&core_mask_regs, GFP_KERNEL)?; + + dev_info!(self.dev.as_ref(), "Core masks: {:#x?}\n", core_masks_packed); + + let num_cores = id_counts_1 & 0xff; + + if num_cores > 32 { + dev_err!( + self.dev.as_ref(), + "Too many cores per cluster ({} > 32)\n", + num_cores + ); + return Err(ENODEV); + } + + if num_cores * num_clusters > (core_mask_regs.len() * 32) as u32 { + dev_err!( + self.dev.as_ref(), + "Too many total cores ({} x {} > {})\n", + num_clusters, + num_cores, + core_mask_regs.len() * 32 + ); + return Err(ENODEV); + } + + let mut core_masks = KVec::new(); + let mut total_active_cores: u32 = 0; + + let max_core_mask = ((1u64 << num_cores) - 1) as u32; + for _ in 0..num_clusters { + let mask = core_mask_regs[0] & max_core_mask; + core_masks.push(mask, GFP_KERNEL)?; + for i in 0..core_mask_regs.len() { + core_mask_regs[i] >>= num_cores; + if i < (core_mask_regs.len() - 1) { + core_mask_regs[i] |= core_mask_regs[i + 1] << (32 - num_cores); + } + } + total_active_cores += mask.count_ones(); + } + + if core_mask_regs.iter().any(|a| *a != 0) { + dev_err!( + self.dev.as_ref(), + "Leftover core mask: {:#x?}\n", + core_mask_regs + ); + return Err(EIO); + } + + let (gpu_rev, gpu_rev_id) = match (id_version >> 8) & 0xff { + 0x00 => (hw::GpuRevision::A0, hw::GpuRevisionID::A0), + 0x01 => (hw::GpuRevision::A1, hw::GpuRevisionID::A1), + 0x10 => (hw::GpuRevision::B0, hw::GpuRevisionID::B0), + 0x11 => (hw::GpuRevision::B1, hw::GpuRevisionID::B1), + 0x20 => (hw::GpuRevision::C0, hw::GpuRevisionID::C0), + 0x21 => (hw::GpuRevision::C1, hw::GpuRevisionID::C1), + a => { + dev_err!(self.dev.as_ref(), "Unknown GPU revision {}\n", a); + return Err(ENODEV); + } + }; + + Ok(hw::GpuIdConfig { + gpu_gen: match (id_version >> 24) & 0xff { + 4 => hw::GpuGen::G13, + 5 => hw::GpuGen::G14, + 6 => hw::GpuGen::G14, // G14X has a separate ID + a => { + dev_err!(self.dev.as_ref(), "Unknown GPU generation {}\n", a); + return Err(ENODEV); + } + }, + gpu_variant: match (id_version >> 16) & 0xff { + 1 => hw::GpuVariant::P, // Guess + 2 => hw::GpuVariant::G, + 3 => hw::GpuVariant::S, + 4 => { + if num_clusters > 4 { + hw::GpuVariant::D + } else { + hw::GpuVariant::C + } + } + a => { + dev_err!(self.dev.as_ref(), "Unknown GPU variant {}\n", a); + return Err(ENODEV); + } + }, + gpu_rev, + gpu_rev_id, + num_clusters, + num_cores, + num_frags: num_cores, // Used to be id_counts_1[15:8] but does not work for G14X + num_gps: (id_counts_2 >> 16) & 0xff, + total_active_cores, + core_masks, + core_masks_packed, + }) + } + + /// Get the fault information from the MMU status register, if one occurred. + pub(crate) fn get_fault_info(&self, cfg: &'static hw::HwConfig) -> Option { + let g14x = cfg.gpu_core as u32 >= hw::GpuCore::G14S as u32; + + let fault_info = if g14x { + self.sgx_read64::() + } else { + self.sgx_read64::() + }; + + if fault_info & 1 == 0 { + return None; + } + + let fault_addr = if g14x { + self.sgx_read64::() + } else { + fault_info >> 30 + }; + + let unit_code = ((fault_info >> 9) & 0xff) as u8; + let unit = match unit_code { + 0x00..=0x9f => match unit_code & 0xf { + 0x0 => FaultUnit::DCMP(unit_code >> 4), + 0x1 => FaultUnit::UL1C(unit_code >> 4), + 0x2 => FaultUnit::CMP(unit_code >> 4), + 0x3 => FaultUnit::GSL1(unit_code >> 4), + 0x4 => FaultUnit::IAP(unit_code >> 4), + 0x5 => FaultUnit::VCE(unit_code >> 4), + 0x6 => FaultUnit::TE(unit_code >> 4), + 0x7 => FaultUnit::RAS(unit_code >> 4), + 0x8 => FaultUnit::VDM(unit_code >> 4), + 0x9 => FaultUnit::PPP(unit_code >> 4), + 0xa => FaultUnit::IPF(unit_code >> 4), + 0xb => FaultUnit::IPF_CPF(unit_code >> 4), + 0xc => FaultUnit::VF(unit_code >> 4), + 0xd => FaultUnit::VF_CPF(unit_code >> 4), + 0xe => FaultUnit::ZLS(unit_code >> 4), + _ => FaultUnit::Unknown(unit_code), + }, + 0xa1 => FaultUnit::dPM, + 0xa2 => FaultUnit::dCDM_KS(0), + 0xa3 => FaultUnit::dCDM_KS(1), + 0xa4 => FaultUnit::dCDM_KS(2), + 0xa5 => FaultUnit::dIPP, + 0xa6 => FaultUnit::dIPP_CS, + 0xa7 => FaultUnit::dVDM_CSD, + 0xa8 => FaultUnit::dVDM_SSD, + 0xa9 => FaultUnit::dVDM_ILF, + 0xaa => FaultUnit::dVDM_ILD, + 0xab => FaultUnit::dRDE(0), + 0xac => FaultUnit::dRDE(1), + 0xad => FaultUnit::FC, + 0xae => FaultUnit::GSL2, + 0xb0..=0xb7 => FaultUnit::GL2CC_META(unit_code & 0xf), + 0xb8 => FaultUnit::GL2CC_MB, + 0xd0..=0xdf if g14x => match unit_code & 0xf { + 0x0 => FaultUnit::gCDM_CS, + 0x1 => FaultUnit::gCDM_ID, + 0x2 => FaultUnit::gCDM_CSR, + 0x3 => FaultUnit::gCDM_CSW, + 0x4 => FaultUnit::gCDM_CTXR, + 0x5 => FaultUnit::gCDM_CTXW, + 0x6 => FaultUnit::gIPP, + 0x7 => FaultUnit::gIPP_CS, + 0x8 => FaultUnit::gKSM_RCE, + _ => FaultUnit::Unknown(unit_code), + }, + 0xe0..=0xff if g14x => match unit_code & 0xf { + 0x0 => FaultUnit::gPM_SP((unit_code >> 4) & 1), + 0x1 => FaultUnit::gVDM_CSD_SP((unit_code >> 4) & 1), + 0x2 => FaultUnit::gVDM_SSD_SP((unit_code >> 4) & 1), + 0x3 => FaultUnit::gVDM_ILF_SP((unit_code >> 4) & 1), + 0x4 => FaultUnit::gVDM_TFP_SP((unit_code >> 4) & 1), + 0x5 => FaultUnit::gVDM_MMB_SP((unit_code >> 4) & 1), + 0x6 => FaultUnit::gRDE0_SP((unit_code >> 4) & 1), + _ => FaultUnit::Unknown(unit_code), + }, + 0xe0..=0xff if !g14x => match unit_code & 0xf { + 0x0 => FaultUnit::gPM_SP((unit_code >> 4) & 1), + 0x1 => FaultUnit::gVDM_CSD_SP((unit_code >> 4) & 1), + 0x2 => FaultUnit::gVDM_SSD_SP((unit_code >> 4) & 1), + 0x3 => FaultUnit::gVDM_ILF_SP((unit_code >> 4) & 1), + 0x4 => FaultUnit::gVDM_TFP_SP((unit_code >> 4) & 1), + 0x5 => FaultUnit::gVDM_MMB_SP((unit_code >> 4) & 1), + 0x6 => FaultUnit::gCDM_CS_KS0_SP((unit_code >> 4) & 1), + 0x7 => FaultUnit::gCDM_CS_KS1_SP((unit_code >> 4) & 1), + 0x8 => FaultUnit::gCDM_CS_KS2_SP((unit_code >> 4) & 1), + 0x9 => FaultUnit::gCDM_KS0_SP((unit_code >> 4) & 1), + 0xa => FaultUnit::gCDM_KS1_SP((unit_code >> 4) & 1), + 0xb => FaultUnit::gCDM_KS2_SP((unit_code >> 4) & 1), + 0xc => FaultUnit::gIPP_SP((unit_code >> 4) & 1), + 0xd => FaultUnit::gIPP_CS_SP((unit_code >> 4) & 1), + 0xe => FaultUnit::gRDE0_SP((unit_code >> 4) & 1), + 0xf => FaultUnit::gRDE1_SP((unit_code >> 4) & 1), + _ => FaultUnit::Unknown(unit_code), + }, + _ => FaultUnit::Unknown(unit_code), + }; + + let reason = match (fault_info >> 1) & 0x7 { + 0 => FaultReason::Unmapped, + 1 => FaultReason::AfFault, + 2 => FaultReason::WriteOnly, + 3 => FaultReason::ReadOnly, + 4 => FaultReason::NoAccess, + a => FaultReason::Unknown(a as u8), + }; + + Some(FaultInfo { + address: fault_addr << 6, + sideband: ((fault_info >> 23) & 0x7f) as u8, + vm_slot: ((fault_info >> 17) & 0x3f) as u32, + unit_code, + unit, + level: ((fault_info >> 7) & 3) as u8, + unk_5: ((fault_info >> 5) & 3) as u8, + read: (fault_info & (1 << 4)) != 0, + reason, + }) + } +} diff --git a/drivers/gpu/drm/asahi/slotalloc.rs b/drivers/gpu/drm/asahi/slotalloc.rs new file mode 100644 index 00000000000000..fde7470fe57791 --- /dev/null +++ b/drivers/gpu/drm/asahi/slotalloc.rs @@ -0,0 +1,323 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Generic slot allocator +//! +//! This is a simple allocator to manage fixed-size pools of GPU resources that are transiently +//! required during command execution. Each item resides in a "slot" at a given index. Users borrow +//! and return free items from the available pool. +//! +//! Allocations are "sticky", and return a token that callers can use to request the same slot +//! again later. This allows slots to be lazily invalidated, so that multiple uses by the same user +//! avoid any actual cleanup work. +//! +//! The allocation policy is currently a simple LRU mechanism, doing a full linear scan over the +//! slots when no token was previously provided. This is probably good enough, since in the absence +//! of serious system contention most allocation requests will be immediately fulfilled from the +//! previous slot without doing an LRU scan. + +use core::num::NonZeroUsize; +use core::ops::{ + Deref, + DerefMut, // +}; +use kernel::{ + error::{ + code::*, + Result, // + }, + prelude::*, + str::CStr, + sync::{ + Arc, + CondVar, + LockClassKey, + Mutex, // + }, +}; + +/// Trait representing a single item within a slot. +pub(crate) trait SlotItem { + /// Arbitrary user data associated with the SlotAllocator. + type Data; + + /// Called eagerly when this item is released back into the available pool. + fn release(&mut self, _data: &mut Self::Data, _slot: u32) {} +} + +/// Trivial implementation for users which do not require any slot data nor any allocator data. +impl SlotItem for () { + type Data = (); +} + +/// Represents a current or previous allocation of an item from a slot. Users keep `SlotToken`s +/// around across allocations to request that, if possible, the same slot be reused. +#[derive(Copy, Clone, Debug)] +pub(crate) struct SlotToken { + time: u64, + slot: u32, +} + +impl SlotToken { + /// Returns the slot index that this token represents a past assignment to. + pub(crate) fn last_slot(&self) -> u32 { + self.slot + } +} + +/// A guard representing active ownership of a slot. +pub(crate) struct Guard { + item: Option, + changed: bool, + token: SlotToken, + alloc: Arc>, +} + +impl Guard { + /// Returns the active slot owned by this `Guard`. + pub(crate) fn slot(&self) -> u32 { + self.token.slot + } + + /// Returns `true` if the slot changed since the last allocation (or no `SlotToken` was + /// provided), or `false` if the previously allocated slot was successfully re-acquired with + /// no other users in the interim. + pub(crate) fn changed(&self) -> bool { + self.changed + } + + /// Returns a `SlotToken` that can be used to re-request the same slot at a later time, after + /// this `Guard` is dropped. + pub(crate) fn token(&self) -> SlotToken { + self.token + } +} + +impl Deref for Guard { + type Target = T; + + fn deref(&self) -> &Self::Target { + self.item.as_ref().expect("SlotItem Guard lost our item!") + } +} + +impl DerefMut for Guard { + fn deref_mut(&mut self) -> &mut Self::Target { + self.item.as_mut().expect("SlotItem Guard lost our item!") + } +} + +/// A slot item that is currently free. +struct Entry { + item: T, + get_time: u64, + drop_time: u64, +} + +/// Inner data for the `SlotAllocator`, protected by a `Mutex`. +struct SlotAllocatorInner { + data: T::Data, + slots: KVec>>, + get_count: u64, + drop_count: u64, + slot_limit: usize, +} + +/// A single slot allocator instance. +#[pin_data] +struct SlotAllocatorOuter { + #[pin] + inner: Mutex>, + #[pin] + cond: CondVar, +} + +/// A shared reference to a slot allocator instance. +pub(crate) struct SlotAllocator(Arc>); + +impl SlotAllocator { + /// Creates a new `SlotAllocator`, with a fixed number of slots and arbitrary associated data. + /// + /// The caller provides a constructor callback which takes a reference to the `T::Data` and + /// creates a single slot. This is called during construction to create all the initial + /// items, which then live the lifetime of the `SlotAllocator`. + pub(crate) fn new( + num_slots: u32, + mut data: T::Data, + mut constructor: impl FnMut(&mut T::Data, u32) -> Option, + name: &'static CStr, + lock_key1: Pin<&'static LockClassKey>, + lock_key2: Pin<&'static LockClassKey>, + ) -> Result> { + let mut slots = KVec::with_capacity(num_slots as usize, GFP_KERNEL)?; + + for i in 0..num_slots { + slots + .push( + constructor(&mut data, i).map(|item| Entry { + item, + get_time: 0, + drop_time: 0, + }), + GFP_KERNEL, + ) + .expect("try_push() failed after reservation"); + } + + let inner = SlotAllocatorInner { + data, + slots, + get_count: 0, + drop_count: 0, + slot_limit: usize::MAX, + }; + + let alloc = Arc::pin_init( + pin_init!(SlotAllocatorOuter { + // SAFETY: `mutex_init!` is called below. + inner <- Mutex::new(inner, name, lock_key1), + // SAFETY: `condvar_init!` is called below. + cond <- CondVar::new(name, lock_key2), + }), + GFP_KERNEL, + )?; + + Ok(SlotAllocator(alloc)) + } + + /// Calls a callback on the inner data associated with this allocator, taking the lock. + pub(crate) fn with_inner(&self, cb: impl FnOnce(&mut T::Data) -> RetVal) -> RetVal { + let mut inner = self.0.inner.lock(); + cb(&mut inner.data) + } + + /// Set the slot limit for this allocator. New bindings will not use slots above + /// this threshold. + pub(crate) fn set_limit(&self, limit: Option) { + let mut inner = self.0.inner.lock(); + inner.slot_limit = limit.unwrap_or(NonZeroUsize::MAX).get(); + } + + /// Gets a fresh slot, optionally reusing a previous allocation if a `SlotToken` is provided. + /// + /// Blocks if no slots are free. + pub(crate) fn get(&self, token: Option) -> Result> { + self.get_inner(token, |_a, _b| Ok(())) + } + + /// Gets a fresh slot, optionally reusing a previous allocation if a `SlotToken` is provided. + /// + /// Blocks if no slots are free. + /// + /// This version allows the caller to pass in a callback that gets a mutable reference to the + /// user data for the allocator and the freshly acquired slot, which is called before the + /// allocator lock is released. This can be used to perform bookkeeping associated with + /// specific slots (such as tracking their current owner). + pub(crate) fn get_inner( + &self, + token: Option, + cb: impl FnOnce(&mut T::Data, &mut Guard) -> Result<()>, + ) -> Result> { + let mut inner = self.0.inner.lock(); + + if let Some(token) = token { + if (token.slot as usize) < inner.slot_limit { + let slot = &mut inner.slots[token.slot as usize]; + if slot.is_some() { + let count = slot.as_ref().unwrap().get_time; + if count == token.time { + let mut guard = Guard { + item: Some(slot.take().unwrap().item), + token, + changed: false, + alloc: self.0.clone(), + }; + cb(&mut inner.data, &mut guard)?; + return Ok(guard); + } + } + } + } + + let mut first = true; + let slot = loop { + let mut oldest_time = u64::MAX; + let mut oldest_slot = 0u32; + + for (i, slot) in inner.slots.iter().enumerate() { + if i >= inner.slot_limit { + break; + } + if let Some(slot) = slot.as_ref() { + if slot.drop_time < oldest_time { + oldest_slot = i as u32; + oldest_time = slot.drop_time; + } + } + } + + if oldest_time == u64::MAX { + if first && inner.slot_limit == usize::MAX { + pr_warn!( + "{}: out of slots, blocking\n", + core::any::type_name::() + ); + } + first = false; + if self.0.cond.wait_interruptible(&mut inner) { + return Err(ERESTARTSYS); + } + } else { + break oldest_slot; + } + }; + + inner.get_count += 1; + + let item = inner.slots[slot as usize] + .take() + .expect("Someone stole our slot?") + .item; + + let mut guard = Guard { + item: Some(item), + changed: true, + token: SlotToken { + time: inner.get_count, + slot, + }, + alloc: self.0.clone(), + }; + + cb(&mut inner.data, &mut guard)?; + Ok(guard) + } +} + +impl Clone for SlotAllocator { + fn clone(&self) -> Self { + SlotAllocator(self.0.clone()) + } +} + +impl Drop for Guard { + fn drop(&mut self) { + let mut inner = self.alloc.inner.lock(); + if inner.slots[self.token.slot as usize].is_some() { + pr_crit!( + "{}: tried to return an item into a full slot ({})\n", + core::any::type_name::(), + self.token.slot + ); + } else { + inner.drop_count += 1; + let mut item = self.item.take().expect("Guard lost its item"); + item.release(&mut inner.data, self.token.slot); + inner.slots[self.token.slot as usize] = Some(Entry { + item, + get_time: self.token.time, + drop_time: inner.drop_count, + }); + self.alloc.cond.notify_one(); + } + } +} diff --git a/drivers/gpu/drm/asahi/util.rs b/drivers/gpu/drm/asahi/util.rs new file mode 100644 index 00000000000000..1a41d8f16d4432 --- /dev/null +++ b/drivers/gpu/drm/asahi/util.rs @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Miscellaneous utility functions + +use core::ops::{ + Add, + BitAnd, + Div, + Not, + Sub, // +}; +use kernel::prelude::*; + +/// Aligns an integer type to a power of two. +pub(crate) fn align(a: T, b: T) -> T +where + T: Copy + + Default + + BitAnd + + Not + + Add + + Sub + + Div + + core::cmp::PartialEq, +{ + let def: T = Default::default(); + #[allow(clippy::eq_op)] + let one: T = !def / !def; + + assert!((b & (b - one)) == def); + + (a + b - one) & !(b - one) +} + +/// Aligns an integer type down to a power of two. +pub(crate) fn align_down(a: T, b: T) -> T +where + T: Copy + + Default + + BitAnd + + Not + + Sub + + Div + + core::cmp::PartialEq, +{ + let def: T = Default::default(); + #[allow(clippy::eq_op)] + let one: T = !def / !def; + + assert!((b & (b - one)) == def); + + a & !(b - one) +} + +pub(crate) trait RangeExt { + fn overlaps(&self, other: Self) -> bool; + fn is_superset(&self, other: Self) -> bool; + // fn len(&self) -> usize; + fn range(&self) -> T; +} + +impl + Default + Copy + Sub> RangeExt for core::ops::Range +where + usize: core::convert::TryFrom, + >::Error: core::fmt::Debug, +{ + fn overlaps(&self, other: Self) -> bool { + !(self.is_empty() || other.is_empty() || self.end <= other.start || other.end <= self.start) + } + fn is_superset(&self, other: Self) -> bool { + !self.is_empty() + && (other.is_empty() || (other.start >= self.start && other.end <= self.end)) + } + fn range(&self) -> T { + if self.is_empty() { + Default::default() + } else { + self.end - self.start + } + } + // fn len(&self) -> usize { + // self.range().try_into().unwrap() + // } +} + +pub(crate) fn gcd(in_n: u64, in_m: u64) -> u64 { + let mut n = in_n; + let mut m = in_m; + + while n != 0 { + let remainder = m % n; + m = n; + n = remainder; + } + + m +} + +pub(crate) unsafe trait AnyBitPattern: Default + Sized + Copy + 'static {} + +pub(crate) struct Reader<'a> { + buffer: &'a [u8], + offset: usize, +} + +impl<'a> Reader<'a> { + pub(crate) fn new(buffer: &'a [u8]) -> Self { + Reader { buffer, offset: 0 } + } + + pub(crate) fn read_up_to(&mut self, max_size: usize) -> Result { + let mut obj: T = Default::default(); + let size: usize = core::mem::size_of::().min(max_size); + let range = self.offset..self.offset + size; + let src = self.buffer.get(range).ok_or(EINVAL)?; + + // SAFETY: The output pointer is valid, and the size does not exceed + // the type size, and all bit patterns are valid. + let dst = unsafe { core::slice::from_raw_parts_mut(&mut obj as *mut _ as *mut u8, size) }; + + dst.copy_from_slice(src); + self.offset += size; + Ok(obj) + } + + pub(crate) fn read(&mut self) -> Result { + self.read_up_to(!0) + } + + pub(crate) fn is_empty(&self) -> bool { + self.offset >= self.buffer.len() + } + + pub(crate) fn skip(&mut self, size: usize) { + self.offset += size + } + + pub(crate) fn rewind(&mut self) { + self.offset = 0 + } +} diff --git a/drivers/gpu/drm/asahi/vm/mod.rs b/drivers/gpu/drm/asahi/vm/mod.rs new file mode 100644 index 00000000000000..63cf8a76cd5ce4 --- /dev/null +++ b/drivers/gpu/drm/asahi/vm/mod.rs @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Virtual address space management + +mod range; diff --git a/drivers/gpu/drm/asahi/vm/range.rs b/drivers/gpu/drm/asahi/vm/range.rs new file mode 100644 index 00000000000000..727d29a5cccf02 --- /dev/null +++ b/drivers/gpu/drm/asahi/vm/range.rs @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +// Copied from tyr's mmu/vm/range.rs + +//! Range allocator. +//! +//! This module allows you to search for unused ranges to store GEM objects. + +use kernel::alloc::Flags; +use kernel::maple_tree::MapleTreeAlloc; +use kernel::prelude::*; +use kernel::sync::Arc; + +use core::ops::Range; + +/// The actual storage for the ranges. +/// +/// All ranges must fit within the `range` field. +/// +/// The implementation is different on 32-bit and 64-bit cpus. On 64-bit, the 64-bit addresses are +/// stored directly in the maple tree, but on 32-bit, the maple tree stores the ranges translated +/// in the range zero until `range.end-range.start`. This is done because the maple tree uses +/// unsigned long as its address type, which is too small to store the 64-bit address directly on +/// 32-bit machines. +#[pin_data] +struct RangeAllocInner { + #[pin] + maple: MapleTreeAlloc<()>, + range: Range, +} + +/// This object allows you to allocate ranges on the inner maple tree. +pub(crate) struct RangeAlloc { + inner: Arc, +} + +/// Represents a live range in the maple tree. +/// +/// The destructor removes the range from the maple tree, allowing others to allocate it in the +/// future. +pub(crate) struct LiveRange { + inner: Arc, + offset: u64, + size: usize, +} + +impl RangeAlloc { + pub(crate) fn new(start: u64, end: u64, gfp: Flags) -> Result { + if end < start { + return Err(EINVAL); + } + + let inner = Arc::pin_init( + try_pin_init!(RangeAllocInner { + maple <- MapleTreeAlloc::new(), + range: start..end, + }), + gfp, + )?; + + Ok(RangeAlloc { inner }) + } + + pub(crate) fn allocate(&self, size: usize, gfp: Flags) -> Result { + let maple_start = self.inner.range.start as usize; + let maple_end = self.inner.range.end as usize; + + let offset = self + .inner + .maple + .alloc_range(size, (), maple_start..maple_end, gfp)?; + + Ok(LiveRange { + inner: self.inner.clone(), + offset: offset as u64, + size, + }) + } + + pub(crate) fn insert(&self, start: u64, end: u64, gfp: Flags) -> Result { + if end < start { + return Err(EINVAL); + } + if start < self.inner.range.start { + return Err(EINVAL); + } + if end > self.inner.range.end { + return Err(EINVAL); + } + + self.inner + .maple + .insert_range(start as usize..end as usize, (), gfp)?; + + Ok(LiveRange { + inner: self.inner.clone(), + offset: start, + size: (end - start) as usize, + }) + } +} + +impl LiveRange { + pub(crate) fn size(&self) -> usize { + self.size + } + + pub(crate) fn start(&self) -> u64 { + self.offset + } + + pub(crate) fn end(&self) -> u64 { + self.offset + self.size as u64 + } + + pub(crate) fn range(&self) -> Range { + self.start()..self.end() + } +} + +impl Drop for LiveRange { + fn drop(&mut self) { + self.inner.maple.erase(self.offset as usize); + } +} diff --git a/drivers/gpu/drm/asahi/workqueue.rs b/drivers/gpu/drm/asahi/workqueue.rs new file mode 100644 index 00000000000000..55b6058d50224f --- /dev/null +++ b/drivers/gpu/drm/asahi/workqueue.rs @@ -0,0 +1,1015 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! GPU command execution queues +//! +//! The AGX GPU firmware schedules GPU work commands out of work queues, which are ring buffers of +//! pointers to work commands. There can be an arbitrary number of work queues. Work queues have an +//! associated type (vertex, fragment, or compute) and may only contain generic commands or commands +//! specific to that type. +//! +//! This module manages queueing work commands into a work queue and submitting them for execution +//! by the firmware. An active work queue needs an event to signal completion of its work, which is +//! owned by what we call a batch. This event then notifies the work queue when work is completed, +//! and that triggers freeing of all resources associated with that work. An idle work queue gives +//! up its associated event. + +use crate::debug::*; +use crate::fw::channels::{ + ChannelErrorType, + PipeType, // +}; +use crate::fw::types::*; +use crate::fw::workqueue::*; +use crate::no_debug; +use crate::object::OpaqueGpuObject; +use crate::{ + channel, + driver, + event, + fw, + gpu, + regs, // +}; +use core::any::Any; +use core::num::NonZeroU64; +use core::sync::atomic::Ordering; +use kernel::{ + dma_fence, + error::code::*, + new_mutex, + prelude::*, + sync::{ + lock::{ + mutex::MutexBackend, + Guard, // + }, + Arc, + Mutex, // + }, + workqueue::{ + self, + impl_has_work, + new_work, + Work, + WorkItem, // + }, // +}; + +pub(crate) trait OpaqueCommandObject: OpaqueGpuObject {} + +impl OpaqueCommandObject for GpuObject where T: Command {} + +const DEBUG_CLASS: DebugFlags = DebugFlags::WorkQueue; + +const MAX_JOB_SLOTS: u32 = 127; + +/// An enum of possible errors that might cause a piece of work to fail execution. +#[derive(Copy, Clone, Debug, PartialEq, Eq)] +pub(crate) enum WorkError { + /// GPU timeout (command execution took too long). + Timeout, + /// GPU MMU fault (invalid access). + Fault(regs::FaultInfo), + /// Work failed due to an error caused by other concurrent GPU work. + Killed, + /// Channel error + ChannelError(ChannelErrorType), + /// The GPU crashed. + NoDevice, + /// Unknown reason. + Unknown, +} + +impl From for kernel::error::Error { + fn from(err: WorkError) -> Self { + match err { + WorkError::Timeout => ETIMEDOUT, + // Not EFAULT because that's for userspace faults + WorkError::Fault(_) => EIO, + WorkError::Unknown => ENODATA, + WorkError::Killed => ECANCELED, + WorkError::NoDevice => ENODEV, + WorkError::ChannelError(_) => EIO, + } + } +} + +/// A GPU context tracking structure, which must be explicitly invalidated when dropped. +pub(crate) struct GpuContext { + dev: driver::AsahiDevRef, + data: Option>>, +} +no_debug!(GpuContext); + +impl GpuContext { + /// Allocate a new GPU context. + pub(crate) fn new( + dev: &driver::AsahiDevice, + alloc: &mut gpu::KernelAllocators, + buffer: Arc, + ) -> Result { + Ok(GpuContext { + dev: dev.into(), + data: Some(KBox::new( + alloc.shared.new_object( + fw::workqueue::GpuContextData { _buffer: buffer }, + |_inner| Default::default(), + )?, + GFP_KERNEL, + )?), + }) + } + + /// Returns the GPU pointer to the inner GPU context data structure. + pub(crate) fn gpu_pointer(&self) -> GpuPointer<'_, fw::workqueue::GpuContextData> { + self.data.as_ref().unwrap().gpu_pointer() + } +} + +impl Drop for GpuContext { + fn drop(&mut self) { + mod_dev_dbg!(self.dev, "GpuContext: Freeing GPU context\n"); + let data = self.data.take().unwrap(); + (*self.dev).gpu.free_context(data); + } +} + +struct SubmittedWork +where + O: OpaqueCommandObject, + C: FnOnce(Option) + Send + Sync + 'static, +{ + object: O, + value: EventValue, + error: Option, + wptr: u32, + vm_slot: u32, + callback: Option, + fence: dma_fence::Fence, +} + +pub(crate) trait GenSubmittedWork: Send + Sync { + fn gpu_va(&self) -> NonZeroU64; + fn value(&self) -> event::EventValue; + fn wptr(&self) -> u32; + fn set_wptr(&mut self, wptr: u32); + fn mark_error(&mut self, error: WorkError); + fn complete(&mut self); + fn get_fence(&self) -> dma_fence::Fence; +} + +#[pin_data] +struct SubmittedWorkContainer { + #[pin] + work: Work, + inner: KBox, +} + +impl_has_work! { + impl HasWork for SubmittedWorkContainer { self.work } +} + +impl WorkItem for SubmittedWorkContainer { + type Pointer = Pin>; + + fn run(this: Pin>) { + mod_pr_debug!("WorkQueue: Freeing command @ {:?}\n", this.inner.gpu_va()); + } +} + +impl SubmittedWorkContainer { + fn inner_mut(self: Pin<&mut Self>) -> &mut KBox { + // SAFETY: inner does not require structural pinning. + unsafe { &mut self.get_unchecked_mut().inner } + } +} + +impl) + Send + Sync> GenSubmittedWork + for SubmittedWork +{ + fn gpu_va(&self) -> NonZeroU64 { + self.object.gpu_va() + } + + fn value(&self) -> event::EventValue { + self.value + } + + fn wptr(&self) -> u32 { + self.wptr + } + + fn set_wptr(&mut self, wptr: u32) { + self.wptr = wptr; + } + + fn complete(&mut self) { + if let Some(cb) = self.callback.take() { + cb(self.error); + } + } + + fn mark_error(&mut self, error: WorkError) { + mod_pr_debug!("WorkQueue: Command at value {:#x?} failed\n", self.value); + self.error = Some(match error { + WorkError::Fault(info) if info.vm_slot != self.vm_slot => WorkError::Killed, + err => err, + }); + } + + fn get_fence(&self) -> dma_fence::Fence { + self.fence.clone() + } +} + +/// Inner data for managing a single work queue. +#[versions(AGX)] +struct WorkQueueInner { + dev: driver::AsahiDevRef, + event_manager: Arc, + info: GpuObject, + new: bool, + pipe_type: PipeType, + size: u32, + wptr: u32, + pending: KVec>>, + last_token: Option, + pending_jobs: usize, + last_submitted: Option, + last_completed: Option, + event: Option<(event::Event, event::EventValue)>, + priority: u32, + commit_seq: u64, + submit_seq: u64, + event_seq: u64, +} + +/// An instance of a work queue. +#[versions(AGX)] +#[pin_data] +pub(crate) struct WorkQueue { + info_pointer: GpuWeakPointer, + #[pin] + inner: Mutex, +} + +#[versions(AGX)] +impl WorkQueueInner::ver { + /// Return the GPU done pointer, representing how many work items have been completed by the + /// GPU. + fn doneptr(&self) -> u32 { + self.info + .state + .with(|raw, _inner| raw.gpu_doneptr.load(Ordering::Acquire)) + } +} + +#[versions(AGX)] +#[derive(Copy, Clone)] +pub(crate) struct QueueEventInfo { + pub(crate) stamp_pointer: GpuWeakPointer, + pub(crate) fw_stamp_pointer: GpuWeakPointer, + pub(crate) slot: u32, + pub(crate) value: event::EventValue, + pub(crate) cmd_seq: u64, + pub(crate) event_seq: u64, + pub(crate) info_ptr: GpuWeakPointer, +} + +#[versions(AGX)] +pub(crate) struct Job { + wq: Arc, + event_info: QueueEventInfo::ver, + start_value: EventValue, + pending: KVec>>, + committed: bool, + submitted: bool, + event_count: usize, + fence: dma_fence::Fence, +} + +#[versions(AGX)] +pub(crate) struct JobSubmission<'a> { + inner: Option>, + wptr: u32, + event_count: usize, + command_count: usize, +} + +#[versions(AGX)] +impl Job::ver { + pub(crate) fn event_info(&self) -> QueueEventInfo::ver { + let mut info = self.event_info; + info.cmd_seq += self.pending.len() as u64; + info.event_seq += self.event_count as u64; + + info + } + + pub(crate) fn next_seq(&mut self) { + self.event_count += 1; + self.event_info.value.increment(); + } + + pub(crate) fn add( + &mut self, + command: O, + vm_slot: u32, + ) -> Result { + self.add_cb(command, vm_slot, |_| {}) + } + + pub(crate) fn add_cb( + &mut self, + command: O, + vm_slot: u32, + callback: impl FnOnce(Option) + Sync + Send + 'static, + ) -> Result { + if self.committed { + pr_err!("WorkQueue: Tried to mutate committed Job\n"); + return Err(EINVAL); + } + + let fence = self.fence.clone(); + let value = self.event_info.value.next(); + + self.pending.push( + KBox::try_pin_init( + try_pin_init!(SubmittedWorkContainer { + work <- new_work!("SubmittedWorkWrapper::work"), + inner: KBox::new(SubmittedWork::<_, _> { + object: command, + value, + error: None, + callback: Some(callback), + wptr: 0, + vm_slot, + fence, + }, GFP_KERNEL)? + }), + GFP_KERNEL, + )?, + GFP_KERNEL, + )?; + + Ok(()) + } + + pub(crate) fn commit(&mut self) -> Result { + if self.committed { + pr_err!("WorkQueue: Tried to commit committed Job\n"); + return Err(EINVAL); + } + + if self.pending.is_empty() { + pr_err!("WorkQueue: Job::commit() with no commands\n"); + return Err(EINVAL); + } + + let mut inner = self.wq.inner.lock(); + + let ev = inner.event.as_mut().expect("WorkQueue: Job lost its event"); + + if ev.1 != self.start_value { + pr_err!( + "WorkQueue: Job::commit() out of order (event slot {} {:?} != {:?}\n", + ev.0.slot(), + ev.1, + self.start_value + ); + return Err(EINVAL); + } + + ev.1 = self.event_info.value; + inner.commit_seq += self.pending.len() as u64; + inner.event_seq += self.event_count as u64; + self.committed = true; + + Ok(()) + } + + pub(crate) fn can_submit(&self) -> Option { + let inner = self.wq.inner.lock(); + if inner.free_slots() > self.event_count && inner.free_space() > self.pending.len() { + None + } else if let Some(work) = inner.pending.first() { + Some(work.inner.get_fence()) + } else { + pr_err!( + "WorkQueue: Cannot submit, but queue is empty? {} > {}, {} > {} (pend={} ls={:#x?} lc={:#x?}) ev={:#x?} cur={:#x?} slot {:?}\n", + inner.free_slots(), + self.event_count, + inner.free_space(), + self.pending.len(), + inner.pending.len(), + inner.last_submitted, + inner.last_completed, + inner.event.as_ref().map(|a| a.1), + inner.event.as_ref().map(|a| a.0.current()), + inner.event.as_ref().map(|a| a.0.slot()), + ); + None + } + } + + pub(crate) fn submit(&mut self) -> Result> { + if !self.committed { + pr_err!("WorkQueue: Tried to submit uncommitted Job\n"); + return Err(EINVAL); + } + + if self.submitted { + pr_err!("WorkQueue: Tried to submit Job twice\n"); + return Err(EINVAL); + } + + if self.pending.is_empty() { + pr_err!("WorkQueue: Job::submit() with no commands\n"); + return Err(EINVAL); + } + + let mut inner = self.wq.inner.lock(); + + if inner.submit_seq != self.event_info.cmd_seq { + pr_err!( + "WorkQueue: Job::submit() out of order (submit_seq {} != {})\n", + inner.submit_seq, + self.event_info.cmd_seq + ); + return Err(EINVAL); + } + + if inner.commit_seq < (self.event_info.cmd_seq + self.pending.len() as u64) { + pr_err!( + "WorkQueue: Job::submit() out of order (commit_seq {} != {})\n", + inner.commit_seq, + (self.event_info.cmd_seq + self.pending.len() as u64) + ); + return Err(EINVAL); + } + + let mut wptr = inner.wptr; + let command_count = self.pending.len(); + + if inner.free_space() <= command_count { + pr_err!("WorkQueue: Job does not fit in ring buffer\n"); + return Err(EBUSY); + } + + inner.pending.reserve(command_count, GFP_KERNEL)?; + + inner.last_submitted = Some(self.event_info.value); + mod_dev_dbg!( + inner.dev, + "WorkQueue: submitting {} cmds at {:#x?}, lc {:#x?}, cur {:#x?}, pending {}, events {}\n", + self.pending.len(), + inner.last_submitted, + inner.last_completed, + inner.event.as_ref().map(|a| a.0.current()), + inner.pending.len(), + self.event_count, + ); + + for mut command in self.pending.drain(..) { + command.as_mut().inner_mut().set_wptr(wptr); + + let next_wptr = (wptr + 1) % inner.size; + assert!(inner.doneptr() != next_wptr); + inner.info.ring[wptr as usize] = command.inner.gpu_va().get(); + wptr = next_wptr; + + // Cannot fail, since we did a reserve(1) above + inner + .pending + .push(command, GFP_KERNEL) + .expect("push() failed after reserve()"); + } + + self.submitted = true; + + Ok(JobSubmission::ver { + inner: Some(inner), + wptr, + command_count, + event_count: self.event_count, + }) + } +} + +#[versions(AGX)] +impl<'a> JobSubmission::ver<'a> { + pub(crate) fn run(mut self, channel: &mut channel::PipeChannel::ver) { + let command_count = self.command_count; + let mut inner = self.inner.take().expect("No inner?"); + let wptr = self.wptr; + core::mem::forget(self); + + inner + .info + .state + .with(|raw, _inner| raw.cpu_wptr.store(wptr, Ordering::Release)); + + inner.wptr = wptr; + + let event = inner.event.as_mut().expect("JobSubmission lost its event"); + + let event_slot = event.0.slot(); + + let msg = fw::channels::RunWorkQueueMsg::ver { + pipe_type: inner.pipe_type, + work_queue: Some(inner.info.weak_pointer()), + wptr: inner.wptr, + event_slot, + is_new: inner.new, + __pad: Default::default(), + }; + channel.send(&msg); + inner.new = false; + + inner.submit_seq += command_count as u64; + } + + pub(crate) fn pipe_type(&self) -> PipeType { + self.inner.as_ref().expect("No inner?").pipe_type + } + + pub(crate) fn priority(&self) -> u32 { + self.inner.as_ref().expect("No inner?").priority + } +} + +#[versions(AGX)] +impl Drop for Job::ver { + fn drop(&mut self) { + mod_pr_debug!("WorkQueue: Dropping Job\n"); + let mut inner = self.wq.inner.lock(); + + if !self.committed { + pr_info!( + "WorkQueue: Dropping uncommitted job with {} events\n", + self.event_count + ); + } + + if self.committed && !self.submitted { + let pipe_type = inner.pipe_type; + let event = inner.event.as_mut().expect("Job lost its event"); + pr_info!( + "WorkQueue({:?}): Roll back {} events (slot {} val {:#x?}) and {} commands\n", + pipe_type, + self.event_count, + event.0.slot(), + event.1, + self.pending.len() + ); + event.1.sub(self.event_count as u32); + inner.commit_seq -= self.pending.len() as u64; + inner.event_seq -= self.event_count as u64; + } + + inner.pending_jobs -= 1; + + if inner.pending.is_empty() && inner.pending_jobs == 0 { + mod_pr_debug!("WorkQueue({:?}): Dropping event\n", inner.pipe_type); + inner.event = None; + inner.last_submitted = None; + inner.last_completed = None; + } + mod_pr_debug!("WorkQueue({:?}): Dropped Job\n", inner.pipe_type); + } +} + +#[versions(AGX)] +impl<'a> Drop for JobSubmission::ver<'a> { + fn drop(&mut self) { + let inner = self.inner.as_mut().expect("No inner?"); + mod_pr_debug!("WorkQueue({:?}): Dropping JobSubmission\n", inner.pipe_type); + + let new_len = inner.pending.len() - self.command_count; + inner.pending.truncate(new_len); + + let pipe_type = inner.pipe_type; + let event = inner.event.as_mut().expect("JobSubmission lost its event"); + pr_info!( + "WorkQueue({:?}): JobSubmission: Roll back {} events (slot {} val {:#x?}) and {} commands\n", + pipe_type, + self.event_count, + event.0.slot(), + event.1, + self.command_count + ); + event.1.sub(self.event_count as u32); + let val = event.1; + inner.commit_seq -= self.command_count as u64; + inner.event_seq -= self.event_count as u64; + inner.last_submitted = Some(val); + mod_pr_debug!("WorkQueue({:?}): Dropped JobSubmission\n", inner.pipe_type); + } +} + +#[versions(AGX)] +impl WorkQueueInner::ver { + /// Return the number of free entries in the workqueue + pub(crate) fn free_space(&self) -> usize { + self.size as usize - self.pending.len() - 1 + } + + pub(crate) fn free_slots(&self) -> usize { + let busy_slots = if let Some(ls) = self.last_submitted { + let lc = self + .last_completed + .expect("last_submitted but not completed?"); + ls.delta(&lc) + } else { + 0 + }; + + ((MAX_JOB_SLOTS as i32) - busy_slots).max(0) as usize + } +} + +#[versions(AGX)] +impl WorkQueue::ver { + /// Create a new WorkQueue of a given type and priority. + #[allow(clippy::too_many_arguments)] + pub(crate) fn new( + dev: &driver::AsahiDevice, + alloc: &mut gpu::KernelAllocators, + event_manager: Arc, + gpu_context: Arc, + notifier_list: Arc>, + pipe_type: PipeType, + id: u64, + priority: u32, + size: u32, + ) -> Result> { + let gpu_buf = alloc.private.array_empty_tagged(0x2c18, b"GPBF")?; + let mut state = alloc.shared.new_default::()?; + let ring = alloc.shared.array_empty(size as usize)?; + let mut prio = *raw::PRIORITY.get(priority as usize).ok_or(EINVAL)?; + + if pipe_type == PipeType::Compute && !debug_enabled(DebugFlags::Debug0) { + // Hack to disable compute preemption until we fix it + prio.0 = 0; + prio.5 = 1; + } + + let inner = WorkQueueInner::ver { + dev: dev.into(), + event_manager, + // Use shared (coherent) state with verbose faults so we can dump state correctly + info: if debug_enabled(DebugFlags::VerboseFaults) { + &mut alloc.shared + } else { + &mut alloc.private + } + .new_init( + try_init!(QueueInfo::ver { + state: { + state.with_mut(|raw, _inner| { + raw.rb_size = size; + }); + state + }, + ring, + gpu_buf, + notifier_list: notifier_list, + gpu_context: gpu_context, + }), + |inner, _p| { + try_init!(raw::QueueInfo::ver { + state: inner.state.gpu_pointer(), + ring: inner.ring.gpu_pointer(), + notifier_list: inner.notifier_list.gpu_pointer(), + gpu_buf: inner.gpu_buf.gpu_pointer(), + gpu_rptr1: Default::default(), + gpu_rptr2: Default::default(), + gpu_rptr3: Default::default(), + event_id: AtomicI32::new(-1), + priority: prio, + unk_4c: -1, + uuid: id as u32, + unk_54: -1, + unk_58: Default::default(), + busy: Default::default(), + __pad: Default::default(), + #[ver(V >= V13_2 && G < G14X)] + unk_84_0: 0, + unk_84_state: Default::default(), + error_count: Default::default(), + unk_8c: 0, + unk_90: 0, + unk_94: 0, + pending: Default::default(), + unk_9c: 0, + gpu_context: inner.gpu_context.gpu_pointer(), + unk_a8: Default::default(), + #[ver(V >= V13_2 && G < G14X)] + unk_b0: 0, + }) + }, + )?, + new: true, + pipe_type, + size, + wptr: 0, + pending: KVec::new(), + last_token: None, + event: None, + priority, + pending_jobs: 0, + commit_seq: 0, + submit_seq: 0, + event_seq: 0, + last_completed: None, + last_submitted: None, + }; + + let info_pointer = inner.info.weak_pointer(); + + Arc::pin_init( + pin_init!(Self { + info_pointer, + inner <- match pipe_type { + PipeType::Vertex => new_mutex!(inner, "WorkQueue::inner (Vertex)"), + PipeType::Fragment => new_mutex!(inner, "WorkQueue::inner (Fragment)"), + PipeType::Compute => new_mutex!(inner, "WorkQueue::inner (Compute)"), + }, + }), + GFP_KERNEL, + ) + } + + pub(crate) fn event_info(&self) -> Option { + let inner = self.inner.lock(); + + inner.event.as_ref().map(|ev| QueueEventInfo::ver { + stamp_pointer: ev.0.stamp_pointer(), + fw_stamp_pointer: ev.0.fw_stamp_pointer(), + slot: ev.0.slot(), + value: ev.1, + cmd_seq: inner.commit_seq, + event_seq: inner.event_seq, + info_ptr: self.info_pointer, + }) + } + + pub(crate) fn new_job(self: &Arc, fence: dma_fence::Fence) -> Result { + let mut inner = self.inner.lock(); + + if inner.event.is_none() { + mod_pr_debug!("WorkQueue({:?}): Grabbing event\n", inner.pipe_type); + let event = inner.event_manager.get(inner.last_token, self.clone())?; + let cur = event.current(); + inner.last_token = Some(event.token()); + mod_pr_debug!( + "WorkQueue({:?}): Grabbed event slot {}: {:#x?}\n", + inner.pipe_type, + event.slot(), + cur + ); + inner.event = Some((event, cur)); + inner.last_submitted = Some(cur); + inner.last_completed = Some(cur); + } + + inner.pending_jobs += 1; + + let ev = &inner.event.as_ref().unwrap(); + + mod_pr_debug!( + "WorkQueue({:?}): New job at value {:#x?} slot {}\n", + inner.pipe_type, + ev.1, + ev.0.slot() + ); + Ok(Job::ver { + wq: self.clone(), + event_info: QueueEventInfo::ver { + stamp_pointer: ev.0.stamp_pointer(), + fw_stamp_pointer: ev.0.fw_stamp_pointer(), + slot: ev.0.slot(), + value: ev.1, + cmd_seq: inner.commit_seq, + event_seq: inner.event_seq, + info_ptr: self.info_pointer, + }, + start_value: ev.1, + pending: KVec::new(), + event_count: 0, + committed: false, + submitted: false, + fence, + }) + } + + pub(crate) fn pipe_type(&self) -> PipeType { + self.inner.lock().pipe_type + } + + pub(crate) fn dump_info(&self) { + pr_info!("WorkQueue @ {:?}:", self.info_pointer); + self.inner.lock().info.with(|raw, _inner| { + pr_info!(" GPU rptr1: {:#x}", raw.gpu_rptr1.load(Ordering::Relaxed)); + pr_info!(" GPU rptr1: {:#x}", raw.gpu_rptr2.load(Ordering::Relaxed)); + pr_info!(" GPU rptr1: {:#x}", raw.gpu_rptr3.load(Ordering::Relaxed)); + pr_info!(" Event ID: {:#x}", raw.event_id.load(Ordering::Relaxed)); + pr_info!(" Busy: {:#x}", raw.busy.load(Ordering::Relaxed)); + pr_info!(" Unk 84: {:#x}", raw.unk_84_state.load(Ordering::Relaxed)); + pr_info!( + " Error count: {:#x}", + raw.error_count.load(Ordering::Relaxed) + ); + pr_info!(" Pending: {:#x}", raw.pending.load(Ordering::Relaxed)); + }); + } + + pub(crate) fn info_pointer(&self) -> GpuWeakPointer { + self.info_pointer + } +} + +/// Trait used to erase the version-specific type of WorkQueues, to avoid leaking +/// version-specificity into the event module. +pub(crate) trait WorkQueue { + /// Cast as an Any type. + fn as_any(&self) -> &dyn Any; + + fn signal(&self) -> bool; + fn mark_error(&self, value: event::EventValue, error: WorkError); + fn fail_all(&self, error: WorkError); +} + +#[versions(AGX)] +impl WorkQueue for WorkQueue::ver { + fn as_any(&self) -> &dyn Any { + self + } + + /// Signal a workqueue that some work was completed. + /// + /// This will check the event stamp value to find out exactly how many commands were processed. + fn signal(&self) -> bool { + let mut inner = self.inner.lock(); + let event = inner.event.as_ref(); + let value = match event { + None => { + mod_pr_debug!("WorkQueue: signal() called but no event?\n"); + + if inner.pending_jobs > 0 || !inner.pending.is_empty() { + pr_crit!("WorkQueue: signal() called with no event and pending jobs.\n"); + } + return true; + } + Some(event) => event.0.current(), + }; + + if let Some(lc) = inner.last_completed { + if value < lc { + pr_err!( + "WorkQueue: event rolled back? cur {:#x?}, lc {:#x?}, ls {:#x?}", + value, + inner.last_completed, + inner.last_submitted + ); + } + } else { + pr_crit!("WorkQueue: signal() called with no last_completed.\n"); + } + inner.last_completed = Some(value); + + mod_pr_debug!( + "WorkQueue({:?}): Signaling event {:?} value {:#x?}\n", + inner.pipe_type, + inner.last_token, + value + ); + + let mut completed_commands: usize = 0; + + for cmd in inner.pending.iter() { + if cmd.inner.value() <= value { + mod_pr_debug!( + "WorkQueue({:?}): Command at value {:#x?} complete\n", + inner.pipe_type, + cmd.inner.value() + ); + completed_commands += 1; + } else { + break; + } + } + + if completed_commands == 0 { + return inner.pending.is_empty(); + } + + let last_wptr = inner.pending[completed_commands - 1].inner.wptr(); + let pipe_type = inner.pipe_type; + + for mut cmd in inner.pending.drain(..completed_commands) { + mod_pr_debug!( + "WorkQueue({:?}): Queueing command @ {:?} for cleanup\n", + pipe_type, + cmd.inner.gpu_va() + ); + cmd.as_mut().inner_mut().complete(); + workqueue::system().enqueue(cmd); + } + + mod_pr_debug!( + "WorkQueue({:?}): Completed {} commands, left pending {}, ls {:#x?}, lc {:#x?}\n", + inner.pipe_type, + completed_commands, + inner.pending.len(), + inner.last_submitted, + inner.last_completed, + ); + + inner + .info + .state + .with(|raw, _inner| raw.cpu_freeptr.store(last_wptr, Ordering::Release)); + + let empty = inner.pending.is_empty(); + if empty && inner.pending_jobs == 0 { + inner.event = None; + inner.last_submitted = None; + inner.last_completed = None; + } + + empty + } + + /// Mark this queue's work up to a certain stamp value as having failed. + fn mark_error(&self, value: event::EventValue, error: WorkError) { + // If anything is marked completed, we can consider it successful + // at this point, even if we didn't get the signal event yet. + self.signal(); + + let mut inner = self.inner.lock(); + + if inner.event.is_none() { + mod_pr_debug!("WorkQueue: signal_fault() called but no event?\n"); + + if inner.pending_jobs > 0 || !inner.pending.is_empty() { + pr_crit!("WorkQueue: signal_fault() called with no event and pending jobs.\n"); + } + return; + } + + mod_pr_debug!( + "WorkQueue({:?}): Signaling fault for event {:?} at value {:#x?}\n", + inner.pipe_type, + inner.last_token, + value + ); + + for cmd in inner.pending.iter_mut() { + if cmd.inner.value() <= value { + cmd.as_mut().inner_mut().mark_error(error); + } else { + break; + } + } + } + + /// Mark all of this queue's work as having failed, and complete it. + fn fail_all(&self, error: WorkError) { + // If anything is marked completed, we can consider it successful + // at this point, even if we didn't get the signal event yet. + self.signal(); + + let mut inner = self.inner.lock(); + + if inner.event.is_none() { + mod_pr_debug!("WorkQueue: fail_all() called but no event?\n"); + + if inner.pending_jobs > 0 || !inner.pending.is_empty() { + pr_crit!("WorkQueue: fail_all() called with no event and pending jobs.\n"); + } + return; + } + + mod_pr_debug!( + "WorkQueue({:?}): Failing all jobs {:?}\n", + inner.pipe_type, + error + ); + + let mut cmds = KVec::new(); + + core::mem::swap(&mut inner.pending, &mut cmds); + + if inner.pending_jobs == 0 { + inner.event = None; + } + + core::mem::drop(inner); + + for mut cmd in cmds { + cmd.as_mut().inner_mut().mark_error(error); + cmd.as_mut().inner_mut().complete(); + } + } +} diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c index 4a7ba0918eca19..3787db014501ed 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c @@ -365,13 +365,34 @@ void atmel_xlcdc_plane_setup_scaler(struct atmel_hlcdc_plane *plane, xfactor); /* - * With YCbCr 4:2:2 and YCbYcr 4:2:0 window resampling, configuration - * register LCDC_HEOCFG25.VXSCFACT and LCDC_HEOCFG27.HXSCFACT is half + * With YCbCr 4:2:0 window resampling, configuration register + * LCDC_HEOCFG25.VXSCFACT and LCDC_HEOCFG27.HXSCFACT values are half * the value of yfactor and xfactor. + * + * On the other hand, with YCbCr 4:2:2 window resampling, only the + * configuration register LCDC_HEOCFG27.HXSCFACT value is half the value + * of the xfactor; the value of LCDC_HEOCFG25.VXSCFACT is yfactor (no + * division by 2). */ - if (state->base.fb->format->format == DRM_FORMAT_YUV420) { + switch (state->base.fb->format->format) { + /* YCbCr 4:2:2 */ + case DRM_FORMAT_YUYV: + case DRM_FORMAT_UYVY: + case DRM_FORMAT_YVYU: + case DRM_FORMAT_VYUY: + case DRM_FORMAT_YUV422: + case DRM_FORMAT_NV61: + xfactor /= 2; + break; + + /* YCbCr 4:2:0 */ + case DRM_FORMAT_YUV420: + case DRM_FORMAT_NV21: yfactor /= 2; xfactor /= 2; + break; + default: + break; } atmel_hlcdc_layer_write_cfg(&plane->layer, desc->layout.scaler_config + 2, diff --git a/drivers/gpu/drm/bridge/synopsys/dw-dp.c b/drivers/gpu/drm/bridge/synopsys/dw-dp.c index 9bbfe8da3de026..e82960163018aa 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-dp.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-dp.c @@ -2060,33 +2060,41 @@ struct dw_dp *dw_dp_bind(struct device *dev, struct drm_encoder *encoder, } ret = drm_bridge_attach(encoder, bridge, NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR); - if (ret) + if (ret) { dev_err_probe(dev, ret, "Failed to attach bridge\n"); + goto unregister_aux; + } dw_dp_init_hw(dp); ret = phy_init(dp->phy); if (ret) { dev_err_probe(dev, ret, "phy init failed\n"); - return ERR_PTR(ret); + goto unregister_aux; } ret = devm_add_action_or_reset(dev, dw_dp_phy_exit, dp); if (ret) - return ERR_PTR(ret); + goto unregister_aux; dp->irq = platform_get_irq(pdev, 0); - if (dp->irq < 0) - return ERR_PTR(ret); + if (dp->irq < 0) { + ret = dp->irq; + goto unregister_aux; + } ret = devm_request_threaded_irq(dev, dp->irq, NULL, dw_dp_irq, IRQF_ONESHOT, dev_name(dev), dp); if (ret) { dev_err_probe(dev, ret, "failed to request irq\n"); - return ERR_PTR(ret); + goto unregister_aux; } return dp; + +unregister_aux: + drm_dp_aux_unregister(&dp->aux); + return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(dw_dp_bind); diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c index 39332c57f2c542..c85eb340e5a352 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c @@ -143,6 +143,7 @@ struct dw_hdmi_qp { } phy; struct regmap *regm; + int main_irq; unsigned long tmds_char_rate; }; @@ -1068,6 +1069,7 @@ struct dw_hdmi_qp *dw_hdmi_qp_bind(struct platform_device *pdev, dw_hdmi_qp_init_hw(hdmi); + hdmi->main_irq = plat_data->main_irq; ret = devm_request_threaded_irq(dev, plat_data->main_irq, dw_hdmi_qp_main_hardirq, NULL, IRQF_SHARED, dev_name(dev), hdmi); @@ -1106,9 +1108,16 @@ struct dw_hdmi_qp *dw_hdmi_qp_bind(struct platform_device *pdev, } EXPORT_SYMBOL_GPL(dw_hdmi_qp_bind); +void dw_hdmi_qp_suspend(struct device *dev, struct dw_hdmi_qp *hdmi) +{ + disable_irq(hdmi->main_irq); +} +EXPORT_SYMBOL_GPL(dw_hdmi_qp_suspend); + void dw_hdmi_qp_resume(struct device *dev, struct dw_hdmi_qp *hdmi) { dw_hdmi_qp_init_hw(hdmi); + enable_irq(hdmi->main_irq); } EXPORT_SYMBOL_GPL(dw_hdmi_qp_resume); diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index 033c44326552ab..fffb47b62f437b 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -429,7 +429,14 @@ static void sn65dsi83_handle_errors(struct sn65dsi83 *ctx) */ ret = regmap_read(ctx->regmap, REG_IRQ_STAT, &irq_stat); - if (ret || irq_stat) { + + /* + * Some hardware (Toradex Verdin AM62) is known to report the + * PLL_UNLOCK error interrupt while working without visible + * problems. In lack of a reliable way to discriminate such cases + * from user-visible PLL_UNLOCK cases, ignore that bit entirely. + */ + if (ret || irq_stat & ~REG_IRQ_STAT_CHA_PLL_UNLOCK) { /* * IRQ acknowledged is not always possible (the bridge can be in * a state where it doesn't answer anymore). To prevent an @@ -654,7 +661,7 @@ static void sn65dsi83_atomic_enable(struct drm_bridge *bridge, if (ctx->irq) { /* Enable irq to detect errors */ regmap_write(ctx->regmap, REG_IRQ_GLOBAL, REG_IRQ_GLOBAL_IRQ_EN); - regmap_write(ctx->regmap, REG_IRQ_EN, 0xff); + regmap_write(ctx->regmap, REG_IRQ_EN, 0xff & ~REG_IRQ_EN_CHA_PLL_UNLOCK_EN); } else { /* Use the polling task */ sn65dsi83_monitor_start(ctx); diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index d5ebe6ea0acbc5..bbec1c184f6521 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1162,8 +1162,18 @@ crtc_needs_disable(struct drm_crtc_state *old_state, new_state->self_refresh_active; } -static void -encoder_bridge_disable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_encoder_bridge_disable - disable bridges and encoder + * @dev: DRM device + * @state: the driver state object + * + * Loops over all connectors in the current state and if the CRTC needs + * it, disables the bridge chain all the way, then disables the encoder + * afterwards. + */ +void +drm_atomic_helper_commit_encoder_bridge_disable(struct drm_device *dev, + struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *old_conn_state, *new_conn_state; @@ -1229,9 +1239,18 @@ encoder_bridge_disable(struct drm_device *dev, struct drm_atomic_state *state) } } } +EXPORT_SYMBOL(drm_atomic_helper_commit_encoder_bridge_disable); -static void -crtc_disable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_crtc_disable - disable CRTSs + * @dev: DRM device + * @state: the driver state object + * + * Loops over all CRTCs in the current state and if the CRTC needs + * it, disables it. + */ +void +drm_atomic_helper_commit_crtc_disable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_crtc *crtc; struct drm_crtc_state *old_crtc_state, *new_crtc_state; @@ -1282,9 +1301,18 @@ crtc_disable(struct drm_device *dev, struct drm_atomic_state *state) drm_crtc_vblank_put(crtc); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_crtc_disable); -static void -encoder_bridge_post_disable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_encoder_bridge_post_disable - post-disable encoder bridges + * @dev: DRM device + * @state: the driver state object + * + * Loops over all connectors in the current state and if the CRTC needs + * it, post-disables all encoder bridges. + */ +void +drm_atomic_helper_commit_encoder_bridge_post_disable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *old_conn_state, *new_conn_state; @@ -1335,15 +1363,16 @@ encoder_bridge_post_disable(struct drm_device *dev, struct drm_atomic_state *sta drm_bridge_put(bridge); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_encoder_bridge_post_disable); static void disable_outputs(struct drm_device *dev, struct drm_atomic_state *state) { - encoder_bridge_disable(dev, state); + drm_atomic_helper_commit_encoder_bridge_disable(dev, state); - crtc_disable(dev, state); + drm_atomic_helper_commit_encoder_bridge_post_disable(dev, state); - encoder_bridge_post_disable(dev, state); + drm_atomic_helper_commit_crtc_disable(dev, state); } /** @@ -1446,8 +1475,17 @@ void drm_atomic_helper_calc_timestamping_constants(struct drm_atomic_state *stat } EXPORT_SYMBOL(drm_atomic_helper_calc_timestamping_constants); -static void -crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_crtc_set_mode - set the new mode + * @dev: DRM device + * @state: the driver state object + * + * Loops over all connectors in the current state and if the mode has + * changed, change the mode of the CRTC, then call down the bridge + * chain and change the mode in all bridges as well. + */ +void +drm_atomic_helper_commit_crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_crtc *crtc; struct drm_crtc_state *new_crtc_state; @@ -1508,6 +1546,7 @@ crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *state) drm_bridge_put(bridge); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_crtc_set_mode); /** * drm_atomic_helper_commit_modeset_disables - modeset commit to disable outputs @@ -1531,12 +1570,21 @@ void drm_atomic_helper_commit_modeset_disables(struct drm_device *dev, drm_atomic_helper_update_legacy_modeset_state(dev, state); drm_atomic_helper_calc_timestamping_constants(state); - crtc_set_mode(dev, state); + drm_atomic_helper_commit_crtc_set_mode(dev, state); } EXPORT_SYMBOL(drm_atomic_helper_commit_modeset_disables); -static void drm_atomic_helper_commit_writebacks(struct drm_device *dev, - struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_writebacks - issue writebacks + * @dev: DRM device + * @state: atomic state object being committed + * + * This loops over the connectors, checks if the new state requires + * a writeback job to be issued and in that case issues an atomic + * commit on each connector. + */ +void drm_atomic_helper_commit_writebacks(struct drm_device *dev, + struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *new_conn_state; @@ -1555,9 +1603,18 @@ static void drm_atomic_helper_commit_writebacks(struct drm_device *dev, } } } +EXPORT_SYMBOL(drm_atomic_helper_commit_writebacks); -static void -encoder_bridge_pre_enable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_encoder_bridge_pre_enable - pre-enable bridges + * @dev: DRM device + * @state: atomic state object being committed + * + * This loops over the connectors and if the CRTC needs it, pre-enables + * the entire bridge chain. + */ +void +drm_atomic_helper_commit_encoder_bridge_pre_enable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *new_conn_state; @@ -1588,9 +1645,18 @@ encoder_bridge_pre_enable(struct drm_device *dev, struct drm_atomic_state *state drm_bridge_put(bridge); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_encoder_bridge_pre_enable); -static void -crtc_enable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_crtc_enable - enables the CRTCs + * @dev: DRM device + * @state: atomic state object being committed + * + * This loops over CRTCs in the new state, and of the CRTC needs + * it, enables it. + */ +void +drm_atomic_helper_commit_crtc_enable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_crtc *crtc; struct drm_crtc_state *old_crtc_state; @@ -1619,9 +1685,18 @@ crtc_enable(struct drm_device *dev, struct drm_atomic_state *state) } } } +EXPORT_SYMBOL(drm_atomic_helper_commit_crtc_enable); -static void -encoder_bridge_enable(struct drm_device *dev, struct drm_atomic_state *state) +/** + * drm_atomic_helper_commit_encoder_bridge_enable - enables the bridges + * @dev: DRM device + * @state: atomic state object being committed + * + * This loops over all connectors in the new state, and of the CRTC needs + * it, enables the entire bridge chain. + */ +void +drm_atomic_helper_commit_encoder_bridge_enable(struct drm_device *dev, struct drm_atomic_state *state) { struct drm_connector *connector; struct drm_connector_state *new_conn_state; @@ -1664,6 +1739,7 @@ encoder_bridge_enable(struct drm_device *dev, struct drm_atomic_state *state) drm_bridge_put(bridge); } } +EXPORT_SYMBOL(drm_atomic_helper_commit_encoder_bridge_enable); /** * drm_atomic_helper_commit_modeset_enables - modeset commit to enable outputs @@ -1682,11 +1758,11 @@ encoder_bridge_enable(struct drm_device *dev, struct drm_atomic_state *state) void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev, struct drm_atomic_state *state) { - encoder_bridge_pre_enable(dev, state); + drm_atomic_helper_commit_crtc_enable(dev, state); - crtc_enable(dev, state); + drm_atomic_helper_commit_encoder_bridge_pre_enable(dev, state); - encoder_bridge_enable(dev, state); + drm_atomic_helper_commit_encoder_bridge_enable(dev, state); drm_atomic_helper_commit_writebacks(dev, state); } diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index a94061f373de54..3f1a9892f2a392 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -12,8 +12,17 @@ #include +enum drm_buddy_free_tree { + DRM_BUDDY_CLEAR_TREE = 0, + DRM_BUDDY_DIRTY_TREE, + DRM_BUDDY_MAX_FREE_TREES, +}; + static struct kmem_cache *slab_blocks; +#define for_each_free_tree(tree) \ + for ((tree) = 0; (tree) < DRM_BUDDY_MAX_FREE_TREES; (tree)++) + static struct drm_buddy_block *drm_block_alloc(struct drm_buddy *mm, struct drm_buddy_block *parent, unsigned int order, @@ -31,6 +40,8 @@ static struct drm_buddy_block *drm_block_alloc(struct drm_buddy *mm, block->header |= order; block->parent = parent; + RB_CLEAR_NODE(&block->rb); + BUG_ON(block->header & DRM_BUDDY_HEADER_UNUSED); return block; } @@ -41,23 +52,64 @@ static void drm_block_free(struct drm_buddy *mm, kmem_cache_free(slab_blocks, block); } -static void list_insert_sorted(struct drm_buddy *mm, - struct drm_buddy_block *block) +static enum drm_buddy_free_tree +get_block_tree(struct drm_buddy_block *block) { - struct drm_buddy_block *node; - struct list_head *head; + return drm_buddy_block_is_clear(block) ? + DRM_BUDDY_CLEAR_TREE : DRM_BUDDY_DIRTY_TREE; +} - head = &mm->free_list[drm_buddy_block_order(block)]; - if (list_empty(head)) { - list_add(&block->link, head); - return; - } +static struct drm_buddy_block * +rbtree_get_free_block(const struct rb_node *node) +{ + return node ? rb_entry(node, struct drm_buddy_block, rb) : NULL; +} - list_for_each_entry(node, head, link) - if (drm_buddy_block_offset(block) < drm_buddy_block_offset(node)) - break; +static struct drm_buddy_block * +rbtree_last_free_block(struct rb_root *root) +{ + return rbtree_get_free_block(rb_last(root)); +} - __list_add(&block->link, node->link.prev, &node->link); +static bool rbtree_is_empty(struct rb_root *root) +{ + return RB_EMPTY_ROOT(root); +} + +static bool drm_buddy_block_offset_less(const struct drm_buddy_block *block, + const struct drm_buddy_block *node) +{ + return drm_buddy_block_offset(block) < drm_buddy_block_offset(node); +} + +static bool rbtree_block_offset_less(struct rb_node *block, + const struct rb_node *node) +{ + return drm_buddy_block_offset_less(rbtree_get_free_block(block), + rbtree_get_free_block(node)); +} + +static void rbtree_insert(struct drm_buddy *mm, + struct drm_buddy_block *block, + enum drm_buddy_free_tree tree) +{ + rb_add(&block->rb, + &mm->free_trees[tree][drm_buddy_block_order(block)], + rbtree_block_offset_less); +} + +static void rbtree_remove(struct drm_buddy *mm, + struct drm_buddy_block *block) +{ + unsigned int order = drm_buddy_block_order(block); + enum drm_buddy_free_tree tree; + struct rb_root *root; + + tree = get_block_tree(block); + root = &mm->free_trees[tree][order]; + + rb_erase(&block->rb, root); + RB_CLEAR_NODE(&block->rb); } static void clear_reset(struct drm_buddy_block *block) @@ -70,29 +122,34 @@ static void mark_cleared(struct drm_buddy_block *block) block->header |= DRM_BUDDY_HEADER_CLEAR; } -static void mark_allocated(struct drm_buddy_block *block) +static void mark_allocated(struct drm_buddy *mm, + struct drm_buddy_block *block) { block->header &= ~DRM_BUDDY_HEADER_STATE; block->header |= DRM_BUDDY_ALLOCATED; - list_del(&block->link); + rbtree_remove(mm, block); } static void mark_free(struct drm_buddy *mm, struct drm_buddy_block *block) { + enum drm_buddy_free_tree tree; + block->header &= ~DRM_BUDDY_HEADER_STATE; block->header |= DRM_BUDDY_FREE; - list_insert_sorted(mm, block); + tree = get_block_tree(block); + rbtree_insert(mm, block, tree); } -static void mark_split(struct drm_buddy_block *block) +static void mark_split(struct drm_buddy *mm, + struct drm_buddy_block *block) { block->header &= ~DRM_BUDDY_HEADER_STATE; block->header |= DRM_BUDDY_SPLIT; - list_del(&block->link); + rbtree_remove(mm, block); } static inline bool overlaps(u64 s1, u64 e1, u64 s2, u64 e2) @@ -148,7 +205,7 @@ static unsigned int __drm_buddy_free(struct drm_buddy *mm, mark_cleared(parent); } - list_del(&buddy->link); + rbtree_remove(mm, buddy); if (force_merge && drm_buddy_block_is_clear(buddy)) mm->clear_avail -= drm_buddy_block_size(mm, buddy); @@ -169,7 +226,7 @@ static int __force_merge(struct drm_buddy *mm, u64 end, unsigned int min_order) { - unsigned int order; + unsigned int tree, order; int i; if (!min_order) @@ -178,44 +235,48 @@ static int __force_merge(struct drm_buddy *mm, if (min_order > mm->max_order) return -EINVAL; - for (i = min_order - 1; i >= 0; i--) { - struct drm_buddy_block *block, *prev; + for_each_free_tree(tree) { + for (i = min_order - 1; i >= 0; i--) { + struct rb_node *iter = rb_last(&mm->free_trees[tree][i]); - list_for_each_entry_safe_reverse(block, prev, &mm->free_list[i], link) { - struct drm_buddy_block *buddy; - u64 block_start, block_end; + while (iter) { + struct drm_buddy_block *block, *buddy; + u64 block_start, block_end; - if (!block->parent) - continue; + block = rbtree_get_free_block(iter); + iter = rb_prev(iter); - block_start = drm_buddy_block_offset(block); - block_end = block_start + drm_buddy_block_size(mm, block) - 1; + if (!block || !block->parent) + continue; - if (!contains(start, end, block_start, block_end)) - continue; + block_start = drm_buddy_block_offset(block); + block_end = block_start + drm_buddy_block_size(mm, block) - 1; - buddy = __get_buddy(block); - if (!drm_buddy_block_is_free(buddy)) - continue; + if (!contains(start, end, block_start, block_end)) + continue; - WARN_ON(drm_buddy_block_is_clear(block) == - drm_buddy_block_is_clear(buddy)); + buddy = __get_buddy(block); + if (!drm_buddy_block_is_free(buddy)) + continue; - /* - * If the prev block is same as buddy, don't access the - * block in the next iteration as we would free the - * buddy block as part of the free function. - */ - if (prev == buddy) - prev = list_prev_entry(prev, link); + WARN_ON(drm_buddy_block_is_clear(block) == + drm_buddy_block_is_clear(buddy)); - list_del(&block->link); - if (drm_buddy_block_is_clear(block)) - mm->clear_avail -= drm_buddy_block_size(mm, block); + /* + * Advance to the next node when the current node is the buddy, + * as freeing the block will also remove its buddy from the tree. + */ + if (iter == &buddy->rb) + iter = rb_prev(iter); - order = __drm_buddy_free(mm, block, true); - if (order >= min_order) - return 0; + rbtree_remove(mm, block); + if (drm_buddy_block_is_clear(block)) + mm->clear_avail -= drm_buddy_block_size(mm, block); + + order = __drm_buddy_free(mm, block, true); + if (order >= min_order) + return 0; + } } } @@ -236,8 +297,8 @@ static int __force_merge(struct drm_buddy *mm, */ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size) { - unsigned int i; - u64 offset; + unsigned int i, j, root_count = 0; + u64 offset = 0; if (size < chunk_size) return -EINVAL; @@ -258,14 +319,22 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size) BUG_ON(mm->max_order > DRM_BUDDY_MAX_ORDER); - mm->free_list = kmalloc_array(mm->max_order + 1, - sizeof(struct list_head), - GFP_KERNEL); - if (!mm->free_list) + mm->free_trees = kmalloc_array(DRM_BUDDY_MAX_FREE_TREES, + sizeof(*mm->free_trees), + GFP_KERNEL); + if (!mm->free_trees) return -ENOMEM; - for (i = 0; i <= mm->max_order; ++i) - INIT_LIST_HEAD(&mm->free_list[i]); + for_each_free_tree(i) { + mm->free_trees[i] = kmalloc_array(mm->max_order + 1, + sizeof(struct rb_root), + GFP_KERNEL); + if (!mm->free_trees[i]) + goto out_free_tree; + + for (j = 0; j <= mm->max_order; ++j) + mm->free_trees[i][j] = RB_ROOT; + } mm->n_roots = hweight64(size); @@ -273,10 +342,7 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size) sizeof(struct drm_buddy_block *), GFP_KERNEL); if (!mm->roots) - goto out_free_list; - - offset = 0; - i = 0; + goto out_free_tree; /* * Split into power-of-two blocks, in case we are given a size that is @@ -296,24 +362,26 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size) mark_free(mm, root); - BUG_ON(i > mm->max_order); + BUG_ON(root_count > mm->max_order); BUG_ON(drm_buddy_block_size(mm, root) < chunk_size); - mm->roots[i] = root; + mm->roots[root_count] = root; offset += root_size; size -= root_size; - i++; + root_count++; } while (size); return 0; out_free_roots: - while (i--) - drm_block_free(mm, mm->roots[i]); + while (root_count--) + drm_block_free(mm, mm->roots[root_count]); kfree(mm->roots); -out_free_list: - kfree(mm->free_list); +out_free_tree: + while (i--) + kfree(mm->free_trees[i]); + kfree(mm->free_trees); return -ENOMEM; } EXPORT_SYMBOL(drm_buddy_init); @@ -323,7 +391,7 @@ EXPORT_SYMBOL(drm_buddy_init); * * @mm: DRM buddy manager to free * - * Cleanup memory manager resources and the freelist + * Cleanup memory manager resources and the freetree */ void drm_buddy_fini(struct drm_buddy *mm) { @@ -349,8 +417,10 @@ void drm_buddy_fini(struct drm_buddy *mm) WARN_ON(mm->avail != mm->size); + for_each_free_tree(i) + kfree(mm->free_trees[i]); + kfree(mm->free_trees); kfree(mm->roots); - kfree(mm->free_list); } EXPORT_SYMBOL(drm_buddy_fini); @@ -374,8 +444,7 @@ static int split_block(struct drm_buddy *mm, return -ENOMEM; } - mark_free(mm, block->left); - mark_free(mm, block->right); + mark_split(mm, block); if (drm_buddy_block_is_clear(block)) { mark_cleared(block->left); @@ -383,7 +452,8 @@ static int split_block(struct drm_buddy *mm, clear_reset(block); } - mark_split(block); + mark_free(mm, block->left); + mark_free(mm, block->right); return 0; } @@ -412,10 +482,11 @@ EXPORT_SYMBOL(drm_get_buddy); * @is_clear: blocks clear state * * Reset the clear state based on @is_clear value for each block - * in the freelist. + * in the freetree. */ void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear) { + enum drm_buddy_free_tree src_tree, dst_tree; u64 root_size, size, start; unsigned int order; int i; @@ -430,19 +501,24 @@ void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear) size -= root_size; } + src_tree = is_clear ? DRM_BUDDY_DIRTY_TREE : DRM_BUDDY_CLEAR_TREE; + dst_tree = is_clear ? DRM_BUDDY_CLEAR_TREE : DRM_BUDDY_DIRTY_TREE; + for (i = 0; i <= mm->max_order; ++i) { - struct drm_buddy_block *block; - - list_for_each_entry_reverse(block, &mm->free_list[i], link) { - if (is_clear != drm_buddy_block_is_clear(block)) { - if (is_clear) { - mark_cleared(block); - mm->clear_avail += drm_buddy_block_size(mm, block); - } else { - clear_reset(block); - mm->clear_avail -= drm_buddy_block_size(mm, block); - } + struct rb_root *root = &mm->free_trees[src_tree][i]; + struct drm_buddy_block *block, *tmp; + + rbtree_postorder_for_each_entry_safe(block, tmp, root, rb) { + rbtree_remove(mm, block); + if (is_clear) { + mark_cleared(block); + mm->clear_avail += drm_buddy_block_size(mm, block); + } else { + clear_reset(block); + mm->clear_avail -= drm_buddy_block_size(mm, block); } + + rbtree_insert(mm, block, dst_tree); } } } @@ -632,23 +708,17 @@ __drm_buddy_alloc_range_bias(struct drm_buddy *mm, } static struct drm_buddy_block * -get_maxblock(struct drm_buddy *mm, unsigned int order, - unsigned long flags) +get_maxblock(struct drm_buddy *mm, + unsigned int order, + enum drm_buddy_free_tree tree) { struct drm_buddy_block *max_block = NULL, *block = NULL; + struct rb_root *root; unsigned int i; for (i = order; i <= mm->max_order; ++i) { - struct drm_buddy_block *tmp_block; - - list_for_each_entry_reverse(tmp_block, &mm->free_list[i], link) { - if (block_incompatible(tmp_block, flags)) - continue; - - block = tmp_block; - break; - } - + root = &mm->free_trees[tree][i]; + block = rbtree_last_free_block(root); if (!block) continue; @@ -667,46 +737,44 @@ get_maxblock(struct drm_buddy *mm, unsigned int order, } static struct drm_buddy_block * -alloc_from_freelist(struct drm_buddy *mm, +alloc_from_freetree(struct drm_buddy *mm, unsigned int order, unsigned long flags) { struct drm_buddy_block *block = NULL; + struct rb_root *root; + enum drm_buddy_free_tree tree; unsigned int tmp; int err; + tree = (flags & DRM_BUDDY_CLEAR_ALLOCATION) ? + DRM_BUDDY_CLEAR_TREE : DRM_BUDDY_DIRTY_TREE; + if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) { - block = get_maxblock(mm, order, flags); + block = get_maxblock(mm, order, tree); if (block) /* Store the obtained block order */ tmp = drm_buddy_block_order(block); } else { for (tmp = order; tmp <= mm->max_order; ++tmp) { - struct drm_buddy_block *tmp_block; - - list_for_each_entry_reverse(tmp_block, &mm->free_list[tmp], link) { - if (block_incompatible(tmp_block, flags)) - continue; - - block = tmp_block; - break; - } - + /* Get RB tree root for this order and tree */ + root = &mm->free_trees[tree][tmp]; + block = rbtree_last_free_block(root); if (block) break; } } if (!block) { - /* Fallback method */ + /* Try allocating from the other tree */ + tree = (tree == DRM_BUDDY_CLEAR_TREE) ? + DRM_BUDDY_DIRTY_TREE : DRM_BUDDY_CLEAR_TREE; + for (tmp = order; tmp <= mm->max_order; ++tmp) { - if (!list_empty(&mm->free_list[tmp])) { - block = list_last_entry(&mm->free_list[tmp], - struct drm_buddy_block, - link); - if (block) - break; - } + root = &mm->free_trees[tree][tmp]; + block = rbtree_last_free_block(root); + if (block) + break; } if (!block) @@ -771,7 +839,7 @@ static int __alloc_range(struct drm_buddy *mm, if (contains(start, end, block_start, block_end)) { if (drm_buddy_block_is_free(block)) { - mark_allocated(block); + mark_allocated(mm, block); total_allocated += drm_buddy_block_size(mm, block); mm->avail -= drm_buddy_block_size(mm, block); if (drm_buddy_block_is_clear(block)) @@ -849,10 +917,9 @@ static int __alloc_contig_try_harder(struct drm_buddy *mm, { u64 rhs_offset, lhs_offset, lhs_size, filled; struct drm_buddy_block *block; - struct list_head *list; + unsigned int tree, order; LIST_HEAD(blocks_lhs); unsigned long pages; - unsigned int order; u64 modify_size; int err; @@ -862,35 +929,45 @@ static int __alloc_contig_try_harder(struct drm_buddy *mm, if (order == 0) return -ENOSPC; - list = &mm->free_list[order]; - if (list_empty(list)) - return -ENOSPC; + for_each_free_tree(tree) { + struct rb_root *root; + struct rb_node *iter; + + root = &mm->free_trees[tree][order]; + if (rbtree_is_empty(root)) + continue; - list_for_each_entry_reverse(block, list, link) { - /* Allocate blocks traversing RHS */ - rhs_offset = drm_buddy_block_offset(block); - err = __drm_buddy_alloc_range(mm, rhs_offset, size, - &filled, blocks); - if (!err || err != -ENOSPC) - return err; - - lhs_size = max((size - filled), min_block_size); - if (!IS_ALIGNED(lhs_size, min_block_size)) - lhs_size = round_up(lhs_size, min_block_size); - - /* Allocate blocks traversing LHS */ - lhs_offset = drm_buddy_block_offset(block) - lhs_size; - err = __drm_buddy_alloc_range(mm, lhs_offset, lhs_size, - NULL, &blocks_lhs); - if (!err) { - list_splice(&blocks_lhs, blocks); - return 0; - } else if (err != -ENOSPC) { + iter = rb_last(root); + while (iter) { + block = rbtree_get_free_block(iter); + + /* Allocate blocks traversing RHS */ + rhs_offset = drm_buddy_block_offset(block); + err = __drm_buddy_alloc_range(mm, rhs_offset, size, + &filled, blocks); + if (!err || err != -ENOSPC) + return err; + + lhs_size = max((size - filled), min_block_size); + if (!IS_ALIGNED(lhs_size, min_block_size)) + lhs_size = round_up(lhs_size, min_block_size); + + /* Allocate blocks traversing LHS */ + lhs_offset = drm_buddy_block_offset(block) - lhs_size; + err = __drm_buddy_alloc_range(mm, lhs_offset, lhs_size, + NULL, &blocks_lhs); + if (!err) { + list_splice(&blocks_lhs, blocks); + return 0; + } else if (err != -ENOSPC) { + drm_buddy_free_list_internal(mm, blocks); + return err; + } + /* Free blocks for the next iteration */ drm_buddy_free_list_internal(mm, blocks); - return err; + + iter = rb_prev(iter); } - /* Free blocks for the next iteration */ - drm_buddy_free_list_internal(mm, blocks); } return -ENOSPC; @@ -976,7 +1053,7 @@ int drm_buddy_block_trim(struct drm_buddy *mm, list_add(&block->tmp_link, &dfs); err = __alloc_range(mm, &dfs, new_start, new_size, blocks, NULL); if (err) { - mark_allocated(block); + mark_allocated(mm, block); mm->avail -= drm_buddy_block_size(mm, block); if (drm_buddy_block_is_clear(block)) mm->clear_avail -= drm_buddy_block_size(mm, block); @@ -999,8 +1076,8 @@ __drm_buddy_alloc_blocks(struct drm_buddy *mm, return __drm_buddy_alloc_range_bias(mm, start, end, order, flags); else - /* Allocate from freelist */ - return alloc_from_freelist(mm, order, flags); + /* Allocate from freetree */ + return alloc_from_freetree(mm, order, flags); } /** @@ -1017,8 +1094,8 @@ __drm_buddy_alloc_blocks(struct drm_buddy *mm, * alloc_range_bias() called on range limitations, which traverses * the tree and returns the desired block. * - * alloc_from_freelist() called when *no* range restrictions - * are enforced, which picks the block from the freelist. + * alloc_from_freetree() called when *no* range restrictions + * are enforced, which picks the block from the freetree. * * Returns: * 0 on success, error code on failure. @@ -1120,7 +1197,7 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm, } } while (1); - mark_allocated(block); + mark_allocated(mm, block); mm->avail -= drm_buddy_block_size(mm, block); if (drm_buddy_block_is_clear(block)) mm->clear_avail -= drm_buddy_block_size(mm, block); @@ -1201,12 +1278,18 @@ void drm_buddy_print(struct drm_buddy *mm, struct drm_printer *p) mm->chunk_size >> 10, mm->size >> 20, mm->avail >> 20, mm->clear_avail >> 20); for (order = mm->max_order; order >= 0; order--) { - struct drm_buddy_block *block; + struct drm_buddy_block *block, *tmp; + struct rb_root *root; u64 count = 0, free; + unsigned int tree; - list_for_each_entry(block, &mm->free_list[order], link) { - BUG_ON(!drm_buddy_block_is_free(block)); - count++; + for_each_free_tree(tree) { + root = &mm->free_trees[tree][order]; + + rbtree_postorder_for_each_entry_safe(block, tmp, root, rb) { + BUG_ON(!drm_buddy_block_is_free(block)); + count++; + } } drm_printf(p, "order-%2d ", order); diff --git a/drivers/gpu/drm/drm_displayid.c b/drivers/gpu/drm/drm_displayid.c index b4fd43783c5096..58d0bb6d267689 100644 --- a/drivers/gpu/drm/drm_displayid.c +++ b/drivers/gpu/drm/drm_displayid.c @@ -9,6 +9,34 @@ #include "drm_crtc_internal.h" #include "drm_displayid_internal.h" +enum { + QUIRK_IGNORE_CHECKSUM, +}; + +struct displayid_quirk { + const struct drm_edid_ident ident; + u8 quirks; +}; + +static const struct displayid_quirk quirks[] = { + { + .ident = DRM_EDID_IDENT_INIT('C', 'S', 'O', 5142, "MNE007ZA1-5"), + .quirks = BIT(QUIRK_IGNORE_CHECKSUM), + }, +}; + +static u8 get_quirks(const struct drm_edid *drm_edid) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(quirks); i++) { + if (drm_edid_match(drm_edid, &quirks[i].ident)) + return quirks[i].quirks; + } + + return 0; +} + static const struct displayid_header * displayid_get_header(const u8 *displayid, int length, int index) { @@ -23,7 +51,7 @@ displayid_get_header(const u8 *displayid, int length, int index) } static const struct displayid_header * -validate_displayid(const u8 *displayid, int length, int idx) +validate_displayid(const u8 *displayid, int length, int idx, bool ignore_checksum) { int i, dispid_length; u8 csum = 0; @@ -41,33 +69,35 @@ validate_displayid(const u8 *displayid, int length, int idx) for (i = 0; i < dispid_length; i++) csum += displayid[idx + i]; if (csum) { - DRM_NOTE("DisplayID checksum invalid, remainder is %d\n", csum); - return ERR_PTR(-EINVAL); + DRM_NOTE("DisplayID checksum invalid, remainder is %d%s\n", csum, + ignore_checksum ? " (ignoring)" : ""); + + if (!ignore_checksum) + return ERR_PTR(-EINVAL); } return base; } -static const u8 *drm_find_displayid_extension(const struct drm_edid *drm_edid, - int *length, int *idx, - int *ext_index) +static const u8 *find_next_displayid_extension(struct displayid_iter *iter) { const struct displayid_header *base; const u8 *displayid; + bool ignore_checksum = iter->quirks & BIT(QUIRK_IGNORE_CHECKSUM); - displayid = drm_edid_find_extension(drm_edid, DISPLAYID_EXT, ext_index); + displayid = drm_edid_find_extension(iter->drm_edid, DISPLAYID_EXT, &iter->ext_index); if (!displayid) return NULL; /* EDID extensions block checksum isn't for us */ - *length = EDID_LENGTH - 1; - *idx = 1; + iter->length = EDID_LENGTH - 1; + iter->idx = 1; - base = validate_displayid(displayid, *length, *idx); + base = validate_displayid(displayid, iter->length, iter->idx, ignore_checksum); if (IS_ERR(base)) return NULL; - *length = *idx + sizeof(*base) + base->bytes; + iter->length = iter->idx + sizeof(*base) + base->bytes; return displayid; } @@ -78,6 +108,7 @@ void displayid_iter_edid_begin(const struct drm_edid *drm_edid, memset(iter, 0, sizeof(*iter)); iter->drm_edid = drm_edid; + iter->quirks = get_quirks(drm_edid); } static const struct displayid_block * @@ -126,10 +157,7 @@ __displayid_iter_next(struct displayid_iter *iter) /* The first section we encounter is the base section */ bool base_section = !iter->section; - iter->section = drm_find_displayid_extension(iter->drm_edid, - &iter->length, - &iter->idx, - &iter->ext_index); + iter->section = find_next_displayid_extension(iter); if (!iter->section) { iter->drm_edid = NULL; return NULL; diff --git a/drivers/gpu/drm/drm_displayid_internal.h b/drivers/gpu/drm/drm_displayid_internal.h index 957dd0619f5c5c..5b1b32f7351662 100644 --- a/drivers/gpu/drm/drm_displayid_internal.h +++ b/drivers/gpu/drm/drm_displayid_internal.h @@ -167,6 +167,8 @@ struct displayid_iter { u8 version; u8 primary_use; + + u8 quirks; }; void displayid_iter_edid_begin(const struct drm_edid *drm_edid, diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index f884d155a832a3..11e7141c1524b8 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -970,33 +970,41 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, { struct drm_gem_change_handle *args = data; struct drm_gem_object *obj; - int ret; + int handle, ret; if (!drm_core_check_feature(dev, DRIVER_GEM)) return -EOPNOTSUPP; + /* idr_alloc() limitation. */ + if (args->new_handle > INT_MAX) + return -EINVAL; + handle = args->new_handle; + obj = drm_gem_object_lookup(file_priv, args->handle); if (!obj) return -ENOENT; - if (args->handle == args->new_handle) - return 0; + if (args->handle == handle) { + ret = 0; + goto out; + } mutex_lock(&file_priv->prime.lock); spin_lock(&file_priv->table_lock); - ret = idr_alloc(&file_priv->object_idr, obj, - args->new_handle, args->new_handle + 1, GFP_NOWAIT); + ret = idr_alloc(&file_priv->object_idr, obj, handle, handle + 1, + GFP_NOWAIT); spin_unlock(&file_priv->table_lock); if (ret < 0) goto out_unlock; if (obj->dma_buf) { - ret = drm_prime_add_buf_handle(&file_priv->prime, obj->dma_buf, args->new_handle); + ret = drm_prime_add_buf_handle(&file_priv->prime, obj->dma_buf, + handle); if (ret < 0) { spin_lock(&file_priv->table_lock); - idr_remove(&file_priv->object_idr, args->new_handle); + idr_remove(&file_priv->object_idr, handle); spin_unlock(&file_priv->table_lock); goto out_unlock; } @@ -1012,6 +1020,8 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data, out_unlock: mutex_unlock(&file_priv->prime.lock); +out: + drm_gem_object_put(obj); return ret; } diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 5d1349c34afd3d..3cb39757896d06 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -48,28 +48,12 @@ static const struct drm_gem_object_funcs drm_gem_shmem_funcs = { .vm_ops = &drm_gem_shmem_vm_ops, }; -static struct drm_gem_shmem_object * -__drm_gem_shmem_create(struct drm_device *dev, size_t size, bool private, - struct vfsmount *gemfs) +static int __drm_gem_shmem_init(struct drm_device *dev, struct drm_gem_shmem_object *shmem, + size_t size, bool private, struct vfsmount *gemfs) { - struct drm_gem_shmem_object *shmem; - struct drm_gem_object *obj; + struct drm_gem_object *obj = &shmem->base; int ret = 0; - size = PAGE_ALIGN(size); - - if (dev->driver->gem_create_object) { - obj = dev->driver->gem_create_object(dev, size); - if (IS_ERR(obj)) - return ERR_CAST(obj); - shmem = to_drm_gem_shmem_obj(obj); - } else { - shmem = kzalloc(sizeof(*shmem), GFP_KERNEL); - if (!shmem) - return ERR_PTR(-ENOMEM); - obj = &shmem->base; - } - if (!obj->funcs) obj->funcs = &drm_gem_shmem_funcs; @@ -81,7 +65,7 @@ __drm_gem_shmem_create(struct drm_device *dev, size_t size, bool private, } if (ret) { drm_gem_private_object_fini(obj); - goto err_free; + return ret; } ret = drm_gem_create_mmap_offset(obj); @@ -102,14 +86,55 @@ __drm_gem_shmem_create(struct drm_device *dev, size_t size, bool private, __GFP_RETRY_MAYFAIL | __GFP_NOWARN); } - return shmem; - + return 0; err_release: drm_gem_object_release(obj); -err_free: - kfree(obj); + return ret; +} - return ERR_PTR(ret); +/** + * drm_gem_shmem_init - Initialize an allocated object. + * @dev: DRM device + * @obj: The allocated shmem GEM object. + * + * Returns: + * 0 on success, or a negative error code on failure. + */ +int drm_gem_shmem_init(struct drm_device *dev, struct drm_gem_shmem_object *shmem, size_t size) +{ + return __drm_gem_shmem_init(dev, shmem, size, false, NULL); +} +EXPORT_SYMBOL_GPL(drm_gem_shmem_init); + +static struct drm_gem_shmem_object * +__drm_gem_shmem_create(struct drm_device *dev, size_t size, bool private, + struct vfsmount *gemfs) +{ + struct drm_gem_shmem_object *shmem; + struct drm_gem_object *obj; + int ret = 0; + + size = PAGE_ALIGN(size); + + if (dev->driver->gem_create_object) { + obj = dev->driver->gem_create_object(dev, size); + if (IS_ERR(obj)) + return ERR_CAST(obj); + shmem = to_drm_gem_shmem_obj(obj); + } else { + shmem = kzalloc(sizeof(*shmem), GFP_KERNEL); + if (!shmem) + return ERR_PTR(-ENOMEM); + obj = &shmem->base; + } + + ret = __drm_gem_shmem_init(dev, shmem, size, private, gemfs); + if (ret) { + kfree(obj); + return ERR_PTR(ret); + } + + return shmem; } /** * drm_gem_shmem_create - Allocate an object with the given size @@ -150,13 +175,13 @@ struct drm_gem_shmem_object *drm_gem_shmem_create_with_mnt(struct drm_device *de EXPORT_SYMBOL_GPL(drm_gem_shmem_create_with_mnt); /** - * drm_gem_shmem_free - Free resources associated with a shmem GEM object - * @shmem: shmem GEM object to free + * drm_gem_shmem_release - Release resources associated with a shmem GEM object. + * @shmem: shmem GEM object * - * This function cleans up the GEM object state and frees the memory used to - * store the object itself. + * This function cleans up the GEM object state, but does not free the memory used to store the + * object itself. This function is meant to be a dedicated helper for the Rust GEM bindings. */ -void drm_gem_shmem_free(struct drm_gem_shmem_object *shmem) +void drm_gem_shmem_release(struct drm_gem_shmem_object *shmem) { struct drm_gem_object *obj = &shmem->base; @@ -183,6 +208,19 @@ void drm_gem_shmem_free(struct drm_gem_shmem_object *shmem) } drm_gem_object_release(obj); +} +EXPORT_SYMBOL_GPL(drm_gem_shmem_release); + +/** + * drm_gem_shmem_free - Free resources associated with a shmem GEM object + * @shmem: shmem GEM object to free + * + * This function cleans up the GEM object state and frees the memory used to + * store the object itself. + */ +void drm_gem_shmem_free(struct drm_gem_shmem_object *shmem) +{ + drm_gem_shmem_release(shmem); kfree(shmem); } EXPORT_SYMBOL_GPL(drm_gem_shmem_free); @@ -863,4 +901,4 @@ EXPORT_SYMBOL_GPL(drm_gem_shmem_prime_import_no_map); MODULE_DESCRIPTION("DRM SHMEM memory-management helpers"); MODULE_IMPORT_NS("DMA_BUF"); -MODULE_LICENSE("GPL v2"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c index af63f4d003155d..65d67356e449dd 100644 --- a/drivers/gpu/drm/drm_gpuvm.c +++ b/drivers/gpu/drm/drm_gpuvm.c @@ -876,6 +876,31 @@ __drm_gpuvm_bo_list_add(struct drm_gpuvm *gpuvm, spinlock_t *lock, cond_spin_unlock(lock, !!lock); } +/** + * drm_gpuvm_bo_is_zombie() - check whether this vm_bo is scheduled for cleanup + * @vm_bo: the &drm_gpuvm_bo + * + * When a vm_bo is scheduled for cleanup using the bo_defer list, it is not + * immediately removed from the evict and extobj lists. Therefore, anyone + * iterating these lists should skip entries that are being destroyed. + * + * Checking the refcount without incrementing it is okay as long as the lock + * protecting the evict/extobj list is held for as long as you are using the + * vm_bo, because even if the refcount hits zero while you are using it, freeing + * the vm_bo requires taking the list's lock. + * + * Zombie entries can be observed on the evict and extobj lists regardless of + * whether DRM_GPUVM_RESV_PROTECTED is used, but they remain on the lists for a + * longer time when the resv lock is used because we can't take the resv lock + * during run_job() in immediate mode, meaning that they need to remain on the + * lists until drm_gpuvm_bo_deferred_cleanup() is called. + */ +static bool +drm_gpuvm_bo_is_zombie(struct drm_gpuvm_bo *vm_bo) +{ + return !kref_read(&vm_bo->kref); +} + /** * drm_gpuvm_bo_list_add() - insert a vm_bo into the given list * @__vm_bo: the &drm_gpuvm_bo @@ -1081,6 +1106,8 @@ drm_gpuvm_init(struct drm_gpuvm *gpuvm, const char *name, INIT_LIST_HEAD(&gpuvm->evict.list); spin_lock_init(&gpuvm->evict.lock); + init_llist_head(&gpuvm->bo_defer); + kref_init(&gpuvm->kref); gpuvm->name = name ? name : "unknown"; @@ -1122,6 +1149,8 @@ drm_gpuvm_fini(struct drm_gpuvm *gpuvm) "Extobj list should be empty.\n"); drm_WARN(gpuvm->drm, !list_empty(&gpuvm->evict.list), "Evict list should be empty.\n"); + drm_WARN(gpuvm->drm, !llist_empty(&gpuvm->bo_defer), + "VM BO cleanup list should be empty.\n"); drm_gem_object_put(gpuvm->r_obj); } @@ -1217,6 +1246,9 @@ drm_gpuvm_prepare_objects_locked(struct drm_gpuvm *gpuvm, drm_gpuvm_resv_assert_held(gpuvm); list_for_each_entry(vm_bo, &gpuvm->extobj.list, list.entry.extobj) { + if (drm_gpuvm_bo_is_zombie(vm_bo)) + continue; + ret = exec_prepare_obj(exec, vm_bo->obj, num_fences); if (ret) break; @@ -1460,6 +1492,9 @@ drm_gpuvm_validate_locked(struct drm_gpuvm *gpuvm, struct drm_exec *exec) list_for_each_entry_safe(vm_bo, next, &gpuvm->evict.list, list.entry.evict) { + if (drm_gpuvm_bo_is_zombie(vm_bo)) + continue; + ret = ops->vm_bo_validate(vm_bo, exec); if (ret) break; @@ -1560,6 +1595,7 @@ drm_gpuvm_bo_create(struct drm_gpuvm *gpuvm, INIT_LIST_HEAD(&vm_bo->list.entry.extobj); INIT_LIST_HEAD(&vm_bo->list.entry.evict); + init_llist_node(&vm_bo->list.entry.bo_defer); return vm_bo; } @@ -1621,6 +1657,126 @@ drm_gpuvm_bo_put(struct drm_gpuvm_bo *vm_bo) } EXPORT_SYMBOL_GPL(drm_gpuvm_bo_put); +/* + * drm_gpuvm_bo_into_zombie() - called when the vm_bo becomes a zombie due to + * deferred cleanup + * + * If deferred cleanup is used, then this must be called right after the vm_bo + * refcount drops to zero. Must be called with GEM mutex held. After releasing + * the GEM mutex, drm_gpuvm_bo_defer_zombie_cleanup() must be called. + */ +static void +drm_gpuvm_bo_into_zombie(struct kref *kref) +{ + struct drm_gpuvm_bo *vm_bo = container_of(kref, struct drm_gpuvm_bo, + kref); + + if (!drm_gpuvm_resv_protected(vm_bo->vm)) { + drm_gpuvm_bo_list_del(vm_bo, extobj, true); + drm_gpuvm_bo_list_del(vm_bo, evict, true); + } + + list_del(&vm_bo->list.entry.gem); +} + +/* + * drm_gpuvm_bo_defer_zombie_cleanup() - adds a new zombie vm_bo to the + * bo_defer list + * + * Called after drm_gpuvm_bo_into_zombie(). GEM mutex must not be held. + * + * It's important that the GEM stays alive for the duration in which we hold + * the mutex, but the instant we add the vm_bo to bo_defer, another thread + * might call drm_gpuvm_bo_deferred_cleanup() and put the GEM. Therefore, to + * avoid kfreeing a mutex we are holding, the GEM mutex must be released + * *before* calling this function. + */ +static void +drm_gpuvm_bo_defer_zombie_cleanup(struct drm_gpuvm_bo *vm_bo) +{ + llist_add(&vm_bo->list.entry.bo_defer, &vm_bo->vm->bo_defer); +} + +static void +drm_gpuvm_bo_defer_free(struct kref *kref) +{ + struct drm_gpuvm_bo *vm_bo = container_of(kref, struct drm_gpuvm_bo, + kref); + + drm_gpuvm_bo_into_zombie(kref); + mutex_unlock(&vm_bo->obj->gpuva.lock); + drm_gpuvm_bo_defer_zombie_cleanup(vm_bo); +} + +/** + * drm_gpuvm_bo_put_deferred() - drop a struct drm_gpuvm_bo reference with + * deferred cleanup + * @vm_bo: the &drm_gpuvm_bo to release the reference of + * + * This releases a reference to @vm_bo. + * + * This might take and release the GEMs GPUVA lock. You should call + * drm_gpuvm_bo_deferred_cleanup() later to complete the cleanup process. + * + * Returns: true if vm_bo is being destroyed, false otherwise. + */ +bool +drm_gpuvm_bo_put_deferred(struct drm_gpuvm_bo *vm_bo) +{ + if (!vm_bo) + return false; + + drm_WARN_ON(vm_bo->vm->drm, !drm_gpuvm_immediate_mode(vm_bo->vm)); + + return !!kref_put_mutex(&vm_bo->kref, + drm_gpuvm_bo_defer_free, + &vm_bo->obj->gpuva.lock); +} +EXPORT_SYMBOL_GPL(drm_gpuvm_bo_put_deferred); + +/** + * drm_gpuvm_bo_deferred_cleanup() - clean up BOs in the deferred list + * deferred cleanup + * @gpuvm: the VM to clean up + * + * Cleans up &drm_gpuvm_bo instances in the deferred cleanup list. + */ +void +drm_gpuvm_bo_deferred_cleanup(struct drm_gpuvm *gpuvm) +{ + const struct drm_gpuvm_ops *ops = gpuvm->ops; + struct drm_gpuvm_bo *vm_bo; + struct drm_gem_object *obj; + struct llist_node *bo_defer; + + bo_defer = llist_del_all(&gpuvm->bo_defer); + if (!bo_defer) + return; + + if (drm_gpuvm_resv_protected(gpuvm)) { + dma_resv_lock(drm_gpuvm_resv(gpuvm), NULL); + llist_for_each_entry(vm_bo, bo_defer, list.entry.bo_defer) { + drm_gpuvm_bo_list_del(vm_bo, extobj, false); + drm_gpuvm_bo_list_del(vm_bo, evict, false); + } + dma_resv_unlock(drm_gpuvm_resv(gpuvm)); + } + + while (bo_defer) { + vm_bo = llist_entry(bo_defer, struct drm_gpuvm_bo, list.entry.bo_defer); + bo_defer = bo_defer->next; + obj = vm_bo->obj; + if (ops && ops->vm_bo_free) + ops->vm_bo_free(vm_bo); + else + kfree(vm_bo); + + drm_gpuvm_put(gpuvm); + drm_gem_object_put(obj); + } +} +EXPORT_SYMBOL_GPL(drm_gpuvm_bo_deferred_cleanup); + static struct drm_gpuvm_bo * __drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm, struct drm_gem_object *obj) @@ -1948,6 +2104,40 @@ drm_gpuva_unlink(struct drm_gpuva *va) } EXPORT_SYMBOL_GPL(drm_gpuva_unlink); +/** + * drm_gpuva_unlink_defer() - unlink a &drm_gpuva with deferred vm_bo cleanup + * @va: the &drm_gpuva to unlink + * + * Similar to drm_gpuva_unlink(), but uses drm_gpuvm_bo_put_deferred() and takes + * the lock for the caller. + */ +void +drm_gpuva_unlink_defer(struct drm_gpuva *va) +{ + struct drm_gem_object *obj = va->gem.obj; + struct drm_gpuvm_bo *vm_bo = va->vm_bo; + bool should_defer_bo; + + if (unlikely(!obj)) + return; + + drm_WARN_ON(vm_bo->vm->drm, !drm_gpuvm_immediate_mode(vm_bo->vm)); + + mutex_lock(&obj->gpuva.lock); + list_del_init(&va->gem.entry); + + /* + * This is drm_gpuvm_bo_put_deferred() except we already hold the mutex. + */ + should_defer_bo = kref_put(&vm_bo->kref, drm_gpuvm_bo_into_zombie); + mutex_unlock(&obj->gpuva.lock); + if (should_defer_bo) + drm_gpuvm_bo_defer_zombie_cleanup(vm_bo); + + va->vm_bo = NULL; +} +EXPORT_SYMBOL_GPL(drm_gpuva_unlink_defer); + /** * drm_gpuva_find_first() - find the first &drm_gpuva in the given range * @gpuvm: the &drm_gpuvm to search in @@ -2134,6 +2324,7 @@ op_map_cb(const struct drm_gpuvm_ops *fn, void *priv, op.map.va.range = req->map.va.range; op.map.gem.obj = req->map.gem.obj; op.map.gem.offset = req->map.gem.offset; + op.map.flags = req->map.flags; return fn->sm_step_map(&op, priv); } @@ -2172,6 +2363,97 @@ op_unmap_cb(const struct drm_gpuvm_ops *fn, void *priv, return fn->sm_step_unmap(&op, priv); } +static bool can_merge_flags(struct drm_gpuvm *gpuvm, enum drm_gpuva_flags a, + enum drm_gpuva_flags b) +{ + if (gpuvm->ops->sm_can_merge_flags) + return gpuvm->ops->sm_can_merge_flags(a, b); + return a == b; +} + +static bool __can_merge(struct drm_gpuvm *gpuvm, const struct drm_gpuva_op_map *a, + const struct drm_gpuva_op_map *b) +{ + /* Only GEM-based mappings can be merged, and they must point to + * the same GEM object. + */ + if (a->gem.obj != b->gem.obj || !a->gem.obj) + return false; + + if (can_merge_flags(gpuvm, a->flags, b->flags)) + return false; + + /* Order VAs for the rest of the checks. */ + if (a->va.addr > b->va.addr) + swap(a, b); + + /* We assume the caller already checked that VAs overlap or are + * contiguous. + */ + if (drm_WARN_ON(gpuvm->drm, b->va.addr > a->va.addr + a->va.range)) + return false; + + if (a->flags & DRM_GPUVA_REPEAT) { + u64 va_diff = b->va.addr - a->va.addr; + + /* If this is a repeated mapping, both the GEM range + * and offset must match. + */ + if (a->gem.range != b->gem.range || + a->gem.offset != b->gem.offset) + return false; + + /* The difference between the VA addresses must be a + * multiple of the repeated range, otherwise there's + * a shift. + */ + if (do_div(va_diff, a->gem.range)) + return false; + + return true; + } + + /* We intentionally ignore u64 underflows because all we care about + * here is whether the VA diff matches the GEM offset diff. + */ + return b->va.addr - a->va.addr == b->gem.offset - a->gem.offset; +} + +static bool can_merge(struct drm_gpuvm *gpuvm, const struct drm_gpuva *a, + const struct drm_gpuva_op_map *b) +{ + struct drm_gpuva_op_map tmp = { + .va.addr = a->va.addr, + .va.range = a->va.range, + .gem.offset = a->gem.offset, + .gem.obj = a->gem.obj, + .flags = a->flags, + }; + + return __can_merge(gpuvm, &tmp, b); +} + +static int validate_map_request(struct drm_gpuvm *gpuvm, + const struct drm_gpuva_op_map *req) +{ + if (unlikely(!drm_gpuvm_range_valid(gpuvm, req->va.addr, req->va.range))) + return -EINVAL; + + if (req->flags & DRM_GPUVA_REPEAT) { + u64 va_range = req->va.range; + + /* For a repeated mapping, GEM range must be > 0 + * and a multiple of the VA range. + */ + if (unlikely(!req->gem.range || + va_range < req->gem.range || + do_div(va_range, req->gem.range))) + return -EINVAL; + } + + return 0; +} + static int __drm_gpuvm_sm_map(struct drm_gpuvm *gpuvm, const struct drm_gpuvm_ops *ops, void *priv, @@ -2187,7 +2469,8 @@ __drm_gpuvm_sm_map(struct drm_gpuvm *gpuvm, u64 req_end = req_addr + req_range; int ret; - if (unlikely(!drm_gpuvm_range_valid(gpuvm, req_addr, req_range))) + ret = validate_map_request(gpuvm, &req->map); + if (unlikely(ret)) return -EINVAL; drm_gpuvm_for_each_va_range_safe(va, next, gpuvm, req_addr, req_end) { @@ -2196,7 +2479,7 @@ __drm_gpuvm_sm_map(struct drm_gpuvm *gpuvm, u64 addr = va->va.addr; u64 range = va->va.range; u64 end = addr + range; - bool merge = !!va->gem.obj; + bool merge = can_merge(gpuvm, va, &req->map); if (madvise && obj) continue; @@ -2224,7 +2507,10 @@ __drm_gpuvm_sm_map(struct drm_gpuvm *gpuvm, .va.addr = req_end, .va.range = range - req_range, .gem.obj = obj, - .gem.offset = offset + req_range, + .gem.range = va->gem.range, + .gem.offset = offset + + (va->flags & DRM_GPUVA_REPEAT ? 0 : req_range), + .flags = va->flags, }; struct drm_gpuva_op_unmap u = { .va = va, @@ -2245,7 +2531,9 @@ __drm_gpuvm_sm_map(struct drm_gpuvm *gpuvm, .va.addr = addr, .va.range = ls_range, .gem.obj = obj, + .gem.range = va->gem.range, .gem.offset = offset, + .flags = va->flags, }; struct drm_gpuva_op_unmap u = { .va = va }; @@ -2287,8 +2575,10 @@ __drm_gpuvm_sm_map(struct drm_gpuvm *gpuvm, .va.addr = req_end, .va.range = end - req_end, .gem.obj = obj, - .gem.offset = offset + ls_range + - req_range, + .gem.range = va->gem.range, + .gem.offset = offset + + (va->flags & DRM_GPUVA_REPEAT ? 0 : ls_range + req_range), + .flags = va->flags, }; ret = op_remap_cb(ops, priv, &p, &n, &u); @@ -2325,7 +2615,10 @@ __drm_gpuvm_sm_map(struct drm_gpuvm *gpuvm, .va.addr = req_end, .va.range = end - req_end, .gem.obj = obj, - .gem.offset = offset + req_end - addr, + .gem.range = va->gem.range, + .gem.offset = offset + + (va->flags & DRM_GPUVA_REPEAT ? 0 : req_end - addr), + .flags = va->flags, }; struct drm_gpuva_op_unmap u = { .va = va, @@ -2376,7 +2669,9 @@ __drm_gpuvm_sm_unmap(struct drm_gpuvm *gpuvm, prev.va.addr = addr; prev.va.range = req_addr - addr; prev.gem.obj = obj; + prev.gem.range = va->gem.range; prev.gem.offset = offset; + prev.flags = va->flags; prev_split = true; } @@ -2385,7 +2680,10 @@ __drm_gpuvm_sm_unmap(struct drm_gpuvm *gpuvm, next.va.addr = req_end; next.va.range = end - req_end; next.gem.obj = obj; - next.gem.offset = offset + (req_end - addr); + prev.gem.range = va->gem.range; + next.gem.offset = offset + + (va->flags & DRM_GPUVA_REPEAT ? 0 : req_end - addr); + next.flags = va->flags; next_split = true; } @@ -2928,6 +3226,55 @@ drm_gpuvm_prefetch_ops_create(struct drm_gpuvm *gpuvm, } EXPORT_SYMBOL_GPL(drm_gpuvm_prefetch_ops_create); +/** + * drm_gpuvm_bo_unmap() - unmaps a GEM + * @vm_bo: the &drm_gpuvm_bo abstraction + * + * This function calls the unmap callback for every GPUVA attached to a GEM. + * + * It is the callers responsibility to protect the GEMs GPUVA list against + * concurrent access using the GEMs dma_resv lock. + * + * Returns: a pointer to the &drm_gpuva_ops on success, an ERR_PTR on failure + */ +int +drm_gpuvm_bo_unmap(struct drm_gpuvm_bo *vm_bo, void *priv) +{ + struct drm_gpuva_ops *ops; + struct drm_gpuva_op *op; + int ret; + + if (unlikely(!vm_bo->vm)) + return -EINVAL; + + const struct drm_gpuvm_ops *vm_ops = vm_bo->vm->ops; + + if (unlikely(!(vm_ops && vm_ops->sm_step_unmap))) + return -EINVAL; + + if (drm_gpuvm_immediate_mode(vm_bo->vm)) { + guard(mutex)(&vm_bo->obj->gpuva.lock); + ops = drm_gpuvm_bo_unmap_ops_create(vm_bo); + } else { + ops = drm_gpuvm_bo_unmap_ops_create(vm_bo); + } + if (IS_ERR(ops)) + return PTR_ERR(ops); + + drm_gpuva_for_each_op(op, ops) { + drm_WARN_ON(vm_bo->vm->drm, op->op != DRM_GPUVA_OP_UNMAP); + + ret = op_unmap_cb(vm_ops, priv, op->unmap.va, false, false); + if (ret) + goto cleanup; + } + +cleanup: + drm_gpuva_ops_free(vm_bo->vm, ops); + return ret; +} +EXPORT_SYMBOL_GPL(drm_gpuvm_bo_unmap); + /** * drm_gpuvm_bo_unmap_ops_create() - creates the &drm_gpuva_ops to unmap a GEM * @vm_bo: the &drm_gpuvm_bo abstraction diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c index 22c44807e3fe97..445cf0e6589fa2 100644 --- a/drivers/gpu/drm/drm_pagemap.c +++ b/drivers/gpu/drm/drm_pagemap.c @@ -3,6 +3,7 @@ * Copyright © 2024-2025 Intel Corporation */ +#include #include #include #include @@ -408,10 +409,14 @@ int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation, drm_pagemap_get_devmem_page(page, zdd); } - err = ops->copy_to_devmem(pages, pagemap_addr, npages); + err = ops->copy_to_devmem(pages, pagemap_addr, npages, + devmem_allocation->pre_migrate_fence); if (err) goto err_finalize; + dma_fence_put(devmem_allocation->pre_migrate_fence); + devmem_allocation->pre_migrate_fence = NULL; + /* Upon success bind devmem allocation to range and zdd */ devmem_allocation->timeslice_expiration = get_jiffies_64() + msecs_to_jiffies(timeslice_ms); @@ -596,7 +601,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation) for (i = 0; i < npages; ++i) pages[i] = migrate_pfn_to_page(src[i]); - err = ops->copy_to_ram(pages, pagemap_addr, npages); + err = ops->copy_to_ram(pages, pagemap_addr, npages, NULL); if (err) goto err_finalize; @@ -732,7 +737,7 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas, for (i = 0; i < npages; ++i) pages[i] = migrate_pfn_to_page(migrate.src[i]); - err = ops->copy_to_ram(pages, pagemap_addr, npages); + err = ops->copy_to_ram(pages, pagemap_addr, npages, NULL); if (err) goto err_finalize; @@ -813,11 +818,14 @@ EXPORT_SYMBOL_GPL(drm_pagemap_pagemap_ops_get); * @ops: Pointer to the operations structure for GPU SVM device memory * @dpagemap: The struct drm_pagemap we're allocating from. * @size: Size of device memory allocation + * @pre_migrate_fence: Fence to wait for or pipeline behind before migration starts. + * (May be NULL). */ void drm_pagemap_devmem_init(struct drm_pagemap_devmem *devmem_allocation, struct device *dev, struct mm_struct *mm, const struct drm_pagemap_devmem_ops *ops, - struct drm_pagemap *dpagemap, size_t size) + struct drm_pagemap *dpagemap, size_t size, + struct dma_fence *pre_migrate_fence) { init_completion(&devmem_allocation->detached); devmem_allocation->dev = dev; @@ -825,6 +833,7 @@ void drm_pagemap_devmem_init(struct drm_pagemap_devmem *devmem_allocation, devmem_allocation->ops = ops; devmem_allocation->dpagemap = dpagemap; devmem_allocation->size = size; + devmem_allocation->pre_migrate_fence = pre_migrate_fence; } EXPORT_SYMBOL_GPL(drm_pagemap_devmem_init); diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index a30493ed97157f..4cadea997129da 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -338,14 +338,14 @@ static int drm_plane_create_hotspot_properties(struct drm_plane *plane) prop_x = drm_property_create_signed_range(plane->dev, 0, "HOTSPOT_X", INT_MIN, INT_MAX); - if (IS_ERR(prop_x)) - return PTR_ERR(prop_x); + if (!prop_x) + return -ENOMEM; prop_y = drm_property_create_signed_range(plane->dev, 0, "HOTSPOT_Y", INT_MIN, INT_MAX); - if (IS_ERR(prop_y)) { + if (!prop_y) { drm_property_destroy(plane->dev, prop_x); - return PTR_ERR(prop_y); + return -ENOMEM; } drm_object_attach_property(&plane->base, prop_x, 0); diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index 23646e55f142c3..06c29ff2aac0e1 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -199,6 +199,7 @@ struct drm_exynos_file_private { struct exynos_drm_private { struct device *g2d_dev; struct device *dma_dev; + struct device *vidi_dev; void *mapping; /* for atomic commit */ diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index e094b8bbc0f124..37733f2ac0e7a6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -186,29 +186,37 @@ static ssize_t vidi_store_connection(struct device *dev, const char *buf, size_t len) { struct vidi_context *ctx = dev_get_drvdata(dev); - int ret; + int ret, new_connected; - ret = kstrtoint(buf, 0, &ctx->connected); + ret = kstrtoint(buf, 0, &new_connected); if (ret) return ret; - - if (ctx->connected > 1) + if (new_connected > 1) return -EINVAL; + mutex_lock(&ctx->lock); + /* * Use fake edid data for test. If raw_edid is set then it can't be * tested. */ if (ctx->raw_edid) { DRM_DEV_DEBUG_KMS(dev, "edid data is not fake data.\n"); - return -EINVAL; + ret = -EINVAL; + goto fail; } + ctx->connected = new_connected; + mutex_unlock(&ctx->lock); + DRM_DEV_DEBUG_KMS(dev, "requested connection.\n"); drm_helper_hpd_irq_event(ctx->drm_dev); return len; +fail: + mutex_unlock(&ctx->lock); + return ret; } static DEVICE_ATTR(connection, 0644, vidi_show_connection, @@ -223,9 +231,14 @@ ATTRIBUTE_GROUPS(vidi); int vidi_connection_ioctl(struct drm_device *drm_dev, void *data, struct drm_file *file_priv) { - struct vidi_context *ctx = dev_get_drvdata(drm_dev->dev); + struct exynos_drm_private *priv = drm_dev->dev_private; + struct device *dev = priv ? priv->vidi_dev : NULL; + struct vidi_context *ctx = dev ? dev_get_drvdata(dev) : NULL; struct drm_exynos_vidi_connection *vidi = data; + if (!ctx) + return -ENODEV; + if (!vidi) { DRM_DEV_DEBUG_KMS(ctx->dev, "user data for vidi is null.\n"); @@ -238,21 +251,38 @@ int vidi_connection_ioctl(struct drm_device *drm_dev, void *data, return -EINVAL; } + mutex_lock(&ctx->lock); if (ctx->connected == vidi->connection) { + mutex_unlock(&ctx->lock); DRM_DEV_DEBUG_KMS(ctx->dev, "same connection request.\n"); return -EINVAL; } + mutex_unlock(&ctx->lock); if (vidi->connection) { const struct drm_edid *drm_edid; - const struct edid *raw_edid; + const void __user *edid_userptr = u64_to_user_ptr(vidi->edid); + void *edid_buf; + struct edid hdr; size_t size; - raw_edid = (const struct edid *)(unsigned long)vidi->edid; - size = (raw_edid->extensions + 1) * EDID_LENGTH; + if (copy_from_user(&hdr, edid_userptr, sizeof(hdr))) + return -EFAULT; + + size = (hdr.extensions + 1) * EDID_LENGTH; + + edid_buf = kmalloc(size, GFP_KERNEL); + if (!edid_buf) + return -ENOMEM; - drm_edid = drm_edid_alloc(raw_edid, size); + if (copy_from_user(edid_buf, edid_userptr, size)) { + kfree(edid_buf); + return -EFAULT; + } + + drm_edid = drm_edid_alloc(edid_buf, size); + kfree(edid_buf); if (!drm_edid) return -ENOMEM; @@ -262,14 +292,21 @@ int vidi_connection_ioctl(struct drm_device *drm_dev, void *data, "edid data is invalid.\n"); return -EINVAL; } + mutex_lock(&ctx->lock); ctx->raw_edid = drm_edid; + mutex_unlock(&ctx->lock); } else { /* with connection = 0, free raw_edid */ + mutex_lock(&ctx->lock); drm_edid_free(ctx->raw_edid); ctx->raw_edid = NULL; + mutex_unlock(&ctx->lock); } + mutex_lock(&ctx->lock); ctx->connected = vidi->connection; + mutex_unlock(&ctx->lock); + drm_helper_hpd_irq_event(ctx->drm_dev); return 0; @@ -284,7 +321,7 @@ static enum drm_connector_status vidi_detect(struct drm_connector *connector, * connection request would come from user side * to do hotplug through specific ioctl. */ - return ctx->connected ? connector_status_connected : + return READ_ONCE(ctx->connected) ? connector_status_connected : connector_status_disconnected; } @@ -307,11 +344,15 @@ static int vidi_get_modes(struct drm_connector *connector) const struct drm_edid *drm_edid; int count; + mutex_lock(&ctx->lock); + if (ctx->raw_edid) drm_edid = drm_edid_dup(ctx->raw_edid); else drm_edid = drm_edid_alloc(fake_edid_info, sizeof(fake_edid_info)); + mutex_unlock(&ctx->lock); + drm_edid_connector_update(connector, drm_edid); count = drm_edid_connector_add_modes(connector); @@ -371,6 +412,7 @@ static int vidi_bind(struct device *dev, struct device *master, void *data) { struct vidi_context *ctx = dev_get_drvdata(dev); struct drm_device *drm_dev = data; + struct exynos_drm_private *priv = drm_dev->dev_private; struct drm_encoder *encoder = &ctx->encoder; struct exynos_drm_plane *exynos_plane; struct exynos_drm_plane_config plane_config = { 0 }; @@ -378,6 +420,8 @@ static int vidi_bind(struct device *dev, struct device *master, void *data) int ret; ctx->drm_dev = drm_dev; + if (priv) + priv->vidi_dev = dev; plane_config.pixel_formats = formats; plane_config.num_pixel_formats = ARRAY_SIZE(formats); @@ -423,8 +467,12 @@ static int vidi_bind(struct device *dev, struct device *master, void *data) static void vidi_unbind(struct device *dev, struct device *master, void *data) { struct vidi_context *ctx = dev_get_drvdata(dev); + struct drm_device *drm_dev = data; + struct exynos_drm_private *priv = drm_dev->dev_private; timer_delete_sync(&ctx->timer); + if (priv) + priv->vidi_dev = NULL; } static const struct component_ops vidi_component_ops = { @@ -456,9 +504,13 @@ static void vidi_remove(struct platform_device *pdev) { struct vidi_context *ctx = platform_get_drvdata(pdev); + mutex_lock(&ctx->lock); + drm_edid_free(ctx->raw_edid); ctx->raw_edid = NULL; + mutex_unlock(&ctx->lock); + component_del(&pdev->dev, &vidi_component_ops); } diff --git a/drivers/gpu/drm/gma500/fbdev.c b/drivers/gpu/drm/gma500/fbdev.c index 32d31e5f5f1a78..a6af21514cff73 100644 --- a/drivers/gpu/drm/gma500/fbdev.c +++ b/drivers/gpu/drm/gma500/fbdev.c @@ -50,48 +50,6 @@ static const struct vm_operations_struct psb_fbdev_vm_ops = { * struct fb_ops */ -#define CMAP_TOHW(_val, _width) ((((_val) << (_width)) + 0x7FFF - (_val)) >> 16) - -static int psb_fbdev_fb_setcolreg(unsigned int regno, - unsigned int red, unsigned int green, - unsigned int blue, unsigned int transp, - struct fb_info *info) -{ - struct drm_fb_helper *fb_helper = info->par; - struct drm_framebuffer *fb = fb_helper->fb; - uint32_t v; - - if (!fb) - return -ENOMEM; - - if (regno > 255) - return 1; - - red = CMAP_TOHW(red, info->var.red.length); - blue = CMAP_TOHW(blue, info->var.blue.length); - green = CMAP_TOHW(green, info->var.green.length); - transp = CMAP_TOHW(transp, info->var.transp.length); - - v = (red << info->var.red.offset) | - (green << info->var.green.offset) | - (blue << info->var.blue.offset) | - (transp << info->var.transp.offset); - - if (regno < 16) { - switch (fb->format->cpp[0] * 8) { - case 16: - ((uint32_t *) info->pseudo_palette)[regno] = v; - break; - case 24: - case 32: - ((uint32_t *) info->pseudo_palette)[regno] = v; - break; - } - } - - return 0; -} - static int psb_fbdev_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) { if (vma->vm_pgoff != 0) @@ -135,7 +93,6 @@ static const struct fb_ops psb_fbdev_fb_ops = { .owner = THIS_MODULE, __FB_DEFAULT_IOMEM_OPS_RDWR, DRM_FB_HELPER_DEFAULT_OPS, - .fb_setcolreg = psb_fbdev_fb_setcolreg, __FB_DEFAULT_IOMEM_OPS_DRAW, .fb_mmap = psb_fbdev_fb_mmap, .fb_destroy = psb_fbdev_fb_destroy, diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c index 54d9aa9998e596..cfd66c879ae407 100644 --- a/drivers/gpu/drm/gud/gud_pipe.c +++ b/drivers/gpu/drm/gud/gud_pipe.c @@ -457,27 +457,20 @@ int gud_plane_atomic_check(struct drm_plane *plane, struct drm_plane_state *old_plane_state = drm_atomic_get_old_plane_state(state, plane); struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state, plane); struct drm_crtc *crtc = new_plane_state->crtc; - struct drm_crtc_state *crtc_state; + struct drm_crtc_state *crtc_state = NULL; const struct drm_display_mode *mode; struct drm_framebuffer *old_fb = old_plane_state->fb; struct drm_connector_state *connector_state = NULL; struct drm_framebuffer *fb = new_plane_state->fb; - const struct drm_format_info *format = fb->format; + const struct drm_format_info *format; struct drm_connector *connector; unsigned int i, num_properties; struct gud_state_req *req; int idx, ret; size_t len; - if (drm_WARN_ON_ONCE(plane->dev, !fb)) - return -EINVAL; - - if (drm_WARN_ON_ONCE(plane->dev, !crtc)) - return -EINVAL; - - crtc_state = drm_atomic_get_new_crtc_state(state, crtc); - - mode = &crtc_state->mode; + if (crtc) + crtc_state = drm_atomic_get_new_crtc_state(state, crtc); ret = drm_atomic_helper_check_plane_state(new_plane_state, crtc_state, DRM_PLANE_NO_SCALING, @@ -492,6 +485,9 @@ int gud_plane_atomic_check(struct drm_plane *plane, if (old_plane_state->rotation != new_plane_state->rotation) crtc_state->mode_changed = true; + mode = &crtc_state->mode; + format = fb->format; + if (old_fb && old_fb->format != format) crtc_state->mode_changed = true; @@ -598,7 +594,7 @@ void gud_plane_atomic_update(struct drm_plane *plane, struct drm_atomic_helper_damage_iter iter; int ret, idx; - if (crtc->state->mode_changed || !crtc->state->enable) { + if (!crtc || crtc->state->mode_changed || !crtc->state->enable) { cancel_work_sync(&gdrm->work); mutex_lock(&gdrm->damage_lock); if (gdrm->fb) { diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_comm.h b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_comm.h index 4add05c7f161a0..f9ee7ebfec55c3 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_comm.h +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_comm.h @@ -40,6 +40,10 @@ struct hibmc_dp_dev { struct mutex lock; /* protects concurrent RW in hibmc_dp_reg_write_field() */ struct hibmc_dp_link link; u8 dpcd[DP_RECEIVER_CAP_SIZE]; + u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS]; + struct drm_dp_desc desc; + bool is_branch; + int hpd_status; void __iomem *serdes_base; }; diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_config.h b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_config.h index 08f9e1caf7fcbb..efb30a7584758c 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_config.h +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_config.h @@ -17,5 +17,7 @@ #define HIBMC_DP_LINK_RATE_CAL 27 #define HIBMC_DP_SYNC_DELAY(lanes) ((lanes) == 0x2 ? 86 : 46) #define HIBMC_DP_INT_ENABLE 0xc +/* HIBMC_DP_LINK_RATE_CAL * 10000 * 80% = 216000 */ +#define DP_MODE_VALI_CAL 216000 #endif diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.c b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.c index 8f0daec7d17490..d5bd3c45649b2f 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.c +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.c @@ -2,6 +2,7 @@ // Copyright (c) 2024 Hisilicon Limited. #include +#include #include #include "dp_config.h" #include "dp_comm.h" @@ -176,13 +177,18 @@ int hibmc_dp_hw_init(struct hibmc_dp *dp) dp_dev->link.cap.lanes = 0x2; dp_dev->link.cap.link_rate = DP_LINK_BW_8_1; - /* hdcp data */ - writel(HIBMC_DP_HDCP, dp_dev->base + HIBMC_DP_HDCP_CFG); /* int init */ writel(0, dp_dev->base + HIBMC_DP_INTR_ENABLE); writel(HIBMC_DP_INT_RST, dp_dev->base + HIBMC_DP_INTR_ORIGINAL_STATUS); + /* clr colorbar */ + writel(0, dp_dev->base + HIBMC_DP_COLOR_BAR_CTRL); /* rst */ + writel(0, dp_dev->base + HIBMC_DP_DPTX_RST_CTRL); + usleep_range(30, 50); + /* de-rst */ writel(HIBMC_DP_DPTX_RST, dp_dev->base + HIBMC_DP_DPTX_RST_CTRL); + /* hdcp data */ + writel(HIBMC_DP_HDCP, dp_dev->base + HIBMC_DP_HDCP_CFG); /* clock enable */ writel(HIBMC_DP_CLK_EN, dp_dev->base + HIBMC_DP_DPTX_CLK_CTRL); @@ -263,6 +269,16 @@ void hibmc_dp_reset_link(struct hibmc_dp *dp) dp->dp_dev->link.status.channel_equalized = false; } +u8 hibmc_dp_get_link_rate(struct hibmc_dp *dp) +{ + return dp->dp_dev->link.cap.link_rate; +} + +u8 hibmc_dp_get_lanes(struct hibmc_dp *dp) +{ + return dp->dp_dev->link.cap.lanes; +} + static const struct hibmc_dp_color_raw g_rgb_raw[] = { {CBAR_COLOR_BAR, 0x000, 0x000, 0x000}, {CBAR_WHITE, 0xfff, 0xfff, 0xfff}, @@ -305,3 +321,21 @@ void hibmc_dp_set_cbar(struct hibmc_dp *dp, const struct hibmc_dp_cbar_cfg *cfg) hibmc_dp_reg_write_field(dp_dev, HIBMC_DP_COLOR_BAR_CTRL, BIT(0), cfg->enable); writel(HIBMC_DP_SYNC_EN_MASK, dp_dev->base + HIBMC_DP_TIMING_SYNC_CTRL); } + +bool hibmc_dp_check_hpd_status(struct hibmc_dp *dp, int exp_status) +{ + u32 status; + int ret; + + ret = readl_poll_timeout(dp->dp_dev->base + HIBMC_DP_HPD_STATUS, status, + FIELD_GET(HIBMC_DP_HPD_CUR_STATE, status) == exp_status, + 1000, 100000); /* DP spec says 100ms */ + if (ret) { + drm_dbg_dp(dp->drm_dev, "wait hpd status timeout"); + return false; + } + + dp->dp_dev->hpd_status = exp_status; + + return true; +} diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.h b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.h index 665f5b166dfb5c..31316fe1ea8dbf 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.h +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.h @@ -14,6 +14,11 @@ struct hibmc_dp_dev; +enum hibmc_hpd_status { + HIBMC_HPD_OUT, + HIBMC_HPD_IN, +}; + enum hibmc_dp_cbar_pattern { CBAR_COLOR_BAR, CBAR_WHITE, @@ -60,5 +65,8 @@ void hibmc_dp_reset_link(struct hibmc_dp *dp); void hibmc_dp_hpd_cfg(struct hibmc_dp *dp); void hibmc_dp_enable_int(struct hibmc_dp *dp); void hibmc_dp_disable_int(struct hibmc_dp *dp); +bool hibmc_dp_check_hpd_status(struct hibmc_dp *dp, int exp_status); +u8 hibmc_dp_get_link_rate(struct hibmc_dp *dp); +u8 hibmc_dp_get_lanes(struct hibmc_dp *dp); #endif diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_reg.h b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_reg.h index 394b1e933c3ae7..64306abcd98666 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_reg.h +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_reg.h @@ -24,6 +24,9 @@ #define HIBMC_DP_CFG_AUX_READY_DATA_BYTE GENMASK(16, 12) #define HIBMC_DP_CFG_AUX GENMASK(24, 17) +#define HIBMC_DP_HPD_STATUS 0x98 +#define HIBMC_DP_HPD_CUR_STATE GENMASK(7, 4) + #define HIBMC_DP_PHYIF_CTRL0 0xa0 #define HIBMC_DP_CFG_SCRAMBLE_EN BIT(0) #define HIBMC_DP_CFG_PAT_SEL GENMASK(7, 4) diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_dp.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_dp.c index d06832e62e966e..616821e3c933bc 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_dp.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_dp.c @@ -12,6 +12,8 @@ #include "hibmc_drm_drv.h" #include "dp/dp_hw.h" +#include "dp/dp_comm.h" +#include "dp/dp_config.h" #define DP_MASKED_SINK_HPD_PLUG_INT BIT(2) @@ -31,17 +33,76 @@ static int hibmc_dp_connector_get_modes(struct drm_connector *connector) return count; } +static bool hibmc_dp_get_dpcd(struct hibmc_dp_dev *dp_dev) +{ + int ret; + + ret = drm_dp_read_dpcd_caps(dp_dev->aux, dp_dev->dpcd); + if (ret) + return false; + + dp_dev->is_branch = drm_dp_is_branch(dp_dev->dpcd); + + ret = drm_dp_read_desc(dp_dev->aux, &dp_dev->desc, dp_dev->is_branch); + if (ret) + return false; + + ret = drm_dp_read_downstream_info(dp_dev->aux, dp_dev->dpcd, dp_dev->downstream_ports); + if (ret) + return false; + + return true; +} + static int hibmc_dp_detect(struct drm_connector *connector, struct drm_modeset_acquire_ctx *ctx, bool force) { - mdelay(200); + struct hibmc_dp *dp = to_hibmc_dp(connector); + struct hibmc_dp_dev *dp_dev = dp->dp_dev; + int ret; + + if (dp->irq_status) { + if (dp_dev->hpd_status != HIBMC_HPD_IN) + return connector_status_disconnected; + } + + if (!hibmc_dp_get_dpcd(dp_dev)) + return connector_status_disconnected; + + if (!dp_dev->is_branch) + return connector_status_connected; + + if (drm_dp_read_sink_count_cap(connector, dp_dev->dpcd, &dp_dev->desc) && + dp_dev->downstream_ports[0] & DP_DS_PORT_HPD) { + ret = drm_dp_read_sink_count(dp_dev->aux); + if (ret > 0) + return connector_status_connected; + } + + return connector_status_disconnected; +} + +static int hibmc_dp_mode_valid(struct drm_connector *connector, + const struct drm_display_mode *mode, + struct drm_modeset_acquire_ctx *ctx, + enum drm_mode_status *status) +{ + struct hibmc_dp *dp = to_hibmc_dp(connector); + u64 cur_val, max_val; - return drm_connector_helper_detect_from_ddc(connector, ctx, force); + /* check DP link BW */ + cur_val = (u64)mode->clock * HIBMC_DP_BPP; + max_val = (u64)hibmc_dp_get_link_rate(dp) * DP_MODE_VALI_CAL * hibmc_dp_get_lanes(dp); + + *status = cur_val > max_val ? MODE_CLOCK_HIGH : MODE_OK; + + return 0; } static const struct drm_connector_helper_funcs hibmc_dp_conn_helper_funcs = { .get_modes = hibmc_dp_connector_get_modes, .detect_ctx = hibmc_dp_detect, + .mode_valid_ctx = hibmc_dp_mode_valid, }; static int hibmc_dp_late_register(struct drm_connector *connector) @@ -115,7 +176,7 @@ irqreturn_t hibmc_dp_hpd_isr(int irq, void *arg) { struct drm_device *dev = (struct drm_device *)arg; struct hibmc_drm_private *priv = to_hibmc_drm_private(dev); - int idx; + int idx, exp_status; if (!drm_dev_enter(dev, &idx)) return -ENODEV; @@ -123,12 +184,14 @@ irqreturn_t hibmc_dp_hpd_isr(int irq, void *arg) if (priv->dp.irq_status & DP_MASKED_SINK_HPD_PLUG_INT) { drm_dbg_dp(&priv->dev, "HPD IN isr occur!\n"); hibmc_dp_hpd_cfg(&priv->dp); + exp_status = HIBMC_HPD_IN; } else { drm_dbg_dp(&priv->dev, "HPD OUT isr occur!\n"); hibmc_dp_reset_link(&priv->dp); + exp_status = HIBMC_HPD_OUT; } - if (dev->registered) + if (hibmc_dp_check_hpd_status(&priv->dp, exp_status)) drm_connector_helper_hpd_irq_event(&priv->dp.connector); drm_dev_exit(idx); diff --git a/drivers/gpu/drm/i915/display/intel_acpi.c b/drivers/gpu/drm/i915/display/intel_acpi.c index 1addd628824137..1e8b9d1756988d 100644 --- a/drivers/gpu/drm/i915/display/intel_acpi.c +++ b/drivers/gpu/drm/i915/display/intel_acpi.c @@ -96,6 +96,7 @@ static void intel_dsm_platform_mux_info(acpi_handle dhandle) if (!pkg->package.count) { DRM_DEBUG_DRIVER("no connection in _DSM\n"); + ACPI_FREE(pkg); return; } diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index 7c4709d58aa345..7daf72b69bae4f 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -207,6 +207,35 @@ static const struct drm_fb_helper_funcs intel_fb_helper_funcs = { .fb_set_suspend = intelfb_set_suspend, }; +static void intel_fbdev_fill_mode_cmd(struct drm_fb_helper_surface_size *sizes, + struct drm_mode_fb_cmd2 *mode_cmd) +{ + /* we don't do packed 24bpp */ + if (sizes->surface_bpp == 24) + sizes->surface_bpp = 32; + + mode_cmd->width = sizes->surface_width; + mode_cmd->height = sizes->surface_height; + + mode_cmd->pitches[0] = ALIGN(mode_cmd->width * DIV_ROUND_UP(sizes->surface_bpp, 8), 64); + mode_cmd->pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp, + sizes->surface_depth); +} + +static struct intel_framebuffer * +__intel_fbdev_fb_alloc(struct intel_display *display, + struct drm_fb_helper_surface_size *sizes) +{ + struct drm_mode_fb_cmd2 mode_cmd = {}; + struct intel_framebuffer *fb; + + intel_fbdev_fill_mode_cmd(sizes, &mode_cmd); + + fb = intel_fbdev_fb_alloc(display->drm, &mode_cmd); + + return fb; +} + int intel_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, struct drm_fb_helper_surface_size *sizes) { @@ -234,12 +263,18 @@ int intel_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, drm_framebuffer_put(&fb->base); fb = NULL; } + + wakeref = intel_display_rpm_get(display); + if (!fb || drm_WARN_ON(display->drm, !intel_fb_bo(&fb->base))) { drm_dbg_kms(display->drm, "no BIOS fb, allocating a new one\n"); - fb = intel_fbdev_fb_alloc(helper, sizes); - if (IS_ERR(fb)) - return PTR_ERR(fb); + + fb = __intel_fbdev_fb_alloc(display, sizes); + if (IS_ERR(fb)) { + ret = PTR_ERR(fb); + goto out_unlock; + } } else { drm_dbg_kms(display->drm, "re-using BIOS fb\n"); prealloc = true; @@ -247,8 +282,6 @@ int intel_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, sizes->fb_height = fb->base.height; } - wakeref = intel_display_rpm_get(display); - /* Pin the GGTT vma for our access via info->screen_base. * This also validates that any existing fb inherited from the * BIOS is suitable for own access. diff --git a/drivers/gpu/drm/i915/display/intel_fbdev_fb.c b/drivers/gpu/drm/i915/display/intel_fbdev_fb.c index 210aee9ae88b88..685612e6afc53e 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev_fb.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev_fb.c @@ -3,7 +3,7 @@ * Copyright © 2023 Intel Corporation */ -#include +#include #include "gem/i915_gem_lmem.h" @@ -13,29 +13,16 @@ #include "intel_fb.h" #include "intel_fbdev_fb.h" -struct intel_framebuffer *intel_fbdev_fb_alloc(struct drm_fb_helper *helper, - struct drm_fb_helper_surface_size *sizes) +struct intel_framebuffer *intel_fbdev_fb_alloc(struct drm_device *drm, + struct drm_mode_fb_cmd2 *mode_cmd) { - struct intel_display *display = to_intel_display(helper->dev); - struct drm_i915_private *dev_priv = to_i915(display->drm); + struct intel_display *display = to_intel_display(drm); + struct drm_i915_private *dev_priv = to_i915(drm); struct drm_framebuffer *fb; - struct drm_mode_fb_cmd2 mode_cmd = {}; struct drm_i915_gem_object *obj; int size; - /* we don't do packed 24bpp */ - if (sizes->surface_bpp == 24) - sizes->surface_bpp = 32; - - mode_cmd.width = sizes->surface_width; - mode_cmd.height = sizes->surface_height; - - mode_cmd.pitches[0] = ALIGN(mode_cmd.width * - DIV_ROUND_UP(sizes->surface_bpp, 8), 64); - mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp, - sizes->surface_depth); - - size = mode_cmd.pitches[0] * mode_cmd.height; + size = mode_cmd->pitches[0] * mode_cmd->height; size = PAGE_ALIGN(size); obj = ERR_PTR(-ENODEV); @@ -58,18 +45,25 @@ struct intel_framebuffer *intel_fbdev_fb_alloc(struct drm_fb_helper *helper, } if (IS_ERR(obj)) { - drm_err(display->drm, "failed to allocate framebuffer (%pe)\n", obj); + drm_err(drm, "failed to allocate framebuffer (%pe)\n", obj); return ERR_PTR(-ENOMEM); } fb = intel_framebuffer_create(intel_bo_to_drm_bo(obj), - drm_get_format_info(display->drm, - mode_cmd.pixel_format, - mode_cmd.modifier[0]), - &mode_cmd); + drm_get_format_info(drm, + mode_cmd->pixel_format, + mode_cmd->modifier[0]), + mode_cmd); + if (IS_ERR(fb)) { + i915_gem_object_put(obj); + goto err; + } + i915_gem_object_put(obj); return to_intel_framebuffer(fb); +err: + return ERR_CAST(fb); } int intel_fbdev_fb_fill_info(struct intel_display *display, struct fb_info *info, diff --git a/drivers/gpu/drm/i915/display/intel_fbdev_fb.h b/drivers/gpu/drm/i915/display/intel_fbdev_fb.h index cb795727271502..83454ffbf79cd6 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev_fb.h +++ b/drivers/gpu/drm/i915/display/intel_fbdev_fb.h @@ -6,15 +6,15 @@ #ifndef __INTEL_FBDEV_FB_H__ #define __INTEL_FBDEV_FB_H__ -struct drm_fb_helper; -struct drm_fb_helper_surface_size; +struct drm_device; struct drm_gem_object; +struct drm_mode_fb_cmd2; struct fb_info; struct i915_vma; struct intel_display; -struct intel_framebuffer *intel_fbdev_fb_alloc(struct drm_fb_helper *helper, - struct drm_fb_helper_surface_size *sizes); +struct intel_framebuffer *intel_fbdev_fb_alloc(struct drm_device *drm, + struct drm_mode_fb_cmd2 *mode_cmd); int intel_fbdev_fb_fill_info(struct intel_display *display, struct fb_info *info, struct drm_gem_object *obj, struct i915_vma *vma); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 39c7c32e1e74ed..bcae382acdf565 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -950,13 +950,13 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) vma = eb_lookup_vma(eb, eb->exec[i].handle); if (IS_ERR(vma)) { err = PTR_ERR(vma); - goto err; + return err; } err = eb_validate_vma(eb, &eb->exec[i], vma); if (unlikely(err)) { i915_vma_put(vma); - goto err; + return err; } err = eb_add_vma(eb, ¤t_batch, i, vma); @@ -965,19 +965,8 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) if (i915_gem_object_is_userptr(vma->obj)) { err = i915_gem_object_userptr_submit_init(vma->obj); - if (err) { - if (i + 1 < eb->buffer_count) { - /* - * Execbuffer code expects last vma entry to be NULL, - * since we already initialized this entry, - * set the next value to NULL or we mess up - * cleanup handling. - */ - eb->vma[i + 1].vma = NULL; - } - + if (err) return err; - } eb->vma[i].flags |= __EXEC_OBJECT_USERPTR_INIT; eb->args->flags |= __EXEC_USERPTR_USED; @@ -985,10 +974,6 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) } return 0; - -err: - eb->vma[i].vma = NULL; - return err; } static int eb_lock_vmas(struct i915_execbuffer *eb) @@ -3374,7 +3359,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, eb.exec = exec; eb.vma = (struct eb_vma *)(exec + args->buffer_count + 1); - eb.vma[0].vma = NULL; + memset(eb.vma, 0, (args->buffer_count + 1) * sizeof(struct eb_vma)); + eb.batch_pool = NULL; eb.invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS; @@ -3583,7 +3569,18 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data, if (err) return err; - /* Allocate extra slots for use by the command parser */ + /* + * Allocate extra slots for use by the command parser. + * + * Note that this allocation handles two different arrays (the + * exec2_list array, and the eventual eb.vma array introduced in + * i915_gem_do_execbuffer()), that reside in virtually contiguous + * memory. Also note that the allocation intentionally doesn't fill the + * area with zeros, because the exec2_list part doesn't need to be, as + * it's immediately overwritten by user data a few lines below. + * However, the eb.vma part is explicitly zeroed later in + * i915_gem_do_execbuffer(). + */ exec2_list = kvmalloc_array(count + 2, eb_element_size(), __GFP_NOWARN | GFP_KERNEL); if (exec2_list == NULL) { diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h index b3b75be9ced5d3..e9a4e6090fe0a0 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.h +++ b/drivers/gpu/drm/i915/intel_memory_region.h @@ -72,7 +72,7 @@ struct intel_memory_region { u16 instance; enum intel_region_id id; char name[16]; - char uabi_name[16]; + char uabi_name[20]; bool private; /* not for userspace */ struct { diff --git a/drivers/gpu/drm/imagination/pvr_device.c b/drivers/gpu/drm/imagination/pvr_device.c index 294b6019b4155b..78d6b8a0a4506c 100644 --- a/drivers/gpu/drm/imagination/pvr_device.c +++ b/drivers/gpu/drm/imagination/pvr_device.c @@ -48,7 +48,7 @@ * * Return: * * 0 on success, or - * * Any error returned by devm_platform_ioremap_resource(). + * * Any error returned by devm_platform_get_and_ioremap_resource(). */ static int pvr_device_reg_init(struct pvr_device *pvr_dev) diff --git a/drivers/gpu/drm/imagination/pvr_fw_trace.c b/drivers/gpu/drm/imagination/pvr_fw_trace.c index a1098b5214856d..e7f4554510fd46 100644 --- a/drivers/gpu/drm/imagination/pvr_fw_trace.c +++ b/drivers/gpu/drm/imagination/pvr_fw_trace.c @@ -136,6 +136,7 @@ update_logtype(struct pvr_device *pvr_dev, u32 group_mask) struct rogue_fwif_kccb_cmd cmd; int idx; int err; + int slot; if (group_mask) fw_trace->tracebuf_ctrl->log_type = ROGUE_FWIF_LOG_TYPE_TRACE | group_mask; @@ -153,8 +154,13 @@ update_logtype(struct pvr_device *pvr_dev, u32 group_mask) cmd.cmd_type = ROGUE_FWIF_KCCB_CMD_LOGTYPE_UPDATE; cmd.kccb_flags = 0; - err = pvr_kccb_send_cmd(pvr_dev, &cmd, NULL); + err = pvr_kccb_send_cmd(pvr_dev, &cmd, &slot); + if (err) + goto err_drm_dev_exit; + + err = pvr_kccb_wait_for_completion(pvr_dev, slot, HZ, NULL); +err_drm_dev_exit: drm_dev_exit(idx); err_up_read: diff --git a/drivers/gpu/drm/imagination/pvr_gem.c b/drivers/gpu/drm/imagination/pvr_gem.c index a66cf082af2445..c07c9a91519039 100644 --- a/drivers/gpu/drm/imagination/pvr_gem.c +++ b/drivers/gpu/drm/imagination/pvr_gem.c @@ -28,6 +28,16 @@ static void pvr_gem_object_free(struct drm_gem_object *obj) drm_gem_shmem_object_free(obj); } +static struct dma_buf *pvr_gem_export(struct drm_gem_object *obj, int flags) +{ + struct pvr_gem_object *pvr_obj = gem_to_pvr_gem(obj); + + if (pvr_obj->flags & DRM_PVR_BO_PM_FW_PROTECT) + return ERR_PTR(-EPERM); + + return drm_gem_prime_export(obj, flags); +} + static int pvr_gem_mmap(struct drm_gem_object *gem_obj, struct vm_area_struct *vma) { struct pvr_gem_object *pvr_obj = gem_to_pvr_gem(gem_obj); @@ -42,6 +52,7 @@ static int pvr_gem_mmap(struct drm_gem_object *gem_obj, struct vm_area_struct *v static const struct drm_gem_object_funcs pvr_gem_object_funcs = { .free = pvr_gem_object_free, .print_info = drm_gem_shmem_object_print_info, + .export = pvr_gem_export, .pin = drm_gem_shmem_object_pin, .unpin = drm_gem_shmem_object_unpin, .get_sg_table = drm_gem_shmem_object_get_sg_table, diff --git a/drivers/gpu/drm/imx/ipuv3/imx-tve.c b/drivers/gpu/drm/imx/ipuv3/imx-tve.c index c5629e155d25ae..99c2e20fa3f762 100644 --- a/drivers/gpu/drm/imx/ipuv3/imx-tve.c +++ b/drivers/gpu/drm/imx/ipuv3/imx-tve.c @@ -525,6 +525,13 @@ static const struct component_ops imx_tve_ops = { .bind = imx_tve_bind, }; +static void imx_tve_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int imx_tve_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -546,6 +553,12 @@ static int imx_tve_probe(struct platform_device *pdev) if (ddc_node) { tve->ddc = of_find_i2c_adapter_by_node(ddc_node); of_node_put(ddc_node); + if (tve->ddc) { + ret = devm_add_action_or_reset(dev, imx_tve_put_device, + &tve->ddc->dev); + if (ret) + return ret; + } } tve->mode = of_get_tve_mode(np); diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c index ac6620e10262e3..9672ea1f91a2b5 100644 --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c @@ -621,15 +621,27 @@ int mtk_find_possible_crtcs(struct drm_device *drm, struct device *dev) return ret; } -int mtk_ddp_comp_init(struct device_node *node, struct mtk_ddp_comp *comp, +static void mtk_ddp_comp_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + +static void mtk_ddp_comp_clk_put(void *_clk) +{ + struct clk *clk = _clk; + + clk_put(clk); +} + +int mtk_ddp_comp_init(struct device *dev, struct device_node *node, struct mtk_ddp_comp *comp, unsigned int comp_id) { struct platform_device *comp_pdev; enum mtk_ddp_comp_type type; struct mtk_ddp_comp_dev *priv; -#if IS_REACHABLE(CONFIG_MTK_CMDQ) int ret; -#endif if (comp_id >= DDP_COMPONENT_DRM_ID_MAX) return -EINVAL; @@ -651,6 +663,10 @@ int mtk_ddp_comp_init(struct device_node *node, struct mtk_ddp_comp *comp, } comp->dev = &comp_pdev->dev; + ret = devm_add_action_or_reset(dev, mtk_ddp_comp_put_device, comp->dev); + if (ret) + return ret; + if (type == MTK_DISP_AAL || type == MTK_DISP_BLS || type == MTK_DISP_CCORR || @@ -666,15 +682,22 @@ int mtk_ddp_comp_init(struct device_node *node, struct mtk_ddp_comp *comp, type == MTK_DSI) return 0; - priv = devm_kzalloc(comp->dev, sizeof(*priv), GFP_KERNEL); + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; - priv->regs = of_iomap(node, 0); + priv->regs = devm_of_iomap(dev, node, 0, NULL); + if (IS_ERR(priv->regs)) + return PTR_ERR(priv->regs); + priv->clk = of_clk_get(node, 0); if (IS_ERR(priv->clk)) return PTR_ERR(priv->clk); + ret = devm_add_action_or_reset(dev, mtk_ddp_comp_clk_put, priv->clk); + if (ret) + return ret; + #if IS_REACHABLE(CONFIG_MTK_CMDQ) ret = cmdq_dev_get_client_reg(comp->dev, &priv->cmdq_reg, 0); if (ret) diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h index 7289b3dcf22f22..3f3d43f4330da4 100644 --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h @@ -350,7 +350,7 @@ static inline void mtk_ddp_comp_encoder_index_set(struct mtk_ddp_comp *comp) int mtk_ddp_comp_get_id(struct device_node *node, enum mtk_ddp_comp_type comp_type); int mtk_find_possible_crtcs(struct drm_device *drm, struct device *dev); -int mtk_ddp_comp_init(struct device_node *comp_node, struct mtk_ddp_comp *comp, +int mtk_ddp_comp_init(struct device *dev, struct device_node *comp_node, struct mtk_ddp_comp *comp, unsigned int comp_id); enum mtk_ddp_comp_type mtk_ddp_comp_get_type(unsigned int comp_id); void mtk_ddp_write(struct cmdq_pkt *cmdq_pkt, unsigned int value, diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ccorr.c b/drivers/gpu/drm/mediatek/mtk_disp_ccorr.c index 10d60d2c2a568e..6d7bf4afa78d3a 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ccorr.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ccorr.c @@ -80,27 +80,6 @@ void mtk_ccorr_stop(struct device *dev) writel_relaxed(0x0, ccorr->regs + DISP_CCORR_EN); } -/* Converts a DRM S31.32 value to the HW S1.n format. */ -static u16 mtk_ctm_s31_32_to_s1_n(u64 in, u32 n) -{ - u16 r; - - /* Sign bit. */ - r = in & BIT_ULL(63) ? BIT(n + 1) : 0; - - if ((in & GENMASK_ULL(62, 33)) > 0) { - /* identity value 0x100000000 -> 0x400(mt8183), */ - /* identity value 0x100000000 -> 0x800(mt8192), */ - /* if bigger this, set it to max 0x7ff. */ - r |= GENMASK(n, 0); - } else { - /* take the n+1 most important bits. */ - r |= (in >> (32 - n)) & GENMASK(n, 0); - } - - return r; -} - void mtk_ccorr_ctm_set(struct device *dev, struct drm_crtc_state *state) { struct mtk_disp_ccorr *ccorr = dev_get_drvdata(dev); @@ -119,7 +98,7 @@ void mtk_ccorr_ctm_set(struct device *dev, struct drm_crtc_state *state) input = ctm->matrix; for (i = 0; i < ARRAY_SIZE(coeffs); i++) - coeffs[i] = mtk_ctm_s31_32_to_s1_n(input[i], matrix_bits); + coeffs[i] = drm_color_ctm_s31_32_to_qm_n(input[i], 2, matrix_bits); mtk_ddp_write(cmdq_pkt, coeffs[0] << 16 | coeffs[1], &ccorr->cmdq_reg, ccorr->regs, DISP_CCORR_COEF_0); diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c index fe97bb97e004ad..c0af3e3b51d554 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c @@ -527,6 +527,13 @@ bool mtk_ovl_adaptor_is_comp_present(struct device_node *node) type == OVL_ADAPTOR_TYPE_PADDING; } +static void ovl_adaptor_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int ovl_adaptor_comp_init(struct device *dev, struct component_match **match) { struct mtk_disp_ovl_adaptor *priv = dev_get_drvdata(dev); @@ -560,6 +567,11 @@ static int ovl_adaptor_comp_init(struct device *dev, struct component_match **ma if (!comp_pdev) return -EPROBE_DEFER; + ret = devm_add_action_or_reset(dev, ovl_adaptor_put_device, + &comp_pdev->dev); + if (ret) + return ret; + priv->ovl_adaptor_comp[id] = &comp_pdev->dev; drm_of_component_match_add(dev, match, component_compare_of, node); diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c index bef6eeb30d3ecc..b0b1e158600f34 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp.c +++ b/drivers/gpu/drm/mediatek/mtk_dp.c @@ -2087,6 +2087,7 @@ static int mtk_dp_dt_parse(struct mtk_dp *mtk_dp, endpoint = of_graph_get_endpoint_by_regs(pdev->dev.of_node, 1, -1); len = of_property_count_elems_of_size(endpoint, "data-lanes", sizeof(u32)); + of_node_put(endpoint); if (len < 0 || len > 4 || len == 3) { dev_err(dev, "invalid data lane size: %d\n", len); return -EINVAL; diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index 61cab32e213afa..53360b5d12ba56 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -836,20 +836,6 @@ static int mtk_dpi_bridge_attach(struct drm_bridge *bridge, enum drm_bridge_attach_flags flags) { struct mtk_dpi *dpi = bridge_to_dpi(bridge); - int ret; - - dpi->next_bridge = devm_drm_of_get_bridge(dpi->dev, dpi->dev->of_node, 1, -1); - if (IS_ERR(dpi->next_bridge)) { - ret = PTR_ERR(dpi->next_bridge); - if (ret == -EPROBE_DEFER) - return ret; - - /* Old devicetree has only one endpoint */ - dpi->next_bridge = devm_drm_of_get_bridge(dpi->dev, dpi->dev->of_node, 0, 0); - if (IS_ERR(dpi->next_bridge)) - return dev_err_probe(dpi->dev, PTR_ERR(dpi->next_bridge), - "Failed to get bridge\n"); - } return drm_bridge_attach(encoder, dpi->next_bridge, &dpi->bridge, flags); @@ -1319,6 +1305,15 @@ static int mtk_dpi_probe(struct platform_device *pdev) if (dpi->irq < 0) return dpi->irq; + dpi->next_bridge = devm_drm_of_get_bridge(dpi->dev, dpi->dev->of_node, 1, -1); + if (IS_ERR(dpi->next_bridge) && PTR_ERR(dpi->next_bridge) == -ENODEV) { + /* Old devicetree has only one endpoint */ + dpi->next_bridge = devm_drm_of_get_bridge(dpi->dev, dpi->dev->of_node, 0, 0); + } + if (IS_ERR(dpi->next_bridge)) + return dev_err_probe(dpi->dev, PTR_ERR(dpi->next_bridge), + "Failed to get bridge\n"); + platform_set_drvdata(pdev, dpi); dpi->bridge.of_node = dev->of_node; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 31ff2922758a44..a94c51a8326162 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -1123,7 +1123,7 @@ static int mtk_drm_probe(struct platform_device *pdev) (void *)private->mmsys_dev, sizeof(*private->mmsys_dev)); private->ddp_comp[DDP_COMPONENT_DRM_OVL_ADAPTOR].dev = &ovl_adaptor->dev; - mtk_ddp_comp_init(NULL, &private->ddp_comp[DDP_COMPONENT_DRM_OVL_ADAPTOR], + mtk_ddp_comp_init(dev, NULL, &private->ddp_comp[DDP_COMPONENT_DRM_OVL_ADAPTOR], DDP_COMPONENT_DRM_OVL_ADAPTOR); component_match_add(dev, &match, compare_dev, &ovl_adaptor->dev); } @@ -1189,7 +1189,7 @@ static int mtk_drm_probe(struct platform_device *pdev) node); } - ret = mtk_ddp_comp_init(node, &private->ddp_comp[comp_id], comp_id); + ret = mtk_ddp_comp_init(dev, node, &private->ddp_comp[comp_id], comp_id); if (ret) { of_node_put(node); goto err_node; diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 0e2bcd5f67b767..d7726091819c47 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -1002,12 +1002,6 @@ static int mtk_dsi_host_attach(struct mipi_dsi_host *host, return PTR_ERR(dsi->next_bridge); } - /* - * set flag to request the DSI host bridge be pre-enabled before device bridge - * in the chain, so the DSI host is ready when the device bridge is pre-enabled - */ - dsi->next_bridge->pre_enable_prev_first = true; - drm_bridge_add(&dsi->bridge); ret = component_add(host->dev, &mtk_dsi_component_ops); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index b766dd5e6c8de6..306e2c90731144 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1345,6 +1345,13 @@ static const struct drm_bridge_funcs mtk_hdmi_bridge_funcs = { .edid_read = mtk_hdmi_bridge_edid_read, }; +static void mtk_hdmi_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int mtk_hdmi_get_cec_dev(struct mtk_hdmi *hdmi, struct device *dev, struct device_node *np) { struct platform_device *cec_pdev; @@ -1369,6 +1376,10 @@ static int mtk_hdmi_get_cec_dev(struct mtk_hdmi *hdmi, struct device *dev, struc } of_node_put(cec_np); + ret = devm_add_action_or_reset(dev, mtk_hdmi_put_device, &cec_pdev->dev); + if (ret) + return ret; + /* * The mediatek,syscon-hdmi property contains a phandle link to the * MMSYS_CONFIG device and the register offset of the HDMI_SYS_CFG @@ -1423,6 +1434,10 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, if (!hdmi->ddc_adpt) return dev_err_probe(dev, -EINVAL, "Failed to get ddc i2c adapter by node\n"); + ret = devm_add_action_or_reset(dev, mtk_hdmi_put_device, &hdmi->ddc_adpt->dev); + if (ret) + return ret; + ret = mtk_hdmi_get_cec_dev(hdmi, dev, np); if (ret) return ret; diff --git a/drivers/gpu/drm/mgag200/mgag200_bmc.c b/drivers/gpu/drm/mgag200/mgag200_bmc.c index a689c71ff1653d..bbdeb791c5b38b 100644 --- a/drivers/gpu/drm/mgag200/mgag200_bmc.c +++ b/drivers/gpu/drm/mgag200/mgag200_bmc.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only #include +#include #include #include @@ -12,7 +13,7 @@ void mgag200_bmc_stop_scanout(struct mga_device *mdev) { u8 tmp; - int iter_max; + int ret; /* * 1 - The first step is to inform the BMC of an upcoming mode @@ -42,30 +43,22 @@ void mgag200_bmc_stop_scanout(struct mga_device *mdev) /* * 3a- The third step is to verify if there is an active scan. - * We are waiting for a 0 on remhsyncsts ). + * We are waiting for a 0 on remhsyncsts (). */ - iter_max = 300; - while (!(tmp & 0x1) && iter_max) { - WREG8(DAC_INDEX, MGA1064_SPAREREG); - tmp = RREG8(DAC_DATA); - udelay(1000); - iter_max--; - } + ret = read_poll_timeout(RREG_DAC, tmp, !(tmp & 0x1), + 1000, 300000, false, + MGA1064_SPAREREG); + if (ret == -ETIMEDOUT) + return; /* - * 3b- This step occurs only if the remove is actually + * 3b- This step occurs only if the remote BMC is actually * scanning. We are waiting for the end of the frame which is * a 1 on remvsyncsts (XSPAREREG<1>) */ - if (iter_max) { - iter_max = 300; - while ((tmp & 0x2) && iter_max) { - WREG8(DAC_INDEX, MGA1064_SPAREREG); - tmp = RREG8(DAC_DATA); - udelay(1000); - iter_max--; - } - } + (void)read_poll_timeout(RREG_DAC, tmp, (tmp & 0x2), + 1000, 300000, false, + MGA1064_SPAREREG); } void mgag200_bmc_start_scanout(struct mga_device *mdev) diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h index f4bf40cd7c88a8..a875c4bf8cbe4c 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.h +++ b/drivers/gpu/drm/mgag200/mgag200_drv.h @@ -111,6 +111,12 @@ #define DAC_INDEX 0x3c00 #define DAC_DATA 0x3c0a +#define RREG_DAC(reg) \ + ({ \ + WREG8(DAC_INDEX, reg); \ + RREG8(DAC_DATA); \ + }) \ + #define WREG_DAC(reg, v) \ do { \ WREG8(DAC_INDEX, reg); \ diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index 951d715dea3011..d019177462cf7f 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -161,6 +161,30 @@ static void mgag200_set_startadd(struct mga_device *mdev, WREG_ECRT(0x00, crtcext0); } +/* + * Set the opmode for the hardware swapper for Big-Endian processor + * support for the frame buffer aperture and DMAWIN space. + */ +static void mgag200_set_datasiz(struct mga_device *mdev, u32 format) +{ +#if defined(__BIG_ENDIAN) + u32 opmode = RREG32(MGAREG_OPMODE); + + opmode &= ~(GENMASK(17, 16) | GENMASK(9, 8) | GENMASK(3, 2)); + + /* Big-endian byte-swapping */ + switch (format) { + case DRM_FORMAT_RGB565: + opmode |= 0x10100; + break; + case DRM_FORMAT_XRGB8888: + opmode |= 0x20200; + break; + } + WREG32(MGAREG_OPMODE, opmode); +#endif +} + void mgag200_init_registers(struct mga_device *mdev) { u8 crtc11, misc; @@ -496,6 +520,7 @@ void mgag200_primary_plane_helper_atomic_update(struct drm_plane *plane, struct drm_atomic_helper_damage_iter iter; struct drm_rect damage; + mgag200_set_datasiz(mdev, fb->format->format); drm_atomic_helper_damage_iter_init(&iter, old_plane_state, plane_state); drm_atomic_for_each_plane_damage(&iter, &damage) { mgag200_handle_damage(mdev, shadow_plane_state->data, fb, &damage); diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c index ec38db45d8a366..e67ed58aa3d8fd 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c @@ -77,7 +77,10 @@ static bool a2xx_me_init(struct msm_gpu *gpu) /* Vertex and Pixel Shader Start Addresses in instructions * (3 DWORDS per instruction) */ - OUT_RING(ring, 0x80000180); + if (adreno_is_a225(adreno_gpu)) + OUT_RING(ring, 0x80000300); + else + OUT_RING(ring, 0x80000180); /* Maximum Contexts */ OUT_RING(ring, 0x00000001); /* Write Confirm Interval and The CP will wait the @@ -234,7 +237,7 @@ static int a2xx_hw_init(struct msm_gpu *gpu) * word (0x20xxxx for A200, 0x220xxx for A220, 0x225xxx for A225). * Older firmware files, which lack protection support, have 0 instead. */ - if (ptr[1] == 0) { + if (ptr[1] == 0 && !a2xx_gpu->protection_disabled) { dev_warn(gpu->dev->dev, "Legacy firmware detected, disabling protection support\n"); a2xx_gpu->protection_disabled = true; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c index 44df6410bce176..31974a4d7e14b9 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c @@ -501,8 +501,6 @@ static const struct adreno_reglist a690_hwcg[] = { {REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222}, {REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111}, {REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555}, - {REG_A6XX_GPU_GMU_AO_GMU_CGC_DELAY_CNTL, 0x10111}, - {REG_A6XX_GPU_GMU_AO_GMU_CGC_HYST_CNTL, 0x5555}, {} }; @@ -1360,6 +1358,7 @@ static const u32 a750_ifpc_reglist_regs[] = { REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(2), REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(3), REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(4), + REG_A6XX_RBBM_PERFCTR_CNTL, REG_A6XX_TPL1_NC_MODE_CNTL, REG_A6XX_SP_NC_MODE_CNTL, REG_A6XX_CP_DBG_ECO_CNTL, diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 4e6dc16e4a4c48..21a3f9b0ab4c25 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -485,8 +485,9 @@ static void a6xx_gemnoc_workaround(struct a6xx_gmu *gmu) * in the power down sequence not being fully executed. That in turn can * prevent CX_GDSC from collapsing. Assert Qactive to avoid this. */ - if (adreno_is_a621(adreno_gpu) || adreno_is_7c3(adreno_gpu)) - gmu_write(gmu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, BIT(0)); + if (adreno_is_a7xx(adreno_gpu) || (adreno_is_a621(adreno_gpu) || + adreno_is_7c3(adreno_gpu))) + gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_CX_FALNEXT_INTF, BIT(0)); } /* Let the GMU know that we are about to go into slumber */ @@ -522,10 +523,9 @@ static int a6xx_gmu_notify_slumber(struct a6xx_gmu *gmu) } out: - a6xx_gemnoc_workaround(gmu); - /* Put fence into allow mode */ gmu_write(gmu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0); + a6xx_gemnoc_workaround(gmu); return ret; } @@ -1492,13 +1492,14 @@ static unsigned int a6xx_gmu_get_arc_level(struct device *dev, } static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes, - unsigned long *freqs, int freqs_count, const char *id) + unsigned long *freqs, int freqs_count, + const char *pri_id, const char *sec_id) { int i, j; const u16 *pri, *sec; size_t pri_count, sec_count; - pri = cmd_db_read_aux_data(id, &pri_count); + pri = cmd_db_read_aux_data(pri_id, &pri_count); if (IS_ERR(pri)) return PTR_ERR(pri); /* @@ -1509,13 +1510,7 @@ static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes, if (!pri_count) return -EINVAL; - /* - * Some targets have a separate gfx mxc rail. So try to read that first and then fall back - * to regular mx rail if it is missing - */ - sec = cmd_db_read_aux_data("gmxc.lvl", &sec_count); - if (IS_ERR(sec) && sec != ERR_PTR(-EPROBE_DEFER)) - sec = cmd_db_read_aux_data("mx.lvl", &sec_count); + sec = cmd_db_read_aux_data(sec_id, &sec_count); if (IS_ERR(sec)) return PTR_ERR(sec); @@ -1583,15 +1578,24 @@ static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *gmu) struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; const struct a6xx_info *info = adreno_gpu->info->a6xx; struct msm_gpu *gpu = &adreno_gpu->base; + const char *sec_id; + const u16 *gmxc; int ret; + gmxc = cmd_db_read_aux_data("gmxc.lvl", NULL); + if (gmxc == ERR_PTR(-EPROBE_DEFER)) + return -EPROBE_DEFER; + + /* If GMxC is present, prefer that as secondary rail for GX votes */ + sec_id = IS_ERR_OR_NULL(gmxc) ? "mx.lvl" : "gmxc.lvl"; + /* Build the GX votes */ ret = a6xx_gmu_rpmh_arc_votes_init(&gpu->pdev->dev, gmu->gx_arc_votes, - gmu->gpu_freqs, gmu->nr_gpu_freqs, "gfx.lvl"); + gmu->gpu_freqs, gmu->nr_gpu_freqs, "gfx.lvl", sec_id); /* Build the CX votes */ ret |= a6xx_gmu_rpmh_arc_votes_init(gmu->dev, gmu->cx_arc_votes, - gmu->gmu_freqs, gmu->nr_gmu_freqs, "cx.lvl"); + gmu->gmu_freqs, gmu->nr_gmu_freqs, "cx.lvl", "mx.lvl"); /* Build the interconnect votes */ if (info->bcms && gmu->nr_gpu_bws > 1) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index b8f8ae940b55f5..d1eaa849b19783 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -224,7 +224,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, OUT_RING(ring, submit->seqno - 1); OUT_PKT7(ring, CP_THREAD_CONTROL, 1); - OUT_RING(ring, CP_SET_THREAD_BOTH); + OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BOTH); /* Reset state used to synchronize BR and BV */ OUT_PKT7(ring, CP_RESET_CONTEXT_STATE, 1); @@ -235,7 +235,13 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, CP_RESET_CONTEXT_STATE_0_RESET_GLOBAL_LOCAL_TS); OUT_PKT7(ring, CP_THREAD_CONTROL, 1); - OUT_RING(ring, CP_SET_THREAD_BR); + OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BOTH); + + OUT_PKT7(ring, CP_EVENT_WRITE, 1); + OUT_RING(ring, LRZ_FLUSH); + + OUT_PKT7(ring, CP_THREAD_CONTROL, 1); + OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BR); } if (!sysprof) { @@ -831,15 +837,17 @@ static void a7xx_patch_pwrup_reglist(struct msm_gpu *gpu) lock->gpu_req = lock->cpu_req = lock->turn = 0; reglist = adreno_gpu->info->a6xx->ifpc_reglist; - lock->ifpc_list_len = reglist->count; + if (reglist) { + lock->ifpc_list_len = reglist->count; - /* - * For each entry in each of the lists, write the offset and the current - * register value into the GPU buffer - */ - for (i = 0; i < reglist->count; i++) { - *dest++ = reglist->regs[i]; - *dest++ = gpu_read(gpu, reglist->regs[i]); + /* + * For each entry in each of the lists, write the offset and the current + * register value into the GPU buffer + */ + for (i = 0; i < reglist->count; i++) { + *dest++ = reglist->regs[i]; + *dest++ = gpu_read(gpu, reglist->regs[i]); + } } reglist = adreno_gpu->info->a6xx->pwrup_reglist; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 4c7f3c642f6ac0..9cec333e23e15b 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -1255,7 +1255,7 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, return; /* Set the fence to ALLOW mode so we can access the registers */ - gpu_write(gpu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0); + gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0); _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[2], &a6xx_state->gmu_registers[3], false); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_preempt.c b/drivers/gpu/drm/msm/adreno/a6xx_preempt.c index afc5f4aa3b1733..747a22afad9f6f 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_preempt.c @@ -454,11 +454,11 @@ void a6xx_preempt_init(struct msm_gpu *gpu) gpu->vm, &a6xx_gpu->preempt_postamble_bo, &a6xx_gpu->preempt_postamble_iova); - preempt_prepare_postamble(a6xx_gpu); - if (IS_ERR(a6xx_gpu->preempt_postamble_ptr)) goto fail; + preempt_prepare_postamble(a6xx_gpu); + timer_setup(&a6xx_gpu->preempt_timer, a6xx_preempt_timer, 0); return; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h index 8f978b9c345202..2f8688224f3430 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h @@ -13,6 +13,7 @@ static const struct dpu_caps sc7280_dpu_caps = { .has_dim_layer = true, .has_idle_pc = true, .max_linewidth = 2400, + .has_3d_merge = true, .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, }; @@ -134,17 +135,24 @@ static const struct dpu_pingpong_cfg sc7280_pp[] = { .name = "pingpong_2", .id = PINGPONG_2, .base = 0x6b000, .len = 0, .sblk = &sc7280_pp_sblk, - .merge_3d = 0, + .merge_3d = MERGE_3D_1, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), }, { .name = "pingpong_3", .id = PINGPONG_3, .base = 0x6c000, .len = 0, .sblk = &sc7280_pp_sblk, - .merge_3d = 0, + .merge_3d = MERGE_3D_1, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), }, }; +static const struct dpu_merge_3d_cfg sc7280_merge_3d[] = { + { + .name = "merge_3d_1", .id = MERGE_3D_1, + .base = 0x4f000, .len = 0x8, + }, +}; + /* NOTE: sc7280 only has one DSC hard slice encoder */ static const struct dpu_dsc_cfg sc7280_dsc[] = { { @@ -247,6 +255,8 @@ const struct dpu_mdss_cfg dpu_sc7280_cfg = { .mixer = sc7280_lm, .pingpong_count = ARRAY_SIZE(sc7280_pp), .pingpong = sc7280_pp, + .merge_3d_count = ARRAY_SIZE(sc7280_merge_3d), + .merge_3d = sc7280_merge_3d, .dsc_count = ARRAY_SIZE(sc7280_dsc), .dsc = sc7280_dsc, .wb_count = ARRAY_SIZE(sc7280_wb), diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 258edaa18fc02f..777eab5ad844ec 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -784,24 +784,24 @@ static void _dpu_encoder_update_vsync_source(struct dpu_encoder_virt *dpu_enc, return; } + vsync_cfg.vsync_source = disp_info->vsync_source; + vsync_cfg.frame_rate = drm_mode_vrefresh(&dpu_enc->base.crtc->state->adjusted_mode); + if (hw_mdptop->ops.setup_vsync_source) { for (i = 0; i < dpu_enc->num_phys_encs; i++) vsync_cfg.ppnumber[i] = dpu_enc->hw_pp[i]->idx; vsync_cfg.pp_count = dpu_enc->num_phys_encs; - vsync_cfg.frame_rate = drm_mode_vrefresh(&dpu_enc->base.crtc->state->adjusted_mode); - - vsync_cfg.vsync_source = disp_info->vsync_source; hw_mdptop->ops.setup_vsync_source(hw_mdptop, &vsync_cfg); + } - for (i = 0; i < dpu_enc->num_phys_encs; i++) { - phys_enc = dpu_enc->phys_encs[i]; + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + phys_enc = dpu_enc->phys_encs[i]; - if (phys_enc->has_intf_te && phys_enc->hw_intf->ops.vsync_sel) - phys_enc->hw_intf->ops.vsync_sel(phys_enc->hw_intf, - vsync_cfg.vsync_source); - } + if (phys_enc->has_intf_te && phys_enc->hw_intf->ops.vsync_sel) + phys_enc->hw_intf->ops.vsync_sel(phys_enc->hw_intf, + &vsync_cfg); } } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c index 0ec6d67c7c70b1..93db1484f60698 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c @@ -681,10 +681,11 @@ static int dpu_encoder_phys_cmd_wait_for_commit_done( if (!dpu_encoder_phys_cmd_is_master(phys_enc)) return 0; - if (phys_enc->hw_ctl->ops.is_started(phys_enc->hw_ctl)) - return dpu_encoder_phys_cmd_wait_for_tx_complete(phys_enc); + if (phys_enc->irq[INTR_IDX_CTL_START] && + !phys_enc->hw_ctl->ops.is_started(phys_enc->hw_ctl)) + return _dpu_encoder_phys_cmd_wait_for_ctl_start(phys_enc); - return _dpu_encoder_phys_cmd_wait_for_ctl_start(phys_enc); + return dpu_encoder_phys_cmd_wait_for_tx_complete(phys_enc); } static void dpu_encoder_phys_cmd_handle_post_kickoff( diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c index 46f348972a975d..6d28f2281c7657 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c @@ -247,14 +247,12 @@ static void dpu_encoder_phys_wb_setup_ctl(struct dpu_encoder_phys *phys_enc) if (hw_cdm) intf_cfg.cdm = hw_cdm->idx; - if (phys_enc->hw_pp->merge_3d && phys_enc->hw_pp->merge_3d->ops.setup_3d_mode) - phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d, - mode_3d); + if (hw_pp && hw_pp->merge_3d && hw_pp->merge_3d->ops.setup_3d_mode) + hw_pp->merge_3d->ops.setup_3d_mode(hw_pp->merge_3d, mode_3d); /* setup which pp blk will connect to this wb */ - if (hw_pp && phys_enc->hw_wb->ops.bind_pingpong_blk) - phys_enc->hw_wb->ops.bind_pingpong_blk(phys_enc->hw_wb, - phys_enc->hw_pp->idx); + if (hw_pp && hw_wb->ops.bind_pingpong_blk) + hw_wb->ops.bind_pingpong_blk(hw_wb, hw_pp->idx); phys_enc->hw_ctl->ops.setup_intf_cfg(phys_enc->hw_ctl, &intf_cfg); } else if (phys_enc->hw_ctl && phys_enc->hw_ctl->ops.setup_intf_cfg) { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h index b7013c9822d232..cc7cc6f6f7cda6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h @@ -71,12 +71,6 @@ struct dpu_hw_dsc *dpu_hw_dsc_init_1_2(struct drm_device *dev, const struct dpu_dsc_cfg *cfg, void __iomem *addr); -/** - * dpu_hw_dsc_destroy - destroys dsc driver context - * @dsc: Pointer to dsc driver context returned by dpu_hw_dsc_init - */ -void dpu_hw_dsc_destroy(struct dpu_hw_dsc *dsc); - static inline struct dpu_hw_dsc *to_dpu_hw_dsc(struct dpu_hw_blk *hw) { return container_of(hw, struct dpu_hw_dsc, base); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c index a80ac82a96255d..7e620f59098499 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c @@ -67,6 +67,10 @@ #define INTF_MISR_CTRL 0x180 #define INTF_MISR_SIGNATURE 0x184 +#define INTF_WD_TIMER_0_CTL 0x230 +#define INTF_WD_TIMER_0_CTL2 0x234 +#define INTF_WD_TIMER_0_LOAD_VALUE 0x238 + #define INTF_MUX 0x25C #define INTF_STATUS 0x26C #define INTF_AVR_CONTROL 0x270 @@ -475,7 +479,20 @@ static int dpu_hw_intf_get_vsync_info(struct dpu_hw_intf *intf, } static void dpu_hw_intf_vsync_sel(struct dpu_hw_intf *intf, - enum dpu_vsync_source vsync_source) + struct dpu_vsync_source_cfg *cfg) +{ + struct dpu_hw_blk_reg_map *c; + + if (!intf) + return; + + c = &intf->hw; + + DPU_REG_WRITE(c, INTF_TEAR_MDP_VSYNC_SEL, (cfg->vsync_source & 0xf)); +} + +static void dpu_hw_intf_vsync_sel_v8(struct dpu_hw_intf *intf, + struct dpu_vsync_source_cfg *cfg) { struct dpu_hw_blk_reg_map *c; @@ -484,7 +501,30 @@ static void dpu_hw_intf_vsync_sel(struct dpu_hw_intf *intf, c = &intf->hw; - DPU_REG_WRITE(c, INTF_TEAR_MDP_VSYNC_SEL, (vsync_source & 0xf)); + if (cfg->vsync_source >= DPU_VSYNC_SOURCE_WD_TIMER_4 && + cfg->vsync_source <= DPU_VSYNC_SOURCE_WD_TIMER_1) { + pr_warn_once("DPU 8.x supports only GPIOs and timer0 as TE sources\n"); + return; + } + + if (cfg->vsync_source == DPU_VSYNC_SOURCE_WD_TIMER_0) { + u32 reg; + + DPU_REG_WRITE(c, INTF_WD_TIMER_0_LOAD_VALUE, + CALCULATE_WD_LOAD_VALUE(cfg->frame_rate)); + + DPU_REG_WRITE(c, INTF_WD_TIMER_0_CTL, BIT(0)); /* clear timer */ + + reg = BIT(8); /* enable heartbeat timer */ + reg |= BIT(0); /* enable WD timer */ + reg |= BIT(1); /* select default 16 clock ticks */ + DPU_REG_WRITE(c, INTF_WD_TIMER_0_CTL2, reg); + + /* make sure that timers are enabled/disabled for vsync state */ + wmb(); + } + + dpu_hw_intf_vsync_sel(intf, cfg); } static void dpu_hw_intf_disable_autorefresh(struct dpu_hw_intf *intf, @@ -598,7 +638,10 @@ struct dpu_hw_intf *dpu_hw_intf_init(struct drm_device *dev, c->ops.enable_tearcheck = dpu_hw_intf_enable_te; c->ops.disable_tearcheck = dpu_hw_intf_disable_te; c->ops.connect_external_te = dpu_hw_intf_connect_external_te; - c->ops.vsync_sel = dpu_hw_intf_vsync_sel; + if (mdss_rev->core_major_ver >= 8) + c->ops.vsync_sel = dpu_hw_intf_vsync_sel_v8; + else + c->ops.vsync_sel = dpu_hw_intf_vsync_sel; c->ops.disable_autorefresh = dpu_hw_intf_disable_autorefresh; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h index f31067a9aaf1d6..e84ab849d71a98 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h @@ -12,6 +12,7 @@ #include "dpu_hw_util.h" struct dpu_hw_intf; +struct dpu_vsync_source_cfg; /* intf timing settings */ struct dpu_hw_intf_timing_params { @@ -107,7 +108,7 @@ struct dpu_hw_intf_ops { int (*connect_external_te)(struct dpu_hw_intf *intf, bool enable_external_te); - void (*vsync_sel)(struct dpu_hw_intf *intf, enum dpu_vsync_source vsync_source); + void (*vsync_sel)(struct dpu_hw_intf *intf, struct dpu_vsync_source_cfg *cfg); /** * Disable autorefresh if enabled diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c index 6f1fc790ad6d81..6ff4902fce08ee 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c @@ -72,6 +72,8 @@ #define SSPP_EXCL_REC_XY_REC1 0x188 #define SSPP_EXCL_REC_SIZE 0x1B4 #define SSPP_EXCL_REC_XY 0x1B8 +#define SSPP_UBWC_STATIC_CTRL_REC1 0x1c0 +#define SSPP_UBWC_ERROR_STATUS_REC1 0x1c8 #define SSPP_CLK_CTRL 0x330 /* SSPP_SRC_OP_MODE & OP_MODE_REC1 */ @@ -215,7 +217,7 @@ static void dpu_hw_sspp_setup_format(struct dpu_sw_pipe *pipe, u32 chroma_samp, unpack, src_format; u32 opmode = 0; u32 fast_clear = 0; - u32 op_mode_off, unpack_pat_off, format_off; + u32 op_mode_off, unpack_pat_off, format_off, ubwc_ctrl_off, ubwc_error_off; if (!ctx || !fmt) return; @@ -225,10 +227,21 @@ static void dpu_hw_sspp_setup_format(struct dpu_sw_pipe *pipe, op_mode_off = SSPP_SRC_OP_MODE; unpack_pat_off = SSPP_SRC_UNPACK_PATTERN; format_off = SSPP_SRC_FORMAT; + ubwc_ctrl_off = SSPP_UBWC_STATIC_CTRL; + ubwc_error_off = SSPP_UBWC_ERROR_STATUS; } else { op_mode_off = SSPP_SRC_OP_MODE_REC1; unpack_pat_off = SSPP_SRC_UNPACK_PATTERN_REC1; format_off = SSPP_SRC_FORMAT_REC1; + + /* reg wasn't present before DPU 8.0 */ + if (ctx->mdss_ver->core_major_ver >= 8) { + ubwc_ctrl_off = SSPP_UBWC_STATIC_CTRL_REC1; + ubwc_error_off = SSPP_UBWC_ERROR_STATUS_REC1; + } else { + ubwc_ctrl_off = SSPP_UBWC_STATIC_CTRL; + ubwc_error_off = SSPP_UBWC_ERROR_STATUS; + } } c = &ctx->hw; @@ -270,33 +283,35 @@ static void dpu_hw_sspp_setup_format(struct dpu_sw_pipe *pipe, ((fmt->bpp - 1) << 9); if (fmt->fetch_mode != MDP_FETCH_LINEAR) { + u32 hbb = ctx->ubwc->highest_bank_bit - 13; + if (MSM_FORMAT_IS_UBWC(fmt)) opmode |= MDSS_MDP_OP_BWC_EN; src_format |= (fmt->fetch_mode & 3) << 30; /*FRAME_FORMAT */ DPU_REG_WRITE(c, SSPP_FETCH_CONFIG, DPU_FETCH_CONFIG_RESET_VALUE | - ctx->ubwc->highest_bank_bit << 18); + hbb << 18); switch (ctx->ubwc->ubwc_enc_version) { case UBWC_1_0: fast_clear = fmt->alpha_enable ? BIT(31) : 0; - DPU_REG_WRITE(c, SSPP_UBWC_STATIC_CTRL, + DPU_REG_WRITE(c, ubwc_ctrl_off, fast_clear | (ctx->ubwc->ubwc_swizzle & 0x1) | BIT(8) | - (ctx->ubwc->highest_bank_bit << 4)); + (hbb << 4)); break; case UBWC_2_0: fast_clear = fmt->alpha_enable ? BIT(31) : 0; - DPU_REG_WRITE(c, SSPP_UBWC_STATIC_CTRL, + DPU_REG_WRITE(c, ubwc_ctrl_off, fast_clear | (ctx->ubwc->ubwc_swizzle) | - (ctx->ubwc->highest_bank_bit << 4)); + (hbb << 4)); break; case UBWC_3_0: - DPU_REG_WRITE(c, SSPP_UBWC_STATIC_CTRL, + DPU_REG_WRITE(c, ubwc_ctrl_off, BIT(30) | (ctx->ubwc->ubwc_swizzle) | - (ctx->ubwc->highest_bank_bit << 4)); + (hbb << 4)); break; case UBWC_4_0: - DPU_REG_WRITE(c, SSPP_UBWC_STATIC_CTRL, + DPU_REG_WRITE(c, ubwc_ctrl_off, MSM_FORMAT_IS_YUV(fmt) ? 0 : BIT(30)); break; } @@ -325,7 +340,7 @@ static void dpu_hw_sspp_setup_format(struct dpu_sw_pipe *pipe, DPU_REG_WRITE(c, op_mode_off, opmode); /* clear previous UBWC error */ - DPU_REG_WRITE(c, SSPP_UBWC_ERROR_STATUS, BIT(31)); + DPU_REG_WRITE(c, ubwc_error_off, BIT(31)); } static void dpu_hw_sspp_setup_pe_config(struct dpu_hw_sspp *ctx, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c index 96dc10589bee6c..1ebd75d4f9be8d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c @@ -22,13 +22,6 @@ #define TRAFFIC_SHAPER_WR_CLIENT(num) (0x060 + (num * 4)) #define TRAFFIC_SHAPER_FIXPOINT_FACTOR 4 -#define MDP_TICK_COUNT 16 -#define XO_CLK_RATE 19200 -#define MS_TICKS_IN_SEC 1000 - -#define CALCULATE_WD_LOAD_VALUE(fps) \ - ((uint32_t)((MS_TICKS_IN_SEC * XO_CLK_RATE)/(MDP_TICK_COUNT * fps))) - static void dpu_hw_setup_split_pipe(struct dpu_hw_mdp *mdp, struct split_pipe_cfg *cfg) { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h index 67b08e99335dcf..6fe65bc3bff4e8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h @@ -21,6 +21,13 @@ #define TO_S15D16(_x_)((_x_) << 7) +#define MDP_TICK_COUNT 16 +#define XO_CLK_RATE 19200 +#define MS_TICKS_IN_SEC 1000 + +#define CALCULATE_WD_LOAD_VALUE(fps) \ + ((uint32_t)((MS_TICKS_IN_SEC * XO_CLK_RATE)/(MDP_TICK_COUNT * fps))) + extern const struct dpu_csc_cfg dpu_csc_YUV2RGB_601L; extern const struct dpu_csc_cfg dpu_csc10_YUV2RGB_601L; extern const struct dpu_csc_cfg dpu_csc10_rgb2yuv_601l; diff --git a/drivers/gpu/drm/msm/disp/mdp_format.c b/drivers/gpu/drm/msm/disp/mdp_format.c index 426782d50cb49d..eebedb1a2636e7 100644 --- a/drivers/gpu/drm/msm/disp/mdp_format.c +++ b/drivers/gpu/drm/msm/disp/mdp_format.c @@ -479,25 +479,25 @@ static const struct msm_format mdp_formats[] = { 0, BPC8, BPC8, BPC8, C2_R_Cr, C0_G_Y, C1_B_Cb, C0_G_Y, false, CHROMA_H2V1, 4, 2, MSM_FORMAT_FLAG_YUV, - MDP_FETCH_LINEAR, 2), + MDP_FETCH_LINEAR, 1), INTERLEAVED_YUV_FMT(UYVY, 0, BPC8, BPC8, BPC8, C1_B_Cb, C0_G_Y, C2_R_Cr, C0_G_Y, false, CHROMA_H2V1, 4, 2, MSM_FORMAT_FLAG_YUV, - MDP_FETCH_LINEAR, 2), + MDP_FETCH_LINEAR, 1), INTERLEAVED_YUV_FMT(YUYV, 0, BPC8, BPC8, BPC8, C0_G_Y, C1_B_Cb, C0_G_Y, C2_R_Cr, false, CHROMA_H2V1, 4, 2, MSM_FORMAT_FLAG_YUV, - MDP_FETCH_LINEAR, 2), + MDP_FETCH_LINEAR, 1), INTERLEAVED_YUV_FMT(YVYU, 0, BPC8, BPC8, BPC8, C0_G_Y, C2_R_Cr, C0_G_Y, C1_B_Cb, false, CHROMA_H2V1, 4, 2, MSM_FORMAT_FLAG_YUV, - MDP_FETCH_LINEAR, 2), + MDP_FETCH_LINEAR, 1), /* 3 plane YUV */ PLANAR_YUV_FMT(YUV420, diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index c42fd2c17a328f..38ed4de8313e31 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -2395,20 +2395,32 @@ static void msm_dp_ctrl_config_msa(struct msm_dp_ctrl_private *ctrl, bool is_ycbcr_420) { u32 pixel_m, pixel_n; - u32 mvid, nvid, pixel_div = 0, dispcc_input_rate; + u32 mvid, nvid, pixel_div, dispcc_input_rate; u32 const nvid_fixed = DP_LINK_CONSTANT_N_VALUE; u32 const link_rate_hbr2 = 540000; u32 const link_rate_hbr3 = 810000; unsigned long den, num; - if (rate == link_rate_hbr3) + switch (rate) { + case link_rate_hbr3: pixel_div = 6; - else if (rate == 162000 || rate == 270000) - pixel_div = 2; - else if (rate == link_rate_hbr2) + break; + case link_rate_hbr2: pixel_div = 4; - else + break; + case 162000: + case 270000: + pixel_div = 2; + break; + default: + /* + * This cannot be reached but the compiler is not able to know + * that statically so return early to avoid a possibly invalid + * division. + */ DRM_ERROR("Invalid pixel mux divider\n"); + return; + } dispcc_input_rate = (rate * 10) / pixel_div; diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index d87d47cc7ec3eb..f247aad5539758 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -133,8 +133,8 @@ struct msm_dp_desc { static const struct msm_dp_desc msm_dp_desc_sa8775p[] = { { .io_start = 0x0af54000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true }, { .io_start = 0x0af5c000, .id = MSM_DP_CONTROLLER_1, .wide_bus_supported = true }, - { .io_start = 0x22154000, .id = MSM_DP_CONTROLLER_2, .wide_bus_supported = true }, - { .io_start = 0x2215c000, .id = MSM_DP_CONTROLLER_3, .wide_bus_supported = true }, + { .io_start = 0x22154000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true }, + { .io_start = 0x2215c000, .id = MSM_DP_CONTROLLER_1, .wide_bus_supported = true }, {} }; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c index fdefcbd9c2848a..a156c7e7cea832 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c @@ -628,12 +628,7 @@ static int dsi_pll_14nm_postdiv_determine_rate(struct clk_hw *hw, DBG("DSI%d PLL parent rate=%lu", pll_14nm->phy->id, req->rate); - req->rate = divider_round_rate(hw, req->rate, &req->best_parent_rate, - NULL, - postdiv->width, - postdiv->flags); - - return 0; + return divider_determine_rate(hw, req, NULL, postdiv->width, postdiv->flags); } static int dsi_pll_14nm_postdiv_set_rate(struct clk_hw *hw, unsigned long rate, diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 17759abc46d7d7..dd0605fe1243da 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -287,16 +287,17 @@ static void crashstate_get_bos(struct msm_gpu_state *state, struct msm_gem_submi state->bos = kcalloc(cnt, sizeof(struct msm_gpu_state_bo), GFP_KERNEL); - drm_gpuvm_for_each_va (vma, submit->vm) { - bool dump = rd_full || (vma->flags & MSM_VMA_DUMP); + if (state->bos) + drm_gpuvm_for_each_va(vma, submit->vm) { + bool dump = rd_full || (vma->flags & MSM_VMA_DUMP); - /* Skip MAP_NULL/PRR VMAs: */ - if (!vma->gem.obj) - continue; + /* Skip MAP_NULL/PRR VMAs: */ + if (!vma->gem.obj) + continue; - msm_gpu_crashstate_get_bo(state, vma->gem.obj, vma->va.addr, - dump, vma->gem.offset, vma->va.range); - } + msm_gpu_crashstate_get_bo(state, vma->gem.obj, vma->va.addr, + dump, vma->gem.offset, vma->va.range); + } drm_exec_fini(&exec); } else { @@ -348,6 +349,10 @@ static void crashstate_get_vm_logs(struct msm_gpu_state *state, struct msm_gem_v state->vm_logs = kmalloc_array( state->nr_vm_logs, sizeof(vm->log[0]), GFP_KERNEL); + if (!state->vm_logs) { + state->nr_vm_logs = 0; + } + for (int i = 0; i < state->nr_vm_logs; i++) { int idx = (i + first) & vm_log_mask; diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index 2d0e3e784c044d..4dbb1b1d879f1b 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -229,7 +229,7 @@ static void msm_mdss_setup_ubwc_dec_50(struct msm_mdss *msm_mdss) { const struct qcom_ubwc_cfg_data *data = msm_mdss->mdss_data; u32 value = MDSS_UBWC_STATIC_UBWC_SWIZZLE(data->ubwc_swizzle) | - MDSS_UBWC_STATIC_HIGHEST_BANK_BIT(data->highest_bank_bit); + MDSS_UBWC_STATIC_HIGHEST_BANK_BIT(data->highest_bank_bit - 13); if (data->ubwc_bank_spread) value |= MDSS_UBWC_STATIC_UBWC_BANK_SPREAD; diff --git a/drivers/gpu/drm/nouveau/dispnv04/nouveau_i2c_encoder.c b/drivers/gpu/drm/nouveau/dispnv04/nouveau_i2c_encoder.c index e2bf99c433366b..a60209097a20a6 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/nouveau_i2c_encoder.c +++ b/drivers/gpu/drm/nouveau/dispnv04/nouveau_i2c_encoder.c @@ -94,26 +94,6 @@ int nouveau_i2c_encoder_init(struct drm_device *dev, return err; } -/** - * nouveau_i2c_encoder_destroy - Unregister the I2C device backing an encoder - * @drm_encoder: Encoder to be unregistered. - * - * This should be called from the @destroy method of an I2C slave - * encoder driver once I2C access is no longer needed. - */ -void nouveau_i2c_encoder_destroy(struct drm_encoder *drm_encoder) -{ - struct nouveau_i2c_encoder *encoder = to_encoder_i2c(drm_encoder); - struct i2c_client *client = nouveau_i2c_encoder_get_client(drm_encoder); - struct module *module = client->dev.driver->owner; - - i2c_unregister_device(client); - encoder->i2c_client = NULL; - - module_put(module); -} -EXPORT_SYMBOL(nouveau_i2c_encoder_destroy); - /* * Wrapper fxns which can be plugged in to drm_encoder_helper_funcs: */ diff --git a/drivers/gpu/drm/nouveau/dispnv50/atom.h b/drivers/gpu/drm/nouveau/dispnv50/atom.h index 93f8f4f645784e..b43c4f9bbcdf58 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/atom.h +++ b/drivers/gpu/drm/nouveau/dispnv50/atom.h @@ -152,8 +152,21 @@ static inline struct nv50_head_atom * nv50_head_atom_get(struct drm_atomic_state *state, struct drm_crtc *crtc) { struct drm_crtc_state *statec = drm_atomic_get_crtc_state(state, crtc); + if (IS_ERR(statec)) return (void *)statec; + + return nv50_head_atom(statec); +} + +static inline struct nv50_head_atom * +nv50_head_atom_get_new(struct drm_atomic_state *state, struct drm_crtc *crtc) +{ + struct drm_crtc_state *statec = drm_atomic_get_new_crtc_state(state, crtc); + + if (!statec) + return NULL; + return nv50_head_atom(statec); } diff --git a/drivers/gpu/drm/nouveau/dispnv50/curs507a.c b/drivers/gpu/drm/nouveau/dispnv50/curs507a.c index a95ee5dcc2e394..1a889139cb0530 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/curs507a.c +++ b/drivers/gpu/drm/nouveau/dispnv50/curs507a.c @@ -84,6 +84,7 @@ curs507a_prepare(struct nv50_wndw *wndw, struct nv50_head_atom *asyh, asyh->curs.handle = handle; asyh->curs.offset = offset; asyh->set.curs = asyh->curs.visible; + nv50_atom(asyh->state.state)->lock_core = true; } } diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index ef9e410babbfba..9a2c20fce0f3eb 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -583,7 +583,7 @@ nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) asyw->image.offset[0] = nvbo->offset; if (wndw->func->prepare) { - asyh = nv50_head_atom_get(asyw->state.state, asyw->state.crtc); + asyh = nv50_head_atom_get_new(asyw->state.state, asyw->state.crtc); if (IS_ERR(asyh)) return PTR_ERR(asyh); diff --git a/drivers/gpu/drm/nouveau/include/dispnv04/i2c/encoder_i2c.h b/drivers/gpu/drm/nouveau/include/dispnv04/i2c/encoder_i2c.h index 31334aa90781b3..869820701a56eb 100644 --- a/drivers/gpu/drm/nouveau/include/dispnv04/i2c/encoder_i2c.h +++ b/drivers/gpu/drm/nouveau/include/dispnv04/i2c/encoder_i2c.h @@ -202,7 +202,24 @@ static inline struct i2c_client *nouveau_i2c_encoder_get_client(struct drm_encod return to_encoder_i2c(encoder)->i2c_client; } -void nouveau_i2c_encoder_destroy(struct drm_encoder *encoder); +/** + * nouveau_i2c_encoder_destroy - Unregister the I2C device backing an encoder + * @drm_encoder: Encoder to be unregistered. + * + * This should be called from the @destroy method of an I2C slave + * encoder driver once I2C access is no longer needed. + */ +static __always_inline void nouveau_i2c_encoder_destroy(struct drm_encoder *drm_encoder) +{ + struct nouveau_i2c_encoder *encoder = to_encoder_i2c(drm_encoder); + struct i2c_client *client = nouveau_i2c_encoder_get_client(drm_encoder); + struct module *module = client->dev.driver->owner; + + i2c_unregister_device(client); + encoder->i2c_client = NULL; + + module_put(module); +} /* * Wrapper fxns which can be plugged in to drm_encoder_helper_funcs: diff --git a/drivers/gpu/drm/nouveau/include/nvif/client.h b/drivers/gpu/drm/nouveau/include/nvif/client.h index 03f1d564eb124d..b698c74306f8fe 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/client.h +++ b/drivers/gpu/drm/nouveau/include/nvif/client.h @@ -11,7 +11,7 @@ struct nvif_client { int nvif_client_ctor(struct nvif_client *parent, const char *name, struct nvif_client *); void nvif_client_dtor(struct nvif_client *); -int nvif_client_suspend(struct nvif_client *); +int nvif_client_suspend(struct nvif_client *, bool); int nvif_client_resume(struct nvif_client *); /*XXX*/ diff --git a/drivers/gpu/drm/nouveau/include/nvif/driver.h b/drivers/gpu/drm/nouveau/include/nvif/driver.h index 7b08ff769039a3..61c8a177b28fdc 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/driver.h +++ b/drivers/gpu/drm/nouveau/include/nvif/driver.h @@ -8,7 +8,7 @@ struct nvif_driver { const char *name; int (*init)(const char *name, u64 device, const char *cfg, const char *dbg, void **priv); - int (*suspend)(void *priv); + int (*suspend)(void *priv, bool runtime); int (*resume)(void *priv); int (*ioctl)(void *priv, void *data, u32 size, void **hack); void __iomem *(*map)(void *priv, u64 handle, u32 size); diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h index 99579e7b937605..954a89d43bada1 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h @@ -2,6 +2,7 @@ #ifndef __NVKM_DEVICE_H__ #define __NVKM_DEVICE_H__ #include +#include #include enum nvkm_subdev_type; @@ -93,7 +94,7 @@ struct nvkm_device_func { void *(*dtor)(struct nvkm_device *); int (*preinit)(struct nvkm_device *); int (*init)(struct nvkm_device *); - void (*fini)(struct nvkm_device *, bool suspend); + void (*fini)(struct nvkm_device *, enum nvkm_suspend_state suspend); int (*irq)(struct nvkm_device *); resource_size_t (*resource_addr)(struct nvkm_device *, enum nvkm_bar_id); resource_size_t (*resource_size)(struct nvkm_device *, enum nvkm_bar_id); diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/engine.h b/drivers/gpu/drm/nouveau/include/nvkm/core/engine.h index 738899fcf30b6a..1e97be6c65644e 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/core/engine.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/core/engine.h @@ -20,7 +20,7 @@ struct nvkm_engine_func { int (*oneinit)(struct nvkm_engine *); int (*info)(struct nvkm_engine *, u64 mthd, u64 *data); int (*init)(struct nvkm_engine *); - int (*fini)(struct nvkm_engine *, bool suspend); + int (*fini)(struct nvkm_engine *, enum nvkm_suspend_state suspend); int (*reset)(struct nvkm_engine *); int (*nonstall)(struct nvkm_engine *); void (*intr)(struct nvkm_engine *); diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/object.h b/drivers/gpu/drm/nouveau/include/nvkm/core/object.h index 10107ef3ca49ef..54d356154274f9 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/core/object.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/core/object.h @@ -2,6 +2,7 @@ #ifndef __NVKM_OBJECT_H__ #define __NVKM_OBJECT_H__ #include +#include struct nvkm_event; struct nvkm_gpuobj; struct nvkm_uevent; @@ -27,7 +28,7 @@ enum nvkm_object_map { struct nvkm_object_func { void *(*dtor)(struct nvkm_object *); int (*init)(struct nvkm_object *); - int (*fini)(struct nvkm_object *, bool suspend); + int (*fini)(struct nvkm_object *, enum nvkm_suspend_state suspend); int (*mthd)(struct nvkm_object *, u32 mthd, void *data, u32 size); int (*ntfy)(struct nvkm_object *, u32 mthd, struct nvkm_event **); int (*map)(struct nvkm_object *, void *argv, u32 argc, @@ -49,7 +50,7 @@ int nvkm_object_new(const struct nvkm_oclass *, void *data, u32 size, void nvkm_object_del(struct nvkm_object **); void *nvkm_object_dtor(struct nvkm_object *); int nvkm_object_init(struct nvkm_object *); -int nvkm_object_fini(struct nvkm_object *, bool suspend); +int nvkm_object_fini(struct nvkm_object *, enum nvkm_suspend_state); int nvkm_object_mthd(struct nvkm_object *, u32 mthd, void *data, u32 size); int nvkm_object_ntfy(struct nvkm_object *, u32 mthd, struct nvkm_event **); int nvkm_object_map(struct nvkm_object *, void *argv, u32 argc, diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/oproxy.h b/drivers/gpu/drm/nouveau/include/nvkm/core/oproxy.h index 0e70a9afba33d4..cf66aee4d111d2 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/core/oproxy.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/core/oproxy.h @@ -13,7 +13,7 @@ struct nvkm_oproxy { struct nvkm_oproxy_func { void (*dtor[2])(struct nvkm_oproxy *); int (*init[2])(struct nvkm_oproxy *); - int (*fini[2])(struct nvkm_oproxy *, bool suspend); + int (*fini[2])(struct nvkm_oproxy *, enum nvkm_suspend_state suspend); }; void nvkm_oproxy_ctor(const struct nvkm_oproxy_func *, diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h b/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h index bce6e1ba09ea04..bd6b1b658e40f3 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/core/subdev.h @@ -40,7 +40,7 @@ struct nvkm_subdev_func { int (*oneinit)(struct nvkm_subdev *); int (*info)(struct nvkm_subdev *, u64 mthd, u64 *data); int (*init)(struct nvkm_subdev *); - int (*fini)(struct nvkm_subdev *, bool suspend); + int (*fini)(struct nvkm_subdev *, enum nvkm_suspend_state suspend); void (*intr)(struct nvkm_subdev *); }; @@ -65,7 +65,7 @@ void nvkm_subdev_unref(struct nvkm_subdev *); int nvkm_subdev_preinit(struct nvkm_subdev *); int nvkm_subdev_oneinit(struct nvkm_subdev *); int nvkm_subdev_init(struct nvkm_subdev *); -int nvkm_subdev_fini(struct nvkm_subdev *, bool suspend); +int nvkm_subdev_fini(struct nvkm_subdev *, enum nvkm_suspend_state suspend); int nvkm_subdev_info(struct nvkm_subdev *, u64, u64 *); void nvkm_subdev_intr(struct nvkm_subdev *); diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/suspend_state.h b/drivers/gpu/drm/nouveau/include/nvkm/core/suspend_state.h new file mode 100644 index 00000000000000..134120fb71f4eb --- /dev/null +++ b/drivers/gpu/drm/nouveau/include/nvkm/core/suspend_state.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: MIT */ +#ifndef __NVKM_SUSPEND_STATE_H__ +#define __NVKM_SUSPEND_STATE_H__ + +enum nvkm_suspend_state { + NVKM_POWEROFF, + NVKM_SUSPEND, + NVKM_RUNTIME_SUSPEND, +}; + +#endif diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/conn.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/conn.h index d1beaad0c82b62..834ed6587aa528 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/conn.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/conn.h @@ -1,28 +1,81 @@ /* SPDX-License-Identifier: MIT */ #ifndef __NVBIOS_CONN_H__ #define __NVBIOS_CONN_H__ + +/* + * An enumerator representing all of the possible VBIOS connector types defined + * by Nvidia at + * https://nvidia.github.io/open-gpu-doc/DCB/DCB-4.x-Specification.html. + * + * [1] Nvidia's documentation actually claims DCB_CONNECTOR_HDMI_0 is a "3-Pin + * DIN Stereo Connector". This seems very likely to be a documentation typo + * or some sort of funny historical baggage, because we've treated this + * connector type as HDMI for years without issue. + * TODO: Check with Nvidia what's actually happening here. + */ enum dcb_connector_type { - DCB_CONNECTOR_VGA = 0x00, - DCB_CONNECTOR_TV_0 = 0x10, - DCB_CONNECTOR_TV_1 = 0x11, - DCB_CONNECTOR_TV_3 = 0x13, - DCB_CONNECTOR_DVI_I = 0x30, - DCB_CONNECTOR_DVI_D = 0x31, - DCB_CONNECTOR_DMS59_0 = 0x38, - DCB_CONNECTOR_DMS59_1 = 0x39, - DCB_CONNECTOR_LVDS = 0x40, - DCB_CONNECTOR_LVDS_SPWG = 0x41, - DCB_CONNECTOR_DP = 0x46, - DCB_CONNECTOR_eDP = 0x47, - DCB_CONNECTOR_mDP = 0x48, - DCB_CONNECTOR_HDMI_0 = 0x60, - DCB_CONNECTOR_HDMI_1 = 0x61, - DCB_CONNECTOR_HDMI_C = 0x63, - DCB_CONNECTOR_DMS59_DP0 = 0x64, - DCB_CONNECTOR_DMS59_DP1 = 0x65, - DCB_CONNECTOR_WFD = 0x70, - DCB_CONNECTOR_USB_C = 0x71, - DCB_CONNECTOR_NONE = 0xff + /* Analog outputs */ + DCB_CONNECTOR_VGA = 0x00, // VGA 15-pin connector + DCB_CONNECTOR_DVI_A = 0x01, // DVI-A + DCB_CONNECTOR_POD_VGA = 0x02, // Pod - VGA 15-pin connector + DCB_CONNECTOR_TV_0 = 0x10, // TV - Composite Out + DCB_CONNECTOR_TV_1 = 0x11, // TV - S-Video Out + DCB_CONNECTOR_TV_2 = 0x12, // TV - S-Video Breakout - Composite + DCB_CONNECTOR_TV_3 = 0x13, // HDTV Component - YPrPb + DCB_CONNECTOR_TV_SCART = 0x14, // TV - SCART Connector + DCB_CONNECTOR_TV_SCART_D = 0x16, // TV - Composite SCART over D-connector + DCB_CONNECTOR_TV_DTERM = 0x17, // HDTV - D-connector (EIAJ4120) + DCB_CONNECTOR_POD_TV_3 = 0x18, // Pod - HDTV - YPrPb + DCB_CONNECTOR_POD_TV_1 = 0x19, // Pod - S-Video + DCB_CONNECTOR_POD_TV_0 = 0x1a, // Pod - Composite + + /* DVI digital outputs */ + DCB_CONNECTOR_DVI_I_TV_1 = 0x20, // DVI-I-TV-S-Video + DCB_CONNECTOR_DVI_I_TV_0 = 0x21, // DVI-I-TV-Composite + DCB_CONNECTOR_DVI_I_TV_2 = 0x22, // DVI-I-TV-S-Video Breakout-Composite + DCB_CONNECTOR_DVI_I = 0x30, // DVI-I + DCB_CONNECTOR_DVI_D = 0x31, // DVI-D + DCB_CONNECTOR_DVI_ADC = 0x32, // Apple Display Connector (ADC) + DCB_CONNECTOR_DMS59_0 = 0x38, // LFH-DVI-I-1 + DCB_CONNECTOR_DMS59_1 = 0x39, // LFH-DVI-I-2 + DCB_CONNECTOR_BNC = 0x3c, // BNC Connector [for SDI?] + + /* LVDS / TMDS digital outputs */ + DCB_CONNECTOR_LVDS = 0x40, // LVDS-SPWG-Attached [is this name correct?] + DCB_CONNECTOR_LVDS_SPWG = 0x41, // LVDS-OEM-Attached (non-removable) + DCB_CONNECTOR_LVDS_REM = 0x42, // LVDS-SPWG-Detached [following naming above] + DCB_CONNECTOR_LVDS_SPWG_REM = 0x43, // LVDS-OEM-Detached (removable) + DCB_CONNECTOR_TMDS = 0x45, // TMDS-OEM-Attached (non-removable) + + /* DP digital outputs */ + DCB_CONNECTOR_DP = 0x46, // DisplayPort External Connector + DCB_CONNECTOR_eDP = 0x47, // DisplayPort Internal Connector + DCB_CONNECTOR_mDP = 0x48, // DisplayPort (Mini) External Connector + + /* Dock outputs (not used) */ + DCB_CONNECTOR_DOCK_VGA_0 = 0x50, // VGA 15-pin if not docked + DCB_CONNECTOR_DOCK_VGA_1 = 0x51, // VGA 15-pin if docked + DCB_CONNECTOR_DOCK_DVI_I_0 = 0x52, // DVI-I if not docked + DCB_CONNECTOR_DOCK_DVI_I_1 = 0x53, // DVI-I if docked + DCB_CONNECTOR_DOCK_DVI_D_0 = 0x54, // DVI-D if not docked + DCB_CONNECTOR_DOCK_DVI_D_1 = 0x55, // DVI-D if docked + DCB_CONNECTOR_DOCK_DP_0 = 0x56, // DisplayPort if not docked + DCB_CONNECTOR_DOCK_DP_1 = 0x57, // DisplayPort if docked + DCB_CONNECTOR_DOCK_mDP_0 = 0x58, // DisplayPort (Mini) if not docked + DCB_CONNECTOR_DOCK_mDP_1 = 0x59, // DisplayPort (Mini) if docked + + /* HDMI? digital outputs */ + DCB_CONNECTOR_HDMI_0 = 0x60, // HDMI? See [1] in top-level enum comment above + DCB_CONNECTOR_HDMI_1 = 0x61, // HDMI-A connector + DCB_CONNECTOR_SPDIF = 0x62, // Audio S/PDIF connector + DCB_CONNECTOR_HDMI_C = 0x63, // HDMI-C (Mini) connector + + /* Misc. digital outputs */ + DCB_CONNECTOR_DMS59_DP0 = 0x64, // LFH-DP-1 + DCB_CONNECTOR_DMS59_DP1 = 0x65, // LFH-DP-2 + DCB_CONNECTOR_WFD = 0x70, // Virtual connector for Wifi Display (WFD) + DCB_CONNECTOR_USB_C = 0x71, // [DP over USB-C; not present in docs] + DCB_CONNECTOR_NONE = 0xff // Skip Entry }; struct nvbios_connT { diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h index 226c7ec56b8ed9..64fed208e4cf85 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h @@ -44,6 +44,9 @@ typedef void (*nvkm_gsp_event_func)(struct nvkm_gsp_event *, void *repv, u32 rep * NVKM_GSP_RPC_REPLY_NOWAIT - If specified, immediately return to the * caller after the GSP RPC command is issued. * + * NVKM_GSP_RPC_REPLY_NOSEQ - If specified, exactly like NOWAIT + * but don't emit RPC sequence number. + * * NVKM_GSP_RPC_REPLY_RECV - If specified, wait and receive the entire GSP * RPC message after the GSP RPC command is issued. * @@ -53,6 +56,7 @@ typedef void (*nvkm_gsp_event_func)(struct nvkm_gsp_event *, void *repv, u32 rep */ enum nvkm_gsp_rpc_reply_policy { NVKM_GSP_RPC_REPLY_NOWAIT = 0, + NVKM_GSP_RPC_REPLY_NOSEQ, NVKM_GSP_RPC_REPLY_RECV, NVKM_GSP_RPC_REPLY_POLL, }; @@ -73,6 +77,10 @@ struct nvkm_gsp { const struct firmware *bl; const struct firmware *rm; + + struct { + struct nvkm_falcon_fw sb; + } falcon; } fws; struct nvkm_firmware fw; @@ -238,6 +246,8 @@ struct nvkm_gsp { /* The size of the registry RPC */ size_t registry_rpc_size; + u32 rpc_seq; + #ifdef CONFIG_DEBUG_FS /* * Logging buffers in debugfs. The wrapper objects need to remain diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 1527b801f013aa..dc469e571c0aa4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -983,7 +983,7 @@ nouveau_do_suspend(struct nouveau_drm *drm, bool runtime) } NV_DEBUG(drm, "suspending object tree...\n"); - ret = nvif_client_suspend(&drm->_client); + ret = nvif_client_suspend(&drm->_client, runtime); if (ret) goto fail_client; diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 869d4335c0f45c..4a193b7d6d9e40 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -183,11 +183,11 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha fctx->context = drm->runl[chan->runlist].context_base + chan->chid; if (chan == drm->cechan) - strcpy(fctx->name, "copy engine channel"); + strscpy(fctx->name, "copy engine channel"); else if (chan == drm->channel) - strcpy(fctx->name, "generic kernel channel"); + strscpy(fctx->name, "generic kernel channel"); else - strcpy(fctx->name, cli->name); + strscpy(fctx->name, cli->name); kref_init(&fctx->fence_ref); if (!priv->uevent) diff --git a/drivers/gpu/drm/nouveau/nouveau_nvif.c b/drivers/gpu/drm/nouveau/nouveau_nvif.c index adb802421fda58..eeb4ebbc16bf6a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_nvif.c +++ b/drivers/gpu/drm/nouveau/nouveau_nvif.c @@ -62,10 +62,16 @@ nvkm_client_resume(void *priv) } static int -nvkm_client_suspend(void *priv) +nvkm_client_suspend(void *priv, bool runtime) { struct nvkm_client *client = priv; - return nvkm_object_fini(&client->object, true); + enum nvkm_suspend_state state; + + if (runtime) + state = NVKM_RUNTIME_SUSPEND; + else + state = NVKM_SUSPEND; + return nvkm_object_fini(&client->object, state); } static int diff --git a/drivers/gpu/drm/nouveau/nvif/client.c b/drivers/gpu/drm/nouveau/nvif/client.c index fdf5054ed7d83c..36d3c99786bd5c 100644 --- a/drivers/gpu/drm/nouveau/nvif/client.c +++ b/drivers/gpu/drm/nouveau/nvif/client.c @@ -30,9 +30,9 @@ #include int -nvif_client_suspend(struct nvif_client *client) +nvif_client_suspend(struct nvif_client *client, bool runtime) { - return client->driver->suspend(client->object.priv); + return client->driver->suspend(client->object.priv, runtime); } int diff --git a/drivers/gpu/drm/nouveau/nvkm/core/engine.c b/drivers/gpu/drm/nouveau/nvkm/core/engine.c index 36a31e9eea228e..5bf62940d7be1e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/engine.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/engine.c @@ -41,7 +41,7 @@ nvkm_engine_reset(struct nvkm_engine *engine) if (engine->func->reset) return engine->func->reset(engine); - nvkm_subdev_fini(&engine->subdev, false); + nvkm_subdev_fini(&engine->subdev, NVKM_POWEROFF); return nvkm_subdev_init(&engine->subdev); } @@ -98,7 +98,7 @@ nvkm_engine_info(struct nvkm_subdev *subdev, u64 mthd, u64 *data) } static int -nvkm_engine_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_engine_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_engine *engine = nvkm_engine(subdev); if (engine->func->fini) diff --git a/drivers/gpu/drm/nouveau/nvkm/core/ioctl.c b/drivers/gpu/drm/nouveau/nvkm/core/ioctl.c index 45051a1249daca..b8fc9be678515f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/ioctl.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/ioctl.c @@ -141,7 +141,7 @@ nvkm_ioctl_new(struct nvkm_client *client, } ret = -EEXIST; } - nvkm_object_fini(object, false); + nvkm_object_fini(object, NVKM_POWEROFF); } nvkm_object_del(&object); @@ -160,7 +160,7 @@ nvkm_ioctl_del(struct nvkm_client *client, nvif_ioctl(object, "delete size %d\n", size); if (!(ret = nvif_unvers(ret, &data, &size, args->none))) { nvif_ioctl(object, "delete\n"); - nvkm_object_fini(object, false); + nvkm_object_fini(object, NVKM_POWEROFF); nvkm_object_del(&object); } diff --git a/drivers/gpu/drm/nouveau/nvkm/core/object.c b/drivers/gpu/drm/nouveau/nvkm/core/object.c index 390c265cf8af42..af9f00f74c2886 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/object.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/object.c @@ -142,13 +142,25 @@ nvkm_object_bind(struct nvkm_object *object, struct nvkm_gpuobj *gpuobj, } int -nvkm_object_fini(struct nvkm_object *object, bool suspend) +nvkm_object_fini(struct nvkm_object *object, enum nvkm_suspend_state suspend) { - const char *action = suspend ? "suspend" : "fini"; + const char *action; struct nvkm_object *child; s64 time; int ret; + switch (suspend) { + case NVKM_POWEROFF: + default: + action = "fini"; + break; + case NVKM_SUSPEND: + action = "suspend"; + break; + case NVKM_RUNTIME_SUSPEND: + action = "runtime"; + break; + } nvif_debug(object, "%s children...\n", action); time = ktime_to_us(ktime_get()); list_for_each_entry_reverse(child, &object->tree, head) { @@ -212,11 +224,11 @@ nvkm_object_init(struct nvkm_object *object) fail_child: list_for_each_entry_continue_reverse(child, &object->tree, head) - nvkm_object_fini(child, false); + nvkm_object_fini(child, NVKM_POWEROFF); fail: nvif_error(object, "init failed with %d\n", ret); if (object->func->fini) - object->func->fini(object, false); + object->func->fini(object, NVKM_POWEROFF); return ret; } diff --git a/drivers/gpu/drm/nouveau/nvkm/core/oproxy.c b/drivers/gpu/drm/nouveau/nvkm/core/oproxy.c index 5db80d1780f089..7c9edf7527686f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/oproxy.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/oproxy.c @@ -87,7 +87,7 @@ nvkm_oproxy_uevent(struct nvkm_object *object, void *argv, u32 argc, } static int -nvkm_oproxy_fini(struct nvkm_object *object, bool suspend) +nvkm_oproxy_fini(struct nvkm_object *object, enum nvkm_suspend_state suspend) { struct nvkm_oproxy *oproxy = nvkm_oproxy(object); int ret; diff --git a/drivers/gpu/drm/nouveau/nvkm/core/subdev.c b/drivers/gpu/drm/nouveau/nvkm/core/subdev.c index 6c20e827a069a5..b7045d1c841586 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/subdev.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/subdev.c @@ -51,12 +51,24 @@ nvkm_subdev_info(struct nvkm_subdev *subdev, u64 mthd, u64 *data) } int -nvkm_subdev_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_subdev_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_device *device = subdev->device; - const char *action = suspend ? "suspend" : subdev->use.enabled ? "fini" : "reset"; + const char *action; s64 time; + switch (suspend) { + case NVKM_POWEROFF: + default: + action = subdev->use.enabled ? "fini" : "reset"; + break; + case NVKM_SUSPEND: + action = "suspend"; + break; + case NVKM_RUNTIME_SUSPEND: + action = "runtime"; + break; + } nvkm_trace(subdev, "%s running...\n", action); time = ktime_to_us(ktime_get()); @@ -186,7 +198,7 @@ void nvkm_subdev_unref(struct nvkm_subdev *subdev) { if (refcount_dec_and_mutex_lock(&subdev->use.refcount, &subdev->use.mutex)) { - nvkm_subdev_fini(subdev, false); + nvkm_subdev_fini(subdev, NVKM_POWEROFF); mutex_unlock(&subdev->use.mutex); } } diff --git a/drivers/gpu/drm/nouveau/nvkm/core/uevent.c b/drivers/gpu/drm/nouveau/nvkm/core/uevent.c index cc254c390a5719..46beb6e470ee36 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/uevent.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/uevent.c @@ -73,7 +73,7 @@ nvkm_uevent_mthd(struct nvkm_object *object, u32 mthd, void *argv, u32 argc) } static int -nvkm_uevent_fini(struct nvkm_object *object, bool suspend) +nvkm_uevent_fini(struct nvkm_object *object, enum nvkm_suspend_state suspend) { struct nvkm_uevent *uevent = nvkm_uevent(object); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/ce/ga100.c b/drivers/gpu/drm/nouveau/nvkm/engine/ce/ga100.c index 1c0c6013870602..1a3caf69760827 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/ce/ga100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/ce/ga100.c @@ -46,7 +46,7 @@ ga100_ce_nonstall(struct nvkm_engine *engine) } int -ga100_ce_fini(struct nvkm_engine *engine, bool suspend) +ga100_ce_fini(struct nvkm_engine *engine, enum nvkm_suspend_state suspend) { nvkm_inth_block(&engine->subdev.inth); return 0; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/ce/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/ce/priv.h index 34fd2657134b81..f07b4585331043 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/ce/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/ce/priv.h @@ -14,7 +14,7 @@ extern const struct nvkm_object_func gv100_ce_cclass; int ga100_ce_oneinit(struct nvkm_engine *); int ga100_ce_init(struct nvkm_engine *); -int ga100_ce_fini(struct nvkm_engine *, bool); +int ga100_ce_fini(struct nvkm_engine *, enum nvkm_suspend_state); int ga100_ce_nonstall(struct nvkm_engine *); u32 gb202_ce_grce_mask(struct nvkm_device *); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 3375a59ebf1a4a..a965914f1c2fbb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2935,13 +2935,25 @@ nvkm_device_engine(struct nvkm_device *device, int type, int inst) } int -nvkm_device_fini(struct nvkm_device *device, bool suspend) +nvkm_device_fini(struct nvkm_device *device, enum nvkm_suspend_state suspend) { - const char *action = suspend ? "suspend" : "fini"; + const char *action; struct nvkm_subdev *subdev; int ret; s64 time; + switch (suspend) { + case NVKM_POWEROFF: + default: + action = "fini"; + break; + case NVKM_SUSPEND: + action = "suspend"; + break; + case NVKM_RUNTIME_SUSPEND: + action = "runtime"; + break; + } nvdev_trace(device, "%s running...\n", action); time = ktime_to_us(ktime_get()); @@ -3031,7 +3043,7 @@ nvkm_device_init(struct nvkm_device *device) if (ret) return ret; - nvkm_device_fini(device, false); + nvkm_device_fini(device, NVKM_POWEROFF); nvdev_trace(device, "init running...\n"); time = ktime_to_us(ktime_get()); @@ -3059,9 +3071,9 @@ nvkm_device_init(struct nvkm_device *device) fail_subdev: list_for_each_entry_from(subdev, &device->subdev, head) - nvkm_subdev_fini(subdev, false); + nvkm_subdev_fini(subdev, NVKM_POWEROFF); fail: - nvkm_device_fini(device, false); + nvkm_device_fini(device, NVKM_POWEROFF); nvdev_error(device, "init failed with %d\n", ret); return ret; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c index 8f0261a0d618bf..4c29b60460d48d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c @@ -1605,10 +1605,10 @@ nvkm_device_pci_irq(struct nvkm_device *device) } static void -nvkm_device_pci_fini(struct nvkm_device *device, bool suspend) +nvkm_device_pci_fini(struct nvkm_device *device, enum nvkm_suspend_state suspend) { struct nvkm_device_pci *pdev = nvkm_device_pci(device); - if (suspend) { + if (suspend != NVKM_POWEROFF) { pci_disable_device(pdev->pdev); pdev->suspend = true; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h index 75ee7506d4432b..d0c40f0342442d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h @@ -56,5 +56,5 @@ int nvkm_device_ctor(const struct nvkm_device_func *, const char *name, const char *cfg, const char *dbg, struct nvkm_device *); int nvkm_device_init(struct nvkm_device *); -int nvkm_device_fini(struct nvkm_device *, bool suspend); +int nvkm_device_fini(struct nvkm_device *, enum nvkm_suspend_state suspend); #endif diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c index 58191b7a0494ef..32ff3181f47b67 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c @@ -218,7 +218,7 @@ nvkm_udevice_map(struct nvkm_object *object, void *argv, u32 argc, } static int -nvkm_udevice_fini(struct nvkm_object *object, bool suspend) +nvkm_udevice_fini(struct nvkm_object *object, enum nvkm_suspend_state suspend) { struct nvkm_udevice *udev = nvkm_udevice(object); struct nvkm_device *device = udev->device; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c index b24eb1e560bc7c..84745f60912e0b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c @@ -99,13 +99,13 @@ nvkm_disp_intr(struct nvkm_engine *engine) } static int -nvkm_disp_fini(struct nvkm_engine *engine, bool suspend) +nvkm_disp_fini(struct nvkm_engine *engine, enum nvkm_suspend_state suspend) { struct nvkm_disp *disp = nvkm_disp(engine); struct nvkm_outp *outp; if (disp->func->fini) - disp->func->fini(disp, suspend); + disp->func->fini(disp, suspend != NVKM_POWEROFF); list_for_each_entry(outp, &disp->outps, head) { if (outp->func->fini) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/chan.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/chan.c index 9b84e357d3544e..57a62a2de7c7da 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/chan.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/chan.c @@ -128,7 +128,7 @@ nvkm_disp_chan_child_get(struct nvkm_object *object, int index, struct nvkm_ocla } static int -nvkm_disp_chan_fini(struct nvkm_object *object, bool suspend) +nvkm_disp_chan_fini(struct nvkm_object *object, enum nvkm_suspend_state suspend) { struct nvkm_disp_chan *chan = nvkm_disp_chan(object); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uconn.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uconn.c index 2dab6612c4fc84..23d1e5c27bb1e4 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uconn.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uconn.c @@ -191,27 +191,60 @@ nvkm_uconn_new(const struct nvkm_oclass *oclass, void *argv, u32 argc, struct nv spin_lock(&disp->client.lock); if (!conn->object.func) { switch (conn->info.type) { - case DCB_CONNECTOR_VGA : args->v0.type = NVIF_CONN_V0_VGA; break; - case DCB_CONNECTOR_TV_0 : - case DCB_CONNECTOR_TV_1 : - case DCB_CONNECTOR_TV_3 : args->v0.type = NVIF_CONN_V0_TV; break; - case DCB_CONNECTOR_DMS59_0 : - case DCB_CONNECTOR_DMS59_1 : - case DCB_CONNECTOR_DVI_I : args->v0.type = NVIF_CONN_V0_DVI_I; break; - case DCB_CONNECTOR_DVI_D : args->v0.type = NVIF_CONN_V0_DVI_D; break; - case DCB_CONNECTOR_LVDS : args->v0.type = NVIF_CONN_V0_LVDS; break; - case DCB_CONNECTOR_LVDS_SPWG: args->v0.type = NVIF_CONN_V0_LVDS_SPWG; break; - case DCB_CONNECTOR_DMS59_DP0: - case DCB_CONNECTOR_DMS59_DP1: - case DCB_CONNECTOR_DP : - case DCB_CONNECTOR_mDP : - case DCB_CONNECTOR_USB_C : args->v0.type = NVIF_CONN_V0_DP; break; - case DCB_CONNECTOR_eDP : args->v0.type = NVIF_CONN_V0_EDP; break; - case DCB_CONNECTOR_HDMI_0 : - case DCB_CONNECTOR_HDMI_1 : - case DCB_CONNECTOR_HDMI_C : args->v0.type = NVIF_CONN_V0_HDMI; break; + /* VGA */ + case DCB_CONNECTOR_DVI_A : + case DCB_CONNECTOR_POD_VGA : + case DCB_CONNECTOR_VGA : args->v0.type = NVIF_CONN_V0_VGA; break; + + /* TV */ + case DCB_CONNECTOR_TV_0 : + case DCB_CONNECTOR_TV_1 : + case DCB_CONNECTOR_TV_2 : + case DCB_CONNECTOR_TV_SCART : + case DCB_CONNECTOR_TV_SCART_D : + case DCB_CONNECTOR_TV_DTERM : + case DCB_CONNECTOR_POD_TV_3 : + case DCB_CONNECTOR_POD_TV_1 : + case DCB_CONNECTOR_POD_TV_0 : + case DCB_CONNECTOR_TV_3 : args->v0.type = NVIF_CONN_V0_TV; break; + + /* DVI */ + case DCB_CONNECTOR_DVI_I_TV_1 : + case DCB_CONNECTOR_DVI_I_TV_0 : + case DCB_CONNECTOR_DVI_I_TV_2 : + case DCB_CONNECTOR_DVI_ADC : + case DCB_CONNECTOR_DMS59_0 : + case DCB_CONNECTOR_DMS59_1 : + case DCB_CONNECTOR_DVI_I : args->v0.type = NVIF_CONN_V0_DVI_I; break; + case DCB_CONNECTOR_TMDS : + case DCB_CONNECTOR_DVI_D : args->v0.type = NVIF_CONN_V0_DVI_D; break; + + /* LVDS */ + case DCB_CONNECTOR_LVDS : args->v0.type = NVIF_CONN_V0_LVDS; break; + case DCB_CONNECTOR_LVDS_SPWG : args->v0.type = NVIF_CONN_V0_LVDS_SPWG; break; + + /* DP */ + case DCB_CONNECTOR_DMS59_DP0 : + case DCB_CONNECTOR_DMS59_DP1 : + case DCB_CONNECTOR_DP : + case DCB_CONNECTOR_mDP : + case DCB_CONNECTOR_USB_C : args->v0.type = NVIF_CONN_V0_DP; break; + case DCB_CONNECTOR_eDP : args->v0.type = NVIF_CONN_V0_EDP; break; + + /* HDMI */ + case DCB_CONNECTOR_HDMI_0 : + case DCB_CONNECTOR_HDMI_1 : + case DCB_CONNECTOR_HDMI_C : args->v0.type = NVIF_CONN_V0_HDMI; break; + + /* + * Dock & unused outputs. + * BNC, SPDIF, WFD, and detached LVDS go here. + */ default: - WARN_ON(1); + nvkm_warn(&disp->engine.subdev, + "unimplemented connector type 0x%02x\n", + conn->info.type); + args->v0.type = NVIF_CONN_V0_VGA; ret = -EINVAL; break; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/falcon.c b/drivers/gpu/drm/nouveau/nvkm/engine/falcon.c index fd5ee9f0af360c..cf8e356867b4fc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/falcon.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/falcon.c @@ -93,13 +93,13 @@ nvkm_falcon_intr(struct nvkm_engine *engine) } static int -nvkm_falcon_fini(struct nvkm_engine *engine, bool suspend) +nvkm_falcon_fini(struct nvkm_engine *engine, enum nvkm_suspend_state suspend) { struct nvkm_falcon *falcon = nvkm_falcon(engine); struct nvkm_device *device = falcon->engine.subdev.device; const u32 base = falcon->addr; - if (!suspend) { + if (suspend == NVKM_POWEROFF) { nvkm_memory_unref(&falcon->core); if (falcon->external) { vfree(falcon->data.data); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c index 6fd4e60634fbe4..1561287a32f208 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c @@ -122,7 +122,7 @@ nvkm_fifo_class_get(struct nvkm_oclass *oclass, int index, const struct nvkm_dev } static int -nvkm_fifo_fini(struct nvkm_engine *engine, bool suspend) +nvkm_fifo_fini(struct nvkm_engine *engine, enum nvkm_suspend_state suspend) { struct nvkm_fifo *fifo = nvkm_fifo(engine); struct nvkm_runl *runl; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/uchan.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/uchan.c index 52420a1edca52a..c978b97e10c64a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/uchan.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/uchan.c @@ -72,7 +72,7 @@ struct nvkm_uobj { }; static int -nvkm_uchan_object_fini_1(struct nvkm_oproxy *oproxy, bool suspend) +nvkm_uchan_object_fini_1(struct nvkm_oproxy *oproxy, enum nvkm_suspend_state suspend) { struct nvkm_uobj *uobj = container_of(oproxy, typeof(*uobj), oproxy); struct nvkm_chan *chan = uobj->chan; @@ -87,7 +87,7 @@ nvkm_uchan_object_fini_1(struct nvkm_oproxy *oproxy, bool suspend) nvkm_chan_cctx_bind(chan, ectx->engn, NULL); if (refcount_dec_and_test(&ectx->uses)) - nvkm_object_fini(ectx->object, false); + nvkm_object_fini(ectx->object, NVKM_POWEROFF); mutex_unlock(&chan->cgrp->mutex); } @@ -269,7 +269,7 @@ nvkm_uchan_map(struct nvkm_object *object, void *argv, u32 argc, } static int -nvkm_uchan_fini(struct nvkm_object *object, bool suspend) +nvkm_uchan_fini(struct nvkm_object *object, enum nvkm_suspend_state suspend) { struct nvkm_chan *chan = nvkm_uchan(object)->chan; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/base.c index f5e68f09df768d..cd4908b1b4dfff 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/base.c @@ -168,11 +168,11 @@ nvkm_gr_init(struct nvkm_engine *engine) } static int -nvkm_gr_fini(struct nvkm_engine *engine, bool suspend) +nvkm_gr_fini(struct nvkm_engine *engine, enum nvkm_suspend_state suspend) { struct nvkm_gr *gr = nvkm_gr(engine); if (gr->func->fini) - return gr->func->fini(gr, suspend); + return gr->func->fini(gr, suspend != NVKM_POWEROFF); return 0; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c index 3ea447f6a45b51..3608215f0f11c8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c @@ -2330,7 +2330,7 @@ gf100_gr_reset(struct nvkm_gr *base) WARN_ON(gf100_gr_fecs_halt_pipeline(gr)); - subdev->func->fini(subdev, false); + subdev->func->fini(subdev, NVKM_POWEROFF); nvkm_mc_disable(device, subdev->type, subdev->inst); if (gr->func->gpccs.reset) gr->func->gpccs.reset(gr); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv04.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv04.c index ca822f07b63e9e..82937df8b8c0d2 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv04.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv04.c @@ -1158,7 +1158,7 @@ nv04_gr_chan_dtor(struct nvkm_object *object) } static int -nv04_gr_chan_fini(struct nvkm_object *object, bool suspend) +nv04_gr_chan_fini(struct nvkm_object *object, enum nvkm_suspend_state suspend) { struct nv04_gr_chan *chan = nv04_gr_chan(object); struct nv04_gr *gr = chan->gr; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv10.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv10.c index 92ef7c9b29101c..fcb4e4fce83f7a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv10.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv10.c @@ -951,7 +951,7 @@ nv10_gr_context_switch(struct nv10_gr *gr) } static int -nv10_gr_chan_fini(struct nvkm_object *object, bool suspend) +nv10_gr_chan_fini(struct nvkm_object *object, enum nvkm_suspend_state suspend) { struct nv10_gr_chan *chan = nv10_gr_chan(object); struct nv10_gr *gr = chan->gr; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv20.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv20.c index 13407fafe94797..ab57b3b40228e8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv20.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv20.c @@ -27,7 +27,7 @@ nv20_gr_chan_init(struct nvkm_object *object) } int -nv20_gr_chan_fini(struct nvkm_object *object, bool suspend) +nv20_gr_chan_fini(struct nvkm_object *object, enum nvkm_suspend_state suspend) { struct nv20_gr_chan *chan = nv20_gr_chan(object); struct nv20_gr *gr = chan->gr; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv20.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv20.h index c0d2be53413e0d..786c7832f7acdb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv20.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv20.h @@ -31,5 +31,5 @@ struct nv20_gr_chan { void *nv20_gr_chan_dtor(struct nvkm_object *); int nv20_gr_chan_init(struct nvkm_object *); -int nv20_gr_chan_fini(struct nvkm_object *, bool); +int nv20_gr_chan_fini(struct nvkm_object *, enum nvkm_suspend_state); #endif diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c index b609b0150ba140..e3e797cf30349e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c @@ -89,7 +89,7 @@ nv40_gr_chan_bind(struct nvkm_object *object, struct nvkm_gpuobj *parent, } static int -nv40_gr_chan_fini(struct nvkm_object *object, bool suspend) +nv40_gr_chan_fini(struct nvkm_object *object, enum nvkm_suspend_state suspend) { struct nv40_gr_chan *chan = nv40_gr_chan(object); struct nv40_gr *gr = chan->gr; @@ -101,7 +101,7 @@ nv40_gr_chan_fini(struct nvkm_object *object, bool suspend) nvkm_mask(device, 0x400720, 0x00000001, 0x00000000); if (nvkm_rd32(device, 0x40032c) == inst) { - if (suspend) { + if (suspend != NVKM_POWEROFF) { nvkm_wr32(device, 0x400720, 0x00000000); nvkm_wr32(device, 0x400784, inst); nvkm_mask(device, 0x400310, 0x00000020, 0x00000020); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c index 4b1374adbda3a1..38146f9cc81c4e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c @@ -65,7 +65,7 @@ nv44_mpeg_chan_bind(struct nvkm_object *object, struct nvkm_gpuobj *parent, } static int -nv44_mpeg_chan_fini(struct nvkm_object *object, bool suspend) +nv44_mpeg_chan_fini(struct nvkm_object *object, enum nvkm_suspend_state suspend) { struct nv44_mpeg_chan *chan = nv44_mpeg_chan(object); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/base.c index f2c60da5d1e86f..3e4d6a680ee954 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/base.c @@ -37,7 +37,7 @@ nvkm_sec2_finimsg(void *priv, struct nvfw_falcon_msg *hdr) } static int -nvkm_sec2_fini(struct nvkm_engine *engine, bool suspend) +nvkm_sec2_fini(struct nvkm_engine *engine, enum nvkm_suspend_state suspend) { struct nvkm_sec2 *sec2 = nvkm_sec2(engine); struct nvkm_subdev *subdev = &sec2->engine.subdev; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/xtensa.c b/drivers/gpu/drm/nouveau/nvkm/engine/xtensa.c index f7d3ba0afb5564..910a5bb2d191db 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/xtensa.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/xtensa.c @@ -76,7 +76,7 @@ nvkm_xtensa_intr(struct nvkm_engine *engine) } static int -nvkm_xtensa_fini(struct nvkm_engine *engine, bool suspend) +nvkm_xtensa_fini(struct nvkm_engine *engine, enum nvkm_suspend_state suspend) { struct nvkm_xtensa *xtensa = nvkm_xtensa(engine); struct nvkm_device *device = xtensa->engine.subdev.device; @@ -85,7 +85,7 @@ nvkm_xtensa_fini(struct nvkm_engine *engine, bool suspend) nvkm_wr32(device, base + 0xd84, 0); /* INTR_EN */ nvkm_wr32(device, base + 0xd94, 0); /* FIFO_CTRL */ - if (!suspend) + if (suspend == NVKM_POWEROFF) nvkm_memory_unref(&xtensa->gpu_fw); return 0; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c index 9b8ca4e898f903..13d829593180c6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c @@ -182,7 +182,7 @@ nvkm_acr_managed_falcon(struct nvkm_device *device, enum nvkm_acr_lsf_id id) } static int -nvkm_acr_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_acr_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { if (!subdev->use.enabled) return 0; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/base.c index 91bc53be97ffc2..7dee55bf9ada9e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/base.c @@ -90,7 +90,7 @@ nvkm_bar_bar2_init(struct nvkm_device *device) } static int -nvkm_bar_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_bar_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_bar *bar = nvkm_bar(subdev); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c index 178dc56909c274..71420f81714b35 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c @@ -577,7 +577,7 @@ nvkm_clk_read(struct nvkm_clk *clk, enum nv_clk_src src) } static int -nvkm_clk_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_clk_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_clk *clk = nvkm_clk(subdev); flush_work(&clk->work); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/base.c index 3d9319c319c647..ad5ec9ee1294db 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/base.c @@ -67,11 +67,11 @@ nvkm_devinit_post(struct nvkm_devinit *init) } static int -nvkm_devinit_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_devinit_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_devinit *init = nvkm_devinit(subdev); /* force full reinit on resume */ - if (suspend) + if (suspend != NVKM_POWEROFF) init->post = true; return 0; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c index b53ac9a2552fa7..d8d32bb5bcd9e7 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c @@ -51,7 +51,7 @@ nvkm_fault_intr(struct nvkm_subdev *subdev) } static int -nvkm_fault_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_fault_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_fault *fault = nvkm_fault(subdev); if (fault->func->fini) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/user.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/user.c index cd2fbc0472d8e7..8ab052d18e5d36 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/user.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/user.c @@ -56,7 +56,7 @@ nvkm_ufault_map(struct nvkm_object *object, void *argv, u32 argc, } static int -nvkm_ufault_fini(struct nvkm_object *object, bool suspend) +nvkm_ufault_fini(struct nvkm_object *object, enum nvkm_suspend_state suspend) { struct nvkm_fault_buffer *buffer = nvkm_fault_buffer(object); buffer->fault->func->buffer.fini(buffer); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c index 8a286a9349ac62..7ce1b65e2c1c29 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c @@ -279,7 +279,7 @@ nvkm_fb_ctor(const struct nvkm_fb_func *func, struct nvkm_device *device, mutex_init(&fb->tags.mutex); if (func->sysmem.flush_page_init) { - fb->sysmem.flush_page = alloc_page(GFP_KERNEL | __GFP_ZERO); + fb->sysmem.flush_page = alloc_page(GFP_KERNEL | GFP_DMA32 | __GFP_ZERO); if (!fb->sysmem.flush_page) return -ENOMEM; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/base.c index b196baa376dcdb..b2c34878a68f63 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/base.c @@ -144,7 +144,7 @@ nvkm_gpio_intr(struct nvkm_subdev *subdev) } static int -nvkm_gpio_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_gpio_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_gpio *gpio = nvkm_gpio(subdev); u32 mask = (1ULL << gpio->func->lines) - 1; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ad102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ad102.c index 35d1fcef520bf0..c456a96268231a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ad102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ad102.c @@ -30,6 +30,9 @@ ad102_gsp = { .booter.ctor = ga102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c index 7ccb4176106653..30cb843ba35cdd 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c @@ -48,7 +48,7 @@ nvkm_gsp_intr_stall(struct nvkm_gsp *gsp, enum nvkm_subdev_type type, int inst) } static int -nvkm_gsp_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_gsp_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_gsp *gsp = nvkm_gsp(subdev); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c index 5b721bd9d79949..851140e8012200 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c @@ -259,18 +259,16 @@ nvkm_gsp_fwsec_v3(struct nvkm_gsp *gsp, const char *name, } static int -nvkm_gsp_fwsec(struct nvkm_gsp *gsp, const char *name, u32 init_cmd) +nvkm_gsp_fwsec_init(struct nvkm_gsp *gsp, struct nvkm_falcon_fw *fw, const char *name, u32 init_cmd) { struct nvkm_subdev *subdev = &gsp->subdev; struct nvkm_device *device = subdev->device; struct nvkm_bios *bios = device->bios; const union nvfw_falcon_ucode_desc *desc; struct nvbios_pmuE flcn_ucode; - u8 idx, ver, hdr; u32 data; u16 size, vers; - struct nvkm_falcon_fw fw = {}; - u32 mbox0 = 0; + u8 idx, ver, hdr; int ret; /* Lookup in VBIOS. */ @@ -291,8 +289,8 @@ nvkm_gsp_fwsec(struct nvkm_gsp *gsp, const char *name, u32 init_cmd) vers = (desc->v2.Hdr & 0x0000ff00) >> 8; switch (vers) { - case 2: ret = nvkm_gsp_fwsec_v2(gsp, name, &desc->v2, size, init_cmd, &fw); break; - case 3: ret = nvkm_gsp_fwsec_v3(gsp, name, &desc->v3, size, init_cmd, &fw); break; + case 2: ret = nvkm_gsp_fwsec_v2(gsp, name, &desc->v2, size, init_cmd, fw); break; + case 3: ret = nvkm_gsp_fwsec_v3(gsp, name, &desc->v3, size, init_cmd, fw); break; default: nvkm_error(subdev, "%s(v%d): version unknown\n", name, vers); return -EINVAL; @@ -303,15 +301,19 @@ nvkm_gsp_fwsec(struct nvkm_gsp *gsp, const char *name, u32 init_cmd) return ret; } - /* Boot. */ - ret = nvkm_falcon_fw_boot(&fw, subdev, true, &mbox0, NULL, 0, 0); - nvkm_falcon_fw_dtor(&fw); - if (ret) - return ret; - return 0; } +static int +nvkm_gsp_fwsec_boot(struct nvkm_gsp *gsp, struct nvkm_falcon_fw *fw) +{ + struct nvkm_subdev *subdev = &gsp->subdev; + u32 mbox0 = 0; + + /* Boot */ + return nvkm_falcon_fw_boot(fw, subdev, true, &mbox0, NULL, 0, 0); +} + int nvkm_gsp_fwsec_sb(struct nvkm_gsp *gsp) { @@ -320,7 +322,7 @@ nvkm_gsp_fwsec_sb(struct nvkm_gsp *gsp) int ret; u32 err; - ret = nvkm_gsp_fwsec(gsp, "fwsec-sb", NVFW_FALCON_APPIF_DMEMMAPPER_CMD_SB); + ret = nvkm_gsp_fwsec_boot(gsp, &gsp->fws.falcon.sb); if (ret) return ret; @@ -334,27 +336,42 @@ nvkm_gsp_fwsec_sb(struct nvkm_gsp *gsp) return 0; } +int +nvkm_gsp_fwsec_sb_init(struct nvkm_gsp *gsp) +{ + return nvkm_gsp_fwsec_init(gsp, &gsp->fws.falcon.sb, "fwsec-sb", + NVFW_FALCON_APPIF_DMEMMAPPER_CMD_SB); +} + int nvkm_gsp_fwsec_frts(struct nvkm_gsp *gsp) { struct nvkm_subdev *subdev = &gsp->subdev; struct nvkm_device *device = subdev->device; + struct nvkm_falcon_fw fw = {}; int ret; u32 err, wpr2_lo, wpr2_hi; - ret = nvkm_gsp_fwsec(gsp, "fwsec-frts", NVFW_FALCON_APPIF_DMEMMAPPER_CMD_FRTS); + ret = nvkm_gsp_fwsec_init(gsp, &fw, "fwsec-frts", NVFW_FALCON_APPIF_DMEMMAPPER_CMD_FRTS); if (ret) return ret; + ret = nvkm_gsp_fwsec_boot(gsp, &fw); + if (ret) + goto fwsec_dtor; + /* Verify. */ err = nvkm_rd32(device, 0x001400 + (0xe * 4)) >> 16; if (err) { nvkm_error(subdev, "fwsec-frts: 0x%04x\n", err); - return -EIO; + ret = -EIO; + } else { + wpr2_lo = nvkm_rd32(device, 0x1fa824); + wpr2_hi = nvkm_rd32(device, 0x1fa828); + nvkm_debug(subdev, "fwsec-frts: WPR2 @ %08x - %08x\n", wpr2_lo, wpr2_hi); } - wpr2_lo = nvkm_rd32(device, 0x1fa824); - wpr2_hi = nvkm_rd32(device, 0x1fa828); - nvkm_debug(subdev, "fwsec-frts: WPR2 @ %08x - %08x\n", wpr2_lo, wpr2_hi); - return 0; +fwsec_dtor: + nvkm_falcon_fw_dtor(&fw); + return ret; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c index d201e8697226be..27a13aeccd3cb3 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c @@ -47,6 +47,9 @@ ga100_gsp = { .booter.ctor = tu102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga102.c index 917f7e2f6c466a..b6b3eb6f4c006e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga102.c @@ -158,6 +158,9 @@ ga102_gsp_r535 = { .booter.ctor = ga102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/gh100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/gh100.c index b0dd5fce7bad36..88436a26417799 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/gh100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/gh100.c @@ -17,7 +17,7 @@ #include int -gh100_gsp_fini(struct nvkm_gsp *gsp, bool suspend) +gh100_gsp_fini(struct nvkm_gsp *gsp, enum nvkm_suspend_state suspend) { struct nvkm_falcon *falcon = &gsp->falcon; int ret, time = 4000; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h index c3494b7ac572bc..71b7203bef5073 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h @@ -6,7 +6,9 @@ enum nvkm_acr_lsf_id; int nvkm_gsp_fwsec_frts(struct nvkm_gsp *); + int nvkm_gsp_fwsec_sb(struct nvkm_gsp *); +int nvkm_gsp_fwsec_sb_init(struct nvkm_gsp *gsp); struct nvkm_gsp_fwif { int version; @@ -49,10 +51,15 @@ struct nvkm_gsp_func { struct nvkm_falcon *, struct nvkm_falcon_fw *); } booter; + struct { + int (*ctor)(struct nvkm_gsp *); + void (*dtor)(struct nvkm_gsp *); + } fwsec_sb; + void (*dtor)(struct nvkm_gsp *); int (*oneinit)(struct nvkm_gsp *); int (*init)(struct nvkm_gsp *); - int (*fini)(struct nvkm_gsp *, bool suspend); + int (*fini)(struct nvkm_gsp *, enum nvkm_suspend_state suspend); int (*reset)(struct nvkm_gsp *); struct { @@ -64,9 +71,11 @@ extern const struct nvkm_falcon_func tu102_gsp_flcn; extern const struct nvkm_falcon_fw_func tu102_gsp_fwsec; int tu102_gsp_booter_ctor(struct nvkm_gsp *, const char *, const struct firmware *, struct nvkm_falcon *, struct nvkm_falcon_fw *); +int tu102_gsp_fwsec_sb_ctor(struct nvkm_gsp *); +void tu102_gsp_fwsec_sb_dtor(struct nvkm_gsp *); int tu102_gsp_oneinit(struct nvkm_gsp *); int tu102_gsp_init(struct nvkm_gsp *); -int tu102_gsp_fini(struct nvkm_gsp *, bool suspend); +int tu102_gsp_fini(struct nvkm_gsp *, enum nvkm_suspend_state suspend); int tu102_gsp_reset(struct nvkm_gsp *); u64 tu102_gsp_wpr_heap_size(struct nvkm_gsp *); @@ -78,15 +87,28 @@ int ga102_gsp_reset(struct nvkm_gsp *); int gh100_gsp_oneinit(struct nvkm_gsp *); int gh100_gsp_init(struct nvkm_gsp *); -int gh100_gsp_fini(struct nvkm_gsp *, bool suspend); +int gh100_gsp_fini(struct nvkm_gsp *, enum nvkm_suspend_state suspend); void r535_gsp_dtor(struct nvkm_gsp *); int r535_gsp_oneinit(struct nvkm_gsp *); int r535_gsp_init(struct nvkm_gsp *); -int r535_gsp_fini(struct nvkm_gsp *, bool suspend); +int r535_gsp_fini(struct nvkm_gsp *, enum nvkm_suspend_state suspend); int nvkm_gsp_new_(const struct nvkm_gsp_fwif *, struct nvkm_device *, enum nvkm_subdev_type, int, struct nvkm_gsp **); +static inline int nvkm_gsp_fwsec_sb_ctor(struct nvkm_gsp *gsp) +{ + if (gsp->func->fwsec_sb.ctor) + return gsp->func->fwsec_sb.ctor(gsp); + return 0; +} + +static inline void nvkm_gsp_fwsec_sb_dtor(struct nvkm_gsp *gsp) +{ + if (gsp->func->fwsec_sb.dtor) + gsp->func->fwsec_sb.dtor(gsp); +} + extern const struct nvkm_gsp_func gv100_gsp; #endif diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fbsr.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fbsr.c index 150e22fde2ac20..e962d0e8f83777 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fbsr.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fbsr.c @@ -208,7 +208,7 @@ r535_fbsr_resume(struct nvkm_gsp *gsp) } static int -r535_fbsr_suspend(struct nvkm_gsp *gsp) +r535_fbsr_suspend(struct nvkm_gsp *gsp, bool runtime) { struct nvkm_subdev *subdev = &gsp->subdev; struct nvkm_device *device = subdev->device; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c index 32e6a065d6d7a5..7fb13434c051de 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c @@ -704,7 +704,7 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp) build_registry(gsp, rpc); - return nvkm_gsp_rpc_wr(gsp, rpc, NVKM_GSP_RPC_REPLY_NOWAIT); + return nvkm_gsp_rpc_wr(gsp, rpc, NVKM_GSP_RPC_REPLY_NOSEQ); fail: clean_registry(gsp); @@ -921,7 +921,7 @@ r535_gsp_set_system_info(struct nvkm_gsp *gsp) info->pciConfigMirrorSize = device->pci->func->cfg.size; r535_gsp_acpi_info(gsp, &info->acpiMethodData); - return nvkm_gsp_rpc_wr(gsp, info, NVKM_GSP_RPC_REPLY_NOWAIT); + return nvkm_gsp_rpc_wr(gsp, info, NVKM_GSP_RPC_REPLY_NOSEQ); } static int @@ -1721,7 +1721,7 @@ r535_gsp_sr_data_size(struct nvkm_gsp *gsp) } int -r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend) +r535_gsp_fini(struct nvkm_gsp *gsp, enum nvkm_suspend_state suspend) { struct nvkm_rm *rm = gsp->rm; int ret; @@ -1748,7 +1748,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend) sr->sysmemAddrOfSuspendResumeData = gsp->sr.radix3.lvl0.addr; sr->sizeOfSuspendResumeData = len; - ret = rm->api->fbsr->suspend(gsp); + ret = rm->api->fbsr->suspend(gsp, suspend == NVKM_RUNTIME_SUSPEND); if (ret) { nvkm_gsp_mem_dtor(&gsp->sr.meta); nvkm_gsp_radix3_dtor(gsp, &gsp->sr.radix3); @@ -1817,12 +1817,16 @@ r535_gsp_rm_boot_ctor(struct nvkm_gsp *gsp) RM_RISCV_UCODE_DESC *desc; int ret; + ret = nvkm_gsp_fwsec_sb_ctor(gsp); + if (ret) + return ret; + hdr = nvfw_bin_hdr(&gsp->subdev, fw->data); desc = (void *)fw->data + hdr->header_offset; ret = nvkm_gsp_mem_ctor(gsp, hdr->data_size, &gsp->boot.fw); if (ret) - return ret; + goto dtor_fwsec; memcpy(gsp->boot.fw.data, fw->data + hdr->data_offset, hdr->data_size); @@ -1831,6 +1835,9 @@ r535_gsp_rm_boot_ctor(struct nvkm_gsp *gsp) gsp->boot.manifest_offset = desc->manifestOffset; gsp->boot.app_version = desc->appVersion; return 0; +dtor_fwsec: + nvkm_gsp_fwsec_sb_dtor(gsp); + return ret; } static const struct nvkm_firmware_func @@ -2101,6 +2108,7 @@ r535_gsp_dtor(struct nvkm_gsp *gsp) mutex_destroy(&gsp->cmdq.mutex); nvkm_gsp_dtor_fws(gsp); + nvkm_gsp_fwsec_sb_dtor(gsp); nvkm_gsp_mem_dtor(&gsp->rmargs); nvkm_gsp_mem_dtor(&gsp->wpr_meta); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c index 0dc4782df8c0c1..3ca3de8f434082 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c @@ -557,6 +557,7 @@ r535_gsp_rpc_handle_reply(struct nvkm_gsp *gsp, u32 fn, switch (policy) { case NVKM_GSP_RPC_REPLY_NOWAIT: + case NVKM_GSP_RPC_REPLY_NOSEQ: break; case NVKM_GSP_RPC_REPLY_RECV: reply = r535_gsp_msg_recv(gsp, fn, gsp_rpc_len); @@ -588,6 +589,11 @@ r535_gsp_rpc_send(struct nvkm_gsp *gsp, void *payload, rpc->data, rpc->length - sizeof(*rpc), true); } + if (policy == NVKM_GSP_RPC_REPLY_NOSEQ) + rpc->sequence = 0; + else + rpc->sequence = gsp->rpc_seq++; + ret = r535_gsp_cmdq_push(gsp, rpc); if (ret) return ERR_PTR(ret); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/fbsr.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/fbsr.c index 2945d5b4e57070..8ef8b4f6558830 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/fbsr.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/fbsr.c @@ -62,7 +62,7 @@ r570_fbsr_resume(struct nvkm_gsp *gsp) } static int -r570_fbsr_init(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size) +r570_fbsr_init(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size, bool runtime) { NV2080_CTRL_INTERNAL_FBSR_INIT_PARAMS *ctrl; struct nvkm_gsp_object memlist; @@ -81,7 +81,7 @@ r570_fbsr_init(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size) ctrl->hClient = gsp->internal.client.object.handle; ctrl->hSysMem = memlist.handle; ctrl->sysmemAddrOfSuspendResumeData = gsp->sr.meta.addr; - ctrl->bEnteringGcoffState = 1; + ctrl->bEnteringGcoffState = runtime ? 1 : 0; ret = nvkm_gsp_rm_ctrl_wr(&gsp->internal.device.subdevice, ctrl); if (ret) @@ -92,7 +92,7 @@ r570_fbsr_init(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size) } static int -r570_fbsr_suspend(struct nvkm_gsp *gsp) +r570_fbsr_suspend(struct nvkm_gsp *gsp, bool runtime) { struct nvkm_subdev *subdev = &gsp->subdev; struct nvkm_device *device = subdev->device; @@ -133,7 +133,7 @@ r570_fbsr_suspend(struct nvkm_gsp *gsp) return ret; /* Initialise FBSR on RM. */ - ret = r570_fbsr_init(gsp, &gsp->sr.fbsr, size); + ret = r570_fbsr_init(gsp, &gsp->sr.fbsr, size, runtime); if (ret) { nvkm_gsp_sg_free(device, &gsp->sr.fbsr); return ret; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c index 9d2fa4e66d5982..996941c668ba9e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r570/gsp.c @@ -176,7 +176,7 @@ r570_gsp_set_system_info(struct nvkm_gsp *gsp) info->bIsPrimary = video_is_primary_device(device->dev); info->bPreserveVideoMemoryAllocations = false; - return nvkm_gsp_rpc_wr(gsp, info, NVKM_GSP_RPC_REPLY_NOWAIT); + return nvkm_gsp_rpc_wr(gsp, info, NVKM_GSP_RPC_REPLY_NOSEQ); } static void diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h index 393ea775941fae..4f0ae6cc085c3d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/rm.h @@ -78,7 +78,7 @@ struct nvkm_rm_api { } *device; const struct nvkm_rm_api_fbsr { - int (*suspend)(struct nvkm_gsp *); + int (*suspend)(struct nvkm_gsp *, bool runtime); void (*resume)(struct nvkm_gsp *); } *fbsr; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c index 81e56da0474a1d..19cb269e7a2659 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c @@ -30,6 +30,18 @@ #include #include +int +tu102_gsp_fwsec_sb_ctor(struct nvkm_gsp *gsp) +{ + return nvkm_gsp_fwsec_sb_init(gsp); +} + +void +tu102_gsp_fwsec_sb_dtor(struct nvkm_gsp *gsp) +{ + nvkm_falcon_fw_dtor(&gsp->fws.falcon.sb); +} + static int tu102_gsp_booter_unload(struct nvkm_gsp *gsp, u32 mbox0, u32 mbox1) { @@ -149,7 +161,7 @@ tu102_gsp_reset(struct nvkm_gsp *gsp) } int -tu102_gsp_fini(struct nvkm_gsp *gsp, bool suspend) +tu102_gsp_fini(struct nvkm_gsp *gsp, enum nvkm_suspend_state suspend) { u32 mbox0 = 0xff, mbox1 = 0xff; int ret; @@ -370,6 +382,9 @@ tu102_gsp = { .booter.ctor = tu102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu116.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu116.c index 97eb046c25d07d..58cf2584242182 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu116.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu116.c @@ -30,6 +30,9 @@ tu116_gsp = { .booter.ctor = tu102_gsp_booter_ctor, + .fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor, + .fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor, + .dtor = r535_gsp_dtor, .oneinit = tu102_gsp_oneinit, .init = tu102_gsp_init, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/base.c index 7ec17e8435a136..454bb21815a272 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/base.c @@ -135,7 +135,7 @@ nvkm_i2c_intr(struct nvkm_subdev *subdev) } static int -nvkm_i2c_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_i2c_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_i2c *i2c = nvkm_i2c(subdev); struct nvkm_i2c_pad *pad; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c index 2f55bab8e132ff..6b9ed61684a027 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c @@ -176,7 +176,7 @@ nvkm_instmem_boot(struct nvkm_instmem *imem) } static int -nvkm_instmem_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_instmem_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_instmem *imem = nvkm_instmem(subdev); int ret; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c index 6867934256a768..0f3e0d324a529c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c @@ -74,7 +74,7 @@ nvkm_pci_rom_shadow(struct nvkm_pci *pci, bool shadow) } static int -nvkm_pci_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_pci_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_pci *pci = nvkm_pci(subdev); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/base.c index 8f2f50ad4ded1f..9e9004ec4588b8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/base.c @@ -77,7 +77,7 @@ nvkm_pmu_intr(struct nvkm_subdev *subdev) } static int -nvkm_pmu_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_pmu_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_pmu *pmu = nvkm_pmu(subdev); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c index fc5ee118e91067..1510aba339560b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c @@ -341,15 +341,15 @@ nvkm_therm_intr(struct nvkm_subdev *subdev) } static int -nvkm_therm_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_therm_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_therm *therm = nvkm_therm(subdev); if (therm->func->fini) therm->func->fini(therm); - nvkm_therm_fan_fini(therm, suspend); - nvkm_therm_sensor_fini(therm, suspend); + nvkm_therm_fan_fini(therm, suspend != NVKM_POWEROFF); + nvkm_therm_sensor_fini(therm, suspend != NVKM_POWEROFF); if (suspend) { therm->suspend = therm->mode; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c index 8b0da0c062685d..a5c3c282b5d077 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c @@ -149,7 +149,7 @@ nvkm_timer_intr(struct nvkm_subdev *subdev) } static int -nvkm_timer_fini(struct nvkm_subdev *subdev, bool suspend) +nvkm_timer_fini(struct nvkm_subdev *subdev, enum nvkm_suspend_state suspend) { struct nvkm_timer *tmr = nvkm_timer(subdev); tmr->func->alarm_fini(tmr); diff --git a/drivers/gpu/drm/nova/Kconfig b/drivers/gpu/drm/nova/Kconfig index cca6a3fea879b8..3e637ad7b5bad9 100644 --- a/drivers/gpu/drm/nova/Kconfig +++ b/drivers/gpu/drm/nova/Kconfig @@ -1,9 +1,11 @@ config DRM_NOVA tristate "Nova DRM driver" + depends on 64BIT depends on DRM=y depends on PCI depends on RUST select AUXILIARY_BUS + select NOVA_CORE default n help Choose this if you want to build the Nova DRM driver for Nvidia diff --git a/drivers/gpu/drm/nova/driver.rs b/drivers/gpu/drm/nova/driver.rs index 91b7380f83ab4a..2fd6863ae683db 100644 --- a/drivers/gpu/drm/nova/driver.rs +++ b/drivers/gpu/drm/nova/driver.rs @@ -63,6 +63,8 @@ impl drm::Driver for NovaDriver { const INFO: drm::DriverInfo = INFO; + const FEATURES: u32 = drm::driver::FEAT_GEM; + kernel::declare_drm_ioctls! { (NOVA_GETPARAM, drm_nova_getparam, ioctl::RENDER_ALLOW, File::get_param), (NOVA_GEM_CREATE, drm_nova_gem_create, ioctl::AUTH | ioctl::RENDER_ALLOW, File::gem_create), diff --git a/drivers/gpu/drm/nova/file.rs b/drivers/gpu/drm/nova/file.rs index 90b9d2d0ec4ae0..acc63e6bc63389 100644 --- a/drivers/gpu/drm/nova/file.rs +++ b/drivers/gpu/drm/nova/file.rs @@ -4,6 +4,7 @@ use crate::driver::{NovaDevice, NovaDriver}; use crate::gem::NovaObject; use kernel::{ alloc::flags::*, + bindings, drm::{self, gem::BaseObject}, pci, prelude::*, @@ -18,6 +19,8 @@ impl drm::file::DriverFile for File { fn open(_dev: &NovaDevice) -> Result>> { Ok(KBox::new(Self, GFP_KERNEL)?.into()) } + + fn as_raw(&self) -> *mut bindings::drm_file { todo!() } } impl File { diff --git a/drivers/gpu/drm/nova/gem.rs b/drivers/gpu/drm/nova/gem.rs index 2760ba4f3450be..680f91919e8421 100644 --- a/drivers/gpu/drm/nova/gem.rs +++ b/drivers/gpu/drm/nova/gem.rs @@ -16,10 +16,12 @@ use crate::{ #[pin_data] pub(crate) struct NovaObject {} +#[vtable] impl gem::DriverObject for NovaObject { type Driver = NovaDriver; + type Args = (); - fn new(_dev: &NovaDevice, _size: usize) -> impl PinInit { + fn new(_dev: &NovaDevice, _size: usize, _args: Self::Args) -> impl PinInit { try_pin_init!(NovaObject {}) } } @@ -33,7 +35,7 @@ impl NovaObject { return Err(EINVAL); } - gem::Object::new(dev, aligned_size) + gem::Object::new(dev, aligned_size, ()) } /// Look up a GEM object handle for a `File` and return an `ObjectRef` for it. diff --git a/drivers/gpu/drm/panel/panel-lg-sw43408.c b/drivers/gpu/drm/panel/panel-lg-sw43408.c index 46a56ea92ad9ff..6e307fba658f78 100644 --- a/drivers/gpu/drm/panel/panel-lg-sw43408.c +++ b/drivers/gpu/drm/panel/panel-lg-sw43408.c @@ -294,10 +294,6 @@ static void sw43408_remove(struct mipi_dsi_device *dsi) struct sw43408_panel *ctx = mipi_dsi_get_drvdata(dsi); int ret; - ret = sw43408_unprepare(&ctx->base); - if (ret < 0) - dev_err(&dsi->dev, "failed to unprepare panel: %d\n", ret); - ret = mipi_dsi_detach(dsi); if (ret < 0) dev_err(&dsi->dev, "failed to detach from DSI host: %d\n", ret); diff --git a/drivers/gpu/drm/panel/panel-novatek-nt35560.c b/drivers/gpu/drm/panel/panel-novatek-nt35560.c index 561e6643dcbb67..6e5173f98a2264 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt35560.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt35560.c @@ -213,7 +213,7 @@ static const struct backlight_properties nt35560_bl_props = { static void nt35560_read_id(struct mipi_dsi_multi_context *dsi_ctx) { - struct device dev = dsi_ctx->dsi->dev; + struct device *dev = &dsi_ctx->dsi->dev; u8 vendor, version, panel; u16 val; @@ -225,7 +225,7 @@ static void nt35560_read_id(struct mipi_dsi_multi_context *dsi_ctx) return; if (vendor == 0x00) { - dev_err(&dev, "device vendor ID is zero\n"); + dev_err(dev, "device vendor ID is zero\n"); dsi_ctx->accum_err = -ENODEV; return; } @@ -236,12 +236,12 @@ static void nt35560_read_id(struct mipi_dsi_multi_context *dsi_ctx) case DISPLAY_SONY_ACX424AKP_ID2: case DISPLAY_SONY_ACX424AKP_ID3: case DISPLAY_SONY_ACX424AKP_ID4: - dev_info(&dev, + dev_info(dev, "MTP vendor: %02x, version: %02x, panel: %02x\n", vendor, version, panel); break; default: - dev_info(&dev, + dev_info(dev, "unknown vendor: %02x, version: %02x, panel: %02x\n", vendor, version, panel); break; diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 0019de93be1b66..271f9339919376 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -623,49 +623,6 @@ static struct panel_simple *panel_simple_probe(struct device *dev) if (IS_ERR(desc)) return ERR_CAST(desc); - panel = devm_drm_panel_alloc(dev, struct panel_simple, base, - &panel_simple_funcs, desc->connector_type); - if (IS_ERR(panel)) - return ERR_CAST(panel); - - panel->desc = desc; - - panel->supply = devm_regulator_get(dev, "power"); - if (IS_ERR(panel->supply)) - return ERR_CAST(panel->supply); - - panel->enable_gpio = devm_gpiod_get_optional(dev, "enable", - GPIOD_OUT_LOW); - if (IS_ERR(panel->enable_gpio)) - return dev_err_cast_probe(dev, panel->enable_gpio, - "failed to request GPIO\n"); - - err = of_drm_get_panel_orientation(dev->of_node, &panel->orientation); - if (err) { - dev_err(dev, "%pOF: failed to get orientation %d\n", dev->of_node, err); - return ERR_PTR(err); - } - - ddc = of_parse_phandle(dev->of_node, "ddc-i2c-bus", 0); - if (ddc) { - panel->ddc = of_find_i2c_adapter_by_node(ddc); - of_node_put(ddc); - - if (!panel->ddc) - return ERR_PTR(-EPROBE_DEFER); - } - - if (!of_device_is_compatible(dev->of_node, "panel-dpi") && - !of_get_display_timing(dev->of_node, "panel-timing", &dt)) - panel_simple_parse_panel_timing_node(dev, panel, &dt); - - if (desc->connector_type == DRM_MODE_CONNECTOR_LVDS) { - /* Optional data-mapping property for overriding bus format */ - err = panel_simple_override_nondefault_lvds_datamapping(dev, panel); - if (err) - goto free_ddc; - } - connector_type = desc->connector_type; /* Catch common mistakes for panels. */ switch (connector_type) { @@ -690,8 +647,7 @@ static struct panel_simple *panel_simple_probe(struct device *dev) break; case DRM_MODE_CONNECTOR_eDP: dev_warn(dev, "eDP panels moved to panel-edp\n"); - err = -EINVAL; - goto free_ddc; + return ERR_PTR(-EINVAL); case DRM_MODE_CONNECTOR_DSI: if (desc->bpc != 6 && desc->bpc != 8) dev_warn(dev, "Expected bpc in {6,8} but got: %u\n", desc->bpc); @@ -720,6 +676,49 @@ static struct panel_simple *panel_simple_probe(struct device *dev) break; } + panel = devm_drm_panel_alloc(dev, struct panel_simple, base, + &panel_simple_funcs, connector_type); + if (IS_ERR(panel)) + return ERR_CAST(panel); + + panel->desc = desc; + + panel->supply = devm_regulator_get(dev, "power"); + if (IS_ERR(panel->supply)) + return ERR_CAST(panel->supply); + + panel->enable_gpio = devm_gpiod_get_optional(dev, "enable", + GPIOD_OUT_LOW); + if (IS_ERR(panel->enable_gpio)) + return dev_err_cast_probe(dev, panel->enable_gpio, + "failed to request GPIO\n"); + + err = of_drm_get_panel_orientation(dev->of_node, &panel->orientation); + if (err) { + dev_err(dev, "%pOF: failed to get orientation %d\n", dev->of_node, err); + return ERR_PTR(err); + } + + ddc = of_parse_phandle(dev->of_node, "ddc-i2c-bus", 0); + if (ddc) { + panel->ddc = of_find_i2c_adapter_by_node(ddc); + of_node_put(ddc); + + if (!panel->ddc) + return ERR_PTR(-EPROBE_DEFER); + } + + if (!of_device_is_compatible(dev->of_node, "panel-dpi") && + !of_get_display_timing(dev->of_node, "panel-timing", &dt)) + panel_simple_parse_panel_timing_node(dev, panel, &dt); + + if (desc->connector_type == DRM_MODE_CONNECTOR_LVDS) { + /* Optional data-mapping property for overriding bus format */ + err = panel_simple_override_nondefault_lvds_datamapping(dev, panel); + if (err) + goto free_ddc; + } + dev_set_drvdata(dev, panel); /* @@ -1900,6 +1899,7 @@ static const struct panel_desc dataimage_scf0700c48ggu18 = { }, .bus_format = MEDIA_BUS_FMT_RGB888_1X24, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, }; static const struct display_timing dlc_dlc0700yzg_1_timing = { diff --git a/drivers/gpu/drm/panel/panel-sony-td4353-jdi.c b/drivers/gpu/drm/panel/panel-sony-td4353-jdi.c index 7c989b70ab5130..a14c86c60d19d7 100644 --- a/drivers/gpu/drm/panel/panel-sony-td4353-jdi.c +++ b/drivers/gpu/drm/panel/panel-sony-td4353-jdi.c @@ -212,6 +212,8 @@ static int sony_td4353_jdi_probe(struct mipi_dsi_device *dsi) if (ret) return dev_err_probe(dev, ret, "Failed to get backlight\n"); + ctx->panel.prepare_prev_first = true; + drm_panel_add(&ctx->panel); ret = mipi_dsi_attach(dsi); diff --git a/drivers/gpu/drm/panel/panel-visionox-rm69299.c b/drivers/gpu/drm/panel/panel-visionox-rm69299.c index 909c280eab1fb4..66c30db3b73a71 100644 --- a/drivers/gpu/drm/panel/panel-visionox-rm69299.c +++ b/drivers/gpu/drm/panel/panel-visionox-rm69299.c @@ -192,7 +192,7 @@ static int visionox_rm69299_unprepare(struct drm_panel *panel) struct visionox_rm69299 *ctx = panel_to_ctx(panel); struct mipi_dsi_multi_context dsi_ctx = { .dsi = ctx->dsi }; - ctx->dsi->mode_flags = 0; + ctx->dsi->mode_flags &= ~MIPI_DSI_MODE_LPM; mipi_dsi_dcs_set_display_off_multi(&dsi_ctx); @@ -247,7 +247,7 @@ static const struct drm_display_mode visionox_rm69299_1080x2248_60hz = { }; static const struct drm_display_mode visionox_rm69299_1080x2160_60hz = { - .clock = 158695, + .clock = (2160 + 8 + 4 + 4) * (1080 + 26 + 2 + 36) * 60 / 1000, .hdisplay = 1080, .hsync_start = 1080 + 26, .hsync_end = 1080 + 26 + 2, diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c index 81df49880bd87c..962a10e00848ef 100644 --- a/drivers/gpu/drm/panthor/panthor_device.c +++ b/drivers/gpu/drm/panthor/panthor_device.c @@ -83,6 +83,8 @@ void panthor_device_unplug(struct panthor_device *ptdev) return; } + drm_WARN_ON(&ptdev->base, pm_runtime_get_sync(ptdev->base.dev) < 0); + /* Call drm_dev_unplug() so any access to HW blocks happening after * that point get rejected. */ @@ -93,8 +95,6 @@ void panthor_device_unplug(struct panthor_device *ptdev) */ mutex_unlock(&ptdev->unplug.lock); - drm_WARN_ON(&ptdev->base, pm_runtime_get_sync(ptdev->base.dev) < 0); - /* Now, try to cleanly shutdown the GPU before the device resources * get reclaimed. */ diff --git a/drivers/gpu/drm/panthor/panthor_gem.c b/drivers/gpu/drm/panthor/panthor_gem.c index 3f43686f019588..43471babff86cb 100644 --- a/drivers/gpu/drm/panthor/panthor_gem.c +++ b/drivers/gpu/drm/panthor/panthor_gem.c @@ -86,7 +86,6 @@ static void panthor_gem_free_object(struct drm_gem_object *obj) void panthor_kernel_bo_destroy(struct panthor_kernel_bo *bo) { struct panthor_vm *vm; - int ret; if (IS_ERR_OR_NULL(bo)) return; @@ -94,18 +93,11 @@ void panthor_kernel_bo_destroy(struct panthor_kernel_bo *bo) vm = bo->vm; panthor_kernel_bo_vunmap(bo); - if (drm_WARN_ON(bo->obj->dev, - to_panthor_bo(bo->obj)->exclusive_vm_root_gem != panthor_vm_root_gem(vm))) - goto out_free_bo; - - ret = panthor_vm_unmap_range(vm, bo->va_node.start, bo->va_node.size); - if (ret) - goto out_free_bo; - + drm_WARN_ON(bo->obj->dev, + to_panthor_bo(bo->obj)->exclusive_vm_root_gem != panthor_vm_root_gem(vm)); + panthor_vm_unmap_range(vm, bo->va_node.start, bo->va_node.size); panthor_vm_free_va(vm, &bo->va_node); drm_gem_object_put(bo->obj); - -out_free_bo: panthor_vm_put(vm); kfree(bo); } @@ -152,6 +144,9 @@ panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm, bo = to_panthor_bo(&obj->base); kbo->obj = &obj->base; bo->flags = bo_flags; + bo->exclusive_vm_root_gem = panthor_vm_root_gem(vm); + drm_gem_object_get(bo->exclusive_vm_root_gem); + bo->base.base.resv = bo->exclusive_vm_root_gem->resv; if (vm == panthor_fw_vm(ptdev)) debug_flags |= PANTHOR_DEBUGFS_GEM_USAGE_FLAG_FW_MAPPED; @@ -175,9 +170,6 @@ panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm, goto err_free_va; kbo->vm = panthor_vm_get(vm); - bo->exclusive_vm_root_gem = panthor_vm_root_gem(vm); - drm_gem_object_get(bo->exclusive_vm_root_gem); - bo->base.base.resv = bo->exclusive_vm_root_gem->resv; return kbo; err_free_va: diff --git a/drivers/gpu/drm/panthor/panthor_gpu.c b/drivers/gpu/drm/panthor/panthor_gpu.c index db69449a5be099..77d0f4ced12064 100644 --- a/drivers/gpu/drm/panthor/panthor_gpu.c +++ b/drivers/gpu/drm/panthor/panthor_gpu.c @@ -49,7 +49,7 @@ struct panthor_gpu { static void panthor_gpu_coherency_set(struct panthor_device *ptdev) { gpu_write(ptdev, GPU_COHERENCY_PROTOCOL, - ptdev->coherent ? GPU_COHERENCY_PROT_BIT(ACE_LITE) : GPU_COHERENCY_NONE); + ptdev->coherent ? GPU_COHERENCY_ACE_LITE : GPU_COHERENCY_NONE); } static void panthor_gpu_irq_handler(struct panthor_device *ptdev, u32 status) @@ -259,38 +259,42 @@ int panthor_gpu_l2_power_on(struct panthor_device *ptdev) int panthor_gpu_flush_caches(struct panthor_device *ptdev, u32 l2, u32 lsc, u32 other) { - bool timedout = false; unsigned long flags; + int ret = 0; /* Serialize cache flush operations. */ guard(mutex)(&ptdev->gpu->cache_flush_lock); spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags); - if (!drm_WARN_ON(&ptdev->base, - ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED)) { + if (!(ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED)) { ptdev->gpu->pending_reqs |= GPU_IRQ_CLEAN_CACHES_COMPLETED; gpu_write(ptdev, GPU_CMD, GPU_FLUSH_CACHES(l2, lsc, other)); + } else { + ret = -EIO; } spin_unlock_irqrestore(&ptdev->gpu->reqs_lock, flags); + if (ret) + return ret; + if (!wait_event_timeout(ptdev->gpu->reqs_acked, !(ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED), msecs_to_jiffies(100))) { spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags); if ((ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED) != 0 && !(gpu_read(ptdev, GPU_INT_RAWSTAT) & GPU_IRQ_CLEAN_CACHES_COMPLETED)) - timedout = true; + ret = -ETIMEDOUT; else ptdev->gpu->pending_reqs &= ~GPU_IRQ_CLEAN_CACHES_COMPLETED; spin_unlock_irqrestore(&ptdev->gpu->reqs_lock, flags); } - if (timedout) { + if (ret) { + panthor_device_schedule_reset(ptdev); drm_err(&ptdev->base, "Flush caches timeout"); - return -ETIMEDOUT; } - return 0; + return ret; } /** @@ -330,6 +334,7 @@ int panthor_gpu_soft_reset(struct panthor_device *ptdev) return -ETIMEDOUT; } + ptdev->gpu->pending_reqs = 0; return 0; } diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c index 7870e7dbaa5d45..1572d2c116993d 100644 --- a/drivers/gpu/drm/panthor/panthor_mmu.c +++ b/drivers/gpu/drm/panthor/panthor_mmu.c @@ -181,20 +181,6 @@ struct panthor_vm_op_ctx { u64 range; } va; - /** - * @returned_vmas: List of panthor_vma objects returned after a VM operation. - * - * For unmap operations, this will contain all VMAs that were covered by the - * specified VA range. - * - * For map operations, this will contain all VMAs that previously mapped to - * the specified VA range. - * - * Those VMAs, and the resources they point to will be released as part of - * the op_ctx cleanup operation. - */ - struct list_head returned_vmas; - /** @map: Fields specific to a map operation. */ struct { /** @map.vm_bo: Buffer object to map. */ @@ -1081,47 +1067,18 @@ void panthor_vm_free_va(struct panthor_vm *vm, struct drm_mm_node *va_node) mutex_unlock(&vm->mm_lock); } -static void panthor_vm_bo_put(struct drm_gpuvm_bo *vm_bo) +static void panthor_vm_bo_free(struct drm_gpuvm_bo *vm_bo) { struct panthor_gem_object *bo = to_panthor_bo(vm_bo->obj); - struct drm_gpuvm *vm = vm_bo->vm; - bool unpin; - /* We must retain the GEM before calling drm_gpuvm_bo_put(), - * otherwise the mutex might be destroyed while we hold it. - * Same goes for the VM, since we take the VM resv lock. - */ - drm_gem_object_get(&bo->base.base); - drm_gpuvm_get(vm); - - /* We take the resv lock to protect against concurrent accesses to the - * gpuvm evicted/extobj lists that are modified in - * drm_gpuvm_bo_destroy(), which is called if drm_gpuvm_bo_put() - * releases sthe last vm_bo reference. - * We take the BO GPUVA list lock to protect the vm_bo removal from the - * GEM vm_bo list. - */ - dma_resv_lock(drm_gpuvm_resv(vm), NULL); - mutex_lock(&bo->base.base.gpuva.lock); - unpin = drm_gpuvm_bo_put(vm_bo); - mutex_unlock(&bo->base.base.gpuva.lock); - dma_resv_unlock(drm_gpuvm_resv(vm)); - - /* If the vm_bo object was destroyed, release the pin reference that - * was hold by this object. - */ - if (unpin && !drm_gem_is_imported(&bo->base.base)) + if (!drm_gem_is_imported(&bo->base.base)) drm_gem_shmem_unpin(&bo->base); - - drm_gpuvm_put(vm); - drm_gem_object_put(&bo->base.base); + kfree(vm_bo); } static void panthor_vm_cleanup_op_ctx(struct panthor_vm_op_ctx *op_ctx, struct panthor_vm *vm) { - struct panthor_vma *vma, *tmp_vma; - u32 remaining_pt_count = op_ctx->rsvd_page_tables.count - op_ctx->rsvd_page_tables.ptr; @@ -1134,16 +1091,26 @@ static void panthor_vm_cleanup_op_ctx(struct panthor_vm_op_ctx *op_ctx, kfree(op_ctx->rsvd_page_tables.pages); if (op_ctx->map.vm_bo) - panthor_vm_bo_put(op_ctx->map.vm_bo); + drm_gpuvm_bo_put_deferred(op_ctx->map.vm_bo); for (u32 i = 0; i < ARRAY_SIZE(op_ctx->preallocated_vmas); i++) kfree(op_ctx->preallocated_vmas[i]); - list_for_each_entry_safe(vma, tmp_vma, &op_ctx->returned_vmas, node) { - list_del(&vma->node); - panthor_vm_bo_put(vma->base.vm_bo); - kfree(vma); + drm_gpuvm_bo_deferred_cleanup(&vm->base); +} + +static void +panthor_vm_op_ctx_return_vma(struct panthor_vm_op_ctx *op_ctx, + struct panthor_vma *vma) +{ + for (u32 i = 0; i < ARRAY_SIZE(op_ctx->preallocated_vmas); i++) { + if (!op_ctx->preallocated_vmas[i]) { + op_ctx->preallocated_vmas[i] = vma; + return; + } } + + WARN_ON_ONCE(1); } static struct panthor_vma * @@ -1236,7 +1203,6 @@ static int panthor_vm_prepare_map_op_ctx(struct panthor_vm_op_ctx *op_ctx, return -EINVAL; memset(op_ctx, 0, sizeof(*op_ctx)); - INIT_LIST_HEAD(&op_ctx->returned_vmas); op_ctx->flags = flags; op_ctx->va.range = size; op_ctx->va.addr = va; @@ -1247,7 +1213,9 @@ static int panthor_vm_prepare_map_op_ctx(struct panthor_vm_op_ctx *op_ctx, if (!drm_gem_is_imported(&bo->base.base)) { /* Pre-reserve the BO pages, so the map operation doesn't have to - * allocate. + * allocate. This pin is dropped in panthor_vm_bo_free(), so + * once we have successfully called drm_gpuvm_bo_create(), + * GPUVM will take care of dropping the pin for us. */ ret = drm_gem_shmem_pin(&bo->base); if (ret) @@ -1286,16 +1254,6 @@ static int panthor_vm_prepare_map_op_ctx(struct panthor_vm_op_ctx *op_ctx, mutex_unlock(&bo->base.base.gpuva.lock); dma_resv_unlock(panthor_vm_resv(vm)); - /* If the a vm_bo for this combination exists, it already - * retains a pin ref, and we can release the one we took earlier. - * - * If our pre-allocated vm_bo is picked, it now retains the pin ref, - * which will be released in panthor_vm_bo_put(). - */ - if (preallocated_vm_bo != op_ctx->map.vm_bo && - !drm_gem_is_imported(&bo->base.base)) - drm_gem_shmem_unpin(&bo->base); - op_ctx->map.bo_offset = offset; /* L1, L2 and L3 page tables. @@ -1343,7 +1301,6 @@ static int panthor_vm_prepare_unmap_op_ctx(struct panthor_vm_op_ctx *op_ctx, int ret; memset(op_ctx, 0, sizeof(*op_ctx)); - INIT_LIST_HEAD(&op_ctx->returned_vmas); op_ctx->va.range = size; op_ctx->va.addr = va; op_ctx->flags = DRM_PANTHOR_VM_BIND_OP_TYPE_UNMAP; @@ -1391,7 +1348,6 @@ static void panthor_vm_prepare_sync_only_op_ctx(struct panthor_vm_op_ctx *op_ctx struct panthor_vm *vm) { memset(op_ctx, 0, sizeof(*op_ctx)); - INIT_LIST_HEAD(&op_ctx->returned_vmas); op_ctx->flags = DRM_PANTHOR_VM_BIND_OP_TYPE_SYNC_ONLY; } @@ -1547,6 +1503,10 @@ static void panthor_vm_destroy(struct panthor_vm *vm) vm->destroyed = true; + /* Tell scheduler to stop all GPU work related to this VM */ + if (refcount_read(&vm->as.active_cnt) > 0) + panthor_sched_prepare_for_vm_destruction(vm->ptdev); + mutex_lock(&vm->heaps.lock); panthor_heap_pool_destroy(vm->heaps.pool); vm->heaps.pool = NULL; @@ -2037,26 +1997,13 @@ static void panthor_vma_link(struct panthor_vm *vm, mutex_lock(&bo->base.base.gpuva.lock); drm_gpuva_link(&vma->base, vm_bo); - drm_WARN_ON(&vm->ptdev->base, drm_gpuvm_bo_put(vm_bo)); mutex_unlock(&bo->base.base.gpuva.lock); } -static void panthor_vma_unlink(struct panthor_vm *vm, - struct panthor_vma *vma) +static void panthor_vma_unlink(struct panthor_vma *vma) { - struct panthor_gem_object *bo = to_panthor_bo(vma->base.gem.obj); - struct drm_gpuvm_bo *vm_bo = drm_gpuvm_bo_get(vma->base.vm_bo); - - mutex_lock(&bo->base.base.gpuva.lock); - drm_gpuva_unlink(&vma->base); - mutex_unlock(&bo->base.base.gpuva.lock); - - /* drm_gpuva_unlink() release the vm_bo, but we manually retained it - * when entering this function, so we can implement deferred VMA - * destruction. Re-assign it here. - */ - vma->base.vm_bo = vm_bo; - list_add_tail(&vma->node, &vm->op_ctx->returned_vmas); + drm_gpuva_unlink_defer(&vma->base); + kfree(vma); } static void panthor_vma_init(struct panthor_vma *vma, u32 flags) @@ -2085,15 +2032,17 @@ static int panthor_gpuva_sm_step_map(struct drm_gpuva_op *op, void *priv) ret = panthor_vm_map_pages(vm, op->map.va.addr, flags_to_prot(vma->flags), op_ctx->map.sgt, op->map.gem.offset, op->map.va.range); - if (ret) + if (ret) { + panthor_vm_op_ctx_return_vma(op_ctx, vma); return ret; + } - /* Ref owned by the mapping now, clear the obj field so we don't release the - * pinning/obj ref behind GPUVA's back. - */ drm_gpuva_map(&vm->base, &vma->base, &op->map); panthor_vma_link(vm, vma, op_ctx->map.vm_bo); + + drm_gpuvm_bo_put_deferred(op_ctx->map.vm_bo); op_ctx->map.vm_bo = NULL; + return 0; } @@ -2132,16 +2081,14 @@ static int panthor_gpuva_sm_step_remap(struct drm_gpuva_op *op, * owned by the old mapping which will be released when this * mapping is destroyed, we need to grab a ref here. */ - panthor_vma_link(vm, prev_vma, - drm_gpuvm_bo_get(op->remap.unmap->va->vm_bo)); + panthor_vma_link(vm, prev_vma, op->remap.unmap->va->vm_bo); } if (next_vma) { - panthor_vma_link(vm, next_vma, - drm_gpuvm_bo_get(op->remap.unmap->va->vm_bo)); + panthor_vma_link(vm, next_vma, op->remap.unmap->va->vm_bo); } - panthor_vma_unlink(vm, unmap_vma); + panthor_vma_unlink(unmap_vma); return 0; } @@ -2158,12 +2105,13 @@ static int panthor_gpuva_sm_step_unmap(struct drm_gpuva_op *op, return ret; drm_gpuva_unmap(&op->unmap); - panthor_vma_unlink(vm, unmap_vma); + panthor_vma_unlink(unmap_vma); return 0; } static const struct drm_gpuvm_ops panthor_gpuvm_ops = { .vm_free = panthor_vm_free, + .vm_bo_free = panthor_vm_bo_free, .sm_step_map = panthor_gpuva_sm_step_map, .sm_step_remap = panthor_gpuva_sm_step_remap, .sm_step_unmap = panthor_gpuva_sm_step_unmap, diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c index 3d1f57e3990f4a..c7dd98936bd6bf 100644 --- a/drivers/gpu/drm/panthor/panthor_sched.c +++ b/drivers/gpu/drm/panthor/panthor_sched.c @@ -772,6 +772,12 @@ struct panthor_job_profiling_data { */ #define MAX_GROUPS_PER_POOL 128 +/* + * Mark added on an entry of group pool Xarray to identify if the group has + * been fully initialized and can be accessed elsewhere in the driver code. + */ +#define GROUP_REGISTERED XA_MARK_1 + /** * struct panthor_group_pool - Group pool * @@ -895,7 +901,8 @@ static void group_free_queue(struct panthor_group *group, struct panthor_queue * if (IS_ERR_OR_NULL(queue)) return; - drm_sched_entity_destroy(&queue->entity); + if (queue->entity.fence_context) + drm_sched_entity_destroy(&queue->entity); if (queue->scheduler.ops) drm_sched_fini(&queue->scheduler); @@ -1895,10 +1902,10 @@ struct panthor_sched_tick_ctx { struct list_head groups[PANTHOR_CSG_PRIORITY_COUNT]; u32 idle_group_count; u32 group_count; - enum panthor_csg_priority min_priority; struct panthor_vm *vms[MAX_CS_PER_CSG]; u32 as_count; bool immediate_tick; + bool stop_tick; u32 csg_upd_failed_mask; }; @@ -1963,17 +1970,21 @@ tick_ctx_pick_groups_from_list(const struct panthor_scheduler *sched, if (!owned_by_tick_ctx) group_get(group); - list_move_tail(&group->run_node, &ctx->groups[group->priority]); ctx->group_count++; + + /* If we have more than one active group with the same priority, + * we need to keep ticking to rotate the CSG priority. + */ if (group_is_idle(group)) ctx->idle_group_count++; + else if (!list_empty(&ctx->groups[group->priority])) + ctx->stop_tick = false; + + list_move_tail(&group->run_node, &ctx->groups[group->priority]); if (i == ctx->as_count) ctx->vms[ctx->as_count++] = group->vm; - if (ctx->min_priority > group->priority) - ctx->min_priority = group->priority; - if (tick_ctx_is_full(sched, ctx)) return; } @@ -1982,31 +1993,22 @@ tick_ctx_pick_groups_from_list(const struct panthor_scheduler *sched, static void tick_ctx_insert_old_group(struct panthor_scheduler *sched, struct panthor_sched_tick_ctx *ctx, - struct panthor_group *group, - bool full_tick) + struct panthor_group *group) { struct panthor_csg_slot *csg_slot = &sched->csg_slots[group->csg_id]; struct panthor_group *other_group; - if (!full_tick) { - list_add_tail(&group->run_node, &ctx->old_groups[group->priority]); - return; - } - - /* Rotate to make sure groups with lower CSG slot - * priorities have a chance to get a higher CSG slot - * priority next time they get picked. This priority - * has an impact on resource request ordering, so it's - * important to make sure we don't let one group starve - * all other groups with the same group priority. - */ + /* Class groups in descending priority order so we can easily rotate. */ list_for_each_entry(other_group, &ctx->old_groups[csg_slot->group->priority], run_node) { struct panthor_csg_slot *other_csg_slot = &sched->csg_slots[other_group->csg_id]; - if (other_csg_slot->priority > csg_slot->priority) { - list_add_tail(&csg_slot->group->run_node, &other_group->run_node); + /* Our group has a higher prio than the one we're testing against, + * place it just before. + */ + if (csg_slot->priority > other_csg_slot->priority) { + list_add_tail(&group->run_node, &other_group->run_node); return; } } @@ -2016,8 +2018,7 @@ tick_ctx_insert_old_group(struct panthor_scheduler *sched, static void tick_ctx_init(struct panthor_scheduler *sched, - struct panthor_sched_tick_ctx *ctx, - bool full_tick) + struct panthor_sched_tick_ctx *ctx) { struct panthor_device *ptdev = sched->ptdev; struct panthor_csg_slots_upd_ctx upd_ctx; @@ -2027,7 +2028,7 @@ tick_ctx_init(struct panthor_scheduler *sched, memset(ctx, 0, sizeof(*ctx)); csgs_upd_ctx_init(&upd_ctx); - ctx->min_priority = PANTHOR_CSG_PRIORITY_COUNT; + ctx->stop_tick = true; for (i = 0; i < ARRAY_SIZE(ctx->groups); i++) { INIT_LIST_HEAD(&ctx->groups[i]); INIT_LIST_HEAD(&ctx->old_groups[i]); @@ -2055,7 +2056,7 @@ tick_ctx_init(struct panthor_scheduler *sched, group->fatal_queues |= GENMASK(group->queue_count - 1, 0); } - tick_ctx_insert_old_group(sched, ctx, group, full_tick); + tick_ctx_insert_old_group(sched, ctx, group); csgs_upd_ctx_queue_reqs(ptdev, &upd_ctx, i, csg_iface->output->ack ^ CSG_STATUS_UPDATE, CSG_STATUS_UPDATE); @@ -2339,32 +2340,18 @@ static u64 tick_ctx_update_resched_target(struct panthor_scheduler *sched, const struct panthor_sched_tick_ctx *ctx) { - /* We had space left, no need to reschedule until some external event happens. */ - if (!tick_ctx_is_full(sched, ctx)) - goto no_tick; - - /* If idle groups were scheduled, no need to wake up until some external - * event happens (group unblocked, new job submitted, ...). - */ - if (ctx->idle_group_count) - goto no_tick; + u64 resched_target; - if (drm_WARN_ON(&sched->ptdev->base, ctx->min_priority >= PANTHOR_CSG_PRIORITY_COUNT)) + if (ctx->stop_tick) goto no_tick; - /* If there are groups of the same priority waiting, we need to - * keep the scheduler ticking, otherwise, we'll just wait for - * new groups with higher priority to be queued. - */ - if (!list_empty(&sched->groups.runnable[ctx->min_priority])) { - u64 resched_target = sched->last_tick + sched->tick_period; + resched_target = sched->last_tick + sched->tick_period; - if (time_before64(sched->resched_target, sched->last_tick) || - time_before64(resched_target, sched->resched_target)) - sched->resched_target = resched_target; + if (time_before64(sched->resched_target, sched->last_tick) || + time_before64(resched_target, sched->resched_target)) + sched->resched_target = resched_target; - return sched->resched_target - sched->last_tick; - } + return sched->resched_target - sched->last_tick; no_tick: sched->resched_target = U64_MAX; @@ -2377,9 +2364,11 @@ static void tick_work(struct work_struct *work) tick_work.work); struct panthor_device *ptdev = sched->ptdev; struct panthor_sched_tick_ctx ctx; + u64 resched_target = sched->resched_target; u64 remaining_jiffies = 0, resched_delay; u64 now = get_jiffies_64(); int prio, ret, cookie; + bool full_tick; if (!drm_dev_enter(&ptdev->base, &cookie)) return; @@ -2388,18 +2377,24 @@ static void tick_work(struct work_struct *work) if (drm_WARN_ON(&ptdev->base, ret)) goto out_dev_exit; - if (time_before64(now, sched->resched_target)) - remaining_jiffies = sched->resched_target - now; + /* If the tick is stopped, calculate when the next tick would be */ + if (resched_target == U64_MAX) + resched_target = sched->last_tick + sched->tick_period; + + if (time_before64(now, resched_target)) + remaining_jiffies = resched_target - now; + + full_tick = remaining_jiffies == 0; mutex_lock(&sched->lock); if (panthor_device_reset_is_pending(sched->ptdev)) goto out_unlock; - tick_ctx_init(sched, &ctx, remaining_jiffies != 0); + tick_ctx_init(sched, &ctx); if (ctx.csg_upd_failed_mask) goto out_cleanup_ctx; - if (remaining_jiffies) { + if (!full_tick) { /* Scheduling forced in the middle of a tick. Only RT groups * can preempt non-RT ones. Currently running RT groups can't be * preempted. @@ -2421,9 +2416,29 @@ static void tick_work(struct work_struct *work) for (prio = PANTHOR_CSG_PRIORITY_COUNT - 1; prio >= 0 && !tick_ctx_is_full(sched, &ctx); prio--) { + struct panthor_group *old_highest_prio_group = + list_first_entry_or_null(&ctx.old_groups[prio], + struct panthor_group, run_node); + + /* Pull out the group with the highest prio for rotation. */ + if (old_highest_prio_group) + list_del(&old_highest_prio_group->run_node); + + /* Re-insert old active groups so they get a chance to run with higher prio. */ + tick_ctx_pick_groups_from_list(sched, &ctx, &ctx.old_groups[prio], true, true); + + /* Fill the remaining slots with runnable groups. */ tick_ctx_pick_groups_from_list(sched, &ctx, &sched->groups.runnable[prio], true, false); - tick_ctx_pick_groups_from_list(sched, &ctx, &ctx.old_groups[prio], true, true); + + /* Re-insert the old group with the highest prio, and give it a chance to be + * scheduled again (but with a lower prio) if there's room left. + */ + if (old_highest_prio_group) { + list_add_tail(&old_highest_prio_group->run_node, &ctx.old_groups[prio]); + tick_ctx_pick_groups_from_list(sched, &ctx, &ctx.old_groups[prio], + true, true); + } } /* If we have free CSG slots left, pick idle groups */ @@ -2548,14 +2563,33 @@ static void sync_upd_work(struct work_struct *work) sched_queue_delayed_work(sched, tick, 0); } +static void sched_resume_tick(struct panthor_device *ptdev) +{ + struct panthor_scheduler *sched = ptdev->scheduler; + u64 delay_jiffies, now; + + drm_WARN_ON(&ptdev->base, sched->resched_target != U64_MAX); + + /* Scheduler tick was off, recalculate the resched_target based on the + * last tick event, and queue the scheduler work. + */ + now = get_jiffies_64(); + sched->resched_target = sched->last_tick + sched->tick_period; + if (sched->used_csg_slot_count == sched->csg_slot_count && + time_before64(now, sched->resched_target)) + delay_jiffies = min_t(unsigned long, sched->resched_target - now, ULONG_MAX); + else + delay_jiffies = 0; + + sched_queue_delayed_work(sched, tick, delay_jiffies); +} + static void group_schedule_locked(struct panthor_group *group, u32 queue_mask) { struct panthor_device *ptdev = group->ptdev; struct panthor_scheduler *sched = ptdev->scheduler; struct list_head *queue = &sched->groups.runnable[group->priority]; - u64 delay_jiffies = 0; bool was_idle; - u64 now; if (!group_can_run(group)) return; @@ -2600,13 +2634,7 @@ static void group_schedule_locked(struct panthor_group *group, u32 queue_mask) /* Scheduler tick was off, recalculate the resched_target based on the * last tick event, and queue the scheduler work. */ - now = get_jiffies_64(); - sched->resched_target = sched->last_tick + sched->tick_period; - if (sched->used_csg_slot_count == sched->csg_slot_count && - time_before64(now, sched->resched_target)) - delay_jiffies = min_t(unsigned long, sched->resched_target - now, ULONG_MAX); - - sched_queue_delayed_work(sched, tick, delay_jiffies); + sched_resume_tick(ptdev); } static void queue_stop(struct panthor_queue *queue, @@ -2679,6 +2707,20 @@ void panthor_sched_report_mmu_fault(struct panthor_device *ptdev) panthor_sched_immediate_tick(ptdev); } +void panthor_sched_prepare_for_vm_destruction(struct panthor_device *ptdev) +{ + /* FW can write out internal state, like the heap context, during CSG + * suspend. It is therefore important that the scheduler has fully + * evicted any pending and related groups before VM destruction can + * safely continue. Failure to do so can lead to GPU page faults. + * A controlled termination of a Panthor instance involves destroying + * the group(s) before the VM. This means any relevant group eviction + * has already been initiated by this point, and we just need to + * ensure that any pending tick_work() has been completed. + */ + flush_work(&ptdev->scheduler->tick_work.work); +} + void panthor_sched_resume(struct panthor_device *ptdev) { /* Force a tick to re-evaluate after a resume. */ @@ -2899,7 +2941,7 @@ void panthor_fdinfo_gather_group_samples(struct panthor_file *pfile) return; xa_lock(&gpool->xa); - xa_for_each(&gpool->xa, i, group) { + xa_for_each_marked(&gpool->xa, i, group, GROUP_REGISTERED) { guard(spinlock)(&group->fdinfo.lock); pfile->stats.cycles += group->fdinfo.data.cycles; pfile->stats.time += group->fdinfo.data.time; @@ -3207,6 +3249,18 @@ queue_run_job(struct drm_sched_job *sched_job) group_schedule_locked(group, BIT(job->queue_idx)); } else { + u32 queue_mask = BIT(job->queue_idx); + bool resume_tick = group_is_idle(group) && + (group->idle_queues & queue_mask) && + !(group->blocked_queues & queue_mask) && + sched->resched_target == U64_MAX; + + /* We just added something to the queue, so it's no longer idle. */ + group->idle_queues &= ~queue_mask; + + if (resume_tick) + sched_resume_tick(ptdev); + gpu_write(ptdev, CSF_DOORBELL(queue->doorbell_id), 1); if (!sched->pm.has_ref && !(group->blocked_queues & BIT(job->queue_idx))) { @@ -3403,6 +3457,8 @@ group_create_queue(struct panthor_group *group, drm_sched = &queue->scheduler; ret = drm_sched_entity_init(&queue->entity, 0, &drm_sched, 1, NULL); + if (ret) + goto err_free_queue; return queue; @@ -3572,6 +3628,8 @@ int panthor_group_create(struct panthor_file *pfile, group_init_task_info(group); + xa_set_mark(&gpool->xa, gid, GROUP_REGISTERED); + return gid; err_put_group: @@ -3586,6 +3644,9 @@ int panthor_group_destroy(struct panthor_file *pfile, u32 group_handle) struct panthor_scheduler *sched = ptdev->scheduler; struct panthor_group *group; + if (!xa_get_mark(&gpool->xa, group_handle, GROUP_REGISTERED)) + return -EINVAL; + group = xa_erase(&gpool->xa, group_handle); if (!group) return -EINVAL; @@ -3611,12 +3672,12 @@ int panthor_group_destroy(struct panthor_file *pfile, u32 group_handle) } static struct panthor_group *group_from_handle(struct panthor_group_pool *pool, - u32 group_handle) + unsigned long group_handle) { struct panthor_group *group; xa_lock(&pool->xa); - group = group_get(xa_load(&pool->xa, group_handle)); + group = group_get(xa_find(&pool->xa, &group_handle, group_handle, GROUP_REGISTERED)); xa_unlock(&pool->xa); return group; @@ -3703,7 +3764,7 @@ panthor_fdinfo_gather_group_mem_info(struct panthor_file *pfile, return; xa_lock(&gpool->xa); - xa_for_each(&gpool->xa, i, group) { + xa_for_each_marked(&gpool->xa, i, group, GROUP_REGISTERED) { stats->resident += group->fdinfo.kbo_sizes; if (group->csg_id >= 0) stats->active += group->fdinfo.kbo_sizes; @@ -3856,6 +3917,7 @@ void panthor_sched_unplug(struct panthor_device *ptdev) struct panthor_scheduler *sched = ptdev->scheduler; cancel_delayed_work_sync(&sched->tick_work); + disable_work_sync(&sched->fw_events_work); mutex_lock(&sched->lock); if (sched->pm.has_ref) { diff --git a/drivers/gpu/drm/panthor/panthor_sched.h b/drivers/gpu/drm/panthor/panthor_sched.h index 742b0b4ff3a3c5..6a560ab0a5b317 100644 --- a/drivers/gpu/drm/panthor/panthor_sched.h +++ b/drivers/gpu/drm/panthor/panthor_sched.h @@ -49,6 +49,7 @@ void panthor_sched_suspend(struct panthor_device *ptdev); void panthor_sched_resume(struct panthor_device *ptdev); void panthor_sched_report_mmu_fault(struct panthor_device *ptdev); +void panthor_sched_prepare_for_vm_destruction(struct panthor_device *ptdev); void panthor_sched_report_fw_events(struct panthor_device *ptdev, u32 events); void panthor_fdinfo_gather_group_samples(struct panthor_file *pfile); diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c index 56ff6a3fb48348..d7dc83cf7b00ac 100644 --- a/drivers/gpu/drm/pl111/pl111_drv.c +++ b/drivers/gpu/drm/pl111/pl111_drv.c @@ -295,7 +295,7 @@ static int pl111_amba_probe(struct amba_device *amba_dev, variant->name, priv); if (ret != 0) { dev_err(dev, "%s failed irq %d\n", __func__, ret); - return ret; + goto dev_put; } ret = pl111_modeset_init(drm); diff --git a/drivers/gpu/drm/radeon/pptable.h b/drivers/gpu/drm/radeon/pptable.h index 969a8fb0ee9e0b..f4e71046dc91c2 100644 --- a/drivers/gpu/drm/radeon/pptable.h +++ b/drivers/gpu/drm/radeon/pptable.h @@ -450,7 +450,7 @@ typedef struct _ClockInfoArray{ //sizeof(ATOM_PPLIB_CLOCK_INFO) UCHAR ucEntrySize; - UCHAR clockInfo[] __counted_by(ucNumEntries); + UCHAR clockInfo[] /*__counted_by(ucNumEntries)*/; }ClockInfoArray; typedef struct _NonClockInfoArray{ diff --git a/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi_regs.h b/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi_regs.h index 76521276e2af8e..dd871e17dcf535 100644 --- a/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi_regs.h +++ b/drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi_regs.h @@ -50,8 +50,8 @@ #define TXCMPPD3R 0x16c #define RXSETR 0x200 -#define RXSETR_CRCEN (((n) & 0xf) << 24) -#define RXSETR_ECCEN (((n) & 0xf) << 16) +#define RXSETR_CRCEN(n) (((n) & 0xf) << 24) +#define RXSETR_ECCEN(n) (((n) & 0xf) << 16) #define RXPSETR 0x210 #define RXPSETR_LPPDACC (1 << 0) #define RXPSR 0x220 diff --git a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c index ed6e8f036f4b3d..409f1a1e82a061 100644 --- a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c @@ -267,12 +267,7 @@ static irqreturn_t dw_hdmi_qp_rk3576_hardirq(int irq, void *dev_id) static irqreturn_t dw_hdmi_qp_rk3576_irq(int irq, void *dev_id) { struct rockchip_hdmi_qp *hdmi = dev_id; - u32 intr_stat, val; - - regmap_read(hdmi->regmap, RK3576_IOC_HDMI_HPD_STATUS, &intr_stat); - - if (!intr_stat) - return IRQ_NONE; + u32 val; val = FIELD_PREP_WM16(RK3576_HDMI_HPD_INT_CLR, 1); regmap_write(hdmi->regmap, RK3576_IOC_MISC_CON0, val); @@ -597,6 +592,15 @@ static void dw_hdmi_qp_rockchip_remove(struct platform_device *pdev) component_del(&pdev->dev, &dw_hdmi_qp_rockchip_ops); } +static int __maybe_unused dw_hdmi_qp_rockchip_suspend(struct device *dev) +{ + struct rockchip_hdmi_qp *hdmi = dev_get_drvdata(dev); + + dw_hdmi_qp_suspend(dev, hdmi->hdmi); + + return 0; +} + static int __maybe_unused dw_hdmi_qp_rockchip_resume(struct device *dev) { struct rockchip_hdmi_qp *hdmi = dev_get_drvdata(dev); @@ -612,7 +616,8 @@ static int __maybe_unused dw_hdmi_qp_rockchip_resume(struct device *dev) } static const struct dev_pm_ops dw_hdmi_qp_rockchip_pm = { - SET_SYSTEM_SLEEP_PM_OPS(NULL, dw_hdmi_qp_rockchip_resume) + SET_SYSTEM_SLEEP_PM_OPS(dw_hdmi_qp_rockchip_suspend, + dw_hdmi_qp_rockchip_resume) }; struct platform_driver dw_hdmi_qp_rockchip_pltfm_driver = { diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index eb77bde9f6283c..e693160e9b7f56 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -96,6 +96,9 @@ void rockchip_drm_dma_init_device(struct drm_device *drm_dev, private->iommu_dev = ERR_PTR(-ENODEV); else if (!private->iommu_dev) private->iommu_dev = dev; + + if (!IS_ERR(private->iommu_dev)) + drm_dev_set_dma_dev(drm_dev, private->iommu_dev); } static int rockchip_drm_init_iommu(struct drm_device *drm_dev) diff --git a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c index 38c49030c7ab64..f3950e8476a75b 100644 --- a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c +++ b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c @@ -1369,6 +1369,25 @@ static const struct vop2_regs_dump rk3588_regs_dump[] = { }, }; +/* + * phys_id is used to identify a main window(Cluster Win/Smart Win, not + * include the sub win of a cluster or the multi area) that can do overlay + * in main overlay stage. + */ +static struct vop2_win *vop2_find_win_by_phys_id(struct vop2 *vop2, uint8_t phys_id) +{ + struct vop2_win *win; + int i; + + for (i = 0; i < vop2->data->win_size; i++) { + win = &vop2->win[i]; + if (win->data->phys_id == phys_id) + return win; + } + + return NULL; +} + static unsigned long rk3568_set_intf_mux(struct vop2_video_port *vp, int id, u32 polflags) { struct vop2 *vop2 = vp->vop2; @@ -1842,15 +1861,31 @@ static void vop2_parse_alpha(struct vop2_alpha_config *alpha_config, alpha->dst_alpha_ctrl.bits.factor_mode = ALPHA_SRC_INVERSE; } -static int vop2_find_start_mixer_id_for_vp(struct vop2 *vop2, u8 port_id) +static int vop2_find_start_mixer_id_for_vp(struct vop2_video_port *vp) { - struct vop2_video_port *vp; - int used_layer = 0; + struct vop2 *vop2 = vp->vop2; + struct vop2_win *win; + u32 layer_sel = vop2->old_layer_sel; + u32 used_layer = 0; + unsigned long win_mask = vp->win_mask; + unsigned long phys_id; + bool match; int i; - for (i = 0; i < port_id; i++) { - vp = &vop2->vps[i]; - used_layer += hweight32(vp->win_mask); + for (i = 0; i < 31; i += 4) { + match = false; + for_each_set_bit(phys_id, &win_mask, ROCKCHIP_VOP2_ESMART3) { + win = vop2_find_win_by_phys_id(vop2, phys_id); + if (win->data->layer_sel_id[vp->id] == ((layer_sel >> i) & 0xf)) { + match = true; + break; + } + } + + if (!match) + used_layer += 1; + else + break; } return used_layer; @@ -1935,7 +1970,7 @@ static void vop2_setup_alpha(struct vop2_video_port *vp) u32 dst_global_alpha = DRM_BLEND_ALPHA_OPAQUE; if (vop2->version <= VOP_VERSION_RK3588) - mixer_id = vop2_find_start_mixer_id_for_vp(vop2, vp->id); + mixer_id = vop2_find_start_mixer_id_for_vp(vp); else mixer_id = 0; @@ -2069,7 +2104,7 @@ static void rk3568_vop2_wait_for_port_mux_done(struct vop2 *vop2) * Spin until the previous port_mux figuration is done. */ ret = readx_poll_timeout_atomic(rk3568_vop2_read_port_mux, vop2, port_mux_sel, - port_mux_sel == vop2->old_port_sel, 0, 50 * 1000); + port_mux_sel == vop2->old_port_sel, 10, 50 * 1000); if (ret) DRM_DEV_ERROR(vop2->dev, "wait port_mux done timeout: 0x%x--0x%x\n", port_mux_sel, vop2->old_port_sel); @@ -2089,7 +2124,7 @@ static void rk3568_vop2_wait_for_layer_cfg_done(struct vop2 *vop2, u32 cfg) * Spin until the previous layer configuration is done. */ ret = readx_poll_timeout_atomic(rk3568_vop2_read_layer_cfg, vop2, atv_layer_cfg, - atv_layer_cfg == cfg, 0, 50 * 1000); + atv_layer_cfg == cfg, 10, 50 * 1000); if (ret) DRM_DEV_ERROR(vop2->dev, "wait layer cfg done timeout: 0x%x--0x%x\n", atv_layer_cfg, cfg); @@ -2109,6 +2144,7 @@ static void rk3568_vop2_setup_layer_mixer(struct vop2_video_port *vp) u8 layer_sel_id; unsigned int ofs; u32 ovl_ctrl; + u32 cfg_done; int i; struct vop2_video_port *vp0 = &vop2->vps[0]; struct vop2_video_port *vp1 = &vop2->vps[1]; @@ -2263,8 +2299,16 @@ static void rk3568_vop2_setup_layer_mixer(struct vop2_video_port *vp) rk3568_vop2_wait_for_port_mux_done(vop2); } - if (layer_sel != old_layer_sel && atv_layer_sel != old_layer_sel) - rk3568_vop2_wait_for_layer_cfg_done(vop2, vop2->old_layer_sel); + if (layer_sel != old_layer_sel && atv_layer_sel != old_layer_sel) { + cfg_done = vop2_readl(vop2, RK3568_REG_CFG_DONE); + cfg_done &= (BIT(vop2->data->nr_vps) - 1); + cfg_done &= ~BIT(vp->id); + /* + * Changes of other VPs' overlays have not taken effect + */ + if (cfg_done) + rk3568_vop2_wait_for_layer_cfg_done(vop2, vop2->old_layer_sel); + } vop2_writel(vop2, RK3568_OVL_LAYER_SEL, layer_sel); mutex_unlock(&vop2->ovl_lock); diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index fe174a4857be7f..e1920f3f920aee 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -420,7 +420,12 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity, /* * Fence is from the same scheduler, only need to wait for - * it to be scheduled + * it to be scheduled. + * + * Note: s_fence->sched could have been freed and reallocated + * as another scheduler. This false positive case is okay, as if + * the old scheduler was freed all of its jobs must have + * signaled their completion fences. */ fence = dma_fence_get(&s_fence->scheduled); dma_fence_put(entity->dependency); diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c index 9391d6f0dc01d7..d05ab041a581a6 100644 --- a/drivers/gpu/drm/scheduler/sched_fence.c +++ b/drivers/gpu/drm/scheduler/sched_fence.c @@ -92,7 +92,7 @@ static const char *drm_sched_fence_get_driver_name(struct dma_fence *fence) static const char *drm_sched_fence_get_timeline_name(struct dma_fence *f) { struct drm_sched_fence *fence = to_drm_sched_fence(f); - return (const char *)fence->sched->name; + return (const char *)fence->sched_name; } static void drm_sched_fence_free_rcu(struct rcu_head *rcu) @@ -228,6 +228,8 @@ void drm_sched_fence_init(struct drm_sched_fence *fence, unsigned seq; fence->sched = entity->rq->sched; + strscpy(fence->sched_name, entity->rq->sched->name, + sizeof(fence->sched_name)); seq = atomic_inc_return(&entity->fence_seq); dma_fence_init(&fence->scheduled, &drm_sched_fence_ops_scheduled, &fence->lock, entity->fence_context, seq); diff --git a/drivers/gpu/drm/sysfb/drm_sysfb_helper.h b/drivers/gpu/drm/sysfb/drm_sysfb_helper.h index 89633e30ca625a..265a1b8a934932 100644 --- a/drivers/gpu/drm/sysfb/drm_sysfb_helper.h +++ b/drivers/gpu/drm/sysfb/drm_sysfb_helper.h @@ -47,15 +47,6 @@ const struct drm_format_info *drm_sysfb_get_format_si(struct drm_device *dev, const struct screen_info *si); #endif -/* - * Input parsing - */ - -int drm_sysfb_get_validated_int(struct drm_device *dev, const char *name, - u64 value, u32 max); -int drm_sysfb_get_validated_int0(struct drm_device *dev, const char *name, - u64 value, u32 max); - /* * Display modes */ diff --git a/drivers/gpu/drm/sysfb/simpledrm.c b/drivers/gpu/drm/sysfb/simpledrm.c index 0358164a623c9e..d98cffd9b341d2 100644 --- a/drivers/gpu/drm/sysfb/simpledrm.c +++ b/drivers/gpu/drm/sysfb/simpledrm.c @@ -839,6 +839,12 @@ static int simpledrm_probe(struct platform_device *pdev) struct drm_device *dev; int ret; + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (ret) + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to set dma mask\n"); + sdev = simpledrm_device_create(&simpledrm_driver, pdev); if (IS_ERR(sdev)) return PTR_ERR(sdev); diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c index 8cd2969e7d4bfe..c4820f5e765813 100644 --- a/drivers/gpu/drm/tegra/hdmi.c +++ b/drivers/gpu/drm/tegra/hdmi.c @@ -658,7 +658,7 @@ static void tegra_hdmi_write_infopack(struct tegra_hdmi *hdmi, const void *data, { const u8 *ptr = data; unsigned long offset; - size_t i, j; + size_t i; u32 value; switch (ptr[0]) { @@ -691,7 +691,7 @@ static void tegra_hdmi_write_infopack(struct tegra_hdmi *hdmi, const void *data, * - subpack_low: bytes 0 - 3 * - subpack_high: bytes 4 - 6 (with byte 7 padded to 0x00) */ - for (i = 3, j = 0; i < size; i += 7, j += 8) { + for (i = 3; i < size; i += 7) { size_t rem = size - i, num = min_t(size_t, rem, 4); value = tegra_hdmi_subpack(&ptr[i], num); diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index 21f3dfdcc5c957..bc7dd562cf6b6b 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -1864,7 +1864,7 @@ static void tegra_sor_hdmi_write_infopack(struct tegra_sor *sor, { const u8 *ptr = data; unsigned long offset; - size_t i, j; + size_t i; u32 value; switch (ptr[0]) { @@ -1897,7 +1897,7 @@ static void tegra_sor_hdmi_write_infopack(struct tegra_sor *sor, * - subpack_low: bytes 0 - 3 * - subpack_high: bytes 4 - 6 (with byte 7 padded to 0x00) */ - for (i = 3, j = 0; i < size; i += 7, j += 8) { + for (i = 3; i < size; i += 7) { size_t rem = size - i, num = min_t(size_t, rem, 4); value = tegra_sor_hdmi_subpack(&ptr[i], num); diff --git a/drivers/gpu/drm/tests/drm_atomic_state_test.c b/drivers/gpu/drm/tests/drm_atomic_state_test.c index 2f6ac7a09f4458..bc27f65b282339 100644 --- a/drivers/gpu/drm/tests/drm_atomic_state_test.c +++ b/drivers/gpu/drm/tests/drm_atomic_state_test.c @@ -156,24 +156,29 @@ static int set_up_atomic_state(struct kunit *test, if (connector) { conn_state = drm_atomic_get_connector_state(state, connector); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, conn_state); + if (IS_ERR(conn_state)) + return PTR_ERR(conn_state); ret = drm_atomic_set_crtc_for_connector(conn_state, crtc); - KUNIT_EXPECT_EQ(test, ret, 0); + if (ret) + return ret; } crtc_state = drm_atomic_get_crtc_state(state, crtc); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_state); + if (IS_ERR(crtc_state)) + return PTR_ERR(crtc_state); ret = drm_atomic_set_mode_for_crtc(crtc_state, &drm_atomic_test_mode); - KUNIT_EXPECT_EQ(test, ret, 0); + if (ret) + return ret; crtc_state->enable = true; crtc_state->active = true; if (connector) { ret = drm_atomic_commit(state); - KUNIT_ASSERT_EQ(test, ret, 0); + if (ret) + return ret; } else { // dummy connector mask crtc_state->connector_mask = DRM_TEST_CONN_0; @@ -206,7 +211,13 @@ static void drm_test_check_connector_changed_modeset(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); // first modeset to enable +retry_set_up: ret = set_up_atomic_state(test, priv, old_conn, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_set_up; + } KUNIT_ASSERT_EQ(test, ret, 0); state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); @@ -277,13 +288,26 @@ static void drm_test_check_valid_clones(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_set_up: ret = set_up_atomic_state(test, priv, NULL, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_set_up; + } KUNIT_ASSERT_EQ(test, ret, 0); state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); +retry: crtc_state = drm_atomic_get_crtc_state(state, priv->crtc); + if (PTR_ERR(crtc_state) == -EDEADLK) { + drm_atomic_state_clear(state); + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry; + } KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_state); crtc_state->encoder_mask = param->encoder_mask; @@ -292,6 +316,12 @@ static void drm_test_check_valid_clones(struct kunit *test) crtc_state->mode_changed = true; ret = drm_atomic_helper_check_modeset(drm, state); + if (ret == -EDEADLK) { + drm_atomic_state_clear(state); + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry; + } KUNIT_ASSERT_EQ(test, ret, param->expected_result); drm_modeset_drop_locks(&ctx); diff --git a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c index 8bd412735000cb..70f9aa70214303 100644 --- a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c +++ b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c @@ -257,10 +257,16 @@ static void drm_test_check_broadcast_rgb_crtc_mode_changed(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); @@ -326,10 +332,16 @@ static void drm_test_check_broadcast_rgb_crtc_mode_not_changed(struct kunit *tes drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); @@ -397,10 +409,16 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); @@ -457,10 +475,17 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode_vic_1(struct kunit *test) KUNIT_ASSERT_NOT_NULL(test, mode); crtc = priv->crtc; + +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, mode, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); @@ -518,10 +543,16 @@ static void drm_test_check_broadcast_rgb_full_cea_mode(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); @@ -580,10 +611,17 @@ static void drm_test_check_broadcast_rgb_full_cea_mode_vic_1(struct kunit *test) KUNIT_ASSERT_NOT_NULL(test, mode); crtc = priv->crtc; + +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, mode, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); @@ -643,10 +681,16 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); @@ -705,10 +749,17 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode_vic_1(struct kunit *te KUNIT_ASSERT_NOT_NULL(test, mode); crtc = priv->crtc; + +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, mode, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); @@ -870,10 +921,16 @@ static void drm_test_check_output_bpc_crtc_mode_changed(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); @@ -946,10 +1003,16 @@ static void drm_test_check_output_bpc_crtc_mode_not_changed(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); @@ -1022,10 +1085,16 @@ static void drm_test_check_output_bpc_dvi(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); conn_state = conn->state; @@ -1069,10 +1138,16 @@ static void drm_test_check_tmds_char_rate_rgb_8bpc(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); conn_state = conn->state; @@ -1118,10 +1193,16 @@ static void drm_test_check_tmds_char_rate_rgb_10bpc(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); conn_state = conn->state; @@ -1167,10 +1248,16 @@ static void drm_test_check_tmds_char_rate_rgb_12bpc(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); conn_state = conn->state; @@ -1218,10 +1305,16 @@ static void drm_test_check_hdmi_funcs_reject_rate(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); /* You shouldn't be doing that at home. */ @@ -1292,10 +1385,16 @@ static void drm_test_check_max_tmds_rate_bpc_fallback_rgb(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1440,10 +1539,16 @@ static void drm_test_check_max_tmds_rate_bpc_fallback_ignore_yuv422(struct kunit drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1669,10 +1774,17 @@ static void drm_test_check_output_bpc_format_vic_1(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); crtc = priv->crtc; + +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, mode, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1736,10 +1848,16 @@ static void drm_test_check_output_bpc_format_driver_rgb_only(struct kunit *test) drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1805,10 +1923,16 @@ static void drm_test_check_output_bpc_format_display_rgb_only(struct kunit *test drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1865,10 +1989,16 @@ static void drm_test_check_output_bpc_format_driver_8bpc_only(struct kunit *test drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1927,10 +2057,16 @@ static void drm_test_check_output_bpc_format_display_8bpc_only(struct kunit *tes drm_modeset_acquire_init(&ctx, 0); +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1970,10 +2106,17 @@ static void drm_test_check_disable_connector(struct kunit *test) drm = &priv->drm; crtc = priv->crtc; + +retry_conn_enable: ret = drm_kunit_helper_enable_crtc_connector(test, drm, crtc, conn, preferred, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) + goto retry_conn_enable; + } KUNIT_ASSERT_EQ(test, ret, 0); state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); diff --git a/drivers/gpu/drm/tidss/tidss_dispc.c b/drivers/gpu/drm/tidss/tidss_dispc.c index 7c8c15a5c39b3f..6bf1171d0bc2db 100644 --- a/drivers/gpu/drm/tidss/tidss_dispc.c +++ b/drivers/gpu/drm/tidss/tidss_dispc.c @@ -57,12 +57,6 @@ static const u16 tidss_k2g_common_regs[DISPC_COMMON_REG_TABLE_LEN] = { }; const struct dispc_features dispc_k2g_feats = { - .min_pclk_khz = 4375, - - .max_pclk_khz = { - [DISPC_VP_DPI] = 150000, - }, - /* * XXX According TRM the RGB input buffer width up to 2560 should * work on 3 taps, but in practice it only works up to 1280. @@ -145,11 +139,6 @@ static const u16 tidss_am65x_common_regs[DISPC_COMMON_REG_TABLE_LEN] = { }; const struct dispc_features dispc_am65x_feats = { - .max_pclk_khz = { - [DISPC_VP_DPI] = 165000, - [DISPC_VP_OLDI_AM65X] = 165000, - }, - .scaling = { .in_width_max_5tap_rgb = 1280, .in_width_max_3tap_rgb = 2560, @@ -245,11 +234,6 @@ static const u16 tidss_j721e_common_regs[DISPC_COMMON_REG_TABLE_LEN] = { }; const struct dispc_features dispc_j721e_feats = { - .max_pclk_khz = { - [DISPC_VP_DPI] = 170000, - [DISPC_VP_INTERNAL] = 600000, - }, - .scaling = { .in_width_max_5tap_rgb = 2048, .in_width_max_3tap_rgb = 4096, @@ -316,11 +300,6 @@ const struct dispc_features dispc_j721e_feats = { }; const struct dispc_features dispc_am625_feats = { - .max_pclk_khz = { - [DISPC_VP_DPI] = 165000, - [DISPC_VP_INTERNAL] = 170000, - }, - .scaling = { .in_width_max_5tap_rgb = 1280, .in_width_max_3tap_rgb = 2560, @@ -377,15 +356,6 @@ const struct dispc_features dispc_am625_feats = { }; const struct dispc_features dispc_am62a7_feats = { - /* - * if the code reaches dispc_mode_valid with VP1, - * it should return MODE_BAD. - */ - .max_pclk_khz = { - [DISPC_VP_TIED_OFF] = 0, - [DISPC_VP_DPI] = 165000, - }, - .scaling = { .in_width_max_5tap_rgb = 1280, .in_width_max_3tap_rgb = 2560, @@ -442,10 +412,6 @@ const struct dispc_features dispc_am62a7_feats = { }; const struct dispc_features dispc_am62l_feats = { - .max_pclk_khz = { - [DISPC_VP_DPI] = 165000, - }, - .subrev = DISPC_AM62L, .common = "common", @@ -1331,33 +1297,61 @@ static void dispc_vp_set_default_color(struct dispc_device *dispc, DISPC_OVR_DEFAULT_COLOR2, (v >> 32) & 0xffff); } +/* + * Calculate the percentage difference between the requested pixel clock rate + * and the effective rate resulting from calculating the clock divider value. + */ +unsigned int dispc_pclk_diff(unsigned long rate, unsigned long real_rate) +{ + int r = rate / 100, rr = real_rate / 100; + + return (unsigned int)(abs(((rr - r) * 100) / r)); +} + +static int check_pixel_clock(struct dispc_device *dispc, u32 hw_videoport, + unsigned long clock) +{ + unsigned long round_clock; + + /* + * For VP's with external clocking, clock operations must be + * delegated to respective driver, so we skip the check here. + */ + if (dispc->tidss->is_ext_vp_clk[hw_videoport]) + return 0; + + round_clock = clk_round_rate(dispc->vp_clk[hw_videoport], clock); + /* + * To keep the check consistent with dispc_vp_set_clk_rate(), we + * use the same 5% check here. + */ + if (dispc_pclk_diff(clock, round_clock) > 5) + return -EINVAL; + + return 0; +} + enum drm_mode_status dispc_vp_mode_valid(struct dispc_device *dispc, u32 hw_videoport, const struct drm_display_mode *mode) { u32 hsw, hfp, hbp, vsw, vfp, vbp; enum dispc_vp_bus_type bus_type; - int max_pclk; bus_type = dispc->feat->vp_bus_type[hw_videoport]; - max_pclk = dispc->feat->max_pclk_khz[bus_type]; - - if (WARN_ON(max_pclk == 0)) + if (WARN_ON(bus_type == DISPC_VP_TIED_OFF)) return MODE_BAD; - if (mode->clock < dispc->feat->min_pclk_khz) - return MODE_CLOCK_LOW; - - if (mode->clock > max_pclk) - return MODE_CLOCK_HIGH; - if (mode->hdisplay > 4096) return MODE_BAD; if (mode->vdisplay > 4096) return MODE_BAD; + if (check_pixel_clock(dispc, hw_videoport, mode->clock * 1000)) + return MODE_CLOCK_RANGE; + /* TODO: add interlace support */ if (mode->flags & DRM_MODE_FLAG_INTERLACE) return MODE_NO_INTERLACE; @@ -1421,17 +1415,6 @@ void dispc_vp_disable_clk(struct dispc_device *dispc, u32 hw_videoport) clk_disable_unprepare(dispc->vp_clk[hw_videoport]); } -/* - * Calculate the percentage difference between the requested pixel clock rate - * and the effective rate resulting from calculating the clock divider value. - */ -unsigned int dispc_pclk_diff(unsigned long rate, unsigned long real_rate) -{ - int r = rate / 100, rr = real_rate / 100; - - return (unsigned int)(abs(((rr - r) * 100) / r)); -} - int dispc_vp_set_clk_rate(struct dispc_device *dispc, u32 hw_videoport, unsigned long rate) { diff --git a/drivers/gpu/drm/tidss/tidss_dispc.h b/drivers/gpu/drm/tidss/tidss_dispc.h index 60c1b400eb8933..42279312dcc1b3 100644 --- a/drivers/gpu/drm/tidss/tidss_dispc.h +++ b/drivers/gpu/drm/tidss/tidss_dispc.h @@ -77,9 +77,6 @@ enum dispc_dss_subrevision { }; struct dispc_features { - int min_pclk_khz; - int max_pclk_khz[DISPC_VP_MAX_BUS_TYPE]; - struct dispc_features_scaling scaling; enum dispc_dss_subrevision subrev; diff --git a/drivers/gpu/drm/tidss/tidss_drv.h b/drivers/gpu/drm/tidss/tidss_drv.h index 84454a4855d115..e1c1f41d8b4beb 100644 --- a/drivers/gpu/drm/tidss/tidss_drv.h +++ b/drivers/gpu/drm/tidss/tidss_drv.h @@ -24,6 +24,8 @@ struct tidss_device { const struct dispc_features *feat; struct dispc_device *dispc; + bool is_ext_vp_clk[TIDSS_MAX_PORTS]; + unsigned int num_crtcs; struct drm_crtc *crtcs[TIDSS_MAX_PORTS]; diff --git a/drivers/gpu/drm/tidss/tidss_kms.c b/drivers/gpu/drm/tidss/tidss_kms.c index c34eb90cddbeac..9f5f98e707f2cc 100644 --- a/drivers/gpu/drm/tidss/tidss_kms.c +++ b/drivers/gpu/drm/tidss/tidss_kms.c @@ -28,9 +28,33 @@ static void tidss_atomic_commit_tail(struct drm_atomic_state *old_state) tidss_runtime_get(tidss); - drm_atomic_helper_commit_modeset_disables(ddev, old_state); - drm_atomic_helper_commit_planes(ddev, old_state, DRM_PLANE_COMMIT_ACTIVE_ONLY); - drm_atomic_helper_commit_modeset_enables(ddev, old_state); + /* + * TI's OLDI and DSI encoders need to be set up before the crtc is + * enabled. Thus drm_atomic_helper_commit_modeset_enables() and + * drm_atomic_helper_commit_modeset_disables() cannot be used here, as + * they enable the crtc before bridges' pre-enable, and disable the crtc + * after bridges' post-disable. + * + * Open code the functions here and first call the bridges' pre-enables, + * then crtc enable, then bridges' post-enable (and vice versa for + * disable). + */ + + drm_atomic_helper_commit_encoder_bridge_disable(ddev, old_state); + drm_atomic_helper_commit_crtc_disable(ddev, old_state); + drm_atomic_helper_commit_encoder_bridge_post_disable(ddev, old_state); + + drm_atomic_helper_update_legacy_modeset_state(ddev, old_state); + drm_atomic_helper_calc_timestamping_constants(old_state); + drm_atomic_helper_commit_crtc_set_mode(ddev, old_state); + + drm_atomic_helper_commit_planes(ddev, old_state, + DRM_PLANE_COMMIT_ACTIVE_ONLY); + + drm_atomic_helper_commit_encoder_bridge_pre_enable(ddev, old_state); + drm_atomic_helper_commit_crtc_enable(ddev, old_state); + drm_atomic_helper_commit_encoder_bridge_enable(ddev, old_state); + drm_atomic_helper_commit_writebacks(ddev, old_state); drm_atomic_helper_commit_hw_done(old_state); drm_atomic_helper_wait_for_flip_done(ddev, old_state); diff --git a/drivers/gpu/drm/tidss/tidss_oldi.c b/drivers/gpu/drm/tidss/tidss_oldi.c index 7688251beba280..17c535bfa05765 100644 --- a/drivers/gpu/drm/tidss/tidss_oldi.c +++ b/drivers/gpu/drm/tidss/tidss_oldi.c @@ -309,6 +309,25 @@ static u32 *tidss_oldi_atomic_get_input_bus_fmts(struct drm_bridge *bridge, return input_fmts; } +static enum drm_mode_status +tidss_oldi_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + struct tidss_oldi *oldi = drm_bridge_to_tidss_oldi(bridge); + unsigned long round_clock; + + round_clock = clk_round_rate(oldi->serial, mode->clock * 7 * 1000); + /* + * To keep the check consistent with dispc_vp_set_clk_rate(), + * we use the same 5% check here. + */ + if (dispc_pclk_diff(mode->clock * 7 * 1000, round_clock) > 5) + return -EINVAL; + + return 0; +} + static const struct drm_bridge_funcs tidss_oldi_bridge_funcs = { .attach = tidss_oldi_bridge_attach, .atomic_pre_enable = tidss_oldi_atomic_pre_enable, @@ -317,6 +336,7 @@ static const struct drm_bridge_funcs tidss_oldi_bridge_funcs = { .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, .atomic_reset = drm_atomic_helper_bridge_reset, + .mode_valid = tidss_oldi_mode_valid, }; static int get_oldi_mode(struct device_node *oldi_tx, int *companion_instance) @@ -430,6 +450,7 @@ void tidss_oldi_deinit(struct tidss_device *tidss) for (int i = 0; i < tidss->num_oldis; i++) { if (tidss->oldis[i]) { drm_bridge_remove(&tidss->oldis[i]->bridge); + tidss->is_ext_vp_clk[tidss->oldis[i]->parent_vp] = false; tidss->oldis[i] = NULL; } } @@ -580,6 +601,7 @@ int tidss_oldi_init(struct tidss_device *tidss) oldi->bridge.timings = &default_tidss_oldi_timings; tidss->oldis[tidss->num_oldis++] = oldi; + tidss->is_ext_vp_clk[oldi->parent_vp] = true; oldi->tidss = tidss; drm_bridge_add(&oldi->bridge); diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c index b5f60b2b2d0e72..41802c9bd14759 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c @@ -586,7 +586,7 @@ static void tilcdc_crtc_recover_work(struct work_struct *work) drm_modeset_unlock(&crtc->mutex); } -static void tilcdc_crtc_destroy(struct drm_crtc *crtc) +void tilcdc_crtc_destroy(struct drm_crtc *crtc) { struct tilcdc_drm_private *priv = crtc->dev->dev_private; diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c index 7caec4d38ddf0c..3dcbec312bacb4 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c @@ -172,8 +172,7 @@ static void tilcdc_fini(struct drm_device *dev) if (priv->crtc) tilcdc_crtc_shutdown(priv->crtc); - if (priv->is_registered) - drm_dev_unregister(dev); + drm_dev_unregister(dev); drm_kms_helper_poll_fini(dev); drm_atomic_helper_shutdown(dev); @@ -220,21 +219,21 @@ static int tilcdc_init(const struct drm_driver *ddrv, struct device *dev) priv->wq = alloc_ordered_workqueue("tilcdc", 0); if (!priv->wq) { ret = -ENOMEM; - goto init_failed; + goto put_drm; } priv->mmio = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->mmio)) { dev_err(dev, "failed to request / ioremap\n"); ret = PTR_ERR(priv->mmio); - goto init_failed; + goto free_wq; } priv->clk = clk_get(dev, "fck"); if (IS_ERR(priv->clk)) { dev_err(dev, "failed to get functional clock\n"); ret = -ENODEV; - goto init_failed; + goto free_wq; } pm_runtime_enable(dev); @@ -313,7 +312,7 @@ static int tilcdc_init(const struct drm_driver *ddrv, struct device *dev) ret = tilcdc_crtc_create(ddev); if (ret < 0) { dev_err(dev, "failed to create crtc\n"); - goto init_failed; + goto disable_pm; } modeset_init(ddev); @@ -324,46 +323,46 @@ static int tilcdc_init(const struct drm_driver *ddrv, struct device *dev) if (ret) { dev_err(dev, "failed to register cpufreq notifier\n"); priv->freq_transition.notifier_call = NULL; - goto init_failed; + goto destroy_crtc; } #endif if (priv->is_componentized) { ret = component_bind_all(dev, ddev); if (ret < 0) - goto init_failed; + goto unregister_cpufreq_notif; ret = tilcdc_add_component_encoder(ddev); if (ret < 0) - goto init_failed; + goto unbind_component; } else { ret = tilcdc_attach_external_device(ddev); if (ret) - goto init_failed; + goto unregister_cpufreq_notif; } if (!priv->external_connector && ((priv->num_encoders == 0) || (priv->num_connectors == 0))) { dev_err(dev, "no encoders/connectors found\n"); ret = -EPROBE_DEFER; - goto init_failed; + goto unbind_component; } ret = drm_vblank_init(ddev, 1); if (ret < 0) { dev_err(dev, "failed to initialize vblank\n"); - goto init_failed; + goto unbind_component; } ret = platform_get_irq(pdev, 0); if (ret < 0) - goto init_failed; + goto unbind_component; priv->irq = ret; ret = tilcdc_irq_install(ddev, priv->irq); if (ret < 0) { dev_err(dev, "failed to install IRQ handler\n"); - goto init_failed; + goto unbind_component; } drm_mode_config_reset(ddev); @@ -372,16 +371,34 @@ static int tilcdc_init(const struct drm_driver *ddrv, struct device *dev) ret = drm_dev_register(ddev, 0); if (ret) - goto init_failed; - priv->is_registered = true; + goto stop_poll; drm_client_setup_with_color_mode(ddev, bpp); return 0; -init_failed: - tilcdc_fini(ddev); +stop_poll: + drm_kms_helper_poll_fini(ddev); + tilcdc_irq_uninstall(ddev); +unbind_component: + if (priv->is_componentized) + component_unbind_all(dev, ddev); +unregister_cpufreq_notif: +#ifdef CONFIG_CPU_FREQ + cpufreq_unregister_notifier(&priv->freq_transition, + CPUFREQ_TRANSITION_NOTIFIER); +destroy_crtc: +#endif + tilcdc_crtc_destroy(priv->crtc); +disable_pm: + pm_runtime_disable(dev); + clk_put(priv->clk); +free_wq: + destroy_workqueue(priv->wq); +put_drm: platform_set_drvdata(pdev, NULL); + ddev->dev_private = NULL; + drm_dev_put(ddev); return ret; } diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.h b/drivers/gpu/drm/tilcdc/tilcdc_drv.h index b818448c83f612..58b276f82a669a 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_drv.h +++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.h @@ -82,7 +82,6 @@ struct tilcdc_drm_private { struct drm_encoder *external_encoder; struct drm_connector *external_connector; - bool is_registered; bool is_componentized; bool irq_enabled; }; @@ -164,6 +163,7 @@ void tilcdc_crtc_set_panel_info(struct drm_crtc *crtc, void tilcdc_crtc_set_simulate_vesa_sync(struct drm_crtc *crtc, bool simulate_vesa_sync); void tilcdc_crtc_shutdown(struct drm_crtc *crtc); +void tilcdc_crtc_destroy(struct drm_crtc *crtc); int tilcdc_crtc_update_fb(struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_pending_vblank_event *event); diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index b47020fca19923..e6abc7b40b1895 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -434,6 +434,11 @@ int ttm_bo_access(struct ttm_buffer_object *bo, unsigned long offset, if (ret) return ret; + if (!bo->resource) { + ret = -ENODATA; + goto unlock; + } + switch (bo->resource->mem_type) { case TTM_PL_SYSTEM: fallthrough; @@ -448,6 +453,7 @@ int ttm_bo_access(struct ttm_buffer_object *bo, unsigned long offset, ret = -EIO; } +unlock: ttm_bo_unreserve(bo); return ret; diff --git a/drivers/gpu/drm/tyr/Kconfig b/drivers/gpu/drm/tyr/Kconfig index 4b55308fd2eb4a..e933e647802722 100644 --- a/drivers/gpu/drm/tyr/Kconfig +++ b/drivers/gpu/drm/tyr/Kconfig @@ -6,6 +6,7 @@ config DRM_TYR depends on RUST depends on ARM || ARM64 || COMPILE_TEST depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_LPAE + depends on COMMON_CLK default n help Rust DRM driver for ARM Mali CSF-based GPUs. diff --git a/drivers/gpu/drm/tyr/driver.rs b/drivers/gpu/drm/tyr/driver.rs index d5625dd1e41c84..d14d5a9fdfb01e 100644 --- a/drivers/gpu/drm/tyr/driver.rs +++ b/drivers/gpu/drm/tyr/driver.rs @@ -186,6 +186,8 @@ impl drm::Driver for TyrDriver { const INFO: drm::DriverInfo = INFO; + const FEATURES: u32 = drm::driver::FEAT_GEM; + kernel::declare_drm_ioctls! { (PANTHOR_DEV_QUERY, drm_panthor_dev_query, ioctl::RENDER_ALLOW, File::dev_query), } diff --git a/drivers/gpu/drm/tyr/file.rs b/drivers/gpu/drm/tyr/file.rs index 0ef432947b73d5..bac43d701b5bed 100644 --- a/drivers/gpu/drm/tyr/file.rs +++ b/drivers/gpu/drm/tyr/file.rs @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 or MIT +use kernel::bindings; use kernel::drm; use kernel::prelude::*; use kernel::uaccess::UserSlice; @@ -20,6 +21,8 @@ impl drm::file::DriverFile for File { fn open(_dev: &drm::Device) -> Result>> { KBox::try_pin_init(try_pin_init!(Self {}), GFP_KERNEL) } + + fn as_raw(&self) -> *mut bindings::drm_file { todo!() } } impl File { diff --git a/drivers/gpu/drm/tyr/gem.rs b/drivers/gpu/drm/tyr/gem.rs index 1273bf89dbd5d7..83493904a13f5e 100644 --- a/drivers/gpu/drm/tyr/gem.rs +++ b/drivers/gpu/drm/tyr/gem.rs @@ -9,10 +9,12 @@ use kernel::prelude::*; #[pin_data] pub(crate) struct TyrObject {} +#[vtable] impl gem::DriverObject for TyrObject { type Driver = TyrDriver; + type Args = (); - fn new(_dev: &TyrDevice, _size: usize) -> impl PinInit { + fn new(_dev: &TyrDevice, _size: usize, _args: ()) -> impl PinInit { try_pin_init!(TyrObject {}) } } diff --git a/drivers/gpu/drm/vgem/vgem_fence.c b/drivers/gpu/drm/vgem/vgem_fence.c index fd76730fd38c07..07db319c3d7f9c 100644 --- a/drivers/gpu/drm/vgem/vgem_fence.c +++ b/drivers/gpu/drm/vgem/vgem_fence.c @@ -79,7 +79,7 @@ static struct dma_fence *vgem_fence_create(struct vgem_file *vfile, dma_fence_init(&fence->base, &vgem_fence_ops, &fence->lock, dma_fence_context_alloc(1), 1); - timer_setup(&fence->timer, vgem_fence_timeout, 0); + timer_setup(&fence->timer, vgem_fence_timeout, TIMER_IRQSAFE); /* We force the fence to expire within 10s to prevent driver hangs */ mod_timer(&fence->timer, jiffies + VGEM_FENCE_TIMEOUT); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index f031a312c78356..b22887e8c8815d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -32,9 +32,15 @@ #include -static void vmw_bo_release(struct vmw_bo *vbo) +/** + * vmw_bo_free - vmw_bo destructor + * + * @bo: Pointer to the embedded struct ttm_buffer_object + */ +static void vmw_bo_free(struct ttm_buffer_object *bo) { struct vmw_resource *res; + struct vmw_bo *vbo = to_vmw_bo(&bo->base); WARN_ON(kref_read(&vbo->tbo.base.refcount) != 0); vmw_bo_unmap(vbo); @@ -62,20 +68,8 @@ static void vmw_bo_release(struct vmw_bo *vbo) } vmw_surface_unreference(&vbo->dumb_surface); } - drm_gem_object_release(&vbo->tbo.base); -} - -/** - * vmw_bo_free - vmw_bo destructor - * - * @bo: Pointer to the embedded struct ttm_buffer_object - */ -static void vmw_bo_free(struct ttm_buffer_object *bo) -{ - struct vmw_bo *vbo = to_vmw_bo(&bo->base); - WARN_ON(!RB_EMPTY_ROOT(&vbo->res_tree)); - vmw_bo_release(vbo); + drm_gem_object_release(&vbo->tbo.base); WARN_ON(vbo->dirty); kfree(vbo); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 54ea1b513950a8..535d844191e7a6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -763,13 +763,15 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev, return ERR_PTR(ret); } - ttm_bo_reserve(&bo->tbo, false, false, NULL); - ret = vmw_bo_dirty_add(bo); - if (!ret && surface && surface->res.func->dirty_alloc) { - surface->res.coherent = true; - ret = surface->res.func->dirty_alloc(&surface->res); + if (bo) { + ttm_bo_reserve(&bo->tbo, false, false, NULL); + ret = vmw_bo_dirty_add(bo); + if (!ret && surface && surface->res.func->dirty_alloc) { + surface->res.coherent = true; + ret = surface->res.func->dirty_alloc(&surface->res); + } + ttm_bo_unreserve(&bo->tbo); } - ttm_bo_unreserve(&bo->tbo); return &vfb->base; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index 69dfe69ce0f87d..a8c8c9375d2973 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -923,8 +923,10 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv, ttm_bo_unreserve(&buf->tbo); res = vmw_shader_alloc(dev_priv, buf, size, 0, shader_type); - if (unlikely(ret != 0)) + if (IS_ERR(res)) { + ret = PTR_ERR(res); goto no_reserve; + } ret = vmw_cmdbuf_res_add(man, vmw_cmdbuf_res_shader, vmw_shader_key(user_key, shader_type), diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig index 4b288eb3f5b0e5..c34be1be155b39 100644 --- a/drivers/gpu/drm/xe/Kconfig +++ b/drivers/gpu/drm/xe/Kconfig @@ -39,7 +39,7 @@ config DRM_XE select DRM_TTM select DRM_TTM_HELPER select DRM_EXEC - select DRM_GPUSVM if !UML && DEVICE_PRIVATE + select DRM_GPUSVM if !UML select DRM_GPUVM select DRM_SCHED select MMU_NOTIFIER diff --git a/drivers/gpu/drm/xe/display/intel_fbdev_fb.c b/drivers/gpu/drm/xe/display/intel_fbdev_fb.c index 8ea9a472113c41..8eaf1cc7fdf930 100644 --- a/drivers/gpu/drm/xe/display/intel_fbdev_fb.c +++ b/drivers/gpu/drm/xe/display/intel_fbdev_fb.c @@ -3,7 +3,7 @@ * Copyright © 2023 Intel Corporation */ -#include +#include #include "intel_display_core.h" #include "intel_display_types.h" @@ -15,29 +15,15 @@ #include -struct intel_framebuffer *intel_fbdev_fb_alloc(struct drm_fb_helper *helper, - struct drm_fb_helper_surface_size *sizes) +struct intel_framebuffer *intel_fbdev_fb_alloc(struct drm_device *drm, + struct drm_mode_fb_cmd2 *mode_cmd) { struct drm_framebuffer *fb; - struct drm_device *dev = helper->dev; - struct xe_device *xe = to_xe_device(dev); - struct drm_mode_fb_cmd2 mode_cmd = {}; + struct xe_device *xe = to_xe_device(drm); struct xe_bo *obj; int size; - /* we don't do packed 24bpp */ - if (sizes->surface_bpp == 24) - sizes->surface_bpp = 32; - - mode_cmd.width = sizes->surface_width; - mode_cmd.height = sizes->surface_height; - - mode_cmd.pitches[0] = ALIGN(mode_cmd.width * - DIV_ROUND_UP(sizes->surface_bpp, 8), XE_PAGE_SIZE); - mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp, - sizes->surface_depth); - - size = mode_cmd.pitches[0] * mode_cmd.height; + size = mode_cmd->pitches[0] * mode_cmd->height; size = PAGE_ALIGN(size); obj = ERR_PTR(-ENODEV); @@ -67,10 +53,10 @@ struct intel_framebuffer *intel_fbdev_fb_alloc(struct drm_fb_helper *helper, } fb = intel_framebuffer_create(&obj->ttm.base, - drm_get_format_info(dev, - mode_cmd.pixel_format, - mode_cmd.modifier[0]), - &mode_cmd); + drm_get_format_info(drm, + mode_cmd->pixel_format, + mode_cmd->modifier[0]), + mode_cmd); if (IS_ERR(fb)) { xe_bo_unpin_map_no_vm(obj); goto err; diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 4410e28dee54be..a270aef7c49807 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -1008,6 +1008,7 @@ static long xe_bo_shrink_purge(struct ttm_operation_ctx *ctx, unsigned long *scanned) { struct xe_device *xe = ttm_to_xe_device(bo->bdev); + struct ttm_tt *tt = bo->ttm; long lret; /* Fake move to system, without copying data. */ @@ -1032,8 +1033,10 @@ static long xe_bo_shrink_purge(struct ttm_operation_ctx *ctx, .writeback = false, .allow_move = false}); - if (lret > 0) + if (lret > 0) { xe_ttm_tt_account_subtract(xe, bo->ttm); + update_global_total_pages(bo->bdev, -(long)tt->num_pages); + } return lret; } @@ -1119,8 +1122,10 @@ long xe_bo_shrink(struct ttm_operation_ctx *ctx, struct ttm_buffer_object *bo, if (needs_rpm) xe_pm_runtime_put(xe); - if (lret > 0) + if (lret > 0) { xe_ttm_tt_account_subtract(xe, tt); + update_global_total_pages(bo->bdev, -(long)tt->num_pages); + } out_unref: xe_bo_put(xe_bo); @@ -1480,7 +1485,7 @@ static bool xe_ttm_bo_lock_in_destructor(struct ttm_buffer_object *ttm_bo) * always succeed here, as long as we hold the lru lock. */ spin_lock(&ttm_bo->bdev->lru_lock); - locked = dma_resv_trylock(ttm_bo->base.resv); + locked = dma_resv_trylock(&ttm_bo->base._resv); spin_unlock(&ttm_bo->bdev->lru_lock); xe_assert(xe, locked); @@ -1500,13 +1505,6 @@ static void xe_ttm_bo_release_notify(struct ttm_buffer_object *ttm_bo) bo = ttm_to_xe_bo(ttm_bo); xe_assert(xe_bo_device(bo), !(bo->created && kref_read(&ttm_bo->base.refcount))); - /* - * Corner case where TTM fails to allocate memory and this BOs resv - * still points the VMs resv - */ - if (ttm_bo->base.resv != &ttm_bo->base._resv) - return; - if (!xe_ttm_bo_lock_in_destructor(ttm_bo)) return; @@ -1516,14 +1514,14 @@ static void xe_ttm_bo_release_notify(struct ttm_buffer_object *ttm_bo) * TODO: Don't do this for external bos once we scrub them after * unbind. */ - dma_resv_for_each_fence(&cursor, ttm_bo->base.resv, + dma_resv_for_each_fence(&cursor, &ttm_bo->base._resv, DMA_RESV_USAGE_BOOKKEEP, fence) { if (xe_fence_is_xe_preempt(fence) && !dma_fence_is_signaled(fence)) { if (!replacement) replacement = dma_fence_get_stub(); - dma_resv_replace_fences(ttm_bo->base.resv, + dma_resv_replace_fences(&ttm_bo->base._resv, fence->context, replacement, DMA_RESV_USAGE_BOOKKEEP); @@ -1531,7 +1529,7 @@ static void xe_ttm_bo_release_notify(struct ttm_buffer_object *ttm_bo) } dma_fence_put(replacement); - dma_resv_unlock(ttm_bo->base.resv); + dma_resv_unlock(&ttm_bo->base._resv); } static void xe_ttm_bo_delete_mem_notify(struct ttm_buffer_object *ttm_bo) @@ -1897,7 +1895,7 @@ static vm_fault_t xe_bo_cpu_fault(struct vm_fault *vmf) int err = 0; int idx; - if (!drm_dev_enter(&xe->drm, &idx)) + if (xe_device_wedged(xe) || !drm_dev_enter(&xe->drm, &idx)) return ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot); ret = xe_bo_cpu_fault_fastpath(vmf, xe, bo, needs_rpm); diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c index 1396634231857e..6688b2954d20b5 100644 --- a/drivers/gpu/drm/xe/xe_configfs.c +++ b/drivers/gpu/drm/xe/xe_configfs.c @@ -258,11 +258,10 @@ static bool is_bound(struct xe_config_group_device *dev) return false; ret = pci_get_drvdata(pdev); - pci_dev_put(pdev); - if (ret) pci_dbg(pdev, "Already bound to driver\n"); + pci_dev_put(pdev); return ret; } diff --git a/drivers/gpu/drm/xe/xe_configfs.h b/drivers/gpu/drm/xe/xe_configfs.h index c61e0e47ed94c1..08cce375ae0f37 100644 --- a/drivers/gpu/drm/xe/xe_configfs.h +++ b/drivers/gpu/drm/xe/xe_configfs.h @@ -19,9 +19,11 @@ void xe_configfs_check_device(struct pci_dev *pdev); bool xe_configfs_get_survivability_mode(struct pci_dev *pdev); u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev); bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev); -u32 xe_configfs_get_ctx_restore_mid_bb(struct pci_dev *pdev, enum xe_engine_class, +u32 xe_configfs_get_ctx_restore_mid_bb(struct pci_dev *pdev, + enum xe_engine_class class, const u32 **cs); -u32 xe_configfs_get_ctx_restore_post_bb(struct pci_dev *pdev, enum xe_engine_class, +u32 xe_configfs_get_ctx_restore_post_bb(struct pci_dev *pdev, + enum xe_engine_class class, const u32 **cs); #else static inline int xe_configfs_init(void) { return 0; } @@ -30,9 +32,11 @@ static inline void xe_configfs_check_device(struct pci_dev *pdev) { } static inline bool xe_configfs_get_survivability_mode(struct pci_dev *pdev) { return false; } static inline u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev) { return U64_MAX; } static inline bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev) { return false; } -static inline u32 xe_configfs_get_ctx_restore_mid_bb(struct pci_dev *pdev, enum xe_engine_class, +static inline u32 xe_configfs_get_ctx_restore_mid_bb(struct pci_dev *pdev, + enum xe_engine_class class, const u32 **cs) { return 0; } -static inline u32 xe_configfs_get_ctx_restore_post_bb(struct pci_dev *pdev, enum xe_engine_class, +static inline u32 xe_configfs_get_ctx_restore_post_bb(struct pci_dev *pdev, + enum xe_engine_class class, const u32 **cs) { return 0; } #endif diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c index cd977dbd1ef63e..7b48bf90cab8f4 100644 --- a/drivers/gpu/drm/xe/xe_debugfs.c +++ b/drivers/gpu/drm/xe/xe_debugfs.c @@ -255,14 +255,64 @@ static ssize_t wedged_mode_show(struct file *f, char __user *ubuf, return simple_read_from_buffer(ubuf, size, pos, buf, len); } +static int __wedged_mode_set_reset_policy(struct xe_gt *gt, enum xe_wedged_mode mode) +{ + bool enable_engine_reset; + int ret; + + enable_engine_reset = (mode != XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET); + ret = xe_guc_ads_scheduler_policy_toggle_reset(>->uc.guc.ads, + enable_engine_reset); + if (ret) + xe_gt_err(gt, "Failed to update GuC ADS scheduler policy (%pe)\n", ERR_PTR(ret)); + + return ret; +} + +static int wedged_mode_set_reset_policy(struct xe_device *xe, enum xe_wedged_mode mode) +{ + struct xe_gt *gt; + int ret; + u8 id; + + guard(xe_pm_runtime)(xe); + for_each_gt(gt, xe, id) { + ret = __wedged_mode_set_reset_policy(gt, mode); + if (ret) { + if (id > 0) { + xe->wedged.inconsistent_reset = true; + drm_err(&xe->drm, "Inconsistent reset policy state between GTs\n"); + } + return ret; + } + } + + xe->wedged.inconsistent_reset = false; + + return 0; +} + +static bool wedged_mode_needs_policy_update(struct xe_device *xe, enum xe_wedged_mode mode) +{ + if (xe->wedged.inconsistent_reset) + return true; + + if (xe->wedged.mode == mode) + return false; + + if (xe->wedged.mode == XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET || + mode == XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET) + return true; + + return false; +} + static ssize_t wedged_mode_set(struct file *f, const char __user *ubuf, size_t size, loff_t *pos) { struct xe_device *xe = file_inode(f)->i_private; - struct xe_gt *gt; u32 wedged_mode; ssize_t ret; - u8 id; ret = kstrtouint_from_user(ubuf, size, 0, &wedged_mode); if (ret) @@ -271,22 +321,14 @@ static ssize_t wedged_mode_set(struct file *f, const char __user *ubuf, if (wedged_mode > 2) return -EINVAL; - if (xe->wedged.mode == wedged_mode) - return size; + if (wedged_mode_needs_policy_update(xe, wedged_mode)) { + ret = wedged_mode_set_reset_policy(xe, wedged_mode); + if (ret) + return ret; + } xe->wedged.mode = wedged_mode; - xe_pm_runtime_get(xe); - for_each_gt(gt, xe, id) { - ret = xe_guc_ads_scheduler_policy_toggle_reset(>->uc.guc.ads); - if (ret) { - xe_gt_err(gt, "Failed to update GuC ADS scheduler policy. GuC may still cause engine reset even with wedged_mode=2\n"); - xe_pm_runtime_put(xe); - return -EIO; - } - } - xe_pm_runtime_put(xe); - return size; } diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 456899238377ed..0d69cd0e4e7985 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -966,6 +966,7 @@ int xe_device_probe(struct xe_device *xe) err_unregister_display: xe_display_unregister(xe); + drm_dev_unregister(&xe->drm); return err; } @@ -974,8 +975,6 @@ void xe_device_remove(struct xe_device *xe) { xe_display_unregister(xe); - xe_nvm_fini(xe); - drm_dev_unplug(&xe->drm); xe_bo_pci_dev_remove_all(xe); @@ -1046,7 +1045,7 @@ static void tdf_request_sync(struct xe_device *xe) * transient and need to be flushed.. */ if (xe_mmio_wait32(>->mmio, XE2_TDF_CTRL, TRANSIENT_FLUSH_REQUEST, 0, - 150, NULL, false)) + 300, NULL, false)) xe_gt_err_once(gt, "TD flush timeout\n"); xe_force_wake_put(gt_to_fw(gt), fw_ref); diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 74d7af830b85d8..0e80f2940c9963 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -42,6 +42,22 @@ struct xe_pat_ops; struct xe_pxp; struct xe_vram_region; +/** + * enum xe_wedged_mode - possible wedged modes + * @XE_WEDGED_MODE_NEVER: Device will never be declared wedged. + * @XE_WEDGED_MODE_UPON_CRITICAL_ERROR: Device will be declared wedged only + * when critical error occurs like GT reset failure or firmware failure. + * This is the default mode. + * @XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET: Device will be declared wedged on + * any hang. In this mode, engine resets are disabled to avoid automatic + * recovery attempts. This mode is primarily intended for debugging hangs. + */ +enum xe_wedged_mode { + XE_WEDGED_MODE_NEVER = 0, + XE_WEDGED_MODE_UPON_CRITICAL_ERROR = 1, + XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET = 2, +}; + #define XE_BO_INVALID_OFFSET LONG_MAX #define GRAPHICS_VER(xe) ((xe)->info.graphics_verx100 / 100) @@ -556,6 +572,8 @@ struct xe_device { int mode; /** @wedged.method: Recovery method to be sent in the drm device wedged uevent */ unsigned long method; + /** @wedged.inconsistent_reset: Inconsistent reset policy state between GTs */ + bool inconsistent_reset; } wedged; /** @bo_device: Struct to control async free of BOs */ diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index a7d67725c3ee19..2650c5abb36542 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -113,7 +113,7 @@ static struct sg_table *xe_dma_buf_map(struct dma_buf_attachment *attach, case XE_PL_TT: sgt = drm_prime_pages_to_sg(obj->dev, bo->ttm.ttm->pages, - bo->ttm.ttm->num_pages); + obj->size >> PAGE_SHIFT); if (IS_ERR(sgt)) return sgt; diff --git a/drivers/gpu/drm/xe/xe_eu_stall.c b/drivers/gpu/drm/xe/xe_eu_stall.c index f5cfdf29fde345..33a3764e3e71b0 100644 --- a/drivers/gpu/drm/xe/xe_eu_stall.c +++ b/drivers/gpu/drm/xe/xe_eu_stall.c @@ -290,7 +290,7 @@ static int xe_eu_stall_user_ext_set_property(struct xe_device *xe, u64 extension return -EFAULT; if (XE_IOCTL_DBG(xe, ext.property >= ARRAY_SIZE(xe_set_eu_stall_property_funcs)) || - XE_IOCTL_DBG(xe, ext.pad)) + XE_IOCTL_DBG(xe, !ext.property) || XE_IOCTL_DBG(xe, ext.pad)) return -EINVAL; idx = array_index_nospec(ext.property, ARRAY_SIZE(xe_set_eu_stall_property_funcs)); diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index a8ab363a804658..87a32b61bece66 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -130,7 +130,8 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) if (XE_IOCTL_DBG(xe, args->extensions) || XE_IOCTL_DBG(xe, args->pad[0] || args->pad[1] || args->pad[2]) || - XE_IOCTL_DBG(xe, args->reserved[0] || args->reserved[1])) + XE_IOCTL_DBG(xe, args->reserved[0] || args->reserved[1]) || + XE_IOCTL_DBG(xe, args->num_syncs > DRM_XE_MAX_SYNCS)) return -EINVAL; q = xe_exec_queue_lookup(xef, args->exec_queue_id); @@ -181,9 +182,9 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) goto err_syncs; } - if (xe_exec_queue_is_parallel(q)) { - err = copy_from_user(addresses, addresses_user, sizeof(u64) * - q->width); + if (args->num_batch_buffer && xe_exec_queue_is_parallel(q)) { + err = copy_from_user(addresses, addresses_user, + sizeof(u64) * q->width); if (err) { err = -EFAULT; goto err_syncs; diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index cb5f204c08ed6e..231d1fbe5eefa7 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -284,6 +284,7 @@ struct xe_exec_queue *xe_exec_queue_create_class(struct xe_device *xe, struct xe * @xe: Xe device. * @tile: tile which bind exec queue belongs to. * @flags: exec queue creation flags + * @user_vm: The user VM which this exec queue belongs to * @extensions: exec queue creation extensions * * Normalize bind exec queue creation. Bind exec queue is tied to migration VM @@ -297,6 +298,7 @@ struct xe_exec_queue *xe_exec_queue_create_class(struct xe_device *xe, struct xe */ struct xe_exec_queue *xe_exec_queue_create_bind(struct xe_device *xe, struct xe_tile *tile, + struct xe_vm *user_vm, u32 flags, u64 extensions) { struct xe_gt *gt = tile->primary_gt; @@ -333,6 +335,9 @@ struct xe_exec_queue *xe_exec_queue_create_bind(struct xe_device *xe, xe_exec_queue_put(q); return ERR_PTR(err); } + + if (user_vm) + q->user_vm = xe_vm_get(user_vm); } return q; @@ -357,6 +362,11 @@ void xe_exec_queue_destroy(struct kref *ref) xe_exec_queue_put(eq); } + if (q->user_vm) { + xe_vm_put(q->user_vm); + q->user_vm = NULL; + } + q->ops->destroy(q); } @@ -692,6 +702,22 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, XE_IOCTL_DBG(xe, eci[0].engine_instance != 0)) return -EINVAL; + vm = xe_vm_lookup(xef, args->vm_id); + if (XE_IOCTL_DBG(xe, !vm)) + return -ENOENT; + + err = down_read_interruptible(&vm->lock); + if (err) { + xe_vm_put(vm); + return err; + } + + if (XE_IOCTL_DBG(xe, xe_vm_is_closed_or_banned(vm))) { + up_read(&vm->lock); + xe_vm_put(vm); + return -ENOENT; + } + for_each_tile(tile, xe, id) { struct xe_exec_queue *new; @@ -699,9 +725,11 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, if (id) flags |= EXEC_QUEUE_FLAG_BIND_ENGINE_CHILD; - new = xe_exec_queue_create_bind(xe, tile, flags, + new = xe_exec_queue_create_bind(xe, tile, vm, flags, args->extensions); if (IS_ERR(new)) { + up_read(&vm->lock); + xe_vm_put(vm); err = PTR_ERR(new); if (q) goto put_exec_queue; @@ -713,6 +741,8 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data, list_add_tail(&new->multi_gt_list, &q->multi_gt_link); } + up_read(&vm->lock); + xe_vm_put(vm); } else { logical_mask = calc_validate_logical_mask(xe, eci, args->width, diff --git a/drivers/gpu/drm/xe/xe_exec_queue.h b/drivers/gpu/drm/xe/xe_exec_queue.h index 15ec852e7f7e78..5343c1b8cab540 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.h +++ b/drivers/gpu/drm/xe/xe_exec_queue.h @@ -24,6 +24,7 @@ struct xe_exec_queue *xe_exec_queue_create_class(struct xe_device *xe, struct xe u32 flags, u64 extensions); struct xe_exec_queue *xe_exec_queue_create_bind(struct xe_device *xe, struct xe_tile *tile, + struct xe_vm *user_vm, u32 flags, u64 extensions); void xe_exec_queue_fini(struct xe_exec_queue *q); diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index df1c69dc81f17b..38906cb7608ca4 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -54,6 +54,12 @@ struct xe_exec_queue { struct kref refcount; /** @vm: VM (address space) for this exec queue */ struct xe_vm *vm; + /** + * @user_vm: User VM (address space) for this exec queue (bind queues + * only) + */ + struct xe_vm *user_vm; + /** @class: class of this exec queue */ enum xe_engine_class class; /** diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c index 5edc0cad47e20d..20d9171bd3d0ab 100644 --- a/drivers/gpu/drm/xe/xe_ggtt.c +++ b/drivers/gpu/drm/xe/xe_ggtt.c @@ -291,7 +291,7 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt) else ggtt->pt_ops = &xelp_pt_ops; - ggtt->wq = alloc_workqueue("xe-ggtt-wq", 0, WQ_MEM_RECLAIM); + ggtt->wq = alloc_workqueue("xe-ggtt-wq", WQ_MEM_RECLAIM, 0); if (!ggtt->wq) return -ENOMEM; diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 6d3db5e55d98ae..61bed3b04dedd2 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -784,9 +784,6 @@ static int do_gt_restart(struct xe_gt *gt) xe_gt_sriov_pf_init_hw(gt); xe_mocs_init(gt); - err = xe_uc_start(>->uc); - if (err) - return err; for_each_hw_engine(hwe, gt, id) xe_reg_sr_apply_mmio(&hwe->reg_sr, gt); @@ -794,6 +791,10 @@ static int do_gt_restart(struct xe_gt *gt) /* Get CCS mode in sync between sw/hw */ xe_gt_apply_ccs_mode(gt); + err = xe_uc_start(>->uc); + if (err) + return err; + /* Restore GT freq to expected values */ xe_gt_sanitize_freq(gt); diff --git a/drivers/gpu/drm/xe/xe_gt_freq.c b/drivers/gpu/drm/xe/xe_gt_freq.c index 4ff1b6b58d6be4..e8e70fd2e8c42d 100644 --- a/drivers/gpu/drm/xe/xe_gt_freq.c +++ b/drivers/gpu/drm/xe/xe_gt_freq.c @@ -296,8 +296,10 @@ int xe_gt_freq_init(struct xe_gt *gt) return -ENOMEM; err = sysfs_create_files(gt->freq, freq_attrs); - if (err) + if (err) { + kobject_put(gt->freq); return err; + } err = devm_add_action_or_reset(xe->drm.dev, freq_fini, gt->freq); if (err) diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c index bdc9d9877ec490..3e3d1d52f63026 100644 --- a/drivers/gpu/drm/xe/xe_gt_idle.c +++ b/drivers/gpu/drm/xe/xe_gt_idle.c @@ -5,6 +5,7 @@ #include +#include #include "xe_force_wake.h" #include "xe_device.h" #include "xe_gt.h" @@ -16,6 +17,7 @@ #include "xe_mmio.h" #include "xe_pm.h" #include "xe_sriov.h" +#include "xe_wa.h" /** * DOC: Xe GT Idle @@ -145,6 +147,12 @@ void xe_gt_idle_enable_pg(struct xe_gt *gt) xe_mmio_write32(mmio, RENDER_POWERGATE_IDLE_HYSTERESIS, 25); } + if (XE_GT_WA(gt, 14020316580)) + gtidle->powergate_enable &= ~(VDN_HCP_POWERGATE_ENABLE(0) | + VDN_MFXVDENC_POWERGATE_ENABLE(0) | + VDN_HCP_POWERGATE_ENABLE(2) | + VDN_MFXVDENC_POWERGATE_ENABLE(2)); + xe_mmio_write32(mmio, POWERGATE_ENABLE, gtidle->powergate_enable); xe_force_wake_put(gt_to_fw(gt), fw_ref); } diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c index 00789844ea4d03..ae0c88da422b2b 100644 --- a/drivers/gpu/drm/xe/xe_guc.c +++ b/drivers/gpu/drm/xe/xe_guc.c @@ -1632,7 +1632,7 @@ int xe_guc_start(struct xe_guc *guc) return xe_guc_submit_start(guc); } -void xe_guc_print_info(struct xe_guc *guc, struct drm_printer *p) +int xe_guc_print_info(struct xe_guc *guc, struct drm_printer *p) { struct xe_gt *gt = guc_to_gt(guc); unsigned int fw_ref; @@ -1644,7 +1644,7 @@ void xe_guc_print_info(struct xe_guc *guc, struct drm_printer *p) if (!IS_SRIOV_VF(gt_to_xe(gt))) { fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT); if (!fw_ref) - return; + return -EIO; status = xe_mmio_read32(>->mmio, GUC_STATUS); @@ -1672,6 +1672,8 @@ void xe_guc_print_info(struct xe_guc *guc, struct drm_printer *p) drm_puts(p, "\n"); xe_guc_submit_print(guc, p); + + return 0; } /** diff --git a/drivers/gpu/drm/xe/xe_guc.h b/drivers/gpu/drm/xe/xe_guc.h index 1cca05967e621c..3b858933749bd2 100644 --- a/drivers/gpu/drm/xe/xe_guc.h +++ b/drivers/gpu/drm/xe/xe_guc.h @@ -45,7 +45,7 @@ int xe_guc_self_cfg32(struct xe_guc *guc, u16 key, u32 val); int xe_guc_self_cfg64(struct xe_guc *guc, u16 key, u64 val); void xe_guc_irq_handler(struct xe_guc *guc, const u16 iir); void xe_guc_sanitize(struct xe_guc *guc); -void xe_guc_print_info(struct xe_guc *guc, struct drm_printer *p); +int xe_guc_print_info(struct xe_guc *guc, struct drm_printer *p); int xe_guc_reset_prepare(struct xe_guc *guc); void xe_guc_reset_wait(struct xe_guc *guc); void xe_guc_stop_prepare(struct xe_guc *guc); diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c index 58e0b0294a5bcf..0e2bece1d8b83b 100644 --- a/drivers/gpu/drm/xe/xe_guc_ads.c +++ b/drivers/gpu/drm/xe/xe_guc_ads.c @@ -979,16 +979,17 @@ static int guc_ads_action_update_policies(struct xe_guc_ads *ads, u32 policy_off /** * xe_guc_ads_scheduler_policy_toggle_reset - Toggle reset policy * @ads: Additional data structures object + * @enable_engine_reset: true to enable engine resets, false otherwise * - * This function update the GuC's engine reset policy based on wedged.mode. + * This function update the GuC's engine reset policy. * * Return: 0 on success, and negative error code otherwise. */ -int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads) +int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads, + bool enable_engine_reset) { struct guc_policies *policies; struct xe_guc *guc = ads_to_guc(ads); - struct xe_device *xe = ads_to_xe(ads); CLASS(xe_guc_buf, buf)(&guc->buf, sizeof(*policies)); if (!xe_guc_buf_is_valid(buf)) @@ -1000,10 +1001,11 @@ int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads) policies->dpc_promote_time = ads_blob_read(ads, policies.dpc_promote_time); policies->max_num_work_items = ads_blob_read(ads, policies.max_num_work_items); policies->is_valid = 1; - if (xe->wedged.mode == 2) - policies->global_flags |= GLOBAL_POLICY_DISABLE_ENGINE_RESET; - else + + if (enable_engine_reset) policies->global_flags &= ~GLOBAL_POLICY_DISABLE_ENGINE_RESET; + else + policies->global_flags |= GLOBAL_POLICY_DISABLE_ENGINE_RESET; return guc_ads_action_update_policies(ads, xe_guc_buf_flush(buf)); } diff --git a/drivers/gpu/drm/xe/xe_guc_ads.h b/drivers/gpu/drm/xe/xe_guc_ads.h index 2e6674c760ff91..7a39f361cb17d7 100644 --- a/drivers/gpu/drm/xe/xe_guc_ads.h +++ b/drivers/gpu/drm/xe/xe_guc_ads.h @@ -6,6 +6,8 @@ #ifndef _XE_GUC_ADS_H_ #define _XE_GUC_ADS_H_ +#include + struct xe_guc_ads; int xe_guc_ads_init(struct xe_guc_ads *ads); @@ -13,6 +15,7 @@ int xe_guc_ads_init_post_hwconfig(struct xe_guc_ads *ads); void xe_guc_ads_populate(struct xe_guc_ads *ads); void xe_guc_ads_populate_minimal(struct xe_guc_ads *ads); void xe_guc_ads_populate_post_load(struct xe_guc_ads *ads); -int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads); +int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads, + bool enable_engine_reset); #endif diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index b7afe8e983cb79..3aac1a7aa2e7b2 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -106,7 +106,9 @@ static void g2h_fence_cancel(struct g2h_fence *g2h_fence) { g2h_fence->cancel = true; g2h_fence->fail = true; - g2h_fence->done = true; + + /* WRITE_ONCE pairs with READ_ONCEs in guc_ct_send_recv. */ + WRITE_ONCE(g2h_fence->done, true); } static bool g2h_fence_needs_alloc(struct g2h_fence *g2h_fence) @@ -1128,10 +1130,13 @@ static int guc_ct_send_recv(struct xe_guc_ct *ct, const u32 *action, u32 len, return ret; } - ret = wait_event_timeout(ct->g2h_fence_wq, g2h_fence.done, HZ); + /* READ_ONCEs pairs with WRITE_ONCEs in parse_g2h_response + * and g2h_fence_cancel. + */ + ret = wait_event_timeout(ct->g2h_fence_wq, READ_ONCE(g2h_fence.done), HZ); if (!ret) { LNL_FLUSH_WORK(&ct->g2h_worker); - if (g2h_fence.done) { + if (READ_ONCE(g2h_fence.done)) { xe_gt_warn(gt, "G2H fence %u, action %04x, done\n", g2h_fence.seqno, action[0]); ret = 1; @@ -1375,7 +1380,8 @@ static int parse_g2h_response(struct xe_guc_ct *ct, u32 *msg, u32 len) g2h_release_space(ct, GUC_CTB_HXG_MSG_MAX_LEN); - g2h_fence->done = true; + /* WRITE_ONCE pairs with READ_ONCEs in guc_ct_send_recv. */ + WRITE_ONCE(g2h_fence->done, true); smp_mb(); wake_up_all(&ct->g2h_fence_wq); diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c index 53fdf59524c41a..a3e9796e6430f7 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc.c +++ b/drivers/gpu/drm/xe/xe_guc_pc.c @@ -1231,6 +1231,36 @@ int xe_guc_pc_set_power_profile(struct xe_guc_pc *pc, const char *buf) return ret; } +static int pc_action_set_dcc(struct xe_guc_pc *pc, bool enable) +{ + int ret; + + ret = pc_action_set_param(pc, + SLPC_PARAM_TASK_ENABLE_DCC, + enable); + if (!ret) + return pc_action_set_param(pc, + SLPC_PARAM_TASK_DISABLE_DCC, + !enable); + else + return ret; +} + +static int pc_modify_defaults(struct xe_guc_pc *pc) +{ + struct xe_device *xe = pc_to_xe(pc); + struct xe_gt *gt = pc_to_gt(pc); + int ret = 0; + + if (xe->info.platform == XE_PANTHERLAKE) { + ret = pc_action_set_dcc(pc, false); + if (unlikely(ret)) + xe_gt_err(gt, "Failed to modify DCC default: %pe\n", ERR_PTR(ret)); + } + + return ret; +} + /** * xe_guc_pc_start - Start GuC's Power Conservation component * @pc: Xe_GuC_PC instance @@ -1288,6 +1318,10 @@ int xe_guc_pc_start(struct xe_guc_pc *pc) ktime_ms_delta(ktime_get(), earlier)); } + ret = pc_modify_defaults(pc); + if (ret) + return ret; + ret = pc_init_freqs(pc); if (ret) goto out; diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 94ed8159496f10..474789bf6506fa 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -670,6 +670,24 @@ static u32 wq_space_until_wrap(struct xe_exec_queue *q) return (WQ_SIZE - q->guc->wqi_tail); } +static inline void relaxed_ms_sleep(unsigned int delay_ms) +{ + unsigned long min_us, max_us; + + if (!delay_ms) + return; + + if (delay_ms > 20) { + msleep(delay_ms); + return; + } + + min_us = mul_u32_u32(delay_ms, 1000); + max_us = min_us + 500; + + usleep_range(min_us, max_us); +} + static int wq_wait_for_space(struct xe_exec_queue *q, u32 wqi_size) { struct xe_guc *guc = exec_queue_to_guc(q); @@ -1559,7 +1577,7 @@ static void __guc_exec_queue_process_msg_suspend(struct xe_sched_msg *msg) since_resume_ms; if (wait_ms > 0 && q->guc->resume_time) - msleep(wait_ms); + relaxed_ms_sleep(wait_ms); set_exec_queue_suspended(q); disable_scheduling(q, false); diff --git a/drivers/gpu/drm/xe/xe_heci_gsc.c b/drivers/gpu/drm/xe/xe_heci_gsc.c index a415ca48879140..32d509b1139153 100644 --- a/drivers/gpu/drm/xe/xe_heci_gsc.c +++ b/drivers/gpu/drm/xe/xe_heci_gsc.c @@ -221,7 +221,7 @@ void xe_heci_gsc_irq_handler(struct xe_device *xe, u32 iir) if (xe->heci_gsc.irq < 0) return; - ret = generic_handle_irq(xe->heci_gsc.irq); + ret = generic_handle_irq_safe(xe->heci_gsc.irq); if (ret) drm_err_ratelimited(&xe->drm, "error handling GSC irq: %d\n", ret); } @@ -241,7 +241,7 @@ void xe_heci_csc_irq_handler(struct xe_device *xe, u32 iir) if (xe->heci_gsc.irq < 0) return; - ret = generic_handle_irq(xe->heci_gsc.irq); + ret = generic_handle_irq_safe(xe->heci_gsc.irq); if (ret) drm_err_ratelimited(&xe->drm, "error handling GSC irq: %d\n", ret); } diff --git a/drivers/gpu/drm/xe/xe_late_bind_fw_types.h b/drivers/gpu/drm/xe/xe_late_bind_fw_types.h index 0f5da89ce98b8a..2a8a985c37e71a 100644 --- a/drivers/gpu/drm/xe/xe_late_bind_fw_types.h +++ b/drivers/gpu/drm/xe/xe_late_bind_fw_types.h @@ -15,10 +15,12 @@ #define XE_LB_MAX_PAYLOAD_SIZE SZ_4K /** - * xe_late_bind_fw_id - enum to determine late binding fw index + * enum xe_late_bind_fw_id - enum to determine late binding fw index */ enum xe_late_bind_fw_id { + /** @XE_LB_FW_FAN_CONTROL: Fan control */ XE_LB_FW_FAN_CONTROL = 0, + /** @XE_LB_FW_MAX_ID: Number of IDs */ XE_LB_FW_MAX_ID }; diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index 47e9df7750725a..9f29dbe890f667 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -1050,6 +1050,9 @@ static ssize_t setup_utilization_wa(struct xe_lrc *lrc, { u32 *cmd = batch; + if (IS_SRIOV_VF(gt_to_xe(lrc->gt))) + return 0; + if (xe_gt_WARN_ON(lrc->gt, max_len < 12)) return -ENOSPC; @@ -1182,7 +1185,7 @@ static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc, return -ENOSPC; *cmd++ = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1); - *cmd++ = CS_DEBUG_MODE1(0).addr; + *cmd++ = CS_DEBUG_MODE2(0).addr; *cmd++ = _MASKED_BIT_ENABLE(INSTRUCTION_STATE_CACHE_INVALIDATE); return cmd - batch; diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index a36ce7dce8cc0e..b6905f35d6c81f 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -1813,6 +1813,7 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m, unsigned long sram_offset, struct drm_pagemap_addr *sram_addr, u64 vram_addr, + struct dma_fence *deps, const enum xe_migrate_copy_dir dir) { struct xe_gt *gt = m->tile->primary_gt; @@ -1890,6 +1891,14 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m, xe_sched_job_add_migrate_flush(job, MI_INVALIDATE_TLB); + if (deps && !dma_fence_is_signaled(deps)) { + dma_fence_get(deps); + err = drm_sched_job_add_dependency(&job->drm, deps); + if (err) + dma_fence_wait(deps, false); + err = 0; + } + mutex_lock(&m->job_mutex); xe_sched_job_arm(job); fence = dma_fence_get(&job->drm.s_fence->finished); @@ -1915,6 +1924,8 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m, * @npages: Number of pages to migrate. * @src_addr: Array of DMA information (source of migrate) * @dst_addr: Device physical address of VRAM (destination of migrate) + * @deps: struct dma_fence representing the dependencies that need + * to be signaled before migration. * * Copy from an array dma addresses to a VRAM device physical address * @@ -1924,10 +1935,11 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m, struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, unsigned long npages, struct drm_pagemap_addr *src_addr, - u64 dst_addr) + u64 dst_addr, + struct dma_fence *deps) { return xe_migrate_vram(m, npages * PAGE_SIZE, 0, src_addr, dst_addr, - XE_MIGRATE_COPY_TO_VRAM); + deps, XE_MIGRATE_COPY_TO_VRAM); } /** @@ -1936,6 +1948,8 @@ struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, * @npages: Number of pages to migrate. * @src_addr: Device physical address of VRAM (source of migrate) * @dst_addr: Array of DMA information (destination of migrate) + * @deps: struct dma_fence representing the dependencies that need + * to be signaled before migration. * * Copy from a VRAM device physical address to an array dma addresses * @@ -1945,10 +1959,11 @@ struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, struct dma_fence *xe_migrate_from_vram(struct xe_migrate *m, unsigned long npages, u64 src_addr, - struct drm_pagemap_addr *dst_addr) + struct drm_pagemap_addr *dst_addr, + struct dma_fence *deps) { return xe_migrate_vram(m, npages * PAGE_SIZE, 0, dst_addr, src_addr, - XE_MIGRATE_COPY_TO_SRAM); + deps, XE_MIGRATE_COPY_TO_SRAM); } static void xe_migrate_dma_unmap(struct xe_device *xe, @@ -2121,7 +2136,7 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, __fence = xe_migrate_vram(m, current_bytes, (unsigned long)buf & ~PAGE_MASK, &pagemap_addr[current_page], - vram_addr, write ? + vram_addr, NULL, write ? XE_MIGRATE_COPY_TO_VRAM : XE_MIGRATE_COPY_TO_SRAM); if (IS_ERR(__fence)) { @@ -2167,7 +2182,7 @@ void xe_migrate_job_lock(struct xe_migrate *m, struct xe_exec_queue *q) if (is_migrate) mutex_lock(&m->job_mutex); else - xe_vm_assert_held(q->vm); /* User queues VM's should be locked */ + xe_vm_assert_held(q->user_vm); /* User queues VM's should be locked */ } /** @@ -2185,7 +2200,7 @@ void xe_migrate_job_unlock(struct xe_migrate *m, struct xe_exec_queue *q) if (is_migrate) mutex_unlock(&m->job_mutex); else - xe_vm_assert_held(q->vm); /* User queues VM's should be locked */ + xe_vm_assert_held(q->user_vm); /* User queues VM's should be locked */ } #if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST) diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h index 4fad324b625356..bc55f650204b83 100644 --- a/drivers/gpu/drm/xe/xe_migrate.h +++ b/drivers/gpu/drm/xe/xe_migrate.h @@ -111,12 +111,14 @@ int xe_migrate_init(struct xe_migrate *m); struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, unsigned long npages, struct drm_pagemap_addr *src_addr, - u64 dst_addr); + u64 dst_addr, + struct dma_fence *deps); struct dma_fence *xe_migrate_from_vram(struct xe_migrate *m, unsigned long npages, u64 src_addr, - struct drm_pagemap_addr *dst_addr); + struct drm_pagemap_addr *dst_addr, + struct dma_fence *deps); struct dma_fence *xe_migrate_copy(struct xe_migrate *m, struct xe_bo *src_bo, diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c index ef6f3ea573a2cd..6752881af093ab 100644 --- a/drivers/gpu/drm/xe/xe_mmio.c +++ b/drivers/gpu/drm/xe/xe_mmio.c @@ -260,11 +260,11 @@ u64 xe_mmio_read64_2x32(struct xe_mmio *mmio, struct xe_reg reg) struct xe_reg reg_udw = { .addr = reg.addr + 0x4 }; u32 ldw, udw, oldudw, retries; - reg.addr = xe_mmio_adjusted_addr(mmio, reg.addr); - reg_udw.addr = xe_mmio_adjusted_addr(mmio, reg_udw.addr); - - /* we shouldn't adjust just one register address */ - xe_tile_assert(mmio->tile, reg_udw.addr == reg.addr + 0x4); + /* + * The two dwords of a 64-bit register can never straddle the offset + * adjustment cutoff. + */ + xe_tile_assert(mmio->tile, !in_range(mmio->adj_limit, reg.addr + 1, 7)); oldudw = xe_mmio_read32(mmio, reg_udw); for (retries = 5; retries; --retries) { diff --git a/drivers/gpu/drm/xe/xe_module.h b/drivers/gpu/drm/xe/xe_module.h index 5a3bfea8b7b4c4..b6684953927016 100644 --- a/drivers/gpu/drm/xe/xe_module.h +++ b/drivers/gpu/drm/xe/xe_module.h @@ -12,7 +12,7 @@ struct xe_modparam { bool force_execlist; bool probe_display; - u32 force_vram_bar_size; + int force_vram_bar_size; int guc_log_level; char *guc_firmware_path; char *huc_firmware_path; diff --git a/drivers/gpu/drm/xe/xe_nvm.c b/drivers/gpu/drm/xe/xe_nvm.c index 33f4ac82fc80ab..6da42b2b5e4673 100644 --- a/drivers/gpu/drm/xe/xe_nvm.c +++ b/drivers/gpu/drm/xe/xe_nvm.c @@ -83,6 +83,27 @@ static bool xe_nvm_writable_override(struct xe_device *xe) return writable_override; } +static void xe_nvm_fini(void *arg) +{ + struct xe_device *xe = arg; + struct intel_dg_nvm_dev *nvm = xe->nvm; + + if (!xe->info.has_gsc_nvm) + return; + + /* No access to internal NVM from VFs */ + if (IS_SRIOV_VF(xe)) + return; + + /* Nvm pointer should not be NULL here */ + if (WARN_ON(!nvm)) + return; + + auxiliary_device_delete(&nvm->aux_dev); + auxiliary_device_uninit(&nvm->aux_dev); + xe->nvm = NULL; +} + int xe_nvm_init(struct xe_device *xe) { struct pci_dev *pdev = to_pci_dev(xe->drm.dev); @@ -132,39 +153,17 @@ int xe_nvm_init(struct xe_device *xe) ret = auxiliary_device_init(aux_dev); if (ret) { drm_err(&xe->drm, "xe-nvm aux init failed %d\n", ret); - goto err; + kfree(nvm); + xe->nvm = NULL; + return ret; } ret = auxiliary_device_add(aux_dev); if (ret) { drm_err(&xe->drm, "xe-nvm aux add failed %d\n", ret); auxiliary_device_uninit(aux_dev); - goto err; + xe->nvm = NULL; + return ret; } - return 0; - -err: - kfree(nvm); - xe->nvm = NULL; - return ret; -} - -void xe_nvm_fini(struct xe_device *xe) -{ - struct intel_dg_nvm_dev *nvm = xe->nvm; - - if (!xe->info.has_gsc_nvm) - return; - - /* No access to internal NVM from VFs */ - if (IS_SRIOV_VF(xe)) - return; - - /* Nvm pointer should not be NULL here */ - if (WARN_ON(!nvm)) - return; - - auxiliary_device_delete(&nvm->aux_dev); - auxiliary_device_uninit(&nvm->aux_dev); - xe->nvm = NULL; + return devm_add_action_or_reset(xe->drm.dev, xe_nvm_fini, xe); } diff --git a/drivers/gpu/drm/xe/xe_nvm.h b/drivers/gpu/drm/xe/xe_nvm.h index 7f3d5f57bed088..fd3467ad35a4d9 100644 --- a/drivers/gpu/drm/xe/xe_nvm.h +++ b/drivers/gpu/drm/xe/xe_nvm.h @@ -10,6 +10,4 @@ struct xe_device; int xe_nvm_init(struct xe_device *xe); -void xe_nvm_fini(struct xe_device *xe); - #endif diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index 125698a9ecf1c4..7fbce93f07193f 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -1104,11 +1104,12 @@ static int xe_oa_enable_metric_set(struct xe_oa_stream *stream) oag_buf_size_select(stream) | oag_configure_mmio_trigger(stream, true)); - xe_mmio_write32(mmio, __oa_regs(stream)->oa_ctx_ctrl, stream->periodic ? - (OAG_OAGLBCTXCTRL_COUNTER_RESUME | + xe_mmio_write32(mmio, __oa_regs(stream)->oa_ctx_ctrl, + OAG_OAGLBCTXCTRL_COUNTER_RESUME | + (stream->periodic ? OAG_OAGLBCTXCTRL_TIMER_ENABLE | REG_FIELD_PREP(OAG_OAGLBCTXCTRL_TIMER_PERIOD_MASK, - stream->period_exponent)) : 0); + stream->period_exponent) : 0)); /* * Initialize Super Queue Internal Cnt Register @@ -1253,6 +1254,9 @@ static int xe_oa_set_no_preempt(struct xe_oa *oa, u64 value, static int xe_oa_set_prop_num_syncs(struct xe_oa *oa, u64 value, struct xe_oa_open_param *param) { + if (XE_IOCTL_DBG(oa->xe, value > DRM_XE_MAX_SYNCS)) + return -EINVAL; + param->num_syncs = value; return 0; } @@ -1342,7 +1346,7 @@ static int xe_oa_user_ext_set_property(struct xe_oa *oa, enum xe_oa_user_extn_fr ARRAY_SIZE(xe_oa_set_property_funcs_config)); if (XE_IOCTL_DBG(oa->xe, ext.property >= ARRAY_SIZE(xe_oa_set_property_funcs_open)) || - XE_IOCTL_DBG(oa->xe, ext.pad)) + XE_IOCTL_DBG(oa->xe, !ext.property) || XE_IOCTL_DBG(oa->xe, ext.pad)) return -EINVAL; idx = array_index_nospec(ext.property, ARRAY_SIZE(xe_oa_set_property_funcs_open)); @@ -2403,11 +2407,13 @@ int xe_oa_add_config_ioctl(struct drm_device *dev, u64 data, struct drm_file *fi goto sysfs_err; } - mutex_unlock(&oa->metrics_lock); + id = oa_config->id; - drm_dbg(&oa->xe->drm, "Added config %s id=%i\n", oa_config->uuid, oa_config->id); + drm_dbg(&oa->xe->drm, "Added config %s id=%i\n", oa_config->uuid, id); + + mutex_unlock(&oa->metrics_lock); - return oa_config->id; + return id; sysfs_err: mutex_unlock(&oa->metrics_lock); diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index 2c5a44377994b3..a74e800846ffac 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -300,9 +301,15 @@ ALLOW_ERROR_INJECTION(xe_pm_init_early, ERRNO); /* See xe_pci_probe() */ static u32 vram_threshold_value(struct xe_device *xe) { - /* FIXME: D3Cold temporarily disabled by default on BMG */ - if (xe->info.platform == XE_BATTLEMAGE) - return 0; + if (xe->info.platform == XE_BATTLEMAGE) { + const char *product_name; + + product_name = dmi_get_system_info(DMI_PRODUCT_NAME); + if (product_name && strstr(product_name, "NUC13RNG")) { + drm_warn(&xe->drm, "BMG + D3Cold not supported on this platform\n"); + return 0; + } + } return DEFAULT_VRAM_THRESHOLD; } @@ -660,6 +667,13 @@ static void xe_pm_runtime_lockdep_prime(void) /** * xe_pm_runtime_get - Get a runtime_pm reference and resume synchronously * @xe: xe device instance + * + * When possible, scope-based runtime PM (through guard(xe_pm_runtime)) is + * be preferred over direct usage of this function. Manual get/put handling + * should only be used when the function contains goto-based logic which + * can break scope-based handling, or when the lifetime of the runtime PM + * reference does not match a specific scope (e.g., runtime PM obtained in one + * function and released in a different one). */ void xe_pm_runtime_get(struct xe_device *xe) { @@ -692,6 +706,13 @@ void xe_pm_runtime_put(struct xe_device *xe) * xe_pm_runtime_get_ioctl - Get a runtime_pm reference before ioctl * @xe: xe device instance * + * When possible, scope-based runtime PM (through + * ACQUIRE(xe_pm_runtime_ioctl, ...)) is be preferred over direct usage of this + * function. Manual get/put handling should only be used when the function + * contains goto-based logic which can break scope-based handling, or when the + * lifetime of the runtime PM reference does not match a specific scope (e.g., + * runtime PM obtained in one function and released in a different one). + * * Returns: Any number greater than or equal to 0 for success, negative error * code otherwise. */ @@ -761,6 +782,13 @@ static bool xe_pm_suspending_or_resuming(struct xe_device *xe) * It will warn if not protected. * The reference should be put back after this function regardless, since it * will always bump the usage counter, regardless. + * + * When possible, scope-based runtime PM (through guard(xe_pm_runtime_noresume)) + * is be preferred over direct usage of this function. Manual get/put handling + * should only be used when the function contains goto-based logic which can + * break scope-based handling, or when the lifetime of the runtime PM reference + * does not match a specific scope (e.g., runtime PM obtained in one function + * and released in a different one). */ void xe_pm_runtime_get_noresume(struct xe_device *xe) { diff --git a/drivers/gpu/drm/xe/xe_pm.h b/drivers/gpu/drm/xe/xe_pm.h index 59678b310e55f1..e8005775be39e6 100644 --- a/drivers/gpu/drm/xe/xe_pm.h +++ b/drivers/gpu/drm/xe/xe_pm.h @@ -6,6 +6,7 @@ #ifndef _XE_PM_H_ #define _XE_PM_H_ +#include #include #define DEFAULT_VRAM_THRESHOLD 300 /* in MB */ @@ -35,4 +36,20 @@ bool xe_rpm_reclaim_safe(const struct xe_device *xe); struct task_struct *xe_pm_read_callback_task(struct xe_device *xe); int xe_pm_module_init(void); +static inline void __xe_pm_runtime_noop(struct xe_device *xe) {} + +DEFINE_GUARD(xe_pm_runtime, struct xe_device *, + xe_pm_runtime_get(_T), xe_pm_runtime_put(_T)) +DEFINE_GUARD(xe_pm_runtime_noresume, struct xe_device *, + xe_pm_runtime_get_noresume(_T), xe_pm_runtime_put(_T)) +DEFINE_GUARD_COND(xe_pm_runtime, _ioctl, xe_pm_runtime_get_ioctl(_T), _RET >= 0) + +/* + * Used when a function needs to release runtime PM in all possible cases + * and error paths, but the wakeref was already acquired by a different + * function (i.e., get() has already happened so only a put() is needed). + */ +DEFINE_GUARD(xe_pm_runtime_release_only, struct xe_device *, + __xe_pm_runtime_noop(_T), xe_pm_runtime_put(_T)); + #endif diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c index 2e9ff33ed2fe2a..856089f64c341d 100644 --- a/drivers/gpu/drm/xe/xe_query.c +++ b/drivers/gpu/drm/xe/xe_query.c @@ -491,7 +491,7 @@ static int copy_mask(void __user **ptr, if (copy_to_user(*ptr, topo, sizeof(*topo))) return -EFAULT; - *ptr += sizeof(topo); + *ptr += sizeof(*topo); if (copy_to_user(*ptr, mask, mask_size)) return -EFAULT; diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c index 8dec616c37c983..739a3eb180b53c 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c @@ -276,7 +276,7 @@ int xe_sriov_vf_ccs_init(struct xe_device *xe) flags = EXEC_QUEUE_FLAG_KERNEL | EXEC_QUEUE_FLAG_PERMANENT | EXEC_QUEUE_FLAG_MIGRATE; - q = xe_exec_queue_create_bind(xe, tile, flags, 0); + q = xe_exec_queue_create_bind(xe, tile, NULL, flags, 0); if (IS_ERR(q)) { err = PTR_ERR(q); goto err_ret; diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c index 129e7818565c82..65452c20609ed8 100644 --- a/drivers/gpu/drm/xe/xe_svm.c +++ b/drivers/gpu/drm/xe/xe_svm.c @@ -477,7 +477,8 @@ static void xe_svm_copy_us_stats_incr(struct xe_gt *gt, static int xe_svm_copy(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages, const enum xe_svm_copy_dir dir) + unsigned long npages, const enum xe_svm_copy_dir dir, + struct dma_fence *pre_migrate_fence) { struct xe_vram_region *vr = NULL; struct xe_gt *gt = NULL; @@ -566,7 +567,8 @@ static int xe_svm_copy(struct page **pages, __fence = xe_migrate_from_vram(vr->migrate, i - pos + incr, vram_addr, - &pagemap_addr[pos]); + &pagemap_addr[pos], + pre_migrate_fence); } else { vm_dbg(&xe->drm, "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%ld", @@ -575,13 +577,14 @@ static int xe_svm_copy(struct page **pages, __fence = xe_migrate_to_vram(vr->migrate, i - pos + incr, &pagemap_addr[pos], - vram_addr); + vram_addr, + pre_migrate_fence); } if (IS_ERR(__fence)) { err = PTR_ERR(__fence); goto err_out; } - + pre_migrate_fence = NULL; dma_fence_put(fence); fence = __fence; } @@ -604,20 +607,22 @@ static int xe_svm_copy(struct page **pages, vram_addr, (u64)pagemap_addr[pos].addr, 1); __fence = xe_migrate_from_vram(vr->migrate, 1, vram_addr, - &pagemap_addr[pos]); + &pagemap_addr[pos], + pre_migrate_fence); } else { vm_dbg(&xe->drm, "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%d", (u64)pagemap_addr[pos].addr, vram_addr, 1); __fence = xe_migrate_to_vram(vr->migrate, 1, &pagemap_addr[pos], - vram_addr); + vram_addr, + pre_migrate_fence); } if (IS_ERR(__fence)) { err = PTR_ERR(__fence); goto err_out; } - + pre_migrate_fence = NULL; dma_fence_put(fence); fence = __fence; } @@ -630,6 +635,8 @@ static int xe_svm_copy(struct page **pages, dma_fence_wait(fence, false); dma_fence_put(fence); } + if (pre_migrate_fence) + dma_fence_wait(pre_migrate_fence, false); /* * XXX: We can't derive the GT here (or anywhere in this functions, but @@ -646,16 +653,20 @@ static int xe_svm_copy(struct page **pages, static int xe_svm_copy_to_devmem(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages) + unsigned long npages, + struct dma_fence *pre_migrate_fence) { - return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_VRAM); + return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_VRAM, + pre_migrate_fence); } static int xe_svm_copy_to_ram(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages) + unsigned long npages, + struct dma_fence *pre_migrate_fence) { - return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_SRAM); + return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_SRAM, + pre_migrate_fence); } static struct xe_bo *to_xe_bo(struct drm_pagemap_devmem *devmem_allocation) @@ -668,6 +679,7 @@ static void xe_svm_devmem_release(struct drm_pagemap_devmem *devmem_allocation) struct xe_bo *bo = to_xe_bo(devmem_allocation); struct xe_device *xe = xe_bo_device(bo); + dma_fence_put(devmem_allocation->pre_migrate_fence); xe_bo_put_async(bo); xe_pm_runtime_put(xe); } @@ -862,6 +874,7 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap, unsigned long timeslice_ms) { struct xe_vram_region *vr = container_of(dpagemap, typeof(*vr), dpagemap); + struct dma_fence *pre_migrate_fence = NULL; struct xe_device *xe = vr->xe; struct device *dev = xe->drm.dev; struct drm_buddy_block *block; @@ -888,8 +901,20 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap, break; } + /* Ensure that any clearing or async eviction will complete before migration. */ + if (!dma_resv_test_signaled(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL)) { + err = dma_resv_get_singleton(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL, + &pre_migrate_fence); + if (err) + dma_resv_wait_timeout(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL, + false, MAX_SCHEDULE_TIMEOUT); + else if (pre_migrate_fence) + dma_fence_enable_sw_signaling(pre_migrate_fence); + } + drm_pagemap_devmem_init(&bo->devmem_allocation, dev, mm, - &dpagemap_devmem_ops, dpagemap, end - start); + &dpagemap_devmem_ops, dpagemap, end - start, + pre_migrate_fence); blocks = &to_xe_ttm_vram_mgr_resource(bo->ttm.resource)->blocks; list_for_each_entry(block, blocks, link) @@ -942,7 +967,7 @@ bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range, struct xe_vm xe_assert(vm->xe, IS_DGFX(vm->xe)); if (xe_svm_range_in_vram(range)) { - drm_info(&vm->xe->drm, "Range is already in VRAM\n"); + drm_dbg(&vm->xe->drm, "Range is already in VRAM\n"); return false; } diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h index 0955d2ac8d7448..fa757dd07954d9 100644 --- a/drivers/gpu/drm/xe/xe_svm.h +++ b/drivers/gpu/drm/xe/xe_svm.h @@ -214,7 +214,7 @@ int xe_svm_init(struct xe_vm *vm) { #if IS_ENABLED(CONFIG_DRM_GPUSVM) return drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM (simple)", &vm->xe->drm, - NULL, NULL, 0, 0, 0, NULL, NULL, 0); + NULL, 0, 0, 0, NULL, NULL, 0); #else return 0; #endif diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index cdd1dc540a59e6..145cd9ffa36b3f 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1481,7 +1481,10 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) INIT_WORK(&vm->destroy_work, vm_destroy_work_func); INIT_LIST_HEAD(&vm->preempt.exec_queues); - vm->preempt.min_run_period_ms = 10; /* FIXME: Wire up to uAPI */ + if (flags & XE_VM_FLAG_FAULT_MODE) + vm->preempt.min_run_period_ms = 0; + else + vm->preempt.min_run_period_ms = 5; for_each_tile(tile, xe, id) xe_range_fence_tree_init(&vm->rftree[id]); @@ -1587,7 +1590,7 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) if (!vm->pt_root[id]) continue; - q = xe_exec_queue_create_bind(xe, tile, create_flags, 0); + q = xe_exec_queue_create_bind(xe, tile, vm, create_flags, 0); if (IS_ERR(q)) { err = PTR_ERR(q); goto err_close; @@ -3282,6 +3285,9 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm, if (XE_IOCTL_DBG(xe, args->extensions)) return -EINVAL; + if (XE_IOCTL_DBG(xe, args->num_syncs > DRM_XE_MAX_SYNCS)) + return -EINVAL; + if (args->num_binds > 1) { u64 __user *bind_user = u64_to_user_ptr(args->vector_of_binds); @@ -3530,6 +3536,11 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) } } + if (XE_IOCTL_DBG(xe, q && vm != q->user_vm)) { + err = -EINVAL; + goto put_exec_queue; + } + /* Ensure all UNMAPs visible */ xe_svm_flush(vm); diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h index ef8a5019574e6f..016f6786134cb2 100644 --- a/drivers/gpu/drm/xe/xe_vm.h +++ b/drivers/gpu/drm/xe/xe_vm.h @@ -379,7 +379,7 @@ static inline void xe_vm_set_validation_exec(struct xe_vm *vm, struct drm_exec * } /** - * xe_vm_set_validation_exec() - Accessor to read the drm_exec object + * xe_vm_validation_exec() - Accessor to read the drm_exec object * @vm: The vm we want to register a drm_exec object with. * * Return: The drm_exec object used to lock the vm's resv. The value diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index d6e2a0fdd4b359..fd5b5919c40206 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -268,7 +268,7 @@ struct xe_vm { * @min_run_period_ms: The minimum run period before preempting * an engine again */ - s64 min_run_period_ms; + unsigned int min_run_period_ms; /** @exec_queues: list of exec queues attached to this VM */ struct list_head exec_queues; /** @num_exec_queues: number exec queues attached to this VM */ diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c index 3cf30718b20039..2a2e9f2c091631 100644 --- a/drivers/gpu/drm/xe/xe_wa.c +++ b/drivers/gpu/drm/xe/xe_wa.c @@ -270,14 +270,6 @@ static const struct xe_rtp_entry_sr gt_was[] = { XE_RTP_ACTIONS(SET(VDBOX_CGCTL3F1C(0), MFXPIPE_CLKGATE_DIS)), XE_RTP_ENTRY_FLAG(FOREACH_ENGINE), }, - { XE_RTP_NAME("14020316580"), - XE_RTP_RULES(MEDIA_VERSION(1301)), - XE_RTP_ACTIONS(CLR(POWERGATE_ENABLE, - VDN_HCP_POWERGATE_ENABLE(0) | - VDN_MFXVDENC_POWERGATE_ENABLE(0) | - VDN_HCP_POWERGATE_ENABLE(2) | - VDN_MFXVDENC_POWERGATE_ENABLE(2))), - }, { XE_RTP_NAME("14019449301"), XE_RTP_RULES(MEDIA_VERSION(1301), ENGINE_CLASS(VIDEO_DECODE)), XE_RTP_ACTIONS(SET(VDBOX_CGCTL3F08(0), CG3DDISHRS_CLKGATE_DIS)), @@ -575,16 +567,6 @@ static const struct xe_rtp_entry_sr engine_was[] = { FUNC(xe_rtp_match_first_render_or_compute)), XE_RTP_ACTIONS(SET(ROW_CHICKEN, EARLY_EOT_DIS)) }, - { XE_RTP_NAME("14019988906"), - XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, 2002), - FUNC(xe_rtp_match_first_render_or_compute)), - XE_RTP_ACTIONS(SET(XEHP_PSS_CHICKEN, FLSH_IGNORES_PSD)) - }, - { XE_RTP_NAME("14019877138"), - XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, 2002), - FUNC(xe_rtp_match_first_render_or_compute)), - XE_RTP_ACTIONS(SET(XEHP_PSS_CHICKEN, FD_END_COLLECT)) - }, { XE_RTP_NAME("14020338487"), XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, 2002), FUNC(xe_rtp_match_first_render_or_compute)), @@ -881,6 +863,14 @@ static const struct xe_rtp_entry_sr lrc_was[] = { XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)), XE_RTP_ACTIONS(SET(WM_CHICKEN3, HIZ_PLANE_COMPRESSION_DIS)) }, + { XE_RTP_NAME("14019988906"), + XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, 2002), ENGINE_CLASS(RENDER)), + XE_RTP_ACTIONS(SET(XEHP_PSS_CHICKEN, FLSH_IGNORES_PSD)) + }, + { XE_RTP_NAME("14019877138"), + XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, 2002), ENGINE_CLASS(RENDER)), + XE_RTP_ACTIONS(SET(XEHP_PSS_CHICKEN, FD_END_COLLECT)) + }, { XE_RTP_NAME("14021490052"), XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)), XE_RTP_ACTIONS(SET(FF_MODE, diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules index f3a6d5d239cecb..1d32fa1c3b2d75 100644 --- a/drivers/gpu/drm/xe/xe_wa_oob.rules +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules @@ -81,3 +81,4 @@ 15015404425_disable PLATFORM(PANTHERLAKE), MEDIA_STEP(B0, FOREVER) 16026007364 MEDIA_VERSION(3000) +14020316580 MEDIA_VERSION(1301) diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c index f63d14a57a1d95..acc7d82e0585e8 100644 --- a/drivers/gpu/host1x/syncpt.c +++ b/drivers/gpu/host1x/syncpt.c @@ -345,8 +345,6 @@ static void syncpt_release(struct kref *ref) sp->locked = false; - mutex_lock(&sp->host->syncpt_mutex); - host1x_syncpt_base_free(sp->base); kfree(sp->name); sp->base = NULL; @@ -369,7 +367,7 @@ void host1x_syncpt_put(struct host1x_syncpt *sp) if (!sp) return; - kref_put(&sp->ref, syncpt_release); + kref_put_mutex(&sp->ref, syncpt_release, &sp->host->syncpt_mutex); } EXPORT_SYMBOL(host1x_syncpt_put); diff --git a/drivers/gpu/nova-core/Kconfig b/drivers/gpu/nova-core/Kconfig index 20d3e6d0d796ef..527920f9c4d39c 100644 --- a/drivers/gpu/nova-core/Kconfig +++ b/drivers/gpu/nova-core/Kconfig @@ -3,7 +3,7 @@ config NOVA_CORE depends on 64BIT depends on PCI depends on RUST - depends on RUST_FW_LOADER_ABSTRACTIONS + select RUST_FW_LOADER_ABSTRACTIONS select AUXILIARY_BUS default n help diff --git a/drivers/gpu/nova-core/firmware/gsp.rs b/drivers/gpu/nova-core/firmware/gsp.rs index 9b70095434c61f..6b0761460a57d3 100644 --- a/drivers/gpu/nova-core/firmware/gsp.rs +++ b/drivers/gpu/nova-core/firmware/gsp.rs @@ -202,10 +202,10 @@ impl GspFirmware { let mut level0_data = kvec![0u8; GSP_PAGE_SIZE]?; // Fill level 1 page entry. - #[allow(clippy::useless_conversion)] - let level1_entry = u64::from(level1.iter().next().unwrap().dma_address()); - let dst = &mut level0_data[..size_of_val(&level1_entry)]; - dst.copy_from_slice(&level1_entry.to_le_bytes()); + let level1_entry = level1.iter().next().ok_or(EINVAL)?; + let level1_entry_addr = level1_entry.dma_address(); + let dst = &mut level0_data[..size_of_val(&level1_entry_addr)]; + dst.copy_from_slice(&level1_entry_addr.to_le_bytes()); // Turn the level0 page table into a [`DmaObject`]. DmaObject::from_data(dev, &level0_data)? diff --git a/drivers/greybus/gb-beagleplay.c b/drivers/greybus/gb-beagleplay.c index 9610f878da1b68..87186f891a6acb 100644 --- a/drivers/greybus/gb-beagleplay.c +++ b/drivers/greybus/gb-beagleplay.c @@ -644,8 +644,8 @@ static int cc1352_bootloader_wait_for_ack(struct gb_beagleplay *bg) ret = wait_for_completion_timeout( &bg->fwl_ack_com, msecs_to_jiffies(CC1352_BOOTLOADER_TIMEOUT)); - if (ret < 0) - return dev_err_probe(&bg->sd->dev, ret, + if (!ret) + return dev_err_probe(&bg->sd->dev, -ETIMEDOUT, "Failed to acquire ack semaphore"); switch (READ_ONCE(bg->fwl_ack)) { @@ -683,8 +683,8 @@ static int cc1352_bootloader_get_status(struct gb_beagleplay *bg) ret = wait_for_completion_timeout( &bg->fwl_cmd_response_com, msecs_to_jiffies(CC1352_BOOTLOADER_TIMEOUT)); - if (ret < 0) - return dev_err_probe(&bg->sd->dev, ret, + if (!ret) + return dev_err_probe(&bg->sd->dev, -ETIMEDOUT, "Failed to acquire last status semaphore"); switch (READ_ONCE(bg->fwl_cmd_response)) { @@ -768,8 +768,8 @@ static int cc1352_bootloader_crc32(struct gb_beagleplay *bg, u32 *crc32) ret = wait_for_completion_timeout( &bg->fwl_cmd_response_com, msecs_to_jiffies(CC1352_BOOTLOADER_TIMEOUT)); - if (ret < 0) - return dev_err_probe(&bg->sd->dev, ret, + if (!ret) + return dev_err_probe(&bg->sd->dev, -ETIMEDOUT, "Failed to acquire last status semaphore"); *crc32 = READ_ONCE(bg->fwl_cmd_response); diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 04420a713be085..988e06c80fb28d 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -730,7 +730,8 @@ config HID_MAGICMOUSE Support for the Apple Magic Mouse/Trackpad multi-touch. Say Y here if you want support for the multi-touch features of the - Apple Wireless "Magic" Mouse and the Apple Wireless "Magic" Trackpad. + Apple Wireless "Magic" Mouse, the Apple Wireless "Magic" Trackpad and + force touch Trackpads in Macbooks starting from 2015. config HID_MALTRON tristate "Maltron L90 keyboard" @@ -1445,4 +1446,8 @@ endif # HID source "drivers/hid/usbhid/Kconfig" +source "drivers/hid/spi-hid/Kconfig" + +source "drivers/hid/dockchannel-hid/Kconfig" + endif # HID_SUPPORT diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile index 361a7daedeb854..2ed4942821539f 100644 --- a/drivers/hid/Makefile +++ b/drivers/hid/Makefile @@ -173,6 +173,12 @@ obj-$(CONFIG_INTEL_ISH_HID) += intel-ish-hid/ obj-$(CONFIG_AMD_SFH_HID) += amd-sfh-hid/ +obj-$(CONFIG_HID_DOCKCHANNEL) += dockchannel-hid/ + +obj-$(CONFIG_SPI_HID_APPLE_CORE) += spi-hid/ + +obj-$(CONFIG_HID_DOCKCHANNEL) += dockchannel-hid/ + obj-$(CONFIG_SURFACE_HID_CORE) += surface-hid/ obj-$(CONFIG_INTEL_THC_HID) += intel-thc-hid/ diff --git a/drivers/hid/dockchannel-hid/Kconfig b/drivers/hid/dockchannel-hid/Kconfig new file mode 100644 index 00000000000000..254961ad15e19c --- /dev/null +++ b/drivers/hid/dockchannel-hid/Kconfig @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0-only OR MIT +menu "DockChannel HID support" + depends on APPLE_DOCKCHANNEL + +config HID_DOCKCHANNEL + tristate "HID over DockChannel transport layer for Apple Silicon SoCs" + depends on APPLE_DOCKCHANNEL && INPUT && OF && HID + help + Say Y here if you use an M2 or later Apple Silicon based laptop. + The keyboard and touchpad are HID based devices connected via the + proprietary DockChannel interface. + +endmenu diff --git a/drivers/hid/dockchannel-hid/Makefile b/drivers/hid/dockchannel-hid/Makefile new file mode 100644 index 00000000000000..7dba766b047fcc --- /dev/null +++ b/drivers/hid/dockchannel-hid/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-only OR MIT +# +# Makefile for DockChannel HID transport drivers +# + +obj-$(CONFIG_HID_DOCKCHANNEL) += dockchannel-hid.o diff --git a/drivers/hid/dockchannel-hid/dockchannel-hid.c b/drivers/hid/dockchannel-hid/dockchannel-hid.c new file mode 100644 index 00000000000000..a712a724ded30b --- /dev/null +++ b/drivers/hid/dockchannel-hid/dockchannel-hid.c @@ -0,0 +1,1213 @@ +/* + * SPDX-License-Identifier: GPL-2.0 OR MIT + * + * Apple DockChannel HID transport driver + * + * Copyright The Asahi Linux Contributors + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "../hid-ids.h" + +#define COMMAND_TIMEOUT_MS 1000 +#define START_TIMEOUT_MS 2000 + +#define MAX_INTERFACES 16 + +/* Data + checksum */ +#define MAX_PKT_SIZE (0xffff + 4) + +#define DCHID_CHANNEL_CMD 0x11 +#define DCHID_CHANNEL_REPORT 0x12 + +struct dchid_hdr { + u8 hdr_len; + u8 channel; + u16 length; + u8 seq; + u8 iface; + u16 pad; +} __packed; + +#define IFACE_COMM 0 + +#define FLAGS_GROUP GENMASK(7, 6) +#define FLAGS_REQ GENMASK(5, 0) + +#define REQ_SET_REPORT 0 +#define REQ_GET_REPORT 1 + +struct dchid_subhdr { + u8 flags; + u8 unk; + u16 length; + u32 retcode; +} __packed; + +#define EVENT_GPIO_CMD 0xa0 +#define EVENT_INIT 0xf0 +#define EVENT_READY 0xf1 + +struct dchid_init_hdr { + u8 type; + u8 unk1; + u8 unk2; + u8 iface; + char name[16]; + u8 more_packets; + u8 unkpad; +} __packed; + +#define INIT_HID_DESCRIPTOR 0 +#define INIT_GPIO_REQUEST 1 +#define INIT_TERMINATOR 2 +#define INIT_PRODUCT_NAME 7 + +#define CMD_RESET_INTERFACE 0x40 +#define CMD_SEND_FIRMWARE 0x95 +#define CMD_ENABLE_INTERFACE 0xb4 +#define CMD_ACK_GPIO_CMD 0xa1 + +struct dchid_init_block_hdr { + u16 type; + u16 length; +} __packed; + +#define MAX_GPIO_NAME 32 + +struct dchid_gpio_request { + u16 unk; + u16 id; + char name[MAX_GPIO_NAME]; +} __packed; + +struct dchid_gpio_cmd { + u8 type; + u8 iface; + u8 gpio; + u8 unk; + u8 cmd; +} __packed; + +struct dchid_gpio_ack { + u8 type; + u32 retcode; + u8 cmd[]; +} __packed; + +#define STM_REPORT_ID 0x10 +#define STM_REPORT_SERIAL 0x11 +#define STM_REPORT_KEYBTYPE 0x14 + +struct dchid_stm_id { + u8 unk; + u16 vendor_id; + u16 product_id; + u16 version_number; + u8 unk2; + u8 unk3; + u8 keyboard_type; + u8 serial_length; + /* Serial follows, but we grab it with a different report. */ +} __packed; + +#define FW_MAGIC 0x46444948 +#define FW_VER 1 + +struct fw_header { + u32 magic; + u32 version; + u32 hdr_length; + u32 data_length; + u32 iface_offset; +} __packed; + +struct dchid_work { + struct work_struct work; + struct dchid_iface *iface; + + struct dchid_hdr hdr; + u8 data[]; +}; + +struct dchid_iface { + struct dockchannel_hid *dchid; + struct hid_device *hid; + struct workqueue_struct *wq; + + bool creating; + struct work_struct create_work; + + int index; + const char *name; + const struct device_node *of_node; + + uint8_t tx_seq; + bool deferred; + bool starting; + bool open; + struct completion ready; + + void *hid_desc; + size_t hid_desc_len; + + struct gpio_desc *gpio; + char gpio_name[MAX_GPIO_NAME]; + int gpio_id; + + struct mutex out_mutex; + u32 out_flags; + int out_report; + u32 retcode; + void *resp_buf; + size_t resp_size; + struct completion out_complete; + + u32 keyboard_layout_id; +}; + +struct dockchannel_hid { + struct device *dev; + struct dockchannel *dc; + struct device_link *helper_link; + + bool id_ready; + struct dchid_stm_id device_id; + char serial[64]; + + struct dchid_iface *comm; + struct dchid_iface *ifaces[MAX_INTERFACES]; + + u8 pkt_buf[MAX_PKT_SIZE]; + + /* Workqueue to asynchronously create HID devices */ + struct workqueue_struct *new_iface_wq; +}; + +static ssize_t apple_layout_id_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hid_device *hdev = to_hid_device(dev); + struct dchid_iface *iface = hdev->driver_data; + + return scnprintf(buf, PAGE_SIZE, "%d\n", iface->keyboard_layout_id); +} + +static DEVICE_ATTR_RO(apple_layout_id); + +static struct dchid_iface * +dchid_get_interface(struct dockchannel_hid *dchid, int index, const char *name) +{ + struct dchid_iface *iface; + + if (index >= MAX_INTERFACES) { + dev_err(dchid->dev, "Interface index %d out of range\n", index); + return NULL; + } + + if (dchid->ifaces[index]) + return dchid->ifaces[index]; + + iface = devm_kzalloc(dchid->dev, sizeof(struct dchid_iface), GFP_KERNEL); + if (!iface) + return NULL; + + iface->index = index; + iface->name = devm_kstrdup(dchid->dev, name, GFP_KERNEL); + iface->dchid = dchid; + iface->out_report= -1; + init_completion(&iface->out_complete); + init_completion(&iface->ready); + mutex_init(&iface->out_mutex); + iface->wq = alloc_ordered_workqueue("dchid-%s", WQ_MEM_RECLAIM, iface->name); + if (!iface->wq) + return NULL; + + /* Comm is not a HID subdevice */ + if (!strcmp(name, "comm")) { + dchid->ifaces[index] = iface; + return iface; + } + + iface->of_node = of_get_child_by_name(dchid->dev->of_node, name); + if (!iface->of_node) { + dev_warn(dchid->dev, "No OF node for subdevice %s, ignoring.", name); + return NULL; + } + + dchid->ifaces[index] = iface; + return iface; +} + +static u32 dchid_checksum(void *p, size_t length) +{ + u32 sum = 0; + + while (length >= 4) { + sum += get_unaligned_le32(p); + p += 4; + length -= 4; + } + + WARN_ON_ONCE(length); + return sum; +} + +static int dchid_send(struct dchid_iface *iface, u32 flags, void *msg, size_t size) +{ + u32 checksum = 0xffffffff; + size_t wsize = round_down(size, 4); + size_t tsize = size - wsize; + int ret; + struct { + struct dchid_hdr hdr; + struct dchid_subhdr sub; + } __packed h; + + memset(&h, 0, sizeof(h)); + h.hdr.hdr_len = sizeof(h.hdr); + h.hdr.channel = DCHID_CHANNEL_CMD; + h.hdr.length = round_up(size, 4) + sizeof(h.sub); + h.hdr.seq = iface->tx_seq; + h.hdr.iface = iface->index; + h.sub.flags = flags; + h.sub.length = size; + + ret = dockchannel_send(iface->dchid->dc, &h, sizeof(h)); + if (ret < 0) + return ret; + checksum -= dchid_checksum(&h, sizeof(h)); + + ret = dockchannel_send(iface->dchid->dc, msg, wsize); + if (ret < 0) + return ret; + checksum -= dchid_checksum(msg, wsize); + + if (tsize) { + u8 tail[4] = {0, 0, 0, 0}; + + memcpy(tail, msg + wsize, tsize); + ret = dockchannel_send(iface->dchid->dc, tail, sizeof(tail)); + if (ret < 0) + return ret; + checksum -= dchid_checksum(tail, sizeof(tail)); + } + + ret = dockchannel_send(iface->dchid->dc, &checksum, sizeof(checksum)); + if (ret < 0) + return ret; + + return 0; +} + +static int dchid_cmd(struct dchid_iface *iface, u32 type, u32 req, + void *data, size_t size, void *resp_buf, size_t resp_size) +{ + int ret; + int report_id = *(u8*)data; + + mutex_lock(&iface->out_mutex); + + WARN_ON(iface->out_report != -1); + iface->out_report = report_id; + iface->out_flags = FIELD_PREP(FLAGS_GROUP, type) | FIELD_PREP(FLAGS_REQ, req); + iface->resp_buf = resp_buf; + iface->resp_size = resp_size; + reinit_completion(&iface->out_complete); + + ret = dchid_send(iface, iface->out_flags, data, size); + if (ret < 0) + goto done; + + if (!wait_for_completion_timeout(&iface->out_complete, msecs_to_jiffies(COMMAND_TIMEOUT_MS))) { + dev_err(iface->dchid->dev, "output report 0x%x to iface %d (%s) timed out\n", + report_id, iface->index, iface->name); + ret = -ETIMEDOUT; + goto done; + } + + ret = iface->resp_size; + if (iface->retcode) { + dev_err(iface->dchid->dev, + "output report 0x%x to iface %d (%s) failed with err 0x%x\n", + report_id, iface->index, iface->name, iface->retcode); + ret = -EIO; + } + +done: + iface->tx_seq++; + iface->out_report = -1; + iface->out_flags = 0; + iface->resp_buf = NULL; + iface->resp_size = 0; + mutex_unlock(&iface->out_mutex); + return ret; +} + +static int dchid_comm_cmd(struct dockchannel_hid *dchid, void *cmd, size_t size) +{ + return dchid_cmd(dchid->comm, HID_FEATURE_REPORT, REQ_SET_REPORT, cmd, size, NULL, 0); +} + +static int dchid_enable_interface(struct dchid_iface *iface) +{ + u8 msg[] = { CMD_ENABLE_INTERFACE, iface->index }; + + return dchid_comm_cmd(iface->dchid, msg, sizeof(msg)); +} + +static int dchid_reset_interface(struct dchid_iface *iface, int state) +{ + u8 msg[] = { CMD_RESET_INTERFACE, 1, iface->index, state }; + + return dchid_comm_cmd(iface->dchid, msg, sizeof(msg)); +} + +static int dchid_send_firmware(struct dchid_iface *iface, void *firmware, size_t size) +{ + struct { + u8 cmd; + u8 unk1; + u8 unk2; + u8 iface; + u64 addr; + u32 size; + } __packed msg = { + .cmd = CMD_SEND_FIRMWARE, + .unk1 = 2, + .unk2 = 0, + .iface = iface->index, + .size = size, + }; + dma_addr_t addr; + void *buf = dmam_alloc_coherent(iface->dchid->dev, size, &addr, GFP_KERNEL); + + if (IS_ERR_OR_NULL(buf)) + return buf ? PTR_ERR(buf) : -ENOMEM; + + msg.addr = addr; + memcpy(buf, firmware, size); + wmb(); + + return dchid_comm_cmd(iface->dchid, &msg, sizeof(msg)); +} + +static int dchid_get_firmware(struct dchid_iface *iface, void **firmware, size_t *size) +{ + int ret; + const char *fw_name; + const struct firmware *fw; + struct fw_header *hdr; + u8 *fw_data; + + ret = of_property_read_string(iface->of_node, "firmware-name", &fw_name); + if (ret) { + /* Firmware is only for some devices */ + *firmware = NULL; + *size = 0; + return 0; + } + + ret = request_firmware(&fw, fw_name, iface->dchid->dev); + if (ret) + return ret; + + hdr = (struct fw_header *)fw->data; + + if (hdr->magic != FW_MAGIC || hdr->version != FW_VER || + hdr->hdr_length < sizeof(*hdr) || hdr->hdr_length > fw->size || + (hdr->hdr_length + (size_t)hdr->data_length) > fw->size || + hdr->iface_offset >= hdr->data_length) { + dev_warn(iface->dchid->dev, "%s: invalid firmware header\n", + fw_name); + ret = -EINVAL; + goto done; + } + + fw_data = devm_kmemdup(iface->dchid->dev, fw->data + hdr->hdr_length, + hdr->data_length, GFP_KERNEL); + if (!fw_data) { + ret = -ENOMEM; + goto done; + } + + if (hdr->iface_offset) + fw_data[hdr->iface_offset] = iface->index; + + *firmware = fw_data; + *size = hdr->data_length; + +done: + release_firmware(fw); + return ret; +} + +static int dchid_request_gpio(struct dchid_iface *iface) +{ + char prop_name[MAX_GPIO_NAME + 16]; + + if (iface->gpio) + return 0; + + dev_info(iface->dchid->dev, "Requesting GPIO %s#%d: %s\n", + iface->name, iface->gpio_id, iface->gpio_name); + + snprintf(prop_name, sizeof(prop_name), "apple,%s", iface->gpio_name); + + iface->gpio = devm_gpiod_get_index(iface->dchid->dev, prop_name, 0, GPIOD_OUT_LOW); + + if (IS_ERR_OR_NULL(iface->gpio)) { + dev_err(iface->dchid->dev, "Failed to request GPIO %s-gpios\n", prop_name); + iface->gpio = NULL; + return -1; + } + + return 0; +} + +static int dchid_start_interface(struct dchid_iface *iface) +{ + void *fw; + size_t size; + int ret; + + if (iface->starting) { + dev_warn(iface->dchid->dev, "Interface %s is already starting", iface->name); + return -EINPROGRESS; + } + + dev_info(iface->dchid->dev, "Starting interface %s\n", iface->name); + + iface->starting = true; + + /* Look to see if we need firmware */ + ret = dchid_get_firmware(iface, &fw, &size); + if (ret < 0) + goto err; + + /* If we need a GPIO, make sure we have it. */ + if (iface->gpio_id) { + ret = dchid_request_gpio(iface); + if (ret < 0) + goto err; + } + + /* Only multi-touch has firmware */ + if (fw && size) { + + /* Send firmware to the device */ + dev_info(iface->dchid->dev, "Sending firmware for %s\n", iface->name); + ret = dchid_send_firmware(iface, fw, size); + if (ret < 0) { + dev_err(iface->dchid->dev, "Failed to send %s firmwareS", iface->name); + goto err; + } + + /* After loading firmware, multi-touch needs a reset */ + dev_info(iface->dchid->dev, "Resetting %s\n", iface->name); + dchid_reset_interface(iface, 0); + dchid_reset_interface(iface, 2); + } + + return 0; + +err: + iface->starting = false; + return ret; +} + +static int dchid_start(struct hid_device *hdev) +{ + struct dchid_iface *iface = hdev->driver_data; + + if (iface->keyboard_layout_id) { + int ret = device_create_file(&hdev->dev, &dev_attr_apple_layout_id); + if (ret) { + dev_warn(iface->dchid->dev, "Failed to create apple_layout_id: %d", ret); + iface->keyboard_layout_id = 0; + } + } + + return 0; +}; + +static void dchid_stop(struct hid_device *hdev) +{ + struct dchid_iface *iface = hdev->driver_data; + + if (iface->keyboard_layout_id) + device_remove_file(&hdev->dev, &dev_attr_apple_layout_id); +} + +static int dchid_open(struct hid_device *hdev) +{ + struct dchid_iface *iface = hdev->driver_data; + int ret; + + if (!completion_done(&iface->ready)) { + ret = dchid_start_interface(iface); + if (ret < 0) + return ret; + + if (!wait_for_completion_timeout(&iface->ready, msecs_to_jiffies(START_TIMEOUT_MS))) { + dev_err(iface->dchid->dev, "iface %s start timed out\n", iface->name); + return -ETIMEDOUT; + } + } + + iface->open = true; + return 0; +} + +static void dchid_close(struct hid_device *hdev) +{ + struct dchid_iface *iface = hdev->driver_data; + + iface->open = false; +} + +static int dchid_parse(struct hid_device *hdev) +{ + struct dchid_iface *iface = hdev->driver_data; + + return hid_parse_report(hdev, iface->hid_desc, iface->hid_desc_len); +} + +/* Note: buf excludes report number! For ease of fetching strings/etc. */ +static int dchid_get_report_cmd(struct dchid_iface *iface, u8 reportnum, void *buf, size_t len) +{ + int ret = dchid_cmd(iface, HID_FEATURE_REPORT, REQ_GET_REPORT, &reportnum, 1, buf, len); + + return ret <= 0 ? ret : ret - 1; +} + +/* Note: buf includes report number! */ +static int dchid_set_report(struct dchid_iface *iface, void *buf, size_t len) +{ + return dchid_cmd(iface, HID_OUTPUT_REPORT, REQ_SET_REPORT, buf, len, NULL, 0); +} + +static int dchid_raw_request(struct hid_device *hdev, + unsigned char reportnum, __u8 *buf, size_t len, + unsigned char rtype, int reqtype) +{ + struct dchid_iface *iface = hdev->driver_data; + + switch (reqtype) { + case HID_REQ_GET_REPORT: + buf[0] = reportnum; + return dchid_cmd(iface, rtype, REQ_GET_REPORT, &reportnum, 1, buf + 1, len - 1); + case HID_REQ_SET_REPORT: + return dchid_set_report(iface, buf, len); + default: + return -EIO; + } + + return 0; +} + +static struct hid_ll_driver dchid_ll = { + .start = &dchid_start, + .stop = &dchid_stop, + .open = &dchid_open, + .close = &dchid_close, + .parse = &dchid_parse, + .raw_request = &dchid_raw_request, +}; + +static void dchid_create_interface_work(struct work_struct *ws) +{ + struct dchid_iface *iface = container_of(ws, struct dchid_iface, create_work); + struct dockchannel_hid *dchid = iface->dchid; + struct hid_device *hid; + int ret; + + if (iface->hid) { + dev_warn(dchid->dev, "Interface %s already created!\n", + iface->name); + return; + } + + dev_info(dchid->dev, "New interface %s\n", iface->name); + + /* Start the interface. This is not the entire init process, as firmware is loaded later on device open. */ + ret = dchid_enable_interface(iface); + if (ret < 0) { + dev_warn(dchid->dev, "Failed to enable %s: %d\n", iface->name, ret); + return; + } + + iface->deferred = false; + + hid = hid_allocate_device(); + if (IS_ERR(hid)) + return; + + snprintf(hid->name, sizeof(hid->name), "Apple MTP %s", iface->name); + snprintf(hid->phys, sizeof(hid->phys), "%s.%d (%s)", + dev_name(dchid->dev), iface->index, iface->name); + strscpy(hid->uniq, dchid->serial, sizeof(hid->uniq)); + + hid->ll_driver = &dchid_ll; + hid->bus = BUS_HOST; + hid->vendor = dchid->device_id.vendor_id; + hid->product = dchid->device_id.product_id; + hid->version = dchid->device_id.version_number; + hid->type = HID_TYPE_OTHER; + if (!strcmp(iface->name, "multi-touch")) { + hid->type = HID_TYPE_SPI_MOUSE; + } else if (!strcmp(iface->name, "keyboard")) { + u32 country_code = 0; + + hid->type = HID_TYPE_SPI_KEYBOARD; + + /* + * We have to get the country code from the device tree, since the + * device provides no reliable way to get this info. + */ + if (!of_property_read_u32(iface->of_node, "hid-country-code", &country_code)) + hid->country = country_code; + + of_property_read_u32(iface->of_node, "apple,keyboard-layout-id", + &iface->keyboard_layout_id); + } + + hid->dev.parent = iface->dchid->dev; + hid->driver_data = iface; + + iface->hid = hid; + + ret = hid_add_device(hid); + if (ret < 0) { + iface->hid = NULL; + hid_destroy_device(hid); + dev_warn(iface->dchid->dev, "Failed to register hid device %s", iface->name); + } +} + +static int dchid_create_interface(struct dchid_iface *iface) +{ + if (iface->creating) + return -EBUSY; + + iface->creating = true; + INIT_WORK(&iface->create_work, dchid_create_interface_work); + return queue_work(iface->dchid->new_iface_wq, &iface->create_work); +} + +static void dchid_handle_descriptor(struct dchid_iface *iface, void *hid_desc, size_t desc_len) +{ + if (iface->hid) { + dev_warn(iface->dchid->dev, "Tried to initialize already started interface %s!\n", + iface->name); + return; + } + + iface->hid_desc = devm_kmemdup(iface->dchid->dev, hid_desc, desc_len, GFP_KERNEL); + if (!iface->hid_desc) + return; + + iface->hid_desc_len = desc_len; +} + +static void dchid_handle_ready(struct dockchannel_hid *dchid, void *data, size_t length) +{ + struct dchid_iface *iface; + u8 *pkt = data; + u8 index; + int i, ret; + + if (length < 2) { + dev_err(dchid->dev, "Bad length for ready message: %zu\n", length); + return; + } + + index = pkt[1]; + + if (index >= MAX_INTERFACES) { + dev_err(dchid->dev, "Got ready notification for bad iface %d\n", index); + return; + } + + iface = dchid->ifaces[index]; + if (!iface) { + dev_err(dchid->dev, "Got ready notification for unknown iface %d\n", index); + return; + } + + dev_info(dchid->dev, "Interface %s is now ready\n", iface->name); + complete_all(&iface->ready); + + /* When STM is ready, grab global device info */ + if (!strcmp(iface->name, "stm")) { + ret = dchid_get_report_cmd(iface, STM_REPORT_ID, &dchid->device_id, + sizeof(dchid->device_id)); + if (ret < sizeof(dchid->device_id)) { + dev_warn(iface->dchid->dev, "Failed to get device ID from STM!\n"); + /* Fake it and keep going. Things might still work... */ + memset(&dchid->device_id, 0, sizeof(dchid->device_id)); + dchid->device_id.vendor_id = HOST_VENDOR_ID_APPLE; + } + ret = dchid_get_report_cmd(iface, STM_REPORT_SERIAL, dchid->serial, + sizeof(dchid->serial) - 1); + if (ret < 0) { + dev_warn(iface->dchid->dev, "Failed to get serial from STM!\n"); + dchid->serial[0] = 0; + } + + dchid->id_ready = true; + for (i = 0; i < MAX_INTERFACES; i++) { + if (!dchid->ifaces[i] || !dchid->ifaces[i]->deferred) + continue; + dchid_create_interface(dchid->ifaces[i]); + } + } +} + +static void dchid_handle_init(struct dockchannel_hid *dchid, void *data, size_t length) +{ + struct dchid_init_hdr *hdr = data; + struct dchid_iface *iface; + struct dchid_init_block_hdr *blk; + + if (length < sizeof(*hdr)) + return; + + iface = dchid_get_interface(dchid, hdr->iface, hdr->name); + if (!iface) + return; + + data += sizeof(*hdr); + length -= sizeof(*hdr); + + while (length >= sizeof(*blk)) { + blk = data; + data += sizeof(*blk); + length -= sizeof(*blk); + + if (blk->length > length) + break; + + switch (blk->type) { + case INIT_HID_DESCRIPTOR: + dchid_handle_descriptor(iface, data, blk->length); + break; + + case INIT_GPIO_REQUEST: { + struct dchid_gpio_request *req = data; + + if (sizeof(*req) > length) + break; + + if (iface->gpio_id) { + dev_err(dchid->dev, + "Cannot request more than one GPIO per interface!\n"); + break; + } + + strscpy(iface->gpio_name, req->name, MAX_GPIO_NAME); + iface->gpio_id = req->id; + break; + } + + case INIT_TERMINATOR: + break; + + case INIT_PRODUCT_NAME: { + char *product = data; + + if (product[blk->length - 1] != 0) { + dev_warn(dchid->dev, "Unterminated product name for %s\n", + iface->name); + } else { + dev_info(dchid->dev, "Product name for %s: %s\n", + iface->name, product); + } + break; + } + + default: + dev_warn(dchid->dev, "Unknown init packet %d for %s\n", + blk->type, iface->name); + break; + } + + data += blk->length; + length -= blk->length; + + if (blk->type == INIT_TERMINATOR) + break; + } + + if (hdr->more_packets) + return; + + /* We need to enable STM first, since it'll give us the device IDs */ + if (iface->dchid->id_ready || !strcmp(iface->name, "stm")) { + dchid_create_interface(iface); + } else { + iface->deferred = true; + } +} + +static void dchid_handle_gpio(struct dockchannel_hid *dchid, void *data, size_t length) +{ + struct dchid_gpio_cmd *cmd = data; + struct dchid_iface *iface; + u32 retcode = 0xe000f00d; /* Give it a random Apple-style error code */ + struct dchid_gpio_ack *ack; + + if (length < sizeof(*cmd)) + return; + + if (cmd->iface >= MAX_INTERFACES || !(iface = dchid->ifaces[cmd->iface])) { + dev_err(dchid->dev, "Got GPIO command for bad inteface %d\n", cmd->iface); + goto err; + } + + if (dchid_request_gpio(iface) < 0) + goto err; + + if (!iface->gpio || cmd->gpio != iface->gpio_id) { + dev_err(dchid->dev, "Got GPIO command for bad GPIO %s#%d\n", + iface->name, cmd->gpio); + goto err; + } + + dev_info(dchid->dev, "GPIO command: %s#%d: %d\n", iface->name, cmd->gpio, cmd->cmd); + + switch (cmd->cmd) { + case 3: + /* Pulse. */ + gpiod_set_value_cansleep(iface->gpio, 1); + msleep(10); /* Random guess... */ + gpiod_set_value_cansleep(iface->gpio, 0); + retcode = 0; + break; + default: + dev_err(dchid->dev, "Unknown GPIO command %d\n", cmd->cmd ); + break; + } + +err: + /* Ack it */ + ack = kzalloc(sizeof(*ack) + length, GFP_KERNEL); + if (!ack) + return; + + ack->type = CMD_ACK_GPIO_CMD; + ack->retcode = retcode; + memcpy(ack->cmd, data, length); + + if (dchid_comm_cmd(dchid, ack, sizeof(*ack) + length) < 0) + dev_err(dchid->dev, "Failed to ACK GPIO command\n"); + + kfree(ack); +} + +static void dchid_handle_event(struct dockchannel_hid *dchid, void *data, size_t length) +{ + u8 *p = data; + switch (*p) { + case EVENT_INIT: + dchid_handle_init(dchid, data, length); + break; + case EVENT_READY: + dchid_handle_ready(dchid, data, length); + break; + case EVENT_GPIO_CMD: + dchid_handle_gpio(dchid, data, length); + break; + } +} + +static void dchid_handle_report(struct dchid_iface *iface, void *data, size_t length) +{ + struct dockchannel_hid *dchid = iface->dchid; + + if (!iface->hid) { + dev_warn(dchid->dev, "Report received but %s is not initialized!\n", iface->name); + return; + } + + if (!iface->open) + return; + + hid_input_report(iface->hid, HID_INPUT_REPORT, data, length, 1); +} + +static void dchid_packet_work(struct work_struct *ws) +{ + struct dchid_work *work = container_of(ws, struct dchid_work, work); + struct dchid_subhdr *shdr = (void *)work->data; + struct dockchannel_hid *dchid = work->iface->dchid; + int type = FIELD_GET(FLAGS_GROUP, shdr->flags); + u8 *payload = work->data + sizeof(*shdr); + + if (shdr->length + sizeof(*shdr) > work->hdr.length) { + dev_err(dchid->dev, "Bad sub header length (%d > %zu)\n", + shdr->length, work->hdr.length - sizeof(*shdr)); + return; + } + + switch (type) { + case HID_INPUT_REPORT: + if (work->hdr.iface == IFACE_COMM) + dchid_handle_event(dchid, payload, shdr->length); + else + dchid_handle_report(work->iface, payload, shdr->length); + break; + default: + dev_err(dchid->dev, "Received unknown packet type %d\n", type); + break; + } + + kfree(work); +} + +static void dchid_handle_ack(struct dchid_iface *iface, struct dchid_hdr *hdr, void *data) +{ + struct dchid_subhdr *shdr = (void *)data; + u8 *payload = data + sizeof(*shdr); + + if (shdr->length + sizeof(*shdr) > hdr->length) { + dev_err(iface->dchid->dev, "Bad sub header length (%d > %ld)\n", + shdr->length, hdr->length - sizeof(*shdr)); + return; + } + if (shdr->flags != iface->out_flags) { + dev_err(iface->dchid->dev, + "Received unexpected flags 0x%x on ACK channel (expFected 0x%x)\n", + shdr->flags, iface->out_flags); + return; + } + + if (shdr->length < 1) { + dev_err(iface->dchid->dev, "Received length 0 output report ack\n"); + return; + } + if (iface->tx_seq != hdr->seq) { + dev_err(iface->dchid->dev, "Received ACK with bad seq (expected %d, got %d)\n", + iface->tx_seq, hdr->seq); + return; + } + if (iface->out_report != payload[0]) { + dev_err(iface->dchid->dev, "Received ACK with bad report (expected %d, got %d\n", + iface->out_report, payload[0]); + return; + } + + if (iface->resp_buf && iface->resp_size) + memcpy(iface->resp_buf, payload + 1, min((size_t)shdr->length - 1, iface->resp_size)); + + iface->resp_size = shdr->length; + iface->out_report = -1; + iface->retcode = shdr->retcode; + complete(&iface->out_complete); +} + +static void dchid_handle_packet(void *cookie, size_t avail) +{ + struct dockchannel_hid *dchid = cookie; + struct dchid_hdr hdr; + struct dchid_work *work; + struct dchid_iface *iface; + u32 checksum; + + if (dockchannel_recv(dchid->dc, &hdr, sizeof(hdr)) != sizeof(hdr)) { + dev_err(dchid->dev, "Read failed (header)\n"); + return; + } + + if (hdr.hdr_len != sizeof(hdr)) { + dev_err(dchid->dev, "Bad header length %d\n", hdr.hdr_len); + goto done; + } + + if (dockchannel_recv(dchid->dc, dchid->pkt_buf, hdr.length + 4) != (hdr.length + 4)) { + dev_err(dchid->dev, "Read failed (body)\n"); + goto done; + } + + checksum = dchid_checksum(&hdr, sizeof(hdr)); + checksum += dchid_checksum(dchid->pkt_buf, hdr.length + 4); + + if (checksum != 0xffffffff) { + dev_err(dchid->dev, "Checksum mismatch (iface %d): 0x%08x != 0xffffffff\n", + hdr.iface, checksum); + goto done; + } + + + if (hdr.iface >= MAX_INTERFACES) { + dev_err(dchid->dev, "Bad iface %d\n", hdr.iface); + } + + iface = dchid->ifaces[hdr.iface]; + + if (!iface) { + dev_err(dchid->dev, "Received packet for uninitialized iface %d\n", hdr.iface); + goto done; + } + + switch (hdr.channel) { + case DCHID_CHANNEL_CMD: + dchid_handle_ack(iface, &hdr, dchid->pkt_buf); + goto done; + case DCHID_CHANNEL_REPORT: + break; + default: + dev_warn(dchid->dev, "Unknown channel 0x%x, treating as report...\n", + hdr.channel); + break; + } + + work = kzalloc(sizeof(*work) + hdr.length, GFP_KERNEL); + if (!work) + return; + + work->hdr = hdr; + work->iface = iface; + memcpy(work->data, dchid->pkt_buf, hdr.length); + INIT_WORK(&work->work, dchid_packet_work); + + queue_work(iface->wq, &work->work); + +done: + dockchannel_await(dchid->dc, dchid_handle_packet, dchid, sizeof(struct dchid_hdr)); +} + +static int dockchannel_hid_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dockchannel_hid *dchid; + struct device_node *child, *helper; + struct platform_device *helper_pdev; + struct property *prop; + int ret; + + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (ret) + return ret; + + dchid = devm_kzalloc(dev, sizeof(*dchid), GFP_KERNEL); + if (!dchid) { + return -ENOMEM; + } + + dchid->dev = dev; + + /* + * First make sure all the GPIOs are available, in cased we need to defer. + * This is necessary because MTP will request them by name later, and by then + * it's too late to defer the probe. + */ + + for_each_child_of_node(dev->of_node, child) { + for_each_property_of_node(child, prop) { + size_t len = strlen(prop->name); + struct gpio_desc *gpio; + + if (len < 12 || strncmp("apple,", prop->name, 6) || + strcmp("-gpios", prop->name + len - 6)) + continue; + + gpio = fwnode_gpiod_get_index(&child->fwnode, prop->name, 0, GPIOD_ASIS, + prop->name); + if (IS_ERR_OR_NULL(gpio)) { + if (PTR_ERR(gpio) == -EPROBE_DEFER) { + of_node_put(child); + return -EPROBE_DEFER; + } + } else { + gpiod_put(gpio); + } + } + } + + /* + * Make sure we also have the MTP coprocessor available, and + * defer probe if the helper hasn't probed yet. + */ + helper = of_parse_phandle(dev->of_node, "apple,helper-cpu", 0); + if (!helper) { + dev_err(dev, "Missing apple,helper-cpu property"); + return -EINVAL; + } + + helper_pdev = of_find_device_by_node(helper); + of_node_put(helper); + if (!helper_pdev) { + dev_err(dev, "Failed to find helper device"); + return -EINVAL; + } + + dchid->helper_link = device_link_add(dev, &helper_pdev->dev, + DL_FLAG_AUTOREMOVE_CONSUMER); + put_device(&helper_pdev->dev); + if (!dchid->helper_link) { + dev_err(dev, "Failed to link to helper device"); + return -EINVAL; + } + + if (dchid->helper_link->supplier->links.status != DL_DEV_DRIVER_BOUND) + return -EPROBE_DEFER; + + /* Now it is safe to begin initializing */ + dchid->dc = dockchannel_init(pdev); + if (IS_ERR_OR_NULL(dchid->dc)) { + return PTR_ERR(dchid->dc); + } + dchid->new_iface_wq = alloc_workqueue("dchid-new", WQ_MEM_RECLAIM, 0); + if (!dchid->new_iface_wq) + return -ENOMEM; + + dchid->comm = dchid_get_interface(dchid, IFACE_COMM, "comm"); + if (!dchid->comm) { + dev_err(dchid->dev, "Failed to initialize comm interface"); + return -EIO; + } + + dev_info(dchid->dev, "Initialized, awaiting packets\n"); + dockchannel_await(dchid->dc, dchid_handle_packet, dchid, sizeof(struct dchid_hdr)); + + return 0; +} + +static void dockchannel_hid_remove(struct platform_device *pdev) +{ + BUG_ON(1); +} + +static const struct of_device_id dockchannel_hid_of_match[] = { + { .compatible = "apple,dockchannel-hid" }, + {}, +}; +MODULE_DEVICE_TABLE(of, dockchannel_hid_of_match); +MODULE_FIRMWARE("apple/tpmtfw-*.bin"); + +static struct platform_driver dockchannel_hid_driver = { + .driver = { + .name = "dockchannel-hid", + .of_match_table = dockchannel_hid_of_match, + }, + .probe = dockchannel_hid_probe, + .remove = dockchannel_hid_remove, +}; +module_platform_driver(dockchannel_hid_driver); + +MODULE_DESCRIPTION("Apple DockChannel HID transport driver"); +MODULE_AUTHOR("Hector Martin "); +MODULE_LICENSE("Dual MIT/GPL"); diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 57da4f86a9fa7f..6d80a7e3cf185c 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -54,10 +54,16 @@ #define APPLE_MAGIC_REPORT_ID_POWER 3 #define APPLE_MAGIC_REPORT_ID_BRIGHTNESS 1 +// DO NOT UPSTREAM: +// temporary Fn key mode until xkeyboard-config has keyboard layouts with media +// key mappings. At that point auto mode can drop function key mappings and this +// mode can be dropped. +#define FKEYS_IGNORE 5 + static unsigned int fnmode = 3; module_param(fnmode, uint, 0644); MODULE_PARM_DESC(fnmode, "Mode of fn key on Apple keyboards (0 = disabled, " - "1 = fkeyslast, 2 = fkeysfirst, [3] = auto, 4 = fkeysdisabled)"); + "1 = fkeyslast, 2 = fkeysfirst, [3] = auto, 4 = fkeysdisabled, 5 = fkeysignore))"); static int iso_layout = -1; module_param(iso_layout, int, 0644); @@ -277,6 +283,16 @@ static const struct apple_key_translation apple_fn_keys[] = { { } }; +static const struct apple_key_translation apple_fn_keys_minimal[] = { + { KEY_BACKSPACE, KEY_DELETE }, + { KEY_ENTER, KEY_INSERT }, + { KEY_UP, KEY_PAGEUP }, + { KEY_DOWN, KEY_PAGEDOWN }, + { KEY_LEFT, KEY_HOME }, + { KEY_RIGHT, KEY_END }, + { } +}; + static const struct apple_key_translation powerbook_fn_keys[] = { { KEY_BACKSPACE, KEY_DELETE }, { KEY_F1, KEY_BRIGHTNESSDOWN, APPLE_FLAG_FKEY }, @@ -433,6 +449,8 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input, real_fnmode = 2; else real_fnmode = 1; + } else if (fnmode == FKEYS_IGNORE) { + real_fnmode = 2; } else { real_fnmode = fnmode; } @@ -473,6 +491,23 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input, asc->fn_on = !!value; if (real_fnmode) { + switch (hid->bus) { + case BUS_HOST: + case BUS_SPI: + switch (hid->product) { + case SPI_DEVICE_ID_APPLE_MACBOOK_PRO13_2020: + case HOST_DEVICE_ID_APPLE_MACBOOK_PRO13_2022: + table = macbookpro_dedicated_esc_fn_keys; + break; + default: + if (fnmode == FKEYS_IGNORE) + table = apple_fn_keys_minimal; + else + table = magic_keyboard_2021_and_2024_fn_keys; + break; + } + break; + default: switch (hid->product) { case USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI: case USB_DEVICE_ID_APPLE_ALU_WIRELESS_ISO: @@ -521,6 +556,7 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input, else table = apple_fn_keys; } + } trans = apple_find_translation(table, code); @@ -704,6 +740,7 @@ static void apple_setup_input(struct input_dev *input) /* Enable all needed keys */ apple_setup_key_translation(input, apple_fn_keys); + apple_setup_key_translation(input, apple_fn_keys_minimal); apple_setup_key_translation(input, powerbook_fn_keys); apple_setup_key_translation(input, powerbook_numlock_keys); apple_setup_key_translation(input, apple_iso_keyboard); @@ -938,6 +975,15 @@ static int apple_probe(struct hid_device *hdev, struct apple_sc *asc; int ret; + if ((id->bus == BUS_SPI || id->bus == BUS_HOST) && id->vendor == SPI_VENDOR_ID_APPLE && + hdev->type != HID_TYPE_SPI_KEYBOARD) + return -ENODEV; + + // key remapping will happen in xkeyboard-config so ignore + // APPLE_ISO_TILDE_QUIRK + if ((id->bus == BUS_SPI || id->bus == BUS_HOST) && fnmode == FKEYS_IGNORE) + quirks &= ~APPLE_ISO_TILDE_QUIRK; + asc = devm_kzalloc(&hdev->dev, sizeof(*asc), GFP_KERNEL); if (asc == NULL) { hid_err(hdev, "can't alloc apple descriptor\n"); @@ -1192,6 +1238,8 @@ static const struct hid_device_id apple_devices[] = { .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY), .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN }, + { HID_SPI_DEVICE(SPI_VENDOR_ID_APPLE, HID_ANY_ID), + .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK }, // TODO: remove APPLE_ISO_TILDE_QUIRK { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021), .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY }, { HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021), @@ -1204,6 +1252,8 @@ static const struct hid_device_id apple_devices[] = { .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY }, { HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_2021), .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK }, + { HID_DEVICE(BUS_HOST, HID_GROUP_ANY, HOST_VENDOR_ID_APPLE, HID_ANY_ID), + .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK }, // TODO: remove APPLE_ISO_TILDE_QUIRK { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024), .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY }, { HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024), diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index a5b3a8ca2fcbc8..3b1b999e7e5150 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -468,7 +468,10 @@ static int hid_parser_global(struct hid_parser *parser, struct hid_item *item) case HID_GLOBAL_ITEM_TAG_REPORT_SIZE: parser->global.report_size = item_udata(item); - if (parser->global.report_size > 256) { + /* Arbitrary maximum. Some Apple devices have 16384 here. + * This * HID_MAX_USAGES must fit in a signed integer. + */ + if (parser->global.report_size > 16384) { hid_err(parser->device, "invalid report_size %d\n", parser->global.report_size); return -1; @@ -2319,6 +2322,12 @@ int hid_connect(struct hid_device *hdev, unsigned int connect_mask) case BUS_SDW: bus = "SOUNDWIRE"; break; + case BUS_SPI: + bus = "SPI"; + break; + case BUS_HOST: + bus = "HOST"; + break; case BUS_VIRTUAL: bus = "VIRTUAL"; break; diff --git a/drivers/hid/hid-elecom.c b/drivers/hid/hid-elecom.c index 981d1b6e96589c..2003d2dcda7cc7 100644 --- a/drivers/hid/hid-elecom.c +++ b/drivers/hid/hid-elecom.c @@ -77,7 +77,7 @@ static const __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, break; case USB_DEVICE_ID_ELECOM_M_XT3URBK_00FB: case USB_DEVICE_ID_ELECOM_M_XT3URBK_018F: - case USB_DEVICE_ID_ELECOM_M_XT3DRBK: + case USB_DEVICE_ID_ELECOM_M_XT3DRBK_00FC: case USB_DEVICE_ID_ELECOM_M_XT4DRBK: /* * Report descriptor format: @@ -102,6 +102,16 @@ static const __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, */ mouse_button_fixup(hdev, rdesc, *rsize, 12, 30, 14, 20, 8); break; + case USB_DEVICE_ID_ELECOM_M_XT3DRBK_018C: + /* + * Report descriptor format: + * 22: button bit count + * 30: padding bit count + * 24: button report size + * 16: button usage maximum + */ + mouse_button_fixup(hdev, rdesc, *rsize, 22, 30, 24, 16, 6); + break; case USB_DEVICE_ID_ELECOM_M_DT2DRBK: case USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C: /* @@ -122,7 +132,8 @@ static const struct hid_device_id elecom_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XGL20DLBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK_00FB) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK_018F) }, - { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK_00FC) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK_018C) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT4DRBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index c4589075a5ed68..232da54c403c4f 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -93,6 +93,8 @@ #define USB_VENDOR_ID_APPLE 0x05ac #define BT_VENDOR_ID_APPLE 0x004c +#define SPI_VENDOR_ID_APPLE 0x05ac +#define HOST_VENDOR_ID_APPLE 0x05ac #define USB_DEVICE_ID_APPLE_MIGHTYMOUSE 0x0304 #define USB_DEVICE_ID_APPLE_MAGICMOUSE 0x030d #define USB_DEVICE_ID_APPLE_MAGICMOUSE2 0x0269 @@ -197,6 +199,14 @@ #define USB_DEVICE_ID_APPLE_IRCONTROL5 0x8243 #define USB_DEVICE_ID_APPLE_TOUCHBAR_BACKLIGHT 0x8102 #define USB_DEVICE_ID_APPLE_TOUCHBAR_DISPLAY 0x8302 +#define SPI_DEVICE_ID_APPLE_MACBOOK_AIR_2020 0x0281 +#define SPI_DEVICE_ID_APPLE_MACBOOK_PRO13_2020 0x0341 +#define SPI_DEVICE_ID_APPLE_MACBOOK_PRO14_2021 0x0342 +#define SPI_DEVICE_ID_APPLE_MACBOOK_PRO16_2021 0x0343 +#define HOST_DEVICE_ID_APPLE_MACBOOK_AIR13_2022 0x0351 +#define HOST_DEVICE_ID_APPLE_MACBOOK_PRO14_2023 0x0352 +#define HOST_DEVICE_ID_APPLE_MACBOOK_PRO16_2023 0x0353 +#define HOST_DEVICE_ID_APPLE_MACBOOK_PRO13_2022 0x0354 #define USB_VENDOR_ID_ASETEK 0x2433 #define USB_DEVICE_ID_ASETEK_INVICTA 0xf300 @@ -317,6 +327,7 @@ #define USB_DEVICE_ID_CHICONY_ACER_SWITCH12 0x1421 #define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA 0xb824 #define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA2 0xb82c +#define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA3 0xb882 #define USB_VENDOR_ID_CHUNGHWAT 0x2247 #define USB_DEVICE_ID_CHUNGHWAT_MULTITOUCH 0x0001 @@ -438,6 +449,9 @@ #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001 0xa001 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002 0xc002 +#define USB_VENDOR_ID_EDIFIER 0x2d99 +#define USB_DEVICE_ID_EDIFIER_QR30 0xa101 /* EDIFIER Hal0 2.0 SE */ + #define USB_VENDOR_ID_ELAN 0x04f3 #define USB_DEVICE_ID_TOSHIBA_CLICK_L9W 0x0401 #define USB_DEVICE_ID_HP_X2 0x074d @@ -451,7 +465,8 @@ #define USB_DEVICE_ID_ELECOM_M_XGL20DLBK 0x00e6 #define USB_DEVICE_ID_ELECOM_M_XT3URBK_00FB 0x00fb #define USB_DEVICE_ID_ELECOM_M_XT3URBK_018F 0x018f -#define USB_DEVICE_ID_ELECOM_M_XT3DRBK 0x00fc +#define USB_DEVICE_ID_ELECOM_M_XT3DRBK_00FC 0x00fc +#define USB_DEVICE_ID_ELECOM_M_XT3DRBK_018C 0x018c #define USB_DEVICE_ID_ELECOM_M_XT4DRBK 0x00fd #define USB_DEVICE_ID_ELECOM_M_DT1URBK 0x00fe #define USB_DEVICE_ID_ELECOM_M_DT1DRBK 0x00ff diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 2bbb645c2ff418..32a96ae2946f1d 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -878,7 +878,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel switch (usage->hid) { /* These usage IDs map directly to the usage codes. */ - case HID_GD_X: case HID_GD_Y: case HID_GD_Z: + case HID_GD_X: case HID_GD_Y: case HID_GD_RX: case HID_GD_RY: case HID_GD_RZ: if (field->flags & HID_MAIN_ITEM_RELATIVE) map_rel(usage->hid & 0xf); @@ -886,6 +886,22 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel map_abs_clear(usage->hid & 0xf); break; + case HID_GD_Z: + /* HID_GD_Z is mapped to ABS_DISTANCE for stylus/pen */ + if (field->flags & HID_MAIN_ITEM_RELATIVE) { + map_rel(usage->hid & 0xf); + } else { + if (field->application == HID_DG_PEN || + field->physical == HID_DG_PEN || + field->logical == HID_DG_STYLUS || + field->physical == HID_DG_STYLUS || + field->application == HID_DG_DIGITIZER) + map_abs_clear(ABS_DISTANCE); + else + map_abs_clear(usage->hid & 0xf); + } + break; + case HID_GD_WHEEL: if (field->flags & HID_MAIN_ITEM_RELATIVE) { set_bit(REL_WHEEL, input->relbit); diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index cce54dd9884a3e..3b5412541c925b 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -805,7 +805,6 @@ static void delayedwork_callback(struct work_struct *work) struct dj_workitem workitem; unsigned long flags; int count; - int retval; dbg_hid("%s\n", __func__); @@ -842,11 +841,7 @@ static void delayedwork_callback(struct work_struct *work) logi_dj_recv_destroy_djhid_device(djrcv_dev, &workitem); break; case WORKITEM_TYPE_UNKNOWN: - retval = logi_dj_recv_query_paired_devices(djrcv_dev); - if (retval) { - hid_err(djrcv_dev->hidpp, "%s: logi_dj_recv_query_paired_devices error: %d\n", - __func__, retval); - } + logi_dj_recv_query_paired_devices(djrcv_dev); break; case WORKITEM_TYPE_EMPTY: dbg_hid("%s: device list is empty\n", __func__); @@ -1239,8 +1234,10 @@ static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev) djrcv_dev->last_query = jiffies; - if (djrcv_dev->type != recvr_type_dj) - return logi_dj_recv_query_hidpp_devices(djrcv_dev); + if (djrcv_dev->type != recvr_type_dj) { + retval = logi_dj_recv_query_hidpp_devices(djrcv_dev); + goto out; + } dj_report = kzalloc(sizeof(struct dj_report), GFP_KERNEL); if (!dj_report) @@ -1250,6 +1247,10 @@ static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev) dj_report->report_type = REPORT_TYPE_CMD_GET_PAIRED_DEVICES; retval = logi_dj_recv_send_report(djrcv_dev, dj_report); kfree(dj_report); +out: + if (retval < 0) + hid_err(djrcv_dev->hidpp, "%s error:%d\n", __func__, retval); + return retval; } @@ -1275,6 +1276,8 @@ static int logi_dj_recv_switch_to_dj_mode(struct dj_receiver_dev *djrcv_dev, (u8)timeout; retval = logi_dj_recv_send_report(djrcv_dev, dj_report); + if (retval) + goto out; /* * Ugly sleep to work around a USB 3.0 bug when the receiver is @@ -1283,11 +1286,6 @@ static int logi_dj_recv_switch_to_dj_mode(struct dj_receiver_dev *djrcv_dev, * 50 msec should gives enough time to the receiver to be ready. */ msleep(50); - - if (retval) { - kfree(dj_report); - return retval; - } } /* @@ -1313,7 +1311,12 @@ static int logi_dj_recv_switch_to_dj_mode(struct dj_receiver_dev *djrcv_dev, HIDPP_REPORT_SHORT_LENGTH, HID_OUTPUT_REPORT, HID_REQ_SET_REPORT); +out: kfree(dj_report); + + if (retval < 0) + hid_err(hdev, "%s error:%d\n", __func__, retval); + return retval; } @@ -1835,11 +1838,8 @@ static int logi_dj_probe(struct hid_device *hdev, if (has_hidpp) { retval = logi_dj_recv_switch_to_dj_mode(djrcv_dev, 0); - if (retval < 0) { - hid_err(hdev, "%s: logi_dj_recv_switch_to_dj_mode returned error:%d\n", - __func__, retval); + if (retval < 0) goto switch_to_dj_mode_fail; - } } /* This is enabling the polling urb on the IN endpoint */ @@ -1857,15 +1857,11 @@ static int logi_dj_probe(struct hid_device *hdev, spin_lock_irqsave(&djrcv_dev->lock, flags); djrcv_dev->ready = true; spin_unlock_irqrestore(&djrcv_dev->lock, flags); - retval = logi_dj_recv_query_paired_devices(djrcv_dev); - if (retval < 0) { - hid_err(hdev, "%s: logi_dj_recv_query_paired_devices error:%d\n", - __func__, retval); - /* - * This can happen with a KVM, let the probe succeed, - * logi_dj_recv_queue_unknown_work will retry later. - */ - } + /* + * This can fail with a KVM. Ignore errors to let the probe + * succeed, logi_dj_recv_queue_unknown_work will retry later. + */ + logi_dj_recv_query_paired_devices(djrcv_dev); } return 0; @@ -1882,18 +1878,12 @@ static int logi_dj_probe(struct hid_device *hdev, #ifdef CONFIG_PM static int logi_dj_reset_resume(struct hid_device *hdev) { - int retval; struct dj_receiver_dev *djrcv_dev = hid_get_drvdata(hdev); if (!djrcv_dev || djrcv_dev->hidpp != hdev) return 0; - retval = logi_dj_recv_switch_to_dj_mode(djrcv_dev, 0); - if (retval < 0) { - hid_err(hdev, "%s: logi_dj_recv_switch_to_dj_mode returned error:%d\n", - __func__, retval); - } - + logi_dj_recv_switch_to_dj_mode(djrcv_dev, 0); return 0; } #endif diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 5e763de4b94fd4..9b612f62d0fba3 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -352,10 +352,15 @@ static int hidpp_send_message_sync(struct hidpp_device *hidpp, do { ret = __do_hidpp_send_message_sync(hidpp, message, response); - if (ret != HIDPP20_ERROR_BUSY) + if (response->report_id == REPORT_ID_HIDPP_SHORT && + ret != HIDPP_ERROR_BUSY) + break; + if ((response->report_id == REPORT_ID_HIDPP_LONG || + response->report_id == REPORT_ID_HIDPP_VERY_LONG) && + ret != HIDPP20_ERROR_BUSY) break; - dbg_hid("%s:got busy hidpp 2.0 error %02X, retrying\n", __func__, ret); + dbg_hid("%s:got busy hidpp error %02X, retrying\n", __func__, ret); } while (--max_retries); mutex_unlock(&hidpp->send_mutex); @@ -4656,6 +4661,8 @@ static const struct hid_device_id hidpp_devices[] = { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb025) }, { /* MX Master 3S mouse over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb034) }, + { /* MX Anywhere 3S mouse over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb037) }, { /* MX Anywhere 3SB mouse over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb038) }, {} diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index 7d4a25c6de0eb7..ae6f48071e1f32 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -60,8 +60,14 @@ MODULE_PARM_DESC(report_undeciphered, "Report undeciphered multi-touch state fie #define MOUSE_REPORT_ID 0x29 #define MOUSE2_REPORT_ID 0x12 #define DOUBLE_REPORT_ID 0xf7 +#define SPI_REPORT_ID 0x02 +#define SPI_RESET_REPORT_ID 0x60 +#define MTP_REPORT_ID 0x75 +#define SENSOR_DIMENSIONS_REPORT_ID 0xd9 #define USB_BATTERY_TIMEOUT_SEC 60 +#define MAX_CONTACTS 16 + /* These definitions are not precise, but they're close enough. (Bits * 0x03 seem to indicate the aspect ratio of the touch, bits 0x70 seem * to be some kind of bit mask -- 0x20 may be a near-field reading, @@ -112,30 +118,53 @@ MODULE_PARM_DESC(report_undeciphered, "Report undeciphered multi-touch state fie #define TRACKPAD2_RES_Y \ ((TRACKPAD2_MAX_Y - TRACKPAD2_MIN_Y) / (TRACKPAD2_DIMENSION_Y / 100)) +/* These are fallback values, since the real values will be queried from the device. */ +#define J314_TP_DIMENSION_X (float)13000 +#define J314_TP_MIN_X -5900 +#define J314_TP_MAX_X 6500 +#define J314_TP_RES_X \ + ((J314_TP_MAX_X - J314_TP_MIN_X) / (J314_TP_DIMENSION_X / 100)) +#define J314_TP_DIMENSION_Y (float)8100 +#define J314_TP_MIN_Y -200 +#define J314_TP_MAX_Y 7400 +#define J314_TP_RES_Y \ + ((J314_TP_MAX_Y - J314_TP_MIN_Y) / (J314_TP_DIMENSION_Y / 100)) + +#define J314_TP_MAX_FINGER_ORIENTATION 16384 + +struct magicmouse_input_ops { + int (*raw_event)(struct hid_device *hdev, + struct hid_report *report, u8 *data, int size); + int (*setup_input)(struct input_dev *input, struct hid_device *hdev); +}; + /** * struct magicmouse_sc - Tracks Magic Mouse-specific data. * @input: Input device through which we report events. * @quirks: Currently unused. + * @query_dimensions: Whether to query and update dimensions on first open * @ntouches: Number of touches in most recent touch report. * @scroll_accel: Number of consecutive scroll motions. * @scroll_jiffies: Time of last scroll motion. + * @pos: multi touch position data of the last report. * @touches: Most recent data for a touch, indexed by tracking ID. * @tracking_ids: Mapping of current touch input data to @touches. * @hdev: Pointer to the underlying HID device. * @work: Workqueue to handle initialization retry for quirky devices. * @battery_timer: Timer for obtaining battery level information. + * @input_ops: Input ops based on device type. */ struct magicmouse_sc { struct input_dev *input; unsigned long quirks; + bool query_dimensions; int ntouches; int scroll_accel; unsigned long scroll_jiffies; + struct input_mt_pos pos[MAX_CONTACTS]; struct { - short x; - short y; short scroll_x; short scroll_y; short scroll_x_hr; @@ -143,14 +172,112 @@ struct magicmouse_sc { u8 size; bool scroll_x_active; bool scroll_y_active; - } touches[16]; - int tracking_ids[16]; + } touches[MAX_CONTACTS]; + int tracking_ids[MAX_CONTACTS]; struct hid_device *hdev; struct delayed_work work; struct timer_list battery_timer; + struct magicmouse_input_ops input_ops; }; +static int magicmouse_enable_multitouch(struct hid_device *hdev); + +static inline int le16_to_int(__le16 x) +{ + return (signed short)le16_to_cpu(x); +} + +static int magicmouse_open(struct input_dev *dev) +{ + struct hid_device *hdev = input_get_drvdata(dev); + struct magicmouse_sc *msc = hid_get_drvdata(hdev); + int ret; + + ret = hid_hw_open(hdev); + if (ret) + return ret; + + /* + * Some devices repond with 'invalid report id' when feature + * report switching it into multitouch mode is sent to it. + * + * This results in -EIO from the _raw low-level transport callback, + * but there seems to be no other way of switching the mode. + * Thus the super-ugly hacky success check below. + * + * MTP devices do not need this. + */ + if (hdev->bus != BUS_HOST) { + ret = magicmouse_enable_multitouch(hdev); + if (ret != -EIO && ret < 0) { + hid_err(hdev, "unable to request touch data (%d)\n", ret); + return ret; + } + if (ret == -EIO && (hdev->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 || + hdev->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC)) { + schedule_delayed_work(&msc->work, msecs_to_jiffies(500)); + } + } + + /* + * For Apple Silicon trackpads, we want to query the dimensions on + * device open. This is because doing so requires the firmware, but + * we don't want to force a firmware load until the device is opened + * for the first time. So do that here and update the input properties + * just in time before userspace queries them. + */ + if (msc->query_dimensions) { + struct input_dev *input = msc->input; + u8 buf[32]; + struct { + __le32 width; + __le32 height; + __le16 min_x; + __le16 min_y; + __le16 max_x; + __le16 max_y; + } dim; + uint32_t x_span, y_span; + + ret = hid_hw_raw_request(hdev, SENSOR_DIMENSIONS_REPORT_ID, buf, sizeof(buf), HID_FEATURE_REPORT, HID_REQ_GET_REPORT); + if (ret < (int)(1 + sizeof(dim))) { + hid_err(hdev, "unable to request dimensions (%d)\n", ret); + return ret; + } + + memcpy(&dim, buf + 1, sizeof(dim)); + + /* finger position */ + input_set_abs_params(input, ABS_MT_POSITION_X, + le16_to_int(dim.min_x), le16_to_int(dim.max_x), 0, 0); + /* Y axis is inverted */ + input_set_abs_params(input, ABS_MT_POSITION_Y, + -le16_to_int(dim.max_y), -le16_to_int(dim.min_y), 0, 0); + x_span = le16_to_int(dim.max_x) - le16_to_int(dim.min_x); + y_span = le16_to_int(dim.max_y) - le16_to_int(dim.min_y); + + /* X/Y resolution */ + input_abs_set_res(input, ABS_MT_POSITION_X, 100 * x_span / le32_to_cpu(dim.width) ); + input_abs_set_res(input, ABS_MT_POSITION_Y, 100 * y_span / le32_to_cpu(dim.height) ); + + /* copy info, as input_mt_init_slots() does */ + dev->absinfo[ABS_X] = dev->absinfo[ABS_MT_POSITION_X]; + dev->absinfo[ABS_Y] = dev->absinfo[ABS_MT_POSITION_Y]; + + msc->query_dimensions = false; + } + + return 0; +} + +static void magicmouse_close(struct input_dev *dev) +{ + struct hid_device *hdev = input_get_drvdata(dev); + + hid_hw_close(hdev); +} + static int magicmouse_firm_touch(struct magicmouse_sc *msc) { int touch = -1; @@ -192,7 +319,7 @@ static void magicmouse_emit_buttons(struct magicmouse_sc *msc, int state) } else if (last_state != 0) { state = last_state; } else if ((id = magicmouse_firm_touch(msc)) >= 0) { - int x = msc->touches[id].x; + int x = msc->pos[id].x; if (x < middle_button_start) state = 1; else if (x > middle_button_stop) @@ -256,8 +383,8 @@ static void magicmouse_emit_touch(struct magicmouse_sc *msc, int raw_id, u8 *tda /* Store tracking ID and other fields. */ msc->tracking_ids[raw_id] = id; - msc->touches[id].x = x; - msc->touches[id].y = y; + msc->pos[id].x = x; + msc->pos[id].y = y; msc->touches[id].size = size; /* If requested, emulate a scroll wheel by detecting small @@ -387,6 +514,14 @@ static int magicmouse_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, int size) { struct magicmouse_sc *msc = hid_get_drvdata(hdev); + + return msc->input_ops.raw_event(hdev, report, data, size); +} + +static int magicmouse_raw_event_usb(struct hid_device *hdev, + struct hid_report *report, u8 *data, int size) +{ + struct magicmouse_sc *msc = hid_get_drvdata(hdev); struct input_dev *input = msc->input; int x = 0, y = 0, ii, clicks = 0, npoints; @@ -518,6 +653,174 @@ static int magicmouse_raw_event(struct hid_device *hdev, return 1; } +/** + * struct tp_finger - single trackpad finger structure, le16-aligned + * + * @unknown1: unknown + * @unknown2: unknown + * @abs_x: absolute x coordinate + * @abs_y: absolute y coordinate + * @rel_x: relative x coordinate + * @rel_y: relative y coordinate + * @tool_major: tool area, major axis + * @tool_minor: tool area, minor axis + * @orientation: 16384 when point, else 15 bit angle + * @touch_major: touch area, major axis + * @touch_minor: touch area, minor axis + * @unused: zeros + * @pressure: pressure on forcetouch touchpad + * @multi: one finger: varies, more fingers: constant + */ +struct tp_finger { + __le16 unknown1; + __le16 unknown2; + __le16 abs_x; + __le16 abs_y; + __le16 rel_x; + __le16 rel_y; + __le16 tool_major; + __le16 tool_minor; + __le16 orientation; + __le16 touch_major; + __le16 touch_minor; + __le16 unused[2]; + __le16 pressure; + __le16 multi; +} __attribute__((packed, aligned(2))); + +/** + * vendor trackpad report + * + * @num_fingers: the number of fingers being reported in @fingers + * @buttons: same as HID buttons + */ +struct tp_header { + // HID vendor part, up to 1751 bytes + u8 unknown[22]; + u8 num_fingers; + u8 buttons; + u8 unknown3[14]; +}; + +/** + * standard HID mouse report + * + * @report_id: reportid + * @buttons: HID Usage Buttons 3 1-bit reports + */ +struct tp_mouse_report { + // HID mouse report + u8 report_id; + u8 buttons; + u8 rel_x; + u8 rel_y; + u8 padding[4]; +}; + +static void report_finger_data(struct input_dev *input, int slot, + const struct input_mt_pos *pos, + const struct tp_finger *f) +{ + input_mt_slot(input, slot); + input_mt_report_slot_state(input, MT_TOOL_FINGER, true); + + input_report_abs(input, ABS_MT_TOUCH_MAJOR, + le16_to_int(f->touch_major) << 1); + input_report_abs(input, ABS_MT_TOUCH_MINOR, + le16_to_int(f->touch_minor) << 1); + input_report_abs(input, ABS_MT_WIDTH_MAJOR, + le16_to_int(f->tool_major) << 1); + input_report_abs(input, ABS_MT_WIDTH_MINOR, + le16_to_int(f->tool_minor) << 1); + input_report_abs(input, ABS_MT_ORIENTATION, + J314_TP_MAX_FINGER_ORIENTATION - le16_to_int(f->orientation)); + input_report_abs(input, ABS_MT_PRESSURE, le16_to_int(f->pressure)); + input_report_abs(input, ABS_MT_POSITION_X, pos->x); + input_report_abs(input, ABS_MT_POSITION_Y, pos->y); +} + +static int magicmouse_raw_event_mtp(struct hid_device *hdev, + struct hid_report *report, u8 *data, int size) +{ + struct magicmouse_sc *msc = hid_get_drvdata(hdev); + struct input_dev *input = msc->input; + struct tp_header *tp_hdr; + struct tp_finger *f; + int i, n; + u32 npoints; + const size_t hdr_sz = sizeof(struct tp_header); + const size_t touch_sz = sizeof(struct tp_finger); + u8 map_contacs[MAX_CONTACTS]; + + // hid_warn(hdev, "%s\n", __func__); + // print_hex_dump_debug("appleft ev: ", DUMP_PREFIX_OFFSET, 16, 1, data, + // size, false); + + /* Expect 46 bytes of prefix, and N * 30 bytes of touch data. */ + if (size < hdr_sz || ((size - hdr_sz) % touch_sz) != 0) + return 0; + + tp_hdr = (struct tp_header *)data; + + npoints = (size - hdr_sz) / touch_sz; + if (npoints < tp_hdr->num_fingers || npoints > MAX_CONTACTS) { + hid_warn(hdev, + "unexpected number of touches (%u) for " + "report\n", + npoints); + return 0; + } + + n = 0; + for (i = 0; i < tp_hdr->num_fingers; i++) { + f = (struct tp_finger *)(data + hdr_sz + i * touch_sz); + if (le16_to_int(f->touch_major) == 0) + continue; + + hid_dbg(hdev, "ev x:%04x y:%04x\n", le16_to_int(f->abs_x), + le16_to_int(f->abs_y)); + msc->pos[n].x = le16_to_int(f->abs_x); + msc->pos[n].y = -le16_to_int(f->abs_y); + map_contacs[n] = i; + n++; + } + + input_mt_assign_slots(input, msc->tracking_ids, msc->pos, n, 0); + + for (i = 0; i < n; i++) { + int idx = map_contacs[i]; + f = (struct tp_finger *)(data + hdr_sz + idx * touch_sz); + report_finger_data(input, msc->tracking_ids[i], &msc->pos[i], f); + } + + input_mt_sync_frame(input); + input_report_key(input, BTN_MOUSE, tp_hdr->buttons & 1); + + input_sync(input); + return 1; +} + +static int magicmouse_raw_event_spi(struct hid_device *hdev, + struct hid_report *report, u8 *data, int size) +{ + struct magicmouse_sc *msc = hid_get_drvdata(hdev); + const size_t hdr_sz = sizeof(struct tp_mouse_report); + + if (!size) + return 0; + + if (data[0] == SPI_RESET_REPORT_ID) { + hid_info(hdev, "Touch controller was reset, re-enabling touch mode\n"); + schedule_delayed_work(&msc->work, msecs_to_jiffies(10)); + return 1; + } + + if (data[0] != SPI_REPORT_ID || size < hdr_sz) + return 0; + + return magicmouse_raw_event_mtp(hdev, report, data + hdr_sz, size - hdr_sz); +} + static int magicmouse_event(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage, __s32 value) { @@ -536,7 +839,17 @@ static int magicmouse_event(struct hid_device *hdev, struct hid_field *field, return 0; } -static int magicmouse_setup_input(struct input_dev *input, struct hid_device *hdev) + +static int magicmouse_setup_input(struct input_dev *input, + struct hid_device *hdev) +{ + struct magicmouse_sc *msc = hid_get_drvdata(hdev); + + return msc->input_ops.setup_input(input, hdev); +} + +static int magicmouse_setup_input_usb(struct input_dev *input, + struct hid_device *hdev) { int error; int mt_flags = 0; @@ -615,7 +928,7 @@ static int magicmouse_setup_input(struct input_dev *input, struct hid_device *hd __set_bit(EV_ABS, input->evbit); - error = input_mt_init_slots(input, 16, mt_flags); + error = input_mt_init_slots(input, MAX_CONTACTS, mt_flags); if (error) return error; input_set_abs_params(input, ABS_MT_TOUCH_MAJOR, 0, 255 << 2, @@ -695,6 +1008,109 @@ static int magicmouse_setup_input(struct input_dev *input, struct hid_device *hd */ __clear_bit(EV_REP, input->evbit); + /* + * This isn't strictly speaking needed for USB, but enabling MT on + * device open is probably more robust than only doing it once on probe + * even if USB devices are not known to suffer from the SPI reset issue. + */ + input->open = magicmouse_open; + input->close = magicmouse_close; + return 0; +} + +static int magicmouse_setup_input_mtp(struct input_dev *input, + struct hid_device *hdev) +{ + int error; + int mt_flags = 0; + struct magicmouse_sc *msc = hid_get_drvdata(hdev); + + __set_bit(INPUT_PROP_BUTTONPAD, input->propbit); + __clear_bit(BTN_0, input->keybit); + __clear_bit(BTN_RIGHT, input->keybit); + __clear_bit(BTN_MIDDLE, input->keybit); + __clear_bit(EV_REL, input->evbit); + __clear_bit(REL_X, input->relbit); + __clear_bit(REL_Y, input->relbit); + + mt_flags = INPUT_MT_POINTER | INPUT_MT_DROP_UNUSED | INPUT_MT_TRACK; + + /* finger touch area */ + input_set_abs_params(input, ABS_MT_TOUCH_MAJOR, 0, 5000, 0, 0); + input_set_abs_params(input, ABS_MT_TOUCH_MINOR, 0, 5000, 0, 0); + + /* finger approach area */ + input_set_abs_params(input, ABS_MT_WIDTH_MAJOR, 0, 5000, 0, 0); + input_set_abs_params(input, ABS_MT_WIDTH_MINOR, 0, 5000, 0, 0); + + /* Note: Touch Y position from the device is inverted relative + * to how pointer motion is reported (and relative to how USB + * HID recommends the coordinates work). This driver keeps + * the origin at the same position, and just uses the additive + * inverse of the reported Y. + */ + + input_set_abs_params(input, ABS_MT_PRESSURE, 0, 6000, 0, 0); + + /* + * This makes libinput recognize this as a PressurePad and + * stop trying to use pressure for touch size. Pressure unit + * seems to be ~grams on these touchpads. + */ + input_abs_set_res(input, ABS_MT_PRESSURE, 1); + + /* finger orientation */ + input_set_abs_params(input, ABS_MT_ORIENTATION, -J314_TP_MAX_FINGER_ORIENTATION, + J314_TP_MAX_FINGER_ORIENTATION, 0, 0); + + /* finger position */ + input_set_abs_params(input, ABS_MT_POSITION_X, J314_TP_MIN_X, J314_TP_MAX_X, + 0, 0); + /* Y axis is inverted */ + input_set_abs_params(input, ABS_MT_POSITION_Y, -J314_TP_MAX_Y, -J314_TP_MIN_Y, + 0, 0); + + /* X/Y resolution */ + input_abs_set_res(input, ABS_MT_POSITION_X, J314_TP_RES_X); + input_abs_set_res(input, ABS_MT_POSITION_Y, J314_TP_RES_Y); + + input_set_events_per_packet(input, 60); + + /* touchpad button */ + input_set_capability(input, EV_KEY, BTN_MOUSE); + + /* + * hid-input may mark device as using autorepeat, but the trackpad does + * not actually want it. + */ + __clear_bit(EV_REP, input->evbit); + + error = input_mt_init_slots(input, MAX_CONTACTS, mt_flags); + if (error) + return error; + + /* + * Override the default input->open function to send the MT + * enable every time the device is opened. This ensures it works + * even if we missed a reset event due to the device being closed. + * input->close is overridden for symmetry. + * + * This also takes care of the dimensions query. + */ + input->open = magicmouse_open; + input->close = magicmouse_close; + msc->query_dimensions = true; + + return 0; +} + +static int magicmouse_setup_input_spi(struct input_dev *input, + struct hid_device *hdev) +{ + int ret = magicmouse_setup_input_mtp(input, hdev); + if (ret) + return ret; + return 0; } @@ -748,6 +1164,10 @@ static int magicmouse_enable_multitouch(struct hid_device *hdev) int feature_size; switch (hdev->product) { + case SPI_DEVICE_ID_APPLE_MACBOOK_AIR_2020: + case SPI_DEVICE_ID_APPLE_MACBOOK_PRO13_2020: + case SPI_DEVICE_ID_APPLE_MACBOOK_PRO14_2021: + case SPI_DEVICE_ID_APPLE_MACBOOK_PRO16_2021: case USB_DEVICE_ID_APPLE_MAGICTRACKPAD2: case USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC: switch (hdev->vendor) { @@ -755,7 +1175,7 @@ static int magicmouse_enable_multitouch(struct hid_device *hdev) feature_size = sizeof(feature_mt_trackpad2_bt); feature = feature_mt_trackpad2_bt; break; - default: /* USB_VENDOR_ID_APPLE */ + default: /* USB_VENDOR_ID_APPLE || SPI_VENDOR_ID_APPLE */ feature_size = sizeof(feature_mt_trackpad2_usb); feature = feature_mt_trackpad2_usb; } @@ -852,12 +1272,29 @@ static int magicmouse_probe(struct hid_device *hdev, struct hid_report *report; int ret; + if ((id->bus == BUS_SPI || id->bus == BUS_HOST) && id->vendor == SPI_VENDOR_ID_APPLE && + hdev->type != HID_TYPE_SPI_MOUSE) + return -ENODEV; + msc = devm_kzalloc(&hdev->dev, sizeof(*msc), GFP_KERNEL); if (msc == NULL) { hid_err(hdev, "can't alloc magicmouse descriptor\n"); return -ENOMEM; } + // internal trackpad use a data format use input ops to avoid + // conflicts with the report ID. + if (id->bus == BUS_HOST) { + msc->input_ops.raw_event = magicmouse_raw_event_mtp; + msc->input_ops.setup_input = magicmouse_setup_input_mtp; + } else if (id->bus == BUS_SPI) { + msc->input_ops.raw_event = magicmouse_raw_event_spi; + msc->input_ops.setup_input = magicmouse_setup_input_spi; + } else { + msc->input_ops.raw_event = magicmouse_raw_event_usb; + msc->input_ops.setup_input = magicmouse_setup_input_usb; + } + msc->scroll_accel = SCROLL_ACCEL_DEFAULT; msc->hdev = hdev; INIT_DEFERRABLE_WORK(&msc->work, magicmouse_enable_mt_work); @@ -916,11 +1353,20 @@ static int magicmouse_probe(struct hid_device *hdev, TRACKPAD2_USB_REPORT_ID, 0); } break; - default: /* USB_DEVICE_ID_APPLE_MAGICTRACKPAD */ - report = hid_register_report(hdev, HID_INPUT_REPORT, - TRACKPAD_REPORT_ID, 0); - report = hid_register_report(hdev, HID_INPUT_REPORT, - DOUBLE_REPORT_ID, 0); + default: + switch (id->bus) { + case BUS_HOST: + report = hid_register_report(hdev, HID_INPUT_REPORT, MTP_REPORT_ID, 0); + break; + case BUS_SPI: + report = hid_register_report(hdev, HID_INPUT_REPORT, SPI_REPORT_ID, 0); + break; + default: /* USB_DEVICE_ID_APPLE_MAGICTRACKPAD */ + report = hid_register_report(hdev, HID_INPUT_REPORT, + TRACKPAD_REPORT_ID, 0); + report = hid_register_report(hdev, HID_INPUT_REPORT, + DOUBLE_REPORT_ID, 0); + } } if (!report) { @@ -930,22 +1376,14 @@ static int magicmouse_probe(struct hid_device *hdev, } report->size = 6; - /* - * Some devices repond with 'invalid report id' when feature - * report switching it into multitouch mode is sent to it. - * - * This results in -EIO from the _raw low-level transport callback, - * but there seems to be no other way of switching the mode. - * Thus the super-ugly hacky success check below. - */ - ret = magicmouse_enable_multitouch(hdev); - if (ret != -EIO && ret < 0) { - hid_err(hdev, "unable to request touch data (%d)\n", ret); - goto err_stop_hw; - } - if (ret == -EIO && (id->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2 || - id->product == USB_DEVICE_ID_APPLE_MAGICMOUSE2_USBC)) { - schedule_delayed_work(&msc->work, msecs_to_jiffies(500)); + /* MTP devices do not need the MT enable, this is handled by the MTP driver */ + if (id->bus == BUS_HOST) + return 0; + + /* SPI devices need to watch for reset events to re-send the MT enable */ + if (id->bus == BUS_SPI) { + report = hid_register_report(hdev, HID_INPUT_REPORT, SPI_RESET_REPORT_ID, 0); + report->size = 2; } return 0; @@ -1023,10 +1461,24 @@ static const struct hid_device_id magic_mice[] = { USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC), .driver_data = 0 }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGICTRACKPAD2_USBC), .driver_data = 0 }, + { HID_SPI_DEVICE(SPI_VENDOR_ID_APPLE, HID_ANY_ID), + .driver_data = 0 }, + { HID_DEVICE(BUS_HOST, HID_GROUP_ANY, HOST_VENDOR_ID_APPLE, + HID_ANY_ID), .driver_data = 0 }, { } }; MODULE_DEVICE_TABLE(hid, magic_mice); +#ifdef CONFIG_PM +static int magicmouse_reset_resume(struct hid_device *hdev) +{ + if (hdev->bus == BUS_SPI) + return magicmouse_enable_multitouch(hdev); + + return 0; +} +#endif + static struct hid_driver magicmouse_driver = { .name = "magicmouse", .id_table = magic_mice, @@ -1037,6 +1489,10 @@ static struct hid_driver magicmouse_driver = { .event = magicmouse_event, .input_mapping = magicmouse_input_mapping, .input_configured = magicmouse_input_configured, +#ifdef CONFIG_PM + .reset_resume = magicmouse_reset_resume, +#endif + }; module_hid_driver(magicmouse_driver); diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 179dc316b4b518..a0c1ad5acb6706 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -393,6 +393,7 @@ static const struct mt_class mt_classes[] = { { .name = MT_CLS_VTL, .quirks = MT_QUIRK_ALWAYS_VALID | MT_QUIRK_CONTACT_CNT_ACCURATE | + MT_QUIRK_STICKY_FINGERS | MT_QUIRK_FORCE_GET_FEATURE, }, { .name = MT_CLS_GOOGLE, diff --git a/drivers/hid/hid-playstation.c b/drivers/hid/hid-playstation.c index 128aa6abd10bed..2ec6d4445e84ba 100644 --- a/drivers/hid/hid-playstation.c +++ b/drivers/hid/hid-playstation.c @@ -753,11 +753,16 @@ ps_gamepad_create(struct hid_device *hdev, if (IS_ERR(gamepad)) return ERR_CAST(gamepad); + /* Set initial resting state for joysticks to 128 (center) */ input_set_abs_params(gamepad, ABS_X, 0, 255, 0, 0); + gamepad->absinfo[ABS_X].value = 128; input_set_abs_params(gamepad, ABS_Y, 0, 255, 0, 0); + gamepad->absinfo[ABS_Y].value = 128; input_set_abs_params(gamepad, ABS_Z, 0, 255, 0, 0); input_set_abs_params(gamepad, ABS_RX, 0, 255, 0, 0); + gamepad->absinfo[ABS_RX].value = 128; input_set_abs_params(gamepad, ABS_RY, 0, 255, 0, 0); + gamepad->absinfo[ABS_RY].value = 128; input_set_abs_params(gamepad, ABS_RZ, 0, 255, 0, 0); input_set_abs_params(gamepad, ABS_HAT0X, -1, 1, 0, 0); @@ -769,7 +774,9 @@ ps_gamepad_create(struct hid_device *hdev, #if IS_ENABLED(CONFIG_PLAYSTATION_FF) if (play_effect) { input_set_capability(gamepad, EV_FF, FF_RUMBLE); - input_ff_create_memless(gamepad, NULL, play_effect); + ret = input_ff_create_memless(gamepad, NULL, play_effect); + if (ret) + return ERR_PTR(ret); } #endif diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index c89a015686c07e..11438039cdb7f7 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -81,6 +81,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_PS3), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_EGALAX_TOUCHCONTROLLER), HID_QUIRK_MULTI_INPUT | HID_QUIRK_NOGET }, + { HID_USB_DEVICE(USB_VENDOR_ID_EDIFIER, USB_DEVICE_ID_EDIFIER_QR30), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, HID_ANY_ID), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_EMS, USB_DEVICE_ID_EMS_TRIO_LINKER_PLUS_II), HID_QUIRK_MULTI_INPUT }, @@ -232,6 +233,15 @@ static const struct hid_device_id hid_quirks[] = { * used as a driver. See hid_scan_report(). */ static const struct hid_device_id hid_have_special_driver[] = { +#if IS_ENABLED(CONFIG_APPLEDISPLAY) + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9218) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9219) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x921c) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x921d) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9222) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9226) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9236) }, +#endif #if IS_ENABLED(CONFIG_HID_A4TECH) { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_WCP32PU) }, { HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_X5_005D) }, @@ -412,7 +422,8 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XGL20DLBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK_00FB) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK_018F) }, - { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK_00FC) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK_018C) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT4DRBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) }, @@ -769,6 +780,7 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_BERKSHIRE, USB_DEVICE_ID_BERKSHIRE_PCWD) }, { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA) }, { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA2) }, + { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA3) }, { HID_USB_DEVICE(USB_VENDOR_ID_CIDC, 0x0103) }, { HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_RADIO_SI470X) }, { HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_RADIO_SI4713) }, diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 63f46a2e57882f..5a183af3d5c6a6 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -286,6 +286,7 @@ static int i2c_hid_get_report(struct i2c_hid *ihid, * In addition to report data device will supply data length * in the first 2 bytes of the response, so adjust . */ + recv_len = min(recv_len, ihid->bufsize - sizeof(__le16)); error = i2c_hid_xfer(ihid, ihid->cmdbuf, length, ihid->rawbuf, recv_len + sizeof(__le16)); if (error) { diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c index 3ddaa2cd39d555..3692d1db3bc764 100644 --- a/drivers/hid/intel-ish-hid/ipc/ipc.c +++ b/drivers/hid/intel-ish-hid/ipc/ipc.c @@ -628,7 +628,7 @@ static void recv_ipc(struct ishtp_device *dev, uint32_t doorbell_val) if (!ishtp_dev) { ishtp_dev = dev; } - schedule_work(&fw_reset_work); + queue_work(dev->unbound_wq, &fw_reset_work); break; case MNG_RESET_NOTIFY_ACK: @@ -933,6 +933,25 @@ static const struct ishtp_hw_ops ish_hw_ops = { .dma_no_cache_snooping = _dma_no_cache_snooping }; +static void ishtp_free_workqueue(void *wq) +{ + destroy_workqueue(wq); +} + +static struct workqueue_struct *devm_ishtp_alloc_workqueue(struct device *dev) +{ + struct workqueue_struct *wq; + + wq = alloc_workqueue("ishtp_unbound_%d", WQ_UNBOUND, 0, dev->id); + if (!wq) + return NULL; + + if (devm_add_action_or_reset(dev, ishtp_free_workqueue, wq)) + return NULL; + + return wq; +} + /** * ish_dev_init() -Initialize ISH devoce * @pdev: PCI device @@ -953,6 +972,10 @@ struct ishtp_device *ish_dev_init(struct pci_dev *pdev) if (!dev) return NULL; + dev->unbound_wq = devm_ishtp_alloc_workqueue(&pdev->dev); + if (!dev->unbound_wq) + return NULL; + dev->devc = &pdev->dev; ishtp_device_init(dev); diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 9d150ce234f253..b748ac6fbfdc73 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -384,7 +384,7 @@ static int __maybe_unused ish_resume(struct device *device) ish_resume_device = device; dev->resume_flag = 1; - schedule_work(&resume_work); + queue_work(dev->unbound_wq, &resume_work); return 0; } diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c index d8c3c54a8c0f2a..12a43c64e81560 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c +++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c @@ -495,6 +495,7 @@ static int ishtp_enum_enum_devices(struct ishtp_cl *hid_ishtp_cl) int rv; /* Send HOSTIF_DM_ENUM_DEVICES */ + client_data->enum_devices_done = false; memset(&msg, 0, sizeof(struct hostif_msg)); msg.hdr.command = HOSTIF_DM_ENUM_DEVICES; rv = ishtp_cl_send(hid_ishtp_cl, (unsigned char *)&msg, @@ -860,7 +861,7 @@ static int hid_ishtp_cl_reset(struct ishtp_cl_device *cl_device) hid_ishtp_trace(client_data, "%s hid_ishtp_cl %p\n", __func__, hid_ishtp_cl); - schedule_work(&client_data->work); + queue_work(ishtp_get_workqueue(cl_device), &client_data->work); return 0; } @@ -902,7 +903,7 @@ static int hid_ishtp_cl_resume(struct device *device) hid_ishtp_trace(client_data, "%s hid_ishtp_cl %p\n", __func__, hid_ishtp_cl); - schedule_work(&client_data->resume_work); + queue_work(ishtp_get_workqueue(cl_device), &client_data->resume_work); return 0; } diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index 93a0432e705814..b890fbf97a75cd 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -240,9 +240,17 @@ static int ishtp_cl_bus_match(struct device *dev, const struct device_driver *dr { struct ishtp_cl_device *device = to_ishtp_cl_device(dev); struct ishtp_cl_driver *driver = to_ishtp_cl_driver(drv); + struct ishtp_fw_client *client = device->fw_client; + const struct ishtp_device_id *id; - return(device->fw_client ? guid_equal(&driver->id[0].guid, - &device->fw_client->props.protocol_name) : 0); + if (client) { + for (id = driver->id; !guid_is_null(&id->guid); id++) { + if (guid_equal(&id->guid, &client->props.protocol_name)) + return 1; + } + } + + return 0; } /** @@ -541,7 +549,7 @@ void ishtp_cl_bus_rx_event(struct ishtp_cl_device *device) return; if (device->event_cb) - schedule_work(&device->event_work); + queue_work(device->ishtp_dev->unbound_wq, &device->event_work); } /** @@ -722,7 +730,7 @@ void ishtp_bus_remove_all_clients(struct ishtp_device *ishtp_dev, spin_lock_irqsave(&ishtp_dev->cl_list_lock, flags); list_for_each_entry(cl, &ishtp_dev->cl_list, link) { cl->state = ISHTP_CL_DISCONNECTED; - if (warm_reset && cl->device->reference_count) + if (warm_reset && cl->device && cl->device->reference_count) continue; /* @@ -876,6 +884,22 @@ struct device *ishtp_get_pci_device(struct ishtp_cl_device *device) } EXPORT_SYMBOL(ishtp_get_pci_device); +/** + * ishtp_get_workqueue - Retrieve the workqueue associated with an ISHTP device + * @cl_device: Pointer to the ISHTP client device structure + * + * Returns the workqueue_struct pointer (unbound_wq) associated with the given + * ISHTP client device. This workqueue is typically used for scheduling work + * related to the device. + * + * Return: Pointer to struct workqueue_struct. + */ +struct workqueue_struct *ishtp_get_workqueue(struct ishtp_cl_device *cl_device) +{ + return cl_device->ishtp_dev->unbound_wq; +} +EXPORT_SYMBOL(ishtp_get_workqueue); + /** * ishtp_trace_callback() - Return trace callback * @cl_device: ISH-TP client device instance diff --git a/drivers/hid/intel-ish-hid/ishtp/hbm.c b/drivers/hid/intel-ish-hid/ishtp/hbm.c index 8ee5467127d872..97c4fcd9e3c6f2 100644 --- a/drivers/hid/intel-ish-hid/ishtp/hbm.c +++ b/drivers/hid/intel-ish-hid/ishtp/hbm.c @@ -573,7 +573,7 @@ void ishtp_hbm_dispatch(struct ishtp_device *dev, /* Start firmware loading process if it has loader capability */ if (version_res->host_version_supported & ISHTP_SUPPORT_CAP_LOADER) - schedule_work(&dev->work_fw_loader); + queue_work(dev->unbound_wq, &dev->work_fw_loader); dev->version.major_version = HBM_MAJOR_VERSION; dev->version.minor_version = HBM_MINOR_VERSION; @@ -864,7 +864,7 @@ void recv_hbm(struct ishtp_device *dev, struct ishtp_msg_hdr *ishtp_hdr) dev->rd_msg_fifo_tail = (dev->rd_msg_fifo_tail + IPC_PAYLOAD_SIZE) % (RD_INT_FIFO_SIZE * IPC_PAYLOAD_SIZE); spin_unlock_irqrestore(&dev->rd_msg_spinlock, flags); - schedule_work(&dev->bh_hbm_work); + queue_work(dev->unbound_wq, &dev->bh_hbm_work); eoi: return; } diff --git a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h index 23db97ecf21cd9..4b0596eadf1cce 100644 --- a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h +++ b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h @@ -175,6 +175,9 @@ struct ishtp_device { struct hbm_version version; int transfer_path; /* Choice of transfer path: IPC or DMA */ + /* Alloc a dedicated unbound workqueue for ishtp device */ + struct workqueue_struct *unbound_wq; + /* work structure for scheduling firmware loading tasks */ struct work_struct work_fw_loader; /* waitq for waiting for command response from the firmware loader */ diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c index 636a6830650150..7e220a4c5ded7b 100644 --- a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c +++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c @@ -1593,7 +1593,7 @@ int thc_i2c_set_rx_max_size(struct thc_device *dev, u32 max_rx_size) if (!max_rx_size) return -EOPNOTSUPP; - ret = regmap_read(dev->thc_regmap, THC_M_PRT_SW_SEQ_STS_OFFSET, &val); + ret = regmap_read(dev->thc_regmap, THC_M_PRT_SPI_ICRRD_OPCODE_OFFSET, &val); if (ret) return ret; @@ -1662,7 +1662,7 @@ int thc_i2c_set_rx_int_delay(struct thc_device *dev, u32 delay_us) if (!delay_us) return -EOPNOTSUPP; - ret = regmap_read(dev->thc_regmap, THC_M_PRT_SW_SEQ_STS_OFFSET, &val); + ret = regmap_read(dev->thc_regmap, THC_M_PRT_SPI_ICRRD_OPCODE_OFFSET, &val); if (ret) return ret; diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c index 82b8854843e052..6ee675e0a73845 100644 --- a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c +++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c @@ -232,6 +232,7 @@ static int setup_dma_buffers(struct thc_device *dev, return 0; memset(config->sgls, 0, sizeof(config->sgls)); + memset(config->sgls_nent_pages, 0, sizeof(config->sgls_nent_pages)); memset(config->sgls_nent, 0, sizeof(config->sgls_nent)); cpu_addr = dma_alloc_coherent(dev->dev, prd_tbls_size, @@ -254,6 +255,7 @@ static int setup_dma_buffers(struct thc_device *dev, } count = dma_map_sg(dev->dev, config->sgls[i], nent, dir); + config->sgls_nent_pages[i] = nent; config->sgls_nent[i] = count; } @@ -299,7 +301,7 @@ static void release_dma_buffers(struct thc_device *dev, continue; dma_unmap_sg(dev->dev, config->sgls[i], - config->sgls_nent[i], + config->sgls_nent_pages[i], config->dir); sgl_free(config->sgls[i]); @@ -573,6 +575,11 @@ static int read_dma_buffer(struct thc_device *dev, return -EINVAL; } + if (!read_config->prd_tbls || !read_config->sgls[prd_table_index]) { + dev_err_once(dev->dev, "PRD tables are not ready yet\n"); + return -EINVAL; + } + prd_tbl = &read_config->prd_tbls[prd_table_index]; mes_len = calc_message_len(prd_tbl, &nent); if (mes_len > read_config->max_packet_size) { diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h index 78917400492caf..541d33995baf36 100644 --- a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h +++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h @@ -91,6 +91,7 @@ struct thc_prd_table { * @dir: Direction of DMA for this config * @prd_tbls: PRD tables for current DMA * @sgls: Array of pointers to scatter-gather lists + * @sgls_nent_pages: Number of pages per scatter-gather list * @sgls_nent: Actual number of entries per scatter-gather list * @prd_tbl_num: Actual number of PRD tables * @max_packet_size: Size of the buffer needed for 1 DMA message (1 PRD table) @@ -107,6 +108,7 @@ struct thc_dma_configuration { struct thc_prd_table *prd_tbls; struct scatterlist *sgls[PRD_TABLES_NUM]; + u8 sgls_nent_pages[PRD_TABLES_NUM]; u8 sgls_nent[PRD_TABLES_NUM]; u8 prd_tbl_num; diff --git a/drivers/hid/spi-hid/Kconfig b/drivers/hid/spi-hid/Kconfig new file mode 100644 index 00000000000000..59076c6ebeed9b --- /dev/null +++ b/drivers/hid/spi-hid/Kconfig @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: GPL-2.0-only +menu "SPI HID support" + depends on SPI + +config SPI_HID_APPLE_OF + tristate "HID over SPI transport layer for Apple Silicon SoCs" + depends on INPUT && OF + select SPI_HID_APPLE_CORE + help + Say Y here if you use Apple Silicon based laptop. The keyboard and + touchpad are HID based devices connected via SPI. + + If unsure, say N. + + This support is also available as a module. If so, the module + will be called spi-hid-apple-of. It will also build/depend on the + module spi-hid-apple. + +endmenu + +config SPI_HID_APPLE_CORE + tristate + select HID + select CRC16 diff --git a/drivers/hid/spi-hid/Makefile b/drivers/hid/spi-hid/Makefile new file mode 100644 index 00000000000000..f276ee12cb94fc --- /dev/null +++ b/drivers/hid/spi-hid/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for SPI HID tarnsport drivers +# + +obj-$(CONFIG_SPI_HID_APPLE_CORE) += spi-hid-apple.o + +spi-hid-apple-objs = spi-hid-apple-core.o + +obj-$(CONFIG_SPI_HID_APPLE_OF) += spi-hid-apple-of.o diff --git a/drivers/hid/spi-hid/spi-hid-apple-core.c b/drivers/hid/spi-hid/spi-hid-apple-core.c new file mode 100644 index 00000000000000..2ed909895391c8 --- /dev/null +++ b/drivers/hid/spi-hid/spi-hid-apple-core.c @@ -0,0 +1,1194 @@ +/* + * SPDX-License-Identifier: GPL-2.0 + * + * Apple SPI HID transport driver + * + * Copyright (C) The Asahi Linux Contributors + * + * Based on: drivers/input/applespi.c + * + * MacBook (Pro) SPI keyboard and touchpad driver + * + * Copyright (c) 2015-2018 Federico Lorenzi + * Copyright (c) 2017-2018 Ronald Tschalär + * + */ + +//#define DEBUG 2 + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "spi-hid-apple.h" + +#define SPIHID_DEF_WAIT msecs_to_jiffies(1000) + +#define SPIHID_MAX_INPUT_REPORT_SIZE 0x800 + +/* support only keyboard, trackpad and management dev for now */ +#define SPIHID_MAX_DEVICES 3 + +#define SPIHID_DEVICE_ID_MNGT 0x0 +#define SPIHID_DEVICE_ID_KBD 0x1 +#define SPIHID_DEVICE_ID_TP 0x2 +#define SPIHID_DEVICE_ID_INFO 0xd0 + +#define SPIHID_READ_PACKET 0x20 +#define SPIHID_WRITE_PACKET 0x40 + +#define SPIHID_DESC_MAX 512 + +#define SPIHID_SET_LEDS 0x0151 /* caps lock */ + +#define SPI_RW_CHG_DELAY_US 200 /* 'Inter Stage Us'? */ + +static const u8 spi_hid_apple_booted[4] = { 0xa0, 0x80, 0x00, 0x00 }; +static const u8 spi_hid_apple_status_ok[4] = { 0xac, 0x27, 0x68, 0xd5 }; + +struct spihid_interface { + struct hid_device *hid; + u8 *hid_desc; + u32 hid_desc_len; + u32 id; + unsigned country; + u32 max_control_report_len; + u32 max_input_report_len; + u32 max_output_report_len; + u8 name[32]; + u8 reply_buf[SPIHID_DESC_MAX]; + u32 reply_len; + bool ready; +}; + +struct spihid_input_report { + u8 *buf; + u32 length; + u32 offset; + u8 device; + u8 flags; +}; + +struct spihid_apple { + struct spi_device *spidev; + + struct spihid_apple_ops *ops; + + struct spihid_interface mngt; + struct spihid_interface kbd; + struct spihid_interface tp; + + wait_queue_head_t wait; + struct mutex tx_lock; //< protects against concurrent SPI writes + + struct spi_message rx_msg; + struct spi_message tx_msg; + struct spi_transfer rx_transfer; + struct spi_transfer tx_transfer; + struct spi_transfer status_transfer; + + u8 *rx_buf; + u8 *tx_buf; + u8 *status_buf; + + u8 vendor[32]; + u8 product[64]; + u8 serial[32]; + + u32 num_devices; + + u32 vendor_id; + u32 product_id; + u32 version_number; + + u8 msg_id; + + /* fragmented HID report */ + struct spihid_input_report report; + + /* state tracking flags */ + bool status_booted; + +#ifdef IRQ_WAKE_SUPPORT + bool irq_wake_enabled; +#endif +}; + +/** + * struct spihid_msg_hdr - common header of protocol messages. + * + * Each message begins with fixed header, followed by a message-type specific + * payload, and ends with a 16-bit crc. Because of the varying lengths of the + * payload, the crc is defined at the end of each payload struct, rather than + * in this struct. + * + * @unknown0: request type? output, input (0x10), feature, protocol + * @unknown1: maybe report id? + * @unknown2: mostly zero, in info request maybe device num + * @id: incremented on each message, rolls over after 255; there is a + * separate counter for each message type. + * @rsplen: response length (the exact nature of this field is quite + * speculative). On a request/write this is often the same as + * @length, though in some cases it has been seen to be much larger + * (e.g. 0x400); on a response/read this the same as on the + * request; for reads that are not responses it is 0. + * @length: length of the remainder of the data in the whole message + * structure (after re-assembly in case of being split over + * multiple spi-packets), minus the trailing crc. The total size + * of a message is therefore @length + 10. + */ + +struct spihid_msg_hdr { + u8 unknown0; + u8 unknown1; + u8 unknown2; + u8 id; + __le16 rsplen; + __le16 length; +}; + +/** + * struct spihid_transfer_packet - a complete spi packet; always 256 bytes. This carries + * the (parts of the) message in the data. But note that this does not + * necessarily contain a complete message, as in some cases (e.g. many + * fingers pressed) the message is split over multiple packets (see the + * @offset, @remain, and @length fields). In general the data parts in + * spihid_transfer_packet's are concatenated until @remaining is 0, and the + * result is an message. + * + * @flags: 0x40 = write (to device), 0x20 = read (from device); note that + * the response to a write still has 0x40. + * @device: 1 = keyboard, 2 = touchpad + * @offset: specifies the offset of this packet's data in the complete + * message; i.e. > 0 indicates this is a continuation packet (in + * the second packet for a message split over multiple packets + * this would then be the same as the @length in the first packet) + * @remain: number of message bytes remaining in subsequents packets (in + * the first packet of a message split over two packets this would + * then be the same as the @length in the second packet) + * @length: length of the valid data in the @data in this packet + * @data: all or part of a message + * @crc16: crc over this whole structure minus this @crc16 field. This + * covers just this packet, even on multi-packet messages (in + * contrast to the crc in the message). + */ +struct spihid_transfer_packet { + u8 flags; + u8 device; + __le16 offset; + __le16 remain; + __le16 length; + u8 data[246]; + __le16 crc16; +}; + +/* + * how HID is mapped onto the protocol is not fully clear. This are the known + * reports/request: + * + * pkt.flags pkt.dev? msg.u0 msg.u1 msg.u2 + * info 0x40 0xd0 0x20 0x01 0xd0 + * + * info mngt: 0x40 0xd0 0x20 0x10 0x00 + * info kbd: 0x40 0xd0 0x20 0x10 0x01 + * info tp: 0x40 0xd0 0x20 0x10 0x02 + * + * desc kbd: 0x40 0xd0 0x20 0x10 0x01 + * desc trackpad: 0x40 0xd0 0x20 0x10 0x02 + * + * mt mode: 0x40 0x02 0x52 0x02 0x00 set protocol? + * capslock led 0x40 0x01 0x51 0x01 0x00 output report + * + * report kbd: 0x20 0x01 0x10 0x01 0x00 input report + * report tp: 0x20 0x02 0x10 0x02 0x00 input report + * + */ + + +static int spihid_apple_request(struct spihid_apple *spihid, u8 target, u8 unk0, + u8 unk1, u8 unk2, u16 resp_len, u8 *buf, + size_t len) +{ + struct spihid_transfer_packet *pkt; + struct spihid_msg_hdr *hdr; + u16 crc; + int err; + + /* know reports are small enoug to fit in a single packet */ + if (len > sizeof(pkt->data) - sizeof(*hdr) - sizeof(__le16)) + return -EINVAL; + + err = mutex_lock_interruptible(&spihid->tx_lock); + if (err < 0) + return err; + + pkt = (struct spihid_transfer_packet *)spihid->tx_buf; + + memset(pkt, 0, sizeof(*pkt)); + pkt->flags = SPIHID_WRITE_PACKET; + pkt->device = target; + pkt->length = cpu_to_le16(sizeof(*hdr) + len + sizeof(__le16)); + + hdr = (struct spihid_msg_hdr *)&pkt->data[0]; + hdr->unknown0 = unk0; + hdr->unknown1 = unk1; + hdr->unknown2 = unk2; + hdr->id = spihid->msg_id++; + hdr->rsplen = cpu_to_le16(resp_len); + hdr->length = cpu_to_le16(len); + + if (len) + memcpy(pkt->data + sizeof(*hdr), buf, len); + crc = crc16(0, &pkt->data[0], sizeof(*hdr) + len); + put_unaligned_le16(crc, pkt->data + sizeof(*hdr) + len); + + pkt->crc16 = cpu_to_le16(crc16(0, spihid->tx_buf, + offsetof(struct spihid_transfer_packet, crc16))); + + memset(spihid->status_buf, 0, sizeof(spi_hid_apple_status_ok)); + + err = spi_sync(spihid->spidev, &spihid->tx_msg); + + if (memcmp(spihid->status_buf, spi_hid_apple_status_ok, + sizeof(spi_hid_apple_status_ok))) { + u8 *b = spihid->status_buf; + dev_warn_ratelimited(&spihid->spidev->dev, "status message " + "mismatch: %02x %02x %02x %02x\n", + b[0], b[1], b[2], b[3]); + } + mutex_unlock(&spihid->tx_lock); + if (err < 0) + return err; + + return (int)len; +} + +static struct spihid_apple *spihid_get_data(struct spihid_interface *idev) +{ + switch (idev->id) { + case SPIHID_DEVICE_ID_KBD: + return container_of(idev, struct spihid_apple, kbd); + case SPIHID_DEVICE_ID_TP: + return container_of(idev, struct spihid_apple, tp); + default: + return NULL; + } +} + +static int apple_ll_start(struct hid_device *hdev) +{ + /* no-op SPI transport is already setup */ + return 0; +}; + +static void apple_ll_stop(struct hid_device *hdev) +{ + /* no-op, devices will be desstroyed on driver destruction */ +} + +static int apple_ll_open(struct hid_device *hdev) +{ + struct spihid_apple *spihid; + struct spihid_interface *idev = hdev->driver_data; + + if (idev->hid_desc_len == 0) { + spihid = spihid_get_data(idev); + dev_warn(&spihid->spidev->dev, + "HID descriptor missing for dev %u", idev->id); + } else + idev->ready = true; + + return 0; +} + +static void apple_ll_close(struct hid_device *hdev) +{ + struct spihid_interface *idev = hdev->driver_data; + idev->ready = false; +} + +static int apple_ll_parse(struct hid_device *hdev) +{ + struct spihid_interface *idev = hdev->driver_data; + + return hid_parse_report(hdev, idev->hid_desc, idev->hid_desc_len); +} + +static int apple_ll_raw_request(struct hid_device *hdev, + unsigned char reportnum, __u8 *buf, size_t len, + unsigned char rtype, int reqtype) +{ + struct spihid_interface *idev = hdev->driver_data; + struct spihid_apple *spihid = spihid_get_data(idev); + int ret; + + dev_dbg(&spihid->spidev->dev, + "apple_ll_raw_request: device:%u reportnum:%hhu rtype:%hhu", + idev->id, reportnum, rtype); + + switch (reqtype) { + case HID_REQ_GET_REPORT: + if (rtype != HID_FEATURE_REPORT) + return -EINVAL; + + idev->reply_len = 0; + ret = spihid_apple_request(spihid, idev->id, 0x32, reportnum, 0x00, len, NULL, 0); + if (ret < 0) + return ret; + + ret = wait_event_interruptible_timeout(spihid->wait, idev->reply_len, + SPIHID_DEF_WAIT); + if (ret == 0) + ret = -ETIMEDOUT; + if (ret < 0) { + dev_err(&spihid->spidev->dev, "waiting for get report failed: %d", ret); + return ret; + } + memcpy(buf, idev->reply_buf, max_t(size_t, len, idev->reply_len)); + return idev->reply_len; + + case HID_REQ_SET_REPORT: + if (buf[0] != reportnum) + return -EINVAL; + if (reportnum != idev->id) { + dev_warn(&spihid->spidev->dev, + "device:%u reportnum:" + "%hhu mismatch", + idev->id, reportnum); + return -EINVAL; + } + return spihid_apple_request(spihid, idev->id, 0x52, reportnum, 0x00, 2, buf, len); + default: + return -EIO; + } +} + +static int apple_ll_output_report(struct hid_device *hdev, __u8 *buf, + size_t len) +{ + struct spihid_interface *idev = hdev->driver_data; + struct spihid_apple *spihid = spihid_get_data(idev); + if (!spihid) + return -1; + + dev_dbg(&spihid->spidev->dev, + "apple_ll_output_report: device:%u len:%zu:", + idev->id, len); + // second idev->id should maybe be buf[0]? + return spihid_apple_request(spihid, idev->id, 0x51, idev->id, 0x00, 0, buf, len); +} + +static struct hid_ll_driver apple_hid_ll = { + .start = &apple_ll_start, + .stop = &apple_ll_stop, + .open = &apple_ll_open, + .close = &apple_ll_close, + .parse = &apple_ll_parse, + .raw_request = &apple_ll_raw_request, + .output_report = &apple_ll_output_report, + .max_buffer_size = SPIHID_MAX_INPUT_REPORT_SIZE, +}; + +static struct spihid_interface *spihid_get_iface(struct spihid_apple *spihid, + u32 iface) +{ + switch (iface) { + case SPIHID_DEVICE_ID_MNGT: + return &spihid->mngt; + case SPIHID_DEVICE_ID_KBD: + return &spihid->kbd; + case SPIHID_DEVICE_ID_TP: + return &spihid->tp; + default: + return NULL; + } +} + +static int spihid_verify_msg(struct spihid_apple *spihid, u8 *buf, size_t len) +{ + u16 msg_crc, crc; + struct device *dev = &spihid->spidev->dev; + + crc = crc16(0, buf, len - sizeof(__le16)); + msg_crc = get_unaligned_le16(buf + len - sizeof(__le16)); + if (crc != msg_crc) { + dev_warn_ratelimited(dev, "Read message crc mismatch\n"); + return 0; + } + return 1; +} + +static bool spihid_status_report(struct spihid_apple *spihid, u8 *pl, + size_t len) +{ + struct device *dev = &spihid->spidev->dev; + dev_dbg(dev, "%s: len: %zu", __func__, len); + if (len == 5 && pl[0] == 0xe0) + return true; + + return false; +} + +static bool spihid_process_input_report(struct spihid_apple *spihid, u32 device, + struct spihid_msg_hdr *hdr, u8 *payload, + size_t len) +{ + //dev_dbg(&spihid>spidev->dev, "input report: req:%hx iface:%u ", hdr->unknown0, device); + if (hdr->unknown0 != 0x10) + return false; + + /* HID device as well but Vendor usage only, handle it internally for now */ + if (device == 0) { + if (hdr->unknown1 == 0xe0) { + return spihid_status_report(spihid, payload, len); + } + } else if (device < SPIHID_MAX_DEVICES) { + struct spihid_interface *iface = + spihid_get_iface(spihid, device); + if (iface && iface->hid && iface->ready) { + hid_input_report(iface->hid, HID_INPUT_REPORT, payload, + len, 1); + return true; + } + } else + dev_dbg(&spihid->spidev->dev, + "unexpected iface:%u for input report", device); + + return false; +} + +struct spihid_device_info { + __le16 u0[2]; + __le16 num_devices; + __le16 vendor_id; + __le16 product_id; + __le16 version_number; + __le16 vendor_str[2]; //< offset and string length + __le16 product_str[2]; //< offset and string length + __le16 serial_str[2]; //< offset and string length +}; + +static bool spihid_process_device_info(struct spihid_apple *spihid, u32 iface, + u8 *payload, size_t len) +{ + struct device *dev = &spihid->spidev->dev; + + if (iface != SPIHID_DEVICE_ID_INFO) + return false; + + if (spihid->vendor_id == 0 && + len >= sizeof(struct spihid_device_info)) { + struct spihid_device_info *info = + (struct spihid_device_info *)payload; + u16 voff, vlen, poff, plen, soff, slen; + u32 num_devices; + + num_devices = __le16_to_cpu(info->num_devices); + + if (num_devices < SPIHID_MAX_DEVICES) { + dev_err(dev, + "Device info reports %u devices, expecting at least 3", + num_devices); + return false; + } + spihid->num_devices = num_devices; + + if (spihid->num_devices > SPIHID_MAX_DEVICES) { + dev_info( + dev, + "limiting the number of devices to mngt, kbd and mouse"); + spihid->num_devices = SPIHID_MAX_DEVICES; + } + + spihid->vendor_id = __le16_to_cpu(info->vendor_id); + spihid->product_id = __le16_to_cpu(info->product_id); + spihid->version_number = __le16_to_cpu(info->version_number); + + voff = __le16_to_cpu(info->vendor_str[0]); + vlen = __le16_to_cpu(info->vendor_str[1]); + + if (voff < len && vlen <= len - voff && + vlen < sizeof(spihid->vendor)) { + memcpy(spihid->vendor, payload + voff, vlen); + spihid->vendor[vlen] = '\0'; + } + + poff = __le16_to_cpu(info->product_str[0]); + plen = __le16_to_cpu(info->product_str[1]); + + if (poff < len && plen <= len - poff && + plen < sizeof(spihid->product)) { + memcpy(spihid->product, payload + poff, plen); + spihid->product[plen] = '\0'; + } + + soff = __le16_to_cpu(info->serial_str[0]); + slen = __le16_to_cpu(info->serial_str[1]); + + if (soff < len && slen <= len - soff && + slen < sizeof(spihid->serial)) { + memcpy(spihid->vendor, payload + soff, slen); + spihid->serial[slen] = '\0'; + } + + wake_up_interruptible(&spihid->wait); + } + return true; +} + +struct spihid_iface_info { + u8 u_0; + u8 interface_num; + u8 u_2; + u8 u_3; + u8 u_4; + u8 country_code; + __le16 max_input_report_len; + __le16 max_output_report_len; + __le16 max_control_report_len; + __le16 name_offset; + __le16 name_length; +}; + +static bool spihid_process_iface_info(struct spihid_apple *spihid, u32 num, + u8 *payload, size_t len) +{ + struct spihid_iface_info *info; + struct spihid_interface *iface = spihid_get_iface(spihid, num); + u32 name_off, name_len; + + if (!iface) + return false; + + if (!iface->max_input_report_len) { + if (len < sizeof(*info)) + return false; + + info = (struct spihid_iface_info *)payload; + + iface->max_input_report_len = + le16_to_cpu(info->max_input_report_len); + iface->max_output_report_len = + le16_to_cpu(info->max_output_report_len); + iface->max_control_report_len = + le16_to_cpu(info->max_control_report_len); + iface->country = info->country_code; + + name_off = le16_to_cpu(info->name_offset); + name_len = le16_to_cpu(info->name_length); + + if (name_off < len && name_len <= len - name_off && + name_len < sizeof(iface->name)) { + memcpy(iface->name, payload + name_off, name_len); + iface->name[name_len] = '\0'; + } + + dev_dbg(&spihid->spidev->dev, "Info for %s, country code: 0x%x", + iface->name, iface->country); + + wake_up_interruptible(&spihid->wait); + } + + return true; +} + +static int spihid_register_hid_device(struct spihid_apple *spihid, + struct spihid_interface *idev, u8 device); + +static bool spihid_process_iface_hid_report_desc(struct spihid_apple *spihid, + u32 num, u8 *payload, + size_t len) +{ + struct spihid_interface *iface = spihid_get_iface(spihid, num); + + if (!iface) + return false; + + if (iface->hid_desc_len == 0) { + if (len > SPIHID_DESC_MAX) + return false; + memcpy(iface->hid_desc, payload, len); + iface->hid_desc_len = len; + + /* do not register the mngt iface as HID device */ + if (num > 0) + spihid_register_hid_device(spihid, iface, num); + + wake_up_interruptible(&spihid->wait); + } + return true; +} + +static bool spihid_process_iface_get_report(struct spihid_apple *spihid, + u32 device, u8 report, + u8 *payload, size_t len) +{ + struct spihid_interface *iface = spihid_get_iface(spihid, device); + + if (!iface) + return false; + + if (len > sizeof(iface->reply_buf) || len < 1) + return false; + + memcpy(iface->reply_buf, payload, len); + iface->reply_len = len; + + wake_up_interruptible(&spihid->wait); + + return true; +} + +static bool spihid_process_response(struct spihid_apple *spihid, u32 device, + struct spihid_msg_hdr *hdr, u8 *payload, + size_t len) +{ + if (hdr->unknown0 == 0x20) { + switch (hdr->unknown1) { + case 0x01: + return spihid_process_device_info(spihid, hdr->unknown2, + payload, len); + case 0x02: + return spihid_process_iface_info(spihid, hdr->unknown2, + payload, len); + case 0x10: + return spihid_process_iface_hid_report_desc( + spihid, hdr->unknown2, payload, len); + default: + break; + } + } + + if (hdr->unknown0 == 0x32) { + return spihid_process_iface_get_report(spihid, device, hdr->unknown1, payload, len); + } + + return false; +} + +static void spihid_process_message(struct spihid_apple *spihid, u8 *data, + size_t length, u8 device, u8 flags) +{ + struct device *dev = &spihid->spidev->dev; + struct spihid_msg_hdr *hdr; + bool handled = false; + size_t payload_len; + u8 *payload; + + if (!spihid_verify_msg(spihid, data, length)) + return; + + hdr = (struct spihid_msg_hdr *)data; + payload_len = le16_to_cpu(hdr->length); + + if (payload_len == 0 || + (payload_len + sizeof(struct spihid_msg_hdr) + 2) > length) + return; + + payload = data + sizeof(struct spihid_msg_hdr); + + switch (flags) { + case SPIHID_READ_PACKET: + handled = spihid_process_input_report(spihid, device, hdr, + payload, payload_len); + break; + case SPIHID_WRITE_PACKET: + handled = spihid_process_response(spihid, device, hdr, payload, + payload_len); + break; + default: + break; + } + +#if defined(DEBUG) && DEBUG > 1 + { + dev_dbg(dev, + "R msg: req:%02hhx rep:%02hhx dev:%02hhx id:%hu len:%hu\n", + hdr->unknown0, hdr->unknown1, hdr->unknown2, hdr->id, + hdr->length); + print_hex_dump_debug("spihid msg: ", DUMP_PREFIX_OFFSET, 16, 1, + payload, le16_to_cpu(hdr->length), true); + } +#else + if (!handled) { + dev_dbg(dev, + "R unhandled msg: req:%02hhx rep:%02hhx dev:%02hhx id:%hu len:%hu\n", + hdr->unknown0, hdr->unknown1, hdr->unknown2, hdr->id, + hdr->length); + print_hex_dump_debug("spihid msg: ", DUMP_PREFIX_OFFSET, 16, 1, + payload, le16_to_cpu(hdr->length), true); + } +#endif +} + +static void spihid_assemble_message(struct spihid_apple *spihid, + struct spihid_transfer_packet *pkt) +{ + size_t length, offset, remain; + struct device *dev = &spihid->spidev->dev; + struct spihid_input_report *rep = &spihid->report; + + length = le16_to_cpu(pkt->length); + remain = le16_to_cpu(pkt->remain); + offset = le16_to_cpu(pkt->offset); + + if (offset + length + remain > U16_MAX) { + return; + } + + if (pkt->device != rep->device || pkt->flags != rep->flags || + offset != rep->offset) { + rep->device = 0; + rep->flags = 0; + rep->offset = 0; + rep->length = 0; + } + + if (offset == 0) { + if (rep->offset != 0) { + dev_warn(dev, "incomplete report off:%u len:%u", + rep->offset, rep->length); + } + memcpy(rep->buf, pkt->data, length); + rep->offset = length; + rep->length = length + remain; + rep->device = pkt->device; + rep->flags = pkt->flags; + } else if (offset == rep->offset) { + if (offset + length + remain != rep->length) { + dev_warn(dev, "incomplete report off:%u len:%u", + rep->offset, rep->length); + return; + } + memcpy(rep->buf + offset, pkt->data, length); + rep->offset += length; + + if (rep->offset == rep->length) { + spihid_process_message(spihid, rep->buf, rep->length, + rep->device, rep->flags); + rep->device = 0; + rep->flags = 0; + rep->offset = 0; + rep->length = 0; + } + } +} + +static void spihid_process_read(struct spihid_apple *spihid) +{ + u16 crc; + size_t length; + struct device *dev = &spihid->spidev->dev; + struct spihid_transfer_packet *pkt; + + pkt = (struct spihid_transfer_packet *)spihid->rx_buf; + + /* check transfer packet crc */ + crc = crc16(0, spihid->rx_buf, + offsetof(struct spihid_transfer_packet, crc16)); + if (crc != le16_to_cpu(pkt->crc16)) { + dev_warn_ratelimited(dev, "Read package crc mismatch\n"); + return; + } + + length = le16_to_cpu(pkt->length); + + if (length < sizeof(struct spihid_msg_hdr) + 2) { + if (length == sizeof(spi_hid_apple_booted) && + !memcmp(pkt->data, spi_hid_apple_booted, length)) { + if (!spihid->status_booted) { + spihid->status_booted = true; + wake_up_interruptible(&spihid->wait); + } + } else { + dev_info(dev, "R short packet: len:%zu\n", length); + print_hex_dump(KERN_INFO, "spihid pkt:", + DUMP_PREFIX_OFFSET, 16, 1, pkt->data, + length, false); + } + return; + } + +#if defined(DEBUG) && DEBUG > 1 + dev_dbg(dev, + "R pkt: flags:%02hhx dev:%02hhx off:%hu remain:%hu, len:%zu\n", + pkt->flags, pkt->device, pkt->offset, pkt->remain, length); +#if defined(DEBUG) && DEBUG > 2 + print_hex_dump_debug("spihid pkt: ", DUMP_PREFIX_OFFSET, 16, 1, + spihid->rx_buf, + sizeof(struct spihid_transfer_packet), true); +#endif +#endif + + if (length > sizeof(pkt->data)) { + dev_warn_ratelimited(dev, "Invalid pkt len:%zu", length); + return; + } + + /* short message */ + if (pkt->offset == 0 && pkt->remain == 0) { + spihid_process_message(spihid, pkt->data, length, pkt->device, + pkt->flags); + } else { + spihid_assemble_message(spihid, pkt); + } +} + +static void spihid_read_packet_sync(struct spihid_apple *spihid) +{ + int err; + + err = spi_sync(spihid->spidev, &spihid->rx_msg); + if (!err) { + spihid_process_read(spihid); + } else { + dev_warn(&spihid->spidev->dev, "RX failed: %d\n", err); + } +} + +irqreturn_t spihid_apple_core_irq(int irq, void *data) +{ + struct spi_device *spi = data; + struct spihid_apple *spihid = spi_get_drvdata(spi); + + spihid_read_packet_sync(spihid); + + return IRQ_HANDLED; +} +EXPORT_SYMBOL_GPL(spihid_apple_core_irq); + +static void spihid_apple_setup_spi_msgs(struct spihid_apple *spihid) +{ + memset(&spihid->rx_transfer, 0, sizeof(spihid->rx_transfer)); + + spihid->rx_transfer.rx_buf = spihid->rx_buf; + spihid->rx_transfer.len = sizeof(struct spihid_transfer_packet); + + spi_message_init(&spihid->rx_msg); + spi_message_add_tail(&spihid->rx_transfer, &spihid->rx_msg); + + memset(&spihid->tx_transfer, 0, sizeof(spihid->rx_transfer)); + memset(&spihid->status_transfer, 0, sizeof(spihid->status_transfer)); + + spihid->tx_transfer.tx_buf = spihid->tx_buf; + spihid->tx_transfer.len = sizeof(struct spihid_transfer_packet); + spihid->tx_transfer.delay.unit = SPI_DELAY_UNIT_USECS; + spihid->tx_transfer.delay.value = SPI_RW_CHG_DELAY_US; + + spihid->status_transfer.rx_buf = spihid->status_buf; + spihid->status_transfer.len = sizeof(spi_hid_apple_status_ok); + + spi_message_init(&spihid->tx_msg); + spi_message_add_tail(&spihid->tx_transfer, &spihid->tx_msg); + spi_message_add_tail(&spihid->status_transfer, &spihid->tx_msg); +} + +static int spihid_apple_setup_spi(struct spihid_apple *spihid) +{ + spihid_apple_setup_spi_msgs(spihid); + + return spihid->ops->power_on(spihid->ops); +} + +static int spihid_register_hid_device(struct spihid_apple *spihid, + struct spihid_interface *iface, u8 device) +{ + int ret; + char *suffix; + struct hid_device *hid; + + iface->id = device; + + hid = hid_allocate_device(); + if (IS_ERR(hid)) + return PTR_ERR(hid); + + /* + * Use 'Apple SPI Keyboard' and 'Apple SPI Trackpad' as input device + * names. The device names need to be distinct since at least Kwin uses + * the tripple Vendor ID, Product ID, Name to identify devices. + */ + snprintf(hid->name, sizeof(hid->name), "Apple SPI %s", iface->name); + // strip ' / Boot' suffix from the name + suffix = strstr(hid->name, " / Boot"); + if (suffix) + suffix[0] = '\0'; + snprintf(hid->phys, sizeof(hid->phys), "%s (%hhx)", + dev_name(&spihid->spidev->dev), device); + strscpy(hid->uniq, spihid->serial, sizeof(hid->uniq)); + + hid->ll_driver = &apple_hid_ll; + hid->bus = BUS_SPI; + hid->vendor = spihid->vendor_id; + hid->product = spihid->product_id; + hid->version = spihid->version_number; + + if (device == SPIHID_DEVICE_ID_KBD) + hid->type = HID_TYPE_SPI_KEYBOARD; + else if (device == SPIHID_DEVICE_ID_TP) + hid->type = HID_TYPE_SPI_MOUSE; + + hid->country = iface->country; + hid->dev.parent = &spihid->spidev->dev; + hid->driver_data = iface; + + ret = hid_add_device(hid); + if (ret < 0) { + hid_destroy_device(hid); + dev_warn(&spihid->spidev->dev, + "Failed to register hid device %hhu", device); + return ret; + } + + iface->hid = hid; + + return 0; +} + +static void spihid_destroy_hid_device(struct spihid_interface *iface) +{ + if (iface->hid) { + hid_destroy_device(iface->hid); + iface->hid = NULL; + } + iface->ready = false; +} + +int spihid_apple_core_probe(struct spi_device *spi, struct spihid_apple_ops *ops) +{ + struct device *dev = &spi->dev; + struct spihid_apple *spihid; + int err, i; + + if (!ops || !ops->power_on || !ops->power_off || !ops->enable_irq || !ops->disable_irq) + return -EINVAL; + + spihid = devm_kzalloc(dev, sizeof(*spihid), GFP_KERNEL); + if (!spihid) + return -ENOMEM; + + spihid->ops = ops; + spihid->spidev = spi; + + // init spi + spi_set_drvdata(spi, spihid); + + /* + * allocate SPI buffers + * Overallocate the receice buffer since it passed directly into + * hid_input_report / hid_report_raw_event. The later expects the buffer + * to be HID_MAX_BUFFER_SIZE (16k) or hid_ll_driver.max_buffer_size if + * set. + */ + spihid->rx_buf = devm_kmalloc( + &spi->dev, SPIHID_MAX_INPUT_REPORT_SIZE, GFP_KERNEL); + spihid->tx_buf = devm_kmalloc( + &spi->dev, sizeof(struct spihid_transfer_packet), GFP_KERNEL); + spihid->status_buf = devm_kmalloc( + &spi->dev, sizeof(spi_hid_apple_status_ok), GFP_KERNEL); + + if (!spihid->rx_buf || !spihid->tx_buf || !spihid->status_buf) + return -ENOMEM; + + spihid->report.buf = + devm_kmalloc(dev, SPIHID_MAX_INPUT_REPORT_SIZE, GFP_KERNEL); + + spihid->kbd.hid_desc = devm_kmalloc(dev, SPIHID_DESC_MAX, GFP_KERNEL); + spihid->tp.hid_desc = devm_kmalloc(dev, SPIHID_DESC_MAX, GFP_KERNEL); + + if (!spihid->report.buf || !spihid->kbd.hid_desc || + !spihid->tp.hid_desc) + return -ENOMEM; + + init_waitqueue_head(&spihid->wait); + + mutex_init(&spihid->tx_lock); + + /* Init spi transfer buffers and power device on */ + err = spihid_apple_setup_spi(spihid); + if (err < 0) + goto error; + + /* enable HID irq */ + spihid->ops->enable_irq(spihid->ops); + + // wait for boot message + err = wait_event_interruptible_timeout(spihid->wait, + spihid->status_booted, + msecs_to_jiffies(1000)); + if (err == 0) + err = -ENODEV; + if (err < 0) { + dev_err(dev, "waiting for device boot failed: %d", err); + goto error; + } + + /* request device information */ + dev_dbg(dev, "request device info"); + spihid_apple_request(spihid, 0xd0, 0x20, 0x01, 0xd0, 0, NULL, 0); + err = wait_event_interruptible_timeout(spihid->wait, spihid->vendor_id, + SPIHID_DEF_WAIT); + if (err == 0) + err = -ENODEV; + if (err < 0) { + dev_err(dev, "waiting for device info failed: %d", err); + goto error; + } + + /* request interface information */ + for (i = 0; i < spihid->num_devices; i++) { + struct spihid_interface *iface = spihid_get_iface(spihid, i); + if (!iface) + continue; + dev_dbg(dev, "request interface info 0x%02x", i); + spihid_apple_request(spihid, 0xd0, 0x20, 0x02, i, + SPIHID_DESC_MAX, NULL, 0); + err = wait_event_interruptible_timeout( + spihid->wait, iface->max_input_report_len, + SPIHID_DEF_WAIT); + } + + /* request HID report descriptors */ + for (i = 1; i < spihid->num_devices; i++) { + struct spihid_interface *iface = spihid_get_iface(spihid, i); + if (!iface) + continue; + dev_dbg(dev, "request hid report desc 0x%02x", i); + spihid_apple_request(spihid, 0xd0, 0x20, 0x10, i, + SPIHID_DESC_MAX, NULL, 0); + wait_event_interruptible_timeout( + spihid->wait, iface->hid_desc_len, SPIHID_DEF_WAIT); + } + + return 0; +error: + return err; +} +EXPORT_SYMBOL_GPL(spihid_apple_core_probe); + +void spihid_apple_core_remove(struct spi_device *spi) +{ + struct spihid_apple *spihid = spi_get_drvdata(spi); + + /* destroy input devices */ + + spihid_destroy_hid_device(&spihid->tp); + spihid_destroy_hid_device(&spihid->kbd); + + /* disable irq */ + spihid->ops->disable_irq(spihid->ops); + + /* power SPI device down */ + spihid->ops->power_off(spihid->ops); +} +EXPORT_SYMBOL_GPL(spihid_apple_core_remove); + +void spihid_apple_core_shutdown(struct spi_device *spi) +{ + struct spihid_apple *spihid = spi_get_drvdata(spi); + + /* disable irq */ + spihid->ops->disable_irq(spihid->ops); + + /* power SPI device down */ + spihid->ops->power_off(spihid->ops); +} +EXPORT_SYMBOL_GPL(spihid_apple_core_shutdown); + +#ifdef CONFIG_PM_SLEEP +static int spihid_apple_core_suspend(struct device *dev) +{ + int ret; +#ifdef IRQ_WAKE_SUPPORT + int wake_status; +#endif + struct spihid_apple *spihid = spi_get_drvdata(to_spi_device(dev)); + + if (spihid->tp.hid) { + ret = hid_driver_suspend(spihid->tp.hid, PMSG_SUSPEND); + if (ret < 0) + return ret; + } + + if (spihid->kbd.hid) { + ret = hid_driver_suspend(spihid->kbd.hid, PMSG_SUSPEND); + if (ret < 0) { + if (spihid->tp.hid) + hid_driver_resume(spihid->tp.hid); + return ret; + } + } + + /* Save some power */ + spihid->ops->disable_irq(spihid->ops); + +#ifdef IRQ_WAKE_SUPPORT + if (device_may_wakeup(dev)) { + wake_status = spihid->ops->enable_irq_wake(spihid->ops); + if (!wake_status) + spihid->irq_wake_enabled = true; + else + dev_warn(dev, "Failed to enable irq wake: %d\n", + wake_status); + } else { + spihid->ops->power_off(spihid->ops); + } +#else + spihid->ops->power_off(spihid->ops); +#endif + + return 0; +} + +static int spihid_apple_core_resume(struct device *dev) +{ + int ret_tp = 0, ret_kbd = 0; + struct spihid_apple *spihid = spi_get_drvdata(to_spi_device(dev)); +#ifdef IRQ_WAKE_SUPPORT + int wake_status; + + if (!device_may_wakeup(dev)) { + spihid->ops->power_on(spihid->ops); + } else if (spihid->irq_wake_enabled) { + wake_status = spihid->ops->disable_irq_wake(spihid->ops); + if (!wake_status) + spihid->irq_wake_enabled = false; + else + dev_warn(dev, "Failed to disable irq wake: %d\n", + wake_status); + } +#endif + + spihid->ops->enable_irq(spihid->ops); + spihid->ops->power_on(spihid->ops); + + if (spihid->tp.hid) + ret_tp = hid_driver_reset_resume(spihid->tp.hid); + if (spihid->kbd.hid) + ret_kbd = hid_driver_reset_resume(spihid->kbd.hid); + + if (ret_tp < 0) + return ret_tp; + + return ret_kbd; +} +#endif + +const struct dev_pm_ops spihid_apple_core_pm = { + SET_SYSTEM_SLEEP_PM_OPS(spihid_apple_core_suspend, + spihid_apple_core_resume) +}; +EXPORT_SYMBOL_GPL(spihid_apple_core_pm); + +MODULE_DESCRIPTION("Apple SPI HID transport driver"); +MODULE_AUTHOR("Janne Grunau "); +MODULE_LICENSE("GPL"); diff --git a/drivers/hid/spi-hid/spi-hid-apple-of.c b/drivers/hid/spi-hid/spi-hid-apple-of.c new file mode 100644 index 00000000000000..b631212b836d30 --- /dev/null +++ b/drivers/hid/spi-hid/spi-hid-apple-of.c @@ -0,0 +1,153 @@ +/* + * SPDX-License-Identifier: GPL-2.0 + * + * Apple SPI HID transport driver - Open Firmware + * + * Copyright (C) The Asahi Linux Contributors + */ + +#include +#include +#include +#include + +#include "spi-hid-apple.h" + + +struct spihid_apple_of { + struct spihid_apple_ops ops; + + struct gpio_desc *enable_gpio; + int irq; +}; + +static int spihid_apple_of_power_on(struct spihid_apple_ops *ops) +{ + struct spihid_apple_of *sh_of = container_of(ops, struct spihid_apple_of, ops); + + /* reset the controller on boot */ + gpiod_direction_output(sh_of->enable_gpio, 1); + msleep(5); + gpiod_direction_output(sh_of->enable_gpio, 0); + msleep(5); + /* turn SPI device on */ + gpiod_direction_output(sh_of->enable_gpio, 1); + msleep(50); + + return 0; +} + +static int spihid_apple_of_power_off(struct spihid_apple_ops *ops) +{ + struct spihid_apple_of *sh_of = container_of(ops, struct spihid_apple_of, ops); + + /* turn SPI device off */ + gpiod_direction_output(sh_of->enable_gpio, 0); + + return 0; +} + +static int spihid_apple_of_enable_irq(struct spihid_apple_ops *ops) +{ + struct spihid_apple_of *sh_of = container_of(ops, struct spihid_apple_of, ops); + + enable_irq(sh_of->irq); + + return 0; +} + +static int spihid_apple_of_disable_irq(struct spihid_apple_ops *ops) +{ + struct spihid_apple_of *sh_of = container_of(ops, struct spihid_apple_of, ops); + + disable_irq(sh_of->irq); + + return 0; +} + +static int spihid_apple_of_enable_irq_wake(struct spihid_apple_ops *ops) +{ + struct spihid_apple_of *sh_of = container_of(ops, struct spihid_apple_of, ops); + + return enable_irq_wake(sh_of->irq); +} + +static int spihid_apple_of_disable_irq_wake(struct spihid_apple_ops *ops) +{ + struct spihid_apple_of *sh_of = container_of(ops, struct spihid_apple_of, ops); + + return disable_irq_wake(sh_of->irq); +} + +static int spihid_apple_of_probe(struct spi_device *spi) +{ + struct device *dev = &spi->dev; + struct spihid_apple_of *spihid_of; + int err; + + spihid_of = devm_kzalloc(dev, sizeof(*spihid_of), GFP_KERNEL); + if (!spihid_of) + return -ENOMEM; + + spihid_of->ops.power_on = spihid_apple_of_power_on; + spihid_of->ops.power_off = spihid_apple_of_power_off; + spihid_of->ops.enable_irq = spihid_apple_of_enable_irq; + spihid_of->ops.disable_irq = spihid_apple_of_disable_irq; + spihid_of->ops.enable_irq_wake = spihid_apple_of_enable_irq_wake; + spihid_of->ops.disable_irq_wake = spihid_apple_of_disable_irq_wake; + + spihid_of->enable_gpio = devm_gpiod_get_index(dev, "spien", 0, 0); + if (IS_ERR(spihid_of->enable_gpio)) { + err = PTR_ERR(spihid_of->enable_gpio); + dev_err(dev, "failed to get 'spien' gpio pin: %d", err); + return err; + } + + spihid_of->irq = of_irq_get(dev->of_node, 0); + if (spihid_of->irq < 0) { + err = spihid_of->irq; + dev_err(dev, "failed to get 'extended-irq': %d", err); + return err; + } + err = devm_request_threaded_irq(dev, spihid_of->irq, NULL, + spihid_apple_core_irq, IRQF_ONESHOT | IRQF_NO_AUTOEN, + "spi-hid-apple-irq", spi); + if (err < 0) { + dev_err(dev, "failed to request extended-irq %d: %d", + spihid_of->irq, err); + return err; + } + + return spihid_apple_core_probe(spi, &spihid_of->ops); +} + +static const struct of_device_id spihid_apple_of_match[] = { + { .compatible = "apple,spi-hid-transport" }, + {}, +}; +MODULE_DEVICE_TABLE(of, spihid_apple_of_match); + +static struct spi_device_id spihid_apple_of_id[] = { + { "spi-hid-transport", 0 }, + {} +}; +MODULE_DEVICE_TABLE(spi, spihid_apple_of_id); + +static struct spi_driver spihid_apple_of_driver = { + .driver = { + .name = "spi-hid-apple-of", + .pm = &spihid_apple_core_pm, + .of_match_table = of_match_ptr(spihid_apple_of_match), + }, + + .id_table = spihid_apple_of_id, + .probe = spihid_apple_of_probe, + .remove = spihid_apple_core_remove, + .shutdown = spihid_apple_core_shutdown, +}; + +module_spi_driver(spihid_apple_of_driver); + +MODULE_DESCRIPTION("Apple SPI HID transport driver for OpenFirmware systems"); +MODULE_AUTHOR("Janne Grunau "); +MODULE_LICENSE("GPL"); diff --git a/drivers/hid/spi-hid/spi-hid-apple.h b/drivers/hid/spi-hid/spi-hid-apple.h new file mode 100644 index 00000000000000..9abecd1ba78028 --- /dev/null +++ b/drivers/hid/spi-hid/spi-hid-apple.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ + +#ifndef SPI_HID_APPLE_H +#define SPI_HID_APPLE_H + +#include +#include + +/** + * struct spihid_apple_ops - Ops to control the device from the core driver. + * + * @power_on: reset and power the device on. + * @power_off: power the device off. + * @enable_irq: enable irq or ACPI gpe. + * @disable_irq: disable irq or ACPI gpe. + */ + +struct spihid_apple_ops { + int (*power_on)(struct spihid_apple_ops *ops); + int (*power_off)(struct spihid_apple_ops *ops); + int (*enable_irq)(struct spihid_apple_ops *ops); + int (*disable_irq)(struct spihid_apple_ops *ops); + int (*enable_irq_wake)(struct spihid_apple_ops *ops); + int (*disable_irq_wake)(struct spihid_apple_ops *ops); +}; + +irqreturn_t spihid_apple_core_irq(int irq, void *data); + +int spihid_apple_core_probe(struct spi_device *spi, struct spihid_apple_ops *ops); +void spihid_apple_core_remove(struct spi_device *spi); +void spihid_apple_core_shutdown(struct spi_device *spi); + +extern const struct dev_pm_ops spihid_apple_core_pm; + +#endif /* SPI_HID_APPLE_H */ diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index aac0051a2cf655..758eb21430cda0 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -985,6 +985,7 @@ static int usbhid_parse(struct hid_device *hid) struct usb_device *dev = interface_to_usbdev (intf); struct hid_descriptor *hdesc; struct hid_class_descriptor *hcdesc; + __u8 fixed_opt_descriptors_size; u32 quirks = 0; unsigned int rsize = 0; char *rdesc; @@ -1015,7 +1016,21 @@ static int usbhid_parse(struct hid_device *hid) (hdesc->bNumDescriptors - 1) * sizeof(*hcdesc)) { dbg_hid("hid descriptor invalid, bLen=%hhu bNum=%hhu\n", hdesc->bLength, hdesc->bNumDescriptors); - return -EINVAL; + + /* + * Some devices may expose a wrong number of descriptors compared + * to the provided length. + * However, we ignore the optional hid class descriptors entirely + * so we can safely recompute the proper field. + */ + if (hdesc->bLength >= sizeof(*hdesc)) { + fixed_opt_descriptors_size = hdesc->bLength - sizeof(*hdesc); + + hid_warn(intf, "fixing wrong optional hid class descriptors count\n"); + hdesc->bNumDescriptors = fixed_opt_descriptors_size / sizeof(*hcdesc) + 1; + } else { + return -EINVAL; + } } hid->version = le16_to_cpu(hdesc->bcdHID); diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index e109a620c83fc8..71fd3ea4fa8bd5 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -195,13 +195,15 @@ static void hv_kmsg_dump(struct kmsg_dumper *dumper, /* * Write dump contents to the page. No need to synchronize; panic should - * be single-threaded. + * be single-threaded. Ignore failures from kmsg_dump_get_buffer() since + * panic notification should be done even if there is no message data. + * Don't assume bytes_written is set in case of failure, so initialize it. */ kmsg_dump_rewind(&iter); - kmsg_dump_get_buffer(&iter, false, hv_panic_page, HV_HYP_PAGE_SIZE, + bytes_written = 0; + (void)kmsg_dump_get_buffer(&iter, false, hv_panic_page, HV_HYP_PAGE_SIZE, &bytes_written); - if (!bytes_written) - return; + /* * P3 to contain the physical address of the panic page & P4 to * contain the size of the panic data in that page. Rest of the @@ -210,7 +212,7 @@ static void hv_kmsg_dump(struct kmsg_dumper *dumper, hv_set_msr(HV_MSR_CRASH_P0, 0); hv_set_msr(HV_MSR_CRASH_P1, 0); hv_set_msr(HV_MSR_CRASH_P2, 0); - hv_set_msr(HV_MSR_CRASH_P3, virt_to_phys(hv_panic_page)); + hv_set_msr(HV_MSR_CRASH_P3, bytes_written ? virt_to_phys(hv_panic_page) : 0); hv_set_msr(HV_MSR_CRASH_P4, bytes_written); /* diff --git a/drivers/hv/mshv_eventfd.c b/drivers/hv/mshv_eventfd.c index 806674722868b6..05d643f54f45a7 100644 --- a/drivers/hv/mshv_eventfd.c +++ b/drivers/hv/mshv_eventfd.c @@ -87,8 +87,9 @@ static void mshv_irqfd_resampler_ack(struct mshv_irq_ack_notifier *mian) idx = srcu_read_lock(&partition->pt_irq_srcu); - hlist_for_each_entry_rcu(irqfd, &resampler->rsmplr_irqfd_list, - irqfd_resampler_hnode) { + hlist_for_each_entry_srcu(irqfd, &resampler->rsmplr_irqfd_list, + irqfd_resampler_hnode, + srcu_read_lock_held(&partition->pt_irq_srcu)) { if (hv_should_clear_interrupt(irqfd->irqfd_lapic_irq.lapic_control.interrupt_type)) hv_call_clear_virtual_interrupt(partition->pt_id); diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c index e3b2bd417c4640..4e04bef5443799 100644 --- a/drivers/hv/mshv_root_main.c +++ b/drivers/hv/mshv_root_main.c @@ -159,6 +159,7 @@ static int mshv_ioctl_passthru_hvcall(struct mshv_partition *partition, unsigned int pages_order; void *input_pg = NULL; void *output_pg = NULL; + u16 reps_completed; if (copy_from_user(&args, user_args, sizeof(args))) return -EFAULT; @@ -210,41 +211,42 @@ static int mshv_ioctl_passthru_hvcall(struct mshv_partition *partition, */ *(u64 *)input_pg = partition->pt_id; - if (args.reps) - status = hv_do_rep_hypercall(args.code, args.reps, 0, - input_pg, output_pg); - else - status = hv_do_hypercall(args.code, input_pg, output_pg); - - if (hv_result(status) == HV_STATUS_CALL_PENDING) { - if (is_async) { - mshv_async_hvcall_handler(partition, &status); - } else { /* Paranoia check. This shouldn't happen! */ - ret = -EBADFD; - goto free_pages_out; + reps_completed = 0; + do { + if (args.reps) { + status = hv_do_rep_hypercall_ex(args.code, args.reps, + 0, reps_completed, + input_pg, output_pg); + reps_completed = hv_repcomp(status); + } else { + status = hv_do_hypercall(args.code, input_pg, output_pg); } - } - if (hv_result(status) == HV_STATUS_INSUFFICIENT_MEMORY) { - ret = hv_call_deposit_pages(NUMA_NO_NODE, partition->pt_id, 1); - if (!ret) - ret = -EAGAIN; - } else if (!hv_result_success(status)) { - ret = hv_result_to_errno(status); - } + if (hv_result(status) == HV_STATUS_CALL_PENDING) { + if (is_async) { + mshv_async_hvcall_handler(partition, &status); + } else { /* Paranoia check. This shouldn't happen! */ + ret = -EBADFD; + goto free_pages_out; + } + } + + if (hv_result_success(status)) + break; + + if (hv_result(status) != HV_STATUS_INSUFFICIENT_MEMORY) + ret = hv_result_to_errno(status); + else + ret = hv_call_deposit_pages(NUMA_NO_NODE, + partition->pt_id, 1); + } while (!ret); - /* - * Always return the status and output data regardless of result. - * The VMM may need it to determine how to proceed. E.g. the status may - * contain the number of reps completed if a rep hypercall partially - * succeeded. - */ args.status = hv_result(status); - args.reps = args.reps ? hv_repcomp(status) : 0; + args.reps = reps_completed; if (copy_to_user(user_args, &args, sizeof(args))) ret = -EFAULT; - if (output_pg && + if (!ret && output_pg && copy_to_user((void __user *)args.out_ptr, output_pg, args.out_sz)) ret = -EFAULT; @@ -1172,21 +1174,6 @@ mshv_partition_region_by_gfn(struct mshv_partition *partition, u64 gfn) return NULL; } -static struct mshv_mem_region * -mshv_partition_region_by_uaddr(struct mshv_partition *partition, u64 uaddr) -{ - struct mshv_mem_region *region; - - hlist_for_each_entry(region, &partition->pt_mem_regions, hnode) { - if (uaddr >= region->start_uaddr && - uaddr < region->start_uaddr + - (region->nr_pages << HV_HYP_PAGE_SHIFT)) - return region; - } - - return NULL; -} - /* * NB: caller checks and makes sure mem->size is page aligned * Returns: 0 with regionpp updated on success, or -errno @@ -1196,15 +1183,21 @@ static int mshv_partition_create_region(struct mshv_partition *partition, struct mshv_mem_region **regionpp, bool is_mmio) { - struct mshv_mem_region *region; + struct mshv_mem_region *region, *rg; u64 nr_pages = HVPFN_DOWN(mem->size); /* Reject overlapping regions */ - if (mshv_partition_region_by_gfn(partition, mem->guest_pfn) || - mshv_partition_region_by_gfn(partition, mem->guest_pfn + nr_pages - 1) || - mshv_partition_region_by_uaddr(partition, mem->userspace_addr) || - mshv_partition_region_by_uaddr(partition, mem->userspace_addr + mem->size - 1)) + hlist_for_each_entry(rg, &partition->pt_mem_regions, hnode) { + u64 rg_size = rg->nr_pages << HV_HYP_PAGE_SHIFT; + + if ((mem->guest_pfn + nr_pages <= rg->start_gfn || + rg->start_gfn + rg->nr_pages <= mem->guest_pfn) && + (mem->userspace_addr + mem->size <= rg->start_uaddr || + rg->start_uaddr + rg_size <= mem->userspace_addr)) + continue; + return -EEXIST; + } region = vzalloc(sizeof(*region) + sizeof(struct page *) * nr_pages); if (!region) diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 69591dc7bad269..3ab62277b6be6c 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -1306,7 +1307,7 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu) } } -static void vmbus_isr(void) +static void __vmbus_isr(void) { struct hv_per_cpu_context *hv_cpu = this_cpu_ptr(hv_context.cpu_context); @@ -1330,6 +1331,53 @@ static void vmbus_isr(void) add_interrupt_randomness(vmbus_interrupt); } +static DEFINE_PER_CPU(bool, vmbus_irq_pending); +static DEFINE_PER_CPU(struct task_struct *, vmbus_irqd); + +static void vmbus_irqd_wake(void) +{ + struct task_struct *tsk = __this_cpu_read(vmbus_irqd); + + __this_cpu_write(vmbus_irq_pending, true); + wake_up_process(tsk); +} + +static void vmbus_irqd_setup(unsigned int cpu) +{ + sched_set_fifo(current); +} + +static int vmbus_irqd_should_run(unsigned int cpu) +{ + return __this_cpu_read(vmbus_irq_pending); +} + +static void run_vmbus_irqd(unsigned int cpu) +{ + __this_cpu_write(vmbus_irq_pending, false); + __vmbus_isr(); +} + +static bool vmbus_irq_initialized; + +static struct smp_hotplug_thread vmbus_irq_threads = { + .store = &vmbus_irqd, + .setup = vmbus_irqd_setup, + .thread_should_run = vmbus_irqd_should_run, + .thread_fn = run_vmbus_irqd, + .thread_comm = "vmbus_irq/%u", +}; + +static void vmbus_isr(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + vmbus_irqd_wake(); + } else { + lockdep_hardirq_threaded(); + __vmbus_isr(); + } +} + static irqreturn_t vmbus_percpu_isr(int irq, void *dev_id) { vmbus_isr(); @@ -1375,6 +1423,13 @@ static int vmbus_bus_init(void) * the VMbus interrupt handler. */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) && !vmbus_irq_initialized) { + ret = smpboot_register_percpu_thread(&vmbus_irq_threads); + if (ret) + goto err_kthread; + vmbus_irq_initialized = true; + } + if (vmbus_irq == -1) { hv_setup_vmbus_handler(vmbus_isr); } else { @@ -1449,6 +1504,11 @@ static int vmbus_bus_init(void) free_percpu(vmbus_evt); } err_setup: + if (IS_ENABLED(CONFIG_PREEMPT_RT) && vmbus_irq_initialized) { + smpboot_unregister_percpu_thread(&vmbus_irq_threads); + vmbus_irq_initialized = false; + } +err_kthread: bus_unregister(&hv_bus); return ret; } @@ -2914,6 +2974,10 @@ static void __exit vmbus_exit(void) free_percpu_irq(vmbus_irq, vmbus_evt); free_percpu(vmbus_evt); } + if (IS_ENABLED(CONFIG_PREEMPT_RT) && vmbus_irq_initialized) { + smpboot_unregister_percpu_thread(&vmbus_irq_threads); + vmbus_irq_initialized = false; + } for_each_online_cpu(cpu) { struct hv_per_cpu_context *hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 2760feb9f83b5d..d6e9e39d276280 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -1174,6 +1174,18 @@ config SENSORS_LTQ_CPUTEMP If you say yes here you get support for the temperature sensor inside your CPU. +config SENSORS_MACSMC_HWMON + tristate "Apple SMC (Apple Silicon)" + depends on MFD_MACSMC && OF + help + This driver enables hwmon support for current, power, temperature, + and voltage sensors, as well as fan speed reporting and control + on Apple Silicon devices. Say Y here if you have an Apple Silicon + device. + + This driver can also be built as a module. If so, the module will + be called macsmc-hwmon. + config SENSORS_MAX1111 tristate "Maxim MAX1111 Serial 8-bit ADC chip and compatibles" depends on SPI_MASTER diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile index 73b2abdcc6dd9c..f9c049ce912469 100644 --- a/drivers/hwmon/Makefile +++ b/drivers/hwmon/Makefile @@ -148,6 +148,7 @@ obj-$(CONFIG_SENSORS_LTC4260) += ltc4260.o obj-$(CONFIG_SENSORS_LTC4261) += ltc4261.o obj-$(CONFIG_SENSORS_LTC4282) += ltc4282.o obj-$(CONFIG_SENSORS_LTQ_CPUTEMP) += ltq-cputemp.o +obj-$(CONFIG_SENSORS_MACSMC_HWMON) += macsmc-hwmon.o obj-$(CONFIG_SENSORS_MAX1111) += max1111.o obj-$(CONFIG_SENSORS_MAX127) += max127.o obj-$(CONFIG_SENSORS_MAX16065) += max16065.o diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c index 29ccdc2fb7ff85..de408df0c4d786 100644 --- a/drivers/hwmon/acpi_power_meter.c +++ b/drivers/hwmon/acpi_power_meter.c @@ -47,6 +47,8 @@ static int cap_in_hardware; static bool force_cap_on; +static DEFINE_MUTEX(acpi_notify_lock); + static int can_cap_in_hardware(void) { return force_cap_on || cap_in_hardware; @@ -823,18 +825,26 @@ static void acpi_power_meter_notify(struct acpi_device *device, u32 event) resource = acpi_driver_data(device); + guard(mutex)(&acpi_notify_lock); + switch (event) { case METER_NOTIFY_CONFIG: + if (!IS_ERR(resource->hwmon_dev)) + hwmon_device_unregister(resource->hwmon_dev); + mutex_lock(&resource->lock); + free_capabilities(resource); remove_domain_devices(resource); - hwmon_device_unregister(resource->hwmon_dev); res = read_capabilities(resource); if (res) dev_err_once(&device->dev, "read capabilities failed.\n"); res = read_domain_devices(resource); if (res && res != -ENODEV) dev_err_once(&device->dev, "read domain devices failed.\n"); + + mutex_unlock(&resource->lock); + resource->hwmon_dev = hwmon_device_register_with_info(&device->dev, ACPI_POWER_METER_NAME, @@ -843,7 +853,7 @@ static void acpi_power_meter_notify(struct acpi_device *device, u32 event) power_extra_groups); if (IS_ERR(resource->hwmon_dev)) dev_err_once(&device->dev, "register hwmon device failed.\n"); - mutex_unlock(&resource->lock); + break; case METER_NOTIFY_TRIP: sysfs_notify(&device->dev.kobj, NULL, POWER_AVERAGE_NAME); @@ -953,7 +963,8 @@ static void acpi_power_meter_remove(struct acpi_device *device) return; resource = acpi_driver_data(device); - hwmon_device_unregister(resource->hwmon_dev); + if (!IS_ERR(resource->hwmon_dev)) + hwmon_device_unregister(resource->hwmon_dev); remove_domain_devices(resource); free_capabilities(resource); diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index cbe1a74a3deea3..f3d484a9f708b7 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -76,6 +76,9 @@ #define DELL_SMM_NO_TEMP 10 #define DELL_SMM_NO_FANS 4 +/* limit fan multiplier to avoid overflow */ +#define DELL_SMM_MAX_FAN_MULT (INT_MAX / U16_MAX) + struct smm_regs { unsigned int eax; unsigned int ebx; @@ -861,9 +864,9 @@ static umode_t dell_smm_is_visible(const void *drvdata, enum hwmon_sensor_types if (auto_fan) { /* * The setting affects all fans, so only create a - * single attribute. + * single attribute for the first fan channel. */ - if (channel != 1) + if (channel != 0) return 0; /* @@ -1253,6 +1256,12 @@ static int dell_smm_init_data(struct device *dev, const struct dell_smm_ops *ops data->ops = ops; /* All options must not be 0 */ data->i8k_fan_mult = fan_mult ? : I8K_FAN_MULT; + if (data->i8k_fan_mult > DELL_SMM_MAX_FAN_MULT) { + dev_err(dev, + "fan multiplier %u is too large (max %u)\n", + data->i8k_fan_mult, DELL_SMM_MAX_FAN_MULT); + return -EINVAL; + } data->i8k_fan_max = fan_max ? : I8K_FAN_HIGH; data->i8k_pwm_mult = DIV_ROUND_UP(255, data->i8k_fan_max); @@ -1621,6 +1630,14 @@ static const struct dmi_system_id i8k_whitelist_fan_control[] __initconst = { }, .driver_data = (void *)&i8k_fan_control_data[I8K_FAN_30A3_31A3], }, + { + .ident = "Dell G15 5510", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Dell G15 5510"), + }, + .driver_data = (void *)&i8k_fan_control_data[I8K_FAN_30A3_31A3], + }, { .ident = "Dell G15 5511", .matches = { diff --git a/drivers/hwmon/emc2305.c b/drivers/hwmon/emc2305.c index 60809289f8169d..ceae96c07ac45b 100644 --- a/drivers/hwmon/emc2305.c +++ b/drivers/hwmon/emc2305.c @@ -593,10 +593,8 @@ static int emc2305_probe_childs_from_dt(struct device *dev) for_each_child_of_node(dev->of_node, child) { if (of_property_present(child, "reg")) { ret = emc2305_of_parse_pwm_child(dev, child, data); - if (ret) { - of_node_put(child); + if (ret) continue; - } count++; } } @@ -685,8 +683,10 @@ static int emc2305_probe(struct i2c_client *client) i = 0; for_each_child_of_node(dev->of_node, child) { ret = emc2305_set_single_tz(dev, child, i); - if (ret != 0) + if (ret != 0) { + of_node_put(child); return ret; + } i++; } } else { diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c index 516c34bb61c9cf..a8892ced1e549f 100644 --- a/drivers/hwmon/gpio-fan.c +++ b/drivers/hwmon/gpio-fan.c @@ -148,7 +148,7 @@ static int set_fan_speed(struct gpio_fan_data *fan_data, int speed_index) int ret; ret = pm_runtime_put_sync(fan_data->dev); - if (ret < 0) + if (ret < 0 && ret != -ENOSYS) return ret; } @@ -291,7 +291,7 @@ static ssize_t set_rpm(struct device *dev, struct device_attribute *attr, { struct gpio_fan_data *fan_data = dev_get_drvdata(dev); unsigned long rpm; - int ret = count; + int ret; if (kstrtoul(buf, 10, &rpm)) return -EINVAL; @@ -308,7 +308,7 @@ static ssize_t set_rpm(struct device *dev, struct device_attribute *attr, exit_unlock: mutex_unlock(&fan_data->lock); - return ret; + return ret ? ret : count; } static DEVICE_ATTR_RW(pwm1); diff --git a/drivers/hwmon/ltc4282.c b/drivers/hwmon/ltc4282.c index 1d664a2d7b3cb9..58c2d3a6243293 100644 --- a/drivers/hwmon/ltc4282.c +++ b/drivers/hwmon/ltc4282.c @@ -1018,8 +1018,9 @@ static umode_t ltc4282_in_is_visible(const struct ltc4282_state *st, u32 attr) case hwmon_in_max: case hwmon_in_min: case hwmon_in_enable: - case hwmon_in_reset_history: return 0644; + case hwmon_in_reset_history: + return 0200; default: return 0; } @@ -1038,8 +1039,9 @@ static umode_t ltc4282_curr_is_visible(u32 attr) return 0444; case hwmon_curr_max: case hwmon_curr_min: - case hwmon_curr_reset_history: return 0644; + case hwmon_curr_reset_history: + return 0200; default: return 0; } @@ -1057,8 +1059,9 @@ static umode_t ltc4282_power_is_visible(u32 attr) return 0444; case hwmon_power_max: case hwmon_power_min: - case hwmon_power_reset_history: return 0644; + case hwmon_power_reset_history: + return 0200; default: return 0; } diff --git a/drivers/hwmon/macsmc-hwmon.c b/drivers/hwmon/macsmc-hwmon.c new file mode 100644 index 00000000000000..d0de488393f332 --- /dev/null +++ b/drivers/hwmon/macsmc-hwmon.c @@ -0,0 +1,851 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Apple SMC hwmon driver for Apple Silicon platforms + * + * The System Management Controller on Apple Silicon devices is responsible for + * measuring data from sensors across the SoC and machine. These include power, + * temperature, voltage and current sensors. Some "sensors" actually expose + * derived values. An example of this is the key PHPC, which is an estimate + * of the heat energy being dissipated by the SoC. + * + * While each SoC only has one SMC variant, each platform exposes a different + * set of sensors. For example, M1 MacBooks expose battery telemetry sensors + * which are not present on the M1 Mac mini. For this reason, the available + * sensors for a given platform are described in the device tree in a child + * node of the SMC device. We must walk this list of available sensors and + * populate the required hwmon data structures at runtime. + * + * Originally based on a concept by Jean-Francois Bortolotti + * + * Copyright The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include +#include + +#define MAX_LABEL_LENGTH 32 + +/* Temperature, voltage, current, power, fan(s) */ +#define NUM_SENSOR_TYPES 5 + +#define FLT_EXP_BIAS 127 +#define FLT_EXP_MASK GENMASK(30, 23) +#define FLT_MANT_BIAS 23 +#define FLT_MANT_MASK GENMASK(22, 0) +#define FLT_SIGN_MASK BIT(31) + +static bool fan_control; +module_param_unsafe(fan_control, bool, 0644); +MODULE_PARM_DESC(fan_control, + "Override the SMC to set your own fan speeds on supported machines"); + +struct macsmc_hwmon_sensor { + struct apple_smc_key_info info; + smc_key macsmc_key; + char label[MAX_LABEL_LENGTH]; + u32 attrs; +}; + +struct macsmc_hwmon_fan { + struct macsmc_hwmon_sensor now; + struct macsmc_hwmon_sensor min; + struct macsmc_hwmon_sensor max; + struct macsmc_hwmon_sensor set; + struct macsmc_hwmon_sensor mode; + char label[MAX_LABEL_LENGTH]; + u32 attrs; + bool manual; +}; + +struct macsmc_hwmon_sensors { + struct hwmon_channel_info channel_info; + struct macsmc_hwmon_sensor *sensors; + u32 count; +}; + +struct macsmc_hwmon_fans { + struct hwmon_channel_info channel_info; + struct macsmc_hwmon_fan *fans; + u32 count; +}; + +struct macsmc_hwmon { + struct device *dev; + struct apple_smc *smc; + struct device *hwmon_dev; + struct hwmon_chip_info chip_info; + /* Chip + sensor types + NULL */ + const struct hwmon_channel_info *channel_infos[1 + NUM_SENSOR_TYPES + 1]; + struct macsmc_hwmon_sensors temp; + struct macsmc_hwmon_sensors volt; + struct macsmc_hwmon_sensors curr; + struct macsmc_hwmon_sensors power; + struct macsmc_hwmon_fans fan; +}; + +static int macsmc_hwmon_read_label(struct device *dev, + enum hwmon_sensor_types type, u32 attr, + int channel, const char **str) +{ + struct macsmc_hwmon *hwmon = dev_get_drvdata(dev); + + switch (type) { + case hwmon_temp: + *str = hwmon->temp.sensors[channel].label; + break; + case hwmon_in: + *str = hwmon->volt.sensors[channel].label; + break; + case hwmon_curr: + *str = hwmon->curr.sensors[channel].label; + break; + case hwmon_power: + *str = hwmon->power.sensors[channel].label; + break; + case hwmon_fan: + *str = hwmon->fan.fans[channel].label; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +/* + * A number of sensors report data in a 48.16 fixed-point decimal format that is + * not used by any other function of the SMC. + */ +static int macsmc_hwmon_read_ioft_scaled(struct apple_smc *smc, smc_key key, + u64 *p, int scale) +{ + u64 val; + int ret; + + ret = apple_smc_read_u64(smc, key, &val); + if (ret < 0) + return ret; + + *p = mult_frac(val, scale, 65536); + + return 0; +} + +/* + * Many sensors report their data as IEEE-754 floats. No other SMC function uses + * them. + */ +static int macsmc_hwmon_read_f32_scaled(struct apple_smc *smc, smc_key key, + int *p, int scale) +{ + u32 fval; + u64 val; + int ret, exp; + + ret = apple_smc_read_u32(smc, key, &fval); + if (ret < 0) + return ret; + + val = ((u64)((fval & FLT_MANT_MASK) | BIT(23))); + exp = ((fval >> 23) & 0xff) - FLT_EXP_BIAS - FLT_MANT_BIAS; + + /* We never have negatively scaled SMC floats */ + val *= scale; + + if (exp > 63) + val = U64_MAX; + else if (exp < -63) + val = 0; + else if (exp < 0) + val >>= -exp; + else if (exp != 0 && (val & ~((1UL << (64 - exp)) - 1))) /* overflow */ + val = U64_MAX; + else + val <<= exp; + + if (fval & FLT_SIGN_MASK) { + if (val > (-(s64)INT_MIN)) + *p = INT_MIN; + else + *p = -val; + } else { + if (val > INT_MAX) + *p = INT_MAX; + else + *p = val; + } + + return 0; +} + +/* + * The SMC has keys of multiple types, denoted by a FourCC of the same format + * as the key ID. We don't know what data type a key encodes until we poke at it. + */ +static int macsmc_hwmon_read_key(struct apple_smc *smc, + struct macsmc_hwmon_sensor *sensor, int scale, + long *val) +{ + int ret; + + switch (sensor->info.type_code) { + /* 32-bit IEEE 754 float */ + case __SMC_KEY('f', 'l', 't', ' '): { + u32 flt_ = 0; + + ret = macsmc_hwmon_read_f32_scaled(smc, sensor->macsmc_key, + &flt_, scale); + if (ret) + return ret; + + *val = flt_; + break; + } + /* 48.16 fixed point decimal */ + case __SMC_KEY('i', 'o', 'f', 't'): { + u64 ioft = 0; + + ret = macsmc_hwmon_read_ioft_scaled(smc, sensor->macsmc_key, + &ioft, scale); + if (ret) + return ret; + + *val = (long)ioft; + break; + } + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int macsmc_hwmon_write_f32(struct apple_smc *smc, smc_key key, int value) +{ + u64 val; + u32 fval = 0; + int exp = 0, neg; + + val = abs(value); + neg = val != value; + + if (val) { + int msb = __fls(val) - exp; + + if (msb > 23) { + val >>= msb - FLT_MANT_BIAS; + exp -= msb - FLT_MANT_BIAS; + } else if (msb < 23) { + val <<= FLT_MANT_BIAS - msb; + exp += msb; + } + + fval = FIELD_PREP(FLT_SIGN_MASK, neg) | + FIELD_PREP(FLT_EXP_MASK, exp + FLT_EXP_BIAS) | + FIELD_PREP(FLT_MANT_MASK, val); + } + + return apple_smc_write_u32(smc, key, fval); +} + +static int macsmc_hwmon_write_key(struct apple_smc *smc, + struct macsmc_hwmon_sensor *sensor, long val) +{ + switch (sensor->info.type_code) { + /* 32-bit IEEE 754 float */ + case __SMC_KEY('f', 'l', 't', ' '): + return macsmc_hwmon_write_f32(smc, sensor->macsmc_key, val); + /* unsigned 8-bit integer */ + case __SMC_KEY('u', 'i', '8', ' '): + return apple_smc_write_u8(smc, sensor->macsmc_key, val); + default: + return -EOPNOTSUPP; + } +} + +static int macsmc_hwmon_read_fan(struct macsmc_hwmon *hwmon, u32 attr, int chan, + long *val) +{ + switch (attr) { + case hwmon_fan_input: + return macsmc_hwmon_read_key(hwmon->smc, + &hwmon->fan.fans[chan].now, 1, val); + case hwmon_fan_min: + return macsmc_hwmon_read_key(hwmon->smc, + &hwmon->fan.fans[chan].min, 1, val); + case hwmon_fan_max: + return macsmc_hwmon_read_key(hwmon->smc, + &hwmon->fan.fans[chan].max, 1, val); + case hwmon_fan_target: + return macsmc_hwmon_read_key(hwmon->smc, + &hwmon->fan.fans[chan].set, 1, val); + default: + return -EOPNOTSUPP; + } +} + +static int macsmc_hwmon_write_fan(struct device *dev, u32 attr, int channel, + long val) +{ + struct macsmc_hwmon *hwmon = dev_get_drvdata(dev); + long min, max; + int ret; + + if (!fan_control || hwmon->fan.fans[channel].mode.macsmc_key == 0) + return -EOPNOTSUPP; + + /* + * The SMC does no sanity checks on requested fan speeds, so we need to. + */ + ret = macsmc_hwmon_read_key(hwmon->smc, &hwmon->fan.fans[channel].min, + 1, &min); + if (ret) + return ret; + + ret = macsmc_hwmon_read_key(hwmon->smc, &hwmon->fan.fans[channel].max, + 1, &max); + if (ret) + return ret; + + if (val >= min && val <= max) { + if (!hwmon->fan.fans[channel].manual) { + /* Write 1 to mode key for manual control */ + ret = macsmc_hwmon_write_key(hwmon->smc, + &hwmon->fan.fans[channel].mode, 1); + if (ret < 0) + return ret; + + hwmon->fan.fans[channel].manual = true; + } + return macsmc_hwmon_write_key(hwmon->smc, + &hwmon->fan.fans[channel].set, val); + } else if (!val) { + if (hwmon->fan.fans[channel].manual) { + ret = macsmc_hwmon_write_key(hwmon->smc, + &hwmon->fan.fans[channel].mode, 0); + if (ret < 0) + return ret; + + hwmon->fan.fans[channel].manual = false; + } + } else { + return -EINVAL; + } + + return 0; +} + +static int macsmc_hwmon_read(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long *val) +{ + struct macsmc_hwmon *hwmon = dev_get_drvdata(dev); + int ret = 0; + + switch (type) { + case hwmon_temp: + ret = macsmc_hwmon_read_key(hwmon->smc, + &hwmon->temp.sensors[channel], 1000, val); + break; + case hwmon_in: + ret = macsmc_hwmon_read_key(hwmon->smc, + &hwmon->volt.sensors[channel], 1000, val); + break; + case hwmon_curr: + ret = macsmc_hwmon_read_key(hwmon->smc, + &hwmon->curr.sensors[channel], 1000, val); + break; + case hwmon_power: + /* SMC returns power in Watts with acceptable precision to scale to uW */ + ret = macsmc_hwmon_read_key(hwmon->smc, + &hwmon->power.sensors[channel], + 1000000, val); + break; + case hwmon_fan: + ret = macsmc_hwmon_read_fan(hwmon, attr, channel, val); + break; + default: + return -EOPNOTSUPP; + } + + return ret; +} + +static int macsmc_hwmon_write(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long val) +{ + switch (type) { + case hwmon_fan: + return macsmc_hwmon_write_fan(dev, attr, channel, val); + default: + return -EOPNOTSUPP; + } +} + +static umode_t macsmc_hwmon_fan_is_visible(const struct macsmc_hwmon_fan *fan, + u32 attr) +{ + if (fan->attrs & BIT(attr)) { + if (attr == hwmon_fan_target && fan_control && fan->mode.macsmc_key) + return 0644; + + return 0444; + } + + return 0; +} + +static umode_t macsmc_hwmon_is_visible(const void *data, + enum hwmon_sensor_types type, u32 attr, + int channel) +{ + const struct macsmc_hwmon *hwmon = data; + struct macsmc_hwmon_sensor *sensor; + + switch (type) { + case hwmon_in: + sensor = &hwmon->volt.sensors[channel]; + break; + case hwmon_curr: + sensor = &hwmon->curr.sensors[channel]; + break; + case hwmon_power: + sensor = &hwmon->power.sensors[channel]; + break; + case hwmon_temp: + sensor = &hwmon->temp.sensors[channel]; + break; + case hwmon_fan: + return macsmc_hwmon_fan_is_visible(&hwmon->fan.fans[channel], attr); + default: + return 0; + } + + /* Sensors only register ro attributes */ + if (sensor->attrs & BIT(attr)) + return 0444; + + return 0; +} + +static const struct hwmon_ops macsmc_hwmon_ops = { + .is_visible = macsmc_hwmon_is_visible, + .read = macsmc_hwmon_read, + .read_string = macsmc_hwmon_read_label, + .write = macsmc_hwmon_write, +}; + +/* + * Get the key metadata, including key data type, from the SMC. + */ +static int macsmc_hwmon_parse_key(struct device *dev, struct apple_smc *smc, + struct macsmc_hwmon_sensor *sensor, + const char *key) +{ + int ret; + + ret = apple_smc_get_key_info(smc, _SMC_KEY(key), &sensor->info); + if (ret) { + dev_dbg(dev, "Failed to retrieve key info for %s\n", key); + return ret; + } + + sensor->macsmc_key = _SMC_KEY(key); + + return 0; +} + +/* + * A sensor is a single key-value pair as made available by the SMC. + * The devicetree gives us the SMC key ID and a friendly name where the + * purpose of the sensor is known. + */ +static int macsmc_hwmon_create_sensor(struct device *dev, struct apple_smc *smc, + struct device_node *sensor_node, + struct macsmc_hwmon_sensor *sensor) +{ + const char *key, *label; + int ret; + + ret = of_property_read_string(sensor_node, "apple,key-id", &key); + if (ret) { + dev_dbg(dev, "Could not find apple,key-id in sensor node\n"); + return ret; + } + + ret = macsmc_hwmon_parse_key(dev, smc, sensor, key); + if (ret) + return ret; + + ret = of_property_read_string(sensor_node, "label", &label); + if (ret) + dev_dbg(dev, "No label found for sensor %s\n", key); + else + strscpy_pad(sensor->label, label, sizeof(sensor->label)); + + return 0; +} + +/* + * Fan data is exposed by the SMC as multiple sensors. + * + * The devicetree schema reuses apple,key-id for the actual fan speed sensor. + * Min, max and target keys do not need labels, so we can reuse label + * for naming the entire fan. + */ +static int macsmc_hwmon_create_fan(struct device *dev, struct apple_smc *smc, + struct device_node *fan_node, + struct macsmc_hwmon_fan *fan) +{ + const char *label, *now, *min, *max, *set, *mode; + int ret; + + ret = of_property_read_string(fan_node, "apple,key-id", &now); + if (ret) { + dev_err(dev, "apple,key-id not found in fan node!\n"); + return ret; + } + + ret = macsmc_hwmon_parse_key(dev, smc, &fan->now, now); + if (ret) + return ret; + + fan->attrs = HWMON_F_INPUT; + + ret = of_property_read_string(fan_node, "label", &label); + if (ret) { + dev_dbg(dev, "No label found for fan %s\n", now); + } else { + strscpy_pad(fan->label, label, sizeof(fan->label)); + fan->attrs |= HWMON_F_LABEL; + } + + /* The following keys are not required to simply monitor fan speed */ + if (!of_property_read_string(fan_node, "apple,fan-minimum", &min)) { + ret = macsmc_hwmon_parse_key(dev, smc, &fan->min, min); + if (ret) + return ret; + + fan->attrs |= HWMON_F_MIN; + } + + if (!of_property_read_string(fan_node, "apple,fan-maximum", &max)) { + ret = macsmc_hwmon_parse_key(dev, smc, &fan->max, max); + if (ret) + return ret; + + fan->attrs |= HWMON_F_MAX; + } + + if (!of_property_read_string(fan_node, "apple,fan-target", &set)) { + ret = macsmc_hwmon_parse_key(dev, smc, &fan->set, set); + if (ret) + return ret; + + fan->attrs |= HWMON_F_TARGET; + } + + if (!of_property_read_string(fan_node, "apple,fan-mode", &mode)) { + ret = macsmc_hwmon_parse_key(dev, smc, &fan->mode, mode); + if (ret) + return ret; + } + + /* Initialise fan control mode to automatic */ + fan->manual = false; + + return 0; +} + +static int macsmc_hwmon_populate_sensors(struct macsmc_hwmon *hwmon, + struct device_node *hwmon_node) +{ + struct device_node *key_node __maybe_unused; + struct macsmc_hwmon_sensor *sensor; + u32 n_current = 0, n_fan = 0, n_power = 0, n_temperature = 0, n_voltage = 0; + + for_each_child_of_node_with_prefix(hwmon_node, key_node, "current-") { + n_current++; + } + + if (n_current) { + hwmon->curr.sensors = devm_kcalloc(hwmon->dev, n_current, + sizeof(struct macsmc_hwmon_sensor), GFP_KERNEL); + if (!hwmon->curr.sensors) + return -ENOMEM; + + for_each_child_of_node_with_prefix(hwmon_node, key_node, "current-") { + sensor = &hwmon->curr.sensors[hwmon->curr.count]; + if (!macsmc_hwmon_create_sensor(hwmon->dev, hwmon->smc, key_node, sensor)) { + sensor->attrs = HWMON_C_INPUT; + + if (*sensor->label) + sensor->attrs |= HWMON_C_LABEL; + + hwmon->curr.count++; + } + } + } + + for_each_child_of_node_with_prefix(hwmon_node, key_node, "fan-") { + n_fan++; + } + + if (n_fan) { + hwmon->fan.fans = devm_kcalloc(hwmon->dev, n_fan, + sizeof(struct macsmc_hwmon_fan), GFP_KERNEL); + if (!hwmon->fan.fans) + return -ENOMEM; + + for_each_child_of_node_with_prefix(hwmon_node, key_node, "fan-") { + if (!macsmc_hwmon_create_fan(hwmon->dev, hwmon->smc, key_node, + &hwmon->fan.fans[hwmon->fan.count])) + hwmon->fan.count++; + } + } + + for_each_child_of_node_with_prefix(hwmon_node, key_node, "power-") { + n_power++; + } + + if (n_power) { + hwmon->power.sensors = devm_kcalloc(hwmon->dev, n_power, + sizeof(struct macsmc_hwmon_sensor), GFP_KERNEL); + if (!hwmon->power.sensors) + return -ENOMEM; + + for_each_child_of_node_with_prefix(hwmon_node, key_node, "power-") { + sensor = &hwmon->power.sensors[hwmon->power.count]; + if (!macsmc_hwmon_create_sensor(hwmon->dev, hwmon->smc, key_node, sensor)) { + sensor->attrs = HWMON_P_INPUT; + + if (*sensor->label) + sensor->attrs |= HWMON_P_LABEL; + + hwmon->power.count++; + } + } + } + + for_each_child_of_node_with_prefix(hwmon_node, key_node, "temperature-") { + n_temperature++; + } + + if (n_temperature) { + hwmon->temp.sensors = devm_kcalloc(hwmon->dev, n_temperature, + sizeof(struct macsmc_hwmon_sensor), GFP_KERNEL); + if (!hwmon->temp.sensors) + return -ENOMEM; + + for_each_child_of_node_with_prefix(hwmon_node, key_node, "temperature-") { + sensor = &hwmon->temp.sensors[hwmon->temp.count]; + if (!macsmc_hwmon_create_sensor(hwmon->dev, hwmon->smc, key_node, sensor)) { + sensor->attrs = HWMON_T_INPUT; + + if (*sensor->label) + sensor->attrs |= HWMON_T_LABEL; + + hwmon->temp.count++; + } + } + } + + for_each_child_of_node_with_prefix(hwmon_node, key_node, "voltage-") { + n_voltage++; + } + + if (n_voltage) { + hwmon->volt.sensors = devm_kcalloc(hwmon->dev, n_voltage, + sizeof(struct macsmc_hwmon_sensor), GFP_KERNEL); + if (!hwmon->volt.sensors) + return -ENOMEM; + + for_each_child_of_node_with_prefix(hwmon_node, key_node, "volt-") { + sensor = &hwmon->temp.sensors[hwmon->temp.count]; + if (!macsmc_hwmon_create_sensor(hwmon->dev, hwmon->smc, key_node, sensor)) { + sensor->attrs = HWMON_I_INPUT; + + if (*sensor->label) + sensor->attrs |= HWMON_I_LABEL; + + hwmon->volt.count++; + } + } + } + + return 0; +} + +/* Create NULL-terminated config arrays */ +static void macsmc_hwmon_populate_configs(u32 *configs, const struct macsmc_hwmon_sensors *sensors) +{ + int idx; + + for (idx = 0; idx < sensors->count; idx++) + configs[idx] = sensors->sensors[idx].attrs; +} + +static void macsmc_hwmon_populate_fan_configs(u32 *configs, const struct macsmc_hwmon_fans *fans) +{ + int idx; + + for (idx = 0; idx < fans->count; idx++) + configs[idx] = fans->fans[idx].attrs; +} + +static const struct hwmon_channel_info *const macsmc_chip_channel_info = + HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ); + +static int macsmc_hwmon_create_infos(struct macsmc_hwmon *hwmon) +{ + struct hwmon_channel_info *channel_info; + int i = 0; + + /* chip */ + hwmon->channel_infos[i++] = macsmc_chip_channel_info; + + if (hwmon->curr.count) { + channel_info = &hwmon->curr.channel_info; + channel_info->type = hwmon_curr; + channel_info->config = devm_kcalloc(hwmon->dev, hwmon->curr.count + 1, + sizeof(u32), GFP_KERNEL); + if (!channel_info->config) + return -ENOMEM; + + macsmc_hwmon_populate_configs((u32 *)channel_info->config, &hwmon->curr); + hwmon->channel_infos[i++] = channel_info; + } + + if (hwmon->fan.count) { + channel_info = &hwmon->fan.channel_info; + channel_info->type = hwmon_fan; + channel_info->config = devm_kcalloc(hwmon->dev, hwmon->fan.count + 1, + sizeof(u32), GFP_KERNEL); + if (!channel_info->config) + return -ENOMEM; + + macsmc_hwmon_populate_fan_configs((u32 *)channel_info->config, &hwmon->fan); + hwmon->channel_infos[i++] = channel_info; + } + + if (hwmon->power.count) { + channel_info = &hwmon->power.channel_info; + channel_info->type = hwmon_power; + channel_info->config = devm_kcalloc(hwmon->dev, hwmon->power.count + 1, + sizeof(u32), GFP_KERNEL); + if (!channel_info->config) + return -ENOMEM; + + macsmc_hwmon_populate_configs((u32 *)channel_info->config, &hwmon->power); + hwmon->channel_infos[i++] = channel_info; + } + + if (hwmon->temp.count) { + channel_info = &hwmon->temp.channel_info; + channel_info->type = hwmon_temp; + channel_info->config = devm_kcalloc(hwmon->dev, hwmon->temp.count + 1, + sizeof(u32), GFP_KERNEL); + if (!channel_info->config) + return -ENOMEM; + + macsmc_hwmon_populate_configs((u32 *)channel_info->config, &hwmon->temp); + hwmon->channel_infos[i++] = channel_info; + } + + if (hwmon->volt.count) { + channel_info = &hwmon->volt.channel_info; + channel_info->type = hwmon_in; + channel_info->config = devm_kcalloc(hwmon->dev, hwmon->volt.count + 1, + sizeof(u32), GFP_KERNEL); + if (!channel_info->config) + return -ENOMEM; + + macsmc_hwmon_populate_configs((u32 *)channel_info->config, &hwmon->volt); + hwmon->channel_infos[i++] = channel_info; + } + + return 0; +} + +static int macsmc_hwmon_probe(struct platform_device *pdev) +{ + struct apple_smc *smc = dev_get_drvdata(pdev->dev.parent); + struct macsmc_hwmon *hwmon; + int ret; + + /* + * The MFD driver will try to probe us unconditionally. Some devices + * with the SMC do not have hwmon capabilities. Only probe if we have + * a hwmon node. + */ + if (!pdev->dev.of_node) + return -ENODEV; + + hwmon = devm_kzalloc(&pdev->dev, sizeof(*hwmon), + GFP_KERNEL); + if (!hwmon) + return -ENOMEM; + + hwmon->dev = &pdev->dev; + hwmon->smc = smc; + + ret = macsmc_hwmon_populate_sensors(hwmon, hwmon->dev->of_node); + if (ret) { + dev_err(hwmon->dev, "Could not parse sensors\n"); + return ret; + } + + if (!hwmon->curr.count && !hwmon->fan.count && + !hwmon->power.count && !hwmon->temp.count && + !hwmon->volt.count) { + dev_err(hwmon->dev, + "No valid sensors found of any supported type\n"); + return -ENODEV; + } + + ret = macsmc_hwmon_create_infos(hwmon); + if (ret) + return ret; + + hwmon->chip_info.ops = &macsmc_hwmon_ops; + hwmon->chip_info.info = + (const struct hwmon_channel_info *const *)&hwmon->channel_infos; + + hwmon->hwmon_dev = devm_hwmon_device_register_with_info(&pdev->dev, + "macsmc_hwmon", hwmon, + &hwmon->chip_info, NULL); + if (IS_ERR(hwmon->hwmon_dev)) + return dev_err_probe(hwmon->dev, PTR_ERR(hwmon->hwmon_dev), + "Probing SMC hwmon device failed\n"); + + dev_info(hwmon->dev, "Registered SMC hwmon device. Sensors:"); + dev_info(hwmon->dev, + "Current: %d, Fans: %d, Power: %d, Temperature: %d, Voltage: %d", + hwmon->curr.count, hwmon->fan.count, + hwmon->power.count, hwmon->temp.count, + hwmon->volt.count); + + return 0; +} + +static const struct of_device_id macsmc_hwmon_of_table[] = { + { .compatible = "apple,smc-hwmon" }, + {} +}; +MODULE_DEVICE_TABLE(of, macsmc_hwmon_of_table); + +static struct platform_driver macsmc_hwmon_driver = { + .probe = macsmc_hwmon_probe, + .driver = { + .name = "macsmc-hwmon", + .of_match_table = macsmc_hwmon_of_table, + }, +}; +module_platform_driver(macsmc_hwmon_driver); + +MODULE_DESCRIPTION("Apple Silicon SMC hwmon driver"); +MODULE_AUTHOR("James Calligeros "); +MODULE_LICENSE("Dual MIT/GPL"); diff --git a/drivers/hwmon/max16065.c b/drivers/hwmon/max16065.c index 0ccb5eb596fc40..4c9e7892a73c1b 100644 --- a/drivers/hwmon/max16065.c +++ b/drivers/hwmon/max16065.c @@ -216,12 +216,13 @@ static ssize_t max16065_current_show(struct device *dev, struct device_attribute *da, char *buf) { struct max16065_data *data = max16065_update_device(dev); + int curr_sense = data->curr_sense; - if (unlikely(data->curr_sense < 0)) - return data->curr_sense; + if (unlikely(curr_sense < 0)) + return curr_sense; return sysfs_emit(buf, "%d\n", - ADC_TO_CURR(data->curr_sense, data->curr_gain)); + ADC_TO_CURR(curr_sense, data->curr_gain)); } static ssize_t max16065_limit_store(struct device *dev, diff --git a/drivers/hwmon/max6697.c b/drivers/hwmon/max6697.c index 0735a1d2c20fdc..6926d787b5ad12 100644 --- a/drivers/hwmon/max6697.c +++ b/drivers/hwmon/max6697.c @@ -548,7 +548,7 @@ static int max6697_probe(struct i2c_client *client) struct regmap *regmap; int err; - regmap = regmap_init_i2c(client, &max6697_regmap_config); + regmap = devm_regmap_init_i2c(client, &max6697_regmap_config); if (IS_ERR(regmap)) return PTR_ERR(regmap); diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index b3694a4209b975..89928d38831b61 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -749,6 +749,7 @@ static ssize_t occ_show_extended(struct device *dev, * are dynamically allocated, we cannot use the existing kernel macros which * stringify the name argument. */ +__printf(7, 8) static void occ_init_attribute(struct occ_attribute *attr, int mode, ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf), ssize_t (*store)(struct device *dev, struct device_attribute *attr, diff --git a/drivers/hwmon/pmbus/mpq8785.c b/drivers/hwmon/pmbus/mpq8785.c index 1f56aaf4dde807..87bd039c77b9b3 100644 --- a/drivers/hwmon/pmbus/mpq8785.c +++ b/drivers/hwmon/pmbus/mpq8785.c @@ -47,6 +47,33 @@ static int mpq8785_identify(struct i2c_client *client, return 0; }; +static int mpq8785_read_byte_data(struct i2c_client *client, int page, int reg) +{ + int ret; + + switch (reg) { + case PMBUS_VOUT_MODE: + ret = pmbus_read_byte_data(client, page, reg); + if (ret < 0) + return ret; + + if ((ret >> 5) == 1) { + /* + * The MPQ8785 chip reports VOUT_MODE as VID mode, but the driver + * treats VID as direct mode. Without this, identification would fail + * due to mode mismatch. + * This override ensures the reported mode matches the driver + * configuration, allowing successful initialization. + */ + return PB_VOUT_MODE_DIRECT; + } + + return ret; + default: + return -ENODATA; + } +} + static int mpm82504_read_word_data(struct i2c_client *client, int page, int phase, int reg) { @@ -129,6 +156,7 @@ static int mpq8785_probe(struct i2c_client *client) break; case mpq8785: info->identify = mpq8785_identify; + info->read_byte_data = mpq8785_read_byte_data; break; default: return -ENODEV; diff --git a/drivers/hwmon/sy7636a-hwmon.c b/drivers/hwmon/sy7636a-hwmon.c index a12fc0ce70e76e..d51daaf63d632e 100644 --- a/drivers/hwmon/sy7636a-hwmon.c +++ b/drivers/hwmon/sy7636a-hwmon.c @@ -66,18 +66,13 @@ static const struct hwmon_chip_info sy7636a_chip_info = { static int sy7636a_sensor_probe(struct platform_device *pdev) { struct regmap *regmap = dev_get_regmap(pdev->dev.parent, NULL); - struct regulator *regulator; struct device *hwmon_dev; int err; if (!regmap) return -EPROBE_DEFER; - regulator = devm_regulator_get(&pdev->dev, "vcom"); - if (IS_ERR(regulator)) - return PTR_ERR(regulator); - - err = regulator_enable(regulator); + err = devm_regulator_get_enable(&pdev->dev, "vcom"); if (err) return err; diff --git a/drivers/hwmon/tmp401.c b/drivers/hwmon/tmp401.c index 02c5a3bb1071cb..84aaf817144cfa 100644 --- a/drivers/hwmon/tmp401.c +++ b/drivers/hwmon/tmp401.c @@ -401,7 +401,7 @@ static int tmp401_chip_read(struct device *dev, u32 attr, int channel, long *val ret = regmap_read(data->regmap, TMP401_CONVERSION_RATE, ®val); if (ret < 0) return ret; - *val = (1 << (7 - regval)) * 125; + *val = (1 << (7 - min(regval, 7))) * 125; break; case hwmon_chip_temp_reset_history: *val = 0; diff --git a/drivers/hwmon/w83791d.c b/drivers/hwmon/w83791d.c index ace854b370a054..996e36951f9dad 100644 --- a/drivers/hwmon/w83791d.c +++ b/drivers/hwmon/w83791d.c @@ -218,9 +218,14 @@ static u8 fan_to_reg(long rpm, int div) return clamp_val((1350000 + rpm * div / 2) / (rpm * div), 1, 254); } -#define FAN_FROM_REG(val, div) ((val) == 0 ? -1 : \ - ((val) == 255 ? 0 : \ - 1350000 / ((val) * (div)))) +static int fan_from_reg(int val, int div) +{ + if (val == 0) + return -1; + if (val == 255) + return 0; + return 1350000 / (val * div); +} /* for temp1 which is 8-bit resolution, LSB = 1 degree Celsius */ #define TEMP1_FROM_REG(val) ((val) * 1000) @@ -521,7 +526,7 @@ static ssize_t show_##reg(struct device *dev, struct device_attribute *attr, \ struct w83791d_data *data = w83791d_update_device(dev); \ int nr = sensor_attr->index; \ return sprintf(buf, "%d\n", \ - FAN_FROM_REG(data->reg[nr], DIV_FROM_REG(data->fan_div[nr]))); \ + fan_from_reg(data->reg[nr], DIV_FROM_REG(data->fan_div[nr]))); \ } show_fan_reg(fan); @@ -585,10 +590,10 @@ static ssize_t store_fan_div(struct device *dev, struct device_attribute *attr, if (err) return err; + mutex_lock(&data->update_lock); /* Save fan_min */ - min = FAN_FROM_REG(data->fan_min[nr], DIV_FROM_REG(data->fan_div[nr])); + min = fan_from_reg(data->fan_min[nr], DIV_FROM_REG(data->fan_div[nr])); - mutex_lock(&data->update_lock); data->fan_div[nr] = div_to_reg(nr, val); switch (nr) { diff --git a/drivers/hwmon/w83l786ng.c b/drivers/hwmon/w83l786ng.c index 9b81bd406e0596..1d9109ca1585e7 100644 --- a/drivers/hwmon/w83l786ng.c +++ b/drivers/hwmon/w83l786ng.c @@ -76,15 +76,25 @@ FAN_TO_REG(long rpm, int div) return clamp_val((1350000 + rpm * div / 2) / (rpm * div), 1, 254); } -#define FAN_FROM_REG(val, div) ((val) == 0 ? -1 : \ - ((val) == 255 ? 0 : \ - 1350000 / ((val) * (div)))) +static int fan_from_reg(int val, int div) +{ + if (val == 0) + return -1; + if (val == 255) + return 0; + return 1350000 / (val * div); +} /* for temp */ #define TEMP_TO_REG(val) (clamp_val(((val) < 0 ? (val) + 0x100 * 1000 \ : (val)) / 1000, 0, 0xff)) -#define TEMP_FROM_REG(val) (((val) & 0x80 ? \ - (val) - 0x100 : (val)) * 1000) + +static int temp_from_reg(int val) +{ + if (val & 0x80) + return (val - 0x100) * 1000; + return val * 1000; +} /* * The analog voltage inputs have 8mV LSB. Since the sysfs output is @@ -280,7 +290,7 @@ static ssize_t show_##reg(struct device *dev, struct device_attribute *attr, \ int nr = to_sensor_dev_attr(attr)->index; \ struct w83l786ng_data *data = w83l786ng_update_device(dev); \ return sprintf(buf, "%d\n", \ - FAN_FROM_REG(data->reg[nr], DIV_FROM_REG(data->fan_div[nr]))); \ + fan_from_reg(data->reg[nr], DIV_FROM_REG(data->fan_div[nr]))); \ } show_fan_reg(fan); @@ -347,7 +357,7 @@ store_fan_div(struct device *dev, struct device_attribute *attr, /* Save fan_min */ mutex_lock(&data->update_lock); - min = FAN_FROM_REG(data->fan_min[nr], DIV_FROM_REG(data->fan_div[nr])); + min = fan_from_reg(data->fan_min[nr], DIV_FROM_REG(data->fan_div[nr])); data->fan_div[nr] = DIV_TO_REG(val); @@ -409,7 +419,7 @@ show_temp(struct device *dev, struct device_attribute *attr, char *buf) int nr = sensor_attr->nr; int index = sensor_attr->index; struct w83l786ng_data *data = w83l786ng_update_device(dev); - return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp[nr][index])); + return sprintf(buf, "%d\n", temp_from_reg(data->temp[nr][index])); } static ssize_t diff --git a/drivers/hwspinlock/omap_hwspinlock.c b/drivers/hwspinlock/omap_hwspinlock.c index 27b47b8623c09c..2d8de835bc2429 100644 --- a/drivers/hwspinlock/omap_hwspinlock.c +++ b/drivers/hwspinlock/omap_hwspinlock.c @@ -88,7 +88,9 @@ static int omap_hwspinlock_probe(struct platform_device *pdev) * make sure the module is enabled and clocked before reading * the module SYSSTATUS register */ - devm_pm_runtime_enable(&pdev->dev); + ret = devm_pm_runtime_enable(&pdev->dev); + if (ret) + return ret; ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) return ret; diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index f677c08233ba1a..5c256af6e54af0 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -520,6 +520,7 @@ static void etm_event_start(struct perf_event *event, int flags) goto out; path = etm_event_cpu_path(event_data, cpu); + path->handle = handle; /* We need a sink, no need to continue without one */ sink = coresight_get_sink(path); if (WARN_ON_ONCE(!sink)) diff --git a/drivers/hwtracing/coresight/coresight-etm3x-core.c b/drivers/hwtracing/coresight/coresight-etm3x-core.c index 45630a1cd32fbd..0c011b7041696a 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-core.c @@ -439,13 +439,26 @@ struct etm_enable_arg { int rc; }; -static void etm_enable_hw_smp_call(void *info) +static void etm_enable_sysfs_smp_call(void *info) { struct etm_enable_arg *arg = info; + struct coresight_device *csdev; if (WARN_ON(!arg)) return; + + csdev = arg->drvdata->csdev; + if (!coresight_take_mode(csdev, CS_MODE_SYSFS)) { + /* Someone is already using the tracer */ + arg->rc = -EBUSY; + return; + } + arg->rc = etm_enable_hw(arg->drvdata); + + /* The tracer didn't start */ + if (arg->rc) + coresight_set_mode(csdev, CS_MODE_DISABLED); } static int etm_cpu_id(struct coresight_device *csdev) @@ -465,16 +478,26 @@ static int etm_enable_perf(struct coresight_device *csdev, struct coresight_path *path) { struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + int ret; if (WARN_ON_ONCE(drvdata->cpu != smp_processor_id())) return -EINVAL; + if (!coresight_take_mode(csdev, CS_MODE_PERF)) + return -EBUSY; + /* Configure the tracer based on the session's specifics */ etm_parse_event_config(drvdata, event); drvdata->traceid = path->trace_id; /* And enable it */ - return etm_enable_hw(drvdata); + ret = etm_enable_hw(drvdata); + + /* Failed to start tracer; roll back to DISABLED mode */ + if (ret) + coresight_set_mode(csdev, CS_MODE_DISABLED); + + return ret; } static int etm_enable_sysfs(struct coresight_device *csdev, struct coresight_path *path) @@ -494,7 +517,7 @@ static int etm_enable_sysfs(struct coresight_device *csdev, struct coresight_pat if (cpu_online(drvdata->cpu)) { arg.drvdata = drvdata; ret = smp_call_function_single(drvdata->cpu, - etm_enable_hw_smp_call, &arg, 1); + etm_enable_sysfs_smp_call, &arg, 1); if (!ret) ret = arg.rc; if (!ret) @@ -517,12 +540,6 @@ static int etm_enable(struct coresight_device *csdev, struct perf_event *event, enum cs_mode mode, struct coresight_path *path) { int ret; - struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - if (!coresight_take_mode(csdev, mode)) { - /* Someone is already using the tracer */ - return -EBUSY; - } switch (mode) { case CS_MODE_SYSFS: @@ -535,17 +552,12 @@ static int etm_enable(struct coresight_device *csdev, struct perf_event *event, ret = -EINVAL; } - /* The tracer didn't start */ - if (ret) - coresight_set_mode(drvdata->csdev, CS_MODE_DISABLED); - return ret; } -static void etm_disable_hw(void *info) +static void etm_disable_hw(struct etm_drvdata *drvdata) { int i; - struct etm_drvdata *drvdata = info; struct etm_config *config = &drvdata->config; struct coresight_device *csdev = drvdata->csdev; @@ -567,6 +579,15 @@ static void etm_disable_hw(void *info) "cpu: %d disable smp call done\n", drvdata->cpu); } +static void etm_disable_sysfs_smp_call(void *info) +{ + struct etm_drvdata *drvdata = info; + + etm_disable_hw(drvdata); + + coresight_set_mode(drvdata->csdev, CS_MODE_DISABLED); +} + static void etm_disable_perf(struct coresight_device *csdev) { struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); @@ -588,6 +609,8 @@ static void etm_disable_perf(struct coresight_device *csdev) CS_LOCK(drvdata->csa.base); + coresight_set_mode(drvdata->csdev, CS_MODE_DISABLED); + /* * perf will release trace ids when _free_aux() * is called at the end of the session @@ -612,7 +635,8 @@ static void etm_disable_sysfs(struct coresight_device *csdev) * Executing etm_disable_hw on the cpu whose ETM is being disabled * ensures that register writes occur when cpu is powered. */ - smp_call_function_single(drvdata->cpu, etm_disable_hw, drvdata, 1); + smp_call_function_single(drvdata->cpu, etm_disable_sysfs_smp_call, + drvdata, 1); spin_unlock(&drvdata->spinlock); cpus_read_unlock(); @@ -652,9 +676,6 @@ static void etm_disable(struct coresight_device *csdev, WARN_ON_ONCE(mode); return; } - - if (mode) - coresight_set_mode(csdev, CS_MODE_DISABLED); } static const struct coresight_ops_source etm_source_ops = { @@ -774,16 +795,16 @@ static int __init etm_hp_setup(void) { int ret; - ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ARM_CORESIGHT_STARTING, - "arm/coresight:starting", - etm_starting_cpu, etm_dying_cpu); + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING, + "arm/coresight:starting", + etm_starting_cpu, etm_dying_cpu); if (ret) return ret; - ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN, - "arm/coresight:online", - etm_online_cpu, NULL); + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "arm/coresight:online", + etm_online_cpu, NULL); /* HP dyn state ID returned in ret on success */ if (ret > 0) { diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 020f070bf17dc0..fdda924a2c7117 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -446,10 +446,24 @@ static int etm4_enable_trace_unit(struct etmv4_drvdata *drvdata) etm4x_relaxed_write32(csa, TRCRSR_TA, TRCRSR); etm4x_allow_trace(drvdata); + + /* + * According to software usage PKLXF in Arm ARM (ARM DDI 0487 L.a), + * execute a Context synchronization event to guarantee the trace unit + * will observe the new values of the System registers. + */ + if (!csa->io_mem) + isb(); + /* Enable the trace unit */ etm4x_relaxed_write32(csa, 1, TRCPRGCTLR); - /* Synchronize the register updates for sysreg access */ + /* + * As recommended by section 4.3.7 ("Synchronization when using system + * instructions to progrom the trace unit") of ARM IHI 0064H.b, the + * self-hosted trace analyzer must perform a Context synchronization + * event between writing to the TRCPRGCTLR and reading the TRCSTATR. + */ if (!csa->io_mem) isb(); @@ -589,13 +603,26 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata) return rc; } -static void etm4_enable_hw_smp_call(void *info) +static void etm4_enable_sysfs_smp_call(void *info) { struct etm4_enable_arg *arg = info; + struct coresight_device *csdev; if (WARN_ON(!arg)) return; + + csdev = arg->drvdata->csdev; + if (!coresight_take_mode(csdev, CS_MODE_SYSFS)) { + /* Someone is already using the tracer */ + arg->rc = -EBUSY; + return; + } + arg->rc = etm4_enable_hw(arg->drvdata); + + /* The tracer didn't start */ + if (arg->rc) + coresight_set_mode(csdev, CS_MODE_DISABLED); } /* @@ -808,13 +835,14 @@ static int etm4_enable_perf(struct coresight_device *csdev, struct perf_event *event, struct coresight_path *path) { - int ret = 0; struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + int ret; - if (WARN_ON_ONCE(drvdata->cpu != smp_processor_id())) { - ret = -EINVAL; - goto out; - } + if (WARN_ON_ONCE(drvdata->cpu != smp_processor_id())) + return -EINVAL; + + if (!coresight_take_mode(csdev, CS_MODE_PERF)) + return -EBUSY; /* Configure the tracer based on the session's specifics */ ret = etm4_parse_event_config(csdev, event); @@ -830,6 +858,9 @@ static int etm4_enable_perf(struct coresight_device *csdev, ret = etm4_enable_hw(drvdata); out: + /* Failed to start tracer; roll back to DISABLED mode */ + if (ret) + coresight_set_mode(csdev, CS_MODE_DISABLED); return ret; } @@ -861,7 +892,7 @@ static int etm4_enable_sysfs(struct coresight_device *csdev, struct coresight_pa */ arg.drvdata = drvdata; ret = smp_call_function_single(drvdata->cpu, - etm4_enable_hw_smp_call, &arg, 1); + etm4_enable_sysfs_smp_call, &arg, 1); if (!ret) ret = arg.rc; if (!ret) @@ -882,11 +913,6 @@ static int etm4_enable(struct coresight_device *csdev, struct perf_event *event, { int ret; - if (!coresight_take_mode(csdev, mode)) { - /* Someone is already using the tracer */ - return -EBUSY; - } - switch (mode) { case CS_MODE_SYSFS: ret = etm4_enable_sysfs(csdev, path); @@ -898,10 +924,6 @@ static int etm4_enable(struct coresight_device *csdev, struct perf_event *event, ret = -EINVAL; } - /* The tracer didn't start */ - if (ret) - coresight_set_mode(csdev, CS_MODE_DISABLED); - return ret; } @@ -923,11 +945,16 @@ static void etm4_disable_trace_unit(struct etmv4_drvdata *drvdata) */ etm4x_prohibit_trace(drvdata); /* - * Make sure everything completes before disabling, as recommended - * by section 7.3.77 ("TRCVICTLR, ViewInst Main Control Register, - * SSTATUS") of ARM IHI 0064D + * Prevent being speculative at the point of disabling the trace unit, + * as recommended by section 7.3.77 ("TRCVICTLR, ViewInst Main Control + * Register, SSTATUS") of ARM IHI 0064D */ dsb(sy); + /* + * According to software usage VKHHY in Arm ARM (ARM DDI 0487 L.a), + * execute a Context synchronization event to guarantee no new + * program-flow trace is generated. + */ isb(); /* Trace synchronization barrier, is a nop if not supported */ tsb_csync(); @@ -953,10 +980,9 @@ static void etm4_disable_trace_unit(struct etmv4_drvdata *drvdata) isb(); } -static void etm4_disable_hw(void *info) +static void etm4_disable_hw(struct etmv4_drvdata *drvdata) { u32 control; - struct etmv4_drvdata *drvdata = info; struct etmv4_config *config = &drvdata->config; struct coresight_device *csdev = drvdata->csdev; struct csdev_access *csa = &csdev->access; @@ -993,6 +1019,15 @@ static void etm4_disable_hw(void *info) "cpu: %d disable smp call done\n", drvdata->cpu); } +static void etm4_disable_sysfs_smp_call(void *info) +{ + struct etmv4_drvdata *drvdata = info; + + etm4_disable_hw(drvdata); + + coresight_set_mode(drvdata->csdev, CS_MODE_DISABLED); +} + static int etm4_disable_perf(struct coresight_device *csdev, struct perf_event *event) { @@ -1022,6 +1057,8 @@ static int etm4_disable_perf(struct coresight_device *csdev, /* TRCVICTLR::SSSTATUS, bit[9] */ filters->ssstatus = (control & BIT(9)); + coresight_set_mode(drvdata->csdev, CS_MODE_DISABLED); + /* * perf will release trace ids when _free_aux() is * called at the end of the session. @@ -1047,7 +1084,8 @@ static void etm4_disable_sysfs(struct coresight_device *csdev) * Executing etm4_disable_hw on the cpu whose ETM is being disabled * ensures that register writes occur when cpu is powered. */ - smp_call_function_single(drvdata->cpu, etm4_disable_hw, drvdata, 1); + smp_call_function_single(drvdata->cpu, etm4_disable_sysfs_smp_call, + drvdata, 1); raw_spin_unlock(&drvdata->spinlock); @@ -1087,9 +1125,6 @@ static void etm4_disable(struct coresight_device *csdev, etm4_disable_perf(csdev, event); break; } - - if (mode) - coresight_set_mode(csdev, CS_MODE_DISABLED); } static int etm4_resume_perf(struct coresight_device *csdev) @@ -1823,9 +1858,11 @@ static int __etm4_cpu_save(struct etmv4_drvdata *drvdata) goto out; } + if (!drvdata->paused) + etm4_disable_trace_unit(drvdata); + state = drvdata->save_state; - state->trcprgctlr = etm4x_read32(csa, TRCPRGCTLR); if (drvdata->nr_pe) state->trcprocselr = etm4x_read32(csa, TRCPROCSELR); state->trcconfigr = etm4x_read32(csa, TRCCONFIGR); @@ -1908,7 +1945,7 @@ static int __etm4_cpu_save(struct etmv4_drvdata *drvdata) state->trcpdcr = etm4x_read32(csa, TRCPDCR); /* wait for TRCSTATR.IDLE to go up */ - if (etm4x_wait_status(csa, TRCSTATR_PMSTABLE_BIT, 1)) { + if (etm4x_wait_status(csa, TRCSTATR_IDLE_BIT, 1)) { dev_err(etm_dev, "timeout while waiting for Idle Trace Status\n"); etm4_os_unlock(drvdata); @@ -1935,9 +1972,6 @@ static int etm4_cpu_save(struct etmv4_drvdata *drvdata) { int ret = 0; - /* Save the TRFCR irrespective of whether the ETM is ON */ - if (drvdata->trfcr) - drvdata->save_trfcr = read_trfcr(); /* * Save and restore the ETM Trace registers only if * the ETM is active. @@ -1959,7 +1993,6 @@ static void __etm4_cpu_restore(struct etmv4_drvdata *drvdata) etm4_cs_unlock(drvdata, csa); etm4x_relaxed_write32(csa, state->trcclaimset, TRCCLAIMSET); - etm4x_relaxed_write32(csa, state->trcprgctlr, TRCPRGCTLR); if (drvdata->nr_pe) etm4x_relaxed_write32(csa, state->trcprocselr, TRCPROCSELR); etm4x_relaxed_write32(csa, state->trcconfigr, TRCCONFIGR); @@ -2044,13 +2077,15 @@ static void __etm4_cpu_restore(struct etmv4_drvdata *drvdata) /* Unlock the OS lock to re-enable trace and external debug access */ etm4_os_unlock(drvdata); + + if (!drvdata->paused) + etm4_enable_trace_unit(drvdata); + etm4_cs_lock(drvdata, csa); } static void etm4_cpu_restore(struct etmv4_drvdata *drvdata) { - if (drvdata->trfcr) - write_trfcr(drvdata->save_trfcr); if (drvdata->state_needs_restore) __etm4_cpu_restore(drvdata); } diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 13ec9ecef46f5b..b8796b4271025f 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -866,7 +866,6 @@ struct etmv4_config { * struct etm4_save_state - state to be preserved when ETM is without power */ struct etmv4_save_state { - u32 trcprgctlr; u32 trcprocselr; u32 trcconfigr; u32 trcauxctlr; @@ -980,7 +979,6 @@ struct etmv4_save_state { * at runtime, due to the additional setting of TRFCR_CX when * in EL2. Otherwise, 0. * @config: structure holding configuration parameters. - * @save_trfcr: Saved TRFCR_EL1 register during a CPU PM event. * @save_state: State to be preserved across power loss * @state_needs_restore: True when there is context to restore after PM exit * @skip_power_up: Indicates if an implementation can skip powering up @@ -1037,7 +1035,6 @@ struct etmv4_drvdata { bool lpoverride; u64 trfcr; struct etmv4_config config; - u64 save_trfcr; struct etmv4_save_state *save_state; bool state_needs_restore; bool skip_power_up; diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index b07fcdb3fe1a8c..9144b273d415f0 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -1250,6 +1250,13 @@ static struct etr_buf *tmc_etr_get_sysfs_buffer(struct coresight_device *csdev) * with the lock released. */ raw_spin_lock_irqsave(&drvdata->spinlock, flags); + + /* + * If the ETR is already enabled, continue with the existing buffer. + */ + if (coresight_get_mode(csdev) == CS_MODE_SYSFS) + goto out; + sysfs_buf = READ_ONCE(drvdata->sysfs_buf); if (!sysfs_buf || (sysfs_buf->size != drvdata->size)) { raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); @@ -1299,6 +1306,19 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev) raw_spin_lock_irqsave(&drvdata->spinlock, flags); + /* + * Since the sysfs buffer allocation and the hardware enablement is not + * in the same critical region, it's possible to race with the perf. + */ + if (coresight_get_mode(csdev) == CS_MODE_PERF) { + drvdata->sysfs_buf = NULL; + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + + /* Free allocated memory out side of the spinlock */ + tmc_etr_free_sysfs_buf(sysfs_buf); + return -EBUSY; + } + /* * In sysFS mode we can have multiple writers per sink. Since this * sink is already enabled no memory is needed and the HW need not be @@ -1327,7 +1347,8 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev) struct etr_buf *tmc_etr_get_buffer(struct coresight_device *csdev, enum cs_mode mode, void *data) { - struct perf_output_handle *handle = data; + struct coresight_path *path = data; + struct perf_output_handle *handle = path->handle; struct etr_perf_buffer *etr_perf; switch (mode) { diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 47d9e6c3bac041..e3a7ab112ea955 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -810,13 +810,20 @@ static int intel_th_output_open(struct inode *inode, struct file *file) int err; dev = bus_find_device_by_devt(&intel_th_bus, inode->i_rdev); - if (!dev || !dev->driver) + if (!dev) return -ENODEV; + if (!dev->driver) { + err = -ENODEV; + goto out_put_device; + } + thdrv = to_intel_th_driver(dev->driver); fops = fops_get(thdrv->fops); - if (!fops) - return -ENODEV; + if (!fops) { + err = -ENODEV; + goto out_put_device; + } replace_fops(file, fops); @@ -824,14 +831,30 @@ static int intel_th_output_open(struct inode *inode, struct file *file) if (file->f_op->open) { err = file->f_op->open(inode, file); - return err; + if (err) + goto out_put_device; } + return 0; + +out_put_device: + put_device(dev); + + return err; +} + +static int intel_th_output_release(struct inode *inode, struct file *file) +{ + struct intel_th_device *thdev = file->private_data; + + put_device(&thdev->dev); + return 0; } static const struct file_operations intel_th_output_fops = { .open = intel_th_output_open, + .release = intel_th_output_release, .llseek = noop_llseek, }; diff --git a/drivers/i2c/busses/i2c-amd-mp2-pci.c b/drivers/i2c/busses/i2c-amd-mp2-pci.c index ef7370d3dbea31..60edbabc2986be 100644 --- a/drivers/i2c/busses/i2c-amd-mp2-pci.c +++ b/drivers/i2c/busses/i2c-amd-mp2-pci.c @@ -458,13 +458,16 @@ struct amd_mp2_dev *amd_mp2_find_device(void) { struct device *dev; struct pci_dev *pci_dev; + struct amd_mp2_dev *mp2_dev; dev = driver_find_next_device(&amd_mp2_pci_driver.driver, NULL); if (!dev) return NULL; pci_dev = to_pci_dev(dev); - return (struct amd_mp2_dev *)pci_get_drvdata(pci_dev); + mp2_dev = (struct amd_mp2_dev *)pci_get_drvdata(pci_dev); + put_device(dev); + return mp2_dev; } EXPORT_SYMBOL_GPL(amd_mp2_find_device); diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h index 347843b4f5dd7a..436555543c79d0 100644 --- a/drivers/i2c/busses/i2c-designware-core.h +++ b/drivers/i2c/busses/i2c-designware-core.h @@ -78,6 +78,7 @@ #define DW_IC_TX_ABRT_SOURCE 0x80 #define DW_IC_ENABLE_STATUS 0x9c #define DW_IC_CLR_RESTART_DET 0xa8 +#define DW_IC_SMBUS_INTR_MASK 0xcc #define DW_IC_COMP_PARAM_1 0xf4 #define DW_IC_COMP_VERSION 0xf8 #define DW_IC_SDA_HOLD_MIN_VERS 0x3131312A /* "111*" == v1.11* */ diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index 41e9b5ecad2013..45bfca05bb300f 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -220,6 +220,13 @@ static int i2c_dw_init_master(struct dw_i2c_dev *dev) /* Disable the adapter */ __i2c_dw_disable(dev); + /* + * Mask SMBus interrupts to block storms from broken + * firmware that leaves IC_SMBUS=1; the handler never + * services them. + */ + regmap_write(dev->map, DW_IC_SMBUS_INTR_MASK, 0); + /* Write standard speed timing parameters */ regmap_write(dev->map, DW_IC_SS_SCL_HCNT, dev->ss_hcnt); regmap_write(dev->map, DW_IC_SS_SCL_LCNT, dev->ss_lcnt); diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index 2a0962a0b44175..d882126c1778cb 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -592,6 +592,13 @@ static bool is_use_dma(struct lpi2c_imx_struct *lpi2c_imx, struct i2c_msg *msg) if (!lpi2c_imx->can_use_dma) return false; + /* + * A system-wide suspend or resume transition is in progress. LPI2C should use PIO to + * transfer data to avoid issue caused by no ready DMA HW resource. + */ + if (pm_suspend_in_progress()) + return false; + /* * When the length of data is less than I2C_DMA_THRESHOLD, * cpu mode is used directly to avoid low performance. diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index dcce882f3ebaaf..85f554044cf1ee 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -1103,7 +1103,8 @@ static irqreturn_t i2c_imx_master_isr(struct imx_i2c_struct *i2c_imx, unsigned i case IMX_I2C_STATE_READ_BLOCK_DATA_LEN: i2c_imx_isr_read_block_data_len(i2c_imx); - i2c_imx->state = IMX_I2C_STATE_READ_CONTINUE; + if (i2c_imx->state == IMX_I2C_STATE_READ_BLOCK_DATA_LEN) + i2c_imx->state = IMX_I2C_STATE_READ_CONTINUE; break; case IMX_I2C_STATE_WRITE: diff --git a/drivers/i2c/busses/i2c-k1.c b/drivers/i2c/busses/i2c-k1.c index 6b918770e612e0..8ef6d5d1927b72 100644 --- a/drivers/i2c/busses/i2c-k1.c +++ b/drivers/i2c/busses/i2c-k1.c @@ -158,11 +158,16 @@ static int spacemit_i2c_handle_err(struct spacemit_i2c_dev *i2c) { dev_dbg(i2c->dev, "i2c error status: 0x%08x\n", i2c->status); - if (i2c->status & (SPACEMIT_SR_BED | SPACEMIT_SR_ALD)) { + /* Arbitration Loss Detected */ + if (i2c->status & SPACEMIT_SR_ALD) { spacemit_i2c_reset(i2c); return -EAGAIN; } + /* Bus Error No ACK/NAK */ + if (i2c->status & SPACEMIT_SR_BED) + spacemit_i2c_reset(i2c); + return i2c->status & SPACEMIT_SR_ACKNAK ? -ENXIO : -EIO; } @@ -224,6 +229,12 @@ static void spacemit_i2c_check_bus_release(struct spacemit_i2c_dev *i2c) } } +static inline void +spacemit_i2c_clear_int_status(struct spacemit_i2c_dev *i2c, u32 mask) +{ + writel(mask & SPACEMIT_I2C_INT_STATUS_MASK, i2c->base + SPACEMIT_ISR); +} + static void spacemit_i2c_init(struct spacemit_i2c_dev *i2c) { u32 val; @@ -267,12 +278,8 @@ static void spacemit_i2c_init(struct spacemit_i2c_dev *i2c) val = readl(i2c->base + SPACEMIT_IRCR); val |= SPACEMIT_RCR_SDA_GLITCH_NOFIX; writel(val, i2c->base + SPACEMIT_IRCR); -} -static inline void -spacemit_i2c_clear_int_status(struct spacemit_i2c_dev *i2c, u32 mask) -{ - writel(mask & SPACEMIT_I2C_INT_STATUS_MASK, i2c->base + SPACEMIT_ISR); + spacemit_i2c_clear_int_status(i2c, SPACEMIT_I2C_INT_STATUS_MASK); } static void spacemit_i2c_start(struct spacemit_i2c_dev *i2c) @@ -559,7 +566,7 @@ static int spacemit_i2c_probe(struct platform_device *pdev) return dev_err_probe(dev, i2c->irq, "failed to get irq resource"); ret = devm_request_irq(i2c->dev, i2c->irq, spacemit_i2c_irq_handler, - IRQF_NO_SUSPEND | IRQF_ONESHOT, dev_name(i2c->dev), i2c); + IRQF_NO_SUSPEND, dev_name(i2c->dev), i2c); if (ret) return dev_err_probe(dev, ret, "failed to request irq"); diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 43fdd89b8bebc8..bfb352b04902c4 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -97,6 +97,7 @@ struct geni_i2c_dev { dma_addr_t dma_addr; struct dma_chan *tx_c; struct dma_chan *rx_c; + bool no_dma; bool gpi_mode; bool abort_done; }; @@ -425,7 +426,7 @@ static int geni_i2c_rx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, size_t len = msg->len; struct i2c_msg *cur; - dma_buf = i2c_get_dma_safe_msg_buf(msg, 32); + dma_buf = gi2c->no_dma ? NULL : i2c_get_dma_safe_msg_buf(msg, 32); if (dma_buf) geni_se_select_mode(se, GENI_SE_DMA); else @@ -464,7 +465,7 @@ static int geni_i2c_tx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, size_t len = msg->len; struct i2c_msg *cur; - dma_buf = i2c_get_dma_safe_msg_buf(msg, 32); + dma_buf = gi2c->no_dma ? NULL : i2c_get_dma_safe_msg_buf(msg, 32); if (dma_buf) geni_se_select_mode(se, GENI_SE_DMA); else @@ -880,10 +881,12 @@ static int geni_i2c_probe(struct platform_device *pdev) goto err_resources; } - if (desc && desc->no_dma_support) + if (desc && desc->no_dma_support) { fifo_disable = false; - else + gi2c->no_dma = true; + } else { fifo_disable = readl_relaxed(gi2c->se.base + GENI_IF_DISABLE_RO) & FIFO_IF_DISABLE; + } if (fifo_disable) { /* FIFO is disabled, so we can only use GPI DMA */ diff --git a/drivers/i2c/busses/i2c-riic.c b/drivers/i2c/busses/i2c-riic.c index 3e8f126cb7f749..9e3595b3623e4a 100644 --- a/drivers/i2c/busses/i2c-riic.c +++ b/drivers/i2c/busses/i2c-riic.c @@ -670,12 +670,39 @@ static const struct riic_of_data riic_rz_t2h_info = { static int riic_i2c_suspend(struct device *dev) { - struct riic_dev *riic = dev_get_drvdata(dev); - int ret; + /* + * Some I2C devices may need the I2C controller to remain active + * during resume_noirq() or suspend_noirq(). If the controller is + * autosuspended, there is no way to wake it up once runtime PM is + * disabled (in suspend_late()). + * + * During system resume, the I2C controller will be available only + * after runtime PM is re-enabled (in resume_early()). However, this + * may be too late for some devices. + * + * Wake up the controller in the suspend() callback while runtime PM + * is still enabled. The I2C controller will remain available until + * the suspend_noirq() callback (pm_runtime_force_suspend()) is + * called. During resume, the I2C controller can be restored by the + * resume_noirq() callback (pm_runtime_force_resume()). + * + * Finally, the resume() callback re-enables autosuspend, ensuring + * the I2C controller remains available until the system enters + * suspend_noirq() and from resume_noirq(). + */ + return pm_runtime_resume_and_get(dev); +} - ret = pm_runtime_resume_and_get(dev); - if (ret) - return ret; +static int riic_i2c_resume(struct device *dev) +{ + pm_runtime_put_autosuspend(dev); + + return 0; +} + +static int riic_i2c_suspend_noirq(struct device *dev) +{ + struct riic_dev *riic = dev_get_drvdata(dev); i2c_mark_adapter_suspended(&riic->adapter); @@ -683,12 +710,12 @@ static int riic_i2c_suspend(struct device *dev) riic_clear_set_bit(riic, ICCR1_ICE, 0, RIIC_ICCR1); pm_runtime_mark_last_busy(dev); - pm_runtime_put_sync(dev); + pm_runtime_force_suspend(dev); return reset_control_assert(riic->rstc); } -static int riic_i2c_resume(struct device *dev) +static int riic_i2c_resume_noirq(struct device *dev) { struct riic_dev *riic = dev_get_drvdata(dev); int ret; @@ -697,6 +724,10 @@ static int riic_i2c_resume(struct device *dev) if (ret) return ret; + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + ret = riic_init_hw(riic); if (ret) { /* @@ -714,6 +745,7 @@ static int riic_i2c_resume(struct device *dev) } static const struct dev_pm_ops riic_i2c_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(riic_i2c_suspend_noirq, riic_i2c_resume_noirq) SYSTEM_SLEEP_PM_OPS(riic_i2c_suspend, riic_i2c_resume) }; diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index d946db75df7068..425e36b36009bf 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -620,7 +620,8 @@ static int i3c_set_hotjoin(struct i3c_master_controller *master, bool enable) else ret = master->ops->disable_hotjoin(master); - master->hotjoin = enable; + if (!ret) + master->hotjoin = enable; i3c_bus_normaluse_unlock(&master->bus); @@ -2883,17 +2884,18 @@ int i3c_master_register(struct i3c_master_controller *master, INIT_LIST_HEAD(&master->boardinfo.i2c); INIT_LIST_HEAD(&master->boardinfo.i3c); - ret = i3c_bus_init(i3cbus, master->dev.of_node); - if (ret) - return ret; - device_initialize(&master->dev); - dev_set_name(&master->dev, "i3c-%d", i3cbus->id); master->dev.dma_mask = parent->dma_mask; master->dev.coherent_dma_mask = parent->coherent_dma_mask; master->dev.dma_parms = parent->dma_parms; + ret = i3c_bus_init(i3cbus, master->dev.of_node); + if (ret) + goto err_put_dev; + + dev_set_name(&master->dev, "i3c-%d", i3cbus->id); + ret = of_populate_i3c_bus(master); if (ret) goto err_put_dev; diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 9ceedf09c3b6a6..c06595cb740103 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -1094,6 +1094,7 @@ static int dw_i3c_master_i2c_xfers(struct i2c_dev_desc *dev, dev_err(master->dev, "<%s> cannot resume i3c bus master, err: %d\n", __func__, ret); + dw_i3c_master_free_xfer(xfer); return ret; } @@ -1563,6 +1564,8 @@ int dw_i3c_common_probe(struct dw_i3c_master *master, spin_lock_init(&master->xferqueue.lock); INIT_LIST_HEAD(&master->xferqueue.list); + spin_lock_init(&master->devs_lock); + writel(INTR_ALL, master->regs + INTR_STATUS); irq = platform_get_irq(pdev, 0); ret = devm_request_irq(&pdev->dev, irq, diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c index 9641e66a4e5f2d..e70a64f2a32fa5 100644 --- a/drivers/i3c/master/svc-i3c-master.c +++ b/drivers/i3c/master/svc-i3c-master.c @@ -406,21 +406,27 @@ static int svc_i3c_master_handle_ibi(struct svc_i3c_master *master, int ret, val; u8 *buf; - slot = i3c_generic_ibi_get_free_slot(data->ibi_pool); - if (!slot) - return -ENOSPC; - - slot->len = 0; - buf = slot->data; - + /* + * Wait for transfer to complete before returning. Otherwise, the EmitStop + * request might be sent when the transfer is not complete. + */ ret = readl_relaxed_poll_timeout(master->regs + SVC_I3C_MSTATUS, val, SVC_I3C_MSTATUS_COMPLETE(val), 0, 1000); if (ret) { dev_err(master->dev, "Timeout when polling for COMPLETE\n"); - i3c_generic_ibi_recycle_slot(data->ibi_pool, slot); return ret; } + slot = i3c_generic_ibi_get_free_slot(data->ibi_pool); + if (!slot) { + dev_dbg(master->dev, "No free ibi slot, drop the data\n"); + writel(SVC_I3C_MDATACTRL_FLUSHRB, master->regs + SVC_I3C_MDATACTRL); + return -ENOSPC; + } + + slot->len = 0; + buf = slot->data; + while (SVC_I3C_MSTATUS_RXPEND(readl(master->regs + SVC_I3C_MSTATUS)) && slot->len < SVC_I3C_FIFO_SIZE) { mdatactrl = readl(master->regs + SVC_I3C_MDATACTRL); diff --git a/drivers/iio/accel/adxl380.c b/drivers/iio/accel/adxl380.c index 0cf3c68158293c..6d82873357cb8d 100644 --- a/drivers/iio/accel/adxl380.c +++ b/drivers/iio/accel/adxl380.c @@ -1728,9 +1728,9 @@ static int adxl380_config_irq(struct iio_dev *indio_dev) st->int_map[1] = ADXL380_INT0_MAP1_REG; } else { st->irq = fwnode_irq_get_byname(dev_fwnode(st->dev), "INT1"); - if (st->irq > 0) - return dev_err_probe(st->dev, -ENODEV, - "no interrupt name specified"); + if (st->irq < 0) + return dev_err_probe(st->dev, st->irq, + "no interrupt name specified\n"); st->int_map[0] = ADXL380_INT1_MAP0_REG; st->int_map[1] = ADXL380_INT1_MAP1_REG; } diff --git a/drivers/iio/accel/sca3000.c b/drivers/iio/accel/sca3000.c index bfa8a3f5a92f43..9ef4d6e2746697 100644 --- a/drivers/iio/accel/sca3000.c +++ b/drivers/iio/accel/sca3000.c @@ -1489,7 +1489,11 @@ static int sca3000_probe(struct spi_device *spi) if (ret) goto error_free_irq; - return iio_device_register(indio_dev); + ret = iio_device_register(indio_dev); + if (ret) + goto error_free_irq; + + return 0; error_free_irq: if (spi->irq) diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index a7961c610ed203..1a9447c81b0f70 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -517,7 +517,6 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .wai_addr = ST_SENSORS_DEFAULT_WAI_ADDRESS, .sensors_supported = { [0] = H3LIS331DL_ACCEL_DEV_NAME, - [1] = IIS328DQ_ACCEL_DEV_NAME, }, .ch = (struct iio_chan_spec *)st_accel_12bit_channels, .odr = { @@ -584,6 +583,77 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .multi_read_bit = true, .bootime = 2, }, + { + .wai = 0x32, + .wai_addr = ST_SENSORS_DEFAULT_WAI_ADDRESS, + .sensors_supported = { + [0] = IIS328DQ_ACCEL_DEV_NAME, + }, + .ch = (struct iio_chan_spec *)st_accel_12bit_channels, + .odr = { + .addr = 0x20, + .mask = 0x18, + .odr_avl = { + { .hz = 50, .value = 0x00, }, + { .hz = 100, .value = 0x01, }, + { .hz = 400, .value = 0x02, }, + { .hz = 1000, .value = 0x03, }, + }, + }, + .pw = { + .addr = 0x20, + .mask = 0x20, + .value_on = ST_SENSORS_DEFAULT_POWER_ON_VALUE, + .value_off = ST_SENSORS_DEFAULT_POWER_OFF_VALUE, + }, + .enable_axis = { + .addr = ST_SENSORS_DEFAULT_AXIS_ADDR, + .mask = ST_SENSORS_DEFAULT_AXIS_MASK, + }, + .fs = { + .addr = 0x23, + .mask = 0x30, + .fs_avl = { + [0] = { + .num = ST_ACCEL_FS_AVL_100G, + .value = 0x00, + .gain = IIO_G_TO_M_S_2(980), + }, + [1] = { + .num = ST_ACCEL_FS_AVL_200G, + .value = 0x01, + .gain = IIO_G_TO_M_S_2(1950), + }, + [2] = { + .num = ST_ACCEL_FS_AVL_400G, + .value = 0x03, + .gain = IIO_G_TO_M_S_2(3910), + }, + }, + }, + .bdu = { + .addr = 0x23, + .mask = 0x80, + }, + .drdy_irq = { + .int1 = { + .addr = 0x22, + .mask = 0x02, + }, + .int2 = { + .addr = 0x22, + .mask = 0x10, + }, + .addr_ihl = 0x22, + .mask_ihl = 0x80, + }, + .sim = { + .addr = 0x23, + .value = BIT(0), + }, + .multi_read_bit = true, + .bootime = 2, + }, { /* No WAI register present */ .sensors_supported = { diff --git a/drivers/iio/adc/ad4080.c b/drivers/iio/adc/ad4080.c index 6e61787ed3213f..e15310fcd21a36 100644 --- a/drivers/iio/adc/ad4080.c +++ b/drivers/iio/adc/ad4080.c @@ -125,7 +125,7 @@ /* Miscellaneous Definitions */ #define AD4080_SPI_READ BIT(7) -#define AD4080_CHIP_ID GENMASK(2, 0) +#define AD4080_CHIP_ID 0x0050 #define AD4080_LVDS_CNV_CLK_CNT_MAX 7 @@ -445,7 +445,8 @@ static int ad4080_setup(struct iio_dev *indio_dev) { struct ad4080_state *st = iio_priv(indio_dev); struct device *dev = regmap_get_device(st->regmap); - unsigned int id; + __le16 id_le; + u16 id; int ret; ret = regmap_write(st->regmap, AD4080_REG_INTERFACE_CONFIG_A, @@ -458,10 +459,12 @@ static int ad4080_setup(struct iio_dev *indio_dev) if (ret) return ret; - ret = regmap_read(st->regmap, AD4080_REG_CHIP_TYPE, &id); + ret = regmap_bulk_read(st->regmap, AD4080_REG_PRODUCT_ID_L, &id_le, + sizeof(id_le)); if (ret) return ret; + id = le16_to_cpu(id_le); if (id != AD4080_CHIP_ID) dev_info(dev, "Unrecognized CHIP_ID 0x%X\n", id); diff --git a/drivers/iio/adc/ad7280a.c b/drivers/iio/adc/ad7280a.c index 50a6ff7c8b1c73..ba12a3796e2b1b 100644 --- a/drivers/iio/adc/ad7280a.c +++ b/drivers/iio/adc/ad7280a.c @@ -1024,7 +1024,9 @@ static int ad7280_probe(struct spi_device *spi) st->spi->max_speed_hz = AD7280A_MAX_SPI_CLK_HZ; st->spi->mode = SPI_MODE_1; - spi_setup(st->spi); + ret = spi_setup(st->spi); + if (ret < 0) + return ret; st->ctrl_lb = FIELD_PREP(AD7280A_CTRL_LB_ACQ_TIME_MSK, st->acquisition_time) | FIELD_PREP(AD7280A_CTRL_LB_THERMISTOR_MSK, st->thermistor_term_en); diff --git a/drivers/iio/adc/ad7606_par.c b/drivers/iio/adc/ad7606_par.c index 634852c4bbd2c5..b81e707ab40c56 100644 --- a/drivers/iio/adc/ad7606_par.c +++ b/drivers/iio/adc/ad7606_par.c @@ -43,7 +43,8 @@ static int ad7606_par_bus_setup_iio_backend(struct device *dev, struct iio_dev *indio_dev) { struct ad7606_state *st = iio_priv(indio_dev); - unsigned int ret, c; + unsigned int c; + int ret; struct iio_backend_data_fmt data = { .sign_extend = true, .enable = true, diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c index f7a9f46ea0dc40..2d8f8da3671dac 100644 --- a/drivers/iio/adc/ad9467.c +++ b/drivers/iio/adc/ad9467.c @@ -95,7 +95,7 @@ #define CHIPID_AD9434 0x6A #define AD9434_DEF_OUTPUT_MODE 0x00 -#define AD9434_REG_VREF_MASK 0xC0 +#define AD9434_REG_VREF_MASK GENMASK(4, 0) /* * Analog Devices AD9467 16-Bit, 200/250 MSPS ADC diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c index b4c36e6a7490aa..aa4ba3f5a50603 100644 --- a/drivers/iio/adc/at91-sama5d2_adc.c +++ b/drivers/iio/adc/at91-sama5d2_adc.c @@ -2481,6 +2481,7 @@ static void at91_adc_remove(struct platform_device *pdev) struct at91_adc_state *st = iio_priv(indio_dev); iio_device_unregister(indio_dev); + cancel_work_sync(&st->touch_st.workq); at91_adc_dma_disable(st); diff --git a/drivers/iio/adc/exynos_adc.c b/drivers/iio/adc/exynos_adc.c index 1484adff00df38..f2400897818c5a 100644 --- a/drivers/iio/adc/exynos_adc.c +++ b/drivers/iio/adc/exynos_adc.c @@ -540,15 +540,6 @@ static const struct iio_chan_spec exynos_adc_iio_channels[] = { ADC_CHANNEL(9, "adc9"), }; -static int exynos_adc_remove_devices(struct device *dev, void *c) -{ - struct platform_device *pdev = to_platform_device(dev); - - platform_device_unregister(pdev); - - return 0; -} - static int exynos_adc_probe(struct platform_device *pdev) { struct exynos_adc *info = NULL; @@ -660,8 +651,7 @@ static int exynos_adc_probe(struct platform_device *pdev) return 0; err_of_populate: - device_for_each_child(&indio_dev->dev, NULL, - exynos_adc_remove_devices); + of_platform_depopulate(&indio_dev->dev); iio_device_unregister(indio_dev); err_irq: free_irq(info->irq, info); @@ -681,8 +671,7 @@ static void exynos_adc_remove(struct platform_device *pdev) struct iio_dev *indio_dev = platform_get_drvdata(pdev); struct exynos_adc *info = iio_priv(indio_dev); - device_for_each_child(&indio_dev->dev, NULL, - exynos_adc_remove_devices); + of_platform_depopulate(&indio_dev->dev); iio_device_unregister(indio_dev); free_irq(info->irq, info); if (info->data->exit_hw) diff --git a/drivers/iio/adc/pac1934.c b/drivers/iio/adc/pac1934.c index 48df1650926052..edaff72e9d792a 100644 --- a/drivers/iio/adc/pac1934.c +++ b/drivers/iio/adc/pac1934.c @@ -665,9 +665,9 @@ static int pac1934_reg_snapshot(struct pac1934_chip_info *info, /* add the power_acc field */ curr_energy += inc; - clamp(curr_energy, PAC_193X_MIN_POWER_ACC, PAC_193X_MAX_POWER_ACC); - - reg_data->energy_sec_acc[cnt] = curr_energy; + reg_data->energy_sec_acc[cnt] = clamp(curr_energy, + PAC_193X_MIN_POWER_ACC, + PAC_193X_MAX_POWER_ACC); } offset_reg_data_p += PAC1934_VPOWER_ACC_REG_LEN; diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index 99f274adc870dc..a1a28584de9303 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -123,7 +123,7 @@ static void tiadc_step_config(struct iio_dev *indio_dev) chan = adc_dev->channel_line[i]; - if (adc_dev->step_avg[i]) + if (adc_dev->step_avg[i] && adc_dev->step_avg[i] <= STEPCONFIG_AVG_16) stepconfig = STEPCONFIG_AVG(ffs(adc_dev->step_avg[i]) - 1) | STEPCONFIG_FIFO1; else diff --git a/drivers/iio/chemical/scd4x.c b/drivers/iio/chemical/scd4x.c index 8859f89fb2a942..0fd839176e264e 100644 --- a/drivers/iio/chemical/scd4x.c +++ b/drivers/iio/chemical/scd4x.c @@ -584,7 +584,7 @@ static const struct iio_chan_spec scd4x_channels[] = { .sign = 'u', .realbits = 16, .storagebits = 16, - .endianness = IIO_BE, + .endianness = IIO_CPU, }, }, { @@ -599,7 +599,7 @@ static const struct iio_chan_spec scd4x_channels[] = { .sign = 'u', .realbits = 16, .storagebits = 16, - .endianness = IIO_BE, + .endianness = IIO_CPU, }, }, { @@ -612,7 +612,7 @@ static const struct iio_chan_spec scd4x_channels[] = { .sign = 'u', .realbits = 16, .storagebits = 16, - .endianness = IIO_BE, + .endianness = IIO_CPU, }, }, }; diff --git a/drivers/iio/common/Kconfig b/drivers/iio/common/Kconfig index 1ccb5ccf370660..e3818ef567822b 100644 --- a/drivers/iio/common/Kconfig +++ b/drivers/iio/common/Kconfig @@ -3,6 +3,7 @@ # IIO common modules # +source "drivers/iio/common/aop_sensors/Kconfig" source "drivers/iio/common/cros_ec_sensors/Kconfig" source "drivers/iio/common/hid-sensors/Kconfig" source "drivers/iio/common/inv_sensors/Kconfig" diff --git a/drivers/iio/common/Makefile b/drivers/iio/common/Makefile index d3e952239a6219..5f99a429725d66 100644 --- a/drivers/iio/common/Makefile +++ b/drivers/iio/common/Makefile @@ -8,6 +8,7 @@ # # When adding new entries keep the list in alphabetical order +obj-y += aop_sensors/ obj-y += cros_ec_sensors/ obj-y += hid-sensors/ obj-y += inv_sensors/ diff --git a/drivers/iio/common/aop_sensors/Kconfig b/drivers/iio/common/aop_sensors/Kconfig new file mode 100644 index 00000000000000..6f6949bdf6a5d8 --- /dev/null +++ b/drivers/iio/common/aop_sensors/Kconfig @@ -0,0 +1,22 @@ +# SPDX-License-Identifier: GPL-2.0-only OR MIT + +config IIO_AOP_SENSOR_LAS + tristate "AOP Lid angle sensor" + depends on ARCH_APPLE || COMPILE_TEST + depends on RUST + depends on SYSFS + select APPLE_AOP + help + Module to handle the lid angle sensor attached to the AOP + coprocessor on Apple laptops. + +config IIO_AOP_SENSOR_ALS + tristate "AOP Ambient light sensor" + depends on ARCH_APPLE || COMPILE_TEST + depends on RUST + depends on SYSFS + depends on RUST_FW_LOADER_ABSTRACTIONS + select APPLE_AOP + help + Module to handle the ambient light sensor attached to the AOP + coprocessor on Apple laptops. diff --git a/drivers/iio/common/aop_sensors/Makefile b/drivers/iio/common/aop_sensors/Makefile new file mode 100644 index 00000000000000..8da5a19efe0f0c --- /dev/null +++ b/drivers/iio/common/aop_sensors/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only OR MIT + +obj-$(CONFIG_IIO_AOP_SENSOR_LAS) += aop_las.o +obj-$(CONFIG_IIO_AOP_SENSOR_ALS) += aop_als.o diff --git a/drivers/iio/common/aop_sensors/aop_als.rs b/drivers/iio/common/aop_sensors/aop_als.rs new file mode 100644 index 00000000000000..41994e2f7ffbc2 --- /dev/null +++ b/drivers/iio/common/aop_sensors/aop_als.rs @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Apple AOP ambient light sensor driver +//! +//! Copyright (C) The Asahi Linux Contributors + +use kernel::{ + bindings, c_str, + device::Core, + firmware::Firmware, + iio::common::aop_sensors::{AopSensorData, IIORegistration, MessageProcessor}, + module_platform_driver, of, platform, + prelude::*, + soc::apple::aop::{EPICService, AOP}, + sync::Arc, + types::ForeignOwnable, +}; + +const EPIC_SUBTYPE_GET_AOP_PROPERTY: u16 = 0xa; +const EPIC_SUBTYPE_SET_ALS_PROPERTY: u16 = 0x4; +const LUX_OFFSET_CT720: usize = 0x1d; +const LUX_OFFSET_VD6286: usize = 0x28; + +fn get_lux_offset(aop: &dyn AOP, dev: &platform::Device, svc: &EPICService) -> Result { + let name = get_aop_property(aop, svc, 0xf, 16)?.1; + match name.as_slice() { + b"Redbird\0" => Ok(LUX_OFFSET_VD6286), + b"FireFish2\0" => Ok(LUX_OFFSET_CT720), + _ => { + dev_warn!( + dev.as_ref(), + "Unknown sensor type {:?}", + core::str::from_utf8(&name) + ); + Err(EIO) + } + } +} + +fn enable_als(aop: &dyn AOP, dev: &platform::Device, svc: &EPICService) -> Result<()> { + let fw = Firmware::request(c_str!("apple/aop-als-cal.bin"), dev.as_ref())?; + set_als_property(aop, svc, 0xb, fw.data())?; + set_als_property(aop, svc, 0, &200000u32.to_le_bytes())?; + + Ok(()) +} + +fn get_aop_property( + aop: &dyn AOP, + svc: &EPICService, + tag: u32, + data_len: usize, +) -> Result<(u32, KVec)> { + let mut buf = KVec::new(); + buf.resize(8, 0, GFP_KERNEL)?; + buf[4..8].copy_from_slice(&tag.to_le_bytes()); + aop.epic_call_ret(svc, EPIC_SUBTYPE_GET_AOP_PROPERTY, &buf, data_len) +} + +fn set_als_property(aop: &dyn AOP, svc: &EPICService, tag: u32, data: &[u8]) -> Result { + let mut buf = KVec::new(); + buf.resize(data.len() + 8, 0, GFP_KERNEL)?; + buf[8..].copy_from_slice(data); + buf[4..8].copy_from_slice(&tag.to_le_bytes()); + aop.epic_call(svc, EPIC_SUBTYPE_SET_ALS_PROPERTY, &buf) +} + +fn f32_to_u32(f: u32) -> u32 { + if f & 0x80000000 != 0 { + return 0; + } + let exp = ((f & 0x7f800000) >> 23) as i32 - 127; + if exp < 0 { + return 0; + } + if exp == 128 && f & 0x7fffff != 0 { + return 0; + } + let mant = f & 0x7fffff | 0x800000; + if exp <= 23 { + return mant >> (23 - exp); + } + if exp >= 32 { + return u32::MAX; + } + mant << (exp - 23) +} + +struct MsgProc(usize); + +impl MessageProcessor for MsgProc { + fn process(&self, message: &[u8]) -> u32 { + let offset = self.0; + let raw = u32::from_le_bytes(message[offset..offset + 4].try_into().unwrap()); + f32_to_u32(raw) + } +} + +#[repr(transparent)] +struct IIOAopAlsDriver(IIORegistration); + +kernel::of_device_table!( + OF_TABLE, + MODULE_OF_TABLE, + (), + [(of::DeviceId::new(c_str!("apple,aop-als")), ())] +); + +impl platform::Driver for IIOAopAlsDriver { + type IdInfo = (); + + const OF_ID_TABLE: Option> = Some(&OF_TABLE); + + fn probe( + pdev: &platform::Device, + _info: Option<&()>, + ) -> Result>> { + let dev = pdev.as_ref(); + let parent = dev.parent().unwrap(); + // SAFETY: our parent is AOP, and AopDriver is repr(transparent) for Arc + let adata_ptr = unsafe { Pin::>>::borrow(parent.get_drvdata()) }; + let adata = (&*adata_ptr).clone(); + // SAFETY: AOP sets the platform data correctly + let service = unsafe { *((*dev.as_raw()).platform_data as *const EPICService) }; + let ty = bindings::BINDINGS_IIO_LIGHT; + let offset = get_lux_offset(adata.as_ref(), pdev, &service)?; + let data = AopSensorData::new(dev.into(), ty, MsgProc(offset))?; + adata.add_fakehid_listener(service, data.clone())?; + enable_als(adata.as_ref(), pdev, &service)?; + let info_mask = 1 << bindings::BINDINGS_IIO_CHAN_INFO_PROCESSED; + Ok(KBox::pin( + IIOAopAlsDriver(IIORegistration::::new( + data, + c_str!("aop-sensors-als"), + ty, + info_mask, + &THIS_MODULE, + )?), + GFP_KERNEL, + )?) + } +} + +module_platform_driver! { + type: IIOAopAlsDriver, + name: "iio_aop_als", + description: "AOP ambient light sensor driver", + license: "Dual MIT/GPL", + alias: ["platform:iio_aop_als"], + firmware: ["apple/aop-als-cal.bin"], +} diff --git a/drivers/iio/common/aop_sensors/aop_las.rs b/drivers/iio/common/aop_sensors/aop_las.rs new file mode 100644 index 00000000000000..35bb8ec35e28f4 --- /dev/null +++ b/drivers/iio/common/aop_sensors/aop_las.rs @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Apple AOP lid angle sensor driver +//! +//! Copyright (C) The Asahi Linux Contributors + +use kernel::{ + bindings, c_str, + device::Core, + iio::common::aop_sensors::{AopSensorData, IIORegistration, MessageProcessor}, + module_platform_driver, of, platform, + prelude::*, + soc::apple::aop::{EPICService, AOP}, + sync::Arc, + types::ForeignOwnable, +}; + +struct MsgProc; + +impl MessageProcessor for MsgProc { + fn process(&self, message: &[u8]) -> u32 { + message[1] as u32 + } +} + +#[repr(transparent)] +struct IIOAopLasDriver(IIORegistration); + +kernel::of_device_table!( + OF_TABLE, + MODULE_OF_TABLE, + (), + [(of::DeviceId::new(c_str!("apple,aop-las")), ())] +); + +impl platform::Driver for IIOAopLasDriver { + type IdInfo = (); + + const OF_ID_TABLE: Option> = Some(&OF_TABLE); + + fn probe( + pdev: &platform::Device, + _info: Option<&()>, + ) -> Result>> { + let dev = pdev.as_ref(); + let parent = dev.parent().unwrap(); + // SAFETY: our parent is AOP, and AopDriver is repr(transparent) for Arc + let adata_ptr = unsafe { Pin::>>::borrow(parent.get_drvdata()) }; + let adata = (&*adata_ptr).clone(); + // SAFETY: AOP sets the platform data correctly + let service = unsafe { *((*dev.as_raw()).platform_data as *const EPICService) }; + + let ty = bindings::BINDINGS_IIO_ANGL; + let data = AopSensorData::new(dev.into(), ty, MsgProc)?; + adata.add_fakehid_listener(service, data.clone())?; + let info_mask = 1 << bindings::BINDINGS_IIO_CHAN_INFO_RAW; + Ok(KBox::pin( + IIOAopLasDriver(IIORegistration::::new( + data, + c_str!("aop-sensors-las"), + ty, + info_mask, + &THIS_MODULE, + )?), + GFP_KERNEL, + )?) + } +} + +module_platform_driver! { + type: IIOAopLasDriver, + name: "iio_aop_las", + description: "AOP lid angle sensor driver", + license: "Dual MIT/GPL", + alias: ["platform:iio_aop_las"], +} diff --git a/drivers/iio/dac/ad3552r-hs.c b/drivers/iio/dac/ad3552r-hs.c index 41b96b48ba98b6..a9578afa7015d2 100644 --- a/drivers/iio/dac/ad3552r-hs.c +++ b/drivers/iio/dac/ad3552r-hs.c @@ -549,12 +549,15 @@ static ssize_t ad3552r_hs_write_data_source(struct file *f, guard(mutex)(&st->lock); + if (count >= sizeof(buf)) + return -ENOSPC; + ret = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, userbuf, count); if (ret < 0) return ret; - buf[count] = '\0'; + buf[ret] = '\0'; ret = match_string(dbgfs_attr_source, ARRAY_SIZE(dbgfs_attr_source), buf); diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c index d9cae9555e5df4..4b18498aa0749e 100644 --- a/drivers/iio/dac/ad5686.c +++ b/drivers/iio/dac/ad5686.c @@ -434,6 +434,12 @@ static const struct ad5686_chip_info ad5686_chip_info_tbl[] = { .num_channels = 4, .regmap_type = AD5686_REGMAP, }, + [ID_AD5695R] = { + .channels = ad5685r_channels, + .int_vref_mv = 2500, + .num_channels = 4, + .regmap_type = AD5686_REGMAP, + }, [ID_AD5696] = { .channels = ad5686_channels, .num_channels = 4, diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c index 67ae7d1012bc27..ee2fcd20545dee 100644 --- a/drivers/iio/gyro/mpu3050-core.c +++ b/drivers/iio/gyro/mpu3050-core.c @@ -1162,10 +1162,8 @@ int mpu3050_common_probe(struct device *dev, mpu3050->regs[1].supply = mpu3050_reg_vlogic; ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(mpu3050->regs), mpu3050->regs); - if (ret) { - dev_err(dev, "Cannot get regulators\n"); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "Cannot get regulators\n"); ret = mpu3050_power_up(mpu3050); if (ret) diff --git a/drivers/iio/imu/bmi270/bmi270_spi.c b/drivers/iio/imu/bmi270/bmi270_spi.c index 19dd7734f9d07c..80c9fa1d685abc 100644 --- a/drivers/iio/imu/bmi270/bmi270_spi.c +++ b/drivers/iio/imu/bmi270/bmi270_spi.c @@ -60,7 +60,7 @@ static int bmi270_spi_probe(struct spi_device *spi) &bmi270_spi_regmap_config); if (IS_ERR(regmap)) return dev_err_probe(dev, PTR_ERR(regmap), - "Failed to init i2c regmap"); + "Failed to init spi regmap\n"); return bmi270_core_probe(dev, regmap, chip_info); } diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h index 381b016fa52434..56244d49ab2fcc 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h @@ -383,7 +383,7 @@ enum st_lsm6dsx_fifo_mode { * @id: Sensor identifier. * @hw: Pointer to instance of struct st_lsm6dsx_hw. * @gain: Configured sensor sensitivity. - * @odr: Output data rate of the sensor [Hz]. + * @odr: Output data rate of the sensor [mHz]. * @samples_to_discard: Number of samples to discard for filters settling time. * @watermark: Sensor watermark level. * @decimator: Sensor decimation factor. diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c index a2daf0c14d965d..28ebb27d892495 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c @@ -101,6 +101,13 @@ static const struct iio_chan_spec st_lsm6dsx_acc_channels[] = { IIO_CHAN_SOFT_TIMESTAMP(3), }; +static const struct iio_chan_spec st_lsm6ds0_acc_channels[] = { + ST_LSM6DSX_CHANNEL(IIO_ACCEL, 0x28, IIO_MOD_X, 0), + ST_LSM6DSX_CHANNEL(IIO_ACCEL, 0x2a, IIO_MOD_Y, 1), + ST_LSM6DSX_CHANNEL(IIO_ACCEL, 0x2c, IIO_MOD_Z, 2), + IIO_CHAN_SOFT_TIMESTAMP(3), +}; + static const struct iio_chan_spec st_lsm6dsx_gyro_channels[] = { ST_LSM6DSX_CHANNEL(IIO_ANGL_VEL, 0x22, IIO_MOD_X, 0), ST_LSM6DSX_CHANNEL(IIO_ANGL_VEL, 0x24, IIO_MOD_Y, 1), @@ -142,8 +149,8 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = { }, .channels = { [ST_LSM6DSX_ID_ACC] = { - .chan = st_lsm6dsx_acc_channels, - .len = ARRAY_SIZE(st_lsm6dsx_acc_channels), + .chan = st_lsm6ds0_acc_channels, + .len = ARRAY_SIZE(st_lsm6ds0_acc_channels), }, [ST_LSM6DSX_ID_GYRO] = { .chan = st_lsm6ds0_gyro_channels, @@ -1449,8 +1456,8 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = { }, .channels = { [ST_LSM6DSX_ID_ACC] = { - .chan = st_lsm6dsx_acc_channels, - .len = ARRAY_SIZE(st_lsm6dsx_acc_channels), + .chan = st_lsm6ds0_acc_channels, + .len = ARRAY_SIZE(st_lsm6ds0_acc_channels), }, [ST_LSM6DSX_ID_GYRO] = { .chan = st_lsm6dsx_gyro_channels, diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 88c3d585a1bd0c..117ffad4f3769a 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1654,6 +1654,10 @@ static void iio_dev_release(struct device *device) iio_device_detach_buffers(indio_dev); + mutex_destroy(&iio_dev_opaque->info_exist_lock); + mutex_destroy(&iio_dev_opaque->mlock); + + lockdep_unregister_key(&iio_dev_opaque->info_exist_key); lockdep_unregister_key(&iio_dev_opaque->mlock_key); ida_free(&iio_ida, iio_dev_opaque->id); @@ -1694,12 +1698,6 @@ struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv) ACCESS_PRIVATE(indio_dev, priv) = (char *)iio_dev_opaque + ALIGN(sizeof(*iio_dev_opaque), IIO_DMA_MINALIGN); - indio_dev->dev.parent = parent; - indio_dev->dev.type = &iio_device_type; - indio_dev->dev.bus = &iio_bus_type; - device_initialize(&indio_dev->dev); - mutex_init(&iio_dev_opaque->mlock); - mutex_init(&iio_dev_opaque->info_exist_lock); INIT_LIST_HEAD(&iio_dev_opaque->channel_attr_list); iio_dev_opaque->id = ida_alloc(&iio_ida, GFP_KERNEL); @@ -1720,7 +1718,15 @@ struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv) INIT_LIST_HEAD(&iio_dev_opaque->ioctl_handlers); lockdep_register_key(&iio_dev_opaque->mlock_key); - lockdep_set_class(&iio_dev_opaque->mlock, &iio_dev_opaque->mlock_key); + lockdep_register_key(&iio_dev_opaque->info_exist_key); + + mutex_init_with_key(&iio_dev_opaque->mlock, &iio_dev_opaque->mlock_key); + mutex_init_with_key(&iio_dev_opaque->info_exist_lock, &iio_dev_opaque->info_exist_key); + + indio_dev->dev.parent = parent; + indio_dev->dev.type = &iio_device_type; + indio_dev->dev.bus = &iio_bus_type; + device_initialize(&indio_dev->dev); return indio_dev; } diff --git a/drivers/iio/pressure/mprls0025pa.c b/drivers/iio/pressure/mprls0025pa.c index 2336f2760eaeb7..d4133fef91fac4 100644 --- a/drivers/iio/pressure/mprls0025pa.c +++ b/drivers/iio/pressure/mprls0025pa.c @@ -59,7 +59,7 @@ * * Values given to the userspace in sysfs interface: * * raw - press_cnt - * * offset - (-1 * outputmin) - pmin / scale + * * offset - (-1 * outputmin) + pmin / scale * note: With all sensors from the datasheet pmin = 0 * which reduces the offset to (-1 * outputmin) */ @@ -160,8 +160,8 @@ static const struct iio_chan_spec mpr_channels[] = { BIT(IIO_CHAN_INFO_OFFSET), .scan_index = 0, .scan_type = { - .sign = 's', - .realbits = 32, + .sign = 'u', + .realbits = 24, .storagebits = 32, .endianness = IIO_CPU, }, @@ -313,8 +313,7 @@ static int mpr_read_raw(struct iio_dev *indio_dev, return IIO_VAL_INT_PLUS_NANO; case IIO_CHAN_INFO_OFFSET: *val = data->offset; - *val2 = data->offset2; - return IIO_VAL_INT_PLUS_NANO; + return IIO_VAL_INT; default: return -EINVAL; } @@ -330,8 +329,9 @@ int mpr_common_probe(struct device *dev, const struct mpr_ops *ops, int irq) struct mpr_data *data; struct iio_dev *indio_dev; const char *triplet; - s64 scale, offset; + s64 odelta, pdelta; u32 func; + s32 tmp; indio_dev = devm_iio_device_alloc(dev, sizeof(*data)); if (!indio_dev) @@ -405,23 +405,17 @@ int mpr_common_probe(struct device *dev, const struct mpr_ops *ops, int irq) data->outmin = mpr_func_spec[data->function].output_min; data->outmax = mpr_func_spec[data->function].output_max; - /* use 64 bit calculation for preserving a reasonable precision */ - scale = div_s64(((s64)(data->pmax - data->pmin)) * NANO, - data->outmax - data->outmin); - data->scale = div_s64_rem(scale, NANO, &data->scale2); - /* - * multiply with NANO before dividing by scale and later divide by NANO - * again. - */ - offset = ((-1LL) * (s64)data->outmin) * NANO - - div_s64(div_s64((s64)data->pmin * NANO, scale), NANO); - data->offset = div_s64_rem(offset, NANO, &data->offset2); + odelta = data->outmax - data->outmin; + pdelta = data->pmax - data->pmin; + + data->scale = div_s64_rem(div_s64(pdelta * NANO, odelta), NANO, &tmp); + data->scale2 = tmp; + + data->offset = div_s64(odelta * data->pmin, pdelta) - data->outmin; if (data->irq > 0) { - ret = devm_request_irq(dev, data->irq, mpr_eoc_handler, - IRQF_TRIGGER_RISING, - dev_name(dev), - data); + ret = devm_request_irq(dev, data->irq, mpr_eoc_handler, 0, + dev_name(dev), data); if (ret) return dev_err_probe(dev, ret, "request irq %d failed\n", data->irq); diff --git a/drivers/iio/pressure/mprls0025pa.h b/drivers/iio/pressure/mprls0025pa.h index d62a018eaff32b..b6944b30512677 100644 --- a/drivers/iio/pressure/mprls0025pa.h +++ b/drivers/iio/pressure/mprls0025pa.h @@ -53,7 +53,6 @@ enum mpr_func_id { * @scale: pressure scale * @scale2: pressure scale, decimal number * @offset: pressure offset - * @offset2: pressure offset, decimal number * @gpiod_reset: reset * @irq: end of conversion irq. used to distinguish between irq mode and * reading in a loop until data is ready @@ -75,7 +74,6 @@ struct mpr_data { int scale; int scale2; int offset; - int offset2; struct gpio_desc *gpiod_reset; int irq; struct completion completion; diff --git a/drivers/iio/pressure/mprls0025pa_spi.c b/drivers/iio/pressure/mprls0025pa_spi.c index d04102f8a4a035..cf17eb2e720830 100644 --- a/drivers/iio/pressure/mprls0025pa_spi.c +++ b/drivers/iio/pressure/mprls0025pa_spi.c @@ -8,6 +8,7 @@ * https://prod-edam.honeywell.com/content/dam/honeywell-edam/sps/siot/en-us/products/sensors/pressure-sensors/board-mount-pressure-sensors/micropressure-mpr-series/documents/sps-siot-mpr-series-datasheet-32332628-ciid-172626.pdf */ +#include #include #include #include @@ -40,17 +41,25 @@ static int mpr_spi_xfer(struct mpr_data *data, const u8 cmd, const u8 pkt_len) { struct spi_device *spi = to_spi_device(data->dev); struct mpr_spi_buf *buf = spi_get_drvdata(spi); - struct spi_transfer xfer; + struct spi_transfer xfers[2] = { }; if (pkt_len > MPR_MEASUREMENT_RD_SIZE) return -EOVERFLOW; buf->tx[0] = cmd; - xfer.tx_buf = buf->tx; - xfer.rx_buf = data->buffer; - xfer.len = pkt_len; - return spi_sync_transfer(spi, &xfer, 1); + /* + * Dummy transfer with no data, just cause a 2.5us+ delay between the CS assert + * and the first clock edge as per the datasheet tHDSS timing requirement. + */ + xfers[0].delay.value = 2500; + xfers[0].delay.unit = SPI_DELAY_UNIT_NSECS; + + xfers[1].tx_buf = buf->tx; + xfers[1].rx_buf = data->buffer; + xfers[1].len = pkt_len; + + return spi_sync_transfer(spi, xfers, ARRAY_SIZE(xfers)); } static const struct mpr_ops mpr_spi_ops = { diff --git a/drivers/iio/test/Kconfig b/drivers/iio/test/Kconfig index 6e65e929791ca2..4fc17dd0dcd770 100644 --- a/drivers/iio/test/Kconfig +++ b/drivers/iio/test/Kconfig @@ -8,7 +8,6 @@ config IIO_GTS_KUNIT_TEST tristate "Test IIO gain-time-scale helpers" if !KUNIT_ALL_TESTS depends on KUNIT select IIO_GTS_HELPER - select TEST_KUNIT_DEVICE_HELPERS default KUNIT_ALL_TESTS help build unit tests for the IIO light sensor gain-time-scale helpers. diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 61596cda2b65f3..35ba852a172aad 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -80,37 +80,25 @@ static const struct nla_policy ib_nl_addr_policy[LS_NLA_TYPE_MAX] = { .min = sizeof(struct rdma_nla_ls_gid)}, }; -static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh) +static void ib_nl_process_ip_rsep(const struct nlmsghdr *nlh) { struct nlattr *tb[LS_NLA_TYPE_MAX] = {}; + union ib_gid gid; + struct addr_req *req; + int found = 0; int ret; if (nlh->nlmsg_flags & RDMA_NL_LS_F_ERR) - return false; + return; ret = nla_parse_deprecated(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh), nlmsg_len(nlh), ib_nl_addr_policy, NULL); if (ret) - return false; - - return true; -} - -static void ib_nl_process_good_ip_rsep(const struct nlmsghdr *nlh) -{ - const struct nlattr *head, *curr; - union ib_gid gid; - struct addr_req *req; - int len, rem; - int found = 0; - - head = (const struct nlattr *)nlmsg_data(nlh); - len = nlmsg_len(nlh); + return; - nla_for_each_attr(curr, head, len, rem) { - if (curr->nla_type == LS_NLA_TYPE_DGID) - memcpy(&gid, nla_data(curr), nla_len(curr)); - } + if (!tb[LS_NLA_TYPE_DGID]) + return; + memcpy(&gid, nla_data(tb[LS_NLA_TYPE_DGID]), sizeof(gid)); spin_lock_bh(&lock); list_for_each_entry(req, &req_list, list) { @@ -137,8 +125,7 @@ int ib_nl_handle_ip_res_resp(struct sk_buff *skb, !(NETLINK_CB(skb).sk)) return -EPERM; - if (ib_nl_is_good_ip_resp(nlh)) - ib_nl_process_good_ip_rsep(nlh); + ib_nl_process_ip_rsep(nlh); return 0; } diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index 81cf3c902e8195..0fc1c5bce2f0d3 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -1537,7 +1537,8 @@ static void ib_cache_event_task(struct work_struct *_work) * the cache. */ ret = ib_cache_update(work->event.device, work->event.element.port_num, - work->event.event == IB_EVENT_GID_CHANGE, + work->event.event == IB_EVENT_GID_CHANGE || + work->event.event == IB_EVENT_CLIENT_REREGISTER, work->event.event == IB_EVENT_PKEY_CHANGE, work->enforce_security); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 5b2d3ae3f9fce8..ce511800b056cf 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2009,6 +2009,7 @@ static void destroy_mc(struct rdma_id_private *id_priv, ib_sa_free_multicast(mc->sa_mc); if (rdma_protocol_roce(id_priv->id.device, id_priv->id.port_num)) { + struct rdma_cm_event *event = &mc->iboe_join.event; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct net_device *ndev = NULL; @@ -2031,6 +2032,8 @@ static void destroy_mc(struct rdma_id_private *id_priv, dev_put(ndev); cancel_work_sync(&mc->iboe_join.work); + if (event->event == RDMA_CM_EVENT_MULTICAST_JOIN) + rdma_destroy_ah_attr(&event->param.ud.ah_attr); } kfree(mc); } diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index b4f3c835844a92..e3ba236d7c09fb 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -2881,8 +2881,10 @@ int ib_del_sub_device_and_put(struct ib_device *sub) { struct ib_device *parent = sub->parent; - if (!parent) + if (!parent) { + ib_device_put(sub); return -EOPNOTSUPP; + } mutex_lock(&parent->subdev_lock); list_del(&sub->subdev_list); diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index 62410578dec37d..eb942ab9c40559 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -95,7 +95,6 @@ static struct workqueue_struct *iwcm_wq; struct iwcm_work { struct work_struct work; struct iwcm_id_private *cm_id; - struct list_head list; struct iw_cm_event event; struct list_head free_list; }; @@ -178,7 +177,6 @@ static int alloc_work_entries(struct iwcm_id_private *cm_id_priv, int count) return -ENOMEM; } work->cm_id = cm_id_priv; - INIT_LIST_HEAD(&work->list); put_work(work); } return 0; @@ -213,7 +211,6 @@ static void free_cm_id(struct iwcm_id_private *cm_id_priv) static bool iwcm_deref_id(struct iwcm_id_private *cm_id_priv) { if (refcount_dec_and_test(&cm_id_priv->refcount)) { - BUG_ON(!list_empty(&cm_id_priv->work_list)); free_cm_id(cm_id_priv); return true; } @@ -260,7 +257,6 @@ struct iw_cm_id *iw_create_cm_id(struct ib_device *device, refcount_set(&cm_id_priv->refcount, 1); init_waitqueue_head(&cm_id_priv->connect_wait); init_completion(&cm_id_priv->destroy_comp); - INIT_LIST_HEAD(&cm_id_priv->work_list); INIT_LIST_HEAD(&cm_id_priv->work_free_list); return &cm_id_priv->id; @@ -1007,13 +1003,13 @@ static int process_event(struct iwcm_id_private *cm_id_priv, } /* - * Process events on the work_list for the cm_id. If the callback - * function requests that the cm_id be deleted, a flag is set in the - * cm_id flags to indicate that when the last reference is - * removed, the cm_id is to be destroyed. This is necessary to - * distinguish between an object that will be destroyed by the app - * thread asleep on the destroy_comp list vs. an object destroyed - * here synchronously when the last reference is removed. + * Process events for the cm_id. If the callback function requests + * that the cm_id be deleted, a flag is set in the cm_id flags to + * indicate that when the last reference is removed, the cm_id is + * to be destroyed. This is necessary to distinguish between an + * object that will be destroyed by the app thread asleep on the + * destroy_comp list vs. an object destroyed here synchronously + * when the last reference is removed. */ static void cm_work_handler(struct work_struct *_work) { @@ -1024,35 +1020,26 @@ static void cm_work_handler(struct work_struct *_work) int ret = 0; spin_lock_irqsave(&cm_id_priv->lock, flags); - while (!list_empty(&cm_id_priv->work_list)) { - work = list_first_entry(&cm_id_priv->work_list, - struct iwcm_work, list); - list_del_init(&work->list); - levent = work->event; - put_work(work); - spin_unlock_irqrestore(&cm_id_priv->lock, flags); - - if (!test_bit(IWCM_F_DROP_EVENTS, &cm_id_priv->flags)) { - ret = process_event(cm_id_priv, &levent); - if (ret) { - destroy_cm_id(&cm_id_priv->id); - WARN_ON_ONCE(iwcm_deref_id(cm_id_priv)); - } - } else - pr_debug("dropping event %d\n", levent.event); - if (iwcm_deref_id(cm_id_priv)) - return; - spin_lock_irqsave(&cm_id_priv->lock, flags); - } + levent = work->event; + put_work(work); spin_unlock_irqrestore(&cm_id_priv->lock, flags); + + if (!test_bit(IWCM_F_DROP_EVENTS, &cm_id_priv->flags)) { + ret = process_event(cm_id_priv, &levent); + if (ret) { + destroy_cm_id(&cm_id_priv->id); + WARN_ON_ONCE(iwcm_deref_id(cm_id_priv)); + } + } else + pr_debug("dropping event %d\n", levent.event); + if (iwcm_deref_id(cm_id_priv)) + return; } /* * This function is called on interrupt context. Schedule events on * the iwcm_wq thread to allow callback functions to downcall into - * the CM and/or block. Events are queued to a per-CM_ID - * work_list. If this is the first event on the work_list, the work - * element is also queued on the iwcm_wq thread. + * the CM and/or block. * * Each event holds a reference on the cm_id. Until the last posted * event has been delivered and processed, the cm_id cannot be @@ -1094,7 +1081,6 @@ static int cm_event_handler(struct iw_cm_id *cm_id, } refcount_inc(&cm_id_priv->refcount); - list_add_tail(&work->list, &cm_id_priv->work_list); queue_work(iwcm_wq, &work->work); out: spin_unlock_irqrestore(&cm_id_priv->lock, flags); diff --git a/drivers/infiniband/core/iwcm.h b/drivers/infiniband/core/iwcm.h index bf74639be1287c..b56fb12edece40 100644 --- a/drivers/infiniband/core/iwcm.h +++ b/drivers/infiniband/core/iwcm.h @@ -50,7 +50,6 @@ struct iwcm_id_private { struct ib_qp *qp; struct completion destroy_comp; wait_queue_head_t connect_wait; - struct list_head work_list; spinlock_t lock; refcount_t refcount; struct list_head work_free_list; diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c index 6354ddf2a274ce..2522ff1cc462c7 100644 --- a/drivers/infiniband/core/rw.c +++ b/drivers/infiniband/core/rw.c @@ -651,34 +651,57 @@ unsigned int rdma_rw_mr_factor(struct ib_device *device, u32 port_num, } EXPORT_SYMBOL(rdma_rw_mr_factor); +/** + * rdma_rw_max_send_wr - compute max Send WRs needed for RDMA R/W contexts + * @dev: RDMA device + * @port_num: port number + * @max_rdma_ctxs: number of rdma_rw_ctx structures + * @create_flags: QP create flags (pass IB_QP_CREATE_INTEGRITY_EN if + * data integrity will be enabled on the QP) + * + * Returns the total number of Send Queue entries needed for + * @max_rdma_ctxs. The result accounts for memory registration and + * invalidation work requests when the device requires them. + * + * ULPs use this to size Send Queues and Send CQs before creating a + * Queue Pair. + */ +unsigned int rdma_rw_max_send_wr(struct ib_device *dev, u32 port_num, + unsigned int max_rdma_ctxs, u32 create_flags) +{ + unsigned int factor = 1; + unsigned int result; + + if (create_flags & IB_QP_CREATE_INTEGRITY_EN || + rdma_rw_can_use_mr(dev, port_num)) + factor += 2; /* reg + inv */ + + if (check_mul_overflow(factor, max_rdma_ctxs, &result)) + return UINT_MAX; + return result; +} +EXPORT_SYMBOL(rdma_rw_max_send_wr); + void rdma_rw_init_qp(struct ib_device *dev, struct ib_qp_init_attr *attr) { - u32 factor; + unsigned int factor = 1; WARN_ON_ONCE(attr->port_num == 0); /* - * Each context needs at least one RDMA READ or WRITE WR. - * - * For some hardware we might need more, eventually we should ask the - * HCA driver for a multiplier here. - */ - factor = 1; - - /* - * If the device needs MRs to perform RDMA READ or WRITE operations, - * we'll need two additional MRs for the registrations and the - * invalidation. + * If the device uses MRs to perform RDMA READ or WRITE operations, + * or if data integrity is enabled, account for registration and + * invalidation work requests. */ if (attr->create_flags & IB_QP_CREATE_INTEGRITY_EN || rdma_rw_can_use_mr(dev, attr->port_num)) - factor += 2; /* inv + reg */ + factor += 2; /* reg + inv */ attr->cap.max_send_wr += factor * attr->cap.max_rdma_ctxs; /* - * But maybe we were just too high in the sky and the device doesn't - * even support all we need, and we'll have to live with what we get.. + * The device might not support all we need, and we'll have to + * live with what we get. */ attr->cap.max_send_wr = min_t(u32, attr->cap.max_send_wr, dev->attrs.max_qp_wr); diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index fd67fc9fe85a46..2f7e3c4483fc57 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -514,7 +514,8 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, struct rdma_ah_attr ah_attr; struct ib_ah *ah; __be64 *tid; - int ret, data_len, hdr_len, copy_offset, rmpp_active; + int ret, hdr_len, copy_offset, rmpp_active; + size_t data_len; u8 base_version; if (count < hdr_size(file) + IB_MGMT_RMPP_HDR) @@ -588,7 +589,10 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, } base_version = ((struct ib_mad_hdr *)&packet->mad.data)->base_version; - data_len = count - hdr_size(file) - hdr_len; + if (check_sub_overflow(count, hdr_size(file) + hdr_len, &data_len)) { + ret = -EINVAL; + goto err_ah; + } packet->msg = ib_create_send_mad(agent, be32_to_cpu(packet->mad.hdr.qpn), packet->mad.hdr.pkey_index, rmpp_active, diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index ce16404cdfb8cc..f4616deeca5453 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -2049,7 +2049,10 @@ static int ib_uverbs_post_send(struct uverbs_attr_bundle *attrs) if (ret) return ret; - user_wr = kmalloc(cmd.wqe_size, GFP_KERNEL); + if (cmd.wqe_size < sizeof(struct ib_uverbs_send_wr)) + return -EINVAL; + + user_wr = kmalloc(cmd.wqe_size, GFP_KERNEL | __GFP_NOWARN); if (!user_wr) return -ENOMEM; @@ -2239,7 +2242,7 @@ ib_uverbs_unmarshall_recv(struct uverbs_req_iter *iter, u32 wr_count, if (ret) return ERR_PTR(ret); - user_wr = kmalloc(wqe_size, GFP_KERNEL); + user_wr = kmalloc(wqe_size, GFP_KERNEL | __GFP_NOWARN); if (!user_wr) return ERR_PTR(-ENOMEM); diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 3a5f81402d2f8b..d279e301f5a1a8 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -735,7 +735,7 @@ int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr, (struct in6_addr *)dgid); return 0; } else if (net_type == RDMA_NETWORK_IPV6 || - net_type == RDMA_NETWORK_IB || RDMA_NETWORK_ROCE_V1) { + net_type == RDMA_NETWORK_IB || net_type == RDMA_NETWORK_ROCE_V1) { *dgid = hdr->ibgrh.dgid; *sgid = hdr->ibgrh.sgid; return 0; diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.h b/drivers/infiniband/hw/bnxt_re/hw_counters.h index 09d371d442aa78..cebec033f4a014 100644 --- a/drivers/infiniband/hw/bnxt_re/hw_counters.h +++ b/drivers/infiniband/hw/bnxt_re/hw_counters.h @@ -89,6 +89,9 @@ enum bnxt_re_hw_stats { BNXT_RE_RES_SRQ_LOAD_ERR, BNXT_RE_RES_TX_PCI_ERR, BNXT_RE_RES_RX_PCI_ERR, + BNXT_RE_REQ_CQE_ERROR, + BNXT_RE_RESP_CQE_ERROR, + BNXT_RE_RESP_REMOTE_ACCESS_ERRS, BNXT_RE_OUT_OF_SEQ_ERR, BNXT_RE_TX_ATOMIC_REQ, BNXT_RE_TX_READ_REQ, @@ -110,9 +113,6 @@ enum bnxt_re_hw_stats { BNXT_RE_TX_CNP, BNXT_RE_RX_CNP, BNXT_RE_RX_ECN, - BNXT_RE_REQ_CQE_ERROR, - BNXT_RE_RESP_CQE_ERROR, - BNXT_RE_RESP_REMOTE_ACCESS_ERRS, BNXT_RE_NUM_EXT_COUNTERS }; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 84ce3fce2826b7..ff91511bd3389e 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -601,7 +601,8 @@ static int bnxt_re_create_fence_mr(struct bnxt_re_pd *pd) mr->qplib_mr.va = (u64)(unsigned long)fence->va; mr->qplib_mr.total_size = BNXT_RE_FENCE_BYTES; rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &mr->qplib_mr, NULL, - BNXT_RE_FENCE_PBL_SIZE, PAGE_SIZE); + BNXT_RE_FENCE_PBL_SIZE, PAGE_SIZE, + _is_alloc_mr_unified(rdev->dev_attr->dev_cap_flags)); if (rc) { ibdev_err(&rdev->ibdev, "Failed to register fence-MR\n"); goto fail; @@ -2918,14 +2919,9 @@ int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr, wqe.rawqp1.lflags |= SQ_SEND_RAWETH_QP1_LFLAGS_ROCE_CRC; } - switch (wr->send_flags) { - case IB_SEND_IP_CSUM: + if (wr->send_flags & IB_SEND_IP_CSUM) wqe.rawqp1.lflags |= SQ_SEND_RAWETH_QP1_LFLAGS_IP_CHKSUM; - break; - default: - break; - } fallthrough; case IB_WR_SEND_WITH_INV: rc = bnxt_re_build_send_wqe(qp, wr, &wqe); @@ -4027,7 +4023,7 @@ struct ib_mr *bnxt_re_get_dma_mr(struct ib_pd *ib_pd, int mr_access_flags) mr->qplib_mr.hwq.level = PBL_LVL_MAX; mr->qplib_mr.total_size = -1; /* Infinte length */ rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &mr->qplib_mr, NULL, 0, - PAGE_SIZE); + PAGE_SIZE, false); if (rc) goto fail_mr; @@ -4257,7 +4253,8 @@ static struct ib_mr *__bnxt_re_user_reg_mr(struct ib_pd *ib_pd, u64 length, u64 umem_pgs = ib_umem_num_dma_blocks(umem, page_size); rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &mr->qplib_mr, umem, - umem_pgs, page_size); + umem_pgs, page_size, + _is_alloc_mr_unified(rdev->dev_attr->dev_cap_flags)); if (rc) { ibdev_err(&rdev->ibdev, "Failed to register user MR - rc = %d\n", rc); rc = -EIO; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 295a9610f3e677..4dad0cfcfa98d1 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -1112,7 +1112,7 @@ static int bnxt_qplib_map_creq_db(struct bnxt_qplib_rcfw *rcfw, u32 reg_offt) creq_db->dbinfo.flags = 0; creq_db->reg.bar_id = RCFW_COMM_CONS_PCI_BAR_REGION; creq_db->reg.bar_base = pci_resource_start(pdev, creq_db->reg.bar_id); - if (!creq_db->reg.bar_id) + if (!creq_db->reg.bar_base) dev_err(&pdev->dev, "QPLIB: CREQ BAR region %d resc start is 0!", creq_db->reg.bar_id); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 875d7b52c06ab9..4d674a3aee1aa3 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -64,9 +64,7 @@ static void __free_pbl(struct bnxt_qplib_res *res, struct bnxt_qplib_pbl *pbl, for (i = 0; i < pbl->pg_count; i++) { if (pbl->pg_arr[i]) dma_free_coherent(&pdev->dev, pbl->pg_size, - (void *)((unsigned long) - pbl->pg_arr[i] & - PAGE_MASK), + pbl->pg_arr[i], pbl->pg_map_arr[i]); else dev_warn(&pdev->dev, @@ -237,7 +235,7 @@ int bnxt_qplib_alloc_init_hwq(struct bnxt_qplib_hwq *hwq, if (npbl % BIT(MAX_PDL_LVL_SHIFT)) npde++; /* Alloc PDE pages */ - sginfo.pgsize = npde * pg_size; + sginfo.pgsize = npde * ROCE_PG_SIZE_4K; sginfo.npages = 1; rc = __alloc_pbl(res, &hwq->pbl[PBL_LVL_0], &sginfo); if (rc) @@ -245,7 +243,7 @@ int bnxt_qplib_alloc_init_hwq(struct bnxt_qplib_hwq *hwq, /* Alloc PBL pages */ sginfo.npages = npbl; - sginfo.pgsize = PAGE_SIZE; + sginfo.pgsize = ROCE_PG_SIZE_4K; rc = __alloc_pbl(res, &hwq->pbl[PBL_LVL_1], &sginfo); if (rc) goto fail; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 9ef581ed785c82..408a34df266721 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -162,7 +162,7 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw) attr->max_srq_wqes = le32_to_cpu(sb->max_srq_wr) - 1; attr->max_srq_sges = sb->max_srq_sge; attr->max_pkey = 1; - attr->max_inline_data = le32_to_cpu(sb->max_inline_data); + attr->max_inline_data = attr->max_qp_sges * sizeof(struct sq_sge); if (!bnxt_qplib_is_chip_gen_p7(rcfw->res->cctx)) attr->l2_db_size = (sb->l2_db_space_size + 1) * (0x01 << RCFW_DBR_BASE_PAGE_SHIFT); @@ -578,7 +578,7 @@ int bnxt_qplib_dereg_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw, } int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, - struct ib_umem *umem, int num_pbls, u32 buf_pg_size) + struct ib_umem *umem, int num_pbls, u32 buf_pg_size, bool unified_mr) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct bnxt_qplib_hwq_attr hwq_attr = {}; @@ -640,7 +640,7 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, req.access = (mr->access_flags & BNXT_QPLIB_MR_ACCESS_MASK); req.va = cpu_to_le64(mr->va); req.key = cpu_to_le32(mr->lkey); - if (_is_alloc_mr_unified(res->dattr->dev_cap_flags)) + if (unified_mr) req.key = cpu_to_le32(mr->pd->id); req.flags = cpu_to_le16(mr->flags); req.mr_size = cpu_to_le64(mr->total_size); @@ -651,7 +651,7 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, if (rc) goto fail; - if (_is_alloc_mr_unified(res->dattr->dev_cap_flags)) { + if (unified_mr) { mr->lkey = le32_to_cpu(resp.xid); mr->rkey = mr->lkey; } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h index 147b5d9c03138b..5a45c55c6464c9 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h @@ -341,7 +341,7 @@ int bnxt_qplib_alloc_mrw(struct bnxt_qplib_res *res, int bnxt_qplib_dereg_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw, bool block); int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, - struct ib_umem *umem, int num_pbls, u32 buf_pg_size); + struct ib_umem *umem, int num_pbls, u32 buf_pg_size, bool unified_mr); int bnxt_qplib_free_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr); int bnxt_qplib_alloc_fast_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, int max); diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 22d3e25c3b9d11..755bba8d58bbc9 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -1320,13 +1320,9 @@ static int umem_to_page_list(struct efa_dev *dev, u32 hp_cnt, u8 hp_shift) { - u32 pages_in_hp = BIT(hp_shift - PAGE_SHIFT); struct ib_block_iter biter; unsigned int hp_idx = 0; - ibdev_dbg(&dev->ibdev, "hp_cnt[%u], pages_in_hp[%u]\n", - hp_cnt, pages_in_hp); - rdma_umem_for_each_dma_block(umem, &biter, BIT(hp_shift)) page_list[hp_idx++] = rdma_block_iter_dma_address(&biter); diff --git a/drivers/infiniband/hw/hns/hns_roce_ah.c b/drivers/infiniband/hw/hns/hns_roce_ah.c index 307c35888b3003..3b6c6a6e9f9779 100644 --- a/drivers/infiniband/hw/hns/hns_roce_ah.c +++ b/drivers/infiniband/hw/hns/hns_roce_ah.c @@ -61,7 +61,7 @@ int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, u8 tclass = get_tclass(grh); u8 priority = 0; u8 tc_mode = 0; - int ret; + int ret = 0; if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08 && udata) { ret = -EOPNOTSUPP; @@ -78,19 +78,18 @@ int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, ah->av.flowlabel = grh->flow_label; ah->av.udp_sport = get_ah_udp_sport(ah_attr); ah->av.tclass = tclass; + ah->av.sl = rdma_ah_get_sl(ah_attr); - ret = hr_dev->hw->get_dscp(hr_dev, tclass, &tc_mode, &priority); - if (ret == -EOPNOTSUPP) - ret = 0; - - if (ret && grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) - goto err_out; + if (grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) { + ret = hr_dev->hw->get_dscp(hr_dev, tclass, &tc_mode, &priority); + if (ret == -EOPNOTSUPP) + ret = 0; + else if (ret) + goto err_out; - if (tc_mode == HNAE3_TC_MAP_MODE_DSCP && - grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) - ah->av.sl = priority; - else - ah->av.sl = rdma_ah_get_sl(ah_attr); + if (tc_mode == HNAE3_TC_MAP_MODE_DSCP) + ah->av.sl = priority; + } if (!check_sl_valid(hr_dev, ah->av.sl)) { ret = -EINVAL; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 63052c0e76133b..f895731ad74a0f 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -3661,6 +3661,23 @@ static void hns_roce_v2_write_cqc(struct hns_roce_dev *hr_dev, HNS_ROCE_V2_CQ_DEFAULT_INTERVAL); } +static bool left_sw_wc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq) +{ + struct hns_roce_qp *hr_qp; + + list_for_each_entry(hr_qp, &hr_cq->sq_list, sq_node) { + if (hr_qp->sq.head != hr_qp->sq.tail) + return true; + } + + list_for_each_entry(hr_qp, &hr_cq->rq_list, rq_node) { + if (hr_qp->rq.head != hr_qp->rq.tail) + return true; + } + + return false; +} + static int hns_roce_v2_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) { @@ -3669,6 +3686,12 @@ static int hns_roce_v2_req_notify_cq(struct ib_cq *ibcq, struct hns_roce_v2_db cq_db = {}; u32 notify_flag; + if (hr_dev->state >= HNS_ROCE_DEVICE_STATE_RST_DOWN) { + if ((flags & IB_CQ_REPORT_MISSED_EVENTS) && + left_sw_wc(hr_dev, hr_cq)) + return 1; + return 0; + } /* * flags = 0, then notify_flag : next * flags = 1, then notify flag : solocited @@ -4975,20 +4998,22 @@ static int hns_roce_set_sl(struct ib_qp *ibqp, struct ib_device *ibdev = &hr_dev->ib_dev; int ret; - ret = hns_roce_hw_v2_get_dscp(hr_dev, get_tclass(&attr->ah_attr.grh), - &hr_qp->tc_mode, &hr_qp->priority); - if (ret && ret != -EOPNOTSUPP && - grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) { - ibdev_err_ratelimited(ibdev, - "failed to get dscp, ret = %d.\n", ret); - return ret; - } + hr_qp->sl = rdma_ah_get_sl(&attr->ah_attr); - if (hr_qp->tc_mode == HNAE3_TC_MAP_MODE_DSCP && - grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) - hr_qp->sl = hr_qp->priority; - else - hr_qp->sl = rdma_ah_get_sl(&attr->ah_attr); + if (grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) { + ret = hns_roce_hw_v2_get_dscp(hr_dev, + get_tclass(&attr->ah_attr.grh), + &hr_qp->tc_mode, &hr_qp->priority); + if (ret && ret != -EOPNOTSUPP) { + ibdev_err_ratelimited(ibdev, + "failed to get dscp, ret = %d.\n", + ret); + return ret; + } + + if (hr_qp->tc_mode == HNAE3_TC_MAP_MODE_DSCP) + hr_qp->sl = hr_qp->priority; + } if (!check_sl_valid(hr_dev, hr_qp->sl)) return -EINVAL; @@ -6878,7 +6903,8 @@ static int hns_roce_v2_init_eq_table(struct hns_roce_dev *hr_dev) INIT_WORK(&hr_dev->ecc_work, fmea_ram_ecc_work); - hr_dev->irq_workq = alloc_ordered_workqueue("hns_roce_irq_workq", 0); + hr_dev->irq_workq = alloc_ordered_workqueue("hns_roce_irq_workq", + WQ_MEM_RECLAIM); if (!hr_dev->irq_workq) { dev_err(dev, "failed to create irq workqueue.\n"); ret = -ENOMEM; diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c index c6a0a661d6e7ee..f4f4f92ba63aca 100644 --- a/drivers/infiniband/hw/irdma/cm.c +++ b/drivers/infiniband/hw/irdma/cm.c @@ -3710,7 +3710,7 @@ int irdma_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) iwpd = iwqp->iwpd; tagged_offset = (uintptr_t)iwqp->ietf_mem.va; ibmr = irdma_reg_phys_mr(&iwpd->ibpd, iwqp->ietf_mem.pa, buf_len, - IB_ACCESS_LOCAL_WRITE, &tagged_offset); + IB_ACCESS_LOCAL_WRITE, &tagged_offset, false); if (IS_ERR(ibmr)) { ret = -ENOMEM; goto error; diff --git a/drivers/infiniband/hw/irdma/ctrl.c b/drivers/infiniband/hw/irdma/ctrl.c index 4ef1c29032f771..cb970c9090ee0e 100644 --- a/drivers/infiniband/hw/irdma/ctrl.c +++ b/drivers/infiniband/hw/irdma/ctrl.c @@ -3950,11 +3950,13 @@ int irdma_sc_cqp_destroy(struct irdma_sc_cqp *cqp) */ void irdma_sc_ccq_arm(struct irdma_sc_cq *ccq) { + unsigned long flags; u64 temp_val; u16 sw_cq_sel; u8 arm_next_se; u8 arm_seq_num; + spin_lock_irqsave(&ccq->dev->cqp_lock, flags); get_64bit_val(ccq->cq_uk.shadow_area, 32, &temp_val); sw_cq_sel = (u16)FIELD_GET(IRDMA_CQ_DBSA_SW_CQ_SELECT, temp_val); arm_next_se = (u8)FIELD_GET(IRDMA_CQ_DBSA_ARM_NEXT_SE, temp_val); @@ -3965,6 +3967,7 @@ void irdma_sc_ccq_arm(struct irdma_sc_cq *ccq) FIELD_PREP(IRDMA_CQ_DBSA_ARM_NEXT_SE, arm_next_se) | FIELD_PREP(IRDMA_CQ_DBSA_ARM_NEXT, 1); set_64bit_val(ccq->cq_uk.shadow_area, 32, temp_val); + spin_unlock_irqrestore(&ccq->dev->cqp_lock, flags); dma_wmb(); /* make sure shadow area is updated before arming */ @@ -4731,7 +4734,8 @@ static int irdma_sc_aeq_destroy(struct irdma_sc_aeq *aeq, u64 scratch, u64 hdr; dev = aeq->dev; - if (dev->privileged) + + if (dev->hw_attrs.uk_attrs.hw_rev <= IRDMA_GEN_2) writel(0, dev->hw_regs[IRDMA_PFINT_AEQCTL]); cqp = dev->cqp; diff --git a/drivers/infiniband/hw/irdma/icrdma_if.c b/drivers/infiniband/hw/irdma/icrdma_if.c index 27b191f61caf47..b49fd9cf247654 100644 --- a/drivers/infiniband/hw/irdma/icrdma_if.c +++ b/drivers/infiniband/hw/irdma/icrdma_if.c @@ -302,7 +302,8 @@ static int icrdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary err_ctrl_init: icrdma_deinit_interrupts(rf, cdev_info); err_init_interrupts: - kfree(iwdev->rf); + mutex_destroy(&rf->ah_tbl_lock); + kfree(rf); ib_dealloc_device(&iwdev->ibdev); return err; @@ -319,6 +320,9 @@ static void icrdma_remove(struct auxiliary_device *aux_dev) ice_rdma_update_vsi_filter(cdev_info, iwdev->vsi_num, false); irdma_ib_unregister_device(iwdev); icrdma_deinit_interrupts(iwdev->rf, cdev_info); + mutex_destroy(&iwdev->rf->ah_tbl_lock); + + kfree(iwdev->rf); pr_debug("INIT: Gen[%d] func[%d] device remove success\n", rdma_ver, PCI_FUNC(cdev_info->pdev->devfn)); diff --git a/drivers/infiniband/hw/irdma/ig3rdma_if.c b/drivers/infiniband/hw/irdma/ig3rdma_if.c index 1bb42eb298ba69..e1d6670d9396eb 100644 --- a/drivers/infiniband/hw/irdma/ig3rdma_if.c +++ b/drivers/infiniband/hw/irdma/ig3rdma_if.c @@ -55,6 +55,7 @@ static int ig3rdma_vchnl_init(struct irdma_pci_f *rf, ret = irdma_sc_vchnl_init(&rf->sc_dev, &virt_info); if (ret) { destroy_workqueue(rf->vchnl_wq); + mutex_destroy(&rf->sc_dev.vchnl_mutex); return ret; } @@ -124,7 +125,9 @@ static void ig3rdma_decfg_rf(struct irdma_pci_f *rf) { struct irdma_hw *hw = &rf->hw; + mutex_destroy(&rf->ah_tbl_lock); destroy_workqueue(rf->vchnl_wq); + mutex_destroy(&rf->sc_dev.vchnl_mutex); kfree(hw->io_regs); iounmap(hw->rdma_reg.addr); } @@ -149,6 +152,7 @@ static int ig3rdma_cfg_rf(struct irdma_pci_f *rf, err = ig3rdma_cfg_regions(&rf->hw, cdev_info); if (err) { destroy_workqueue(rf->vchnl_wq); + mutex_destroy(&rf->sc_dev.vchnl_mutex); return err; } diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h index 886b30da188aed..65ce4924dbfa61 100644 --- a/drivers/infiniband/hw/irdma/main.h +++ b/drivers/infiniband/hw/irdma/main.h @@ -556,7 +556,7 @@ void irdma_copy_ip_htonl(__be32 *dst, u32 *src); u16 irdma_get_vlan_ipv4(u32 *addr); void irdma_get_vlan_mac_ipv6(u32 *addr, u16 *vlan_id, u8 *mac); struct ib_mr *irdma_reg_phys_mr(struct ib_pd *ib_pd, u64 addr, u64 size, - int acc, u64 *iova_start); + int acc, u64 *iova_start, bool dma_mr); int irdma_upload_qp_context(struct irdma_qp *iwqp, bool freeze, bool raw); void irdma_cqp_ce_handler(struct irdma_pci_f *rf, struct irdma_sc_cq *cq); int irdma_ah_cqp_op(struct irdma_pci_f *rf, struct irdma_sc_ah *sc_ah, u8 cmd, diff --git a/drivers/infiniband/hw/irdma/pble.c b/drivers/infiniband/hw/irdma/pble.c index fa6325adaedecb..28dfad7f940c24 100644 --- a/drivers/infiniband/hw/irdma/pble.c +++ b/drivers/infiniband/hw/irdma/pble.c @@ -506,12 +506,14 @@ int irdma_get_pble(struct irdma_hmc_pble_rsrc *pble_rsrc, void irdma_free_pble(struct irdma_hmc_pble_rsrc *pble_rsrc, struct irdma_pble_alloc *palloc) { - pble_rsrc->freedpbles += palloc->total_cnt; - if (palloc->level == PBLE_LEVEL_2) free_lvl2(pble_rsrc, palloc); else irdma_prm_return_pbles(&pble_rsrc->pinfo, &palloc->level1.chunkinfo); + + mutex_lock(&pble_rsrc->pble_mutex_lock); + pble_rsrc->freedpbles += palloc->total_cnt; pble_rsrc->stats_alloc_freed++; + mutex_unlock(&pble_rsrc->pble_mutex_lock); } diff --git a/drivers/infiniband/hw/irdma/puda.c b/drivers/infiniband/hw/irdma/puda.c index 694e5a9ed15d0f..9cd14a50f1a937 100644 --- a/drivers/infiniband/hw/irdma/puda.c +++ b/drivers/infiniband/hw/irdma/puda.c @@ -685,7 +685,6 @@ static int irdma_puda_qp_create(struct irdma_puda_rsrc *rsrc) ukqp->rq_size = rsrc->rq_size; IRDMA_RING_INIT(ukqp->sq_ring, ukqp->sq_size); - IRDMA_RING_INIT(ukqp->initial_ring, ukqp->sq_size); IRDMA_RING_INIT(ukqp->rq_ring, ukqp->rq_size); ukqp->wqe_alloc_db = qp->pd->dev->wqe_alloc_db; diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c index ce1ae10c30fcad..d5568584ad5e32 100644 --- a/drivers/infiniband/hw/irdma/uk.c +++ b/drivers/infiniband/hw/irdma/uk.c @@ -114,33 +114,8 @@ void irdma_clr_wqes(struct irdma_qp_uk *qp, u32 qp_wqe_idx) */ void irdma_uk_qp_post_wr(struct irdma_qp_uk *qp) { - u64 temp; - u32 hw_sq_tail; - u32 sw_sq_head; - - /* valid bit is written and loads completed before reading shadow */ - mb(); - - /* read the doorbell shadow area */ - get_64bit_val(qp->shadow_area, 0, &temp); - - hw_sq_tail = (u32)FIELD_GET(IRDMA_QP_DBSA_HW_SQ_TAIL, temp); - sw_sq_head = IRDMA_RING_CURRENT_HEAD(qp->sq_ring); - if (sw_sq_head != qp->initial_ring.head) { - if (sw_sq_head != hw_sq_tail) { - if (sw_sq_head > qp->initial_ring.head) { - if (hw_sq_tail >= qp->initial_ring.head && - hw_sq_tail < sw_sq_head) - writel(qp->qp_id, qp->wqe_alloc_db); - } else { - if (hw_sq_tail >= qp->initial_ring.head || - hw_sq_tail < sw_sq_head) - writel(qp->qp_id, qp->wqe_alloc_db); - } - } - } - - qp->initial_ring.head = qp->sq_ring.head; + dma_wmb(); + writel(qp->qp_id, qp->wqe_alloc_db); } /** @@ -1574,7 +1549,6 @@ static void irdma_setup_connection_wqes(struct irdma_qp_uk *qp, qp->conn_wqes = move_cnt; IRDMA_RING_MOVE_HEAD_BY_COUNT_NOCHECK(qp->sq_ring, move_cnt); IRDMA_RING_MOVE_TAIL_BY_COUNT(qp->sq_ring, move_cnt); - IRDMA_RING_MOVE_HEAD_BY_COUNT_NOCHECK(qp->initial_ring, move_cnt); } /** @@ -1719,7 +1693,6 @@ int irdma_uk_qp_init(struct irdma_qp_uk *qp, struct irdma_qp_uk_init_info *info) qp->max_sq_frag_cnt = info->max_sq_frag_cnt; sq_ring_size = qp->sq_size << info->sq_shift; IRDMA_RING_INIT(qp->sq_ring, sq_ring_size); - IRDMA_RING_INIT(qp->initial_ring, sq_ring_size); if (info->first_sq_wq) { irdma_setup_connection_wqes(qp, info); qp->swqe_polarity = 1; diff --git a/drivers/infiniband/hw/irdma/user.h b/drivers/infiniband/hw/irdma/user.h index ab57f689827a02..aeebf768174abd 100644 --- a/drivers/infiniband/hw/irdma/user.h +++ b/drivers/infiniband/hw/irdma/user.h @@ -456,7 +456,6 @@ struct irdma_srq_uk { struct irdma_uk_attrs *uk_attrs; __le64 *shadow_area; struct irdma_ring srq_ring; - struct irdma_ring initial_ring; u32 srq_id; u32 srq_size; u32 max_srq_frag_cnt; diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index 8b94d87b01923e..b6c4ccf38eb78c 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -251,7 +251,7 @@ int irdma_net_event(struct notifier_block *notifier, unsigned long event, void *ptr) { struct neighbour *neigh = ptr; - struct net_device *real_dev, *netdev = (struct net_device *)neigh->dev; + struct net_device *real_dev, *netdev; struct irdma_device *iwdev; struct ib_device *ibdev; __be32 *p; @@ -260,6 +260,7 @@ int irdma_net_event(struct notifier_block *notifier, unsigned long event, switch (event) { case NETEVENT_NEIGH_UPDATE: + netdev = neigh->dev; real_dev = rdma_vlan_dev_real_dev(netdev); if (!real_dev) real_dev = netdev; diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index c883c9ea5a831e..b8655504da2907 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -27,7 +27,8 @@ static int irdma_query_device(struct ib_device *ibdev, irdma_fw_minor_ver(&rf->sc_dev); props->device_cap_flags = IB_DEVICE_MEM_WINDOW | IB_DEVICE_MEM_MGT_EXTENSIONS; - props->kernel_cap_flags = IBK_LOCAL_DMA_LKEY; + if (hw_attrs->uk_attrs.hw_rev < IRDMA_GEN_3) + props->kernel_cap_flags = IBK_LOCAL_DMA_LKEY; props->vendor_id = pcidev->vendor; props->vendor_part_id = pcidev->device; @@ -2306,8 +2307,8 @@ static int irdma_setup_kmode_srq(struct irdma_device *iwdev, ukinfo->srq_size = depth >> shift; ukinfo->shadow_area = mem->va + ring_size; - info->shadow_area_pa = info->srq_pa + ring_size; info->srq_pa = mem->pa; + info->shadow_area_pa = info->srq_pa + ring_size; return 0; } @@ -3108,7 +3109,6 @@ static int irdma_hw_alloc_stag(struct irdma_device *iwdev, info->stag_idx = iwmr->stag >> IRDMA_CQPSQ_STAG_IDX_S; info->pd_id = iwpd->sc_pd.pd_id; info->total_len = iwmr->len; - info->all_memory = pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY; info->remote_access = true; cqp_info->cqp_cmd = IRDMA_OP_ALLOC_STAG; cqp_info->post_sq = 1; @@ -3119,7 +3119,7 @@ static int irdma_hw_alloc_stag(struct irdma_device *iwdev, if (status) return status; - iwmr->is_hwreg = 1; + iwmr->is_hwreg = true; return 0; } @@ -3263,7 +3263,7 @@ static int irdma_hwreg_mr(struct irdma_device *iwdev, struct irdma_mr *iwmr, if (iwdev->rf->sc_dev.hw_attrs.uk_attrs.feature_flags & IRDMA_FEATURE_ATOMIC_OPS) stag_info->remote_atomics_en = (access & IB_ACCESS_REMOTE_ATOMIC) ? 1 : 0; stag_info->pd_id = iwpd->sc_pd.pd_id; - stag_info->all_memory = pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY; + stag_info->all_memory = iwmr->dma_mr; if (stag_info->access_rights & IRDMA_ACCESS_FLAGS_ZERO_BASED) stag_info->addr_type = IRDMA_ADDR_TYPE_ZERO_BASED; else @@ -3290,7 +3290,7 @@ static int irdma_hwreg_mr(struct irdma_device *iwdev, struct irdma_mr *iwmr, irdma_put_cqp_request(&iwdev->rf->cqp, cqp_request); if (!ret) - iwmr->is_hwreg = 1; + iwmr->is_hwreg = true; return ret; } @@ -3663,7 +3663,7 @@ static int irdma_hwdereg_mr(struct ib_mr *ib_mr) if (status) return status; - iwmr->is_hwreg = 0; + iwmr->is_hwreg = false; return 0; } @@ -3786,9 +3786,10 @@ static struct ib_mr *irdma_rereg_user_mr(struct ib_mr *ib_mr, int flags, * @size: size of memory to register * @access: Access rights * @iova_start: start of virtual address for physical buffers + * @dma_mr: Flag indicating whether this region is a PD DMA MR */ struct ib_mr *irdma_reg_phys_mr(struct ib_pd *pd, u64 addr, u64 size, int access, - u64 *iova_start) + u64 *iova_start, bool dma_mr) { struct irdma_device *iwdev = to_iwdev(pd->device); struct irdma_pbl *iwpbl; @@ -3805,6 +3806,7 @@ struct ib_mr *irdma_reg_phys_mr(struct ib_pd *pd, u64 addr, u64 size, int access iwpbl = &iwmr->iwpbl; iwpbl->iwmr = iwmr; iwmr->type = IRDMA_MEMREG_TYPE_MEM; + iwmr->dma_mr = dma_mr; iwpbl->user_base = *iova_start; stag = irdma_create_stag(iwdev); if (!stag) { @@ -3843,7 +3845,7 @@ static struct ib_mr *irdma_get_dma_mr(struct ib_pd *pd, int acc) { u64 kva = 0; - return irdma_reg_phys_mr(pd, 0, 0, acc, &kva); + return irdma_reg_phys_mr(pd, 0, 0, acc, &kva, true); } /** @@ -5500,7 +5502,9 @@ void irdma_ib_dealloc_device(struct ib_device *ibdev) irdma_rt_deinit_hw(iwdev); if (!iwdev->is_vport) { irdma_ctrl_deinit_hw(iwdev->rf); - if (iwdev->rf->vchnl_wq) + if (iwdev->rf->vchnl_wq) { destroy_workqueue(iwdev->rf->vchnl_wq); + mutex_destroy(&iwdev->rf->sc_dev.vchnl_mutex); + } } } diff --git a/drivers/infiniband/hw/irdma/verbs.h b/drivers/infiniband/hw/irdma/verbs.h index ac8b3870183502..aabbb3442098bc 100644 --- a/drivers/infiniband/hw/irdma/verbs.h +++ b/drivers/infiniband/hw/irdma/verbs.h @@ -111,7 +111,8 @@ struct irdma_mr { }; struct ib_umem *region; int access; - u8 is_hwreg; + bool is_hwreg:1; + bool dma_mr:1; u16 type; u32 page_cnt; u64 page_size; diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c index 1becc877912358..7600412b0739ff 100644 --- a/drivers/infiniband/hw/mana/cq.c +++ b/drivers/infiniband/hw/mana/cq.c @@ -56,6 +56,10 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, doorbell = mana_ucontext->doorbell; } else { is_rnic_cq = true; + if (attr->cqe > U32_MAX / COMP_ENTRY_SIZE / 2 + 1) { + ibdev_dbg(ibdev, "CQE %d exceeding limit\n", attr->cqe); + return -EINVAL; + } buf_size = MANA_PAGE_ALIGN(roundup_pow_of_two(attr->cqe * COMP_ENTRY_SIZE)); cq->cqe = buf_size / COMP_ENTRY_SIZE; err = mana_ib_create_kernel_queue(mdev, buf_size, GDMA_CQ, &cq->queue); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index fc1e86f6c40971..5899bd5cb16230 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -557,12 +557,20 @@ static int mlx5_query_port_roce(struct ib_device *device, u32 port_num, * of an error it will still be zeroed out. * Use native port in case of reps */ - if (dev->is_rep) - err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, - 1, 0); - else - err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, - mdev_port_num, 0); + if (dev->is_rep) { + struct mlx5_eswitch_rep *rep; + + rep = dev->port[port_num - 1].rep; + if (rep) { + mdev = mlx5_eswitch_get_core_dev(rep->esw); + WARN_ON(!mdev); + } + mdev_port_num = 1; + } + + err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, + mdev_port_num, 0); + if (err) goto out; ext = !!MLX5_GET_ETH_PROTO(ptys_reg, out, true, eth_proto_capability); @@ -2874,7 +2882,6 @@ static void mlx5_ib_handle_event(struct work_struct *_work) container_of(_work, struct mlx5_ib_event_work, work); struct mlx5_ib_dev *ibdev; struct ib_event ibev; - bool fatal = false; if (work->is_slave) { ibdev = mlx5_ib_get_ibdev_from_mpi(work->mpi); @@ -2885,12 +2892,6 @@ static void mlx5_ib_handle_event(struct work_struct *_work) } switch (work->event) { - case MLX5_DEV_EVENT_SYS_ERROR: - ibev.event = IB_EVENT_DEVICE_FATAL; - mlx5_ib_handle_internal_error(ibdev); - ibev.element.port_num = (u8)(unsigned long)work->param; - fatal = true; - break; case MLX5_EVENT_TYPE_PORT_CHANGE: if (handle_port_change(ibdev, work->param, &ibev)) goto out; @@ -2912,8 +2913,6 @@ static void mlx5_ib_handle_event(struct work_struct *_work) if (ibdev->ib_active) ib_dispatch_event(&ibev); - if (fatal) - ibdev->ib_active = false; out: kfree(work); } @@ -2957,6 +2956,66 @@ static int mlx5_ib_event_slave_port(struct notifier_block *nb, return NOTIFY_OK; } +static void mlx5_ib_handle_sys_error_event(struct work_struct *_work) +{ + struct mlx5_ib_event_work *work = + container_of(_work, struct mlx5_ib_event_work, work); + struct mlx5_ib_dev *ibdev = work->dev; + struct ib_event ibev; + + ibev.event = IB_EVENT_DEVICE_FATAL; + mlx5_ib_handle_internal_error(ibdev); + ibev.element.port_num = (u8)(unsigned long)work->param; + ibev.device = &ibdev->ib_dev; + + if (!rdma_is_port_valid(&ibdev->ib_dev, ibev.element.port_num)) { + mlx5_ib_warn(ibdev, "warning: event on port %d\n", ibev.element.port_num); + goto out; + } + + if (ibdev->ib_active) + ib_dispatch_event(&ibev); + + ibdev->ib_active = false; +out: + kfree(work); +} + +static int mlx5_ib_sys_error_event(struct notifier_block *nb, + unsigned long event, void *param) +{ + struct mlx5_ib_event_work *work; + + if (event != MLX5_DEV_EVENT_SYS_ERROR) + return NOTIFY_DONE; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return NOTIFY_DONE; + + INIT_WORK(&work->work, mlx5_ib_handle_sys_error_event); + work->dev = container_of(nb, struct mlx5_ib_dev, sys_error_events); + work->is_slave = false; + work->param = param; + work->event = event; + + queue_work(mlx5_ib_event_wq, &work->work); + + return NOTIFY_OK; +} + +static int mlx5_ib_stage_sys_error_notifier_init(struct mlx5_ib_dev *dev) +{ + dev->sys_error_events.notifier_call = mlx5_ib_sys_error_event; + mlx5_notifier_register(dev->mdev, &dev->sys_error_events); + return 0; +} + +static void mlx5_ib_stage_sys_error_notifier_cleanup(struct mlx5_ib_dev *dev) +{ + mlx5_notifier_unregister(dev->mdev, &dev->sys_error_events); +} + static int mlx5_ib_get_plane_num(struct mlx5_core_dev *mdev, u8 *num_plane) { struct mlx5_hca_vport_context vport_ctx; @@ -4462,12 +4521,16 @@ static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev) MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_RDMA_CTRL) { err = mlx5_ib_init_ucaps(dev); if (err) - return err; + goto err_ucaps; } dev->ib_dev.use_cq_dim = true; return 0; + +err_ucaps: + bitmap_free(dev->var_table.bitmap); + return err; } static const struct ib_device_ops mlx5_ib_dev_port_ops = { @@ -4803,6 +4866,9 @@ static const struct mlx5_ib_profile pf_profile = { STAGE_CREATE(MLX5_IB_STAGE_WHITELIST_UID, mlx5_ib_devx_init, mlx5_ib_devx_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_SYS_ERROR_NOTIFIER, + mlx5_ib_stage_sys_error_notifier_init, + mlx5_ib_stage_sys_error_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_IB_REG, mlx5_ib_stage_ib_reg_init, mlx5_ib_stage_ib_reg_cleanup), @@ -4860,6 +4926,9 @@ const struct mlx5_ib_profile raw_eth_profile = { STAGE_CREATE(MLX5_IB_STAGE_WHITELIST_UID, mlx5_ib_devx_init, mlx5_ib_devx_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_SYS_ERROR_NOTIFIER, + mlx5_ib_stage_sys_error_notifier_init, + mlx5_ib_stage_sys_error_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_IB_REG, mlx5_ib_stage_ib_reg_init, mlx5_ib_stage_ib_reg_cleanup), diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 09d82d5f95e354..fbccb0362590bb 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -1007,6 +1007,7 @@ enum mlx5_ib_stages { MLX5_IB_STAGE_BFREG, MLX5_IB_STAGE_PRE_IB_REG_UMR, MLX5_IB_STAGE_WHITELIST_UID, + MLX5_IB_STAGE_SYS_ERROR_NOTIFIER, MLX5_IB_STAGE_IB_REG, MLX5_IB_STAGE_DEVICE_NOTIFIER, MLX5_IB_STAGE_POST_IB_REG_UMR, @@ -1165,6 +1166,7 @@ struct mlx5_ib_dev { /* protect accessing data_direct_dev */ struct mutex data_direct_lock; struct notifier_block mdev_events; + struct notifier_block sys_error_events; struct notifier_block lag_events; int num_ports; /* serialize update of capability mask diff --git a/drivers/infiniband/hw/mlx5/std_types.c b/drivers/infiniband/hw/mlx5/std_types.c index 2fcf553044e15e..1ee31611b4b3f1 100644 --- a/drivers/infiniband/hw/mlx5/std_types.c +++ b/drivers/infiniband/hw/mlx5/std_types.c @@ -195,7 +195,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_GET_DATA_DIRECT_SYSFS_PATH)( int out_len = uverbs_attr_get_len(attrs, MLX5_IB_ATTR_GET_DATA_DIRECT_SYSFS_PATH); u32 dev_path_len; - char *dev_path; + char *dev_path = NULL; int ret; c = to_mucontext(ib_uverbs_get_ucontext(attrs)); @@ -223,9 +223,9 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_GET_DATA_DIRECT_SYSFS_PATH)( ret = uverbs_copy_to(attrs, MLX5_IB_ATTR_GET_DATA_DIRECT_SYSFS_PATH, dev_path, dev_path_len); - kfree(dev_path); end: + kfree(dev_path); mutex_unlock(&dev->data_direct_lock); return ret; } diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index a5b2b62f596b05..1390e861bd1d74 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -119,12 +119,15 @@ void retransmit_timer(struct timer_list *t) rxe_dbg_qp(qp, "retransmit timer fired\n"); + if (!rxe_get(qp)) + return; spin_lock_irqsave(&qp->state_lock, flags); if (qp->valid) { qp->comp.timeout = 1; rxe_sched_task(&qp->send_task); } spin_unlock_irqrestore(&qp->state_lock, flags); + rxe_put(qp); } void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb) diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c index bcb97b3ea58ac7..2c486bb616a7c5 100644 --- a/drivers/infiniband/sw/rxe/rxe_mr.c +++ b/drivers/infiniband/sw/rxe/rxe_mr.c @@ -72,14 +72,46 @@ void rxe_mr_init_dma(int access, struct rxe_mr *mr) mr->ibmr.type = IB_MR_TYPE_DMA; } +/* + * Convert iova to page_info index. The page_info stores pages of size + * PAGE_SIZE, but MRs can have different page sizes. This function + * handles the conversion for all cases: + * + * 1. mr->page_size > PAGE_SIZE: + * The MR's iova may not be aligned to mr->page_size. We use the + * aligned base (iova & page_mask) as reference, then calculate + * which PAGE_SIZE sub-page the iova falls into. + * + * 2. mr->page_size <= PAGE_SIZE: + * Use simple shift arithmetic since each page_info entry corresponds + * to one or more MR pages. + */ static unsigned long rxe_mr_iova_to_index(struct rxe_mr *mr, u64 iova) { - return (iova >> mr->page_shift) - (mr->ibmr.iova >> mr->page_shift); + int idx; + + if (mr_page_size(mr) > PAGE_SIZE) + idx = (iova - (mr->ibmr.iova & mr->page_mask)) >> PAGE_SHIFT; + else + idx = (iova >> mr->page_shift) - + (mr->ibmr.iova >> mr->page_shift); + + WARN_ON(idx >= mr->nbuf); + return idx; } +/* + * Convert iova to offset within the page_info entry. + * + * For mr_page_size > PAGE_SIZE, the offset is within the system page. + * For mr_page_size <= PAGE_SIZE, the offset is within the MR page size. + */ static unsigned long rxe_mr_iova_to_page_offset(struct rxe_mr *mr, u64 iova) { - return iova & (mr_page_size(mr) - 1); + if (mr_page_size(mr) > PAGE_SIZE) + return iova & (PAGE_SIZE - 1); + else + return iova & (mr_page_size(mr) - 1); } static bool is_pmem_page(struct page *pg) @@ -93,37 +125,69 @@ static bool is_pmem_page(struct page *pg) static int rxe_mr_fill_pages_from_sgt(struct rxe_mr *mr, struct sg_table *sgt) { - XA_STATE(xas, &mr->page_list, 0); struct sg_page_iter sg_iter; struct page *page; bool persistent = !!(mr->access & IB_ACCESS_FLUSH_PERSISTENT); + WARN_ON(mr_page_size(mr) != PAGE_SIZE); + __sg_page_iter_start(&sg_iter, sgt->sgl, sgt->orig_nents, 0); if (!__sg_page_iter_next(&sg_iter)) return 0; - do { - xas_lock(&xas); - while (true) { - page = sg_page_iter_page(&sg_iter); - - if (persistent && !is_pmem_page(page)) { - rxe_dbg_mr(mr, "Page can't be persistent\n"); - xas_set_err(&xas, -EINVAL); - break; - } + while (true) { + page = sg_page_iter_page(&sg_iter); - xas_store(&xas, page); - if (xas_error(&xas)) - break; - xas_next(&xas); - if (!__sg_page_iter_next(&sg_iter)) - break; + if (persistent && !is_pmem_page(page)) { + rxe_dbg_mr(mr, "Page can't be persistent\n"); + return -EINVAL; } - xas_unlock(&xas); - } while (xas_nomem(&xas, GFP_KERNEL)); - return xas_error(&xas); + mr->page_info[mr->nbuf].page = page; + mr->page_info[mr->nbuf].offset = 0; + mr->nbuf++; + + if (!__sg_page_iter_next(&sg_iter)) + break; + } + + return 0; +} + +static int __alloc_mr_page_info(struct rxe_mr *mr, int num_pages) +{ + mr->page_info = kcalloc(num_pages, sizeof(struct rxe_mr_page), + GFP_KERNEL); + if (!mr->page_info) + return -ENOMEM; + + mr->max_allowed_buf = num_pages; + mr->nbuf = 0; + + return 0; +} + +static int alloc_mr_page_info(struct rxe_mr *mr, int num_pages) +{ + int ret; + + WARN_ON(mr->num_buf); + ret = __alloc_mr_page_info(mr, num_pages); + if (ret) + return ret; + + mr->num_buf = num_pages; + + return 0; +} + +static void free_mr_page_info(struct rxe_mr *mr) +{ + if (!mr->page_info) + return; + + kfree(mr->page_info); + mr->page_info = NULL; } int rxe_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, @@ -134,8 +198,6 @@ int rxe_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, rxe_mr_init(access, mr); - xa_init(&mr->page_list); - umem = ib_umem_get(&rxe->ib_dev, start, length, access); if (IS_ERR(umem)) { rxe_dbg_mr(mr, "Unable to pin memory region err = %d\n", @@ -143,46 +205,24 @@ int rxe_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, return PTR_ERR(umem); } + err = alloc_mr_page_info(mr, ib_umem_num_pages(umem)); + if (err) + goto err2; + err = rxe_mr_fill_pages_from_sgt(mr, &umem->sgt_append.sgt); - if (err) { - ib_umem_release(umem); - return err; - } + if (err) + goto err1; mr->umem = umem; mr->ibmr.type = IB_MR_TYPE_USER; mr->state = RXE_MR_STATE_VALID; return 0; -} - -static int rxe_mr_alloc(struct rxe_mr *mr, int num_buf) -{ - XA_STATE(xas, &mr->page_list, 0); - int i = 0; - int err; - - xa_init(&mr->page_list); - - do { - xas_lock(&xas); - while (i != num_buf) { - xas_store(&xas, XA_ZERO_ENTRY); - if (xas_error(&xas)) - break; - xas_next(&xas); - i++; - } - xas_unlock(&xas); - } while (xas_nomem(&xas, GFP_KERNEL)); - - err = xas_error(&xas); - if (err) - return err; - - mr->num_buf = num_buf; - - return 0; +err1: + free_mr_page_info(mr); +err2: + ib_umem_release(umem); + return err; } int rxe_mr_init_fast(int max_pages, struct rxe_mr *mr) @@ -192,7 +232,7 @@ int rxe_mr_init_fast(int max_pages, struct rxe_mr *mr) /* always allow remote access for FMRs */ rxe_mr_init(RXE_ACCESS_REMOTE, mr); - err = rxe_mr_alloc(mr, max_pages); + err = alloc_mr_page_info(mr, max_pages); if (err) goto err1; @@ -205,26 +245,43 @@ int rxe_mr_init_fast(int max_pages, struct rxe_mr *mr) return err; } +/* + * I) MRs with page_size >= PAGE_SIZE, + * Split a large MR page (mr->page_size) into multiple PAGE_SIZE + * sub-pages and store them in page_info, offset is always 0. + * + * Called when mr->page_size > PAGE_SIZE. Each call to rxe_set_page() + * represents one mr->page_size region, which we must split into + * (mr->page_size >> PAGE_SHIFT) individual pages. + * + * II) MRs with page_size < PAGE_SIZE, + * Save each PAGE_SIZE page and its offset within the system page in page_info. + */ static int rxe_set_page(struct ib_mr *ibmr, u64 dma_addr) { struct rxe_mr *mr = to_rmr(ibmr); - struct page *page = ib_virt_dma_to_page(dma_addr); bool persistent = !!(mr->access & IB_ACCESS_FLUSH_PERSISTENT); - int err; + u32 i, pages_per_mr = mr_page_size(mr) >> PAGE_SHIFT; - if (persistent && !is_pmem_page(page)) { - rxe_dbg_mr(mr, "Page cannot be persistent\n"); - return -EINVAL; - } + pages_per_mr = MAX(1, pages_per_mr); - if (unlikely(mr->nbuf == mr->num_buf)) - return -ENOMEM; + for (i = 0; i < pages_per_mr; i++) { + u64 addr = dma_addr + i * PAGE_SIZE; + struct page *sub_page = ib_virt_dma_to_page(addr); - err = xa_err(xa_store(&mr->page_list, mr->nbuf, page, GFP_KERNEL)); - if (err) - return err; + if (unlikely(mr->nbuf >= mr->max_allowed_buf)) + return -ENOMEM; + + if (persistent && !is_pmem_page(sub_page)) { + rxe_dbg_mr(mr, "Page cannot be persistent\n"); + return -EINVAL; + } + + mr->page_info[mr->nbuf].page = sub_page; + mr->page_info[mr->nbuf].offset = addr & (PAGE_SIZE - 1); + mr->nbuf++; + } - mr->nbuf++; return 0; } @@ -234,6 +291,31 @@ int rxe_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sgl, struct rxe_mr *mr = to_rmr(ibmr); unsigned int page_size = mr_page_size(mr); + /* + * Ensure page_size and PAGE_SIZE are compatible for mapping. + * We require one to be a multiple of the other for correct + * iova-to-page conversion. + */ + if (!IS_ALIGNED(page_size, PAGE_SIZE) && + !IS_ALIGNED(PAGE_SIZE, page_size)) { + rxe_dbg_mr(mr, "MR page size %u must be compatible with PAGE_SIZE %lu\n", + page_size, PAGE_SIZE); + return -EINVAL; + } + + if (mr_page_size(mr) > PAGE_SIZE) { + /* resize page_info if needed */ + u32 map_mr_pages = (page_size >> PAGE_SHIFT) * mr->num_buf; + + if (map_mr_pages > mr->max_allowed_buf) { + rxe_dbg_mr(mr, "requested pages %u exceed max %u\n", + map_mr_pages, mr->max_allowed_buf); + free_mr_page_info(mr); + if (__alloc_mr_page_info(mr, map_mr_pages)) + return -ENOMEM; + } + } + mr->nbuf = 0; mr->page_shift = ilog2(page_size); mr->page_mask = ~((u64)page_size - 1); @@ -245,30 +327,30 @@ int rxe_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sgl, static int rxe_mr_copy_xarray(struct rxe_mr *mr, u64 iova, void *addr, unsigned int length, enum rxe_mr_copy_dir dir) { - unsigned int page_offset = rxe_mr_iova_to_page_offset(mr, iova); - unsigned long index = rxe_mr_iova_to_index(mr, iova); unsigned int bytes; - struct page *page; - void *va; + u8 *va; while (length) { - page = xa_load(&mr->page_list, index); - if (!page) + unsigned long index = rxe_mr_iova_to_index(mr, iova); + struct rxe_mr_page *info = &mr->page_info[index]; + unsigned int page_offset = rxe_mr_iova_to_page_offset(mr, iova); + + if (!info->page) return -EFAULT; - bytes = min_t(unsigned int, length, - mr_page_size(mr) - page_offset); - va = kmap_local_page(page); + page_offset += info->offset; + bytes = min_t(unsigned int, length, PAGE_SIZE - page_offset); + va = kmap_local_page(info->page); + if (dir == RXE_FROM_MR_OBJ) memcpy(addr, va + page_offset, bytes); else memcpy(va + page_offset, addr, bytes); kunmap_local(va); - page_offset = 0; addr += bytes; + iova += bytes; length -= bytes; - index++; } return 0; @@ -426,9 +508,6 @@ int copy_data( static int rxe_mr_flush_pmem_iova(struct rxe_mr *mr, u64 iova, unsigned int length) { - unsigned int page_offset; - unsigned long index; - struct page *page; unsigned int bytes; int err; u8 *va; @@ -438,15 +517,17 @@ static int rxe_mr_flush_pmem_iova(struct rxe_mr *mr, u64 iova, unsigned int leng return err; while (length > 0) { - index = rxe_mr_iova_to_index(mr, iova); - page = xa_load(&mr->page_list, index); - page_offset = rxe_mr_iova_to_page_offset(mr, iova); - if (!page) + unsigned long index = rxe_mr_iova_to_index(mr, iova); + struct rxe_mr_page *info = &mr->page_info[index]; + unsigned int page_offset = rxe_mr_iova_to_page_offset(mr, iova); + + if (!info->page) return -EFAULT; - bytes = min_t(unsigned int, length, - mr_page_size(mr) - page_offset); - va = kmap_local_page(page); + page_offset += info->offset; + bytes = min_t(unsigned int, length, PAGE_SIZE - page_offset); + + va = kmap_local_page(info->page); arch_wb_cache_pmem(va + page_offset, bytes); kunmap_local(va); @@ -502,6 +583,7 @@ enum resp_states rxe_mr_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode, } else { unsigned long index; int err; + struct rxe_mr_page *info; err = mr_check_range(mr, iova, sizeof(value)); if (err) { @@ -510,9 +592,12 @@ enum resp_states rxe_mr_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode, } page_offset = rxe_mr_iova_to_page_offset(mr, iova); index = rxe_mr_iova_to_index(mr, iova); - page = xa_load(&mr->page_list, index); - if (!page) + info = &mr->page_info[index]; + if (!info->page) return RESPST_ERR_RKEY_VIOLATION; + + page_offset += info->offset; + page = info->page; } if (unlikely(page_offset & 0x7)) { @@ -551,6 +636,7 @@ enum resp_states rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value) } else { unsigned long index; int err; + struct rxe_mr_page *info; /* See IBA oA19-28 */ err = mr_check_range(mr, iova, sizeof(value)); @@ -560,9 +646,12 @@ enum resp_states rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value) } page_offset = rxe_mr_iova_to_page_offset(mr, iova); index = rxe_mr_iova_to_index(mr, iova); - page = xa_load(&mr->page_list, index); - if (!page) + info = &mr->page_info[index]; + if (!info->page) return RESPST_ERR_RKEY_VIOLATION; + + page_offset += info->offset; + page = info->page; } /* See IBA A19.4.2 */ @@ -726,5 +815,5 @@ void rxe_mr_cleanup(struct rxe_pool_elem *elem) ib_umem_release(mr->umem); if (mr->ibmr.type != IB_MR_TYPE_DMA) - xa_destroy(&mr->page_list); + free_mr_page_info(mr); } diff --git a/drivers/infiniband/sw/rxe/rxe_odp.c b/drivers/infiniband/sw/rxe/rxe_odp.c index f58e3ec6252f52..4d4e3b324dd294 100644 --- a/drivers/infiniband/sw/rxe/rxe_odp.c +++ b/drivers/infiniband/sw/rxe/rxe_odp.c @@ -179,8 +179,10 @@ static int rxe_odp_map_range_and_lock(struct rxe_mr *mr, u64 iova, int length, u return err; need_fault = rxe_check_pagefault(umem_odp, iova, length); - if (need_fault) + if (need_fault) { + mutex_unlock(&umem_odp->umem_mutex); return -EFAULT; + } } return 0; diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 373b03f223bebc..12d03f390b0978 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -102,6 +102,8 @@ void rnr_nak_timer(struct timer_list *t) rxe_dbg_qp(qp, "nak timer fired\n"); + if (!rxe_get(qp)) + return; spin_lock_irqsave(&qp->state_lock, flags); if (qp->valid) { /* request a send queue retry */ @@ -110,6 +112,7 @@ void rnr_nak_timer(struct timer_list *t) rxe_sched_task(&qp->send_task); } spin_unlock_irqrestore(&qp->state_lock, flags); + rxe_put(qp); } static void req_check_sq_drain_done(struct rxe_qp *qp) diff --git a/drivers/infiniband/sw/rxe/rxe_srq.c b/drivers/infiniband/sw/rxe/rxe_srq.c index 3661cb627d28a9..c9a7cd38953d31 100644 --- a/drivers/infiniband/sw/rxe/rxe_srq.c +++ b/drivers/infiniband/sw/rxe/rxe_srq.c @@ -77,9 +77,6 @@ int rxe_srq_from_init(struct rxe_dev *rxe, struct rxe_srq *srq, goto err_free; } - srq->rq.queue = q; - init->attr.max_wr = srq->rq.max_wr; - if (uresp) { if (copy_to_user(&uresp->srq_num, &srq->srq_num, sizeof(uresp->srq_num))) { @@ -88,6 +85,9 @@ int rxe_srq_from_init(struct rxe_dev *rxe, struct rxe_srq *srq, } } + srq->rq.queue = q; + init->attr.max_wr = srq->rq.max_wr; + return 0; err_free: @@ -171,7 +171,7 @@ int rxe_srq_from_attr(struct rxe_dev *rxe, struct rxe_srq *srq, udata, mi, &srq->rq.producer_lock, &srq->rq.consumer_lock); if (err) - goto err_free; + return err; srq->rq.max_wr = attr->max_wr; } @@ -180,11 +180,6 @@ int rxe_srq_from_attr(struct rxe_dev *rxe, struct rxe_srq *srq, srq->limit = attr->srq_limit; return 0; - -err_free: - rxe_queue_cleanup(q); - srq->rq.queue = NULL; - return err; } void rxe_srq_cleanup(struct rxe_pool_elem *elem) diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index fd48075810dd10..1b8ed1031bd57f 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -335,6 +335,11 @@ static inline int rkey_is_mw(u32 rkey) return (index >= RXE_MIN_MW_INDEX) && (index <= RXE_MAX_MW_INDEX); } +struct rxe_mr_page { + struct page *page; + unsigned int offset; /* offset in system page */ +}; + struct rxe_mr { struct rxe_pool_elem elem; struct ib_mr ibmr; @@ -351,10 +356,13 @@ struct rxe_mr { unsigned int page_shift; u64 page_mask; + /* size of page_info when mr allocated */ u32 num_buf; + /* real size of page_info */ + u32 max_allowed_buf; u32 nbuf; - struct xarray page_list; + struct rxe_mr_page *page_info; }; static inline unsigned int mr_page_size(struct rxe_mr *mr) diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c index a10820e3388782..e8a88b378d51d4 100644 --- a/drivers/infiniband/sw/siw/siw_qp_rx.c +++ b/drivers/infiniband/sw/siw/siw_qp_rx.c @@ -1435,7 +1435,8 @@ int siw_tcp_rx_data(read_descriptor_t *rd_desc, struct sk_buff *skb, } if (unlikely(rv != 0 && rv != -EAGAIN)) { if ((srx->state > SIW_GET_HDR || - qp->rx_fpdu->more_ddp_segs) && run_completion) + (qp->rx_fpdu && qp->rx_fpdu->more_ddp_segs)) && + run_completion) siw_rdmap_complete(qp, rv); siw_dbg_qp(qp, "rx error %d, rx state %d\n", rv, diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index 71387811b28158..2b397a544cb936 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -1464,6 +1464,7 @@ static void query_fast_reg_mode(struct rtrs_clt_path *clt_path) mr_page_shift = max(12, ffs(ib_dev->attrs.page_size_cap) - 1); max_pages_per_mr = ib_dev->attrs.max_mr_size; do_div(max_pages_per_mr, (1ull << mr_page_shift)); + max_pages_per_mr = min_not_zero((u32)max_pages_per_mr, U32_MAX); clt_path->max_pages_per_mr = min3(clt_path->max_pages_per_mr, (u32)max_pages_per_mr, ib_dev->attrs.max_fast_reg_page_list_len); diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c index ef4abdea3c2d2e..adb798e2a54ae1 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c @@ -208,7 +208,6 @@ static int rdma_write_sg(struct rtrs_srv_op *id) size_t sg_cnt; int err, offset; bool need_inval; - u32 rkey = 0; struct ib_reg_wr rwr; struct ib_sge *plist; struct ib_sge list; @@ -240,11 +239,6 @@ static int rdma_write_sg(struct rtrs_srv_op *id) wr->wr.num_sge = 1; wr->remote_addr = le64_to_cpu(id->rd_msg->desc[0].addr); wr->rkey = le32_to_cpu(id->rd_msg->desc[0].key); - if (rkey == 0) - rkey = wr->rkey; - else - /* Only one key is actually used */ - WARN_ON_ONCE(rkey != wr->rkey); wr->wr.opcode = IB_WR_RDMA_WRITE; wr->wr.wr_cqe = &io_comp_cqe; @@ -277,7 +271,7 @@ static int rdma_write_sg(struct rtrs_srv_op *id) inv_wr.opcode = IB_WR_SEND_WITH_INV; inv_wr.wr_cqe = &io_comp_cqe; inv_wr.send_flags = 0; - inv_wr.ex.invalidate_rkey = rkey; + inv_wr.ex.invalidate_rkey = wr->rkey; } imm_wr.wr.next = NULL; @@ -601,7 +595,7 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path) srv_path->mrs_num++) { struct rtrs_srv_mr *srv_mr = &srv_path->mrs[srv_path->mrs_num]; struct scatterlist *s; - int nr, nr_sgt, chunks; + int nr, nr_sgt, chunks, ind; sgt = &srv_mr->sgt; chunks = chunks_per_mr * srv_path->mrs_num; @@ -631,7 +625,7 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path) } nr = ib_map_mr_sg(mr, sgt->sgl, nr_sgt, NULL, max_chunk_size); - if (nr != nr_sgt) { + if (nr < nr_sgt) { err = nr < 0 ? nr : -EINVAL; goto dereg_mr; } @@ -647,9 +641,24 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path) goto dereg_mr; } } - /* Eventually dma addr for each chunk can be cached */ - for_each_sg(sgt->sgl, s, nr_sgt, i) - srv_path->dma_addr[chunks + i] = sg_dma_address(s); + + /* + * Cache DMA addresses by traversing sg entries. If + * regions were merged, an inner loop is required to + * populate the DMA address array by traversing larger + * regions. + */ + ind = chunks; + for_each_sg(sgt->sgl, s, nr_sgt, i) { + unsigned int dma_len = sg_dma_len(s); + u64 dma_addr = sg_dma_address(s); + u64 dma_addr_end = dma_addr + dma_len; + + do { + srv_path->dma_addr[ind++] = dma_addr; + dma_addr += max_chunk_size; + } while (dma_addr < dma_addr_end); + } ib_update_fast_reg_key(mr, ib_inc_rkey(mr->rkey)); srv_mr->mr = mr; @@ -1450,7 +1459,7 @@ static struct rtrs_srv_sess *get_or_create_srv(struct rtrs_srv_ctx *ctx, kfree(srv->chunks); err_free_srv: - kfree(srv); + put_device(&srv->dev); return ERR_PTR(-ENOMEM); } diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index d72e89c25e5031..363d509493866a 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -133,6 +133,8 @@ static const struct xpad_device { } xpad_device[] = { /* Please keep this list sorted by vendor and product ID. */ { 0x0079, 0x18d4, "GPD Win 2 X-Box Controller", 0, XTYPE_XBOX360 }, + { 0x0351, 0x1000, "CRKD LP Blueberry Burst Pro Edition (Xbox)", 0, XTYPE_XBOX360 }, + { 0x0351, 0x2000, "CRKD LP Black Tribal Edition (Xbox) ", 0, XTYPE_XBOX360 }, { 0x03eb, 0xff01, "Wooting One (Legacy)", 0, XTYPE_XBOX360 }, { 0x03eb, 0xff02, "Wooting Two (Legacy)", 0, XTYPE_XBOX360 }, { 0x03f0, 0x038D, "HyperX Clutch", 0, XTYPE_XBOX360 }, /* wired */ @@ -420,6 +422,7 @@ static const struct xpad_device { { 0x3285, 0x0663, "Nacon Evol-X", 0, XTYPE_XBOXONE }, { 0x3537, 0x1004, "GameSir T4 Kaleid", 0, XTYPE_XBOX360 }, { 0x3537, 0x1010, "GameSir G7 SE", 0, XTYPE_XBOXONE }, + { 0x3651, 0x1000, "CRKD SG", 0, XTYPE_XBOX360 }, { 0x366c, 0x0005, "ByoWave Proteus Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE, FLAG_DELAY_INIT }, { 0x3767, 0x0101, "Fanatec Speedster 3 Forceshock Wheel", 0, XTYPE_XBOX }, { 0x37d7, 0x2501, "Flydigi Apex 5", 0, XTYPE_XBOX360 }, @@ -518,6 +521,7 @@ static const struct usb_device_id xpad_table[] = { */ { USB_INTERFACE_INFO('X', 'B', 0) }, /* Xbox USB-IF not-approved class */ XPAD_XBOX360_VENDOR(0x0079), /* GPD Win 2 controller */ + XPAD_XBOX360_VENDOR(0x0351), /* CRKD Controllers */ XPAD_XBOX360_VENDOR(0x03eb), /* Wooting Keyboards (Legacy) */ XPAD_XBOX360_VENDOR(0x03f0), /* HP HyperX Xbox 360 controllers */ XPAD_XBOXONE_VENDOR(0x03f0), /* HP HyperX Xbox One controllers */ @@ -578,6 +582,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOXONE_VENDOR(0x3285), /* Nacon Evol-X */ XPAD_XBOX360_VENDOR(0x3537), /* GameSir Controllers */ XPAD_XBOXONE_VENDOR(0x3537), /* GameSir Controllers */ + XPAD_XBOX360_VENDOR(0x3651), /* CRKD Controllers */ XPAD_XBOXONE_VENDOR(0x366c), /* ByoWave controllers */ XPAD_XBOX360_VENDOR(0x37d7), /* Flydigi Controllers */ XPAD_XBOX360_VENDOR(0x413d), /* Black Shark Green Ghost Controller */ diff --git a/drivers/input/keyboard/lkkbd.c b/drivers/input/keyboard/lkkbd.c index c035216dd27c12..2f130f819363c6 100644 --- a/drivers/input/keyboard/lkkbd.c +++ b/drivers/input/keyboard/lkkbd.c @@ -670,7 +670,8 @@ static int lkkbd_connect(struct serio *serio, struct serio_driver *drv) return 0; - fail3: serio_close(serio); + fail3: disable_work_sync(&lk->tq); + serio_close(serio); fail2: serio_set_drvdata(serio, NULL); fail1: input_free_device(input_dev); kfree(lk); @@ -684,6 +685,8 @@ static void lkkbd_disconnect(struct serio *serio) { struct lkkbd *lk = serio_get_drvdata(serio); + disable_work_sync(&lk->tq); + input_get_device(lk->dev); input_unregister_device(lk->dev); serio_close(serio); diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig index cc2558630797e6..aa3d86afbad077 100644 --- a/drivers/input/misc/Kconfig +++ b/drivers/input/misc/Kconfig @@ -992,4 +992,15 @@ config INPUT_STPMIC1_ONKEY To compile this driver as a module, choose M here: the module will be called stpmic1_onkey. +config INPUT_MACSMC_INPUT + tristate "Apple Mac SMC lid/buttons" + depends on MFD_MACSMC + help + Say Y here if you want to use the input events delivered via the + SMC controller on Apple Mac machines using the macsmc driver. + This includes lid open/close and the power button. + + To compile this driver as a module, choose M here: the + module will be called macsmc-input. + endif diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile index f5ebfa9d998314..9667a53372ce26 100644 --- a/drivers/input/misc/Makefile +++ b/drivers/input/misc/Makefile @@ -52,6 +52,7 @@ obj-$(CONFIG_INPUT_IQS7222) += iqs7222.o obj-$(CONFIG_INPUT_KEYSPAN_REMOTE) += keyspan_remote.o obj-$(CONFIG_INPUT_KXTJ9) += kxtj9.o obj-$(CONFIG_INPUT_M68K_BEEP) += m68kspkr.o +obj-$(CONFIG_INPUT_MACSMC_INPUT) += macsmc-input.o obj-$(CONFIG_INPUT_MAX7360_ROTARY) += max7360-rotary.o obj-$(CONFIG_INPUT_MAX77650_ONKEY) += max77650-onkey.o obj-$(CONFIG_INPUT_MAX77693_HAPTIC) += max77693-haptic.o diff --git a/drivers/input/misc/macsmc-input.c b/drivers/input/misc/macsmc-input.c new file mode 100644 index 00000000000000..2cead3b7f45fed --- /dev/null +++ b/drivers/input/misc/macsmc-input.c @@ -0,0 +1,210 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Apple SMC input event driver + * Copyright The Asahi Linux Contributors + * + * This driver exposes HID events from the SMC as an input device. + * This includes the lid open/close and power button notifications. + */ + +#include +#include +#include +#include +#include +#include + +/** + * struct macsmc_input + * @dev: Underlying struct device for the input sub-device + * @smc: Pointer to apple_smc struct of the mfd parent + * @input: Allocated input_dev; devres managed + * @nb: Notifier block used for incoming events from SMC (e.g. button pressed down) + * @wakeup_mode: Set to true when system is suspended and power button events should wake it + */ +struct macsmc_input { + struct device *dev; + struct apple_smc *smc; + struct input_dev *input; + struct notifier_block nb; + bool wakeup_mode; +}; + +#define SMC_EV_BTN 0x7201 +#define SMC_EV_LID 0x7203 + +#define BTN_POWER 0x01 /* power button on e.g. Mac Mini chasis pressed */ +#define BTN_TOUCHID 0x06 /* combined TouchID / power button on MacBooks pressed */ +#define BTN_POWER_HELD_SHORT 0xfe /* power button briefly held down */ +#define BTN_POWER_HELD_LONG 0x00 /* power button held down; sent just before forced poweroff */ + +static void macsmc_input_event_button(struct macsmc_input *smcin, unsigned long event) +{ + u8 button = (event >> 8) & 0xff; + u8 state = !!(event & 0xff); + + switch (button) { + case BTN_POWER: + case BTN_TOUCHID: + pm_wakeup_dev_event(smcin->dev, 0, (smcin->wakeup_mode && state)); + /* + * Suppress KEY_POWER reports when suspended to avoid powering down + * immediately after waking from s2idle. + * */ + if (smcin->wakeup_mode) + return; + + input_report_key(smcin->input, KEY_POWER, state); + input_sync(smcin->input); + break; + case BTN_POWER_HELD_SHORT: /* power button held down; ignore */ + break; + case BTN_POWER_HELD_LONG: + /* + * If we get here the power button has been held down for a while and + * we have about 4 seconds before forced power-off is triggered by SMC. + * Try to do an emergency shutdown to make sure the NVMe cache is + * flushed. macOS actually does this by panicing (!)... + */ + if (state) { + dev_crit(smcin->dev, "Triggering forced shutdown!\n"); + if (kernel_can_power_off()) + kernel_power_off(); + else /* Missing macsmc-reboot driver? */ + kernel_restart("SMC power button triggered restart"); + } + break; + default: + dev_warn(smcin->dev, "Unknown SMC button event: %04lx\n", event & 0xffff); + } +} + +static void macsmc_input_event_lid(struct macsmc_input *smcin, unsigned long event) +{ + u8 lid_state = !!((event >> 8) & 0xff); + + pm_wakeup_dev_event(smcin->dev, 0, (smcin->wakeup_mode && !lid_state)); + input_report_switch(smcin->input, SW_LID, lid_state); + input_sync(smcin->input); +} + +static int macsmc_input_event(struct notifier_block *nb, unsigned long event, void *data) +{ + struct macsmc_input *smcin = container_of(nb, struct macsmc_input, nb); + u16 type = event >> 16; + + switch (type) { + case SMC_EV_BTN: + macsmc_input_event_button(smcin, event); + return NOTIFY_OK; + case SMC_EV_LID: + macsmc_input_event_lid(smcin, event); + return NOTIFY_OK; + default: + /* SMC event meant for another driver */ + return NOTIFY_DONE; + } +} + +static int macsmc_input_probe(struct platform_device *pdev) +{ + struct apple_smc *smc = dev_get_drvdata(pdev->dev.parent); + struct macsmc_input *smcin; + bool have_lid, have_power; + int error; + + /* Bail early if this SMC neither supports power button nor lid events */ + have_lid = apple_smc_key_exists(smc, SMC_KEY(MSLD)); + have_power = apple_smc_key_exists(smc, SMC_KEY(bHLD)); + if (!have_lid && !have_power) + return -ENODEV; + + smcin = devm_kzalloc(&pdev->dev, sizeof(*smcin), GFP_KERNEL); + if (!smcin) + return -ENOMEM; + + smcin->dev = &pdev->dev; + smcin->smc = smc; + platform_set_drvdata(pdev, smcin); + + smcin->input = devm_input_allocate_device(&pdev->dev); + if (!smcin->input) + return -ENOMEM; + + smcin->input->phys = "macsmc-input (0)"; + smcin->input->name = "Apple SMC power/lid events"; + + if (have_lid) + input_set_capability(smcin->input, EV_SW, SW_LID); + if (have_power) + input_set_capability(smcin->input, EV_KEY, KEY_POWER); + + if (have_lid) { + u8 val; + + error = apple_smc_read_u8(smc, SMC_KEY(MSLD), &val); + if (error < 0) + dev_warn(&pdev->dev, "Failed to read initial lid state\n"); + else + input_report_switch(smcin->input, SW_LID, val); + } + + if (have_power) { + u32 val; + + error = apple_smc_read_u32(smc, SMC_KEY(bHLD), &val); + if (error < 0) + dev_warn(&pdev->dev, "Failed to read initial power button state\n"); + else + input_report_key(smcin->input, KEY_POWER, val & 1); + } + + error = input_register_device(smcin->input); + if (error) { + dev_err(&pdev->dev, "Failed to register input device: %d\n", error); + return error; + } + + input_sync(smcin->input); + + smcin->nb.notifier_call = macsmc_input_event; + blocking_notifier_chain_register(&smc->event_handlers, &smcin->nb); + + device_init_wakeup(&pdev->dev, true); + + return 0; +} + +static int macsmc_input_pm_prepare(struct device *dev) +{ + struct macsmc_input *smcin = dev_get_drvdata(dev); + + smcin->wakeup_mode = true; + return 0; +} + +static void macsmc_input_pm_complete(struct device *dev) +{ + struct macsmc_input *smcin = dev_get_drvdata(dev); + + smcin->wakeup_mode = false; +} + +static const struct dev_pm_ops macsmc_input_pm_ops = { + .prepare = macsmc_input_pm_prepare, + .complete = macsmc_input_pm_complete, +}; + +static struct platform_driver macsmc_input_driver = { + .driver = { + .name = "macsmc-input", + .pm = &macsmc_input_pm_ops, + }, + .probe = macsmc_input_probe, +}; +module_platform_driver(macsmc_input_driver); + +MODULE_AUTHOR("Hector Martin "); +MODULE_LICENSE("Dual MIT/GPL"); +MODULE_DESCRIPTION("Apple SMC input driver"); +MODULE_ALIAS("platform:macsmc-input"); diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index d0cb9fb9482185..df8953a5196e1b 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -2975,6 +2975,7 @@ static void alps_disconnect(struct psmouse *psmouse) psmouse_reset(psmouse); timer_shutdown_sync(&priv->timer); + disable_delayed_work_sync(&priv->dev3_register_work); if (priv->dev2) input_unregister_device(priv->dev2); if (!IS_ERR_OR_NULL(priv->dev3)) diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 1caa6c4ca435c7..d2cf940b105a69 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -115,6 +115,17 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { }, .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_NEVER) }, + { + /* + * ASUS Zenbook UX425QA_UM425QA + * Some Zenbooks report "Zenbook" with a lowercase b. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "Zenbook UX425QA_UM425QA"), + }, + .driver_data = (void *)(SERIO_QUIRK_PROBE_DEFER | SERIO_QUIRK_RESET_NEVER) + }, { /* ASUS ZenBook UX425UA/QA */ .matches = { @@ -1169,6 +1180,20 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "X5KK45xS_X5SP45xS"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "WUJIE Series-X5SP4NAG"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, /* * A lot of modern Clevo barebones have touchpad and/or keyboard issues * after suspend fixable with the forcenorestore quirk. diff --git a/drivers/input/touchscreen/apple_z2.c b/drivers/input/touchscreen/apple_z2.c index 0de161eae59a05..271ababf0ad559 100644 --- a/drivers/input/touchscreen/apple_z2.c +++ b/drivers/input/touchscreen/apple_z2.c @@ -21,6 +21,7 @@ #define APPLE_Z2_TOUCH_STARTED 3 #define APPLE_Z2_TOUCH_MOVED 4 #define APPLE_Z2_CMD_READ_INTERRUPT_DATA 0xEB +#define APPLE_Z2_REPLY_INTERRUPT_DATA 0xE1 #define APPLE_Z2_HBPP_CMD_BLOB 0x3001 #define APPLE_Z2_FW_MAGIC 0x5746325A #define LOAD_COMMAND_INIT_PAYLOAD 0 @@ -142,6 +143,9 @@ static int apple_z2_read_packet(struct apple_z2 *z2) if (error) return error; + if (z2->rx_buf[0] != APPLE_Z2_REPLY_INTERRUPT_DATA) + return 0; + pkt_len = (get_unaligned_le16(z2->rx_buf + 1) + 8) & 0xfffffffc; error = spi_read(z2->spidev, z2->rx_buf, pkt_len); diff --git a/drivers/input/touchscreen/ti_am335x_tsc.c b/drivers/input/touchscreen/ti_am335x_tsc.c index 93d659ff90aa94..73980142f492b8 100644 --- a/drivers/input/touchscreen/ti_am335x_tsc.c +++ b/drivers/input/touchscreen/ti_am335x_tsc.c @@ -85,7 +85,7 @@ static int titsc_config_wires(struct titsc *ts_dev) wire_order[i] = ts_dev->config_inp[i] & 0x0F; if (WARN_ON(analog_line[i] > 7)) return -EINVAL; - if (WARN_ON(wire_order[i] > ARRAY_SIZE(config_pins))) + if (WARN_ON(wire_order[i] >= ARRAY_SIZE(config_pins))) return -EINVAL; } diff --git a/drivers/interconnect/debugfs-client.c b/drivers/interconnect/debugfs-client.c index bc3fd8a7b9eb41..24d7b5a5779450 100644 --- a/drivers/interconnect/debugfs-client.c +++ b/drivers/interconnect/debugfs-client.c @@ -117,7 +117,12 @@ static int icc_commit_set(void *data, u64 val) mutex_lock(&debugfs_lock); - if (IS_ERR_OR_NULL(cur_path)) { + if (!cur_path) { + ret = -EINVAL; + goto out; + } + + if (IS_ERR(cur_path)) { ret = PTR_ERR(cur_path); goto out; } @@ -145,6 +150,11 @@ int icc_debugfs_client_init(struct dentry *icc_dir) return ret; } + src_node = devm_kstrdup(&pdev->dev, "", GFP_KERNEL); + dst_node = devm_kstrdup(&pdev->dev, "", GFP_KERNEL); + if (!src_node || !dst_node) + return -ENOMEM; + client_dir = debugfs_create_dir("test_client", icc_dir); debugfs_create_str("src_node", 0600, client_dir, &src_node); diff --git a/drivers/interconnect/mediatek/icc-emi.c b/drivers/interconnect/mediatek/icc-emi.c index 7da740b5fa8d62..dfa3a9cd939983 100644 --- a/drivers/interconnect/mediatek/icc-emi.c +++ b/drivers/interconnect/mediatek/icc-emi.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -22,7 +23,9 @@ static int mtk_emi_icc_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, { struct mtk_icc_node *in = node->data; - *agg_avg += avg_bw; + if (check_add_overflow(*agg_avg, avg_bw, agg_avg)) + *agg_avg = U32_MAX; + *agg_peak = max_t(u32, *agg_peak, peak_bw); in->sum_avg = *agg_avg; @@ -40,7 +43,7 @@ static int mtk_emi_icc_set(struct icc_node *src, struct icc_node *dst) if (unlikely(!src->provider)) return -EINVAL; - dev = src->provider->dev; + dev = src->provider->dev->parent; switch (node->ep) { case 0: @@ -97,7 +100,7 @@ int mtk_emi_icc_probe(struct platform_device *pdev) if (!data) return -ENOMEM; - provider->dev = pdev->dev.parent; + provider->dev = dev; provider->set = mtk_emi_icc_set; provider->aggregate = mtk_emi_icc_aggregate; provider->xlate = of_icc_xlate_onecell; diff --git a/drivers/interconnect/qcom/msm8996.c b/drivers/interconnect/qcom/msm8996.c index b73566c9b21f9d..84cfafb22aa17d 100644 --- a/drivers/interconnect/qcom/msm8996.c +++ b/drivers/interconnect/qcom/msm8996.c @@ -552,6 +552,7 @@ static struct qcom_icc_node mas_venus_vmem = { static const u16 mas_snoc_pnoc_links[] = { MSM8996_SLAVE_BLSP_1, MSM8996_SLAVE_BLSP_2, + MSM8996_SLAVE_USB_HS, MSM8996_SLAVE_SDCC_1, MSM8996_SLAVE_SDCC_2, MSM8996_SLAVE_SDCC_4, diff --git a/drivers/interconnect/qcom/sdx75.c b/drivers/interconnect/qcom/sdx75.c index 7ef1f17f3292e1..2def75f67eb8e0 100644 --- a/drivers/interconnect/qcom/sdx75.c +++ b/drivers/interconnect/qcom/sdx75.c @@ -16,15 +16,6 @@ #include "icc-rpmh.h" #include "sdx75.h" -static struct qcom_icc_node qpic_core_master = { - .name = "qpic_core_master", - .id = SDX75_MASTER_QPIC_CORE, - .channels = 1, - .buswidth = 4, - .num_links = 1, - .links = { SDX75_SLAVE_QPIC_CORE }, -}; - static struct qcom_icc_node qup0_core_master = { .name = "qup0_core_master", .id = SDX75_MASTER_QUP_CORE_0, @@ -375,14 +366,6 @@ static struct qcom_icc_node xm_usb3 = { .links = { SDX75_SLAVE_A1NOC_CFG }, }; -static struct qcom_icc_node qpic_core_slave = { - .name = "qpic_core_slave", - .id = SDX75_SLAVE_QPIC_CORE, - .channels = 1, - .buswidth = 4, - .num_links = 0, -}; - static struct qcom_icc_node qup0_core_slave = { .name = "qup0_core_slave", .id = SDX75_SLAVE_QUP_CORE_0, @@ -831,12 +814,6 @@ static struct qcom_icc_bcm bcm_mc0 = { .nodes = { &ebi }, }; -static struct qcom_icc_bcm bcm_qp0 = { - .name = "QP0", - .num_nodes = 1, - .nodes = { &qpic_core_slave }, -}; - static struct qcom_icc_bcm bcm_qup0 = { .name = "QUP0", .keepalive = true, @@ -898,14 +875,11 @@ static struct qcom_icc_bcm bcm_sn4 = { }; static struct qcom_icc_bcm * const clk_virt_bcms[] = { - &bcm_qp0, &bcm_qup0, }; static struct qcom_icc_node * const clk_virt_nodes[] = { - [MASTER_QPIC_CORE] = &qpic_core_master, [MASTER_QUP_CORE_0] = &qup0_core_master, - [SLAVE_QPIC_CORE] = &qpic_core_slave, [SLAVE_QUP_CORE_0] = &qup0_core_slave, }; diff --git a/drivers/interconnect/qcom/sdx75.h b/drivers/interconnect/qcom/sdx75.h index 24e88715992010..34f51add59dc00 100644 --- a/drivers/interconnect/qcom/sdx75.h +++ b/drivers/interconnect/qcom/sdx75.h @@ -33,7 +33,6 @@ #define SDX75_MASTER_QDSS_ETR 24 #define SDX75_MASTER_QDSS_ETR_1 25 #define SDX75_MASTER_QPIC 26 -#define SDX75_MASTER_QPIC_CORE 27 #define SDX75_MASTER_QUP_0 28 #define SDX75_MASTER_QUP_CORE_0 29 #define SDX75_MASTER_SDCC_1 30 @@ -76,7 +75,6 @@ #define SDX75_SLAVE_QDSS_CFG 67 #define SDX75_SLAVE_QDSS_STM 68 #define SDX75_SLAVE_QPIC 69 -#define SDX75_SLAVE_QPIC_CORE 70 #define SDX75_SLAVE_QUP_0 71 #define SDX75_SLAVE_QUP_CORE_0 72 #define SDX75_SLAVE_SDCC_1 73 diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 9b4b589a54b57e..bf77fdf5529f48 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -15,7 +15,6 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data); irqreturn_t amd_iommu_int_thread_evtlog(int irq, void *data); irqreturn_t amd_iommu_int_thread_pprlog(int irq, void *data); irqreturn_t amd_iommu_int_thread_galog(int irq, void *data); -irqreturn_t amd_iommu_int_handler(int irq, void *data); void amd_iommu_restart_log(struct amd_iommu *iommu, const char *evt_type, u8 cntrl_intr, u8 cntrl_log, u32 status_run_mask, u32 status_overflow_mask); diff --git a/drivers/iommu/amd/debugfs.c b/drivers/iommu/amd/debugfs.c index 10fa217a711993..20b04996441d62 100644 --- a/drivers/iommu/amd/debugfs.c +++ b/drivers/iommu/amd/debugfs.c @@ -37,7 +37,7 @@ static ssize_t iommu_mmio_write(struct file *filp, const char __user *ubuf, if (ret) return ret; - if (iommu->dbg_mmio_offset > iommu->mmio_phys_end - 4) { + if (iommu->dbg_mmio_offset > iommu->mmio_phys_end - sizeof(u64)) { iommu->dbg_mmio_offset = -1; return -EINVAL; } diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index f2991c11867cba..53afb1cb0a6fcc 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -1136,9 +1136,13 @@ static void set_dte_bit(struct dev_table_entry *dte, u8 bit) static bool __reuse_device_table(struct amd_iommu *iommu) { struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg; - u32 lo, hi, old_devtb_size; + struct dev_table_entry *old_dev_tbl_entry; + u32 lo, hi, old_devtb_size, devid; phys_addr_t old_devtb_phys; + u16 dom_id; + bool dte_v; u64 entry; + int ret; /* Each IOMMU use separate device table with the same size */ lo = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET); @@ -1173,6 +1177,23 @@ static bool __reuse_device_table(struct amd_iommu *iommu) return false; } + for (devid = 0; devid <= pci_seg->last_bdf; devid++) { + old_dev_tbl_entry = &pci_seg->old_dev_tbl_cpy[devid]; + dte_v = FIELD_GET(DTE_FLAG_V, old_dev_tbl_entry->data[0]); + dom_id = FIELD_GET(DEV_DOMID_MASK, old_dev_tbl_entry->data[1]); + + if (!dte_v || !dom_id) + continue; + /* + * ID reservation can fail with -ENOSPC when there + * are multiple devices present in the same domain, + * hence check only for -ENOMEM. + */ + ret = ida_alloc_range(&pdom_ids, dom_id, dom_id, GFP_KERNEL); + if (ret == -ENOMEM) + return false; + } + return true; } @@ -1710,13 +1731,22 @@ static struct amd_iommu_pci_seg *__init alloc_pci_segment(u16 id, list_add_tail(&pci_seg->list, &amd_iommu_pci_seg_list); if (alloc_dev_table(pci_seg)) - return NULL; + goto err_free_pci_seg; if (alloc_alias_table(pci_seg)) - return NULL; + goto err_free_dev_table; if (alloc_rlookup_table(pci_seg)) - return NULL; + goto err_free_alias_table; return pci_seg; + +err_free_alias_table: + free_alias_table(pci_seg); +err_free_dev_table: + free_dev_table(pci_seg); +err_free_pci_seg: + list_del(&pci_seg->list); + kfree(pci_seg); + return NULL; } static struct amd_iommu_pci_seg *__init get_pci_segment(u16 id, @@ -2325,12 +2355,8 @@ static int iommu_setup_msi(struct amd_iommu *iommu) if (r) return r; - r = request_threaded_irq(iommu->dev->irq, - amd_iommu_int_handler, - amd_iommu_int_thread, - 0, "AMD-Vi", - iommu); - + r = request_threaded_irq(iommu->dev->irq, NULL, amd_iommu_int_thread, + IRQF_ONESHOT, "AMD-Vi", iommu); if (r) { pci_disable_msi(iommu->dev); return r; @@ -2504,8 +2530,8 @@ static int __iommu_setup_intcapxt(struct amd_iommu *iommu, const char *devname, return irq; } - ret = request_threaded_irq(irq, amd_iommu_int_handler, - thread_fn, 0, devname, iommu); + ret = request_threaded_irq(irq, NULL, thread_fn, IRQF_ONESHOT, devname, + iommu); if (ret) { irq_domain_free_irqs(irq, 1); irq_domain_remove(domain); diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 2e1865daa1cee8..30dd482fe0953d 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1146,11 +1146,6 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data) return IRQ_HANDLED; } -irqreturn_t amd_iommu_int_handler(int irq, void *data) -{ - return IRQ_WAKE_THREAD; -} - /**************************************************************************** * * IOMMU command queuing functions @@ -2426,8 +2421,6 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev) goto out_err; } -out_err: - iommu_completion_wait(iommu); if (FEATURE_NUM_INT_REMAP_SUP_2K(amd_iommu_efr2)) @@ -2438,6 +2431,7 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev) if (dev_is_pci(dev)) pci_prepare_ats(to_pci_dev(dev), PAGE_SHIFT); +out_err: return iommu_dev; } @@ -3354,7 +3348,7 @@ static int __modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index, static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index, struct irte_ga *irte) { - bool ret; + int ret; ret = __modify_irte_ga(iommu, devid, index, irte); if (ret) diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index 95a4e62b8f63c3..c01258b479c208 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -28,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -201,6 +203,7 @@ struct apple_dart_hw { * @lock: lock for hardware operations involving this dart * @pgsize: pagesize supported by this DART * @supports_bypass: indicates if this DART supports bypass mode + * @locked: indicates if this DART is locked * @sid2group: maps stream ids to iommu_groups * @iommu: iommu core device */ @@ -222,12 +225,18 @@ struct apple_dart { u32 num_streams; u32 supports_bypass : 1; u32 four_level : 1; + u32 locked : 1; + + dma_addr_t dma_min; + dma_addr_t dma_max; struct iommu_group *sid2group[DART_MAX_STREAMS]; struct iommu_device iommu; u32 save_tcr[DART_MAX_STREAMS]; u32 save_ttbr[DART_MAX_STREAMS][DART_MAX_TTBR]; + + u64 *locked_ttbr[DART_MAX_STREAMS][DART_MAX_TTBR]; }; /* @@ -267,6 +276,7 @@ struct apple_dart_domain { struct io_pgtable_ops *pgtbl_ops; bool finalized; + u64 mask; struct mutex init_lock; struct apple_dart_atomic_stream_map stream_maps[MAX_DARTS_PER_DEVICE]; @@ -284,6 +294,7 @@ struct apple_dart_domain { struct apple_dart_master_cfg { /* Intersection of DART capabilitles */ u32 supports_bypass : 1; + u32 locked : 1; struct apple_dart_stream_map stream_maps[MAX_DARTS_PER_DEVICE]; }; @@ -378,6 +389,82 @@ apple_dart_hw_clear_all_ttbrs(struct apple_dart_stream_map *stream_map) apple_dart_hw_clear_ttbr(stream_map, i); } +static int +apple_dart_hw_map_locked_ttbr(struct apple_dart_stream_map *stream_map, u8 idx) +{ + struct apple_dart *dart = stream_map->dart; + int sid; + + for_each_set_bit(sid, stream_map->sidmap, dart->num_streams) { + u32 ttbr; + phys_addr_t phys; + u64 *l1_tbl; + + ttbr = readl(dart->regs + DART_TTBR(dart, sid, idx)); + + if (!(ttbr & dart->hw->ttbr_valid)) { + dev_err(dart->dev, "Invalid ttbr[%u] for locked dart\n", + idx); + return -EIO; + } + + ttbr &= ~dart->hw->ttbr_valid; + + if (dart->hw->ttbr_addr_field_shift) + ttbr >>= dart->hw->ttbr_addr_field_shift; + phys = ((phys_addr_t) ttbr) << dart->hw->ttbr_shift; + + l1_tbl = devm_memremap(dart->dev, phys, dart->pgsize, + MEMREMAP_WB); + if (!l1_tbl) + return -ENOMEM; + + dart->locked_ttbr[sid][idx] = l1_tbl; + } + + return 0; +} + +static int +apple_dart_hw_unmap_locked_ttbr(struct apple_dart_stream_map *stream_map, + u8 idx) +{ + struct apple_dart *dart = stream_map->dart; + int sid; + + for_each_set_bit(sid, stream_map->sidmap, dart->num_streams) { + /* TODO: locked L1 table might need to be restored to boot state */ + if (dart->locked_ttbr[sid][idx]) { + memset(dart->locked_ttbr[sid][idx], 0, dart->pgsize); + devm_memunmap(dart->dev, dart->locked_ttbr[sid][idx]); + } + dart->locked_ttbr[sid][idx] = NULL; + } + + return 0; +} + +static int +apple_dart_hw_sync_locked(struct io_pgtable_cfg *cfg, + struct apple_dart_stream_map *stream_map) +{ + struct apple_dart *dart = stream_map->dart; + int sid; + + for_each_set_bit(sid, stream_map->sidmap, dart->num_streams) { + for (int idx = 0; idx < dart->hw->ttbr_count; idx++) { + u64 *ttbrep = dart->locked_ttbr[sid][idx]; + u64 *ptep = cfg->apple_dart_cfg.ttbr[idx]; + if (!ttbrep || !ptep) + continue; + for (int entry = 0; entry < dart->pgsize / sizeof(*ptep); entry++) + ttbrep[entry] = ptep[entry]; + } + } + + return 0; +} + static int apple_dart_t8020_hw_stream_command(struct apple_dart_stream_map *stream_map, u32 command) @@ -464,17 +551,9 @@ apple_dart_t8110_hw_invalidate_tlb(struct apple_dart_stream_map *stream_map) static int apple_dart_hw_reset(struct apple_dart *dart) { - u32 config; struct apple_dart_stream_map stream_map; int i; - config = readl(dart->regs + dart->hw->lock); - if (config & dart->hw->lock_bit) { - dev_err(dart->dev, "DART is locked down until reboot: %08x\n", - config); - return -EINVAL; - } - stream_map.dart = dart; bitmap_zero(stream_map.sidmap, DART_MAX_STREAMS); bitmap_set(stream_map.sidmap, 0, dart->num_streams); @@ -499,6 +578,8 @@ static void apple_dart_domain_flush_tlb(struct apple_dart_domain *domain) int i, j; struct apple_dart_atomic_stream_map *domain_stream_map; struct apple_dart_stream_map stream_map; + struct io_pgtable_cfg *pgtbl_cfg = + &io_pgtable_ops_to_pgtable(domain->pgtbl_ops)->cfg; for_each_stream_map(i, domain, domain_stream_map) { stream_map.dart = domain_stream_map->dart; @@ -506,7 +587,13 @@ static void apple_dart_domain_flush_tlb(struct apple_dart_domain *domain) for (j = 0; j < BITS_TO_LONGS(stream_map.dart->num_streams); j++) stream_map.sidmap[j] = atomic_long_read(&domain_stream_map->sidmap[j]); + WARN_ON(pm_runtime_get_sync(stream_map.dart->dev) < 0); + + if (stream_map.dart->locked) + apple_dart_hw_sync_locked(pgtbl_cfg, &stream_map); + stream_map.dart->hw->invalidate_tlb(&stream_map); + pm_runtime_put(stream_map.dart->dev); } } @@ -537,7 +624,7 @@ static phys_addr_t apple_dart_iova_to_phys(struct iommu_domain *domain, if (!ops) return 0; - return ops->iova_to_phys(ops, iova); + return ops->iova_to_phys(ops, iova & dart_domain->mask); } static int apple_dart_map_pages(struct iommu_domain *domain, unsigned long iova, @@ -551,8 +638,8 @@ static int apple_dart_map_pages(struct iommu_domain *domain, unsigned long iova, if (!ops) return -ENODEV; - return ops->map_pages(ops, iova, paddr, pgsize, pgcount, prot, gfp, - mapped); + return ops->map_pages(ops, iova & dart_domain->mask, paddr, pgsize, + pgcount, prot, gfp, mapped); } static size_t apple_dart_unmap_pages(struct iommu_domain *domain, @@ -563,7 +650,8 @@ static size_t apple_dart_unmap_pages(struct iommu_domain *domain, struct apple_dart_domain *dart_domain = to_dart_domain(domain); struct io_pgtable_ops *ops = dart_domain->pgtbl_ops; - return ops->unmap_pages(ops, iova, pgsize, pgcount, gather); + return ops->unmap_pages(ops, iova & dart_domain->mask, pgsize, pgcount, + gather); } static void @@ -574,9 +662,10 @@ apple_dart_setup_translation(struct apple_dart_domain *domain, struct io_pgtable_cfg *pgtbl_cfg = &io_pgtable_ops_to_pgtable(domain->pgtbl_ops)->cfg; - for (i = 0; i < pgtbl_cfg->apple_dart_cfg.n_ttbrs; ++i) - apple_dart_hw_set_ttbr(stream_map, i, - pgtbl_cfg->apple_dart_cfg.ttbr[i]); + for (i = 0; i < pgtbl_cfg->apple_dart_cfg.n_ttbrs; ++i) { + u64 ttbr = virt_to_phys(pgtbl_cfg->apple_dart_cfg.ttbr[i]); + apple_dart_hw_set_ttbr(stream_map, i, ttbr); + } for (; i < stream_map->dart->hw->ttbr_count; ++i) apple_dart_hw_clear_ttbr(stream_map, i); @@ -585,11 +674,31 @@ apple_dart_setup_translation(struct apple_dart_domain *domain, stream_map->dart->hw->invalidate_tlb(stream_map); } +static void +apple_dart_setup_translation_locked(struct apple_dart_domain *domain, + struct apple_dart_stream_map *stream_map) +{ + int i; + struct io_pgtable_cfg *pgtbl_cfg = + &io_pgtable_ops_to_pgtable(domain->pgtbl_ops)->cfg; + + /* Locked DARTs are set up by the bootloader. */ + for (i = 0; i < pgtbl_cfg->apple_dart_cfg.n_ttbrs; ++i) + apple_dart_hw_map_locked_ttbr(stream_map, i); + for (; i < stream_map->dart->hw->ttbr_count; ++i) + apple_dart_hw_unmap_locked_ttbr(stream_map, i); + + apple_dart_hw_sync_locked(pgtbl_cfg, stream_map); + stream_map->dart->hw->invalidate_tlb(stream_map); +} + static int apple_dart_finalize_domain(struct apple_dart_domain *dart_domain, struct apple_dart_master_cfg *cfg) { struct apple_dart *dart = cfg->stream_maps[0].dart; struct io_pgtable_cfg pgtbl_cfg; + dma_addr_t dma_max = dart->dma_max; + u32 ias = min_t(u32, dart->ias, fls64(dma_max)); int ret = 0; int i, j; @@ -610,12 +719,48 @@ static int apple_dart_finalize_domain(struct apple_dart_domain *dart_domain, pgtbl_cfg = (struct io_pgtable_cfg){ .pgsize_bitmap = dart->pgsize, - .ias = dart->ias, + .ias = ias, .oas = dart->oas, .coherent_walk = 1, .iommu_dev = dart->dev, }; + if (dart->locked) { + unsigned long *sidmap; + int sid; + u32 ttbr; + + /* Locked DARTs can only have a single stream bound */ + sidmap = cfg->stream_maps[0].sidmap; + sid = find_first_bit(sidmap, dart->num_streams); + + WARN_ON((sid < 0) || bitmap_weight(sidmap, dart->num_streams) > 1); + ttbr = readl(dart->regs + DART_TTBR(dart, sid, 0)); + + WARN_ON(!(ttbr & dart->hw->ttbr_valid)); + + /* If the DART is locked, we need to keep the translation level count. */ + if (dart->hw->tcr_4level && dart->ias > 36) { + if (readl(dart->regs + DART_TCR(dart, sid)) & dart->hw->tcr_4level) { + if (ias < 37) { + dev_info(dart->dev, "Expanded to ias=37 due to lock\n"); + pgtbl_cfg.ias = 37; + } + } else if (ias > 36) { + dev_info(dart->dev, "Limited to ias=36 due to lock\n"); + pgtbl_cfg.ias = 36; + if (dart->dma_min == 0 && dma_max == DMA_BIT_MASK(dart->ias)) { + dma_max = DMA_BIT_MASK(pgtbl_cfg.ias); + } else if ((dart->dma_min ^ dma_max) & ~DMA_BIT_MASK(36)) { + dev_err(dart->dev, + "Invalid DMA range for locked 3-level PT\n"); + ret = -ENOMEM; + goto done; + } + } + } + } + dart_domain->pgtbl_ops = alloc_io_pgtable_ops(dart->hw->fmt, &pgtbl_cfg, &dart_domain->domain); if (!dart_domain->pgtbl_ops) { @@ -623,10 +768,16 @@ static int apple_dart_finalize_domain(struct apple_dart_domain *dart_domain, goto done; } + if (pgtbl_cfg.pgsize_bitmap == SZ_4K) + dart_domain->mask = DMA_BIT_MASK(min_t(u32, dart->ias, 32)); + else if (pgtbl_cfg.apple_dart_cfg.n_levels == 3) + dart_domain->mask = DMA_BIT_MASK(min_t(u32, dart->ias, 36)); + else if (pgtbl_cfg.apple_dart_cfg.n_levels == 4) + dart_domain->mask = DMA_BIT_MASK(min_t(u32, dart->ias, 47)); + dart_domain->domain.pgsize_bitmap = pgtbl_cfg.pgsize_bitmap; - dart_domain->domain.geometry.aperture_start = 0; - dart_domain->domain.geometry.aperture_end = - (dma_addr_t)DMA_BIT_MASK(pgtbl_cfg.ias); + dart_domain->domain.geometry.aperture_start = dart->dma_min; + dart_domain->domain.geometry.aperture_end = dma_max; dart_domain->domain.geometry.force_aperture = true; dart_domain->finalized = true; @@ -679,17 +830,29 @@ static int apple_dart_attach_dev_paging(struct iommu_domain *domain, struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev); struct apple_dart_domain *dart_domain = to_dart_domain(domain); + for_each_stream_map(i, cfg, stream_map) + WARN_ON(pm_runtime_get_sync(stream_map->dart->dev) < 0); + ret = apple_dart_finalize_domain(dart_domain, cfg); if (ret) - return ret; + goto err; ret = apple_dart_domain_add_streams(dart_domain, cfg); if (ret) - return ret; + goto err; + + for_each_stream_map(i, cfg, stream_map) { + if (!stream_map->dart->locked) + apple_dart_setup_translation(dart_domain, stream_map); + else + apple_dart_setup_translation_locked(dart_domain, + stream_map); + } +err: for_each_stream_map(i, cfg, stream_map) - apple_dart_setup_translation(dart_domain, stream_map); - return 0; + pm_runtime_put(stream_map->dart->dev); + return ret; } static int apple_dart_attach_dev_identity(struct iommu_domain *domain, @@ -702,8 +865,17 @@ static int apple_dart_attach_dev_identity(struct iommu_domain *domain, if (!cfg->supports_bypass) return -EINVAL; + if (cfg->locked) + return -EINVAL; + + for_each_stream_map(i, cfg, stream_map) + WARN_ON(pm_runtime_get_sync(stream_map->dart->dev) < 0); + for_each_stream_map(i, cfg, stream_map) apple_dart_hw_enable_bypass(stream_map); + + for_each_stream_map(i, cfg, stream_map) + pm_runtime_put(stream_map->dart->dev); return 0; } @@ -723,8 +895,17 @@ static int apple_dart_attach_dev_blocked(struct iommu_domain *domain, struct apple_dart_stream_map *stream_map; int i; + if (cfg->locked) + return -EINVAL; + + for_each_stream_map(i, cfg, stream_map) + WARN_ON(pm_runtime_get_sync(stream_map->dart->dev) < 0); + for_each_stream_map(i, cfg, stream_map) apple_dart_hw_disable_dma(stream_map); + + for_each_stream_map(i, cfg, stream_map) + pm_runtime_put(stream_map->dart->dev); return 0; } @@ -743,21 +924,29 @@ static struct iommu_device *apple_dart_probe_device(struct device *dev) struct apple_dart_stream_map *stream_map; int i; - if (!cfg) + if (!dev_iommu_fwspec_get(dev) || !cfg) return ERR_PTR(-ENODEV); for_each_stream_map(i, cfg, stream_map) - device_link_add( - dev, stream_map->dart->dev, - DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_SUPPLIER); + device_link_add(dev, stream_map->dart->dev, + DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_SUPPLIER | + DL_FLAG_RPM_ACTIVE); return &cfg->stream_maps[0].dart->iommu; } static void apple_dart_release_device(struct device *dev) { + int i, j; + struct apple_dart_stream_map *stream_map; struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev); + for_each_stream_map(j, cfg, stream_map) { + if (stream_map->dart->locked) + for (i = 0; i < stream_map->dart->hw->ttbr_count; ++i) + apple_dart_hw_unmap_locked_ttbr(stream_map, i); + } + kfree(cfg); } @@ -802,6 +991,8 @@ static int apple_dart_of_xlate(struct device *dev, struct apple_dart *cfg_dart; int i, sid; + put_device(&iommu_pdev->dev); + if (args->args_count != 1) return -EINVAL; sid = args->args[0]; @@ -812,6 +1003,8 @@ static int apple_dart_of_xlate(struct device *dev, return -ENOMEM; /* Will be ANDed with DART capabilities */ cfg->supports_bypass = true; + /* Will be ORed with DART capabilities*/ + cfg->locked = false; } dev_iommu_priv_set(dev, cfg); @@ -824,6 +1017,7 @@ static int apple_dart_of_xlate(struct device *dev, } cfg->supports_bypass &= dart->supports_bypass; + cfg->locked |= dart->locked; for (i = 0; i < MAX_DARTS_PER_DEVICE; ++i) { if (cfg->stream_maps[i].dart == dart) { @@ -966,6 +1160,8 @@ static int apple_dart_def_domain_type(struct device *dev) return IOMMU_DOMAIN_IDENTITY; if (!cfg->supports_bypass) return IOMMU_DOMAIN_DMA; + if (cfg->locked) + return IOMMU_DOMAIN_DMA; return 0; } @@ -998,12 +1194,12 @@ static void apple_dart_get_resv_regions(struct device *dev, static const struct iommu_ops apple_dart_iommu_ops = { .identity_domain = &apple_dart_identity_domain, .blocked_domain = &apple_dart_blocked_domain, + .def_domain_type = apple_dart_def_domain_type, .domain_alloc_paging = apple_dart_domain_alloc_paging, .probe_device = apple_dart_probe_device, .release_device = apple_dart_release_device, .device_group = apple_dart_device_group, .of_xlate = apple_dart_of_xlate, - .def_domain_type = apple_dart_def_domain_type, .get_resv_regions = apple_dart_get_resv_regions, .owner = THIS_MODULE, .default_domain_ops = &(const struct iommu_domain_ops) { @@ -1097,6 +1293,22 @@ static irqreturn_t apple_dart_t8110_irq(int irq, void *dev) return IRQ_HANDLED; } +static irqreturn_t apple_dart_irq(int irq, void *dev) +{ + irqreturn_t ret; + struct apple_dart *dart = dev; + + WARN_ON(pm_runtime_get_sync(dart->dev) < 0); + ret = dart->hw->irq_handler(irq, dev); + pm_runtime_put(dart->dev); + return ret; +} + +static bool apple_dart_is_locked(struct apple_dart *dart) +{ + return !!(readl(dart->regs + dart->hw->lock) & dart->hw->lock_bit); +} + static int apple_dart_probe(struct platform_device *pdev) { int ret; @@ -1104,6 +1316,7 @@ static int apple_dart_probe(struct platform_device *pdev) struct resource *res; struct apple_dart *dart; struct device *dev = &pdev->dev; + u64 dma_range[2]; dart = devm_kzalloc(dev, sizeof(*dart), GFP_KERNEL); if (!dart) @@ -1135,6 +1348,14 @@ static int apple_dart_probe(struct platform_device *pdev) if (ret) return ret; + pm_runtime_get_noresume(dev); + pm_runtime_set_active(dev); + pm_runtime_irq_safe(dev); + + ret = devm_pm_runtime_enable(dev); + if (ret) + goto err_clk_disable; + dart_params[0] = readl(dart->regs + DART_PARAMS1); dart_params[1] = readl(dart->regs + DART_PARAMS2); dart->pgsize = 1 << FIELD_GET(DART_PARAMS1_PAGE_SHIFT, dart_params[0]); @@ -1158,6 +1379,26 @@ static int apple_dart_probe(struct platform_device *pdev) break; } + dart->dma_min = 0; + dart->dma_max = DMA_BIT_MASK(dart->ias); + + ret = of_property_read_u64_array(dev->of_node, "apple,dma-range", dma_range, 2); + if (ret == -EINVAL) { + ret = 0; + } else if (ret) { + goto err_clk_disable; + } else { + dart->dma_min = dma_range[0]; + dart->dma_max = dma_range[0] + dma_range[1] - 1; + if ((dart->dma_min ^ dart->dma_max) & ~DMA_BIT_MASK(dart->ias)) { + dev_err(&pdev->dev, "Invalid DMA range for ias=%d\n", + dart->ias); + goto err_clk_disable; + } + dev_info(&pdev->dev, "Limiting DMA range to %pad..%pad\n", + &dart->dma_min, &dart->dma_max); + } + if (dart->num_streams > DART_MAX_STREAMS) { dev_err(&pdev->dev, "Too many streams (%d > %d)\n", dart->num_streams, DART_MAX_STREAMS); @@ -1165,11 +1406,14 @@ static int apple_dart_probe(struct platform_device *pdev) goto err_clk_disable; } - ret = apple_dart_hw_reset(dart); - if (ret) - goto err_clk_disable; + dart->locked = apple_dart_is_locked(dart); + if (!dart->locked) { + ret = apple_dart_hw_reset(dart); + if (ret) + goto err_clk_disable; + } - ret = request_irq(dart->irq, dart->hw->irq_handler, IRQF_SHARED, + ret = request_irq(dart->irq, apple_dart_irq, IRQF_SHARED, "apple-dart fault handler", dart); if (ret) goto err_clk_disable; @@ -1185,11 +1429,13 @@ static int apple_dart_probe(struct platform_device *pdev) if (ret) goto err_sysfs_remove; + pm_runtime_put(dev); + dev_info( &pdev->dev, - "DART [pagesize %x, %d streams, bypass support: %d, bypass forced: %d, AS %d -> %d] initialized\n", + "DART [pagesize %x, %d streams, bypass support: %d, bypass forced: %d, locked: %d, AS %d -> %d] initialized\n", dart->pgsize, dart->num_streams, dart->supports_bypass, - dart->pgsize > PAGE_SIZE, dart->ias, dart->oas); + dart->pgsize > PAGE_SIZE, dart->locked, dart->ias, dart->oas); return 0; err_sysfs_remove: @@ -1197,6 +1443,7 @@ static int apple_dart_probe(struct platform_device *pdev) err_free_irq: free_irq(dart->irq, dart); err_clk_disable: + pm_runtime_put(dev); clk_bulk_disable_unprepare(dart->num_clks, dart->clks); return ret; @@ -1206,7 +1453,9 @@ static void apple_dart_remove(struct platform_device *pdev) { struct apple_dart *dart = platform_get_drvdata(pdev); - apple_dart_hw_reset(dart); + if (!dart->locked) + apple_dart_hw_reset(dart); + free_irq(dart->irq, dart); iommu_device_unregister(&dart->iommu); @@ -1324,6 +1573,10 @@ static __maybe_unused int apple_dart_suspend(struct device *dev) struct apple_dart *dart = dev_get_drvdata(dev); unsigned int sid, idx; + /* Locked DARTs can't be restored so skip saving their registers. */ + if (dart->locked) + return 0; + for (sid = 0; sid < dart->num_streams; sid++) { dart->save_tcr[sid] = readl(dart->regs + DART_TCR(dart, sid)); for (idx = 0; idx < dart->hw->ttbr_count; idx++) @@ -1340,6 +1593,10 @@ static __maybe_unused int apple_dart_resume(struct device *dev) unsigned int sid, idx; int ret; + /* Locked DARTs can't be restored, and they should not need it */ + if (dart->locked) + return 0; + ret = apple_dart_hw_reset(dart); if (ret) { dev_err(dev, "Failed to reset DART on resume\n"); @@ -1356,7 +1613,7 @@ static __maybe_unused int apple_dart_resume(struct device *dev) return 0; } -static DEFINE_SIMPLE_DEV_PM_OPS(apple_dart_pm_ops, apple_dart_suspend, apple_dart_resume); +static DEFINE_RUNTIME_DEV_PM_OPS(apple_dart_pm_ops, apple_dart_suspend, apple_dart_resume, NULL); static const struct of_device_id apple_dart_of_match[] = { { .compatible = "apple,t8103-dart", .data = &apple_dart_hw_t8103 }, @@ -1372,7 +1629,7 @@ static struct platform_driver apple_dart_driver = { .name = "apple-dart", .of_match_table = apple_dart_of_match, .suppress_bind_attrs = true, - .pm = pm_sleep_ptr(&apple_dart_pm_ops), + .pm = pm_ptr(&apple_dart_pm_ops), }, .probe = apple_dart_probe, .remove = apple_dart_remove, diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 2a8b46b948f050..9780f40ba3e654 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -1464,7 +1464,7 @@ static int arm_smmu_alloc_cd_tables(struct arm_smmu_master *master) cd_table->l2.l1tab = dma_alloc_coherent(smmu->dev, l1size, &cd_table->cdtab_dma, GFP_KERNEL); - if (!cd_table->l2.l2ptrs) { + if (!cd_table->l2.l1tab) { ret = -ENOMEM; goto err_free_l2ptrs; } diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c index 378104cd395e59..04cc7a9036e431 100644 --- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c +++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c @@ -1078,6 +1078,9 @@ static int tegra241_vcmdq_hw_init_user(struct tegra241_vcmdq *vcmdq) { char header[64]; + /* Reset VCMDQ */ + tegra241_vcmdq_hw_deinit(vcmdq); + /* Configure the vcmdq only; User space does the enabling */ writeq_relaxed(vcmdq->cmdq.q.q_base, REG_VCMDQ_PAGE1(vcmdq, BASE)); diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c index db9b9a8e139c87..4565a58bb213f4 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c @@ -228,3 +228,17 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu) return smmu; } + +int __init arm_smmu_impl_module_init(void) +{ + if (IS_ENABLED(CONFIG_ARM_SMMU_QCOM)) + return qcom_smmu_module_init(); + + return 0; +} + +void __exit arm_smmu_impl_module_exit(void) +{ + if (IS_ENABLED(CONFIG_ARM_SMMU_QCOM)) + qcom_smmu_module_exit(); +} diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index 57c097e8761308..2c442aa2181571 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -431,17 +431,19 @@ static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu) /* * Some platforms support more than the Arm SMMU architected maximum of - * 128 stream matching groups. For unknown reasons, the additional - * groups don't exhibit the same behavior as the architected registers, - * so limit the groups to 128 until the behavior is fixed for the other - * groups. + * 128 stream matching groups. The additional registers appear to have + * the same behavior as the architected registers in the hardware. + * However, on some firmware versions, the hypervisor does not + * correctly trap and emulate accesses to the additional registers, + * resulting in unexpected behavior. + * + * If there are more than 128 groups, use the last reliable group to + * detect if we need to apply the bypass quirk. */ - if (smmu->num_mapping_groups > 128) { - dev_notice(smmu->dev, "\tLimiting the stream matching groups to 128\n"); - smmu->num_mapping_groups = 128; - } - - last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1); + if (smmu->num_mapping_groups > 128) + last_s2cr = ARM_SMMU_GR0_S2CR(127); + else + last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1); /* * With some firmware versions writes to S2CR of type FAULT are @@ -464,6 +466,11 @@ static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu) reg = FIELD_PREP(ARM_SMMU_CBAR_TYPE, CBAR_TYPE_S1_TRANS_S2_BYPASS); arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(qsmmu->bypass_cbndx), reg); + + if (smmu->num_mapping_groups > 128) { + dev_notice(smmu->dev, "\tLimiting the stream matching groups to 128\n"); + smmu->num_mapping_groups = 128; + } } for (i = 0; i < smmu->num_mapping_groups; i++) { @@ -766,10 +773,6 @@ struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu) { const struct device_node *np = smmu->dev->of_node; const struct of_device_id *match; - static u8 tbu_registered; - - if (!tbu_registered++) - platform_driver_register(&qcom_smmu_tbu_driver); #ifdef CONFIG_ACPI if (np == NULL) { @@ -794,3 +797,13 @@ struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu) return smmu; } + +int __init qcom_smmu_module_init(void) +{ + return platform_driver_register(&qcom_smmu_tbu_driver); +} + +void __exit qcom_smmu_module_exit(void) +{ + platform_driver_unregister(&qcom_smmu_tbu_driver); +} diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 4ced4b5bee4df3..488632b8eeab61 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -2362,7 +2362,29 @@ static struct platform_driver arm_smmu_driver = { .remove = arm_smmu_device_remove, .shutdown = arm_smmu_device_shutdown, }; -module_platform_driver(arm_smmu_driver); + +static int __init arm_smmu_init(void) +{ + int ret; + + ret = platform_driver_register(&arm_smmu_driver); + if (ret) + return ret; + + ret = arm_smmu_impl_module_init(); + if (ret) + platform_driver_unregister(&arm_smmu_driver); + + return ret; +} +module_init(arm_smmu_init); + +static void __exit arm_smmu_exit(void) +{ + arm_smmu_impl_module_exit(); + platform_driver_unregister(&arm_smmu_driver); +} +module_exit(arm_smmu_exit); MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations"); MODULE_AUTHOR("Will Deacon "); diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h index 2dbf3243b5ad2d..26d2e33cd328b8 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.h +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h @@ -540,6 +540,11 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu); struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu); struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu); +int __init arm_smmu_impl_module_init(void); +void __exit arm_smmu_impl_module_exit(void); +int __init qcom_smmu_module_init(void); +void __exit qcom_smmu_module_exit(void); + void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx); int arm_mmu500_reset(struct arm_smmu_device *smmu); diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c index c5be95e560317e..9c1166a3af6c98 100644 --- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c +++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c @@ -565,14 +565,14 @@ static int qcom_iommu_of_xlate(struct device *dev, qcom_iommu = platform_get_drvdata(iommu_pdev); + put_device(&iommu_pdev->dev); + /* make sure the asid specified in dt is valid, so we don't have * to sanity check this elsewhere: */ if (WARN_ON(asid > qcom_iommu->max_asid) || - WARN_ON(qcom_iommu->ctxs[asid] == NULL)) { - put_device(&iommu_pdev->dev); + WARN_ON(qcom_iommu->ctxs[asid] == NULL)) return -EINVAL; - } if (!dev_iommu_priv_get(dev)) { dev_iommu_priv_set(dev, qcom_iommu); @@ -581,10 +581,8 @@ static int qcom_iommu_of_xlate(struct device *dev, * multiple different iommu devices. Multiple context * banks are ok, but multiple devices are not: */ - if (WARN_ON(qcom_iommu != dev_iommu_priv_get(dev))) { - put_device(&iommu_pdev->dev); + if (WARN_ON(qcom_iommu != dev_iommu_priv_get(dev))) return -EINVAL; - } } return iommu_fwspec_add_ids(dev, &asid, 1); diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index f1fb27681b0bdc..f0cc2c3d9c5d29 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -572,8 +572,13 @@ static int iova_reserve_iommu_regions(struct device *dev, if (region->type == IOMMU_RESV_SW_MSI) continue; - lo = iova_pfn(iovad, region->start); - hi = iova_pfn(iovad, region->start + region->length - 1); + if (region->type == IOMMU_RESV_TRANSLATED) { + lo = iova_pfn(iovad, region->dva); + hi = iova_pfn(iovad, region->dva + region->length - 1); + } else { + lo = iova_pfn(iovad, region->start); + hi = iova_pfn(iovad, region->start + region->length - 1); + } reserve_iova(iovad, lo, hi); if (region->type == IOMMU_RESV_MSI) diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index b6edd178fe25e7..ce9e935cb84c3d 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1446,17 +1446,14 @@ static int exynos_iommu_of_xlate(struct device *dev, return -ENODEV; data = platform_get_drvdata(sysmmu); - if (!data) { - put_device(&sysmmu->dev); + put_device(&sysmmu->dev); + if (!data) return -ENODEV; - } if (!owner) { owner = kzalloc(sizeof(*owner), GFP_KERNEL); - if (!owner) { - put_device(&sysmmu->dev); + if (!owner) return -ENOMEM; - } INIT_LIST_HEAD(&owner->controllers); mutex_init(&owner->rpm_lock); diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig index f2f538c7065032..17a91f881b2e9b 100644 --- a/drivers/iommu/intel/Kconfig +++ b/drivers/iommu/intel/Kconfig @@ -66,7 +66,7 @@ config INTEL_IOMMU_DEFAULT_ON config INTEL_IOMMU_FLOPPY_WA def_bool y - depends on X86 + depends on X86 && BLK_DEV_FD help Floppy disk drivers are known to bypass DMA API calls thereby failing to work when IOMMU is enabled. This diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index e236c7ec221f4b..49e83c8566a32f 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1722,10 +1722,12 @@ static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8 } did = context_domain_id(context); - context_clear_entry(context); + context_clear_present(context); __iommu_flush_cache(iommu, context, sizeof(*context)); spin_unlock(&iommu->lock); intel_context_flush_no_pasid(info, context, did); + context_clear_entry(context); + __iommu_flush_cache(iommu, context, sizeof(*context)); } int __domain_setup_first_level(struct intel_iommu *iommu, struct device *dev, diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 3056583d7f56b2..9198ac7f6bbab2 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -969,7 +969,26 @@ static inline unsigned long lvl_to_nr_pages(unsigned int lvl) static inline void context_set_present(struct context_entry *context) { - context->lo |= 1; + u64 val; + + dma_wmb(); + val = READ_ONCE(context->lo) | 1; + WRITE_ONCE(context->lo, val); +} + +/* + * Clear the Present (P) bit (bit 0) of a context table entry. This initiates + * the transition of the entry's ownership from hardware to software. The + * caller is responsible for fulfilling the invalidation handshake recommended + * by the VT-d spec, Section 6.5.3.3 (Guidance to Software for Invalidations). + */ +static inline void context_clear_present(struct context_entry *context) +{ + u64 val; + + val = READ_ONCE(context->lo) & GENMASK_ULL(63, 1); + WRITE_ONCE(context->lo, val); + dma_wmb(); } static inline void context_set_fault_enable(struct context_entry *context) @@ -1097,7 +1116,7 @@ static inline void qi_desc_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, struct qi_desc *desc) { u8 dw = 0, dr = 0; - int ih = 0; + int ih = addr & 1; if (cap_write_drain(iommu->cap)) dw = 1; diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 4f9b01dc91e86f..8bcbfe3d9c7221 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -1303,17 +1303,17 @@ static struct irq_chip intel_ir_chip = { * irq_enter(); * handle_edge_irq() * irq_chip_ack_parent() - * irq_move_irq(); // No EOI + * intel_ack_posted_msi_irq(); // No EOI * handle_irq_event() * driver_handler() * handle_edge_irq() * irq_chip_ack_parent() - * irq_move_irq(); // No EOI + * intel_ack_posted_msi_irq(); // No EOI * handle_irq_event() * driver_handler() * handle_edge_irq() * irq_chip_ack_parent() - * irq_move_irq(); // No EOI + * intel_ack_posted_msi_irq(); // No EOI * handle_irq_event() * driver_handler() * apic_eoi() @@ -1322,7 +1322,7 @@ static struct irq_chip intel_ir_chip = { */ static struct irq_chip intel_ir_chip_post_msi = { .name = "INTEL-IR-POST", - .irq_ack = irq_move_irq, + .irq_ack = intel_ack_posted_msi_irq, .irq_set_affinity = intel_ir_set_affinity, .irq_compose_msi_msg = intel_ir_compose_msi_msg, .irq_set_vcpu_affinity = intel_ir_set_vcpu_affinity, diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 52f678975da745..d13099a6cb9c3e 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -153,6 +153,9 @@ static struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid) if (!entries) return NULL; + if (!ecap_coherent(info->iommu->ecap)) + clflush_cache_range(entries, VTD_PAGE_SIZE); + /* * The pasid directory table entry won't be freed after * allocation. No worry about the race with free and @@ -165,10 +168,8 @@ static struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid) iommu_free_pages(entries); goto retry; } - if (!ecap_coherent(info->iommu->ecap)) { - clflush_cache_range(entries, VTD_PAGE_SIZE); + if (!ecap_coherent(info->iommu->ecap)) clflush_cache_range(&dir[dir_index].val, sizeof(*dir)); - } } return &entries[index]; @@ -272,7 +273,7 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev, did = pasid_get_domain_id(pte); pgtt = pasid_pte_get_pgtt(pte); - intel_pasid_clear_entry(dev, pasid, fault_ignore); + pasid_clear_present(pte); spin_unlock(&iommu->lock); if (!ecap_coherent(iommu->ecap)) @@ -286,6 +287,10 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev, iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH); devtlb_invalidation_with_pasid(iommu, dev, pasid); + intel_pasid_clear_entry(dev, pasid, fault_ignore); + if (!ecap_coherent(iommu->ecap)) + clflush_cache_range(pte, sizeof(*pte)); + if (!fault_ignore) intel_iommu_drain_pasid_prq(dev, pasid); } @@ -1023,7 +1028,7 @@ static int device_pasid_table_setup(struct device *dev, u8 bus, u8 devfn) } if (context_copied(iommu, bus, devfn)) { - context_clear_entry(context); + context_clear_present(context); __iommu_flush_cache(iommu, context, sizeof(*context)); /* @@ -1043,6 +1048,9 @@ static int device_pasid_table_setup(struct device *dev, u8 bus, u8 devfn) iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); devtlb_invalidation_with_pasid(iommu, dev, IOMMU_NO_PASID); + context_clear_entry(context); + __iommu_flush_cache(iommu, context, sizeof(*context)); + /* * At this point, the device is supposed to finish reset at * its driver probe stage, so no in-flight DMA will exist, diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index a771a77d4239c4..637373995be803 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -233,9 +233,23 @@ static inline void pasid_set_wpe(struct pasid_entry *pe) */ static inline void pasid_set_present(struct pasid_entry *pe) { + dma_wmb(); pasid_set_bits(&pe->val[0], 1 << 0, 1); } +/* + * Clear the Present (P) bit (bit 0) of a scalable-mode PASID table entry. + * This initiates the transition of the entry's ownership from hardware + * to software. The caller is responsible for fulfilling the invalidation + * handshake recommended by the VT-d spec, Section 6.5.3.3 (Guidance to + * Software for Invalidations). + */ +static inline void pasid_clear_present(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[0], 1 << 0, 0); + dma_wmb(); +} + /* * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID * entry. diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 7e8e2216c294a9..040f5c4672564c 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -639,7 +639,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, pte = READ_ONCE(*ptep); if (!pte) { WARN_ON(!(data->iop.cfg.quirks & IO_PGTABLE_QUIRK_NO_WARN)); - return -ENOENT; + return 0; } /* If the size matches this level, we're in the right place */ diff --git a/drivers/iommu/io-pgtable-dart.c b/drivers/iommu/io-pgtable-dart.c index 54d287cc0dd1b8..2334a2ea04bb3a 100644 --- a/drivers/iommu/io-pgtable-dart.c +++ b/drivers/iommu/io-pgtable-dart.c @@ -435,7 +435,7 @@ apple_dart_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie) iommu_alloc_pages_sz(GFP_KERNEL, DART_GRANULE(data)); if (!data->pgd[i]) goto out_free_data; - cfg->apple_dart_cfg.ttbr[i] = virt_to_phys(data->pgd[i]); + cfg->apple_dart_cfg.ttbr[i] = data->pgd[i]; } return &data->iop; diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index 1a51cfd82808df..e1e63c2be82b2a 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -3,6 +3,7 @@ * Helpers for IOMMU drivers implementing SVA */ #include +#include #include #include #include @@ -10,6 +11,8 @@ #include "iommu-priv.h" static DEFINE_MUTEX(iommu_sva_lock); +static bool iommu_sva_present; +static LIST_HEAD(iommu_sva_mms); static struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm); @@ -42,6 +45,7 @@ static struct iommu_mm_data *iommu_alloc_mm_data(struct mm_struct *mm, struct de return ERR_PTR(-ENOSPC); } iommu_mm->pasid = pasid; + iommu_mm->mm = mm; INIT_LIST_HEAD(&iommu_mm->sva_domains); /* * Make sure the write to mm->iommu_mm is not reordered in front of @@ -132,8 +136,13 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm if (ret) goto out_free_domain; domain->users = 1; - list_add(&domain->next, &mm->iommu_mm->sva_domains); + if (list_empty(&iommu_mm->sva_domains)) { + if (list_empty(&iommu_sva_mms)) + iommu_sva_present = true; + list_add(&iommu_mm->mm_list_elm, &iommu_sva_mms); + } + list_add(&domain->next, &iommu_mm->sva_domains); out: refcount_set(&handle->users, 1); mutex_unlock(&iommu_sva_lock); @@ -175,6 +184,13 @@ void iommu_sva_unbind_device(struct iommu_sva *handle) list_del(&domain->next); iommu_domain_free(domain); } + + if (list_empty(&iommu_mm->sva_domains)) { + list_del(&iommu_mm->mm_list_elm); + if (list_empty(&iommu_sva_mms)) + iommu_sva_present = false; + } + mutex_unlock(&iommu_sva_lock); kfree(handle); } @@ -312,3 +328,15 @@ static struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, return domain; } + +void iommu_sva_invalidate_kva_range(unsigned long start, unsigned long end) +{ + struct iommu_mm_data *iommu_mm; + + guard(mutex)(&iommu_sva_lock); + if (!iommu_sva_present) + return; + + list_for_each_entry(iommu_mm, &iommu_sva_mms, mm_list_elm) + mmu_notifier_arch_invalidate_secondary_tlbs(iommu_mm->mm, start, end); +} diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 59244c744eabd2..06e5e7d6d53897 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -90,6 +90,7 @@ static const char * const iommu_group_resv_type_string[] = { [IOMMU_RESV_RESERVED] = "reserved", [IOMMU_RESV_MSI] = "msi", [IOMMU_RESV_SW_MSI] = "msi", + [IOMMU_RESV_TRANSLATED] = "translated", }; #define IOMMU_CMD_LINE_DMA_API BIT(0) @@ -132,8 +133,8 @@ static void __iommu_group_set_domain_nofail(struct iommu_group *group, static int iommu_setup_default_domain(struct iommu_group *group, int target_type); -static int iommu_create_device_direct_mappings(struct iommu_domain *domain, - struct device *dev); +static int iommu_create_device_fw_mappings(struct iommu_domain *domain, + struct device *dev); static ssize_t iommu_group_store_type(struct iommu_group *group, const char *buf, size_t count); static struct group_device *iommu_group_alloc_device(struct iommu_group *group, @@ -626,7 +627,7 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list list_add_tail(&gdev->list, &group->devices); WARN_ON(group->default_domain && !group->domain); if (group->default_domain) - iommu_create_device_direct_mappings(group->default_domain, dev); + iommu_create_device_fw_mappings(group->default_domain, dev); if (group->domain) { ret = __iommu_device_set_domain(group, dev, group->domain, 0); if (ret) @@ -1154,8 +1155,8 @@ int iommu_group_set_name(struct iommu_group *group, const char *name) } EXPORT_SYMBOL_GPL(iommu_group_set_name); -static int iommu_create_device_direct_mappings(struct iommu_domain *domain, - struct device *dev) +static int iommu_create_device_fw_mappings(struct iommu_domain *domain, + struct device *dev) { struct iommu_resv_region *entry; struct list_head mappings; @@ -1172,27 +1173,35 @@ static int iommu_create_device_direct_mappings(struct iommu_domain *domain, /* We need to consider overlapping regions for different devices */ list_for_each_entry(entry, &mappings, list) { - dma_addr_t start, end, addr; + dma_addr_t start, end, addr, iova; size_t map_size = 0; if (entry->type == IOMMU_RESV_DIRECT) dev->iommu->require_direct = 1; + if (entry->type == IOMMU_RESV_TRANSLATED) + dev->iommu->require_translated = 1; if ((entry->type != IOMMU_RESV_DIRECT && - entry->type != IOMMU_RESV_DIRECT_RELAXABLE) || + entry->type != IOMMU_RESV_DIRECT_RELAXABLE && + entry->type != IOMMU_RESV_TRANSLATED) || !iommu_is_dma_domain(domain)) continue; start = ALIGN(entry->start, pg_size); end = ALIGN(entry->start + entry->length, pg_size); - for (addr = start; addr <= end; addr += pg_size) { + if (entry->type == IOMMU_RESV_TRANSLATED) + iova = ALIGN(entry->dva, pg_size); + else + iova = start; + + for (addr = start; addr <= end; addr += pg_size, iova += pg_size) { phys_addr_t phys_addr; if (addr == end) goto map_end; - phys_addr = iommu_iova_to_phys(domain, addr); + phys_addr = iommu_iova_to_phys(domain, iova); if (!phys_addr) { map_size += pg_size; continue; @@ -1200,7 +1209,7 @@ static int iommu_create_device_direct_mappings(struct iommu_domain *domain, map_end: if (map_size) { - ret = iommu_map(domain, addr - map_size, + ret = iommu_map(domain, iova - map_size, addr - map_size, map_size, entry->prot, GFP_KERNEL); if (ret) @@ -2302,6 +2311,19 @@ static int __iommu_device_set_domain(struct iommu_group *group, "Firmware has requested this device have a 1:1 IOMMU mapping, rejecting configuring the device without a 1:1 mapping. Contact your platform vendor.\n"); return -EINVAL; } + /* + * If the device requires IOMMU_RESV_TRANSLATED then we cannot allow + * the identy or blocking domain to be attached as it does not contain + * the required translated mapping. + */ + if (dev->iommu->require_translated && + (new_domain->type == IOMMU_DOMAIN_IDENTITY || + new_domain->type == IOMMU_DOMAIN_BLOCKED || + new_domain == group->blocking_domain)) { + dev_warn(dev, + "Firmware has requested this device have a translated IOMMU mapping, rejecting configuring the device without a translated mapping. Contact your platform vendor.\n"); + return -EINVAL; + } if (dev->iommu->attach_deferred) { if (new_domain == group->default_domain) @@ -2841,10 +2863,11 @@ void iommu_put_resv_regions(struct device *dev, struct list_head *list) } EXPORT_SYMBOL(iommu_put_resv_regions); -struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start, - size_t length, int prot, - enum iommu_resv_type type, - gfp_t gfp) +struct iommu_resv_region *iommu_alloc_resv_region_tr(phys_addr_t start, + dma_addr_t dva_start, + size_t length, int prot, + enum iommu_resv_type type, + gfp_t gfp) { struct iommu_resv_region *region; @@ -2854,11 +2877,25 @@ struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start, INIT_LIST_HEAD(®ion->list); region->start = start; + if (type == IOMMU_RESV_TRANSLATED) + region->dva = dva_start; region->length = length; region->prot = prot; region->type = type; return region; } +EXPORT_SYMBOL_GPL(iommu_alloc_resv_region_tr); + +struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start, + size_t length, int prot, + enum iommu_resv_type type, + gfp_t gfp) +{ + if (type == IOMMU_RESV_TRANSLATED) + return NULL; + + return iommu_alloc_resv_region_tr(start, 0, length, prot, type, gfp); +} EXPORT_SYMBOL_GPL(iommu_alloc_resv_region); void iommu_set_default_passthrough(bool cmd_line) @@ -2983,7 +3020,7 @@ static int iommu_setup_default_domain(struct iommu_group *group, struct iommu_domain *old_dom = group->default_domain; struct group_device *gdev; struct iommu_domain *dom; - bool direct_failed; + bool fw_failed; int req_type; int ret; @@ -3013,10 +3050,10 @@ static int iommu_setup_default_domain(struct iommu_group *group, * mapped before their device is attached, in order to guarantee * continuity with any FW activity */ - direct_failed = false; + fw_failed = false; for_each_group_device(group, gdev) { - if (iommu_create_device_direct_mappings(dom, gdev->dev)) { - direct_failed = true; + if (iommu_create_device_fw_mappings(dom, gdev->dev)) { + fw_failed = true; dev_warn_once( gdev->dev->iommu->iommu_dev->dev, "IOMMU driver was not able to establish FW requested direct mapping."); @@ -3048,9 +3085,9 @@ static int iommu_setup_default_domain(struct iommu_group *group, * trying again after attaching. If this happens it means the device * will not continuously have the IOMMU_RESV_DIRECT map. */ - if (direct_failed) { + if (fw_failed) { for_each_group_device(group, gdev) { - ret = iommu_create_device_direct_mappings(dom, gdev->dev); + ret = iommu_create_device_fw_mappings(dom, gdev->dev); if (ret) goto err_restore_domain; } diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index de178827a078a9..dc0947aaac625a 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -1257,14 +1257,20 @@ static int iommufd_test_add_reserved(struct iommufd_ucmd *ucmd, unsigned int mockpt_id, unsigned long start, size_t length) { + unsigned long last; struct iommufd_ioas *ioas; int rc; + if (!length) + return -EINVAL; + if (check_add_overflow(start, length - 1, &last)) + return -EOVERFLOW; + ioas = iommufd_get_ioas(ucmd->ictx, mockpt_id); if (IS_ERR(ioas)) return PTR_ERR(ioas); down_write(&ioas->iopt.iova_rwsem); - rc = iopt_reserve_iova(&ioas->iopt, start, start + length - 1, NULL); + rc = iopt_reserve_iova(&ioas->iopt, start, last, NULL); up_write(&ioas->iopt.iova_rwsem); iommufd_put_object(ucmd->ictx, &ioas->obj); return rc; diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index ffa892f6571406..02a2a55ffa0a08 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -720,6 +720,8 @@ static int ipmmu_init_platform_device(struct device *dev, dev_iommu_priv_set(dev, platform_get_drvdata(ipmmu_pdev)); + put_device(&ipmmu_pdev->dev); + return 0; } diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 0e0285348d2b8e..64ce041238fd35 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -974,6 +974,8 @@ static int mtk_iommu_of_xlate(struct device *dev, return -EINVAL; dev_iommu_priv_set(dev, platform_get_drvdata(m4updev)); + + put_device(&m4updev->dev); } return iommu_fwspec_add_ids(dev, args->args, 1); @@ -1211,16 +1213,19 @@ static int mtk_iommu_mm_dts_parse(struct device *dev, struct component_match **m } component_match_add(dev, match, component_compare_dev, &plarbdev->dev); - platform_device_put(plarbdev); } - if (!frst_avail_smicomm_node) - return -EINVAL; + if (!frst_avail_smicomm_node) { + ret = -EINVAL; + goto err_larbdev_put; + } pcommdev = of_find_device_by_node(frst_avail_smicomm_node); of_node_put(frst_avail_smicomm_node); - if (!pcommdev) - return -ENODEV; + if (!pcommdev) { + ret = -ENODEV; + goto err_larbdev_put; + } data->smicomm_dev = &pcommdev->dev; link = device_link_add(data->smicomm_dev, dev, @@ -1228,7 +1233,8 @@ static int mtk_iommu_mm_dts_parse(struct device *dev, struct component_match **m platform_device_put(pcommdev); if (!link) { dev_err(dev, "Unable to link %s.\n", dev_name(data->smicomm_dev)); - return -EINVAL; + ret = -EINVAL; + goto err_larbdev_put; } return 0; @@ -1400,8 +1406,12 @@ static int mtk_iommu_probe(struct platform_device *pdev) iommu_device_sysfs_remove(&data->iommu); out_list_del: list_del(&data->list); - if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) + if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) { device_link_remove(data->smicomm_dev, dev); + + for (i = 0; i < MTK_LARB_NR_MAX; i++) + put_device(data->larb_imu[i].dev); + } out_runtime_disable: pm_runtime_disable(dev); return ret; @@ -1421,6 +1431,9 @@ static void mtk_iommu_remove(struct platform_device *pdev) if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) { device_link_remove(data->smicomm_dev, &pdev->dev); component_master_del(&pdev->dev, &mtk_iommu_com_ops); + + for (i = 0; i < MTK_LARB_NR_MAX; i++) + put_device(data->larb_imu[i].dev); } pm_runtime_disable(&pdev->dev); for (i = 0; i < data->plat_data->banks_num; i++) { diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 10cc0b1197e801..44b965a2db923b 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -435,6 +435,8 @@ static int mtk_iommu_v1_create_mapping(struct device *dev, return -EINVAL; dev_iommu_priv_set(dev, platform_get_drvdata(m4updev)); + + put_device(&m4updev->dev); } ret = iommu_fwspec_add_ids(dev, args->args, 1); @@ -646,8 +648,10 @@ static int mtk_iommu_v1_probe(struct platform_device *pdev) struct platform_device *plarbdev; larbnode = of_parse_phandle(dev->of_node, "mediatek,larbs", i); - if (!larbnode) - return -EINVAL; + if (!larbnode) { + ret = -EINVAL; + goto out_put_larbs; + } if (!of_device_is_available(larbnode)) { of_node_put(larbnode); @@ -657,11 +661,14 @@ static int mtk_iommu_v1_probe(struct platform_device *pdev) plarbdev = of_find_device_by_node(larbnode); if (!plarbdev) { of_node_put(larbnode); - return -ENODEV; + ret = -ENODEV; + goto out_put_larbs; } if (!plarbdev->dev.driver) { of_node_put(larbnode); - return -EPROBE_DEFER; + put_device(&plarbdev->dev); + ret = -EPROBE_DEFER; + goto out_put_larbs; } data->larb_imu[i].dev = &plarbdev->dev; @@ -673,7 +680,7 @@ static int mtk_iommu_v1_probe(struct platform_device *pdev) ret = mtk_iommu_v1_hw_init(data); if (ret) - return ret; + goto out_put_larbs; ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL, dev_name(&pdev->dev)); @@ -695,12 +702,17 @@ static int mtk_iommu_v1_probe(struct platform_device *pdev) iommu_device_sysfs_remove(&data->iommu); out_clk_unprepare: clk_disable_unprepare(data->bclk); +out_put_larbs: + for (i = 0; i < MTK_LARB_NR_MAX; i++) + put_device(data->larb_imu[i].dev); + return ret; } static void mtk_iommu_v1_remove(struct platform_device *pdev) { struct mtk_iommu_v1_data *data = platform_get_drvdata(pdev); + int i; iommu_device_sysfs_remove(&data->iommu); iommu_device_unregister(&data->iommu); @@ -708,6 +720,9 @@ static void mtk_iommu_v1_remove(struct platform_device *pdev) clk_disable_unprepare(data->bclk); devm_free_irq(&pdev->dev, data->irq, data); component_master_del(&pdev->dev, &mtk_iommu_v1_com_ops); + + for (i = 0; i < MTK_LARB_NR_MAX; i++) + put_device(data->larb_imu[i].dev); } static int __maybe_unused mtk_iommu_v1_suspend(struct device *dev) diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index 6b989a62def20e..69377addd6cebb 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -147,6 +147,8 @@ int of_iommu_configure(struct device *dev, struct device_node *master_np, of_pci_check_device_ats(dev, master_np); } else { err = of_iommu_configure_device(master_np, dev, id); + if (err == -EPROBE_DEFER) + iommu_fwspec_free(dev); } if (err && dev_iommu_present) @@ -187,9 +189,7 @@ iommu_resv_region_get_type(struct device *dev, if (start == phys->start && end == phys->end) return IOMMU_RESV_DIRECT; - dev_warn(dev, "treating non-direct mapping [%pr] -> [%pap-%pap] as reservation\n", phys, - &start, &end); - return IOMMU_RESV_RESERVED; + return IOMMU_RESV_TRANSLATED; } /** @@ -260,8 +260,13 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list) } type = iommu_resv_region_get_type(dev, &phys, iova, length); - region = iommu_alloc_resv_region(iova, length, prot, type, + if (type == IOMMU_RESV_TRANSLATED) + region = iommu_alloc_resv_region_tr(phys.start, iova, length, prot, type, + GFP_KERNEL); + else + region = iommu_alloc_resv_region(iova, length, prot, type, GFP_KERNEL); + if (region) list_add_tail(®ion->list, list); } diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 5c6f5943f44b1f..c0315c86cd187a 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1675,6 +1675,7 @@ static struct iommu_device *omap_iommu_probe_device(struct device *dev) } oiommu = platform_get_drvdata(pdev); + put_device(&pdev->dev); if (!oiommu) { of_node_put(np); kfree(arch_data); @@ -1682,7 +1683,6 @@ static struct iommu_device *omap_iommu_probe_device(struct device *dev) } tmp->iommu_dev = oiommu; - tmp->dev = &pdev->dev; of_node_put(np); } diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h index 27697109ec79a5..50b39be61abc7d 100644 --- a/drivers/iommu/omap-iommu.h +++ b/drivers/iommu/omap-iommu.h @@ -88,7 +88,6 @@ struct omap_iommu { /** * struct omap_iommu_arch_data - omap iommu private data * @iommu_dev: handle of the OMAP iommu device - * @dev: handle of the iommu device * * This is an omap iommu private data object, which binds an iommu user * to its iommu device. This object should be placed at the iommu user's @@ -97,7 +96,6 @@ struct omap_iommu { */ struct omap_iommu_arch_data { struct omap_iommu *iommu_dev; - struct device *dev; }; struct cr_regs { diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c index de10b569d9a940..6306570d57db4f 100644 --- a/drivers/iommu/sun50i-iommu.c +++ b/drivers/iommu/sun50i-iommu.c @@ -839,6 +839,8 @@ static int sun50i_iommu_of_xlate(struct device *dev, dev_iommu_priv_set(dev, platform_get_drvdata(iommu_pdev)); + put_device(&iommu_pdev->dev); + return iommu_fwspec_add_ids(dev, &id, 1); } diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 36cdd5fbab0779..f6f26a07282083 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -830,10 +830,9 @@ static struct tegra_smmu *tegra_smmu_find(struct device_node *np) return NULL; mc = platform_get_drvdata(pdev); - if (!mc) { - put_device(&pdev->dev); + put_device(&pdev->dev); + if (!mc) return NULL; - } return mc->smmu; } diff --git a/drivers/irqchip/irq-apple-aic.c b/drivers/irqchip/irq-apple-aic.c index 032d66dceb8ec4..ad04d1fcc5e7dc 100644 --- a/drivers/irqchip/irq-apple-aic.c +++ b/drivers/irqchip/irq-apple-aic.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include #include @@ -134,8 +135,15 @@ #define AIC2_IRQ_CFG 0x2000 +/* + * AIC v3 registers (MMIO) + */ + +#define AIC3_IRQ_CFG 0x10000 + /* * AIC2 registers are laid out like this, starting at AIC2_IRQ_CFG: + * AIC3 registers use the same layout but start at AIC3_IRQ_CFG: * * Repeat for each die: * IRQ_CFG: u32 * MAX_IRQS @@ -293,6 +301,15 @@ static const struct aic_info aic2_info __initconst = { .local_fast_ipi = true, }; +static const struct aic_info aic3_info __initconst = { + .version = 3, + + .irq_cfg = AIC3_IRQ_CFG, + + .fast_ipi = true, + .local_fast_ipi = true, +}; + static const struct of_device_id aic_info_match[] = { { .compatible = "apple,t8103-aic", @@ -310,6 +327,10 @@ static const struct of_device_id aic_info_match[] = { .compatible = "apple,aic2", .data = &aic2_info, }, + { + .compatible = "apple,t8122-aic3", + .data = &aic3_info, + }, {} }; @@ -624,7 +645,7 @@ static int aic_irq_domain_map(struct irq_domain *id, unsigned int irq, u32 type = FIELD_GET(AIC_EVENT_TYPE, hw); struct irq_chip *chip = &aic_chip; - if (ic->info.version == 2) + if (ic->info.version == 2 || ic->info.version == 3) chip = &aic2_chip; if (type == AIC_EVENT_TYPE_IRQ) { @@ -974,6 +995,7 @@ static int __init aic_of_ic_init(struct device_node *node, struct device_node *p break; } + case 3: case 2: { u32 info1, info3; @@ -1048,7 +1070,7 @@ static int __init aic_of_ic_init(struct device_node *node, struct device_node *p off += irqc->info.die_stride; } - if (irqc->info.version == 2) { + if (irqc->info.version == 2 || irqc->info.version == 3) { u32 config = aic_ic_read(irqc, AIC2_CONFIG); config |= AIC2_CONFIG_ENABLE; @@ -1099,3 +1121,4 @@ static int __init aic_of_ic_init(struct device_node *node, struct device_node *p IRQCHIP_DECLARE(apple_aic, "apple,aic", aic_of_ic_init); IRQCHIP_DECLARE(apple_aic2, "apple,aic2", aic_of_ic_init); +IRQCHIP_DECLARE(apple_aic3, "apple,t8122-aic3", aic_of_ic_init); diff --git a/drivers/irqchip/irq-bcm2712-mip.c b/drivers/irqchip/irq-bcm2712-mip.c index 9bd7bc0bf6d597..4761974ad650a9 100644 --- a/drivers/irqchip/irq-bcm2712-mip.c +++ b/drivers/irqchip/irq-bcm2712-mip.c @@ -232,17 +232,12 @@ static int mip_parse_dt(struct mip_priv *mip, struct device_node *np) return ret; } -static int __init mip_of_msi_init(struct device_node *node, struct device_node *parent) +static int mip_msi_probe(struct platform_device *pdev, struct device_node *parent) { - struct platform_device *pdev; + struct device_node *node = pdev->dev.of_node; struct mip_priv *mip; int ret; - pdev = of_find_device_by_node(node); - of_node_put(node); - if (!pdev) - return -EPROBE_DEFER; - mip = kzalloc(sizeof(*mip), GFP_KERNEL); if (!mip) return -ENOMEM; @@ -285,7 +280,7 @@ static int __init mip_of_msi_init(struct device_node *node, struct device_node * } IRQCHIP_PLATFORM_DRIVER_BEGIN(mip_msi) -IRQCHIP_MATCH("brcm,bcm2712-mip", mip_of_msi_init) +IRQCHIP_MATCH("brcm,bcm2712-mip", mip_msi_probe) IRQCHIP_PLATFORM_DRIVER_END(mip_msi) MODULE_DESCRIPTION("Broadcom BCM2712 MSI-X interrupt controller"); MODULE_AUTHOR("Phil Elwell "); diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c index 04fac0cc857fd0..821b288587cab4 100644 --- a/drivers/irqchip/irq-bcm7038-l1.c +++ b/drivers/irqchip/irq-bcm7038-l1.c @@ -219,9 +219,8 @@ static int bcm7038_l1_set_affinity(struct irq_data *d, } #endif -static int __init bcm7038_l1_init_one(struct device_node *dn, - unsigned int idx, - struct bcm7038_l1_chip *intc) +static int bcm7038_l1_init_one(struct device_node *dn, unsigned int idx, + struct bcm7038_l1_chip *intc) { struct resource res; resource_size_t sz; @@ -395,9 +394,9 @@ static const struct irq_domain_ops bcm7038_l1_domain_ops = { .map = bcm7038_l1_map, }; -static int __init bcm7038_l1_of_init(struct device_node *dn, - struct device_node *parent) +static int bcm7038_l1_probe(struct platform_device *pdev, struct device_node *parent) { + struct device_node *dn = pdev->dev.of_node; struct bcm7038_l1_chip *intc; int idx, ret; @@ -455,7 +454,7 @@ static int __init bcm7038_l1_of_init(struct device_node *dn, } IRQCHIP_PLATFORM_DRIVER_BEGIN(bcm7038_l1) -IRQCHIP_MATCH("brcm,bcm7038-l1-intc", bcm7038_l1_of_init) +IRQCHIP_MATCH("brcm,bcm7038-l1-intc", bcm7038_l1_probe) IRQCHIP_PLATFORM_DRIVER_END(bcm7038_l1) MODULE_DESCRIPTION("Broadcom STB 7038-style L1/L2 interrupt controller"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c index ff22c310440181..518c9d4366a55a 100644 --- a/drivers/irqchip/irq-bcm7120-l2.c +++ b/drivers/irqchip/irq-bcm7120-l2.c @@ -143,8 +143,7 @@ static int bcm7120_l2_intc_init_one(struct device_node *dn, return 0; } -static int __init bcm7120_l2_intc_iomap_7120(struct device_node *dn, - struct bcm7120_l2_intc_data *data) +static int bcm7120_l2_intc_iomap_7120(struct device_node *dn, struct bcm7120_l2_intc_data *data) { int ret; @@ -177,8 +176,7 @@ static int __init bcm7120_l2_intc_iomap_7120(struct device_node *dn, return 0; } -static int __init bcm7120_l2_intc_iomap_3380(struct device_node *dn, - struct bcm7120_l2_intc_data *data) +static int bcm7120_l2_intc_iomap_3380(struct device_node *dn, struct bcm7120_l2_intc_data *data) { unsigned int gc_idx; @@ -208,15 +206,14 @@ static int __init bcm7120_l2_intc_iomap_3380(struct device_node *dn, return 0; } -static int __init bcm7120_l2_intc_probe(struct device_node *dn, - struct device_node *parent, +static int bcm7120_l2_intc_probe(struct platform_device *pdev, struct device_node *parent, int (*iomap_regs_fn)(struct device_node *, - struct bcm7120_l2_intc_data *), + struct bcm7120_l2_intc_data *), const char *intc_name) { unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN; + struct device_node *dn = pdev->dev.of_node; struct bcm7120_l2_intc_data *data; - struct platform_device *pdev; struct irq_chip_generic *gc; struct irq_chip_type *ct; int ret = 0; @@ -227,14 +224,7 @@ static int __init bcm7120_l2_intc_probe(struct device_node *dn, if (!data) return -ENOMEM; - pdev = of_find_device_by_node(dn); - if (!pdev) { - ret = -ENODEV; - goto out_free_data; - } - data->num_parent_irqs = platform_irq_count(pdev); - put_device(&pdev->dev); if (data->num_parent_irqs <= 0) { pr_err("invalid number of parent interrupts\n"); ret = -ENOMEM; @@ -334,22 +324,19 @@ static int __init bcm7120_l2_intc_probe(struct device_node *dn, if (data->map_base[idx]) iounmap(data->map_base[idx]); } -out_free_data: kfree(data); return ret; } -static int __init bcm7120_l2_intc_probe_7120(struct device_node *dn, - struct device_node *parent) +static int bcm7120_l2_intc_probe_7120(struct platform_device *pdev, struct device_node *parent) { - return bcm7120_l2_intc_probe(dn, parent, bcm7120_l2_intc_iomap_7120, + return bcm7120_l2_intc_probe(pdev, parent, bcm7120_l2_intc_iomap_7120, "BCM7120 L2"); } -static int __init bcm7120_l2_intc_probe_3380(struct device_node *dn, - struct device_node *parent) +static int bcm7120_l2_intc_probe_3380(struct platform_device *pdev, struct device_node *parent) { - return bcm7120_l2_intc_probe(dn, parent, bcm7120_l2_intc_iomap_3380, + return bcm7120_l2_intc_probe(pdev, parent, bcm7120_l2_intc_iomap_3380, "BCM3380 L2"); } diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c index 1bec5b2cd3f0ed..bb7078d6524f9b 100644 --- a/drivers/irqchip/irq-brcmstb-l2.c +++ b/drivers/irqchip/irq-brcmstb-l2.c @@ -138,13 +138,12 @@ static void brcmstb_l2_intc_resume(struct irq_data *d) irq_reg_writel(gc, ~b->saved_mask, ct->regs.enable); } -static int __init brcmstb_l2_intc_of_init(struct device_node *np, - struct device_node *parent, - const struct brcmstb_intc_init_params - *init_params) +static int brcmstb_l2_intc_probe(struct platform_device *pdev, struct device_node *parent, + const struct brcmstb_intc_init_params *init_params) { unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN; unsigned int set = 0; + struct device_node *np = pdev->dev.of_node; struct brcmstb_l2_intc_data *data; struct irq_chip_type *ct; int ret; @@ -257,23 +256,21 @@ static int __init brcmstb_l2_intc_of_init(struct device_node *np, return ret; } -static int __init brcmstb_l2_edge_intc_of_init(struct device_node *np, - struct device_node *parent) +static int brcmstb_l2_edge_intc_probe(struct platform_device *pdev, struct device_node *parent) { - return brcmstb_l2_intc_of_init(np, parent, &l2_edge_intc_init); + return brcmstb_l2_intc_probe(pdev, parent, &l2_edge_intc_init); } -static int __init brcmstb_l2_lvl_intc_of_init(struct device_node *np, - struct device_node *parent) +static int brcmstb_l2_lvl_intc_probe(struct platform_device *pdev, struct device_node *parent) { - return brcmstb_l2_intc_of_init(np, parent, &l2_lvl_intc_init); + return brcmstb_l2_intc_probe(pdev, parent, &l2_lvl_intc_init); } IRQCHIP_PLATFORM_DRIVER_BEGIN(brcmstb_l2) -IRQCHIP_MATCH("brcm,l2-intc", brcmstb_l2_edge_intc_of_init) -IRQCHIP_MATCH("brcm,hif-spi-l2-intc", brcmstb_l2_edge_intc_of_init) -IRQCHIP_MATCH("brcm,upg-aux-aon-l2-intc", brcmstb_l2_edge_intc_of_init) -IRQCHIP_MATCH("brcm,bcm7271-l2-intc", brcmstb_l2_lvl_intc_of_init) +IRQCHIP_MATCH("brcm,l2-intc", brcmstb_l2_edge_intc_probe) +IRQCHIP_MATCH("brcm,hif-spi-l2-intc", brcmstb_l2_edge_intc_probe) +IRQCHIP_MATCH("brcm,upg-aux-aon-l2-intc", brcmstb_l2_edge_intc_probe) +IRQCHIP_MATCH("brcm,bcm7271-l2-intc", brcmstb_l2_lvl_intc_probe) IRQCHIP_PLATFORM_DRIVER_END(brcmstb_l2) MODULE_DESCRIPTION("Broadcom STB generic L2 interrupt controller"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 467cb78435a9b6..9e020c74be7839 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -709,7 +709,7 @@ static struct its_collection *its_build_mapd_cmd(struct its_node *its, struct its_cmd_block *cmd, struct its_cmd_desc *desc) { - unsigned long itt_addr; + phys_addr_t itt_addr; u8 size = ilog2(desc->its_mapd_cmd.dev->nr_ites); itt_addr = virt_to_phys(desc->its_mapd_cmd.dev->itt); @@ -879,7 +879,7 @@ static struct its_vpe *its_build_vmapp_cmd(struct its_node *its, struct its_cmd_desc *desc) { struct its_vpe *vpe = valid_vpe(its, desc->its_vmapp_cmd.vpe); - unsigned long vpt_addr, vconf_addr; + phys_addr_t vpt_addr, vconf_addr; u64 target; bool alloc; @@ -2477,10 +2477,10 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser, baser->psz = psz; tmp = indirect ? GITS_LVL1_ENTRY_SIZE : esz; - pr_info("ITS@%pa: allocated %d %s @%lx (%s, esz %d, psz %dK, shr %d)\n", + pr_info("ITS@%pa: allocated %d %s @%llx (%s, esz %d, psz %dK, shr %d)\n", &its->phys_base, (int)(PAGE_ORDER_TO_SIZE(order) / (int)tmp), its_base_type_string[type], - (unsigned long)virt_to_phys(base), + (u64)virt_to_phys(base), indirect ? "indirect" : "flat", (int)esz, psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT); diff --git a/drivers/irqchip/irq-gic-v5-its.c b/drivers/irqchip/irq-gic-v5-its.c index 554485f0be1fbf..8e22134b9f4867 100644 --- a/drivers/irqchip/irq-gic-v5-its.c +++ b/drivers/irqchip/irq-gic-v5-its.c @@ -849,7 +849,7 @@ static int gicv5_its_map_event(struct gicv5_its_dev *its_dev, u16 event_id, u32 itte = gicv5_its_device_get_itte_ref(its_dev, event_id); - if (FIELD_GET(GICV5_ITTL2E_VALID, *itte)) + if (FIELD_GET(GICV5_ITTL2E_VALID, le64_to_cpu(*itte))) return -EEXIST; itt_entry = FIELD_PREP(GICV5_ITTL2E_LPI_ID, lpi) | diff --git a/drivers/irqchip/irq-imx-mu-msi.c b/drivers/irqchip/irq-imx-mu-msi.c index d2a4e8a61a42b1..c598f2f52fc6f3 100644 --- a/drivers/irqchip/irq-imx-mu-msi.c +++ b/drivers/irqchip/irq-imx-mu-msi.c @@ -296,11 +296,9 @@ static const struct imx_mu_dcfg imx_mu_cfg_imx8ulp = { }, }; -static int __init imx_mu_of_init(struct device_node *dn, - struct device_node *parent, - const struct imx_mu_dcfg *cfg) +static int imx_mu_probe(struct platform_device *pdev, struct device_node *parent, + const struct imx_mu_dcfg *cfg) { - struct platform_device *pdev = of_find_device_by_node(dn); struct device_link *pd_link_a; struct device_link *pd_link_b; struct imx_mu_msi *msi_data; @@ -416,31 +414,27 @@ static const struct dev_pm_ops imx_mu_pm_ops = { imx_mu_runtime_resume, NULL) }; -static int __init imx_mu_imx7ulp_of_init(struct device_node *dn, - struct device_node *parent) +static int imx_mu_imx7ulp_probe(struct platform_device *pdev, struct device_node *parent) { - return imx_mu_of_init(dn, parent, &imx_mu_cfg_imx7ulp); + return imx_mu_probe(pdev, parent, &imx_mu_cfg_imx7ulp); } -static int __init imx_mu_imx6sx_of_init(struct device_node *dn, - struct device_node *parent) +static int imx_mu_imx6sx_probe(struct platform_device *pdev, struct device_node *parent) { - return imx_mu_of_init(dn, parent, &imx_mu_cfg_imx6sx); + return imx_mu_probe(pdev, parent, &imx_mu_cfg_imx6sx); } -static int __init imx_mu_imx8ulp_of_init(struct device_node *dn, - struct device_node *parent) +static int imx_mu_imx8ulp_probe(struct platform_device *pdev, struct device_node *parent) { - return imx_mu_of_init(dn, parent, &imx_mu_cfg_imx8ulp); + return imx_mu_probe(pdev, parent, &imx_mu_cfg_imx8ulp); } IRQCHIP_PLATFORM_DRIVER_BEGIN(imx_mu_msi) -IRQCHIP_MATCH("fsl,imx7ulp-mu-msi", imx_mu_imx7ulp_of_init) -IRQCHIP_MATCH("fsl,imx6sx-mu-msi", imx_mu_imx6sx_of_init) -IRQCHIP_MATCH("fsl,imx8ulp-mu-msi", imx_mu_imx8ulp_of_init) +IRQCHIP_MATCH("fsl,imx7ulp-mu-msi", imx_mu_imx7ulp_probe) +IRQCHIP_MATCH("fsl,imx6sx-mu-msi", imx_mu_imx6sx_probe) +IRQCHIP_MATCH("fsl,imx8ulp-mu-msi", imx_mu_imx8ulp_probe) IRQCHIP_PLATFORM_DRIVER_END(imx_mu_msi, .pm = &imx_mu_pm_ops) - MODULE_AUTHOR("Frank Li "); MODULE_DESCRIPTION("Freescale MU MSI controller driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/irqchip/irq-mchp-eic.c b/drivers/irqchip/irq-mchp-eic.c index 516a3a0e359cc3..979bb86929f8eb 100644 --- a/drivers/irqchip/irq-mchp-eic.c +++ b/drivers/irqchip/irq-mchp-eic.c @@ -166,7 +166,7 @@ static int mchp_eic_domain_alloc(struct irq_domain *domain, unsigned int virq, ret = irq_domain_translate_twocell(domain, fwspec, &hwirq, &type); if (ret || hwirq >= MCHP_EIC_NIRQ) - return ret; + return ret ?: -EINVAL; switch (type) { case IRQ_TYPE_EDGE_RISING: @@ -199,8 +199,9 @@ static const struct irq_domain_ops mchp_eic_domain_ops = { .free = irq_domain_free_irqs_common, }; -static int mchp_eic_init(struct device_node *node, struct device_node *parent) +static int mchp_eic_probe(struct platform_device *pdev, struct device_node *parent) { + struct device_node *node = pdev->dev.of_node; struct irq_domain *parent_domain = NULL; int ret, i; @@ -273,7 +274,7 @@ static int mchp_eic_init(struct device_node *node, struct device_node *parent) } IRQCHIP_PLATFORM_DRIVER_BEGIN(mchp_eic) -IRQCHIP_MATCH("microchip,sama7g5-eic", mchp_eic_init) +IRQCHIP_MATCH("microchip,sama7g5-eic", mchp_eic_probe) IRQCHIP_PLATFORM_DRIVER_END(mchp_eic) MODULE_DESCRIPTION("Microchip External Interrupt Controller"); diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c index 7d177626d64ba4..09ebf1d9c21b03 100644 --- a/drivers/irqchip/irq-meson-gpio.c +++ b/drivers/irqchip/irq-meson-gpio.c @@ -572,8 +572,9 @@ static int meson_gpio_irq_parse_dt(struct device_node *node, struct meson_gpio_i return 0; } -static int meson_gpio_irq_of_init(struct device_node *node, struct device_node *parent) +static int meson_gpio_irq_probe(struct platform_device *pdev, struct device_node *parent) { + struct device_node *node = pdev->dev.of_node; struct irq_domain *domain, *parent_domain; struct meson_gpio_irq_controller *ctl; int ret; @@ -630,7 +631,7 @@ static int meson_gpio_irq_of_init(struct device_node *node, struct device_node * } IRQCHIP_PLATFORM_DRIVER_BEGIN(meson_gpio_intc) -IRQCHIP_MATCH("amlogic,meson-gpio-intc", meson_gpio_irq_of_init) +IRQCHIP_MATCH("amlogic,meson-gpio-intc", meson_gpio_irq_probe) IRQCHIP_PLATFORM_DRIVER_END(meson_gpio_intc) MODULE_AUTHOR("Jerome Brunet "); diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c index 8d569f7c5a7aaa..83f31ea657b74a 100644 --- a/drivers/irqchip/irq-qcom-mpm.c +++ b/drivers/irqchip/irq-qcom-mpm.c @@ -320,9 +320,9 @@ static bool gic_hwirq_is_mapped(struct mpm_gic_map *maps, int cnt, u32 hwirq) return false; } -static int qcom_mpm_init(struct device_node *np, struct device_node *parent) +static int qcom_mpm_probe(struct platform_device *pdev, struct device_node *parent) { - struct platform_device *pdev = of_find_device_by_node(np); + struct device_node *np = pdev->dev.of_node; struct device *dev = &pdev->dev; struct irq_domain *parent_domain; struct generic_pm_domain *genpd; @@ -478,7 +478,7 @@ static int qcom_mpm_init(struct device_node *np, struct device_node *parent) } IRQCHIP_PLATFORM_DRIVER_BEGIN(qcom_mpm) -IRQCHIP_MATCH("qcom,mpm", qcom_mpm_init) +IRQCHIP_MATCH("qcom,mpm", qcom_mpm_probe) IRQCHIP_PLATFORM_DRIVER_END(qcom_mpm) MODULE_DESCRIPTION("Qualcomm Technologies, Inc. MSM Power Manager"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c index 2a54adeb4cc714..1bf19deb02c4e9 100644 --- a/drivers/irqchip/irq-renesas-rzg2l.c +++ b/drivers/irqchip/irq-renesas-rzg2l.c @@ -8,7 +8,6 @@ */ #include -#include #include #include #include @@ -528,18 +527,15 @@ static int rzg2l_irqc_parse_interrupts(struct rzg2l_irqc_priv *priv, return 0; } -static int rzg2l_irqc_common_init(struct device_node *node, struct device_node *parent, - const struct irq_chip *irq_chip) +static int rzg2l_irqc_common_probe(struct platform_device *pdev, struct device_node *parent, + const struct irq_chip *irq_chip) { - struct platform_device *pdev = of_find_device_by_node(node); - struct device *dev __free(put_device) = pdev ? &pdev->dev : NULL; struct irq_domain *irq_domain, *parent_domain; + struct device_node *node = pdev->dev.of_node; + struct device *dev = &pdev->dev; struct reset_control *resetn; int ret; - if (!pdev) - return -ENODEV; - parent_domain = irq_find_host(parent); if (!parent_domain) return dev_err_probe(dev, -ENODEV, "cannot find parent domain\n"); @@ -583,35 +579,22 @@ static int rzg2l_irqc_common_init(struct device_node *node, struct device_node * register_syscore_ops(&rzg2l_irqc_syscore_ops); - /* - * Prevent the cleanup function from invoking put_device by assigning - * NULL to dev. - * - * make coccicheck will complain about missing put_device calls, but - * those are false positives, as dev will be automatically "put" via - * __free_put_device on the failing path. - * On the successful path we don't actually want to "put" dev. - */ - dev = NULL; - return 0; } -static int __init rzg2l_irqc_init(struct device_node *node, - struct device_node *parent) +static int rzg2l_irqc_probe(struct platform_device *pdev, struct device_node *parent) { - return rzg2l_irqc_common_init(node, parent, &rzg2l_irqc_chip); + return rzg2l_irqc_common_probe(pdev, parent, &rzg2l_irqc_chip); } -static int __init rzfive_irqc_init(struct device_node *node, - struct device_node *parent) +static int rzfive_irqc_probe(struct platform_device *pdev, struct device_node *parent) { - return rzg2l_irqc_common_init(node, parent, &rzfive_irqc_chip); + return rzg2l_irqc_common_probe(pdev, parent, &rzfive_irqc_chip); } IRQCHIP_PLATFORM_DRIVER_BEGIN(rzg2l_irqc) -IRQCHIP_MATCH("renesas,rzg2l-irqc", rzg2l_irqc_init) -IRQCHIP_MATCH("renesas,r9a07g043f-irqc", rzfive_irqc_init) +IRQCHIP_MATCH("renesas,rzg2l-irqc", rzg2l_irqc_probe) +IRQCHIP_MATCH("renesas,r9a07g043f-irqc", rzfive_irqc_probe) IRQCHIP_PLATFORM_DRIVER_END(rzg2l_irqc) MODULE_AUTHOR("Lad Prabhakar "); MODULE_DESCRIPTION("Renesas RZ/G2L IRQC Driver"); diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c index 9018d9c3911e3e..3dab62ededec92 100644 --- a/drivers/irqchip/irq-renesas-rzv2h.c +++ b/drivers/irqchip/irq-renesas-rzv2h.c @@ -89,6 +89,8 @@ #define ICU_RZG3E_TSSEL_MAX_VAL 0x8c #define ICU_RZV2H_TSSEL_MAX_VAL 0x55 +#define field_get(_mask, _reg) (((_reg) & (_mask)) >> (ffs(_mask) - 1)) + /** * struct rzv2h_hw_info - Interrupt Control Unit controller hardware info structure. * @tssel_lut: TINT lookup table @@ -328,6 +330,7 @@ static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type) u32 titsr, titsr_k, titsel_n, tien; struct rzv2h_icu_priv *priv; u32 tssr, tssr_k, tssel_n; + u32 titsr_cur, tssr_cur; unsigned int hwirq; u32 tint, sense; int tint_nr; @@ -376,12 +379,18 @@ static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type) guard(raw_spinlock)(&priv->lock); tssr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TSSR(tssr_k)); + titsr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TITSR(titsr_k)); + + tssr_cur = field_get(ICU_TSSR_TSSEL_MASK(tssel_n, priv->info->field_width), tssr); + titsr_cur = field_get(ICU_TITSR_TITSEL_MASK(titsel_n), titsr); + if (tssr_cur == tint && titsr_cur == sense) + return 0; + tssr &= ~(ICU_TSSR_TSSEL_MASK(tssel_n, priv->info->field_width) | tien); tssr |= ICU_TSSR_TSSEL_PREP(tint, tssel_n, priv->info->field_width); writel_relaxed(tssr, priv->base + priv->info->t_offs + ICU_TSSR(tssr_k)); - titsr = readl_relaxed(priv->base + priv->info->t_offs + ICU_TITSR(titsr_k)); titsr &= ~ICU_TITSR_TITSEL_MASK(titsel_n); titsr |= ICU_TITSR_TITSEL_PREP(sense, titsel_n); @@ -490,29 +499,15 @@ static int rzv2h_icu_parse_interrupts(struct rzv2h_icu_priv *priv, struct device return 0; } -static void rzv2h_icu_put_device(void *data) -{ - put_device(data); -} - -static int rzv2h_icu_init_common(struct device_node *node, struct device_node *parent, - const struct rzv2h_hw_info *hw_info) +static int rzv2h_icu_probe_common(struct platform_device *pdev, struct device_node *parent, + const struct rzv2h_hw_info *hw_info) { struct irq_domain *irq_domain, *parent_domain; + struct device_node *node = pdev->dev.of_node; struct rzv2h_icu_priv *rzv2h_icu_data; - struct platform_device *pdev; struct reset_control *resetn; int ret; - pdev = of_find_device_by_node(node); - if (!pdev) - return -ENODEV; - - ret = devm_add_action_or_reset(&pdev->dev, rzv2h_icu_put_device, - &pdev->dev); - if (ret < 0) - return ret; - parent_domain = irq_find_host(parent); if (!parent_domain) { dev_err(&pdev->dev, "cannot find parent domain\n"); @@ -618,19 +613,19 @@ static const struct rzv2h_hw_info rzv2h_hw_params = { .field_width = 8, }; -static int rzg3e_icu_init(struct device_node *node, struct device_node *parent) +static int rzg3e_icu_probe(struct platform_device *pdev, struct device_node *parent) { - return rzv2h_icu_init_common(node, parent, &rzg3e_hw_params); + return rzv2h_icu_probe_common(pdev, parent, &rzg3e_hw_params); } -static int rzv2h_icu_init(struct device_node *node, struct device_node *parent) +static int rzv2h_icu_probe(struct platform_device *pdev, struct device_node *parent) { - return rzv2h_icu_init_common(node, parent, &rzv2h_hw_params); + return rzv2h_icu_probe_common(pdev, parent, &rzv2h_hw_params); } IRQCHIP_PLATFORM_DRIVER_BEGIN(rzv2h_icu) -IRQCHIP_MATCH("renesas,r9a09g047-icu", rzg3e_icu_init) -IRQCHIP_MATCH("renesas,r9a09g057-icu", rzv2h_icu_init) +IRQCHIP_MATCH("renesas,r9a09g047-icu", rzg3e_icu_probe) +IRQCHIP_MATCH("renesas,r9a09g057-icu", rzv2h_icu_probe) IRQCHIP_PLATFORM_DRIVER_END(rzv2h_icu) MODULE_AUTHOR("Fabrizio Castro "); MODULE_DESCRIPTION("Renesas RZ/V2H(P) ICU Driver"); diff --git a/drivers/irqchip/irq-starfive-jh8100-intc.c b/drivers/irqchip/irq-starfive-jh8100-intc.c index 2460798ec158b6..705361b4ebe07d 100644 --- a/drivers/irqchip/irq-starfive-jh8100-intc.c +++ b/drivers/irqchip/irq-starfive-jh8100-intc.c @@ -114,9 +114,9 @@ static void starfive_intc_irq_handler(struct irq_desc *desc) chained_irq_exit(chip, desc); } -static int __init starfive_intc_init(struct device_node *intc, - struct device_node *parent) +static int starfive_intc_probe(struct platform_device *pdev, struct device_node *parent) { + struct device_node *intc = pdev->dev.of_node; struct starfive_irq_chip *irqc; struct reset_control *rst; struct clk *clk; @@ -199,7 +199,7 @@ static int __init starfive_intc_init(struct device_node *intc, } IRQCHIP_PLATFORM_DRIVER_BEGIN(starfive_intc) -IRQCHIP_MATCH("starfive,jh8100-intc", starfive_intc_init) +IRQCHIP_MATCH("starfive,jh8100-intc", starfive_intc_probe) IRQCHIP_PLATFORM_DRIVER_END(starfive_intc) MODULE_DESCRIPTION("StarFive JH8100 External Interrupt Controller"); diff --git a/drivers/irqchip/irqchip.c b/drivers/irqchip/irqchip.c index 0ee7b6b71f5fa5..689c8e44890192 100644 --- a/drivers/irqchip/irqchip.c +++ b/drivers/irqchip/irqchip.c @@ -36,11 +36,10 @@ int platform_irqchip_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct device_node *par_np __free(device_node) = of_irq_find_parent(np); - of_irq_init_cb_t irq_init_cb = of_device_get_match_data(&pdev->dev); + platform_irq_probe_t irq_probe = of_device_get_match_data(&pdev->dev); - if (!irq_init_cb) { + if (!irq_probe) return -EINVAL; - } if (par_np == np) par_np = NULL; @@ -53,10 +52,9 @@ int platform_irqchip_probe(struct platform_device *pdev) * interrupt controller. The actual initialization callback of this * interrupt controller can check for specific domains as necessary. */ - if (par_np && !irq_find_matching_host(par_np, DOMAIN_BUS_ANY)) { + if (par_np && !irq_find_matching_host(par_np, DOMAIN_BUS_ANY)) return -EPROBE_DEFER; - } - return irq_init_cb(np, par_np); + return irq_probe(pdev, par_np); } EXPORT_SYMBOL_GPL(platform_irqchip_probe); diff --git a/drivers/irqchip/qcom-irq-combiner.c b/drivers/irqchip/qcom-irq-combiner.c index 18e696dc7f4d64..9308088773be7f 100644 --- a/drivers/irqchip/qcom-irq-combiner.c +++ b/drivers/irqchip/qcom-irq-combiner.c @@ -222,7 +222,7 @@ static int get_registers(struct platform_device *pdev, struct combiner *comb) return 0; } -static int __init combiner_probe(struct platform_device *pdev) +static int combiner_probe(struct platform_device *pdev) { struct combiner *combiner; int nregs; diff --git a/drivers/irqchip/qcom-pdc.c b/drivers/irqchip/qcom-pdc.c index 52d77546aacb95..518f7f0f3dab57 100644 --- a/drivers/irqchip/qcom-pdc.c +++ b/drivers/irqchip/qcom-pdc.c @@ -350,9 +350,10 @@ static int pdc_setup_pin_mapping(struct device_node *np) #define QCOM_PDC_SIZE 0x30000 -static int qcom_pdc_init(struct device_node *node, struct device_node *parent) +static int qcom_pdc_probe(struct platform_device *pdev, struct device_node *parent) { struct irq_domain *parent_domain, *pdc_domain; + struct device_node *node = pdev->dev.of_node; resource_size_t res_size; struct resource res; int ret; @@ -428,7 +429,7 @@ static int qcom_pdc_init(struct device_node *node, struct device_node *parent) } IRQCHIP_PLATFORM_DRIVER_BEGIN(qcom_pdc) -IRQCHIP_MATCH("qcom,pdc", qcom_pdc_init) +IRQCHIP_MATCH("qcom,pdc", qcom_pdc_probe) IRQCHIP_PLATFORM_DRIVER_END(qcom_pdc) MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Power Domain Controller"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c index df98144a953946..33521c328a8273 100644 --- a/drivers/isdn/mISDN/timerdev.c +++ b/drivers/isdn/mISDN/timerdev.c @@ -109,14 +109,14 @@ mISDN_read(struct file *filep, char __user *buf, size_t count, loff_t *off) spin_unlock_irq(&dev->lock); if (filep->f_flags & O_NONBLOCK) return -EAGAIN; - wait_event_interruptible(dev->wait, (dev->work || + wait_event_interruptible(dev->wait, (READ_ONCE(dev->work) || !list_empty(list))); if (signal_pending(current)) return -ERESTARTSYS; spin_lock_irq(&dev->lock); } if (dev->work) - dev->work = 0; + WRITE_ONCE(dev->work, 0); if (!list_empty(list)) { timer = list_first_entry(list, struct mISDNtimer, list); list_del(&timer->list); @@ -141,13 +141,16 @@ mISDN_poll(struct file *filep, poll_table *wait) if (*debug & DEBUG_TIMER) printk(KERN_DEBUG "%s(%p, %p)\n", __func__, filep, wait); if (dev) { + u32 work; + poll_wait(filep, &dev->wait, wait); mask = 0; - if (dev->work || !list_empty(&dev->expired)) + work = READ_ONCE(dev->work); + if (work || !list_empty(&dev->expired)) mask |= (EPOLLIN | EPOLLRDNORM); if (*debug & DEBUG_TIMER) printk(KERN_DEBUG "%s work(%d) empty(%d)\n", __func__, - dev->work, list_empty(&dev->expired)); + work, list_empty(&dev->expired)); } return mask; } @@ -172,7 +175,7 @@ misdn_add_timer(struct mISDNtimerdev *dev, int timeout) struct mISDNtimer *timer; if (!timeout) { - dev->work = 1; + WRITE_ONCE(dev->work, 1); wake_up_interruptible(&dev->wait); id = 0; } else { diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index f3faf37f9a08ac..6b9fa060c3a117 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -560,11 +560,6 @@ int led_classdev_register_ext(struct device *parent, #ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED led_cdev->brightness_hw_changed = -1; #endif - /* add to the list of leds */ - down_write(&leds_list_lock); - list_add_tail(&led_cdev->node, &leds_list); - up_write(&leds_list_lock); - if (!led_cdev->max_brightness) led_cdev->max_brightness = LED_FULL; @@ -574,6 +569,11 @@ int led_classdev_register_ext(struct device *parent, led_init_core(led_cdev); + /* add to the list of leds */ + down_write(&leds_list_lock); + list_add_tail(&led_cdev->node, &leds_list); + up_write(&leds_list_lock); + #ifdef CONFIG_LEDS_TRIGGERS led_trigger_set_default(led_cdev); #endif diff --git a/drivers/leds/leds-cros_ec.c b/drivers/leds/leds-cros_ec.c index 377cf04e202a1e..bea3cc3fbfd2d4 100644 --- a/drivers/leds/leds-cros_ec.c +++ b/drivers/leds/leds-cros_ec.c @@ -142,9 +142,6 @@ static int cros_ec_led_count_subleds(struct device *dev, } } - if (!num_subleds) - return -EINVAL; - *max_brightness = common_range; return num_subleds; } @@ -189,6 +186,8 @@ static int cros_ec_led_probe_one(struct device *dev, struct cros_ec_device *cros &priv->led_mc_cdev.led_cdev.max_brightness); if (num_subleds < 0) return num_subleds; + if (num_subleds == 0) + return 0; /* LED without any colors, skip */ priv->cros_ec = cros_ec; priv->led_id = id; diff --git a/drivers/leds/leds-expresswire.c b/drivers/leds/leds-expresswire.c index bb69be228a6d3c..25c6b159a6ee93 100644 --- a/drivers/leds/leds-expresswire.c +++ b/drivers/leds/leds-expresswire.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -16,37 +17,41 @@ void expresswire_power_off(struct expresswire_common_props *props) { gpiod_set_value_cansleep(props->ctrl_gpio, 0); - usleep_range(props->timing.poweroff_us, props->timing.poweroff_us * 2); + fsleep(props->timing.poweroff_us); } EXPORT_SYMBOL_NS_GPL(expresswire_power_off, "EXPRESSWIRE"); void expresswire_enable(struct expresswire_common_props *props) { + unsigned long flags; + + local_irq_save(flags); + gpiod_set_value(props->ctrl_gpio, 1); udelay(props->timing.detect_delay_us); gpiod_set_value(props->ctrl_gpio, 0); udelay(props->timing.detect_us); gpiod_set_value(props->ctrl_gpio, 1); + + local_irq_restore(flags); } EXPORT_SYMBOL_NS_GPL(expresswire_enable, "EXPRESSWIRE"); -void expresswire_start(struct expresswire_common_props *props) +static void expresswire_start(struct expresswire_common_props *props) { gpiod_set_value(props->ctrl_gpio, 1); udelay(props->timing.data_start_us); } -EXPORT_SYMBOL_NS_GPL(expresswire_start, "EXPRESSWIRE"); -void expresswire_end(struct expresswire_common_props *props) +static void expresswire_end(struct expresswire_common_props *props) { gpiod_set_value(props->ctrl_gpio, 0); udelay(props->timing.end_of_data_low_us); gpiod_set_value(props->ctrl_gpio, 1); udelay(props->timing.end_of_data_high_us); } -EXPORT_SYMBOL_NS_GPL(expresswire_end, "EXPRESSWIRE"); -void expresswire_set_bit(struct expresswire_common_props *props, bool bit) +static void expresswire_set_bit(struct expresswire_common_props *props, bool bit) { if (bit) { gpiod_set_value(props->ctrl_gpio, 0); @@ -60,13 +65,18 @@ void expresswire_set_bit(struct expresswire_common_props *props, bool bit) udelay(props->timing.short_bitset_us); } } -EXPORT_SYMBOL_NS_GPL(expresswire_set_bit, "EXPRESSWIRE"); void expresswire_write_u8(struct expresswire_common_props *props, u8 val) { + unsigned long flags; + + local_irq_save(flags); + expresswire_start(props); for (int i = 7; i >= 0; i--) expresswire_set_bit(props, val & BIT(i)); expresswire_end(props); + + local_irq_restore(flags); } EXPORT_SYMBOL_NS_GPL(expresswire_write_u8, "EXPRESSWIRE"); diff --git a/drivers/leds/leds-lp50xx.c b/drivers/leds/leds-lp50xx.c index 94f8ef6b482c91..e2a9c8592953ca 100644 --- a/drivers/leds/leds-lp50xx.c +++ b/drivers/leds/leds-lp50xx.c @@ -50,11 +50,17 @@ #define LP50XX_SW_RESET 0xff #define LP50XX_CHIP_EN BIT(6) +#define LP50XX_CHIP_DISABLE 0x00 +#define LP50XX_START_TIME_US 500 +#define LP50XX_RESET_TIME_US 3 + +#define LP50XX_EN_GPIO_LOW 0 +#define LP50XX_EN_GPIO_HIGH 1 /* There are 3 LED outputs per bank */ #define LP50XX_LEDS_PER_MODULE 3 -#define LP5009_MAX_LED_MODULES 2 +#define LP5009_MAX_LED_MODULES 3 #define LP5012_MAX_LED_MODULES 4 #define LP5018_MAX_LED_MODULES 6 #define LP5024_MAX_LED_MODULES 8 @@ -341,17 +347,15 @@ static int lp50xx_brightness_set(struct led_classdev *cdev, return ret; } -static int lp50xx_set_banks(struct lp50xx *priv, u32 led_banks[]) +static int lp50xx_set_banks(struct lp50xx *priv, u32 led_banks[], int num_leds) { u8 led_config_lo, led_config_hi; u32 bank_enable_mask = 0; int ret; int i; - for (i = 0; i < priv->chip_info->max_modules; i++) { - if (led_banks[i]) - bank_enable_mask |= (1 << led_banks[i]); - } + for (i = 0; i < num_leds; i++) + bank_enable_mask |= (1 << led_banks[i]); led_config_lo = bank_enable_mask; led_config_hi = bank_enable_mask >> 8; @@ -371,19 +375,42 @@ static int lp50xx_reset(struct lp50xx *priv) return regmap_write(priv->regmap, priv->chip_info->reset_reg, LP50XX_SW_RESET); } -static int lp50xx_enable_disable(struct lp50xx *priv, int enable_disable) +static int lp50xx_enable(struct lp50xx *priv) { int ret; - ret = gpiod_direction_output(priv->enable_gpio, enable_disable); + if (priv->enable_gpio) { + ret = gpiod_direction_output(priv->enable_gpio, LP50XX_EN_GPIO_HIGH); + if (ret) + return ret; + + udelay(LP50XX_START_TIME_US); + } + + ret = lp50xx_reset(priv); if (ret) return ret; - if (enable_disable) - return regmap_write(priv->regmap, LP50XX_DEV_CFG0, LP50XX_CHIP_EN); - else - return regmap_write(priv->regmap, LP50XX_DEV_CFG0, 0); + return regmap_write(priv->regmap, LP50XX_DEV_CFG0, LP50XX_CHIP_EN); +} + +static int lp50xx_disable(struct lp50xx *priv) +{ + int ret; + + ret = regmap_write(priv->regmap, LP50XX_DEV_CFG0, LP50XX_CHIP_DISABLE); + if (ret) + return ret; + if (priv->enable_gpio) { + ret = gpiod_direction_output(priv->enable_gpio, LP50XX_EN_GPIO_LOW); + if (ret) + return ret; + + udelay(LP50XX_RESET_TIME_US); + } + + return 0; } static int lp50xx_probe_leds(struct fwnode_handle *child, struct lp50xx *priv, @@ -405,7 +432,7 @@ static int lp50xx_probe_leds(struct fwnode_handle *child, struct lp50xx *priv, return ret; } - ret = lp50xx_set_banks(priv, led_banks); + ret = lp50xx_set_banks(priv, led_banks, num_leds); if (ret) { dev_err(priv->dev, "Cannot setup banked LEDs\n"); return ret; @@ -447,6 +474,10 @@ static int lp50xx_probe_dt(struct lp50xx *priv) return dev_err_probe(priv->dev, PTR_ERR(priv->enable_gpio), "Failed to get enable GPIO\n"); + ret = lp50xx_enable(priv); + if (ret) + return ret; + priv->regulator = devm_regulator_get(priv->dev, "vled"); if (IS_ERR(priv->regulator)) priv->regulator = NULL; @@ -547,14 +578,6 @@ static int lp50xx_probe(struct i2c_client *client) return ret; } - ret = lp50xx_reset(led); - if (ret) - return ret; - - ret = lp50xx_enable_disable(led, 1); - if (ret) - return ret; - return lp50xx_probe_dt(led); } @@ -563,7 +586,7 @@ static void lp50xx_remove(struct i2c_client *client) struct lp50xx *led = i2c_get_clientdata(client); int ret; - ret = lp50xx_enable_disable(led, 0); + ret = lp50xx_disable(led); if (ret) dev_err(led->dev, "Failed to disable chip\n"); diff --git a/drivers/leds/leds-netxbig.c b/drivers/leds/leds-netxbig.c index e95287416ef879..99df46f2d9f528 100644 --- a/drivers/leds/leds-netxbig.c +++ b/drivers/leds/leds-netxbig.c @@ -364,6 +364,9 @@ static int netxbig_gpio_ext_get(struct device *dev, if (!addr) return -ENOMEM; + gpio_ext->addr = addr; + gpio_ext->num_addr = 0; + /* * We cannot use devm_ managed resources with these GPIO descriptors * since they are associated with the "GPIO extension device" which @@ -375,45 +378,58 @@ static int netxbig_gpio_ext_get(struct device *dev, gpiod = gpiod_get_index(gpio_ext_dev, "addr", i, GPIOD_OUT_LOW); if (IS_ERR(gpiod)) - return PTR_ERR(gpiod); + goto err_set_code; gpiod_set_consumer_name(gpiod, "GPIO extension addr"); addr[i] = gpiod; + gpio_ext->num_addr++; } - gpio_ext->addr = addr; - gpio_ext->num_addr = num_addr; ret = gpiod_count(gpio_ext_dev, "data"); if (ret < 0) { dev_err(dev, "Failed to count GPIOs in DT property data-gpios\n"); - return ret; + goto err_free_addr; } num_data = ret; data = devm_kcalloc(dev, num_data, sizeof(*data), GFP_KERNEL); - if (!data) - return -ENOMEM; + if (!data) { + ret = -ENOMEM; + goto err_free_addr; + } + + gpio_ext->data = data; + gpio_ext->num_data = 0; for (i = 0; i < num_data; i++) { gpiod = gpiod_get_index(gpio_ext_dev, "data", i, GPIOD_OUT_LOW); if (IS_ERR(gpiod)) - return PTR_ERR(gpiod); + goto err_free_data; gpiod_set_consumer_name(gpiod, "GPIO extension data"); data[i] = gpiod; + gpio_ext->num_data++; } - gpio_ext->data = data; - gpio_ext->num_data = num_data; gpiod = gpiod_get(gpio_ext_dev, "enable", GPIOD_OUT_LOW); if (IS_ERR(gpiod)) { dev_err(dev, "Failed to get GPIO from DT property enable-gpio\n"); - return PTR_ERR(gpiod); + goto err_free_data; } gpiod_set_consumer_name(gpiod, "GPIO extension enable"); gpio_ext->enable = gpiod; return devm_add_action_or_reset(dev, netxbig_gpio_ext_remove, gpio_ext); + +err_free_data: + for (i = 0; i < gpio_ext->num_data; i++) + gpiod_put(gpio_ext->data[i]); +err_set_code: + ret = PTR_ERR(gpiod); +err_free_addr: + for (i = 0; i < gpio_ext->num_addr; i++) + gpiod_put(gpio_ext->addr[i]); + return ret; } static int netxbig_leds_get_of_pdata(struct device *dev, diff --git a/drivers/leds/leds-upboard.c b/drivers/leds/leds-upboard.c index b350eb294280fd..12989b2f195309 100644 --- a/drivers/leds/leds-upboard.c +++ b/drivers/leds/leds-upboard.c @@ -123,4 +123,4 @@ MODULE_AUTHOR("Gary Wang "); MODULE_AUTHOR("Thomas Richard "); MODULE_DESCRIPTION("UP Board LED driver"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:upboard-led"); +MODULE_ALIAS("platform:upboard-leds"); diff --git a/drivers/leds/rgb/leds-qcom-lpg.c b/drivers/leds/rgb/leds-qcom-lpg.c index 4f2a178e3d265a..a460782dadca41 100644 --- a/drivers/leds/rgb/leds-qcom-lpg.c +++ b/drivers/leds/rgb/leds-qcom-lpg.c @@ -2,7 +2,7 @@ /* * Copyright (c) 2017-2022 Linaro Ltd * Copyright (c) 2010-2012, The Linux Foundation. All rights reserved. - * Copyright (c) 2023-2024, Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include #include @@ -369,7 +369,7 @@ static int lpg_lut_store(struct lpg *lpg, struct led_pattern *pattern, { unsigned int idx; u16 val; - int i; + int i, ret; idx = bitmap_find_next_zero_area(lpg->lut_bitmap, lpg->lut_size, 0, len, 0); @@ -379,8 +379,10 @@ static int lpg_lut_store(struct lpg *lpg, struct led_pattern *pattern, for (i = 0; i < len; i++) { val = pattern[i].brightness; - regmap_bulk_write(lpg->map, lpg->lut_base + LPG_LUT_REG(idx + i), - &val, sizeof(val)); + ret = regmap_bulk_write(lpg->map, lpg->lut_base + LPG_LUT_REG(idx + i), + &val, sizeof(val)); + if (ret) + return ret; } bitmap_set(lpg->lut_bitmap, idx, len); @@ -1247,8 +1249,6 @@ static int lpg_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, lpg_apply(chan); - triled_set(lpg, chan->triled_mask, chan->enabled ? chan->triled_mask : 0); - out_unlock: mutex_unlock(&lpg->lock); diff --git a/drivers/macintosh/mac_hid.c b/drivers/macintosh/mac_hid.c index 369d72f59b3c10..06fd910b3fd1a0 100644 --- a/drivers/macintosh/mac_hid.c +++ b/drivers/macintosh/mac_hid.c @@ -187,13 +187,14 @@ static int mac_hid_toggle_emumouse(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; - int old_val = *valp; + int old_val; int rc; rc = mutex_lock_killable(&mac_hid_emumouse_mutex); if (rc) return rc; + old_val = *valp; rc = proc_dointvec(table, write, buffer, lenp, ppos); if (rc == 0 && write && *valp != old_val) { diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c index ff292b9e0be9ee..0e0a66359d4c38 100644 --- a/drivers/mailbox/pcc.c +++ b/drivers/mailbox/pcc.c @@ -305,22 +305,6 @@ static void pcc_chan_acknowledge(struct pcc_chan_info *pchan) pcc_chan_reg_read_modify_write(&pchan->db); } -static void *write_response(struct pcc_chan_info *pchan) -{ - struct pcc_header pcc_header; - void *buffer; - int data_len; - - memcpy_fromio(&pcc_header, pchan->chan.shmem, - sizeof(pcc_header)); - data_len = pcc_header.length - sizeof(u32) + sizeof(struct pcc_header); - - buffer = pchan->chan.rx_alloc(pchan->chan.mchan->cl, data_len); - if (buffer != NULL) - memcpy_fromio(buffer, pchan->chan.shmem, data_len); - return buffer; -} - /** * pcc_mbox_irq - PCC mailbox interrupt handler * @irq: interrupt number @@ -332,8 +316,6 @@ static irqreturn_t pcc_mbox_irq(int irq, void *p) { struct pcc_chan_info *pchan; struct mbox_chan *chan = p; - struct pcc_header *pcc_header = chan->active_req; - void *handle = NULL; pchan = chan->con_priv; @@ -357,17 +339,7 @@ static irqreturn_t pcc_mbox_irq(int irq, void *p) * required to avoid any possible race in updatation of this flag. */ pchan->chan_in_use = false; - - if (pchan->chan.rx_alloc) - handle = write_response(pchan); - - if (chan->active_req) { - pcc_header = chan->active_req; - if (pcc_header->flags & PCC_CMD_COMPLETION_NOTIFY) - mbox_chan_txdone(chan, 0); - } - - mbox_chan_received_data(chan, handle); + mbox_chan_received_data(chan, NULL); pcc_chan_acknowledge(pchan); @@ -411,24 +383,9 @@ pcc_mbox_request_channel(struct mbox_client *cl, int subspace_id) pcc_mchan = &pchan->chan; pcc_mchan->shmem = acpi_os_ioremap(pcc_mchan->shmem_base_addr, pcc_mchan->shmem_size); - if (!pcc_mchan->shmem) - goto err; - - pcc_mchan->manage_writes = false; - - /* This indicates that the channel is ready to accept messages. - * This needs to happen after the channel has registered - * its callback. There is no access point to do that in - * the mailbox API. That implies that the mailbox client must - * have set the allocate callback function prior to - * sending any messages. - */ - if (pchan->type == ACPI_PCCT_TYPE_EXT_PCC_SLAVE_SUBSPACE) - pcc_chan_reg_read_modify_write(&pchan->cmd_update); - - return pcc_mchan; + if (pcc_mchan->shmem) + return pcc_mchan; -err: mbox_free_channel(chan); return ERR_PTR(-ENXIO); } @@ -459,38 +416,8 @@ void pcc_mbox_free_channel(struct pcc_mbox_chan *pchan) } EXPORT_SYMBOL_GPL(pcc_mbox_free_channel); -static int pcc_write_to_buffer(struct mbox_chan *chan, void *data) -{ - struct pcc_chan_info *pchan = chan->con_priv; - struct pcc_mbox_chan *pcc_mbox_chan = &pchan->chan; - struct pcc_header *pcc_header = data; - - if (!pchan->chan.manage_writes) - return 0; - - /* The PCC header length includes the command field - * but not the other values from the header. - */ - int len = pcc_header->length - sizeof(u32) + sizeof(struct pcc_header); - u64 val; - - pcc_chan_reg_read(&pchan->cmd_complete, &val); - if (!val) { - pr_info("%s pchan->cmd_complete not set", __func__); - return -1; - } - memcpy_toio(pcc_mbox_chan->shmem, data, len); - return 0; -} - - /** - * pcc_send_data - Called from Mailbox Controller code. If - * pchan->chan.rx_alloc is set, then the command complete - * flag is checked and the data is written to the shared - * buffer io memory. - * - * If pchan->chan.rx_alloc is not set, then it is used + * pcc_send_data - Called from Mailbox Controller code. Used * here only to ring the channel doorbell. The PCC client * specific read/write is done in the client driver in * order to maintain atomicity over PCC channel once @@ -506,37 +433,17 @@ static int pcc_send_data(struct mbox_chan *chan, void *data) int ret; struct pcc_chan_info *pchan = chan->con_priv; - ret = pcc_write_to_buffer(chan, data); - if (ret) - return ret; - ret = pcc_chan_reg_read_modify_write(&pchan->cmd_update); if (ret) return ret; ret = pcc_chan_reg_read_modify_write(&pchan->db); - if (!ret && pchan->plat_irq > 0) pchan->chan_in_use = true; return ret; } - -static bool pcc_last_tx_done(struct mbox_chan *chan) -{ - struct pcc_chan_info *pchan = chan->con_priv; - u64 val; - - pcc_chan_reg_read(&pchan->cmd_complete, &val); - if (!val) - return false; - else - return true; -} - - - /** * pcc_startup - Called from Mailbox Controller code. Used here * to request the interrupt. @@ -582,7 +489,6 @@ static const struct mbox_chan_ops pcc_chan_ops = { .send_data = pcc_send_data, .startup = pcc_startup, .shutdown = pcc_shutdown, - .last_tx_done = pcc_last_tx_done, }; /** diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c index c1367223e71a0f..3d487d75c483d7 100644 --- a/drivers/mcb/mcb-core.c +++ b/drivers/mcb/mcb-core.c @@ -85,7 +85,8 @@ static void mcb_remove(struct device *dev) struct mcb_device *mdev = to_mcb_device(dev); struct module *carrier_mod; - mdrv->remove(mdev); + if (mdrv->remove) + mdrv->remove(mdev); carrier_mod = mdev->dev.parent->driver->owner; module_put(carrier_mod); @@ -176,13 +177,13 @@ static const struct device_type mcb_carrier_device_type = { * @owner: The @mcb_driver's module * @mod_name: The name of the @mcb_driver's module * - * Register a @mcb_driver at the system. Perform some sanity checks, if - * the .probe and .remove methods are provided by the driver. + * Register a @mcb_driver at the system. Perform a sanity check, if + * .probe method is provided by the driver. */ int __mcb_register_driver(struct mcb_driver *drv, struct module *owner, const char *mod_name) { - if (!drv->probe || !drv->remove) + if (!drv->probe) return -EINVAL; drv->driver.owner = owner; diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 1d33e40d26ea51..cca5756030d71e 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -273,6 +273,8 @@ struct bcache_device { struct bio_set bio_split; + struct bio_set bio_detached; + unsigned int data_csum:1; int (*cache_miss)(struct btree *b, struct search *s, @@ -755,6 +757,13 @@ struct bbio { struct bio bio; }; +struct detached_dev_io_private { + struct bcache_device *d; + unsigned long start_time; + struct bio *orig_bio; + struct bio bio; +}; + #define BTREE_PRIO USHRT_MAX #define INITIAL_PRIO 32768U diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index af345dc6fde14f..6cba1180be8aab 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1077,68 +1077,59 @@ static CLOSURE_CALLBACK(cached_dev_nodata) continue_at(cl, cached_dev_bio_complete, NULL); } -struct detached_dev_io_private { - struct bcache_device *d; - unsigned long start_time; - bio_end_io_t *bi_end_io; - void *bi_private; - struct block_device *orig_bdev; -}; - static void detached_dev_end_io(struct bio *bio) { - struct detached_dev_io_private *ddip; - - ddip = bio->bi_private; - bio->bi_end_io = ddip->bi_end_io; - bio->bi_private = ddip->bi_private; + struct detached_dev_io_private *ddip = + container_of(bio, struct detached_dev_io_private, bio); + struct bio *orig_bio = ddip->orig_bio; /* Count on the bcache device */ - bio_end_io_acct_remapped(bio, ddip->start_time, ddip->orig_bdev); + bio_end_io_acct(orig_bio, ddip->start_time); if (bio->bi_status) { - struct cached_dev *dc = container_of(ddip->d, - struct cached_dev, disk); + struct cached_dev *dc = bio->bi_private; + /* should count I/O error for backing device here */ bch_count_backing_io_errors(dc, bio); + orig_bio->bi_status = bio->bi_status; } - kfree(ddip); - bio->bi_end_io(bio); + bio_put(bio); + bio_endio(orig_bio); } -static void detached_dev_do_request(struct bcache_device *d, struct bio *bio, - struct block_device *orig_bdev, unsigned long start_time) +static void detached_dev_do_request(struct bcache_device *d, + struct bio *orig_bio, unsigned long start_time) { struct detached_dev_io_private *ddip; struct cached_dev *dc = container_of(d, struct cached_dev, disk); + struct bio *clone_bio; - /* - * no need to call closure_get(&dc->disk.cl), - * because upper layer had already opened bcache device, - * which would call closure_get(&dc->disk.cl) - */ - ddip = kzalloc(sizeof(struct detached_dev_io_private), GFP_NOIO); - if (!ddip) { - bio->bi_status = BLK_STS_RESOURCE; - bio->bi_end_io(bio); + if (bio_op(orig_bio) == REQ_OP_DISCARD && + !bdev_max_discard_sectors(dc->bdev)) { + bio_end_io_acct(orig_bio, start_time); + bio_endio(orig_bio); return; } - ddip->d = d; + clone_bio = bio_alloc_clone(dc->bdev, orig_bio, GFP_NOIO, + &d->bio_detached); + if (!clone_bio) { + orig_bio->bi_status = BLK_STS_RESOURCE; + bio_endio(orig_bio); + return; + } + + ddip = container_of(clone_bio, struct detached_dev_io_private, bio); /* Count on the bcache device */ - ddip->orig_bdev = orig_bdev; + ddip->d = d; ddip->start_time = start_time; - ddip->bi_end_io = bio->bi_end_io; - ddip->bi_private = bio->bi_private; - bio->bi_end_io = detached_dev_end_io; - bio->bi_private = ddip; - - if ((bio_op(bio) == REQ_OP_DISCARD) && - !bdev_max_discard_sectors(dc->bdev)) - bio->bi_end_io(bio); - else - submit_bio_noacct(bio); + ddip->orig_bio = orig_bio; + + clone_bio->bi_end_io = detached_dev_end_io; + clone_bio->bi_private = dc; + + submit_bio_noacct(clone_bio); } static void quit_max_writeback_rate(struct cache_set *c, @@ -1214,10 +1205,10 @@ void cached_dev_submit_bio(struct bio *bio) start_time = bio_start_io_acct(bio); - bio_set_dev(bio, dc->bdev); bio->bi_iter.bi_sector += dc->sb.data_offset; if (cached_dev_get(dc)) { + bio_set_dev(bio, dc->bdev); s = search_alloc(bio, d, orig_bdev, start_time); trace_bcache_request_start(s->d, bio); @@ -1237,9 +1228,10 @@ void cached_dev_submit_bio(struct bio *bio) else cached_dev_read(dc, s); } - } else + } else { /* I/O request sent to backing device */ - detached_dev_do_request(d, bio, orig_bdev, start_time); + detached_dev_do_request(d, bio, start_time); + } } static int cached_dev_ioctl(struct bcache_device *d, blk_mode_t mode, diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 6d250e366412c7..9218b9dbd4af2f 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -887,6 +887,7 @@ static void bcache_device_free(struct bcache_device *d) } bioset_exit(&d->bio_split); + bioset_exit(&d->bio_detached); kvfree(d->full_dirty_stripes); kvfree(d->stripe_sectors_dirty); @@ -949,6 +950,11 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER)) goto out_ida_remove; + if (bioset_init(&d->bio_detached, 4, + offsetof(struct detached_dev_io_private, bio), + BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER)) + goto out_bioset_split_exit; + if (lim.logical_block_size > PAGE_SIZE && cached_bdev) { /* * This should only happen with BCACHE_SB_VERSION_BDEV. @@ -964,7 +970,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, d->disk = blk_alloc_disk(&lim, NUMA_NO_NODE); if (IS_ERR(d->disk)) - goto out_bioset_exit; + goto out_bioset_detach_exit; set_capacity(d->disk, sectors); snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx); @@ -976,7 +982,9 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, d->disk->private_data = d; return 0; -out_bioset_exit: +out_bioset_detach_exit: + bioset_exit(&d->bio_detached); +out_bioset_split_exit: bioset_exit(&d->bio_split); out_ida_remove: ida_free(&bcache_device_idx, idx); diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index e6d28be11c5c6c..5235f3e4924b7a 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1374,7 +1374,7 @@ static void submit_io(struct dm_buffer *b, enum req_op op, unsigned short ioprio { unsigned int n_sectors; sector_t sector; - unsigned int offset, end; + unsigned int offset, end, align; b->end_io = end_io; @@ -1388,9 +1388,11 @@ static void submit_io(struct dm_buffer *b, enum req_op op, unsigned short ioprio b->c->write_callback(b); offset = b->write_start; end = b->write_end; - offset &= -DM_BUFIO_WRITE_ALIGN; - end += DM_BUFIO_WRITE_ALIGN - 1; - end &= -DM_BUFIO_WRITE_ALIGN; + align = max(DM_BUFIO_WRITE_ALIGN, + bdev_physical_block_size(b->c->bdev)); + offset &= -align; + end += align - 1; + end &= -align; if (unlikely(end > b->c->block_size)) end = b->c->block_size; diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index 6abb31ca966231..b354e74a670e0f 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -103,7 +103,7 @@ static int __ebs_rw_bvec(struct ebs_c *ec, enum req_op op, struct bio_vec *bv, } else { flush_dcache_page(bv->bv_page); memcpy(ba, pa, cur_len); - dm_bufio_mark_partial_buffer_dirty(b, buf_off, buf_off + cur_len); + dm_bufio_mark_buffer_dirty(b); } dm_bufio_release(b); diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index b6797663753818..061b4d3108132c 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -29,7 +29,7 @@ typedef sector_t chunk_t; * chunk within the device. */ struct dm_exception { - struct hlist_bl_node hash_list; + struct hlist_node hash_list; chunk_t old_chunk; chunk_t new_chunk; diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 7bb7174f8f4f87..f0c84e7a5daa63 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -432,6 +432,7 @@ static int log_writes_kthread(void *arg) struct log_writes_c *lc = arg; sector_t sector = 0; + set_freezable(); while (!kthread_should_stop()) { bool super = false; bool logging_enabled; diff --git a/drivers/md/dm-pcache/cache.c b/drivers/md/dm-pcache/cache.c index 698697a7a73c66..534bf07b794f14 100644 --- a/drivers/md/dm-pcache/cache.c +++ b/drivers/md/dm-pcache/cache.c @@ -10,7 +10,8 @@ struct kmem_cache *key_cache; static inline struct pcache_cache_info *get_cache_info_addr(struct pcache_cache *cache) { - return cache->cache_info_addr + cache->info_index; + return (struct pcache_cache_info *)((char *)cache->cache_info_addr + + (size_t)cache->info_index * PCACHE_CACHE_INFO_SIZE); } static void cache_info_write(struct pcache_cache *cache) @@ -21,10 +22,10 @@ static void cache_info_write(struct pcache_cache *cache) cache_info->header.crc = pcache_meta_crc(&cache_info->header, sizeof(struct pcache_cache_info)); + cache->info_index = (cache->info_index + 1) % PCACHE_META_INDEX_MAX; memcpy_flushcache(get_cache_info_addr(cache), cache_info, sizeof(struct pcache_cache_info)); - - cache->info_index = (cache->info_index + 1) % PCACHE_META_INDEX_MAX; + pmem_wmb(); } static void cache_info_init_default(struct pcache_cache *cache); @@ -49,6 +50,8 @@ static int cache_info_init(struct pcache_cache *cache, struct pcache_cache_optio return -EINVAL; } + cache->info_index = ((char *)cache_info_addr - (char *)cache->cache_info_addr) / PCACHE_CACHE_INFO_SIZE; + return 0; } @@ -93,10 +96,10 @@ void cache_pos_encode(struct pcache_cache *cache, pos_onmedia.header.seq = seq; pos_onmedia.header.crc = cache_pos_onmedia_crc(&pos_onmedia); + *index = (*index + 1) % PCACHE_META_INDEX_MAX; + memcpy_flushcache(pos_onmedia_addr, &pos_onmedia, sizeof(struct pcache_cache_pos_onmedia)); pmem_wmb(); - - *index = (*index + 1) % PCACHE_META_INDEX_MAX; } int cache_pos_decode(struct pcache_cache *cache, diff --git a/drivers/md/dm-pcache/cache_segment.c b/drivers/md/dm-pcache/cache_segment.c index f0b58980806e07..9d92e2b067ed04 100644 --- a/drivers/md/dm-pcache/cache_segment.c +++ b/drivers/md/dm-pcache/cache_segment.c @@ -26,11 +26,11 @@ static void cache_seg_info_write(struct pcache_cache_segment *cache_seg) seg_info->header.seq++; seg_info->header.crc = pcache_meta_crc(&seg_info->header, sizeof(struct pcache_segment_info)); + cache_seg->info_index = (cache_seg->info_index + 1) % PCACHE_META_INDEX_MAX; + seg_info_addr = get_seg_info_addr(cache_seg); memcpy_flushcache(seg_info_addr, seg_info, sizeof(struct pcache_segment_info)); pmem_wmb(); - - cache_seg->info_index = (cache_seg->info_index + 1) % PCACHE_META_INDEX_MAX; mutex_unlock(&cache_seg->info_lock); } @@ -56,7 +56,10 @@ static int cache_seg_info_load(struct pcache_cache_segment *cache_seg) ret = -EIO; goto out; } - cache_seg->info_index = cache_seg_info_addr - cache_seg_info_addr_base; + + cache_seg->info_index = + ((char *)cache_seg_info_addr - (char *)cache_seg_info_addr_base) / + PCACHE_SEG_INFO_SIZE; out: mutex_unlock(&cache_seg->info_lock); @@ -129,10 +132,10 @@ static void cache_seg_ctrl_write(struct pcache_cache_segment *cache_seg) cache_seg_gen.header.crc = pcache_meta_crc(&cache_seg_gen.header, sizeof(struct pcache_cache_seg_gen)); + cache_seg->gen_index = (cache_seg->gen_index + 1) % PCACHE_META_INDEX_MAX; + memcpy_flushcache(get_cache_seg_gen_addr(cache_seg), &cache_seg_gen, sizeof(struct pcache_cache_seg_gen)); pmem_wmb(); - - cache_seg->gen_index = (cache_seg->gen_index + 1) % PCACHE_META_INDEX_MAX; } static void cache_seg_ctrl_init(struct pcache_cache_segment *cache_seg) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index c6f7129e43d347..4bacdc499984b5 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2287,6 +2287,8 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev) mddev->reshape_position = le64_to_cpu(sb->reshape_position); rs->raid_type = get_raid_type_by_ll(mddev->level, mddev->layout); + if (!rs->raid_type) + return -EINVAL; } } else { diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index f40c18da400007..dbd148967de425 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -40,10 +40,15 @@ static const char dm_snapshot_merge_target_name[] = "snapshot-merge"; #define DM_TRACKED_CHUNK_HASH(x) ((unsigned long)(x) & \ (DM_TRACKED_CHUNK_HASH_SIZE - 1)) +struct dm_hlist_head { + struct hlist_head head; + spinlock_t lock; +}; + struct dm_exception_table { uint32_t hash_mask; unsigned int hash_shift; - struct hlist_bl_head *table; + struct dm_hlist_head *table; }; struct dm_snapshot { @@ -628,8 +633,8 @@ static uint32_t exception_hash(struct dm_exception_table *et, chunk_t chunk); /* Lock to protect access to the completed and pending exception hash tables. */ struct dm_exception_table_lock { - struct hlist_bl_head *complete_slot; - struct hlist_bl_head *pending_slot; + spinlock_t *complete_slot; + spinlock_t *pending_slot; }; static void dm_exception_table_lock_init(struct dm_snapshot *s, chunk_t chunk, @@ -638,20 +643,20 @@ static void dm_exception_table_lock_init(struct dm_snapshot *s, chunk_t chunk, struct dm_exception_table *complete = &s->complete; struct dm_exception_table *pending = &s->pending; - lock->complete_slot = &complete->table[exception_hash(complete, chunk)]; - lock->pending_slot = &pending->table[exception_hash(pending, chunk)]; + lock->complete_slot = &complete->table[exception_hash(complete, chunk)].lock; + lock->pending_slot = &pending->table[exception_hash(pending, chunk)].lock; } static void dm_exception_table_lock(struct dm_exception_table_lock *lock) { - hlist_bl_lock(lock->complete_slot); - hlist_bl_lock(lock->pending_slot); + spin_lock_nested(lock->complete_slot, 1); + spin_lock_nested(lock->pending_slot, 2); } static void dm_exception_table_unlock(struct dm_exception_table_lock *lock) { - hlist_bl_unlock(lock->pending_slot); - hlist_bl_unlock(lock->complete_slot); + spin_unlock(lock->pending_slot); + spin_unlock(lock->complete_slot); } static int dm_exception_table_init(struct dm_exception_table *et, @@ -661,13 +666,15 @@ static int dm_exception_table_init(struct dm_exception_table *et, et->hash_shift = hash_shift; et->hash_mask = size - 1; - et->table = kvmalloc_array(size, sizeof(struct hlist_bl_head), + et->table = kvmalloc_array(size, sizeof(struct dm_hlist_head), GFP_KERNEL); if (!et->table) return -ENOMEM; - for (i = 0; i < size; i++) - INIT_HLIST_BL_HEAD(et->table + i); + for (i = 0; i < size; i++) { + INIT_HLIST_HEAD(&et->table[i].head); + spin_lock_init(&et->table[i].lock); + } return 0; } @@ -675,16 +682,17 @@ static int dm_exception_table_init(struct dm_exception_table *et, static void dm_exception_table_exit(struct dm_exception_table *et, struct kmem_cache *mem) { - struct hlist_bl_head *slot; + struct dm_hlist_head *slot; struct dm_exception *ex; - struct hlist_bl_node *pos, *n; + struct hlist_node *pos; int i, size; size = et->hash_mask + 1; for (i = 0; i < size; i++) { slot = et->table + i; - hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list) { + hlist_for_each_entry_safe(ex, pos, &slot->head, hash_list) { + hlist_del(&ex->hash_list); kmem_cache_free(mem, ex); cond_resched(); } @@ -700,7 +708,7 @@ static uint32_t exception_hash(struct dm_exception_table *et, chunk_t chunk) static void dm_remove_exception(struct dm_exception *e) { - hlist_bl_del(&e->hash_list); + hlist_del(&e->hash_list); } /* @@ -710,12 +718,11 @@ static void dm_remove_exception(struct dm_exception *e) static struct dm_exception *dm_lookup_exception(struct dm_exception_table *et, chunk_t chunk) { - struct hlist_bl_head *slot; - struct hlist_bl_node *pos; + struct hlist_head *slot; struct dm_exception *e; - slot = &et->table[exception_hash(et, chunk)]; - hlist_bl_for_each_entry(e, pos, slot, hash_list) + slot = &et->table[exception_hash(et, chunk)].head; + hlist_for_each_entry(e, slot, hash_list) if (chunk >= e->old_chunk && chunk <= e->old_chunk + dm_consecutive_chunk_count(e)) return e; @@ -762,18 +769,17 @@ static void free_pending_exception(struct dm_snap_pending_exception *pe) static void dm_insert_exception(struct dm_exception_table *eh, struct dm_exception *new_e) { - struct hlist_bl_head *l; - struct hlist_bl_node *pos; + struct hlist_head *l; struct dm_exception *e = NULL; - l = &eh->table[exception_hash(eh, new_e->old_chunk)]; + l = &eh->table[exception_hash(eh, new_e->old_chunk)].head; /* Add immediately if this table doesn't support consecutive chunks */ if (!eh->hash_shift) goto out; /* List is ordered by old_chunk */ - hlist_bl_for_each_entry(e, pos, l, hash_list) { + hlist_for_each_entry(e, l, hash_list) { /* Insert after an existing chunk? */ if (new_e->old_chunk == (e->old_chunk + dm_consecutive_chunk_count(e) + 1) && @@ -804,13 +810,13 @@ static void dm_insert_exception(struct dm_exception_table *eh, * Either the table doesn't support consecutive chunks or slot * l is empty. */ - hlist_bl_add_head(&new_e->hash_list, l); + hlist_add_head(&new_e->hash_list, l); } else if (new_e->old_chunk < e->old_chunk) { /* Add before an existing exception */ - hlist_bl_add_before(&new_e->hash_list, &e->hash_list); + hlist_add_before(&new_e->hash_list, &e->hash_list); } else { /* Add to l's tail: e is the last exception in this slot */ - hlist_bl_add_behind(&new_e->hash_list, &e->hash_list); + hlist_add_behind(&new_e->hash_list, &e->hash_list); } } @@ -820,7 +826,6 @@ static void dm_insert_exception(struct dm_exception_table *eh, */ static int dm_add_exception(void *context, chunk_t old, chunk_t new) { - struct dm_exception_table_lock lock; struct dm_snapshot *s = context; struct dm_exception *e; @@ -833,17 +838,7 @@ static int dm_add_exception(void *context, chunk_t old, chunk_t new) /* Consecutive_count is implicitly initialised to zero */ e->new_chunk = new; - /* - * Although there is no need to lock access to the exception tables - * here, if we don't then hlist_bl_add_head(), called by - * dm_insert_exception(), will complain about accessing the - * corresponding list without locking it first. - */ - dm_exception_table_lock_init(s, old, &lock); - - dm_exception_table_lock(&lock); dm_insert_exception(&s->complete, e); - dm_exception_table_unlock(&lock); return 0; } @@ -873,7 +868,7 @@ static int calc_max_buckets(void) /* use a fixed size of 2MB */ unsigned long mem = 2 * 1024 * 1024; - mem /= sizeof(struct hlist_bl_head); + mem /= sizeof(struct dm_hlist_head); return mem; } diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 72047b47a7a0a3..e41bde1d3b15b8 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -413,10 +413,8 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, if (!verity_fec_is_enabled(v)) return -EOPNOTSUPP; - if (fio->level >= DM_VERITY_FEC_MAX_RECURSION) { - DMWARN_LIMIT("%s: FEC: recursion too deep", v->data_dev->name); + if (fio->level) return -EIO; - } fio->level++; diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h index 09123a61295387..ec37e607cb3f09 100644 --- a/drivers/md/dm-verity-fec.h +++ b/drivers/md/dm-verity-fec.h @@ -23,9 +23,6 @@ #define DM_VERITY_FEC_BUF_MAX \ (1 << (PAGE_SHIFT - DM_VERITY_FEC_BUF_RS_BITS)) -/* maximum recursion level for verity_fec_decode */ -#define DM_VERITY_FEC_MAX_RECURSION 4 - #define DM_VERITY_OPT_FEC_DEV "use_fec_from_device" #define DM_VERITY_OPT_FEC_BLOCKS "fec_blocks" #define DM_VERITY_OPT_FEC_START "fec_start" diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 66a00a8ccb398b..c8695c079cfe08 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -1690,7 +1690,7 @@ static struct target_type verity_target = { .name = "verity", /* Note: the LSMs depend on the singleton and immutable features */ .features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE, - .version = {1, 12, 0}, + .version = {1, 13, 0}, .module = THIS_MODULE, .ctr = verity_ctr, .dtr = verity_dtr, diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c index 78e17dd4d01b82..f4950b5f766d3b 100644 --- a/drivers/md/dm-zone.c +++ b/drivers/md/dm-zone.c @@ -56,7 +56,7 @@ int dm_blk_report_zones(struct gendisk *disk, sector_t sector, { struct mapped_device *md = disk->private_data; struct dm_table *map; - struct dm_table *zone_revalidate_map = md->zone_revalidate_map; + struct dm_table *zone_revalidate_map = READ_ONCE(md->zone_revalidate_map); int srcu_idx, ret = -EIO; bool put_table = false; @@ -66,11 +66,13 @@ int dm_blk_report_zones(struct gendisk *disk, sector_t sector, * Zone revalidation during __bind() is in progress, but this * call is from a different process */ - if (dm_suspended_md(md)) - return -EAGAIN; - map = dm_get_live_table(md, &srcu_idx); put_table = true; + + if (dm_suspended_md(md)) { + ret = -EAGAIN; + goto do_put_table; + } } else { /* Zone revalidation during __bind() */ map = zone_revalidate_map; @@ -80,6 +82,7 @@ int dm_blk_report_zones(struct gendisk *disk, sector_t sector, ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb, data); +do_put_table: if (put_table) dm_put_live_table(md, srcu_idx); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 6c83ab940af752..52f01c44e73a6c 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1363,6 +1363,8 @@ void dm_submit_bio_remap(struct bio *clone, struct bio *tgt_clone) if (!tgt_clone) tgt_clone = clone; + bio_clone_blkg_association(tgt_clone, io->orig_bio); + /* * Account io->origin_bio to DM dev on behalf of target * that took ownership of IO with DM_MAPIO_SUBMITTED. diff --git a/drivers/md/md-llbitmap.c b/drivers/md/md-llbitmap.c index 1eb434306162a5..bcb6eae1c711f6 100644 --- a/drivers/md/md-llbitmap.c +++ b/drivers/md/md-llbitmap.c @@ -712,8 +712,10 @@ static int llbitmap_suspend_timeout(struct llbitmap *llbitmap, int page_idx) percpu_ref_kill(&pctl->active); if (!wait_event_timeout(pctl->wait, percpu_ref_is_zero(&pctl->active), - llbitmap->mddev->bitmap_info.daemon_sleep * HZ)) + llbitmap->mddev->bitmap_info.daemon_sleep * HZ)) { + percpu_ref_resurrect(&pctl->active); return -ETIMEDOUT; + } return 0; } diff --git a/drivers/md/md.c b/drivers/md/md.c index 41c476b40c7a30..e04ddcb03981c9 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -99,7 +99,7 @@ static int remove_and_add_spares(struct mddev *mddev, struct md_rdev *this); static void mddev_detach(struct mddev *mddev); static void export_rdev(struct md_rdev *rdev, struct mddev *mddev); -static void md_wakeup_thread_directly(struct md_thread __rcu *thread); +static void md_wakeup_thread_directly(struct md_thread __rcu **thread); /* * Default number of read corrections we'll attempt on an rdev @@ -730,6 +730,8 @@ static void mddev_clear_bitmap_ops(struct mddev *mddev) int mddev_init(struct mddev *mddev) { + int err = 0; + if (!IS_ENABLED(CONFIG_MD_BITMAP)) mddev->bitmap_id = ID_BITMAP_NONE; else @@ -741,10 +743,23 @@ int mddev_init(struct mddev *mddev) if (percpu_ref_init(&mddev->writes_pending, no_op, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { - percpu_ref_exit(&mddev->active_io); - return -ENOMEM; + err = -ENOMEM; + goto exit_acitve_io; } + err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); + if (err) + goto exit_writes_pending; + + err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); + if (err) + goto exit_bio_set; + + err = bioset_init(&mddev->io_clone_set, BIO_POOL_SIZE, + offsetof(struct md_io_clone, bio_clone), 0); + if (err) + goto exit_sync_set; + /* We want to start with the refcount at zero */ percpu_ref_put(&mddev->writes_pending); @@ -773,11 +788,24 @@ int mddev_init(struct mddev *mddev) INIT_WORK(&mddev->del_work, mddev_delayed_delete); return 0; + +exit_sync_set: + bioset_exit(&mddev->sync_set); +exit_bio_set: + bioset_exit(&mddev->bio_set); +exit_writes_pending: + percpu_ref_exit(&mddev->writes_pending); +exit_acitve_io: + percpu_ref_exit(&mddev->active_io); + return err; } EXPORT_SYMBOL_GPL(mddev_init); void mddev_destroy(struct mddev *mddev) { + bioset_exit(&mddev->bio_set); + bioset_exit(&mddev->sync_set); + bioset_exit(&mddev->io_clone_set); percpu_ref_exit(&mddev->active_io); percpu_ref_exit(&mddev->writes_pending); } @@ -941,8 +969,11 @@ void mddev_unlock(struct mddev *mddev) * do_md_stop. dm raid only uses md_stop to stop. So dm raid * doesn't need to check MD_DELETED when getting reconfig lock */ - if (test_bit(MD_DELETED, &mddev->flags)) + if (test_bit(MD_DELETED, &mddev->flags) && + !test_and_set_bit(MD_DO_DELETE, &mddev->flags)) { + kobject_del(&mddev->kobj); del_gendisk(mddev->gendisk); + } } } EXPORT_SYMBOL_GPL(mddev_unlock); @@ -3843,7 +3874,6 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe static int analyze_sbs(struct mddev *mddev) { - int i; struct md_rdev *rdev, *freshest, *tmp; freshest = NULL; @@ -3870,11 +3900,9 @@ static int analyze_sbs(struct mddev *mddev) super_types[mddev->major_version]. validate_super(mddev, NULL/*freshest*/, freshest); - i = 0; rdev_for_each_safe(rdev, tmp, mddev) { if (mddev->max_disks && - (rdev->desc_nr >= mddev->max_disks || - i > mddev->max_disks)) { + rdev->desc_nr >= mddev->max_disks) { pr_warn("md: %s: %pg: only %d devices permitted\n", mdname(mddev), rdev->bdev, mddev->max_disks); @@ -4368,7 +4396,7 @@ raid_disks_store(struct mddev *mddev, const char *buf, size_t len) if (err < 0) return err; - err = mddev_lock(mddev); + err = mddev_suspend_and_lock(mddev); if (err) return err; if (mddev->pers) @@ -4393,7 +4421,7 @@ raid_disks_store(struct mddev *mddev, const char *buf, size_t len) } else mddev->raid_disks = n; out_unlock: - mddev_unlock(mddev); + mddev_unlock_and_resume(mddev); return err ? err : len; } static struct md_sysfs_entry md_raid_disks = @@ -5134,7 +5162,7 @@ static void stop_sync_thread(struct mddev *mddev, bool locked) * Thread might be blocked waiting for metadata update which will now * never happen */ - md_wakeup_thread_directly(mddev->sync_thread); + md_wakeup_thread_directly(&mddev->sync_thread); if (work_pending(&mddev->sync_work)) flush_work(&mddev->sync_work); @@ -6384,29 +6412,9 @@ int md_run(struct mddev *mddev) nowait = nowait && bdev_nowait(rdev->bdev); } - if (!bioset_initialized(&mddev->bio_set)) { - err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); - if (err) - return err; - } - if (!bioset_initialized(&mddev->sync_set)) { - err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); - if (err) - goto exit_bio_set; - } - - if (!bioset_initialized(&mddev->io_clone_set)) { - err = bioset_init(&mddev->io_clone_set, BIO_POOL_SIZE, - offsetof(struct md_io_clone, bio_clone), 0); - if (err) - goto exit_sync_set; - } - pers = get_pers(mddev->level, mddev->clevel); - if (!pers) { - err = -EINVAL; - goto abort; - } + if (!pers) + return -EINVAL; if (mddev->level != pers->head.id) { mddev->level = pers->head.id; mddev->new_level = pers->head.id; @@ -6417,8 +6425,7 @@ int md_run(struct mddev *mddev) pers->start_reshape == NULL) { /* This personality cannot handle reshaping... */ put_pers(pers); - err = -EINVAL; - goto abort; + return -EINVAL; } if (pers->sync_request) { @@ -6545,12 +6552,6 @@ int md_run(struct mddev *mddev) mddev->private = NULL; put_pers(pers); md_bitmap_destroy(mddev); -abort: - bioset_exit(&mddev->io_clone_set); -exit_sync_set: - bioset_exit(&mddev->sync_set); -exit_bio_set: - bioset_exit(&mddev->bio_set); return err; } EXPORT_SYMBOL_GPL(md_run); @@ -6775,10 +6776,6 @@ static void __md_stop(struct mddev *mddev) mddev->private = NULL; put_pers(pers); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - - bioset_exit(&mddev->bio_set); - bioset_exit(&mddev->sync_set); - bioset_exit(&mddev->io_clone_set); } void md_stop(struct mddev *mddev) @@ -6869,6 +6866,10 @@ static int do_md_stop(struct mddev *mddev, int mode) if (!md_is_rdwr(mddev)) set_disk_ro(disk, 0); + if (mode == 2 && mddev->pers->sync_request && + mddev->to_remove == NULL) + mddev->to_remove = &md_redundancy_group; + __md_stop_writes(mddev); __md_stop(mddev); @@ -8373,22 +8374,21 @@ static int md_thread(void *arg) return 0; } -static void md_wakeup_thread_directly(struct md_thread __rcu *thread) +static void md_wakeup_thread_directly(struct md_thread __rcu **thread) { struct md_thread *t; rcu_read_lock(); - t = rcu_dereference(thread); + t = rcu_dereference(*thread); if (t) wake_up_process(t->tsk); rcu_read_unlock(); } -void md_wakeup_thread(struct md_thread __rcu *thread) +void __md_wakeup_thread(struct md_thread __rcu *thread) { struct md_thread *t; - rcu_read_lock(); t = rcu_dereference(thread); if (t) { pr_debug("md: waking up MD thread %s.\n", t->tsk->comm); @@ -8396,9 +8396,8 @@ void md_wakeup_thread(struct md_thread __rcu *thread) if (wq_has_sleeper(&t->wqueue)) wake_up(&t->wqueue); } - rcu_read_unlock(); } -EXPORT_SYMBOL(md_wakeup_thread); +EXPORT_SYMBOL(__md_wakeup_thread); struct md_thread *md_register_thread(void (*run) (struct md_thread *), struct mddev *mddev, const char *name) diff --git a/drivers/md/md.h b/drivers/md/md.h index 1979c2d4fe89e9..9d66afb8cc6e6c 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -354,6 +354,7 @@ enum mddev_flags { MD_HAS_MULTIPLE_PPLS, MD_NOT_READY, MD_BROKEN, + MD_DO_DELETE, MD_DELETED, }; @@ -735,8 +736,8 @@ static inline int mddev_trylock(struct mddev *mddev) int ret; ret = mutex_trylock(&mddev->reconfig_mutex); - if (!ret && test_bit(MD_DELETED, &mddev->flags)) { - ret = -ENODEV; + if (ret && test_bit(MD_DELETED, &mddev->flags)) { + ret = 0; mutex_unlock(&mddev->reconfig_mutex); } return ret; @@ -882,6 +883,12 @@ struct md_io_clone { #define THREAD_WAKEUP 0 +#define md_wakeup_thread(thread) do { \ + rcu_read_lock(); \ + __md_wakeup_thread(thread); \ + rcu_read_unlock(); \ +} while (0) + static inline void safe_put_page(struct page *p) { if (p) put_page(p); @@ -895,7 +902,7 @@ extern struct md_thread *md_register_thread( struct mddev *mddev, const char *name); extern void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **threadp); -extern void md_wakeup_thread(struct md_thread __rcu *thread); +extern void __md_wakeup_thread(struct md_thread __rcu *thread); extern void md_check_recovery(struct mddev *mddev); extern void md_reap_sync_thread(struct mddev *mddev); extern enum sync_action md_sync_action(struct mddev *mddev); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 592a4023300474..ce7fd688695666 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -3253,6 +3253,7 @@ static int raid1_run(struct mddev *mddev) if (!mddev_is_dm(mddev)) { ret = raid1_set_limits(mddev); if (ret) { + md_unregister_thread(mddev, &conf->thread); if (!mddev->private) raid1_free(mddev, conf); return ret; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 14dcd5142eb477..d58ae150b45022 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3402,7 +3402,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, !test_bit(In_sync, &rdev->flags)) continue; /* This is where we read from */ - any_working = 1; sector = r10_bio->devs[j].addr; if (is_badblock(rdev, sector, max_sync, @@ -3417,6 +3416,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, continue; } } + any_working = 1; bio = r10_bio->devs[0].bio; bio->bi_next = biolist; biolist = bio; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 24b32a0c95b403..3b711a1198adbe 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3751,9 +3751,14 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s, struct r5dev *dev = &sh->dev[disk_idx]; struct r5dev *fdev[2] = { &sh->dev[s->failed_num[0]], &sh->dev[s->failed_num[1]] }; + struct mddev *mddev = sh->raid_conf->mddev; + bool force_rcw = false; int i; - bool force_rcw = (sh->raid_conf->rmw_level == PARITY_DISABLE_RMW); + if (sh->raid_conf->rmw_level == PARITY_DISABLE_RMW || + (mddev->bitmap_ops && mddev->bitmap_ops->blocks_synced && + !mddev->bitmap_ops->blocks_synced(mddev, sh->sector))) + force_rcw = true; if (test_bit(R5_LOCKED, &dev->flags) || test_bit(R5_UPTODATE, &dev->flags)) @@ -4956,7 +4961,8 @@ static void handle_stripe(struct stripe_head *sh) goto finish; if (s.handle_bad_blocks || - test_bit(MD_SB_CHANGE_PENDING, &conf->mddev->sb_flags)) { + (md_is_rdwr(conf->mddev) && + test_bit(MD_SB_CHANGE_PENDING, &conf->mddev->sb_flags))) { set_bit(STRIPE_HANDLE, &sh->state); goto finish; } @@ -6768,7 +6774,8 @@ static void raid5d(struct md_thread *thread) int batch_size, released; unsigned int offset; - if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) + if (md_is_rdwr(mddev) && + test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) break; released = release_stripe_list(conf, conf->temp_inactive_list); @@ -7185,12 +7192,14 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) err = mddev_suspend_and_lock(mddev); if (err) return err; + conf = mddev->private; + if (!conf) { + mddev_unlock_and_resume(mddev); + return -ENODEV; + } raid5_quiesce(mddev, true); - conf = mddev->private; - if (!conf) - err = -ENODEV; - else if (new != conf->worker_cnt_per_group) { + if (new != conf->worker_cnt_per_group) { old_groups = conf->worker_groups; if (old_groups) flush_workqueue(raid5_wq); @@ -8052,7 +8061,8 @@ static int raid5_run(struct mddev *mddev) goto abort; } - if (log_init(conf, journal_dev, raid5_has_ppl(conf))) + ret = log_init(conf, journal_dev, raid5_has_ppl(conf)); + if (ret) goto abort; return 0; diff --git a/drivers/media/cec/core/cec-core.c b/drivers/media/cec/core/cec-core.c index d7259599029f8b..dd6e24a0899bda 100644 --- a/drivers/media/cec/core/cec-core.c +++ b/drivers/media/cec/core/cec-core.c @@ -421,6 +421,7 @@ static int __init cec_devnode_init(void) ret = bus_register(&cec_bus_type); if (ret < 0) { + debugfs_remove_recursive(top_cec_dir); unregister_chrdev_region(cec_dev_t, CEC_NUM_DEVICES); pr_warn("cec: bus_register failed\n"); return -EIO; diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c index a13ec569c82f6d..7123c5fae92cee 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c @@ -258,6 +258,7 @@ static void *vb2_dc_alloc(struct vb2_buffer *vb, if (ret) { dev_err(dev, "dma alloc of size %lu failed\n", size); + put_device(buf->dev); kfree(buf); return ERR_PTR(-ENOMEM); } diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c index b3bf2173c14e1b..7c30731cb9a57b 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c @@ -345,6 +345,7 @@ static int vb2_dma_sg_mmap(void *buf_priv, struct vm_area_struct *vma) return err; } + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); /* * Use common vm_area operations to track buffer refcount. */ diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c index 8fe7c2f728839c..516553fb17e983 100644 --- a/drivers/media/i2c/adv7604.c +++ b/drivers/media/i2c/adv7604.c @@ -3670,7 +3670,7 @@ static int adv76xx_probe(struct i2c_client *client) err = media_entity_pads_init(&sd->entity, state->source_pad + 1, state->pads); if (err) - goto err_work_queues; + goto err_i2c; /* Configure regmaps */ err = configure_regmaps(state); @@ -3711,8 +3711,6 @@ static int adv76xx_probe(struct i2c_client *client) err_entity: media_entity_cleanup(&sd->entity); -err_work_queues: - cancel_delayed_work(&state->delayed_work_enable_hotplug); err_i2c: adv76xx_unregister_clients(state); err_hdl: diff --git a/drivers/media/i2c/adv7842.c b/drivers/media/i2c/adv7842.c index 9780082db8415a..21c3d3682e0b45 100644 --- a/drivers/media/i2c/adv7842.c +++ b/drivers/media/i2c/adv7842.c @@ -2699,6 +2699,7 @@ static int adv7842_cp_log_status(struct v4l2_subdev *sd) /* CP block */ struct adv7842_state *state = to_state(sd); struct v4l2_dv_timings timings; + int temp; u8 reg_io_0x02 = io_read(sd, 0x02); u8 reg_io_0x21 = io_read(sd, 0x21); u8 reg_rep_0x77 = rep_read(sd, 0x77); @@ -2821,8 +2822,9 @@ static int adv7842_cp_log_status(struct v4l2_subdev *sd) (((reg_io_0x02 >> 2) & 0x01) ^ (reg_io_0x02 & 0x01)) ? "(16-235)" : "(0-255)", (reg_io_0x02 & 0x08) ? "enabled" : "disabled"); + temp = cp_read(sd, 0xf4) >> 4; v4l2_info(sd, "Color space conversion: %s\n", - csc_coeff_sel_rb[cp_read(sd, 0xf4) >> 4]); + temp < 0 ? "" : csc_coeff_sel_rb[temp]); if (!is_digital_input(sd)) return 0; @@ -2852,8 +2854,9 @@ static int adv7842_cp_log_status(struct v4l2_subdev *sd) hdmi_read(sd, 0x5f)); v4l2_info(sd, "AV Mute: %s\n", (hdmi_read(sd, 0x04) & 0x40) ? "on" : "off"); + temp = hdmi_read(sd, 0x0b) >> 6; v4l2_info(sd, "Deep color mode: %s\n", - deep_color_mode_txt[hdmi_read(sd, 0x0b) >> 6]); + temp < 0 ? "" : deep_color_mode_txt[temp]); adv7842_log_infoframes(sd); @@ -3626,7 +3629,7 @@ static int adv7842_probe(struct i2c_client *client) err = media_entity_pads_init(&sd->entity, ADV7842_PAD_SOURCE + 1, state->pads); if (err) - goto err_work_queues; + goto err_i2c; err = adv7842_core_init(sd); if (err) @@ -3647,8 +3650,6 @@ static int adv7842_probe(struct i2c_client *client) err_entity: media_entity_cleanup(&sd->entity); -err_work_queues: - cancel_delayed_work(&state->delayed_work_enable_hotplug); err_i2c: adv7842_unregister_clients(sd); err_hdl: diff --git a/drivers/media/i2c/ccs/ccs-core.c b/drivers/media/i2c/ccs/ccs-core.c index 1c889c878abd3a..08e78f0bf25284 100644 --- a/drivers/media/i2c/ccs/ccs-core.c +++ b/drivers/media/i2c/ccs/ccs-core.c @@ -3425,7 +3425,21 @@ static int ccs_probe(struct i2c_client *client) sensor->scale_m = CCS_LIM(sensor, SCALER_N_MIN); /* prepare PLL configuration input values */ - sensor->pll.bus_type = CCS_PLL_BUS_TYPE_CSI2_DPHY; + switch (sensor->hwcfg.csi_signalling_mode) { + case CCS_CSI_SIGNALING_MODE_CSI_2_CPHY: + sensor->pll.bus_type = CCS_PLL_BUS_TYPE_CSI2_CPHY; + break; + case CCS_CSI_SIGNALING_MODE_CSI_2_DPHY: + case SMIAPP_CSI_SIGNALLING_MODE_CCP2_DATA_CLOCK: + case SMIAPP_CSI_SIGNALLING_MODE_CCP2_DATA_STROBE: + sensor->pll.bus_type = CCS_PLL_BUS_TYPE_CSI2_DPHY; + break; + default: + dev_err(&client->dev, "unsupported signalling mode %u\n", + sensor->hwcfg.csi_signalling_mode); + rval = -EINVAL; + goto out_cleanup; + } sensor->pll.csi2.lanes = sensor->hwcfg.lanes; if (CCS_LIM(sensor, CLOCK_CALCULATION) & CCS_CLOCK_CALCULATION_LANE_SPEED) { diff --git a/drivers/media/i2c/imx219.c b/drivers/media/i2c/imx219.c index c680aa6c3a55a9..300935b1ef2497 100644 --- a/drivers/media/i2c/imx219.c +++ b/drivers/media/i2c/imx219.c @@ -856,7 +856,7 @@ static int imx219_set_pad_format(struct v4l2_subdev *sd, const struct imx219_mode *mode; struct v4l2_mbus_framefmt *format; struct v4l2_rect *crop; - u8 bin_h, bin_v; + u8 bin_h, bin_v, binning; u32 prev_line_len; format = v4l2_subdev_state_get_format(state, 0); @@ -877,9 +877,12 @@ static int imx219_set_pad_format(struct v4l2_subdev *sd, bin_h = min(IMX219_PIXEL_ARRAY_WIDTH / format->width, 2U); bin_v = min(IMX219_PIXEL_ARRAY_HEIGHT / format->height, 2U); + /* Ensure bin_h and bin_v are same to avoid 1:2 or 2:1 stretching */ + binning = min(bin_h, bin_v); + crop = v4l2_subdev_state_get_crop(state, 0); - crop->width = format->width * bin_h; - crop->height = format->height * bin_v; + crop->width = format->width * binning; + crop->height = format->height * binning; crop->left = (IMX219_NATIVE_WIDTH - crop->width) / 2; crop->top = (IMX219_NATIVE_HEIGHT - crop->height) / 2; diff --git a/drivers/media/i2c/msp3400-kthreads.c b/drivers/media/i2c/msp3400-kthreads.c index ecabc0e1d32e6e..1d9f41dd7c212c 100644 --- a/drivers/media/i2c/msp3400-kthreads.c +++ b/drivers/media/i2c/msp3400-kthreads.c @@ -596,6 +596,8 @@ int msp3400c_thread(void *data) "carrier2 val: %5d / %s\n", val, cd[i].name); } + if (max1 < 0 || max1 > 3) + goto restart; /* program the msp3400 according to the results */ state->main = msp3400c_carrier_detect_main[max1].cdo; switch (max1) { diff --git a/drivers/media/i2c/tda1997x.c b/drivers/media/i2c/tda1997x.c index 1087d2bddaf29f..3532766cd795d3 100644 --- a/drivers/media/i2c/tda1997x.c +++ b/drivers/media/i2c/tda1997x.c @@ -2797,7 +2797,6 @@ static int tda1997x_probe(struct i2c_client *client) err_free_handler: v4l2_ctrl_handler_free(&state->hdl); err_free_mutex: - cancel_delayed_work(&state->delayed_work_enable_hpd); mutex_destroy(&state->page_lock); mutex_destroy(&state->lock); tda1997x_set_power(state, 0); diff --git a/drivers/media/pci/mgb4/mgb4_trigger.c b/drivers/media/pci/mgb4/mgb4_trigger.c index d7dddc5c8728e8..10c23f0c833d59 100644 --- a/drivers/media/pci/mgb4/mgb4_trigger.c +++ b/drivers/media/pci/mgb4/mgb4_trigger.c @@ -114,7 +114,7 @@ static int probe_trigger(struct iio_dev *indio_dev, int irq) if (!st->trig) return -ENOMEM; - ret = request_irq(irq, &iio_trigger_generic_data_rdy_poll, 0, + ret = request_irq(irq, &iio_trigger_generic_data_rdy_poll, IRQF_NO_THREAD, "mgb4-trigger", st->trig); if (ret) goto error_free_trig; diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig index 9287faafdce587..26c8cff57c38ab 100644 --- a/drivers/media/platform/Kconfig +++ b/drivers/media/platform/Kconfig @@ -65,6 +65,7 @@ config VIDEO_MUX source "drivers/media/platform/allegro-dvt/Kconfig" source "drivers/media/platform/amlogic/Kconfig" source "drivers/media/platform/amphion/Kconfig" +source "drivers/media/platform/apple/Kconfig" source "drivers/media/platform/aspeed/Kconfig" source "drivers/media/platform/atmel/Kconfig" source "drivers/media/platform/broadcom/Kconfig" diff --git a/drivers/media/platform/Makefile b/drivers/media/platform/Makefile index 6fd7db0541c7ec..e8d019518cde7f 100644 --- a/drivers/media/platform/Makefile +++ b/drivers/media/platform/Makefile @@ -8,6 +8,7 @@ obj-y += allegro-dvt/ obj-y += amlogic/ obj-y += amphion/ +obj-y += apple/ obj-y += aspeed/ obj-y += atmel/ obj-y += broadcom/ diff --git a/drivers/media/platform/amphion/vpu_malone.c b/drivers/media/platform/amphion/vpu_malone.c index ba688566dffd04..80802975c4f162 100644 --- a/drivers/media/platform/amphion/vpu_malone.c +++ b/drivers/media/platform/amphion/vpu_malone.c @@ -1337,22 +1337,18 @@ static int vpu_malone_insert_scode_vc1_g_seq(struct malone_scode_t *scode) { if (!scode->inst->total_input_count) return 0; - if (vpu_vb_is_codecconfig(to_vb2_v4l2_buffer(scode->vb))) - scode->need_data = 0; return 0; } static int vpu_malone_insert_scode_vc1_g_pic(struct malone_scode_t *scode) { - struct vb2_v4l2_buffer *vbuf; u8 nal_hdr[MALONE_VC1_NAL_HEADER_LEN]; u32 *data = NULL; int ret; - vbuf = to_vb2_v4l2_buffer(scode->vb); data = vb2_plane_vaddr(scode->vb, 0); - if (scode->inst->total_input_count == 0 || vpu_vb_is_codecconfig(vbuf)) + if (scode->inst->total_input_count == 0) return 0; if (MALONE_VC1_CONTAIN_NAL(*data)) return 0; @@ -1373,8 +1369,6 @@ static int vpu_malone_insert_scode_vc1_l_seq(struct malone_scode_t *scode) int size = 0; u8 rcv_seqhdr[MALONE_VC1_RCV_SEQ_HEADER_LEN]; - if (vpu_vb_is_codecconfig(to_vb2_v4l2_buffer(scode->vb))) - scode->need_data = 0; if (scode->inst->total_input_count) return 0; scode->need_data = 0; @@ -1560,7 +1554,7 @@ static int vpu_malone_input_frame_data(struct vpu_malone_str_buffer __iomem *str scode.vb = vb; scode.wptr = wptr; scode.need_data = 1; - if (vbuf->sequence == 0 || vpu_vb_is_codecconfig(vbuf)) + if (vbuf->sequence == 0) ret = vpu_malone_insert_scode(&scode, SCODE_SEQUENCE); if (ret < 0) @@ -1596,7 +1590,7 @@ static int vpu_malone_input_frame_data(struct vpu_malone_str_buffer __iomem *str * This module is currently only supported for the H264 and HEVC formats, * for other formats, vpu_malone_add_scode() will return 0. */ - if ((disp_imm || low_latency) && !vpu_vb_is_codecconfig(vbuf)) { + if (disp_imm || low_latency) { ret = vpu_malone_add_scode(inst->core->iface, inst->id, &inst->stream_buffer, @@ -1643,7 +1637,6 @@ int vpu_malone_input_frame(struct vpu_shared_addr *shared, struct vpu_inst *inst, struct vb2_buffer *vb) { struct vpu_dec_ctrl *hc = shared->priv; - struct vb2_v4l2_buffer *vbuf; struct vpu_malone_str_buffer __iomem *str_buf = hc->str_buf[inst->id]; u32 disp_imm = hc->codec_param[inst->id].disp_imm; u32 size; @@ -1657,16 +1650,6 @@ int vpu_malone_input_frame(struct vpu_shared_addr *shared, return ret; size = ret; - /* - * if buffer only contain codec data, and the timestamp is invalid, - * don't put the invalid timestamp to resync - * merge the data to next frame - */ - vbuf = to_vb2_v4l2_buffer(vb); - if (vpu_vb_is_codecconfig(vbuf)) { - inst->extra_size += size; - return 0; - } if (inst->extra_size) { size += inst->extra_size; inst->extra_size = 0; diff --git a/drivers/media/platform/amphion/vpu_v4l2.c b/drivers/media/platform/amphion/vpu_v4l2.c index fcb2eff813ac45..47dff9a35bb46d 100644 --- a/drivers/media/platform/amphion/vpu_v4l2.c +++ b/drivers/media/platform/amphion/vpu_v4l2.c @@ -349,16 +349,6 @@ struct vb2_v4l2_buffer *vpu_next_src_buf(struct vpu_inst *inst) if (!src_buf || vpu_get_buffer_state(src_buf) == VPU_BUF_STATE_IDLE) return NULL; - while (vpu_vb_is_codecconfig(src_buf)) { - v4l2_m2m_src_buf_remove(inst->fh.m2m_ctx); - vpu_set_buffer_state(src_buf, VPU_BUF_STATE_IDLE); - v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE); - - src_buf = v4l2_m2m_next_src_buf(inst->fh.m2m_ctx); - if (!src_buf || vpu_get_buffer_state(src_buf) == VPU_BUF_STATE_IDLE) - return NULL; - } - return src_buf; } @@ -713,15 +703,15 @@ static int vpu_v4l2_release(struct vpu_inst *inst) { vpu_trace(inst->vpu->dev, "%p\n", inst); - vpu_release_core(inst->core); - put_device(inst->dev); - if (inst->workqueue) { cancel_work_sync(&inst->msg_work); destroy_workqueue(inst->workqueue); inst->workqueue = NULL; } + vpu_release_core(inst->core); + put_device(inst->dev); + v4l2_ctrl_handler_free(&inst->ctrl_handler); mutex_destroy(&inst->lock); diff --git a/drivers/media/platform/amphion/vpu_v4l2.h b/drivers/media/platform/amphion/vpu_v4l2.h index 4a87b06ae52030..da9945f25e327f 100644 --- a/drivers/media/platform/amphion/vpu_v4l2.h +++ b/drivers/media/platform/amphion/vpu_v4l2.h @@ -39,14 +39,4 @@ static inline struct vpu_format *vpu_get_format(struct vpu_inst *inst, u32 type) else return &inst->cap_format; } - -static inline int vpu_vb_is_codecconfig(struct vb2_v4l2_buffer *vbuf) -{ -#ifdef V4L2_BUF_FLAG_CODECCONFIG - return (vbuf->flags & V4L2_BUF_FLAG_CODECCONFIG) ? 1 : 0; -#else - return 0; -#endif -} - #endif diff --git a/drivers/media/platform/apple/Kconfig b/drivers/media/platform/apple/Kconfig new file mode 100644 index 00000000000000..f16508bff5242a --- /dev/null +++ b/drivers/media/platform/apple/Kconfig @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0-only + +comment "Apple media platform drivers" + +source "drivers/media/platform/apple/isp/Kconfig" diff --git a/drivers/media/platform/apple/Makefile b/drivers/media/platform/apple/Makefile new file mode 100644 index 00000000000000..d8fe985b0e6c37 --- /dev/null +++ b/drivers/media/platform/apple/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-y += isp/ diff --git a/drivers/media/platform/apple/isp/.gitignore b/drivers/media/platform/apple/isp/.gitignore new file mode 100644 index 00000000000000..bd7fab40e0d98a --- /dev/null +++ b/drivers/media/platform/apple/isp/.gitignore @@ -0,0 +1 @@ +.clang-format diff --git a/drivers/media/platform/apple/isp/Kconfig b/drivers/media/platform/apple/isp/Kconfig new file mode 100644 index 00000000000000..5695bef44adf5b --- /dev/null +++ b/drivers/media/platform/apple/isp/Kconfig @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config VIDEO_APPLE_ISP + tristate "Apple Silicon Image Signal Processor driver" + select VIDEOBUF2_CORE + select VIDEOBUF2_V4L2 + select VIDEOBUF2_DMA_SG + depends on ARCH_APPLE || COMPILE_TEST + depends on OF_ADDRESS + depends on V4L_PLATFORM_DRIVERS + depends on VIDEO_DEV diff --git a/drivers/media/platform/apple/isp/Makefile b/drivers/media/platform/apple/isp/Makefile new file mode 100644 index 00000000000000..4649f32987f025 --- /dev/null +++ b/drivers/media/platform/apple/isp/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only +apple-isp-y := isp-cam.o isp-cmd.o isp-drv.o isp-fw.o isp-iommu.o isp-ipc.o isp-v4l2.o +obj-$(CONFIG_VIDEO_APPLE_ISP) += apple-isp.o diff --git a/drivers/media/platform/apple/isp/isp-cam.c b/drivers/media/platform/apple/isp/isp-cam.c new file mode 100644 index 00000000000000..c889173bd348f3 --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-cam.c @@ -0,0 +1,498 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#include + +#include "isp-cam.h" +#include "isp-cmd.h" +#include "isp-fw.h" +#include "isp-iommu.h" + +#define ISP_MAX_PRESETS 32 + +struct isp_setfile { + u32 version; + u32 magic; + const char *path; + size_t size; +}; + +// clang-format off +static const struct isp_setfile isp_setfiles[] = { + [ISP_IMX248_1820_01] = {0x248, 0x18200103, "apple/isp_1820_01XX.dat", 0x442c}, + [ISP_IMX248_1822_02] = {0x248, 0x18220201, "apple/isp_1822_02XX.dat", 0x442c}, + [ISP_IMX343_5221_02] = {0x343, 0x52210211, "apple/isp_5221_02XX.dat", 0x4870}, + [ISP_IMX354_9251_02] = {0x354, 0x92510208, "apple/isp_9251_02XX.dat", 0xa5ec}, + [ISP_IMX356_4820_01] = {0x356, 0x48200107, "apple/isp_4820_01XX.dat", 0x9324}, + [ISP_IMX356_4820_02] = {0x356, 0x48200206, "apple/isp_4820_02XX.dat", 0x9324}, + [ISP_IMX364_8720_01] = {0x364, 0x87200103, "apple/isp_8720_01XX.dat", 0x36ac}, + [ISP_IMX364_8723_01] = {0x364, 0x87230101, "apple/isp_8723_01XX.dat", 0x361c}, + [ISP_IMX372_3820_01] = {0x372, 0x38200108, "apple/isp_3820_01XX.dat", 0xfdb0}, + [ISP_IMX372_3820_02] = {0x372, 0x38200205, "apple/isp_3820_02XX.dat", 0xfdb0}, + [ISP_IMX372_3820_11] = {0x372, 0x38201104, "apple/isp_3820_11XX.dat", 0xfdb0}, + [ISP_IMX372_3820_12] = {0x372, 0x38201204, "apple/isp_3820_12XX.dat", 0xfdb0}, + [ISP_IMX405_9720_01] = {0x405, 0x97200102, "apple/isp_9720_01XX.dat", 0x92c8}, + [ISP_IMX405_9721_01] = {0x405, 0x97210102, "apple/isp_9721_01XX.dat", 0x9818}, + [ISP_IMX405_9723_01] = {0x405, 0x97230101, "apple/isp_9723_01XX.dat", 0x92c8}, + [ISP_IMX414_2520_01] = {0x414, 0x25200102, "apple/isp_2520_01XX.dat", 0xa444}, + [ISP_IMX503_7820_01] = {0x503, 0x78200109, "apple/isp_7820_01XX.dat", 0xb268}, + [ISP_IMX503_7820_02] = {0x503, 0x78200206, "apple/isp_7820_02XX.dat", 0xb268}, + [ISP_IMX505_3921_01] = {0x505, 0x39210102, "apple/isp_3921_01XX.dat", 0x89b0}, + [ISP_IMX514_2820_01] = {0x514, 0x28200108, "apple/isp_2820_01XX.dat", 0xa198}, + [ISP_IMX514_2820_02] = {0x514, 0x28200205, "apple/isp_2820_02XX.dat", 0xa198}, + [ISP_IMX514_2820_03] = {0x514, 0x28200305, "apple/isp_2820_03XX.dat", 0xa198}, + [ISP_IMX514_2820_04] = {0x514, 0x28200405, "apple/isp_2820_04XX.dat", 0xa198}, + [ISP_IMX558_1921_01] = {0x558, 0x19210106, "apple/isp_1921_01XX.dat", 0xad40}, + [ISP_IMX558_1922_02] = {0x558, 0x19220201, "apple/isp_1922_02XX.dat", 0xad40}, + [ISP_IMX603_7920_01] = {0x603, 0x79200109, "apple/isp_7920_01XX.dat", 0xad2c}, + [ISP_IMX603_7920_02] = {0x603, 0x79200205, "apple/isp_7920_02XX.dat", 0xad2c}, + [ISP_IMX603_7921_01] = {0x603, 0x79210104, "apple/isp_7921_01XX.dat", 0xad90}, + [ISP_IMX613_4920_01] = {0x613, 0x49200108, "apple/isp_4920_01XX.dat", 0x9324}, + [ISP_IMX613_4920_02] = {0x613, 0x49200204, "apple/isp_4920_02XX.dat", 0x9324}, + [ISP_IMX614_2921_01] = {0x614, 0x29210107, "apple/isp_2921_01XX.dat", 0xed6c}, + [ISP_IMX614_2921_02] = {0x614, 0x29210202, "apple/isp_2921_02XX.dat", 0xed6c}, + [ISP_IMX614_2922_02] = {0x614, 0x29220201, "apple/isp_2922_02XX.dat", 0xed6c}, + [ISP_IMX633_3622_01] = {0x633, 0x36220111, "apple/isp_3622_01XX.dat", 0x100d4}, + [ISP_IMX703_7721_01] = {0x703, 0x77210106, "apple/isp_7721_01XX.dat", 0x936c}, + [ISP_IMX703_7722_01] = {0x703, 0x77220106, "apple/isp_7722_01XX.dat", 0xac20}, + [ISP_IMX713_4721_01] = {0x713, 0x47210107, "apple/isp_4721_01XX.dat", 0x936c}, + [ISP_IMX713_4722_01] = {0x713, 0x47220109, "apple/isp_4722_01XX.dat", 0x9218}, + [ISP_IMX714_2022_01] = {0x714, 0x20220107, "apple/isp_2022_01XX.dat", 0xa198}, + [ISP_IMX772_3721_01] = {0x772, 0x37210106, "apple/isp_3721_01XX.dat", 0xfdf8}, + [ISP_IMX772_3721_11] = {0x772, 0x37211106, "apple/isp_3721_11XX.dat", 0xfe14}, + [ISP_IMX772_3722_01] = {0x772, 0x37220104, "apple/isp_3722_01XX.dat", 0xfca4}, + [ISP_IMX772_3723_01] = {0x772, 0x37230106, "apple/isp_3723_01XX.dat", 0xfca4}, + [ISP_IMX814_2123_01] = {0x814, 0x21230101, "apple/isp_2123_01XX.dat", 0xed54}, + [ISP_IMX853_7622_01] = {0x853, 0x76220112, "apple/isp_7622_01XX.dat", 0x247f8}, + [ISP_IMX913_7523_01] = {0x913, 0x75230107, "apple/isp_7523_01XX.dat", 0x247f8}, + [ISP_VD56G0_6221_01] = {0xd56, 0x62210102, "apple/isp_6221_01XX.dat", 0x1b80}, + [ISP_VD56G0_6222_01] = {0xd56, 0x62220102, "apple/isp_6222_01XX.dat", 0x1b80}, +}; +// clang-format on + +static int isp_ch_get_sensor_id(struct apple_isp *isp, u32 ch) +{ + struct isp_format *fmt = isp_get_format(isp, ch); + enum isp_sensor_id id; + int err = 0; + + /* TODO need more datapoints to figure out the sub-versions + * Defaulting to 1st release for now, the calib files aren't too different. + */ + switch (fmt->version) { + case 0x248: + id = ISP_IMX248_1820_01; + break; + case 0x343: + id = ISP_IMX343_5221_02; + break; + case 0x354: + id = ISP_IMX354_9251_02; + break; + case 0x356: + id = ISP_IMX356_4820_01; + break; + case 0x364: + id = ISP_IMX364_8720_01; + break; + case 0x372: + id = ISP_IMX372_3820_01; + break; + case 0x405: + id = ISP_IMX405_9720_01; + break; + case 0x414: + id = ISP_IMX414_2520_01; + break; + case 0x503: + id = ISP_IMX503_7820_01; + break; + case 0x505: + id = ISP_IMX505_3921_01; + break; + case 0x514: + id = ISP_IMX514_2820_01; + break; + case 0x558: + id = ISP_IMX558_1921_01; + break; + case 0x603: + id = ISP_IMX603_7920_01; + break; + case 0x613: + id = ISP_IMX613_4920_01; + break; + case 0x614: + id = ISP_IMX614_2921_01; + break; + case 0x633: + id = ISP_IMX633_3622_01; + break; + case 0x703: + id = ISP_IMX703_7721_01; + break; + case 0x713: + id = ISP_IMX713_4721_01; + break; + case 0x714: + id = ISP_IMX714_2022_01; + break; + case 0x772: + id = ISP_IMX772_3721_01; + break; + case 0x814: + id = ISP_IMX814_2123_01; + break; + case 0x853: + id = ISP_IMX853_7622_01; + break; + case 0x913: + id = ISP_IMX913_7523_01; + break; + case 0xd56: + id = ISP_VD56G0_6221_01; + break; + default: + err = -EINVAL; + break; + } + + if (err) + dev_err(isp->dev, "invalid sensor version: 0x%x\n", + fmt->version); + else + fmt->id = id; + + return err; +} + +static int isp_ch_get_camera_preset(struct apple_isp *isp, u32 ch, u32 ps) +{ + int err = 0; + + struct cmd_ch_camera_config *args; /* Too big to allocate on stack */ + args = kzalloc(sizeof(*args), GFP_KERNEL); + if (!args) + return -ENOMEM; + + err = isp_cmd_ch_camera_config_get(isp, ch, ps, args); + if (err) + goto exit; + + pr_info("apple-isp: ps: CISP_CMD_CH_CAMERA_CONFIG_GET: %d\n", ps); + print_hex_dump(KERN_INFO, "apple-isp: ps: ", DUMP_PREFIX_NONE, 32, 4, + args, sizeof(*args), false); + +exit: + kfree(args); + + return err; +} + +static int isp_ch_cache_sensor_info(struct apple_isp *isp, u32 ch) +{ + struct isp_format *fmt = isp_get_format(isp, ch); + int err = 0; + + struct cmd_ch_info *args; /* Too big to allocate on stack */ + args = kzalloc(sizeof(*args), GFP_KERNEL); + if (!args) + return -ENOMEM; + + err = isp_cmd_ch_info_get(isp, ch, args); + if (err) + goto exit; + + dev_info(isp->dev, "found sensor %x %s on ch %d\n", args->version, + args->module_sn, ch); + + fmt->version = args->version; + + pr_info("apple-isp: ch: CISP_CMD_CH_INFO_GET: %d\n", ch); + print_hex_dump(KERN_INFO, "apple-isp: ch: ", DUMP_PREFIX_NONE, 32, 4, + args, sizeof(*args), false); + + for (u32 ps = 0; ps < args->num_presets; ps++) { + isp_ch_get_camera_preset(isp, ch, ps); + } + + err = isp_ch_get_sensor_id(isp, ch); + if (err || + (fmt->id != ISP_IMX248_1820_01 && fmt->id != ISP_IMX558_1921_01 && + fmt->id != ISP_IMX364_8720_01)) { + dev_err(isp->dev, + "ch %d: unsupported sensor. Please file a bug report with hardware info & dmesg trace.\n", + ch); + return -ENODEV; + } + +exit: + kfree(args); + + return err; +} + +static int isp_detect_camera(struct apple_isp *isp) +{ + int err; + + struct cmd_config_get args; + memset(&args, 0, sizeof(args)); + + err = isp_cmd_config_get(isp, &args); + if (err) + return err; + + pr_info("apple-isp: CISP_CMD_CONFIG_GET: \n"); + print_hex_dump(KERN_INFO, "apple-isp: ", DUMP_PREFIX_NONE, 32, 4, &args, + sizeof(args), false); + + if (!args.num_channels) { + dev_err(isp->dev, "did not detect any channels\n"); + return -ENODEV; + } + + if (args.num_channels > ISP_MAX_CHANNELS) { + dev_warn(isp->dev, "found %d channels when maximum is %d\n", + args.num_channels, ISP_MAX_CHANNELS); + args.num_channels = ISP_MAX_CHANNELS; + } + + if (args.num_channels > 1) { + dev_warn( + isp->dev, + "warning: driver doesn't support multiple channels. Please file a bug report with hardware info & dmesg trace.\n"); + } + + isp->num_channels = args.num_channels; + isp->current_ch = 0; + + err = isp_ch_cache_sensor_info(isp, isp->current_ch); + if (err) { + dev_err(isp->dev, "failed to cache sensor info\n"); + return err; + } + + return 0; +} + +int apple_isp_detect_camera(struct apple_isp *isp) +{ + int err; + + /* RPM must be enabled prior to calling this */ + err = apple_isp_firmware_boot(isp); + if (err) { + dev_err(isp->dev, + "failed to boot firmware for initial sensor detection: %d\n", + err); + return -EPROBE_DEFER; + } + + err = isp_detect_camera(isp); + + isp_cmd_flicker_sensor_set(isp, 0); + + isp_cmd_ch_stop(isp, 0); + isp_cmd_ch_buffer_return(isp, isp->current_ch); + + apple_isp_firmware_shutdown(isp); + + return err; +} + +static int isp_ch_load_setfile(struct apple_isp *isp, u32 ch) +{ + struct isp_format *fmt = isp_get_format(isp, ch); + const struct isp_setfile *setfile = &isp_setfiles[fmt->id]; + const struct firmware *fw; + u32 magic; + int err; + + err = request_firmware(&fw, setfile->path, isp->dev); + if (err) { + dev_err(isp->dev, "failed to request setfile '%s': %d\n", + setfile->path, err); + return err; + } + + if (fw->size < setfile->size) { + dev_err(isp->dev, "setfile too small (0x%lx/0x%zx)\n", fw->size, + setfile->size); + release_firmware(fw); + return -EINVAL; + } + + magic = be32_to_cpup((__be32 *)fw->data); + if (magic != setfile->magic) { + dev_err(isp->dev, "setfile '%s' corrupted?\n", setfile->path); + release_firmware(fw); + return -EINVAL; + } + + memcpy(isp->data_surf->virt, (void *)fw->data, setfile->size); + release_firmware(fw); + + return isp_cmd_ch_set_file_load(isp, ch, isp->data_surf->iova, + setfile->size); +} + +static int isp_ch_configure_capture(struct apple_isp *isp, u32 ch) +{ + struct isp_format *fmt = isp_get_format(isp, ch); + int err; + + isp_cmd_flicker_sensor_set(isp, 0); + + /* The setfile isn't requisite but then we don't get calibration */ + err = isp_ch_load_setfile(isp, ch); + if (err) { + dev_err(isp->dev, "warning: calibration data not loaded: %d\n", + err); + + /* If this failed due to a signal, propagate */ + if (err == -EINTR) + return err; + } + + if (isp->hw->lpdp) { + err = isp_cmd_ch_lpdp_hs_receiver_tuning_set(isp, ch, 1, 15); + if (err) + return err; + } + + err = isp_cmd_ch_sbs_enable(isp, ch, 1); + if (err) + return err; + + err = isp_cmd_ch_camera_config_select(isp, ch, fmt->preset->index); + if (err) + return err; + + err = isp_cmd_ch_buffer_recycle_mode_set( + isp, ch, CISP_BUFFER_RECYCLE_MODE_EMPTY_ONLY); + if (err) + return err; + + err = isp_cmd_ch_buffer_recycle_start(isp, ch); + if (err) + return err; + + err = isp_cmd_ch_crop_set(isp, ch, fmt->preset->crop_offset.x, + fmt->preset->crop_offset.y, + fmt->preset->crop_size.x, + fmt->preset->crop_size.y); + if (err) + return err; + + err = isp_cmd_ch_output_config_set(isp, ch, fmt->preset->output_dim.x, + fmt->preset->output_dim.y, + fmt->strides, CISP_COLORSPACE_REC709, + CISP_OUTPUT_FORMAT_YUV_2PLANE); + if (err) + return err; + + err = isp_cmd_ch_preview_stream_set(isp, ch, 1); + if (err) + return err; + + err = isp_cmd_ch_cnr_start(isp, ch); + if (err) + return err; + + err = isp_cmd_ch_mbnr_enable(isp, ch, 0, ISP_MBNR_MODE_ENABLE, 1); + if (err) + return err; + + err = isp_cmd_apple_ch_ae_fd_scene_metering_config_set(isp, ch); + if (err) + return err; + + err = isp_cmd_apple_ch_ae_metering_mode_set(isp, ch, 3); + if (err) + return err; + + err = isp_cmd_ch_ae_stability_set(isp, ch, 32); + if (err) + return err; + + err = isp_cmd_ch_ae_stability_to_stable_set(isp, ch, 20); + if (err) + return err; + + err = isp_cmd_ch_sif_pixel_format_set(isp, ch); + if (err) + return err; + + err = isp_cmd_ch_ae_frame_rate_max_set(isp, ch, ISP_FRAME_RATE_DEN); + if (err) + return err; + + err = isp_cmd_ch_ae_frame_rate_min_set(isp, ch, ISP_FRAME_RATE_DEN2); + if (err) + return err; + + err = isp_cmd_apple_ch_temporal_filter_start(isp, ch, isp->temporal_filter); + if (err) + return err; + + err = isp_cmd_apple_ch_motion_history_start(isp, ch); + if (err) + return err; + + err = isp_cmd_apple_ch_temporal_filter_enable(isp, ch); + if (err) + return err; + + err = isp_cmd_ch_buffer_pool_config_set(isp, ch, CISP_POOL_TYPE_META); + if (err) + return err; + + err = isp_cmd_ch_buffer_pool_config_set(isp, ch, + CISP_POOL_TYPE_META_CAPTURE); + if (err) + return err; + + return 0; +} + +static int isp_configure_capture(struct apple_isp *isp) +{ + return isp_ch_configure_capture(isp, isp->current_ch); +} + +int apple_isp_start_camera(struct apple_isp *isp) +{ + int err; + + err = apple_isp_firmware_boot(isp); + if (err < 0) { + dev_err(isp->dev, "failed to boot firmware: %d\n", err); + return err; + } + + err = isp_configure_capture(isp); + if (err) { + dev_err(isp->dev, "failed to configure capture: %d\n", err); + apple_isp_firmware_shutdown(isp); + return err; + } + + return 0; +} + +void apple_isp_stop_camera(struct apple_isp *isp) +{ + apple_isp_firmware_shutdown(isp); +} + +int apple_isp_start_capture(struct apple_isp *isp) +{ + return isp_cmd_ch_start(isp, 0); // TODO channel mask +} + +void apple_isp_stop_capture(struct apple_isp *isp) +{ + isp_cmd_ch_stop(isp, 0); // TODO channel mask + isp_cmd_ch_buffer_return(isp, isp->current_ch); +} diff --git a/drivers/media/platform/apple/isp/isp-cam.h b/drivers/media/platform/apple/isp/isp-cam.h new file mode 100644 index 00000000000000..f4fa4224c7a934 --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-cam.h @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#ifndef __ISP_CAM_H__ +#define __ISP_CAM_H__ + +#include "isp-drv.h" + +#define ISP_FRAME_RATE_NUM 256 +#define ISP_FRAME_RATE_DEN 7680 +#define ISP_FRAME_RATE_DEN2 3840 + +int apple_isp_detect_camera(struct apple_isp *isp); + +int apple_isp_start_camera(struct apple_isp *isp); +void apple_isp_stop_camera(struct apple_isp *isp); + +int apple_isp_start_capture(struct apple_isp *isp); +void apple_isp_stop_capture(struct apple_isp *isp); + +#endif /* __ISP_CAM_H__ */ diff --git a/drivers/media/platform/apple/isp/isp-cmd.c b/drivers/media/platform/apple/isp/isp-cmd.c new file mode 100644 index 00000000000000..ee491d2cb42c5b --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-cmd.c @@ -0,0 +1,634 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#include "isp-cmd.h" +#include "isp-drv.h" +#include "isp-iommu.h" +#include "isp-ipc.h" + +#define CISP_OPCODE_SHIFT 32UL +#define CISP_OPCODE(x) (((u64)(x)) << CISP_OPCODE_SHIFT) +#define CISP_OPCODE_GET(x) (((u64)(x)) >> CISP_OPCODE_SHIFT) + +#define CISP_TIMEOUT msecs_to_jiffies(3000) +#define CISP_SEND_IN(x, a) (cisp_send((x), &(a), sizeof(a), 0, CISP_TIMEOUT)) +#define CISP_SEND_INOUT(x, a) (cisp_send((x), &(a), sizeof(a), sizeof(a), CISP_TIMEOUT)) +#define CISP_SEND_OUT(x, a) (cisp_send_read((x), (a), sizeof(*a), sizeof(*a))) +#define CISP_POST_IN(x, a) (cisp_send((x), &(a), sizeof(a), 0, 0)) +#define CISP_POST_INOUT(x, a) (cisp_send((x), &(a), sizeof(a), sizeof(a), 0)) + +static int cisp_send(struct apple_isp *isp, void *args, u32 insize, u32 outsize, int timeout) +{ + struct isp_channel *chan = isp->chan_io; + struct isp_message *req = &chan->req; + int err; + + req->arg0 = isp->cmd_iova; + req->arg1 = insize; + req->arg2 = outsize; + + memcpy(isp->cmd_virt, args, insize); + err = ipc_chan_send(isp, chan, timeout); + if (err) { + u64 opcode; + memcpy(&opcode, args, sizeof(opcode)); + dev_err(isp->dev, + "%s: failed to send OPCODE 0x%04llx: [0x%llx, 0x%llx, 0x%llx]\n", + chan->name, CISP_OPCODE_GET(opcode), req->arg0, + req->arg1, req->arg2); + } + + return err; +} + +static int cisp_send_read(struct apple_isp *isp, void *args, u32 insize, + u32 outsize) +{ + /* TODO do I need to lock the iova space? */ + int err = cisp_send(isp, args, insize, outsize, CISP_TIMEOUT); + if (err) + return err; + + memcpy(args, isp->cmd_virt, outsize); + return 0; +} + +int isp_cmd_start(struct apple_isp *isp, u32 mode) +{ + struct cmd_start args = { + .opcode = CISP_OPCODE(CISP_CMD_START), + .mode = mode, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_stop(struct apple_isp *isp, u32 mode) +{ + struct cmd_stop args = { + .opcode = CISP_OPCODE(CISP_CMD_STOP), + .mode = mode, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_power_down(struct apple_isp *isp) +{ + struct cmd_power_down args = { + .opcode = CISP_OPCODE(CISP_CMD_POWER_DOWN), + }; + return CISP_POST_INOUT(isp, args); +} + +int isp_cmd_suspend(struct apple_isp *isp) +{ + struct cmd_suspend args = { + .opcode = CISP_OPCODE(CISP_CMD_SUSPEND), + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_print_enable(struct apple_isp *isp, u32 enable) +{ + struct cmd_print_enable args = { + .opcode = CISP_OPCODE(CISP_CMD_PRINT_ENABLE), + .enable = enable, + }; + return CISP_SEND_INOUT(isp, args); +} + +int isp_cmd_trace_enable(struct apple_isp *isp, u32 enable) +{ + struct cmd_trace_enable args = { + .opcode = CISP_OPCODE(CISP_CMD_TRACE_ENABLE), + .enable = enable, + }; + return CISP_SEND_INOUT(isp, args); +} + +int isp_cmd_config_get(struct apple_isp *isp, struct cmd_config_get *args) +{ + args->opcode = CISP_OPCODE(CISP_CMD_CONFIG_GET); + return CISP_SEND_OUT(isp, args); +} + +int isp_cmd_set_isp_pmu_base(struct apple_isp *isp, u64 pmu_base) +{ + struct cmd_set_isp_pmu_base args = { + .opcode = CISP_OPCODE(CISP_CMD_SET_ISP_PMU_BASE), + .pmu_base = pmu_base, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_set_dsid_clr_req_base2(struct apple_isp *isp, u64 dsid_clr_base0, + u64 dsid_clr_base1, u64 dsid_clr_base2, + u64 dsid_clr_base3, u32 dsid_clr_range0, + u32 dsid_clr_range1, u32 dsid_clr_range2, + u32 dsid_clr_range3) +{ + struct cmd_set_dsid_clr_req_base2 args = { + .opcode = CISP_OPCODE(CISP_CMD_SET_DSID_CLR_REG_BASE2), + .dsid_clr_base0 = dsid_clr_base0, + .dsid_clr_base1 = dsid_clr_base1, + .dsid_clr_base2 = dsid_clr_base2, + .dsid_clr_base3 = dsid_clr_base3, + .dsid_clr_range0 = dsid_clr_range0, + .dsid_clr_range1 = dsid_clr_range1, + .dsid_clr_range2 = dsid_clr_range2, + .dsid_clr_range3 = dsid_clr_range3, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_set_dsid_clr_req_base(struct apple_isp *isp, u64 dsid_clr_base, + u32 dsid_clr_range) +{ + struct cmd_set_dsid_clr_req_base args = { + .opcode = CISP_OPCODE(CISP_CMD_SET_DSID_CLR_REG_BASE), + .dsid_clr_base = dsid_clr_base, + .dsid_clr_range = dsid_clr_range, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_pmp_ctrl_set(struct apple_isp *isp, u64 clock_scratch, + u64 clock_base, u8 clock_bit, u8 clock_size, + u64 bandwidth_scratch, u64 bandwidth_base, + u8 bandwidth_bit, u8 bandwidth_size) +{ + struct cmd_pmp_ctrl_set args = { + .opcode = CISP_OPCODE(CISP_CMD_PMP_CTRL_SET), + .clock_scratch = clock_scratch, + .clock_base = clock_base, + .clock_bit = clock_bit, + .clock_size = clock_size, + .clock_pad = 0, + .bandwidth_scratch = bandwidth_scratch, + .bandwidth_base = bandwidth_base, + .bandwidth_bit = bandwidth_bit, + .bandwidth_size = bandwidth_size, + .bandwidth_pad = 0, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_fid_enter(struct apple_isp *isp) +{ + struct cmd_fid_enter args = { + .opcode = CISP_OPCODE(CISP_CMD_FID_ENTER), + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_fid_exit(struct apple_isp *isp) +{ + struct cmd_fid_exit args = { + .opcode = CISP_OPCODE(CISP_CMD_FID_EXIT), + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_start(struct apple_isp *isp, u32 chan) +{ + struct cmd_ch_start args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_START), + .chan = chan, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_stop(struct apple_isp *isp, u32 chan) +{ + struct cmd_ch_stop args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_STOP), + .chan = chan, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_flicker_sensor_set(struct apple_isp *isp, u32 mode) +{ + struct cmd_flicker_sensor_set args = { + .opcode = CISP_OPCODE(CISP_CMD_FLICKER_SENSOR_SET), + .mode = mode, + }; + return CISP_SEND_INOUT(isp, args); +} + +int isp_cmd_ch_info_get(struct apple_isp *isp, u32 chan, + struct cmd_ch_info *args) +{ + args->opcode = CISP_OPCODE(CISP_CMD_CH_INFO_GET); + args->chan = chan; + return CISP_SEND_OUT(isp, args); +} + +int isp_cmd_ch_camera_config_get(struct apple_isp *isp, u32 chan, u32 preset, + struct cmd_ch_camera_config *args) +{ + args->opcode = CISP_OPCODE(CISP_CMD_CH_CAMERA_CONFIG_GET); + args->preset = preset; + args->chan = chan; + return CISP_SEND_OUT(isp, args); +} + +int isp_cmd_ch_camera_config_current_get(struct apple_isp *isp, u32 chan, + struct cmd_ch_camera_config *args) +{ + args->opcode = CISP_OPCODE(CISP_CMD_CH_CAMERA_CONFIG_CURRENT_GET); + args->chan = chan; + return CISP_SEND_OUT(isp, args); +} + +int isp_cmd_ch_camera_config_select(struct apple_isp *isp, u32 chan, u32 preset) +{ + struct cmd_ch_camera_config_select args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_CAMERA_CONFIG_SELECT), + .chan = chan, + .preset = preset, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_buffer_return(struct apple_isp *isp, u32 chan) +{ + struct cmd_ch_buffer_return args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_BUFFER_RETURN), + .chan = chan, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_set_file_load(struct apple_isp *isp, u32 chan, u64 addr, + u32 size) +{ + if (isp->fw_compat >= ISP_FIRMWARE_V_13_5) { + struct cmd_ch_set_file_load64 args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_SET_FILE_LOAD), + .chan = chan, + .addr = addr, + .size = size, + }; + return CISP_SEND_IN(isp, args); + } else { + struct cmd_ch_set_file_load args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_SET_FILE_LOAD), + .chan = chan, + .addr = addr, + .size = size, + }; + return CISP_SEND_IN(isp, args); + } +} + +int isp_cmd_ch_sbs_enable(struct apple_isp *isp, u32 chan, u32 enable) +{ + struct cmd_ch_sbs_enable args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_SBS_ENABLE), + .chan = chan, + .enable = enable, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_crop_set(struct apple_isp *isp, u32 chan, u32 x1, u32 y1, u32 x2, + u32 y2) +{ + struct cmd_ch_crop_set args = { + .opcode = CISP_OPCODE(isp->hw->scl1 ? CISP_CMD_CH_CROP_SCL1_SET + : CISP_CMD_CH_CROP_SET), + .chan = chan, + .x1 = x1, + .y1 = y1, + .x2 = x2, + .y2 = y2, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_output_config_set(struct apple_isp *isp, u32 chan, u32 width, + u32 height, u32 strides[3], u32 colorspace, u32 format) +{ + struct cmd_ch_output_config_set args = { + .opcode = CISP_OPCODE(isp->hw->scl1 ? CISP_CMD_CH_OUTPUT_CONFIG_SCL1_SET + : CISP_CMD_CH_OUTPUT_CONFIG_SET), + .chan = chan, + .width = width, + .height = height, + .colorspace = colorspace, + .format = format, + .padding_rows = 0, + .unk_h0 = height, + .compress = 0, + .unk_w2 = width, + }; + memcpy(args.strides, strides, sizeof(args.strides)); + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_preview_stream_set(struct apple_isp *isp, u32 chan, u32 stream) +{ + struct cmd_ch_preview_stream_set args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_PREVIEW_STREAM_SET), + .chan = chan, + .stream = stream, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_als_disable(struct apple_isp *isp, u32 chan) +{ + struct cmd_ch_als_disable args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_ALS_DISABLE), + .chan = chan, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_cnr_start(struct apple_isp *isp, u32 chan) +{ + struct cmd_ch_cnr_start args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_CNR_START), + .chan = chan, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_mbnr_enable(struct apple_isp *isp, u32 chan, u32 use_case, + u32 mode, u32 enable_chroma) +{ + struct cmd_ch_mbnr_enable args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_MBNR_ENABLE), + .chan = chan, + .use_case = use_case, + .mode = mode, + .enable_chroma = enable_chroma, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_sif_pixel_format_set(struct apple_isp *isp, u32 chan) +{ + struct cmd_ch_sif_pixel_format_set args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_SIF_PIXEL_FORMAT_SET), + .chan = chan, + .format = 3, + .type = 1, + .compress = 0, + .unk_10 = 0, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_buffer_recycle_mode_set(struct apple_isp *isp, u32 chan, + u32 mode) +{ + struct cmd_ch_buffer_recycle_mode_set args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_BUFFER_RECYCLE_MODE_SET), + .chan = chan, + .mode = mode, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_buffer_recycle_start(struct apple_isp *isp, u32 chan) +{ + struct cmd_ch_buffer_recycle_start args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_BUFFER_RECYCLE_START), + .chan = chan, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_buffer_pool_config_set(struct apple_isp *isp, u32 chan, u16 type) +{ + struct cmd_ch_buffer_pool_config_set args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_BUFFER_POOL_CONFIG_SET), + .chan = chan, + .type = type, + .count = ISP_MAX_BUFFERS, + .meta_size0 = isp->hw->meta_size, + .meta_size1 = isp->hw->meta_size, + .unk0 = 0, + .unk1 = 0, + .unk2 = 0, + .data_blocks = 1, + .compress = 0, + }; + return CISP_SEND_INOUT(isp, args); +} + +int isp_cmd_ch_buffer_pool_return(struct apple_isp *isp, u32 chan) +{ + struct cmd_ch_buffer_pool_return args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_BUFFER_POOL_RETURN), + .chan = chan, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_apple_ch_temporal_filter_start(struct apple_isp *isp, u32 chan, u32 arg) +{ + struct cmd_apple_ch_temporal_filter_start args = { + .opcode = CISP_OPCODE(CISP_CMD_APPLE_CH_TEMPORAL_FILTER_START), + .chan = chan, + .unk_c = 1, + .unk_10 = arg, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_apple_ch_temporal_filter_stop(struct apple_isp *isp, u32 chan) +{ + struct cmd_apple_ch_temporal_filter_stop args = { + .opcode = CISP_OPCODE(CISP_CMD_APPLE_CH_TEMPORAL_FILTER_STOP), + .chan = chan, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_apple_ch_motion_history_start(struct apple_isp *isp, u32 chan) +{ + struct cmd_apple_ch_motion_history_start args = { + .opcode = CISP_OPCODE(CISP_CMD_APPLE_CH_MOTION_HISTORY_START), + .chan = chan, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_apple_ch_motion_history_stop(struct apple_isp *isp, u32 chan) +{ + struct cmd_apple_ch_motion_history_stop args = { + .opcode = CISP_OPCODE(CISP_CMD_APPLE_CH_MOTION_HISTORY_STOP), + .chan = chan, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_apple_ch_temporal_filter_enable(struct apple_isp *isp, u32 chan) +{ + struct cmd_apple_ch_temporal_filter_enable args = { + .opcode = CISP_OPCODE(CISP_CMD_APPLE_CH_TEMPORAL_FILTER_ENABLE), + .chan = chan, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_apple_ch_temporal_filter_disable(struct apple_isp *isp, u32 chan) +{ + struct cmd_apple_ch_temporal_filter_disable args = { + .opcode = + CISP_OPCODE(CISP_CMD_APPLE_CH_TEMPORAL_FILTER_DISABLE), + .chan = chan, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_ae_stability_set(struct apple_isp *isp, u32 chan, u32 stability) +{ + struct cmd_ch_ae_stability_set args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_AE_STABILITY_SET), + .chan = chan, + .stability = stability, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_ae_stability_to_stable_set(struct apple_isp *isp, u32 chan, + u32 stability) +{ + struct cmd_ch_ae_stability_to_stable_set args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_AE_STABILITY_TO_STABLE_SET), + .chan = chan, + .stability = stability, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_ae_frame_rate_max_get(struct apple_isp *isp, u32 chan, + struct cmd_ch_ae_frame_rate_max_get *args) +{ + args->opcode = CISP_OPCODE(CISP_CMD_CH_AE_FRAME_RATE_MAX_GET); + args->chan = chan; + return CISP_SEND_OUT(isp, args); +} + +int isp_cmd_ch_ae_frame_rate_max_set(struct apple_isp *isp, u32 chan, + u32 framerate) +{ + struct cmd_ch_ae_frame_rate_max_set args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_AE_FRAME_RATE_MAX_SET), + .chan = chan, + .framerate = framerate, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_ae_frame_rate_min_set(struct apple_isp *isp, u32 chan, + u32 framerate) +{ + struct cmd_ch_ae_frame_rate_min_set args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_AE_FRAME_RATE_MIN_SET), + .chan = chan, + .framerate = framerate, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_apple_ch_ae_fd_scene_metering_config_set(struct apple_isp *isp, + u32 chan) +{ + struct cmd_apple_ch_ae_fd_scene_metering_config_set args = { + .opcode = CISP_OPCODE( + CISP_CMD_APPLE_CH_AE_FD_SCENE_METERING_CONFIG_SET), + .chan = chan, + .unk_c = 0xb8, + .unk_10 = 0x2000200, + .unk_14 = 0x280800, + .unk_18 = 0xe10028, + .unk_1c = 0xa0399, + .unk_20 = 0x3cc02cc, + }; + return CISP_SEND_INOUT(isp, args); +} + +int isp_cmd_apple_ch_ae_metering_mode_set(struct apple_isp *isp, u32 chan, + u32 mode) +{ + struct cmd_apple_ch_ae_metering_mode_set args = { + .opcode = CISP_OPCODE(CISP_CMD_APPLE_CH_AE_METERING_MODE_SET), + .chan = chan, + .mode = mode, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_apple_ch_ae_flicker_freq_update_current_set(struct apple_isp *isp, + u32 chan, u32 freq) +{ + struct cmd_apple_ch_ae_flicker_freq_update_current_set args = { + .opcode = CISP_OPCODE( + CISP_CMD_APPLE_CH_AE_FLICKER_FREQ_UPDATE_CURRENT_SET), + .chan = chan, + .freq = freq, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_semantic_video_enable(struct apple_isp *isp, u32 chan, + u32 enable) +{ + struct cmd_ch_semantic_video_enable args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_SEMANTIC_VIDEO_ENABLE), + .chan = chan, + .enable = enable, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_semantic_awb_enable(struct apple_isp *isp, u32 chan, u32 enable) +{ + struct cmd_ch_semantic_awb_enable args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_SEMANTIC_AWB_ENABLE), + .chan = chan, + .enable = enable, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_lpdp_hs_receiver_tuning_set(struct apple_isp *isp, u32 chan, u32 unk1, u32 unk2) +{ + struct cmd_ch_lpdp_hs_receiver_tuning_set args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_LPDP_HS_RECEIVER_TUNING_SET), + .chan = chan, + .unk1 = unk1, + .unk2 = unk2, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_property_write(struct apple_isp *isp, u32 chan, u32 prop, u32 val) +{ + struct cmd_ch_property_write args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_PROPERTY_WRITE), + .chan = chan, + .prop = prop, + .val = val, + }; + return CISP_SEND_IN(isp, args); +} + +int isp_cmd_ch_property_read(struct apple_isp *isp, u32 chan, u32 prop, u32 *val) +{ + struct cmd_ch_property_write args = { + .opcode = CISP_OPCODE(CISP_CMD_CH_PROPERTY_READ), + .chan = chan, + .prop = prop, + .val = 0xdeadbeef, + }; + int ret = CISP_SEND_OUT(isp, &args); + + *val = args.val; + + return ret; +} diff --git a/drivers/media/platform/apple/isp/isp-cmd.h b/drivers/media/platform/apple/isp/isp-cmd.h new file mode 100644 index 00000000000000..5a3c8cd9177e48 --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-cmd.h @@ -0,0 +1,691 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#ifndef __ISP_CMD_H__ +#define __ISP_CMD_H__ + +#include "isp-drv.h" + +#define CISP_CMD_START 0x0000 +#define CISP_CMD_STOP 0x0001 +#define CISP_CMD_CONFIG_GET 0x0003 +#define CISP_CMD_PRINT_ENABLE 0x0004 +#define CISP_CMD_BUILDINFO 0x0006 +#define CISP_CMD_GET_BES_PARAM 0x000f +#define CISP_CMD_POWER_DOWN 0x0010 +#define CISP_CMD_SET_ISP_PMU_BASE 0x0011 +#define CISP_CMD_PMP_CTRL_SET 0x001c +#define CISP_CMD_TRACE_ENABLE 0x001d +#define CISP_CMD_SUSPEND 0x0021 +#define CISP_CMD_FID_ENTER 0x0022 +#define CISP_CMD_FID_EXIT 0x0023 +#define CISP_CMD_FLICKER_SENSOR_SET 0x0024 +#define CISP_CMD_CH_START 0x0100 +#define CISP_CMD_CH_STOP 0x0101 +#define CISP_CMD_CH_BUFFER_RETURN 0x0104 +#define CISP_CMD_CH_CAMERA_CONFIG_CURRENT_GET 0x0105 +#define CISP_CMD_CH_CAMERA_CONFIG_GET 0x0106 +#define CISP_CMD_CH_CAMERA_CONFIG_SELECT 0x0107 +#define CISP_CMD_CH_INFO_GET 0x010d +#define CISP_CMD_CH_BUFFER_RECYCLE_MODE_SET 0x010e +#define CISP_CMD_CH_BUFFER_RECYCLE_START 0x010f +#define CISP_CMD_CH_BUFFER_RECYCLE_STOP 0x0110 +#define CISP_CMD_CH_SET_FILE_LOAD 0x0111 +#define CISP_CMD_CH_SIF_PIXEL_FORMAT_SET 0x0115 +#define CISP_CMD_CH_BUFFER_POOL_CONFIG_GET 0x0116 +#define CISP_CMD_CH_BUFFER_POOL_CONFIG_SET 0x0117 +#define CISP_CMD_CH_CAMERA_MIPI_FREQUENCY_GET 0x011a +#define CISP_CMD_CH_CAMERA_PIX_FREQUENCY_GET 0x011f +#define CISP_CMD_CH_PROPERTY_WRITE 0x0122 +#define CISP_CMD_CH_PROPERTY_READ 0x0123 +#define CISP_CMD_CH_LOCAL_RAW_BUFFER_ENABLE 0x0125 +#define CISP_CMD_CH_META_DATA_ENABLE 0x0126 +#define CISP_CMD_CH_CAMERA_MIPI_FREQUENCY_TOTAL_GET 0x0133 +#define CISP_CMD_CH_SBS_ENABLE 0x013b +#define CISP_CMD_CH_LSC_POLYNOMIAL_COEFF_GET 0x0142 +#define CISP_CMD_CH_SET_META_DATA_REQUIRED 0x014f +#define CISP_CMD_CH_BUFFER_POOL_RETURN 0x015b +#define CISP_CMD_CH_CAMERA_AGILE_FREQ_ARRAY_CURRENT_GET 0x015e +#define CISP_CMD_CH_AE_START 0x0200 +#define CISP_CMD_CH_AE_STOP 0x0201 +#define CISP_CMD_CH_AE_FRAME_RATE_MAX_GET 0x0207 +#define CISP_CMD_CH_AE_FRAME_RATE_MAX_SET 0x0208 +#define CISP_CMD_CH_AE_FRAME_RATE_MIN_GET 0x0209 +#define CISP_CMD_CH_AE_FRAME_RATE_MIN_SET 0x020a +#define CISP_CMD_CH_AE_STABILITY_SET 0x021a +#define CISP_CMD_CH_AE_STABILITY_TO_STABLE_SET 0x0229 +#define CISP_CMD_CH_SENSOR_NVM_GET 0x0501 +#define CISP_CMD_CH_SENSOR_PERMODULE_LSC_INFO_GET 0x0507 +#define CISP_CMD_CH_SENSOR_PERMODULE_LSC_GRID_GET 0x0511 +#define CISP_CMD_CH_LPDP_HS_RECEIVER_TUNING_SET 0x051b +#define CISP_CMD_CH_FOCUS_LIMITS_GET 0x0701 +#define CISP_CMD_CH_CROP_GET 0x0800 +#define CISP_CMD_CH_CROP_SET 0x0801 +#define CISP_CMD_CH_SCALER_CROP_SET 0x080a +#define CISP_CMD_CH_CROP_SCL1_GET 0x080b +#define CISP_CMD_CH_CROP_SCL1_SET 0x080c +#define CISP_CMD_CH_SCALER_CROP_SCL1_SET 0x080d +#define CISP_CMD_CH_ALS_ENABLE 0x0a1c +#define CISP_CMD_CH_ALS_DISABLE 0x0a1d +#define CISP_CMD_CH_CNR_START 0x0a2f +#define CISP_CMD_CH_MBNR_ENABLE 0x0a3a +#define CISP_CMD_CH_OUTPUT_CONFIG_SET 0x0b01 +#define CISP_CMD_CH_OUTPUT_CONFIG_SCL1_SET 0x0b09 +#define CISP_CMD_CH_PREVIEW_STREAM_SET 0x0b0d +#define CISP_CMD_CH_SEMANTIC_VIDEO_ENABLE 0x0b17 +#define CISP_CMD_CH_SEMANTIC_AWB_ENABLE 0x0b18 +#define CISP_CMD_CH_FACE_DETECTION_START 0x0d00 +#define CISP_CMD_CH_FACE_DETECTION_STOP 0x0d01 +#define CISP_CMD_CH_FACE_DETECTION_CONFIG_GET 0x0d02 +#define CISP_CMD_CH_FACE_DETECTION_CONFIG_SET 0x0d03 +#define CISP_CMD_CH_FACE_DETECTION_DISABLE 0x0d04 +#define CISP_CMD_CH_FACE_DETECTION_ENABLE 0x0d05 +#define CISP_CMD_CH_FID_START 0x3000 +#define CISP_CMD_CH_FID_STOP 0x3001 +#define CISP_CMD_IPC_ENDPOINT_SET2 0x300c +#define CISP_CMD_IPC_ENDPOINT_UNSET2 0x300d +#define CISP_CMD_SET_DSID_CLR_REG_BASE2 0x3204 +#define CISP_CMD_SET_DSID_CLR_REG_BASE 0x3205 +#define CISP_CMD_APPLE_CH_AE_METERING_MODE_SET 0x8206 +#define CISP_CMD_APPLE_CH_AE_FD_SCENE_METERING_CONFIG_SET 0x820e +#define CISP_CMD_APPLE_CH_AE_FLICKER_FREQ_UPDATE_CURRENT_SET 0x8212 +#define CISP_CMD_APPLE_CH_TEMPORAL_FILTER_START 0xc100 +#define CISP_CMD_APPLE_CH_TEMPORAL_FILTER_STOP 0xc101 +#define CISP_CMD_APPLE_CH_MOTION_HISTORY_START 0xc102 +#define CISP_CMD_APPLE_CH_MOTION_HISTORY_STOP 0xc103 +#define CISP_CMD_APPLE_CH_TEMPORAL_FILTER_ENABLE 0xc113 +#define CISP_CMD_APPLE_CH_TEMPORAL_FILTER_DISABLE 0xc114 + +#define CISP_POOL_TYPE_META 0x0 +#define CISP_POOL_TYPE_RENDERED 0x1 +#define CISP_POOL_TYPE_FD 0x2 +#define CISP_POOL_TYPE_RAW 0x3 +#define CISP_POOL_TYPE_STAT 0x4 +#define CISP_POOL_TYPE_RAW_AUX 0x5 +#define CISP_POOL_TYPE_YCC 0x6 +#define CISP_POOL_TYPE_CAPTURE_FULL_RES 0x7 +#define CISP_POOL_TYPE_META_CAPTURE 0x8 +#define CISP_POOL_TYPE_RENDERED_SCL1 0x9 +#define CISP_POOL_TYPE_STAT_PIXELOUTPUT 0x11 +#define CISP_POOL_TYPE_FSCL 0x12 +#define CISP_POOL_TYPE_CAPTURE_FULL_RES_YCC 0x13 +#define CISP_POOL_TYPE_RENDERED_RAW 0x14 +#define CISP_POOL_TYPE_CAPTURE_PDC_RAW 0x16 +#define CISP_POOL_TYPE_FPC_DATA 0x17 +#define CISP_POOL_TYPE_AICAM_SEG 0x19 +#define CISP_POOL_TYPE_SPD 0x1a +#define CISP_POOL_TYPE_META_DEPTH 0x1c +#define CISP_POOL_TYPE_JASPER_DEPTH 0x1d +#define CISP_POOL_TYPE_RAW_SIFR 0x1f +#define CISP_POOL_TYPE_FEP_THUMBNAIL_DYNAMIC_POOL_RAW 0x21 + +#define CISP_COLORSPACE_REC709 0x1 +#define CISP_OUTPUT_FORMAT_YUV_2PLANE 0x0 +#define CISP_OUTPUT_FORMAT_YUV_1PLANE 0x1 +#define CISP_OUTPUT_FORMAT_RGB 0x2 +#define CISP_BUFFER_RECYCLE_MODE_EMPTY_ONLY 0x1 + +struct cmd_start { + u64 opcode; + u32 mode; +} __packed; +static_assert(sizeof(struct cmd_start) == 0xc); + +struct cmd_stop { + u64 opcode; + u32 mode; +} __packed; +static_assert(sizeof(struct cmd_stop) == 0xc); + +struct cmd_power_down { + u64 opcode; +} __packed; +static_assert(sizeof(struct cmd_power_down) == 0x8); + +struct cmd_suspend { + u64 opcode; +} __packed; +static_assert(sizeof(struct cmd_suspend) == 0x8); + +struct cmd_print_enable { + u64 opcode; + u32 enable; +} __packed; +static_assert(sizeof(struct cmd_print_enable) == 0xc); + +struct cmd_trace_enable { + u64 opcode; + u32 enable; +} __packed; +static_assert(sizeof(struct cmd_trace_enable) == 0xc); + +struct cmd_config_get { + u64 opcode; + u32 timestamp_freq; + u32 num_channels; + u32 unk_10; + u32 unk_14; + u32 unk_18; +} __packed; +static_assert(sizeof(struct cmd_config_get) == 0x1c); + +struct cmd_set_isp_pmu_base { + u64 opcode; + u64 pmu_base; +} __packed; +static_assert(sizeof(struct cmd_set_isp_pmu_base) == 0x10); + +struct cmd_set_dsid_clr_req_base2 { + u64 opcode; + u64 dsid_clr_base0; + u64 dsid_clr_base1; + u64 dsid_clr_base2; + u64 dsid_clr_base3; + u32 dsid_clr_range0; + u32 dsid_clr_range1; + u32 dsid_clr_range2; + u32 dsid_clr_range3; +} __packed; +static_assert(sizeof(struct cmd_set_dsid_clr_req_base2) == 0x38); + +struct cmd_set_dsid_clr_req_base { + u64 opcode; + u64 dsid_clr_base; + u32 dsid_clr_range; +} __packed; +static_assert(sizeof(struct cmd_set_dsid_clr_req_base) == 0x14); + +struct cmd_pmp_ctrl_set { + u64 opcode; + u64 clock_scratch; + u64 clock_base; + u8 clock_bit; + u8 clock_size; + u16 clock_pad; + u64 bandwidth_scratch; + u64 bandwidth_base; + u8 bandwidth_bit; + u8 bandwidth_size; + u16 bandwidth_pad; +} __packed; +static_assert(sizeof(struct cmd_pmp_ctrl_set) == 0x30); + +struct cmd_fid_enter { + u64 opcode; +} __packed; +static_assert(sizeof(struct cmd_fid_enter) == 0x8); + +struct cmd_fid_exit { + u64 opcode; +} __packed; +static_assert(sizeof(struct cmd_fid_exit) == 0x8); + +struct cmd_ipc_endpoint_set2 { + u64 opcode; + u32 unk; + u64 addr1; + u32 size1; + u64 addr2; + u32 size2; + u64 regs; + u32 unk2; +} __packed; +static_assert(sizeof(struct cmd_ipc_endpoint_set2) == 0x30); + +struct cmd_flicker_sensor_set { + u64 opcode; + u32 mode; +} __packed; +static_assert(sizeof(struct cmd_flicker_sensor_set) == 0xc); + +int isp_cmd_start(struct apple_isp *isp, u32 mode); +int isp_cmd_stop(struct apple_isp *isp, u32 mode); +int isp_cmd_power_down(struct apple_isp *isp); +int isp_cmd_suspend(struct apple_isp *isp); +int isp_cmd_print_enable(struct apple_isp *isp, u32 enable); +int isp_cmd_trace_enable(struct apple_isp *isp, u32 enable); +int isp_cmd_config_get(struct apple_isp *isp, struct cmd_config_get *args); +int isp_cmd_set_isp_pmu_base(struct apple_isp *isp, u64 pmu_base); +int isp_cmd_set_dsid_clr_req_base(struct apple_isp *isp, u64 dsid_clr_base, + u32 dsid_clr_range); +int isp_cmd_set_dsid_clr_req_base2(struct apple_isp *isp, u64 dsid_clr_base0, + u64 dsid_clr_base1, u64 dsid_clr_base2, + u64 dsid_clr_base3, u32 dsid_clr_range0, + u32 dsid_clr_range1, u32 dsid_clr_range2, + u32 dsid_clr_range3); +int isp_cmd_pmp_ctrl_set(struct apple_isp *isp, u64 clock_scratch, + u64 clock_base, u8 clock_bit, u8 clock_size, + u64 bandwidth_scratch, u64 bandwidth_base, + u8 bandwidth_bit, u8 bandwidth_size); +int isp_cmd_fid_enter(struct apple_isp *isp); +int isp_cmd_fid_exit(struct apple_isp *isp); +int isp_cmd_flicker_sensor_set(struct apple_isp *isp, u32 mode); + +struct cmd_ch_start { + u64 opcode; + u32 chan; +} __packed; +static_assert(sizeof(struct cmd_ch_start) == 0xc); + +struct cmd_ch_stop { + u64 opcode; + u32 chan; +} __packed; +static_assert(sizeof(struct cmd_ch_stop) == 0xc); + +struct cmd_ch_info { + u64 opcode; + u32 chan; + u32 unk_c; // 0x7da0001, 0x7db0001 + u32 unk_10; // 0x300ac, 0x5006d + u32 unk_14; // 0x40007, 0x10007 + u32 unk_18; // 0x5, 0x2 + u32 unk_1c; // 0x1, 0x1 + u32 version; + u32 unk_24; // 0x7, 0x9 + u32 unk_28; // 0x1, 0x1410 + u32 unk_2c; // 0x7, 0x2 + u32 pad_30[7]; + u32 unk_4c; // 0x10000, 0x50000 + u32 unk_50; // 0x1, 0x1 + u32 unk_54; // 0x0, 0x0 + u32 unk_58; // 0x4, 0x4 + u32 unk_5c; // 0x10, 0x20 + u32 num_presets; + u32 unk_64; // 0x0, 0x0 + u32 unk_68; // 0x44c0, 0x4680 + u32 unk_6c; // 0x40, 0x40 + u32 unk_70; // 0x1, 0x1 + u32 unk_74; // 0x2, 0x2 + u32 unk_78; // 0x4000, 0x4000 + u32 unk_7c; // 0x40, 0x40 + u32 unk_80; // 0x1, 0x1 + u32 pad_84[2]; + u32 unk_8c; // 0x36, 0x36 + u32 pad_90[2]; + u32 timestamp_freq; + u16 pad_9c; + char module_sn[20]; + u16 pad_b0; + u32 unk_b4; // 0x8, 0x8 + u32 pad_b8[2]; + u32 unk_c0; // 0x4, 0x1 + u32 unk_c4; // 0x0, 0x0 + u32 unk_c8; // 0x0, 0x100 + u32 pad_cc[4]; + u32 unk_dc; // 0xff0000, 0xff0000 + u32 unk_e0; // 0xc00, 0xc00 + u32 unk_e4; // 0x0, 0x0 + u32 unk_e8; // 0x1c, 0x1c + u32 unk_ec; // 0x640, 0x680 + u32 unk_f0; // 0x4, 0x4 + u32 unk_f4; // 0x4, 0x4 + u32 pad_f8[6]; + u32 unk_110; // 0x0, 0x7800000 + u32 unk_114; // 0x0, 0x780 +} __packed; +static_assert(sizeof(struct cmd_ch_info) == 0x118); + +struct cmd_ch_camera_config { + u64 opcode; + u32 chan; + u32 preset; + u16 in_width; + u16 in_height; + u16 out_width; + u16 out_height; + u32 unk_28; + u32 unk_2c; + u32 unk_30[16]; + u32 sensor_clk; + u32 unk_64[4]; + u32 timestamp_freq; + u32 unk_78[2]; + u32 unk_80[16]; + u32 in_width2; // repeated in u32?? + u32 in_height2; + u32 unk_c8[3]; + u32 out_width2; + u32 out_height2; +} __packed; +static_assert(sizeof(struct cmd_ch_camera_config) == 0xdc); + +struct cmd_ch_camera_config_select { + u64 opcode; + u32 chan; + u32 preset; +} __packed; +static_assert(sizeof(struct cmd_ch_camera_config_select) == 0x10); + +struct cmd_ch_set_file_load { + u64 opcode; + u32 chan; + u32 addr; + u32 size; +} __packed; +static_assert(sizeof(struct cmd_ch_set_file_load) == 0x14); + +struct cmd_ch_set_file_load64 { + u64 opcode; + u32 chan; + u64 addr; + u32 size; +} __packed; +static_assert(sizeof(struct cmd_ch_set_file_load64) == 0x18); + +struct cmd_ch_buffer_return { + u64 opcode; + u32 chan; +} __packed; +static_assert(sizeof(struct cmd_ch_buffer_return) == 0xc); + +struct cmd_ch_sbs_enable { + u64 opcode; + u32 chan; + u32 enable; +} __packed; +static_assert(sizeof(struct cmd_ch_sbs_enable) == 0x10); + +struct cmd_ch_crop_set { + u64 opcode; + u32 chan; + u32 x1; + u32 y1; + u32 x2; + u32 y2; +} __packed; +static_assert(sizeof(struct cmd_ch_crop_set) == 0x1c); + +struct cmd_ch_output_config_set { + u64 opcode; + u32 chan; + u32 width; + u32 height; + u32 colorspace; + u32 format; + u32 strides[3]; + u32 padding_rows; + u32 unk_h0; + u32 compress; + u32 unk_w2; +} __packed; +static_assert(sizeof(struct cmd_ch_output_config_set) == 0x38); + +struct cmd_ch_preview_stream_set { + u64 opcode; + u32 chan; + u32 stream; +} __packed; +static_assert(sizeof(struct cmd_ch_preview_stream_set) == 0x10); + +struct cmd_ch_als_disable { + u64 opcode; + u32 chan; +} __packed; +static_assert(sizeof(struct cmd_ch_als_disable) == 0xc); + +struct cmd_ch_cnr_start { + u64 opcode; + u32 chan; +} __packed; +static_assert(sizeof(struct cmd_ch_cnr_start) == 0xc); + +struct cmd_ch_mbnr_enable { + u64 opcode; + u32 chan; + u32 use_case; + u32 mode; + u32 enable_chroma; +} __packed; +static_assert(sizeof(struct cmd_ch_mbnr_enable) == 0x18); + +struct cmd_ch_sif_pixel_format_set { + u64 opcode; + u32 chan; + u8 format; + u8 type; + u16 compress; + u32 unk_10; +} __packed; +static_assert(sizeof(struct cmd_ch_sif_pixel_format_set) == 0x14); + +struct cmd_ch_lpdp_hs_receiver_tuning_set { + u64 opcode; + u32 chan; + u32 unk1; + u32 unk2; +} __packed; +static_assert(sizeof(struct cmd_ch_lpdp_hs_receiver_tuning_set) == 0x14); + +struct cmd_ch_property_write { + u64 opcode; + u32 chan; + u32 prop; + u32 val; + u32 unk1; + u32 unk2; +} __packed; +static_assert(sizeof(struct cmd_ch_property_write) == 0x1c); + +int isp_cmd_ch_start(struct apple_isp *isp, u32 chan); +int isp_cmd_ch_stop(struct apple_isp *isp, u32 chan); +int isp_cmd_ch_info_get(struct apple_isp *isp, u32 chan, + struct cmd_ch_info *args); +int isp_cmd_ch_camera_config_get(struct apple_isp *isp, u32 chan, u32 preset, + struct cmd_ch_camera_config *args); +int isp_cmd_ch_camera_config_current_get(struct apple_isp *isp, u32 chan, + struct cmd_ch_camera_config *args); +int isp_cmd_ch_camera_config_select(struct apple_isp *isp, u32 chan, + u32 preset); +int isp_cmd_ch_set_file_load(struct apple_isp *isp, u32 chan, u64 addr, + u32 size); +int isp_cmd_ch_buffer_return(struct apple_isp *isp, u32 chan); +int isp_cmd_ch_sbs_enable(struct apple_isp *isp, u32 chan, u32 enable); +int isp_cmd_ch_crop_set(struct apple_isp *isp, u32 chan, u32 x1, u32 y1, u32 x2, + u32 y2); +int isp_cmd_ch_output_config_set(struct apple_isp *isp, u32 chan, u32 width, + u32 height, u32 strides[3], u32 colorspace, u32 format); +int isp_cmd_ch_preview_stream_set(struct apple_isp *isp, u32 chan, u32 stream); +int isp_cmd_ch_als_disable(struct apple_isp *isp, u32 chan); +int isp_cmd_ch_cnr_start(struct apple_isp *isp, u32 chan); +int isp_cmd_ch_mbnr_enable(struct apple_isp *isp, u32 chan, u32 use_case, + u32 mode, u32 enable_chroma); +int isp_cmd_ch_sif_pixel_format_set(struct apple_isp *isp, u32 chan); +int isp_cmd_ch_lpdp_hs_receiver_tuning_set(struct apple_isp *isp, u32 chan, u32 unk1, u32 unk2); + +int isp_cmd_ch_property_read(struct apple_isp *isp, u32 chan, u32 prop, u32 *val); +int isp_cmd_ch_property_write(struct apple_isp *isp, u32 chan, u32 prop, u32 val); + +enum isp_mbnr_mode { + ISP_MBNR_MODE_DISABLE = 0, + ISP_MBNR_MODE_ENABLE = 1, + ISP_MBNR_MODE_BYPASS = 2, +}; + +struct cmd_ch_buffer_recycle_mode_set { + u64 opcode; + u32 chan; + u32 mode; +} __packed; +static_assert(sizeof(struct cmd_ch_buffer_recycle_mode_set) == 0x10); + +struct cmd_ch_buffer_recycle_start { + u64 opcode; + u32 chan; +} __packed; +static_assert(sizeof(struct cmd_ch_buffer_recycle_start) == 0xc); + +struct cmd_ch_buffer_pool_config_set { + u64 opcode; + u32 chan; + u16 type; + u16 count; + u32 meta_size0; + u32 meta_size1; + u64 unk0; + u64 unk1; + u64 unk2; + u32 zero[0x19]; + u32 data_blocks; + u32 compress; +} __packed; +static_assert(sizeof(struct cmd_ch_buffer_pool_config_set) == 0x9c); + +struct cmd_ch_buffer_pool_return { + u64 opcode; + u32 chan; +} __packed; +static_assert(sizeof(struct cmd_ch_buffer_pool_return) == 0xc); + +int isp_cmd_ch_buffer_recycle_mode_set(struct apple_isp *isp, u32 chan, + u32 mode); +int isp_cmd_ch_buffer_recycle_start(struct apple_isp *isp, u32 chan); +int isp_cmd_ch_buffer_pool_config_set(struct apple_isp *isp, u32 chan, + u16 type); +int isp_cmd_ch_buffer_pool_config_get(struct apple_isp *isp, u32 chan, + u16 type); +int isp_cmd_ch_buffer_pool_return(struct apple_isp *isp, u32 chan); + +struct cmd_apple_ch_temporal_filter_start { + u64 opcode; + u32 chan; + u32 unk_c; + u32 unk_10; +} __packed; +static_assert(sizeof(struct cmd_apple_ch_temporal_filter_start) == 0x14); + +struct cmd_apple_ch_temporal_filter_stop { + u64 opcode; + u32 chan; +} __packed; +static_assert(sizeof(struct cmd_apple_ch_temporal_filter_stop) == 0xc); + +struct cmd_apple_ch_motion_history_start { + u64 opcode; + u32 chan; +} __packed; +static_assert(sizeof(struct cmd_apple_ch_motion_history_start) == 0xc); + +struct cmd_apple_ch_motion_history_stop { + u64 opcode; + u32 chan; +} __packed; +static_assert(sizeof(struct cmd_apple_ch_motion_history_stop) == 0xc); + +struct cmd_apple_ch_temporal_filter_enable { + u64 opcode; + u32 chan; +} __packed; +static_assert(sizeof(struct cmd_apple_ch_temporal_filter_enable) == 0xc); + +struct cmd_apple_ch_temporal_filter_disable { + u64 opcode; + u32 chan; +} __packed; +static_assert(sizeof(struct cmd_apple_ch_temporal_filter_disable) == 0xc); + +int isp_cmd_apple_ch_temporal_filter_start(struct apple_isp *isp, u32 chan, u32 arg); +int isp_cmd_apple_ch_temporal_filter_stop(struct apple_isp *isp, u32 chan); +int isp_cmd_apple_ch_motion_history_start(struct apple_isp *isp, u32 chan); +int isp_cmd_apple_ch_motion_history_stop(struct apple_isp *isp, u32 chan); +int isp_cmd_apple_ch_temporal_filter_enable(struct apple_isp *isp, u32 chan); +int isp_cmd_apple_ch_temporal_filter_disable(struct apple_isp *isp, u32 chan); + +struct cmd_ch_ae_stability_set { + u64 opcode; + u32 chan; + u32 stability; +} __packed; +static_assert(sizeof(struct cmd_ch_ae_stability_set) == 0x10); + +struct cmd_ch_ae_stability_to_stable_set { + u64 opcode; + u32 chan; + u32 stability; +} __packed; +static_assert(sizeof(struct cmd_ch_ae_stability_to_stable_set) == 0x10); + +struct cmd_ch_ae_frame_rate_max_get { + u64 opcode; + u32 chan; + u32 framerate; +} __packed; +static_assert(sizeof(struct cmd_ch_ae_frame_rate_max_get) == 0x10); + +struct cmd_ch_ae_frame_rate_max_set { + u64 opcode; + u32 chan; + u32 framerate; +} __packed; +static_assert(sizeof(struct cmd_ch_ae_frame_rate_max_set) == 0x10); + +struct cmd_ch_ae_frame_rate_min_set { + u64 opcode; + u32 chan; + u32 framerate; +} __packed; +static_assert(sizeof(struct cmd_ch_ae_frame_rate_min_set) == 0x10); + +struct cmd_apple_ch_ae_fd_scene_metering_config_set { + u64 opcode; + u32 chan; + u32 unk_c; + u32 unk_10; + u32 unk_14; + u32 unk_18; + u32 unk_1c; + u32 unk_20; +} __packed; +static_assert(sizeof(struct cmd_apple_ch_ae_fd_scene_metering_config_set) == + 0x24); + +struct cmd_apple_ch_ae_metering_mode_set { + u64 opcode; + u32 chan; + u32 mode; +} __packed; +static_assert(sizeof(struct cmd_apple_ch_ae_metering_mode_set) == 0x10); + +struct cmd_apple_ch_ae_flicker_freq_update_current_set { + u64 opcode; + u32 chan; + u32 freq; +} __packed; +static_assert(sizeof(struct cmd_apple_ch_ae_flicker_freq_update_current_set) == + 0x10); + +int isp_cmd_ch_ae_stability_set(struct apple_isp *isp, u32 chan, u32 stability); +int isp_cmd_ch_ae_stability_to_stable_set(struct apple_isp *isp, u32 chan, + u32 stability); +int isp_cmd_ch_ae_frame_rate_max_get(struct apple_isp *isp, u32 chan, + struct cmd_ch_ae_frame_rate_max_get *args); +int isp_cmd_ch_ae_frame_rate_max_set(struct apple_isp *isp, u32 chan, + u32 framerate); +int isp_cmd_ch_ae_frame_rate_min_set(struct apple_isp *isp, u32 chan, + u32 framerate); +int isp_cmd_apple_ch_ae_fd_scene_metering_config_set(struct apple_isp *isp, + u32 chan); +int isp_cmd_apple_ch_ae_metering_mode_set(struct apple_isp *isp, u32 chan, + u32 mode); +int isp_cmd_apple_ch_ae_flicker_freq_update_current_set(struct apple_isp *isp, + u32 chan, u32 freq); + +struct cmd_ch_semantic_video_enable { + u64 opcode; + u32 chan; + u32 enable; +} __packed; +static_assert(sizeof(struct cmd_ch_semantic_video_enable) == 0x10); + +struct cmd_ch_semantic_awb_enable { + u64 opcode; + u32 chan; + u32 enable; +} __packed; +static_assert(sizeof(struct cmd_ch_semantic_awb_enable) == 0x10); + +int isp_cmd_ch_semantic_video_enable(struct apple_isp *isp, u32 chan, + u32 enable); +int isp_cmd_ch_semantic_awb_enable(struct apple_isp *isp, u32 chan, u32 enable); + +#endif /* __ISP_CMD_H__ */ diff --git a/drivers/media/platform/apple/isp/isp-drv.c b/drivers/media/platform/apple/isp/isp-drv.c new file mode 100644 index 00000000000000..848f7abd535a7f --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-drv.c @@ -0,0 +1,594 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Apple Image Signal Processor driver + * + * Copyright (C) 2023 The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "isp-cam.h" +#include "isp-fw.h" +#include "isp-iommu.h" +#include "isp-v4l2.h" + +static void apple_isp_detach_genpd(struct apple_isp *isp) +{ + if (isp->pd_count <= 1) + return; + + for (int i = isp->pd_count - 1; i >= 0; i--) { + if (isp->pd_link[i]) + device_link_del(isp->pd_link[i]); + if (!IS_ERR_OR_NULL(isp->pd_dev[i])) + dev_pm_domain_detach(isp->pd_dev[i], true); + } + + return; +} + +static int apple_isp_attach_genpd(struct apple_isp *isp) +{ + struct device *dev = isp->dev; + + isp->pd_count = of_count_phandle_with_args( + dev->of_node, "power-domains", "#power-domain-cells"); + if (isp->pd_count <= 1) + return 0; + + isp->pd_dev = devm_kcalloc(dev, isp->pd_count, sizeof(*isp->pd_dev), + GFP_KERNEL); + if (!isp->pd_dev) + return -ENOMEM; + + isp->pd_link = devm_kcalloc(dev, isp->pd_count, sizeof(*isp->pd_link), + GFP_KERNEL); + if (!isp->pd_link) + return -ENOMEM; + + for (int i = 0; i < isp->pd_count; i++) { + int flags = DL_FLAG_STATELESS; + + /* Primary power domain uses RPM integration */ + if (i == 0) + flags |= DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE; + + isp->pd_dev[i] = dev_pm_domain_attach_by_id(dev, i); + if (IS_ERR(isp->pd_dev[i])) { + apple_isp_detach_genpd(isp); + return PTR_ERR(isp->pd_dev[i]); + } + + isp->pd_link[i] = + device_link_add(dev, isp->pd_dev[i], flags); + + if (!isp->pd_link[i]) { + apple_isp_detach_genpd(isp); + return -EINVAL; + } + } + + return 0; +} + +static int apple_isp_init_iommu(struct apple_isp *isp) +{ + struct device *dev = isp->dev; + phys_addr_t heap_base; + size_t heap_size; + u64 vm_size; + int err; + int idx; + int size; + struct device_node *mem_node; + const __be32 *maps, *end; + + isp->domain = iommu_get_domain_for_dev(isp->dev); + if (!isp->domain) + return -ENODEV; + isp->shift = __ffs(isp->domain->pgsize_bitmap); + + idx = of_property_match_string(dev->of_node, "memory-region-names", + "heap"); + mem_node = of_parse_phandle(dev->of_node, "memory-region", idx); + if (!mem_node) { + dev_err(dev, "No memory-region found for heap\n"); + return -ENODEV; + } + + maps = of_get_property(mem_node, "iommu-addresses", &size); + if (!maps || !size) { + dev_err(dev, "No valid iommu-addresses found for heap\n"); + return -ENODEV; + } + + end = maps + size / sizeof(__be32); + + while (maps < end) { + maps++; + maps = of_translate_dma_region(dev->of_node, maps, &heap_base, + &heap_size); + } + + isp->fw.heap_top = heap_base + heap_size; + + err = of_property_read_u64(dev->of_node, "apple,dart-vm-size", + &vm_size); + if (err) { + dev_err(dev, "failed to read 'apple,dart-vm-size': %d\n", err); + return err; + } + + // FIXME: refactor this, maybe use regular iova stuff? + drm_mm_init(&isp->iovad, isp->fw.heap_top, + vm_size - (heap_base & 0xffffffff)); + + return 0; +} + +static void apple_isp_free_iommu(struct apple_isp *isp) +{ + drm_mm_takedown(&isp->iovad); +} + +static int isp_of_read_coord(struct device *dev, struct device_node *np, + const char *prop, struct coord *val) +{ + u32 xy[2]; + int ret; + + ret = of_property_read_u32_array(np, prop, xy, 2); + if (ret) { + dev_err(dev, "failed to read '%s' property\n", prop); + return ret; + } + + val->x = xy[0]; + val->y = xy[1]; + return 0; +} + +static int apple_isp_init_presets(struct apple_isp *isp) +{ + struct device *dev = isp->dev; + struct isp_preset *preset; + int err = 0; + + struct device_node *np __free(device_node) = + of_get_child_by_name(dev->of_node, "sensor-presets"); + if (!np) { + dev_err(dev, "failed to get DT node 'presets'\n"); + return -EINVAL; + } + + isp->num_presets = of_get_child_count(np); + if (!isp->num_presets) { + dev_err(dev, "no sensor presets found\n"); + return -EINVAL; + } + + isp->presets = devm_kzalloc( + dev, sizeof(*isp->presets) * isp->num_presets, GFP_KERNEL); + if (!isp->presets) + return -ENOMEM; + + preset = isp->presets; + for_each_child_of_node_scoped(np, child) { + u32 xywh[4]; + + err = of_property_read_u32(child, "apple,config-index", + &preset->index); + if (err) { + dev_err(dev, "no apple,config-index property\n"); + return err; + } + + err = isp_of_read_coord(dev, child, "apple,input-size", + &preset->input_dim); + if (err) + return err; + err = isp_of_read_coord(dev, child, "apple,output-size", + &preset->output_dim); + if (err) + return err; + + err = of_property_read_u32_array(child, "apple,crop", xywh, 4); + if (err) { + dev_err(dev, "failed to read 'apple,crop' property\n"); + return err; + } + preset->crop_offset.x = xywh[0]; + preset->crop_offset.y = xywh[1]; + preset->crop_size.x = xywh[2]; + preset->crop_size.y = xywh[3]; + + preset++; + } + + return 0; +} + +static const char * isp_fw2str(enum isp_firmware_version version) +{ + switch (version) { + case ISP_FIRMWARE_V_12_3: + return "12.3"; + case ISP_FIRMWARE_V_12_4: + return "12.4"; + case ISP_FIRMWARE_V_13_5: + return "13.5"; + default: + return "unknown"; + } +} + +#define ISP_FW_VERSION_MIN_LEN 3 +#define ISP_FW_VERSION_MAX_LEN 5 + +static enum isp_firmware_version isp_read_fw_version(struct device *dev, + const char *name) +{ + u32 ver[ISP_FW_VERSION_MAX_LEN]; + int len = of_property_read_variable_u32_array(dev->of_node, name, ver, + ISP_FW_VERSION_MIN_LEN, + ISP_FW_VERSION_MAX_LEN); + + switch (len) { + case 3: + if (ver[0] == 12 && ver[1] == 3 && ver[2] <= 1) + return ISP_FIRMWARE_V_12_3; + else if (ver[0] == 12 && ver[1] == 4 && ver[2] == 0) + return ISP_FIRMWARE_V_12_4; + else if (ver[0] == 13 && ver[1] == 5 && ver[2] == 0) + return ISP_FIRMWARE_V_13_5; + + dev_warn(dev, "unknown %s: %d.%d.%d\n", name, ver[0], ver[1], ver[2]); + break; + case 4: + dev_warn(dev, "unknown %s: %d.%d.%d.%d\n", name, ver[0], ver[1], + ver[2], ver[3]); + break; + case 5: + dev_warn(dev, "unknown %s: %d.%d.%d.%d.%d\n", name, ver[0], + ver[1], ver[2], ver[3], ver[4]); + break; + default: + dev_warn(dev, "could not parse %s: %d\n", name, len); + break; + } + + return ISP_FIRMWARE_V_UNKNOWN; +} + +static enum isp_firmware_version isp_check_firmware_version(struct device *dev) +{ + enum isp_firmware_version version, compat; + + /* firmware version is just informative */ + version = isp_read_fw_version(dev, "apple,firmware-version"); + compat = isp_read_fw_version(dev, "apple,firmware-compat"); + + dev_info(dev, "ISP firmware-compat: %s (FW: %s)\n", isp_fw2str(compat), + isp_fw2str(version)); + + return compat; +} + +static int apple_isp_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct apple_isp *isp; + int err; + + err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(42)); + if (err) + return err; + + isp = devm_kzalloc(dev, sizeof(*isp), GFP_KERNEL); + if (!isp) + return -ENOMEM; + + isp->dev = dev; + isp->hw = of_device_get_match_data(dev); + platform_set_drvdata(pdev, isp); + dev_set_drvdata(dev, isp); + + /* Differences between firmware versions are rather minor so try to work + * with unknown firmware. + */ + isp->fw_compat = isp_check_firmware_version(dev); + + err = of_property_read_u32(dev->of_node, "apple,platform-id", + &isp->platform_id); + if (err) { + dev_err(dev, "failed to get 'apple,platform-id' property: %d\n", + err); + return err; + } + + err = of_property_read_u32(dev->of_node, "apple,temporal-filter", + &isp->temporal_filter); + if (err) + isp->temporal_filter = 0; + + err = apple_isp_init_presets(isp); + if (err) { + dev_err(dev, "failed to initialize presets\n"); + return err; + } + + err = apple_isp_attach_genpd(isp); + if (err) { + dev_err(dev, "failed to attatch power domains\n"); + return err; + } + + isp->coproc = devm_platform_ioremap_resource_byname(pdev, "coproc"); + if (IS_ERR(isp->coproc)) { + err = PTR_ERR(isp->coproc); + goto detach_genpd; + } + + isp->mbox = devm_platform_ioremap_resource_byname(pdev, "mbox"); + if (IS_ERR(isp->mbox)) { + err = PTR_ERR(isp->mbox); + goto detach_genpd; + } + + isp->gpio = devm_platform_ioremap_resource_byname(pdev, "gpio"); + if (IS_ERR(isp->gpio)) { + err = PTR_ERR(isp->gpio); + goto detach_genpd; + } + + isp->mbox2 = devm_platform_ioremap_resource_byname(pdev, "mbox2"); + if (IS_ERR(isp->mbox2)) { + err = PTR_ERR(isp->mbox2); + goto detach_genpd; + } + + isp->irq = platform_get_irq(pdev, 0); + if (isp->irq < 0) { + err = isp->irq; + goto detach_genpd; + } + if (!isp->irq) { + err = -ENODEV; + goto detach_genpd; + } + + mutex_init(&isp->iovad_lock); + mutex_init(&isp->video_lock); + spin_lock_init(&isp->buf_lock); + init_waitqueue_head(&isp->wait); + INIT_LIST_HEAD(&isp->gc); + INIT_LIST_HEAD(&isp->bufs_pending); + INIT_LIST_HEAD(&isp->bufs_submitted); + isp->wq = alloc_workqueue("apple-isp-wq", WQ_UNBOUND, 0); + if (!isp->wq) { + dev_err(dev, "failed to create workqueue\n"); + err = -ENOMEM; + goto detach_genpd; + } + + err = apple_isp_init_iommu(isp); + if (err) { + dev_err(dev, "failed to init iommu: %d\n", err); + goto destroy_wq; + } + + err = apple_isp_alloc_firmware_surface(isp); + if (err) { + dev_err(dev, "failed to alloc firmware surface: %d\n", err); + goto free_iommu; + } + + pm_runtime_enable(dev); + + err = apple_isp_detect_camera(isp); + if (err) { + dev_err(dev, "failed to detect camera: %d\n", err); + goto free_surface; + } + + err = apple_isp_setup_video(isp); + if (err) { + dev_err(dev, "failed to register video device: %d\n", err); + goto free_surface; + } + + dev_info(dev, "apple-isp probe!\n"); + + return 0; + +free_surface: + pm_runtime_disable(dev); + apple_isp_free_firmware_surface(isp); +free_iommu: + apple_isp_free_iommu(isp); +destroy_wq: + destroy_workqueue(isp->wq); +detach_genpd: + apple_isp_detach_genpd(isp); + return err; +} + +static void apple_isp_remove(struct platform_device *pdev) +{ + struct apple_isp *isp = platform_get_drvdata(pdev); + + apple_isp_remove_video(isp); + pm_runtime_disable(isp->dev); + apple_isp_free_firmware_surface(isp); + apple_isp_free_iommu(isp); + destroy_workqueue(isp->wq); + apple_isp_detach_genpd(isp); +} + +static const struct apple_isp_hw apple_isp_hw_t8103 = { + .gen = ISP_GEN_T8103, + .pmu_base = 0x23b704000, + + .dsid_count = 4, + .dsid_clr_base0 = 0x200014000, + .dsid_clr_base1 = 0x200054000, + .dsid_clr_base2 = 0x200094000, + .dsid_clr_base3 = 0x2000d4000, + .dsid_clr_range0 = 0x1000, + .dsid_clr_range1 = 0x1000, + .dsid_clr_range2 = 0x1000, + .dsid_clr_range3 = 0x1000, + + .clock_scratch = 0x23b738010, + .clock_base = 0x23bc3c000, + .clock_bit = 0x1, + .clock_size = 0x4, + .bandwidth_scratch = 0x23b73800c, + .bandwidth_base = 0x23bc3c000, + .bandwidth_bit = 0x0, + .bandwidth_size = 0x4, + + .scl1 = false, + .lpdp = false, + .meta_size = ISP_META_SIZE_T8103, +}; + +static const struct apple_isp_hw apple_isp_hw_t6000 = { + .gen = ISP_GEN_T8103, + .pmu_base = 0x28e584000, + + .dsid_count = 1, + .dsid_clr_base0 = 0x200014000, + .dsid_clr_base1 = 0x200054000, + .dsid_clr_base2 = 0x200094000, + .dsid_clr_base3 = 0x2000d4000, + .dsid_clr_range0 = 0x1000, + .dsid_clr_range1 = 0x1000, + .dsid_clr_range2 = 0x1000, + .dsid_clr_range3 = 0x1000, + + .clock_scratch = 0x28e3d0868, + .clock_base = 0x0, + .clock_bit = 0x0, + .clock_size = 0x8, + .bandwidth_scratch = 0x28e3d0980, + .bandwidth_base = 0x0, + .bandwidth_bit = 0x0, + .bandwidth_size = 0x8, + + .scl1 = false, + .lpdp = false, + .meta_size = ISP_META_SIZE_T8103, +}; + +static const struct apple_isp_hw apple_isp_hw_t8112 = { + .gen = ISP_GEN_T8112, + .pmu_base = 0x23b704000, + + .dsid_count = 1, + .dsid_clr_base0 = 0x200f14000, + .dsid_clr_range0 = 0x1000, + + .clock_scratch = 0x23b3d0560, + .clock_base = 0x0, + .clock_bit = 0x0, + .clock_size = 0x8, + .bandwidth_scratch = 0x23b3d05d0, + .bandwidth_base = 0x0, + .bandwidth_bit = 0x0, + .bandwidth_size = 0x8, + + .scl1 = false, + .lpdp = false, + .meta_size = ISP_META_SIZE_T8112, +}; + +static const struct apple_isp_hw apple_isp_hw_t6020 = { + .gen = ISP_GEN_T8112, + .pmu_base = 0x290284000, + + .dsid_count = 1, + .dsid_clr_base0 = 0x200f14000, + .dsid_clr_range0 = 0x1000, + + .clock_scratch = 0x28e3d10a8, + .clock_base = 0x0, + .clock_bit = 0x0, + .clock_size = 0x8, + .bandwidth_scratch = 0x28e3d1200, + .bandwidth_base = 0x0, + .bandwidth_bit = 0x0, + .bandwidth_size = 0x8, + + .scl1 = true, + .lpdp = true, + .meta_size = ISP_META_SIZE_T8112, +}; + +static const struct of_device_id apple_isp_of_match[] = { + { .compatible = "apple,t8103-isp", .data = &apple_isp_hw_t8103 }, + { .compatible = "apple,t8112-isp", .data = &apple_isp_hw_t8112 }, + { .compatible = "apple,t6000-isp", .data = &apple_isp_hw_t6000 }, + { .compatible = "apple,t6020-isp", .data = &apple_isp_hw_t6020 }, + {}, +}; +MODULE_DEVICE_TABLE(of, apple_isp_of_match); + +static __maybe_unused int apple_isp_runtime_suspend(struct device *dev) +{ + /* RPM sleep is called when the V4L2 file handle is closed */ + return 0; +} + +static __maybe_unused int apple_isp_runtime_resume(struct device *dev) +{ + return 0; +} + +static __maybe_unused int apple_isp_suspend(struct device *dev) +{ + struct apple_isp *isp = dev_get_drvdata(dev); + + /* We must restore V4L2 context on system resume. If we were streaming + * before, we (essentially) stop streaming and start streaming again. + */ + apple_isp_video_suspend(isp); + + return 0; +} + +static __maybe_unused int apple_isp_resume(struct device *dev) +{ + struct apple_isp *isp = dev_get_drvdata(dev); + + apple_isp_video_resume(isp); + + return 0; +} + +static const struct dev_pm_ops apple_isp_pm_ops = { + SYSTEM_SLEEP_PM_OPS(apple_isp_suspend, apple_isp_resume) + RUNTIME_PM_OPS(apple_isp_runtime_suspend, apple_isp_runtime_resume, NULL) +}; + +static struct platform_driver apple_isp_driver = { + .driver = { + .name = "apple-isp", + .of_match_table = apple_isp_of_match, + .pm = pm_ptr(&apple_isp_pm_ops), + }, + .probe = apple_isp_probe, + .remove = apple_isp_remove, +}; +module_platform_driver(apple_isp_driver); + +MODULE_AUTHOR("Eileen Yoon "); +MODULE_DESCRIPTION("Apple ISP driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/media/platform/apple/isp/isp-drv.h b/drivers/media/platform/apple/isp/isp-drv.h new file mode 100644 index 00000000000000..96a1d0b39f860d --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-drv.h @@ -0,0 +1,290 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#ifndef __ISP_DRV_H__ +#define __ISP_DRV_H__ + +#include +#include +#include +#include + +#include +#include +#include +#include + +/* #define APPLE_ISP_DEBUG */ +#define APPLE_ISP_DEVICE_NAME "apple-isp" +#define APPLE_ISP_CARD_NAME "FaceTime HD Camera" + +#define ISP_MAX_CHANNELS 6 +#define ISP_IPC_MESSAGE_SIZE 64 +#define ISP_IPC_FLAG_ACK 0x1 +#define ISP_META_SIZE_T8103 0x4640 +#define ISP_META_SIZE_T8112 0x4840 + +/* used to limit the user space buffers to the buffer_pool_config */ +#define ISP_MAX_BUFFERS 16 + +enum isp_generation { + ISP_GEN_T8103, + ISP_GEN_T8112, +}; + +enum isp_firmware_version { + ISP_FIRMWARE_V_UNKNOWN, + ISP_FIRMWARE_V_12_3, + ISP_FIRMWARE_V_12_4, + ISP_FIRMWARE_V_13_5, +}; + +struct isp_surf { + struct drm_mm_node *mm; + struct list_head head; + u64 size; + u64 type; + u32 num_pages; + struct page **pages; + struct sg_table sgt; + dma_addr_t iova; + void *virt; + refcount_t refcount; + bool gc; + bool submitted; +}; + +struct isp_message { + u64 arg0; + u64 arg1; + u64 arg2; + u64 arg3; + u64 arg4; + u64 arg5; + u64 arg6; + u64 arg7; +} __packed; +static_assert(sizeof(struct isp_message) == ISP_IPC_MESSAGE_SIZE); + +struct isp_channel { + char *name; + u32 type; + u32 src; + u32 num; + u64 size; + dma_addr_t iova; + void *virt; + u32 doorbell; + u32 cursor; + struct mutex lock; + struct isp_message req; + struct isp_message rsp; + const struct isp_chan_ops *ops; +}; + +struct coord { + u32 x; + u32 y; +}; + +struct isp_preset { + u32 index; + struct coord input_dim; + struct coord output_dim; + struct coord crop_offset; + struct coord crop_size; +}; + +struct apple_isp_hw { + enum isp_generation gen; + u64 pmu_base; + + int dsid_count; + u64 dsid_clr_base0; + u64 dsid_clr_base1; + u64 dsid_clr_base2; + u64 dsid_clr_base3; + u32 dsid_clr_range0; + u32 dsid_clr_range1; + u32 dsid_clr_range2; + u32 dsid_clr_range3; + + u64 clock_scratch; + u64 clock_base; + u8 clock_bit; + u8 clock_size; + u64 bandwidth_scratch; + u64 bandwidth_base; + u8 bandwidth_bit; + u8 bandwidth_size; + + u32 meta_size; + bool scl1; + bool lpdp; +}; + +enum isp_sensor_id { + ISP_IMX248_1820_01, + ISP_IMX248_1822_02, + ISP_IMX343_5221_02, + ISP_IMX354_9251_02, + ISP_IMX356_4820_01, + ISP_IMX356_4820_02, + ISP_IMX364_8720_01, + ISP_IMX364_8723_01, + ISP_IMX372_3820_01, + ISP_IMX372_3820_02, + ISP_IMX372_3820_11, + ISP_IMX372_3820_12, + ISP_IMX405_9720_01, + ISP_IMX405_9721_01, + ISP_IMX405_9723_01, + ISP_IMX414_2520_01, + ISP_IMX503_7820_01, + ISP_IMX503_7820_02, + ISP_IMX505_3921_01, + ISP_IMX514_2820_01, + ISP_IMX514_2820_02, + ISP_IMX514_2820_03, + ISP_IMX514_2820_04, + ISP_IMX558_1921_01, + ISP_IMX558_1922_02, + ISP_IMX603_7920_01, + ISP_IMX603_7920_02, + ISP_IMX603_7921_01, + ISP_IMX613_4920_01, + ISP_IMX613_4920_02, + ISP_IMX614_2921_01, + ISP_IMX614_2921_02, + ISP_IMX614_2922_02, + ISP_IMX633_3622_01, + ISP_IMX703_7721_01, + ISP_IMX703_7722_01, + ISP_IMX713_4721_01, + ISP_IMX713_4722_01, + ISP_IMX714_2022_01, + ISP_IMX772_3721_01, + ISP_IMX772_3721_11, + ISP_IMX772_3722_01, + ISP_IMX772_3723_01, + ISP_IMX814_2123_01, + ISP_IMX853_7622_01, + ISP_IMX913_7523_01, + ISP_VD56G0_6221_01, + ISP_VD56G0_6222_01, +}; + +struct isp_format { + enum isp_sensor_id id; + u32 version; + struct isp_preset *preset; + unsigned int num_planes; + u32 strides[VB2_MAX_PLANES]; + size_t plane_size[VB2_MAX_PLANES]; + size_t total_size; +}; + +struct apple_isp { + struct device *dev; + const struct apple_isp_hw *hw; + enum isp_firmware_version fw_compat; + u32 platform_id; + u32 temporal_filter; + struct isp_preset *presets; + int num_presets; + + int num_channels; + struct isp_format fmts[ISP_MAX_CHANNELS]; + unsigned int current_ch; + + struct video_device vdev; + struct media_device mdev; + struct v4l2_device v4l2_dev; + struct vb2_queue vbq; + struct mutex video_lock; + unsigned int sequence; + bool multiplanar; + + int pd_count; + struct device **pd_dev; + struct device_link **pd_link; + bool pds_active; + + int irq; + + void __iomem *coproc; + void __iomem *mbox; + void __iomem *gpio; + void __iomem *mbox2; + + struct iommu_domain *domain; + unsigned long shift; + struct drm_mm iovad; /* TODO iova.c can't allocate bottom-up */ + struct mutex iovad_lock; + + struct isp_firmware { + u64 heap_top; + } fw; + + struct isp_surf *ipc_surf; + struct isp_surf *extra_surf; + struct isp_surf *data_surf; + struct isp_surf *log_surf; + struct isp_surf *bt_surf; + struct isp_surf *meta_surfs[ISP_MAX_BUFFERS]; + struct list_head gc; + struct workqueue_struct *wq; + + int num_ipc_chans; + struct isp_channel **ipc_chans; + struct isp_channel *chan_tm; /* TERMINAL */ + struct isp_channel *chan_io; /* IO */ + struct isp_channel *chan_dg; /* DEBUG */ + struct isp_channel *chan_bh; /* BUF_H2T */ + struct isp_channel *chan_bt; /* BUF_T2H */ + struct isp_channel *chan_sm; /* SHAREDMALLOC */ + struct isp_channel *chan_it; /* IO_T2H */ + + wait_queue_head_t wait; + dma_addr_t cmd_iova; + void *cmd_virt; + + unsigned long state; + spinlock_t buf_lock; + struct list_head bufs_pending; + struct list_head bufs_submitted; +}; + +struct isp_chan_ops { + int (*handle)(struct apple_isp *isp, struct isp_channel *chan); +}; + +struct isp_buffer { + struct vb2_v4l2_buffer vb; + struct list_head link; + struct isp_surf surfs[VB2_MAX_PLANES]; +}; + +#define to_isp_buffer(x) container_of((x), struct isp_buffer, vb) + +enum { + ISP_STATE_STREAMING, + ISP_STATE_LOGGING, + ISP_STATE_SLEEPING, +}; + +#ifdef APPLE_ISP_DEBUG +#define isp_dbg(isp, fmt, ...) \ + dev_info((isp)->dev, "[%s] " fmt, __func__, ##__VA_ARGS__) +#else +#define isp_dbg(isp, fmt, ...) \ + dev_dbg((isp)->dev, "[%s] " fmt, __func__, ##__VA_ARGS__) +#endif + +#define isp_err(isp, fmt, ...) \ + dev_err((isp)->dev, "[%s] " fmt, __func__, ##__VA_ARGS__) + +#define isp_get_format(isp, ch) (&(isp)->fmts[(ch)]) +#define isp_get_current_format(isp) (isp_get_format(isp, isp->current_ch)) + +#endif /* __ISP_DRV_H__ */ diff --git a/drivers/media/platform/apple/isp/isp-fw.c b/drivers/media/platform/apple/isp/isp-fw.c new file mode 100644 index 00000000000000..a39f5fb4445fa7 --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-fw.c @@ -0,0 +1,788 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#include "isp-fw.h" + +#include +#include +#include +#include + +#include "isp-cmd.h" +#include "isp-iommu.h" +#include "isp-ipc.h" +#include "isp-regs.h" +#include "isp-v4l2.h" + +#define ISP_FIRMWARE_MDELAY 1 +#define ISP_FIRMWARE_MAX_TRIES 1000 + +#define ISP_FIRMWARE_IPC_SIZE 0x1c000 +#define ISP_FIRMWARE_DATA_SIZE 0x28000 + +#define ISP_COPROC_IN_WFI 0x3 + +static inline u32 isp_coproc_read32(struct apple_isp *isp, u32 reg) +{ + return readl(isp->coproc + reg); +} + +static inline void isp_coproc_write32(struct apple_isp *isp, u32 reg, u32 val) +{ + writel(val, isp->coproc + reg); +} + +static inline u32 isp_gpio_read32(struct apple_isp *isp, u32 reg) +{ + return readl(isp->gpio + reg); +} + +static inline void isp_gpio_write32(struct apple_isp *isp, u32 reg, u32 val) +{ + writel(val, isp->gpio + reg); +} + +static int apple_isp_power_up_domains(struct apple_isp *isp) +{ + int ret; + + if (isp->pds_active) + return 0; + + for (int i = 1; i < isp->pd_count; i++) { + ret = pm_runtime_get_sync(isp->pd_dev[i]); + if (ret < 0) { + dev_err(isp->dev, + "Failed to power up power domain %d: %d\n", i, ret); + while (--i != 1) + pm_runtime_put_sync(isp->pd_dev[i]); + return ret; + } + } + + isp->pds_active = true; + + return 0; +} + +static void apple_isp_power_down_domains(struct apple_isp *isp) +{ + int ret; + + if (!isp->pds_active) + return; + + for (int i = isp->pd_count - 1; i >= 1; i--) { + ret = pm_runtime_put_sync(isp->pd_dev[i]); + if (ret < 0) + dev_err(isp->dev, + "Failed to power up power domain %d: %d\n", i, ret); + } + + isp->pds_active = false; +} + +void *apple_isp_translate(struct apple_isp *isp, struct isp_surf *surf, + dma_addr_t iova, size_t size) +{ + dma_addr_t end = iova + size; + if (!surf) { + dev_err(isp->dev, + "Failed to translate IPC iova 0x%llx (0x%zx): No surface\n", + (long long)iova, size); + return NULL; + } + + if (end < iova || iova < surf->iova || + end > (surf->iova + surf->size)) { + dev_err(isp->dev, + "Failed to translate IPC iova 0x%llx (0x%zx): Out of bounds\n", + (long long)iova, size); + return NULL; + } + + if (!surf->virt) { + dev_err(isp->dev, + "Failed to translate IPC iova 0x%llx (0x%zx): No VMap\n", + (long long)iova, size); + return NULL; + } + + return surf->virt + (iova - surf->iova); +} + +struct isp_firmware_bootargs { + u32 pad_0[2]; + u64 ipc_iova; + u64 shared_base; + u64 shared_size; + u64 extra_iova; + u64 extra_size; + u32 platform_id; + u32 pad_40; + u64 logbuf_addr; + u64 logbuf_size; + u64 logbuf_entsize; + u32 ipc_size; + u32 pad_60[5]; + u32 unk5; + u32 pad_7c[13]; + u32 pad_b0; + u32 unk7; + u32 pad_b8[5]; + u32 unk_iova1; + u32 pad_c0[47]; + u32 unk9; +} __packed; +static_assert(sizeof(struct isp_firmware_bootargs) == 0x180); + +struct isp_chan_desc { + char name[64]; + u32 type; + u32 src; + u32 num; + u32 pad; + u64 iova; + u32 padding[0x2a]; +} __packed; +static_assert(sizeof(struct isp_chan_desc) == 0x100); + +static const struct isp_chan_ops tm_ops = { + .handle = ipc_tm_handle, +}; + +static const struct isp_chan_ops sm_ops = { + .handle = ipc_sm_handle, +}; + +static const struct isp_chan_ops bt_ops = { + .handle = ipc_bt_handle, +}; + +static irqreturn_t apple_isp_isr(int irq, void *dev) +{ + struct apple_isp *isp = dev; + + isp_mbox2_write32(isp, ISP_MBOX2_IRQ_ACK, + isp_mbox_read32(isp, ISP_MBOX_IRQ_INTERRUPT)); + + return IRQ_WAKE_THREAD; +} + +static irqreturn_t apple_isp_isr_thread(int irq, void *dev) +{ + struct apple_isp *isp = dev; + + wake_up_all(&isp->wait); + + ipc_chan_handle(isp, isp->chan_sm); + wake_up_all(&isp->wait); /* Some commands depend on sm */ + + ipc_chan_handle(isp, isp->chan_tm); + + ipc_chan_handle(isp, isp->chan_bt); + wake_up_all(&isp->wait); + + return IRQ_HANDLED; +} + +static void isp_disable_irq(struct apple_isp *isp) +{ + isp_mbox_write32(isp, ISP_MBOX_IRQ_ENABLE, 0x0); + free_irq(isp->irq, isp); + isp_gpio_write32(isp, ISP_GPIO_1, 0xfeedbabe); /* real funny */ +} + +static int isp_enable_irq(struct apple_isp *isp) +{ + int err; + + err = request_threaded_irq(isp->irq, apple_isp_isr, + apple_isp_isr_thread, 0, "apple-isp", isp); + if (err < 0) { + isp_err(isp, "failed to request IRQ#%u (%d)\n", isp->irq, err); + return err; + } + + isp_dbg(isp, "about to enable interrupts...\n"); + + isp_mbox_write32(isp, ISP_MBOX_IRQ_ENABLE, 0xf); + + return 0; +} + +static int isp_reset_coproc(struct apple_isp *isp) +{ + int retries; + u32 status; + u32 val; + + isp_coproc_write32(isp, ISP_COPROC_EDPRCR, 0x2); + + isp_coproc_write32(isp, ISP_COPROC_FABRIC_0, 0xff00ff); + isp_coproc_write32(isp, ISP_COPROC_FABRIC_1, 0xff00ff); + isp_coproc_write32(isp, ISP_COPROC_FABRIC_2, 0xff00ff); + isp_coproc_write32(isp, ISP_COPROC_FABRIC_3, 0xff00ff); + + isp_coproc_write32(isp, ISP_COPROC_IRQ_MASK_0, 0xffffffff); + isp_coproc_write32(isp, ISP_COPROC_IRQ_MASK_1, 0xffffffff); + isp_coproc_write32(isp, ISP_COPROC_IRQ_MASK_2, 0xffffffff); + isp_coproc_write32(isp, ISP_COPROC_IRQ_MASK_3, 0xffffffff); + isp_coproc_write32(isp, ISP_COPROC_IRQ_MASK_4, 0xffffffff); + isp_coproc_write32(isp, ISP_COPROC_IRQ_MASK_5, 0xffffffff); + + for (retries = 0; retries < 128; retries++) { + val = isp_coproc_read32(isp, 0x818); + if (val == 0) + break; + } + + for (retries = 0; retries < 128; retries++) { + val = isp_coproc_read32(isp, 0x81c); + if (val == 0) + break; + } + + for (retries = 0; retries < ISP_FIRMWARE_MAX_TRIES; retries++) { + status = isp_coproc_read32(isp, ISP_COPROC_STATUS); + if (status & ISP_COPROC_IN_WFI) { + isp_dbg(isp, "%d: coproc in WFI (status: 0x%x)\n", + retries, status); + break; + } + mdelay(ISP_FIRMWARE_MDELAY); + } + if (retries >= ISP_FIRMWARE_MAX_TRIES) { + isp_err(isp, "coproc NOT in WFI (status: 0x%x)\n", status); + return -ENODEV; + } + + return 0; +} + +static void isp_firmware_shutdown_stage1(struct apple_isp *isp) +{ + isp_coproc_write32(isp, ISP_COPROC_CONTROL, 0x0); + + apple_isp_power_down_domains(isp); +} + +static int isp_firmware_boot_stage1(struct apple_isp *isp) +{ + int err, retries; + // u32 val; + + err = apple_isp_power_up_domains(isp); + if (err < 0) + return err; + + + isp_gpio_write32(isp, ISP_GPIO_CLOCK_EN, 0x1); + +#if 0 + /* This doesn't work well with system sleep */ + val = isp_gpio_read32(isp, ISP_GPIO_1); + if (val == 0xfeedbabe) { + err = isp_reset_coproc(isp); + if (err < 0) + return err; + } +#endif + + err = isp_reset_coproc(isp); + if (err < 0) + return err; + + isp_gpio_write32(isp, ISP_GPIO_0, 0x0); + isp_gpio_write32(isp, ISP_GPIO_1, 0x0); + isp_gpio_write32(isp, ISP_GPIO_2, 0x0); + isp_gpio_write32(isp, ISP_GPIO_3, 0x0); + isp_gpio_write32(isp, ISP_GPIO_4, 0x0); + isp_gpio_write32(isp, ISP_GPIO_5, 0x0); + isp_gpio_write32(isp, ISP_GPIO_6, 0x0); + isp_gpio_write32(isp, ISP_GPIO_7, 0x0); + + isp_mbox_write32(isp, ISP_MBOX_IRQ_ENABLE, 0x0); + + isp_coproc_write32(isp, ISP_COPROC_CONTROL, 0x0); + isp_coproc_write32(isp, ISP_COPROC_CONTROL, 0x10); + + /* Wait for ISP_GPIO_7 to 0x0 -> 0x8042006 */ + for (retries = 0; retries < ISP_FIRMWARE_MAX_TRIES; retries++) { + u32 val = isp_gpio_read32(isp, ISP_GPIO_7); + if (val == 0x8042006) { + isp_dbg(isp, + "got first magic number (0x%x) from firmware\n", + val); + break; + } + mdelay(ISP_FIRMWARE_MDELAY); + } + if (retries >= ISP_FIRMWARE_MAX_TRIES) { + isp_err(isp, + "never received first magic number from firmware\n"); + return -ENODEV; + } + + return 0; +} + +int apple_isp_alloc_firmware_surface(struct apple_isp *isp) +{ + /* These are static, so let's do it once and for all */ + isp->ipc_surf = isp_alloc_surface_vmap(isp, ISP_FIRMWARE_IPC_SIZE); + if (!isp->ipc_surf) { + isp_err(isp, "failed to alloc shared surface for ipc\n"); + return -ENOMEM; + } + dev_info(isp->dev, "IPC surface iova: 0x%llx\n", + (long long)isp->ipc_surf->iova); + + isp->data_surf = isp_alloc_surface_vmap(isp, ISP_FIRMWARE_DATA_SIZE); + if (!isp->data_surf) { + isp_err(isp, "failed to alloc shared surface for data files\n"); + isp_free_surface(isp, isp->ipc_surf); + return -ENOMEM; + } + dev_info(isp->dev, "Data surface iova: 0x%llx\n", + (long long)isp->data_surf->iova); + + return 0; +} + +void apple_isp_free_firmware_surface(struct apple_isp *isp) +{ + isp_free_surface(isp, isp->data_surf); + isp_free_surface(isp, isp->ipc_surf); +} + +static void isp_firmware_shutdown_stage2(struct apple_isp *isp) +{ + isp_free_surface(isp, isp->extra_surf); +} + +static int isp_firmware_boot_stage2(struct apple_isp *isp) +{ + struct isp_firmware_bootargs args; + dma_addr_t args_iova; + void *args_virt; + int err, retries; + + u32 num_ipc_chans = isp_gpio_read32(isp, ISP_GPIO_0); + u32 args_offset = isp_gpio_read32(isp, ISP_GPIO_1); + u32 extra_size = isp_gpio_read32(isp, ISP_GPIO_3); + isp->num_ipc_chans = num_ipc_chans; + + if (!isp->num_ipc_chans) { + dev_err(isp->dev, "No IPC channels found\n"); + return -ENODEV; + } + + if (isp->num_ipc_chans != 7) + dev_warn(isp->dev, "unexpected channel count (%d)\n", + num_ipc_chans); + + isp->extra_surf = isp_alloc_surface_vmap(isp, extra_size); + if (!isp->extra_surf) { + isp_err(isp, "failed to alloc surface for extra heap\n"); + return -ENOMEM; + } + + args_iova = isp->ipc_surf->iova + args_offset + 0x40; + args_virt = isp->ipc_surf->virt + args_offset + 0x40; + isp->cmd_iova = args_iova + sizeof(args) + 0x40; + isp->cmd_virt = args_virt + sizeof(args) + 0x40; + + memset(&args, 0, sizeof(args)); + args.ipc_iova = isp->ipc_surf->iova; + args.ipc_size = isp->ipc_surf->size; + args.shared_base = isp->fw.heap_top & 0xffffffff; + args.shared_size = 0x10000000UL - args.shared_base; + args.extra_iova = isp->extra_surf->iova; + args.extra_size = isp->extra_surf->size; + args.platform_id = isp->platform_id; + args.unk5 = 0x40; + args.unk7 = 0x1; // 0? + args.unk_iova1 = args_iova + sizeof(args) - 0xc; + args.unk9 = 0x3; + memcpy(args_virt, &args, sizeof(args)); + + isp_gpio_write32(isp, ISP_GPIO_0, args_iova); + isp_gpio_write32(isp, ISP_GPIO_1, args_iova >> 32); + dma_wmb(); + + /* Wait for ISP_GPIO_7 to 0xf7fbdff9 -> 0x8042006 */ + isp_gpio_write32(isp, ISP_GPIO_7, 0xf7fbdff9); + + for (retries = 0; retries < ISP_FIRMWARE_MAX_TRIES; retries++) { + u32 val = isp_gpio_read32(isp, ISP_GPIO_7); + if (val == 0x8042006) { + isp_dbg(isp, + "got second magic number (0x%x) from firmware\n", + val); + break; + } + mdelay(ISP_FIRMWARE_MDELAY); + } + if (retries >= ISP_FIRMWARE_MAX_TRIES) { + isp_err(isp, + "never received second magic number from firmware\n"); + err = -ENODEV; + goto free_extra; + } + + return 0; + +free_extra: + isp_free_surface(isp, isp->extra_surf); + return err; +} + +static inline struct isp_channel *isp_get_chan_index(struct apple_isp *isp, + const char *name) +{ + for (int i = 0; i < isp->num_ipc_chans; i++) { + if (!strcasecmp(isp->ipc_chans[i]->name, name)) + return isp->ipc_chans[i]; + } + return NULL; +} + +static void isp_free_channel_info(struct apple_isp *isp) +{ + for (int i = 0; i < isp->num_ipc_chans; i++) { + struct isp_channel *chan = isp->ipc_chans[i]; + if (!chan) + continue; + kfree(chan->name); + kfree(chan); + isp->ipc_chans[i] = NULL; + } + kfree(isp->ipc_chans); + isp->ipc_chans = NULL; +} + +static int isp_fill_channel_info(struct apple_isp *isp) +{ + u64 table_iova = isp_gpio_read32(isp, ISP_GPIO_0) | + ((u64)isp_gpio_read32(isp, ISP_GPIO_1)) << 32; + void *table_virt = apple_isp_ipc_translate( + isp, table_iova, + sizeof(struct isp_chan_desc) * isp->num_ipc_chans); + + if (!table_virt) { + dev_err(isp->dev, "Failed to find channel table\n"); + return -EIO; + } + + isp->ipc_chans = kcalloc(isp->num_ipc_chans, + sizeof(struct isp_channel *), GFP_KERNEL); + if (!isp->ipc_chans) + goto out; + + for (int i = 0; i < isp->num_ipc_chans; i++) { + struct isp_chan_desc desc; + void *desc_virt = table_virt + (i * sizeof(desc)); + struct isp_channel *chan = + kzalloc(sizeof(struct isp_channel), GFP_KERNEL); + if (!chan) + goto out; + isp->ipc_chans[i] = chan; + + memcpy(&desc, desc_virt, sizeof(desc)); + chan->name = kstrdup(desc.name, GFP_KERNEL); + chan->type = desc.type; + chan->src = desc.src; + chan->doorbell = 1 << chan->src; + chan->num = desc.num; + chan->size = desc.num * ISP_IPC_MESSAGE_SIZE; + chan->iova = desc.iova; + chan->virt = + apple_isp_ipc_translate(isp, desc.iova, chan->size); + chan->cursor = 0; + mutex_init(&chan->lock); + + if (!chan->virt) { + dev_err(isp->dev, "Failed to find channel buffer\n"); + goto out; + } + + if ((chan->type != ISP_IPC_CHAN_TYPE_COMMAND) && + (chan->type != ISP_IPC_CHAN_TYPE_REPLY) && + (chan->type != ISP_IPC_CHAN_TYPE_REPORT)) { + isp_err(isp, "invalid ipc chan type (%d)\n", + chan->type); + goto out; + } + + isp_dbg(isp, "chan: %s type: %d src: %d num: %d iova: 0x%llx\n", + chan->name, chan->type, chan->src, chan->num, + chan->iova); + } + + isp->chan_tm = isp_get_chan_index(isp, "TERMINAL"); + isp->chan_io = isp_get_chan_index(isp, "IO"); + isp->chan_dg = isp_get_chan_index(isp, "DEBUG"); + isp->chan_bh = isp_get_chan_index(isp, "BUF_H2T"); + isp->chan_bt = isp_get_chan_index(isp, "BUF_T2H"); + isp->chan_sm = isp_get_chan_index(isp, "SHAREDMALLOC"); + isp->chan_it = isp_get_chan_index(isp, "IO_T2H"); + + if (!isp->chan_tm || !isp->chan_io || !isp->chan_dg || !isp->chan_bh || + !isp->chan_bt || !isp->chan_sm || !isp->chan_it) { + isp_err(isp, "did not find all of the required ipc chans\n"); + goto out; + } + + isp->chan_tm->ops = &tm_ops; + isp->chan_sm->ops = &sm_ops; + isp->chan_bt->ops = &bt_ops; + + return 0; +out: + isp_free_channel_info(isp); + return -ENOMEM; +} + +static void isp_firmware_shutdown_stage3(struct apple_isp *isp) +{ + isp_free_channel_info(isp); +} + +static int isp_firmware_boot_stage3(struct apple_isp *isp) +{ + int err, retries; + + err = isp_fill_channel_info(isp); + if (err < 0) + return err; + + /* Mask the command channels to prepare for submission */ + for (int i = 0; i < isp->num_ipc_chans; i++) { + struct isp_channel *chan = isp->ipc_chans[i]; + if (chan->type != ISP_IPC_CHAN_TYPE_COMMAND) + continue; + for (int j = 0; j < chan->num; j++) { + struct isp_message msg; + void *msg_virt = chan->virt + (j * sizeof(msg)); + + memset(&msg, 0, sizeof(msg)); + msg.arg0 = ISP_IPC_FLAG_ACK; + memcpy(msg_virt, &msg, sizeof(msg)); + } + } + dma_wmb(); + + /* Wait for ISP_GPIO_3 to 0x8042006 -> 0x0 */ + isp_gpio_write32(isp, ISP_GPIO_3, 0x8042006); + + for (retries = 0; retries < ISP_FIRMWARE_MAX_TRIES; retries++) { + u32 val = isp_gpio_read32(isp, ISP_GPIO_3); + if (val == 0x0) { + isp_dbg(isp, + "got third magic number (0x%x) from firmware\n", + val); + break; + } + mdelay(ISP_FIRMWARE_MDELAY); + } + if (retries >= ISP_FIRMWARE_MAX_TRIES) { + isp_err(isp, + "never received third magic number from firmware\n"); + isp_free_channel_info(isp); + return -ENODEV; + } + + isp_dbg(isp, "firmware booted!\n"); + + return 0; +} + +static int isp_stop_command_processor(struct apple_isp *isp) +{ + int retries; + +#if 0 + int res = isp_cmd_stop(isp, 0); + if (res) { + isp_err(isp, "isp_cmd_stop() failed\n"); + return res; + } + + /* Wait for ISP_GPIO_0 to 0xf7fbdff9 -> 0x8042006 */ + isp_gpio_write32(isp, ISP_GPIO_0, 0xf7fbdff9); + + isp_cmd_power_down(isp); +#else + isp_gpio_write32(isp, ISP_GPIO_0, 0xf7fbdff9); + + int res = isp_cmd_suspend(isp); + if (res) { + isp_err(isp, "isp_cmd_suspend() failed\n"); + return res; + } +#endif + + for (retries = 0; retries < ISP_FIRMWARE_MAX_TRIES; retries++) { + u32 val = isp_gpio_read32(isp, ISP_GPIO_0); + if (val == 0x8042006) { + isp_dbg(isp, "got magic number (0x%x) from firmware\n", + val); + break; + } + mdelay(ISP_FIRMWARE_MDELAY); + } + if (retries >= ISP_FIRMWARE_MAX_TRIES) { + isp_err(isp, "never received magic number from firmware\n"); + return -ENODEV; + } + + return 0; +} + +static int isp_start_command_processor(struct apple_isp *isp) +{ + int err; + + err = isp_cmd_print_enable(isp, 1); + if (err) + return err; + + err = isp_cmd_set_isp_pmu_base(isp, isp->hw->pmu_base); + if (err) + return err; + + if (isp->hw->dsid_count == 1) { + err = isp_cmd_set_dsid_clr_req_base( + isp, isp->hw->dsid_clr_base0, isp->hw->dsid_clr_range0); + if (err) + return err; + } else { + err = isp_cmd_set_dsid_clr_req_base2( + isp, isp->hw->dsid_clr_base0, isp->hw->dsid_clr_base1, + isp->hw->dsid_clr_base2, isp->hw->dsid_clr_base3, + isp->hw->dsid_clr_range0, isp->hw->dsid_clr_range1, + isp->hw->dsid_clr_range2, isp->hw->dsid_clr_range3); + if (err) + return err; + } + + err = isp_cmd_pmp_ctrl_set( + isp, isp->hw->clock_scratch, isp->hw->clock_base, + isp->hw->clock_bit, isp->hw->clock_size, + isp->hw->bandwidth_scratch, isp->hw->bandwidth_base, + isp->hw->bandwidth_bit, isp->hw->bandwidth_size); + if (err) + return err; + + err = isp_cmd_start(isp, 0); + if (err) + return err; + + /* Now we can access CISP_CMD_CH_* commands */ + + return 0; +} + +static void isp_collect_gc_surface(struct apple_isp *isp) +{ + struct isp_surf *tmp, *surf; + + isp->log_surf = NULL; + isp->bt_surf = NULL; + + list_for_each_entry_safe_reverse(surf, tmp, &isp->gc, head) { + isp_dbg(isp, "freeing iova: 0x%llx size: 0x%llx virt: %pS\n", + surf->iova, surf->size, (void *)surf->virt); + isp_free_surface(isp, surf); + } +} + +static int isp_firmware_boot(struct apple_isp *isp) +{ + int err; + + err = isp_firmware_boot_stage1(isp); + if (err < 0) { + isp_err(isp, "failed firmware boot stage 1: %d\n", err); + goto garbage_collect; + } + + err = isp_firmware_boot_stage2(isp); + if (err < 0) { + isp_err(isp, "failed firmware boot stage 2: %d\n", err); + goto shutdown_stage1; + } + + err = isp_firmware_boot_stage3(isp); + if (err < 0) { + isp_err(isp, "failed firmware boot stage 3: %d\n", err); + goto shutdown_stage2; + } + + err = isp_enable_irq(isp); + if (err < 0) { + isp_err(isp, "failed to enable interrupts: %d\n", err); + goto shutdown_stage3; + } + + err = isp_start_command_processor(isp); + if (err < 0) { + isp_err(isp, "failed to start command processor: %d\n", err); + goto disable_irqs; + } + + flush_workqueue(isp->wq); + + return 0; + +disable_irqs: + isp_disable_irq(isp); +shutdown_stage3: + isp_firmware_shutdown_stage3(isp); +shutdown_stage2: + isp_firmware_shutdown_stage2(isp); +shutdown_stage1: + isp_firmware_shutdown_stage1(isp); +garbage_collect: + isp_collect_gc_surface(isp); + return err; +} + +static void isp_firmware_shutdown(struct apple_isp *isp) +{ + flush_workqueue(isp->wq); + isp_stop_command_processor(isp); + isp_disable_irq(isp); + isp_firmware_shutdown_stage3(isp); + isp_firmware_shutdown_stage2(isp); + isp_firmware_shutdown_stage1(isp); + isp_collect_gc_surface(isp); +} + +int apple_isp_firmware_boot(struct apple_isp *isp) +{ + int err; + + /* Needs to be power cycled for IOMMU to behave correctly */ + err = pm_runtime_resume_and_get(isp->dev); + if (err < 0) { + dev_err(isp->dev, "failed to enable power: %d\n", err); + return err; + } + + err = isp_firmware_boot(isp); + if (err) { + dev_err(isp->dev, "failed to boot firmware: %d\n", err); + pm_runtime_put_sync(isp->dev); + return err; + } + + return 0; +} + +void apple_isp_firmware_shutdown(struct apple_isp *isp) +{ + isp_firmware_shutdown(isp); + pm_runtime_put_sync(isp->dev); +} diff --git a/drivers/media/platform/apple/isp/isp-fw.h b/drivers/media/platform/apple/isp/isp-fw.h new file mode 100644 index 00000000000000..974216f0989f91 --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-fw.h @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#ifndef __ISP_FW_H__ +#define __ISP_FW_H__ + +#include "isp-drv.h" + +int apple_isp_alloc_firmware_surface(struct apple_isp *isp); +void apple_isp_free_firmware_surface(struct apple_isp *isp); + +int apple_isp_firmware_boot(struct apple_isp *isp); +void apple_isp_firmware_shutdown(struct apple_isp *isp); + +void *apple_isp_translate(struct apple_isp *isp, struct isp_surf *surf, + dma_addr_t iova, size_t size); + +static inline void *apple_isp_ipc_translate(struct apple_isp *isp, + dma_addr_t iova, size_t size) +{ + return apple_isp_translate(isp, isp->ipc_surf, iova, size); +} + +#endif /* __ISP_FW_H__ */ diff --git a/drivers/media/platform/apple/isp/isp-iommu.c b/drivers/media/platform/apple/isp/isp-iommu.c new file mode 100644 index 00000000000000..1ddd089d77355a --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-iommu.c @@ -0,0 +1,250 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#include +#include + +#include "isp-iommu.h" + +static void isp_surf_free_pages(struct isp_surf *surf) +{ + for (u32 i = 0; i < surf->num_pages && surf->pages[i] != NULL; i++) { + __free_page(surf->pages[i]); + } + kvfree(surf->pages); +} + +static int isp_surf_alloc_pages(struct isp_surf *surf) +{ + surf->pages = kvmalloc_array(surf->num_pages, sizeof(*surf->pages), + GFP_KERNEL); + if (!surf->pages) + return -ENOMEM; + + for (u32 i = 0; i < surf->num_pages; i++) { + surf->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (surf->pages[i] == NULL) + goto free_pages; + } + + return 0; + +free_pages: + isp_surf_free_pages(surf); + return -ENOMEM; +} + +int isp_surf_vmap(struct apple_isp *isp, struct isp_surf *surf) +{ + surf->virt = vmap(surf->pages, surf->num_pages, VM_MAP, + pgprot_writecombine(PAGE_KERNEL)); + if (surf->virt == NULL) { + dev_err(isp->dev, "failed to vmap size 0x%llx\n", surf->size); + return -EINVAL; + } + + return 0; +} + +static void isp_surf_vunmap(struct apple_isp *isp, struct isp_surf *surf) +{ + if (surf->virt) + vunmap(surf->virt); + surf->virt = NULL; +} + +static void isp_surf_unreserve_iova(struct apple_isp *isp, + struct isp_surf *surf) +{ + if (surf->mm) { + mutex_lock(&isp->iovad_lock); + drm_mm_remove_node(surf->mm); + mutex_unlock(&isp->iovad_lock); + kfree(surf->mm); + } + surf->mm = NULL; +} + +static int isp_surf_reserve_iova(struct apple_isp *isp, struct isp_surf *surf) +{ + int err; + + surf->mm = kzalloc(sizeof(*surf->mm), GFP_KERNEL); + if (!surf->mm) + return -ENOMEM; + + mutex_lock(&isp->iovad_lock); + err = drm_mm_insert_node_generic(&isp->iovad, surf->mm, + ALIGN(surf->size, 1UL << isp->shift), + 1UL << isp->shift, 0, 0); + mutex_unlock(&isp->iovad_lock); + if (err < 0) { + dev_err(isp->dev, "failed to reserve 0x%llx of iova space\n", + surf->size); + goto mm_free; + } + + surf->iova = surf->mm->start; + + return 0; +mm_free: + kfree(surf->mm); + surf->mm = NULL; + return err; +} + +static void isp_surf_iommu_unmap(struct apple_isp *isp, struct isp_surf *surf) +{ + iommu_unmap(isp->domain, surf->iova, surf->size); + sg_free_table(&surf->sgt); +} + +static int isp_surf_iommu_map(struct apple_isp *isp, struct isp_surf *surf) +{ + unsigned long size; + int err; + + err = sg_alloc_table_from_pages(&surf->sgt, surf->pages, + surf->num_pages, 0, surf->size, + GFP_KERNEL); + if (err < 0) { + dev_err(isp->dev, "failed to alloc sgt from pages\n"); + return err; + } + + size = iommu_map_sgtable(isp->domain, surf->iova, &surf->sgt, + IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE); + if (size < surf->size) { + dev_err(isp->dev, "failed to iommu_map sgt to iova 0x%llx\n", + surf->iova); + sg_free_table(&surf->sgt); + return -ENXIO; + } + + return 0; +} + +static void __isp_surf_init(struct apple_isp *isp, struct isp_surf *surf, + u64 size, bool gc) +{ + surf->mm = NULL; + surf->virt = NULL; + surf->size = ALIGN(size, 1UL << isp->shift); + surf->num_pages = surf->size >> isp->shift; + surf->gc = gc; +} + +struct isp_surf *__isp_alloc_surface(struct apple_isp *isp, u64 size, bool gc) +{ + int err; + + struct isp_surf *surf = kzalloc(sizeof(struct isp_surf), GFP_KERNEL); + if (!surf) + return NULL; + + __isp_surf_init(isp, surf, size, gc); + + err = isp_surf_alloc_pages(surf); + if (err < 0) { + dev_err(isp->dev, "failed to allocate %d pages\n", + surf->num_pages); + goto free_surf; + } + + err = isp_surf_reserve_iova(isp, surf); + if (err < 0) { + dev_err(isp->dev, "failed to reserve 0x%llx of iova space\n", + surf->size); + goto free_pages; + } + + err = isp_surf_iommu_map(isp, surf); + if (err < 0) { + dev_err(isp->dev, + "failed to iommu_map size 0x%llx to iova 0x%llx\n", + surf->size, surf->iova); + goto unreserve_iova; + } + + refcount_set(&surf->refcount, 1); + if (surf->gc) + list_add_tail(&surf->head, &isp->gc); + + return surf; + +unreserve_iova: + isp_surf_unreserve_iova(isp, surf); +free_pages: + isp_surf_free_pages(surf); +free_surf: + kfree(surf); + return NULL; +} + +struct isp_surf *isp_alloc_surface_vmap(struct apple_isp *isp, u64 size) +{ + int err; + + struct isp_surf *surf = __isp_alloc_surface(isp, size, false); + if (!surf) + return NULL; + + err = isp_surf_vmap(isp, surf); + if (err < 0) { + dev_err(isp->dev, "failed to vmap iova 0x%llx - 0x%llx\n", + surf->iova, surf->iova + surf->size); + isp_free_surface(isp, surf); + return NULL; + } + + return surf; +} + +void isp_free_surface(struct apple_isp *isp, struct isp_surf *surf) +{ + if (refcount_dec_and_test(&surf->refcount)) { + isp_surf_vunmap(isp, surf); + isp_surf_iommu_unmap(isp, surf); + isp_surf_unreserve_iova(isp, surf); + isp_surf_free_pages(surf); + if (surf->gc) + list_del(&surf->head); + kfree(surf); + } +} + +int apple_isp_iommu_map_sgt(struct apple_isp *isp, struct isp_surf *surf, + struct sg_table *sgt, u64 size) +{ + int err; + ssize_t mapped; + + // TODO userptr sends unaligned sizes + surf->mm = NULL; + surf->size = size; + + err = isp_surf_reserve_iova(isp, surf); + if (err < 0) { + dev_err(isp->dev, "failed to reserve 0x%llx of iova space\n", + surf->size); + return err; + } + + mapped = iommu_map_sgtable(isp->domain, surf->iova, sgt, + IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE); + if (mapped < surf->size) { + dev_err(isp->dev, "failed to iommu_map sgt to iova 0x%llx\n", + surf->iova); + isp_surf_unreserve_iova(isp, surf); + return -ENXIO; + } + surf->size = mapped; + + return 0; +} + +void apple_isp_iommu_unmap_sgt(struct apple_isp *isp, struct isp_surf *surf) +{ + iommu_unmap(isp->domain, surf->iova, surf->size); + isp_surf_unreserve_iova(isp, surf); +} diff --git a/drivers/media/platform/apple/isp/isp-iommu.h b/drivers/media/platform/apple/isp/isp-iommu.h new file mode 100644 index 00000000000000..b99a182e284b72 --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-iommu.h @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#ifndef __ISP_IOMMU_H__ +#define __ISP_IOMMU_H__ + +#include "isp-drv.h" + +struct isp_surf *__isp_alloc_surface(struct apple_isp *isp, u64 size, bool gc); +#define isp_alloc_surface(isp, size) (__isp_alloc_surface(isp, size, false)) +#define isp_alloc_surface_gc(isp, size) (__isp_alloc_surface(isp, size, true)) +struct isp_surf *isp_alloc_surface_vmap(struct apple_isp *isp, u64 size); +int isp_surf_vmap(struct apple_isp *isp, struct isp_surf *surf); +void isp_free_surface(struct apple_isp *isp, struct isp_surf *surf); + +int apple_isp_iommu_map_sgt(struct apple_isp *isp, struct isp_surf *surf, + struct sg_table *sgt, u64 size); +void apple_isp_iommu_unmap_sgt(struct apple_isp *isp, struct isp_surf *surf); + +#endif /* __ISP_IOMMU_H__ */ diff --git a/drivers/media/platform/apple/isp/isp-ipc.c b/drivers/media/platform/apple/isp/isp-ipc.c new file mode 100644 index 00000000000000..a1948717a31968 --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-ipc.c @@ -0,0 +1,275 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#include "isp-iommu.h" +#include "isp-ipc.h" +#include "isp-regs.h" +#include "isp-fw.h" + +#define ISP_IPC_FLAG_TERMINAL_ACK 0x3 +#define ISP_IPC_BUFEXC_STAT_META_OFFSET 0x10 + +struct isp_sm_deferred_work { + struct work_struct work; + struct apple_isp *isp; + struct isp_surf *surf; +}; + +struct isp_bufexc_stat { + u64 unk_0; // 2 + u64 unk_8; // 2 + + u64 meta_iova; + u64 pad_20[3]; + u64 meta_size; // 0x4640 + u64 unk_38; + + u32 unk_40; // 1 + u32 unk_44; + u64 unk_48; + + u64 iova0; + u64 iova1; + u64 iova2; + u64 iova3; + u32 pad_70[4]; + + u32 unk_80; // 2 + u32 unk_84; // 1 + u32 unk_88; // 0x10 || 0x13 + u32 unk_8c; + u32 pad_90[96]; + + u32 unk_210; // 0x28 + u32 unk_214; + u32 index; + u16 bes_width; // 1296, 0x510 + u16 bes_height; // 736, 0x2e0 + + u32 unk_220; // 0x0 || 0x1 + u32 pad_224[3]; + u32 unk_230; // 0xf7ed38 + u32 unk_234; // 3 + u32 pad_238[2]; + u32 pad_240[16]; +} __packed; +static_assert(sizeof(struct isp_bufexc_stat) == ISP_IPC_BUFEXC_STAT_SIZE); + +static inline void *chan_msg_virt(struct isp_channel *chan, u32 index) +{ + return chan->virt + (index * ISP_IPC_MESSAGE_SIZE); +} + +static inline void chan_read_msg_index(struct apple_isp *isp, + struct isp_channel *chan, + struct isp_message *msg, u32 index) +{ + memcpy(msg, chan_msg_virt(chan, index), sizeof(*msg)); +} + +static inline void chan_read_msg(struct apple_isp *isp, + struct isp_channel *chan, + struct isp_message *msg) +{ + chan_read_msg_index(isp, chan, msg, chan->cursor); +} + +static inline void chan_write_msg_index(struct apple_isp *isp, + struct isp_channel *chan, + struct isp_message *msg, u32 index) +{ + u64 *p0 = chan_msg_virt(chan, index); + memcpy(p0 + 1, &msg->arg1, sizeof(*msg) - 8); + + /* Make sure we write arg0 last, since that indicates message validity. */ + + dma_wmb(); + *p0 = msg->arg0; + dma_wmb(); +} + +static inline void chan_write_msg(struct apple_isp *isp, + struct isp_channel *chan, + struct isp_message *msg) +{ + chan_write_msg_index(isp, chan, msg, chan->cursor); +} + +static inline void chan_update_cursor(struct isp_channel *chan) +{ + if (chan->cursor >= (chan->num - 1)) { + chan->cursor = 0; + } else { + chan->cursor += 1; + } +} + +static int chan_handle_once(struct apple_isp *isp, struct isp_channel *chan) +{ + int err; + + lockdep_assert_held(&chan->lock); + + err = chan->ops->handle(isp, chan); + if (err < 0) { + dev_err(isp->dev, "%s: handler failed: %d)\n", chan->name, err); + return err; + } + + chan_write_msg(isp, chan, &chan->rsp); + + isp_mbox2_write32(isp, ISP_MBOX2_IRQ_DOORBELL, chan->doorbell); + + chan_update_cursor(chan); + + return 0; +} + +static inline bool chan_rx_done(struct apple_isp *isp, struct isp_channel *chan) +{ + if (((chan->req.arg0 & 0xf) == ISP_IPC_FLAG_ACK) || + ((chan->req.arg0 & 0xf) == ISP_IPC_FLAG_TERMINAL_ACK)) { + return true; + } + return false; +} + +int ipc_chan_handle(struct apple_isp *isp, struct isp_channel *chan) +{ + int err = 0; + + mutex_lock(&chan->lock); + while (1) { + chan_read_msg(isp, chan, &chan->req); + if (chan_rx_done(isp, chan)) { + err = 0; + break; + } + err = chan_handle_once(isp, chan); + if (err < 0) { + break; + } + } + mutex_unlock(&chan->lock); + + return err; +} + +static inline bool chan_tx_done(struct apple_isp *isp, struct isp_channel *chan) +{ + dma_rmb(); + + chan_read_msg(isp, chan, &chan->rsp); + if ((chan->rsp.arg0) == (chan->req.arg0 | ISP_IPC_FLAG_ACK)) { + chan_update_cursor(chan); + return true; + } + return false; +} + +int ipc_chan_send(struct apple_isp *isp, struct isp_channel *chan, + unsigned long timeout) +{ + long t; + + chan_write_msg(isp, chan, &chan->req); + dma_wmb(); + + isp_mbox2_write32(isp, ISP_MBOX2_IRQ_DOORBELL, chan->doorbell); + + if (!timeout) + return 0; + + t = wait_event_timeout(isp->wait, chan_tx_done(isp, chan), timeout); + if (t == 0) { + dev_err(isp->dev, + "%s: timed out on request [0x%llx, 0x%llx, 0x%llx]\n", + chan->name, chan->req.arg0, chan->req.arg1, + chan->req.arg2); + return -ETIME; + } + + isp_dbg(isp, "%s: request success (%ld)\n", chan->name, t); + + return 0; +} + +int ipc_tm_handle(struct apple_isp *isp, struct isp_channel *chan) +{ + struct isp_message *rsp = &chan->rsp; + +#ifdef APPLE_ISP_DEBUG + struct isp_message *req = &chan->req; + char buf[512]; + dma_addr_t iova = req->arg0 & ~ISP_IPC_FLAG_TERMINAL_ACK; + u32 size = req->arg1; + if (iova && size && size < sizeof(buf) && + isp->log_surf) { + void *p = apple_isp_translate(isp, isp->log_surf, iova, size); + if (p) { + size = min_t(u32, size, 512); + memcpy(buf, p, size); + isp_dbg(isp, "ISPASC: %.*s", size, buf); + } + } +#endif + + rsp->arg0 = ISP_IPC_FLAG_ACK; + rsp->arg1 = 0x0; + rsp->arg2 = 0x0; + + return 0; +} + +int ipc_sm_handle(struct apple_isp *isp, struct isp_channel *chan) +{ + struct isp_message *req = &chan->req, *rsp = &chan->rsp; + int err; + + if (req->arg0 == 0x0) { + struct isp_surf *surf; + + surf = isp_alloc_surface_gc(isp, req->arg1); + if (!surf) { + isp_err(isp, "failed to alloc requested size 0x%llx\n", + req->arg1); + return -ENOMEM; + } + surf->type = req->arg2; + + rsp->arg0 = surf->iova | ISP_IPC_FLAG_ACK; + rsp->arg1 = 0x0; + rsp->arg2 = 0x0; /* macOS uses this to index surfaces */ + + switch (surf->type) { + case 0x4c4f47: /* "LOG" */ + isp->log_surf = surf; + break; + case 0x4d495343: /* "MISC" */ + /* Hacky... maybe there's a better way to identify this surface? */ + if (surf->size == 0xc000) + isp->bt_surf = surf; + break; + default: + // skip vmap + return 0; + } + + err = isp_surf_vmap(isp, surf); + if (err < 0) { + isp_err(isp, "failed to vmap iova=0x%llx size=0x%llx\n", + surf->iova, surf->size); + } + } else { + /* This should be the shared surface free request, but + * 1) The fw doesn't request to free all of what it requested + * 2) The fw continues to access the surface after + * So we link it to the gc, which runs after fw shutdown + */ + rsp->arg0 = req->arg0 | ISP_IPC_FLAG_ACK; + rsp->arg1 = 0x0; + rsp->arg2 = 0x0; + } + + return 0; +} diff --git a/drivers/media/platform/apple/isp/isp-ipc.h b/drivers/media/platform/apple/isp/isp-ipc.h new file mode 100644 index 00000000000000..0c1d681835c72f --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-ipc.h @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#ifndef __ISP_IPC_H__ +#define __ISP_IPC_H__ + +#include "isp-drv.h" + +#define ISP_IPC_CHAN_TYPE_COMMAND 0 +#define ISP_IPC_CHAN_TYPE_REPLY 1 +#define ISP_IPC_CHAN_TYPE_REPORT 2 + +#define ISP_IPC_BUFEXC_STAT_SIZE 0x280 +#define ISP_IPC_BUFEXC_FLAG_RENDER 0x10000000 +#define ISP_IPC_BUFEXC_FLAG_COMMAND 0x30000000 +#define ISP_IPC_BUFEXC_FLAG_ACK 0x80000000 + +int ipc_chan_handle(struct apple_isp *isp, struct isp_channel *chan); +int ipc_chan_send(struct apple_isp *isp, struct isp_channel *chan, + unsigned long timeout); + +int ipc_tm_handle(struct apple_isp *isp, struct isp_channel *chan); +int ipc_sm_handle(struct apple_isp *isp, struct isp_channel *chan); + +#endif /* __ISP_IPC_H__ */ diff --git a/drivers/media/platform/apple/isp/isp-regs.h b/drivers/media/platform/apple/isp/isp-regs.h new file mode 100644 index 00000000000000..7357fa10fa5483 --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-regs.h @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#ifndef __ISP_REGS_H__ +#define __ISP_REGS_H__ + +#include "isp-drv.h" + +#define ISP_COPROC_FABRIC_0 0x738 +#define ISP_COPROC_FABRIC_1 0x798 +#define ISP_COPROC_FABRIC_2 0x7f8 +#define ISP_COPROC_FABRIC_3 0x858 + +#define ISP_COPROC_RVBAR 0x1050000 +#define ISP_COPROC_EDPRCR 0x1010310 +#define ISP_COPROC_CONTROL 0x1400044 +#define ISP_COPROC_STATUS 0x1400048 + +#define ISP_COPROC_IRQ_MASK_0 0x1400a00 +#define ISP_COPROC_IRQ_MASK_1 0x1400a04 +#define ISP_COPROC_IRQ_MASK_2 0x1400a08 +#define ISP_COPROC_IRQ_MASK_3 0x1400a0c +#define ISP_COPROC_IRQ_MASK_4 0x1400a10 +#define ISP_COPROC_IRQ_MASK_5 0x1400a14 + +#define ISP_MBOX_IRQ_INTERRUPT 0x00 +#define ISP_MBOX_IRQ_ENABLE 0x04 +#define ISP_MBOX2_IRQ_DOORBELL 0x00 +#define ISP_MBOX2_IRQ_ACK 0x0c + +#define ISP_GPIO_0 0x00 +#define ISP_GPIO_1 0x04 +#define ISP_GPIO_2 0x08 +#define ISP_GPIO_3 0x0c +#define ISP_GPIO_4 0x10 +#define ISP_GPIO_5 0x14 +#define ISP_GPIO_6 0x18 +#define ISP_GPIO_7 0x1c +#define ISP_GPIO_CLOCK_EN 0x20 + +static inline u32 isp_mbox_read32(struct apple_isp *isp, u32 reg) +{ + return readl(isp->mbox + reg); +} + +static inline void isp_mbox_write32(struct apple_isp *isp, u32 reg, u32 val) +{ + writel(val, isp->mbox + reg); +} + +static inline void isp_mbox2_write32(struct apple_isp *isp, u32 reg, u32 val) +{ + writel(val, isp->mbox2 + reg); +} + +#endif /* __ISP_REGS_H__ */ diff --git a/drivers/media/platform/apple/isp/isp-v4l2.c b/drivers/media/platform/apple/isp/isp-v4l2.c new file mode 100644 index 00000000000000..0561653ea7becd --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-v4l2.c @@ -0,0 +1,910 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#include + +#include +#include +#include +#include +#include + +#include "isp-cam.h" +#include "isp-cmd.h" +#include "isp-iommu.h" +#include "isp-ipc.h" +#include "isp-fw.h" +#include "isp-v4l2.h" + +#define ISP_MIN_FRAMES 2 +#define ISP_MAX_PLANES 4 +#define ISP_MAX_PIX_FORMATS 2 +#define ISP_BUFFER_TIMEOUT msecs_to_jiffies(1500) +#define ISP_STRIDE_ALIGNMENT 64 + +static bool multiplanar = false; +module_param(multiplanar, bool, 0644); +MODULE_PARM_DESC(multiplanar, "Enable multiplanar API"); + +struct isp_buflist_buffer { + u64 iovas[ISP_MAX_PLANES]; + u32 flags[ISP_MAX_PLANES]; + u32 num_planes; + u32 pool_type; + u32 tag; + u32 pad; +} __packed; +static_assert(sizeof(struct isp_buflist_buffer) == 0x40); + +struct isp_buflist { + u64 type; + u64 num_buffers; + struct isp_buflist_buffer buffers[]; +}; + +int ipc_bt_handle(struct apple_isp *isp, struct isp_channel *chan) +{ + struct isp_message *req = &chan->req, *rsp = &chan->rsp; + struct isp_buffer *tmp, *buf; + struct isp_buflist *bl; + u32 count; + int err = 0; + + /* printk("H2T: 0x%llx 0x%llx 0x%llx\n", (long long)req->arg0, + (long long)req->arg1, (long long)req->arg2); */ + + if (req->arg1 < sizeof(struct isp_buflist)) { + dev_err(isp->dev, "%s: Bad length 0x%llx\n", chan->name, + req->arg1); + return -EIO; + } + + bl = apple_isp_translate(isp, isp->bt_surf, req->arg0, req->arg1); + + count = bl->num_buffers; + if (count > (req->arg1 - sizeof(struct isp_buffer)) / + sizeof(struct isp_buflist_buffer)) { + dev_err(isp->dev, "%s: Bad length 0x%llx\n", chan->name, + req->arg1); + return -EIO; + } + + spin_lock(&isp->buf_lock); + for (int i = 0; i < count; i++) { + struct isp_buflist_buffer *bufd = &bl->buffers[i]; + + /* printk("Return: 0x%llx (%d)\n", bufd->iovas[0], + bufd->pool_type); */ + + if (bufd->pool_type == 0) { + for (int j = 0; j < ARRAY_SIZE(isp->meta_surfs); j++) { + struct isp_surf *meta = isp->meta_surfs[j]; + if ((u32)bufd->iovas[0] == (u32)meta->iova) { + WARN_ON(!meta->submitted); + meta->submitted = false; + } + } + } else { + list_for_each_entry_safe_reverse( + buf, tmp, &isp->bufs_submitted, link) { + if ((u32)buf->surfs[0].iova == + (u32)bufd->iovas[0]) { + enum vb2_buffer_state state = + VB2_BUF_STATE_ERROR; + + buf->vb.vb2_buf.timestamp = + ktime_get_ns(); + buf->vb.sequence = isp->sequence++; + buf->vb.field = V4L2_FIELD_NONE; + if (req->arg2 == + ISP_IPC_BUFEXC_FLAG_RENDER) + state = VB2_BUF_STATE_DONE; + vb2_buffer_done(&buf->vb.vb2_buf, + state); + list_del(&buf->link); + } + } + } + } + spin_unlock(&isp->buf_lock); + + rsp->arg0 = req->arg0 | ISP_IPC_FLAG_ACK; + rsp->arg1 = 0x0; + rsp->arg2 = ISP_IPC_BUFEXC_FLAG_ACK; + + return err; +} + +static int isp_submit_buffers(struct apple_isp *isp) +{ + struct isp_format *fmt = isp_get_current_format(isp); + struct isp_channel *chan = isp->chan_bh; + struct isp_message *req = &chan->req; + struct isp_buffer *buf, *tmp; + unsigned long flags; + size_t offset; + int err; + + struct isp_buflist *bl = isp->cmd_virt; + struct isp_buflist_buffer *bufd = &bl->buffers[0]; + + bl->type = 1; + bl->num_buffers = 0; + + spin_lock_irqsave(&isp->buf_lock, flags); + for (int i = 0; i < ARRAY_SIZE(isp->meta_surfs); i++) { + struct isp_surf *meta = isp->meta_surfs[i]; + + if (meta->submitted) + continue; + + /* printk("Submit: 0x%llx .. 0x%llx (meta)\n", meta->iova, + meta->iova + meta->size); */ + + bufd->num_planes = 1; + bufd->pool_type = 0; + bufd->iovas[0] = meta->iova; + bufd->flags[0] = 0x40000000; + bufd++; + bl->num_buffers++; + + meta->submitted = true; + } + + while ((buf = list_first_entry_or_null(&isp->bufs_pending, + struct isp_buffer, link))) { + memset(bufd, 0, sizeof(*bufd)); + + bufd->num_planes = fmt->num_planes; + bufd->pool_type = isp->hw->scl1 ? CISP_POOL_TYPE_RENDERED_SCL1 : + CISP_POOL_TYPE_RENDERED; + offset = 0; + for (int j = 0; j < fmt->num_planes; j++) { + bufd->iovas[j] = buf->surfs[0].iova + offset; + bufd->flags[j] = 0x40000000; + offset += fmt->plane_size[j]; + } + + /* printk("Submit: 0x%llx .. 0x%llx (render)\n", + buf->surfs[0].iova, + buf->surfs[0].iova + buf->surfs[0].size); */ + bufd++; + bl->num_buffers++; + + /* + * Queue the buffer as submitted and release the lock for now. + * We need to do this before actually submitting to avoid a + * race with the buffer return codepath. + */ + list_move_tail(&buf->link, &isp->bufs_submitted); + } + + spin_unlock_irqrestore(&isp->buf_lock, flags); + + req->arg0 = isp->cmd_iova; + req->arg1 = max_t(u64, ISP_IPC_BUFEXC_STAT_SIZE, + ((uintptr_t)bufd - (uintptr_t)bl)); + req->arg2 = ISP_IPC_BUFEXC_FLAG_COMMAND; + + err = ipc_chan_send(isp, chan, ISP_BUFFER_TIMEOUT); + if (err) { + /* If we fail, consider the buffer not submitted. */ + dev_err(isp->dev, + "%s: failed to send bufs: [0x%llx, 0x%llx, 0x%llx]\n", + chan->name, req->arg0, req->arg1, req->arg2); + + /* + * Try to find the buffer in the list, and if it's + * still there, move it back to the pending list. + */ + spin_lock_irqsave(&isp->buf_lock, flags); + + bufd = &bl->buffers[0]; + for (int i = 0; i < bl->num_buffers; i++, bufd++) { + list_for_each_entry_safe_reverse( + buf, tmp, &isp->bufs_submitted, link) { + if (bufd->iovas[0] == buf->surfs[0].iova) { + list_move_tail(&buf->link, + &isp->bufs_pending); + } + } + for (int j = 0; j < ARRAY_SIZE(isp->meta_surfs); j++) { + struct isp_surf *meta = isp->meta_surfs[j]; + if (bufd->iovas[0] == meta->iova) { + meta->submitted = false; + } + } + } + + spin_unlock_irqrestore(&isp->buf_lock, flags); + } + + return err; +} + +/* + * Videobuf2 section + */ +static int isp_vb2_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers, + unsigned int *num_planes, unsigned int sizes[], + struct device *alloc_devs[]) +{ + struct apple_isp *isp = vb2_get_drv_priv(vq); + struct isp_format *fmt = isp_get_current_format(isp); + + /* This is not strictly neccessary but makes it easy to enforce that + * at most 16 buffers are submitted at once. ISP on t6001 (FW 12.3) + * times out if more buffers are submitted than set in the buffer pool + * config before streaming is started. + */ + *nbuffers = min_t(unsigned int, *nbuffers, ISP_MAX_BUFFERS); + + if (*num_planes) { + if (sizes[0] < fmt->total_size) + return -EINVAL; + + return 0; + } + + *num_planes = 1; + sizes[0] = fmt->total_size; + + return 0; +} + +static void __isp_vb2_buf_cleanup(struct vb2_buffer *vb, unsigned int i) +{ + struct apple_isp *isp = vb2_get_drv_priv(vb->vb2_queue); + struct isp_buffer *buf = + container_of(vb, struct isp_buffer, vb.vb2_buf); + + while (i--) + apple_isp_iommu_unmap_sgt(isp, &buf->surfs[i]); +} + +static void isp_vb2_buf_cleanup(struct vb2_buffer *vb) +{ + __isp_vb2_buf_cleanup(vb, vb->num_planes); +} + +static int isp_vb2_buf_init(struct vb2_buffer *vb) +{ + struct apple_isp *isp = vb2_get_drv_priv(vb->vb2_queue); + struct isp_buffer *buf = + container_of(vb, struct isp_buffer, vb.vb2_buf); + unsigned int i; + int err; + + for (i = 0; i < vb->num_planes; i++) { + struct sg_table *sgt = vb2_dma_sg_plane_desc(vb, i); + err = apple_isp_iommu_map_sgt(isp, &buf->surfs[i], sgt, + vb2_plane_size(vb, i)); + if (err) + goto cleanup; + } + + return 0; + +cleanup: + __isp_vb2_buf_cleanup(vb, i); + return err; +} + +static int isp_vb2_buf_prepare(struct vb2_buffer *vb) +{ + struct apple_isp *isp = vb2_get_drv_priv(vb->vb2_queue); + struct isp_format *fmt = isp_get_current_format(isp); + + if (vb2_plane_size(vb, 0) < fmt->total_size) + return -EINVAL; + + vb2_set_plane_payload(vb, 0, fmt->total_size); + + return 0; +} + +static void isp_vb2_release_buffers(struct apple_isp *isp, + enum vb2_buffer_state state) +{ + struct isp_buffer *buf; + unsigned long flags; + + spin_lock_irqsave(&isp->buf_lock, flags); + list_for_each_entry(buf, &isp->bufs_submitted, link) + vb2_buffer_done(&buf->vb.vb2_buf, state); + INIT_LIST_HEAD(&isp->bufs_submitted); + list_for_each_entry(buf, &isp->bufs_pending, link) + vb2_buffer_done(&buf->vb.vb2_buf, state); + INIT_LIST_HEAD(&isp->bufs_pending); + spin_unlock_irqrestore(&isp->buf_lock, flags); +} + +static void isp_vb2_buf_queue(struct vb2_buffer *vb) +{ + struct apple_isp *isp = vb2_get_drv_priv(vb->vb2_queue); + struct isp_buffer *buf = + container_of(vb, struct isp_buffer, vb.vb2_buf); + unsigned long flags; + bool empty; + + spin_lock_irqsave(&isp->buf_lock, flags); + empty = list_empty(&isp->bufs_pending) && + list_empty(&isp->bufs_submitted); + list_add_tail(&buf->link, &isp->bufs_pending); + spin_unlock_irqrestore(&isp->buf_lock, flags); + + if (test_bit(ISP_STATE_STREAMING, &isp->state) && !empty) + isp_submit_buffers(isp); +} + +static int apple_isp_start_streaming(struct apple_isp *isp) +{ + int err; + + err = apple_isp_start_camera(isp); + if (err) { + dev_err(isp->dev, "failed to start camera: %d\n", err); + goto release_buffers; + } + + err = isp_submit_buffers(isp); + if (err) { + dev_err(isp->dev, "failed to send initial batch: %d\n", err); + goto stop_camera; + } + + err = apple_isp_start_capture(isp); + if (err) { + dev_err(isp->dev, "failed to start capture: %d\n", err); + goto stop_camera; + } + + set_bit(ISP_STATE_STREAMING, &isp->state); + + return 0; + +stop_camera: + apple_isp_stop_camera(isp); +release_buffers: + isp_vb2_release_buffers(isp, VB2_BUF_STATE_QUEUED); + return err; +} + +static void apple_isp_stop_streaming(struct apple_isp *isp) +{ + clear_bit(ISP_STATE_STREAMING, &isp->state); + apple_isp_stop_capture(isp); + apple_isp_stop_camera(isp); +} + +static int isp_vb2_start_streaming(struct vb2_queue *q, unsigned int count) +{ + struct apple_isp *isp = vb2_get_drv_priv(q); + + isp->sequence = 0; + + return apple_isp_start_streaming(isp); +} + +static void isp_vb2_stop_streaming(struct vb2_queue *q) +{ + struct apple_isp *isp = vb2_get_drv_priv(q); + + apple_isp_stop_streaming(isp); + isp_vb2_release_buffers(isp, VB2_BUF_STATE_ERROR); +} + +int apple_isp_video_suspend(struct apple_isp *isp) +{ + /* Swap into STATE_SLEEPING as isp_vb2_buf_queue() submits on + * STATE_STREAMING. + */ + if (test_bit(ISP_STATE_STREAMING, &isp->state)) { + /* Signal buffers to be recycled for clean shutdown */ + isp_vb2_release_buffers(isp, VB2_BUF_STATE_QUEUED); + apple_isp_stop_streaming(isp); + set_bit(ISP_STATE_SLEEPING, &isp->state); + } + + return 0; +} + +int apple_isp_video_resume(struct apple_isp *isp) +{ + if (test_bit(ISP_STATE_SLEEPING, &isp->state)) { + clear_bit(ISP_STATE_SLEEPING, &isp->state); + apple_isp_start_streaming(isp); + } + + return 0; +} + +static const struct vb2_ops isp_vb2_ops = { + .queue_setup = isp_vb2_queue_setup, + .buf_init = isp_vb2_buf_init, + .buf_cleanup = isp_vb2_buf_cleanup, + .buf_prepare = isp_vb2_buf_prepare, + .buf_queue = isp_vb2_buf_queue, + .start_streaming = isp_vb2_start_streaming, + .stop_streaming = isp_vb2_stop_streaming, + .wait_prepare = vb2_ops_wait_prepare, + .wait_finish = vb2_ops_wait_finish, +}; + +static int isp_set_preset(struct apple_isp *isp, struct isp_format *fmt, + struct isp_preset *preset) +{ + int i; + size_t total_size; + + fmt->preset = preset; + + /* I really fucking hope they all use NV12. */ + fmt->num_planes = 2; + fmt->strides[0] = ALIGN(preset->output_dim.x, ISP_STRIDE_ALIGNMENT); + /* UV subsampled interleaved */ + fmt->strides[1] = ALIGN(preset->output_dim.x, ISP_STRIDE_ALIGNMENT); + fmt->plane_size[0] = fmt->strides[0] * preset->output_dim.y; + fmt->plane_size[1] = fmt->strides[1] * preset->output_dim.y / 2; + + total_size = 0; + for (i = 0; i < fmt->num_planes; i++) + total_size += fmt->plane_size[i]; + fmt->total_size = total_size; + + return 0; +} + +static struct isp_preset *isp_select_preset(struct apple_isp *isp, u32 width, + u32 height) +{ + struct isp_preset *preset, *best = &isp->presets[0]; + int i, score, best_score = INT_MAX; + + /* Default if no dimensions */ + if (width == 0 || height == 0) + return &isp->presets[0]; + + for (i = 0; i < isp->num_presets; i++) { + preset = &isp->presets[i]; + score = abs((int)preset->output_dim.x - (int)width) + + abs((int)preset->output_dim.y - (int)height); + if (score < best_score) { + best = preset; + best_score = score; + } + } + + return best; +} + +/* + * V4L2 ioctl section + */ +static int isp_vidioc_querycap(struct file *file, void *priv, + struct v4l2_capability *cap) +{ + strscpy(cap->card, APPLE_ISP_CARD_NAME, sizeof(cap->card)); + strscpy(cap->driver, APPLE_ISP_DEVICE_NAME, sizeof(cap->driver)); + + return 0; +} + +static int isp_vidioc_enum_format(struct file *file, void *fh, + struct v4l2_fmtdesc *f) +{ + struct apple_isp *isp = video_drvdata(file); + + if (f->index >= ISP_MAX_PIX_FORMATS) + return -EINVAL; + + switch (f->index) { + case 0: + f->pixelformat = V4L2_PIX_FMT_NV12; + break; + case 1: + if (!isp->multiplanar) + return -EINVAL; + f->pixelformat = V4L2_PIX_FMT_NV12M; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int isp_vidioc_enum_framesizes(struct file *file, void *fh, + struct v4l2_frmsizeenum *f) +{ + struct apple_isp *isp = video_drvdata(file); + + if (f->index >= isp->num_presets) + return -EINVAL; + + if ((f->pixel_format != V4L2_PIX_FMT_NV12) && + (f->pixel_format != V4L2_PIX_FMT_NV12M)) + return -EINVAL; + + f->discrete.width = isp->presets[f->index].output_dim.x; + f->discrete.height = isp->presets[f->index].output_dim.y; + f->type = V4L2_FRMSIZE_TYPE_DISCRETE; + + return 0; +} + +static int isp_vidioc_enum_frameintervals(struct file *filp, void *priv, + struct v4l2_frmivalenum *interval) +{ + if (interval->index != 0) + return -EINVAL; + + interval->type = V4L2_FRMIVAL_TYPE_DISCRETE; + interval->discrete.numerator = 1; + interval->discrete.denominator = 30; + return 0; +} + +static inline void isp_get_sp_pix_format(struct apple_isp *isp, + struct v4l2_format *f, + struct isp_format *fmt) +{ + f->fmt.pix.width = fmt->preset->output_dim.x; + f->fmt.pix.height = fmt->preset->output_dim.y; + f->fmt.pix.bytesperline = fmt->strides[0]; + f->fmt.pix.sizeimage = fmt->total_size; + + f->fmt.pix.field = V4L2_FIELD_NONE; + f->fmt.pix.pixelformat = V4L2_PIX_FMT_NV12; + f->fmt.pix.colorspace = V4L2_COLORSPACE_REC709; + f->fmt.pix.ycbcr_enc = V4L2_YCBCR_ENC_709; + f->fmt.pix.xfer_func = V4L2_XFER_FUNC_709; +} + +static inline void isp_get_mp_pix_format(struct apple_isp *isp, + struct v4l2_format *f, + struct isp_format *fmt) +{ + f->fmt.pix_mp.width = fmt->preset->output_dim.x; + f->fmt.pix_mp.height = fmt->preset->output_dim.y; + f->fmt.pix_mp.num_planes = fmt->num_planes; + for (int i = 0; i < fmt->num_planes; i++) { + f->fmt.pix_mp.plane_fmt[i].sizeimage = fmt->plane_size[i]; + f->fmt.pix_mp.plane_fmt[i].bytesperline = fmt->strides[i]; + } + + f->fmt.pix_mp.field = V4L2_FIELD_NONE; + f->fmt.pix_mp.pixelformat = V4L2_PIX_FMT_NV12M; + f->fmt.pix_mp.colorspace = V4L2_COLORSPACE_REC709; + f->fmt.pix_mp.ycbcr_enc = V4L2_YCBCR_ENC_709; + f->fmt.pix_mp.xfer_func = V4L2_XFER_FUNC_709; +} + +static int isp_vidioc_get_format(struct file *file, void *fh, + struct v4l2_format *f) +{ + struct apple_isp *isp = video_drvdata(file); + struct isp_format *fmt = isp_get_current_format(isp); + + isp_get_sp_pix_format(isp, f, fmt); + + return 0; +} + +static int isp_vidioc_set_format(struct file *file, void *fh, + struct v4l2_format *f) +{ + struct apple_isp *isp = video_drvdata(file); + struct isp_format *fmt = isp_get_current_format(isp); + struct isp_preset *preset; + int err; + + preset = isp_select_preset(isp, f->fmt.pix.width, f->fmt.pix.height); + err = isp_set_preset(isp, fmt, preset); + if (err) + return err; + + isp_get_sp_pix_format(isp, f, fmt); + + isp->vbq.type = V4L2_BUF_TYPE_VIDEO_CAPTURE; + + return 0; +} + +static int isp_vidioc_try_format(struct file *file, void *fh, + struct v4l2_format *f) +{ + struct apple_isp *isp = video_drvdata(file); + struct isp_format fmt = *isp_get_current_format(isp); + struct isp_preset *preset; + int err; + + preset = isp_select_preset(isp, f->fmt.pix.width, f->fmt.pix.height); + err = isp_set_preset(isp, &fmt, preset); + if (err) + return err; + + isp_get_sp_pix_format(isp, f, &fmt); + + return 0; +} + +static int isp_vidioc_get_format_mplane(struct file *file, void *fh, + struct v4l2_format *f) +{ + struct apple_isp *isp = video_drvdata(file); + struct isp_format *fmt = isp_get_current_format(isp); + + if (!isp->multiplanar) + return -ENOTTY; + + isp_get_mp_pix_format(isp, f, fmt); + + return 0; +} + +static int isp_vidioc_set_format_mplane(struct file *file, void *fh, + struct v4l2_format *f) +{ + struct apple_isp *isp = video_drvdata(file); + struct isp_format *fmt = isp_get_current_format(isp); + struct isp_preset *preset; + int err; + + if (!isp->multiplanar) + return -ENOTTY; + + preset = isp_select_preset(isp, f->fmt.pix_mp.width, + f->fmt.pix_mp.height); + err = isp_set_preset(isp, fmt, preset); + if (err) + return err; + + isp_get_mp_pix_format(isp, f, fmt); + + isp->vbq.type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE; + + return 0; +} + +static int isp_vidioc_try_format_mplane(struct file *file, void *fh, + struct v4l2_format *f) +{ + struct apple_isp *isp = video_drvdata(file); + struct isp_format fmt = *isp_get_current_format(isp); + struct isp_preset *preset; + int err; + + if (!isp->multiplanar) + return -ENOTTY; + + preset = isp_select_preset(isp, f->fmt.pix_mp.width, + f->fmt.pix_mp.height); + err = isp_set_preset(isp, &fmt, preset); + if (err) + return err; + + isp_get_mp_pix_format(isp, f, &fmt); + + return 0; +} + +static int isp_vidioc_enum_input(struct file *file, void *fh, + struct v4l2_input *inp) +{ + if (inp->index) + return -EINVAL; + + strscpy(inp->name, APPLE_ISP_DEVICE_NAME, sizeof(inp->name)); + inp->type = V4L2_INPUT_TYPE_CAMERA; + + return 0; +} + +static int isp_vidioc_get_input(struct file *file, void *fh, unsigned int *i) +{ + *i = 0; + + return 0; +} + +static int isp_vidioc_set_input(struct file *file, void *fh, unsigned int i) +{ + if (i) + return -EINVAL; + + return 0; +} + +static int isp_vidioc_get_param(struct file *file, void *fh, + struct v4l2_streamparm *a) +{ + struct apple_isp *isp = video_drvdata(file); + + if (a->type != V4L2_BUF_TYPE_VIDEO_CAPTURE && + (!isp->multiplanar || + a->type != V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE)) + return -EINVAL; + + a->parm.capture.capability = V4L2_CAP_TIMEPERFRAME; + a->parm.capture.readbuffers = ISP_MIN_FRAMES; + a->parm.capture.timeperframe.numerator = ISP_FRAME_RATE_NUM; + a->parm.capture.timeperframe.denominator = ISP_FRAME_RATE_DEN; + + return 0; +} + +static int isp_vidioc_set_param(struct file *file, void *fh, + struct v4l2_streamparm *a) +{ + struct apple_isp *isp = video_drvdata(file); + + if (a->type != V4L2_BUF_TYPE_VIDEO_CAPTURE && + (!isp->multiplanar || + a->type != V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE)) + return -EINVAL; + + /* Not supporting frame rate sets. No use. Plus floats. */ + a->parm.capture.capability = V4L2_CAP_TIMEPERFRAME; + a->parm.capture.readbuffers = ISP_MIN_FRAMES; + a->parm.capture.timeperframe.numerator = ISP_FRAME_RATE_NUM; + a->parm.capture.timeperframe.denominator = ISP_FRAME_RATE_DEN; + + return 0; +} + +static const struct v4l2_ioctl_ops isp_v4l2_ioctl_ops = { + .vidioc_querycap = isp_vidioc_querycap, + + .vidioc_enum_fmt_vid_cap = isp_vidioc_enum_format, + .vidioc_g_fmt_vid_cap = isp_vidioc_get_format, + .vidioc_s_fmt_vid_cap = isp_vidioc_set_format, + .vidioc_try_fmt_vid_cap = isp_vidioc_try_format, + .vidioc_g_fmt_vid_cap_mplane = isp_vidioc_get_format_mplane, + .vidioc_s_fmt_vid_cap_mplane = isp_vidioc_set_format_mplane, + .vidioc_try_fmt_vid_cap_mplane = isp_vidioc_try_format_mplane, + + .vidioc_enum_framesizes = isp_vidioc_enum_framesizes, + .vidioc_enum_frameintervals = isp_vidioc_enum_frameintervals, + .vidioc_enum_input = isp_vidioc_enum_input, + .vidioc_g_input = isp_vidioc_get_input, + .vidioc_s_input = isp_vidioc_set_input, + .vidioc_g_parm = isp_vidioc_get_param, + .vidioc_s_parm = isp_vidioc_set_param, + + .vidioc_reqbufs = vb2_ioctl_reqbufs, + .vidioc_querybuf = vb2_ioctl_querybuf, + .vidioc_create_bufs = vb2_ioctl_create_bufs, + .vidioc_qbuf = vb2_ioctl_qbuf, + .vidioc_expbuf = vb2_ioctl_expbuf, + .vidioc_dqbuf = vb2_ioctl_dqbuf, + .vidioc_prepare_buf = vb2_ioctl_prepare_buf, + .vidioc_streamon = vb2_ioctl_streamon, + .vidioc_streamoff = vb2_ioctl_streamoff, +}; + +static const struct v4l2_file_operations isp_v4l2_fops = { + .owner = THIS_MODULE, + .open = v4l2_fh_open, + .release = vb2_fop_release, + .read = vb2_fop_read, + .poll = vb2_fop_poll, + .mmap = vb2_fop_mmap, + .unlocked_ioctl = video_ioctl2, +}; + +static const struct media_device_ops isp_media_device_ops = { + .link_notify = v4l2_pipeline_link_notify, +}; + +int apple_isp_setup_video(struct apple_isp *isp) +{ + struct video_device *vdev = &isp->vdev; + struct vb2_queue *vbq = &isp->vbq; + struct isp_format *fmt = isp_get_current_format(isp); + int err; + + err = isp_set_preset(isp, fmt, &isp->presets[0]); + if (err) { + dev_err(isp->dev, "failed to set default preset: %d\n", err); + return err; + } + + for (int i = 0; i < ARRAY_SIZE(isp->meta_surfs); i++) { + isp->meta_surfs[i] = + isp_alloc_surface_vmap(isp, isp->hw->meta_size); + if (!isp->meta_surfs[i]) { + isp_err(isp, "failed to alloc meta surface\n"); + err = -ENOMEM; + goto surf_cleanup; + } + } + + media_device_init(&isp->mdev); + isp->v4l2_dev.mdev = &isp->mdev; + isp->mdev.ops = &isp_media_device_ops; + isp->mdev.dev = isp->dev; + strscpy(isp->mdev.model, APPLE_ISP_DEVICE_NAME, + sizeof(isp->mdev.model)); + + err = media_device_register(&isp->mdev); + if (err) { + dev_err(isp->dev, "failed to register media device: %d\n", err); + goto media_cleanup; + } + + isp->multiplanar = multiplanar; + + err = v4l2_device_register(isp->dev, &isp->v4l2_dev); + if (err) { + dev_err(isp->dev, "failed to register v4l2 device: %d\n", err); + goto media_unregister; + } + + vbq->drv_priv = isp; + vbq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE; + vbq->io_modes = VB2_MMAP; + vbq->dev = isp->dev; + vbq->ops = &isp_vb2_ops; + vbq->mem_ops = &vb2_dma_sg_memops; + vbq->buf_struct_size = sizeof(struct isp_buffer); + vbq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; + vbq->min_queued_buffers = ISP_MIN_FRAMES; + vbq->lock = &isp->video_lock; + + err = vb2_queue_init(vbq); + if (err) { + dev_err(isp->dev, "failed to init vb2 queue: %d\n", err); + goto v4l2_unregister; + } + + vdev->queue = vbq; + vdev->fops = &isp_v4l2_fops; + vdev->ioctl_ops = &isp_v4l2_ioctl_ops; + vdev->device_caps = V4L2_BUF_TYPE_VIDEO_CAPTURE | V4L2_CAP_STREAMING; + if (isp->multiplanar) + vdev->device_caps |= V4L2_CAP_VIDEO_CAPTURE_MPLANE; + vdev->v4l2_dev = &isp->v4l2_dev; + vdev->vfl_type = VFL_TYPE_VIDEO; + vdev->vfl_dir = VFL_DIR_RX; + vdev->release = video_device_release_empty; + vdev->lock = &isp->video_lock; + strscpy(vdev->name, APPLE_ISP_DEVICE_NAME, sizeof(vdev->name)); + video_set_drvdata(vdev, isp); + + err = video_register_device(vdev, VFL_TYPE_VIDEO, 0); + if (err) { + dev_err(isp->dev, "failed to register video device: %d\n", err); + goto v4l2_unregister; + } + + return 0; + +v4l2_unregister: + v4l2_device_unregister(&isp->v4l2_dev); +media_unregister: + media_device_unregister(&isp->mdev); +media_cleanup: + media_device_cleanup(&isp->mdev); +surf_cleanup: + for (int i = 0; i < ARRAY_SIZE(isp->meta_surfs); i++) { + if (isp->meta_surfs[i]) + isp_free_surface(isp, isp->meta_surfs[i]); + isp->meta_surfs[i] = NULL; + } + + return err; +} + +void apple_isp_remove_video(struct apple_isp *isp) +{ + vb2_video_unregister_device(&isp->vdev); + v4l2_device_unregister(&isp->v4l2_dev); + media_device_unregister(&isp->mdev); + media_device_cleanup(&isp->mdev); + for (int i = 0; i < ARRAY_SIZE(isp->meta_surfs); i++) { + if (isp->meta_surfs[i]) + isp_free_surface(isp, isp->meta_surfs[i]); + isp->meta_surfs[i] = NULL; + } +} diff --git a/drivers/media/platform/apple/isp/isp-v4l2.h b/drivers/media/platform/apple/isp/isp-v4l2.h new file mode 100644 index 00000000000000..4d47deeb83b055 --- /dev/null +++ b/drivers/media/platform/apple/isp/isp-v4l2.h @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2023 Eileen Yoon */ + +#ifndef __ISP_V4L2_H__ +#define __ISP_V4L2_H__ + +#include "isp-drv.h" + +int apple_isp_setup_video(struct apple_isp *isp); +void apple_isp_remove_video(struct apple_isp *isp); +int ipc_bt_handle(struct apple_isp *isp, struct isp_channel *chan); + +int apple_isp_video_suspend(struct apple_isp *isp); +int apple_isp_video_resume(struct apple_isp *isp); + +#endif /* __ISP_V4L2_H__ */ diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c index e3038c18ca3621..a4387ed58cac36 100644 --- a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c +++ b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c @@ -1753,8 +1753,10 @@ static int wave5_vpu_open_dec(struct file *filp) spin_lock_init(&inst->state_spinlock); inst->codec_info = kzalloc(sizeof(*inst->codec_info), GFP_KERNEL); - if (!inst->codec_info) + if (!inst->codec_info) { + kfree(inst); return -ENOMEM; + } v4l2_fh_init(&inst->v4l2_fh, vdev); v4l2_fh_add(&inst->v4l2_fh, filp); diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c b/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c index 9bfaa9fb3ceb3e..94fb5d7c87021a 100644 --- a/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c +++ b/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c @@ -1578,8 +1578,10 @@ static int wave5_vpu_open_enc(struct file *filp) inst->ops = &wave5_vpu_enc_inst_ops; inst->codec_info = kzalloc(sizeof(*inst->codec_info), GFP_KERNEL); - if (!inst->codec_info) + if (!inst->codec_info) { + kfree(inst); return -ENOMEM; + } v4l2_fh_init(&inst->v4l2_fh, vdev); v4l2_fh_add(&inst->v4l2_fh, filp); diff --git a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-core.c b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-core.c index 6559d72d5d4278..6d26d4aa1eef2a 100644 --- a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-core.c +++ b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-core.c @@ -157,10 +157,18 @@ void mdp_video_device_release(struct video_device *vdev) kfree(mdp); } +static void mdp_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int mdp_mm_subsys_deploy(struct mdp_dev *mdp, enum mdp_infra_id id) { struct platform_device *mm_pdev = NULL; struct device **dev; + int ret; int i; if (!mdp) @@ -194,6 +202,11 @@ static int mdp_mm_subsys_deploy(struct mdp_dev *mdp, enum mdp_infra_id id) if (WARN_ON(!mm_pdev)) return -ENODEV; + ret = devm_add_action_or_reset(&mdp->pdev->dev, mdp_put_device, + &mm_pdev->dev); + if (ret) + return ret; + *dev = &mm_pdev->dev; } @@ -279,6 +292,7 @@ static int mdp_probe(struct platform_device *pdev) goto err_destroy_clock_wq; } mdp->scp = platform_get_drvdata(mm_pdev); + put_device(&mm_pdev->dev); } mdp->rproc_handle = scp_get_rproc(mdp->scp); diff --git a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c index d7027d600208fc..3632037f78f505 100644 --- a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c +++ b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c @@ -47,30 +47,32 @@ static void mtk_vcodec_vpu_reset_dec_handler(void *priv) { struct mtk_vcodec_dec_dev *dev = priv; struct mtk_vcodec_dec_ctx *ctx; + unsigned long flags; dev_err(&dev->plat_dev->dev, "Watchdog timeout!!"); - mutex_lock(&dev->dev_ctx_lock); + spin_lock_irqsave(&dev->dev_ctx_lock, flags); list_for_each_entry(ctx, &dev->ctx_list, list) { ctx->state = MTK_STATE_ABORT; mtk_v4l2_vdec_dbg(0, ctx, "[%d] Change to state MTK_STATE_ABORT", ctx->id); } - mutex_unlock(&dev->dev_ctx_lock); + spin_unlock_irqrestore(&dev->dev_ctx_lock, flags); } static void mtk_vcodec_vpu_reset_enc_handler(void *priv) { struct mtk_vcodec_enc_dev *dev = priv; struct mtk_vcodec_enc_ctx *ctx; + unsigned long flags; dev_err(&dev->plat_dev->dev, "Watchdog timeout!!"); - mutex_lock(&dev->dev_ctx_lock); + spin_lock_irqsave(&dev->dev_ctx_lock, flags); list_for_each_entry(ctx, &dev->ctx_list, list) { ctx->state = MTK_STATE_ABORT; mtk_v4l2_vdec_dbg(0, ctx, "[%d] Change to state MTK_STATE_ABORT", ctx->id); } - mutex_unlock(&dev->dev_ctx_lock); + spin_unlock_irqrestore(&dev->dev_ctx_lock, flags); } static const struct mtk_vcodec_fw_ops mtk_vcodec_vpu_msg = { @@ -117,8 +119,10 @@ struct mtk_vcodec_fw *mtk_vcodec_fw_vpu_init(void *priv, enum mtk_vcodec_fw_use vpu_wdt_reg_handler(fw_pdev, mtk_vcodec_vpu_reset_enc_handler, priv, rst_id); fw = devm_kzalloc(&plat_dev->dev, sizeof(*fw), GFP_KERNEL); - if (!fw) + if (!fw) { + put_device(&fw_pdev->dev); return ERR_PTR(-ENOMEM); + } fw->type = VPU; fw->ops = &mtk_vcodec_vpu_msg; fw->pdev = fw_pdev; diff --git a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c index 46d176e6de63e3..3b81fae9f9135c 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c @@ -198,6 +198,7 @@ static int fops_vcodec_open(struct file *file) struct mtk_vcodec_dec_ctx *ctx = NULL; int ret = 0, i, hw_count; struct vb2_queue *src_vq; + unsigned long flags; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -267,9 +268,9 @@ static int fops_vcodec_open(struct file *file) ctx->dev->vdec_pdata->init_vdec_params(ctx); - mutex_lock(&dev->dev_ctx_lock); + spin_lock_irqsave(&dev->dev_ctx_lock, flags); list_add(&ctx->list, &dev->ctx_list); - mutex_unlock(&dev->dev_ctx_lock); + spin_unlock_irqrestore(&dev->dev_ctx_lock, flags); mtk_vcodec_dbgfs_create(ctx); mutex_unlock(&dev->dev_mutex); @@ -294,6 +295,7 @@ static int fops_vcodec_release(struct file *file) { struct mtk_vcodec_dec_dev *dev = video_drvdata(file); struct mtk_vcodec_dec_ctx *ctx = file_to_dec_ctx(file); + unsigned long flags; mtk_v4l2_vdec_dbg(0, ctx, "[%d] decoder", ctx->id); mutex_lock(&dev->dev_mutex); @@ -312,9 +314,9 @@ static int fops_vcodec_release(struct file *file) v4l2_ctrl_handler_free(&ctx->ctrl_hdl); mtk_vcodec_dbgfs_remove(dev, ctx->id); - mutex_lock(&dev->dev_ctx_lock); + spin_lock_irqsave(&dev->dev_ctx_lock, flags); list_del_init(&ctx->list); - mutex_unlock(&dev->dev_ctx_lock); + spin_unlock_irqrestore(&dev->dev_ctx_lock, flags); kfree(ctx); mutex_unlock(&dev->dev_mutex); return 0; @@ -407,7 +409,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev) for (i = 0; i < MTK_VDEC_HW_MAX; i++) mutex_init(&dev->dec_mutex[i]); mutex_init(&dev->dev_mutex); - mutex_init(&dev->dev_ctx_lock); + spin_lock_init(&dev->dev_ctx_lock); spin_lock_init(&dev->irqlock); snprintf(dev->v4l2_dev.name, sizeof(dev->v4l2_dev.name), "%s", diff --git a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h index d047d7c580fb69..9d68808e8f9c3c 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h +++ b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h @@ -285,7 +285,7 @@ struct mtk_vcodec_dec_dev { /* decoder hardware mutex lock */ struct mutex dec_mutex[MTK_VDEC_HW_MAX]; struct mutex dev_mutex; - struct mutex dev_ctx_lock; + spinlock_t dev_ctx_lock; struct workqueue_struct *decode_workqueue; spinlock_t irqlock; diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c index 145958206e38a4..40b97f114cf6f0 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c @@ -75,16 +75,17 @@ static void handle_get_param_msg_ack(const struct vdec_vpu_ipi_get_param_ack *ms static bool vpu_dec_check_ap_inst(struct mtk_vcodec_dec_dev *dec_dev, struct vdec_vpu_inst *vpu) { struct mtk_vcodec_dec_ctx *ctx; + unsigned long flags; int ret = false; - mutex_lock(&dec_dev->dev_ctx_lock); + spin_lock_irqsave(&dec_dev->dev_ctx_lock, flags); list_for_each_entry(ctx, &dec_dev->ctx_list, list) { if (!IS_ERR_OR_NULL(ctx) && ctx->vpu_inst == vpu) { ret = true; break; } } - mutex_unlock(&dec_dev->dev_ctx_lock); + spin_unlock_irqrestore(&dec_dev->dev_ctx_lock, flags); return ret; } diff --git a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c index fb1c3bdc2daeb4..82b8ff38e8f1a0 100644 --- a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c +++ b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c @@ -117,6 +117,7 @@ static int fops_vcodec_open(struct file *file) struct mtk_vcodec_enc_ctx *ctx = NULL; int ret = 0; struct vb2_queue *src_vq; + unsigned long flags; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -176,9 +177,9 @@ static int fops_vcodec_open(struct file *file) mtk_v4l2_venc_dbg(2, ctx, "Create instance [%d]@%p m2m_ctx=%p ", ctx->id, ctx, ctx->m2m_ctx); - mutex_lock(&dev->dev_ctx_lock); + spin_lock_irqsave(&dev->dev_ctx_lock, flags); list_add(&ctx->list, &dev->ctx_list); - mutex_unlock(&dev->dev_ctx_lock); + spin_unlock_irqrestore(&dev->dev_ctx_lock, flags); mutex_unlock(&dev->dev_mutex); mtk_v4l2_venc_dbg(0, ctx, "%s encoder [%d]", dev_name(&dev->plat_dev->dev), @@ -203,6 +204,7 @@ static int fops_vcodec_release(struct file *file) { struct mtk_vcodec_enc_dev *dev = video_drvdata(file); struct mtk_vcodec_enc_ctx *ctx = file_to_enc_ctx(file); + unsigned long flags; mtk_v4l2_venc_dbg(1, ctx, "[%d] encoder", ctx->id); mutex_lock(&dev->dev_mutex); @@ -213,9 +215,9 @@ static int fops_vcodec_release(struct file *file) v4l2_fh_exit(&ctx->fh); v4l2_ctrl_handler_free(&ctx->ctrl_hdl); - mutex_lock(&dev->dev_ctx_lock); + spin_lock_irqsave(&dev->dev_ctx_lock, flags); list_del_init(&ctx->list); - mutex_unlock(&dev->dev_ctx_lock); + spin_unlock_irqrestore(&dev->dev_ctx_lock, flags); kfree(ctx); mutex_unlock(&dev->dev_mutex); return 0; @@ -297,7 +299,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev) mutex_init(&dev->enc_mutex); mutex_init(&dev->dev_mutex); - mutex_init(&dev->dev_ctx_lock); + spin_lock_init(&dev->dev_ctx_lock); spin_lock_init(&dev->irqlock); snprintf(dev->v4l2_dev.name, sizeof(dev->v4l2_dev.name), "%s", diff --git a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h index 5b304a5512366e..0cddfa13594f55 100644 --- a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h +++ b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h @@ -206,7 +206,7 @@ struct mtk_vcodec_enc_dev { /* encoder hardware mutex lock */ struct mutex enc_mutex; struct mutex dev_mutex; - struct mutex dev_ctx_lock; + spinlock_t dev_ctx_lock; struct workqueue_struct *encode_workqueue; int enc_irq; diff --git a/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c b/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c index 51bb7ee141b9e5..3c229b1f6b21f4 100644 --- a/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c +++ b/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c @@ -45,16 +45,17 @@ static void handle_enc_encode_msg(struct venc_vpu_inst *vpu, const void *data) static bool vpu_enc_check_ap_inst(struct mtk_vcodec_enc_dev *enc_dev, struct venc_vpu_inst *vpu) { struct mtk_vcodec_enc_ctx *ctx; + unsigned long flags; int ret = false; - mutex_lock(&enc_dev->dev_ctx_lock); + spin_lock_irqsave(&enc_dev->dev_ctx_lock, flags); list_for_each_entry(ctx, &enc_dev->ctx_list, list) { if (!IS_ERR_OR_NULL(ctx) && ctx->vpu_inst == vpu) { ret = true; break; } } - mutex_unlock(&enc_dev->dev_ctx_lock); + spin_unlock_irqrestore(&enc_dev->dev_ctx_lock, flags); return ret; } diff --git a/drivers/media/platform/qcom/iris/iris_common.c b/drivers/media/platform/qcom/iris/iris_common.c index 9fc663bdaf3fc9..7f1c7fe144f707 100644 --- a/drivers/media/platform/qcom/iris/iris_common.c +++ b/drivers/media/platform/qcom/iris/iris_common.c @@ -91,12 +91,14 @@ int iris_process_streamon_input(struct iris_inst *inst) int iris_process_streamon_output(struct iris_inst *inst) { const struct iris_hfi_command_ops *hfi_ops = inst->core->hfi_ops; - bool drain_active = false, drc_active = false; enum iris_inst_sub_state clear_sub_state = 0; + bool drain_active, drc_active, first_ipsc; int ret = 0; iris_scale_power(inst); + first_ipsc = inst->sub_state & IRIS_INST_SUB_FIRST_IPSC; + drain_active = inst->sub_state & IRIS_INST_SUB_DRAIN && inst->sub_state & IRIS_INST_SUB_DRAIN_LAST; @@ -108,7 +110,8 @@ int iris_process_streamon_output(struct iris_inst *inst) else if (drain_active) clear_sub_state = IRIS_INST_SUB_DRAIN | IRIS_INST_SUB_DRAIN_LAST; - if (inst->domain == DECODER && inst->sub_state & IRIS_INST_SUB_INPUT_PAUSE) { + /* Input internal buffer reconfiguration required in case of resolution change */ + if (first_ipsc || drc_active) { ret = iris_alloc_and_queue_input_int_bufs(inst); if (ret) return ret; diff --git a/drivers/media/platform/qcom/iris/iris_vb2.c b/drivers/media/platform/qcom/iris/iris_vb2.c index 139b821f7952fe..db8768d8a8f61c 100644 --- a/drivers/media/platform/qcom/iris/iris_vb2.c +++ b/drivers/media/platform/qcom/iris/iris_vb2.c @@ -231,6 +231,8 @@ void iris_vb2_stop_streaming(struct vb2_queue *q) return; mutex_lock(&inst->lock); + if (inst->state == IRIS_INST_ERROR) + goto exit; if (!V4L2_TYPE_IS_OUTPUT(q->type) && !V4L2_TYPE_IS_CAPTURE(q->type)) @@ -241,10 +243,10 @@ void iris_vb2_stop_streaming(struct vb2_queue *q) goto exit; exit: - iris_helper_buffers_done(inst, q->type, VB2_BUF_STATE_ERROR); - if (ret) + if (ret) { + iris_helper_buffers_done(inst, q->type, VB2_BUF_STATE_ERROR); iris_inst_change_state(inst, IRIS_INST_ERROR); - + } mutex_unlock(&inst->lock); } diff --git a/drivers/media/platform/renesas/rcar_drif.c b/drivers/media/platform/renesas/rcar_drif.c index 11bf47fb8266dc..0844934f7aa68b 100644 --- a/drivers/media/platform/renesas/rcar_drif.c +++ b/drivers/media/platform/renesas/rcar_drif.c @@ -1246,6 +1246,7 @@ static struct device_node *rcar_drif_bond_enabled(struct platform_device *p) if (np && of_device_is_available(np)) return np; + of_node_put(np); return NULL; } diff --git a/drivers/media/platform/samsung/exynos4-is/media-dev.c b/drivers/media/platform/samsung/exynos4-is/media-dev.c index c781853586fd21..e9d7875cf01ec9 100644 --- a/drivers/media/platform/samsung/exynos4-is/media-dev.c +++ b/drivers/media/platform/samsung/exynos4-is/media-dev.c @@ -1399,12 +1399,14 @@ static int subdev_notifier_complete(struct v4l2_async_notifier *notifier) mutex_lock(&fmd->media_dev.graph_mutex); ret = fimc_md_create_links(fmd); - if (ret < 0) - goto unlock; + if (ret < 0) { + mutex_unlock(&fmd->media_dev.graph_mutex); + return ret; + } - ret = v4l2_device_register_subdev_nodes(&fmd->v4l2_dev); -unlock: mutex_unlock(&fmd->media_dev.graph_mutex); + + ret = v4l2_device_register_subdev_nodes(&fmd->v4l2_dev); if (ret < 0) return ret; diff --git a/drivers/media/platform/ti/davinci/vpif_capture.c b/drivers/media/platform/ti/davinci/vpif_capture.c index d053972888d1b4..243c6196b0247c 100644 --- a/drivers/media/platform/ti/davinci/vpif_capture.c +++ b/drivers/media/platform/ti/davinci/vpif_capture.c @@ -1600,7 +1600,7 @@ vpif_capture_get_pdata(struct platform_device *pdev, * This creates device entries by register itself to the V4L2 driver and * initializes fields of each channel objects */ -static __init int vpif_probe(struct platform_device *pdev) +static int vpif_probe(struct platform_device *pdev) { struct vpif_subdev_info *subdevdata; struct i2c_adapter *i2c_adap; @@ -1807,7 +1807,7 @@ static int vpif_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(vpif_pm_ops, vpif_suspend, vpif_resume); -static __refdata struct platform_driver vpif_driver = { +static struct platform_driver vpif_driver = { .driver = { .name = VPIF_DRIVER_NAME, .pm = &vpif_pm_ops, diff --git a/drivers/media/platform/ti/davinci/vpif_display.c b/drivers/media/platform/ti/davinci/vpif_display.c index 70c89549f4b61d..1e7815e9f8e075 100644 --- a/drivers/media/platform/ti/davinci/vpif_display.c +++ b/drivers/media/platform/ti/davinci/vpif_display.c @@ -1214,7 +1214,7 @@ static int vpif_probe_complete(void) * vpif_probe: This function creates device entries by register itself to the * V4L2 driver and initializes fields of each channel objects */ -static __init int vpif_probe(struct platform_device *pdev) +static int vpif_probe(struct platform_device *pdev) { struct vpif_subdev_info *subdevdata; struct i2c_adapter *i2c_adap; @@ -1390,7 +1390,7 @@ static int vpif_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(vpif_pm_ops, vpif_suspend, vpif_resume); -static __refdata struct platform_driver vpif_driver = { +static struct platform_driver vpif_driver = { .driver = { .name = VPIF_DRIVER_NAME, .pm = &vpif_pm_ops, diff --git a/drivers/media/platform/verisilicon/hantro_g2.c b/drivers/media/platform/verisilicon/hantro_g2.c index aae0b562fabb17..318673b66da884 100644 --- a/drivers/media/platform/verisilicon/hantro_g2.c +++ b/drivers/media/platform/verisilicon/hantro_g2.c @@ -5,43 +5,93 @@ * Copyright (C) 2021 Collabora Ltd, Andrzej Pietrasiewicz */ +#include #include "hantro_hw.h" #include "hantro_g2_regs.h" #define G2_ALIGN 16 -void hantro_g2_check_idle(struct hantro_dev *vpu) +static bool hantro_g2_active(struct hantro_ctx *ctx) { - int i; - - for (i = 0; i < 3; i++) { - u32 status; - - /* Make sure the VPU is idle */ - status = vdpu_read(vpu, G2_REG_INTERRUPT); - if (status & G2_REG_INTERRUPT_DEC_E) { - dev_warn(vpu->dev, "device still running, aborting"); - status |= G2_REG_INTERRUPT_DEC_ABORT_E | G2_REG_INTERRUPT_DEC_IRQ_DIS; - vdpu_write(vpu, status, G2_REG_INTERRUPT); - } + struct hantro_dev *vpu = ctx->dev; + u32 status; + + status = vdpu_read(vpu, G2_REG_INTERRUPT); + + return (status & G2_REG_INTERRUPT_DEC_E); +} + +/** + * hantro_g2_reset: + * @ctx: the hantro context + * + * Emulates a reset using Hantro abort function. Failing this procedure would + * results in programming a running IP which leads to CPU hang. + * + * Using a hard reset procedure instead is prefferred. + */ +void hantro_g2_reset(struct hantro_ctx *ctx) +{ + struct hantro_dev *vpu = ctx->dev; + u32 status; + + status = vdpu_read(vpu, G2_REG_INTERRUPT); + if (status & G2_REG_INTERRUPT_DEC_E) { + dev_warn_ratelimited(vpu->dev, "device still running, aborting"); + status |= G2_REG_INTERRUPT_DEC_ABORT_E | G2_REG_INTERRUPT_DEC_IRQ_DIS; + vdpu_write(vpu, status, G2_REG_INTERRUPT); + + do { + mdelay(1); + } while (hantro_g2_active(ctx)); } } irqreturn_t hantro_g2_irq(int irq, void *dev_id) { struct hantro_dev *vpu = dev_id; - enum vb2_buffer_state state; u32 status; status = vdpu_read(vpu, G2_REG_INTERRUPT); - state = (status & G2_REG_INTERRUPT_DEC_RDY_INT) ? - VB2_BUF_STATE_DONE : VB2_BUF_STATE_ERROR; - vdpu_write(vpu, 0, G2_REG_INTERRUPT); - vdpu_write(vpu, G2_REG_CONFIG_DEC_CLK_GATE_E, G2_REG_CONFIG); + if (!(status & G2_REG_INTERRUPT_DEC_IRQ)) + return IRQ_NONE; + + hantro_reg_write(vpu, &g2_dec_irq, 0); + hantro_reg_write(vpu, &g2_dec_int_stat, 0); + hantro_reg_write(vpu, &g2_clk_gate_e, 1); + + if (status & G2_REG_INTERRUPT_DEC_RDY_INT) { + hantro_irq_done(vpu, VB2_BUF_STATE_DONE); + return IRQ_HANDLED; + } + + if (status & G2_REG_INTERRUPT_DEC_ABORT_INT) { + /* disabled on abort, though lets be safe and handle it */ + dev_warn_ratelimited(vpu->dev, "decode operation aborted."); + return IRQ_HANDLED; + } + + if (status & G2_REG_INTERRUPT_DEC_LAST_SLICE_INT) + dev_warn_ratelimited(vpu->dev, "not all macroblocks were decoded."); + + if (status & G2_REG_INTERRUPT_DEC_BUS_INT) + dev_warn_ratelimited(vpu->dev, "bus error detected."); + + if (status & G2_REG_INTERRUPT_DEC_ERROR_INT) + dev_warn_ratelimited(vpu->dev, "decode error detected."); + + if (status & G2_REG_INTERRUPT_DEC_TIMEOUT) + dev_warn_ratelimited(vpu->dev, "frame decode timed out."); - hantro_irq_done(vpu, state); + /** + * If the decoding haven't stopped, let it continue. The hardware timeout + * will trigger if it is trully stuck. + */ + if (status & G2_REG_INTERRUPT_DEC_E) + return IRQ_HANDLED; + hantro_irq_done(vpu, VB2_BUF_STATE_ERROR); return IRQ_HANDLED; } diff --git a/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c b/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c index 0e212198dd65b1..e8c2e83379def5 100644 --- a/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c +++ b/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c @@ -283,6 +283,15 @@ static void set_params(struct hantro_ctx *ctx) hantro_reg_write(vpu, &g2_apf_threshold, 8); } +static u32 get_dpb_index(const struct v4l2_ctrl_hevc_decode_params *decode_params, + const u32 index) +{ + if (index > decode_params->num_active_dpb_entries) + return 0; + + return index; +} + static void set_ref_pic_list(struct hantro_ctx *ctx) { const struct hantro_hevc_dec_ctrls *ctrls = &ctx->hevc_dec.ctrls; @@ -355,8 +364,10 @@ static void set_ref_pic_list(struct hantro_ctx *ctx) list1[j++] = list1[i++]; for (i = 0; i < V4L2_HEVC_DPB_ENTRIES_NUM_MAX; i++) { - hantro_reg_write(vpu, &ref_pic_regs0[i], list0[i]); - hantro_reg_write(vpu, &ref_pic_regs1[i], list1[i]); + hantro_reg_write(vpu, &ref_pic_regs0[i], + get_dpb_index(decode_params, list0[i])); + hantro_reg_write(vpu, &ref_pic_regs1[i], + get_dpb_index(decode_params, list1[i])); } } @@ -582,8 +593,6 @@ int hantro_g2_hevc_dec_run(struct hantro_ctx *ctx) struct hantro_dev *vpu = ctx->dev; int ret; - hantro_g2_check_idle(vpu); - /* Prepare HEVC decoder context. */ ret = hantro_hevc_dec_prepare_run(ctx); if (ret) diff --git a/drivers/media/platform/verisilicon/hantro_g2_regs.h b/drivers/media/platform/verisilicon/hantro_g2_regs.h index b943b1816db7fd..c614951121c79c 100644 --- a/drivers/media/platform/verisilicon/hantro_g2_regs.h +++ b/drivers/media/platform/verisilicon/hantro_g2_regs.h @@ -22,7 +22,14 @@ #define G2_REG_VERSION G2_SWREG(0) #define G2_REG_INTERRUPT G2_SWREG(1) +#define G2_REG_INTERRUPT_DEC_LAST_SLICE_INT BIT(19) +#define G2_REG_INTERRUPT_DEC_TIMEOUT BIT(18) +#define G2_REG_INTERRUPT_DEC_ERROR_INT BIT(16) +#define G2_REG_INTERRUPT_DEC_BUF_INT BIT(14) +#define G2_REG_INTERRUPT_DEC_BUS_INT BIT(13) #define G2_REG_INTERRUPT_DEC_RDY_INT BIT(12) +#define G2_REG_INTERRUPT_DEC_ABORT_INT BIT(11) +#define G2_REG_INTERRUPT_DEC_IRQ BIT(8) #define G2_REG_INTERRUPT_DEC_ABORT_E BIT(5) #define G2_REG_INTERRUPT_DEC_IRQ_DIS BIT(4) #define G2_REG_INTERRUPT_DEC_E BIT(0) @@ -35,6 +42,9 @@ #define BUS_WIDTH_128 2 #define BUS_WIDTH_256 3 +#define g2_dec_int_stat G2_DEC_REG(1, 11, 0xf) +#define g2_dec_irq G2_DEC_REG(1, 8, 0x1) + #define g2_strm_swap G2_DEC_REG(2, 28, 0xf) #define g2_strm_swap_old G2_DEC_REG(2, 27, 0x1f) #define g2_pic_swap G2_DEC_REG(2, 22, 0x1f) @@ -225,6 +235,9 @@ #define vp9_filt_level_seg5 G2_DEC_REG(19, 8, 0x3f) #define vp9_quant_seg5 G2_DEC_REG(19, 0, 0xff) +#define g2_timemout_override_e G2_DEC_REG(45, 31, 0x1) +#define g2_timemout_cycles G2_DEC_REG(45, 0, 0x7fffffff) + #define hevc_cur_poc_00 G2_DEC_REG(46, 24, 0xff) #define hevc_cur_poc_01 G2_DEC_REG(46, 16, 0xff) #define hevc_cur_poc_02 G2_DEC_REG(46, 8, 0xff) diff --git a/drivers/media/platform/verisilicon/hantro_g2_vp9_dec.c b/drivers/media/platform/verisilicon/hantro_g2_vp9_dec.c index 82a478ac645e1d..56c79e339030e8 100644 --- a/drivers/media/platform/verisilicon/hantro_g2_vp9_dec.c +++ b/drivers/media/platform/verisilicon/hantro_g2_vp9_dec.c @@ -893,8 +893,6 @@ int hantro_g2_vp9_dec_run(struct hantro_ctx *ctx) struct vb2_v4l2_buffer *dst; int ret; - hantro_g2_check_idle(ctx->dev); - ret = start_prepare_run(ctx, &decode_params); if (ret) { hantro_end_prepare_run(ctx); diff --git a/drivers/media/platform/verisilicon/hantro_hw.h b/drivers/media/platform/verisilicon/hantro_hw.h index c9b6556f8b2b78..5f2011529f02dc 100644 --- a/drivers/media/platform/verisilicon/hantro_hw.h +++ b/drivers/media/platform/verisilicon/hantro_hw.h @@ -583,6 +583,7 @@ void hantro_g2_vp9_dec_done(struct hantro_ctx *ctx); int hantro_vp9_dec_init(struct hantro_ctx *ctx); void hantro_vp9_dec_exit(struct hantro_ctx *ctx); void hantro_g2_check_idle(struct hantro_dev *vpu); +void hantro_g2_reset(struct hantro_ctx *ctx); irqreturn_t hantro_g2_irq(int irq, void *dev_id); #endif /* HANTRO_HW_H_ */ diff --git a/drivers/media/platform/verisilicon/imx8m_vpu_hw.c b/drivers/media/platform/verisilicon/imx8m_vpu_hw.c index f9f276385c1178..5be0e2e76882f1 100644 --- a/drivers/media/platform/verisilicon/imx8m_vpu_hw.c +++ b/drivers/media/platform/verisilicon/imx8m_vpu_hw.c @@ -294,11 +294,13 @@ static const struct hantro_codec_ops imx8mq_vpu_g1_codec_ops[] = { static const struct hantro_codec_ops imx8mq_vpu_g2_codec_ops[] = { [HANTRO_MODE_HEVC_DEC] = { .run = hantro_g2_hevc_dec_run, + .reset = hantro_g2_reset, .init = hantro_hevc_dec_init, .exit = hantro_hevc_dec_exit, }, [HANTRO_MODE_VP9_DEC] = { .run = hantro_g2_vp9_dec_run, + .reset = hantro_g2_reset, .done = hantro_g2_vp9_dec_done, .init = hantro_vp9_dec_init, .exit = hantro_vp9_dec_exit, diff --git a/drivers/media/rc/st_rc.c b/drivers/media/rc/st_rc.c index 6539fa0a6e7905..6b70bac5f45d6c 100644 --- a/drivers/media/rc/st_rc.c +++ b/drivers/media/rc/st_rc.c @@ -284,7 +284,7 @@ static int st_rc_probe(struct platform_device *pdev) else rc_dev->rx_base = rc_dev->base; - rc_dev->rstc = reset_control_get_optional_exclusive(dev, NULL); + rc_dev->rstc = devm_reset_control_get_optional_exclusive(dev, NULL); if (IS_ERR(rc_dev->rstc)) { ret = PTR_ERR(rc_dev->rstc); goto err; diff --git a/drivers/media/test-drivers/vidtv/vidtv_channel.c b/drivers/media/test-drivers/vidtv/vidtv_channel.c index f3023e91b3ebc8..3541155c6fc635 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_channel.c +++ b/drivers/media/test-drivers/vidtv/vidtv_channel.c @@ -461,12 +461,15 @@ int vidtv_channel_si_init(struct vidtv_mux *m) /* assemble all programs and assign to PAT */ vidtv_psi_pat_program_assign(m->si.pat, programs); + programs = NULL; /* assemble all services and assign to SDT */ vidtv_psi_sdt_service_assign(m->si.sdt, services); + services = NULL; /* assemble all events and assign to EIT */ vidtv_psi_eit_event_assign(m->si.eit, events); + events = NULL; m->si.pmt_secs = vidtv_psi_pmt_create_sec_for_each_pat_entry(m->si.pat, m->pcr_pid); diff --git a/drivers/media/usb/dvb-usb/dtv5100.c b/drivers/media/usb/dvb-usb/dtv5100.c index 3d85c6f7f6ecf4..c448e2ebda1ac0 100644 --- a/drivers/media/usb/dvb-usb/dtv5100.c +++ b/drivers/media/usb/dvb-usb/dtv5100.c @@ -55,6 +55,11 @@ static int dtv5100_i2c_msg(struct dvb_usb_device *d, u8 addr, } index = (addr << 8) + wbuf[0]; + if (rlen > sizeof(st->data)) { + warn("rlen = %x is too big!\n", rlen); + return -EINVAL; + } + memcpy(st->data, rbuf, rlen); msleep(1); /* avoid I2C errors */ return usb_control_msg(d->udev, pipe, request, diff --git a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c index f21c2806eb9fe3..b32bb906a9de29 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c @@ -3622,7 +3622,7 @@ static int pvr2_send_request_ex(struct pvr2_hdw *hdw, pvr2_trace( PVR2_TRACE_ERROR_LEGS, "Attempted to execute %d byte control-read transfer (limit=%d)", - write_len,PVR2_CTL_BUFFSIZE); + read_len, PVR2_CTL_BUFFSIZE); return -EINVAL; } if ((!write_len) && (!read_len)) { diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index 2094e059d7d39a..ec76595f3c4be0 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -1812,7 +1812,7 @@ static int uvc_alloc_urb_buffers(struct uvc_streaming *stream, npackets = UVC_MAX_PACKETS; /* Retry allocations until one succeed. */ - for (; npackets > 1; npackets /= 2) { + for (; npackets > 0; npackets /= 2) { stream->urb_size = psize * npackets; for (i = 0; i < UVC_URBS; ++i) { @@ -1837,6 +1837,7 @@ static int uvc_alloc_urb_buffers(struct uvc_streaming *stream, uvc_dbg(stream->dev, VIDEO, "Failed to allocate URB buffers (%u bytes per packet)\n", psize); + stream->urb_size = 0; return 0; } diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 6cec1858947bf7..55a9fea95195bc 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -406,6 +406,17 @@ config MFD_CS47L92 help Support for Cirrus Logic CS42L92, CS47L92 and CS47L93 Smart Codecs +config MFD_TN48M_CPLD + tristate "Delta Networks TN48M switch CPLD driver" + depends on I2C + depends on ARCH_MVEBU || COMPILE_TEST + select MFD_SIMPLE_MFD_I2C + help + Select this option to enable support for Delta Networks TN48M switch + CPLD. It consists of reset and GPIO drivers. CPLD provides GPIOS-s + for the SFP slots as well as power supply related information. + SFP support depends on the GPIO driver being selected. + config PMIC_DA903X bool "Dialog Semiconductor DA9030/DA9034 PMIC Support" depends on I2C=y diff --git a/drivers/mfd/altera-sysmgr.c b/drivers/mfd/altera-sysmgr.c index fb5f988e61f373..90c6902d537da3 100644 --- a/drivers/mfd/altera-sysmgr.c +++ b/drivers/mfd/altera-sysmgr.c @@ -117,6 +117,8 @@ struct regmap *altr_sysmgr_regmap_lookup_by_phandle(struct device_node *np, sysmgr = dev_get_drvdata(dev); + put_device(dev); + return sysmgr->regmap; } EXPORT_SYMBOL_GPL(altr_sysmgr_regmap_lookup_by_phandle); diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c index 85ff8717d85047..91975536d14d21 100644 --- a/drivers/mfd/arizona-core.c +++ b/drivers/mfd/arizona-core.c @@ -1100,7 +1100,7 @@ int arizona_dev_init(struct arizona *arizona) } else if (val & 0x01) { ret = wm5102_clear_write_sequencer(arizona); if (ret) - return ret; + goto err_reset; } break; default: diff --git a/drivers/mfd/da9055-core.c b/drivers/mfd/da9055-core.c index 1f727ef60d6387..8c989b74f924e3 100644 --- a/drivers/mfd/da9055-core.c +++ b/drivers/mfd/da9055-core.c @@ -388,6 +388,7 @@ int da9055_device_init(struct da9055 *da9055) err: mfd_remove_devices(da9055->dev); + regmap_del_irq_chip(da9055->chip_irq, da9055->irq_data); return ret; } diff --git a/drivers/mfd/macsmc.c b/drivers/mfd/macsmc.c index e6cdae221f1d4e..a7fd896cb45b00 100644 --- a/drivers/mfd/macsmc.c +++ b/drivers/mfd/macsmc.c @@ -45,8 +45,12 @@ #define SMC_TIMEOUT_MS 500 static const struct mfd_cell apple_smc_devs[] = { + MFD_CELL_NAME("macsmc-input"), + MFD_CELL_NAME("macsmc-power"), MFD_CELL_OF("macsmc-gpio", NULL, NULL, 0, 0, "apple,smc-gpio"), + MFD_CELL_OF("macsmc-hwmon", NULL, NULL, 0, 0, "apple,smc-hwmon"), MFD_CELL_OF("macsmc-reboot", NULL, NULL, 0, 0, "apple,smc-reboot"), + MFD_CELL_OF("macsmc-rtc", NULL, NULL, 0, 0, "apple,smc-rtc"), }; static int apple_smc_cmd_locked(struct apple_smc *smc, u64 cmd, u64 arg, @@ -413,6 +417,7 @@ static int apple_smc_probe(struct platform_device *pdev) if (!smc) return -ENOMEM; + mutex_init(&smc->mutex); smc->dev = &pdev->dev; smc->sram_base = devm_platform_get_and_ioremap_resource(pdev, 1, &smc->sram); if (IS_ERR(smc->sram_base)) diff --git a/drivers/mfd/max77620.c b/drivers/mfd/max77620.c index 21d2ab3db2542e..3af2974b302327 100644 --- a/drivers/mfd/max77620.c +++ b/drivers/mfd/max77620.c @@ -254,7 +254,7 @@ static int max77620_irq_global_unmask(void *irq_drv_data) return ret; } -static struct regmap_irq_chip max77620_top_irq_chip = { +static const struct regmap_irq_chip max77620_top_irq_chip = { .name = "max77620-top", .irqs = max77620_top_irqs, .num_irqs = ARRAY_SIZE(max77620_top_irqs), @@ -498,6 +498,7 @@ static int max77620_probe(struct i2c_client *client) const struct i2c_device_id *id = i2c_client_get_device_id(client); const struct regmap_config *rmap_config; struct max77620_chip *chip; + struct regmap_irq_chip *chip_desc; const struct mfd_cell *mfd_cells; int n_mfd_cells; bool pm_off; @@ -508,6 +509,14 @@ static int max77620_probe(struct i2c_client *client) return -ENOMEM; i2c_set_clientdata(client, chip); + + chip_desc = devm_kmemdup(&client->dev, &max77620_top_irq_chip, + sizeof(max77620_top_irq_chip), + GFP_KERNEL); + if (!chip_desc) + return -ENOMEM; + chip_desc->irq_drv_data = chip; + chip->dev = &client->dev; chip->chip_irq = client->irq; chip->chip_id = (enum max77620_chip_id)id->driver_data; @@ -544,11 +553,9 @@ static int max77620_probe(struct i2c_client *client) if (ret < 0) return ret; - max77620_top_irq_chip.irq_drv_data = chip; ret = devm_regmap_add_irq_chip(chip->dev, chip->rmap, client->irq, IRQF_ONESHOT | IRQF_SHARED, 0, - &max77620_top_irq_chip, - &chip->top_irq_data); + chip_desc, &chip->top_irq_data); if (ret < 0) { dev_err(chip->dev, "Failed to add regmap irq: %d\n", ret); return ret; diff --git a/drivers/mfd/mt6358-irq.c b/drivers/mfd/mt6358-irq.c index f467b00d236600..74cf2084304409 100644 --- a/drivers/mfd/mt6358-irq.c +++ b/drivers/mfd/mt6358-irq.c @@ -285,6 +285,7 @@ int mt6358_irq_init(struct mt6397_chip *chip) if (ret) { dev_err(chip->dev, "Failed to register IRQ=%d, ret=%d\n", chip->irq, ret); + irq_domain_remove(chip->irq_domain); return ret; } diff --git a/drivers/mfd/mt6397-irq.c b/drivers/mfd/mt6397-irq.c index 0e463026c5a918..5d2e5459f74449 100644 --- a/drivers/mfd/mt6397-irq.c +++ b/drivers/mfd/mt6397-irq.c @@ -229,6 +229,7 @@ int mt6397_irq_init(struct mt6397_chip *chip) if (ret) { dev_err(chip->dev, "failed to register irq=%d; err: %d\n", chip->irq, ret); + irq_domain_remove(chip->irq_domain); return ret; } diff --git a/drivers/mfd/simple-mfd-i2c.c b/drivers/mfd/simple-mfd-i2c.c index 0a607a1e3ca1de..9f911afafc25ef 100644 --- a/drivers/mfd/simple-mfd-i2c.c +++ b/drivers/mfd/simple-mfd-i2c.c @@ -110,6 +110,7 @@ static const struct simple_mfd_data spacemit_p1 = { }; static const struct of_device_id simple_mfd_i2c_of_match[] = { + { .compatible = "delta,tn48m-cpld" }, { .compatible = "fsl,ls1028aqds-fpga" }, { .compatible = "fsl,lx2160aqds-fpga" }, { .compatible = "fsl,lx2160ardb-fpga" }, diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig index f8b04e49e4baf1..f4eb307cd35ed0 100644 --- a/drivers/misc/mei/Kconfig +++ b/drivers/misc/mei/Kconfig @@ -49,7 +49,7 @@ config INTEL_MEI_TXE config INTEL_MEI_GSC tristate "Intel MEI GSC embedded device" depends on INTEL_MEI_ME - depends on DRM_I915 + depends on DRM_I915 || DRM_XE help Intel auxiliary driver for GSC devices embedded in Intel graphics devices. diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index a4f75dc3692920..fa30899a5fa260 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -122,6 +122,8 @@ #define MEI_DEV_ID_WCL_P 0x4D70 /* Wildcat Lake P */ +#define MEI_DEV_ID_NVL_S 0x6E68 /* Nova Lake Point S */ + /* * MEI HW Section */ diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 86a73684a37325..6f26d516078835 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -1307,6 +1307,7 @@ int mei_register(struct mei_device *dev, struct device *parent) err_del_cdev: cdev_del(dev->cdev); err: + put_device(&dev->dev); mei_minor_free(minor); return ret; } diff --git a/drivers/misc/mei/mei-trace.h b/drivers/misc/mei/mei-trace.h index 5312edbf5190d7..24fa321d88bd8b 100644 --- a/drivers/misc/mei/mei-trace.h +++ b/drivers/misc/mei/mei-trace.h @@ -21,18 +21,18 @@ TRACE_EVENT(mei_reg_read, TP_ARGS(dev, reg, offs, val), TP_STRUCT__entry( __string(dev, dev_name(dev)) - __field(const char *, reg) + __string(reg, reg) __field(u32, offs) __field(u32, val) ), TP_fast_assign( __assign_str(dev); - __entry->reg = reg; + __assign_str(reg); __entry->offs = offs; __entry->val = val; ), TP_printk("[%s] read %s:[%#x] = %#x", - __get_str(dev), __entry->reg, __entry->offs, __entry->val) + __get_str(dev), __get_str(reg), __entry->offs, __entry->val) ); TRACE_EVENT(mei_reg_write, @@ -40,18 +40,18 @@ TRACE_EVENT(mei_reg_write, TP_ARGS(dev, reg, offs, val), TP_STRUCT__entry( __string(dev, dev_name(dev)) - __field(const char *, reg) + __string(reg, reg) __field(u32, offs) __field(u32, val) ), TP_fast_assign( __assign_str(dev); - __entry->reg = reg; + __assign_str(reg); __entry->offs = offs; __entry->val = val; ), TP_printk("[%s] write %s[%#x] = %#x", - __get_str(dev), __entry->reg, __entry->offs, __entry->val) + __get_str(dev), __get_str(reg), __entry->offs, __entry->val) ); TRACE_EVENT(mei_pci_cfg_read, @@ -59,18 +59,18 @@ TRACE_EVENT(mei_pci_cfg_read, TP_ARGS(dev, reg, offs, val), TP_STRUCT__entry( __string(dev, dev_name(dev)) - __field(const char *, reg) + __string(reg, reg) __field(u32, offs) __field(u32, val) ), TP_fast_assign( __assign_str(dev); - __entry->reg = reg; + __assign_str(reg); __entry->offs = offs; __entry->val = val; ), TP_printk("[%s] pci cfg read %s:[%#x] = %#x", - __get_str(dev), __entry->reg, __entry->offs, __entry->val) + __get_str(dev), __get_str(reg), __entry->offs, __entry->val) ); #endif /* _MEI_TRACE_H_ */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 73cad914be9f9b..2a6e569558b943 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -129,6 +129,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_WCL_P, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_NVL_S, MEI_ME_PCH15_CFG)}, + /* required last entry */ {0, } }; diff --git a/drivers/misc/rp1/rp1_pci.c b/drivers/misc/rp1/rp1_pci.c index 803832006ec876..a342bcc6164bb6 100644 --- a/drivers/misc/rp1/rp1_pci.c +++ b/drivers/misc/rp1/rp1_pci.c @@ -289,6 +289,9 @@ static int rp1_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_unload_overlay; } + if (skip_ovl) + of_node_put(rp1_node); + return 0; err_unload_overlay: diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c index 42e7d2a2a90c6e..6d71355528d344 100644 --- a/drivers/misc/uacce/uacce.c +++ b/drivers/misc/uacce/uacce.c @@ -40,20 +40,34 @@ static int uacce_start_queue(struct uacce_queue *q) return 0; } -static int uacce_put_queue(struct uacce_queue *q) +static int uacce_stop_queue(struct uacce_queue *q) { struct uacce_device *uacce = q->uacce; - if ((q->state == UACCE_Q_STARTED) && uacce->ops->stop_queue) + if (q->state != UACCE_Q_STARTED) + return 0; + + if (uacce->ops->stop_queue) uacce->ops->stop_queue(q); - if ((q->state == UACCE_Q_INIT || q->state == UACCE_Q_STARTED) && - uacce->ops->put_queue) + q->state = UACCE_Q_INIT; + + return 0; +} + +static void uacce_put_queue(struct uacce_queue *q) +{ + struct uacce_device *uacce = q->uacce; + + uacce_stop_queue(q); + + if (q->state != UACCE_Q_INIT) + return; + + if (uacce->ops->put_queue) uacce->ops->put_queue(q); q->state = UACCE_Q_ZOMBIE; - - return 0; } static long uacce_fops_unl_ioctl(struct file *filep, @@ -80,7 +94,7 @@ static long uacce_fops_unl_ioctl(struct file *filep, ret = uacce_start_queue(q); break; case UACCE_CMD_PUT_Q: - ret = uacce_put_queue(q); + ret = uacce_stop_queue(q); break; default: if (uacce->ops->ioctl) @@ -214,8 +228,14 @@ static void uacce_vma_close(struct vm_area_struct *vma) } } +static int uacce_vma_mremap(struct vm_area_struct *area) +{ + return -EPERM; +} + static const struct vm_operations_struct uacce_vm_ops = { .close = uacce_vma_close, + .mremap = uacce_vma_mremap, }; static int uacce_fops_mmap(struct file *filep, struct vm_area_struct *vma) @@ -382,6 +402,9 @@ static ssize_t isolate_strategy_show(struct device *dev, struct device_attribute struct uacce_device *uacce = to_uacce_device(dev); u32 val; + if (!uacce->ops->isolate_err_threshold_read) + return -ENOENT; + val = uacce->ops->isolate_err_threshold_read(uacce); return sysfs_emit(buf, "%u\n", val); @@ -394,6 +417,9 @@ static ssize_t isolate_strategy_store(struct device *dev, struct device_attribut unsigned long val; int ret; + if (!uacce->ops->isolate_err_threshold_write) + return -ENOENT; + if (kstrtoul(buf, 0, &val) < 0) return -EINVAL; @@ -519,6 +545,8 @@ EXPORT_SYMBOL_GPL(uacce_alloc); */ int uacce_register(struct uacce_device *uacce) { + int ret; + if (!uacce) return -ENODEV; @@ -529,7 +557,11 @@ int uacce_register(struct uacce_device *uacce) uacce->cdev->ops = &uacce_fops; uacce->cdev->owner = THIS_MODULE; - return cdev_device_add(uacce->cdev, &uacce->dev); + ret = cdev_device_add(uacce->cdev, &uacce->dev); + if (ret) + uacce->cdev = NULL; + + return ret; } EXPORT_SYMBOL_GPL(uacce_register); diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 860378bea557b3..d42c548c073fcc 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -2300,10 +2300,11 @@ void mmc_rescan(struct work_struct *work) * while initializing the legacy SD interface. Therefore, let's start * with UHS-II for now. */ - if (!mmc_attach_sd_uhs2(host)) { - mmc_release_host(host); - goto out; - } + if (host->caps2 & MMC_CAP2_SD_UHS2) + if (!mmc_attach_sd_uhs2(host)) { + mmc_release_host(host); + goto out; + } for (i = 0; i < ARRAY_SIZE(freqs); i++) { unsigned int freq = freqs[i]; diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 10d0ef58ef4931..c94ae4794545de 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -315,14 +315,14 @@ config MMC_SDHCI_ESDHC_MCF config MMC_SDHCI_ESDHC_IMX tristate "SDHCI support for the Freescale eSDHC/uSDHC i.MX controller" - depends on ARCH_MXC || COMPILE_TEST + depends on ARCH_MXC || ARCH_S32 || COMPILE_TEST depends on MMC_SDHCI_PLTFM depends on OF select MMC_SDHCI_IO_ACCESSORS select MMC_CQHCI help This selects the Freescale eSDHC/uSDHC controller support - found on i.MX25, i.MX35 i.MX5x and i.MX6x. + found on i.MX25, i.MX35, i.MX5x, i.MX6x, and S32G. If you have a controller with this interface, say Y or M here. diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c index dc2587ff8519f8..4db3328f46dfbd 100644 --- a/drivers/mmc/host/rtsx_pci_sdmmc.c +++ b/drivers/mmc/host/rtsx_pci_sdmmc.c @@ -1306,6 +1306,46 @@ static int sdmmc_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios) return err; } +static int sdmmc_card_busy(struct mmc_host *mmc) +{ + struct realtek_pci_sdmmc *host = mmc_priv(mmc); + struct rtsx_pcr *pcr = host->pcr; + int err; + u8 stat; + u8 mask = SD_DAT3_STATUS | SD_DAT2_STATUS | SD_DAT1_STATUS + | SD_DAT0_STATUS; + + mutex_lock(&pcr->pcr_mutex); + + rtsx_pci_start_run(pcr); + + err = rtsx_pci_write_register(pcr, SD_BUS_STAT, + SD_CLK_TOGGLE_EN | SD_CLK_FORCE_STOP, + SD_CLK_TOGGLE_EN); + if (err) + goto out; + + mdelay(1); + + err = rtsx_pci_read_register(pcr, SD_BUS_STAT, &stat); + if (err) + goto out; + + err = rtsx_pci_write_register(pcr, SD_BUS_STAT, + SD_CLK_TOGGLE_EN | SD_CLK_FORCE_STOP, 0); +out: + mutex_unlock(&pcr->pcr_mutex); + + if (err) + return err; + + /* check if any pin between dat[0:3] is low */ + if ((stat & mask) != mask) + return 1; + else + return 0; +} + static int sdmmc_execute_tuning(struct mmc_host *mmc, u32 opcode) { struct realtek_pci_sdmmc *host = mmc_priv(mmc); @@ -1418,6 +1458,7 @@ static const struct mmc_host_ops realtek_pci_sdmmc_ops = { .get_ro = sdmmc_get_ro, .get_cd = sdmmc_get_cd, .start_signal_voltage_switch = sdmmc_switch_voltage, + .card_busy = sdmmc_card_busy, .execute_tuning = sdmmc_execute_tuning, .init_sd_express = sdmmc_init_sd_express, }; diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index 4e5edbf2fc9b6f..3b85233131b386 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -344,41 +344,43 @@ static void sdhci_msm_v5_variant_writel_relaxed(u32 val, writel_relaxed(val, host->ioaddr + offset); } -static unsigned int msm_get_clock_mult_for_bus_mode(struct sdhci_host *host) +static unsigned int msm_get_clock_mult_for_bus_mode(struct sdhci_host *host, + unsigned int clock, + unsigned int timing) { - struct mmc_ios ios = host->mmc->ios; /* * The SDHC requires internal clock frequency to be double the * actual clock that will be set for DDR mode. The controller * uses the faster clock(100/400MHz) for some of its parts and * send the actual required clock (50/200MHz) to the card. */ - if (ios.timing == MMC_TIMING_UHS_DDR50 || - ios.timing == MMC_TIMING_MMC_DDR52 || - ios.timing == MMC_TIMING_MMC_HS400 || + if (timing == MMC_TIMING_UHS_DDR50 || + timing == MMC_TIMING_MMC_DDR52 || + (timing == MMC_TIMING_MMC_HS400 && + clock == MMC_HS200_MAX_DTR) || host->flags & SDHCI_HS400_TUNING) return 2; return 1; } static void msm_set_clock_rate_for_bus_mode(struct sdhci_host *host, - unsigned int clock) + unsigned int clock, + unsigned int timing) { struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host); - struct mmc_ios curr_ios = host->mmc->ios; struct clk *core_clk = msm_host->bulk_clks[0].clk; unsigned long achieved_rate; unsigned int desired_rate; unsigned int mult; int rc; - mult = msm_get_clock_mult_for_bus_mode(host); + mult = msm_get_clock_mult_for_bus_mode(host, clock, timing); desired_rate = clock * mult; rc = dev_pm_opp_set_rate(mmc_dev(host->mmc), desired_rate); if (rc) { pr_err("%s: Failed to set clock at rate %u at timing %d\n", - mmc_hostname(host->mmc), desired_rate, curr_ios.timing); + mmc_hostname(host->mmc), desired_rate, timing); return; } @@ -397,7 +399,7 @@ static void msm_set_clock_rate_for_bus_mode(struct sdhci_host *host, msm_host->clk_rate = desired_rate; pr_debug("%s: Setting clock at rate %lu at timing %d\n", - mmc_hostname(host->mmc), achieved_rate, curr_ios.timing); + mmc_hostname(host->mmc), achieved_rate, timing); } /* Platform specific tuning */ @@ -1239,7 +1241,7 @@ static int sdhci_msm_execute_tuning(struct mmc_host *mmc, u32 opcode) */ if (host->flags & SDHCI_HS400_TUNING) { sdhci_msm_hc_select_mode(host); - msm_set_clock_rate_for_bus_mode(host, ios.clock); + msm_set_clock_rate_for_bus_mode(host, ios.clock, ios.timing); host->flags &= ~SDHCI_HS400_TUNING; } @@ -1864,6 +1866,7 @@ static void sdhci_msm_set_clock(struct sdhci_host *host, unsigned int clock) { struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host); + struct mmc_ios ios = host->mmc->ios; if (!clock) { host->mmc->actual_clock = msm_host->clk_rate = 0; @@ -1872,7 +1875,7 @@ static void sdhci_msm_set_clock(struct sdhci_host *host, unsigned int clock) sdhci_msm_hc_select_mode(host); - msm_set_clock_rate_for_bus_mode(host, clock); + msm_set_clock_rate_for_bus_mode(host, ios.clock, ios.timing); out: __sdhci_msm_set_clock(host, clock); } diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c index c6f09b53325d2d..0a4b4696bc01cd 100644 --- a/drivers/mmc/host/sdhci-of-arasan.c +++ b/drivers/mmc/host/sdhci-of-arasan.c @@ -99,7 +99,7 @@ #define HIWORD_UPDATE(val, mask, shift) \ ((val) << (shift) | (mask) << ((shift) + 16)) -#define CD_STABLE_TIMEOUT_US 1000000 +#define CD_STABLE_TIMEOUT_US 2000000 #define CD_STABLE_MAX_SLEEP_US 10 /** diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c index 4e256673a0983e..5ae4e11b1e90c7 100644 --- a/drivers/mmc/host/sdhci-of-dwcmshc.c +++ b/drivers/mmc/host/sdhci-of-dwcmshc.c @@ -608,6 +608,13 @@ static void dwcmshc_rk3568_set_clock(struct sdhci_host *host, unsigned int clock sdhci_writel(host, extra, reg); if (clock <= 52000000) { + if (host->mmc->ios.timing == MMC_TIMING_MMC_HS200 || + host->mmc->ios.timing == MMC_TIMING_MMC_HS400) { + dev_err(mmc_dev(host->mmc), + "Can't reduce the clock below 52MHz in HS200/HS400 mode"); + return; + } + /* * Disable DLL and reset both of sample and drive clock. * The bypass bit and start bit need to be set if DLL is not locked. diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index 47a0a738862b58..93122133202367 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -2129,6 +2130,7 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot( struct sdhci_host *host; int ret, bar = first_bar + slotno; size_t priv_size = chip->fixes ? chip->fixes->priv_size : 0; + u32 cd_debounce_delay_ms; if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) { dev_err(&pdev->dev, "BAR %d is not iomem. Aborting.\n", bar); @@ -2195,6 +2197,10 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot( if (host->mmc->caps & MMC_CAP_CD_WAKE) device_init_wakeup(&pdev->dev, true); + if (device_property_read_u32(&pdev->dev, "cd-debounce-delay-ms", + &cd_debounce_delay_ms)) + cd_debounce_delay_ms = 200; + if (slot->cd_idx >= 0) { struct gpiod_lookup_table *cd_gpio_lookup_table; @@ -2213,7 +2219,7 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot( ret = mmc_gpiod_request_cd(host->mmc, NULL, slot->cd_idx, slot->cd_override_level, - 0); + cd_debounce_delay_ms * 1000); if (ret == -EPROBE_DEFER) goto remove; @@ -2221,6 +2227,16 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot( dev_warn(&pdev->dev, "failed to setup card detect gpio\n"); slot->cd_idx = -1; } + } else if (is_of_node(pdev->dev.fwnode)) { + /* Allow all OF systems to use a CD GPIO if provided */ + + ret = mmc_gpiod_request_cd(host->mmc, "cd", 0, + slot->cd_override_level, + cd_debounce_delay_ms * 1000); + if (ret == -EPROBE_DEFER) + goto remove; + else if (ret == 0) + slot->cd_idx = 0; } if (chip->fixes && chip->fixes->add_host) diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c index b0f91cc9e40e43..740ec79bf0cdb1 100644 --- a/drivers/mmc/host/sdhci-pci-gli.c +++ b/drivers/mmc/host/sdhci-pci-gli.c @@ -2037,7 +2037,8 @@ static const struct sdhci_ops sdhci_gl9755_ops = { const struct sdhci_pci_fixes sdhci_gl9755 = { .quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC, - .quirks2 = SDHCI_QUIRK2_BROKEN_DDR50, + // disable non-working UHS-II mode on apple silicon devices + .quirks2 = SDHCI_QUIRK2_BROKEN_DDR50 | SDHCI_QUIRK2_BROKEN_UHS2, .probe_slot = gli_probe_slot_gl9755, .add_host = sdhci_pci_uhs2_add_host, .remove_host = sdhci_pci_uhs2_remove_host, diff --git a/drivers/mmc/host/sdhci-uhs2.c b/drivers/mmc/host/sdhci-uhs2.c index c459a08d01da52..c7c75d21973234 100644 --- a/drivers/mmc/host/sdhci-uhs2.c +++ b/drivers/mmc/host/sdhci-uhs2.c @@ -1163,7 +1163,8 @@ static void __sdhci_uhs2_add_host_v4(struct sdhci_host *host, u32 caps1) mmc = host->mmc; /* Support UHS2 */ - if (caps1 & SDHCI_SUPPORT_UHS2) + if ((caps1 & SDHCI_SUPPORT_UHS2) && + !(host->quirks2 & SDHCI_QUIRK2_BROKEN_UHS2)) mmc->caps2 |= MMC_CAP2_SD_UHS2; max_current_caps2 = sdhci_readl(host, SDHCI_MAX_CURRENT_1); diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index b6a571d866fa53..d4d520a017b177 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -537,6 +537,8 @@ struct sdhci_host { /* Issue CMD and DATA reset together */ #define SDHCI_QUIRK2_ISSUE_CMD_DAT_RESET_TOGETHER (1<<19) +#define SDHCI_QUIRK2_BROKEN_UHS2 (1<<27) + int irq; /* Device IRQ */ void __iomem *ioaddr; /* Mapped address */ phys_addr_t mapbase; /* physical address base */ diff --git a/drivers/mtd/devices/mtd_intel_dg.c b/drivers/mtd/devices/mtd_intel_dg.c index b438ee5aacc34a..114e69135b8d93 100644 --- a/drivers/mtd/devices/mtd_intel_dg.c +++ b/drivers/mtd/devices/mtd_intel_dg.c @@ -738,6 +738,7 @@ static int intel_dg_mtd_probe(struct auxiliary_device *aux_dev, kref_init(&nvm->refcnt); mutex_init(&nvm->lock); + nvm->nregions = nregions; for (n = 0, i = 0; i < INTEL_DG_NVM_REGIONS; i++) { if (!invm->regions[i].name) @@ -745,13 +746,15 @@ static int intel_dg_mtd_probe(struct auxiliary_device *aux_dev, char *name = kasprintf(GFP_KERNEL, "%s.%s", dev_name(&aux_dev->dev), invm->regions[i].name); - if (!name) - continue; + if (!name) { + ret = -ENOMEM; + goto err; + } + nvm->regions[n].name = name; nvm->regions[n].id = i; n++; } - nvm->nregions = n; /* in case where kasprintf fail */ nvm->base = devm_ioremap_resource(device, &invm->bar); if (IS_ERR(nvm->base)) { diff --git a/drivers/mtd/lpddr/lpddr_cmds.c b/drivers/mtd/lpddr/lpddr_cmds.c index 290fd0119e9841..cd37d58abacb75 100644 --- a/drivers/mtd/lpddr/lpddr_cmds.c +++ b/drivers/mtd/lpddr/lpddr_cmds.c @@ -79,7 +79,7 @@ struct mtd_info *lpddr_cmdset(struct map_info *map) mutex_init(&shared[i].lock); for (j = 0; j < lpddr->qinfo->HWPartsNum; j++) { *chip = lpddr->chips[i]; - chip->start += j << lpddr->chipshift; + chip->start += (unsigned long)j << lpddr->chipshift; chip->oldstate = chip->state = FL_READY; chip->priv = &shared[i]; /* those should be reset too since @@ -559,7 +559,7 @@ static int lpddr_point(struct mtd_info *mtd, loff_t adr, size_t len, break; if ((len + ofs - 1) >> lpddr->chipshift) - thislen = (1<chipshift) - ofs; + thislen = (1UL << lpddr->chipshift) - ofs; else thislen = len; /* get the chip */ @@ -575,7 +575,7 @@ static int lpddr_point(struct mtd_info *mtd, loff_t adr, size_t len, len -= thislen; ofs = 0; - last_end += 1 << lpddr->chipshift; + last_end += 1UL << lpddr->chipshift; chipnum++; chip = &lpddr->chips[chipnum]; } @@ -601,7 +601,7 @@ static int lpddr_unpoint (struct mtd_info *mtd, loff_t adr, size_t len) break; if ((len + ofs - 1) >> lpddr->chipshift) - thislen = (1<chipshift) - ofs; + thislen = (1UL << lpddr->chipshift) - ofs; else thislen = len; diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 994e8c51e67438..2876501a781457 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -425,9 +425,12 @@ int add_mtd_partitions(struct mtd_info *parent, mtd_add_partition_attrs(child); - /* Look for subpartitions */ + /* Look for subpartitions (skip if no maching parser found) */ ret = parse_mtd_partitions(child, parts[i].types, NULL); - if (ret < 0) { + if (ret < 0 && ret == -ENOENT) { + pr_debug("Skip parsing subpartitions: %d\n", ret); + continue; + } else if (ret < 0) { pr_err("Failed to parse subpartitions: %d\n", ret); goto err_del_partitions; } diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c index 32ed38b8939478..21eabedc2ed1c6 100644 --- a/drivers/mtd/nand/raw/cadence-nand-controller.c +++ b/drivers/mtd/nand/raw/cadence-nand-controller.c @@ -1015,7 +1015,7 @@ static int cadence_nand_cdma_send(struct cdns_nand_ctrl *cdns_ctrl, } /* Send SDMA command and wait for finish. */ -static u32 +static int cadence_nand_cdma_send_and_wait(struct cdns_nand_ctrl *cdns_ctrl, u8 thread) { diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c index b54d76547ffb29..fea3705a21386c 100644 --- a/drivers/mtd/nand/raw/lpc32xx_slc.c +++ b/drivers/mtd/nand/raw/lpc32xx_slc.c @@ -937,6 +937,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) dma_release_channel(host->dma_chan); enable_wp: lpc32xx_wp_enable(host); + gpiod_put(host->wp_gpio); return res; } @@ -962,6 +963,7 @@ static void lpc32xx_nand_remove(struct platform_device *pdev) writel(tmp, SLC_CTRL(host->io_base)); lpc32xx_wp_enable(host); + gpiod_put(host->wp_gpio); } static int lpc32xx_nand_resume(struct platform_device *pdev) diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index 303b3016a070bd..38b7eb5b992c85 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -290,13 +290,16 @@ static const struct marvell_hw_ecc_layout marvell_nfc_layouts[] = { MARVELL_LAYOUT( 2048, 512, 4, 1, 1, 2048, 32, 30, 0, 0, 0), MARVELL_LAYOUT( 2048, 512, 8, 2, 1, 1024, 0, 30,1024,32, 30), MARVELL_LAYOUT( 2048, 512, 8, 2, 1, 1024, 0, 30,1024,64, 30), - MARVELL_LAYOUT( 2048, 512, 16, 4, 4, 512, 0, 30, 0, 32, 30), + MARVELL_LAYOUT( 2048, 512, 12, 3, 2, 704, 0, 30,640, 0, 30), + MARVELL_LAYOUT( 2048, 512, 16, 5, 4, 512, 0, 30, 0, 32, 30), MARVELL_LAYOUT( 4096, 512, 4, 2, 2, 2048, 32, 30, 0, 0, 0), - MARVELL_LAYOUT( 4096, 512, 8, 4, 4, 1024, 0, 30, 0, 64, 30), - MARVELL_LAYOUT( 4096, 512, 16, 8, 8, 512, 0, 30, 0, 32, 30), + MARVELL_LAYOUT( 4096, 512, 8, 5, 4, 1024, 0, 30, 0, 64, 30), + MARVELL_LAYOUT( 4096, 512, 12, 6, 5, 704, 0, 30,576, 32, 30), + MARVELL_LAYOUT( 4096, 512, 16, 9, 8, 512, 0, 30, 0, 32, 30), MARVELL_LAYOUT( 8192, 512, 4, 4, 4, 2048, 0, 30, 0, 0, 0), - MARVELL_LAYOUT( 8192, 512, 8, 8, 8, 1024, 0, 30, 0, 160, 30), - MARVELL_LAYOUT( 8192, 512, 16, 16, 16, 512, 0, 30, 0, 32, 30), + MARVELL_LAYOUT( 8192, 512, 8, 9, 8, 1024, 0, 30, 0, 160, 30), + MARVELL_LAYOUT( 8192, 512, 12, 12, 11, 704, 0, 30,448, 64, 30), + MARVELL_LAYOUT( 8192, 512, 16, 17, 16, 512, 0, 30, 0, 32, 30), }; /** diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index c7d9501f646b36..ad6d66309597b3 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -6338,11 +6338,14 @@ static int nand_scan_tail(struct nand_chip *chip) ecc->steps = mtd->writesize / ecc->size; if (!base->ecc.ctx.nsteps) base->ecc.ctx.nsteps = ecc->steps; - if (ecc->steps * ecc->size != mtd->writesize) { - WARN(1, "Invalid ECC parameters\n"); - ret = -EINVAL; - goto err_nand_manuf_cleanup; - } + + /* + * Validity check: Warn if ECC parameters are not compatible with page size. + * Due to the custom handling of ECC blocks in certain controllers the check + * may result in an expected failure. + */ + if (ecc->steps * ecc->size != mtd->writesize) + pr_warn("ECC parameters may be invalid in reference to underlying NAND chip\n"); if (!ecc->total) { ecc->total = ecc->steps * ecc->bytes; diff --git a/drivers/mtd/nand/raw/renesas-nand-controller.c b/drivers/mtd/nand/raw/renesas-nand-controller.c index ac8c1b80d7be96..201dd62b99905a 100644 --- a/drivers/mtd/nand/raw/renesas-nand-controller.c +++ b/drivers/mtd/nand/raw/renesas-nand-controller.c @@ -1336,7 +1336,10 @@ static int rnandc_probe(struct platform_device *pdev) if (IS_ERR(rnandc->regs)) return PTR_ERR(rnandc->regs); - devm_pm_runtime_enable(&pdev->dev); + ret = devm_pm_runtime_enable(&pdev->dev); + if (ret) + return ret; + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) return ret; diff --git a/drivers/mtd/parsers/ofpart_core.c b/drivers/mtd/parsers/ofpart_core.c index abfa687989182f..09961c6f39496e 100644 --- a/drivers/mtd/parsers/ofpart_core.c +++ b/drivers/mtd/parsers/ofpart_core.c @@ -77,6 +77,7 @@ static int parse_fixed_partitions(struct mtd_info *master, of_id = of_match_node(parse_ofpart_match_table, ofpart_node); if (dedicated && !of_id) { /* The 'partitions' subnode might be used by another parser */ + of_node_put(ofpart_node); return 0; } @@ -91,12 +92,18 @@ static int parse_fixed_partitions(struct mtd_info *master, nr_parts++; } - if (nr_parts == 0) + if (nr_parts == 0) { + if (dedicated) + of_node_put(ofpart_node); return 0; + } parts = kcalloc(nr_parts, sizeof(*parts), GFP_KERNEL); - if (!parts) + if (!parts) { + if (dedicated) + of_node_put(ofpart_node); return -ENOMEM; + } i = 0; for_each_child_of_node(ofpart_node, pp) { @@ -175,6 +182,9 @@ static int parse_fixed_partitions(struct mtd_info *master, if (quirks && quirks->post_parse) quirks->post_parse(master, parts, nr_parts); + if (dedicated) + of_node_put(ofpart_node); + *pparts = parts; return nr_parts; @@ -183,6 +193,8 @@ static int parse_fixed_partitions(struct mtd_info *master, master->name, pp, mtd_node); ret = -EINVAL; ofpart_none: + if (dedicated) + of_node_put(ofpart_node); of_node_put(pp); kfree(parts); return ret; diff --git a/drivers/mtd/parsers/tplink_safeloader.c b/drivers/mtd/parsers/tplink_safeloader.c index e358a029dc70cf..4fcaf92d22e4fe 100644 --- a/drivers/mtd/parsers/tplink_safeloader.c +++ b/drivers/mtd/parsers/tplink_safeloader.c @@ -116,6 +116,7 @@ static int mtd_parser_tplink_safeloader_parse(struct mtd_info *mtd, return idx; err_free: + kfree(buf); for (idx -= 1; idx >= 0; idx--) kfree(parts[idx].name); err_free_parts: diff --git a/drivers/mtd/spi-nor/winbond.c b/drivers/mtd/spi-nor/winbond.c index 63a93c9eb9174b..fb855fe44733db 100644 --- a/drivers/mtd/spi-nor/winbond.c +++ b/drivers/mtd/spi-nor/winbond.c @@ -343,6 +343,30 @@ static const struct flash_info winbond_nor_parts[] = { .id = SNOR_ID(0xef, 0x80, 0x20), .name = "w25q512nwm", .otp = SNOR_OTP(256, 3, 0x1000, 0x1000), + }, { + /* W25Q01NWxxIQ */ + .id = SNOR_ID(0xef, 0x60, 0x21), + .flags = SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB | SPI_NOR_TB_SR_BIT6 | SPI_NOR_4BIT_BP, + }, { + /* W25Q01NWxxIM */ + .id = SNOR_ID(0xef, 0x80, 0x21), + .flags = SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB | SPI_NOR_TB_SR_BIT6 | SPI_NOR_4BIT_BP, + }, { + /* W25Q02NWxxIM */ + .id = SNOR_ID(0xef, 0x80, 0x22), + .flags = SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB | SPI_NOR_TB_SR_BIT6 | SPI_NOR_4BIT_BP, + }, { + /* W25H512NWxxAM */ + .id = SNOR_ID(0xef, 0xa0, 0x20), + .flags = SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB | SPI_NOR_TB_SR_BIT6 | SPI_NOR_4BIT_BP, + }, { + /* W25H01NWxxAM */ + .id = SNOR_ID(0xef, 0xa0, 0x21), + .flags = SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB | SPI_NOR_TB_SR_BIT6 | SPI_NOR_4BIT_BP, + }, { + /* W25H02NWxxAM */ + .id = SNOR_ID(0xef, 0xa0, 0x22), + .flags = SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB | SPI_NOR_TB_SR_BIT6 | SPI_NOR_4BIT_BP, }, }; diff --git a/drivers/mux/Kconfig b/drivers/mux/Kconfig index c68132e38138ef..281d3bad07448f 100644 --- a/drivers/mux/Kconfig +++ b/drivers/mux/Kconfig @@ -31,6 +31,19 @@ config MUX_ADGS1408 To compile the driver as a module, choose M here: the module will be called mux-adgs1408. +config MUX_APPLE_DPXBAR + tristate "Apple Silicon Display Crossbar" + depends on ARCH_APPLE + help + Apple Silicon Display Crossbar multiplexer. + + This drivers adds support for the display crossbar used to route + display controller streams to the three different modes + (DP AltMode, USB4 Tunnel #0/#1) of the Type-C ports. + + To compile this driver as a module, chose M here: the module will be + called mux-apple-display-crossbar. + config MUX_GPIO tristate "GPIO-controlled Multiplexer" depends on GPIOLIB || COMPILE_TEST diff --git a/drivers/mux/Makefile b/drivers/mux/Makefile index 6e9fa47daf5663..7b5b3325068010 100644 --- a/drivers/mux/Makefile +++ b/drivers/mux/Makefile @@ -8,9 +8,11 @@ mux-adg792a-objs := adg792a.o mux-adgs1408-objs := adgs1408.o mux-gpio-objs := gpio.o mux-mmio-objs := mmio.o +mux-apple-display-crossbar-objs := apple-display-crossbar.o obj-$(CONFIG_MULTIPLEXER) += mux-core.o obj-$(CONFIG_MUX_ADG792A) += mux-adg792a.o obj-$(CONFIG_MUX_ADGS1408) += mux-adgs1408.o +obj-$(CONFIG_MUX_APPLE_DPXBAR) += mux-apple-display-crossbar.o obj-$(CONFIG_MUX_GPIO) += mux-gpio.o obj-$(CONFIG_MUX_MMIO) += mux-mmio.o diff --git a/drivers/mux/apple-display-crossbar.c b/drivers/mux/apple-display-crossbar.c new file mode 100644 index 00000000000000..9b17371d92c3ba --- /dev/null +++ b/drivers/mux/apple-display-crossbar.c @@ -0,0 +1,463 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Apple Silicon Display Crossbar multiplexer driver + * + * Copyright (C) Asahi Linux Contributors + * + * Author: Sven Peter + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * T602x register interface is cleary different so most of the names below are + * probably wrong. + */ + +#define T602X_FIFO_WR_DPTX_CLK_EN 0x000 +#define T602X_FIFO_WR_N_CLK_EN 0x004 +#define T602X_FIFO_WR_UNK_EN 0x008 +#define T602X_REG_00C 0x00c +#define T602X_REG_014 0x014 +#define T602X_REG_018 0x018 +#define T602X_REG_01C 0x01c +#define T602X_FIFO_RD_PCLK2_EN 0x024 +#define T602X_FIFO_RD_N_CLK_EN 0x028 +#define T602X_FIFO_RD_UNK_EN 0x02c +#define T602X_REG_030 0x030 +#define T602X_REG_034 0x034 + +#define T602X_REG_804_STAT 0x804 // status of 0x004 +#define T602X_REG_810_STAT 0x810 // status of 0x014 +#define T602X_REG_81C_STAT 0x81c // status of 0x024 + +/* + * T8013, T600x, T8112 dp crossbar registers. + */ + +#define FIFO_WR_DPTX_CLK_EN 0x000 +#define FIFO_WR_N_CLK_EN 0x004 +#define FIFO_WR_UNK_EN 0x008 +#define FIFO_RD_PCLK1_EN 0x020 +#define FIFO_RD_PCLK2_EN 0x024 +#define FIFO_RD_N_CLK_EN 0x028 +#define FIFO_RD_UNK_EN 0x02c + +#define OUT_PCLK1_EN 0x040 +#define OUT_PCLK2_EN 0x044 +#define OUT_N_CLK_EN 0x048 +#define OUT_UNK_EN 0x04c + +#define CROSSBAR_DISPEXT_EN 0x050 +#define CROSSBAR_MUX_CTRL 0x060 +#define CROSSBAR_MUX_CTRL_DPPHY_SELECT0 GENMASK(23, 20) +#define CROSSBAR_MUX_CTRL_DPIN1_SELECT0 GENMASK(19, 16) +#define CROSSBAR_MUX_CTRL_DPIN0_SELECT0 GENMASK(15, 12) +#define CROSSBAR_MUX_CTRL_DPPHY_SELECT1 GENMASK(11, 8) +#define CROSSBAR_MUX_CTRL_DPIN1_SELECT1 GENMASK(7, 4) +#define CROSSBAR_MUX_CTRL_DPIN0_SELECT1 GENMASK(3, 0) +#define CROSSBAR_ATC_EN 0x070 + +#define FIFO_WR_DPTX_CLK_EN_STAT 0x800 +#define FIFO_WR_N_CLK_EN_STAT 0x804 +#define FIFO_RD_PCLK1_EN_STAT 0x820 +#define FIFO_RD_PCLK2_EN_STAT 0x824 +#define FIFO_RD_N_CLK_EN_STAT 0x828 + +#define OUT_PCLK1_EN_STAT 0x840 +#define OUT_PCLK2_EN_STAT 0x844 +#define OUT_N_CLK_EN_STAT 0x848 + +#define UNK_TUNABLE 0xc00 + +#define ATC_DPIN0 BIT(0) +#define ATC_DPIN1 BIT(4) +#define ATC_DPPHY BIT(8) + +enum { MUX_DPPHY = 0, MUX_DPIN0 = 1, MUX_DPIN1 = 2, MUX_MAX = 3 }; +static const char *apple_dpxbar_names[MUX_MAX] = { "dpphy", "dpin0", "dpin1" }; + +struct apple_dpxbar_hw { + unsigned int n_ufp; + u32 tunable; + const struct mux_control_ops *ops; +}; + +struct apple_dpxbar { + struct device *dev; + void __iomem *regs; + int selected_dispext[MUX_MAX]; + spinlock_t lock; +}; + +static inline void dpxbar_mask32(struct apple_dpxbar *xbar, u32 reg, u32 mask, + u32 set) +{ + u32 value = readl(xbar->regs + reg); + value &= ~mask; + value |= set; + writel(value, xbar->regs + reg); +} + +static inline void dpxbar_set32(struct apple_dpxbar *xbar, u32 reg, u32 set) +{ + dpxbar_mask32(xbar, reg, 0, set); +} + +static inline void dpxbar_clear32(struct apple_dpxbar *xbar, u32 reg, u32 clear) +{ + dpxbar_mask32(xbar, reg, clear, 0); +} + +static int apple_dpxbar_set_t602x(struct mux_control *mux, int state) +{ + struct apple_dpxbar *dpxbar = mux_chip_priv(mux->chip); + unsigned int index = mux_control_get_index(mux); + unsigned long flags; + unsigned int mux_state; + unsigned int dispext_bit; + unsigned int dispext_bit_en; + bool enable; + int ret = 0; + + if (state == MUX_IDLE_DISCONNECT) { + /* + * Technically this will select dispext0,0 in the mux control + * register. Practically that doesn't matter since everything + * else is disabled. + */ + mux_state = 0; + enable = false; + } else if (state >= 0 && state < 9) { + dispext_bit = 1 << state; + dispext_bit_en = 1 << (2 * state); + mux_state = state; + enable = true; + } else { + return -EINVAL; + } + + spin_lock_irqsave(&dpxbar->lock, flags); + + /* ensure the selected dispext isn't already used in this crossbar */ + if (enable) { + for (int i = 0; i < MUX_MAX; ++i) { + if (i == index) + continue; + if (dpxbar->selected_dispext[i] == state) { + spin_unlock_irqrestore(&dpxbar->lock, flags); + return -EBUSY; + } + } + } + + if (dpxbar->selected_dispext[index] >= 0) { + u32 prev_dispext_bit = 1 << dpxbar->selected_dispext[index]; + u32 prev_dispext_bit_en = 1 << (2 * dpxbar->selected_dispext[index]); + + dpxbar_clear32(dpxbar, T602X_FIFO_RD_UNK_EN, prev_dispext_bit); + dpxbar_clear32(dpxbar, T602X_FIFO_WR_DPTX_CLK_EN, prev_dispext_bit); + dpxbar_clear32(dpxbar, T602X_REG_00C, prev_dispext_bit_en); + + dpxbar_clear32(dpxbar, T602X_REG_01C, 0x100); + + dpxbar_clear32(dpxbar, T602X_FIFO_WR_UNK_EN, prev_dispext_bit); + dpxbar_clear32(dpxbar, T602X_REG_018, prev_dispext_bit_en); + + dpxbar_clear32(dpxbar, T602X_FIFO_RD_N_CLK_EN, 0x100); + + dpxbar_set32(dpxbar, T602X_FIFO_WR_N_CLK_EN, prev_dispext_bit); + dpxbar_set32(dpxbar, T602X_REG_014, 0x4); + + dpxbar_set32(dpxbar, FIFO_RD_PCLK1_EN, 0x100); + + dpxbar->selected_dispext[index] = -1; + } + + if (enable) { + dpxbar_set32(dpxbar, T602X_REG_030, state << 20); + dpxbar_set32(dpxbar, T602X_REG_030, state << 8); + udelay(10); + + dpxbar_clear32(dpxbar, T602X_FIFO_WR_N_CLK_EN, dispext_bit); + dpxbar_clear32(dpxbar, T602X_REG_014, 0x4); + + dpxbar_clear32(dpxbar, T602X_FIFO_RD_PCLK2_EN, 0x100); + + dpxbar_set32(dpxbar, T602X_FIFO_WR_UNK_EN, dispext_bit); + dpxbar_set32(dpxbar, T602X_REG_018, dispext_bit_en); + + dpxbar_set32(dpxbar, T602X_FIFO_RD_N_CLK_EN, 0x100); + dpxbar_set32(dpxbar, T602X_FIFO_WR_DPTX_CLK_EN, dispext_bit); + dpxbar_set32(dpxbar, T602X_REG_00C, dispext_bit); + + dpxbar_set32(dpxbar, T602X_REG_01C, 0x100); + dpxbar_set32(dpxbar, T602X_REG_034, 0x100); + + dpxbar_set32(dpxbar, T602X_FIFO_RD_UNK_EN, dispext_bit); + + dpxbar->selected_dispext[index] = state; + } + + spin_unlock_irqrestore(&dpxbar->lock, flags); + + if (enable) + dev_info(dpxbar->dev, "Switched %s to dispext%u,%u\n", + apple_dpxbar_names[index], mux_state >> 1, + mux_state & 1); + else + dev_info(dpxbar->dev, "Switched %s to disconnected state\n", + apple_dpxbar_names[index]); + + return ret; +} + +static int apple_dpxbar_set(struct mux_control *mux, int state) +{ + struct apple_dpxbar *dpxbar = mux_chip_priv(mux->chip); + unsigned int index = mux_control_get_index(mux); + unsigned long flags; + unsigned int mux_state; + unsigned int dispext_bit; + unsigned int dispext_bit_en; + unsigned int atc_bit; + bool enable; + int ret = 0; + u32 mux_mask, mux_set; + + if (state == MUX_IDLE_DISCONNECT) { + /* + * Technically this will select dispext0,0 in the mux control + * register. Practically that doesn't matter since everything + * else is disabled. + */ + mux_state = 0; + enable = false; + } else if (state >= 0 && state < 9) { + dispext_bit = 1 << state; + dispext_bit_en = 1 << (2 * state); + mux_state = state; + enable = true; + } else { + return -EINVAL; + } + + switch (index) { + case MUX_DPPHY: + mux_mask = CROSSBAR_MUX_CTRL_DPPHY_SELECT0 | + CROSSBAR_MUX_CTRL_DPPHY_SELECT1; + mux_set = + FIELD_PREP(CROSSBAR_MUX_CTRL_DPPHY_SELECT0, mux_state) | + FIELD_PREP(CROSSBAR_MUX_CTRL_DPPHY_SELECT1, mux_state); + atc_bit = ATC_DPPHY; + break; + case MUX_DPIN0: + mux_mask = CROSSBAR_MUX_CTRL_DPIN0_SELECT0 | + CROSSBAR_MUX_CTRL_DPIN0_SELECT1; + mux_set = + FIELD_PREP(CROSSBAR_MUX_CTRL_DPIN0_SELECT0, mux_state) | + FIELD_PREP(CROSSBAR_MUX_CTRL_DPIN0_SELECT1, mux_state); + atc_bit = ATC_DPIN0; + break; + case MUX_DPIN1: + mux_mask = CROSSBAR_MUX_CTRL_DPIN1_SELECT0 | + CROSSBAR_MUX_CTRL_DPIN1_SELECT1; + mux_set = + FIELD_PREP(CROSSBAR_MUX_CTRL_DPIN1_SELECT0, mux_state) | + FIELD_PREP(CROSSBAR_MUX_CTRL_DPIN1_SELECT1, mux_state); + atc_bit = ATC_DPIN1; + break; + default: + return -EINVAL; + } + + spin_lock_irqsave(&dpxbar->lock, flags); + + /* ensure the selected dispext isn't already used in this crossbar */ + if (enable) { + for (int i = 0; i < MUX_MAX; ++i) { + if (i == index) + continue; + if (dpxbar->selected_dispext[i] == state) { + spin_unlock_irqrestore(&dpxbar->lock, flags); + return -EBUSY; + } + } + } + + dpxbar_set32(dpxbar, OUT_N_CLK_EN, atc_bit); + dpxbar_clear32(dpxbar, OUT_UNK_EN, atc_bit); + dpxbar_clear32(dpxbar, OUT_PCLK1_EN, atc_bit); + dpxbar_clear32(dpxbar, CROSSBAR_ATC_EN, atc_bit); + + if (dpxbar->selected_dispext[index] >= 0) { + u32 prev_dispext_bit = 1 << dpxbar->selected_dispext[index]; + u32 prev_dispext_bit_en = 1 << (2 * dpxbar->selected_dispext[index]); + + dpxbar_set32(dpxbar, FIFO_WR_N_CLK_EN, prev_dispext_bit); + dpxbar_set32(dpxbar, FIFO_RD_N_CLK_EN, prev_dispext_bit); + dpxbar_clear32(dpxbar, FIFO_WR_UNK_EN, prev_dispext_bit); + dpxbar_clear32(dpxbar, FIFO_RD_UNK_EN, prev_dispext_bit_en); + dpxbar_clear32(dpxbar, FIFO_WR_DPTX_CLK_EN, prev_dispext_bit); + dpxbar_clear32(dpxbar, FIFO_RD_PCLK1_EN, prev_dispext_bit); + dpxbar_clear32(dpxbar, CROSSBAR_DISPEXT_EN, prev_dispext_bit); + + dpxbar->selected_dispext[index] = -1; + } + + dpxbar_mask32(dpxbar, CROSSBAR_MUX_CTRL, mux_mask, mux_set); + + if (enable) { + dpxbar_clear32(dpxbar, FIFO_WR_N_CLK_EN, dispext_bit); + dpxbar_clear32(dpxbar, FIFO_RD_N_CLK_EN, dispext_bit); + dpxbar_clear32(dpxbar, OUT_N_CLK_EN, atc_bit); + dpxbar_set32(dpxbar, FIFO_WR_UNK_EN, dispext_bit); + dpxbar_set32(dpxbar, FIFO_RD_UNK_EN, dispext_bit_en); + dpxbar_set32(dpxbar, OUT_UNK_EN, atc_bit); + dpxbar_set32(dpxbar, FIFO_WR_DPTX_CLK_EN, dispext_bit); + dpxbar_set32(dpxbar, FIFO_RD_PCLK1_EN, dispext_bit); + dpxbar_set32(dpxbar, OUT_PCLK1_EN, atc_bit); + dpxbar_set32(dpxbar, CROSSBAR_ATC_EN, atc_bit); + dpxbar_set32(dpxbar, CROSSBAR_DISPEXT_EN, dispext_bit); + + /* + * Work around some HW quirk: + * Without toggling the RD_PCLK enable here the connection + * doesn't come up. Testing has shown that a delay of about + * 5 usec is required which is doubled here to be on the + * safe side. + */ + dpxbar_clear32(dpxbar, FIFO_RD_PCLK1_EN, dispext_bit); + udelay(10); + dpxbar_set32(dpxbar, FIFO_RD_PCLK1_EN, dispext_bit); + + dpxbar->selected_dispext[index] = state; + } + + spin_unlock_irqrestore(&dpxbar->lock, flags); + + if (enable) + dev_info(dpxbar->dev, "Switched %s to dispext%u,%u\n", + apple_dpxbar_names[index], mux_state >> 1, + mux_state & 1); + else + dev_info(dpxbar->dev, "Switched %s to disconnected state\n", + apple_dpxbar_names[index]); + + return ret; +} + +static const struct mux_control_ops apple_dpxbar_ops = { + .set = apple_dpxbar_set, +}; + +static const struct mux_control_ops apple_dpxbar_t602x_ops = { + .set = apple_dpxbar_set_t602x, +}; + +static int apple_dpxbar_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mux_chip *mux_chip; + struct apple_dpxbar *dpxbar; + const struct apple_dpxbar_hw *hw; + int ret; + + hw = of_device_get_match_data(dev); + mux_chip = devm_mux_chip_alloc(dev, MUX_MAX, sizeof(*dpxbar)); + if (IS_ERR(mux_chip)) + return PTR_ERR(mux_chip); + + dpxbar = mux_chip_priv(mux_chip); + mux_chip->ops = hw->ops; + spin_lock_init(&dpxbar->lock); + + dpxbar->dev = dev; + dpxbar->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(dpxbar->regs)) + return PTR_ERR(dpxbar->regs); + + if (!of_device_is_compatible(dev->of_node, "apple,t6020-display-crossbar")) { + readl(dpxbar->regs + UNK_TUNABLE); + writel(hw->tunable, dpxbar->regs + UNK_TUNABLE); + readl(dpxbar->regs + UNK_TUNABLE); + } + + for (unsigned int i = 0; i < MUX_MAX; ++i) { + mux_chip->mux[i].states = hw->n_ufp; + mux_chip->mux[i].idle_state = MUX_IDLE_DISCONNECT; + dpxbar->selected_dispext[i] = -1; + } + + ret = devm_mux_chip_register(dev, mux_chip); + if (ret < 0) + return ret; + + return 0; +} + +static const struct apple_dpxbar_hw apple_dpxbar_hw_t8103 = { + .n_ufp = 2, + .tunable = 0, + .ops = &apple_dpxbar_ops, +}; + +static const struct apple_dpxbar_hw apple_dpxbar_hw_t8112 = { + .n_ufp = 4, + .tunable = 4278196325, + .ops = &apple_dpxbar_ops, +}; + +static const struct apple_dpxbar_hw apple_dpxbar_hw_t6000 = { + .n_ufp = 9, + .tunable = 5, + .ops = &apple_dpxbar_ops, +}; + +static const struct apple_dpxbar_hw apple_dpxbar_hw_t6020 = { + .n_ufp = 9, + .ops = &apple_dpxbar_t602x_ops, +}; + +static const struct of_device_id apple_dpxbar_ids[] = { + { + .compatible = "apple,t8103-display-crossbar", + .data = &apple_dpxbar_hw_t8103, + }, + { + .compatible = "apple,t8112-display-crossbar", + .data = &apple_dpxbar_hw_t8112, + }, + { + .compatible = "apple,t6000-display-crossbar", + .data = &apple_dpxbar_hw_t6000, + }, + { + .compatible = "apple,t6020-display-crossbar", + .data = &apple_dpxbar_hw_t6020, + }, + {} +}; +MODULE_DEVICE_TABLE(of, apple_dpxbar_ids); + +static struct platform_driver apple_dpxbar_driver = { + .driver = { + .name = "apple-display-crossbar", + .of_match_table = apple_dpxbar_ids, + }, + .probe = apple_dpxbar_probe, +}; +module_platform_driver(apple_dpxbar_driver); + +MODULE_DESCRIPTION("Apple Silicon display crossbar multiplexer driver"); +MODULE_AUTHOR("Sven Peter "); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 5abef8a3b7758e..dba8f68690947c 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -791,26 +791,29 @@ static int bond_update_speed_duplex(struct slave *slave) struct ethtool_link_ksettings ecmd; int res; - slave->speed = SPEED_UNKNOWN; - slave->duplex = DUPLEX_UNKNOWN; - res = __ethtool_get_link_ksettings(slave_dev, &ecmd); if (res < 0) - return 1; + goto speed_duplex_unknown; if (ecmd.base.speed == 0 || ecmd.base.speed == ((__u32)-1)) - return 1; + goto speed_duplex_unknown; switch (ecmd.base.duplex) { case DUPLEX_FULL: case DUPLEX_HALF: break; default: - return 1; + goto speed_duplex_unknown; } slave->speed = ecmd.base.speed; slave->duplex = ecmd.base.duplex; return 0; + +speed_duplex_unknown: + slave->speed = SPEED_UNKNOWN; + slave->duplex = DUPLEX_UNKNOWN; + + return 1; } const char *bond_slave_link_status(s8 link) @@ -1953,6 +1956,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, */ if (!bond_has_slaves(bond)) { if (bond_dev->type != slave_dev->type) { + if (slave_dev->type != ARPHRD_ETHER && + BOND_MODE(bond) == BOND_MODE_8023AD) { + SLAVE_NL_ERR(bond_dev, slave_dev, extack, + "8023AD mode requires Ethernet devices"); + return -EINVAL; + } slave_dbg(bond_dev, slave_dev, "change device type from %d to %d\n", bond_dev->type, slave_dev->type); @@ -2287,11 +2296,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, unblock_netpoll_tx(); } - /* broadcast mode uses the all_slaves to loop through slaves. */ - if (bond_mode_can_use_xmit_hash(bond) || - BOND_MODE(bond) == BOND_MODE_BROADCAST) - bond_update_slave_arr(bond, NULL); - if (!slave_dev->netdev_ops->ndo_bpf || !slave_dev->netdev_ops->ndo_xdp_xmit) { if (bond->xdp_prog) { @@ -2325,6 +2329,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, bpf_prog_inc(bond->xdp_prog); } + /* broadcast mode uses the all_slaves to loop through slaves. */ + if (bond_mode_can_use_xmit_hash(bond) || + BOND_MODE(bond) == BOND_MODE_BROADCAST) + bond_update_slave_arr(bond, NULL); + bond_xdp_set_features(bond_dev); slave_info(bond_dev, slave_dev, "Enslaving as %s interface with %s link\n", @@ -3132,8 +3141,8 @@ static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 __func__, &sip); return; } - slave->last_rx = jiffies; - slave->target_last_arp_rx[i] = jiffies; + WRITE_ONCE(slave->last_rx, jiffies); + WRITE_ONCE(slave->target_last_arp_rx[i], jiffies); } static int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, @@ -3352,8 +3361,8 @@ static void bond_validate_na(struct bonding *bond, struct slave *slave, __func__, saddr); return; } - slave->last_rx = jiffies; - slave->target_last_arp_rx[i] = jiffies; + WRITE_ONCE(slave->last_rx, jiffies); + WRITE_ONCE(slave->target_last_arp_rx[i], jiffies); } static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, @@ -3423,7 +3432,7 @@ int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, (slave_do_arp_validate_only(bond) && is_ipv6) || #endif !slave_do_arp_validate_only(bond)) - slave->last_rx = jiffies; + WRITE_ONCE(slave->last_rx, jiffies); return RX_HANDLER_ANOTHER; } else if (is_arp) { return bond_arp_rcv(skb, bond, slave); @@ -3491,7 +3500,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) if (slave->link != BOND_LINK_UP) { if (bond_time_in_interval(bond, last_tx, 1) && - bond_time_in_interval(bond, slave->last_rx, 1)) { + bond_time_in_interval(bond, READ_ONCE(slave->last_rx), 1)) { bond_propose_link_state(slave, BOND_LINK_UP); slave_state_changed = 1; @@ -3515,8 +3524,10 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) * when the source ip is 0, so don't take the link down * if we don't know our ip yet */ - if (!bond_time_in_interval(bond, last_tx, bond->params.missed_max) || - !bond_time_in_interval(bond, slave->last_rx, bond->params.missed_max)) { + if (!bond_time_in_interval(bond, last_tx, + bond->params.missed_max) || + !bond_time_in_interval(bond, READ_ONCE(slave->last_rx), + bond->params.missed_max)) { bond_propose_link_state(slave, BOND_LINK_DOWN); slave_state_changed = 1; @@ -4181,8 +4192,9 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const v case BOND_XMIT_POLICY_ENCAP23: case BOND_XMIT_POLICY_ENCAP34: memset(fk, 0, sizeof(*fk)); - return __skb_flow_dissect(NULL, skb, &flow_keys_bonding, - fk, data, l2_proto, nhoff, hlen, 0); + return __skb_flow_dissect(dev_net(bond->dev), skb, + &flow_keys_bonding, fk, data, + l2_proto, nhoff, hlen, 0); default: break; } @@ -4393,9 +4405,13 @@ static int bond_close(struct net_device *bond_dev) bond_work_cancel_all(bond); bond->send_peer_notif = 0; + WRITE_ONCE(bond->recv_probe, NULL); + + /* Wait for any in-flight RX handlers */ + synchronize_net(); + if (bond_is_lb(bond)) bond_alb_deinitialize(bond); - bond->recv_probe = NULL; if (BOND_MODE(bond) == BOND_MODE_8023AD && bond->params.broadcast_neighbor) diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 384499c869b8da..f1c6e9d8f61671 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1152,7 +1152,7 @@ static void _bond_options_arp_ip_target_set(struct bonding *bond, int slot, if (slot >= 0 && slot < BOND_MAX_ARP_TARGETS) { bond_for_each_slave(bond, slave, iter) - slave->target_last_arp_rx[slot] = last_rx; + WRITE_ONCE(slave->target_last_arp_rx[slot], last_rx); targets[slot] = target; } } @@ -1221,8 +1221,8 @@ static int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target) bond_for_each_slave(bond, slave, iter) { targets_rx = slave->target_last_arp_rx; for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++) - targets_rx[i] = targets_rx[i+1]; - targets_rx[i] = 0; + WRITE_ONCE(targets_rx[i], READ_ONCE(targets_rx[i+1])); + WRITE_ONCE(targets_rx[i], 0); } for (i = ind; (i < BOND_MAX_ARP_TARGETS-1) && targets[i+1]; i++) targets[i] = targets[i+1]; @@ -1377,7 +1377,7 @@ static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot, if (slot >= 0 && slot < BOND_MAX_NS_TARGETS) { bond_for_each_slave(bond, slave, iter) { - slave->target_last_arp_rx[slot] = last_rx; + WRITE_ONCE(slave->target_last_arp_rx[slot], last_rx); slave_set_ns_maddr(bond, slave, target, &targets[slot]); } targets[slot] = *target; diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index c398ac42eae905..b90890030751f1 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -284,6 +284,7 @@ static void ser_release(struct work_struct *work) { struct list_head list; struct ser_device *ser, *tmp; + struct tty_struct *tty; spin_lock(&ser_lock); list_replace_init(&ser_release_list, &list); @@ -292,9 +293,11 @@ static void ser_release(struct work_struct *work) if (!list_empty(&list)) { rtnl_lock(); list_for_each_entry_safe(ser, tmp, &list, node) { + tty = ser->tty; dev_close(ser->dev); unregister_netdevice(ser->dev); debugfs_deinit(ser); + tty_kref_put(tty); } rtnl_unlock(); } @@ -355,8 +358,6 @@ static void ldisc_close(struct tty_struct *tty) { struct ser_device *ser = tty->disc_data; - tty_kref_put(ser->tty); - spin_lock(&ser_lock); list_move(&ser->node, &ser_release_list); spin_unlock(&ser_lock); diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 191707d7e3dac2..d6dcb2be563427 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -1100,7 +1100,7 @@ static int at91_can_probe(struct platform_device *pdev) if (IS_ERR(transceiver)) { err = PTR_ERR(transceiver); dev_err_probe(&pdev->dev, err, "failed to get phy\n"); - goto exit_iounmap; + goto exit_free; } dev->netdev_ops = &at91_netdev_ops; diff --git a/drivers/net/can/ctucanfd/ctucanfd_base.c b/drivers/net/can/ctucanfd/ctucanfd_base.c index 8bd3f0fc385c30..33a5ec43462786 100644 --- a/drivers/net/can/ctucanfd/ctucanfd_base.c +++ b/drivers/net/can/ctucanfd/ctucanfd_base.c @@ -310,7 +310,7 @@ static int ctucan_set_secondary_sample_point(struct net_device *ndev) } ssp_cfg = FIELD_PREP(REG_TRV_DELAY_SSP_OFFSET, ssp_offset); - ssp_cfg |= FIELD_PREP(REG_TRV_DELAY_SSP_SRC, 0x1); + ssp_cfg |= FIELD_PREP(REG_TRV_DELAY_SSP_SRC, 0x0); } ctucan_write32(priv, CTUCANFD_TRV_DELAY, ssp_cfg); diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 5355bac4dccbe0..fac8ac79df59f7 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -486,11 +486,17 @@ static void ems_usb_read_bulk_callback(struct urb *urb) urb->transfer_buffer, RX_BUFFER_SIZE, ems_usb_read_bulk_callback, dev); + usb_anchor_urb(urb, &dev->rx_submitted); + retval = usb_submit_urb(urb, GFP_ATOMIC); + if (!retval) + return; + + usb_unanchor_urb(urb); if (retval == -ENODEV) netif_device_detach(netdev); - else if (retval) + else netdev_err(netdev, "failed resubmitting read bulk urb: %d\n", retval); } diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index 9bc1824d7be6aa..e58f0bfa84a4ca 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -541,13 +541,20 @@ static void esd_usb_read_bulk_callback(struct urb *urb) urb->transfer_buffer, ESD_USB_RX_BUFFER_SIZE, esd_usb_read_bulk_callback, dev); + usb_anchor_urb(urb, &dev->rx_submitted); + err = usb_submit_urb(urb, GFP_ATOMIC); + if (!err) + return; + + usb_unanchor_urb(urb); + if (err == -ENODEV) { for (i = 0; i < dev->net_count; i++) { if (dev->nets[i]) netif_device_detach(dev->nets[i]->netdev); } - } else if (err) { + } else { dev_err(dev->udev->dev.parent, "failed resubmitting read bulk urb: %pe\n", ERR_PTR(err)); } diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c index adc91873c083f9..6eeba9baa13179 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.c +++ b/drivers/net/can/usb/etas_es58x/es58x_core.c @@ -1736,7 +1736,7 @@ static int es58x_alloc_rx_urbs(struct es58x_device *es58x_dev) dev_dbg(dev, "%s: Allocated %d rx URBs each of size %u\n", __func__, i, rx_buf_len); - return ret; + return 0; } /** diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 8d8a610f914411..861b583935225c 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -610,7 +610,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) { struct gs_usb *parent = urb->context; struct gs_can *dev; - struct net_device *netdev; + struct net_device *netdev = NULL; int rc; struct net_device_stats *stats; struct gs_host_frame *hf = urb->transfer_buffer; @@ -751,7 +751,13 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) hf, parent->hf_size_rx, gs_usb_receive_bulk_callback, parent); + usb_anchor_urb(urb, &parent->rx_submitted); + rc = usb_submit_urb(urb, GFP_ATOMIC); + if (!rc) + return; + + usb_unanchor_urb(urb); /* USB failure take down all interfaces */ if (rc == -ENODEV) { @@ -760,6 +766,9 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) if (parent->canch[rc]) netif_device_detach(parent->canch[rc]->netdev); } + } else if (rc != -ESHUTDOWN && net_ratelimit()) { + netdev_info(netdev, "failed to re-submit IN URB: %pe\n", + ERR_PTR(rc)); } } @@ -1074,7 +1083,7 @@ static int gs_can_open(struct net_device *netdev) usb_free_urb(urb); out_usb_kill_anchored_urbs: if (!parent->active_channels) { - usb_kill_anchored_urbs(&dev->tx_submitted); + usb_kill_anchored_urbs(&parent->rx_submitted); if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) gs_usb_timestamp_stop(parent); diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 90e77fa0ff4a58..74aa1712686720 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -361,7 +361,14 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb) urb->transfer_buffer, KVASER_USB_RX_BUFFER_SIZE, kvaser_usb_read_bulk_callback, dev); + usb_anchor_urb(urb, &dev->rx_submitted); + err = usb_submit_urb(urb, GFP_ATOMIC); + if (!err) + return; + + usb_unanchor_urb(urb); + if (err == -ENODEV) { for (i = 0; i < dev->nchannels; i++) { struct kvaser_usb_net_priv *priv; @@ -372,7 +379,7 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb) netif_device_detach(priv->netdev); } - } else if (err) { + } else { dev_err(&dev->intf->dev, "Failed resubmitting read bulk urb: %d\n", err); } diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 1f9b915094e64d..40cc158c1a672f 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -608,11 +608,17 @@ static void mcba_usb_read_bulk_callback(struct urb *urb) urb->transfer_buffer, MCBA_USB_RX_BUFF_SIZE, mcba_usb_read_bulk_callback, priv); + usb_anchor_urb(urb, &priv->rx_submitted); + retval = usb_submit_urb(urb, GFP_ATOMIC); + if (!retval) + return; + + usb_unanchor_urb(urb); if (retval == -ENODEV) netif_device_detach(netdev); - else if (retval) + else netdev_err(netdev, "failed resubmitting read bulk urb: %d\n", retval); } diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index 8a5596ce4e4631..0fedfc287f1f63 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -541,11 +541,17 @@ static void usb_8dev_read_bulk_callback(struct urb *urb) urb->transfer_buffer, RX_BUFFER_SIZE, usb_8dev_read_bulk_callback, priv); + usb_anchor_urb(urb, &priv->rx_submitted); + retval = usb_submit_urb(urb, GFP_ATOMIC); + if (!retval) + return; + + usb_unanchor_urb(urb); if (retval == -ENODEV) netif_device_detach(netdev); - else if (retval) + else netdev_err(netdev, "failed resubmitting read bulk urb: %d\n", retval); } diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index eb767edc4c135b..7d6ec2eb7c75ea 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1830,49 +1830,83 @@ static int b53_arl_rw_op(struct b53_device *dev, unsigned int op) return b53_arl_op_wait(dev); } -static int b53_arl_read(struct b53_device *dev, u64 mac, - u16 vid, struct b53_arl_entry *ent, u8 *idx) +static void b53_arl_read_entry_25(struct b53_device *dev, + struct b53_arl_entry *ent, u8 idx) { - DECLARE_BITMAP(free_bins, B53_ARLTBL_MAX_BIN_ENTRIES); - unsigned int i; - int ret; + u8 vid_entry; + u64 mac_vid; - ret = b53_arl_op_wait(dev); - if (ret) - return ret; + b53_read8(dev, B53_ARLIO_PAGE, B53_ARLTBL_VID_ENTRY_25(idx), + &vid_entry); + b53_read64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx), + &mac_vid); + b53_arl_to_entry_25(ent, mac_vid, vid_entry); +} - bitmap_zero(free_bins, dev->num_arl_bins); +static void b53_arl_write_entry_25(struct b53_device *dev, + const struct b53_arl_entry *ent, u8 idx) +{ + u8 vid_entry; + u64 mac_vid; - /* Read the bins */ - for (i = 0; i < dev->num_arl_bins; i++) { - u64 mac_vid; - u32 fwd_entry; + b53_arl_from_entry_25(&mac_vid, &vid_entry, ent); + b53_write8(dev, B53_ARLIO_PAGE, B53_ARLTBL_VID_ENTRY_25(idx), vid_entry); + b53_write64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx), + mac_vid); +} + +static void b53_arl_read_entry_89(struct b53_device *dev, + struct b53_arl_entry *ent, u8 idx) +{ + u64 mac_vid; + u16 fwd_entry; - b53_read64(dev, B53_ARLIO_PAGE, - B53_ARLTBL_MAC_VID_ENTRY(i), &mac_vid); - b53_read32(dev, B53_ARLIO_PAGE, - B53_ARLTBL_DATA_ENTRY(i), &fwd_entry); - b53_arl_to_entry(ent, mac_vid, fwd_entry); + b53_read64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx), + &mac_vid); + b53_read16(dev, B53_ARLIO_PAGE, B53_ARLTBL_DATA_ENTRY(idx), &fwd_entry); + b53_arl_to_entry_89(ent, mac_vid, fwd_entry); +} - if (!(fwd_entry & ARLTBL_VALID)) { - set_bit(i, free_bins); - continue; - } - if ((mac_vid & ARLTBL_MAC_MASK) != mac) - continue; - if (dev->vlan_enabled && - ((mac_vid >> ARLTBL_VID_S) & ARLTBL_VID_MASK) != vid) - continue; - *idx = i; - return 0; - } +static void b53_arl_write_entry_89(struct b53_device *dev, + const struct b53_arl_entry *ent, u8 idx) +{ + u32 fwd_entry; + u64 mac_vid; - *idx = find_first_bit(free_bins, dev->num_arl_bins); - return *idx >= dev->num_arl_bins ? -ENOSPC : -ENOENT; + b53_arl_from_entry_89(&mac_vid, &fwd_entry, ent); + b53_write64(dev, B53_ARLIO_PAGE, + B53_ARLTBL_MAC_VID_ENTRY(idx), mac_vid); + b53_write16(dev, B53_ARLIO_PAGE, + B53_ARLTBL_DATA_ENTRY(idx), fwd_entry); +} + +static void b53_arl_read_entry_95(struct b53_device *dev, + struct b53_arl_entry *ent, u8 idx) +{ + u32 fwd_entry; + u64 mac_vid; + + b53_read64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx), + &mac_vid); + b53_read32(dev, B53_ARLIO_PAGE, B53_ARLTBL_DATA_ENTRY(idx), &fwd_entry); + b53_arl_to_entry(ent, mac_vid, fwd_entry); } -static int b53_arl_read_25(struct b53_device *dev, u64 mac, - u16 vid, struct b53_arl_entry *ent, u8 *idx) +static void b53_arl_write_entry_95(struct b53_device *dev, + const struct b53_arl_entry *ent, u8 idx) +{ + u32 fwd_entry; + u64 mac_vid; + + b53_arl_from_entry(&mac_vid, &fwd_entry, ent); + b53_write64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx), + mac_vid); + b53_write32(dev, B53_ARLIO_PAGE, B53_ARLTBL_DATA_ENTRY(idx), + fwd_entry); +} + +static int b53_arl_read(struct b53_device *dev, const u8 *mac, + u16 vid, struct b53_arl_entry *ent, u8 *idx) { DECLARE_BITMAP(free_bins, B53_ARLTBL_MAX_BIN_ENTRIES); unsigned int i; @@ -1886,21 +1920,15 @@ static int b53_arl_read_25(struct b53_device *dev, u64 mac, /* Read the bins */ for (i = 0; i < dev->num_arl_bins; i++) { - u64 mac_vid; - - b53_read64(dev, B53_ARLIO_PAGE, - B53_ARLTBL_MAC_VID_ENTRY(i), &mac_vid); + b53_arl_read_entry(dev, ent, i); - b53_arl_to_entry_25(ent, mac_vid); - - if (!(mac_vid & ARLTBL_VALID_25)) { + if (!ent->is_valid) { set_bit(i, free_bins); continue; } - if ((mac_vid & ARLTBL_MAC_MASK) != mac) + if (!ether_addr_equal(ent->mac, mac)) continue; - if (dev->vlan_enabled && - ((mac_vid >> ARLTBL_VID_S_65) & ARLTBL_VID_MASK_25) != vid) + if (dev->vlan_enabled && ent->vid != vid) continue; *idx = i; return 0; @@ -1914,9 +1942,8 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, const unsigned char *addr, u16 vid, bool is_valid) { struct b53_arl_entry ent; - u32 fwd_entry; - u64 mac, mac_vid = 0; u8 idx = 0; + u64 mac; int ret; /* Convert the array into a 64-bit MAC */ @@ -1924,18 +1951,19 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, /* Perform a read for the given MAC and VID */ b53_write48(dev, B53_ARLIO_PAGE, B53_MAC_ADDR_IDX, mac); - if (!is5325m(dev)) - b53_write16(dev, B53_ARLIO_PAGE, B53_VLAN_ID_IDX, vid); + if (!is5325m(dev)) { + if (is5325(dev) || is5365(dev)) + b53_write8(dev, B53_ARLIO_PAGE, B53_VLAN_ID_IDX, vid); + else + b53_write16(dev, B53_ARLIO_PAGE, B53_VLAN_ID_IDX, vid); + } /* Issue a read operation for this MAC */ ret = b53_arl_rw_op(dev, 1); if (ret) return ret; - if (is5325(dev) || is5365(dev)) - ret = b53_arl_read_25(dev, mac, vid, &ent, &idx); - else - ret = b53_arl_read(dev, mac, vid, &ent, &idx); + ret = b53_arl_read(dev, addr, vid, &ent, &idx); /* If this is a read, just finish now */ if (op) @@ -1952,7 +1980,6 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, /* We could not find a matching MAC, so reset to a new entry */ dev_dbg(dev->dev, "{%pM,%.4d} not found, using idx: %d\n", addr, vid, idx); - fwd_entry = 0; break; default: dev_dbg(dev->dev, "{%pM,%.4d} found, using idx: %d\n", @@ -1979,17 +2006,7 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, ent.is_static = true; ent.is_age = false; memcpy(ent.mac, addr, ETH_ALEN); - if (is5325(dev) || is5365(dev)) - b53_arl_from_entry_25(&mac_vid, &ent); - else - b53_arl_from_entry(&mac_vid, &fwd_entry, &ent); - - b53_write64(dev, B53_ARLIO_PAGE, - B53_ARLTBL_MAC_VID_ENTRY(idx), mac_vid); - - if (!is5325(dev) && !is5365(dev)) - b53_write32(dev, B53_ARLIO_PAGE, - B53_ARLTBL_DATA_ENTRY(idx), fwd_entry); + b53_arl_write_entry(dev, &ent, idx); return b53_arl_rw_op(dev, 0); } @@ -2024,18 +2041,53 @@ int b53_fdb_del(struct dsa_switch *ds, int port, } EXPORT_SYMBOL(b53_fdb_del); -static int b53_arl_search_wait(struct b53_device *dev) +static void b53_read_arl_srch_ctl(struct b53_device *dev, u8 *val) { - unsigned int timeout = 1000; - u8 reg, offset; + u8 offset; + + if (is5325(dev) || is5365(dev)) + offset = B53_ARL_SRCH_CTL_25; + else if (dev->chip_id == BCM5389_DEVICE_ID || is5397_98(dev) || + is63xx(dev)) + offset = B53_ARL_SRCH_CTL_89; + else + offset = B53_ARL_SRCH_CTL; + + if (is63xx(dev)) { + u16 val16; + + b53_read16(dev, B53_ARLIO_PAGE, offset, &val16); + *val = val16 & 0xff; + } else { + b53_read8(dev, B53_ARLIO_PAGE, offset, val); + } +} + +static void b53_write_arl_srch_ctl(struct b53_device *dev, u8 val) +{ + u8 offset; if (is5325(dev) || is5365(dev)) offset = B53_ARL_SRCH_CTL_25; + else if (dev->chip_id == BCM5389_DEVICE_ID || is5397_98(dev) || + is63xx(dev)) + offset = B53_ARL_SRCH_CTL_89; else offset = B53_ARL_SRCH_CTL; + if (is63xx(dev)) + b53_write16(dev, B53_ARLIO_PAGE, offset, val); + else + b53_write8(dev, B53_ARLIO_PAGE, offset, val); +} + +static int b53_arl_search_wait(struct b53_device *dev) +{ + unsigned int timeout = 1000; + u8 reg; + do { - b53_read8(dev, B53_ARLIO_PAGE, offset, ®); + b53_read_arl_srch_ctl(dev, ®); if (!(reg & ARL_SRCH_STDN)) return -ENOENT; @@ -2048,28 +2100,53 @@ static int b53_arl_search_wait(struct b53_device *dev) return -ETIMEDOUT; } -static void b53_arl_search_rd(struct b53_device *dev, u8 idx, - struct b53_arl_entry *ent) +static void b53_arl_search_read_25(struct b53_device *dev, u8 idx, + struct b53_arl_entry *ent) { u64 mac_vid; + u8 ext; - if (is5325(dev)) { - b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_0_MACVID_25, - &mac_vid); - b53_arl_to_entry_25(ent, mac_vid); - } else if (is5365(dev)) { - b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_0_MACVID_65, - &mac_vid); - b53_arl_to_entry_25(ent, mac_vid); - } else { - u32 fwd_entry; + b53_read8(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_EXT_25, &ext); + b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_0_MACVID_25, + &mac_vid); + b53_arl_search_to_entry_25(ent, mac_vid, ext); +} - b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_MACVID(idx), - &mac_vid); - b53_read32(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL(idx), - &fwd_entry); - b53_arl_to_entry(ent, mac_vid, fwd_entry); - } +static void b53_arl_search_read_89(struct b53_device *dev, u8 idx, + struct b53_arl_entry *ent) +{ + u16 fwd_entry; + u64 mac_vid; + + b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_MACVID_89, + &mac_vid); + b53_read16(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_89, &fwd_entry); + b53_arl_to_entry_89(ent, mac_vid, fwd_entry); +} + +static void b53_arl_search_read_63xx(struct b53_device *dev, u8 idx, + struct b53_arl_entry *ent) +{ + u16 fwd_entry; + u64 mac_vid; + + b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_MACVID_63XX, + &mac_vid); + b53_read16(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_63XX, &fwd_entry); + b53_arl_search_to_entry_63xx(ent, mac_vid, fwd_entry); +} + +static void b53_arl_search_read_95(struct b53_device *dev, u8 idx, + struct b53_arl_entry *ent) +{ + u32 fwd_entry; + u64 mac_vid; + + b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_MACVID(idx), + &mac_vid); + b53_read32(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL(idx), + &fwd_entry); + b53_arl_to_entry(ent, mac_vid, fwd_entry); } static int b53_fdb_copy(int port, const struct b53_arl_entry *ent, @@ -2078,6 +2155,9 @@ static int b53_fdb_copy(int port, const struct b53_arl_entry *ent, if (!ent->is_valid) return 0; + if (is_multicast_ether_addr(ent->mac)) + return 0; + if (port != ent->port) return 0; @@ -2090,36 +2170,28 @@ int b53_fdb_dump(struct dsa_switch *ds, int port, unsigned int count = 0, results_per_hit = 1; struct b53_device *priv = ds->priv; struct b53_arl_entry results[2]; - u8 offset; int ret; - u8 reg; if (priv->num_arl_bins > 2) results_per_hit = 2; mutex_lock(&priv->arl_mutex); - if (is5325(priv) || is5365(priv)) - offset = B53_ARL_SRCH_CTL_25; - else - offset = B53_ARL_SRCH_CTL; - /* Start search operation */ - reg = ARL_SRCH_STDN; - b53_write8(priv, B53_ARLIO_PAGE, offset, reg); + b53_write_arl_srch_ctl(priv, ARL_SRCH_STDN); do { ret = b53_arl_search_wait(priv); if (ret) break; - b53_arl_search_rd(priv, 0, &results[0]); + b53_arl_search_read(priv, 0, &results[0]); ret = b53_fdb_copy(port, &results[0], cb, data); if (ret) break; if (results_per_hit == 2) { - b53_arl_search_rd(priv, 1, &results[1]); + b53_arl_search_read(priv, 1, &results[1]); ret = b53_fdb_copy(port, &results[1], cb, data); if (ret) break; @@ -2645,6 +2717,30 @@ static const struct dsa_switch_ops b53_switch_ops = { .port_change_mtu = b53_change_mtu, }; +static const struct b53_arl_ops b53_arl_ops_25 = { + .arl_read_entry = b53_arl_read_entry_25, + .arl_write_entry = b53_arl_write_entry_25, + .arl_search_read = b53_arl_search_read_25, +}; + +static const struct b53_arl_ops b53_arl_ops_89 = { + .arl_read_entry = b53_arl_read_entry_89, + .arl_write_entry = b53_arl_write_entry_89, + .arl_search_read = b53_arl_search_read_89, +}; + +static const struct b53_arl_ops b53_arl_ops_63xx = { + .arl_read_entry = b53_arl_read_entry_89, + .arl_write_entry = b53_arl_write_entry_89, + .arl_search_read = b53_arl_search_read_63xx, +}; + +static const struct b53_arl_ops b53_arl_ops_95 = { + .arl_read_entry = b53_arl_read_entry_95, + .arl_write_entry = b53_arl_write_entry_95, + .arl_search_read = b53_arl_search_read_95, +}; + struct b53_chip_data { u32 chip_id; const char *dev_name; @@ -2658,6 +2754,7 @@ struct b53_chip_data { u8 duplex_reg; u8 jumbo_pm_reg; u8 jumbo_size_reg; + const struct b53_arl_ops *arl_ops; }; #define B53_VTA_REGS \ @@ -2677,6 +2774,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .arl_buckets = 1024, .imp_port = 5, .duplex_reg = B53_DUPLEX_STAT_FE, + .arl_ops = &b53_arl_ops_25, }, { .chip_id = BCM5365_DEVICE_ID, @@ -2687,6 +2785,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .arl_buckets = 1024, .imp_port = 5, .duplex_reg = B53_DUPLEX_STAT_FE, + .arl_ops = &b53_arl_ops_25, }, { .chip_id = BCM5389_DEVICE_ID, @@ -2700,6 +2799,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_89, }, { .chip_id = BCM5395_DEVICE_ID, @@ -2713,6 +2813,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM5397_DEVICE_ID, @@ -2726,6 +2827,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_89, }, { .chip_id = BCM5398_DEVICE_ID, @@ -2739,6 +2841,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_89, }, { .chip_id = BCM53101_DEVICE_ID, @@ -2752,6 +2855,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53115_DEVICE_ID, @@ -2765,6 +2869,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53125_DEVICE_ID, @@ -2778,6 +2883,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53128_DEVICE_ID, @@ -2791,19 +2897,21 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM63XX_DEVICE_ID, .dev_name = "BCM63xx", .vlans = 4096, .enabled_ports = 0, /* pdata must provide them */ - .arl_bins = 4, - .arl_buckets = 1024, + .arl_bins = 1, + .arl_buckets = 4096, .imp_port = 8, .vta_regs = B53_VTA_REGS_63XX, .duplex_reg = B53_DUPLEX_STAT_63XX, .jumbo_pm_reg = B53_JUMBO_PORT_MASK_63XX, .jumbo_size_reg = B53_JUMBO_MAX_SIZE_63XX, + .arl_ops = &b53_arl_ops_63xx, }, { .chip_id = BCM53010_DEVICE_ID, @@ -2817,6 +2925,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53011_DEVICE_ID, @@ -2830,6 +2939,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53012_DEVICE_ID, @@ -2843,6 +2953,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53018_DEVICE_ID, @@ -2856,6 +2967,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53019_DEVICE_ID, @@ -2869,6 +2981,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM58XX_DEVICE_ID, @@ -2882,6 +2995,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM583XX_DEVICE_ID, @@ -2895,6 +3009,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, /* Starfighter 2 */ { @@ -2909,6 +3024,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM7445_DEVICE_ID, @@ -2922,6 +3038,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM7278_DEVICE_ID, @@ -2935,6 +3052,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53134_DEVICE_ID, @@ -2949,6 +3067,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, }; @@ -2977,6 +3096,7 @@ static int b53_switch_init(struct b53_device *dev) dev->num_vlans = chip->vlans; dev->num_arl_bins = chip->arl_bins; dev->num_arl_buckets = chip->arl_buckets; + dev->arl_ops = chip->arl_ops; break; } } diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 458775f9516437..bd6849e5bb9390 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -58,6 +58,17 @@ struct b53_io_ops { bool link_up); }; +struct b53_arl_entry; + +struct b53_arl_ops { + void (*arl_read_entry)(struct b53_device *dev, + struct b53_arl_entry *ent, u8 idx); + void (*arl_write_entry)(struct b53_device *dev, + const struct b53_arl_entry *ent, u8 idx); + void (*arl_search_read)(struct b53_device *dev, u8 idx, + struct b53_arl_entry *ent); +}; + #define B53_INVALID_LANE 0xff enum { @@ -127,6 +138,7 @@ struct b53_device { struct mutex stats_mutex; struct mutex arl_mutex; const struct b53_io_ops *ops; + const struct b53_arl_ops *arl_ops; /* chip specific data */ u32 chip_id; @@ -329,16 +341,30 @@ static inline void b53_arl_to_entry(struct b53_arl_entry *ent, } static inline void b53_arl_to_entry_25(struct b53_arl_entry *ent, - u64 mac_vid) + u64 mac_vid, u8 vid_entry) { memset(ent, 0, sizeof(*ent)); - ent->port = (mac_vid >> ARLTBL_DATA_PORT_ID_S_25) & - ARLTBL_DATA_PORT_ID_MASK_25; ent->is_valid = !!(mac_vid & ARLTBL_VALID_25); ent->is_age = !!(mac_vid & ARLTBL_AGE_25); ent->is_static = !!(mac_vid & ARLTBL_STATIC_25); u64_to_ether_addr(mac_vid, ent->mac); - ent->vid = mac_vid >> ARLTBL_VID_S_65; + ent->port = (mac_vid & ARLTBL_DATA_PORT_ID_MASK_25) >> + ARLTBL_DATA_PORT_ID_S_25; + if (is_unicast_ether_addr(ent->mac) && ent->port == B53_CPU_PORT) + ent->port = B53_CPU_PORT_25; + ent->vid = vid_entry; +} + +static inline void b53_arl_to_entry_89(struct b53_arl_entry *ent, + u64 mac_vid, u16 fwd_entry) +{ + memset(ent, 0, sizeof(*ent)); + ent->port = fwd_entry & ARLTBL_DATA_PORT_ID_MASK_89; + ent->is_valid = !!(fwd_entry & ARLTBL_VALID_89); + ent->is_age = !!(fwd_entry & ARLTBL_AGE_89); + ent->is_static = !!(fwd_entry & ARLTBL_STATIC_89); + u64_to_ether_addr(mac_vid, ent->mac); + ent->vid = mac_vid >> ARLTBL_VID_S; } static inline void b53_arl_from_entry(u64 *mac_vid, u32 *fwd_entry, @@ -355,20 +381,87 @@ static inline void b53_arl_from_entry(u64 *mac_vid, u32 *fwd_entry, *fwd_entry |= ARLTBL_AGE; } -static inline void b53_arl_from_entry_25(u64 *mac_vid, +static inline void b53_arl_from_entry_25(u64 *mac_vid, u8 *vid_entry, const struct b53_arl_entry *ent) { *mac_vid = ether_addr_to_u64(ent->mac); - *mac_vid |= (u64)(ent->port & ARLTBL_DATA_PORT_ID_MASK_25) << - ARLTBL_DATA_PORT_ID_S_25; - *mac_vid |= (u64)(ent->vid & ARLTBL_VID_MASK_25) << - ARLTBL_VID_S_65; + if (is_unicast_ether_addr(ent->mac) && ent->port == B53_CPU_PORT_25) + *mac_vid |= (u64)B53_CPU_PORT << ARLTBL_DATA_PORT_ID_S_25; + else + *mac_vid |= ((u64)ent->port << ARLTBL_DATA_PORT_ID_S_25) & + ARLTBL_DATA_PORT_ID_MASK_25; if (ent->is_valid) *mac_vid |= ARLTBL_VALID_25; if (ent->is_static) *mac_vid |= ARLTBL_STATIC_25; if (ent->is_age) *mac_vid |= ARLTBL_AGE_25; + *vid_entry = ent->vid; +} + +static inline void b53_arl_from_entry_89(u64 *mac_vid, u32 *fwd_entry, + const struct b53_arl_entry *ent) +{ + *mac_vid = ether_addr_to_u64(ent->mac); + *mac_vid |= (u64)(ent->vid & ARLTBL_VID_MASK) << ARLTBL_VID_S; + *fwd_entry = ent->port & ARLTBL_DATA_PORT_ID_MASK_89; + if (ent->is_valid) + *fwd_entry |= ARLTBL_VALID_89; + if (ent->is_static) + *fwd_entry |= ARLTBL_STATIC_89; + if (ent->is_age) + *fwd_entry |= ARLTBL_AGE_89; +} + +static inline void b53_arl_search_to_entry_25(struct b53_arl_entry *ent, + u64 mac_vid, u8 ext) +{ + memset(ent, 0, sizeof(*ent)); + ent->is_valid = !!(mac_vid & ARLTBL_VALID_25); + ent->is_age = !!(mac_vid & ARLTBL_AGE_25); + ent->is_static = !!(mac_vid & ARLTBL_STATIC_25); + u64_to_ether_addr(mac_vid, ent->mac); + ent->vid = (mac_vid & ARL_SRCH_RSLT_VID_MASK_25) >> + ARL_SRCH_RSLT_VID_S_25; + ent->port = (mac_vid & ARL_SRCH_RSLT_PORT_ID_MASK_25) >> + ARL_SRCH_RSLT_PORT_ID_S_25; + if (is_multicast_ether_addr(ent->mac) && (ext & ARL_SRCH_RSLT_EXT_MC_MII)) + ent->port |= BIT(B53_CPU_PORT_25); + else if (!is_multicast_ether_addr(ent->mac) && ent->port == B53_CPU_PORT) + ent->port = B53_CPU_PORT_25; +} + +static inline void b53_arl_search_to_entry_63xx(struct b53_arl_entry *ent, + u64 mac_vid, u16 fwd_entry) +{ + memset(ent, 0, sizeof(*ent)); + u64_to_ether_addr(mac_vid, ent->mac); + ent->vid = mac_vid >> ARLTBL_VID_S; + + ent->port = fwd_entry & ARL_SRST_PORT_ID_MASK_63XX; + ent->port >>= 1; + + ent->is_age = !!(fwd_entry & ARL_SRST_AGE_63XX); + ent->is_static = !!(fwd_entry & ARL_SRST_STATIC_63XX); + ent->is_valid = 1; +} + +static inline void b53_arl_read_entry(struct b53_device *dev, + struct b53_arl_entry *ent, u8 idx) +{ + dev->arl_ops->arl_read_entry(dev, ent, idx); +} + +static inline void b53_arl_write_entry(struct b53_device *dev, + const struct b53_arl_entry *ent, u8 idx) +{ + dev->arl_ops->arl_write_entry(dev, ent, idx); +} + +static inline void b53_arl_search_read(struct b53_device *dev, u8 idx, + struct b53_arl_entry *ent) +{ + dev->arl_ops->arl_search_read(dev, idx, ent); } #ifdef CONFIG_BCM47XX diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h index 8ce1ce72e93856..b6fe7d207a2c13 100644 --- a/drivers/net/dsa/b53/b53_regs.h +++ b/drivers/net/dsa/b53/b53_regs.h @@ -325,11 +325,9 @@ #define B53_ARLTBL_MAC_VID_ENTRY(n) ((0x10 * (n)) + 0x10) #define ARLTBL_MAC_MASK 0xffffffffffffULL #define ARLTBL_VID_S 48 -#define ARLTBL_VID_MASK_25 0xff #define ARLTBL_VID_MASK 0xfff #define ARLTBL_DATA_PORT_ID_S_25 48 -#define ARLTBL_DATA_PORT_ID_MASK_25 0xf -#define ARLTBL_VID_S_65 53 +#define ARLTBL_DATA_PORT_ID_MASK_25 GENMASK_ULL(53, 48) #define ARLTBL_AGE_25 BIT_ULL(61) #define ARLTBL_STATIC_25 BIT_ULL(62) #define ARLTBL_VALID_25 BIT_ULL(63) @@ -342,12 +340,23 @@ #define ARLTBL_STATIC BIT(15) #define ARLTBL_VALID BIT(16) +/* BCM5389 ARL Table Data Entry N Register format (16 bit) */ +#define ARLTBL_DATA_PORT_ID_MASK_89 GENMASK(8, 0) +#define ARLTBL_TC_MASK_89 GENMASK(12, 10) +#define ARLTBL_AGE_89 BIT(13) +#define ARLTBL_STATIC_89 BIT(14) +#define ARLTBL_VALID_89 BIT(15) + +/* BCM5325/BCM565 ARL Table VID Entry N Registers (8 bit) */ +#define B53_ARLTBL_VID_ENTRY_25(n) ((0x2 * (n)) + 0x30) + /* Maximum number of bin entries in the ARL for all switches */ #define B53_ARLTBL_MAX_BIN_ENTRIES 4 /* ARL Search Control Register (8 bit) */ #define B53_ARL_SRCH_CTL 0x50 #define B53_ARL_SRCH_CTL_25 0x20 +#define B53_ARL_SRCH_CTL_89 0x30 #define ARL_SRCH_VLID BIT(0) #define ARL_SRCH_STDN BIT(7) @@ -355,22 +364,42 @@ #define B53_ARL_SRCH_ADDR 0x51 #define B53_ARL_SRCH_ADDR_25 0x22 #define B53_ARL_SRCH_ADDR_65 0x24 +#define B53_ARL_SRCH_ADDR_89 0x31 +#define B53_ARL_SRCH_ADDR_63XX 0x32 #define ARL_ADDR_MASK GENMASK(14, 0) /* ARL Search MAC/VID Result (64 bit) */ #define B53_ARL_SRCH_RSTL_0_MACVID 0x60 +#define B53_ARL_SRCH_RSLT_MACVID_89 0x33 +#define B53_ARL_SRCH_RSLT_MACVID_63XX 0x34 -/* Single register search result on 5325 */ +/* Single register search result on 5325/5365 */ #define B53_ARL_SRCH_RSTL_0_MACVID_25 0x24 -/* Single register search result on 5365 */ -#define B53_ARL_SRCH_RSTL_0_MACVID_65 0x30 +#define ARL_SRCH_RSLT_PORT_ID_S_25 48 +#define ARL_SRCH_RSLT_PORT_ID_MASK_25 GENMASK_ULL(52, 48) +#define ARL_SRCH_RSLT_VID_S_25 53 +#define ARL_SRCH_RSLT_VID_MASK_25 GENMASK_ULL(60, 53) + +/* BCM5325/5365 Search result extend register (8 bit) */ +#define B53_ARL_SRCH_RSLT_EXT_25 0x2c +#define ARL_SRCH_RSLT_EXT_MC_MII BIT(2) /* ARL Search Data Result (32 bit) */ #define B53_ARL_SRCH_RSTL_0 0x68 +/* BCM5389 ARL Search Data Result (16 bit) */ +#define B53_ARL_SRCH_RSLT_89 0x3b + #define B53_ARL_SRCH_RSTL_MACVID(x) (B53_ARL_SRCH_RSTL_0_MACVID + ((x) * 0x10)) #define B53_ARL_SRCH_RSTL(x) (B53_ARL_SRCH_RSTL_0 + ((x) * 0x10)) +/* 63XX ARL Search Data Result (16 bit) */ +#define B53_ARL_SRCH_RSLT_63XX 0x3c +#define ARL_SRST_PORT_ID_MASK_63XX GENMASK(9, 1) +#define ARL_SRST_TC_MASK_63XX GENMASK(13, 11) +#define ARL_SRST_AGE_63XX BIT(14) +#define ARL_SRST_STATIC_63XX BIT(15) + /************************************************************************* * IEEE 802.1X Registers *************************************************************************/ diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index b4d48997bf4674..09002c853b78e1 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3364,13 +3364,10 @@ static int mv88e6xxx_setup_upstream_port(struct mv88e6xxx_chip *chip, int port) static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) { - struct device_node *phy_handle = NULL; struct fwnode_handle *ports_fwnode; struct fwnode_handle *port_fwnode; struct dsa_switch *ds = chip->ds; struct mv88e6xxx_port *p; - struct dsa_port *dp; - int tx_amp; int err; u16 reg; u32 val; @@ -3582,23 +3579,6 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return err; } - if (chip->info->ops->serdes_set_tx_amplitude) { - dp = dsa_to_port(ds, port); - if (dp) - phy_handle = of_parse_phandle(dp->dn, "phy-handle", 0); - - if (phy_handle && !of_property_read_u32(phy_handle, - "tx-p2p-microvolt", - &tx_amp)) - err = chip->info->ops->serdes_set_tx_amplitude(chip, - port, tx_amp); - if (phy_handle) { - of_node_put(phy_handle); - if (err) - return err; - } - } - /* Port based VLAN map: give each port the same default address * database, and allow bidirectional communication between the * CPU and DSA port(s), and the other ports. @@ -4768,7 +4748,6 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .serdes_irq_mapping = mv88e6352_serdes_irq_mapping, .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, .serdes_get_regs = mv88e6352_serdes_get_regs, - .serdes_set_tx_amplitude = mv88e6352_serdes_set_tx_amplitude, .gpio_ops = &mv88e6352_gpio_ops, .phylink_get_caps = mv88e6352_phylink_get_caps, .pcs_ops = &mv88e6352_pcs_ops, @@ -5044,7 +5023,6 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .serdes_irq_mapping = mv88e6352_serdes_irq_mapping, .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, .serdes_get_regs = mv88e6352_serdes_get_regs, - .serdes_set_tx_amplitude = mv88e6352_serdes_set_tx_amplitude, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, @@ -5481,7 +5459,6 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .serdes_get_stats = mv88e6352_serdes_get_stats, .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, .serdes_get_regs = mv88e6352_serdes_get_regs, - .serdes_set_tx_amplitude = mv88e6352_serdes_set_tx_amplitude, .phylink_get_caps = mv88e6352_phylink_get_caps, .pcs_ops = &mv88e6352_pcs_ops, }; diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 2f211e55cb47b0..e073446ee7d02b 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -642,10 +642,6 @@ struct mv88e6xxx_ops { void (*serdes_get_regs)(struct mv88e6xxx_chip *chip, int port, void *_p); - /* SERDES SGMII/Fiber Output Amplitude */ - int (*serdes_set_tx_amplitude)(struct mv88e6xxx_chip *chip, int port, - int val); - /* Address Translation Unit operations */ int (*atu_get_hash)(struct mv88e6xxx_chip *chip, u8 *hash); int (*atu_set_hash)(struct mv88e6xxx_chip *chip, u8 hash); diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index b3330211edbcaa..a936ee80ce006f 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -25,14 +25,6 @@ static int mv88e6352_serdes_read(struct mv88e6xxx_chip *chip, int reg, reg, val); } -static int mv88e6352_serdes_write(struct mv88e6xxx_chip *chip, int reg, - u16 val) -{ - return mv88e6xxx_phy_page_write(chip, MV88E6352_ADDR_SERDES, - MV88E6352_SERDES_PAGE_FIBER, - reg, val); -} - static int mv88e6390_serdes_read(struct mv88e6xxx_chip *chip, int lane, int device, int reg, u16 *val) { @@ -506,41 +498,3 @@ void mv88e6390_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p) p[i] = reg; } } - -static const int mv88e6352_serdes_p2p_to_reg[] = { - /* Index of value in microvolts corresponds to the register value */ - 14000, 112000, 210000, 308000, 406000, 504000, 602000, 700000, -}; - -int mv88e6352_serdes_set_tx_amplitude(struct mv88e6xxx_chip *chip, int port, - int val) -{ - bool found = false; - u16 ctrl, reg; - int err; - int i; - - err = mv88e6352_g2_scratch_port_has_serdes(chip, port); - if (err <= 0) - return err; - - for (i = 0; i < ARRAY_SIZE(mv88e6352_serdes_p2p_to_reg); ++i) { - if (mv88e6352_serdes_p2p_to_reg[i] == val) { - reg = i; - found = true; - break; - } - } - - if (!found) - return -EINVAL; - - err = mv88e6352_serdes_read(chip, MV88E6352_SERDES_SPEC_CTRL2, &ctrl); - if (err) - return err; - - ctrl &= ~MV88E6352_SERDES_OUT_AMP_MASK; - ctrl |= reg; - - return mv88e6352_serdes_write(chip, MV88E6352_SERDES_SPEC_CTRL2, ctrl); -} diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h index ad887d8601bcbb..17a3e85fabaa34 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.h +++ b/drivers/net/dsa/mv88e6xxx/serdes.h @@ -29,8 +29,6 @@ struct phylink_link_state; #define MV88E6352_SERDES_INT_FIBRE_ENERGY BIT(4) #define MV88E6352_SERDES_INT_STATUS 0x13 -#define MV88E6352_SERDES_SPEC_CTRL2 0x1a -#define MV88E6352_SERDES_OUT_AMP_MASK 0x0007 #define MV88E6341_PORT5_LANE 0x15 @@ -140,9 +138,6 @@ void mv88e6352_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p); int mv88e6390_serdes_get_regs_len(struct mv88e6xxx_chip *chip, int port); void mv88e6390_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p); -int mv88e6352_serdes_set_tx_amplitude(struct mv88e6xxx_chip *chip, int port, - int val); - /* Return the (first) SERDES lane address a port is using, -errno otherwise. */ static inline int mv88e6xxx_serdes_get_lane(struct mv88e6xxx_chip *chip, int port) diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c index 4dbcc49a9e526f..0a05f4156ef4d7 100644 --- a/drivers/net/dsa/xrs700x/xrs700x.c +++ b/drivers/net/dsa/xrs700x/xrs700x.c @@ -566,6 +566,7 @@ static int xrs700x_hsr_join(struct dsa_switch *ds, int port, struct xrs700x *priv = ds->priv; struct net_device *user; int ret, i, hsr_pair[2]; + enum hsr_port_type type; enum hsr_version ver; bool fwd = false; @@ -589,6 +590,16 @@ static int xrs700x_hsr_join(struct dsa_switch *ds, int port, return -EOPNOTSUPP; } + ret = hsr_get_port_type(hsr, dsa_to_port(ds, port)->user, &type); + if (ret) + return ret; + + if (type != HSR_PT_SLAVE_A && type != HSR_PT_SLAVE_B) { + NL_SET_ERR_MSG_MOD(extack, + "Only HSR slave ports can be offloaded"); + return -EOPNOTSUPP; + } + dsa_hsr_foreach_port(dp, ds, hsr) { if (dp->index != port) { partner = dp; diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 8c9cc97efd4eef..4fe4efdb3737fd 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -1473,7 +1473,7 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq, return 0; free_ring: - dma_free_coherent(&pdev->dev, + dma_free_coherent(gendev, sizeof(struct boom_rx_desc) * RX_RING_SIZE + sizeof(struct boom_tx_desc) * TX_RING_SIZE, vp->rx_ring, vp->rx_ring_dma); diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c index 30f9d271e59531..71a2397edf2bbf 100644 --- a/drivers/net/ethernet/adi/adin1110.c +++ b/drivers/net/ethernet/adi/adin1110.c @@ -1089,6 +1089,9 @@ static int adin1110_check_spi(struct adin1110_priv *priv) reset_gpio = devm_gpiod_get_optional(&priv->spidev->dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(reset_gpio)) + return dev_err_probe(&priv->spidev->dev, PTR_ERR(reset_gpio), + "failed to get reset gpio\n"); if (reset_gpio) { /* MISO pin is used for internal configuration, can't have * anyone else disturbing the SDO line. diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 433a646e983177..0394ba6a90a9b2 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -2900,19 +2900,26 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, port->id = id; eth->ports[p] = port; - err = airoha_metadata_dst_alloc(port); - if (err) - return err; + return airoha_metadata_dst_alloc(port); +} - err = register_netdev(dev); - if (err) - goto free_metadata_dst; +static int airoha_register_gdm_devices(struct airoha_eth *eth) +{ + int i; - return 0; + for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { + struct airoha_gdm_port *port = eth->ports[i]; + int err; -free_metadata_dst: - airoha_metadata_dst_free(port); - return err; + if (!port) + continue; + + err = register_netdev(port->dev); + if (err) + return err; + } + + return 0; } static int airoha_probe(struct platform_device *pdev) @@ -2993,6 +3000,10 @@ static int airoha_probe(struct platform_device *pdev) } } + err = airoha_register_gdm_devices(eth); + if (err) + goto error_napi_stop; + return 0; error_napi_stop: @@ -3006,10 +3017,12 @@ static int airoha_probe(struct platform_device *pdev) for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { struct airoha_gdm_port *port = eth->ports[i]; - if (port && port->dev->reg_state == NETREG_REGISTERED) { + if (!port) + continue; + + if (port->dev->reg_state == NETREG_REGISTERED) unregister_netdev(port->dev); - airoha_metadata_dst_free(port); - } + airoha_metadata_dst_free(port); } free_netdev(eth->napi_dev); platform_set_drvdata(pdev, NULL); diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index c0e17035db18ed..190d98970014fa 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -1466,13 +1466,16 @@ void airoha_ppe_deinit(struct airoha_eth *eth) { struct airoha_npu *npu; - rcu_read_lock(); - npu = rcu_dereference(eth->npu); + mutex_lock(&flow_offload_mutex); + + npu = rcu_replace_pointer(eth->npu, NULL, + lockdep_is_held(&flow_offload_mutex)); if (npu) { npu->ops.ppe_deinit(npu); airoha_npu_put(npu); } - rcu_read_unlock(); + + mutex_unlock(&flow_offload_mutex); rhashtable_destroy(ð->ppe->l2_flows); rhashtable_destroy(ð->flow_table); diff --git a/drivers/net/ethernet/amazon/ena/ena_devlink.c b/drivers/net/ethernet/amazon/ena/ena_devlink.c index ac81c24016dd47..4772185e669d29 100644 --- a/drivers/net/ethernet/amazon/ena/ena_devlink.c +++ b/drivers/net/ethernet/amazon/ena/ena_devlink.c @@ -53,10 +53,12 @@ void ena_devlink_disable_phc_param(struct devlink *devlink) { union devlink_param_value value; + devl_lock(devlink); value.vbool = false; devl_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_PHC, value); + devl_unlock(devlink); } static void ena_devlink_port_register(struct devlink *devlink) @@ -145,10 +147,12 @@ static int ena_devlink_configure_params(struct devlink *devlink) return rc; } + devl_lock(devlink); value.vbool = ena_phc_is_enabled(adapter); devl_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_PHC, value); + devl_unlock(devlink); return 0; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 4dc631af793324..ba5e728ae63089 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1823,7 +1823,7 @@ static void xgbe_get_stats64(struct net_device *netdev, s->multicast = pstats->rxmulticastframes_g; s->rx_length_errors = pstats->rxlengtherror; s->rx_crc_errors = pstats->rxcrcerror; - s->rx_fifo_errors = pstats->rxfifooverflow; + s->rx_over_errors = pstats->rxfifooverflow; s->tx_packets = pstats->txframecount_gb; s->tx_bytes = pstats->txoctetcount_gb; @@ -2277,9 +2277,6 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget) goto read_again; if (error || packet->errors) { - if (packet->errors) - netif_err(pdata, rx_err, netdev, - "error in received packet\n"); dev_kfree_skb(skb); goto next_packet; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index a56efc1bee3399..450a573960e7aa 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -1927,6 +1927,7 @@ static void xgbe_set_rx_adap_mode(struct xgbe_prv_data *pdata, { if (pdata->rx_adapt_retries++ >= MAX_RX_ADAPT_RETRIES) { pdata->rx_adapt_retries = 0; + pdata->mode_set = false; return; } @@ -1973,6 +1974,7 @@ static void xgbe_rx_adaptation(struct xgbe_prv_data *pdata) */ netif_dbg(pdata, link, pdata->netdev, "Block_lock done"); pdata->rx_adapt_done = true; + pdata->rx_adapt_retries = 0; pdata->mode_set = false; return; } diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 9fdef874f5ca33..fe15d684990fc7 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -254,14 +254,14 @@ config BNXT_HWMON devices, via the hwmon sysfs interface. config BNGE - tristate "Broadcom Ethernet device support" + tristate "Broadcom ThorUltra Ethernet device support" depends on PCI select NET_DEVLINK select PAGE_POOL help - This driver supports Broadcom 50/100/200/400/800 gigabit Ethernet cards. - The module will be called bng_en. To compile this driver as a module, - choose M here. + This driver supports Broadcom ThorUltra 50/100/200/400/800 gigabit + Ethernet cards. The module will be called bng_en. To compile this + driver as a module, choose M here. config BCMASP tristate "Broadcom ASP 2.0 Ethernet support" diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c index fd35f4b4dc50bb..014340f33345a0 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c @@ -156,7 +156,7 @@ static void bcmasp_netfilt_hw_en_wake(struct bcmasp_priv *priv, ASP_RX_FILTER_NET_OFFSET_L4(32), ASP_RX_FILTER_NET_OFFSET(nfilt->hw_index + 1)); - rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->port + 8) | + rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->ch) | ASP_RX_FILTER_NET_CFG_EN | ASP_RX_FILTER_NET_CFG_L2_EN | ASP_RX_FILTER_NET_CFG_L3_EN | @@ -166,7 +166,7 @@ static void bcmasp_netfilt_hw_en_wake(struct bcmasp_priv *priv, ASP_RX_FILTER_NET_CFG_UMC(nfilt->port), ASP_RX_FILTER_NET_CFG(nfilt->hw_index)); - rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->port + 8) | + rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->ch) | ASP_RX_FILTER_NET_CFG_EN | ASP_RX_FILTER_NET_CFG_L2_EN | ASP_RX_FILTER_NET_CFG_L3_EN | @@ -714,6 +714,7 @@ struct bcmasp_net_filter *bcmasp_netfilt_get_init(struct bcmasp_intf *intf, nfilter = &priv->net_filters[open_index]; nfilter->claimed = true; nfilter->port = intf->port; + nfilter->ch = intf->channel + priv->tx_chan_offset; nfilter->hw_index = open_index; } diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h index 74adfdb50e11d2..e238507be40afd 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h @@ -348,6 +348,7 @@ struct bcmasp_net_filter { bool wake_filter; int port; + int ch; unsigned int hw_index; }; diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index b9973956c48095..ceb6c11431dd9c 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -1261,7 +1261,7 @@ struct bcmasp_intf *bcmasp_interface_create(struct bcmasp_priv *priv, netdev_err(intf->ndev, "invalid PHY mode: %s for port %d\n", phy_modes(intf->phy_interface), intf->port); ret = -EINVAL; - goto err_free_netdev; + goto err_deregister_fixed_link; } ret = of_get_ethdev_address(ndev_dn, ndev); @@ -1286,6 +1286,9 @@ struct bcmasp_intf *bcmasp_interface_create(struct bcmasp_priv *priv, return intf; +err_deregister_fixed_link: + if (of_phy_is_fixed_link(ndev_dn)) + of_phy_deregister_fixed_link(ndev_dn); err_free_netdev: free_netdev(ndev); err: diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 0353359c3fe96c..073d7d490d4b61 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -1789,6 +1789,9 @@ static int b44_nway_reset(struct net_device *dev) u32 bmcr; int r; + if (bp->flags & B44_FLAG_EXTERNAL_PHY) + return phy_ethtool_nway_reset(dev); + spin_lock_irq(&bp->lock); b44_readphy(bp, MII_BMCR, &bmcr); b44_readphy(bp, MII_BMCR, &bmcr); diff --git a/drivers/net/ethernet/broadcom/bnge/bnge.h b/drivers/net/ethernet/broadcom/bnge/bnge.h index 7aed5f81cd51e5..0c154995d9ab5f 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge.h +++ b/drivers/net/ethernet/broadcom/bnge/bnge.h @@ -5,7 +5,7 @@ #define _BNGE_H_ #define DRV_NAME "bng_en" -#define DRV_SUMMARY "Broadcom 800G Ethernet Linux Driver" +#define DRV_SUMMARY "Broadcom ThorUltra NIC Ethernet Driver" #include #include diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_core.c b/drivers/net/ethernet/broadcom/bnge/bnge_core.c index 2c72dd34d50d00..312a9db4d75d1d 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_core.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_core.c @@ -19,7 +19,7 @@ char bnge_driver_name[] = DRV_NAME; static const struct { char *name; } board_info[] = { - [BCM57708] = { "Broadcom BCM57708 50Gb/100Gb/200Gb/400Gb/800Gb Ethernet" }, + [BCM57708] = { "Broadcom BCM57708 ThorUltra 50Gb/100Gb/200Gb/400Gb/800Gb Ethernet" }, }; static const struct pci_device_id bnge_pci_tbl[] = { diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c index 198f49b40dbf00..2994f10446a63c 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c @@ -442,7 +442,7 @@ __bnge_hwrm_reserve_pf_rings(struct bnge_dev *bd, struct bnge_hw_rings *hwr) struct hwrm_func_cfg_input *req; u32 enables = 0; - if (bnge_hwrm_req_init(bd, req, HWRM_FUNC_QCFG)) + if (bnge_hwrm_req_init(bd, req, HWRM_FUNC_CFG)) return NULL; req->fid = cpu_to_le16(0xffff); diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index cb1011f6fd3072..805daae9dd3621 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -6444,7 +6444,6 @@ bnx2_reset_task(struct work_struct *work) if (!(pcicmd & PCI_COMMAND_MEMORY)) { /* in case PCI block has reset */ pci_restore_state(bp->pdev); - pci_save_state(bp->pdev); } rc = bnx2_init_nic(bp, 1); if (rc) { @@ -8718,7 +8717,6 @@ static pci_ers_result_t bnx2_io_slot_reset(struct pci_dev *pdev) } else { pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); if (netif_running(dev)) err = bnx2_init_nic(bp, 1); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index f0f05d7315ac48..8e6eec828d4821 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -14216,7 +14216,6 @@ static pci_ers_result_t bnx2x_io_slot_reset(struct pci_dev *pdev) pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); if (netif_running(dev)) bnx2x_set_power_state(bp, PCI_D0); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index a625e7c311dd7e..95c774d98da66a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1482,9 +1482,11 @@ static u16 bnxt_alloc_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id) struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map; u16 idx = agg_id & MAX_TPA_P5_MASK; - if (test_bit(idx, map->agg_idx_bmap)) - idx = find_first_zero_bit(map->agg_idx_bmap, - BNXT_AGG_IDX_BMAP_SIZE); + if (test_bit(idx, map->agg_idx_bmap)) { + idx = find_first_zero_bit(map->agg_idx_bmap, MAX_TPA_P5); + if (idx >= MAX_TPA_P5) + return INVALID_HW_RING_ID; + } __set_bit(idx, map->agg_idx_bmap); map->agg_id_tbl[agg_id] = idx; return idx; @@ -1548,6 +1550,13 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { agg_id = TPA_START_AGG_ID_P5(tpa_start); agg_id = bnxt_alloc_agg_idx(rxr, agg_id); + if (unlikely(agg_id == INVALID_HW_RING_ID)) { + netdev_warn(bp->dev, "Unable to allocate agg ID for ring %d, agg 0x%x\n", + rxr->bnapi->index, + TPA_START_AGG_ID_P5(tpa_start)); + bnxt_sched_reset_rxr(bp, rxr); + return; + } } else { agg_id = TPA_START_AGG_ID(tpa_start); } @@ -16856,12 +16865,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) init_err_pci_clean: bnxt_hwrm_func_drv_unrgtr(bp); - bnxt_free_hwrm_resources(bp); - bnxt_hwmon_uninit(bp); - bnxt_ethtool_free(bp); bnxt_ptp_clear(bp); kfree(bp->ptp_cfg); bp->ptp_cfg = NULL; + bnxt_free_hwrm_resources(bp); + bnxt_hwmon_uninit(bp); + bnxt_ethtool_free(bp); kfree(bp->fw_health); bp->fw_health = NULL; bnxt_cleanup_pci(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 3613a172483a16..45bbaec75ded48 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1079,11 +1079,9 @@ struct bnxt_tpa_info { struct rx_agg_cmp *agg_arr; }; -#define BNXT_AGG_IDX_BMAP_SIZE (MAX_TPA_P5 / BITS_PER_LONG) - struct bnxt_tpa_idx_map { u16 agg_id_tbl[1024]; - unsigned long agg_idx_bmap[BNXT_AGG_IDX_BMAP_SIZE]; + DECLARE_BITMAP(agg_idx_bmap, MAX_TPA_P5); }; struct bnxt_rx_ring_info { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 3e77a96e5a3e39..c94a391b1ba5b2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -268,13 +268,11 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, case XDP_TX: rx_buf = &rxr->rx_buf_ring[cons]; mapping = rx_buf->mapping - bp->rx_dma_offset; - *event &= BNXT_TX_CMP_EVENT; if (unlikely(xdp_buff_has_frags(xdp))) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); tx_needed += sinfo->nr_frags; - *event = BNXT_AGG_EVENT; } if (tx_avail < tx_needed) { @@ -287,6 +285,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, dma_sync_single_for_device(&pdev->dev, mapping + offset, *len, bp->rx_dir); + *event &= ~BNXT_RX_EVENT; *event |= BNXT_TX_EVENT; __bnxt_xmit_xdp(bp, txr, mapping + offset, *len, NEXT_RX(rxr->rx_prod), xdp); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index d78cafdb20949c..0397a6ebf20f98 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -18349,7 +18349,6 @@ static pci_ers_result_t tg3_io_slot_reset(struct pci_dev *pdev) pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); if (!netdev || !netif_running(netdev)) { rc = PCI_ERS_RESULT_RECOVERED; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index ca2386b8347371..064fccdcf69945 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -744,7 +744,6 @@ static void macb_mac_link_up(struct phylink_config *config, /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down * cleared the pipeline and control registers. */ - bp->macbgem_ops.mog_init_rings(bp); macb_init_buffers(bp); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) @@ -2991,6 +2990,8 @@ static int macb_open(struct net_device *dev) goto pm_exit; } + bp->macbgem_ops.mog_init_rings(bp); + for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { napi_enable(&queue->napi_rx); napi_enable(&queue->napi_tx); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 8e2fcec26ea13c..eb620e8544cf19 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -3515,6 +3515,23 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) */ netdev->netdev_ops = &lionetdevops; + lio = GET_LIO(netdev); + + memset(lio, 0, sizeof(struct lio)); + + lio->ifidx = ifidx_or_pfnum; + + props = &octeon_dev->props[i]; + props->gmxport = resp->cfg_info.linfo.gmxport; + props->netdev = netdev; + + /* Point to the properties for octeon device to which this + * interface belongs. + */ + lio->oct_dev = octeon_dev; + lio->octprops = props; + lio->netdev = netdev; + retval = netif_set_real_num_rx_queues(netdev, num_oqueues); if (retval) { dev_err(&octeon_dev->pci_dev->dev, @@ -3531,16 +3548,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) goto setup_nic_dev_free; } - lio = GET_LIO(netdev); - - memset(lio, 0, sizeof(struct lio)); - - lio->ifidx = ifidx_or_pfnum; - - props = &octeon_dev->props[i]; - props->gmxport = resp->cfg_info.linfo.gmxport; - props->netdev = netdev; - lio->linfo.num_rxpciq = num_oqueues; lio->linfo.num_txpciq = num_iqueues; for (j = 0; j < num_oqueues; j++) { @@ -3606,13 +3613,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) netdev->min_mtu = LIO_MIN_MTU_SIZE; netdev->max_mtu = LIO_MAX_MTU_SIZE; - /* Point to the properties for octeon device to which this - * interface belongs. - */ - lio->oct_dev = octeon_dev; - lio->octprops = props; - lio->netdev = netdev; - dev_dbg(&octeon_dev->pci_dev->dev, "if%d gmx: %d hw_addr: 0x%llx\n", i, lio->linfo.gmxport, CVM_CAST64(lio->linfo.hw_addr)); @@ -3760,6 +3760,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) if (!devlink) { device_unlock(&octeon_dev->pci_dev->dev); dev_err(&octeon_dev->pci_dev->dev, "devlink alloc failed\n"); + i--; goto setup_nic_dev_free; } @@ -3775,11 +3776,11 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) setup_nic_dev_free: - while (i--) { + do { dev_err(&octeon_dev->pci_dev->dev, "NIC ifidx:%d Setup failed\n", i); liquidio_destroy_nic_device(octeon_dev, i); - } + } while (i--); setup_nic_dev_done: diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index 3230dff5ba056c..5c177146b35b11 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -2222,11 +2222,11 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) setup_nic_dev_free: - while (i--) { + do { dev_err(&octeon_dev->pci_dev->dev, "NIC ifidx:%d Setup failed\n", i); liquidio_destroy_nic_device(octeon_dev, i); - } + } while (i--); setup_nic_dev_done: diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index f92a3550e48000..3b1321c8ed143a 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -2933,7 +2933,6 @@ static int t3_reenable_adapter(struct adapter *adapter) } pci_set_master(adapter->pdev); pci_restore_state(adapter->pdev); - pci_save_state(adapter->pdev); /* Free sge resources */ t3_free_sge_resources(adapter); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 392723ef14e512..1ce2091cdc01a4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -5456,7 +5456,6 @@ static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev) if (!adap) { pci_restore_state(pdev); - pci_save_state(pdev); return PCI_ERS_RESULT_RECOVERED; } @@ -5471,7 +5470,6 @@ static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev) pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); if (t4_wait_dev_ready(adap->regs) < 0) return PCI_ERS_RESULT_DISCONNECT; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index bb5d2fa157365f..8ed45bceb5379a 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -3801,6 +3801,7 @@ int be_cmd_get_perm_mac(struct be_adapter *adapter, u8 *mac) { int status; bool pmac_valid = false; + u32 pmac_id; eth_zero_addr(mac); @@ -3813,7 +3814,7 @@ int be_cmd_get_perm_mac(struct be_adapter *adapter, u8 *mac) adapter->if_handle, 0); } else { status = be_cmd_get_mac_from_list(adapter, mac, &pmac_valid, - NULL, adapter->if_handle, 0); + &pmac_id, adapter->if_handle, 0); } return status; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 5bb31c8fab3913..995c159003d790 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2141,7 +2141,7 @@ static int be_get_new_eqd(struct be_eq_obj *eqo) struct be_aic_obj *aic; struct be_rx_obj *rxo; struct be_tx_obj *txo; - u64 rx_pkts = 0, tx_pkts = 0; + u64 rx_pkts = 0, tx_pkts = 0, pkts; ulong now; u32 pps, delta; int i; @@ -2157,15 +2157,17 @@ static int be_get_new_eqd(struct be_eq_obj *eqo) for_all_rx_queues_on_eq(adapter, eqo, rxo, i) { do { start = u64_stats_fetch_begin(&rxo->stats.sync); - rx_pkts += rxo->stats.rx_pkts; + pkts = rxo->stats.rx_pkts; } while (u64_stats_fetch_retry(&rxo->stats.sync, start)); + rx_pkts += pkts; } for_all_tx_queues_on_eq(adapter, eqo, txo, i) { do { start = u64_stats_fetch_begin(&txo->stats.sync); - tx_pkts += txo->stats.tx_reqs; + pkts = txo->stats.tx_reqs; } while (u64_stats_fetch_retry(&txo->stats.sync, start)); + tx_pkts += pkts; } /* Skip, if wrapped around or first calculation */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index b1e1ad9e4b48e6..66240c340492ce 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1531,6 +1531,10 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) } if_id = (status & 0xFFFF0000) >> 16; + if (if_id >= ethsw->sw_attr.num_ifs) { + dev_err(dev, "Invalid if_id %d in IRQ status\n", if_id); + goto out; + } port_priv = ethsw->ports[if_id]; if (status & DPSW_IRQ_EVENT_LINK_CHANGED) @@ -3024,6 +3028,12 @@ static int dpaa2_switch_init(struct fsl_mc_device *sw_dev) goto err_close; } + if (!ethsw->sw_attr.num_ifs) { + dev_err(dev, "DPSW device has no interfaces\n"); + err = -ENODEV; + goto err_close; + } + err = dpsw_get_api_version(ethsw->mc_io, 0, ðsw->major, ðsw->minor); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 0535e92404e3cb..b6e3fb0401619c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1778,7 +1778,8 @@ int enetc_xdp_xmit(struct net_device *ndev, int num_frames, int xdp_tx_bd_cnt, i, k; int xdp_tx_frm_cnt = 0; - if (unlikely(test_bit(ENETC_TX_DOWN, &priv->flags))) + if (unlikely(test_bit(ENETC_TX_DOWN, &priv->flags) || + !netif_carrier_ok(ndev))) return -ENETDOWN; enetc_lock_mdio(); @@ -2502,10 +2503,13 @@ int enetc_configure_si(struct enetc_ndev_priv *priv) struct enetc_hw *hw = &si->hw; int err; - /* set SI cache attributes */ - enetc_wr(hw, ENETC_SICAR0, - ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT); - enetc_wr(hw, ENETC_SICAR1, ENETC_SICAR_MSI); + if (is_enetc_rev1(si)) { + /* set SI cache attributes */ + enetc_wr(hw, ENETC_SICAR0, + ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT); + enetc_wr(hw, ENETC_SICAR1, ENETC_SICAR_MSI); + } + /* enable SI */ enetc_wr(hw, ENETC_SIMR, ENETC_SIMR_EN); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index f279fa597991ec..60c7205ea9ff51 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -79,9 +79,9 @@ struct enetc_lso_t { #define ENETC_RXB_TRUESIZE (PAGE_SIZE >> 1) #define ENETC_RXB_PAD NET_SKB_PAD /* add extra space if needed */ #define ENETC_RXB_DMA_SIZE \ - (SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - ENETC_RXB_PAD) + min(SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - ENETC_RXB_PAD, 0xffff) #define ENETC_RXB_DMA_SIZE_XDP \ - (SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - XDP_PACKET_HEADROOM) + min(SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - XDP_PACKET_HEADROOM, 0xffff) struct enetc_rx_swbd { dma_addr_t dma; diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c index 82c443b28b154d..7dbfbc6fbdcb03 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c @@ -49,10 +49,10 @@ static void enetc4_pf_set_si_primary_mac(struct enetc_hw *hw, int si, if (si != 0) { __raw_writel(upper, hw->port + ENETC4_PSIPMAR0(si)); - __raw_writew(lower, hw->port + ENETC4_PSIPMAR1(si)); + __raw_writel(lower, hw->port + ENETC4_PSIPMAR1(si)); } else { __raw_writel(upper, hw->port + ENETC4_PMAR0); - __raw_writew(lower, hw->port + ENETC4_PMAR1); + __raw_writel(lower, hw->port + ENETC4_PMAR1); } } @@ -63,7 +63,7 @@ static void enetc4_pf_get_si_primary_mac(struct enetc_hw *hw, int si, u16 lower; upper = __raw_readl(hw->port + ENETC4_PSIPMAR0(si)); - lower = __raw_readw(hw->port + ENETC4_PSIPMAR1(si)); + lower = __raw_readl(hw->port + ENETC4_PSIPMAR1(si)); put_unaligned_le32(upper, addr); put_unaligned_le16(lower, addr + 4); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c index 3d5f31879d5c64..a635bfdc30afc2 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c @@ -74,10 +74,6 @@ int enetc4_setup_cbdr(struct enetc_si *si) if (!user->ring) return -ENOMEM; - /* set CBDR cache attributes */ - enetc_wr(hw, ENETC_SICAR2, - ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT); - regs.pir = hw->reg + ENETC_SICBDRPIR; regs.cir = hw->reg + ENETC_SICBDRCIR; regs.mr = hw->reg + ENETC_SICBDRMR; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 377c963258147a..d382220ef2f0d0 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -707,13 +707,24 @@ struct enetc_cmd_rfse { #define ENETC_RFSE_EN BIT(15) #define ENETC_RFSE_MODE_BD 2 +static inline void enetc_get_primary_mac_addr(struct enetc_hw *hw, u8 *addr) +{ + u32 upper; + u16 lower; + + upper = __raw_readl(hw->reg + ENETC_SIPMAR0); + lower = __raw_readl(hw->reg + ENETC_SIPMAR1); + + put_unaligned_le32(upper, addr); + put_unaligned_le16(lower, addr + 4); +} + static inline void enetc_load_primary_mac_addr(struct enetc_hw *hw, struct net_device *ndev) { - u8 addr[ETH_ALEN] __aligned(4); + u8 addr[ETH_ALEN]; - *(u32 *)addr = __raw_readl(hw->reg + ENETC_SIPMAR0); - *(u16 *)(addr + 4) = __raw_readw(hw->reg + ENETC_SIPMAR1); + enetc_get_primary_mac_addr(hw, addr); eth_hw_addr_set(ndev, addr); } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 3222359ac15b77..f30e8fabfaded8 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1151,7 +1151,7 @@ fec_restart(struct net_device *ndev) u32 rcntl = FEC_RCR_MII; if (OPT_ARCH_HAS_MAX_FL) - rcntl |= (fep->netdev->mtu + ETH_HLEN + ETH_FCS_LEN) << 16; + rcntl |= (fep->netdev->mtu + VLAN_ETH_HLEN + ETH_FCS_LEN) << 16; if (fep->bufdesc_ex) fec_ptp_save_state(fep); @@ -1286,12 +1286,13 @@ fec_restart(struct net_device *ndev) /* When Jumbo Frame is enabled, the FIFO may not be large enough * to hold an entire frame. In such cases, if the MTU exceeds - * (PKT_MAXBUF_SIZE - ETH_HLEN - ETH_FCS_LEN), configure the interface - * to operate in cut-through mode, triggered by the FIFO threshold. + * (PKT_MAXBUF_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN), configure + * the interface to operate in cut-through mode, triggered by + * the FIFO threshold. * Otherwise, enable the ENET store-and-forward mode. */ if ((fep->quirks & FEC_QUIRK_JUMBO_FRAME) && - (ndev->mtu > (PKT_MAXBUF_SIZE - ETH_HLEN - ETH_FCS_LEN))) + (ndev->mtu > (PKT_MAXBUF_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN))) writel(0xF, fep->hwp + FEC_X_WMRK); else writel(FEC_TXWMRK_STRFWD, fep->hwp + FEC_X_WMRK); @@ -3948,7 +3949,12 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, txq->bd.cur = bdp; /* Trigger transmission start */ - writel(0, txq->bd.reg_desc_active); + if (!(fep->quirks & FEC_QUIRK_ERR007885) || + !readl(txq->bd.reg_desc_active) || + !readl(txq->bd.reg_desc_active) || + !readl(txq->bd.reg_desc_active) || + !readl(txq->bd.reg_desc_active)) + writel(0, txq->bd.reg_desc_active); return 0; } @@ -4047,7 +4053,7 @@ static int fec_change_mtu(struct net_device *ndev, int new_mtu) if (netif_running(ndev)) return -EBUSY; - order = get_order(new_mtu + ETH_HLEN + ETH_FCS_LEN + order = get_order(new_mtu + VLAN_ETH_HLEN + ETH_FCS_LEN + FEC_DRV_RESERVE_SPACE); fep->rx_frame_size = (PAGE_SIZE << order) - FEC_DRV_RESERVE_SPACE; fep->pagepool_order = order; @@ -4604,7 +4610,7 @@ fec_probe(struct platform_device *pdev) else fep->max_buf_size = PKT_MAXBUF_SIZE; - ndev->max_mtu = fep->max_buf_size - ETH_HLEN - ETH_FCS_LEN; + ndev->max_mtu = fep->max_buf_size - VLAN_ETH_HLEN - ETH_FCS_LEN; ret = register_netdev(ndev); if (ret) diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index affd5a6c44e7b3..131d1210dc4a84 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -1602,8 +1602,10 @@ static void ugeth_mac_config(struct phylink_config *config, unsigned int mode, pr_warn("TBI mode requires that the device tree specify a tbi-handle\n"); tbiphy = of_phy_find_device(ug_info->tbi_node); - if (!tbiphy) + if (!tbiphy) { pr_warn("Could not get TBI device\n"); + return; + } value = phy_read(tbiphy, ENET_TBI_MII_CR); value &= ~0x1000; /* Turn off autonegotiation */ diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index d0a223250845bc..edc0c718f71e9a 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -152,11 +152,13 @@ gve_get_ethtool_stats(struct net_device *netdev, u64 tmp_rx_pkts, tmp_rx_hsplit_pkt, tmp_rx_bytes, tmp_rx_hsplit_bytes, tmp_rx_skb_alloc_fail, tmp_rx_buf_alloc_fail, tmp_rx_desc_err_dropped_pkt, tmp_rx_hsplit_unsplit_pkt, - tmp_tx_pkts, tmp_tx_bytes; + tmp_tx_pkts, tmp_tx_bytes, + tmp_xdp_tx_errors, tmp_xdp_redirect_errors; u64 rx_buf_alloc_fail, rx_desc_err_dropped_pkt, rx_hsplit_unsplit_pkt, rx_pkts, rx_hsplit_pkt, rx_skb_alloc_fail, rx_bytes, tx_pkts, tx_bytes, - tx_dropped; - int stats_idx, base_stats_idx, max_stats_idx; + tx_dropped, xdp_tx_errors, xdp_redirect_errors; + int rx_base_stats_idx, max_rx_stats_idx, max_tx_stats_idx; + int stats_idx, stats_region_len, nic_stats_len; struct stats *report_stats; int *rx_qid_to_stats_idx; int *tx_qid_to_stats_idx; @@ -198,6 +200,7 @@ gve_get_ethtool_stats(struct net_device *netdev, for (rx_pkts = 0, rx_bytes = 0, rx_hsplit_pkt = 0, rx_skb_alloc_fail = 0, rx_buf_alloc_fail = 0, rx_desc_err_dropped_pkt = 0, rx_hsplit_unsplit_pkt = 0, + xdp_tx_errors = 0, xdp_redirect_errors = 0, ring = 0; ring < priv->rx_cfg.num_queues; ring++) { if (priv->rx) { @@ -215,6 +218,9 @@ gve_get_ethtool_stats(struct net_device *netdev, rx->rx_desc_err_dropped_pkt; tmp_rx_hsplit_unsplit_pkt = rx->rx_hsplit_unsplit_pkt; + tmp_xdp_tx_errors = rx->xdp_tx_errors; + tmp_xdp_redirect_errors = + rx->xdp_redirect_errors; } while (u64_stats_fetch_retry(&priv->rx[ring].statss, start)); rx_pkts += tmp_rx_pkts; @@ -224,6 +230,8 @@ gve_get_ethtool_stats(struct net_device *netdev, rx_buf_alloc_fail += tmp_rx_buf_alloc_fail; rx_desc_err_dropped_pkt += tmp_rx_desc_err_dropped_pkt; rx_hsplit_unsplit_pkt += tmp_rx_hsplit_unsplit_pkt; + xdp_tx_errors += tmp_xdp_tx_errors; + xdp_redirect_errors += tmp_xdp_redirect_errors; } } for (tx_pkts = 0, tx_bytes = 0, tx_dropped = 0, ring = 0; @@ -249,8 +257,8 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = rx_bytes; data[i++] = tx_bytes; /* total rx dropped packets */ - data[i++] = rx_skb_alloc_fail + rx_buf_alloc_fail + - rx_desc_err_dropped_pkt; + data[i++] = rx_skb_alloc_fail + rx_desc_err_dropped_pkt + + xdp_tx_errors + xdp_redirect_errors; data[i++] = tx_dropped; data[i++] = priv->tx_timeo_cnt; data[i++] = rx_skb_alloc_fail; @@ -265,20 +273,38 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = priv->stats_report_trigger_cnt; i = GVE_MAIN_STATS_LEN; - /* For rx cross-reporting stats, start from nic rx stats in report */ - base_stats_idx = GVE_TX_STATS_REPORT_NUM * num_tx_queues + - GVE_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues; - /* The boundary between driver stats and NIC stats shifts if there are - * stopped queues. - */ - base_stats_idx += NIC_RX_STATS_REPORT_NUM * num_stopped_rxqs + - NIC_TX_STATS_REPORT_NUM * num_stopped_txqs; - max_stats_idx = NIC_RX_STATS_REPORT_NUM * - (priv->rx_cfg.num_queues - num_stopped_rxqs) + - base_stats_idx; + rx_base_stats_idx = 0; + max_rx_stats_idx = 0; + max_tx_stats_idx = 0; + stats_region_len = priv->stats_report_len - + sizeof(struct gve_stats_report); + nic_stats_len = (NIC_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues + + NIC_TX_STATS_REPORT_NUM * num_tx_queues) * sizeof(struct stats); + if (unlikely((stats_region_len - + nic_stats_len) % sizeof(struct stats))) { + net_err_ratelimited("Starting index of NIC stats should be multiple of stats size"); + } else { + /* For rx cross-reporting stats, + * start from nic rx stats in report + */ + rx_base_stats_idx = (stats_region_len - nic_stats_len) / + sizeof(struct stats); + /* The boundary between driver stats and NIC stats + * shifts if there are stopped queues + */ + rx_base_stats_idx += NIC_RX_STATS_REPORT_NUM * + num_stopped_rxqs + NIC_TX_STATS_REPORT_NUM * + num_stopped_txqs; + max_rx_stats_idx = NIC_RX_STATS_REPORT_NUM * + (priv->rx_cfg.num_queues - num_stopped_rxqs) + + rx_base_stats_idx; + max_tx_stats_idx = NIC_TX_STATS_REPORT_NUM * + (num_tx_queues - num_stopped_txqs) + + max_rx_stats_idx; + } /* Preprocess the stats report for rx, map queue id to start index */ skip_nic_stats = false; - for (stats_idx = base_stats_idx; stats_idx < max_stats_idx; + for (stats_idx = rx_base_stats_idx; stats_idx < max_rx_stats_idx; stats_idx += NIC_RX_STATS_REPORT_NUM) { u32 stat_name = be32_to_cpu(report_stats[stats_idx].stat_name); u32 queue_id = be32_to_cpu(report_stats[stats_idx].queue_id); @@ -311,6 +337,9 @@ gve_get_ethtool_stats(struct net_device *netdev, tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail; tmp_rx_desc_err_dropped_pkt = rx->rx_desc_err_dropped_pkt; + tmp_xdp_tx_errors = rx->xdp_tx_errors; + tmp_xdp_redirect_errors = + rx->xdp_redirect_errors; } while (u64_stats_fetch_retry(&priv->rx[ring].statss, start)); data[i++] = tmp_rx_bytes; @@ -321,8 +350,9 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = rx->rx_frag_alloc_cnt; /* rx dropped packets */ data[i++] = tmp_rx_skb_alloc_fail + - tmp_rx_buf_alloc_fail + - tmp_rx_desc_err_dropped_pkt; + tmp_rx_desc_err_dropped_pkt + + tmp_xdp_tx_errors + + tmp_xdp_redirect_errors; data[i++] = rx->rx_copybreak_pkt; data[i++] = rx->rx_copied_pkt; /* stats from NIC */ @@ -354,14 +384,9 @@ gve_get_ethtool_stats(struct net_device *netdev, i += priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS; } - /* For tx cross-reporting stats, start from nic tx stats in report */ - base_stats_idx = max_stats_idx; - max_stats_idx = NIC_TX_STATS_REPORT_NUM * - (num_tx_queues - num_stopped_txqs) + - max_stats_idx; - /* Preprocess the stats report for tx, map queue id to start index */ skip_nic_stats = false; - for (stats_idx = base_stats_idx; stats_idx < max_stats_idx; + /* NIC TX stats start right after NIC RX stats */ + for (stats_idx = max_rx_stats_idx; stats_idx < max_tx_stats_idx; stats_idx += NIC_TX_STATS_REPORT_NUM) { u32 stat_name = be32_to_cpu(report_stats[stats_idx].stat_name); u32 queue_id = be32_to_cpu(report_stats[stats_idx].queue_id); diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 1be1b1ef31ee30..030800776ead17 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -283,9 +283,9 @@ static int gve_alloc_stats_report(struct gve_priv *priv) int tx_stats_num, rx_stats_num; tx_stats_num = (GVE_TX_STATS_REPORT_NUM + NIC_TX_STATS_REPORT_NUM) * - gve_num_tx_queues(priv); + priv->tx_cfg.max_queues; rx_stats_num = (GVE_RX_STATS_REPORT_NUM + NIC_RX_STATS_REPORT_NUM) * - priv->rx_cfg.num_queues; + priv->rx_cfg.max_queues; priv->stats_report_len = struct_size(priv->stats_report, stats, size_add(tx_stats_num, rx_stats_num)); priv->stats_report = @@ -558,7 +558,7 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv) block->priv = priv; err = request_irq(priv->msix_vectors[msix_idx].vector, gve_is_gqi(priv) ? gve_intr : gve_intr_dqo, - 0, block->name, block); + IRQF_NO_AUTOEN, block->name, block); if (err) { dev_err(&priv->pdev->dev, "Failed to receive msix vector %d\n", i); diff --git a/drivers/net/ethernet/google/gve/gve_utils.c b/drivers/net/ethernet/google/gve/gve_utils.c index ace9b8698021f0..b53b7fcdcdaf16 100644 --- a/drivers/net/ethernet/google/gve/gve_utils.c +++ b/drivers/net/ethernet/google/gve/gve_utils.c @@ -112,11 +112,13 @@ void gve_add_napi(struct gve_priv *priv, int ntfy_idx, netif_napi_add_locked(priv->dev, &block->napi, gve_poll); netif_napi_set_irq_locked(&block->napi, block->irq); + enable_irq(block->irq); } void gve_remove_napi(struct gve_priv *priv, int ntfy_idx) { struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; + disable_irq(block->irq); netif_napi_del_locked(&block->napi); } diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c index e11495b7ee98ca..7234618e8e8187 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c @@ -160,7 +160,6 @@ static pci_ers_result_t hbg_pci_err_slot_reset(struct pci_dev *pdev) pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); hbg_err_reset(priv); return PCI_ERS_RESULT_RECOVERED; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index bfa5568baa926b..c8eba180250e75 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1048,13 +1048,13 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring) int order; if (!alloc_size) - return; + goto not_init; order = get_order(alloc_size); if (order > MAX_PAGE_ORDER) { if (net_ratelimit()) dev_warn(ring_to_dev(ring), "failed to allocate tx spare buffer, exceed to max order\n"); - return; + goto not_init; } tx_spare = devm_kzalloc(ring_to_dev(ring), sizeof(*tx_spare), @@ -1092,6 +1092,13 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring) devm_kfree(ring_to_dev(ring), tx_spare); devm_kzalloc_error: ring->tqp->handle->kinfo.tx_spare_buf_size = 0; +not_init: + /* When driver init or reset_init, the ring->tx_spare is always NULL; + * but when called from hns3_set_ringparam, it's usually not NULL, and + * will be restored if hns3_init_all_ring() failed. So it's safe to set + * ring->tx_spare to NULL here. + */ + ring->tx_spare = NULL; } /* Use hns3_tx_spare_space() to make sure there is enough buffer @@ -2500,44 +2507,47 @@ static netdev_features_t hns3_features_check(struct sk_buff *skb, static void hns3_fetch_stats(struct rtnl_link_stats64 *stats, struct hns3_enet_ring *ring, bool is_tx) { + struct ring_stats ring_stats; unsigned int start; do { start = u64_stats_fetch_begin(&ring->syncp); - if (is_tx) { - stats->tx_bytes += ring->stats.tx_bytes; - stats->tx_packets += ring->stats.tx_pkts; - stats->tx_dropped += ring->stats.sw_err_cnt; - stats->tx_dropped += ring->stats.tx_vlan_err; - stats->tx_dropped += ring->stats.tx_l4_proto_err; - stats->tx_dropped += ring->stats.tx_l2l3l4_err; - stats->tx_dropped += ring->stats.tx_tso_err; - stats->tx_dropped += ring->stats.over_max_recursion; - stats->tx_dropped += ring->stats.hw_limitation; - stats->tx_dropped += ring->stats.copy_bits_err; - stats->tx_dropped += ring->stats.skb2sgl_err; - stats->tx_dropped += ring->stats.map_sg_err; - stats->tx_errors += ring->stats.sw_err_cnt; - stats->tx_errors += ring->stats.tx_vlan_err; - stats->tx_errors += ring->stats.tx_l4_proto_err; - stats->tx_errors += ring->stats.tx_l2l3l4_err; - stats->tx_errors += ring->stats.tx_tso_err; - stats->tx_errors += ring->stats.over_max_recursion; - stats->tx_errors += ring->stats.hw_limitation; - stats->tx_errors += ring->stats.copy_bits_err; - stats->tx_errors += ring->stats.skb2sgl_err; - stats->tx_errors += ring->stats.map_sg_err; - } else { - stats->rx_bytes += ring->stats.rx_bytes; - stats->rx_packets += ring->stats.rx_pkts; - stats->rx_dropped += ring->stats.l2_err; - stats->rx_errors += ring->stats.l2_err; - stats->rx_errors += ring->stats.l3l4_csum_err; - stats->rx_crc_errors += ring->stats.l2_err; - stats->multicast += ring->stats.rx_multicast; - stats->rx_length_errors += ring->stats.err_pkt_len; - } + ring_stats = ring->stats; } while (u64_stats_fetch_retry(&ring->syncp, start)); + + if (is_tx) { + stats->tx_bytes += ring_stats.tx_bytes; + stats->tx_packets += ring_stats.tx_pkts; + stats->tx_dropped += ring_stats.sw_err_cnt; + stats->tx_dropped += ring_stats.tx_vlan_err; + stats->tx_dropped += ring_stats.tx_l4_proto_err; + stats->tx_dropped += ring_stats.tx_l2l3l4_err; + stats->tx_dropped += ring_stats.tx_tso_err; + stats->tx_dropped += ring_stats.over_max_recursion; + stats->tx_dropped += ring_stats.hw_limitation; + stats->tx_dropped += ring_stats.copy_bits_err; + stats->tx_dropped += ring_stats.skb2sgl_err; + stats->tx_dropped += ring_stats.map_sg_err; + stats->tx_errors += ring_stats.sw_err_cnt; + stats->tx_errors += ring_stats.tx_vlan_err; + stats->tx_errors += ring_stats.tx_l4_proto_err; + stats->tx_errors += ring_stats.tx_l2l3l4_err; + stats->tx_errors += ring_stats.tx_tso_err; + stats->tx_errors += ring_stats.over_max_recursion; + stats->tx_errors += ring_stats.hw_limitation; + stats->tx_errors += ring_stats.copy_bits_err; + stats->tx_errors += ring_stats.skb2sgl_err; + stats->tx_errors += ring_stats.map_sg_err; + } else { + stats->rx_bytes += ring_stats.rx_bytes; + stats->rx_packets += ring_stats.rx_pkts; + stats->rx_dropped += ring_stats.l2_err; + stats->rx_errors += ring_stats.l2_err; + stats->rx_errors += ring_stats.l3l4_csum_err; + stats->rx_crc_errors += ring_stats.l2_err; + stats->multicast += ring_stats.rx_multicast; + stats->rx_length_errors += ring_stats.err_pkt_len; + } } static void hns3_nic_get_stats64(struct net_device *netdev, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 9bb708fa42f24e..416e02e7b995fc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -731,7 +731,7 @@ struct hclge_fd_tcam_config_3_cmd { #define HCLGE_FD_AD_QID_M GENMASK(11, 2) #define HCLGE_FD_AD_USE_COUNTER_B 12 #define HCLGE_FD_AD_COUNTER_NUM_S 13 -#define HCLGE_FD_AD_COUNTER_NUM_M GENMASK(20, 13) +#define HCLGE_FD_AD_COUNTER_NUM_M GENMASK(19, 13) #define HCLGE_FD_AD_NXT_STEP_B 20 #define HCLGE_FD_AD_NXT_KEY_S 21 #define HCLGE_FD_AD_NXT_KEY_M GENMASK(25, 21) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 782bb48c9f3d77..5cc5ee9dcd982d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -5690,7 +5690,7 @@ static int hclge_fd_ad_config(struct hclge_dev *hdev, u8 stage, int loc, HCLGE_FD_AD_COUNTER_NUM_S, action->counter_id); hnae3_set_bit(ad_data, HCLGE_FD_AD_NXT_STEP_B, action->use_next_stage); hnae3_set_field(ad_data, HCLGE_FD_AD_NXT_KEY_M, HCLGE_FD_AD_NXT_KEY_S, - action->counter_id); + action->next_input_key); req->ad_data = cpu_to_le64(ad_data); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -10562,6 +10562,9 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, bool writen_to_tbl = false; int ret = 0; + if (vlan_id >= VLAN_N_VID) + return -EINVAL; + /* When device is resetting or reset failed, firmware is unable to * handle mailbox. Just record the vlan id, and remove it after * reset finished. diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index c7ff12a6c0764d..b7d4e06a55d40e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -193,10 +193,10 @@ static int hclge_get_ring_chain_from_mbx( return -EINVAL; for (i = 0; i < ring_num; i++) { - if (req->msg.param[i].tqp_index >= vport->nic.kinfo.rss_size) { + if (req->msg.param[i].tqp_index >= vport->nic.kinfo.num_tqps) { dev_err(&hdev->pdev->dev, "tqp index(%u) is out of range(0-%u)\n", req->msg.param[i].tqp_index, - vport->nic.kinfo.rss_size - 1U); + vport->nic.kinfo.num_tqps - 1U); return -EINVAL; } } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 8fcf220a120d21..70327a73dee326 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -368,12 +368,12 @@ static int hclgevf_knic_setup(struct hclgevf_dev *hdev) new_tqps = kinfo->rss_size * num_tc; kinfo->num_tqps = min(new_tqps, hdev->num_tqps); - kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, kinfo->num_tqps, + kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, hdev->num_tqps, sizeof(struct hnae3_queue *), GFP_KERNEL); if (!kinfo->tqp) return -ENOMEM; - for (i = 0; i < kinfo->num_tqps; i++) { + for (i = 0; i < hdev->num_tqps; i++) { hdev->htqp[i].q.handle = &hdev->nic; hdev->htqp[i].q.tqp_index = i; kinfo->tqp[i] = &hdev->htqp[i].q; diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c index a69b361225e90a..84bee5d6e638e1 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c @@ -43,21 +43,12 @@ static void qp_add_napi(struct hinic3_irq_cfg *irq_cfg) struct hinic3_nic_dev *nic_dev = netdev_priv(irq_cfg->netdev); netif_napi_add(nic_dev->netdev, &irq_cfg->napi, hinic3_poll); - netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id, - NETDEV_QUEUE_TYPE_RX, &irq_cfg->napi); - netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id, - NETDEV_QUEUE_TYPE_TX, &irq_cfg->napi); napi_enable(&irq_cfg->napi); } static void qp_del_napi(struct hinic3_irq_cfg *irq_cfg) { napi_disable(&irq_cfg->napi); - netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id, - NETDEV_QUEUE_TYPE_RX, NULL); - netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id, - NETDEV_QUEUE_TYPE_TX, NULL); - netif_stop_subqueue(irq_cfg->netdev, irq_cfg->irq_id); netif_napi_del(&irq_cfg->napi); } @@ -150,6 +141,11 @@ int hinic3_qps_irq_init(struct net_device *netdev) goto err_release_irqs; } + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_RX, &irq_cfg->napi); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_TX, &irq_cfg->napi); + hinic3_set_msix_auto_mask_state(nic_dev->hwdev, irq_cfg->msix_entry_idx, HINIC3_SET_MSIX_AUTO_MASK); @@ -164,6 +160,10 @@ int hinic3_qps_irq_init(struct net_device *netdev) q_id--; irq_cfg = &nic_dev->q_params.irq_cfg[q_id]; qp_del_napi(irq_cfg); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_RX, NULL); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_TX, NULL); hinic3_set_msix_state(nic_dev->hwdev, irq_cfg->msix_entry_idx, HINIC3_MSIX_DISABLE); hinic3_set_msix_auto_mask_state(nic_dev->hwdev, @@ -184,6 +184,10 @@ void hinic3_qps_irq_uninit(struct net_device *netdev) for (q_id = 0; q_id < nic_dev->q_params.num_qps; q_id++) { irq_cfg = &nic_dev->q_params.irq_cfg[q_id]; qp_del_napi(irq_cfg); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_RX, NULL); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_TX, NULL); hinic3_set_msix_state(nic_dev->hwdev, irq_cfg->msix_entry_idx, HINIC3_MSIX_DISABLE); hinic3_set_msix_auto_mask_state(nic_dev->hwdev, diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 292389aceb2d4a..7f078ec9c14c5f 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -4094,7 +4094,15 @@ static bool e1000_tbi_should_accept(struct e1000_adapter *adapter, u32 length, const u8 *data) { struct e1000_hw *hw = &adapter->hw; - u8 last_byte = *(data + length - 1); + u8 last_byte; + + /* Guard against OOB on data[length - 1] */ + if (unlikely(!length)) + return false; + /* Upper bound: length must not exceed rx_buffer_len */ + if (unlikely(length > adapter->rx_buffer_len)) + return false; + last_byte = *(data + length - 1); if (TBI_ACCEPT(hw, status, errors, length, last_byte)) { unsigned long irq_flags; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 201322dac23305..75896602e732cd 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7195,7 +7195,6 @@ static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev) "Cannot re-enable PCI device after reset.\n"); result = PCI_ERS_RESULT_DISCONNECT; } else { - pdev->state_saved = true; pci_restore_state(pdev); pci_set_master(pdev); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index ae5fe34659cfb1..d75b8a50413d2a 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -2423,12 +2423,6 @@ static pci_ers_result_t fm10k_io_slot_reset(struct pci_dev *pdev) } else { pci_set_master(pdev); pci_restore_state(pdev); - - /* After second error pci->state_saved is false, this - * resets it so EEH doesn't break. - */ - pci_save_state(pdev); - pci_wake_from_d3(pdev, false); result = PCI_ERS_RESULT_RECOVERED; diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 801a57a925dadc..feec9e1e13b36e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -1418,4 +1418,15 @@ static inline struct i40e_veb *i40e_pf_get_main_veb(struct i40e_pf *pf) return (pf->lan_veb != I40E_NO_VEB) ? pf->veb[pf->lan_veb] : NULL; } +static inline u32 i40e_get_max_num_descriptors(const struct i40e_pf *pf) +{ + const struct i40e_hw *hw = &pf->hw; + + switch (hw->mac.type) { + case I40E_MAC_XL710: + return I40E_MAX_NUM_DESCRIPTORS_XL710; + default: + return I40E_MAX_NUM_DESCRIPTORS; + } +} #endif /* _I40E_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 86c72596617a39..61c39e881b008e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2013,18 +2013,6 @@ static void i40e_get_drvinfo(struct net_device *netdev, drvinfo->n_priv_flags += I40E_GL_PRIV_FLAGS_STR_LEN; } -static u32 i40e_get_max_num_descriptors(struct i40e_pf *pf) -{ - struct i40e_hw *hw = &pf->hw; - - switch (hw->mac.type) { - case I40E_MAC_XL710: - return I40E_MAX_NUM_DESCRIPTORS_XL710; - default: - return I40E_MAX_NUM_DESCRIPTORS; - } -} - static void i40e_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, struct kernel_ethtool_ringparam *kernel_ring, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 50be0a60ae13b0..d3bc3207054f90 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2234,6 +2234,7 @@ static void i40e_set_rx_mode(struct net_device *netdev) vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; set_bit(__I40E_MACVLAN_SYNC_PENDING, vsi->back->state); } + i40e_service_event_schedule(vsi->back); } /** @@ -9029,7 +9030,6 @@ int i40e_open(struct net_device *netdev) TCP_FLAG_FIN | TCP_FLAG_CWR) >> 16); wr32(&pf->hw, I40E_GLLAN_TSOMSK_L, be32_to_cpu(TCP_FLAG_CWR) >> 16); - udp_tunnel_get_rx_info(netdev); return 0; } @@ -16455,7 +16455,6 @@ static pci_ers_result_t i40e_pci_error_slot_reset(struct pci_dev *pdev) } else { pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); pci_wake_from_d3(pdev, false); reg = rd32(&pf->hw, I40E_GLGEN_RTRIG); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 081a4526a2f000..cf831c649c9c57 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -656,7 +656,7 @@ static int i40e_config_vsi_tx_queue(struct i40e_vf *vf, u16 vsi_id, /* ring_len has to be multiple of 8 */ if (!IS_ALIGNED(info->ring_len, 8) || - info->ring_len > I40E_MAX_NUM_DESCRIPTORS_XL710) { + info->ring_len > i40e_get_max_num_descriptors(pf)) { ret = -EINVAL; goto error_context; } @@ -726,7 +726,7 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id, /* ring_len has to be multiple of 32 */ if (!IS_ALIGNED(info->ring_len, 32) || - info->ring_len > I40E_MAX_NUM_DESCRIPTORS_XL710) { + info->ring_len > i40e_get_max_num_descriptors(pf)) { ret = -EINVAL; goto error_param; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index c2fbe443ef853a..4b0fc8f354bc90 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1726,11 +1726,11 @@ static int iavf_config_rss_reg(struct iavf_adapter *adapter) u16 i; dw = (u32 *)adapter->rss_key; - for (i = 0; i <= adapter->rss_key_size / 4; i++) + for (i = 0; i < adapter->rss_key_size / 4; i++) wr32(hw, IAVF_VFQF_HKEY(i), dw[i]); dw = (u32 *)adapter->rss_lut; - for (i = 0; i <= adapter->rss_lut_size / 4; i++) + for (i = 0; i < adapter->rss_lut_size / 4; i++) wr32(hw, IAVF_VFQF_HLUT(i), dw[i]); iavf_flush(hw); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.c b/drivers/net/ethernet/intel/iavf/iavf_ptp.c index b4d5eda2e84fc1..9cbd8c15403183 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ptp.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.c @@ -252,6 +252,12 @@ static int iavf_ptp_gettimex64(struct ptp_clock_info *info, return iavf_read_phc_indirect(adapter, ts, sts); } +static int iavf_ptp_settime64(struct ptp_clock_info *info, + const struct timespec64 *ts) +{ + return -EOPNOTSUPP; +} + /** * iavf_ptp_cache_phc_time - Cache PHC time for performing timestamp extension * @adapter: private adapter structure @@ -320,6 +326,7 @@ static int iavf_ptp_register_clock(struct iavf_adapter *adapter) KBUILD_MODNAME, dev_name(dev)); ptp_info->owner = THIS_MODULE; ptp_info->gettimex64 = iavf_ptp_gettimex64; + ptp_info->settime64 = iavf_ptp_settime64; ptp_info->do_aux_work = iavf_ptp_do_aux_work; clock = ptp_clock_register(ptp_info, dev); diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index fb2de521731aee..ac071c5b4ce387 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -459,6 +459,8 @@ static void ice_devlink_reinit_down(struct ice_pf *pf) rtnl_lock(); ice_vsi_decfg(ice_get_main_vsi(pf)); rtnl_unlock(); + ice_deinit_pf(pf); + ice_deinit_hw(&pf->hw); ice_deinit_dev(pf); } @@ -1231,11 +1233,13 @@ static void ice_set_min_max_msix(struct ice_pf *pf) static int ice_devlink_reinit_up(struct ice_pf *pf) { struct ice_vsi *vsi = ice_get_main_vsi(pf); + struct device *dev = ice_pf_to_dev(pf); + bool need_dev_deinit = false; int err; err = ice_init_hw(&pf->hw); if (err) { - dev_err(ice_pf_to_dev(pf), "ice_init_hw failed: %d\n", err); + dev_err(dev, "ice_init_hw failed: %d\n", err); return err; } @@ -1246,13 +1250,19 @@ static int ice_devlink_reinit_up(struct ice_pf *pf) if (err) goto unroll_hw_init; + err = ice_init_pf(pf); + if (err) { + dev_err(dev, "ice_init_pf failed: %d\n", err); + goto unroll_dev_init; + } + vsi->flags = ICE_VSI_FLAG_INIT; rtnl_lock(); err = ice_vsi_cfg(vsi); rtnl_unlock(); if (err) - goto err_vsi_cfg; + goto unroll_pf_init; /* No need to take devl_lock, it's already taken by devlink API */ err = ice_load(pf); @@ -1265,10 +1275,14 @@ static int ice_devlink_reinit_up(struct ice_pf *pf) rtnl_lock(); ice_vsi_decfg(vsi); rtnl_unlock(); -err_vsi_cfg: - ice_deinit_dev(pf); +unroll_pf_init: + ice_deinit_pf(pf); +unroll_dev_init: + need_dev_deinit = true; unroll_hw_init: ice_deinit_hw(&pf->hw); + if (need_dev_deinit) + ice_deinit_dev(pf); return err; } diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 22b8323ff0d0e4..a23ccd4ba08d2c 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -977,6 +977,7 @@ void ice_map_xdp_rings(struct ice_vsi *vsi); int ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); +int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); int ice_set_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size); int ice_get_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size); int ice_set_rss_key(struct ice_vsi *vsi, u8 *seed); @@ -1029,11 +1030,15 @@ int ice_open(struct net_device *netdev); int ice_open_internal(struct net_device *netdev); int ice_stop(struct net_device *netdev); void ice_service_task_schedule(struct ice_pf *pf); +void ice_start_service_task(struct ice_pf *pf); int ice_load(struct ice_pf *pf); void ice_unload(struct ice_pf *pf); void ice_adv_lnk_speed_maps_init(void); +void ice_init_dev_hw(struct ice_pf *pf); int ice_init_dev(struct ice_pf *pf); void ice_deinit_dev(struct ice_pf *pf); +int ice_init_pf(struct ice_pf *pf); +void ice_deinit_pf(struct ice_pf *pf); int ice_change_mtu(struct net_device *netdev, int new_mtu); void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue); int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp); diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 2532b6f82e971e..eb148c8d9e0834 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1161,6 +1161,9 @@ int ice_init_hw(struct ice_hw *hw) status = ice_init_hw_tbls(hw); if (status) goto err_unroll_fltr_mgmt_struct; + + ice_init_dev_hw(hw->back); + mutex_init(&hw->tnl_lock); ice_init_chk_recipe_reuse_support(hw); @@ -2248,7 +2251,7 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res) /* there are some rare cases when trying to release the resource * results in an admin queue timeout, so handle them correctly */ - timeout = jiffies + 10 * ICE_CTL_Q_SQ_CMD_TIMEOUT; + timeout = jiffies + 10 * usecs_to_jiffies(ICE_CTL_Q_SQ_CMD_TIMEOUT); do { status = ice_aq_release_res(hw, res, 0, NULL); if (status != -EIO) diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index dc131779d4267a..06b5677e9bff81 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3621,11 +3621,7 @@ ice_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh) if (!lut) return -ENOMEM; - err = ice_get_rss_key(vsi, rxfh->key); - if (err) - goto out; - - err = ice_get_rss_lut(vsi, lut, vsi->rss_table_size); + err = ice_get_rss(vsi, rxfh->key, lut, vsi->rss_table_size); if (err) goto out; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 4479c824561e9b..3d14932871c58b 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -398,6 +398,8 @@ static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) if (!ring_stats) goto err_out; + u64_stats_init(&ring_stats->syncp); + WRITE_ONCE(tx_ring_stats[i], ring_stats); } @@ -417,6 +419,8 @@ static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) if (!ring_stats) goto err_out; + u64_stats_init(&ring_stats->syncp); + WRITE_ONCE(rx_ring_stats[i], ring_stats); } @@ -2780,12 +2784,14 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi) return; ice_for_each_rxq(vsi, q_idx) - netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, - &vsi->rx_rings[q_idx]->q_vector->napi); + if (vsi->rx_rings[q_idx] && vsi->rx_rings[q_idx]->q_vector) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, + &vsi->rx_rings[q_idx]->q_vector->napi); ice_for_each_txq(vsi, q_idx) - netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, - &vsi->tx_rings[q_idx]->q_vector->napi); + if (vsi->tx_rings[q_idx] && vsi->tx_rings[q_idx]->q_vector) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, + &vsi->tx_rings[q_idx]->q_vector->napi); /* Also set the interrupt number for the NAPI */ ice_for_each_q_vector(vsi, v_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; @@ -3806,22 +3812,31 @@ int ice_vsi_add_vlan_zero(struct ice_vsi *vsi) int ice_vsi_del_vlan_zero(struct ice_vsi *vsi) { struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + struct ice_pf *pf = vsi->back; struct ice_vlan vlan; int err; - vlan = ICE_VLAN(0, 0, 0); - err = vlan_ops->del_vlan(vsi, &vlan); - if (err && err != -EEXIST) - return err; + if (pf->lag && pf->lag->primary) { + dev_dbg(ice_pf_to_dev(pf), "Interface is primary in aggregate - not deleting prune list\n"); + } else { + vlan = ICE_VLAN(0, 0, 0); + err = vlan_ops->del_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + } /* in SVM both VLAN 0 filters are identical */ if (!ice_is_dvm_ena(&vsi->back->hw)) return 0; - vlan = ICE_VLAN(ETH_P_8021Q, 0, 0); - err = vlan_ops->del_vlan(vsi, &vlan); - if (err && err != -EEXIST) - return err; + if (pf->lag && pf->lag->primary) { + dev_dbg(ice_pf_to_dev(pf), "Interface is primary in aggregate - not deleting QinQ prune list\n"); + } else { + vlan = ICE_VLAN(ETH_P_8021Q, 0, 0); + err = vlan_ops->del_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + } /* when deleting the last VLAN filter, make sure to disable the VLAN * promisc mode so the filter isn't left by accident diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 86f5859e88ef53..f2b91f7f878618 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3323,18 +3323,20 @@ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data) if (ice_is_reset_in_progress(pf->state)) goto skip_irq; - if (test_and_clear_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread)) { - /* Process outstanding Tx timestamps. If there is more work, - * re-arm the interrupt to trigger again. - */ - if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) { - wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); - ice_flush(hw); - } - } + if (test_and_clear_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread)) + ice_ptp_process_ts(pf); skip_irq: ice_irq_dynamic_ena(hw, NULL, NULL); + ice_flush(hw); + + if (ice_ptp_tx_tstamps_pending(pf)) { + /* If any new Tx timestamps happened while in interrupt, + * re-arm the interrupt to trigger it again. + */ + wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); + ice_flush(hw); + } return IRQ_HANDLED; } @@ -3949,9 +3951,10 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf) * ice_deinit_pf - Unrolls initialziations done by ice_init_pf * @pf: board private structure to initialize */ -static void ice_deinit_pf(struct ice_pf *pf) +void ice_deinit_pf(struct ice_pf *pf) { - ice_service_task_stop(pf); + /* note that we unroll also on ice_init_pf() failure here */ + mutex_destroy(&pf->lag_mutex); mutex_destroy(&pf->adev_mutex); mutex_destroy(&pf->sw_mutex); @@ -3977,6 +3980,9 @@ static void ice_deinit_pf(struct ice_pf *pf) if (pf->ptp.clock) ptp_clock_unregister(pf->ptp.clock); + if (!xa_empty(&pf->irq_tracker.entries)) + ice_free_irq_msix_misc(pf); + xa_destroy(&pf->dyn_ports); xa_destroy(&pf->sf_nums); } @@ -4030,13 +4036,25 @@ static void ice_set_pf_caps(struct ice_pf *pf) pf->max_pf_rxqs = func_caps->common_cap.num_rxq; } +void ice_start_service_task(struct ice_pf *pf) +{ + timer_setup(&pf->serv_tmr, ice_service_timer, 0); + pf->serv_tmr_period = HZ; + INIT_WORK(&pf->serv_task, ice_service_task); + clear_bit(ICE_SERVICE_SCHED, pf->state); +} + /** * ice_init_pf - Initialize general software structures (struct ice_pf) * @pf: board private structure to initialize + * Return: 0 on success, negative errno otherwise. */ -static int ice_init_pf(struct ice_pf *pf) +int ice_init_pf(struct ice_pf *pf) { - ice_set_pf_caps(pf); + struct udp_tunnel_nic_info *udp_tunnel_nic = &pf->hw.udp_tunnel_nic; + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + int err = -ENOMEM; mutex_init(&pf->sw_mutex); mutex_init(&pf->tc_mutex); @@ -4049,32 +4067,7 @@ static int ice_init_pf(struct ice_pf *pf) init_waitqueue_head(&pf->reset_wait_queue); - /* setup service timer and periodic service task */ - timer_setup(&pf->serv_tmr, ice_service_timer, 0); - pf->serv_tmr_period = HZ; - INIT_WORK(&pf->serv_task, ice_service_task); - clear_bit(ICE_SERVICE_SCHED, pf->state); - mutex_init(&pf->avail_q_mutex); - pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); - if (!pf->avail_txqs) - return -ENOMEM; - - pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL); - if (!pf->avail_rxqs) { - bitmap_free(pf->avail_txqs); - pf->avail_txqs = NULL; - return -ENOMEM; - } - - pf->txtime_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); - if (!pf->txtime_txqs) { - bitmap_free(pf->avail_txqs); - pf->avail_txqs = NULL; - bitmap_free(pf->avail_rxqs); - pf->avail_rxqs = NULL; - return -ENOMEM; - } mutex_init(&pf->vfs.table_lock); hash_init(pf->vfs.table); @@ -4087,7 +4080,36 @@ static int ice_init_pf(struct ice_pf *pf) xa_init(&pf->dyn_ports); xa_init(&pf->sf_nums); + pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); + pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL); + pf->txtime_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); + if (!pf->avail_txqs || !pf->avail_rxqs || !pf->txtime_txqs) + goto undo_init; + + udp_tunnel_nic->set_port = ice_udp_tunnel_set_port; + udp_tunnel_nic->unset_port = ice_udp_tunnel_unset_port; + udp_tunnel_nic->shared = &hw->udp_tunnel_shared; + udp_tunnel_nic->tables[0].n_entries = hw->tnl.valid_count[TNL_VXLAN]; + udp_tunnel_nic->tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN; + udp_tunnel_nic->tables[1].n_entries = hw->tnl.valid_count[TNL_GENEVE]; + udp_tunnel_nic->tables[1].tunnel_types = UDP_TUNNEL_TYPE_GENEVE; + + /* In case of MSIX we are going to setup the misc vector right here + * to handle admin queue events etc. In case of legacy and MSI + * the misc functionality and queue processing is combined in + * the same vector and that gets setup at open. + */ + err = ice_req_irq_msix_misc(pf); + if (err) { + dev_err(dev, "setup of misc vector failed: %d\n", err); + goto undo_init; + } + return 0; +undo_init: + /* deinit handles half-initialized pf just fine */ + ice_deinit_pf(pf); + return err; } /** @@ -4722,9 +4744,8 @@ static void ice_decfg_netdev(struct ice_vsi *vsi) vsi->netdev = NULL; } -int ice_init_dev(struct ice_pf *pf) +void ice_init_dev_hw(struct ice_pf *pf) { - struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; int err; @@ -4744,61 +4765,28 @@ int ice_init_dev(struct ice_pf *pf) */ ice_set_safe_mode_caps(hw); } +} - err = ice_init_pf(pf); - if (err) { - dev_err(dev, "ice_init_pf failed: %d\n", err); - return err; - } - - pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port; - pf->hw.udp_tunnel_nic.unset_port = ice_udp_tunnel_unset_port; - pf->hw.udp_tunnel_nic.shared = &pf->hw.udp_tunnel_shared; - if (pf->hw.tnl.valid_count[TNL_VXLAN]) { - pf->hw.udp_tunnel_nic.tables[0].n_entries = - pf->hw.tnl.valid_count[TNL_VXLAN]; - pf->hw.udp_tunnel_nic.tables[0].tunnel_types = - UDP_TUNNEL_TYPE_VXLAN; - } - if (pf->hw.tnl.valid_count[TNL_GENEVE]) { - pf->hw.udp_tunnel_nic.tables[1].n_entries = - pf->hw.tnl.valid_count[TNL_GENEVE]; - pf->hw.udp_tunnel_nic.tables[1].tunnel_types = - UDP_TUNNEL_TYPE_GENEVE; - } +int ice_init_dev(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + ice_set_pf_caps(pf); err = ice_init_interrupt_scheme(pf); if (err) { dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err); - err = -EIO; - goto unroll_pf_init; + return -EIO; } - /* In case of MSIX we are going to setup the misc vector right here - * to handle admin queue events etc. In case of legacy and MSI - * the misc functionality and queue processing is combined in - * the same vector and that gets setup at open. - */ - err = ice_req_irq_msix_misc(pf); - if (err) { - dev_err(dev, "setup of misc vector failed: %d\n", err); - goto unroll_irq_scheme_init; - } + ice_start_service_task(pf); return 0; - -unroll_irq_scheme_init: - ice_clear_interrupt_scheme(pf); -unroll_pf_init: - ice_deinit_pf(pf); - return err; } void ice_deinit_dev(struct ice_pf *pf) { - ice_free_irq_msix_misc(pf); - ice_deinit_pf(pf); - ice_deinit_hw(&pf->hw); + ice_service_task_stop(pf); /* Service task is already stopped, so call reset directly. */ ice_reset(&pf->hw, ICE_RESET_PFR); @@ -4859,6 +4847,7 @@ static void ice_deinit_features(struct ice_pf *pf) ice_dpll_deinit(pf); if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) xa_destroy(&pf->eswitch.reprs); + ice_hwmon_exit(pf); } static void ice_init_wakeup(struct ice_pf *pf) @@ -5038,21 +5027,24 @@ static void ice_deinit_devlink(struct ice_pf *pf) static int ice_init(struct ice_pf *pf) { + struct device *dev = ice_pf_to_dev(pf); int err; - err = ice_init_dev(pf); - if (err) + err = ice_init_pf(pf); + if (err) { + dev_err(dev, "ice_init_pf failed: %d\n", err); return err; + } if (pf->hw.mac_type == ICE_MAC_E830) { err = pci_enable_ptm(pf->pdev, NULL); if (err) - dev_dbg(ice_pf_to_dev(pf), "PCIe PTM not supported by PCIe bus/controller\n"); + dev_dbg(dev, "PCIe PTM not supported by PCIe bus/controller\n"); } err = ice_alloc_vsis(pf); if (err) - goto err_alloc_vsis; + goto unroll_pf_init; err = ice_init_pf_sw(pf); if (err) @@ -5089,8 +5081,8 @@ static int ice_init(struct ice_pf *pf) ice_deinit_pf_sw(pf); err_init_pf_sw: ice_dealloc_vsis(pf); -err_alloc_vsis: - ice_deinit_dev(pf); +unroll_pf_init: + ice_deinit_pf(pf); return err; } @@ -5101,7 +5093,7 @@ static void ice_deinit(struct ice_pf *pf) ice_deinit_pf_sw(pf); ice_dealloc_vsis(pf); - ice_deinit_dev(pf); + ice_deinit_pf(pf); } /** @@ -5235,6 +5227,7 @@ static int ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) { struct device *dev = &pdev->dev; + bool need_dev_deinit = false; struct ice_adapter *adapter; struct ice_pf *pf; struct ice_hw *hw; @@ -5331,10 +5324,14 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) } pf->adapter = adapter; - err = ice_init(pf); + err = ice_init_dev(pf); if (err) goto unroll_adapter; + err = ice_init(pf); + if (err) + goto unroll_dev_init; + devl_lock(priv_to_devlink(pf)); err = ice_load(pf); if (err) @@ -5352,10 +5349,14 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) unroll_init: devl_unlock(priv_to_devlink(pf)); ice_deinit(pf); +unroll_dev_init: + need_dev_deinit = true; unroll_adapter: ice_adapter_put(pdev); unroll_hw_init: ice_deinit_hw(hw); + if (need_dev_deinit) + ice_deinit_dev(pf); return err; } @@ -5448,12 +5449,6 @@ static void ice_remove(struct pci_dev *pdev) ice_free_vfs(pf); } - ice_hwmon_exit(pf); - - ice_service_task_stop(pf); - ice_aq_cancel_waiting_tasks(pf); - set_bit(ICE_DOWN, pf->state); - if (!ice_is_safe_mode(pf)) ice_remove_arfs(pf); @@ -5471,6 +5466,11 @@ static void ice_remove(struct pci_dev *pdev) ice_set_wake(pf); ice_adapter_put(pdev); + ice_deinit_hw(&pf->hw); + + ice_deinit_dev(pf); + ice_aq_cancel_waiting_tasks(pf); + set_bit(ICE_DOWN, pf->state); } /** @@ -5663,7 +5663,6 @@ static int ice_resume(struct device *dev) pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); - pci_save_state(pdev); if (!pci_device_is_present(pdev)) return -ENODEV; @@ -5763,7 +5762,6 @@ static pci_ers_result_t ice_pci_err_slot_reset(struct pci_dev *pdev) } else { pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); pci_wake_from_d3(pdev, false); /* Check for life */ @@ -6995,7 +6993,6 @@ void ice_update_vsi_stats(struct ice_vsi *vsi) cur_ns->rx_errors = pf->stats.crc_errors + pf->stats.illegal_bytes + pf->stats.rx_undersize + - pf->hw_csum_rx_error + pf->stats.rx_jabber + pf->stats.rx_fragments + pf->stats.rx_oversize; @@ -7818,6 +7815,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) /* Restore timestamp mode settings after VSI rebuild */ ice_ptp_restore_timestamp_mode(pf); + + /* Start PTP periodic work after VSI is fully rebuilt */ + ice_ptp_queue_work(pf); return; err_vsi_rebuild: @@ -8003,6 +8003,34 @@ int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed) return status; } +/** + * ice_get_rss - Get RSS LUT and/or key + * @vsi: Pointer to VSI structure + * @seed: Buffer to store the key in + * @lut: Buffer to store the lookup table entries + * @lut_size: Size of buffer to store the lookup table entries + * + * Return: 0 on success, negative on failure + */ +int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) +{ + int err; + + if (seed) { + err = ice_get_rss_key(vsi, seed); + if (err) + return err; + } + + if (lut) { + err = ice_get_rss_lut(vsi, lut, lut_size); + if (err) + return err; + } + + return 0; +} + /** * ice_set_rss_hfunc - Set RSS HASH function * @vsi: Pointer to VSI structure @@ -9650,9 +9678,6 @@ int ice_open_internal(struct net_device *netdev) netdev_err(netdev, "Failed to open VSI 0x%04X on switch 0x%04X\n", vsi->vsi_num, vsi->vsw->sw_id); - /* Update existing tunnels information */ - udp_tunnel_get_rx_info(netdev); - return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 8ec0f7d0fcebdd..df38345b12d728 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -569,6 +569,9 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) pf = ptp_port_to_pf(ptp_port); hw = &pf->hw; + if (!tx->init) + return; + /* Read the Tx ready status first */ if (tx->has_ready_bitmap) { err = ice_get_phy_tx_tstamp_ready(hw, tx->block, &tstamp_ready); @@ -665,14 +668,9 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) } } -/** - * ice_ptp_tx_tstamp_owner - Process Tx timestamps for all ports on the device - * @pf: Board private structure - */ -static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf) +static void ice_ptp_tx_tstamp_owner(struct ice_pf *pf) { struct ice_ptp_port *port; - unsigned int i; mutex_lock(&pf->adapter->ports.lock); list_for_each_entry(port, &pf->adapter->ports.ports, list_node) { @@ -684,49 +682,6 @@ static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf) ice_ptp_process_tx_tstamp(tx); } mutex_unlock(&pf->adapter->ports.lock); - - for (i = 0; i < ICE_GET_QUAD_NUM(pf->hw.ptp.num_lports); i++) { - u64 tstamp_ready; - int err; - - /* Read the Tx ready status first */ - err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready); - if (err) - break; - else if (tstamp_ready) - return ICE_TX_TSTAMP_WORK_PENDING; - } - - return ICE_TX_TSTAMP_WORK_DONE; -} - -/** - * ice_ptp_tx_tstamp - Process Tx timestamps for this function. - * @tx: Tx tracking structure to initialize - * - * Returns: ICE_TX_TSTAMP_WORK_PENDING if there are any outstanding incomplete - * Tx timestamps, or ICE_TX_TSTAMP_WORK_DONE otherwise. - */ -static enum ice_tx_tstamp_work ice_ptp_tx_tstamp(struct ice_ptp_tx *tx) -{ - bool more_timestamps; - unsigned long flags; - - if (!tx->init) - return ICE_TX_TSTAMP_WORK_DONE; - - /* Process the Tx timestamp tracker */ - ice_ptp_process_tx_tstamp(tx); - - /* Check if there are outstanding Tx timestamps */ - spin_lock_irqsave(&tx->lock, flags); - more_timestamps = tx->init && !bitmap_empty(tx->in_use, tx->len); - spin_unlock_irqrestore(&tx->lock, flags); - - if (more_timestamps) - return ICE_TX_TSTAMP_WORK_PENDING; - - return ICE_TX_TSTAMP_WORK_DONE; } /** @@ -1338,9 +1293,12 @@ void ice_ptp_link_change(struct ice_pf *pf, bool linkup) /* Do not reconfigure E810 or E830 PHY */ return; case ICE_MAC_GENERIC: - case ICE_MAC_GENERIC_3K_E825: ice_ptp_port_phy_restart(ptp_port); return; + case ICE_MAC_GENERIC_3K_E825: + if (linkup) + ice_ptp_port_phy_restart(ptp_port); + return; default: dev_warn(ice_pf_to_dev(pf), "%s: Unknown PHY type\n", __func__); } @@ -2656,30 +2614,92 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) return idx + tx->offset; } -/** - * ice_ptp_process_ts - Process the PTP Tx timestamps - * @pf: Board private structure - * - * Returns: ICE_TX_TSTAMP_WORK_PENDING if there are any outstanding Tx - * timestamps that need processing, and ICE_TX_TSTAMP_WORK_DONE otherwise. - */ -enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf) +void ice_ptp_process_ts(struct ice_pf *pf) { switch (pf->ptp.tx_interrupt_mode) { case ICE_PTP_TX_INTERRUPT_NONE: /* This device has the clock owner handle timestamps for it */ - return ICE_TX_TSTAMP_WORK_DONE; + return; case ICE_PTP_TX_INTERRUPT_SELF: /* This device handles its own timestamps */ - return ice_ptp_tx_tstamp(&pf->ptp.port.tx); + ice_ptp_process_tx_tstamp(&pf->ptp.port.tx); + return; case ICE_PTP_TX_INTERRUPT_ALL: /* This device handles timestamps for all ports */ - return ice_ptp_tx_tstamp_owner(pf); + ice_ptp_tx_tstamp_owner(pf); + return; + default: + WARN_ONCE(1, "Unexpected Tx timestamp interrupt mode %u\n", + pf->ptp.tx_interrupt_mode); + return; + } +} + +static bool ice_port_has_timestamps(struct ice_ptp_tx *tx) +{ + bool more_timestamps; + + scoped_guard(spinlock_irqsave, &tx->lock) { + if (!tx->init) + return false; + + more_timestamps = !bitmap_empty(tx->in_use, tx->len); + } + + return more_timestamps; +} + +static bool ice_any_port_has_timestamps(struct ice_pf *pf) +{ + struct ice_ptp_port *port; + + scoped_guard(mutex, &pf->adapter->ports.lock) { + list_for_each_entry(port, &pf->adapter->ports.ports, + list_node) { + struct ice_ptp_tx *tx = &port->tx; + + if (ice_port_has_timestamps(tx)) + return true; + } + } + + return false; +} + +bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + unsigned int i; + + /* Check software indicator */ + switch (pf->ptp.tx_interrupt_mode) { + case ICE_PTP_TX_INTERRUPT_NONE: + return false; + case ICE_PTP_TX_INTERRUPT_SELF: + if (ice_port_has_timestamps(&pf->ptp.port.tx)) + return true; + break; + case ICE_PTP_TX_INTERRUPT_ALL: + if (ice_any_port_has_timestamps(pf)) + return true; + break; default: WARN_ONCE(1, "Unexpected Tx timestamp interrupt mode %u\n", pf->ptp.tx_interrupt_mode); - return ICE_TX_TSTAMP_WORK_DONE; + break; + } + + /* Check hardware indicator */ + for (i = 0; i < ICE_GET_QUAD_NUM(hw->ptp.num_lports); i++) { + u64 tstamp_ready = 0; + int err; + + err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready); + if (err || tstamp_ready) + return true; } + + return false; } /** @@ -2731,7 +2751,9 @@ irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) return IRQ_WAKE_THREAD; case ICE_MAC_E830: /* E830 can read timestamps in the top half using rd32() */ - if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) { + ice_ptp_process_ts(pf); + + if (ice_ptp_tx_tstamps_pending(pf)) { /* Process outstanding Tx timestamps. If there * is more work, re-arm the interrupt to trigger again. */ @@ -2810,6 +2832,20 @@ static void ice_ptp_periodic_work(struct kthread_work *work) msecs_to_jiffies(err ? 10 : 500)); } +/** + * ice_ptp_queue_work - Queue PTP periodic work for a PF + * @pf: Board private structure + * + * Helper function to queue PTP periodic work after VSI rebuild completes. + * This ensures that PTP work only runs when VSI structures are ready. + */ +void ice_ptp_queue_work(struct ice_pf *pf) +{ + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags) && + pf->ptp.state == ICE_PTP_READY) + kthread_queue_delayed_work(pf->ptp.kworker, &pf->ptp.work, 0); +} + /** * ice_ptp_prepare_rebuild_sec - Prepare second NAC for PTP reset or rebuild * @pf: Board private structure @@ -2828,10 +2864,15 @@ static void ice_ptp_prepare_rebuild_sec(struct ice_pf *pf, bool rebuild, struct ice_pf *peer_pf = ptp_port_to_pf(port); if (!ice_is_primary(&peer_pf->hw)) { - if (rebuild) + if (rebuild) { + /* TODO: When implementing rebuild=true: + * 1. Ensure secondary PFs' VSIs are rebuilt + * 2. Call ice_ptp_queue_work(peer_pf) after VSI rebuild + */ ice_ptp_rebuild(peer_pf, reset_type); - else + } else { ice_ptp_prepare_for_reset(peer_pf, reset_type); + } } } } @@ -2977,9 +3018,6 @@ void ice_ptp_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ptp->state = ICE_PTP_READY; - /* Start periodic work going */ - kthread_queue_delayed_work(ptp->kworker, &ptp->work, 0); - dev_info(ice_pf_to_dev(pf), "PTP reset successful\n"); return; @@ -3184,8 +3222,9 @@ static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf) { switch (pf->hw.mac_type) { case ICE_MAC_GENERIC: - /* E822 based PHY has the clock owner process the interrupt - * for all ports. + case ICE_MAC_GENERIC_3K_E825: + /* E82x hardware has the clock owner process timestamps for + * all ports. */ if (ice_pf_src_tmr_owned(pf)) pf->ptp.tx_interrupt_mode = ICE_PTP_TX_INTERRUPT_ALL; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 137f2070a2d991..4e02f922c1ff8a 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -302,8 +302,9 @@ void ice_ptp_extts_event(struct ice_pf *pf); s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx); void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx); -enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf); +void ice_ptp_process_ts(struct ice_pf *pf); irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf); +bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf); u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts); @@ -315,6 +316,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf, void ice_ptp_init(struct ice_pf *pf); void ice_ptp_release(struct ice_pf *pf); void ice_ptp_link_change(struct ice_pf *pf, bool linkup); +void ice_ptp_queue_work(struct ice_pf *pf); #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ static inline int ice_ptp_hwtstamp_get(struct net_device *netdev, @@ -343,16 +345,18 @@ static inline void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) static inline void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx) { } -static inline bool ice_ptp_process_ts(struct ice_pf *pf) -{ - return true; -} +static inline void ice_ptp_process_ts(struct ice_pf *pf) { } static inline irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) { return IRQ_HANDLED; } +static inline bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf) +{ + return false; +} + static inline u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) { @@ -381,6 +385,10 @@ static inline void ice_ptp_link_change(struct ice_pf *pf, bool linkup) { } +static inline void ice_ptp_queue_work(struct ice_pf *pf) +{ +} + static inline int ice_ptp_clock_index(struct ice_pf *pf) { return -1; diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h index ca4da0c8997947..c74c47bc0b9b9f 100644 --- a/drivers/net/ethernet/intel/idpf/idpf.h +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -131,14 +131,12 @@ enum idpf_cap_field { /** * enum idpf_vport_state - Current vport state - * @__IDPF_VPORT_DOWN: Vport is down - * @__IDPF_VPORT_UP: Vport is up - * @__IDPF_VPORT_STATE_LAST: Must be last, number of states + * @IDPF_VPORT_UP: Vport is up + * @IDPF_VPORT_STATE_NBITS: Must be last, number of states */ enum idpf_vport_state { - __IDPF_VPORT_DOWN, - __IDPF_VPORT_UP, - __IDPF_VPORT_STATE_LAST, + IDPF_VPORT_UP, + IDPF_VPORT_STATE_NBITS }; /** @@ -162,7 +160,7 @@ struct idpf_netdev_priv { u16 vport_idx; u16 max_tx_hdr_size; u16 tx_max_bufs; - enum idpf_vport_state state; + DECLARE_BITMAP(state, IDPF_VPORT_STATE_NBITS); struct rtnl_link_stats64 netstats; spinlock_t stats_lock; }; @@ -286,8 +284,7 @@ struct idpf_port_stats { struct idpf_fsteer_fltr { struct list_head list; - u32 loc; - u32 q_index; + struct ethtool_rx_flow_spec fs; }; /** @@ -426,14 +423,12 @@ enum idpf_user_flags { * @rss_key: RSS hash key * @rss_lut_size: Size of RSS lookup table * @rss_lut: RSS lookup table - * @cached_lut: Used to restore previously init RSS lut */ struct idpf_rss_data { u16 rss_key_size; u8 *rss_key; u16 rss_lut_size; u32 *rss_lut; - u32 *cached_lut; }; /** @@ -560,6 +555,7 @@ struct idpf_vector_lifo { * @max_q: Maximum possible queues * @req_qs_chunks: Queue chunk data for requested queues * @mac_filter_list_lock: Lock to protect mac filters + * @flow_steer_list_lock: Lock to protect fsteer filters * @flags: See enum idpf_vport_config_flags */ struct idpf_vport_config { @@ -567,6 +563,7 @@ struct idpf_vport_config { struct idpf_vport_max_q max_q; struct virtchnl2_add_queues *req_qs_chunks; spinlock_t mac_filter_list_lock; + spinlock_t flow_steer_list_lock; DECLARE_BITMAP(flags, IDPF_VPORT_CONFIG_FLAGS_NBITS); }; diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c index a5a1eec9ade8bd..3e191cf528b690 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c @@ -18,6 +18,7 @@ static int idpf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, { struct idpf_netdev_priv *np = netdev_priv(netdev); struct idpf_vport_user_config_data *user_config; + struct idpf_vport_config *vport_config; struct idpf_fsteer_fltr *f; struct idpf_vport *vport; unsigned int cnt = 0; @@ -25,7 +26,8 @@ static int idpf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); - user_config = &np->adapter->vport_config[np->vport_idx]->user_config; + vport_config = np->adapter->vport_config[np->vport_idx]; + user_config = &vport_config->user_config; switch (cmd->cmd) { case ETHTOOL_GRXRINGS: @@ -36,26 +38,34 @@ static int idpf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, cmd->data = idpf_fsteer_max_rules(vport); break; case ETHTOOL_GRXCLSRULE: - err = -EINVAL; + err = -ENOENT; + spin_lock_bh(&vport_config->flow_steer_list_lock); list_for_each_entry(f, &user_config->flow_steer_list, list) - if (f->loc == cmd->fs.location) { - cmd->fs.ring_cookie = f->q_index; + if (f->fs.location == cmd->fs.location) { + /* Avoid infoleak from padding: zero first, + * then assign fields + */ + memset(&cmd->fs, 0, sizeof(cmd->fs)); + cmd->fs = f->fs; err = 0; break; } + spin_unlock_bh(&vport_config->flow_steer_list_lock); break; case ETHTOOL_GRXCLSRLALL: cmd->data = idpf_fsteer_max_rules(vport); + spin_lock_bh(&vport_config->flow_steer_list_lock); list_for_each_entry(f, &user_config->flow_steer_list, list) { if (cnt == cmd->rule_cnt) { err = -EMSGSIZE; break; } - rule_locs[cnt] = f->loc; + rule_locs[cnt] = f->fs.location; cnt++; } if (!err) cmd->rule_cnt = user_config->num_fsteer_fltrs; + spin_unlock_bh(&vport_config->flow_steer_list_lock); break; default: break; @@ -152,7 +162,7 @@ static int idpf_add_flow_steer(struct net_device *netdev, struct idpf_vport *vport; u32 flow_type, q_index; u16 num_rxq; - int err; + int err = 0; vport = idpf_netdev_to_vport(netdev); vport_config = vport->adapter->vport_config[np->vport_idx]; @@ -178,6 +188,29 @@ static int idpf_add_flow_steer(struct net_device *netdev, if (!rule) return -ENOMEM; + fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); + if (!fltr) { + err = -ENOMEM; + goto out_free_rule; + } + + /* detect duplicate entry and reject before adding rules */ + spin_lock_bh(&vport_config->flow_steer_list_lock); + list_for_each_entry(f, &user_config->flow_steer_list, list) { + if (f->fs.location == fsp->location) { + err = -EEXIST; + break; + } + + if (f->fs.location > fsp->location) + break; + parent = f; + } + spin_unlock_bh(&vport_config->flow_steer_list_lock); + + if (err) + goto out; + rule->vport_id = cpu_to_le32(vport->vport_id); rule->count = cpu_to_le32(1); info = &rule->rule_info[0]; @@ -216,26 +249,20 @@ static int idpf_add_flow_steer(struct net_device *netdev, goto out; } - fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); - if (!fltr) { - err = -ENOMEM; - goto out; - } - - fltr->loc = fsp->location; - fltr->q_index = q_index; - list_for_each_entry(f, &user_config->flow_steer_list, list) { - if (f->loc >= fltr->loc) - break; - parent = f; - } + /* Save a copy of the user's flow spec so ethtool can later retrieve it */ + fltr->fs = *fsp; + spin_lock_bh(&vport_config->flow_steer_list_lock); parent ? list_add(&fltr->list, &parent->list) : list_add(&fltr->list, &user_config->flow_steer_list); user_config->num_fsteer_fltrs++; + spin_unlock_bh(&vport_config->flow_steer_list_lock); + goto out_free_rule; out: + kfree(fltr); +out_free_rule: kfree(rule); return err; } @@ -286,17 +313,20 @@ static int idpf_del_flow_steer(struct net_device *netdev, goto out; } + spin_lock_bh(&vport_config->flow_steer_list_lock); list_for_each_entry_safe(f, iter, &user_config->flow_steer_list, list) { - if (f->loc == fsp->location) { + if (f->fs.location == fsp->location) { list_del(&f->list); kfree(f); user_config->num_fsteer_fltrs--; - goto out; + goto out_unlock; } } - err = -EINVAL; + err = -ENOENT; +out_unlock: + spin_unlock_bh(&vport_config->flow_steer_list_lock); out: kfree(rule); return err; @@ -365,7 +395,10 @@ static u32 idpf_get_rxfh_indir_size(struct net_device *netdev) * @netdev: network interface device structure * @rxfh: pointer to param struct (indir, key, hfunc) * - * Reads the indirection table directly from the hardware. Always returns 0. + * RSS LUT and Key information are read from driver's cached + * copy. When rxhash is off, rss lut will be displayed as zeros. + * + * Return: 0 on success, -errno otherwise. */ static int idpf_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh) @@ -373,10 +406,13 @@ static int idpf_get_rxfh(struct net_device *netdev, struct idpf_netdev_priv *np = netdev_priv(netdev); struct idpf_rss_data *rss_data; struct idpf_adapter *adapter; + struct idpf_vport *vport; + bool rxhash_ena; int err = 0; u16 i; idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); adapter = np->adapter; @@ -386,9 +422,8 @@ static int idpf_get_rxfh(struct net_device *netdev, } rss_data = &adapter->vport_config[np->vport_idx]->user_config.rss_data; - if (np->state != __IDPF_VPORT_UP) - goto unlock_mutex; + rxhash_ena = idpf_is_feature_ena(vport, NETIF_F_RXHASH); rxfh->hfunc = ETH_RSS_HASH_TOP; if (rxfh->key) @@ -396,7 +431,7 @@ static int idpf_get_rxfh(struct net_device *netdev, if (rxfh->indir) { for (i = 0; i < rss_data->rss_lut_size; i++) - rxfh->indir[i] = rss_data->rss_lut[i]; + rxfh->indir[i] = rxhash_ena ? rss_data->rss_lut[i] : 0; } unlock_mutex: @@ -436,8 +471,6 @@ static int idpf_set_rxfh(struct net_device *netdev, } rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; - if (np->state != __IDPF_VPORT_UP) - goto unlock_mutex; if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE && rxfh->hfunc != ETH_RSS_HASH_TOP) { @@ -453,7 +486,8 @@ static int idpf_set_rxfh(struct net_device *netdev, rss_data->rss_lut[lut] = rxfh->indir[lut]; } - err = idpf_config_rss(vport); + if (test_bit(IDPF_VPORT_UP, np->state)) + err = idpf_config_rss(vport); unlock_mutex: idpf_vport_ctrl_unlock(netdev); @@ -1167,7 +1201,7 @@ static void idpf_get_ethtool_stats(struct net_device *netdev, idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); - if (np->state != __IDPF_VPORT_UP) { + if (!test_bit(IDPF_VPORT_UP, np->state)) { idpf_vport_ctrl_unlock(netdev); return; @@ -1319,7 +1353,7 @@ static int idpf_get_q_coalesce(struct net_device *netdev, idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); - if (np->state != __IDPF_VPORT_UP) + if (!test_bit(IDPF_VPORT_UP, np->state)) goto unlock_mutex; if (q_num >= vport->num_rxq && q_num >= vport->num_txq) { @@ -1507,7 +1541,7 @@ static int idpf_set_coalesce(struct net_device *netdev, idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); - if (np->state != __IDPF_VPORT_UP) + if (!test_bit(IDPF_VPORT_UP, np->state)) goto unlock_mutex; for (i = 0; i < vport->num_txq; i++) { @@ -1710,7 +1744,7 @@ static void idpf_get_ts_stats(struct net_device *netdev, ts_stats->err = u64_stats_read(&vport->tstamp_stats.discarded); } while (u64_stats_fetch_retry(&vport->tstamp_stats.stats_sync, start)); - if (np->state != __IDPF_VPORT_UP) + if (!test_bit(IDPF_VPORT_UP, np->state)) goto exit; for (u16 i = 0; i < vport->num_txq_grp; i++) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c index 7e20a07e98e538..6dad0593f7f222 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_idc.c +++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c @@ -322,7 +322,7 @@ static void idpf_idc_vport_dev_down(struct idpf_adapter *adapter) for (i = 0; i < adapter->num_alloc_vports; i++) { struct idpf_vport *vport = adapter->vports[i]; - if (!vport) + if (!vport || !vport->vdev_info) continue; idpf_unplug_aux_dev(vport->vdev_info->adev); diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 8a941f0fb048b4..131a8121839bd0 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -442,6 +442,29 @@ int idpf_intr_req(struct idpf_adapter *adapter) return err; } +/** + * idpf_del_all_flow_steer_filters - Delete all flow steer filters in list + * @vport: main vport struct + * + * Takes flow_steer_list_lock spinlock. Deletes all filters + */ +static void idpf_del_all_flow_steer_filters(struct idpf_vport *vport) +{ + struct idpf_vport_config *vport_config; + struct idpf_fsteer_fltr *f, *ftmp; + + vport_config = vport->adapter->vport_config[vport->idx]; + + spin_lock_bh(&vport_config->flow_steer_list_lock); + list_for_each_entry_safe(f, ftmp, &vport_config->user_config.flow_steer_list, + list) { + list_del(&f->list); + kfree(f); + } + vport_config->user_config.num_fsteer_fltrs = 0; + spin_unlock_bh(&vport_config->flow_steer_list_lock); +} + /** * idpf_find_mac_filter - Search filter list for specific mac filter * @vconfig: Vport config structure @@ -519,7 +542,7 @@ static int idpf_del_mac_filter(struct idpf_vport *vport, } spin_unlock_bh(&vport_config->mac_filter_list_lock); - if (np->state == __IDPF_VPORT_UP) { + if (test_bit(IDPF_VPORT_UP, np->state)) { int err; err = idpf_add_del_mac_filters(vport, np, false, async); @@ -590,7 +613,7 @@ static int idpf_add_mac_filter(struct idpf_vport *vport, if (err) return err; - if (np->state == __IDPF_VPORT_UP) + if (test_bit(IDPF_VPORT_UP, np->state)) err = idpf_add_del_mac_filters(vport, np, true, async); return err; @@ -729,6 +752,65 @@ static int idpf_init_mac_addr(struct idpf_vport *vport, return 0; } +static void idpf_detach_and_close(struct idpf_adapter *adapter) +{ + int max_vports = adapter->max_vports; + + for (int i = 0; i < max_vports; i++) { + struct net_device *netdev = adapter->netdevs[i]; + + /* If the interface is in detached state, that means the + * previous reset was not handled successfully for this + * vport. + */ + if (!netif_device_present(netdev)) + continue; + + /* Hold RTNL to protect racing with callbacks */ + rtnl_lock(); + netif_device_detach(netdev); + if (netif_running(netdev)) { + set_bit(IDPF_VPORT_UP_REQUESTED, + adapter->vport_config[i]->flags); + dev_close(netdev); + } + rtnl_unlock(); + } +} + +static void idpf_attach_and_open(struct idpf_adapter *adapter) +{ + int max_vports = adapter->max_vports; + + for (int i = 0; i < max_vports; i++) { + struct idpf_vport *vport = adapter->vports[i]; + struct idpf_vport_config *vport_config; + struct net_device *netdev; + + /* In case of a critical error in the init task, the vport + * will be freed. Only continue to restore the netdevs + * if the vport is allocated. + */ + if (!vport) + continue; + + /* No need for RTNL on attach as this function is called + * following detach and dev_close(). We do take RTNL for + * dev_open() below as it can race with external callbacks + * following the call to netif_device_attach(). + */ + netdev = adapter->netdevs[i]; + netif_device_attach(netdev); + vport_config = adapter->vport_config[vport->idx]; + if (test_and_clear_bit(IDPF_VPORT_UP_REQUESTED, + vport_config->flags)) { + rtnl_lock(); + dev_open(netdev, NULL); + rtnl_unlock(); + } + } +} + /** * idpf_cfg_netdev - Allocate, configure and register a netdev * @vport: main vport structure @@ -894,7 +976,7 @@ static void idpf_vport_stop(struct idpf_vport *vport, bool rtnl) { struct idpf_netdev_priv *np = netdev_priv(vport->netdev); - if (np->state <= __IDPF_VPORT_DOWN) + if (!test_bit(IDPF_VPORT_UP, np->state)) return; if (rtnl) @@ -921,7 +1003,7 @@ static void idpf_vport_stop(struct idpf_vport *vport, bool rtnl) idpf_xdp_rxq_info_deinit_all(vport); idpf_vport_queues_rel(vport); idpf_vport_intr_rel(vport); - np->state = __IDPF_VPORT_DOWN; + clear_bit(IDPF_VPORT_UP, np->state); if (rtnl) rtnl_unlock(); @@ -991,7 +1073,7 @@ static void idpf_vport_rel(struct idpf_vport *vport) u16 idx = vport->idx; vport_config = adapter->vport_config[vport->idx]; - idpf_deinit_rss(vport); + idpf_deinit_rss_lut(vport); rss_data = &vport_config->user_config.rss_data; kfree(rss_data->rss_key); rss_data->rss_key = NULL; @@ -1023,6 +1105,8 @@ static void idpf_vport_rel(struct idpf_vport *vport) kfree(adapter->vport_config[idx]->req_qs_chunks); adapter->vport_config[idx]->req_qs_chunks = NULL; } + kfree(vport->rx_ptype_lkup); + vport->rx_ptype_lkup = NULL; kfree(vport); adapter->num_alloc_vports--; } @@ -1041,12 +1125,15 @@ static void idpf_vport_dealloc(struct idpf_vport *vport) idpf_idc_deinit_vport_aux_device(vport->vdev_info); idpf_deinit_mac_addr(vport); - idpf_vport_stop(vport, true); - if (!test_bit(IDPF_HR_RESET_IN_PROG, adapter->flags)) + if (!test_bit(IDPF_HR_RESET_IN_PROG, adapter->flags)) { + idpf_vport_stop(vport, true); idpf_decfg_netdev(vport); - if (test_bit(IDPF_REMOVE_IN_PROG, adapter->flags)) + } + if (test_bit(IDPF_REMOVE_IN_PROG, adapter->flags)) { idpf_del_all_mac_filters(vport); + idpf_del_all_flow_steer_filters(vport); + } if (adapter->netdevs[i]) { struct idpf_netdev_priv *np = netdev_priv(adapter->netdevs[i]); @@ -1139,6 +1226,7 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, u16 idx = adapter->next_vport; struct idpf_vport *vport; u16 num_max_q; + int err; if (idx == IDPF_NO_FREE_SLOT) return NULL; @@ -1189,10 +1277,11 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, idpf_vport_init(vport, max_q); - /* This alloc is done separate from the LUT because it's not strictly - * dependent on how many queues we have. If we change number of queues - * and soft reset we'll need a new LUT but the key can remain the same - * for as long as the vport exists. + /* LUT and key are both initialized here. Key is not strictly dependent + * on how many queues we have. If we change number of queues and soft + * reset is initiated, LUT will be freed and a new LUT will be allocated + * as per the updated number of queues during vport bringup. However, + * the key remains the same for as long as the vport exists. */ rss_data = &adapter->vport_config[idx]->user_config.rss_data; rss_data->rss_key = kzalloc(rss_data->rss_key_size, GFP_KERNEL); @@ -1202,6 +1291,11 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, /* Initialize default rss key */ netdev_rss_key_fill((void *)rss_data->rss_key, rss_data->rss_key_size); + /* Initialize default rss LUT */ + err = idpf_init_rss_lut(vport); + if (err) + goto free_rss_key; + /* fill vport slot in the adapter struct */ adapter->vports[idx] = vport; adapter->vport_ids[idx] = idpf_get_vport_id(vport); @@ -1212,6 +1306,8 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, return vport; +free_rss_key: + kfree(rss_data->rss_key); free_vector_idxs: kfree(vport->q_vector_idxs); free_vport: @@ -1271,7 +1367,7 @@ void idpf_mbx_task(struct work_struct *work) idpf_mb_irq_enable(adapter); else queue_delayed_work(adapter->mbx_wq, &adapter->mbx_task, - msecs_to_jiffies(300)); + usecs_to_jiffies(300)); idpf_recv_mb_msg(adapter); } @@ -1345,7 +1441,7 @@ static int idpf_up_complete(struct idpf_vport *vport) netif_tx_start_all_queues(vport->netdev); } - np->state = __IDPF_VPORT_UP; + set_bit(IDPF_VPORT_UP, np->state); return 0; } @@ -1388,10 +1484,9 @@ static int idpf_vport_open(struct idpf_vport *vport, bool rtnl) { struct idpf_netdev_priv *np = netdev_priv(vport->netdev); struct idpf_adapter *adapter = vport->adapter; - struct idpf_vport_config *vport_config; int err; - if (np->state != __IDPF_VPORT_DOWN) + if (test_bit(IDPF_VPORT_UP, np->state)) return -EBUSY; if (rtnl) @@ -1429,14 +1524,14 @@ static int idpf_vport_open(struct idpf_vport *vport, bool rtnl) if (err) { dev_err(&adapter->pdev->dev, "Failed to initialize queue registers for vport %u: %d\n", vport->vport_id, err); - goto queues_rel; + goto intr_deinit; } err = idpf_rx_bufs_init_all(vport); if (err) { dev_err(&adapter->pdev->dev, "Failed to initialize RX buffers for vport %u: %d\n", vport->vport_id, err); - goto queues_rel; + goto intr_deinit; } idpf_rx_init_buf_tail(vport); @@ -1482,13 +1577,9 @@ static int idpf_vport_open(struct idpf_vport *vport, bool rtnl) idpf_restore_features(vport); - vport_config = adapter->vport_config[vport->idx]; - if (vport_config->user_config.rss_data.rss_lut) - err = idpf_config_rss(vport); - else - err = idpf_init_rss(vport); + err = idpf_config_rss(vport); if (err) { - dev_err(&adapter->pdev->dev, "Failed to initialize RSS for vport %u: %d\n", + dev_err(&adapter->pdev->dev, "Failed to configure RSS for vport %u: %d\n", vport->vport_id, err); goto disable_vport; } @@ -1497,7 +1588,7 @@ static int idpf_vport_open(struct idpf_vport *vport, bool rtnl) if (err) { dev_err(&adapter->pdev->dev, "Failed to complete interface up for vport %u: %d\n", vport->vport_id, err); - goto deinit_rss; + goto disable_vport; } if (rtnl) @@ -1505,8 +1596,6 @@ static int idpf_vport_open(struct idpf_vport *vport, bool rtnl) return 0; -deinit_rss: - idpf_deinit_rss(vport); disable_vport: idpf_send_disable_vport_msg(vport); disable_queues: @@ -1544,7 +1633,6 @@ void idpf_init_task(struct work_struct *work) struct idpf_vport_config *vport_config; struct idpf_vport_max_q max_q; struct idpf_adapter *adapter; - struct idpf_netdev_priv *np; struct idpf_vport *vport; u16 num_default_vports; struct pci_dev *pdev; @@ -1579,10 +1667,15 @@ void idpf_init_task(struct work_struct *work) goto unwind_vports; } + err = idpf_send_get_rx_ptype_msg(vport); + if (err) + goto unwind_vports; + index = vport->idx; vport_config = adapter->vport_config[index]; spin_lock_init(&vport_config->mac_filter_list_lock); + spin_lock_init(&vport_config->flow_steer_list_lock); INIT_LIST_HEAD(&vport_config->user_config.mac_filter_list); INIT_LIST_HEAD(&vport_config->user_config.flow_steer_list); @@ -1590,21 +1683,11 @@ void idpf_init_task(struct work_struct *work) err = idpf_check_supported_desc_ids(vport); if (err) { dev_err(&pdev->dev, "failed to get required descriptor ids\n"); - goto cfg_netdev_err; + goto unwind_vports; } if (idpf_cfg_netdev(vport)) - goto cfg_netdev_err; - - err = idpf_send_get_rx_ptype_msg(vport); - if (err) - goto handle_err; - - /* Once state is put into DOWN, driver is ready for dev_open */ - np = netdev_priv(vport->netdev); - np->state = __IDPF_VPORT_DOWN; - if (test_and_clear_bit(IDPF_VPORT_UP_REQUESTED, vport_config->flags)) - idpf_vport_open(vport, true); + goto unwind_vports; /* Spawn and return 'idpf_init_task' work queue until all the * default vports are created @@ -1635,21 +1718,15 @@ void idpf_init_task(struct work_struct *work) set_bit(IDPF_VPORT_REG_NETDEV, vport_config->flags); } - /* As all the required vports are created, clear the reset flag - * unconditionally here in case we were in reset and the link was down. - */ + /* Clear the reset and load bits as all vports are created */ clear_bit(IDPF_HR_RESET_IN_PROG, adapter->flags); + clear_bit(IDPF_HR_DRV_LOAD, adapter->flags); /* Start the statistics task now */ queue_delayed_work(adapter->stats_wq, &adapter->stats_task, msecs_to_jiffies(10 * (pdev->devfn & 0x07))); return; -handle_err: - idpf_decfg_netdev(vport); -cfg_netdev_err: - idpf_vport_rel(vport); - adapter->vports[index] = NULL; unwind_vports: if (default_vport) { for (index = 0; index < adapter->max_vports; index++) { @@ -1657,6 +1734,15 @@ void idpf_init_task(struct work_struct *work) idpf_vport_dealloc(adapter->vports[index]); } } + /* Cleanup after vc_core_init, which has no way of knowing the + * init task failed on driver load. + */ + if (test_and_clear_bit(IDPF_HR_DRV_LOAD, adapter->flags)) { + cancel_delayed_work_sync(&adapter->serv_task); + cancel_delayed_work_sync(&adapter->mbx_task); + } + idpf_ptp_release(adapter); + clear_bit(IDPF_HR_RESET_IN_PROG, adapter->flags); } @@ -1786,27 +1872,6 @@ static int idpf_check_reset_complete(struct idpf_hw *hw, return -EBUSY; } -/** - * idpf_set_vport_state - Set the vport state to be after the reset - * @adapter: Driver specific private structure - */ -static void idpf_set_vport_state(struct idpf_adapter *adapter) -{ - u16 i; - - for (i = 0; i < adapter->max_vports; i++) { - struct idpf_netdev_priv *np; - - if (!adapter->netdevs[i]) - continue; - - np = netdev_priv(adapter->netdevs[i]); - if (np->state == __IDPF_VPORT_UP) - set_bit(IDPF_VPORT_UP_REQUESTED, - adapter->vport_config[i]->flags); - } -} - /** * idpf_init_hard_reset - Initiate a hardware reset * @adapter: Driver specific private structure @@ -1815,37 +1880,25 @@ static void idpf_set_vport_state(struct idpf_adapter *adapter) * reallocate. Also reinitialize the mailbox. Return 0 on success, * negative on failure. */ -static int idpf_init_hard_reset(struct idpf_adapter *adapter) +static void idpf_init_hard_reset(struct idpf_adapter *adapter) { struct idpf_reg_ops *reg_ops = &adapter->dev_ops.reg_ops; struct device *dev = &adapter->pdev->dev; - struct net_device *netdev; int err; - u16 i; + idpf_detach_and_close(adapter); mutex_lock(&adapter->vport_ctrl_lock); dev_info(dev, "Device HW Reset initiated\n"); - /* Avoid TX hangs on reset */ - for (i = 0; i < adapter->max_vports; i++) { - netdev = adapter->netdevs[i]; - if (!netdev) - continue; - - netif_carrier_off(netdev); - netif_tx_disable(netdev); - } - /* Prepare for reset */ - if (test_and_clear_bit(IDPF_HR_DRV_LOAD, adapter->flags)) { + if (test_bit(IDPF_HR_DRV_LOAD, adapter->flags)) { reg_ops->trigger_reset(adapter, IDPF_HR_DRV_LOAD); } else if (test_and_clear_bit(IDPF_HR_FUNC_RESET, adapter->flags)) { bool is_reset = idpf_is_reset_detected(adapter); idpf_idc_issue_reset_event(adapter->cdev_info); - idpf_set_vport_state(adapter); idpf_vc_core_deinit(adapter); if (!is_reset) reg_ops->trigger_reset(adapter, IDPF_HR_FUNC_RESET); @@ -1892,11 +1945,14 @@ static int idpf_init_hard_reset(struct idpf_adapter *adapter) unlock_mutex: mutex_unlock(&adapter->vport_ctrl_lock); - /* Wait until all vports are created to init RDMA CORE AUX */ - if (!err) - err = idpf_idc_init(adapter); - - return err; + /* Attempt to restore netdevs and initialize RDMA CORE AUX device, + * provided vc_core_init succeeded. It is still possible that + * vports are not allocated at this point if the init task failed. + */ + if (!err) { + idpf_attach_and_open(adapter); + idpf_idc_init(adapter); + } } /** @@ -1939,7 +1995,7 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, enum idpf_vport_reset_cause reset_cause) { struct idpf_netdev_priv *np = netdev_priv(vport->netdev); - enum idpf_vport_state current_state = np->state; + bool vport_is_up = test_bit(IDPF_VPORT_UP, np->state); struct idpf_adapter *adapter = vport->adapter; struct idpf_vport *new_vport; int err; @@ -1990,14 +2046,13 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, goto free_vport; } - if (current_state <= __IDPF_VPORT_DOWN) { + if (!vport_is_up) { idpf_send_delete_queues_msg(vport); } else { set_bit(IDPF_VPORT_DEL_QUEUES, vport->flags); idpf_vport_stop(vport, false); } - idpf_deinit_rss(vport); /* We're passing in vport here because we need its wait_queue * to send a message and it should be getting all the vport * config data out of the adapter but we need to be careful not @@ -2023,7 +2078,11 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, if (err) goto err_open; - if (current_state == __IDPF_VPORT_UP) + if (reset_cause == IDPF_SR_Q_CHANGE && + !netif_is_rxfh_configured(vport->netdev)) + idpf_fill_dflt_rss_lut(vport); + + if (vport_is_up) err = idpf_vport_open(vport, false); goto free_vport; @@ -2033,7 +2092,7 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, vport->num_rxq, vport->num_bufq); err_open: - if (current_state == __IDPF_VPORT_UP) + if (vport_is_up) idpf_vport_open(vport, false); free_vport: @@ -2165,40 +2224,6 @@ static void idpf_set_rx_mode(struct net_device *netdev) dev_err(dev, "Failed to set promiscuous mode: %d\n", err); } -/** - * idpf_vport_manage_rss_lut - disable/enable RSS - * @vport: the vport being changed - * - * In the event of disable request for RSS, this function will zero out RSS - * LUT, while in the event of enable request for RSS, it will reconfigure RSS - * LUT with the default LUT configuration. - */ -static int idpf_vport_manage_rss_lut(struct idpf_vport *vport) -{ - bool ena = idpf_is_feature_ena(vport, NETIF_F_RXHASH); - struct idpf_rss_data *rss_data; - u16 idx = vport->idx; - int lut_size; - - rss_data = &vport->adapter->vport_config[idx]->user_config.rss_data; - lut_size = rss_data->rss_lut_size * sizeof(u32); - - if (ena) { - /* This will contain the default or user configured LUT */ - memcpy(rss_data->rss_lut, rss_data->cached_lut, lut_size); - } else { - /* Save a copy of the current LUT to be restored later if - * requested. - */ - memcpy(rss_data->cached_lut, rss_data->rss_lut, lut_size); - - /* Zero out the current LUT to disable */ - memset(rss_data->rss_lut, 0, lut_size); - } - - return idpf_config_rss(vport); -} - /** * idpf_set_features - set the netdev feature flags * @netdev: ptr to the netdev being adjusted @@ -2224,10 +2249,19 @@ static int idpf_set_features(struct net_device *netdev, } if (changed & NETIF_F_RXHASH) { + struct idpf_netdev_priv *np = netdev_priv(netdev); + netdev->features ^= NETIF_F_RXHASH; - err = idpf_vport_manage_rss_lut(vport); - if (err) - goto unlock_mutex; + + /* If the interface is not up when changing the rxhash, update + * to the HW is skipped. The updated LUT will be committed to + * the HW when the interface is brought up. + */ + if (test_bit(IDPF_VPORT_UP, np->state)) { + err = idpf_config_rss(vport); + if (err) + goto unlock_mutex; + } } if (changed & NETIF_F_GRO_HW) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c index 3e1052d070cfdf..0a8b50350b8604 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c @@ -108,11 +108,11 @@ static u64 idpf_ptp_read_src_clk_reg_direct(struct idpf_adapter *adapter, ptp_read_system_prets(sts); idpf_ptp_enable_shtime(adapter); + lo = readl(ptp->dev_clk_regs.dev_clk_ns_l); /* Read the system timestamp post PHC read */ ptp_read_system_postts(sts); - lo = readl(ptp->dev_clk_regs.dev_clk_ns_l); hi = readl(ptp->dev_clk_regs.dev_clk_ns_h); spin_unlock(&ptp->read_dev_clk_lock); diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c index 61e61306614045..e3ddf18dcbf51b 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c @@ -570,7 +570,7 @@ static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget, np = netdev_priv(tx_q->netdev); nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx); - dont_wake = np->state != __IDPF_VPORT_UP || + dont_wake = !test_bit(IDPF_VPORT_UP, np->state) || !netif_carrier_ok(tx_q->netdev); __netif_txq_completed_wake(nq, ss.packets, ss.bytes, IDPF_DESC_UNUSED(tx_q), IDPF_TX_WAKE_THRESH, diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 828f7c444d3093..a48088eb9b8220 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -695,9 +695,10 @@ static int idpf_rx_buf_alloc_singleq(struct idpf_rx_queue *rxq) static int idpf_rx_bufs_init_singleq(struct idpf_rx_queue *rxq) { struct libeth_fq fq = { - .count = rxq->desc_count, - .type = LIBETH_FQE_MTU, - .nid = idpf_q_vector_to_mem(rxq->q_vector), + .count = rxq->desc_count, + .type = LIBETH_FQE_MTU, + .buf_len = IDPF_RX_MAX_BUF_SZ, + .nid = idpf_q_vector_to_mem(rxq->q_vector), }; int ret; @@ -754,6 +755,7 @@ static int idpf_rx_bufs_init(struct idpf_buf_queue *bufq, .truesize = bufq->truesize, .count = bufq->desc_count, .type = type, + .buf_len = IDPF_RX_MAX_BUF_SZ, .hsplit = idpf_queue_has(HSPLIT_EN, bufq), .xdp = idpf_xdp_enabled(bufq->q_vector->vport), .nid = idpf_q_vector_to_mem(bufq->q_vector), @@ -2275,7 +2277,7 @@ static bool idpf_tx_clean_complq(struct idpf_compl_queue *complq, int budget, /* Update BQL */ nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx); - dont_wake = !complq_ok || np->state != __IDPF_VPORT_UP || + dont_wake = !complq_ok || !test_bit(IDPF_VPORT_UP, np->state) || !netif_carrier_ok(tx_q->netdev); /* Check if the TXQ needs to and can be restarted */ __netif_txq_completed_wake(nq, tx_q->cleaned_pkts, tx_q->cleaned_bytes, @@ -3939,7 +3941,7 @@ static void idpf_update_dim_sample(struct idpf_q_vector *q_vector, static void idpf_net_dim(struct idpf_q_vector *q_vector) { struct dim_sample dim_sample = { }; - u64 packets, bytes; + u64 packets, bytes, pkts, bts; u32 i; if (!IDPF_ITR_IS_DYNAMIC(q_vector->tx_intr_mode)) @@ -3951,9 +3953,12 @@ static void idpf_net_dim(struct idpf_q_vector *q_vector) do { start = u64_stats_fetch_begin(&txq->stats_sync); - packets += u64_stats_read(&txq->q_stats.packets); - bytes += u64_stats_read(&txq->q_stats.bytes); + pkts = u64_stats_read(&txq->q_stats.packets); + bts = u64_stats_read(&txq->q_stats.bytes); } while (u64_stats_fetch_retry(&txq->stats_sync, start)); + + packets += pkts; + bytes += bts; } idpf_update_dim_sample(q_vector, &dim_sample, &q_vector->tx_dim, @@ -3970,9 +3975,12 @@ static void idpf_net_dim(struct idpf_q_vector *q_vector) do { start = u64_stats_fetch_begin(&rxq->stats_sync); - packets += u64_stats_read(&rxq->q_stats.packets); - bytes += u64_stats_read(&rxq->q_stats.bytes); + pkts = u64_stats_read(&rxq->q_stats.packets); + bts = u64_stats_read(&rxq->q_stats.bytes); } while (u64_stats_fetch_retry(&rxq->stats_sync, start)); + + packets += pkts; + bytes += bts; } idpf_update_dim_sample(q_vector, &dim_sample, &q_vector->rx_dim, @@ -4641,7 +4649,7 @@ int idpf_config_rss(struct idpf_vport *vport) * idpf_fill_dflt_rss_lut - Fill the indirection table with the default values * @vport: virtual port structure */ -static void idpf_fill_dflt_rss_lut(struct idpf_vport *vport) +void idpf_fill_dflt_rss_lut(struct idpf_vport *vport) { struct idpf_adapter *adapter = vport->adapter; u16 num_active_rxq = vport->num_rxq; @@ -4650,57 +4658,47 @@ static void idpf_fill_dflt_rss_lut(struct idpf_vport *vport) rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; - for (i = 0; i < rss_data->rss_lut_size; i++) { + for (i = 0; i < rss_data->rss_lut_size; i++) rss_data->rss_lut[i] = i % num_active_rxq; - rss_data->cached_lut[i] = rss_data->rss_lut[i]; - } } /** - * idpf_init_rss - Allocate and initialize RSS resources + * idpf_init_rss_lut - Allocate and initialize RSS LUT * @vport: virtual port * - * Return 0 on success, negative on failure + * Return: 0 on success, negative on failure */ -int idpf_init_rss(struct idpf_vport *vport) +int idpf_init_rss_lut(struct idpf_vport *vport) { struct idpf_adapter *adapter = vport->adapter; struct idpf_rss_data *rss_data; - u32 lut_size; rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; + if (!rss_data->rss_lut) { + u32 lut_size; - lut_size = rss_data->rss_lut_size * sizeof(u32); - rss_data->rss_lut = kzalloc(lut_size, GFP_KERNEL); - if (!rss_data->rss_lut) - return -ENOMEM; - - rss_data->cached_lut = kzalloc(lut_size, GFP_KERNEL); - if (!rss_data->cached_lut) { - kfree(rss_data->rss_lut); - rss_data->rss_lut = NULL; - - return -ENOMEM; + lut_size = rss_data->rss_lut_size * sizeof(u32); + rss_data->rss_lut = kzalloc(lut_size, GFP_KERNEL); + if (!rss_data->rss_lut) + return -ENOMEM; } /* Fill the default RSS lut values */ idpf_fill_dflt_rss_lut(vport); - return idpf_config_rss(vport); + return 0; } /** - * idpf_deinit_rss - Release RSS resources + * idpf_deinit_rss_lut - Release RSS LUT * @vport: virtual port */ -void idpf_deinit_rss(struct idpf_vport *vport) +void idpf_deinit_rss_lut(struct idpf_vport *vport) { struct idpf_adapter *adapter = vport->adapter; struct idpf_rss_data *rss_data; rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; - kfree(rss_data->cached_lut); - rss_data->cached_lut = NULL; kfree(rss_data->rss_lut); rss_data->rss_lut = NULL; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index 75b977094741fd..423cc9486dce77 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -101,6 +101,7 @@ do { \ idx = 0; \ } while (0) +#define IDPF_RX_MAX_BUF_SZ (16384 - 128) #define IDPF_RX_BUF_STRIDE 32 #define IDPF_RX_BUF_POST_STRIDE 16 #define IDPF_LOW_WATERMARK 64 @@ -1085,9 +1086,10 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector); void idpf_vport_intr_deinit(struct idpf_vport *vport); int idpf_vport_intr_init(struct idpf_vport *vport); void idpf_vport_intr_ena(struct idpf_vport *vport); +void idpf_fill_dflt_rss_lut(struct idpf_vport *vport); int idpf_config_rss(struct idpf_vport *vport); -int idpf_init_rss(struct idpf_vport *vport); -void idpf_deinit_rss(struct idpf_vport *vport); +int idpf_init_rss_lut(struct idpf_vport *vport); +void idpf_deinit_rss_lut(struct idpf_vport *vport); int idpf_rx_bufs_init_all(struct idpf_vport *vport); struct idpf_q_vector *idpf_find_rxq_vec(const struct idpf_vport *vport, diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index cbb5fa30f5a0ec..cb702eac86c804 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -68,7 +68,7 @@ static void idpf_handle_event_link(struct idpf_adapter *adapter, vport->link_up = v2e->link_status; - if (np->state != __IDPF_VPORT_UP) + if (!test_bit(IDPF_VPORT_UP, np->state)) return; if (vport->link_up) { @@ -1016,6 +1016,9 @@ static int idpf_send_get_lan_memory_regions(struct idpf_adapter *adapter) struct idpf_vc_xn_params xn_params = { .vc_op = VIRTCHNL2_OP_GET_LAN_MEMORY_REGIONS, .recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN, + .send_buf.iov_len = + sizeof(struct virtchnl2_get_lan_memory_regions) + + sizeof(struct virtchnl2_mem_region), .timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC, }; int num_regions, size; @@ -1028,6 +1031,8 @@ static int idpf_send_get_lan_memory_regions(struct idpf_adapter *adapter) return -ENOMEM; xn_params.recv_buf.iov_base = rcvd_regions; + rcvd_regions->num_memory_regions = cpu_to_le16(1); + xn_params.send_buf.iov_base = rcvd_regions; reply_sz = idpf_vc_xn_exec(adapter, &xn_params); if (reply_sz < 0) return reply_sz; @@ -2755,7 +2760,7 @@ int idpf_send_get_stats_msg(struct idpf_vport *vport) /* Don't send get_stats message if the link is down */ - if (np->state <= __IDPF_VPORT_DOWN) + if (!test_bit(IDPF_VPORT_UP, np->state)) return 0; stats_msg.vport_id = cpu_to_le32(vport->vport_id); @@ -2799,6 +2804,10 @@ int idpf_send_get_stats_msg(struct idpf_vport *vport) * @vport: virtual port data structure * @get: flag to set or get rss look up table * + * When rxhash is disabled, RSS LUT will be configured with zeros. If rxhash + * is enabled, the LUT values stored in driver's soft copy will be used to setup + * the HW. + * * Returns 0 on success, negative on failure. */ int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get) @@ -2809,10 +2818,12 @@ int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get) struct idpf_rss_data *rss_data; int buf_size, lut_buf_size; ssize_t reply_sz; + bool rxhash_ena; int i; rss_data = &vport->adapter->vport_config[vport->idx]->user_config.rss_data; + rxhash_ena = idpf_is_feature_ena(vport, NETIF_F_RXHASH); buf_size = struct_size(rl, lut, rss_data->rss_lut_size); rl = kzalloc(buf_size, GFP_KERNEL); if (!rl) @@ -2834,7 +2845,8 @@ int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get) } else { rl->lut_entries = cpu_to_le16(rss_data->rss_lut_size); for (i = 0; i < rss_data->rss_lut_size; i++) - rl->lut[i] = cpu_to_le32(rss_data->rss_lut[i]); + rl->lut[i] = rxhash_ena ? + cpu_to_le32(rss_data->rss_lut[i]) : 0; xn_params.vc_op = VIRTCHNL2_OP_SET_RSS_LUT; } @@ -3565,6 +3577,7 @@ int idpf_vc_core_init(struct idpf_adapter *adapter) */ void idpf_vc_core_deinit(struct idpf_adapter *adapter) { + struct idpf_hw *hw = &adapter->hw; bool remove_in_prog; if (!test_bit(IDPF_VC_CORE_INIT, adapter->flags)) @@ -3588,6 +3601,9 @@ void idpf_vc_core_deinit(struct idpf_adapter *adapter) idpf_vport_params_buf_rel(adapter); + kfree(hw->lan_regs); + hw->lan_regs = NULL; + kfree(adapter->vports); adapter->vports = NULL; diff --git a/drivers/net/ethernet/intel/idpf/xdp.c b/drivers/net/ethernet/intel/idpf/xdp.c index 21ce25b0567f6f..958d16f874248d 100644 --- a/drivers/net/ethernet/intel/idpf/xdp.c +++ b/drivers/net/ethernet/intel/idpf/xdp.c @@ -418,7 +418,7 @@ static int idpf_xdp_setup_prog(struct idpf_vport *vport, if (test_bit(IDPF_REMOVE_IN_PROG, vport->adapter->flags) || !test_bit(IDPF_VPORT_REG_NETDEV, cfg->flags) || !!vport->xdp_prog == !!prog) { - if (np->state == __IDPF_VPORT_UP) + if (test_bit(IDPF_VPORT_UP, np->state)) idpf_xdp_copy_prog_to_rqs(vport, prog); old = xchg(&vport->xdp_prog, prog); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 85f9589cc568cf..dbea37269d2cdb 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -9599,7 +9599,6 @@ static int __igb_resume(struct device *dev, bool rpm) pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); - pci_save_state(pdev); if (!pci_device_is_present(pdev)) return -ENODEV; @@ -9754,7 +9753,6 @@ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev) } else { pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); pci_enable_wake(pdev, PCI_D3hot, 0); pci_enable_wake(pdev, PCI_D3cold, 0); diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 498ba1522ca4d4..9482ab11f050f7 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -443,9 +443,10 @@ #define IGC_TXPBSIZE_DEFAULT ( \ IGC_TXPB0SIZE(20) | IGC_TXPB1SIZE(0) | IGC_TXPB2SIZE(0) | \ IGC_TXPB3SIZE(0) | IGC_OS2BMCPBSIZE(4)) +/* TSN value following I225/I226 SW User Manual Section 7.5.4 */ #define IGC_TXPBSIZE_TSN ( \ - IGC_TXPB0SIZE(7) | IGC_TXPB1SIZE(7) | IGC_TXPB2SIZE(7) | \ - IGC_TXPB3SIZE(7) | IGC_OS2BMCPBSIZE(4)) + IGC_TXPB0SIZE(5) | IGC_TXPB1SIZE(5) | IGC_TXPB2SIZE(5) | \ + IGC_TXPB3SIZE(5) | IGC_OS2BMCPBSIZE(4)) #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */ diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index bb783042d1af9c..4b39329e9e32bf 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1561,8 +1561,8 @@ static int igc_ethtool_set_channels(struct net_device *netdev, if (ch->other_count != NON_Q_VECTORS) return -EINVAL; - /* Do not allow channel reconfiguration when mqprio is enabled */ - if (adapter->strict_priority_enable) + /* Do not allow channel reconfiguration when any TSN qdisc is enabled */ + if (adapter->flags & IGC_FLAG_TSN_ANY_ENABLED) return -EINVAL; /* Verify the number of channels doesn't exceed hw limits */ diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 728d7ca5338bf2..89a321a344d263 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -7530,7 +7530,6 @@ static int __igc_resume(struct device *dev, bool rpm) pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); - pci_save_state(pdev); if (!pci_device_is_present(pdev)) return -ENODEV; @@ -7667,7 +7666,6 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) } else { pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); pci_enable_wake(pdev, PCI_D3hot, 0); pci_enable_wake(pdev, PCI_D3cold, 0); @@ -7761,6 +7759,11 @@ int igc_reinit_queues(struct igc_adapter *adapter) if (netif_running(netdev)) err = igc_open(netdev); + if (!err) { + /* Restore default IEEE 802.1Qbv schedule after queue reinit */ + igc_tsn_clear_schedule(adapter); + } + return err; } diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index b7b46d863bee44..7aae83c108fd76 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -774,36 +774,43 @@ static void igc_ptp_tx_reg_to_stamp(struct igc_adapter *adapter, static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; + u32 txstmpl_old; u64 regval; u32 mask; int i; + /* Establish baseline of TXSTMPL_0 before checking TXTT_0. + * This baseline is used to detect if a new timestamp arrives in + * register 0 during the hardware bug workaround below. + */ + txstmpl_old = rd32(IGC_TXSTMPL); + mask = rd32(IGC_TSYNCTXCTL) & IGC_TSYNCTXCTL_TXTT_ANY; if (mask & IGC_TSYNCTXCTL_TXTT_0) { regval = rd32(IGC_TXSTMPL); regval |= (u64)rd32(IGC_TXSTMPH) << 32; } else { - /* There's a bug in the hardware that could cause - * missing interrupts for TX timestamping. The issue - * is that for new interrupts to be triggered, the - * IGC_TXSTMPH_0 register must be read. + /* TXTT_0 not set - register 0 has no new timestamp initially. + * + * Hardware bug: Future timestamp interrupts won't fire unless + * TXSTMPH_0 is read, even if the timestamp was captured in + * registers 1-3. * - * To avoid discarding a valid timestamp that just - * happened at the "wrong" time, we need to confirm - * that there was no timestamp captured, we do that by - * assuming that no two timestamps in sequence have - * the same nanosecond value. + * Workaround: Read TXSTMPH_0 here to enable future interrupts. + * However, this read clears TXTT_0. If a timestamp arrives in + * register 0 after checking TXTT_0 but before this read, it + * would be lost. * - * So, we read the "low" register, read the "high" - * register (to latch a new timestamp) and read the - * "low" register again, if "old" and "new" versions - * of the "low" register are different, a valid - * timestamp was captured, we can read the "high" - * register again. + * To detect this race: We saved a baseline read of TXSTMPL_0 + * before TXTT_0 check. After performing the workaround read of + * TXSTMPH_0, we read TXSTMPL_0 again. Since consecutive + * timestamps never share the same nanosecond value, a change + * between the baseline and new TXSTMPL_0 indicates a timestamp + * arrived during the race window. If so, read the complete + * timestamp. */ - u32 txstmpl_old, txstmpl_new; + u32 txstmpl_new; - txstmpl_old = rd32(IGC_TXSTMPL); rd32(IGC_TXSTMPH); txstmpl_new = rd32(IGC_TXSTMPL); @@ -818,7 +825,7 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) done: /* Now that the problematic first register was handled, we can - * use retrieve the timestamps from the other registers + * retrieve the timestamps from the other registers * (starting from '1') with less complications. */ for (i = 1; i < IGC_MAX_TX_TSTAMP_REGS; i++) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 3190ce7e44c742..501216970e611f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -11468,20 +11468,17 @@ static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter) */ static int ixgbe_recovery_probe(struct ixgbe_adapter *adapter) { - struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; struct ixgbe_hw *hw = &adapter->hw; - bool disable_dev; int err = -EIO; if (hw->mac.type != ixgbe_mac_e610) - goto clean_up_probe; + return err; ixgbe_get_hw_control(adapter); - mutex_init(&hw->aci.lock); err = ixgbe_get_flash_data(&adapter->hw); if (err) - goto shutdown_aci; + goto err_release_hw_control; timer_setup(&adapter->service_timer, ixgbe_service_timer, 0); INIT_WORK(&adapter->service_task, ixgbe_recovery_service_task); @@ -11504,16 +11501,8 @@ static int ixgbe_recovery_probe(struct ixgbe_adapter *adapter) devl_unlock(adapter->devlink); return 0; -shutdown_aci: - mutex_destroy(&adapter->hw.aci.lock); +err_release_hw_control: ixgbe_release_hw_control(adapter); -clean_up_probe: - disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); - free_netdev(netdev); - devlink_free(adapter->devlink); - pci_release_mem_regions(pdev); - if (disable_dev) - pci_disable_device(pdev); return err; } @@ -11655,8 +11644,13 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_sw_init; - if (ixgbe_check_fw_error(adapter)) - return ixgbe_recovery_probe(adapter); + if (ixgbe_check_fw_error(adapter)) { + err = ixgbe_recovery_probe(adapter); + if (err) + goto err_sw_init; + + return 0; + } if (adapter->hw.mac.type == ixgbe_mac_e610) { err = ixgbe_get_caps(&adapter->hw); @@ -12298,7 +12292,6 @@ static pci_ers_result_t ixgbe_io_slot_reset(struct pci_dev *pdev) adapter->hw.hw_addr = adapter->io_addr; pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); pci_wake_from_d3(pdev, false); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c index 44b201817d94c6..c116da7d7f18c8 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c @@ -1389,7 +1389,7 @@ int mvpp2_ethtool_cls_rule_ins(struct mvpp2_port *port, efs->rule.flow_type = mvpp2_cls_ethtool_flow_to_type(info->fs.flow_type); if (efs->rule.flow_type < 0) { ret = efs->rule.flow_type; - goto clean_rule; + goto clean_eth_rule; } ret = mvpp2_cls_rfs_parse_rule(&efs->rule); diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_cn9k_pf.c b/drivers/net/ethernet/marvell/octeon_ep/octep_cn9k_pf.c index b5805969404fa1..01e82d0b6b2cdd 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_cn9k_pf.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_cn9k_pf.c @@ -307,7 +307,7 @@ static void octep_setup_iq_regs_cn93_pf(struct octep_device *oct, int iq_no) } /* Setup registers for a hardware Rx Queue */ -static void octep_setup_oq_regs_cn93_pf(struct octep_device *oct, int oq_no) +static int octep_setup_oq_regs_cn93_pf(struct octep_device *oct, int oq_no) { u64 reg_val; u64 oq_ctl = 0ULL; @@ -355,6 +355,7 @@ static void octep_setup_oq_regs_cn93_pf(struct octep_device *oct, int oq_no) reg_val = ((u64)time_threshold << 32) | CFG_GET_OQ_INTR_PKT(oct->conf); octep_write_csr64(oct, CN93_SDP_R_OUT_INT_LEVELS(oq_no), reg_val); + return 0; } /* Setup registers for a PF mailbox */ @@ -696,14 +697,26 @@ static void octep_enable_interrupts_cn93_pf(struct octep_device *oct) /* Disable all interrupts */ static void octep_disable_interrupts_cn93_pf(struct octep_device *oct) { - u64 intr_mask = 0ULL; + u64 reg_val, intr_mask = 0ULL; int srn, num_rings, i; srn = CFG_GET_PORTS_PF_SRN(oct->conf); num_rings = CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf); - for (i = 0; i < num_rings; i++) - intr_mask |= (0x1ULL << (srn + i)); + for (i = 0; i < num_rings; i++) { + intr_mask |= BIT_ULL(srn + i); + reg_val = octep_read_csr64(oct, + CN93_SDP_R_IN_INT_LEVELS(srn + i)); + reg_val &= ~CN93_INT_ENA_BIT; + octep_write_csr64(oct, + CN93_SDP_R_IN_INT_LEVELS(srn + i), reg_val); + + reg_val = octep_read_csr64(oct, + CN93_SDP_R_OUT_INT_LEVELS(srn + i)); + reg_val &= ~CN93_INT_ENA_BIT; + octep_write_csr64(oct, + CN93_SDP_R_OUT_INT_LEVELS(srn + i), reg_val); + } octep_write_csr64(oct, CN93_SDP_EPF_IRERR_RINT_ENA_W1C, intr_mask); octep_write_csr64(oct, CN93_SDP_EPF_ORERR_RINT_ENA_W1C, intr_mask); diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_cnxk_pf.c b/drivers/net/ethernet/marvell/octeon_ep/octep_cnxk_pf.c index 5de0b5ecbc5fd1..09a3f1d0645b85 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_cnxk_pf.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_cnxk_pf.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "octep_config.h" #include "octep_main.h" @@ -327,12 +328,14 @@ static void octep_setup_iq_regs_cnxk_pf(struct octep_device *oct, int iq_no) } /* Setup registers for a hardware Rx Queue */ -static void octep_setup_oq_regs_cnxk_pf(struct octep_device *oct, int oq_no) +static int octep_setup_oq_regs_cnxk_pf(struct octep_device *oct, int oq_no) { - u64 reg_val; - u64 oq_ctl = 0ULL; - u32 time_threshold = 0; struct octep_oq *oq = oct->oq[oq_no]; + unsigned long t_out_jiffies; + u32 time_threshold = 0; + u64 oq_ctl = 0ULL; + u64 reg_ba_val; + u64 reg_val; oq_no += CFG_GET_PORTS_PF_SRN(oct->conf); reg_val = octep_read_csr64(oct, CNXK_SDP_R_OUT_CONTROL(oq_no)); @@ -343,6 +346,36 @@ static void octep_setup_oq_regs_cnxk_pf(struct octep_device *oct, int oq_no) reg_val = octep_read_csr64(oct, CNXK_SDP_R_OUT_CONTROL(oq_no)); } while (!(reg_val & CNXK_R_OUT_CTL_IDLE)); } + octep_write_csr64(oct, CNXK_SDP_R_OUT_WMARK(oq_no), oq->max_count); + /* Wait for WMARK to get applied */ + usleep_range(10, 15); + + octep_write_csr64(oct, CNXK_SDP_R_OUT_SLIST_BADDR(oq_no), + oq->desc_ring_dma); + octep_write_csr64(oct, CNXK_SDP_R_OUT_SLIST_RSIZE(oq_no), + oq->max_count); + reg_ba_val = octep_read_csr64(oct, CNXK_SDP_R_OUT_SLIST_BADDR(oq_no)); + + if (reg_ba_val != oq->desc_ring_dma) { + t_out_jiffies = jiffies + 10 * HZ; + do { + if (reg_ba_val == ULLONG_MAX) + return -EFAULT; + octep_write_csr64(oct, + CNXK_SDP_R_OUT_SLIST_BADDR(oq_no), + oq->desc_ring_dma); + octep_write_csr64(oct, + CNXK_SDP_R_OUT_SLIST_RSIZE(oq_no), + oq->max_count); + reg_ba_val = + octep_read_csr64(oct, + CNXK_SDP_R_OUT_SLIST_BADDR(oq_no)); + } while ((reg_ba_val != oq->desc_ring_dma) && + time_before(jiffies, t_out_jiffies)); + + if (reg_ba_val != oq->desc_ring_dma) + return -EAGAIN; + } reg_val &= ~(CNXK_R_OUT_CTL_IMODE); reg_val &= ~(CNXK_R_OUT_CTL_ROR_P); @@ -356,10 +389,6 @@ static void octep_setup_oq_regs_cnxk_pf(struct octep_device *oct, int oq_no) reg_val |= (CNXK_R_OUT_CTL_ES_P); octep_write_csr64(oct, CNXK_SDP_R_OUT_CONTROL(oq_no), reg_val); - octep_write_csr64(oct, CNXK_SDP_R_OUT_SLIST_BADDR(oq_no), - oq->desc_ring_dma); - octep_write_csr64(oct, CNXK_SDP_R_OUT_SLIST_RSIZE(oq_no), - oq->max_count); oq_ctl = octep_read_csr64(oct, CNXK_SDP_R_OUT_CONTROL(oq_no)); @@ -385,6 +414,7 @@ static void octep_setup_oq_regs_cnxk_pf(struct octep_device *oct, int oq_no) reg_val &= ~0xFFFFFFFFULL; reg_val |= CFG_GET_OQ_WMARK(oct->conf); octep_write_csr64(oct, CNXK_SDP_R_OUT_WMARK(oq_no), reg_val); + return 0; } /* Setup registers for a PF mailbox */ @@ -720,14 +750,26 @@ static void octep_enable_interrupts_cnxk_pf(struct octep_device *oct) /* Disable all interrupts */ static void octep_disable_interrupts_cnxk_pf(struct octep_device *oct) { - u64 intr_mask = 0ULL; + u64 reg_val, intr_mask = 0ULL; int srn, num_rings, i; srn = CFG_GET_PORTS_PF_SRN(oct->conf); num_rings = CFG_GET_PORTS_ACTIVE_IO_RINGS(oct->conf); - for (i = 0; i < num_rings; i++) - intr_mask |= (0x1ULL << (srn + i)); + for (i = 0; i < num_rings; i++) { + intr_mask |= BIT_ULL(srn + i); + reg_val = octep_read_csr64(oct, + CNXK_SDP_R_IN_INT_LEVELS(srn + i)); + reg_val &= ~CNXK_INT_ENA_BIT; + octep_write_csr64(oct, + CNXK_SDP_R_IN_INT_LEVELS(srn + i), reg_val); + + reg_val = octep_read_csr64(oct, + CNXK_SDP_R_OUT_INT_LEVELS(srn + i)); + reg_val &= ~CNXK_INT_ENA_BIT; + octep_write_csr64(oct, + CNXK_SDP_R_OUT_INT_LEVELS(srn + i), reg_val); + } octep_write_csr64(oct, CNXK_SDP_EPF_IRERR_RINT_ENA_W1C, intr_mask); octep_write_csr64(oct, CNXK_SDP_EPF_ORERR_RINT_ENA_W1C, intr_mask); diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index bcea3fc26a8c7d..57db7ea2f5be9c 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -1338,7 +1338,7 @@ int octep_device_setup(struct octep_device *oct) ret = octep_ctrl_net_init(oct); if (ret) - return ret; + goto unsupported_dev; INIT_WORK(&oct->tx_timeout_task, octep_tx_timeout_task); INIT_WORK(&oct->ctrl_mbox_task, octep_ctrl_mbox_task); diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h index 81ac4267811c81..35d0ff289a70df 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h @@ -77,7 +77,7 @@ struct octep_pci_win_regs { struct octep_hw_ops { void (*setup_iq_regs)(struct octep_device *oct, int q); - void (*setup_oq_regs)(struct octep_device *oct, int q); + int (*setup_oq_regs)(struct octep_device *oct, int q); void (*setup_mbox_regs)(struct octep_device *oct, int mbox); irqreturn_t (*mbox_intr_handler)(void *ioq_vector); diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h b/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h index ca473502d7a02a..95f1dfff90cce4 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h @@ -386,5 +386,6 @@ #define CN93_PEM_BAR4_INDEX 7 #define CN93_PEM_BAR4_INDEX_SIZE 0x400000ULL #define CN93_PEM_BAR4_INDEX_OFFSET (CN93_PEM_BAR4_INDEX * CN93_PEM_BAR4_INDEX_SIZE) +#define CN93_INT_ENA_BIT BIT_ULL(62) #endif /* _OCTEP_REGS_CN9K_PF_H_ */ diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cnxk_pf.h b/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cnxk_pf.h index e637d7c8224d49..4d172a552f80c5 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cnxk_pf.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cnxk_pf.h @@ -412,5 +412,6 @@ #define CNXK_PEM_BAR4_INDEX 7 #define CNXK_PEM_BAR4_INDEX_SIZE 0x400000ULL #define CNXK_PEM_BAR4_INDEX_OFFSET (CNXK_PEM_BAR4_INDEX * CNXK_PEM_BAR4_INDEX_SIZE) +#define CNXK_INT_ENA_BIT BIT_ULL(62) #endif /* _OCTEP_REGS_CNXK_PF_H_ */ diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c index 82b6b19e76b47a..f2a7c6a76c742a 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c @@ -12,6 +12,8 @@ #include "octep_config.h" #include "octep_main.h" +static void octep_oq_free_ring_buffers(struct octep_oq *oq); + static void octep_oq_reset_indices(struct octep_oq *oq) { oq->host_read_idx = 0; @@ -170,11 +172,15 @@ static int octep_setup_oq(struct octep_device *oct, int q_no) goto oq_fill_buff_err; octep_oq_reset_indices(oq); - oct->hw_ops.setup_oq_regs(oct, q_no); + if (oct->hw_ops.setup_oq_regs(oct, q_no)) + goto oq_setup_err; + oct->num_oqs++; return 0; +oq_setup_err: + octep_oq_free_ring_buffers(oq); oq_fill_buff_err: vfree(oq->buff_info); oq->buff_info = NULL; diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_cn9k.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_cn9k.c index 88937fce75f140..4c769b27c27892 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_cn9k.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_cn9k.c @@ -196,7 +196,7 @@ static void octep_vf_setup_iq_regs_cn93(struct octep_vf_device *oct, int iq_no) } /* Setup registers for a hardware Rx Queue */ -static void octep_vf_setup_oq_regs_cn93(struct octep_vf_device *oct, int oq_no) +static int octep_vf_setup_oq_regs_cn93(struct octep_vf_device *oct, int oq_no) { struct octep_vf_oq *oq = oct->oq[oq_no]; u32 time_threshold = 0; @@ -239,6 +239,7 @@ static void octep_vf_setup_oq_regs_cn93(struct octep_vf_device *oct, int oq_no) time_threshold = CFG_GET_OQ_INTR_TIME(oct->conf); reg_val = ((u64)time_threshold << 32) | CFG_GET_OQ_INTR_PKT(oct->conf); octep_vf_write_csr64(oct, CN93_VF_SDP_R_OUT_INT_LEVELS(oq_no), reg_val); + return 0; } /* Setup registers for a VF mailbox */ diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_cnxk.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_cnxk.c index 1f79dfad42c626..a968b93a67943b 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_cnxk.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_cnxk.c @@ -199,11 +199,13 @@ static void octep_vf_setup_iq_regs_cnxk(struct octep_vf_device *oct, int iq_no) } /* Setup registers for a hardware Rx Queue */ -static void octep_vf_setup_oq_regs_cnxk(struct octep_vf_device *oct, int oq_no) +static int octep_vf_setup_oq_regs_cnxk(struct octep_vf_device *oct, int oq_no) { struct octep_vf_oq *oq = oct->oq[oq_no]; + unsigned long t_out_jiffies; u32 time_threshold = 0; u64 oq_ctl = ULL(0); + u64 reg_ba_val; u64 reg_val; reg_val = octep_vf_read_csr64(oct, CNXK_VF_SDP_R_OUT_CONTROL(oq_no)); @@ -214,6 +216,38 @@ static void octep_vf_setup_oq_regs_cnxk(struct octep_vf_device *oct, int oq_no) reg_val = octep_vf_read_csr64(oct, CNXK_VF_SDP_R_OUT_CONTROL(oq_no)); } while (!(reg_val & CNXK_VF_R_OUT_CTL_IDLE)); } + octep_vf_write_csr64(oct, CNXK_VF_SDP_R_OUT_WMARK(oq_no), + oq->max_count); + /* Wait for WMARK to get applied */ + usleep_range(10, 15); + + octep_vf_write_csr64(oct, CNXK_VF_SDP_R_OUT_SLIST_BADDR(oq_no), + oq->desc_ring_dma); + octep_vf_write_csr64(oct, CNXK_VF_SDP_R_OUT_SLIST_RSIZE(oq_no), + oq->max_count); + reg_ba_val = octep_vf_read_csr64(oct, + CNXK_VF_SDP_R_OUT_SLIST_BADDR(oq_no)); + if (reg_ba_val != oq->desc_ring_dma) { + t_out_jiffies = jiffies + 10 * HZ; + do { + if (reg_ba_val == ULLONG_MAX) + return -EFAULT; + octep_vf_write_csr64(oct, + CNXK_VF_SDP_R_OUT_SLIST_BADDR + (oq_no), oq->desc_ring_dma); + octep_vf_write_csr64(oct, + CNXK_VF_SDP_R_OUT_SLIST_RSIZE + (oq_no), oq->max_count); + reg_ba_val = + octep_vf_read_csr64(oct, + CNXK_VF_SDP_R_OUT_SLIST_BADDR + (oq_no)); + } while ((reg_ba_val != oq->desc_ring_dma) && + time_before(jiffies, t_out_jiffies)); + + if (reg_ba_val != oq->desc_ring_dma) + return -EAGAIN; + } reg_val &= ~(CNXK_VF_R_OUT_CTL_IMODE); reg_val &= ~(CNXK_VF_R_OUT_CTL_ROR_P); @@ -227,8 +261,6 @@ static void octep_vf_setup_oq_regs_cnxk(struct octep_vf_device *oct, int oq_no) reg_val |= (CNXK_VF_R_OUT_CTL_ES_P); octep_vf_write_csr64(oct, CNXK_VF_SDP_R_OUT_CONTROL(oq_no), reg_val); - octep_vf_write_csr64(oct, CNXK_VF_SDP_R_OUT_SLIST_BADDR(oq_no), oq->desc_ring_dma); - octep_vf_write_csr64(oct, CNXK_VF_SDP_R_OUT_SLIST_RSIZE(oq_no), oq->max_count); oq_ctl = octep_vf_read_csr64(oct, CNXK_VF_SDP_R_OUT_CONTROL(oq_no)); /* Clear the ISIZE and BSIZE (22-0) */ @@ -250,6 +282,7 @@ static void octep_vf_setup_oq_regs_cnxk(struct octep_vf_device *oct, int oq_no) reg_val &= ~GENMASK_ULL(31, 0); reg_val |= CFG_GET_OQ_WMARK(oct->conf); octep_vf_write_csr64(oct, CNXK_VF_SDP_R_OUT_WMARK(oq_no), reg_val); + return 0; } /* Setup registers for a VF mailbox */ diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c index 420c3f4cf7417f..1d9760b4b8f471 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c @@ -218,7 +218,7 @@ static int octep_vf_request_irqs(struct octep_vf_device *oct) ioq_irq_err: while (i) { --i; - free_irq(oct->msix_entries[i].vector, oct); + free_irq(oct->msix_entries[i].vector, oct->ioq_vector[i]); } return -1; } diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h index b9f13506f46205..c74cd2369e90d4 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.h @@ -55,7 +55,7 @@ struct octep_vf_mmio { struct octep_vf_hw_ops { void (*setup_iq_regs)(struct octep_vf_device *oct, int q); - void (*setup_oq_regs)(struct octep_vf_device *oct, int q); + int (*setup_oq_regs)(struct octep_vf_device *oct, int q); void (*setup_mbox_regs)(struct octep_vf_device *oct, int mbox); irqreturn_t (*non_ioq_intr_handler)(void *ioq_vector); diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c index d70c8be3cfc40b..6f865dbbba6c67 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c @@ -12,6 +12,8 @@ #include "octep_vf_config.h" #include "octep_vf_main.h" +static void octep_vf_oq_free_ring_buffers(struct octep_vf_oq *oq); + static void octep_vf_oq_reset_indices(struct octep_vf_oq *oq) { oq->host_read_idx = 0; @@ -171,11 +173,15 @@ static int octep_vf_setup_oq(struct octep_vf_device *oct, int q_no) goto oq_fill_buff_err; octep_vf_oq_reset_indices(oq); - oct->hw_ops.setup_oq_regs(oct, q_no); + if (oct->hw_ops.setup_oq_regs(oct, q_no)) + goto oq_setup_err; + oct->num_oqs++; return 0; +oq_setup_err: + octep_vf_oq_free_ring_buffers(oq); oq_fill_buff_err: vfree(oq->buff_info); oq->buff_info = NULL; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 2d78e08f985f0c..8530df8b3fdaf7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -1551,8 +1551,8 @@ static int rvu_get_attach_blkaddr(struct rvu *rvu, int blktype, return -ENODEV; } -static void rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, - int num_lfs, struct rsrc_attach *attach) +static int rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, + int num_lfs, struct rsrc_attach *attach) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); struct rvu_hwinfo *hw = rvu->hw; @@ -1562,21 +1562,21 @@ static void rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, u64 cfg; if (!num_lfs) - return; + return -EINVAL; blkaddr = rvu_get_attach_blkaddr(rvu, blktype, pcifunc, attach); if (blkaddr < 0) - return; + return -EFAULT; block = &hw->block[blkaddr]; if (!block->lf.bmap) - return; + return -ESRCH; for (slot = 0; slot < num_lfs; slot++) { /* Allocate the resource */ lf = rvu_alloc_rsrc(&block->lf); if (lf < 0) - return; + return -EFAULT; cfg = (1ULL << 63) | (pcifunc << 8) | slot; rvu_write64(rvu, blkaddr, block->lfcfg_reg | @@ -1587,6 +1587,8 @@ static void rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, /* Set start MSIX vector for this LF within this PF/VF */ rvu_set_msix_offset(rvu, pfvf, block, lf); } + + return 0; } static int rvu_check_rsrc_availability(struct rvu *rvu, @@ -1724,22 +1726,31 @@ int rvu_mbox_handler_attach_resources(struct rvu *rvu, int err; /* If first request, detach all existing attached resources */ - if (!attach->modify) - rvu_detach_rsrcs(rvu, NULL, pcifunc); + if (!attach->modify) { + err = rvu_detach_rsrcs(rvu, NULL, pcifunc); + if (err) + return err; + } mutex_lock(&rvu->rsrc_lock); /* Check if the request can be accommodated */ err = rvu_check_rsrc_availability(rvu, attach, pcifunc); if (err) - goto exit; + goto fail1; /* Now attach the requested resources */ - if (attach->npalf) - rvu_attach_block(rvu, pcifunc, BLKTYPE_NPA, 1, attach); + if (attach->npalf) { + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_NPA, 1, attach); + if (err) + goto fail1; + } - if (attach->nixlf) - rvu_attach_block(rvu, pcifunc, BLKTYPE_NIX, 1, attach); + if (attach->nixlf) { + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_NIX, 1, attach); + if (err) + goto fail2; + } if (attach->sso) { /* RVU func doesn't know which exact LF or slot is attached @@ -1749,33 +1760,64 @@ int rvu_mbox_handler_attach_resources(struct rvu *rvu, */ if (attach->modify) rvu_detach_block(rvu, pcifunc, BLKTYPE_SSO); - rvu_attach_block(rvu, pcifunc, BLKTYPE_SSO, - attach->sso, attach); + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_SSO, + attach->sso, attach); + if (err) + goto fail3; } if (attach->ssow) { if (attach->modify) rvu_detach_block(rvu, pcifunc, BLKTYPE_SSOW); - rvu_attach_block(rvu, pcifunc, BLKTYPE_SSOW, - attach->ssow, attach); + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_SSOW, + attach->ssow, attach); + if (err) + goto fail4; } if (attach->timlfs) { if (attach->modify) rvu_detach_block(rvu, pcifunc, BLKTYPE_TIM); - rvu_attach_block(rvu, pcifunc, BLKTYPE_TIM, - attach->timlfs, attach); + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_TIM, + attach->timlfs, attach); + if (err) + goto fail5; } if (attach->cptlfs) { if (attach->modify && rvu_attach_from_same_block(rvu, BLKTYPE_CPT, attach)) rvu_detach_block(rvu, pcifunc, BLKTYPE_CPT); - rvu_attach_block(rvu, pcifunc, BLKTYPE_CPT, - attach->cptlfs, attach); + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_CPT, + attach->cptlfs, attach); + if (err) + goto fail6; } -exit: + mutex_unlock(&rvu->rsrc_lock); + return 0; + +fail6: + if (attach->timlfs) + rvu_detach_block(rvu, pcifunc, BLKTYPE_TIM); + +fail5: + if (attach->ssow) + rvu_detach_block(rvu, pcifunc, BLKTYPE_SSOW); + +fail4: + if (attach->sso) + rvu_detach_block(rvu, pcifunc, BLKTYPE_SSO); + +fail3: + if (attach->nixlf) + rvu_detach_block(rvu, pcifunc, BLKTYPE_NIX); + +fail2: + if (attach->npalf) + rvu_detach_block(rvu, pcifunc, BLKTYPE_NPA); + +fail1: mutex_unlock(&rvu->rsrc_lock); return err; } @@ -3590,11 +3632,22 @@ static void rvu_remove(struct pci_dev *pdev) devm_kfree(&pdev->dev, rvu); } +static void rvu_shutdown(struct pci_dev *pdev) +{ + struct rvu *rvu = pci_get_drvdata(pdev); + + if (!rvu) + return; + + rvu_clear_rvum_blk_revid(rvu); +} + static struct pci_driver rvu_driver = { .name = DRV_NAME, .id_table = rvu_id_table, .probe = rvu_probe, .remove = rvu_remove, + .shutdown = rvu_shutdown, }; static int __init rvu_init_module(void) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 3abd750a4bd741..3d91a34f8b57be 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -1222,6 +1222,9 @@ int rvu_mbox_handler_cgx_set_link_mode(struct rvu *rvu, u8 cgx_idx, lmac; void *cgxd; + if (!rvu->fwdata) + return LMAC_AF_ERR_FIRMWARE_DATA_NOT_MAPPED; + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) return -EPERM; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index c7c70429eb6c10..8658cb2143dfc7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -1042,32 +1042,35 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, rvu_write64(rvu, blkaddr, NPC_AF_MCAMEX_BANKX_ACTION(index, bank), *(u64 *)&action); - /* update the VF flow rule action with the VF default entry action */ - if (mcam_index < 0) - npc_update_vf_flow_entry(rvu, mcam, blkaddr, pcifunc, - *(u64 *)&action); - /* update the action change in default rule */ pfvf = rvu_get_pfvf(rvu, pcifunc); if (pfvf->def_ucast_rule) pfvf->def_ucast_rule->rx_action = action; - index = npc_get_nixlf_mcam_index(mcam, pcifunc, - nixlf, NIXLF_PROMISC_ENTRY); + if (mcam_index < 0) { + /* update the VF flow rule action with the VF default + * entry action + */ + npc_update_vf_flow_entry(rvu, mcam, blkaddr, pcifunc, + *(u64 *)&action); - /* If PF's promiscuous entry is enabled, - * Set RSS action for that entry as well - */ - npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr, - alg_idx); + index = npc_get_nixlf_mcam_index(mcam, pcifunc, + nixlf, NIXLF_PROMISC_ENTRY); - index = npc_get_nixlf_mcam_index(mcam, pcifunc, - nixlf, NIXLF_ALLMULTI_ENTRY); - /* If PF's allmulti entry is enabled, - * Set RSS action for that entry as well - */ - npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr, - alg_idx); + /* If PF's promiscuous entry is enabled, + * Set RSS action for that entry as well + */ + npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, + blkaddr, alg_idx); + + index = npc_get_nixlf_mcam_index(mcam, pcifunc, + nixlf, NIXLF_ALLMULTI_ENTRY); + /* If PF's allmulti entry is enabled, + * Set RSS action for that entry as well + */ + npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, + blkaddr, alg_idx); + } } void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c index e4a5f9fa6fd46d..bbfd8231aed5ce 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c @@ -56,7 +56,7 @@ int rvu_sdp_init(struct rvu *rvu) struct rvu_pfvf *pfvf; u32 i = 0; - if (rvu->fwdata->channel_data.valid) { + if (rvu->fwdata && rvu->fwdata->channel_data.valid) { sdp_pf_num[0] = 0; pfvf = &rvu->pf[sdp_pf_num[0]]; pfvf->sdp_info = &rvu->fwdata->channel_data.info; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index 4c7e0f345cb5ba..060c715ebad0a1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -328,7 +328,7 @@ static int cn10k_mcs_write_rx_flowid(struct otx2_nic *pfvf, req->data[0] = FIELD_PREP(MCS_TCAM0_MAC_DA_MASK, mac_da); req->mask[0] = ~0ULL; - req->mask[0] = ~MCS_TCAM0_MAC_DA_MASK; + req->mask[0] &= ~MCS_TCAM0_MAC_DA_MASK; req->data[1] = FIELD_PREP(MCS_TCAM1_ETYPE_MASK, ETH_P_MACSEC); req->mask[1] = ~0ULL; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 1c8a3c078a647d..844ad55dd34b83 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -934,13 +934,8 @@ static inline dma_addr_t otx2_dma_map_page(struct otx2_nic *pfvf, size_t offset, size_t size, enum dma_data_direction dir) { - dma_addr_t iova; - - iova = dma_map_page_attrs(pfvf->dev, page, + return dma_map_page_attrs(pfvf->dev, page, offset, size, dir, DMA_ATTR_SKIP_CPU_SYNC); - if (unlikely(dma_mapping_error(pfvf->dev, iova))) - return (dma_addr_t)NULL; - return iova; } static inline void otx2_dma_unmap_page(struct otx2_nic *pfvf, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index b90e23dc49de98..b6449f0a9e7dd5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -418,6 +418,14 @@ static int otx2_set_ringparam(struct net_device *netdev, */ if (rx_count < pfvf->hw.rq_skid) rx_count = pfvf->hw.rq_skid; + + if (ring->rx_pending < 16) { + netdev_err(netdev, + "rx ring size %u invalid, min is 16\n", + ring->rx_pending); + return -EINVAL; + } + rx_count = Q_COUNT(Q_SIZE(rx_count, 3)); /* Due pipelining impact minimum 2000 unused SQ CQE's diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index e808995703cfd0..bbf25769f4994a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -3255,7 +3255,9 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) netdev->watchdog_timeo = OTX2_TX_TIMEOUT; netdev->netdev_ops = &otx2_netdev_ops; - netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_XSK_ZEROCOPY; netdev->min_mtu = OTX2_MIN_MTU; netdev->max_mtu = otx2_get_max_mtu(pf); @@ -3319,6 +3321,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) err_sriov_cleannup: otx2_sriov_vfcfg_cleanup(pf); err_pf_sriov_init: + otx2_unregister_dl(pf); otx2_shutdown_tc(pf); err_mcam_flow_del: otx2_mcam_flow_del(pf); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c index 2a4c9df4eb7972..e63d95c1842f3d 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c @@ -387,6 +387,8 @@ struct prestera_switch *prestera_devlink_alloc(struct prestera_device *dev) dl = devlink_alloc(&prestera_dl_ops, sizeof(struct prestera_switch), dev->dev); + if (!dl) + return NULL; return devlink_priv(dl); } diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 03d2fc7d9b09f8..d1fbf37bdaf793 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4366,7 +4366,6 @@ static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev) pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); return PCI_ERS_RESULT_RECOVERED; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 36806e813c33cc..1301c56e20d653 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -613,3 +613,19 @@ void mlx5_debug_cq_remove(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) cq->dbg = NULL; } } + +static int vhca_id_show(struct seq_file *file, void *priv) +{ + struct mlx5_core_dev *dev = file->private; + + seq_printf(file, "0x%x\n", MLX5_CAP_GEN(dev, vhca_id)); + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(vhca_id); + +void mlx5_vhca_debugfs_init(struct mlx5_core_dev *dev) +{ + debugfs_create_file("vhca_id", 0400, dev->priv.dbg.dbg_root, dev, + &vhca_id_fops); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 887adf4807d164..ea77fbd98396a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -197,6 +197,11 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, struct pci_dev *pdev = dev->pdev; int ret = 0; + if (mlx5_fw_reset_in_progress(dev)) { + NL_SET_ERR_MSG_MOD(extack, "Can't reload during firmware reset"); + return -EBUSY; + } + if (mlx5_dev_is_lightweight(dev)) { if (action != DEVLINK_RELOAD_ACTION_DRIVER_REINIT) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 080e7eab52c7e9..0b82a6a133d6cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -33,6 +33,7 @@ #include "lib/eq.h" #include "fw_tracer.h" #include "fw_tracer_tracepoint.h" +#include static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer) { @@ -358,6 +359,47 @@ static const char *VAL_PARM = "%llx"; static const char *REPLACE_64_VAL_PARM = "%x%x"; static const char *PARAM_CHAR = "%"; +static bool mlx5_is_valid_spec(const char *str) +{ + /* Parse format specifiers to find the actual type. + * Structure: %[flags][width][.precision][length]type + * Skip flags, width, precision & length. + */ + while (isdigit(*str) || *str == '#' || *str == '.' || *str == 'l') + str++; + + /* Check if it's a valid integer/hex specifier or %%: + * Valid formats: %x, %d, %i, %u, etc. + */ + if (*str != 'x' && *str != 'X' && *str != 'd' && *str != 'i' && + *str != 'u' && *str != 'c' && *str != '%') + return false; + + return true; +} + +static bool mlx5_tracer_validate_params(const char *str) +{ + const char *substr = str; + + if (!str) + return false; + + substr = strstr(substr, PARAM_CHAR); + while (substr) { + if (!mlx5_is_valid_spec(substr + 1)) + return false; + + if (*(substr + 1) == '%') + substr = strstr(substr + 2, PARAM_CHAR); + else + substr = strstr(substr + 1, PARAM_CHAR); + + } + + return true; +} + static int mlx5_tracer_message_hash(u32 message_id) { return jhash_1word(message_id, 0) & (MESSAGE_HASH_SIZE - 1); @@ -419,6 +461,10 @@ static int mlx5_tracer_get_num_of_params(char *str) char *substr, *pstr = str; int num_of_params = 0; + /* Validate that all parameters are valid before processing */ + if (!mlx5_tracer_validate_params(str)) + return -EINVAL; + /* replace %llx with %x%x */ substr = strstr(pstr, VAL_PARM); while (substr) { @@ -427,11 +473,15 @@ static int mlx5_tracer_get_num_of_params(char *str) substr = strstr(pstr, VAL_PARM); } - /* count all the % characters */ + /* count all the % characters, but skip %% (escaped percent) */ substr = strstr(str, PARAM_CHAR); while (substr) { - num_of_params += 1; - str = substr + 1; + if (*(substr + 1) != '%') { + num_of_params += 1; + str = substr + 1; + } else { + str = substr + 2; + } substr = strstr(str, PARAM_CHAR); } @@ -570,14 +620,17 @@ void mlx5_tracer_print_trace(struct tracer_string_format *str_frmt, { char tmp[512]; - snprintf(tmp, sizeof(tmp), str_frmt->string, - str_frmt->params[0], - str_frmt->params[1], - str_frmt->params[2], - str_frmt->params[3], - str_frmt->params[4], - str_frmt->params[5], - str_frmt->params[6]); + if (str_frmt->invalid_string) + snprintf(tmp, sizeof(tmp), "BAD_FORMAT: %s", str_frmt->string); + else + snprintf(tmp, sizeof(tmp), str_frmt->string, + str_frmt->params[0], + str_frmt->params[1], + str_frmt->params[2], + str_frmt->params[3], + str_frmt->params[4], + str_frmt->params[5], + str_frmt->params[6]); trace_mlx5_fw(dev->tracer, trace_timestamp, str_frmt->lost, str_frmt->event_id, tmp); @@ -609,6 +662,13 @@ static int mlx5_tracer_handle_raw_string(struct mlx5_fw_tracer *tracer, return 0; } +static void mlx5_tracer_handle_bad_format_string(struct mlx5_fw_tracer *tracer, + struct tracer_string_format *cur_string) +{ + cur_string->invalid_string = true; + list_add_tail(&cur_string->list, &tracer->ready_strings_list); +} + static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer, struct tracer_event *tracer_event) { @@ -619,12 +679,18 @@ static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer, if (!cur_string) return mlx5_tracer_handle_raw_string(tracer, tracer_event); - cur_string->num_of_params = mlx5_tracer_get_num_of_params(cur_string->string); - cur_string->last_param_num = 0; cur_string->event_id = tracer_event->event_id; cur_string->tmsn = tracer_event->string_event.tmsn; cur_string->timestamp = tracer_event->string_event.timestamp; cur_string->lost = tracer_event->lost_event; + cur_string->last_param_num = 0; + cur_string->num_of_params = mlx5_tracer_get_num_of_params(cur_string->string); + if (cur_string->num_of_params < 0) { + pr_debug("%s Invalid format string parameters\n", + __func__); + mlx5_tracer_handle_bad_format_string(tracer, cur_string); + return 0; + } if (cur_string->num_of_params == 0) /* trace with no params */ list_add_tail(&cur_string->list, &tracer->ready_strings_list); } else { @@ -634,6 +700,11 @@ static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer, __func__, tracer_event->string_event.tmsn); return mlx5_tracer_handle_raw_string(tracer, tracer_event); } + if (cur_string->num_of_params < 0) { + pr_debug("%s string parameter of invalid string, dumping\n", + __func__); + return 0; + } cur_string->last_param_num += 1; if (cur_string->last_param_num > TRACER_MAX_PARAMS) { pr_debug("%s Number of params exceeds the max (%d)\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h index 5c548bb74f07b6..30d0bcba884791 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h @@ -125,6 +125,7 @@ struct tracer_string_format { struct list_head list; u32 timestamp; bool lost; + bool invalid_string; }; enum mlx5_fw_tracer_ownership_state { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index a163f81f07c13d..5bced924a24fb5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -69,7 +69,7 @@ struct page_pool; #define MLX5E_METADATA_ETHER_TYPE (0x8CE4) #define MLX5E_METADATA_ETHER_LEN 8 -#define MLX5E_ETH_HARD_MTU (ETH_HLEN + PSP_ENCAP_HLEN + PSP_TRL_SIZE + VLAN_HLEN + ETH_FCS_LEN) +#define MLX5E_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN) #define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu)) #define MLX5E_SW2HW_MTU(params, swmtu) ((swmtu) + ((params)->hard_mtu)) @@ -179,7 +179,8 @@ static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size) } /* Use this function to get max num channels (rxqs/txqs) only to create netdev */ -static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) +static inline unsigned int +mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) { return is_kdump_kernel() ? MLX5E_MIN_NUM_CHANNELS : @@ -963,7 +964,7 @@ struct mlx5e_priv { }; struct mlx5e_dev { - struct mlx5e_priv *priv; + struct net_device *netdev; struct devlink_port dl_port; }; @@ -1238,10 +1239,13 @@ struct net_device * mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile); int mlx5e_attach_netdev(struct mlx5e_priv *priv); void mlx5e_detach_netdev(struct mlx5e_priv *priv); -void mlx5e_destroy_netdev(struct mlx5e_priv *priv); -int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, - const struct mlx5e_profile *new_profile, void *new_ppriv); -void mlx5e_netdev_attach_nic_profile(struct mlx5e_priv *priv); +void mlx5e_destroy_netdev(struct net_device *netdev); +int mlx5e_netdev_change_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, + void *new_ppriv); +void mlx5e_netdev_attach_nic_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev); void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv); void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index c93ee969ea6477..ec715b158a3421 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -448,22 +448,8 @@ static void mlx5e_ptpsq_unhealthy_work(struct work_struct *work) { struct mlx5e_ptpsq *ptpsq = container_of(work, struct mlx5e_ptpsq, report_unhealthy_work); - struct mlx5e_txqsq *sq = &ptpsq->txqsq; - - /* Recovering the PTP SQ means re-enabling NAPI, which requires the - * netdev instance lock. However, SQ closing has to wait for this work - * task to finish while also holding the same lock. So either get the - * lock or find that the SQ is no longer enabled and thus this work is - * not relevant anymore. - */ - while (!netdev_trylock(sq->netdev)) { - if (!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)) - return; - msleep(20); - } mlx5e_reporter_tx_ptpsq_unhealthy(ptpsq); - netdev_unlock(sq->netdev); } static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index b1415992ffa244..a09a7c05820d68 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Mellanox Technologies. +#include + #include "health.h" #include "params.h" #include "txrx.h" @@ -177,6 +179,16 @@ static int mlx5e_rx_reporter_timeout_recover(void *ctx) rq = ctx; priv = rq->priv; + /* Acquire netdev instance lock to synchronize with channel close and + * reopen flows. Either successfully obtain the lock, or detect that + * channels are closing for another reason, making this work no longer + * necessary. + */ + while (!netdev_trylock(rq->netdev)) { + if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &rq->priv->state)) + return 0; + msleep(20); + } mutex_lock(&priv->state_lock); eq = rq->cq.mcq.eq; @@ -186,6 +198,7 @@ static int mlx5e_rx_reporter_timeout_recover(void *ctx) clear_bit(MLX5E_SQ_STATE_ENABLED, &rq->icosq->state); mutex_unlock(&priv->state_lock); + netdev_unlock(rq->netdev); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 9e2cf191ed3086..9f6454102cf799 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -1,6 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2019 Mellanox Technologies. */ +#include + #include "health.h" #include "en/ptp.h" #include "en/devlink.h" @@ -78,6 +80,18 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx) if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) return 0; + /* Recovering queues means re-enabling NAPI, which requires the netdev + * instance lock. However, SQ closing flows have to wait for work tasks + * to finish while also holding the netdev instance lock. So either get + * the lock or find that the SQ is no longer enabled and thus this work + * is not relevant anymore. + */ + while (!netdev_trylock(dev)) { + if (!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)) + return 0; + msleep(20); + } + err = mlx5_core_query_sq_state(mdev, sq->sqn, &state); if (err) { netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n", @@ -113,9 +127,11 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx) else mlx5e_trigger_napi_sched(sq->cq.napi); + netdev_unlock(dev); return 0; out: clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state); + netdev_unlock(dev); return err; } @@ -136,10 +152,24 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) sq = to_ctx->sq; eq = sq->cq.mcq.eq; priv = sq->priv; + + /* Recovering the TX queues implies re-enabling NAPI, which requires + * the netdev instance lock. + * However, channel closing flows have to wait for this work to finish + * while holding the same lock. So either get the lock or find that + * channels are being closed for other reason and this work is not + * relevant anymore. + */ + while (!netdev_trylock(sq->netdev)) { + if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state)) + return 0; + msleep(20); + } + err = mlx5e_health_channel_eq_recover(sq->netdev, eq, sq->cq.ch_stats); if (!err) { to_ctx->status = 0; /* this sq recovered */ - return err; + goto out; } mutex_lock(&priv->state_lock); @@ -147,7 +177,7 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) mutex_unlock(&priv->state_lock); if (!err) { to_ctx->status = 1; /* all channels recovered */ - return err; + goto out; } to_ctx->status = err; @@ -155,7 +185,8 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) netdev_err(priv->netdev, "mlx5e_safe_reopen_channels failed recovering from a tx_timeout, err(%d).\n", err); - +out: + netdev_unlock(sq->netdev); return err; } @@ -172,10 +203,22 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx) return 0; priv = ptpsq->txqsq.priv; + netdev = priv->netdev; + + /* Recovering the PTP SQ means re-enabling NAPI, which requires the + * netdev instance lock. However, SQ closing has to wait for this work + * task to finish while also holding the same lock. So either get the + * lock or find that the SQ is no longer enabled and thus this work is + * not relevant anymore. + */ + while (!netdev_trylock(netdev)) { + if (!test_bit(MLX5E_SQ_STATE_ENABLED, &ptpsq->txqsq.state)) + return 0; + msleep(20); + } mutex_lock(&priv->state_lock); chs = &priv->channels; - netdev = priv->netdev; carrier_ok = netif_carrier_ok(netdev); netif_carrier_off(netdev); @@ -192,6 +235,7 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx) netif_carrier_on(netdev); mutex_unlock(&priv->state_lock); + netdev_unlock(netdev); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 35d9530037a655..9c7064187ed0ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -342,9 +342,8 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry, rt_dst_entry = &rt->dst; break; case AF_INET6: - rt_dst_entry = ipv6_stub->ipv6_dst_lookup_flow( - dev_net(netdev), NULL, &fl6, NULL); - if (IS_ERR(rt_dst_entry)) + if (!IS_ENABLED(CONFIG_IPV6) || + ip6_dst_lookup(dev_net(netdev), NULL, &rt_dst_entry, &fl6)) goto neigh; break; default: @@ -359,6 +358,9 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry, neigh_ha_snapshot(addr, n, netdev); ether_addr_copy(dst, addr); + if (attrs->dir == XFRM_DEV_OFFLOAD_OUT && + is_zero_ether_addr(addr)) + neigh_event_send(n, NULL); dst_release(rt_dst_entry); neigh_release(n); return; @@ -428,7 +430,8 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, attrs->replay_esn.esn = sa_entry->esn_state.esn; attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb; attrs->replay_esn.overlap = sa_entry->esn_state.overlap; - if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) + if (attrs->dir == XFRM_DEV_OFFLOAD_OUT || + x->xso.type != XFRM_DEV_OFFLOAD_PACKET) goto skip_replay_window; switch (x->replay_esn->replay_window) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c index 8565cfe8d7dce8..943d6fc6e7a047 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c @@ -41,6 +41,7 @@ struct mlx5e_accel_fs_psp_prot { struct mlx5_flow_table *ft; struct mlx5_flow_group *miss_group; struct mlx5_flow_handle *miss_rule; + struct mlx5_modify_hdr *rx_modify_hdr; struct mlx5_flow_destination default_dest; struct mlx5e_psp_rx_err rx_err; u32 refcnt; @@ -217,13 +218,19 @@ static int accel_psp_fs_rx_err_create_ft(struct mlx5e_psp_fs *fs, return err; } -static void accel_psp_fs_rx_fs_destroy(struct mlx5e_accel_fs_psp_prot *fs_prot) +static void accel_psp_fs_rx_fs_destroy(struct mlx5e_psp_fs *fs, + struct mlx5e_accel_fs_psp_prot *fs_prot) { if (fs_prot->def_rule) { mlx5_del_flow_rules(fs_prot->def_rule); fs_prot->def_rule = NULL; } + if (fs_prot->rx_modify_hdr) { + mlx5_modify_header_dealloc(fs->mdev, fs_prot->rx_modify_hdr); + fs_prot->rx_modify_hdr = NULL; + } + if (fs_prot->miss_rule) { mlx5_del_flow_rules(fs_prot->miss_rule); fs_prot->miss_rule = NULL; @@ -327,6 +334,7 @@ static int accel_psp_fs_rx_create_ft(struct mlx5e_psp_fs *fs, modify_hdr = NULL; goto out_err; } + fs_prot->rx_modify_hdr = modify_hdr; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_CRYPTO_DECRYPT | @@ -347,7 +355,7 @@ static int accel_psp_fs_rx_create_ft(struct mlx5e_psp_fs *fs, goto out; out_err: - accel_psp_fs_rx_fs_destroy(fs_prot); + accel_psp_fs_rx_fs_destroy(fs, fs_prot); out: kvfree(flow_group_in); kvfree(spec); @@ -364,7 +372,7 @@ static int accel_psp_fs_rx_destroy(struct mlx5e_psp_fs *fs, enum accel_fs_psp_ty /* The netdev unreg already happened, so all offloaded rule are already removed */ fs_prot = &accel_psp->fs_prot[type]; - accel_psp_fs_rx_fs_destroy(fs_prot); + accel_psp_fs_rx_fs_destroy(fs, fs_prot); accel_psp_fs_rx_err_destroy_ft(fs, &fs_prot->rx_err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c index 828bff1137aff9..fa98d0074531b7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c @@ -177,8 +177,6 @@ bool mlx5e_psp_handle_tx_skb(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); struct net *net = sock_net(skb->sk); - const struct ipv6hdr *ip6; - struct tcphdr *th; if (!mlx5e_psp_set_state(priv, skb, psp_st)) return true; @@ -189,11 +187,18 @@ bool mlx5e_psp_handle_tx_skb(struct net_device *netdev, return false; } if (skb_is_gso(skb)) { - ip6 = ipv6_hdr(skb); - th = inner_tcp_hdr(skb); + int len = skb_shinfo(skb)->gso_size + inner_tcp_hdrlen(skb); + struct tcphdr *th = inner_tcp_hdr(skb); - th->check = ~tcp_v6_check(skb_shinfo(skb)->gso_size + inner_tcp_hdrlen(skb), &ip6->saddr, - &ip6->daddr, 0); + if (skb->protocol == htons(ETH_P_IP)) { + const struct iphdr *ip = ip_hdr(skb); + + th->check = ~tcp_v4_check(len, ip->saddr, ip->daddr, 0); + } else { + const struct ipv6hdr *ip6 = ipv6_hdr(skb); + + th->check = ~tcp_v6_check(len, &ip6->saddr, &ip6->daddr, 0); + } } return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5e17eae81f4b3c..cb993ad2d9ad9e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -688,19 +688,7 @@ static void mlx5e_rq_timeout_work(struct work_struct *timeout_work) struct mlx5e_rq, rx_timeout_work); - /* Acquire netdev instance lock to synchronize with channel close and - * reopen flows. Either successfully obtain the lock, or detect that - * channels are closing for another reason, making this work no longer - * necessary. - */ - while (!netdev_trylock(rq->netdev)) { - if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &rq->priv->state)) - return; - msleep(20); - } - mlx5e_reporter_rx_timeout(rq); - netdev_unlock(rq->netdev); } static int mlx5e_alloc_mpwqe_rq_drop_page(struct mlx5e_rq *rq) @@ -1997,20 +1985,7 @@ void mlx5e_tx_err_cqe_work(struct work_struct *recover_work) struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq, recover_work); - /* Recovering queues means re-enabling NAPI, which requires the netdev - * instance lock. However, SQ closing flows have to wait for work tasks - * to finish while also holding the netdev instance lock. So either get - * the lock or find that the SQ is no longer enabled and thus this work - * is not relevant anymore. - */ - while (!netdev_trylock(sq->netdev)) { - if (!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)) - return; - msleep(20); - } - mlx5e_reporter_tx_err_cqe(sq); - netdev_unlock(sq->netdev); } static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode) @@ -4033,6 +4008,8 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) mlx5e_queue_update_stats(priv); } + netdev_stats_to_stats64(stats, &dev->stats); + if (mlx5e_is_uplink_rep(priv)) { struct mlx5e_vport_stats *vstats = &priv->stats.vport; @@ -4049,21 +4026,21 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) mlx5e_fold_sw_stats64(priv, stats); } - stats->rx_missed_errors = priv->stats.qcnt.rx_out_of_buffer; - stats->rx_dropped = PPORT_2863_GET(pstats, if_in_discards); + stats->rx_missed_errors += priv->stats.qcnt.rx_out_of_buffer; + stats->rx_dropped += PPORT_2863_GET(pstats, if_in_discards); - stats->rx_length_errors = + stats->rx_length_errors += PPORT_802_3_GET(pstats, a_in_range_length_errors) + PPORT_802_3_GET(pstats, a_out_of_range_length_field) + PPORT_802_3_GET(pstats, a_frame_too_long_errors) + VNIC_ENV_GET(&priv->stats.vnic, eth_wqe_too_small); - stats->rx_crc_errors = + stats->rx_crc_errors += PPORT_802_3_GET(pstats, a_frame_check_sequence_errors); - stats->rx_frame_errors = PPORT_802_3_GET(pstats, a_alignment_errors); - stats->tx_aborted_errors = PPORT_2863_GET(pstats, if_out_discards); - stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors + - stats->rx_frame_errors; - stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors; + stats->rx_frame_errors += PPORT_802_3_GET(pstats, a_alignment_errors); + stats->tx_aborted_errors += PPORT_2863_GET(pstats, if_out_discards); + stats->rx_errors += stats->rx_length_errors + stats->rx_crc_errors + + stats->rx_frame_errors; + stats->tx_errors += stats->tx_aborted_errors + stats->tx_carrier_errors; } static void mlx5e_nic_set_rx_mode(struct mlx5e_priv *priv) @@ -5100,19 +5077,6 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) struct net_device *netdev = priv->netdev; int i; - /* Recovering the TX queues implies re-enabling NAPI, which requires - * the netdev instance lock. - * However, channel closing flows have to wait for this work to finish - * while holding the same lock. So either get the lock or find that - * channels are being closed for other reason and this work is not - * relevant anymore. - */ - while (!netdev_trylock(netdev)) { - if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state)) - return; - msleep(20); - } - for (i = 0; i < netdev->real_num_tx_queues; i++) { struct netdev_queue *dev_queue = netdev_get_tx_queue(netdev, i); @@ -5125,8 +5089,6 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) /* break if tried to reopened channels */ break; } - - netdev_unlock(netdev); } static void mlx5e_tx_timeout(struct net_device *dev, unsigned int txqueue) @@ -6305,6 +6267,7 @@ int mlx5e_priv_init(struct mlx5e_priv *priv, void mlx5e_priv_cleanup(struct mlx5e_priv *priv) { + bool destroying = test_bit(MLX5E_STATE_DESTROYING, &priv->state); int i; /* bail if change profile failed and also rollback failed */ @@ -6332,6 +6295,8 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv) } memset(priv, 0, sizeof(*priv)); + if (destroying) /* restore destroying bit, to allow unload */ + set_bit(MLX5E_STATE_DESTROYING, &priv->state); } static unsigned int mlx5e_get_max_num_txqs(struct mlx5_core_dev *mdev, @@ -6564,19 +6529,28 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde return err; } -int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, - const struct mlx5e_profile *new_profile, void *new_ppriv) +int mlx5e_netdev_change_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, + void *new_ppriv) { - const struct mlx5e_profile *orig_profile = priv->profile; - struct net_device *netdev = priv->netdev; - struct mlx5_core_dev *mdev = priv->mdev; - void *orig_ppriv = priv->ppriv; + struct mlx5e_priv *priv = netdev_priv(netdev); + const struct mlx5e_profile *orig_profile; int err, rollback_err; + void *orig_ppriv; - /* cleanup old profile */ - mlx5e_detach_netdev(priv); - priv->profile->cleanup(priv); - mlx5e_priv_cleanup(priv); + orig_profile = priv->profile; + orig_ppriv = priv->ppriv; + + /* NULL could happen if previous change_profile failed to rollback */ + if (priv->profile) { + WARN_ON_ONCE(priv->mdev != mdev); + /* cleanup old profile */ + mlx5e_detach_netdev(priv); + priv->profile->cleanup(priv); + mlx5e_priv_cleanup(priv); + } + /* priv members are not valid from this point ... */ if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv); @@ -6593,23 +6567,33 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, return 0; rollback: + if (!orig_profile) { + netdev_warn(netdev, "no original profile to rollback to\n"); + priv->profile = NULL; + return err; + } + rollback_err = mlx5e_netdev_attach_profile(netdev, mdev, orig_profile, orig_ppriv); - if (rollback_err) - netdev_err(netdev, "%s: failed to rollback to orig profile, %d\n", - __func__, rollback_err); + if (rollback_err) { + netdev_err(netdev, "failed to rollback to orig profile, %d\n", + rollback_err); + priv->profile = NULL; + } return err; } -void mlx5e_netdev_attach_nic_profile(struct mlx5e_priv *priv) +void mlx5e_netdev_attach_nic_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev) { - mlx5e_netdev_change_profile(priv, &mlx5e_nic_profile, NULL); + mlx5e_netdev_change_profile(netdev, mdev, &mlx5e_nic_profile, NULL); } -void mlx5e_destroy_netdev(struct mlx5e_priv *priv) +void mlx5e_destroy_netdev(struct net_device *netdev) { - struct net_device *netdev = priv->netdev; + struct mlx5e_priv *priv = netdev_priv(netdev); - mlx5e_priv_cleanup(priv); + if (priv->profile) + mlx5e_priv_cleanup(priv); free_netdev(netdev); } @@ -6617,8 +6601,8 @@ static int _mlx5e_resume(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; - struct net_device *netdev = priv->netdev; + struct mlx5e_priv *priv = netdev_priv(mlx5e_dev->netdev); + struct net_device *netdev = mlx5e_dev->netdev; struct mlx5_core_dev *mdev = edev->mdev; struct mlx5_core_dev *pos, *to; int err, i; @@ -6664,10 +6648,11 @@ static int mlx5e_resume(struct auxiliary_device *adev) static int _mlx5e_suspend(struct auxiliary_device *adev, bool pre_netdev_reg) { + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; - struct net_device *netdev = priv->netdev; - struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_priv *priv = netdev_priv(mlx5e_dev->netdev); + struct net_device *netdev = mlx5e_dev->netdev; + struct mlx5_core_dev *mdev = edev->mdev; struct mlx5_core_dev *pos; int i; @@ -6728,11 +6713,11 @@ static int _mlx5e_probe(struct auxiliary_device *adev) goto err_devlink_port_unregister; } SET_NETDEV_DEVLINK_PORT(netdev, &mlx5e_dev->dl_port); + mlx5e_dev->netdev = netdev; mlx5e_build_nic_netdev(netdev); priv = netdev_priv(netdev); - mlx5e_dev->priv = priv; priv->profile = profile; priv->ppriv = NULL; @@ -6765,7 +6750,7 @@ static int _mlx5e_probe(struct auxiliary_device *adev) err_profile_cleanup: profile->cleanup(priv); err_destroy_netdev: - mlx5e_destroy_netdev(priv); + mlx5e_destroy_netdev(netdev); err_devlink_port_unregister: mlx5e_devlink_port_unregister(mlx5e_dev); err_devlink_unregister: @@ -6795,18 +6780,20 @@ static void _mlx5e_remove(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; + struct net_device *netdev = mlx5e_dev->netdev; + struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = edev->mdev; mlx5_core_uplink_netdev_set(mdev, NULL); - mlx5e_dcbnl_delete_app(priv); + + if (priv->profile) + mlx5e_dcbnl_delete_app(priv); /* When unload driver, the netdev is in registered state * if it's from legacy mode. If from switchdev mode, it * is already unregistered before changing to NIC profile. */ - if (priv->netdev->reg_state == NETREG_REGISTERED) { - mlx5e_psp_unregister(priv); - unregister_netdev(priv->netdev); + if (netdev->reg_state == NETREG_REGISTERED) { + unregister_netdev(netdev); _mlx5e_suspend(adev, false); } else { struct mlx5_core_dev *pos; @@ -6821,7 +6808,7 @@ static void _mlx5e_remove(struct auxiliary_device *adev) /* Avoid cleanup if profile rollback failed. */ if (priv->profile) priv->profile->cleanup(priv); - mlx5e_destroy_netdev(priv); + mlx5e_destroy_netdev(netdev); mlx5e_devlink_port_unregister(mlx5e_dev); mlx5e_destroy_devlink(mlx5e_dev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 0335ca8277efaa..8b65441246244b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1508,17 +1508,16 @@ mlx5e_vport_uplink_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep * { struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); struct net_device *netdev; - struct mlx5e_priv *priv; int err; netdev = mlx5_uplink_netdev_get(dev); if (!netdev) return 0; - priv = netdev_priv(netdev); - rpriv->netdev = priv->netdev; - err = mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, - rpriv); + /* must not use netdev_priv(netdev), it might not be initialized yet */ + rpriv->netdev = netdev; + err = mlx5e_netdev_change_profile(netdev, dev, + &mlx5e_uplink_rep_profile, rpriv); mlx5_uplink_netdev_put(dev, netdev); return err; } @@ -1546,7 +1545,7 @@ mlx5e_vport_uplink_rep_unload(struct mlx5e_rep_priv *rpriv) if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_SWITCH_LEGACY)) unregister_netdev(netdev); - mlx5e_netdev_attach_nic_profile(priv); + mlx5e_netdev_attach_nic_profile(netdev, priv->mdev); } static int @@ -1612,7 +1611,7 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) priv->profile->cleanup(priv); err_destroy_netdev: - mlx5e_destroy_netdev(netdev_priv(netdev)); + mlx5e_destroy_netdev(netdev); return err; } @@ -1667,7 +1666,7 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) mlx5e_rep_vnic_reporter_destroy(priv); mlx5e_detach_netdev(priv); priv->profile->cleanup(priv); - mlx5e_destroy_netdev(priv); + mlx5e_destroy_netdev(netdev); free_ppriv: kvfree(ppriv); /* mlx5e_rep_priv */ } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index a2802cfc9b9894..a8af84fc976383 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -1608,12 +1608,13 @@ void mlx5e_stats_fec_get(struct mlx5e_priv *priv, { int mode = fec_active_mode(priv->mdev); - if (mode == MLX5E_FEC_NOFEC || - !MLX5_CAP_PCAM_FEATURE(priv->mdev, ppcnt_statistical_group)) + if (mode == MLX5E_FEC_NOFEC) return; - fec_set_corrected_bits_total(priv, fec_stats); - fec_set_block_stats(priv, mode, fec_stats); + if (MLX5_CAP_PCAM_FEATURE(priv->mdev, ppcnt_statistical_group)) { + fec_set_corrected_bits_total(priv, fec_stats); + fec_set_block_stats(priv, mode, fec_stats); + } if (MLX5_CAP_PCAM_REG(priv->mdev, pphcr)) fec_set_histograms_stats(priv, mode, hist); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 00c2763e57ca17..ebea43c235cc3f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2147,11 +2147,14 @@ static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow, static void mlx5e_tc_del_fdb_peers_flow(struct mlx5e_tc_flow *flow) { + struct mlx5_devcom_comp_dev *devcom; + struct mlx5_devcom_comp_dev *pos; + struct mlx5_eswitch *peer_esw; int i; - for (i = 0; i < MLX5_MAX_PORTS; i++) { - if (i == mlx5_get_dev_index(flow->priv->mdev)) - continue; + devcom = flow->priv->mdev->priv.eswitch->devcom; + mlx5_devcom_for_each_peer_entry(devcom, peer_esw, pos) { + i = mlx5_get_dev_index(peer_esw->dev); mlx5e_tc_del_fdb_peer_flow(flow, i); } } @@ -5511,12 +5514,16 @@ int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags) void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw) { + struct mlx5_devcom_comp_dev *devcom; + struct mlx5_devcom_comp_dev *pos; struct mlx5e_tc_flow *flow, *tmp; + struct mlx5_eswitch *peer_esw; int i; - for (i = 0; i < MLX5_MAX_PORTS; i++) { - if (i == mlx5_get_dev_index(esw->dev)) - continue; + devcom = esw->devcom; + + mlx5_devcom_for_each_peer_entry(devcom, peer_esw, pos) { + i = mlx5_get_dev_index(peer_esw->dev); list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows[i], peer[i]) mlx5e_tc_del_fdb_peers_flow(flow); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c index 1c37098e09ea51..49a637829c5941 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c @@ -188,7 +188,7 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw, if (IS_ERR(vport->ingress.acl)) { err = PTR_ERR(vport->ingress.acl); vport->ingress.acl = NULL; - return err; + goto out; } err = esw_acl_ingress_lgcy_groups_create(esw, vport); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 16eb99aba2a7e0..2d91f77b016012 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -1002,7 +1002,7 @@ mlx5_esw_host_functions_enabled(const struct mlx5_core_dev *dev) static inline bool mlx5_esw_vport_vhca_id(struct mlx5_eswitch *esw, u16 vportn, u16 *vhca_id) { - return -EOPNOTSUPP; + return false; } #endif /* CONFIG_MLX5_ESWITCH */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 44a142a041b2fe..784130cdf6c07f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -52,6 +52,7 @@ #include "devlink.h" #include "lag/lag.h" #include "en/tc/post_meter.h" +#include "fw_reset.h" /* There are two match-all miss flows, one for unicast dst mac and * one for multicast. @@ -3807,6 +3808,11 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, if (IS_ERR(esw)) return PTR_ERR(esw); + if (mlx5_fw_reset_in_progress(esw->dev)) { + NL_SET_ERR_MSG_MOD(extack, "Can't change eswitch mode during firmware reset"); + return -EBUSY; + } + if (esw_mode_from_devlink(mode, &mlx5_mode)) return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 1af76da8b1320e..b79544134e2a25 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -1167,7 +1167,8 @@ int mlx5_fs_cmd_set_tx_flow_table_root(struct mlx5_core_dev *dev, u32 ft_id, boo u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {}; u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {}; - if (disconnect && MLX5_CAP_FLOWTABLE_NIC_TX(dev, reset_root_to_default)) + if (disconnect && + !MLX5_CAP_FLOWTABLE_NIC_TX(dev, reset_root_to_default)) return -EOPNOTSUPP; MLX5_SET(set_flow_table_root_in, in, opcode, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 89e399606877ba..4544f1968f73fe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -15,6 +15,7 @@ enum { MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, + MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, }; struct mlx5_fw_reset { @@ -127,6 +128,16 @@ int mlx5_fw_reset_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_ty return mlx5_reg_mfrl_query(dev, reset_level, reset_type, NULL, NULL); } +bool mlx5_fw_reset_in_progress(struct mlx5_core_dev *dev) +{ + struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + + if (!fw_reset) + return false; + + return test_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags); +} + static int mlx5_fw_reset_get_reset_method(struct mlx5_core_dev *dev, u8 *reset_method) { @@ -242,6 +253,8 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev) BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE)); devl_unlock(devlink); } + + clear_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags); } static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev) @@ -461,27 +474,48 @@ static void mlx5_sync_reset_request_event(struct work_struct *work) struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset, reset_request_work); struct mlx5_core_dev *dev = fw_reset->dev; + bool nack_request = false; + struct devlink *devlink; int err; err = mlx5_fw_reset_get_reset_method(dev, &fw_reset->reset_method); - if (err) + if (err) { + nack_request = true; mlx5_core_warn(dev, "Failed reading MFRL, err %d\n", err); + } else if (!mlx5_is_reset_now_capable(dev, fw_reset->reset_method) || + test_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, + &fw_reset->reset_flags)) { + nack_request = true; + } - if (err || test_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, &fw_reset->reset_flags) || - !mlx5_is_reset_now_capable(dev, fw_reset->reset_method)) { + devlink = priv_to_devlink(dev); + /* For external resets, try to acquire devl_lock. Skip if devlink reset is + * pending (lock already held) + */ + if (nack_request || + (!test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, + &fw_reset->reset_flags) && + !devl_trylock(devlink))) { err = mlx5_fw_reset_set_reset_sync_nack(dev); mlx5_core_warn(dev, "PCI Sync FW Update Reset Nack %s", err ? "Failed" : "Sent"); return; } + if (mlx5_sync_reset_set_reset_requested(dev)) - return; + goto unlock; + + set_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags); err = mlx5_fw_reset_set_reset_sync_ack(dev); if (err) mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack Failed. Error code: %d\n", err); else mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack. Device reset is expected.\n"); + +unlock: + if (!test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) + devl_unlock(devlink); } static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev, u16 dev_id) @@ -721,6 +755,8 @@ static void mlx5_sync_reset_abort_event(struct work_struct *work) if (mlx5_sync_reset_clear_reset_requested(dev, true)) return; + + clear_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags); mlx5_core_warn(dev, "PCI Sync FW Update Reset Aborted.\n"); } @@ -757,6 +793,7 @@ static void mlx5_sync_reset_timeout_work(struct work_struct *work) if (mlx5_sync_reset_clear_reset_requested(dev, true)) return; + clear_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags); mlx5_core_warn(dev, "PCI Sync FW Update Reset Timeout.\n"); } @@ -843,7 +880,8 @@ void mlx5_drain_fw_reset(struct mlx5_core_dev *dev) cancel_work_sync(&fw_reset->reset_reload_work); cancel_work_sync(&fw_reset->reset_now_work); cancel_work_sync(&fw_reset->reset_abort_work); - cancel_delayed_work(&fw_reset->reset_timeout_work); + if (test_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags)) + mlx5_sync_reset_clear_reset_requested(dev, true); } static const struct devlink_param mlx5_fw_reset_devlink_params[] = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h index d5b28525c960dc..2d96b2adc1cdf1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h @@ -10,6 +10,7 @@ int mlx5_fw_reset_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_ty int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel, struct netlink_ext_ack *extack); int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev); +bool mlx5_fw_reset_in_progress(struct mlx5_core_dev *dev); int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev); void mlx5_sync_reset_unload_flow(struct mlx5_core_dev *dev, bool locked); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 3db0387bf6dcb7..8ec04a5f434dd4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -1413,6 +1413,7 @@ static int __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev) static void mlx5_lag_unregister_hca_devcom_comp(struct mlx5_core_dev *dev) { mlx5_devcom_unregister_component(dev->priv.hca_devcom_comp); + dev->priv.hca_devcom_comp = NULL; } static int mlx5_lag_register_hca_devcom_comp(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index aee17fcf3b36c3..cdc99fe5c95686 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -173,10 +173,15 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event, } /* Handle multipath entry with lower priority value */ - if (mp->fib.mfi && mp->fib.mfi != fi && + if (mp->fib.mfi && (mp->fib.dst != fen_info->dst || mp->fib.dst_len != fen_info->dst_len) && - fi->fib_priority >= mp->fib.priority) + mp->fib.dst_len <= fen_info->dst_len && + !(mp->fib.dst_len == fen_info->dst_len && + fi->fib_priority < mp->fib.priority)) { + mlx5_core_dbg(ldev->pf[idx].dev, + "Multipath entry with lower priority was rejected\n"); return; + } nh_dev0 = mlx5_lag_get_next_fib_dev(ldev, fi, NULL); nh_dev1 = mlx5_lag_get_next_fib_dev(ldev, fi, nh_dev0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index aad52d3a90e68b..2d86af8f0d9b81 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -67,12 +67,19 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev) static int enable_mpesw(struct mlx5_lag *ldev) { - int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); struct mlx5_core_dev *dev0; int err; + int idx; int i; - if (idx < 0 || ldev->mode != MLX5_LAG_MODE_NONE) + if (ldev->mode == MLX5_LAG_MODE_MPESW) + return 0; + + if (ldev->mode != MLX5_LAG_MODE_NONE) + return -EINVAL; + + idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); + if (idx < 0) return -EINVAL; dev0 = ldev->pf[idx].dev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 70c156591b0ba9..acba430a94da27 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -999,16 +999,10 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) goto err_irq_cleanup; } - err = mlx5_events_init(dev); - if (err) { - mlx5_core_err(dev, "failed to initialize events\n"); - goto err_eq_cleanup; - } - err = mlx5_fw_reset_init(dev); if (err) { mlx5_core_err(dev, "failed to initialize fw reset events\n"); - goto err_events_cleanup; + goto err_eq_cleanup; } mlx5_cq_debugfs_init(dev); @@ -1110,8 +1104,6 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) mlx5_cleanup_reserved_gids(dev); mlx5_cq_debugfs_cleanup(dev); mlx5_fw_reset_cleanup(dev); -err_events_cleanup: - mlx5_events_cleanup(dev); err_eq_cleanup: mlx5_eq_table_cleanup(dev); err_irq_cleanup: @@ -1144,7 +1136,6 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_cleanup_reserved_gids(dev); mlx5_cq_debugfs_cleanup(dev); mlx5_fw_reset_cleanup(dev); - mlx5_events_cleanup(dev); mlx5_eq_table_cleanup(dev); mlx5_irq_table_cleanup(dev); mlx5_devcom_unregister_device(dev->priv.devc); @@ -1812,15 +1803,23 @@ static int mlx5_hca_caps_alloc(struct mlx5_core_dev *dev) return -ENOMEM; } -static int vhca_id_show(struct seq_file *file, void *priv) +static int mlx5_notifiers_init(struct mlx5_core_dev *dev) { - struct mlx5_core_dev *dev = file->private; + int err; + + err = mlx5_events_init(dev); + if (err) { + mlx5_core_err(dev, "failed to initialize events\n"); + return err; + } - seq_printf(file, "0x%x\n", MLX5_CAP_GEN(dev, vhca_id)); return 0; } -DEFINE_SHOW_ATTRIBUTE(vhca_id); +static void mlx5_notifiers_cleanup(struct mlx5_core_dev *dev) +{ + mlx5_events_cleanup(dev); +} int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) { @@ -1846,7 +1845,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) priv->numa_node = dev_to_node(mlx5_core_dma_dev(dev)); priv->dbg.dbg_root = debugfs_create_dir(dev_name(dev->device), mlx5_debugfs_root); - debugfs_create_file("vhca_id", 0400, priv->dbg.dbg_root, dev, &vhca_id_fops); + INIT_LIST_HEAD(&priv->traps); err = mlx5_cmd_init(dev); @@ -1877,6 +1876,10 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) if (err) goto err_hca_caps; + err = mlx5_notifiers_init(dev); + if (err) + goto err_hca_caps; + /* The conjunction of sw_vhca_id with sw_owner_id will be a global * unique id per function which uses mlx5_core. * Those values are supplied to FW as part of the init HCA command to @@ -1919,6 +1922,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev) if (priv->sw_vhca_id > 0) ida_free(&sw_vhca_ida, dev->priv.sw_vhca_id); + mlx5_notifiers_cleanup(dev); mlx5_hca_caps_free(dev); mlx5_adev_cleanup(dev); mlx5_pagealloc_cleanup(dev); @@ -1979,6 +1983,8 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id) goto err_init_one; } + mlx5_vhca_debugfs_init(dev); + pci_save_state(pdev); return 0; @@ -2094,7 +2100,6 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); err = wait_vital(pdev); if (err) { @@ -2189,6 +2194,7 @@ static void shutdown(struct pci_dev *pdev) mlx5_core_info(dev, "Shutdown was called\n"); set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state); + mlx5_drain_fw_reset(dev); mlx5_drain_health_wq(dev); err = mlx5_try_fast_unload(dev); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 082259b56816ce..da5345e19082d6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -258,6 +258,7 @@ int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages); void mlx5_cmd_flush(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); +void mlx5_vhca_debugfs_init(struct mlx5_core_dev *dev); int mlx5_query_pcam_reg(struct mlx5_core_dev *dev, u32 *pcam, u8 feature_group, u8 access_reg_group); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index aa9f2b0a77d36f..876e648c91ba8b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -430,7 +430,8 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, mlx5_qsfp_eeprom_params_set(&query.i2c_address, &query.page, &offset); break; default: - mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id); + mlx5_core_dbg(dev, "Module ID not recognized: 0x%x\n", + module_id); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index b706f1486504a7..c45540fe7d9d95 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -76,6 +76,7 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia goto init_one_err; } + mlx5_vhca_debugfs_init(mdev); return 0; init_one_err: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wc.c b/drivers/net/ethernet/mellanox/mlx5/core/wc.c index 05e5fd777d4f41..8701b7b6a2d515 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wc.c @@ -2,6 +2,7 @@ // Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. #include +#include #include #include "lib/clock.h" #include "mlx5_core.h" @@ -14,7 +15,7 @@ #define TEST_WC_NUM_WQES 255 #define TEST_WC_LOG_CQ_SZ (order_base_2(TEST_WC_NUM_WQES)) #define TEST_WC_SQ_LOG_WQ_SZ TEST_WC_LOG_CQ_SZ -#define TEST_WC_POLLING_MAX_TIME_JIFFIES msecs_to_jiffies(100) +#define TEST_WC_POLLING_MAX_TIME_USEC (100 * USEC_PER_MSEC) struct mlx5_wc_cq { /* data path - accessed per cqe */ @@ -358,7 +359,6 @@ static int mlx5_wc_poll_cq(struct mlx5_wc_sq *sq) static void mlx5_core_test_wc(struct mlx5_core_dev *mdev) { unsigned int offset = 0; - unsigned long expires; struct mlx5_wc_sq *sq; int i, err; @@ -388,13 +388,9 @@ static void mlx5_core_test_wc(struct mlx5_core_dev *mdev) mlx5_wc_post_nop(sq, &offset, true); - expires = jiffies + TEST_WC_POLLING_MAX_TIME_JIFFIES; - do { - err = mlx5_wc_poll_cq(sq); - if (err) - usleep_range(2, 10); - } while (mdev->wc_state == MLX5_WC_STATE_UNINITIALIZED && - time_is_after_jiffies(expires)); + poll_timeout_us(mlx5_wc_poll_cq(sq), + mdev->wc_state != MLX5_WC_STATE_UNINITIALIZED, 10, + TEST_WC_POLLING_MAX_TIME_USEC, false); mlx5_wc_destroy_sq(sq); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c index 5afe6b155ef0d5..81935f87bfcd71 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -440,7 +440,9 @@ int mlxsw_sp_mr_route_add(struct mlxsw_sp_mr_table *mr_table, rhashtable_remove_fast(&mr_table->route_ht, &mr_orig_route->ht_node, mlxsw_sp_mr_route_ht_params); + mutex_lock(&mr_table->route_list_lock); list_del(&mr_orig_route->node); + mutex_unlock(&mr_table->route_list_lock); mlxsw_sp_mr_route_destroy(mr_table, mr_orig_route); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index a2033837182e86..2d0e89bd2fb9ca 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2265,6 +2265,7 @@ mlxsw_sp_neigh_entry_alloc(struct mlxsw_sp *mlxsw_sp, struct neighbour *n, if (!neigh_entry) return NULL; + neigh_hold(n); neigh_entry->key.n = n; neigh_entry->rif = rif; INIT_LIST_HEAD(&neigh_entry->nexthop_list); @@ -2274,6 +2275,7 @@ mlxsw_sp_neigh_entry_alloc(struct mlxsw_sp *mlxsw_sp, struct neighbour *n, static void mlxsw_sp_neigh_entry_free(struct mlxsw_sp_neigh_entry *neigh_entry) { + neigh_release(neigh_entry->key.n); kfree(neigh_entry); } @@ -2858,6 +2860,11 @@ static int mlxsw_sp_router_schedule_work(struct net *net, if (!net_work) return NOTIFY_BAD; + /* Take a reference to ensure the neighbour won't be destructed until + * we drop the reference in the work item. + */ + neigh_clone(n); + INIT_WORK(&net_work->work, cb); net_work->mlxsw_sp = router->mlxsw_sp; net_work->n = n; @@ -2881,11 +2888,6 @@ static int mlxsw_sp_router_schedule_neigh_work(struct mlxsw_sp_router *router, struct net *net; net = neigh_parms_net(n->parms); - - /* Take a reference to ensure the neighbour won't be destructed until we - * drop the reference in delayed work. - */ - neigh_clone(n); return mlxsw_sp_router_schedule_work(net, router, n, mlxsw_sp_router_neigh_event_work); } @@ -4320,6 +4322,8 @@ mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp, if (err) goto err_neigh_entry_insert; + neigh_release(old_n); + read_lock_bh(&n->lock); nud_state = n->nud_state; dead = n->dead; @@ -4328,14 +4332,10 @@ mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp, list_for_each_entry(nh, &neigh_entry->nexthop_list, neigh_list_node) { - neigh_release(old_n); - neigh_clone(n); __mlxsw_sp_nexthop_neigh_update(nh, !entry_connected); mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp); } - neigh_release(n); - return 0; err_neigh_entry_insert: @@ -4428,6 +4428,11 @@ static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp, } } + /* Release the reference taken by neigh_lookup() / neigh_create() since + * neigh_entry already holds one. + */ + neigh_release(n); + /* If that is the first nexthop connected to that neigh, add to * nexthop_neighs_list */ @@ -4454,11 +4459,9 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh) { struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry; - struct neighbour *n; if (!neigh_entry) return; - n = neigh_entry->key.n; __mlxsw_sp_nexthop_neigh_update(nh, true); list_del(&nh->neigh_list_node); @@ -4472,8 +4475,6 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp, if (!neigh_entry->connected && list_empty(&neigh_entry->nexthop_list)) mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry); - - neigh_release(n); } static bool mlxsw_sp_ipip_netdev_ul_up(struct net_device *ol_dev) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c index 95fac020eb93c7..08aed4103323e0 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c @@ -1142,6 +1142,9 @@ static int fbnic_set_cls_rule_ins(struct fbnic_net *fbn, return -EINVAL; } + dest |= FIELD_PREP(FBNIC_RPC_ACT_TBL0_DMA_HINT, + FBNIC_RCD_HDR_AL_DMA_HINT_L4); + /* Write action table values */ act_tcam->dest = dest; act_tcam->rss_en_mask = fbnic_flow_hash_2_rss_en_mask(fbn, hash_idx); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw_log.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw_log.c index 85a883dba385fe..d8a9a7d7c2375f 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_fw_log.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw_log.c @@ -51,8 +51,6 @@ int fbnic_fw_log_init(struct fbnic_dev *fbd) log->data_start = data; log->data_end = data + FBNIC_FW_LOG_SIZE; - fbnic_fw_log_enable(fbd, true); - return 0; } @@ -63,7 +61,6 @@ void fbnic_fw_log_free(struct fbnic_dev *fbd) if (!fbnic_fw_log_ready(fbd)) return; - fbnic_fw_log_disable(fbd); INIT_LIST_HEAD(&log->entries); log->size = 0; vfree(log->data_start); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c index e95be0e7bd9e0d..cbedaa037cfa88 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c @@ -262,6 +262,23 @@ static int fbnic_set_mac(struct net_device *netdev, void *p) return 0; } +static int fbnic_change_mtu(struct net_device *dev, int new_mtu) +{ + struct fbnic_net *fbn = netdev_priv(dev); + + if (fbnic_check_split_frames(fbn->xdp_prog, new_mtu, fbn->hds_thresh)) { + dev_err(&dev->dev, + "MTU %d is larger than HDS threshold %d in XDP mode\n", + new_mtu, fbn->hds_thresh); + + return -EINVAL; + } + + WRITE_ONCE(dev->mtu, new_mtu); + + return 0; +} + void fbnic_clear_rx_mode(struct fbnic_dev *fbd) { struct net_device *netdev = fbd->netdev; @@ -533,6 +550,7 @@ static const struct net_device_ops fbnic_netdev_ops = { .ndo_start_xmit = fbnic_xmit_frame, .ndo_features_check = fbnic_features_check, .ndo_set_mac_address = fbnic_set_mac, + .ndo_change_mtu = fbnic_change_mtu, .ndo_set_rx_mode = fbnic_set_rx_mode, .ndo_get_stats64 = fbnic_get_stats64, .ndo_bpf = fbnic_bpf, @@ -790,6 +808,8 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd) netdev->hw_enc_features |= netdev->features; netdev->features |= NETIF_F_NTUPLE; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_RX_SG; + netdev->min_mtu = IPV6_MIN_MTU; netdev->max_mtu = FBNIC_MAX_JUMBO_FRAME_SIZE - ETH_HLEN; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h index b0a87c57910f26..e6ca23a9957d9f 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h @@ -73,6 +73,8 @@ struct fbnic_net { /* Time stamping filter config */ struct kernel_hwtstamp_config hwtstamp_config; + + bool tx_pause; }; int __fbnic_open(struct fbnic_net *fbn); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c index a7a6b4db8016f3..698b8a85afb318 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c @@ -303,11 +303,17 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto free_irqs; } + err = fbnic_fw_log_init(fbd); + if (err) + dev_warn(fbd->dev, + "Unable to initialize firmware log buffer: %d\n", + err); + err = fbnic_fw_request_mbx(fbd); if (err) { dev_err(&pdev->dev, "Firmware mailbox initialization failure\n"); - goto free_irqs; + goto free_fw_log; } /* Send the request to enable the FW logging to host. Note if this @@ -315,11 +321,7 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * possible the FW is just too old to support the logging and needs * to be updated. */ - err = fbnic_fw_log_init(fbd); - if (err) - dev_warn(fbd->dev, - "Unable to initialize firmware log buffer: %d\n", - err); + fbnic_fw_log_enable(fbd, true); fbnic_devlink_register(fbd); fbnic_devlink_otp_check(fbd, "error detected during probe"); @@ -363,6 +365,8 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * firmware updates for fixes. */ return 0; +free_fw_log: + fbnic_fw_log_free(fbd); free_irqs: fbnic_free_irqs(fbd); err_destroy_health: @@ -397,8 +401,9 @@ static void fbnic_remove(struct pci_dev *pdev) fbnic_hwmon_unregister(fbd); fbnic_dbg_fbd_exit(fbd); fbnic_devlink_unregister(fbd); - fbnic_fw_log_free(fbd); + fbnic_fw_log_disable(fbd); fbnic_fw_free_mbx(fbd); + fbnic_fw_log_free(fbd); fbnic_free_irqs(fbd); fbnic_devlink_health_destroy(fbd); @@ -574,7 +579,6 @@ static pci_ers_result_t fbnic_err_slot_reset(struct pci_dev *pdev) pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); - pci_save_state(pdev); if (pci_enable_device_mem(pdev)) { dev_err(&pdev->dev, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c index 7ce3fdd252828d..62701923cfe96f 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c @@ -208,6 +208,9 @@ fbnic_phylink_mac_link_up(struct phylink_config *config, struct fbnic_net *fbn = netdev_priv(netdev); struct fbnic_dev *fbd = fbn->fbd; + fbn->tx_pause = tx_pause; + fbnic_config_drop_mode(fbn, tx_pause); + fbd->mac->link_up(fbd, tx_pause, rx_pause); } diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c index 7f31e890031c06..42a186db43ea93 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c @@ -338,9 +338,8 @@ void fbnic_rss_reinit(struct fbnic_dev *fbd, struct fbnic_net *fbn) else if (tstamp_mask & (1u << flow_type)) dest |= FBNIC_RPC_ACT_TBL0_TS_ENA; - if (act1_value[flow_type] & FBNIC_RPC_TCAM_ACT1_L4_VALID) - dest |= FIELD_PREP(FBNIC_RPC_ACT_TBL0_DMA_HINT, - FBNIC_RCD_HDR_AL_DMA_HINT_L4); + dest |= FIELD_PREP(FBNIC_RPC_ACT_TBL0_DMA_HINT, + FBNIC_RCD_HDR_AL_DMA_HINT_L4); rss_en_mask = fbnic_flow_hash_2_rss_en_mask(fbn, flow_type); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c index b1e8ce89870f73..fbdf79b6ad2ded 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c @@ -2573,20 +2573,44 @@ static void fbnic_enable_bdq(struct fbnic_ring *hpq, struct fbnic_ring *ppq) } static void fbnic_config_drop_mode_rcq(struct fbnic_napi_vector *nv, - struct fbnic_ring *rcq) + struct fbnic_ring *rcq, bool tx_pause, + bool hdr_split) { + struct fbnic_net *fbn = netdev_priv(nv->napi.dev); u32 drop_mode, rcq_ctl; - drop_mode = FBNIC_QUEUE_RDE_CTL0_DROP_IMMEDIATE; + if (!tx_pause && fbn->num_rx_queues > 1) + drop_mode = FBNIC_QUEUE_RDE_CTL0_DROP_IMMEDIATE; + else + drop_mode = FBNIC_QUEUE_RDE_CTL0_DROP_NEVER; /* Specify packet layout */ rcq_ctl = FIELD_PREP(FBNIC_QUEUE_RDE_CTL0_DROP_MODE_MASK, drop_mode) | FIELD_PREP(FBNIC_QUEUE_RDE_CTL0_MIN_HROOM_MASK, FBNIC_RX_HROOM) | - FIELD_PREP(FBNIC_QUEUE_RDE_CTL0_MIN_TROOM_MASK, FBNIC_RX_TROOM); + FIELD_PREP(FBNIC_QUEUE_RDE_CTL0_MIN_TROOM_MASK, FBNIC_RX_TROOM) | + FIELD_PREP(FBNIC_QUEUE_RDE_CTL0_EN_HDR_SPLIT, hdr_split); fbnic_ring_wr32(rcq, FBNIC_QUEUE_RDE_CTL0, rcq_ctl); } +void fbnic_config_drop_mode(struct fbnic_net *fbn, bool txp) +{ + bool hds; + int i, t; + + hds = fbn->hds_thresh < FBNIC_HDR_BYTES_MIN; + + for (i = 0; i < fbn->num_napi; i++) { + struct fbnic_napi_vector *nv = fbn->napi[i]; + + for (t = 0; t < nv->rxt_count; t++) { + struct fbnic_q_triad *qt = &nv->qt[nv->txt_count + t]; + + fbnic_config_drop_mode_rcq(nv, &qt->cmpl, txp, hds); + } + } +} + static void fbnic_config_rim_threshold(struct fbnic_ring *rcq, u16 nv_idx, u32 rx_desc) { u32 threshold; @@ -2633,20 +2657,18 @@ static void fbnic_enable_rcq(struct fbnic_napi_vector *nv, { struct fbnic_net *fbn = netdev_priv(nv->napi.dev); u32 log_size = fls(rcq->size_mask); - u32 hds_thresh = fbn->hds_thresh; u32 rcq_ctl = 0; - - fbnic_config_drop_mode_rcq(nv, rcq); + bool hdr_split; + u32 hds_thresh; /* Force lower bound on MAX_HEADER_BYTES. Below this, all frames should * be split at L4. It would also result in the frames being split at * L2/L3 depending on the frame size. */ - if (fbn->hds_thresh < FBNIC_HDR_BYTES_MIN) { - rcq_ctl = FBNIC_QUEUE_RDE_CTL0_EN_HDR_SPLIT; - hds_thresh = FBNIC_HDR_BYTES_MIN; - } + hdr_split = fbn->hds_thresh < FBNIC_HDR_BYTES_MIN; + fbnic_config_drop_mode_rcq(nv, rcq, fbn->tx_pause, hdr_split); + hds_thresh = max(fbn->hds_thresh, FBNIC_HDR_BYTES_MIN); rcq_ctl |= FIELD_PREP(FBNIC_QUEUE_RDE_CTL1_PADLEN_MASK, FBNIC_RX_PAD) | FIELD_PREP(FBNIC_QUEUE_RDE_CTL1_MAX_HDR_MASK, hds_thresh) | FIELD_PREP(FBNIC_QUEUE_RDE_CTL1_PAYLD_OFF_MASK, @@ -2699,7 +2721,6 @@ static void __fbnic_nv_enable(struct fbnic_napi_vector *nv) &nv->napi); fbnic_enable_bdq(&qt->sub0, &qt->sub1); - fbnic_config_drop_mode_rcq(nv, &qt->cmpl); fbnic_enable_rcq(nv, &qt->cmpl); } } diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h index ca37da5a0b1797..51a98f27d5d912 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h @@ -66,7 +66,7 @@ struct fbnic_net; (4096 - FBNIC_RX_HROOM - FBNIC_RX_TROOM - FBNIC_RX_PAD) #define FBNIC_HDS_THRESH_DEFAULT \ (1536 - FBNIC_RX_PAD) -#define FBNIC_HDR_BYTES_MIN 128 +#define FBNIC_HDR_BYTES_MIN 256 struct fbnic_pkt_buff { struct xdp_buff buff; @@ -184,6 +184,7 @@ void fbnic_reset_netif_queues(struct fbnic_net *fbn); irqreturn_t fbnic_msix_clean_rings(int irq, void *data); void fbnic_napi_enable(struct fbnic_net *fbn); void fbnic_napi_disable(struct fbnic_net *fbn); +void fbnic_config_drop_mode(struct fbnic_net *fbn, bool tx_pause); void fbnic_enable(struct fbnic_net *fbn); void fbnic_disable(struct fbnic_net *fbn); void fbnic_flush(struct fbnic_net *fbn); diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 9d70b51ca91d62..e4c542fc6c2b87 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -3915,7 +3915,6 @@ static int lan743x_pm_resume(struct device *dev) pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); - pci_save_state(pdev); /* Restore HW_CFG that was saved during pm suspend */ if (adapter->is_pci11x1x) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c index 2f168700f63c11..8b2e07821a9505 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c @@ -576,7 +576,7 @@ static int sparx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) static struct ptp_clock_info sparx5_ptp_clock_info = { .owner = THIS_MODULE, .name = "sparx5 ptp", - .max_adj = 200000, + .max_adj = 10000000, .gettime64 = sparx5_ptp_gettime64, .settime64 = sparx5_ptp_settime64, .adjtime = sparx5_ptp_adjtime, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.h b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.h index 1231a80335d7b1..04f76f1e23f60a 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.h @@ -35,7 +35,7 @@ #define SPX5_SE_BURST_UNIT 4096 /* Dwrr */ -#define SPX5_DWRR_COST_MAX 63 +#define SPX5_DWRR_COST_MAX 31 struct sparx5_shaper { u32 mode; diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 08bee56aea35f3..c345d9b17c8921 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -2307,14 +2307,16 @@ static void ocelot_set_aggr_pgids(struct ocelot *ocelot) /* Now, set PGIDs for each active LAG */ for (lag = 0; lag < ocelot->num_phys_ports; lag++) { - struct net_device *bond = ocelot->ports[lag]->bond; + struct ocelot_port *ocelot_port = ocelot->ports[lag]; int num_active_ports = 0; + struct net_device *bond; unsigned long bond_mask; u8 aggr_idx[16]; - if (!bond || (visited & BIT(lag))) + if (!ocelot_port || !ocelot_port->bond || (visited & BIT(lag))) continue; + bond = ocelot_port->bond; bond_mask = ocelot_get_bond_mask(ocelot, bond); for_each_set_bit(port, &bond_mask, ocelot->num_phys_ports) { diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 469784d3a1a67b..1b82693204640d 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -551,44 +551,81 @@ static int ocelot_port_stop(struct net_device *dev) return 0; } -static netdev_tx_t ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) +static bool ocelot_xmit_timestamp(struct ocelot *ocelot, int port, + struct sk_buff *skb, u32 *rew_op) { - struct ocelot_port_private *priv = netdev_priv(dev); - struct ocelot_port *ocelot_port = &priv->port; - struct ocelot *ocelot = ocelot_port->ocelot; - int port = priv->port.index; - u32 rew_op = 0; - - if (!static_branch_unlikely(&ocelot_fdma_enabled) && - !ocelot_can_inject(ocelot, 0)) - return NETDEV_TX_BUSY; - - /* Check if timestamping is needed */ if (ocelot->ptp && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { struct sk_buff *clone = NULL; if (ocelot_port_txtstamp_request(ocelot, port, skb, &clone)) { kfree_skb(skb); - return NETDEV_TX_OK; + return false; } if (clone) OCELOT_SKB_CB(skb)->clone = clone; - rew_op = ocelot_ptp_rew_op(skb); + *rew_op = ocelot_ptp_rew_op(skb); } - if (static_branch_unlikely(&ocelot_fdma_enabled)) { - ocelot_fdma_inject_frame(ocelot, port, rew_op, skb, dev); - } else { - ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); + return true; +} + +static netdev_tx_t ocelot_port_xmit_fdma(struct sk_buff *skb, + struct net_device *dev) +{ + struct ocelot_port_private *priv = netdev_priv(dev); + struct ocelot_port *ocelot_port = &priv->port; + struct ocelot *ocelot = ocelot_port->ocelot; + int port = priv->port.index; + u32 rew_op = 0; + + if (!ocelot_xmit_timestamp(ocelot, port, skb, &rew_op)) + return NETDEV_TX_OK; + + ocelot_fdma_inject_frame(ocelot, port, rew_op, skb, dev); + + return NETDEV_TX_OK; +} - consume_skb(skb); +static netdev_tx_t ocelot_port_xmit_inj(struct sk_buff *skb, + struct net_device *dev) +{ + struct ocelot_port_private *priv = netdev_priv(dev); + struct ocelot_port *ocelot_port = &priv->port; + struct ocelot *ocelot = ocelot_port->ocelot; + int port = priv->port.index; + u32 rew_op = 0; + + ocelot_lock_inj_grp(ocelot, 0); + + if (!ocelot_can_inject(ocelot, 0)) { + ocelot_unlock_inj_grp(ocelot, 0); + return NETDEV_TX_BUSY; } + if (!ocelot_xmit_timestamp(ocelot, port, skb, &rew_op)) { + ocelot_unlock_inj_grp(ocelot, 0); + return NETDEV_TX_OK; + } + + ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); + + ocelot_unlock_inj_grp(ocelot, 0); + + consume_skb(skb); + return NETDEV_TX_OK; } +static netdev_tx_t ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) +{ + if (static_branch_unlikely(&ocelot_fdma_enabled)) + return ocelot_port_xmit_fdma(skb, dev); + + return ocelot_port_xmit_inj(skb, dev); +} + enum ocelot_action_type { OCELOT_MACT_LEARN, OCELOT_MACT_FORGET, diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index e611ff7fa3faba..7be30a8df26858 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -3416,10 +3416,6 @@ static void myri10ge_watchdog(struct work_struct *work) * nic was resumed from power saving mode. */ pci_restore_state(mgp->pdev); - - /* save state again for accounting reasons */ - pci_save_state(mgp->pdev); - } else { /* if we get back -1's from our slot, perhaps somebody * powered off our card. Don't try to reset it in diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 5026b0263d430b..1e55ccb4822b0b 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -3425,7 +3425,6 @@ static void s2io_reset(struct s2io_nic *sp) /* Restore the PCI state saved during initialization. */ pci_restore_state(sp->pdev); - pci_save_state(sp->pdev); pci_read_config_word(sp->pdev, 0x2, &val16); if (check_pci_device_id(val16) != (u16)PCI_ANY_ID) break; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index 2d9efadb5d2ae1..347b0aff100b9f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -263,9 +263,10 @@ static int ionic_get_link_ksettings(struct net_device *netdev, /* This means there's no module plugged in */ break; default: - dev_info(lif->ionic->dev, "unknown xcvr type pid=%d / 0x%x\n", - idev->port_info->status.xcvr.pid, - idev->port_info->status.xcvr.pid); + dev_dbg_ratelimited(lif->ionic->dev, + "unknown xcvr type pid=%d / 0x%x\n", + idev->port_info->status.xcvr.pid, + idev->port_info->status.xcvr.pid); break; } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 853aabedb128da..d407b031cc2ae4 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2669,9 +2669,6 @@ static void rtl_wol_enable_rx(struct rtl8169_private *tp) static void rtl_prepare_power_down(struct rtl8169_private *tp) { - if (tp->dash_enabled) - return; - if (tp->mac_version == RTL_GIGA_MAC_VER_32 || tp->mac_version == RTL_GIGA_MAC_VER_33) rtl_ephy_write(tp, 0x19, 0xff64); @@ -4807,7 +4804,7 @@ static void rtl8169_down(struct rtl8169_private *tp) rtl_disable_exit_l1(tp); rtl_prepare_power_down(tp); - if (tp->dash_type != RTL_DASH_NONE) + if (tp->dash_type != RTL_DASH_NONE && !tp->saved_wolopts) rtl8168_driver_stop(tp); } diff --git a/drivers/net/ethernet/renesas/rswitch_l2.c b/drivers/net/ethernet/renesas/rswitch_l2.c index 4a69ec77d69c60..9433cd8adced97 100644 --- a/drivers/net/ethernet/renesas/rswitch_l2.c +++ b/drivers/net/ethernet/renesas/rswitch_l2.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Renesas Ethernet Switch device driver * - * Copyright (C) 2025 Renesas Electronics Corporation + * Copyright (C) 2025 - 2026 Renesas Electronics Corporation */ #include @@ -60,6 +60,7 @@ static void rswitch_update_l2_hw_learning(struct rswitch_private *priv) static void rswitch_update_l2_hw_forwarding(struct rswitch_private *priv) { struct rswitch_device *rdev; + bool new_forwarding_offload; unsigned int fwd_mask; /* calculate fwd_mask with zeroes in bits corresponding to ports that @@ -73,8 +74,9 @@ static void rswitch_update_l2_hw_forwarding(struct rswitch_private *priv) } rswitch_for_all_ports(priv, rdev) { - if ((rdev_for_l2_offload(rdev) && rdev->forwarding_requested) || - rdev->forwarding_offloaded) { + new_forwarding_offload = (rdev_for_l2_offload(rdev) && rdev->forwarding_requested); + + if (new_forwarding_offload || rdev->forwarding_offloaded) { /* Update allowed offload destinations even for ports * with L2 offload enabled earlier. * @@ -84,13 +86,10 @@ static void rswitch_update_l2_hw_forwarding(struct rswitch_private *priv) priv->addr + FWPC2(rdev->port)); } - if (rdev_for_l2_offload(rdev) && - rdev->forwarding_requested && - !rdev->forwarding_offloaded) { + if (new_forwarding_offload && !rdev->forwarding_offloaded) rswitch_change_l2_hw_offloading(rdev, true, false); - } else if (rdev->forwarding_offloaded) { + else if (!new_forwarding_offload && rdev->forwarding_offloaded) rswitch_change_l2_hw_offloading(rdev, false, false); - } } } diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 36af94a2e062aa..2794f75df8fcba 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -1524,9 +1524,8 @@ static void rocker_world_port_post_fini(struct rocker_port *rocker_port) { struct rocker_world_ops *wops = rocker_port->rocker->wops; - if (!wops->port_post_fini) - return; - wops->port_post_fini(rocker_port); + if (wops->port_post_fini) + wops->port_post_fini(rocker_port); kfree(rocker_port->wpriv); } diff --git a/drivers/net/ethernet/sfc/mcdi_filters.c b/drivers/net/ethernet/sfc/mcdi_filters.c index 6ef96292909a2f..3db589b90b68ad 100644 --- a/drivers/net/ethernet/sfc/mcdi_filters.c +++ b/drivers/net/ethernet/sfc/mcdi_filters.c @@ -2182,12 +2182,7 @@ int efx_mcdi_rx_pull_rss_context_config(struct efx_nic *efx, int efx_mcdi_rx_pull_rss_config(struct efx_nic *efx) { - int rc; - - mutex_lock(&efx->net_dev->ethtool->rss_lock); - rc = efx_mcdi_rx_pull_rss_context_config(efx, &efx->rss_context); - mutex_unlock(&efx->net_dev->ethtool->rss_lock); - return rc; + return efx_mcdi_rx_pull_rss_context_config(efx, &efx->rss_context); } void efx_mcdi_rx_restore_rss_contexts(struct efx_nic *efx) diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 9d1a83a5fa7e5d..d16c178d103440 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -516,15 +516,7 @@ static inline void smc_rcv(struct net_device *dev) * any other concurrent access and C would always interrupt B. But life * isn't that easy in a SMP world... */ -#define smc_special_trylock(lock, flags) \ -({ \ - int __ret; \ - local_irq_save(flags); \ - __ret = spin_trylock(lock); \ - if (!__ret) \ - local_irq_restore(flags); \ - __ret; \ -}) +#define smc_special_trylock(lock, flags) spin_trylock_irqsave(lock, flags) #define smc_special_lock(lock, flags) spin_lock_irqsave(lock, flags) #define smc_special_unlock(lock, flags) spin_unlock_irqrestore(lock, flags) #else diff --git a/drivers/net/ethernet/spacemit/k1_emac.c b/drivers/net/ethernet/spacemit/k1_emac.c index 220eb5ce75833d..b49c4708bf9eb1 100644 --- a/drivers/net/ethernet/spacemit/k1_emac.c +++ b/drivers/net/ethernet/spacemit/k1_emac.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -38,7 +39,7 @@ #define EMAC_DEFAULT_BUFSIZE 1536 #define EMAC_RX_BUF_2K 2048 -#define EMAC_RX_BUF_4K 4096 +#define EMAC_RX_BUF_MAX FIELD_MAX(RX_DESC_1_BUFFER_SIZE_1_MASK) /* Tuning parameters from SpacemiT */ #define EMAC_TX_FRAMES 64 @@ -202,8 +203,7 @@ static void emac_init_hw(struct emac_priv *priv) { /* Destination address for 802.3x Ethernet flow control */ u8 fc_dest_addr[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x01 }; - - u32 rxirq = 0, dma = 0; + u32 rxirq = 0, dma = 0, frame_sz; regmap_set_bits(priv->regmap_apmu, priv->regmap_apmu_offset + APMU_EMAC_CTRL_REG, @@ -228,6 +228,15 @@ static void emac_init_hw(struct emac_priv *priv) DEFAULT_TX_THRESHOLD); emac_wr(priv, MAC_RECEIVE_PACKET_START_THRESHOLD, DEFAULT_RX_THRESHOLD); + /* Set maximum frame size and jabber size based on configured MTU, + * accounting for Ethernet header, double VLAN tags, and FCS. + */ + frame_sz = priv->ndev->mtu + ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN; + + emac_wr(priv, MAC_MAXIMUM_FRAME_SIZE, frame_sz); + emac_wr(priv, MAC_TRANSMIT_JABBER_SIZE, frame_sz); + emac_wr(priv, MAC_RECEIVE_JABBER_SIZE, frame_sz); + /* Configure flow control (enabled in emac_adjust_link() later) */ emac_set_mac_addr_reg(priv, fc_dest_addr, MAC_FC_SOURCE_ADDRESS_HIGH); emac_wr(priv, MAC_FC_PAUSE_HIGH_THRESHOLD, DEFAULT_FC_FIFO_HIGH); @@ -924,14 +933,14 @@ static int emac_change_mtu(struct net_device *ndev, int mtu) return -EBUSY; } - frame_len = mtu + ETH_HLEN + ETH_FCS_LEN; + frame_len = mtu + ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN; if (frame_len <= EMAC_DEFAULT_BUFSIZE) priv->dma_buf_sz = EMAC_DEFAULT_BUFSIZE; else if (frame_len <= EMAC_RX_BUF_2K) priv->dma_buf_sz = EMAC_RX_BUF_2K; else - priv->dma_buf_sz = EMAC_RX_BUF_4K; + priv->dma_buf_sz = EMAC_RX_BUF_MAX; ndev->mtu = mtu; @@ -1099,7 +1108,13 @@ static int emac_read_stat_cnt(struct emac_priv *priv, u8 cnt, u32 *res, 100, 10000); if (ret) { - netdev_err(priv->ndev, "Read stat timeout\n"); + /* + * This could be caused by the PHY stopping its refclk even when + * the link is up, for power saving. See also comments in + * emac_stats_update(). + */ + dev_err_ratelimited(&priv->ndev->dev, + "Read stat timeout. PHY clock stopped?\n"); return ret; } @@ -1147,17 +1162,25 @@ static void emac_stats_update(struct emac_priv *priv) assert_spin_locked(&priv->stats_lock); - if (!netif_running(priv->ndev) || !netif_device_present(priv->ndev)) { - /* Not up, don't try to update */ + /* + * We can't read statistics if the interface is not up. Also, some PHYs + * stop their reference clocks for link down power saving, which also + * causes reading statistics to time out. Don't update and don't + * reschedule in these cases. + */ + if (!netif_running(priv->ndev) || + !netif_carrier_ok(priv->ndev) || + !netif_device_present(priv->ndev)) { return; } for (i = 0; i < sizeof(priv->tx_stats) / sizeof(*tx_stats); i++) { /* - * If reading stats times out, everything is broken and there's - * nothing we can do. Reading statistics also can't return an - * error, so just return without updating and without - * rescheduling. + * If reading stats times out anyway, the stat registers will be + * stuck, and we can't really recover from that. + * + * Reading statistics also can't return an error, so just return + * without updating and without rescheduling. */ if (emac_tx_read_stat_cnt(priv, i, &res)) return; @@ -1636,6 +1659,12 @@ static void emac_adjust_link(struct net_device *dev) emac_wr(priv, MAC_GLOBAL_CONTROL, ctrl); emac_set_fc_autoneg(priv); + + /* + * Reschedule stats updates now that link is up. See comments in + * emac_stats_update(). + */ + mod_timer(&priv->stats_timer, jiffies); } phy_print_status(phydev); @@ -2005,7 +2034,7 @@ static int emac_probe(struct platform_device *pdev) ndev->hw_features = NETIF_F_SG; ndev->features |= ndev->hw_features; - ndev->max_mtu = EMAC_RX_BUF_4K - (ETH_HLEN + ETH_FCS_LEN); + ndev->max_mtu = EMAC_RX_BUF_MAX - (ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN); ndev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; priv = netdev_priv(ndev); diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 8f34c9ad457f07..23ec3a59ca8f17 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -43,6 +43,11 @@ #define DWXGMAC_ID 0x76 #define DWXLGMAC_ID 0x27 +static inline bool dwmac_is_xmac(enum dwmac_core_type core_type) +{ + return core_type == DWMAC_CORE_GMAC4 || core_type == DWMAC_CORE_XGMAC; +} + #define STMMAC_CHAN0 0 /* Always supported and default for all chips */ /* TX and RX Descriptor Length, these need to be power of two. diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index e8539cad4602e8..1d30f2fb984f1f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -109,7 +109,7 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev, } /* dwc-qos needs GMAC4, AAL, TSO and PMT */ - plat_dat->has_gmac4 = 1; + plat_dat->core_type = DWMAC_CORE_GMAC4; plat_dat->dma_cfg->aal = 1; plat_dat->flags |= STMMAC_FLAG_TSO_EN; plat_dat->pmt = 1; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index e74d00984b889e..b2194e414ec1f6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -565,7 +565,7 @@ static void common_default_data(struct plat_stmmacenet_data *plat) { /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ plat->clk_csr = STMMAC_CSR_20_35M; - plat->has_gmac = 1; + plat->core_type = DWMAC_CORE_GMAC; plat->force_sf_dma_mode = 1; plat->mdio_bus_data->needs_reset = true; @@ -612,8 +612,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->pdev = pdev; plat->phy_addr = -1; plat->clk_csr = STMMAC_CSR_250_300M; - plat->has_gmac = 0; - plat->has_gmac4 = 1; + plat->core_type = DWMAC_CORE_GMAC4; plat->force_sf_dma_mode = 0; plat->flags |= (STMMAC_FLAG_TSO_EN | STMMAC_FLAG_SPH_DISABLE); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index ca4035cbb55b6d..c05f85534f0cac 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -473,7 +473,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) return err; } - plat_dat->has_gmac = true; + plat_dat->core_type = DWMAC_CORE_GMAC; plat_dat->bsp_priv = gmac; plat_dat->set_clk_tx_rate = ipq806x_gmac_set_clk_tx_rate; plat_dat->multicast_filter_bins = 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 592aa9d636e505..47bc3aeee857d1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -90,9 +90,9 @@ static void loongson_default_data(struct pci_dev *pdev, /* Get bus_id, this can be overwritten later */ plat->bus_id = pci_dev_id(pdev); - /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ - plat->clk_csr = STMMAC_CSR_20_35M; - plat->has_gmac = 1; + /* clk_csr_i = 100-150MHz & MDC = clk_csr_i/62 */ + plat->clk_csr = STMMAC_CSR_100_150M; + plat->core_type = DWMAC_CORE_GMAC; plat->force_sf_dma_mode = 1; /* Set default value for multicast hash bins */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c index 2562a6d036a2a3..6fffc9dfbae553 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c @@ -41,7 +41,7 @@ static int lpc18xx_dwmac_probe(struct platform_device *pdev) if (IS_ERR(plat_dat)) return PTR_ERR(plat_dat); - plat_dat->has_gmac = true; + plat_dat->core_type = DWMAC_CORE_GMAC; reg = syscon_regmap_lookup_by_compatible("nxp,lpc1850-creg"); if (IS_ERR(reg)) { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index d8fd4d8f6ced76..74c208dd86519f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -96,7 +96,6 @@ struct ethqos_emac_driver_data { bool rgmii_config_loopback_en; bool has_emac_ge_3; const char *link_clk_name; - bool has_integrated_pcs; u32 dma_addr_width; struct dwmac4_addrs dwmac4_addrs; bool needs_sgmii_loopback; @@ -282,7 +281,6 @@ static const struct ethqos_emac_driver_data emac_v4_0_0_data = { .rgmii_config_loopback_en = false, .has_emac_ge_3 = true, .link_clk_name = "phyaux", - .has_integrated_pcs = true, .needs_sgmii_loopback = true, .dma_addr_width = 36, .dwmac4_addrs = { @@ -848,7 +846,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->fix_mac_speed = ethqos_fix_mac_speed; plat_dat->dump_debug_regs = rgmii_dump; plat_dat->ptp_clk_freq_config = ethqos_ptp_clk_freq_config; - plat_dat->has_gmac4 = 1; + plat_dat->core_type = DWMAC_CORE_GMAC4; if (ethqos->has_emac_ge_3) plat_dat->dwmac4_addrs = &data->dwmac4_addrs; plat_dat->pmt = 1; @@ -856,8 +854,6 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->flags |= STMMAC_FLAG_TSO_EN; if (of_device_is_compatible(np, "qcom,qcs404-ethqos")) plat_dat->flags |= STMMAC_FLAG_RX_CLK_RUNS_IN_LPI; - if (data->has_integrated_pcs) - plat_dat->flags |= STMMAC_FLAG_HAS_INTEGRATED_PCS; if (data->dma_addr_width) plat_dat->host_dma_width = data->dma_addr_width; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 0786816e05f048..643578266dfca7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1751,8 +1751,8 @@ static int rk_gmac_probe(struct platform_device *pdev) /* If the stmmac is not already selected as gmac4, * then make sure we fallback to gmac. */ - if (!plat_dat->has_gmac4) { - plat_dat->has_gmac = true; + if (plat_dat->core_type != DWMAC_CORE_GMAC4) { + plat_dat->core_type = DWMAC_CORE_GMAC; plat_dat->rx_fifo_size = 4096; plat_dat->tx_fifo_size = 2048; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c index 221539d760bc83..ee095ac1320376 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c @@ -146,7 +146,7 @@ static int s32_dwmac_probe(struct platform_device *pdev) gmac->ioaddr = res.addr; /* S32CC core feature set */ - plat->has_gmac4 = true; + plat->core_type = DWMAC_CORE_GMAC4; plat->pmt = 1; plat->flags |= STMMAC_FLAG_SPH_DISABLE; plat->rx_fifo_size = 20480; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 354f01184e6cc2..2ff5db6d41ca08 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -497,7 +497,7 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) plat_dat->pcs_init = socfpga_dwmac_pcs_init; plat_dat->pcs_exit = socfpga_dwmac_pcs_exit; plat_dat->select_pcs = socfpga_dwmac_select_pcs; - plat_dat->has_gmac = true; + plat_dat->core_type = DWMAC_CORE_GMAC; plat_dat->riwt_off = 1; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c index 3b7947a7a7ba70..fcdda2401968b5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c @@ -7,11 +7,16 @@ #include #include +#include #include #include #include "stmmac_platform.h" +struct sophgo_dwmac_data { + bool has_internal_rx_delay; +}; + static int sophgo_sg2044_dwmac_init(struct platform_device *pdev, struct plat_stmmacenet_data *plat_dat, struct stmmac_resources *stmmac_res) @@ -32,6 +37,7 @@ static int sophgo_sg2044_dwmac_init(struct platform_device *pdev, static int sophgo_dwmac_probe(struct platform_device *pdev) { struct plat_stmmacenet_data *plat_dat; + const struct sophgo_dwmac_data *data; struct stmmac_resources stmmac_res; struct device *dev = &pdev->dev; int ret; @@ -50,11 +56,23 @@ static int sophgo_dwmac_probe(struct platform_device *pdev) if (ret) return ret; + data = device_get_match_data(&pdev->dev); + if (data && data->has_internal_rx_delay) { + plat_dat->phy_interface = phy_fix_phy_mode_for_mac_delays(plat_dat->phy_interface, + false, true); + if (plat_dat->phy_interface == PHY_INTERFACE_MODE_NA) + return -EINVAL; + } + return stmmac_dvr_probe(dev, plat_dat, &stmmac_res); } +static const struct sophgo_dwmac_data sg2042_dwmac_data = { + .has_internal_rx_delay = true, +}; + static const struct of_device_id sophgo_dwmac_match[] = { - { .compatible = "sophgo,sg2042-dwmac" }, + { .compatible = "sophgo,sg2042-dwmac", .data = &sg2042_dwmac_data }, { .compatible = "sophgo,sg2044-dwmac" }, { /* sentinel */ } }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index 1eadcf5d1ad632..7f560d78209d16 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -136,7 +136,7 @@ static int sun7i_gmac_probe(struct platform_device *pdev) /* platform data specifying hardware features and callbacks. * hardware features were copied from Allwinner drivers. */ plat_dat->tx_coe = 1; - plat_dat->has_gmac = true; + plat_dat->core_type = DWMAC_CORE_GMAC; plat_dat->bsp_priv = gmac; plat_dat->init = sun7i_gmac_init; plat_dat->exit = sun7i_gmac_exit; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c index dc903b846b1bf4..d765acbe375481 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c @@ -308,7 +308,7 @@ static int tegra_mgbe_probe(struct platform_device *pdev) goto disable_clks; } - plat->has_xgmac = 1; + plat->core_type = DWMAC_CORE_XGMAC; plat->flags |= STMMAC_FLAG_TSO_EN; plat->pmt = 1; plat->bsp_priv = mgbe; diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c index 3f7c765dcb7971..00083ce525492e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.c +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -106,9 +106,7 @@ int stmmac_reset(struct stmmac_priv *priv, void __iomem *ioaddr) } static const struct stmmac_hwif_entry { - bool gmac; - bool gmac4; - bool xgmac; + enum dwmac_core_type core_type; u32 min_id; u32 dev_id; const struct stmmac_regs_off regs; @@ -127,9 +125,7 @@ static const struct stmmac_hwif_entry { } stmmac_hw[] = { /* NOTE: New HW versions shall go to the end of this table */ { - .gmac = false, - .gmac4 = false, - .xgmac = false, + .core_type = DWMAC_CORE_MAC100, .min_id = 0, .regs = { .ptp_off = PTP_GMAC3_X_OFFSET, @@ -146,9 +142,7 @@ static const struct stmmac_hwif_entry { .setup = dwmac100_setup, .quirks = stmmac_dwmac1_quirks, }, { - .gmac = true, - .gmac4 = false, - .xgmac = false, + .core_type = DWMAC_CORE_GMAC, .min_id = 0, .regs = { .ptp_off = PTP_GMAC3_X_OFFSET, @@ -165,9 +159,7 @@ static const struct stmmac_hwif_entry { .setup = dwmac1000_setup, .quirks = stmmac_dwmac1_quirks, }, { - .gmac = false, - .gmac4 = true, - .xgmac = false, + .core_type = DWMAC_CORE_GMAC4, .min_id = 0, .regs = { .ptp_off = PTP_GMAC4_OFFSET, @@ -187,9 +179,7 @@ static const struct stmmac_hwif_entry { .setup = dwmac4_setup, .quirks = stmmac_dwmac4_quirks, }, { - .gmac = false, - .gmac4 = true, - .xgmac = false, + .core_type = DWMAC_CORE_GMAC4, .min_id = DWMAC_CORE_4_00, .regs = { .ptp_off = PTP_GMAC4_OFFSET, @@ -210,9 +200,7 @@ static const struct stmmac_hwif_entry { .setup = dwmac4_setup, .quirks = NULL, }, { - .gmac = false, - .gmac4 = true, - .xgmac = false, + .core_type = DWMAC_CORE_GMAC4, .min_id = DWMAC_CORE_4_10, .regs = { .ptp_off = PTP_GMAC4_OFFSET, @@ -233,9 +221,7 @@ static const struct stmmac_hwif_entry { .setup = dwmac4_setup, .quirks = NULL, }, { - .gmac = false, - .gmac4 = true, - .xgmac = false, + .core_type = DWMAC_CORE_GMAC4, .min_id = DWMAC_CORE_5_10, .regs = { .ptp_off = PTP_GMAC4_OFFSET, @@ -256,9 +242,7 @@ static const struct stmmac_hwif_entry { .setup = dwmac4_setup, .quirks = NULL, }, { - .gmac = false, - .gmac4 = false, - .xgmac = true, + .core_type = DWMAC_CORE_XGMAC, .min_id = DWXGMAC_CORE_2_10, .dev_id = DWXGMAC_ID, .regs = { @@ -280,9 +264,7 @@ static const struct stmmac_hwif_entry { .setup = dwxgmac2_setup, .quirks = NULL, }, { - .gmac = false, - .gmac4 = false, - .xgmac = true, + .core_type = DWMAC_CORE_XGMAC, .min_id = DWXLGMAC_CORE_2_00, .dev_id = DWXLGMAC_ID, .regs = { @@ -308,20 +290,18 @@ static const struct stmmac_hwif_entry { int stmmac_hwif_init(struct stmmac_priv *priv) { - bool needs_xgmac = priv->plat->has_xgmac; - bool needs_gmac4 = priv->plat->has_gmac4; - bool needs_gmac = priv->plat->has_gmac; + enum dwmac_core_type core_type = priv->plat->core_type; const struct stmmac_hwif_entry *entry; struct mac_device_info *mac; bool needs_setup = true; u32 id, dev_id = 0; int i, ret; - if (needs_gmac) { + if (core_type == DWMAC_CORE_GMAC) { id = stmmac_get_id(priv, GMAC_VERSION); - } else if (needs_gmac4 || needs_xgmac) { + } else if (dwmac_is_xmac(core_type)) { id = stmmac_get_id(priv, GMAC4_VERSION); - if (needs_xgmac) + if (core_type == DWMAC_CORE_XGMAC) dev_id = stmmac_get_dev_id(priv, GMAC4_VERSION); } else { id = 0; @@ -331,14 +311,16 @@ int stmmac_hwif_init(struct stmmac_priv *priv) priv->synopsys_id = id; /* Lets assume some safe values first */ - priv->ptpaddr = priv->ioaddr + - (needs_gmac4 ? PTP_GMAC4_OFFSET : PTP_GMAC3_X_OFFSET); - priv->mmcaddr = priv->ioaddr + - (needs_gmac4 ? MMC_GMAC4_OFFSET : MMC_GMAC3_X_OFFSET); - if (needs_gmac4) + if (core_type == DWMAC_CORE_GMAC4) { + priv->ptpaddr = priv->ioaddr + PTP_GMAC4_OFFSET; + priv->mmcaddr = priv->ioaddr + MMC_GMAC4_OFFSET; priv->estaddr = priv->ioaddr + EST_GMAC4_OFFSET; - else if (needs_xgmac) - priv->estaddr = priv->ioaddr + EST_XGMAC_OFFSET; + } else { + priv->ptpaddr = priv->ioaddr + PTP_GMAC3_X_OFFSET; + priv->mmcaddr = priv->ioaddr + MMC_GMAC3_X_OFFSET; + if (core_type == DWMAC_CORE_XGMAC) + priv->estaddr = priv->ioaddr + EST_XGMAC_OFFSET; + } /* Check for HW specific setup first */ if (priv->plat->setup) { @@ -355,16 +337,12 @@ int stmmac_hwif_init(struct stmmac_priv *priv) for (i = ARRAY_SIZE(stmmac_hw) - 1; i >= 0; i--) { entry = &stmmac_hw[i]; - if (needs_gmac ^ entry->gmac) - continue; - if (needs_gmac4 ^ entry->gmac4) - continue; - if (needs_xgmac ^ entry->xgmac) + if (core_type != entry->core_type) continue; /* Use synopsys_id var because some setups can override this */ if (priv->synopsys_id < entry->min_id) continue; - if (needs_xgmac && (dev_id ^ entry->dev_id)) + if (core_type == DWMAC_CORE_XGMAC && (dev_id ^ entry->dev_id)) continue; /* Only use generic HW helpers if needed */ @@ -400,6 +378,7 @@ int stmmac_hwif_init(struct stmmac_priv *priv) } dev_err(priv->device, "Failed to find HW IF (id=0x%x, gmac=%d/%d)\n", - id, needs_gmac, needs_gmac4); + id, core_type == DWMAC_CORE_GMAC, + core_type == DWMAC_CORE_GMAC4); return -EINVAL; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c index 4b513d27a98890..afc516059b8975 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c @@ -53,7 +53,7 @@ static int est_configure(struct stmmac_priv *priv, struct stmmac_est *cfg, } ctrl = readl(est_addr + EST_CONTROL); - if (priv->plat->has_xgmac) { + if (priv->plat->core_type == DWMAC_CORE_XGMAC) { ctrl &= ~EST_XGMAC_PTOV; ctrl |= ((NSEC_PER_SEC / ptp_rate) * EST_XGMAC_PTOV_MUL) << EST_XGMAC_PTOV_SHIFT; @@ -148,7 +148,7 @@ static void est_irq_status(struct stmmac_priv *priv, struct net_device *dev, } if (status & EST_BTRE) { - if (priv->plat->has_xgmac) { + if (priv->plat->core_type == DWMAC_CORE_XGMAC) { btrl = FIELD_GET(EST_XGMAC_BTRL, status); btrl_max = FIELD_MAX(EST_XGMAC_BTRL); } else { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 39fa1ec92f82f9..81d4039e1c0826 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -303,9 +303,10 @@ static void stmmac_ethtool_getdrvinfo(struct net_device *dev, { struct stmmac_priv *priv = netdev_priv(dev); - if (priv->plat->has_gmac || priv->plat->has_gmac4) + if (priv->plat->core_type == DWMAC_CORE_GMAC || + priv->plat->core_type == DWMAC_CORE_GMAC4) strscpy(info->driver, GMAC_ETHTOOL_NAME, sizeof(info->driver)); - else if (priv->plat->has_xgmac) + else if (priv->plat->core_type == DWMAC_CORE_XGMAC) strscpy(info->driver, XGMAC_ETHTOOL_NAME, sizeof(info->driver)); else strscpy(info->driver, MAC100_ETHTOOL_NAME, @@ -322,47 +323,6 @@ static int stmmac_ethtool_get_link_ksettings(struct net_device *dev, { struct stmmac_priv *priv = netdev_priv(dev); - if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) && - (priv->hw->pcs & STMMAC_PCS_RGMII || - priv->hw->pcs & STMMAC_PCS_SGMII)) { - u32 supported, advertising, lp_advertising; - - if (!priv->xstats.pcs_link) { - cmd->base.speed = SPEED_UNKNOWN; - cmd->base.duplex = DUPLEX_UNKNOWN; - return 0; - } - cmd->base.duplex = priv->xstats.pcs_duplex; - - cmd->base.speed = priv->xstats.pcs_speed; - - /* Encoding of PSE bits is defined in 802.3z, 37.2.1.4 */ - - ethtool_convert_link_mode_to_legacy_u32( - &supported, cmd->link_modes.supported); - ethtool_convert_link_mode_to_legacy_u32( - &advertising, cmd->link_modes.advertising); - ethtool_convert_link_mode_to_legacy_u32( - &lp_advertising, cmd->link_modes.lp_advertising); - - /* Reg49[3] always set because ANE is always supported */ - cmd->base.autoneg = ADVERTISED_Autoneg; - supported |= SUPPORTED_Autoneg; - advertising |= ADVERTISED_Autoneg; - lp_advertising |= ADVERTISED_Autoneg; - - cmd->base.port = PORT_OTHER; - - ethtool_convert_legacy_u32_to_link_mode( - cmd->link_modes.supported, supported); - ethtool_convert_legacy_u32_to_link_mode( - cmd->link_modes.advertising, advertising); - ethtool_convert_legacy_u32_to_link_mode( - cmd->link_modes.lp_advertising, lp_advertising); - - return 0; - } - return phylink_ethtool_ksettings_get(priv->phylink, cmd); } @@ -372,20 +332,6 @@ stmmac_ethtool_set_link_ksettings(struct net_device *dev, { struct stmmac_priv *priv = netdev_priv(dev); - if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) && - (priv->hw->pcs & STMMAC_PCS_RGMII || - priv->hw->pcs & STMMAC_PCS_SGMII)) { - /* Only support ANE */ - if (cmd->base.autoneg != AUTONEG_ENABLE) - return -EINVAL; - - mutex_lock(&priv->lock); - stmmac_pcs_ctrl_ane(priv, 1, priv->hw->ps, 0); - mutex_unlock(&priv->lock); - - return 0; - } - return phylink_ethtool_ksettings_set(priv->phylink, cmd); } @@ -406,9 +352,9 @@ static int stmmac_ethtool_get_regs_len(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); - if (priv->plat->has_xgmac) + if (priv->plat->core_type == DWMAC_CORE_XGMAC) return XGMAC_REGSIZE * 4; - else if (priv->plat->has_gmac4) + else if (priv->plat->core_type == DWMAC_CORE_GMAC4) return GMAC4_REG_SPACE_SIZE; return REG_SPACE_SIZE; } @@ -423,12 +369,12 @@ static void stmmac_ethtool_gregs(struct net_device *dev, stmmac_dump_dma_regs(priv, priv->ioaddr, reg_space); /* Copy DMA registers to where ethtool expects them */ - if (priv->plat->has_gmac4) { + if (priv->plat->core_type == DWMAC_CORE_GMAC4) { /* GMAC4 dumps its DMA registers at its DMA_CHAN_BASE_ADDR */ memcpy(®_space[ETHTOOL_DMA_OFFSET], ®_space[GMAC4_DMA_CHAN_BASE_ADDR / 4], NUM_DWMAC4_DMA_REGS * 4); - } else if (!priv->plat->has_xgmac) { + } else if (priv->plat->core_type != DWMAC_CORE_XGMAC) { memcpy(®_space[ETHTOOL_DMA_OFFSET], ®_space[DMA_BUS_MODE / 4], NUM_DWMAC1000_DMA_REGS * 4); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7b90ecd3a55e60..46299b7925b44a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -88,6 +88,7 @@ MODULE_PARM_DESC(phyaddr, "Physical device address"); #define STMMAC_XDP_CONSUMED BIT(0) #define STMMAC_XDP_TX BIT(1) #define STMMAC_XDP_REDIRECT BIT(2) +#define STMMAC_XSK_CONSUMED BIT(3) static int flow_ctrl = 0xdead; module_param(flow_ctrl, int, 0644); @@ -445,7 +446,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, if (!priv->hwts_rx_en) return; /* For GMAC4, the valid timestamp is from CTX next desc. */ - if (priv->plat->has_gmac4 || priv->plat->has_xgmac) + if (dwmac_is_xmac(priv->plat->core_type)) desc = np; /* Check if timestamp is available */ @@ -696,7 +697,7 @@ static int stmmac_hwtstamp_get(struct net_device *dev, static int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags) { - bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + bool xmac = dwmac_is_xmac(priv->plat->core_type); struct timespec64 now; u32 sec_inc = 0; u64 temp = 0; @@ -745,7 +746,7 @@ static int stmmac_init_tstamp_counter(struct stmmac_priv *priv, */ static int stmmac_init_timestamping(struct stmmac_priv *priv) { - bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + bool xmac = dwmac_is_xmac(priv->plat->core_type); int ret; if (priv->plat->ptp_clk_freq_config) @@ -2397,7 +2398,7 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) txfifosz = priv->dma_cap.tx_fifo_size; /* Split up the shared Tx/Rx FIFO memory on DW QoS Eth and DW XGMAC */ - if (priv->plat->has_gmac4 || priv->plat->has_xgmac) { + if (dwmac_is_xmac(priv->plat->core_type)) { rxfifosz /= rx_channels_count; txfifosz /= tx_channels_count; } @@ -4513,7 +4514,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) if (skb_is_gso(skb) && priv->tso) { if (gso & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) return stmmac_tso_xmit(skb, dev); - if (priv->plat->has_gmac4 && (gso & SKB_GSO_UDP_L4)) + if (priv->plat->core_type == DWMAC_CORE_GMAC4 && + (gso & SKB_GSO_UDP_L4)) return stmmac_tso_xmit(skb, dev); } @@ -4878,13 +4880,27 @@ static unsigned int stmmac_rx_buf2_len(struct stmmac_priv *priv, if (!priv->sph) return 0; - /* Not last descriptor */ - if (status & rx_not_ls) + /* For GMAC4, when split header is enabled, in some rare cases, the + * hardware does not fill buf2 of the first descriptor with payload. + * Thus we cannot assume buf2 is always fully filled if it is not + * the last descriptor. Otherwise, the length of buf2 of the second + * descriptor will be calculated wrong and cause an oops. + * + * If this is the last descriptor, 'plen' is the length of the + * received packet that was transferred to system memory. + * Otherwise, it is the accumulated number of bytes that have been + * transferred for the current packet. + * + * Thus 'plen - len' always gives the correct length of buf2. + */ + + /* Not GMAC4 and not last descriptor */ + if (priv->plat->core_type != DWMAC_CORE_GMAC4 && (status & rx_not_ls)) return priv->dma_conf.dma_buf_sz; + /* GMAC4 or last descriptor */ plen = stmmac_get_rx_frame_len(priv, p, coe); - /* Last descriptor */ return plen - len; } @@ -4988,6 +5004,7 @@ static int stmmac_xdp_get_tx_queue(struct stmmac_priv *priv, static int stmmac_xdp_xmit_back(struct stmmac_priv *priv, struct xdp_buff *xdp) { + bool zc = !!(xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL); struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp); int cpu = smp_processor_id(); struct netdev_queue *nq; @@ -5004,9 +5021,18 @@ static int stmmac_xdp_xmit_back(struct stmmac_priv *priv, /* Avoids TX time-out as we are sharing with slow path */ txq_trans_cond_update(nq); - res = stmmac_xdp_xmit_xdpf(priv, queue, xdpf, false); - if (res == STMMAC_XDP_TX) + /* For zero copy XDP_TX action, dma_map is true */ + res = stmmac_xdp_xmit_xdpf(priv, queue, xdpf, zc); + if (res == STMMAC_XDP_TX) { stmmac_flush_tx_descriptors(priv, queue); + } else if (res == STMMAC_XDP_CONSUMED && zc) { + /* xdp has been freed by xdp_convert_buff_to_frame(), + * no need to call xsk_buff_free() again, so return + * STMMAC_XSK_CONSUMED. + */ + res = STMMAC_XSK_CONSUMED; + xdp_return_frame(xdpf); + } __netif_tx_unlock(nq); @@ -5258,10 +5284,10 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue) len = 0; } +read_again: if (count >= limit) break; -read_again: buf1_len = 0; entry = next_entry; buf = &rx_q->buf_pool[entry]; @@ -5356,6 +5382,8 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue) break; case STMMAC_XDP_CONSUMED: xsk_buff_free(buf->xdp); + fallthrough; + case STMMAC_XSK_CONSUMED: rx_dropped++; break; case STMMAC_XDP_TX: @@ -5971,7 +5999,7 @@ static void stmmac_common_interrupt(struct stmmac_priv *priv) u32 queue; bool xmac; - xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + xmac = dwmac_is_xmac(priv->plat->core_type); queues_count = (rx_cnt > tx_cnt) ? rx_cnt : tx_cnt; if (priv->irq_wake) @@ -5985,7 +6013,7 @@ static void stmmac_common_interrupt(struct stmmac_priv *priv) stmmac_fpe_irq_status(priv); /* To handle GMAC own interrupts */ - if ((priv->plat->has_gmac) || xmac) { + if (priv->plat->core_type == DWMAC_CORE_GMAC || xmac) { int status = stmmac_host_irq_status(priv, priv->hw, &priv->xstats); if (unlikely(status)) { @@ -5999,15 +6027,6 @@ static void stmmac_common_interrupt(struct stmmac_priv *priv) for (queue = 0; queue < queues_count; queue++) stmmac_host_mtl_irq_status(priv, priv->hw, queue); - /* PCS link status */ - if (priv->hw->pcs && - !(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS)) { - if (priv->xstats.pcs_link) - netif_carrier_on(priv->dev); - else - netif_carrier_off(priv->dev); - } - stmmac_timestamp_interrupt(priv, priv); } } @@ -6355,7 +6374,7 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) (priv->dma_cap.mbps_1000) ? "Y" : "N"); seq_printf(seq, "\tHalf duplex: %s\n", (priv->dma_cap.half_duplex) ? "Y" : "N"); - if (priv->plat->has_xgmac) { + if (priv->plat->core_type == DWMAC_CORE_XGMAC) { seq_printf(seq, "\tNumber of Additional MAC address registers: %d\n", priv->dma_cap.multi_addr); @@ -6379,7 +6398,7 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) (priv->dma_cap.time_stamp) ? "Y" : "N"); seq_printf(seq, "\tIEEE 1588-2008 Advanced Time Stamp: %s\n", (priv->dma_cap.atime_stamp) ? "Y" : "N"); - if (priv->plat->has_xgmac) + if (priv->plat->core_type == DWMAC_CORE_XGMAC) seq_printf(seq, "\tTimestamp System Time Source: %s\n", dwxgmac_timestamp_source[priv->dma_cap.tssrc]); seq_printf(seq, "\t802.3az - Energy-Efficient Ethernet (EEE): %s\n", @@ -6388,7 +6407,7 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) seq_printf(seq, "\tChecksum Offload in TX: %s\n", (priv->dma_cap.tx_coe) ? "Y" : "N"); if (priv->synopsys_id >= DWMAC_CORE_4_00 || - priv->plat->has_xgmac) { + priv->plat->core_type == DWMAC_CORE_XGMAC) { seq_printf(seq, "\tIP Checksum Offload in RX: %s\n", (priv->dma_cap.rx_coe) ? "Y" : "N"); } else { @@ -7240,8 +7259,9 @@ static int stmmac_hw_init(struct stmmac_priv *priv) * has to be disable and this can be done by passing the * riwt_off field from the platform. */ - if (((priv->synopsys_id >= DWMAC_CORE_3_50) || - (priv->plat->has_xgmac)) && (!priv->plat->riwt_off)) { + if ((priv->synopsys_id >= DWMAC_CORE_3_50 || + priv->plat->core_type == DWMAC_CORE_XGMAC) && + !priv->plat->riwt_off) { priv->use_riwt = 1; dev_info(priv->device, "Enable RX Mitigation via HW Watchdog Timer\n"); @@ -7355,7 +7375,7 @@ static int stmmac_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp) return -ENODATA; /* For GMAC4, the valid timestamp is from CTX next desc. */ - if (priv->plat->has_gmac4 || priv->plat->has_xgmac) + if (dwmac_is_xmac(priv->plat->core_type)) desc_contains_ts = ndesc; /* Check if timestamp is available */ @@ -7511,7 +7531,7 @@ int stmmac_dvr_probe(struct device *device, if ((priv->plat->flags & STMMAC_FLAG_TSO_EN) && (priv->dma_cap.tsoen)) { ndev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6; - if (priv->plat->has_gmac4) + if (priv->plat->core_type == DWMAC_CORE_GMAC4) ndev->hw_features |= NETIF_F_GSO_UDP_L4; priv->tso = true; dev_info(priv->device, "TSO feature enabled\n"); @@ -7564,7 +7584,7 @@ int stmmac_dvr_probe(struct device *device, #ifdef STMMAC_VLAN_TAG_USED /* Both mac100 and gmac support receive VLAN tag detection */ ndev->features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX; - if (priv->plat->has_gmac4 || priv->plat->has_xgmac) { + if (dwmac_is_xmac(priv->plat->core_type)) { ndev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; priv->hw->hw_vlan_en = true; } @@ -7592,7 +7612,7 @@ int stmmac_dvr_probe(struct device *device, /* MTU range: 46 - hw-specific max */ ndev->min_mtu = ETH_ZLEN - ETH_HLEN; - if (priv->plat->has_xgmac) + if (priv->plat->core_type == DWMAC_CORE_XGMAC) ndev->max_mtu = XGMAC_JUMBO_LEN; else if ((priv->plat->enh_desc) || (priv->synopsys_id >= DWMAC_CORE_4_00)) ndev->max_mtu = JUMBO_LEN; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index f408737f6fc73e..2b55b02de380d8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -301,7 +301,7 @@ static int stmmac_mdio_read_c22(struct mii_bus *bus, int phyaddr, int phyreg) struct stmmac_priv *priv = netdev_priv(bus->priv); u32 cmd; - if (priv->plat->has_gmac4) + if (priv->plat->core_type == DWMAC_CORE_GMAC4) cmd = MII_GMAC4_READ; else cmd = 0; @@ -344,7 +344,7 @@ static int stmmac_mdio_write_c22(struct mii_bus *bus, int phyaddr, int phyreg, struct stmmac_priv *priv = netdev_priv(bus->priv); u32 cmd; - if (priv->plat->has_gmac4) + if (priv->plat->core_type == DWMAC_CORE_GMAC4) cmd = MII_GMAC4_WRITE; else cmd = MII_ADDR_GWRITE; @@ -417,7 +417,7 @@ int stmmac_mdio_reset(struct mii_bus *bus) * on MDC, so perform a dummy mdio read. To be updated for GMAC4 * if needed. */ - if (!priv->plat->has_gmac4) + if (priv->plat->core_type != DWMAC_CORE_GMAC4) writel(0, priv->ioaddr + mii_address); #endif return 0; @@ -528,7 +528,7 @@ static u32 stmmac_clk_csr_set(struct stmmac_priv *priv) value = 0; } - if (priv->plat->has_xgmac) { + if (priv->plat->core_type == DWMAC_CORE_XGMAC) { if (clk_rate > 400000000) value = 0x5; else if (clk_rate > 350000000) @@ -600,7 +600,7 @@ int stmmac_mdio_register(struct net_device *ndev) new_bus->name = "stmmac"; - if (priv->plat->has_xgmac) { + if (priv->plat->core_type == DWMAC_CORE_XGMAC) { new_bus->read = &stmmac_xgmac2_mdio_read_c22; new_bus->write = &stmmac_xgmac2_mdio_write_c22; new_bus->read_c45 = &stmmac_xgmac2_mdio_read_c45; @@ -621,7 +621,7 @@ int stmmac_mdio_register(struct net_device *ndev) } else { new_bus->read = &stmmac_mdio_read_c22; new_bus->write = &stmmac_mdio_write_c22; - if (priv->plat->has_gmac4) { + if (priv->plat->core_type == DWMAC_CORE_GMAC4) { new_bus->read_c45 = &stmmac_mdio_read_c45; new_bus->write_c45 = &stmmac_mdio_write_c45; } @@ -649,7 +649,7 @@ int stmmac_mdio_register(struct net_device *ndev) } /* Looks like we need a dummy read for XGMAC only and C45 PHYs */ - if (priv->plat->has_xgmac) + if (priv->plat->core_type == DWMAC_CORE_XGMAC) stmmac_xgmac2_mdio_read_c45(new_bus, 0, 0, 0); /* If fixed-link is set, skip PHY scanning */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 4e3aa611fda83f..94b3a3b272706c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -23,7 +23,7 @@ static void common_default_data(struct plat_stmmacenet_data *plat) { /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ plat->clk_csr = STMMAC_CSR_20_35M; - plat->has_gmac = 1; + plat->core_type = DWMAC_CORE_GMAC; plat->force_sf_dma_mode = 1; plat->mdio_bus_data->needs_reset = true; @@ -76,7 +76,7 @@ static int snps_gmac5_default_data(struct pci_dev *pdev, int i; plat->clk_csr = STMMAC_CSR_250_300M; - plat->has_gmac4 = 1; + plat->core_type = DWMAC_CORE_GMAC4; plat->force_sf_dma_mode = 1; plat->flags |= STMMAC_FLAG_TSO_EN; plat->pmt = 1; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 27bcaae07a7f22..fbb92cc6ab5989 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -552,12 +552,12 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) &pdev->dev, plat->unicast_filter_entries); plat->multicast_filter_bins = dwmac1000_validate_mcast_bins( &pdev->dev, plat->multicast_filter_bins); - plat->has_gmac = 1; + plat->core_type = DWMAC_CORE_GMAC; plat->pmt = 1; } if (of_device_is_compatible(np, "snps,dwmac-3.40a")) { - plat->has_gmac = 1; + plat->core_type = DWMAC_CORE_GMAC; plat->enh_desc = 1; plat->tx_coe = 1; plat->bugged_jumbo = 1; @@ -565,8 +565,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) } if (of_device_compatible_match(np, stmmac_gmac4_compats)) { - plat->has_gmac4 = 1; - plat->has_gmac = 0; + plat->core_type = DWMAC_CORE_GMAC4; plat->pmt = 1; if (of_property_read_bool(np, "snps,tso")) plat->flags |= STMMAC_FLAG_TSO_EN; @@ -580,7 +579,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) } if (of_device_is_compatible(np, "snps,dwxgmac")) { - plat->has_xgmac = 1; + plat->core_type = DWMAC_CORE_XGMAC; plat->pmt = 1; if (of_property_read_bool(np, "snps,tso")) plat->flags |= STMMAC_FLAG_TSO_EN; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 993ff4e87e5570..3e30172fa12948 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -57,7 +57,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) bool xmac, est_rst = false; int ret; - xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + xmac = dwmac_is_xmac(priv->plat->core_type); if (delta < 0) { neg_adj = 1; @@ -344,7 +344,7 @@ void stmmac_ptp_register(struct stmmac_priv *priv) /* Calculate the clock domain crossing (CDC) error if necessary */ priv->plat->cdc_error_adj = 0; - if (priv->plat->has_gmac4) + if (priv->plat->core_type == DWMAC_CORE_GMAC4) priv->plat->cdc_error_adj = (2 * NSEC_PER_SEC) / priv->plat->clk_ptp_rate; /* Update the ptp clock parameters based on feature discovery, when diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c index ff02a79c00d4f5..b18404dd5a8beb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c @@ -122,7 +122,8 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev, /* Extended Rx VLAN Filter Enable */ for (i = 0; i < hw->num_vlan; i++) { - if ((hw->vlan_filter[i] & VLAN_TAG_DATA_VID) == vid) { + if ((hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) && + ((hw->vlan_filter[i] & VLAN_TAG_DATA_VID) == vid)) { ret = vlan_write_filter(dev, hw, i, 0); if (!ret) diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 48f0a96c0e9e3a..6669980829980d 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -2551,6 +2551,9 @@ static int happy_meal_sbus_probe_one(struct platform_device *op, int is_qfe) goto err_out_clear_quattro; } + /* BIGMAC may have bogus sizes */ + if ((op->resource[3].end - op->resource[3].start) >= BMAC_REG_SIZE) + op->resource[3].end = op->resource[3].start + BMAC_REG_SIZE - 1; hp->bigmacregs = devm_platform_ioremap_resource(op, 3); if (IS_ERR(hp->bigmacregs)) { dev_err(&op->dev, "Cannot map BIGMAC registers.\n"); diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index a54d71155263c2..fe5b2926d8ab06 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -209,6 +209,7 @@ config TI_ICSSG_PRUETH_SR1 depends on PRU_REMOTEPROC depends on NET_SWITCHDEV depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER + depends on PTP_1588_CLOCK_OPTIONAL help Support dual Gigabit Ethernet ports over the ICSSG PRU Subsystem. This subsystem is available on the AM65 SR1.0 platform. @@ -234,7 +235,7 @@ config TI_PRUETH depends on PRU_REMOTEPROC depends on NET_SWITCHDEV select TI_ICSS_IEP - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL help Some TI SoCs has Programmable Realtime Unit (PRU) cores which can support Single or Dual Ethernet ports with the help of firmware code diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 54c24cd3d3be63..b0e18bdc2c8510 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -305,12 +305,19 @@ static int cpsw_purge_all_mc(struct net_device *ndev, const u8 *addr, int num) return 0; } -static void cpsw_ndo_set_rx_mode(struct net_device *ndev) +static void cpsw_ndo_set_rx_mode_work(struct work_struct *work) { - struct cpsw_priv *priv = netdev_priv(ndev); + struct cpsw_priv *priv = container_of(work, struct cpsw_priv, rx_mode_work); struct cpsw_common *cpsw = priv->cpsw; + struct net_device *ndev = priv->ndev; int slave_port = -1; + rtnl_lock(); + if (!netif_running(ndev)) + goto unlock_rtnl; + + netif_addr_lock_bh(ndev); + if (cpsw->data.dual_emac) slave_port = priv->emac_port + 1; @@ -318,7 +325,7 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev) /* Enable promiscuous mode */ cpsw_set_promiscious(ndev, true); cpsw_ale_set_allmulti(cpsw->ale, IFF_ALLMULTI, slave_port); - return; + goto unlock_addr; } else { /* Disable promiscuous mode */ cpsw_set_promiscious(ndev, false); @@ -331,6 +338,18 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev) /* add/remove mcast address either for real netdev or for vlan */ __hw_addr_ref_sync_dev(&ndev->mc, ndev, cpsw_add_mc_addr, cpsw_del_mc_addr); + +unlock_addr: + netif_addr_unlock_bh(ndev); +unlock_rtnl: + rtnl_unlock(); +} + +static void cpsw_ndo_set_rx_mode(struct net_device *ndev) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + + schedule_work(&priv->rx_mode_work); } static unsigned int cpsw_rxbuf_total_len(unsigned int len) @@ -1472,6 +1491,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv) priv_sl2->ndev = ndev; priv_sl2->dev = &ndev->dev; priv_sl2->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG); + INIT_WORK(&priv_sl2->rx_mode_work, cpsw_ndo_set_rx_mode_work); if (is_valid_ether_addr(data->slave_data[1].mac_addr)) { memcpy(priv_sl2->mac_addr, data->slave_data[1].mac_addr, @@ -1653,6 +1673,7 @@ static int cpsw_probe(struct platform_device *pdev) priv->dev = dev; priv->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG); priv->emac_port = 0; + INIT_WORK(&priv->rx_mode_work, cpsw_ndo_set_rx_mode_work); if (is_valid_ether_addr(data->slave_data[0].mac_addr)) { memcpy(priv->mac_addr, data->slave_data[0].mac_addr, ETH_ALEN); @@ -1758,6 +1779,8 @@ static int cpsw_probe(struct platform_device *pdev) static void cpsw_remove(struct platform_device *pdev) { struct cpsw_common *cpsw = platform_get_drvdata(pdev); + struct net_device *ndev; + struct cpsw_priv *priv; int i, ret; ret = pm_runtime_resume_and_get(&pdev->dev); @@ -1770,9 +1793,15 @@ static void cpsw_remove(struct platform_device *pdev) return; } - for (i = 0; i < cpsw->data.slaves; i++) - if (cpsw->slaves[i].ndev) - unregister_netdev(cpsw->slaves[i].ndev); + for (i = 0; i < cpsw->data.slaves; i++) { + ndev = cpsw->slaves[i].ndev; + if (!ndev) + continue; + + priv = netdev_priv(ndev); + unregister_netdev(ndev); + disable_work_sync(&priv->rx_mode_work); + } cpts_release(cpsw->cpts); cpdma_ctlr_destroy(cpsw->dma); diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 8b9e2078c6025a..371a099ac4e636 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -248,16 +248,22 @@ static int cpsw_purge_all_mc(struct net_device *ndev, const u8 *addr, int num) return 0; } -static void cpsw_ndo_set_rx_mode(struct net_device *ndev) +static void cpsw_ndo_set_rx_mode_work(struct work_struct *work) { - struct cpsw_priv *priv = netdev_priv(ndev); + struct cpsw_priv *priv = container_of(work, struct cpsw_priv, rx_mode_work); struct cpsw_common *cpsw = priv->cpsw; + struct net_device *ndev = priv->ndev; + rtnl_lock(); + if (!netif_running(ndev)) + goto unlock_rtnl; + + netif_addr_lock_bh(ndev); if (ndev->flags & IFF_PROMISC) { /* Enable promiscuous mode */ cpsw_set_promiscious(ndev, true); cpsw_ale_set_allmulti(cpsw->ale, IFF_ALLMULTI, priv->emac_port); - return; + goto unlock_addr; } /* Disable promiscuous mode */ @@ -270,6 +276,18 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev) /* add/remove mcast address either for real netdev or for vlan */ __hw_addr_ref_sync_dev(&ndev->mc, ndev, cpsw_add_mc_addr, cpsw_del_mc_addr); + +unlock_addr: + netif_addr_unlock_bh(ndev); +unlock_rtnl: + rtnl_unlock(); +} + +static void cpsw_ndo_set_rx_mode(struct net_device *ndev) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + + schedule_work(&priv->rx_mode_work); } static unsigned int cpsw_rxbuf_total_len(unsigned int len) @@ -1398,6 +1416,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw) priv->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG); priv->emac_port = i + 1; priv->tx_packet_min = CPSW_MIN_PACKET_SIZE; + INIT_WORK(&priv->rx_mode_work, cpsw_ndo_set_rx_mode_work); if (is_valid_ether_addr(slave_data->mac_addr)) { ether_addr_copy(priv->mac_addr, slave_data->mac_addr); @@ -1447,13 +1466,18 @@ static int cpsw_create_ports(struct cpsw_common *cpsw) static void cpsw_unregister_ports(struct cpsw_common *cpsw) { + struct net_device *ndev; + struct cpsw_priv *priv; int i = 0; for (i = 0; i < cpsw->data.slaves; i++) { - if (!cpsw->slaves[i].ndev) + ndev = cpsw->slaves[i].ndev; + if (!ndev) continue; - unregister_netdev(cpsw->slaves[i].ndev); + priv = netdev_priv(ndev); + unregister_netdev(ndev); + disable_work_sync(&priv->rx_mode_work); } } diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h index 91add8925e235c..acb6181c5c9e1b 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.h +++ b/drivers/net/ethernet/ti/cpsw_priv.h @@ -391,6 +391,7 @@ struct cpsw_priv { u32 tx_packet_min; struct cpsw_ale_ratelimit ale_bc_ratelimit; struct cpsw_ale_ratelimit ale_mc_ratelimit; + struct work_struct rx_mode_work; }; #define ndev_to_cpsw(ndev) (((struct cpsw_priv *)netdev_priv(ndev))->cpsw) diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig index d138dea7d208d7..ec278f99d2955c 100644 --- a/drivers/net/ethernet/wangxun/Kconfig +++ b/drivers/net/ethernet/wangxun/Kconfig @@ -21,6 +21,7 @@ config LIBWX depends on PTP_1588_CLOCK_OPTIONAL select PAGE_POOL select DIMLIB + select PHYLINK help Common library for Wangxun(R) Ethernet drivers. @@ -29,7 +30,6 @@ config NGBE depends on PCI depends on PTP_1588_CLOCK_OPTIONAL select LIBWX - select PHYLINK help This driver supports Wangxun(R) GbE PCI Express family of adapters. @@ -48,7 +48,6 @@ config TXGBE depends on PTP_1588_CLOCK_OPTIONAL select MARVELL_10G_PHY select REGMAP - select PHYLINK select HWMON if TXGBE=y select SFP select GPIOLIB @@ -71,7 +70,6 @@ config TXGBEVF depends on PCI_MSI depends on PTP_1588_CLOCK_OPTIONAL select LIBWX - select PHYLINK help This driver supports virtual functions for SP1000A, WX1820AL, WX5XXX, WX5XXXAL. diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c index dc87ccad965240..08b9b426f64846 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c @@ -65,7 +65,7 @@ int txgbe_test_hostif(struct wx *wx) buffer.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED; return wx_host_interface_command(wx, (u32 *)&buffer, sizeof(buffer), - WX_HI_COMMAND_TIMEOUT, true); + WX_HI_COMMAND_TIMEOUT, false); } static int txgbe_identify_sfp_hostif(struct wx *wx, struct txgbe_hic_i2c_read *buffer) @@ -103,7 +103,7 @@ static int txgbe_set_phy_link_hostif(struct wx *wx, int speed, int autoneg, int buffer.duplex = duplex; return wx_host_interface_command(wx, (u32 *)&buffer, sizeof(buffer), - WX_HI_COMMAND_TIMEOUT, true); + WX_HI_COMMAND_TIMEOUT, false); } static void txgbe_get_link_capabilities(struct wx *wx) diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c index b9b5554ea8620e..5ad2673f213d65 100644 --- a/drivers/net/fjes/fjes_hw.c +++ b/drivers/net/fjes/fjes_hw.c @@ -334,7 +334,7 @@ int fjes_hw_init(struct fjes_hw *hw) ret = fjes_hw_reset(hw); if (ret) - return ret; + goto err_iounmap; fjes_hw_set_irqmask(hw, REG_ICTL_MASK_ALL, true); @@ -347,8 +347,10 @@ int fjes_hw_init(struct fjes_hw *hw) hw->max_epid = fjes_hw_get_max_epid(hw); hw->my_epid = fjes_hw_get_my_epid(hw); - if ((hw->max_epid == 0) || (hw->my_epid >= hw->max_epid)) - return -ENXIO; + if ((hw->max_epid == 0) || (hw->my_epid >= hw->max_epid)) { + ret = -ENXIO; + goto err_iounmap; + } ret = fjes_hw_setup(hw); @@ -356,6 +358,10 @@ int fjes_hw_init(struct fjes_hw *hw) hw->hw_info.trace_size = FJES_DEBUG_BUFFER_SIZE; return ret; + +err_iounmap: + fjes_hw_iounmap(hw); + return ret; } void fjes_hw_exit(struct fjes_hw *hw) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 39c892e46cb017..25a358524a096e 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1757,6 +1757,9 @@ static int netvsc_set_rxfh(struct net_device *dev, rxfh->hfunc != ETH_RSS_HASH_TOP) return -EOPNOTSUPP; + if (!ndc->rx_table_sz) + return -EOPNOTSUPP; + rndis_dev = ndev->extension; if (rxfh->indir) { for (i = 0; i < ndc->rx_table_sz; i++) diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 50de3ee204dbc9..80f84fc87008b3 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -69,7 +69,6 @@ struct ipvl_dev { DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE); netdev_features_t sfeatures; u32 msg_enable; - spinlock_t addrs_lock; }; struct ipvl_addr { @@ -90,6 +89,7 @@ struct ipvl_port { struct net_device *dev; possible_net_t pnet; struct hlist_head hlhead[IPVLAN_HASH_SIZE]; + spinlock_t addrs_lock; /* guards hash-table and addrs */ struct list_head ipvlans; u16 mode; u16 flags; diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index d7e3ddbcab6f41..6c6677ded82ef8 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -107,17 +107,15 @@ void ipvlan_ht_addr_del(struct ipvl_addr *addr) struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, const void *iaddr, bool is_v6) { - struct ipvl_addr *addr, *ret = NULL; + struct ipvl_addr *addr; - rcu_read_lock(); - list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) { - if (addr_equal(is_v6, addr, iaddr)) { - ret = addr; - break; - } + assert_spin_locked(&ipvlan->port->addrs_lock); + + list_for_each_entry(addr, &ipvlan->addrs, anode) { + if (addr_equal(is_v6, addr, iaddr)) + return addr; } - rcu_read_unlock(); - return ret; + return NULL; } bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6) @@ -737,6 +735,9 @@ static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb, struct ethhdr *eth = eth_hdr(skb); rx_handler_result_t ret = RX_HANDLER_PASS; + if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) + return RX_HANDLER_PASS; + if (is_multicast_ether_addr(eth->h_dest)) { if (ipvlan_external_frame(skb, port)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 660f3db117664e..baccdad695fdad 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -75,6 +75,7 @@ static int ipvlan_port_create(struct net_device *dev) for (idx = 0; idx < IPVLAN_HASH_SIZE; idx++) INIT_HLIST_HEAD(&port->hlhead[idx]); + spin_lock_init(&port->addrs_lock); skb_queue_head_init(&port->backlog); INIT_WORK(&port->wq, ipvlan_process_multicast); ida_init(&port->ida); @@ -181,6 +182,7 @@ static void ipvlan_uninit(struct net_device *dev) static int ipvlan_open(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); + struct ipvl_port *port = ipvlan->port; struct ipvl_addr *addr; if (ipvlan->port->mode == IPVLAN_MODE_L3 || @@ -189,10 +191,10 @@ static int ipvlan_open(struct net_device *dev) else dev->flags &= ~IFF_NOARP; - rcu_read_lock(); - list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) + spin_lock_bh(&port->addrs_lock); + list_for_each_entry(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_add(ipvlan, addr); - rcu_read_unlock(); + spin_unlock_bh(&port->addrs_lock); return 0; } @@ -206,10 +208,10 @@ static int ipvlan_stop(struct net_device *dev) dev_uc_unsync(phy_dev, dev); dev_mc_unsync(phy_dev, dev); - rcu_read_lock(); - list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) + spin_lock_bh(&ipvlan->port->addrs_lock); + list_for_each_entry(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_del(addr); - rcu_read_unlock(); + spin_unlock_bh(&ipvlan->port->addrs_lock); return 0; } @@ -579,7 +581,6 @@ int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params, if (!tb[IFLA_MTU]) ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); - spin_lock_init(&ipvlan->addrs_lock); /* TODO Probably put random address here to be presented to the * world but keep using the physical-dev address for the outgoing @@ -657,13 +658,13 @@ void ipvlan_link_delete(struct net_device *dev, struct list_head *head) struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_addr *addr, *next; - spin_lock_bh(&ipvlan->addrs_lock); + spin_lock_bh(&ipvlan->port->addrs_lock); list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) { ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); kfree_rcu(addr, rcu); } - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); ida_free(&ipvlan->port->ida, dev->dev_id); list_del_rcu(&ipvlan->pnode); @@ -817,6 +818,8 @@ static int ipvlan_add_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; + assert_spin_locked(&ipvlan->port->addrs_lock); + addr = kzalloc(sizeof(struct ipvl_addr), GFP_ATOMIC); if (!addr) return -ENOMEM; @@ -847,16 +850,16 @@ static void ipvlan_del_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; - spin_lock_bh(&ipvlan->addrs_lock); + spin_lock_bh(&ipvlan->port->addrs_lock); addr = ipvlan_find_addr(ipvlan, iaddr, is_v6); if (!addr) { - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); return; } ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); kfree_rcu(addr, rcu); } @@ -878,14 +881,14 @@ static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { int ret = -EINVAL; - spin_lock_bh(&ipvlan->addrs_lock); + spin_lock_bh(&ipvlan->port->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv6=%pI6c addr for %s intf\n", ip6_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip6_addr, true); - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); return ret; } @@ -924,21 +927,24 @@ static int ipvlan_addr6_validator_event(struct notifier_block *unused, struct in6_validator_info *i6vi = (struct in6_validator_info *)ptr; struct net_device *dev = (struct net_device *)i6vi->i6vi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); + int ret = NOTIFY_OK; if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: + spin_lock_bh(&ipvlan->port->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) { NL_SET_ERR_MSG(i6vi->extack, "Address already assigned to an ipvlan device"); - return notifier_from_errno(-EADDRINUSE); + ret = notifier_from_errno(-EADDRINUSE); } + spin_unlock_bh(&ipvlan->port->addrs_lock); break; } - return NOTIFY_OK; + return ret; } #endif @@ -946,14 +952,14 @@ static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { int ret = -EINVAL; - spin_lock_bh(&ipvlan->addrs_lock); + spin_lock_bh(&ipvlan->port->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv4=%pI4 on %s intf.\n", ip4_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip4_addr, false); - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); return ret; } @@ -995,21 +1001,24 @@ static int ipvlan_addr4_validator_event(struct notifier_block *unused, struct in_validator_info *ivi = (struct in_validator_info *)ptr; struct net_device *dev = (struct net_device *)ivi->ivi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); + int ret = NOTIFY_OK; if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: + spin_lock_bh(&ipvlan->port->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) { NL_SET_ERR_MSG(ivi->extack, "Address already assigned to an ipvlan device"); - return notifier_from_errno(-EADDRINUSE); + ret = notifier_from_errno(-EADDRINUSE); } + spin_unlock_bh(&ipvlan->port->addrs_lock); break; } - return NOTIFY_OK; + return ret; } static struct notifier_block ipvlan_addr4_notifier_block __read_mostly = { diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 7966545512cfea..4433b8e95b6acc 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -59,7 +59,7 @@ struct macvlan_port { struct macvlan_source_entry { struct hlist_node hlist; - struct macvlan_dev *vlan; + struct macvlan_dev __rcu *vlan; unsigned char addr[6+2] __aligned(sizeof(u16)); struct rcu_head rcu; }; @@ -146,7 +146,7 @@ static struct macvlan_source_entry *macvlan_hash_lookup_source( hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { if (ether_addr_equal_64bits(entry->addr, addr) && - entry->vlan == vlan) + rcu_access_pointer(entry->vlan) == vlan) return entry; } return NULL; @@ -168,7 +168,7 @@ static int macvlan_hash_add_source(struct macvlan_dev *vlan, return -ENOMEM; ether_addr_copy(entry->addr, addr); - entry->vlan = vlan; + RCU_INIT_POINTER(entry->vlan, vlan); h = &port->vlan_source_hash[macvlan_eth_hash(addr)]; hlist_add_head_rcu(&entry->hlist, h); vlan->macaddr_count++; @@ -187,6 +187,7 @@ static void macvlan_hash_add(struct macvlan_dev *vlan) static void macvlan_hash_del_source(struct macvlan_source_entry *entry) { + RCU_INIT_POINTER(entry->vlan, NULL); hlist_del_rcu(&entry->hlist); kfree_rcu(entry, rcu); } @@ -390,7 +391,7 @@ static void macvlan_flush_sources(struct macvlan_port *port, int i; hash_for_each_safe(port->vlan_source_hash, i, next, entry, hlist) - if (entry->vlan == vlan) + if (rcu_access_pointer(entry->vlan) == vlan) macvlan_hash_del_source(entry); vlan->macaddr_count = 0; @@ -433,9 +434,14 @@ static bool macvlan_forward_source(struct sk_buff *skb, hlist_for_each_entry_rcu(entry, h, hlist) { if (ether_addr_equal_64bits(entry->addr, addr)) { - if (entry->vlan->flags & MACVLAN_FLAG_NODST) + struct macvlan_dev *vlan = rcu_dereference(entry->vlan); + + if (!vlan) + continue; + + if (vlan->flags & MACVLAN_FLAG_NODST) consume = true; - macvlan_forward_source_one(skb, entry->vlan); + macvlan_forward_source_one(skb, vlan); } } @@ -1561,10 +1567,16 @@ int macvlan_common_newlink(struct net_device *dev, /* the macvlan port may be freed by macvlan_uninit when fail to register. * so we destroy the macvlan port only when it's valid. */ - if (create && macvlan_port_get_rtnl(lowerdev)) { + if (macvlan_port_get_rtnl(lowerdev)) { macvlan_flush_sources(port, vlan); - macvlan_port_destroy(port->dev); + if (create) + macvlan_port_destroy(port->dev); } + /* @dev might have been made visible before an error was detected. + * Make sure to observe an RCU grace period before our caller + * (rtnl_newlink()) frees it. + */ + synchronize_net(); return err; } EXPORT_SYMBOL_GPL(macvlan_common_newlink); @@ -1680,7 +1692,7 @@ static int macvlan_fill_info_macaddr(struct sk_buff *skb, struct macvlan_source_entry *entry; hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { - if (entry->vlan != vlan) + if (rcu_access_pointer(entry->vlan) != vlan) continue; if (nla_put(skb, IFLA_MACVLAN_MACADDR, ETH_ALEN, entry->addr)) return 1; diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c index f782d93f826efc..8043b57bdf2509 100644 --- a/drivers/net/mctp/mctp-i2c.c +++ b/drivers/net/mctp/mctp-i2c.c @@ -242,6 +242,12 @@ static int mctp_i2c_slave_cb(struct i2c_client *client, return 0; switch (event) { + case I2C_SLAVE_READ_REQUESTED: + case I2C_SLAVE_READ_PROCESSED: + /* MCTP I2C transport only uses writes */ + midev->rx_pos = 0; + *val = 0xff; + break; case I2C_SLAVE_WRITE_RECEIVED: if (midev->rx_pos < MCTP_I2C_BUFSZ) { midev->rx_buffer[midev->rx_pos] = *val; @@ -279,6 +285,9 @@ static int mctp_i2c_recv(struct mctp_i2c_dev *midev) size_t recvlen; int status; + if (midev->rx_pos == 0) + return 0; + /* + 1 for the PEC */ if (midev->rx_pos < MCTP_I2C_MINLEN + 1) { ndev->stats.rx_length_errors++; diff --git a/drivers/net/mdio/mdio-aspeed.c b/drivers/net/mdio/mdio-aspeed.c index e55be6dc9ae70f..d6b9004c61dc16 100644 --- a/drivers/net/mdio/mdio-aspeed.c +++ b/drivers/net/mdio/mdio-aspeed.c @@ -63,6 +63,13 @@ static int aspeed_mdio_op(struct mii_bus *bus, u8 st, u8 op, u8 phyad, u8 regad, iowrite32(ctrl, ctx->base + ASPEED_MDIO_CTRL); + /* Workaround for read-after-write issue. + * The controller may return stale data if a read follows immediately + * after a write. A dummy read forces the hardware to update its + * internal state, ensuring that the next real read returns correct data. + */ + ioread32(ctx->base + ASPEED_MDIO_CTRL); + return readl_poll_timeout(ctx->base + ASPEED_MDIO_CTRL, ctrl, !(ctrl & ASPEED_MDIO_CTRL_FIRE), ASPEED_MDIO_INTERVAL_US, diff --git a/drivers/net/mdio/mdio-realtek-rtl9300.c b/drivers/net/mdio/mdio-realtek-rtl9300.c index 33694c3ff9a719..405a07075dd115 100644 --- a/drivers/net/mdio/mdio-realtek-rtl9300.c +++ b/drivers/net/mdio/mdio-realtek-rtl9300.c @@ -354,7 +354,6 @@ static int rtl9300_mdiobus_probe_one(struct device *dev, struct rtl9300_mdio_pri struct fwnode_handle *node) { struct rtl9300_mdio_chan *chan; - struct fwnode_handle *child; struct mii_bus *bus; u32 mdio_bus; int err; @@ -371,7 +370,7 @@ static int rtl9300_mdiobus_probe_one(struct device *dev, struct rtl9300_mdio_pri * compatible = "ethernet-phy-ieee802.3-c45". This does mean we can't * support both c45 and c22 on the same MDIO bus. */ - fwnode_for_each_child_node(node, child) + fwnode_for_each_child_node_scoped(node, child) if (fwnode_device_is_compatible(child, "ethernet-phy-ieee802.3-c45")) priv->smi_bus_is_c45[mdio_bus] = true; @@ -409,7 +408,6 @@ static int rtl9300_mdiobus_map_ports(struct device *dev) { struct rtl9300_mdio_priv *priv = dev_get_drvdata(dev); struct device *parent = dev->parent; - struct fwnode_handle *port; int err; struct fwnode_handle *ports __free(fwnode_handle) = @@ -418,7 +416,7 @@ static int rtl9300_mdiobus_map_ports(struct device *dev) return dev_err_probe(dev, -EINVAL, "%pfwP missing ethernet-ports\n", dev_fwnode(parent)); - fwnode_for_each_child_node(ports, port) { + fwnode_for_each_child_node_scoped(ports, port) { struct device_node *mdio_dn; u32 addr; u32 bus; diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 49537d3c41205c..5f17f68f3c0838 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -244,7 +244,9 @@ static int nsim_bpf_create_prog(struct nsim_dev *nsim_dev, &state->state, &nsim_bpf_string_fops); debugfs_create_bool("loaded", 0400, state->ddir, &state->is_loaded); + mutex_lock(&nsim_dev->progs_list_lock); list_add_tail(&state->l, &nsim_dev->bpf_bound_progs); + mutex_unlock(&nsim_dev->progs_list_lock); prog->aux->offload->dev_priv = state; @@ -273,12 +275,16 @@ static int nsim_bpf_translate(struct bpf_prog *prog) static void nsim_bpf_destroy_prog(struct bpf_prog *prog) { struct nsim_bpf_bound_prog *state; + struct nsim_dev *nsim_dev; state = prog->aux->offload->dev_priv; + nsim_dev = state->nsim_dev; WARN(state->is_loaded, "offload state destroyed while program still bound"); debugfs_remove_recursive(state->ddir); + mutex_lock(&nsim_dev->progs_list_lock); list_del(&state->l); + mutex_unlock(&nsim_dev->progs_list_lock); kfree(state); } diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c index 70e8c38ddad6b6..d16b95304aa7e3 100644 --- a/drivers/net/netdevsim/bus.c +++ b/drivers/net/netdevsim/bus.c @@ -332,6 +332,11 @@ static ssize_t link_device_store(const struct bus_type *bus, const char *buf, si rcu_assign_pointer(nsim_a->peer, nsim_b); rcu_assign_pointer(nsim_b->peer, nsim_a); + if (netif_running(dev_a) && netif_running(dev_b)) { + netif_carrier_on(dev_a); + netif_carrier_on(dev_b); + } + out_err: put_net(ns_b); put_net(ns_a); @@ -381,6 +386,9 @@ static ssize_t unlink_device_store(const struct bus_type *bus, const char *buf, if (!peer) goto out_put_netns; + netif_carrier_off(dev); + netif_carrier_off(peer->netdev); + err = 0; RCU_INIT_POINTER(nsim->peer, NULL); RCU_INIT_POINTER(peer->peer, NULL); diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 95f66c1f59db88..56a47c060f2e19 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -1591,6 +1591,7 @@ int nsim_drv_probe(struct nsim_bus_dev *nsim_bus_dev) nsim_dev->max_macs = NSIM_DEV_MAX_MACS_DEFAULT; nsim_dev->test1 = NSIM_DEV_TEST1_DEFAULT; spin_lock_init(&nsim_dev->fa_cookie_lock); + mutex_init(&nsim_dev->progs_list_lock); dev_set_drvdata(&nsim_bus_dev->dev, nsim_dev); @@ -1729,6 +1730,7 @@ void nsim_drv_remove(struct nsim_bus_dev *nsim_bus_dev) devl_unregister(devlink); kfree(nsim_dev->vfconfigs); kfree(nsim_dev->fa_cookie); + mutex_destroy(&nsim_dev->progs_list_lock); devl_unlock(devlink); devlink_free(devlink); dev_set_drvdata(&nsim_bus_dev->dev, NULL); diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 02c1c97b700802..d91c0899e536e7 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -319,6 +319,7 @@ struct nsim_dev { u32 prog_id_gen; struct list_head bpf_bound_progs; struct list_head bpf_bound_maps; + struct mutex progs_list_lock; struct netdev_phys_item_id switch_id; struct list_head port_list; bool fw_update_status; diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c index 3e9e7f8444b344..955c9a37e1f8db 100644 --- a/drivers/net/ovpn/io.c +++ b/drivers/net/ovpn/io.c @@ -355,6 +355,7 @@ netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev) struct ovpn_priv *ovpn = netdev_priv(dev); struct sk_buff *segments, *curr, *next; struct sk_buff_head skb_list; + unsigned int tx_bytes = 0; struct ovpn_peer *peer; __be16 proto; int ret; @@ -365,7 +366,27 @@ netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev) /* verify IP header size in network packet */ proto = ovpn_ip_check_protocol(skb); if (unlikely(!proto || skb->protocol != proto)) - goto drop; + goto drop_no_peer; + + /* retrieve peer serving the destination IP of this packet */ + peer = ovpn_peer_get_by_dst(ovpn, skb); + if (unlikely(!peer)) { + switch (skb->protocol) { + case htons(ETH_P_IP): + net_dbg_ratelimited("%s: no peer to send data to dst=%pI4\n", + netdev_name(ovpn->dev), + &ip_hdr(skb)->daddr); + break; + case htons(ETH_P_IPV6): + net_dbg_ratelimited("%s: no peer to send data to dst=%pI6c\n", + netdev_name(ovpn->dev), + &ipv6_hdr(skb)->daddr); + break; + } + goto drop_no_peer; + } + /* dst was needed for peer selection - it can now be dropped */ + skb_dst_drop(skb); if (skb_is_gso(skb)) { segments = skb_gso_segment(skb, 0); @@ -394,36 +415,28 @@ netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev) continue; } + /* only count what we actually send */ + tx_bytes += curr->len; __skb_queue_tail(&skb_list, curr); } - skb_list.prev->next = NULL; - /* retrieve peer serving the destination IP of this packet */ - peer = ovpn_peer_get_by_dst(ovpn, skb); - if (unlikely(!peer)) { - switch (skb->protocol) { - case htons(ETH_P_IP): - net_dbg_ratelimited("%s: no peer to send data to dst=%pI4\n", - netdev_name(ovpn->dev), - &ip_hdr(skb)->daddr); - break; - case htons(ETH_P_IPV6): - net_dbg_ratelimited("%s: no peer to send data to dst=%pI6c\n", - netdev_name(ovpn->dev), - &ipv6_hdr(skb)->daddr); - break; - } - goto drop; + /* no segments survived: don't jump to 'drop' because we already + * incremented the counter for each failure in the loop + */ + if (unlikely(skb_queue_empty(&skb_list))) { + ovpn_peer_put(peer); + return NETDEV_TX_OK; } - /* dst was needed for peer selection - it can now be dropped */ - skb_dst_drop(skb); + skb_list.prev->next = NULL; - ovpn_peer_stats_increment_tx(&peer->vpn_stats, skb->len); + ovpn_peer_stats_increment_tx(&peer->vpn_stats, tx_bytes); ovpn_send(ovpn, skb_list.next, peer); return NETDEV_TX_OK; drop: + ovpn_peer_put(peer); +drop_no_peer: dev_dstats_tx_dropped(ovpn->dev); skb_tx_error(skb); kfree_skb_list(skb); diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c index 9750871ab65cee..448cee3b3f9fa2 100644 --- a/drivers/net/ovpn/socket.c +++ b/drivers/net/ovpn/socket.c @@ -200,6 +200,22 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer) ovpn_sock->sk = sk; kref_init(&ovpn_sock->refcount); + /* TCP sockets are per-peer, therefore they are linked to their unique + * peer + */ + if (sk->sk_protocol == IPPROTO_TCP) { + INIT_WORK(&ovpn_sock->tcp_tx_work, ovpn_tcp_tx_work); + ovpn_sock->peer = peer; + ovpn_peer_hold(peer); + } else if (sk->sk_protocol == IPPROTO_UDP) { + /* in UDP we only link the ovpn instance since the socket is + * shared among multiple peers + */ + ovpn_sock->ovpn = peer->ovpn; + netdev_hold(peer->ovpn->dev, &ovpn_sock->dev_tracker, + GFP_KERNEL); + } + /* the newly created ovpn_socket is holding reference to sk, * therefore we increase its refcounter. * @@ -212,29 +228,16 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer) ret = ovpn_socket_attach(ovpn_sock, sock, peer); if (ret < 0) { + if (sk->sk_protocol == IPPROTO_TCP) + ovpn_peer_put(peer); + else if (sk->sk_protocol == IPPROTO_UDP) + netdev_put(peer->ovpn->dev, &ovpn_sock->dev_tracker); + sock_put(sk); kfree(ovpn_sock); ovpn_sock = ERR_PTR(ret); - goto sock_release; - } - - /* TCP sockets are per-peer, therefore they are linked to their unique - * peer - */ - if (sk->sk_protocol == IPPROTO_TCP) { - INIT_WORK(&ovpn_sock->tcp_tx_work, ovpn_tcp_tx_work); - ovpn_sock->peer = peer; - ovpn_peer_hold(peer); - } else if (sk->sk_protocol == IPPROTO_UDP) { - /* in UDP we only link the ovpn instance since the socket is - * shared among multiple peers - */ - ovpn_sock->ovpn = peer->ovpn; - netdev_hold(peer->ovpn->dev, &ovpn_sock->dev_tracker, - GFP_KERNEL); } - rcu_assign_sk_user_data(sk, ovpn_sock); sock_release: release_sock(sk); return ovpn_sock; diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c index 0d7f30360d8746..ec2bbc28c19666 100644 --- a/drivers/net/ovpn/tcp.c +++ b/drivers/net/ovpn/tcp.c @@ -199,7 +199,19 @@ void ovpn_tcp_socket_detach(struct ovpn_socket *ovpn_sock) sk->sk_data_ready = peer->tcp.sk_cb.sk_data_ready; sk->sk_write_space = peer->tcp.sk_cb.sk_write_space; sk->sk_prot = peer->tcp.sk_cb.prot; - sk->sk_socket->ops = peer->tcp.sk_cb.ops; + + /* tcp_close() may race this function and could set + * sk->sk_socket to NULL. It does so by invoking + * sock_orphan(), which holds sk_callback_lock before + * doing the assignment. + * + * For this reason we acquire the same lock to avoid + * sk_socket to disappear under our feet + */ + write_lock_bh(&sk->sk_callback_lock); + if (sk->sk_socket) + sk->sk_socket->ops = peer->tcp.sk_cb.ops; + write_unlock_bh(&sk->sk_callback_lock); rcu_assign_sk_user_data(sk, NULL); } @@ -487,6 +499,7 @@ int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock, /* make sure no pre-existing encapsulation handler exists */ if (ovpn_sock->sk->sk_user_data) return -EBUSY; + rcu_assign_sk_user_data(ovpn_sock->sk, ovpn_sock); /* only a fully connected socket is expected. Connection should be * handled in userspace @@ -495,13 +508,14 @@ int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock, net_err_ratelimited("%s: provided TCP socket is not in ESTABLISHED state: %d\n", netdev_name(peer->ovpn->dev), ovpn_sock->sk->sk_state); - return -EINVAL; + ret = -EINVAL; + goto err; } ret = strp_init(&peer->tcp.strp, ovpn_sock->sk, &cb); if (ret < 0) { DEBUG_NET_WARN_ON_ONCE(1); - return ret; + goto err; } INIT_WORK(&peer->tcp.defer_del_work, ovpn_tcp_peer_del_work); @@ -536,6 +550,9 @@ int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock, strp_check_rcv(&peer->tcp.strp); return 0; +err: + rcu_assign_sk_user_data(ovpn_sock->sk, NULL); + return ret; } static void ovpn_tcp_close(struct sock *sk, long timeout) diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c index d6a0f7a0b75d74..272b535ecaad4c 100644 --- a/drivers/net/ovpn/udp.c +++ b/drivers/net/ovpn/udp.c @@ -386,6 +386,7 @@ int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock, struct socket *sock, struct ovpn_priv *ovpn) { struct udp_tunnel_sock_cfg cfg = { + .sk_user_data = ovpn_sock, .encap_type = UDP_ENCAP_OVPNINUDP, .encap_rcv = ovpn_udp_encap_recv, .encap_destroy = ovpn_udp_encap_destroy, diff --git a/drivers/net/pcs/pcs-mtk-lynxi.c b/drivers/net/pcs/pcs-mtk-lynxi.c index 149ddf51d78564..87df3a9dfc9bcc 100644 --- a/drivers/net/pcs/pcs-mtk-lynxi.c +++ b/drivers/net/pcs/pcs-mtk-lynxi.c @@ -93,12 +93,10 @@ static unsigned int mtk_pcs_lynxi_inband_caps(struct phylink_pcs *pcs, { switch (interface) { case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: case PHY_INTERFACE_MODE_SGMII: return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE; - case PHY_INTERFACE_MODE_2500BASEX: - return LINK_INBAND_DISABLE; - default: return 0; } diff --git a/drivers/net/phy/adin1100.c b/drivers/net/phy/adin1100.c index bd7a47a903acae..10b796c2daee7c 100644 --- a/drivers/net/phy/adin1100.c +++ b/drivers/net/phy/adin1100.c @@ -201,7 +201,7 @@ static int adin_set_powerdown_mode(struct phy_device *phydev, bool en) return ret; return phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1, ADIN_CRSM_STAT, ret, - (ret & ADIN_CRSM_SFT_PD_RDY) == val, + !!(ret & ADIN_CRSM_SFT_PD_RDY) == en, 1000, 30000, true); } diff --git a/drivers/net/phy/aquantia/aquantia_firmware.c b/drivers/net/phy/aquantia/aquantia_firmware.c index bbbcc9736b00e1..569256152689f8 100644 --- a/drivers/net/phy/aquantia/aquantia_firmware.c +++ b/drivers/net/phy/aquantia/aquantia_firmware.c @@ -369,7 +369,7 @@ int aqr_firmware_load(struct phy_device *phydev) * assume that, and load a new image. */ ret = aqr_firmware_load_nvmem(phydev); - if (!ret) + if (ret == -EPROBE_DEFER || !ret) return ret; ret = aqr_firmware_load_fs(phydev); diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c index 9766dd99afaa0a..12ff4c1f285d24 100644 --- a/drivers/net/phy/intel-xway.c +++ b/drivers/net/phy/intel-xway.c @@ -277,7 +277,7 @@ static int xway_gphy_init_leds(struct phy_device *phydev) static int xway_gphy_config_init(struct phy_device *phydev) { - struct device_node *np = phydev->mdio.dev.of_node; + struct device_node *np; int err; /* Mask all interrupts */ @@ -286,7 +286,10 @@ static int xway_gphy_config_init(struct phy_device *phydev) return err; /* Use default LED configuration if 'leds' node isn't defined */ - if (!of_get_child_by_name(np, "leds")) + np = of_get_child_by_name(phydev->mdio.dev.of_node, "leds"); + if (np) + of_node_put(np); + else xway_gphy_init_leds(phydev); /* Clear all pending interrupts */ diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c index f3d83b04c9535c..201dee1a16985e 100644 --- a/drivers/net/phy/marvell-88q2xxx.c +++ b/drivers/net/phy/marvell-88q2xxx.c @@ -698,7 +698,7 @@ static int mv88q2xxx_hwmon_write(struct device *dev, switch (attr) { case hwmon_temp_max: - clamp_val(val, -75000, 180000); + val = clamp(val, -75000, 180000); val = (val / 1000) + 75; val = FIELD_PREP(MDIO_MMD_PCS_MV_TEMP_SENSOR3_INT_THRESH_MASK, val); diff --git a/drivers/net/phy/mediatek/mtk-ge-soc.c b/drivers/net/phy/mediatek/mtk-ge-soc.c index cd09fbf92ef23a..2c4bbc236202b7 100644 --- a/drivers/net/phy/mediatek/mtk-ge-soc.c +++ b/drivers/net/phy/mediatek/mtk-ge-soc.c @@ -1167,9 +1167,9 @@ static int mt798x_phy_calibration(struct phy_device *phydev) } buf = (u32 *)nvmem_cell_read(cell, &len); + nvmem_cell_put(cell); if (IS_ERR(buf)) return PTR_ERR(buf); - nvmem_cell_put(cell); if (!buf[0] || !buf[1] || !buf[2] || !buf[3] || len < 4 * sizeof(u32)) { phydev_err(phydev, "invalid efuse data\n"); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 01c87c9b77020e..bc19880107ae42 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -2541,11 +2541,21 @@ static int kszphy_probe(struct phy_device *phydev) kszphy_parse_led_mode(phydev); - clk = devm_clk_get_optional_enabled(&phydev->mdio.dev, "rmii-ref"); + clk = devm_clk_get_optional(&phydev->mdio.dev, "rmii-ref"); /* NOTE: clk may be NULL if building without CONFIG_HAVE_CLK */ if (!IS_ERR_OR_NULL(clk)) { - unsigned long rate = clk_get_rate(clk); bool rmii_ref_clk_sel_25_mhz; + unsigned long rate; + int err; + + err = clk_prepare_enable(clk); + if (err) { + phydev_err(phydev, "Failed to enable rmii-ref clock\n"); + return err; + } + + rate = clk_get_rate(clk); + clk_disable_unprepare(clk); if (type) priv->rmii_ref_clk_sel = type->has_rmii_ref_clk_sel; @@ -2563,13 +2573,12 @@ static int kszphy_probe(struct phy_device *phydev) } } else if (!clk) { /* unnamed clock from the generic ethernet-phy binding */ - clk = devm_clk_get_optional_enabled(&phydev->mdio.dev, NULL); + clk = devm_clk_get_optional(&phydev->mdio.dev, NULL); } if (IS_ERR(clk)) return PTR_ERR(clk); - clk_disable_unprepare(clk); priv->clk = clk; if (ksz8041_fiber_mode(phydev)) diff --git a/drivers/net/phy/motorcomm.c b/drivers/net/phy/motorcomm.c index a3593e66305941..b49897500a5925 100644 --- a/drivers/net/phy/motorcomm.c +++ b/drivers/net/phy/motorcomm.c @@ -1741,10 +1741,10 @@ static int yt8521_led_hw_control_set(struct phy_device *phydev, u8 index, val |= YT8521_LED_1000_ON_EN; if (test_bit(TRIGGER_NETDEV_FULL_DUPLEX, &rules)) - val |= YT8521_LED_HDX_ON_EN; + val |= YT8521_LED_FDX_ON_EN; if (test_bit(TRIGGER_NETDEV_HALF_DUPLEX, &rules)) - val |= YT8521_LED_FDX_ON_EN; + val |= YT8521_LED_HDX_ON_EN; if (test_bit(TRIGGER_NETDEV_TX, &rules) || test_bit(TRIGGER_NETDEV_RX, &rules)) diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index ef0ef1570d3923..48d43f60b8ff8c 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -2625,7 +2625,7 @@ static struct phy_driver vsc85xx_driver[] = { .suspend = &genphy_suspend, .resume = &genphy_resume, .remove = &vsc85xx_remove, - .probe = &vsc8574_probe, + .probe = &vsc8584_probe, .set_wol = &vsc85xx_wol_set, .get_wol = &vsc85xx_wol_get, .get_tunable = &vsc85xx_get_tunable, @@ -2648,12 +2648,12 @@ static struct phy_driver vsc85xx_driver[] = { .config_aneg = &vsc85xx_config_aneg, .aneg_done = &genphy_aneg_done, .read_status = &vsc85xx_read_status, - .handle_interrupt = vsc85xx_handle_interrupt, + .handle_interrupt = vsc8584_handle_interrupt, .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, .remove = &vsc85xx_remove, - .probe = &vsc8574_probe, + .probe = &vsc8584_probe, .set_wol = &vsc85xx_wol_set, .get_wol = &vsc85xx_wol_get, .get_tunable = &vsc85xx_get_tunable, diff --git a/drivers/net/phy/mxl-86110.c b/drivers/net/phy/mxl-86110.c index e5d137a37a1d44..42a5fe3f115f42 100644 --- a/drivers/net/phy/mxl-86110.c +++ b/drivers/net/phy/mxl-86110.c @@ -938,6 +938,9 @@ static struct phy_driver mxl_phy_drvs[] = { PHY_ID_MATCH_EXACT(PHY_ID_MXL86110), .name = "MXL86110 Gigabit Ethernet", .config_init = mxl86110_config_init, + .suspend = genphy_suspend, + .resume = genphy_resume, + .soft_reset = genphy_soft_reset, .get_wol = mxl86110_get_wol, .set_wol = mxl86110_set_wol, .led_brightness_set = mxl86110_led_brightness_set, diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 605ca20ae192d7..0c63e6ba2cb0cd 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -101,6 +101,49 @@ const char *phy_rate_matching_to_str(int rate_matching) } EXPORT_SYMBOL_GPL(phy_rate_matching_to_str); +/** + * phy_fix_phy_mode_for_mac_delays - Convenience function for fixing PHY + * mode based on whether mac adds internal delay + * + * @interface: The current interface mode of the port + * @mac_txid: True if the mac adds internal tx delay + * @mac_rxid: True if the mac adds internal rx delay + * + * Return: fixed PHY mode, or PHY_INTERFACE_MODE_NA if the interface can + * not apply the internal delay + */ +phy_interface_t phy_fix_phy_mode_for_mac_delays(phy_interface_t interface, + bool mac_txid, bool mac_rxid) +{ + if (!phy_interface_mode_is_rgmii(interface)) + return interface; + + if (mac_txid && mac_rxid) { + if (interface == PHY_INTERFACE_MODE_RGMII_ID) + return PHY_INTERFACE_MODE_RGMII; + return PHY_INTERFACE_MODE_NA; + } + + if (mac_txid) { + if (interface == PHY_INTERFACE_MODE_RGMII_ID) + return PHY_INTERFACE_MODE_RGMII_RXID; + if (interface == PHY_INTERFACE_MODE_RGMII_TXID) + return PHY_INTERFACE_MODE_RGMII; + return PHY_INTERFACE_MODE_NA; + } + + if (mac_rxid) { + if (interface == PHY_INTERFACE_MODE_RGMII_ID) + return PHY_INTERFACE_MODE_RGMII_TXID; + if (interface == PHY_INTERFACE_MODE_RGMII_RXID) + return PHY_INTERFACE_MODE_RGMII; + return PHY_INTERFACE_MODE_NA; + } + + return interface; +} +EXPORT_SYMBOL_GPL(phy_fix_phy_mode_for_mac_delays); + /** * phy_interface_num_ports - Return the number of links that can be carried by * a given MAC-PHY physical link. Returns 0 if this is diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c index 16a347084293ef..7c3d277efaf07a 100644 --- a/drivers/net/phy/realtek/realtek_main.c +++ b/drivers/net/phy/realtek/realtek_main.c @@ -89,6 +89,14 @@ #define RTL8211F_LEDCR_MASK GENMASK(4, 0) #define RTL8211F_LEDCR_SHIFT 5 +/* RTL8211F(D)(I)-VD-CG CLKOUT configuration is specified via magic values + * to undocumented register pages. The names here do not reflect the datasheet. + * Unlike other PHY models, CLKOUT configuration does not go through PHYCR2. + */ +#define RTL8211FVD_CLKOUT_PAGE 0xd05 +#define RTL8211FVD_CLKOUT_REG 0x11 +#define RTL8211FVD_CLKOUT_EN BIT(8) + /* RTL8211F RGMII configuration */ #define RTL8211F_RGMII_PAGE 0xd08 @@ -166,9 +174,8 @@ MODULE_AUTHOR("Johnson Leung"); MODULE_LICENSE("GPL"); struct rtl821x_priv { - u16 phycr1; - u16 phycr2; - bool has_phycr2; + bool enable_aldps; + bool disable_clk_out; struct clk *clk; /* rtl8211f */ u16 iner; @@ -218,8 +225,6 @@ static int rtl821x_probe(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; struct rtl821x_priv *priv; - u32 phy_id = phydev->drv->phy_id; - int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -230,24 +235,10 @@ static int rtl821x_probe(struct phy_device *phydev) return dev_err_probe(dev, PTR_ERR(priv->clk), "failed to get phy clock\n"); - ret = phy_read_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR1); - if (ret < 0) - return ret; - - priv->phycr1 = ret & (RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_XTAL_OFF); - if (of_property_read_bool(dev->of_node, "realtek,aldps-enable")) - priv->phycr1 |= RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_XTAL_OFF; - - priv->has_phycr2 = !(phy_id == RTL_8211FVD_PHYID); - if (priv->has_phycr2) { - ret = phy_read_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR2); - if (ret < 0) - return ret; - - priv->phycr2 = ret & RTL8211F_CLKOUT_EN; - if (of_property_read_bool(dev->of_node, "realtek,clkout-disable")) - priv->phycr2 &= ~RTL8211F_CLKOUT_EN; - } + priv->enable_aldps = of_property_read_bool(dev->of_node, + "realtek,aldps-enable"); + priv->disable_clk_out = of_property_read_bool(dev->of_node, + "realtek,clkout-disable"); phydev->priv = priv; @@ -560,22 +551,11 @@ static int rtl8211c_config_init(struct phy_device *phydev) CTL1000_ENABLE_MASTER | CTL1000_AS_MASTER); } -static int rtl8211f_config_init(struct phy_device *phydev) +static int rtl8211f_config_rgmii_delay(struct phy_device *phydev) { - struct rtl821x_priv *priv = phydev->priv; - struct device *dev = &phydev->mdio.dev; u16 val_txdly, val_rxdly; int ret; - ret = phy_modify_paged_changed(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR1, - RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_XTAL_OFF, - priv->phycr1); - if (ret < 0) { - dev_err(dev, "aldps mode configuration failed: %pe\n", - ERR_PTR(ret)); - return ret; - } - switch (phydev->interface) { case PHY_INTERFACE_MODE_RGMII: val_txdly = 0; @@ -605,53 +585,114 @@ static int rtl8211f_config_init(struct phy_device *phydev) RTL8211F_TXCR, RTL8211F_TX_DELAY, val_txdly); if (ret < 0) { - dev_err(dev, "Failed to update the TX delay register\n"); + phydev_err(phydev, "Failed to update the TX delay register: %pe\n", + ERR_PTR(ret)); return ret; } else if (ret) { - dev_dbg(dev, - "%s 2ns TX delay (and changing the value from pin-strapping RXD1 or the bootloader)\n", - str_enable_disable(val_txdly)); + phydev_dbg(phydev, + "%s 2ns TX delay (and changing the value from pin-strapping RXD1 or the bootloader)\n", + str_enable_disable(val_txdly)); } else { - dev_dbg(dev, - "2ns TX delay was already %s (by pin-strapping RXD1 or bootloader configuration)\n", - str_enabled_disabled(val_txdly)); + phydev_dbg(phydev, + "2ns TX delay was already %s (by pin-strapping RXD1 or bootloader configuration)\n", + str_enabled_disabled(val_txdly)); } ret = phy_modify_paged_changed(phydev, RTL8211F_RGMII_PAGE, RTL8211F_RXCR, RTL8211F_RX_DELAY, val_rxdly); if (ret < 0) { - dev_err(dev, "Failed to update the RX delay register\n"); + phydev_err(phydev, "Failed to update the RX delay register: %pe\n", + ERR_PTR(ret)); return ret; } else if (ret) { - dev_dbg(dev, - "%s 2ns RX delay (and changing the value from pin-strapping RXD0 or the bootloader)\n", - str_enable_disable(val_rxdly)); + phydev_dbg(phydev, + "%s 2ns RX delay (and changing the value from pin-strapping RXD0 or the bootloader)\n", + str_enable_disable(val_rxdly)); } else { - dev_dbg(dev, - "2ns RX delay was already %s (by pin-strapping RXD0 or bootloader configuration)\n", - str_enabled_disabled(val_rxdly)); + phydev_dbg(phydev, + "2ns RX delay was already %s (by pin-strapping RXD0 or bootloader configuration)\n", + str_enabled_disabled(val_rxdly)); } - if (!priv->has_phycr2) + return 0; +} + +static int rtl8211f_config_clk_out(struct phy_device *phydev) +{ + struct rtl821x_priv *priv = phydev->priv; + int ret; + + /* The value is preserved if the device tree property is absent */ + if (!priv->disable_clk_out) + return 0; + + if (phydev->drv->phy_id == RTL_8211FVD_PHYID) + ret = phy_modify_paged(phydev, RTL8211FVD_CLKOUT_PAGE, + RTL8211FVD_CLKOUT_REG, + RTL8211FVD_CLKOUT_EN, 0); + else + ret = phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, + RTL8211F_PHYCR2, RTL8211F_CLKOUT_EN, 0); + if (ret) + return ret; + + return genphy_soft_reset(phydev); +} + +/* Advance Link Down Power Saving (ALDPS) mode changes crystal/clock behaviour, + * which causes the RXC clock signal to stop for tens to hundreds of + * milliseconds. + * + * Some MACs need the RXC clock to support their internal RX logic, so ALDPS is + * only enabled based on an opt-in device tree property. + */ +static int rtl8211f_config_aldps(struct phy_device *phydev) +{ + struct rtl821x_priv *priv = phydev->priv; + u16 mask = RTL8211F_ALDPS_PLL_OFF | + RTL8211F_ALDPS_ENABLE | + RTL8211F_ALDPS_XTAL_OFF; + + /* The value is preserved if the device tree property is absent */ + if (!priv->enable_aldps) return 0; + return phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR1, + mask, mask); +} + +static int rtl8211f_config_phy_eee(struct phy_device *phydev) +{ /* Disable PHY-mode EEE so LPI is passed to the MAC */ - ret = phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR2, - RTL8211F_PHYCR2_PHY_EEE_ENABLE, 0); + return phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR2, + RTL8211F_PHYCR2_PHY_EEE_ENABLE, 0); +} + +static int rtl8211f_config_init(struct phy_device *phydev) +{ + struct device *dev = &phydev->mdio.dev; + int ret; + + ret = rtl8211f_config_aldps(phydev); + if (ret) { + dev_err(dev, "aldps mode configuration failed: %pe\n", + ERR_PTR(ret)); + return ret; + } + + ret = rtl8211f_config_rgmii_delay(phydev); if (ret) return ret; - ret = phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, - RTL8211F_PHYCR2, RTL8211F_CLKOUT_EN, - priv->phycr2); - if (ret < 0) { + ret = rtl8211f_config_clk_out(phydev); + if (ret) { dev_err(dev, "clkout configuration failed: %pe\n", ERR_PTR(ret)); return ret; } - return genphy_soft_reset(phydev); + return rtl8211f_config_phy_eee(phydev); } static int rtl821x_suspend(struct phy_device *phydev) diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 0401fa6b24d257..3e023723887c4b 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -479,6 +479,8 @@ static void sfp_quirk_ubnt_uf_instant(const struct sfp_eeprom_id *id, linkmode_zero(caps->link_modes); linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, caps->link_modes); + phy_interface_zero(caps->interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, caps->interfaces); } #define SFP_QUIRK(_v, _p, _s, _f) \ @@ -497,6 +499,8 @@ static const struct sfp_quirk sfp_quirks[] = { SFP_QUIRK("ALCATELLUCENT", "3FE46541AA", sfp_quirk_2500basex, sfp_fixup_nokia), + SFP_QUIRK_F("BIDB", "X-ONU-SFPP", sfp_fixup_potron), + // FLYPRO SFP-10GT-CS-30M uses Rollball protocol to talk to the PHY. SFP_QUIRK_F("FLYPRO", "SFP-10GT-CS-30M", sfp_fixup_rollball), @@ -517,6 +521,8 @@ static const struct sfp_quirk sfp_quirks[] = { SFP_QUIRK_F("HALNy", "HL-GSFP", sfp_fixup_halny_gsfp), + SFP_QUIRK_F("H-COM", "SPP425H-GAB4", sfp_fixup_potron), + // HG MXPD-483II-F 2.5G supports 2500Base-X, but incorrectly reports // 2600MBd in their EERPOM SFP_QUIRK_S("HG GENUINE", "MXPD-483II", sfp_quirk_2500basex), @@ -763,7 +769,7 @@ static int sfp_smbus_byte_write(struct sfp *sfp, bool a2, u8 dev_addr, dev_addr++; } - return 0; + return data - (u8 *)buf; } static int sfp_i2c_configure(struct sfp *sfp, struct i2c_adapter *i2c) diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index 25562b17debe1b..2fd3469d10464e 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -878,7 +878,7 @@ static void __team_queue_override_enabled_check(struct team *team) static void team_queue_override_port_prio_changed(struct team *team, struct team_port *port) { - if (!port->queue_id || team_port_enabled(port)) + if (!port->queue_id || !team_port_enabled(port)) return; __team_queue_override_port_del(team, port); __team_queue_override_port_add(team, port); diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index 7fd763917ae2cf..6ab3486072cb0f 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -335,6 +335,11 @@ int asix_read_phy_addr(struct usbnet *dev, bool internal) offset = (internal ? 1 : 0); ret = buf[offset]; + if (ret >= PHY_MAX_ADDR) { + netdev_err(dev->net, "invalid PHY address: %d\n", ret); + return -ENODEV; + } + netdev_dbg(dev->net, "%s PHY address 0x%x\n", internal ? "internal" : "external", ret); diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index f613e4bc68c851..758a423a459b80 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -210,11 +210,7 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf) ret = asix_read_phy_addr(dev, priv->use_embdphy); if (ret < 0) goto free; - if (ret >= PHY_MAX_ADDR) { - netdev_err(dev->net, "Invalid PHY address %#x\n", ret); - ret = -ENODEV; - goto free; - } + priv->phy_addr = ret; ax88172a_reset_phy(dev, priv->use_embdphy); diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index 6759388692f8e9..3c824340ffb068 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -64,6 +64,16 @@ static const char driver_name[] = "catc"; #define CTRL_QUEUE 16 /* Max control requests in flight (power of two) */ #define RX_PKT_SZ 1600 /* Max size of receive packet for F5U011 */ +/* + * USB endpoints. + */ + +enum catc_usb_ep { + CATC_USB_EP_CONTROL = 0, + CATC_USB_EP_BULK = 1, + CATC_USB_EP_INT_IN = 2, +}; + /* * Control requests. */ @@ -772,6 +782,13 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id u8 broadcast[ETH_ALEN]; u8 *macbuf; int pktsz, ret = -ENOMEM; + static const u8 bulk_ep_addr[] = { + CATC_USB_EP_BULK | USB_DIR_OUT, + CATC_USB_EP_BULK | USB_DIR_IN, + 0}; + static const u8 int_ep_addr[] = { + CATC_USB_EP_INT_IN | USB_DIR_IN, + 0}; macbuf = kmalloc(ETH_ALEN, GFP_KERNEL); if (!macbuf) @@ -784,6 +801,14 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id goto fail_mem; } + /* Verify that all required endpoints are present */ + if (!usb_check_bulk_endpoints(intf, bulk_ep_addr) || + !usb_check_int_endpoints(intf, int_ep_addr)) { + dev_err(dev, "Missing or invalid endpoints\n"); + ret = -ENODEV; + goto fail_mem; + } + netdev = alloc_etherdev(sizeof(struct catc)); if (!netdev) goto fail_mem; @@ -828,14 +853,14 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id usb_fill_control_urb(catc->ctrl_urb, usbdev, usb_sndctrlpipe(usbdev, 0), NULL, NULL, 0, catc_ctrl_done, catc); - usb_fill_bulk_urb(catc->tx_urb, usbdev, usb_sndbulkpipe(usbdev, 1), - NULL, 0, catc_tx_done, catc); + usb_fill_bulk_urb(catc->tx_urb, usbdev, usb_sndbulkpipe(usbdev, CATC_USB_EP_BULK), + NULL, 0, catc_tx_done, catc); - usb_fill_bulk_urb(catc->rx_urb, usbdev, usb_rcvbulkpipe(usbdev, 1), - catc->rx_buf, pktsz, catc_rx_done, catc); + usb_fill_bulk_urb(catc->rx_urb, usbdev, usb_rcvbulkpipe(usbdev, CATC_USB_EP_BULK), + catc->rx_buf, pktsz, catc_rx_done, catc); - usb_fill_int_urb(catc->irq_urb, usbdev, usb_rcvintpipe(usbdev, 2), - catc->irq_buf, 2, catc_irq_done, catc, 1); + usb_fill_int_urb(catc->irq_urb, usbdev, usb_rcvintpipe(usbdev, CATC_USB_EP_INT_IN), + catc->irq_buf, 2, catc_irq_done, catc, 1); if (!catc->is_f5u011) { u32 *buf; diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 8b6d6a1b3c2eca..2b4716ccf0c5ba 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -603,10 +603,6 @@ static const struct usb_device_id products[] = { USB_DEVICE(0x0fe6, 0x8101), /* DM9601 USB to Fast Ethernet Adapter */ .driver_info = (unsigned long)&dm9601_info, }, - { - USB_DEVICE(0x0fe6, 0x9700), /* DM9601 USB to Fast Ethernet Adapter */ - .driver_info = (unsigned long)&dm9601_info, - }, { USB_DEVICE(0x0a46, 0x9000), /* DM9000E */ .driver_info = (unsigned long)&dm9601_info, diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 81ca64debc5b94..c514483134f05f 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -168,6 +168,8 @@ static int update_eth_regs_async(pegasus_t *pegasus) netif_device_detach(pegasus->net); netif_err(pegasus, drv, pegasus->net, "%s returned %d\n", __func__, ret); + usb_free_urb(async_urb); + kfree(req); } return ret; } diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index a22d4bb2cf3b58..6a43054d5171fe 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -8535,19 +8535,6 @@ static int rtl8152_system_resume(struct r8152 *tp) usb_submit_urb(tp->intr_urb, GFP_NOIO); } - /* If the device is RTL8152_INACCESSIBLE here then we should do a - * reset. This is important because the usb_lock_device_for_reset() - * that happens as a result of usb_queue_reset_device() will silently - * fail if the device was suspended or if too much time passed. - * - * NOTE: The device is locked here so we can directly do the reset. - * We don't need usb_lock_device_for_reset() because that's just a - * wrapper over device_lock() and device_resume() (which calls us) - * does that for us. - */ - if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) - usb_reset_device(tp->udev); - return 0; } @@ -8658,19 +8645,33 @@ static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message) static int rtl8152_resume(struct usb_interface *intf) { struct r8152 *tp = usb_get_intfdata(intf); + bool runtime_resume = test_bit(SELECTIVE_SUSPEND, &tp->flags); int ret; mutex_lock(&tp->control); rtl_reset_ocp_base(tp); - if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) + if (runtime_resume) ret = rtl8152_runtime_resume(tp); else ret = rtl8152_system_resume(tp); mutex_unlock(&tp->control); + /* If the device is RTL8152_INACCESSIBLE here then we should do a + * reset. This is important because the usb_lock_device_for_reset() + * that happens as a result of usb_queue_reset_device() will silently + * fail if the device was suspended or if too much time passed. + * + * NOTE: The device is locked here so we can directly do the reset. + * We don't need usb_lock_device_for_reset() because that's just a + * wrapper over device_lock() and device_resume() (which calls us) + * does that for us. + */ + if (!runtime_resume && test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + usb_reset_device(tp->udev); + return ret; } diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 278e6cb6f4d99a..e40b0669d9f4ba 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -211,6 +211,8 @@ static int async_set_registers(rtl8150_t *dev, u16 indx, u16 size, u16 reg) if (res == -ENODEV) netif_device_detach(dev->netdev); dev_err(&dev->udev->dev, "%s failed with %d\n", __func__, res); + kfree(req); + usb_free_urb(async_urb); } return res; } diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 091bc2aca7e8e7..820c4c50697921 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -52,7 +52,7 @@ static int sr_read_reg(struct usbnet *dev, u8 reg, u8 *value) static int sr_write_reg(struct usbnet *dev, u8 reg, u8 value) { - return usbnet_write_cmd(dev, SR_WR_REGS, SR_REQ_WR_REG, + return usbnet_write_cmd(dev, SR_WR_REG, SR_REQ_WR_REG, value, reg, NULL, 0); } @@ -65,7 +65,7 @@ static void sr_write_async(struct usbnet *dev, u8 reg, u16 length, static void sr_write_reg_async(struct usbnet *dev, u8 reg, u8 value) { - usbnet_write_cmd_async(dev, SR_WR_REGS, SR_REQ_WR_REG, + usbnet_write_cmd_async(dev, SR_WR_REG, SR_REQ_WR_REG, value, reg, NULL, 0); } @@ -539,6 +539,11 @@ static const struct usb_device_id products[] = { USB_DEVICE(0x0fe6, 0x9700), /* SR9700 device */ .driver_info = (unsigned long)&sr9700_driver_info, }, + { + /* SR9700 with virtual driver CD-ROM - interface 0 is the CD-ROM device */ + USB_DEVICE_INTERFACE_NUMBER(0x0fe6, 0x9702, 1), + .driver_info = (unsigned long)&sr9700_driver_info, + }, {}, /* END */ }; diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 697cd9d866d3d0..ab5ded8f38cf8a 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1803,9 +1803,12 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) if ((dev->driver_info->flags & FLAG_NOARP) != 0) net->flags |= IFF_NOARP; - /* maybe the remote can't receive an Ethernet MTU */ - if (net->mtu > (dev->hard_mtu - net->hard_header_len)) - net->mtu = dev->hard_mtu - net->hard_header_len; + if (net->max_mtu > (dev->hard_mtu - net->hard_header_len)) + net->max_mtu = dev->hard_mtu - net->hard_header_len; + + if (net->mtu > net->max_mtu) + net->mtu = net->max_mtu; + } else if (!info->in || !info->out) status = usbnet_get_endpoints (dev, udev); else { diff --git a/drivers/net/veth.c b/drivers/net/veth.c index cc502bf022d55c..b00613cb07cf07 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -228,16 +228,20 @@ static void veth_get_ethtool_stats(struct net_device *dev, const struct veth_rq_stats *rq_stats = &rcv_priv->rq[i].stats; const void *base = (void *)&rq_stats->vs; unsigned int start, tx_idx = idx; + u64 buf[VETH_TQ_STATS_LEN]; size_t offset; - tx_idx += (i % dev->real_num_tx_queues) * VETH_TQ_STATS_LEN; do { start = u64_stats_fetch_begin(&rq_stats->syncp); for (j = 0; j < VETH_TQ_STATS_LEN; j++) { offset = veth_tq_stats_desc[j].offset; - data[tx_idx + j] += *(u64 *)(base + offset); + buf[j] = *(u64 *)(base + offset); } } while (u64_stats_fetch_retry(&rq_stats->syncp, start)); + + tx_idx += (i % dev->real_num_tx_queues) * VETH_TQ_STATS_LEN; + for (j = 0; j < VETH_TQ_STATS_LEN; j++) + data[tx_idx + j] += buf[j]; } pp_idx = idx + dev->real_num_tx_queues * VETH_TQ_STATS_LEN; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 8e04adb57f52ad..b67dbe346c8070 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -425,9 +425,6 @@ struct virtnet_info { u16 rss_indir_table_size; u32 rss_hash_types_supported; u32 rss_hash_types_saved; - struct virtio_net_rss_config_hdr *rss_hdr; - struct virtio_net_rss_config_trailer rss_trailer; - u8 rss_hash_key_data[VIRTIO_NET_RSS_MAX_KEY_SIZE]; /* Has control virtqueue */ bool has_cvq; @@ -493,7 +490,16 @@ struct virtnet_info { struct failover *failover; u64 device_stats_cap; + + struct virtio_net_rss_config_hdr *rss_hdr; + + /* Must be last as it ends in a flexible-array member. */ + TRAILING_OVERLAP(struct virtio_net_rss_config_trailer, rss_trailer, hash_key_data, + u8 rss_hash_key_data[VIRTIO_NET_RSS_MAX_KEY_SIZE]; + ); }; +static_assert(offsetof(struct virtnet_info, rss_trailer.hash_key_data) == + offsetof(struct virtnet_info, rss_hash_key_data)); struct padded_vnet_hdr { struct virtio_net_hdr_v1_hash hdr; @@ -3031,16 +3037,16 @@ static int virtnet_receive(struct receive_queue *rq, int budget, else packets = virtnet_receive_packets(vi, rq, budget, xdp_xmit, &stats); + u64_stats_set(&stats.packets, packets); if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) { - if (!try_fill_recv(vi, rq, GFP_ATOMIC)) { - spin_lock(&vi->refill_lock); - if (vi->refill_enabled) - schedule_delayed_work(&vi->refill, 0); - spin_unlock(&vi->refill_lock); - } + if (!try_fill_recv(vi, rq, GFP_ATOMIC)) + /* We need to retry refilling in the next NAPI poll so + * we must return budget to make sure the NAPI is + * repolled. + */ + packets = budget; } - u64_stats_set(&stats.packets, packets); u64_stats_update_begin(&rq->stats.syncp); for (i = 0; i < ARRAY_SIZE(virtnet_rq_stats_desc); i++) { size_t offset = virtnet_rq_stats_desc[i].offset; @@ -3220,9 +3226,10 @@ static int virtnet_open(struct net_device *dev) for (i = 0; i < vi->max_queue_pairs; i++) { if (i < vi->curr_queue_pairs) - /* Make sure we have some buffers: if oom use wq. */ - if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL)) - schedule_delayed_work(&vi->refill, 0); + /* Pre-fill rq agressively, to make sure we are ready to + * get packets immediately. + */ + try_fill_recv(vi, &vi->rq[i], GFP_KERNEL); err = virtnet_enable_queue_pair(vi, i); if (err < 0) @@ -3467,16 +3474,15 @@ static void __virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq, bool refill) { - bool running = netif_running(vi->dev); - bool schedule_refill = false; + if (netif_running(vi->dev)) { + /* Pre-fill rq agressively, to make sure we are ready to get + * packets immediately. + */ + if (refill) + try_fill_recv(vi, rq, GFP_KERNEL); - if (refill && !try_fill_recv(vi, rq, GFP_KERNEL)) - schedule_refill = true; - if (running) virtnet_napi_enable(rq); - - if (schedule_refill) - schedule_delayed_work(&vi->refill, 0); + } } static void virtnet_rx_resume_all(struct virtnet_info *vi) @@ -3783,7 +3789,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) if (vi->has_rss && !netif_is_rxfh_configured(dev)) { old_rss_hdr = vi->rss_hdr; old_rss_trailer = vi->rss_trailer; - vi->rss_hdr = devm_kzalloc(&dev->dev, virtnet_rss_hdr_size(vi), GFP_KERNEL); + vi->rss_hdr = devm_kzalloc(&vi->vdev->dev, virtnet_rss_hdr_size(vi), GFP_KERNEL); if (!vi->rss_hdr) { vi->rss_hdr = old_rss_hdr; return -ENOMEM; @@ -3794,7 +3800,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) if (!virtnet_commit_rss_command(vi)) { /* restore ctrl_rss if commit_rss_command failed */ - devm_kfree(&dev->dev, vi->rss_hdr); + devm_kfree(&vi->vdev->dev, vi->rss_hdr); vi->rss_hdr = old_rss_hdr; vi->rss_trailer = old_rss_trailer; @@ -3802,7 +3808,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) queue_pairs); return -EINVAL; } - devm_kfree(&dev->dev, old_rss_hdr); + devm_kfree(&vi->vdev->dev, old_rss_hdr); goto succ; } @@ -3821,11 +3827,12 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) } succ: vi->curr_queue_pairs = queue_pairs; - /* virtnet_open() will refill when device is going to up. */ - spin_lock_bh(&vi->refill_lock); - if (dev->flags & IFF_UP && vi->refill_enabled) - schedule_delayed_work(&vi->refill, 0); - spin_unlock_bh(&vi->refill_lock); + if (dev->flags & IFF_UP) { + local_bh_disable(); + for (int i = 0; i < vi->curr_queue_pairs; ++i) + virtqueue_napi_schedule(&vi->rq[i].napi, vi->rq[i].vq); + local_bh_enable(); + } return 0; } diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index a5c55e7e4d795f..e957aa12a8a44a 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2349,7 +2349,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, int addr_family; __u8 tos, ttl; int ifindex; - int err; + int err = 0; u32 flags = vxlan->cfg.flags; bool use_cache; bool udp_sum = false; @@ -2454,12 +2454,18 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, rcu_read_lock(); if (addr_family == AF_INET) { - struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); + struct vxlan_sock *sock4; u16 ipcb_flags = 0; struct rtable *rt; __be16 df = 0; __be32 saddr; + sock4 = rcu_dereference(vxlan->vn4_sock); + if (unlikely(!sock4)) { + reason = SKB_DROP_REASON_DEV_READY; + goto tx_error; + } + if (!ifindex) ifindex = sock4->sock->sk->sk_bound_dev_if; @@ -2534,10 +2540,16 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ipcb_flags); #if IS_ENABLED(CONFIG_IPV6) } else { - struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); + struct vxlan_sock *sock6; struct in6_addr saddr; u16 ip6cb_flags = 0; + sock6 = rcu_dereference(vxlan->vn6_sock); + if (unlikely(!sock6)) { + reason = SKB_DROP_REASON_DEV_READY; + goto tx_error; + } + if (!ifindex) ifindex = sock6->sock->sk->sk_bound_dev_if; diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c index 7bbda46cfd93c3..82f120ee1c66d5 100644 --- a/drivers/net/wireless/ath/ath10k/ce.c +++ b/drivers/net/wireless/ath/ath10k/ce.c @@ -1727,8 +1727,8 @@ static void _ath10k_ce_free_pipe(struct ath10k *ar, int ce_id) (ce_state->src_ring->nentries * sizeof(struct ce_desc) + CE_DESC_RING_ALIGN), - ce_state->src_ring->base_addr_owner_space, - ce_state->src_ring->base_addr_ce_space); + ce_state->src_ring->base_addr_owner_space_unaligned, + ce_state->src_ring->base_addr_ce_space_unaligned); kfree(ce_state->src_ring); } @@ -1737,8 +1737,8 @@ static void _ath10k_ce_free_pipe(struct ath10k *ar, int ce_id) (ce_state->dest_ring->nentries * sizeof(struct ce_desc) + CE_DESC_RING_ALIGN), - ce_state->dest_ring->base_addr_owner_space, - ce_state->dest_ring->base_addr_ce_space); + ce_state->dest_ring->base_addr_owner_space_unaligned, + ce_state->dest_ring->base_addr_ce_space_unaligned); kfree(ce_state->dest_ring); } @@ -1758,8 +1758,8 @@ static void _ath10k_ce_free_pipe_64(struct ath10k *ar, int ce_id) (ce_state->src_ring->nentries * sizeof(struct ce_desc_64) + CE_DESC_RING_ALIGN), - ce_state->src_ring->base_addr_owner_space, - ce_state->src_ring->base_addr_ce_space); + ce_state->src_ring->base_addr_owner_space_unaligned, + ce_state->src_ring->base_addr_ce_space_unaligned); kfree(ce_state->src_ring); } @@ -1768,8 +1768,8 @@ static void _ath10k_ce_free_pipe_64(struct ath10k *ar, int ce_id) (ce_state->dest_ring->nentries * sizeof(struct ce_desc_64) + CE_DESC_RING_ALIGN), - ce_state->dest_ring->base_addr_owner_space, - ce_state->dest_ring->base_addr_ce_space); + ce_state->dest_ring->base_addr_owner_space_unaligned, + ce_state->dest_ring->base_addr_ce_space_unaligned); kfree(ce_state->dest_ring); } diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index 6f78f1752cd6ff..9ae3595fb6986d 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -3,7 +3,6 @@ * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ @@ -2493,8 +2492,9 @@ static int ath10k_init_hw_params(struct ath10k *ar) return 0; } -static bool ath10k_core_needs_recovery(struct ath10k *ar) +static void ath10k_core_recovery_check_work(struct work_struct *work) { + struct ath10k *ar = container_of(work, struct ath10k, recovery_check_work); long time_left; /* Sometimes the recovery will fail and then the next all recovery fail, @@ -2504,7 +2504,7 @@ static bool ath10k_core_needs_recovery(struct ath10k *ar) ath10k_err(ar, "consecutive fail %d times, will shutdown driver!", atomic_read(&ar->fail_cont_count)); ar->state = ATH10K_STATE_WEDGED; - return false; + return; } ath10k_dbg(ar, ATH10K_DBG_BOOT, "total recovery count: %d", ++ar->recovery_count); @@ -2518,27 +2518,24 @@ static bool ath10k_core_needs_recovery(struct ath10k *ar) ATH10K_RECOVERY_TIMEOUT_HZ); if (time_left) { ath10k_warn(ar, "previous recovery succeeded, skip this!\n"); - return false; + return; } /* Record the continuous recovery fail count when recovery failed. */ atomic_inc(&ar->fail_cont_count); /* Avoid having multiple recoveries at the same time. */ - return false; + return; } atomic_inc(&ar->pending_recovery); - - return true; + queue_work(ar->workqueue, &ar->restart_work); } void ath10k_core_start_recovery(struct ath10k *ar) { - if (!ath10k_core_needs_recovery(ar)) - return; - - queue_work(ar->workqueue, &ar->restart_work); + /* Use workqueue_aux to avoid blocking recovery tracking */ + queue_work(ar->workqueue_aux, &ar->recovery_check_work); } EXPORT_SYMBOL(ath10k_core_start_recovery); @@ -3734,6 +3731,7 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev, INIT_WORK(&ar->register_work, ath10k_core_register_work); INIT_WORK(&ar->restart_work, ath10k_core_restart); + INIT_WORK(&ar->recovery_check_work, ath10k_core_recovery_check_work); INIT_WORK(&ar->set_coverage_class_work, ath10k_core_set_coverage_class_work); diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h index 8c72ed386edb73..859176fcb5a29d 100644 --- a/drivers/net/wireless/ath/ath10k/core.h +++ b/drivers/net/wireless/ath/ath10k/core.h @@ -3,7 +3,6 @@ * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ @@ -1208,6 +1207,7 @@ struct ath10k { struct work_struct register_work; struct work_struct restart_work; + struct work_struct recovery_check_work; struct work_struct bundle_tx_work; struct work_struct tx_complete_work; diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 154ac7a709824e..da6f7957a0ae7b 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -3,7 +3,6 @@ * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ @@ -5428,6 +5427,7 @@ static void ath10k_stop(struct ieee80211_hw *hw, bool suspend) cancel_work_sync(&ar->set_coverage_class_work); cancel_delayed_work_sync(&ar->scan.timeout); cancel_work_sync(&ar->restart_work); + cancel_work_sync(&ar->recovery_check_work); } static int ath10k_config_ps(struct ath10k *ar) diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index c06d50db40b818..00d0556dafefdb 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -2487,7 +2487,11 @@ void ath10k_sdio_fw_crashed_dump(struct ath10k *ar) if (fast_dump) ath10k_bmi_start(ar); + mutex_lock(&ar->dump_mutex); + + spin_lock_bh(&ar->data_lock); ar->stats.fw_crash_counter++; + spin_unlock_bh(&ar->data_lock); ath10k_sdio_disable_intrs(ar); @@ -2505,6 +2509,8 @@ void ath10k_sdio_fw_crashed_dump(struct ath10k *ar) ath10k_sdio_enable_intrs(ar); + mutex_unlock(&ar->dump_mutex); + ath10k_core_start_recovery(ar); } diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c index 812686173ac8a9..06b4df2370e95d 100644 --- a/drivers/net/wireless/ath/ath11k/core.c +++ b/drivers/net/wireless/ath/ath11k/core.c @@ -997,6 +997,33 @@ static const struct dmi_system_id ath11k_pm_quirk_table[] = { {} }; +static const struct __ath11k_core_usecase_firmware_table { + u32 hw_rev; + const char *compatible; + const char *firmware_name; +} ath11k_core_usecase_firmware_table[] = { + { ATH11K_HW_WCN6855_HW21, "qcom,lemans-evk", "nfa765"}, + { ATH11K_HW_WCN6855_HW21, "qcom,monaco-evk", "nfa765"}, + { ATH11K_HW_WCN6855_HW21, "qcom,hamoa-iot-evk", "nfa765"}, + { /* Sentinel */ } +}; + +const char *ath11k_core_get_usecase_firmware(struct ath11k_base *ab) +{ + const struct __ath11k_core_usecase_firmware_table *entry = NULL; + + entry = ath11k_core_usecase_firmware_table; + while (entry->compatible) { + if (ab->hw_rev == entry->hw_rev && + of_machine_is_compatible(entry->compatible)) + return entry->firmware_name; + entry++; + } + + return NULL; +} +EXPORT_SYMBOL(ath11k_core_get_usecase_firmware); + void ath11k_fw_stats_pdevs_free(struct list_head *head) { struct ath11k_fw_stats_pdev *i, *tmp; diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h index e8780b05ce11e3..834988dad591c7 100644 --- a/drivers/net/wireless/ath/ath11k/core.h +++ b/drivers/net/wireless/ath/ath11k/core.h @@ -1275,6 +1275,7 @@ bool ath11k_core_coldboot_cal_support(struct ath11k_base *ab); const struct firmware *ath11k_core_firmware_request(struct ath11k_base *ab, const char *filename); +const char *ath11k_core_get_usecase_firmware(struct ath11k_base *ab); static inline const char *ath11k_scan_state_str(enum ath11k_scan_state state) { @@ -1329,6 +1330,9 @@ static inline void ath11k_core_create_firmware_path(struct ath11k_base *ab, of_property_read_string(ab->dev->of_node, "firmware-name", &fw_name); + if (!fw_name) + fw_name = ath11k_core_get_usecase_firmware(ab); + if (fw_name && strncmp(filename, "board", 5)) snprintf(buf, buf_len, "%s/%s/%s/%s", ATH11K_FW_DIR, ab->hw_params.fw.dir, fw_name, filename); diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 0e41b5a91d66da..f142c17aa9aa74 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -2235,9 +2235,9 @@ static void ath11k_peer_assoc_h_vht(struct ath11k *ar, arg->peer_nss = min(sta->deflink.rx_nss, max_nss); arg->rx_max_rate = __le16_to_cpu(vht_cap->vht_mcs.rx_highest); arg->rx_mcs_set = __le16_to_cpu(vht_cap->vht_mcs.rx_mcs_map); + arg->rx_mcs_set = ath11k_peer_assoc_h_vht_limit(arg->rx_mcs_set, vht_mcs_mask); arg->tx_max_rate = __le16_to_cpu(vht_cap->vht_mcs.tx_highest); - arg->tx_mcs_set = ath11k_peer_assoc_h_vht_limit( - __le16_to_cpu(vht_cap->vht_mcs.tx_mcs_map), vht_mcs_mask); + arg->tx_mcs_set = __le16_to_cpu(vht_cap->vht_mcs.tx_mcs_map); /* In IPQ8074 platform, VHT mcs rate 10 and 11 is enabled by default. * VHT mcs rate 10 and 11 is not supported in 11ac standard. @@ -2522,10 +2522,10 @@ static void ath11k_peer_assoc_h_he(struct ath11k *ar, he_tx_mcs = v; } v = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_160); + v = ath11k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_rx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_160] = v; v = le16_to_cpu(he_cap->he_mcs_nss_supp.tx_mcs_160); - v = ath11k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_tx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_160] = v; arg->peer_he_mcs_count++; @@ -2535,10 +2535,10 @@ static void ath11k_peer_assoc_h_he(struct ath11k *ar, default: v = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_80); + v = ath11k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_rx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_80] = v; v = le16_to_cpu(he_cap->he_mcs_nss_supp.tx_mcs_80); - v = ath11k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_tx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_80] = v; arg->peer_he_mcs_count++; diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c index d8655badd96d0f..7114eca8810dbf 100644 --- a/drivers/net/wireless/ath/ath11k/pci.c +++ b/drivers/net/wireless/ath/ath11k/pci.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2019-2020 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include @@ -177,6 +177,19 @@ static inline void ath11k_pci_select_static_window(struct ath11k_pci *ab_pci) ab_pci->ab->mem + ATH11K_PCI_WINDOW_REG_ADDRESS); } +static void ath11k_pci_restore_window(struct ath11k_base *ab) +{ + struct ath11k_pci *ab_pci = ath11k_pci_priv(ab); + + spin_lock_bh(&ab_pci->window_lock); + + iowrite32(ATH11K_PCI_WINDOW_ENABLE_BIT | ab_pci->register_window, + ab->mem + ATH11K_PCI_WINDOW_REG_ADDRESS); + ioread32(ab->mem + ATH11K_PCI_WINDOW_REG_ADDRESS); + + spin_unlock_bh(&ab_pci->window_lock); +} + static void ath11k_pci_soc_global_reset(struct ath11k_base *ab) { u32 val, delay; @@ -201,6 +214,11 @@ static void ath11k_pci_soc_global_reset(struct ath11k_base *ab) val = ath11k_pcic_read32(ab, PCIE_SOC_GLOBAL_RESET); if (val == 0xffffffff) ath11k_warn(ab, "link down error during global reset\n"); + + /* Restore window register as its content is cleared during + * hardware global reset, such that it aligns with host cache. + */ + ath11k_pci_restore_window(ab); } static void ath11k_pci_clear_dbg_registers(struct ath11k_base *ab) diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index e3b444333deed1..110035dae8a618 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include #include @@ -2061,10 +2061,13 @@ int ath11k_wmi_send_peer_assoc_cmd(struct ath11k *ar, cmd->peer_bw_rxnss_override |= param->peer_bw_rxnss_override; if (param->vht_capable) { - mcs->rx_max_rate = param->rx_max_rate; - mcs->rx_mcs_set = param->rx_mcs_set; - mcs->tx_max_rate = param->tx_max_rate; - mcs->tx_mcs_set = param->tx_mcs_set; + /* firmware interprets mcs->tx_mcs_set field as peer's + * RX capability + */ + mcs->tx_max_rate = param->rx_max_rate; + mcs->tx_mcs_set = param->rx_mcs_set; + mcs->rx_max_rate = param->tx_max_rate; + mcs->rx_mcs_set = param->tx_mcs_set; } /* HE Rates */ @@ -2088,8 +2091,11 @@ int ath11k_wmi_send_peer_assoc_cmd(struct ath11k *ar, FIELD_PREP(WMI_TLV_LEN, sizeof(*he_mcs) - TLV_HDR_SIZE); - he_mcs->rx_mcs_set = param->peer_he_tx_mcs_set[i]; - he_mcs->tx_mcs_set = param->peer_he_rx_mcs_set[i]; + /* firmware interprets mcs->rx_mcs_set field as peer's + * RX capability + */ + he_mcs->rx_mcs_set = param->peer_he_rx_mcs_set[i]; + he_mcs->tx_mcs_set = param->peer_he_tx_mcs_set[i]; ptr += sizeof(*he_mcs); } diff --git a/drivers/net/wireless/ath/ath11k/wmi.h b/drivers/net/wireless/ath/ath11k/wmi.h index 9fcffaa2f383c9..6e9354297e71d3 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.h +++ b/drivers/net/wireless/ath/ath11k/wmi.h @@ -4133,8 +4133,10 @@ struct wmi_rate_set { struct wmi_vht_rate_set { u32 tlv_header; u32 rx_max_rate; + /* MCS at which the peer can transmit */ u32 rx_mcs_set; u32 tx_max_rate; + /* MCS at which the peer can receive */ u32 tx_mcs_set; u32 tx_max_mcs_nss; } __packed; diff --git a/drivers/net/wireless/ath/ath12k/ce.c b/drivers/net/wireless/ath/ath12k/ce.c index 9a63608838ace3..4aea5844683818 100644 --- a/drivers/net/wireless/ath/ath12k/ce.c +++ b/drivers/net/wireless/ath/ath12k/ce.c @@ -984,8 +984,8 @@ void ath12k_ce_free_pipes(struct ath12k_base *ab) dma_free_coherent(ab->dev, pipe->src_ring->nentries * desc_sz + CE_DESC_RING_ALIGN, - pipe->src_ring->base_addr_owner_space, - pipe->src_ring->base_addr_ce_space); + pipe->src_ring->base_addr_owner_space_unaligned, + pipe->src_ring->base_addr_ce_space_unaligned); kfree(pipe->src_ring); pipe->src_ring = NULL; } @@ -995,8 +995,8 @@ void ath12k_ce_free_pipes(struct ath12k_base *ab) dma_free_coherent(ab->dev, pipe->dest_ring->nentries * desc_sz + CE_DESC_RING_ALIGN, - pipe->dest_ring->base_addr_owner_space, - pipe->dest_ring->base_addr_ce_space); + pipe->dest_ring->base_addr_owner_space_unaligned, + pipe->dest_ring->base_addr_ce_space_unaligned); kfree(pipe->dest_ring); pipe->dest_ring = NULL; } @@ -1007,8 +1007,8 @@ void ath12k_ce_free_pipes(struct ath12k_base *ab) dma_free_coherent(ab->dev, pipe->status_ring->nentries * desc_sz + CE_DESC_RING_ALIGN, - pipe->status_ring->base_addr_owner_space, - pipe->status_ring->base_addr_ce_space); + pipe->status_ring->base_addr_owner_space_unaligned, + pipe->status_ring->base_addr_ce_space_unaligned); kfree(pipe->status_ring); pipe->status_ring = NULL; } diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c index 5d494c5cdc0da3..cc352eef193993 100644 --- a/drivers/net/wireless/ath/ath12k/core.c +++ b/drivers/net/wireless/ath/ath12k/core.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ @@ -1250,7 +1249,6 @@ void ath12k_fw_stats_reset(struct ath12k *ar) spin_lock_bh(&ar->data_lock); ath12k_fw_stats_free(&ar->fw_stats); ar->fw_stats.num_vdev_recvd = 0; - ar->fw_stats.num_bcn_recvd = 0; spin_unlock_bh(&ar->data_lock); } @@ -2106,14 +2104,27 @@ static int ath12k_core_hw_group_create(struct ath12k_hw_group *ag) ret = ath12k_core_soc_create(ab); if (ret) { mutex_unlock(&ab->core_lock); - ath12k_err(ab, "failed to create soc core: %d\n", ret); - return ret; + ath12k_err(ab, "failed to create soc %d core: %d\n", i, ret); + goto destroy; } mutex_unlock(&ab->core_lock); } return 0; + +destroy: + for (i--; i >= 0; i--) { + ab = ag->ab[i]; + if (!ab) + continue; + + mutex_lock(&ab->core_lock); + ath12k_core_soc_destroy(ab); + mutex_unlock(&ab->core_lock); + } + + return ret; } void ath12k_core_hw_group_set_mlo_capable(struct ath12k_hw_group *ag) @@ -2188,7 +2199,7 @@ int ath12k_core_init(struct ath12k_base *ab) if (ret) { mutex_unlock(&ag->mutex); ath12k_warn(ab, "unable to create hw group\n"); - goto err_destroy_hw_group; + goto err_unassign_hw_group; } } @@ -2196,8 +2207,7 @@ int ath12k_core_init(struct ath12k_base *ab) return 0; -err_destroy_hw_group: - ath12k_core_hw_group_destroy(ab->ag); +err_unassign_hw_group: ath12k_core_hw_group_unassign(ab); err_unregister_notifier: ath12k_core_panic_notifier_unregister(ab); diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h index 3d1956966a485a..d7688b383f62c9 100644 --- a/drivers/net/wireless/ath/ath12k/core.h +++ b/drivers/net/wireless/ath/ath12k/core.h @@ -644,7 +644,6 @@ struct ath12k_fw_stats { struct list_head vdevs; struct list_head bcn; u32 num_vdev_recvd; - u32 num_bcn_recvd; }; struct ath12k_dbg_htt_stats { diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c index 48b010a1b7566d..4f749d473d0e1f 100644 --- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c +++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include @@ -29,8 +29,10 @@ print_array_to_buf_index(u8 *buf, u32 offset, const char *header, u32 stats_inde " %u:%u,", stats_index++, le32_to_cpu(array[i])); } /* To overwrite the last trailing comma */ - index--; - *(buf + offset + index) = '\0'; + if (array_len > 0) { + index--; + *(buf + offset + index) = '\0'; + } if (footer) { index += scnprintf(buf + offset + index, diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c index 5e5c14a70316de..99d29eda26cf1d 100644 --- a/drivers/net/wireless/ath/ath12k/dp_rx.c +++ b/drivers/net/wireless/ath/ath12k/dp_rx.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include @@ -3781,6 +3781,48 @@ ath12k_dp_process_rx_err_buf(struct ath12k *ar, struct hal_reo_dest_ring *desc, return 0; } +static int ath12k_dp_h_msdu_buffer_type(struct ath12k_base *ab, + struct list_head *list, + struct hal_reo_dest_ring *desc) +{ + struct ath12k_rx_desc_info *desc_info; + struct ath12k_skb_rxcb *rxcb; + struct sk_buff *msdu; + u64 desc_va; + + desc_va = (u64)le32_to_cpu(desc->buf_va_hi) << 32 | + le32_to_cpu(desc->buf_va_lo); + desc_info = (struct ath12k_rx_desc_info *)(uintptr_t)desc_va; + if (!desc_info) { + u32 cookie; + + cookie = le32_get_bits(desc->buf_addr_info.info1, + BUFFER_ADDR_INFO1_SW_COOKIE); + desc_info = ath12k_dp_get_rx_desc(ab, cookie); + if (!desc_info) { + ath12k_warn(ab, "Invalid cookie in manual descriptor retrieval: 0x%x\n", + cookie); + return -EINVAL; + } + } + + if (desc_info->magic != ATH12K_DP_RX_DESC_MAGIC) { + ath12k_warn(ab, "rx exception, magic check failed with value: %u\n", + desc_info->magic); + return -EINVAL; + } + + msdu = desc_info->skb; + desc_info->skb = NULL; + list_add_tail(&desc_info->list, list); + rxcb = ATH12K_SKB_RXCB(msdu); + dma_unmap_single(ab->dev, rxcb->paddr, msdu->len + skb_tailroom(msdu), + DMA_FROM_DEVICE); + dev_kfree_skb_any(msdu); + + return 0; +} + int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi, int budget) { @@ -3825,6 +3867,26 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi, drop = false; ab->device_stats.err_ring_pkts++; + hw_link_id = le32_get_bits(reo_desc->info0, + HAL_REO_DEST_RING_INFO0_SRC_LINK_ID); + device_id = hw_links[hw_link_id].device_id; + partner_ab = ath12k_ag_to_ab(ag, device_id); + + /* Below case is added to handle data packet from un-associated clients. + * As it is expected that AST lookup will fail for + * un-associated station's data packets. + */ + if (le32_get_bits(reo_desc->info0, HAL_REO_DEST_RING_INFO0_BUFFER_TYPE) == + HAL_REO_DEST_RING_BUFFER_TYPE_MSDU) { + if (!ath12k_dp_h_msdu_buffer_type(partner_ab, + &rx_desc_used_list[device_id], + reo_desc)) { + num_buffs_reaped[device_id]++; + tot_n_bufs_reaped++; + } + goto next_desc; + } + ret = ath12k_hal_desc_reo_parse_err(ab, reo_desc, &paddr, &desc_bank); if (ret) { @@ -3833,11 +3895,6 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi, continue; } - hw_link_id = le32_get_bits(reo_desc->info0, - HAL_REO_DEST_RING_INFO0_SRC_LINK_ID); - device_id = hw_links[hw_link_id].device_id; - partner_ab = ath12k_ag_to_ab(ag, device_id); - pdev_id = ath12k_hw_mac_id_to_pdev_id(partner_ab->hw_params, hw_links[hw_link_id].pdev_idx); ar = partner_ab->pdevs[pdev_id].ar; @@ -3886,6 +3943,7 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi, } } +next_desc: if (tot_n_bufs_reaped >= quota) { tot_n_bufs_reaped = quota; goto exit; diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.c b/drivers/net/wireless/ath/ath12k/hal_rx.c index 669096278fdd48..c4443ca05cd653 100644 --- a/drivers/net/wireless/ath/ath12k/hal_rx.c +++ b/drivers/net/wireless/ath/ath12k/hal_rx.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include "debug.h" @@ -323,7 +323,7 @@ int ath12k_hal_desc_reo_parse_err(struct ath12k_base *ab, { enum hal_reo_dest_ring_push_reason push_reason; enum hal_reo_dest_ring_error_code err_code; - u32 cookie, val; + u32 cookie; push_reason = le32_get_bits(desc->info0, HAL_REO_DEST_RING_INFO0_PUSH_REASON); @@ -338,12 +338,6 @@ int ath12k_hal_desc_reo_parse_err(struct ath12k_base *ab, return -EINVAL; } - val = le32_get_bits(desc->info0, HAL_REO_DEST_RING_INFO0_BUFFER_TYPE); - if (val != HAL_REO_DEST_RING_BUFFER_TYPE_LINK_DESC) { - ath12k_warn(ab, "expected buffer type link_desc"); - return -EINVAL; - } - ath12k_hal_rx_reo_ent_paddr_get(ab, &desc->buf_addr_info, paddr, &cookie); *desc_bank = u32_get_bits(cookie, DP_LINK_DESC_BANK_MASK); diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index db351c92201817..b97469dca0467c 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -2249,7 +2249,6 @@ static void ath12k_peer_assoc_h_vht(struct ath12k *ar, struct cfg80211_chan_def def; enum nl80211_band band; u16 *vht_mcs_mask; - u16 tx_mcs_map; u8 ampdu_factor; u8 max_nss, vht_mcs; int i, vht_nss, nss_idx; @@ -2340,10 +2339,10 @@ static void ath12k_peer_assoc_h_vht(struct ath12k *ar, arg->peer_nss = min(link_sta->rx_nss, max_nss); arg->rx_max_rate = __le16_to_cpu(vht_cap->vht_mcs.rx_highest); arg->rx_mcs_set = __le16_to_cpu(vht_cap->vht_mcs.rx_mcs_map); - arg->tx_max_rate = __le16_to_cpu(vht_cap->vht_mcs.tx_highest); + arg->rx_mcs_set = ath12k_peer_assoc_h_vht_limit(arg->rx_mcs_set, vht_mcs_mask); - tx_mcs_map = __le16_to_cpu(vht_cap->vht_mcs.tx_mcs_map); - arg->tx_mcs_set = ath12k_peer_assoc_h_vht_limit(tx_mcs_map, vht_mcs_mask); + arg->tx_max_rate = __le16_to_cpu(vht_cap->vht_mcs.tx_highest); + arg->tx_mcs_set = __le16_to_cpu(vht_cap->vht_mcs.tx_mcs_map); /* In QCN9274 platform, VHT MCS rate 10 and 11 is enabled by default. * VHT MCS rate 10 and 11 is not supported in 11ac standard. @@ -2625,9 +2624,10 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar, switch (link_sta->bandwidth) { case IEEE80211_STA_RX_BW_160: v = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_160); + v = ath12k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_rx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_160] = v; - v = ath12k_peer_assoc_h_he_limit(v, he_mcs_mask); + v = le16_to_cpu(he_cap->he_mcs_nss_supp.tx_mcs_160); arg->peer_he_tx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_160] = v; arg->peer_he_mcs_count++; @@ -2637,10 +2637,10 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar, default: v = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_80); + v = ath12k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_rx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_80] = v; v = le16_to_cpu(he_cap->he_mcs_nss_supp.tx_mcs_80); - v = ath12k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_tx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_80] = v; arg->peer_he_mcs_count++; @@ -4004,8 +4004,10 @@ ath12k_mac_op_change_vif_links(struct ieee80211_hw *hw, if (WARN_ON(!arvif)) return -EINVAL; - if (!arvif->is_created) + if (!arvif->is_created) { + ath12k_mac_unassign_link_vif(arvif); continue; + } if (WARN_ON(!arvif->ar)) return -EINVAL; @@ -5059,7 +5061,8 @@ static int ath12k_mac_initiate_hw_scan(struct ieee80211_hw *hw, ret = ath12k_mac_vdev_create(ar, arvif); if (ret) { ath12k_warn(ar->ab, "unable to create scan vdev %d\n", ret); - return -EINVAL; + ath12k_mac_unassign_link_vif(arvif); + return ret; } } @@ -5253,7 +5256,8 @@ static void ath12k_mac_op_cancel_hw_scan(struct ieee80211_hw *hw, for_each_set_bit(link_id, &links_map, ATH12K_NUM_MAX_LINKS) { arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); - if (!arvif || arvif->is_started) + if (!arvif || !arvif->is_created || + arvif->ar->scan.arvif != arvif) continue; ar = arvif->ar; @@ -8838,7 +8842,10 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw, return; } } else { - link_id = 0; + if (vif->type == NL80211_IFTYPE_P2P_DEVICE) + link_id = ATH12K_FIRST_SCAN_LINK; + else + link_id = 0; } arvif = rcu_dereference(ahvif->link[link_id]); @@ -9687,6 +9694,12 @@ int ath12k_mac_vdev_create(struct ath12k *ar, struct ath12k_link_vif *arvif) if (vif->type == NL80211_IFTYPE_MONITOR && ar->monitor_vdev_created) return -EINVAL; + if (ar->num_created_vdevs >= TARGET_NUM_VDEVS(ab)) { + ath12k_warn(ab, "failed to create vdev, reached max vdev limit %d\n", + TARGET_NUM_VDEVS(ab)); + return -ENOSPC; + } + link_id = arvif->link_id; if (link_id < IEEE80211_MLD_MAX_NUM_LINKS) { @@ -10046,12 +10059,6 @@ static struct ath12k *ath12k_mac_assign_vif_to_vdev(struct ieee80211_hw *hw, if (arvif->is_created) goto flush; - if (ar->num_created_vdevs > (TARGET_NUM_VDEVS(ab) - 1)) { - ath12k_warn(ab, "failed to create vdev, reached max vdev limit %d\n", - TARGET_NUM_VDEVS(ab)); - goto unlock; - } - ret = ath12k_mac_vdev_create(ar, arvif); if (ret) { ath12k_warn(ab, "failed to create vdev %pM ret %d", vif->addr, ret); @@ -11796,6 +11803,9 @@ static void ath12k_mac_op_flush(struct ieee80211_hw *hw, struct ieee80211_vif *v if (drop) return; + for_each_ar(ah, ar, i) + wiphy_work_flush(hw->wiphy, &ar->wmi_mgmt_tx_work); + /* vif can be NULL when flush() is considered for hw */ if (!vif) { for_each_ar(ah, ar, i) @@ -11803,9 +11813,6 @@ static void ath12k_mac_op_flush(struct ieee80211_hw *hw, struct ieee80211_vif *v return; } - for_each_ar(ah, ar, i) - wiphy_work_flush(hw->wiphy, &ar->wmi_mgmt_tx_work); - ahvif = ath12k_vif_to_ahvif(vif); links = ahvif->links_map; for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { @@ -12831,7 +12838,7 @@ static int ath12k_mac_op_cancel_remain_on_channel(struct ieee80211_hw *hw, ath12k_scan_abort(ar); cancel_delayed_work_sync(&ar->scan.timeout); - wiphy_work_cancel(hw->wiphy, &ar->scan.vdev_clean_wk); + wiphy_work_flush(hw->wiphy, &ar->scan.vdev_clean_wk); return 0; } @@ -12895,6 +12902,7 @@ static int ath12k_mac_op_remain_on_channel(struct ieee80211_hw *hw, if (ret) { ath12k_warn(ar->ab, "unable to create scan vdev for roc: %d\n", ret); + ath12k_mac_unassign_link_vif(arvif); return ret; } } diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c index c729d5526c753d..60b8f7361b7f63 100644 --- a/drivers/net/wireless/ath/ath12k/pci.c +++ b/drivers/net/wireless/ath/ath12k/pci.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include @@ -218,6 +218,19 @@ static inline bool ath12k_pci_is_offset_within_mhi_region(u32 offset) return (offset >= PCI_MHIREGLEN_REG && offset <= PCI_MHI_REGION_END); } +static void ath12k_pci_restore_window(struct ath12k_base *ab) +{ + struct ath12k_pci *ab_pci = ath12k_pci_priv(ab); + + spin_lock_bh(&ab_pci->window_lock); + + iowrite32(WINDOW_ENABLE_BIT | ab_pci->register_window, + ab->mem + WINDOW_REG_ADDRESS); + ioread32(ab->mem + WINDOW_REG_ADDRESS); + + spin_unlock_bh(&ab_pci->window_lock); +} + static void ath12k_pci_soc_global_reset(struct ath12k_base *ab) { u32 val, delay; @@ -242,6 +255,11 @@ static void ath12k_pci_soc_global_reset(struct ath12k_base *ab) val = ath12k_pci_read32(ab, PCIE_SOC_GLOBAL_RESET); if (val == 0xffffffff) ath12k_warn(ab, "link down error during global reset\n"); + + /* Restore window register as its content is cleared during + * hardware global reset, such that it aligns with host cache. + */ + ath12k_pci_restore_window(ab); } static void ath12k_pci_clear_dbg_registers(struct ath12k_base *ab) diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c index 36325e62aa2423..8de9aee2498ec5 100644 --- a/drivers/net/wireless/ath/ath12k/qmi.c +++ b/drivers/net/wireless/ath/ath12k/qmi.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include @@ -3114,9 +3114,10 @@ static void ath12k_qmi_m3_free(struct ath12k_base *ab) if (!m3_mem->vaddr) return; - dma_free_coherent(ab->dev, m3_mem->size, + dma_free_coherent(ab->dev, m3_mem->total_size, m3_mem->vaddr, m3_mem->paddr); m3_mem->vaddr = NULL; + m3_mem->total_size = 0; m3_mem->size = 0; } @@ -3152,7 +3153,7 @@ static int ath12k_qmi_m3_load(struct ath12k_base *ab) /* In recovery/resume cases, M3 buffer is not freed, try to reuse that */ if (m3_mem->vaddr) { - if (m3_mem->size >= m3_len) + if (m3_mem->total_size >= m3_len) goto skip_m3_alloc; /* Old buffer is too small, free and reallocate */ @@ -3164,11 +3165,13 @@ static int ath12k_qmi_m3_load(struct ath12k_base *ab) GFP_KERNEL); if (!m3_mem->vaddr) { ath12k_err(ab, "failed to allocate memory for M3 with size %zu\n", - fw->size); + m3_len); ret = -ENOMEM; goto out; } + m3_mem->total_size = m3_len; + skip_m3_alloc: memcpy(m3_mem->vaddr, m3_data, m3_len); m3_mem->size = m3_len; diff --git a/drivers/net/wireless/ath/ath12k/qmi.h b/drivers/net/wireless/ath/ath12k/qmi.h index 4767d9a2e309e4..7a88268aa1e9e9 100644 --- a/drivers/net/wireless/ath/ath12k/qmi.h +++ b/drivers/net/wireless/ath/ath12k/qmi.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: BSD-3-Clause-Clear */ /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #ifndef ATH12K_QMI_H @@ -120,6 +120,9 @@ struct target_info { }; struct m3_mem_region { + /* total memory allocated */ + u32 total_size; + /* actual memory being used */ u32 size; dma_addr_t paddr; void *vaddr; diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index ff6b3d4ea82084..44e99b47e445d4 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include #include @@ -2367,10 +2367,13 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar, cmd->peer_bw_rxnss_override |= cpu_to_le32(arg->peer_bw_rxnss_override); if (arg->vht_capable) { - mcs->rx_max_rate = cpu_to_le32(arg->rx_max_rate); - mcs->rx_mcs_set = cpu_to_le32(arg->rx_mcs_set); - mcs->tx_max_rate = cpu_to_le32(arg->tx_max_rate); - mcs->tx_mcs_set = cpu_to_le32(arg->tx_mcs_set); + /* Firmware interprets mcs->tx_mcs_set field as peer's + * RX capability + */ + mcs->rx_max_rate = cpu_to_le32(arg->tx_max_rate); + mcs->rx_mcs_set = cpu_to_le32(arg->tx_mcs_set); + mcs->tx_max_rate = cpu_to_le32(arg->rx_max_rate); + mcs->tx_mcs_set = cpu_to_le32(arg->rx_mcs_set); } /* HE Rates */ @@ -6517,16 +6520,9 @@ static int freq_to_idx(struct ath12k *ar, int freq) if (!sband) continue; - for (ch = 0; ch < sband->n_channels; ch++, idx++) { - if (sband->channels[ch].center_freq < - KHZ_TO_MHZ(ar->freq_range.start_freq) || - sband->channels[ch].center_freq > - KHZ_TO_MHZ(ar->freq_range.end_freq)) - continue; - + for (ch = 0; ch < sband->n_channels; ch++, idx++) if (sband->channels[ch].center_freq == freq) goto exit; - } } exit: @@ -8415,18 +8411,10 @@ static void ath12k_wmi_fw_stats_process(struct ath12k *ar, ath12k_warn(ab, "empty beacon stats"); return; } - /* Mark end until we reached the count of all started VDEVs - * within the PDEV - */ - if (ar->num_started_vdevs) - is_end = ((++ar->fw_stats.num_bcn_recvd) == - ar->num_started_vdevs); list_splice_tail_init(&stats->bcn, &ar->fw_stats.bcn); - - if (is_end) - complete(&ar->fw_stats_done); + complete(&ar->fw_stats_done); } } diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h index a8c3190e8ad955..6d9c645e3d5d04 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.h +++ b/drivers/net/wireless/ath/ath12k/wmi.h @@ -4218,8 +4218,10 @@ struct wmi_unit_test_cmd { struct ath12k_wmi_vht_rate_set_params { __le32 tlv_header; __le32 rx_max_rate; + /* MCS at which the peer can transmit */ __le32 rx_mcs_set; __le32 tx_max_rate; + /* MCS at which the peer can receive */ __le32 tx_mcs_set; __le32 tx_max_mcs_nss; } __packed; diff --git a/drivers/net/wireless/ath/ath12k/wow.c b/drivers/net/wireless/ath/ath12k/wow.c index dce9bd0bcaefb8..c78aa95d497911 100644 --- a/drivers/net/wireless/ath/ath12k/wow.c +++ b/drivers/net/wireless/ath/ath12k/wow.c @@ -135,6 +135,9 @@ static int ath12k_wow_cleanup(struct ath12k *ar) lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); list_for_each_entry(arvif, &ar->arvifs, list) { + if (arvif != &arvif->ahvif->deflink) + continue; + ret = ath12k_wow_vif_cleanup(arvif); if (ret) { ath12k_warn(ar->ab, "failed to clean wow wakeups on vdev %i: %d\n", @@ -479,8 +482,12 @@ static int ath12k_wow_set_wakeups(struct ath12k *ar, lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); list_for_each_entry(arvif, &ar->arvifs, list) { + if (arvif != &arvif->ahvif->deflink) + continue; + if (ath12k_wow_is_p2p_vdev(arvif->ahvif)) continue; + ret = ath12k_wow_vif_set_wakeups(arvif, wowlan); if (ret) { ath12k_warn(ar->ab, "failed to set wow wakeups on vdev %i: %d\n", @@ -538,6 +545,9 @@ static int ath12k_wow_nlo_cleanup(struct ath12k *ar) lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); list_for_each_entry(arvif, &ar->arvifs, list) { + if (arvif != &arvif->ahvif->deflink) + continue; + if (ath12k_wow_is_p2p_vdev(arvif->ahvif)) continue; @@ -745,6 +755,9 @@ static int ath12k_wow_arp_ns_offload(struct ath12k *ar, bool enable) list_for_each_entry(arvif, &ar->arvifs, list) { ahvif = arvif->ahvif; + if (arvif != &ahvif->deflink) + continue; + if (ahvif->vdev_type != WMI_VDEV_TYPE_STA) continue; @@ -758,6 +771,7 @@ static int ath12k_wow_arp_ns_offload(struct ath12k *ar, bool enable) if (ret) { ath12k_warn(ar->ab, "failed to set arp ns offload vdev %i: enable %d, ret %d\n", arvif->vdev_id, enable, ret); + kfree(offload); return ret; } } @@ -775,6 +789,9 @@ static int ath12k_gtk_rekey_offload(struct ath12k *ar, bool enable) lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); list_for_each_entry(arvif, &ar->arvifs, list) { + if (arvif != &arvif->ahvif->deflink) + continue; + if (arvif->ahvif->vdev_type != WMI_VDEV_TYPE_STA || !arvif->is_up || !arvif->rekey_data.enable_offload) diff --git a/drivers/net/wireless/ath/ath9k/Kconfig b/drivers/net/wireless/ath/ath9k/Kconfig index 0c47be06c153be..47d570a5ca6a1c 100644 --- a/drivers/net/wireless/ath/ath9k/Kconfig +++ b/drivers/net/wireless/ath/ath9k/Kconfig @@ -47,7 +47,7 @@ config ATH9K_PCI config ATH9K_AHB bool "Atheros ath9k AHB bus support" - depends on ATH9K + depends on ATH9K && OF default n help This option enables the AHB bus support in ath9k. diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile index e5ca0f51182271..6fd805023500be 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile @@ -25,7 +25,11 @@ brcmfmac-objs += \ btcoex.o \ vendor.o \ pno.o \ - xtlv.o + join_param.o \ + scan_param.o \ + xtlv.o \ + interface_create.o + brcmfmac-$(CONFIG_BRCMFMAC_PROTO_BCDC) += \ bcdc.o \ fwsignal.o diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h index fe31051a9e11b1..5efd7f6d757a4c 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h @@ -107,6 +107,7 @@ struct brcmf_bus_ops { void (*debugfs_create)(struct device *dev); int (*reset)(struct device *dev); void (*remove)(struct device *dev); + void (*d2h_mb_rx)(struct device *dev, u32 data); }; @@ -286,6 +287,15 @@ static inline void brcmf_bus_remove(struct brcmf_bus *bus) bus->ops->remove(bus->dev); } +static inline +void brcmf_bus_d2h_mb_rx(struct brcmf_bus *bus, u32 data) +{ + if (!bus->ops->d2h_mb_rx) + return; + + return bus->ops->d2h_mb_rx(bus->dev, data); +} + /* * interface functions from common layer */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index bb96b87b2a6e56..a87965c5d1226a 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -32,7 +32,11 @@ #include "vendor.h" #include "bus.h" #include "common.h" +#include "feature.h" #include "fwvid.h" +#include "xtlv.h" +#include "ratespec.h" +#include "interface_create.h" #define BRCMF_SCAN_IE_LEN_MAX 2048 @@ -64,6 +68,8 @@ #define RSN_CAP_MFPR_MASK BIT(6) #define RSN_CAP_MFPC_MASK BIT(7) #define RSN_PMKID_COUNT_LEN 2 +#define DPP_AKM_SUITE_TYPE 2 +#define WLAN_AKM_SUITE_DPP SUITE(WLAN_OUI_WFA, DPP_AKM_SUITE_TYPE) #define VNDR_IE_CMD_LEN 4 /* length of the set command * string :"add", "del" (+ NUL) @@ -76,10 +82,6 @@ #define DOT11_BCN_PRB_FIXED_LEN 12 /* beacon/probe fixed length */ -#define BRCMF_SCAN_JOIN_ACTIVE_DWELL_TIME_MS 320 -#define BRCMF_SCAN_JOIN_PASSIVE_DWELL_TIME_MS 400 -#define BRCMF_SCAN_JOIN_PROBE_INTERVAL_MS 20 - #define BRCMF_SCAN_CHANNEL_TIME 40 #define BRCMF_SCAN_UNASSOC_TIME 40 #define BRCMF_SCAN_PASSIVE_TIME 120 @@ -98,9 +100,6 @@ #define PKT_TOKEN_IDX 15 #define IDLE_TOKEN_IDX 12 -#define BRCMF_ASSOC_PARAMS_FIXED_SIZE \ - (sizeof(struct brcmf_assoc_params_le) - sizeof(u16)) - #define BRCMF_MAX_CHANSPEC_LIST \ (BRCMF_DCMD_MEDLEN / sizeof(__le32) - 1) @@ -124,6 +123,13 @@ struct cca_msrmnt_query { u32 time_req; }; +/* algo bit vector */ +#define KEY_ALGO_MASK(_algo) (1 << (_algo)) + +/* start enum value for BSS properties */ +#define WL_WSEC_INFO_BSS_BASE 0x0100 +#define WL_WSEC_INFO_BSS_ALGOS (WL_WSEC_INFO_BSS_BASE + 6) + static bool check_vif_up(struct brcmf_cfg80211_vif *vif) { if (!test_bit(BRCMF_VIF_STATUS_READY, &vif->sme_state)) { @@ -178,6 +184,15 @@ static struct ieee80211_rate __wl_rates[] = { .max_power = 30, \ } +#define CHAN6G(_channel) { \ + .band = NL80211_BAND_6GHZ, \ + .center_freq = ((_channel == 2) ? 5935 : 5950 + (5 * (_channel))), \ + .hw_value = (_channel), \ + .max_antenna_gain = 0, \ + .max_power = 30, \ +} + + static struct ieee80211_channel __wl_2ghz_channels[] = { CHAN2G(1, 2412), CHAN2G(2, 2417), CHAN2G(3, 2422), CHAN2G(4, 2427), CHAN2G(5, 2432), CHAN2G(6, 2437), CHAN2G(7, 2442), CHAN2G(8, 2447), @@ -194,6 +209,23 @@ static struct ieee80211_channel __wl_5ghz_channels[] = { CHAN5G(153), CHAN5G(157), CHAN5G(161), CHAN5G(165) }; +static struct ieee80211_channel __wl_6ghz_channels[] = { + CHAN6G(1), CHAN6G(2), CHAN6G(5), CHAN6G(9), CHAN6G(13), + CHAN6G(17), CHAN6G(21), CHAN6G(25), CHAN6G(29), CHAN6G(33), + CHAN6G(37), CHAN6G(41), CHAN6G(45), CHAN6G(49), CHAN6G(53), + CHAN6G(57), CHAN6G(61), CHAN6G(65), CHAN6G(69), CHAN6G(73), + CHAN6G(77), CHAN6G(81), CHAN6G(85), CHAN6G(89), CHAN6G(93), + CHAN6G(97), CHAN6G(101), CHAN6G(105), CHAN6G(109), CHAN6G(113), + CHAN6G(117), CHAN6G(121), CHAN6G(125), CHAN6G(129), CHAN6G(133), + CHAN6G(137), CHAN6G(141), CHAN6G(145), CHAN6G(149), CHAN6G(153), + CHAN6G(157), CHAN6G(161), CHAN6G(165), CHAN6G(169), CHAN6G(173), + CHAN6G(177), CHAN6G(181), CHAN6G(185), CHAN6G(189), CHAN6G(193), + CHAN6G(197), CHAN6G(201), CHAN6G(205), CHAN6G(209), CHAN6G(213), + CHAN6G(217), CHAN6G(221), CHAN6G(225), CHAN6G(229), CHAN6G(233), +}; + +struct ieee80211_sband_iftype_data sdata[NUM_NL80211_BANDS]; + /* Band templates duplicated per wiphy. The channel info * above is added to the band during setup. */ @@ -209,6 +241,12 @@ static const struct ieee80211_supported_band __wl_band_5ghz = { .n_bitrates = wl_a_rates_size, }; +static const struct ieee80211_supported_band __wl_band_6ghz = { + .band = NL80211_BAND_6GHZ, + .bitrates = wl_a_rates, + .n_bitrates = wl_a_rates_size, +}; + /* This is to override regulatory domains defined in cfg80211 module (reg.c) * By default world regulatory domain defined in reg.c puts the flags * NL80211_RRF_NO_IR for 5GHz channels (for * 36..48 and 149..165). @@ -217,35 +255,43 @@ static const struct ieee80211_supported_band __wl_band_5ghz = { * domain are to be done here. */ static const struct ieee80211_regdomain brcmf_regdom = { - .n_reg_rules = 4, + .n_reg_rules = 5, .alpha2 = "99", .reg_rules = { /* IEEE 802.11b/g, channels 1..11 */ - REG_RULE(2412-10, 2472+10, 40, 6, 20, 0), + REG_RULE(2412 - 10, 2472 + 10, 40, 6, 20, 0), /* If any */ /* IEEE 802.11 channel 14 - Only JP enables * this and for 802.11b only */ - REG_RULE(2484-10, 2484+10, 20, 6, 20, 0), + REG_RULE(2484 - 10, 2484 + 10, 20, 6, 20, 0), /* IEEE 802.11a, channel 36..64 */ - REG_RULE(5150-10, 5350+10, 160, 6, 20, 0), + REG_RULE(5150 - 10, 5350 + 10, 160, 6, 20, 0), /* IEEE 802.11a, channel 100..165 */ - REG_RULE(5470-10, 5850+10, 160, 6, 20, 0), } + REG_RULE(5470 - 10, 5850 + 10, 160, 6, 20, 0), + /* IEEE 802.11ax, 6E */ + REG_RULE(5935 - 10, 7115 + 10, 160, 6, 20, 0), } }; /* Note: brcmf_cipher_suites is an array of int defining which cipher suites * are supported. A pointer to this array and the number of entries is passed * on to upper layers. AES_CMAC defines whether or not the driver supports MFP. - * So the cipher suite AES_CMAC has to be the last one in the array, and when - * device does not support MFP then the number of suites will be decreased by 1 + * MFP support includes a few other suites, so if MFP is not supported, + * then the number of suites will be decreased by 4 */ static const u32 brcmf_cipher_suites[] = { WLAN_CIPHER_SUITE_WEP40, WLAN_CIPHER_SUITE_WEP104, WLAN_CIPHER_SUITE_TKIP, WLAN_CIPHER_SUITE_CCMP, - /* Keep as last entry: */ - WLAN_CIPHER_SUITE_AES_CMAC + WLAN_CIPHER_SUITE_CCMP_256, + WLAN_CIPHER_SUITE_GCMP, + WLAN_CIPHER_SUITE_GCMP_256, + /* Keep as last 4 entries: */ + WLAN_CIPHER_SUITE_AES_CMAC, + WLAN_CIPHER_SUITE_BIP_CMAC_256, + WLAN_CIPHER_SUITE_BIP_GMAC_128, + WLAN_CIPHER_SUITE_BIP_GMAC_256 }; /* Vendor specific ie. id = 221, oui and type defines exact ie */ @@ -267,48 +313,6 @@ struct parsed_vndr_ies { struct parsed_vndr_ie_info ie_info[VNDR_IE_PARSE_LIMIT]; }; -#define WL_INTERFACE_CREATE_VER_1 1 -#define WL_INTERFACE_CREATE_VER_2 2 -#define WL_INTERFACE_CREATE_VER_3 3 -#define WL_INTERFACE_CREATE_VER_MAX WL_INTERFACE_CREATE_VER_3 - -#define WL_INTERFACE_MAC_DONT_USE 0x0 -#define WL_INTERFACE_MAC_USE 0x2 - -#define WL_INTERFACE_CREATE_STA 0x0 -#define WL_INTERFACE_CREATE_AP 0x1 - -struct wl_interface_create_v1 { - u16 ver; /* structure version */ - u32 flags; /* flags for operation */ - u8 mac_addr[ETH_ALEN]; /* MAC address */ - u32 wlc_index; /* optional for wlc index */ -}; - -struct wl_interface_create_v2 { - u16 ver; /* structure version */ - u8 pad1[2]; - u32 flags; /* flags for operation */ - u8 mac_addr[ETH_ALEN]; /* MAC address */ - u8 iftype; /* type of interface created */ - u8 pad2; - u32 wlc_index; /* optional for wlc index */ -}; - -struct wl_interface_create_v3 { - u16 ver; /* structure version */ - u16 len; /* length of structure + data */ - u16 fixed_len; /* length of structure */ - u8 iftype; /* type of interface created */ - u8 wlc_index; /* optional for wlc index */ - u32 flags; /* flags for operation */ - u8 mac_addr[ETH_ALEN]; /* MAC address */ - u8 bssid[ETH_ALEN]; /* optional for BSSID */ - u8 if_index; /* interface index request */ - u8 pad[3]; - u8 data[]; /* Optional for specific data */ -}; - static u8 nl80211_band_to_fwil(enum nl80211_band band) { switch (band) { @@ -316,6 +320,8 @@ static u8 nl80211_band_to_fwil(enum nl80211_band band) return WLC_BAND_2G; case NL80211_BAND_5GHZ: return WLC_BAND_5G; + case NL80211_BAND_6GHZ: + return WLC_BAND_6G; default: WARN_ON(1); break; @@ -323,8 +329,25 @@ static u8 nl80211_band_to_fwil(enum nl80211_band band) return 0; } -static u16 chandef_to_chanspec(struct brcmu_d11inf *d11inf, - struct cfg80211_chan_def *ch) +static int nl80211_band_to_chanspec_band(enum nl80211_band band) +{ + switch (band) { + case NL80211_BAND_2GHZ: + return BRCMU_CHAN_BAND_2G; + case NL80211_BAND_5GHZ: + return BRCMU_CHAN_BAND_5G; + case NL80211_BAND_6GHZ: + return BRCMU_CHAN_BAND_6G; + case NL80211_BAND_60GHZ: + default: + WARN_ON_ONCE(1); + // Choose a safe default + return BRCMU_CHAN_BAND_2G; + } +} + +u16 chandef_to_chanspec(struct brcmu_d11inf *d11inf, + struct cfg80211_chan_def *ch) { struct brcmu_chan ch_inf; s32 primary_offset; @@ -382,17 +405,7 @@ static u16 chandef_to_chanspec(struct brcmu_d11inf *d11inf, default: WARN_ON_ONCE(1); } - switch (ch->chan->band) { - case NL80211_BAND_2GHZ: - ch_inf.band = BRCMU_CHAN_BAND_2G; - break; - case NL80211_BAND_5GHZ: - ch_inf.band = BRCMU_CHAN_BAND_5G; - break; - case NL80211_BAND_60GHZ: - default: - WARN_ON_ONCE(1); - } + ch_inf.band = nl80211_band_to_chanspec_band(ch->chan->band); d11inf->encchspec(&ch_inf); brcmf_dbg(TRACE, "chanspec: 0x%x\n", ch_inf.chspec); @@ -404,6 +417,7 @@ u16 channel_to_chanspec(struct brcmu_d11inf *d11inf, { struct brcmu_chan ch_inf; + ch_inf.band = nl80211_band_to_chanspec_band(ch->band); ch_inf.chnum = ieee80211_frequency_to_channel(ch->center_freq); ch_inf.bw = BRCMU_CHAN_BW_20; d11inf->encchspec(&ch_inf); @@ -581,231 +595,6 @@ brcmf_cfg80211_update_proto_addr_mode(struct wireless_dev *wdev) ADDR_INDIRECT); } -static int brcmf_get_first_free_bsscfgidx(struct brcmf_pub *drvr) -{ - int bsscfgidx; - - for (bsscfgidx = 0; bsscfgidx < BRCMF_MAX_IFS; bsscfgidx++) { - /* bsscfgidx 1 is reserved for legacy P2P */ - if (bsscfgidx == 1) - continue; - if (!drvr->iflist[bsscfgidx]) - return bsscfgidx; - } - - return -ENOMEM; -} - -static void brcmf_set_vif_sta_macaddr(struct brcmf_if *ifp, u8 *mac_addr) -{ - u8 mac_idx = ifp->drvr->sta_mac_idx; - - /* set difference MAC address with locally administered bit */ - memcpy(mac_addr, ifp->mac_addr, ETH_ALEN); - mac_addr[0] |= 0x02; - mac_addr[3] ^= mac_idx ? 0xC0 : 0xA0; - mac_idx++; - mac_idx = mac_idx % 2; - ifp->drvr->sta_mac_idx = mac_idx; -} - -static int brcmf_cfg80211_request_sta_if(struct brcmf_if *ifp, u8 *macaddr) -{ - struct wl_interface_create_v1 iface_v1; - struct wl_interface_create_v2 iface_v2; - struct wl_interface_create_v3 iface_v3; - u32 iface_create_ver; - int err; - - /* interface_create version 1 */ - memset(&iface_v1, 0, sizeof(iface_v1)); - iface_v1.ver = WL_INTERFACE_CREATE_VER_1; - iface_v1.flags = WL_INTERFACE_CREATE_STA | - WL_INTERFACE_MAC_USE; - if (!is_zero_ether_addr(macaddr)) - memcpy(iface_v1.mac_addr, macaddr, ETH_ALEN); - else - brcmf_set_vif_sta_macaddr(ifp, iface_v1.mac_addr); - - err = brcmf_fil_iovar_data_get(ifp, "interface_create", - &iface_v1, - sizeof(iface_v1)); - if (err) { - brcmf_info("failed to create interface(v1), err=%d\n", - err); - } else { - brcmf_dbg(INFO, "interface created(v1)\n"); - return 0; - } - - /* interface_create version 2 */ - memset(&iface_v2, 0, sizeof(iface_v2)); - iface_v2.ver = WL_INTERFACE_CREATE_VER_2; - iface_v2.flags = WL_INTERFACE_MAC_USE; - iface_v2.iftype = WL_INTERFACE_CREATE_STA; - if (!is_zero_ether_addr(macaddr)) - memcpy(iface_v2.mac_addr, macaddr, ETH_ALEN); - else - brcmf_set_vif_sta_macaddr(ifp, iface_v2.mac_addr); - - err = brcmf_fil_iovar_data_get(ifp, "interface_create", - &iface_v2, - sizeof(iface_v2)); - if (err) { - brcmf_info("failed to create interface(v2), err=%d\n", - err); - } else { - brcmf_dbg(INFO, "interface created(v2)\n"); - return 0; - } - - /* interface_create version 3+ */ - /* get supported version from firmware side */ - iface_create_ver = 0; - err = brcmf_fil_bsscfg_int_query(ifp, "interface_create", - &iface_create_ver); - if (err) { - brcmf_err("fail to get supported version, err=%d\n", err); - return -EOPNOTSUPP; - } - - switch (iface_create_ver) { - case WL_INTERFACE_CREATE_VER_3: - memset(&iface_v3, 0, sizeof(iface_v3)); - iface_v3.ver = WL_INTERFACE_CREATE_VER_3; - iface_v3.flags = WL_INTERFACE_MAC_USE; - iface_v3.iftype = WL_INTERFACE_CREATE_STA; - if (!is_zero_ether_addr(macaddr)) - memcpy(iface_v3.mac_addr, macaddr, ETH_ALEN); - else - brcmf_set_vif_sta_macaddr(ifp, iface_v3.mac_addr); - - err = brcmf_fil_iovar_data_get(ifp, "interface_create", - &iface_v3, - sizeof(iface_v3)); - - if (!err) - brcmf_dbg(INFO, "interface created(v3)\n"); - break; - default: - brcmf_err("not support interface create(v%d)\n", - iface_create_ver); - err = -EOPNOTSUPP; - break; - } - - if (err) { - brcmf_info("station interface creation failed (%d)\n", - err); - return -EIO; - } - - return 0; -} - -static int brcmf_cfg80211_request_ap_if(struct brcmf_if *ifp) -{ - struct wl_interface_create_v1 iface_v1; - struct wl_interface_create_v2 iface_v2; - struct wl_interface_create_v3 iface_v3; - u32 iface_create_ver; - struct brcmf_pub *drvr = ifp->drvr; - struct brcmf_mbss_ssid_le mbss_ssid_le; - int bsscfgidx; - int err; - - /* interface_create version 1 */ - memset(&iface_v1, 0, sizeof(iface_v1)); - iface_v1.ver = WL_INTERFACE_CREATE_VER_1; - iface_v1.flags = WL_INTERFACE_CREATE_AP | - WL_INTERFACE_MAC_USE; - - brcmf_set_vif_sta_macaddr(ifp, iface_v1.mac_addr); - - err = brcmf_fil_iovar_data_get(ifp, "interface_create", - &iface_v1, - sizeof(iface_v1)); - if (err) { - brcmf_info("failed to create interface(v1), err=%d\n", - err); - } else { - brcmf_dbg(INFO, "interface created(v1)\n"); - return 0; - } - - /* interface_create version 2 */ - memset(&iface_v2, 0, sizeof(iface_v2)); - iface_v2.ver = WL_INTERFACE_CREATE_VER_2; - iface_v2.flags = WL_INTERFACE_MAC_USE; - iface_v2.iftype = WL_INTERFACE_CREATE_AP; - - brcmf_set_vif_sta_macaddr(ifp, iface_v2.mac_addr); - - err = brcmf_fil_iovar_data_get(ifp, "interface_create", - &iface_v2, - sizeof(iface_v2)); - if (err) { - brcmf_info("failed to create interface(v2), err=%d\n", - err); - } else { - brcmf_dbg(INFO, "interface created(v2)\n"); - return 0; - } - - /* interface_create version 3+ */ - /* get supported version from firmware side */ - iface_create_ver = 0; - err = brcmf_fil_bsscfg_int_query(ifp, "interface_create", - &iface_create_ver); - if (err) { - brcmf_err("fail to get supported version, err=%d\n", err); - return -EOPNOTSUPP; - } - - switch (iface_create_ver) { - case WL_INTERFACE_CREATE_VER_3: - memset(&iface_v3, 0, sizeof(iface_v3)); - iface_v3.ver = WL_INTERFACE_CREATE_VER_3; - iface_v3.flags = WL_INTERFACE_MAC_USE; - iface_v3.iftype = WL_INTERFACE_CREATE_AP; - brcmf_set_vif_sta_macaddr(ifp, iface_v3.mac_addr); - - err = brcmf_fil_iovar_data_get(ifp, "interface_create", - &iface_v3, - sizeof(iface_v3)); - - if (!err) - brcmf_dbg(INFO, "interface created(v3)\n"); - break; - default: - brcmf_err("not support interface create(v%d)\n", - iface_create_ver); - err = -EOPNOTSUPP; - break; - } - - if (err) { - brcmf_info("Does not support interface_create (%d)\n", - err); - memset(&mbss_ssid_le, 0, sizeof(mbss_ssid_le)); - bsscfgidx = brcmf_get_first_free_bsscfgidx(ifp->drvr); - if (bsscfgidx < 0) - return bsscfgidx; - - mbss_ssid_le.bsscfgidx = cpu_to_le32(bsscfgidx); - mbss_ssid_le.SSID_len = cpu_to_le32(5); - sprintf(mbss_ssid_le.SSID, "ssid%d", bsscfgidx); - - err = brcmf_fil_bsscfg_data_set(ifp, "bsscfg:ssid", &mbss_ssid_le, - sizeof(mbss_ssid_le)); - - if (err < 0) - bphy_err(drvr, "setting ssid failed %d\n", err); - } - - return err; -} - /** * brcmf_apsta_add_vif() - create a new AP or STA virtual interface * @@ -1058,134 +847,11 @@ bool brcmf_is_apmode_operating(struct wiphy *wiphy) return ret; } -static void brcmf_scan_params_v2_to_v1(struct brcmf_scan_params_v2_le *params_v2_le, - struct brcmf_scan_params_le *params_le) -{ - size_t params_size; - u32 ch; - int n_channels, n_ssids; - - memcpy(¶ms_le->ssid_le, ¶ms_v2_le->ssid_le, - sizeof(params_le->ssid_le)); - memcpy(¶ms_le->bssid, ¶ms_v2_le->bssid, - sizeof(params_le->bssid)); - - params_le->bss_type = params_v2_le->bss_type; - params_le->scan_type = le32_to_cpu(params_v2_le->scan_type); - params_le->nprobes = params_v2_le->nprobes; - params_le->active_time = params_v2_le->active_time; - params_le->passive_time = params_v2_le->passive_time; - params_le->home_time = params_v2_le->home_time; - params_le->channel_num = params_v2_le->channel_num; - - ch = le32_to_cpu(params_v2_le->channel_num); - n_channels = ch & BRCMF_SCAN_PARAMS_COUNT_MASK; - n_ssids = ch >> BRCMF_SCAN_PARAMS_NSSID_SHIFT; - - params_size = sizeof(u16) * n_channels; - if (n_ssids > 0) { - params_size = roundup(params_size, sizeof(u32)); - params_size += sizeof(struct brcmf_ssid_le) * n_ssids; - } - - memcpy(¶ms_le->channel_list[0], - ¶ms_v2_le->channel_list[0], params_size); -} - -static void brcmf_escan_prep(struct brcmf_cfg80211_info *cfg, - struct brcmf_scan_params_v2_le *params_le, - struct cfg80211_scan_request *request) -{ - u32 n_ssids; - u32 n_channels; - s32 i; - s32 offset; - u16 chanspec; - char *ptr; - int length; - struct brcmf_ssid_le ssid_le; - - eth_broadcast_addr(params_le->bssid); - - length = BRCMF_SCAN_PARAMS_V2_FIXED_SIZE; - - params_le->version = cpu_to_le16(BRCMF_SCAN_PARAMS_VERSION_V2); - params_le->bss_type = DOT11_BSSTYPE_ANY; - params_le->scan_type = cpu_to_le32(BRCMF_SCANTYPE_ACTIVE); - params_le->channel_num = 0; - params_le->nprobes = cpu_to_le32(-1); - params_le->active_time = cpu_to_le32(-1); - params_le->passive_time = cpu_to_le32(-1); - params_le->home_time = cpu_to_le32(-1); - memset(¶ms_le->ssid_le, 0, sizeof(params_le->ssid_le)); - - /* Scan abort */ - if (!request) { - length += sizeof(u16); - params_le->channel_num = cpu_to_le32(1); - params_le->channel_list[0] = cpu_to_le16(-1); - params_le->length = cpu_to_le16(length); - return; - } - - n_ssids = request->n_ssids; - n_channels = request->n_channels; - - /* Copy channel array if applicable */ - brcmf_dbg(SCAN, "### List of channelspecs to scan ### %d\n", - n_channels); - if (n_channels > 0) { - length += roundup(sizeof(u16) * n_channels, sizeof(u32)); - for (i = 0; i < n_channels; i++) { - chanspec = channel_to_chanspec(&cfg->d11inf, - request->channels[i]); - brcmf_dbg(SCAN, "Chan : %d, Channel spec: %x\n", - request->channels[i]->hw_value, chanspec); - params_le->channel_list[i] = cpu_to_le16(chanspec); - } - } else { - brcmf_dbg(SCAN, "Scanning all channels\n"); - } - - /* Copy ssid array if applicable */ - brcmf_dbg(SCAN, "### List of SSIDs to scan ### %d\n", n_ssids); - if (n_ssids > 0) { - offset = offsetof(struct brcmf_scan_params_v2_le, channel_list) + - n_channels * sizeof(u16); - offset = roundup(offset, sizeof(u32)); - length += sizeof(ssid_le) * n_ssids; - ptr = (char *)params_le + offset; - for (i = 0; i < n_ssids; i++) { - memset(&ssid_le, 0, sizeof(ssid_le)); - ssid_le.SSID_len = - cpu_to_le32(request->ssids[i].ssid_len); - memcpy(ssid_le.SSID, request->ssids[i].ssid, - request->ssids[i].ssid_len); - if (!ssid_le.SSID_len) - brcmf_dbg(SCAN, "%d: Broadcast scan\n", i); - else - brcmf_dbg(SCAN, "%d: scan for %.32s size=%d\n", - i, ssid_le.SSID, ssid_le.SSID_len); - memcpy(ptr, &ssid_le, sizeof(ssid_le)); - ptr += sizeof(ssid_le); - } - } else { - brcmf_dbg(SCAN, "Performing passive scan\n"); - params_le->scan_type = cpu_to_le32(BRCMF_SCANTYPE_PASSIVE); - } - params_le->length = cpu_to_le16(length); - /* Adding mask to channel numbers */ - params_le->channel_num = - cpu_to_le32((n_ssids << BRCMF_SCAN_PARAMS_NSSID_SHIFT) | - (n_channels & BRCMF_SCAN_PARAMS_COUNT_MASK)); -} - s32 brcmf_notify_escan_complete(struct brcmf_cfg80211_info *cfg, struct brcmf_if *ifp, bool aborted, bool fw_abort) { struct brcmf_pub *drvr = cfg->pub; - struct brcmf_scan_params_v2_le params_v2_le; struct cfg80211_scan_request *scan_request; u64 reqid; u32 bucket; @@ -1201,25 +867,16 @@ s32 brcmf_notify_escan_complete(struct brcmf_cfg80211_info *cfg, timer_delete_sync(&cfg->escan_timeout); if (fw_abort) { + u32 len; + void *data = drvr->scan_param_handler.get_struct_for_request(cfg, &len, NULL); + if (!data){ + bphy_err(drvr, "Scan abort failed to prepare abort struct\n"); + return 0; + } /* Do a scan abort to stop the driver's scan engine */ brcmf_dbg(SCAN, "ABORT scan in firmware\n"); - - brcmf_escan_prep(cfg, ¶ms_v2_le, NULL); - - /* E-Scan (or anyother type) can be aborted by SCAN */ - if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_SCAN_V2)) { - err = brcmf_fil_cmd_data_set(ifp, BRCMF_C_SCAN, - ¶ms_v2_le, - sizeof(params_v2_le)); - } else { - struct brcmf_scan_params_le params_le; - - brcmf_scan_params_v2_to_v1(¶ms_v2_le, ¶ms_le); - err = brcmf_fil_cmd_data_set(ifp, BRCMF_C_SCAN, - ¶ms_le, - sizeof(params_le)); - } - + err = brcmf_fil_cmd_data_set(ifp, BRCMF_C_SCAN, data, len); + kfree(data); if (err) bphy_err(drvr, "Scan abort failed\n"); } @@ -1443,19 +1100,24 @@ brcmf_run_escan(struct brcmf_cfg80211_info *cfg, struct brcmf_if *ifp, struct cfg80211_scan_request *request) { struct brcmf_pub *drvr = cfg->pub; - s32 params_size = BRCMF_SCAN_PARAMS_V2_FIXED_SIZE + - offsetof(struct brcmf_escan_params_le, params_v2_le); + u32 struct_size = 0; + void *prepped_params = NULL; + u32 params_size = 0; struct brcmf_escan_params_le *params; s32 err = 0; brcmf_dbg(SCAN, "E-SCAN START\n"); - if (request != NULL) { - /* Allocate space for populating ssids in struct */ - params_size += sizeof(u32) * ((request->n_channels + 1) / 2); - - /* Allocate space for populating ssids in struct */ - params_size += sizeof(struct brcmf_ssid_le) * request->n_ssids; + prepped_params = drvr->scan_param_handler.get_struct_for_request(cfg, &struct_size, request); + if (!prepped_params) { + err = -EINVAL; + goto exit; + } + params_size = struct_size + + offsetof(struct brcmf_escan_params_le, params_v4_le); + if (!params_size) { + err = -EINVAL; + goto exit; } params = kzalloc(params_size, GFP_KERNEL); @@ -1463,27 +1125,14 @@ brcmf_run_escan(struct brcmf_cfg80211_info *cfg, struct brcmf_if *ifp, err = -ENOMEM; goto exit; } - BUG_ON(params_size + sizeof("escan") >= BRCMF_DCMD_MEDLEN); - brcmf_escan_prep(cfg, ¶ms->params_v2_le, request); - - params->version = cpu_to_le32(BRCMF_ESCAN_REQ_VERSION_V2); - - if (!brcmf_feat_is_enabled(ifp, BRCMF_FEAT_SCAN_V2)) { - struct brcmf_escan_params_le *params_v1; - - params_size -= BRCMF_SCAN_PARAMS_V2_FIXED_SIZE; - params_size += BRCMF_SCAN_PARAMS_FIXED_SIZE; - params_v1 = kzalloc(params_size, GFP_KERNEL); - if (!params_v1) { - err = -ENOMEM; - goto exit_params; - } - params_v1->version = cpu_to_le32(BRCMF_ESCAN_REQ_VERSION); - brcmf_scan_params_v2_to_v1(¶ms->params_v2_le, ¶ms_v1->params_le); - kfree(params); - params = params_v1; - } + /* Copy into the largest part */ + unsafe_memcpy( + ¶ms->params_v4_le, prepped_params, struct_size, + /* A composite flex-array that is at least as large as the memcpy due to the allocation above */); + /* We can now free the original prepped parameters */ + kfree(prepped_params); + params->version = cpu_to_le32(drvr->scan_param_handler.version); params->action = cpu_to_le16(WL_ESCAN_ACTION_START); params->sync_id = cpu_to_le16(0x1234); @@ -1495,7 +1144,6 @@ brcmf_run_escan(struct brcmf_cfg80211_info *cfg, struct brcmf_if *ifp, bphy_err(drvr, "error (%d)\n", err); } -exit_params: kfree(params); exit: return err; @@ -1779,21 +1427,19 @@ static void brcmf_link_down(struct brcmf_cfg80211_vif *vif, u16 reason, brcmf_dbg(TRACE, "Exit\n"); } -static s32 -brcmf_cfg80211_join_ibss(struct wiphy *wiphy, struct net_device *ndev, - struct cfg80211_ibss_params *params) +static s32 brcmf_cfg80211_join_ibss(struct wiphy *wiphy, + struct net_device *ndev, + struct cfg80211_ibss_params *params) { struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy); struct brcmf_if *ifp = netdev_priv(ndev); struct brcmf_cfg80211_profile *profile = &ifp->vif->profile; struct brcmf_pub *drvr = cfg->pub; - struct brcmf_join_params join_params; - size_t join_params_size = 0; - s32 err = 0; + void *join_params; + u32 join_params_size = 0; s32 wsec = 0; s32 bcnprd; - u16 chanspec; - u32 ssid_len; + s32 err = 0; brcmf_dbg(TRACE, "Enter\n"); if (!check_vif_up(ifp->vif)) @@ -1867,58 +1513,39 @@ brcmf_cfg80211_join_ibss(struct wiphy *wiphy, struct net_device *ndev, goto done; } - /* Configure required join parameter */ - memset(&join_params, 0, sizeof(struct brcmf_join_params)); - - /* SSID */ - ssid_len = min_t(u32, params->ssid_len, IEEE80211_MAX_SSID_LEN); - memcpy(join_params.ssid_le.SSID, params->ssid, ssid_len); - join_params.ssid_le.SSID_len = cpu_to_le32(ssid_len); - join_params_size = sizeof(join_params.ssid_le); - - /* BSSID */ if (params->bssid) { - memcpy(join_params.params_le.bssid, params->bssid, ETH_ALEN); - join_params_size += BRCMF_ASSOC_PARAMS_FIXED_SIZE; memcpy(profile->bssid, params->bssid, ETH_ALEN); } else { - eth_broadcast_addr(join_params.params_le.bssid); eth_zero_addr(profile->bssid); } - /* Channel */ + cfg->ibss_starter = false; + cfg->channel = 0; if (params->chandef.chan) { - u32 target_channel; + u16 chanspec; + cfg->channel = ieee80211_frequency_to_channel( + params->chandef.chan->center_freq); + /* adding chanspec */ + chanspec = chandef_to_chanspec(&cfg->d11inf, ¶ms->chandef); - cfg->channel = - ieee80211_frequency_to_channel( - params->chandef.chan->center_freq); - if (params->channel_fixed) { - /* adding chanspec */ - chanspec = chandef_to_chanspec(&cfg->d11inf, - ¶ms->chandef); - join_params.params_le.chanspec_list[0] = - cpu_to_le16(chanspec); - join_params.params_le.chanspec_num = cpu_to_le32(1); - join_params_size += sizeof(join_params.params_le); - } - - /* set channel for starter */ - target_channel = cfg->channel; - err = brcmf_fil_cmd_int_set(ifp, BRCMF_C_SET_CHANNEL, - target_channel); + /* set chanspec */ + err = brcmf_fil_iovar_int_set(ifp, "chanspec", chanspec); if (err) { - bphy_err(drvr, "WLC_SET_CHANNEL failed (%d)\n", err); + bphy_err(drvr, "Setting chanspec failed (%d)\n", err); goto done; } - } else - cfg->channel = 0; - - cfg->ibss_starter = false; - + } - err = brcmf_fil_cmd_data_set(ifp, BRCMF_C_SET_SSID, - &join_params, join_params_size); + join_params = drvr->join_param_handler.get_struct_for_ibss( + cfg, &join_params_size, params); + if (!join_params) { + bphy_err(drvr, "Converting join params failed\n"); + goto done; + } + err = brcmf_fil_cmd_data_set(ifp, BRCMF_C_SET_SSID, join_params, + join_params_size); + /* Free params no matter what */ + kfree(join_params); if (err) { bphy_err(drvr, "WLC_SET_SSID failed (%d)\n", err); goto done; @@ -1969,6 +1596,10 @@ static s32 brcmf_set_wpa_version(struct net_device *ndev, if (drvr->bus_if->fwvid == BRCMF_FWVENDOR_CYW && sme->crypto.akm_suites[0] == WLAN_AKM_SUITE_SAE) val = WPA3_AUTH_SAE_PSK; + else if (sme->crypto.akm_suites[0] == WLAN_AKM_SUITE_SAE) + val = WPA3_AUTH_SAE_PSK; + else if (sme->crypto.akm_suites[0] == WLAN_AKM_SUITE_OWE) + val = WPA3_AUTH_OWE; else val = WPA2_AUTH_PSK | WPA2_AUTH_UNSPECIFIED; } else if (sme->crypto.wpa_versions & NL80211_WPA_VERSION_3) { @@ -2026,6 +1657,48 @@ static s32 brcmf_set_auth_type(struct net_device *ndev, return err; } +static s32 brcmf_set_wsec_info_algos(struct brcmf_if *ifp, u32 algos, u32 mask) +{ + struct brcmf_pub *drvr = ifp->drvr; + s32 err = 0; + struct brcmf_wsec_info *wsec_info; + struct brcmf_xtlv *wsec_info_tlv; + u16 tlv_data_len; + u8 tlv_data[8]; + u32 param_len; + u8 *buf; + + brcmf_dbg(TRACE, "Enter\n"); + + buf = kzalloc(sizeof(struct brcmf_wsec_info) + sizeof(tlv_data), + GFP_KERNEL); + if (!buf) { + bphy_err(drvr, "unable to allocate.\n"); + return -ENOMEM; + } + wsec_info = (struct brcmf_wsec_info *)buf; + wsec_info->version = BRCMF_WSEC_INFO_VER; + wsec_info_tlv = + (struct brcmf_xtlv *)(buf + + offsetof(struct brcmf_wsec_info, tlvs)); + wsec_info->num_tlvs++; + tlv_data_len = sizeof(tlv_data); + memcpy(tlv_data, &algos, sizeof(algos)); + memcpy(tlv_data + sizeof(algos), &mask, sizeof(mask)); + brcmf_xtlv_pack_header(wsec_info_tlv, WL_WSEC_INFO_BSS_ALGOS, + tlv_data_len, tlv_data, 0); + + param_len = offsetof(struct brcmf_wsec_info, tlvs) + + offsetof(struct brcmf_wsec_info_tlv, data) + tlv_data_len; + + err = brcmf_fil_bsscfg_data_set(ifp, "wsec_info", buf, param_len); + if (err) + brcmf_err("set wsec_info_error:%d\n", err); + + kfree(buf); + return err; +} + static s32 brcmf_set_wsec_mode(struct net_device *ndev, struct cfg80211_connect_params *sme) @@ -2038,6 +1711,8 @@ brcmf_set_wsec_mode(struct net_device *ndev, s32 gval = 0; s32 wsec; s32 err = 0; + u32 algos = 0; + u32 mask = 0; if (sme->crypto.n_ciphers_pairwise) { switch (sme->crypto.ciphers_pairwise[0]) { @@ -2054,6 +1729,15 @@ brcmf_set_wsec_mode(struct net_device *ndev, case WLAN_CIPHER_SUITE_AES_CMAC: pval = AES_ENABLED; break; + case WLAN_CIPHER_SUITE_GCMP_256: + if (!brcmf_feat_is_enabled(ifp, BRCMF_FEAT_GCMP)) { + brcmf_err("This chip does not support GCMP\n"); + return -EOPNOTSUPP; + } + pval = AES_ENABLED; + algos = KEY_ALGO_MASK(CRYPTO_ALGO_AES_GCM256); + mask = algos | KEY_ALGO_MASK(CRYPTO_ALGO_AES_CCM); + break; default: bphy_err(drvr, "invalid cipher pairwise (%d)\n", sme->crypto.ciphers_pairwise[0]); @@ -2075,6 +1759,15 @@ brcmf_set_wsec_mode(struct net_device *ndev, case WLAN_CIPHER_SUITE_AES_CMAC: gval = AES_ENABLED; break; + case WLAN_CIPHER_SUITE_GCMP_256: + if (!brcmf_feat_is_enabled(ifp, BRCMF_FEAT_GCMP)) { + brcmf_err("This chip does not support GCMP\n"); + return -EOPNOTSUPP; + } + gval = AES_ENABLED; + algos = KEY_ALGO_MASK(CRYPTO_ALGO_AES_GCM256); + mask = algos | KEY_ALGO_MASK(CRYPTO_ALGO_AES_CCM); + break; default: bphy_err(drvr, "invalid cipher group (%d)\n", sme->crypto.cipher_group); @@ -2083,6 +1776,7 @@ brcmf_set_wsec_mode(struct net_device *ndev, } brcmf_dbg(CONN, "pval (%d) gval (%d)\n", pval, gval); + brcmf_dbg(CONN, "algos (0x%x) mask (0x%x)\n", algos, mask); /* In case of privacy, but no security and WPS then simulate */ /* setting AES. WPS-2.0 allows no security */ if (brcmf_find_wpsie(sme->ie, sme->ie_len) && !pval && !gval && @@ -2095,6 +1789,15 @@ brcmf_set_wsec_mode(struct net_device *ndev, bphy_err(drvr, "error (%d)\n", err); return err; } + if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_GCMP)) { + brcmf_dbg(CONN, "set_wsec_info algos (0x%x) mask (0x%x)\n", + algos, mask); + err = brcmf_set_wsec_info_algos(ifp, algos, mask); + if (err) { + brcmf_err("set wsec_info error (%d)\n", err); + return err; + } + } sec = &profile->sec; sec->cipher_pairwise = sme->crypto.ciphers_pairwise[0]; @@ -2118,9 +1821,13 @@ brcmf_set_key_mgmt(struct net_device *ndev, struct cfg80211_connect_params *sme) u16 rsn_cap; u32 mfp; u16 count; + s32 okc_enable; + u16 pmkid_count; + const u8 *group_mgmt_cs = NULL; profile->use_fwsup = BRCMF_PROFILE_FWSUP_NONE; profile->is_ft = false; + profile->is_okc = false; if (!sme->crypto.n_akm_suites) return 0; @@ -2137,13 +1844,15 @@ brcmf_set_key_mgmt(struct net_device *ndev, struct cfg80211_connect_params *sme) val = WPA_AUTH_UNSPECIFIED; if (sme->want_1x) profile->use_fwsup = BRCMF_PROFILE_FWSUP_1X; + else + profile->use_fwsup = BRCMF_PROFILE_FWSUP_ROAM; break; case WLAN_AKM_SUITE_PSK: val = WPA_AUTH_PSK; break; default: - bphy_err(drvr, "invalid akm suite (%d)\n", - sme->crypto.akm_suites[0]); + bphy_err(drvr, "invalid cipher group (%d)\n", + sme->crypto.cipher_group); return -EINVAL; } } else if (val & (WPA2_AUTH_PSK | WPA2_AUTH_UNSPECIFIED)) { @@ -2152,11 +1861,15 @@ brcmf_set_key_mgmt(struct net_device *ndev, struct cfg80211_connect_params *sme) val = WPA2_AUTH_UNSPECIFIED; if (sme->want_1x) profile->use_fwsup = BRCMF_PROFILE_FWSUP_1X; + else + profile->use_fwsup = BRCMF_PROFILE_FWSUP_ROAM; break; case WLAN_AKM_SUITE_8021X_SHA256: val = WPA2_AUTH_1X_SHA256; if (sme->want_1x) profile->use_fwsup = BRCMF_PROFILE_FWSUP_1X; + else + profile->use_fwsup = BRCMF_PROFILE_FWSUP_ROAM; break; case WLAN_AKM_SUITE_PSK_SHA256: val = WPA2_AUTH_PSK_SHA256; @@ -2169,14 +1882,35 @@ brcmf_set_key_mgmt(struct net_device *ndev, struct cfg80211_connect_params *sme) profile->is_ft = true; if (sme->want_1x) profile->use_fwsup = BRCMF_PROFILE_FWSUP_1X; + else + profile->use_fwsup = BRCMF_PROFILE_FWSUP_ROAM; break; case WLAN_AKM_SUITE_FT_PSK: val = WPA2_AUTH_PSK | WPA2_AUTH_FT; profile->is_ft = true; + if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_FWSUP)) + profile->use_fwsup = BRCMF_PROFILE_FWSUP_PSK; + else + profile->use_fwsup = BRCMF_PROFILE_FWSUP_ROAM; + break; + case WLAN_AKM_SUITE_DPP: + val = WFA_AUTH_DPP; + profile->use_fwsup = BRCMF_PROFILE_FWSUP_NONE; + break; + case WLAN_AKM_SUITE_OWE: + val = WPA3_AUTH_OWE; + profile->use_fwsup = BRCMF_PROFILE_FWSUP_ROAM; + break; + case WLAN_AKM_SUITE_8021X_SUITE_B_192: + val = WPA3_AUTH_1X_SUITE_B_SHA384; + if (sme->want_1x) + profile->use_fwsup = BRCMF_PROFILE_FWSUP_1X; + else + profile->use_fwsup = BRCMF_PROFILE_FWSUP_ROAM; break; default: - bphy_err(drvr, "invalid akm suite (%d)\n", - sme->crypto.akm_suites[0]); + bphy_err(drvr, "invalid cipher group (%d)\n", + sme->crypto.cipher_group); return -EINVAL; } } else if (val & WPA3_AUTH_SAE_PSK) { @@ -2189,17 +1923,38 @@ brcmf_set_key_mgmt(struct net_device *ndev, struct cfg80211_connect_params *sme) profile->is_ft = true; break; default: - bphy_err(drvr, "invalid akm suite (%d)\n", - sme->crypto.akm_suites[0]); + bphy_err(drvr, "invalid cipher group (%d)\n", + sme->crypto.cipher_group); return -EINVAL; } if (sme->crypto.sae_pwd) { profile->use_fwsup = BRCMF_PROFILE_FWSUP_SAE; } } - - if (profile->use_fwsup == BRCMF_PROFILE_FWSUP_1X) + if ((profile->use_fwsup == BRCMF_PROFILE_FWSUP_1X) || + (profile->use_fwsup == BRCMF_PROFILE_FWSUP_ROAM)) { brcmf_dbg(INFO, "using 1X offload\n"); + err = brcmf_fil_bsscfg_int_get(netdev_priv(ndev), "okc_enable", + &okc_enable); + if (err) { + bphy_err(drvr, "get okc_enable failed (%d)\n", err); + } else { + brcmf_dbg(INFO, "get okc_enable (%d)\n", okc_enable); + profile->is_okc = okc_enable; + } + } else if (profile->use_fwsup != BRCMF_PROFILE_FWSUP_SAE && + (val == WPA3_AUTH_SAE_PSK)) { + brcmf_dbg(INFO, "not using SAE offload\n"); + err = brcmf_fil_bsscfg_int_get(netdev_priv(ndev), "okc_enable", + &okc_enable); + if (err) { + bphy_err(drvr, "get okc_enable failed (%d)\n", err); + } else { + brcmf_dbg(INFO, "get okc_enable (%d)\n", okc_enable); + profile->is_okc = okc_enable; + } + } + if (profile->use_fwsup == BRCMF_PROFILE_FWSUP_SAE) brcmf_dbg(INFO, "using SAE offload\n"); @@ -2235,14 +1990,47 @@ brcmf_set_key_mgmt(struct net_device *ndev, struct cfg80211_connect_params *sme) mfp = BRCMF_MFP_REQUIRED; else if (rsn_cap & RSN_CAP_MFPC_MASK) mfp = BRCMF_MFP_CAPABLE; + /* In case of dpp, very low tput is observed if MFPC is set in + * firmmare. Firmware needs to ensure that MFPC is not set when + * MFPR was requested from fmac. However since this change being + * specific to DPP, fmac needs to set wpa_auth prior to mfp, so + * that firmware can use this info to prevent MFPC being set in + * case of dpp. + */ + if (val == WFA_AUTH_DPP) { + brcmf_dbg(CONN, "setting wpa_auth to 0x%0x\n", val); + err = brcmf_fil_bsscfg_int_set(netdev_priv(ndev), "wpa_auth", + val); + if (err) { + bphy_err(drvr, "could not set wpa_auth (%d)\n", err); + return err; + } + } + brcmf_fil_bsscfg_int_set(netdev_priv(ndev), "mfp", mfp); + offset += RSN_CAP_LEN; + if (mfp && (ie_len - offset >= RSN_PMKID_COUNT_LEN)) { + pmkid_count = ie[offset] + (ie[offset + 1] << 8); + offset += RSN_PMKID_COUNT_LEN + (pmkid_count * WLAN_PMKID_LEN); + if (ie_len - offset >= WPA_IE_MIN_OUI_LEN) { + group_mgmt_cs = &ie[offset]; + if (memcmp(group_mgmt_cs, RSN_OUI, TLV_OUI_LEN) == 0) { + brcmf_fil_bsscfg_data_set(ifp, "bip", + (void *)group_mgmt_cs, + WPA_IE_MIN_OUI_LEN); + } + } + } skip_mfp_config: - brcmf_dbg(CONN, "setting wpa_auth to 0x%0x\n", val); - err = brcmf_fil_bsscfg_int_set(netdev_priv(ndev), "wpa_auth", val); - if (err) { - bphy_err(drvr, "could not set wpa_auth (%d)\n", err); - return err; + if (val != WFA_AUTH_DPP) { + brcmf_dbg(CONN, "setting wpa_auth to 0x%0x\n", val); + err = brcmf_fil_bsscfg_int_set(netdev_priv(ndev), "wpa_auth", + val); + if (err) { + bphy_err(drvr, "could not set wpa_auth (%d)\n", err); + return err; + } } return err; @@ -2375,52 +2163,51 @@ static void brcmf_set_join_pref(struct brcmf_if *ifp, static s32 brcmf_cfg80211_connect(struct wiphy *wiphy, struct net_device *ndev, - struct cfg80211_connect_params *sme) + struct cfg80211_connect_params *params) { struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy); struct brcmf_if *ifp = netdev_priv(ndev); struct brcmf_cfg80211_profile *profile = &ifp->vif->profile; - struct ieee80211_channel *chan = sme->channel; + struct ieee80211_channel *chan = params->channel; struct brcmf_pub *drvr = ifp->drvr; - struct brcmf_join_params join_params; - size_t join_params_size; + void *join_params; + u32 join_params_size; + void *fallback_join_params; + u32 fallback_join_params_size; const struct brcmf_tlv *rsn_ie; const struct brcmf_vs_tlv *wpa_ie; const void *ie; u32 ie_len; - struct brcmf_ext_join_params_le *ext_join_params; - u16 chanspec; s32 err = 0; - u32 ssid_len; brcmf_dbg(TRACE, "Enter\n"); if (!check_vif_up(ifp->vif)) return -EIO; - if (!sme->ssid) { + if (!params->ssid) { bphy_err(drvr, "Invalid ssid\n"); return -EOPNOTSUPP; } - if (sme->channel_hint) - chan = sme->channel_hint; + if (params->channel_hint) + chan = params->channel_hint; - if (sme->bssid_hint) - sme->bssid = sme->bssid_hint; + if (params->bssid_hint) + params->bssid = params->bssid_hint; if (ifp->vif == cfg->p2p.bss_idx[P2PAPI_BSSCFG_PRIMARY].vif) { /* A normal (non P2P) connection request setup. */ ie = NULL; ie_len = 0; /* find the WPA_IE */ - wpa_ie = brcmf_find_wpaie((u8 *)sme->ie, sme->ie_len); + wpa_ie = brcmf_find_wpaie((u8 *)params->ie, params->ie_len); if (wpa_ie) { ie = wpa_ie; ie_len = wpa_ie->len + TLV_HDR_LEN; } else { /* find the RSN_IE */ - rsn_ie = brcmf_parse_tlvs((const u8 *)sme->ie, - sme->ie_len, + rsn_ie = brcmf_parse_tlvs((const u8 *)params->ie, + params->ie_len, WLAN_EID_RSN); if (rsn_ie) { ie = rsn_ie; @@ -2431,7 +2218,7 @@ brcmf_cfg80211_connect(struct wiphy *wiphy, struct net_device *ndev, } err = brcmf_vif_set_mgmt_ie(ifp->vif, BRCMF_VNDR_IE_ASSOCREQ_FLAG, - sme->ie, sme->ie_len); + params->ie, params->ie_len); if (err) bphy_err(drvr, "Set Assoc REQ IE Failed\n"); else @@ -2442,166 +2229,129 @@ brcmf_cfg80211_connect(struct wiphy *wiphy, struct net_device *ndev, if (chan) { cfg->channel = ieee80211_frequency_to_channel(chan->center_freq); - chanspec = channel_to_chanspec(&cfg->d11inf, chan); - brcmf_dbg(CONN, "channel=%d, center_req=%d, chanspec=0x%04x\n", - cfg->channel, chan->center_freq, chanspec); + brcmf_dbg(CONN, "channel=%d, center_req=%d\n", + cfg->channel, chan->center_freq); } else { cfg->channel = 0; - chanspec = 0; } - brcmf_dbg(INFO, "ie (%p), ie_len (%zd)\n", sme->ie, sme->ie_len); + brcmf_dbg(INFO, "ie (%p), ie_len (%zd)\n", params->ie, params->ie_len); - err = brcmf_set_wpa_version(ndev, sme); + err = brcmf_set_wpa_version(ndev, params); if (err) { bphy_err(drvr, "wl_set_wpa_version failed (%d)\n", err); goto done; } - sme->auth_type = brcmf_war_auth_type(ifp, sme->auth_type); - err = brcmf_set_auth_type(ndev, sme); + params->auth_type = brcmf_war_auth_type(ifp, params->auth_type); + err = brcmf_set_auth_type(ndev, params); if (err) { bphy_err(drvr, "wl_set_auth_type failed (%d)\n", err); goto done; } - err = brcmf_set_wsec_mode(ndev, sme); + err = brcmf_set_wsec_mode(ndev, params); if (err) { bphy_err(drvr, "wl_set_set_cipher failed (%d)\n", err); goto done; } - err = brcmf_set_key_mgmt(ndev, sme); + err = brcmf_set_key_mgmt(ndev, params); if (err) { bphy_err(drvr, "wl_set_key_mgmt failed (%d)\n", err); goto done; } - err = brcmf_set_sharedkey(ndev, sme); - if (err) { - bphy_err(drvr, "brcmf_set_sharedkey failed (%d)\n", err); - goto done; - } - - if (sme->crypto.psk && - profile->use_fwsup != BRCMF_PROFILE_FWSUP_SAE) { - if (WARN_ON(profile->use_fwsup != BRCMF_PROFILE_FWSUP_NONE)) { - err = -EINVAL; - goto done; - } - brcmf_dbg(INFO, "using PSK offload\n"); - profile->use_fwsup = BRCMF_PROFILE_FWSUP_PSK; - } - - if (profile->use_fwsup != BRCMF_PROFILE_FWSUP_NONE) { - /* enable firmware supplicant for this interface */ - err = brcmf_fil_iovar_int_set(ifp, "sup_wpa", 1); - if (err < 0) { - bphy_err(drvr, "failed to enable fw supplicant\n"); - goto done; - } - } - - if (profile->use_fwsup == BRCMF_PROFILE_FWSUP_PSK) - err = brcmf_set_pmk(ifp, sme->crypto.psk, - BRCMF_WSEC_MAX_PSK_LEN); - else if (profile->use_fwsup == BRCMF_PROFILE_FWSUP_SAE) { - /* clean up user-space RSNE */ - err = brcmf_fil_iovar_data_set(ifp, "wpaie", NULL, 0); - if (err) { - bphy_err(drvr, "failed to clean up user-space RSNE\n"); - goto done; - } - err = brcmf_fwvid_set_sae_password(ifp, &sme->crypto); - if (!err && sme->crypto.psk) - err = brcmf_set_pmk(ifp, sme->crypto.psk, - BRCMF_WSEC_MAX_PSK_LEN); - } - if (err) - goto done; - - /* Join with specific BSSID and cached SSID - * If SSID is zero join based on BSSID only - */ - join_params_size = offsetof(struct brcmf_ext_join_params_le, assoc_le) + - offsetof(struct brcmf_assoc_params_le, chanspec_list); - if (cfg->channel) - join_params_size += sizeof(u16); - ext_join_params = kzalloc(sizeof(*ext_join_params), GFP_KERNEL); - if (ext_join_params == NULL) { - err = -ENOMEM; + err = brcmf_set_sharedkey(ndev, params); + if (err) { + bphy_err(drvr, "brcmf_set_sharedkey failed (%d)\n", err); goto done; } - ssid_len = min_t(u32, sme->ssid_len, IEEE80211_MAX_SSID_LEN); - ext_join_params->ssid_le.SSID_len = cpu_to_le32(ssid_len); - memcpy(&ext_join_params->ssid_le.SSID, sme->ssid, ssid_len); - if (ssid_len < IEEE80211_MAX_SSID_LEN) - brcmf_dbg(CONN, "SSID \"%s\", len (%d)\n", - ext_join_params->ssid_le.SSID, ssid_len); + if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_FWSUP)) { + if (params->crypto.psk) { + if ((profile->use_fwsup != BRCMF_PROFILE_FWSUP_SAE) && + (profile->use_fwsup != BRCMF_PROFILE_FWSUP_PSK)) { + if (WARN_ON(profile->use_fwsup != + BRCMF_PROFILE_FWSUP_NONE)) { + err = -EINVAL; + goto done; + } + brcmf_dbg(INFO, "using PSK offload\n"); + profile->use_fwsup = BRCMF_PROFILE_FWSUP_PSK; + } + } - /* Set up join scan parameters */ - ext_join_params->scan_le.scan_type = -1; - ext_join_params->scan_le.home_time = cpu_to_le32(-1); + if (profile->use_fwsup != BRCMF_PROFILE_FWSUP_NONE) { + /* enable firmware supplicant for this interface */ + err = brcmf_fil_iovar_int_set(ifp, "sup_wpa", 1); + if (err < 0) { + bphy_err(drvr, + "failed to enable fw supplicant\n"); + goto done; + } + } else { + err = brcmf_fil_iovar_int_set(ifp, "sup_wpa", 0); + } - if (sme->bssid) - memcpy(&ext_join_params->assoc_le.bssid, sme->bssid, ETH_ALEN); - else - eth_broadcast_addr(ext_join_params->assoc_le.bssid); + if ((profile->use_fwsup == BRCMF_PROFILE_FWSUP_PSK) && + params->crypto.psk) + err = brcmf_set_pmk(ifp, params->crypto.psk, + BRCMF_WSEC_MAX_PSK_LEN); + else if (profile->use_fwsup == BRCMF_PROFILE_FWSUP_SAE) { + /* clean up user-space RSNE */ + if (brcmf_fil_iovar_data_set(ifp, "wpaie", NULL, 0)) { + bphy_err( + drvr, + "failed to clean up user-space RSNE\n"); + goto done; + } + err = brcmf_fwvid_set_sae_password(ifp, ¶ms->crypto); + if (!err && params->crypto.psk) + err = brcmf_set_pmk(ifp, params->crypto.psk, + BRCMF_WSEC_MAX_PSK_LEN); + } + if (err) + goto done; + } + brcmf_set_join_pref(ifp, ¶ms->bss_select); + if (params->ssid_len < IEEE80211_MAX_SSID_LEN) + brcmf_dbg(CONN, "SSID \"%s\", len (%zu)\n", params->ssid, + params->ssid_len); + join_params = drvr->join_param_handler.get_struct_for_connect( + cfg, &join_params_size, params); - if (cfg->channel) { - ext_join_params->assoc_le.chanspec_num = cpu_to_le32(1); + if (join_params) { + err = brcmf_fil_bsscfg_data_set(ifp, "join", join_params, + join_params_size); - ext_join_params->assoc_le.chanspec_list[0] = - cpu_to_le16(chanspec); - /* Increase dwell time to receive probe response or detect - * beacon from target AP at a noisy air only during connect - * command. - */ - ext_join_params->scan_le.active_time = - cpu_to_le32(BRCMF_SCAN_JOIN_ACTIVE_DWELL_TIME_MS); - ext_join_params->scan_le.passive_time = - cpu_to_le32(BRCMF_SCAN_JOIN_PASSIVE_DWELL_TIME_MS); - /* To sync with presence period of VSDB GO send probe request - * more frequently. Probe request will be stopped when it gets - * probe response from target AP/GO. - */ - ext_join_params->scan_le.nprobes = - cpu_to_le32(BRCMF_SCAN_JOIN_ACTIVE_DWELL_TIME_MS / - BRCMF_SCAN_JOIN_PROBE_INTERVAL_MS); - } else { - ext_join_params->scan_le.active_time = cpu_to_le32(-1); - ext_join_params->scan_le.passive_time = cpu_to_le32(-1); - ext_join_params->scan_le.nprobes = cpu_to_le32(-1); + /* We only free the join parameters if we were successful. + * Otherwise they are used to extract the fallback, below */ + if (!err) { + kfree(join_params); + /* This is it. join command worked, we are done */ + goto done; + } + /* For versions >= 1, this should have worked, so report the error */ + if (drvr->join_param_handler.version >= 1) { + bphy_err(drvr, "Failed to use join iovar to join: %d\n", + err); + } } - brcmf_set_join_pref(ifp, &sme->bss_select); - - err = brcmf_fil_bsscfg_data_set(ifp, "join", ext_join_params, - join_params_size); - kfree(ext_join_params); - if (!err) - /* This is it. join command worked, we are done */ + /* Fallback to using WLC_SET_SSID approach, which just uses join_params parts of the structure */ + fallback_join_params = drvr->join_param_handler.get_join_from_ext_join( + join_params, &fallback_join_params_size); + if (!fallback_join_params) { + bphy_err(drvr, "Unable to generate fallback join params\n"); + kfree(join_params); goto done; - - /* join command failed, fallback to set ssid */ - memset(&join_params, 0, sizeof(join_params)); - join_params_size = sizeof(join_params.ssid_le); - - memcpy(&join_params.ssid_le.SSID, sme->ssid, ssid_len); - join_params.ssid_le.SSID_len = cpu_to_le32(ssid_len); - - if (sme->bssid) - memcpy(join_params.params_le.bssid, sme->bssid, ETH_ALEN); - else - eth_broadcast_addr(join_params.params_le.bssid); - - if (cfg->channel) { - join_params.params_le.chanspec_list[0] = cpu_to_le16(chanspec); - join_params.params_le.chanspec_num = cpu_to_le32(1); - join_params_size += sizeof(join_params.params_le); } err = brcmf_fil_cmd_data_set(ifp, BRCMF_C_SET_SSID, - &join_params, join_params_size); + fallback_join_params, + fallback_join_params_size); + + kfree(join_params); + kfree(fallback_join_params); if (err) bphy_err(drvr, "BRCMF_C_SET_SSID failed (%d)\n", err); @@ -2807,6 +2557,8 @@ brcmf_cfg80211_add_key(struct wiphy *wiphy, struct net_device *ndev, s32 val; s32 wsec; s32 err; + u32 algos = 0; + u32 mask = 0; u8 keybuf[8]; bool ext_key; @@ -2890,6 +2642,30 @@ brcmf_cfg80211_add_key(struct wiphy *wiphy, struct net_device *ndev, val = AES_ENABLED; brcmf_dbg(CONN, "WLAN_CIPHER_SUITE_CCMP\n"); break; + case WLAN_CIPHER_SUITE_GCMP_256: + if (!brcmf_feat_is_enabled(ifp, BRCMF_FEAT_GCMP)) { + brcmf_err("the low layer not support GCMP\n"); + err = -EOPNOTSUPP; + goto done; + } + key->algo = CRYPTO_ALGO_AES_GCM256; + val = AES_ENABLED; + brcmf_dbg(CONN, "WLAN_CIPHER_SUITE_GCMP_256\n"); + algos = KEY_ALGO_MASK(CRYPTO_ALGO_AES_GCM256); + mask = algos | KEY_ALGO_MASK(CRYPTO_ALGO_AES_CCM); + break; + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + if (!brcmf_feat_is_enabled(ifp, BRCMF_FEAT_GCMP)) { + brcmf_err("the low layer not support GCMP\n"); + err = -EOPNOTSUPP; + goto done; + } + key->algo = CRYPTO_ALGO_BIP_GMAC256; + val = AES_ENABLED; + algos = KEY_ALGO_MASK(CRYPTO_ALGO_BIP_GMAC256); + mask = algos | KEY_ALGO_MASK(CRYPTO_ALGO_AES_CCM); + brcmf_dbg(CONN, "WLAN_CIPHER_SUITE_BIP_GMAC_256\n"); + break; default: bphy_err(drvr, "Invalid cipher (0x%x)\n", params->cipher); err = -EINVAL; @@ -2911,6 +2687,17 @@ brcmf_cfg80211_add_key(struct wiphy *wiphy, struct net_device *ndev, bphy_err(drvr, "set wsec error (%d)\n", err); goto done; } + if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_GCMP)) { + brcmf_dbg(CONN, + "set_wsdec_info algos (0x%x) mask (0x%x)\n", + algos, mask); + err = brcmf_set_wsec_info_algos(ifp, algos, mask); + if (err) { + brcmf_err("set wsec_info error (%d)\n", err); + return err; + } + } + done: brcmf_dbg(TRACE, "Exit\n"); @@ -3131,6 +2918,70 @@ brcmf_cfg80211_get_station_ibss(struct brcmf_if *ifp, return 0; } +static void brcmf_convert_ratespec_to_rateinfo(u32 ratespec, + struct rate_info *rateinfo) +{ + /* First extract the bandwidth info */ + switch (ratespec & BRCMF_RSPEC_BW_MASK) { + case BRCMF_RSPEC_BW_20MHZ: + rateinfo->bw = RATE_INFO_BW_20; + break; + case BRCMF_RSPEC_BW_40MHZ: + rateinfo->bw = RATE_INFO_BW_40; + break; + case BRCMF_RSPEC_BW_80MHZ: + rateinfo->bw = RATE_INFO_BW_80; + break; + case BRCMF_RSPEC_BW_160MHZ: + rateinfo->bw = RATE_INFO_BW_160; + break; + case BRCMF_RSPEC_BW_320MHZ: + rateinfo->bw = RATE_INFO_BW_320; + break; + default: + /* Fill in nothing */ + break; + } + if (BRCMF_RSPEC_ISHT(ratespec)) { + rateinfo->flags |= RATE_INFO_FLAGS_MCS; + rateinfo->mcs = ratespec & BRCMF_RSPEC_HT_MCS_MASK; + } else if (BRCMF_RSPEC_ISVHT(ratespec)) { + rateinfo->flags |= RATE_INFO_FLAGS_VHT_MCS; + rateinfo->mcs = ratespec & BRCMF_RSPEC_VHT_MCS_MASK; + rateinfo->nss = (ratespec & BRCMF_RSPEC_VHT_NSS_MASK) >> + BRCMF_RSPEC_VHT_NSS_SHIFT; + } else if (BRCMF_RSPEC_ISHE(ratespec)) { + u32 ltf_gi = BRCMF_RSPEC_HE_LTF_GI(ratespec); + + rateinfo->flags |= RATE_INFO_FLAGS_HE_MCS; + rateinfo->mcs = ratespec & BRCMF_RSPEC_HE_MCS_MASK; + rateinfo->nss = (ratespec & BRCMF_RSPEC_HE_NSS_MASK) >> + BRCMF_RSPEC_HE_NSS_SHIFT; + rateinfo->he_dcm = BRCMF_RSPEC_HE_DCM(ratespec); + if (HE_IS_GI_0_8us(ltf_gi)) { + rateinfo->he_gi = NL80211_RATE_INFO_HE_GI_0_8; + } else if (HE_IS_GI_1_6us(ltf_gi)) { + rateinfo->he_gi = NL80211_RATE_INFO_HE_GI_1_6; + } else if (HE_IS_GI_3_2us(ltf_gi)) { + rateinfo->he_gi = NL80211_RATE_INFO_HE_GI_3_2; + } + } else if (BRCMF_RSPEC_ISEHT(ratespec)) { + u32 ltf_gi = BRCMF_RSPEC_EHT_LTF_GI(ratespec); + + rateinfo->flags |= RATE_INFO_FLAGS_EHT_MCS; + rateinfo->mcs = ratespec & BRCMF_RSPEC_EHT_MCS_MASK; + rateinfo->nss = (ratespec & BRCMF_RSPEC_EHT_NSS_MASK) >> + BRCMF_RSPEC_EHT_NSS_SHIFT; + if (EHT_IS_GI_0_8us(ltf_gi)) { + rateinfo->eht_gi = NL80211_RATE_INFO_EHT_GI_0_8; + } else if (EHT_IS_GI_1_6us(ltf_gi)) { + rateinfo->eht_gi = NL80211_RATE_INFO_EHT_GI_1_6; + } else if (EHT_IS_GI_3_2us(ltf_gi)) { + rateinfo->eht_gi = NL80211_RATE_INFO_EHT_GI_3_2; + } + } +} + static s32 brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev, const u8 *mac, struct station_info *sinfo) @@ -3148,6 +2999,8 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev, s32 count_rssi = 0; int rssi; u32 i; + u16 struct_ver; + u16 info_len; brcmf_dbg(TRACE, "Enter, MAC %pM\n", mac); if (!check_vif_up(ifp->vif)) @@ -3171,7 +3024,9 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev, goto done; } } - brcmf_dbg(TRACE, "version %d\n", le16_to_cpu(sta_info_le.ver)); + info_len = le16_to_cpu(sta_info_le.len); + struct_ver = le16_to_cpu(sta_info_le.ver); + brcmf_dbg(TRACE, "version %d\n", struct_ver); sinfo->filled = BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME); sinfo->inactive_time = le32_to_cpu(sta_info_le.idle) * 1000; sta_flags = le32_to_cpu(sta_info_le.flags); @@ -3205,12 +3060,13 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev, sinfo->rxrate.legacy = le32_to_cpu(sta_info_le.rx_rate) / 100; } - if (le16_to_cpu(sta_info_le.ver) >= 4) { + if (struct_ver >= 4) { sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES); sinfo->tx_bytes = le64_to_cpu(sta_info_le.tx_tot_bytes); sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES); sinfo->rx_bytes = le64_to_cpu(sta_info_le.rx_tot_bytes); } + for (i = 0; i < BRCMF_ANT_MAX; i++) { if (sta_info_le.rssi[i] == 0 || sta_info_le.rx_lastpkt_rssi[i] == 0) @@ -3249,6 +3105,25 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev, } } } + /* Some version 7 structs have ratespecs from the last packet. */ + if (struct_ver >= 7) { + if (info_len >= sizeof(sta_info_le)) { + brcmf_convert_ratespec_to_rateinfo( + le32_to_cpu(sta_info_le.v7.tx_rspec), + &sinfo->txrate); + brcmf_convert_ratespec_to_rateinfo( + le32_to_cpu(sta_info_le.v7.rx_rspec), + &sinfo->rxrate); + } else { + /* We didn't get the fields we were expecting, fallback to nrate */ + u32 nrate = 0; + err = brcmf_fil_iovar_int_get(ifp, "nrate", &nrate); + if (!err) { + brcmf_convert_ratespec_to_rateinfo( + nrate, &sinfo->txrate); + } + } + } done: brcmf_dbg(TRACE, "Exit\n"); return err; @@ -3349,6 +3224,7 @@ static s32 brcmf_inform_single_bss(struct brcmf_cfg80211_info *cfg, struct cfg80211_bss *bss; enum nl80211_band band; struct brcmu_chan ch; + u16 chanspec; u16 channel; u32 freq; u16 notify_capability; @@ -3362,20 +3238,41 @@ static s32 brcmf_inform_single_bss(struct brcmf_cfg80211_info *cfg, return -EINVAL; } + chanspec = le16_to_cpu(bi->chanspec); if (!bi->ctl_ch) { - ch.chspec = le16_to_cpu(bi->chanspec); + ch.chspec = chanspec; cfg->d11inf.decchspec(&ch); bi->ctl_ch = ch.control_ch_num; } channel = bi->ctl_ch; - if (channel <= CH_MAX_2G_CHANNEL) - band = NL80211_BAND_2GHZ; - else + if (CHSPEC_IS6G(chanspec)) + band = NL80211_BAND_6GHZ; + else if (CHSPEC_IS5G(chanspec)) band = NL80211_BAND_5GHZ; + else + band = NL80211_BAND_2GHZ; freq = ieee80211_channel_to_frequency(channel, band); + if (!freq) { + brcmf_err("Invalid frequency %d returned for channel %d, band %d. chanspec was %04x\n", + freq, channel, band, bi->chanspec); + + /* We ignore this BSS ID rather than try to continue on. + * Otherwise we will cause an OOPs because our frequency is 0. + * The main case this occurs is some new frequency band + * we have not seen before, and if we return an error, + * we will cause the scan to fail. It seems better to + * report the error, skip this BSS, and move on. + */ + return 0; + } bss_data.chan = ieee80211_get_channel(wiphy, freq); + if (!bss_data.chan) { + brcmf_err("Could not convert frequency into channel for channel %d, band %d, chanspec was %04x\n", + channel, band, bi->chanspec); + return 0; + } bss_data.boottime_ns = ktime_to_ns(ktime_get_boottime()); notify_capability = le16_to_cpu(bi->capability); @@ -3424,8 +3321,9 @@ static s32 brcmf_inform_bss(struct brcmf_cfg80211_info *cfg) bss_list = (struct brcmf_scan_results *)cfg->escan_info.escan_buf; if (bss_list->count != 0 && - bss_list->version != BRCMF_BSS_INFO_VERSION) { - bphy_err(drvr, "Version %d != WL_BSS_INFO_VERSION\n", + (bss_list->version < BRCMF_BSS_INFO_MIN_VERSION || + bss_list->version > BRCMF_BSS_INFO_MAX_VERSION)) { + bphy_err(drvr, "BSS info version %d unsupported\n", bss_list->version); return -EOPNOTSUPP; } @@ -3463,7 +3361,7 @@ static s32 brcmf_inform_ibss(struct brcmf_cfg80211_info *cfg, buf = kzalloc(WL_BSS_INFO_MAX, GFP_KERNEL); if (buf == NULL) { err = -ENOMEM; - goto CleanUp; + goto cleanup; } *(__le32 *)buf = cpu_to_le32(WL_BSS_INFO_MAX); @@ -3472,7 +3370,7 @@ static s32 brcmf_inform_ibss(struct brcmf_cfg80211_info *cfg, buf, WL_BSS_INFO_MAX); if (err) { bphy_err(drvr, "WLC_GET_BSS_INFO failed: %d\n", err); - goto CleanUp; + goto cleanup; } bi = (struct brcmf_bss_info_le *)(buf + 4); @@ -3482,10 +3380,18 @@ static s32 brcmf_inform_ibss(struct brcmf_cfg80211_info *cfg, if (ch.band == BRCMU_CHAN_BAND_2G) band = wiphy->bands[NL80211_BAND_2GHZ]; - else + else if (ch.band == BRCMU_CHAN_BAND_5G) band = wiphy->bands[NL80211_BAND_5GHZ]; + else + band = wiphy->bands[NL80211_BAND_6GHZ]; freq = ieee80211_channel_to_frequency(ch.control_ch_num, band->band); + if (freq == 0) { + brcmf_err("Invalid frequency %d returned for channel %d, band %d. chanspec was %04x\n", + freq, ch.control_ch_num, ch.band, bi->chanspec); + goto cleanup; + } + cfg->channel = freq; notify_channel = ieee80211_get_channel(wiphy, freq); @@ -3508,12 +3414,12 @@ static s32 brcmf_inform_ibss(struct brcmf_cfg80211_info *cfg, if (!bss) { err = -ENOMEM; - goto CleanUp; + goto cleanup; } cfg80211_put_bss(wiphy, bss); -CleanUp: +cleanup: kfree(buf); @@ -3765,17 +3671,11 @@ brcmf_alloc_internal_escan_request(struct wiphy *wiphy, u32 n_netinfo) { } static int brcmf_internal_escan_add_info(struct cfg80211_scan_request *req, - u8 *ssid, u8 ssid_len, u8 channel) + u8 *ssid, u8 ssid_len, u8 channel, enum nl80211_band band) { struct ieee80211_channel *chan; - enum nl80211_band band; int freq, i; - if (channel <= CH_MAX_2G_CHANNEL) - band = NL80211_BAND_2GHZ; - else - band = NL80211_BAND_5GHZ; - freq = ieee80211_channel_to_frequency(channel, band); if (!freq) return -EINVAL; @@ -3831,53 +3731,30 @@ static int brcmf_start_internal_escan(struct brcmf_if *ifp, u32 fwmap, return 0; } -static struct brcmf_pno_net_info_le * -brcmf_get_netinfo_array(struct brcmf_pno_scanresults_le *pfn_v1) -{ - struct brcmf_pno_scanresults_v2_le *pfn_v2; - struct brcmf_pno_net_info_le *netinfo; - - switch (pfn_v1->version) { - default: - WARN_ON(1); - fallthrough; - case cpu_to_le32(1): - netinfo = (struct brcmf_pno_net_info_le *)(pfn_v1 + 1); - break; - case cpu_to_le32(2): - pfn_v2 = (struct brcmf_pno_scanresults_v2_le *)pfn_v1; - netinfo = (struct brcmf_pno_net_info_le *)(pfn_v2 + 1); - break; - } - - return netinfo; -} - /* PFN result doesn't have all the info which are required by the supplicant * (For e.g IEs) Do a target Escan so that sched scan results are reported * via wl_inform_single_bss in the required format. Escan does require the * scan request in the form of cfg80211_scan_request. For timebeing, create * cfg80211_scan_request one out of the received PNO event. */ -static s32 -brcmf_notify_sched_scan_results(struct brcmf_if *ifp, - const struct brcmf_event_msg *e, void *data) +static s32 brcmf_notify_sched_scan_results(struct brcmf_if *ifp, + const struct brcmf_event_msg *e, + void *data) { struct brcmf_pub *drvr = ifp->drvr; struct brcmf_cfg80211_info *cfg = drvr->config; - struct brcmf_pno_net_info_le *netinfo, *netinfo_start; struct cfg80211_scan_request *request = NULL; struct wiphy *wiphy = cfg_to_wiphy(cfg); int i, err = 0; - struct brcmf_pno_scanresults_le *pfn_result; u32 bucket_map; u32 result_count; u32 status; - u32 datalen; + u32 min_data_len; brcmf_dbg(SCAN, "Enter\n"); + min_data_len = drvr->pno_handler.get_min_data_len(); - if (e->datalen < (sizeof(*pfn_result) + sizeof(*netinfo))) { + if (e->datalen < min_data_len) { brcmf_dbg(SCAN, "Event data too small. Ignore\n"); return 0; } @@ -3887,9 +3764,8 @@ brcmf_notify_sched_scan_results(struct brcmf_if *ifp, return 0; } - pfn_result = (struct brcmf_pno_scanresults_le *)data; - result_count = le32_to_cpu(pfn_result->count); - status = le32_to_cpu(pfn_result->status); + result_count = drvr->pno_handler.get_result_count(data); + status = drvr->pno_handler.get_result_status(data); /* PFN event is limited to fit 512 bytes so we may get * multiple NET_FOUND events. For now place a warning here. @@ -3900,38 +3776,33 @@ brcmf_notify_sched_scan_results(struct brcmf_if *ifp, bphy_err(drvr, "FALSE PNO Event. (pfn_count == 0)\n"); goto out_err; } - - netinfo_start = brcmf_get_netinfo_array(pfn_result); - datalen = e->datalen - ((void *)netinfo_start - (void *)pfn_result); - if (datalen < result_count * sizeof(*netinfo)) { - bphy_err(drvr, "insufficient event data\n"); + err = drvr->pno_handler.validate_pfn_results(data, e->datalen); + if (err) { + bphy_err(drvr, "Invalid escan results (%d)", err); goto out_err; } - - request = brcmf_alloc_internal_escan_request(wiphy, - result_count); + request = brcmf_alloc_internal_escan_request(wiphy, result_count); if (!request) { err = -ENOMEM; goto out_err; } - bucket_map = 0; for (i = 0; i < result_count; i++) { - netinfo = &netinfo_start[i]; - - if (netinfo->SSID_len > IEEE80211_MAX_SSID_LEN) - netinfo->SSID_len = IEEE80211_MAX_SSID_LEN; - brcmf_dbg(SCAN, "SSID:%.32s Channel:%d\n", - netinfo->SSID, netinfo->channel); - bucket_map |= brcmf_pno_get_bucket_map(cfg->pno, netinfo); - err = brcmf_internal_escan_add_info(request, - netinfo->SSID, - netinfo->SSID_len, - netinfo->channel); + u8 channel; + enum nl80211_band band; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len; + + drvr->pno_handler.get_result_info(data, i, &ssid, &ssid_len, + &channel, &band); + brcmf_dbg(SCAN, "SSID:%.32s Channel:%d Band:%d\n", ssid, + channel, band); + bucket_map |= drvr->pno_handler.get_bucket_map(data, i, cfg->pno); + err = brcmf_internal_escan_add_info(request, ssid, ssid_len, + channel, band); if (err) goto out_err; } - if (!bucket_map) goto free_req; @@ -4034,48 +3905,50 @@ static s32 brcmf_config_wowl_pattern(struct brcmf_if *ifp, u8 cmd[4], return ret; } -static s32 -brcmf_wowl_nd_results(struct brcmf_if *ifp, const struct brcmf_event_msg *e, - void *data) +static s32 brcmf_wowl_nd_results(struct brcmf_if *ifp, + const struct brcmf_event_msg *e, void *data) { struct brcmf_pub *drvr = ifp->drvr; struct brcmf_cfg80211_info *cfg = drvr->config; - struct brcmf_pno_scanresults_le *pfn_result; - struct brcmf_pno_net_info_le *netinfo; + u32 min_data_len; + u8 channel; + enum nl80211_band band; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len; + u32 result_count; brcmf_dbg(SCAN, "Enter\n"); - if (e->datalen < (sizeof(*pfn_result) + sizeof(*netinfo))) { + min_data_len = drvr->pno_handler.get_min_data_len(); + + if (e->datalen < min_data_len) { brcmf_dbg(SCAN, "Event data too small. Ignore\n"); return 0; } - pfn_result = (struct brcmf_pno_scanresults_le *)data; if (e->event_code == BRCMF_E_PFN_NET_LOST) { brcmf_dbg(SCAN, "PFN NET LOST event. Ignore\n"); return 0; } - if (le32_to_cpu(pfn_result->count) < 1) { + result_count = drvr->pno_handler.get_result_count(data); + if (result_count < 1) { bphy_err(drvr, "Invalid result count, expected 1 (%d)\n", - le32_to_cpu(pfn_result->count)); + result_count); return -EINVAL; } - netinfo = brcmf_get_netinfo_array(pfn_result); - if (netinfo->SSID_len > IEEE80211_MAX_SSID_LEN) - netinfo->SSID_len = IEEE80211_MAX_SSID_LEN; - memcpy(cfg->wowl.nd->ssid.ssid, netinfo->SSID, netinfo->SSID_len); - cfg->wowl.nd->ssid.ssid_len = netinfo->SSID_len; + drvr->pno_handler.get_result_info(data, 0, &ssid, &ssid_len, &channel, + &band); + memcpy(cfg->wowl.nd->ssid.ssid, ssid, ssid_len); + cfg->wowl.nd->ssid.ssid_len = ssid_len; cfg->wowl.nd->n_channels = 1; cfg->wowl.nd->channels[0] = - ieee80211_channel_to_frequency(netinfo->channel, - netinfo->channel <= CH_MAX_2G_CHANNEL ? - NL80211_BAND_2GHZ : NL80211_BAND_5GHZ); + ieee80211_channel_to_frequency(channel, band); + cfg->wowl.nd_info->n_matches = 1; cfg->wowl.nd_info->matches[0] = cfg->wowl.nd; - /* Inform (the resume task) that the net detect information was recvd */ cfg->wowl.nd_data_completed = true; wake_up(&cfg->wowl.nd_data_wait); @@ -5149,6 +5022,25 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev, settings->inactivity_timeout); dev_role = ifp->vif->wdev.iftype; mbss = ifp->vif->mbss; + /* Bring firmware into correct state for AP mode*/ + if (dev_role == NL80211_IFTYPE_AP) { + brcmf_dbg(TRACE, "set AP mode\n"); + err = brcmf_fil_cmd_int_set(ifp, BRCMF_C_SET_AP, 1); + if (err < 0) { + bphy_err(drvr, "setting AP mode failed %d\n", + err); + goto exit; + } + + bss_enable.bsscfgidx = cpu_to_le32(ifp->bsscfgidx); + bss_enable.enable = cpu_to_le32(WLC_AP_IOV_OP_MANUAL_AP_BSSCFG_CREATE); + err = brcmf_fil_iovar_data_set(ifp, "bss", &bss_enable, + sizeof(bss_enable)); + if (err < 0) { + bphy_err(drvr, "AP role set error, %d\n", err); + goto exit; + } + } /* store current 11d setting */ if (brcmf_fil_cmd_int_get(ifp, BRCMF_C_GET_REGULATORY, @@ -5742,6 +5634,9 @@ static int brcmf_cfg80211_get_channel(struct wiphy *wiphy, case BRCMU_CHAN_BAND_5G: band = NL80211_BAND_5GHZ; break; + case BRCMU_CHAN_BAND_6G: + band = NL80211_BAND_6GHZ; + break; } switch (ch.bw) { @@ -5763,9 +5658,19 @@ static int brcmf_cfg80211_get_channel(struct wiphy *wiphy, } freq = ieee80211_channel_to_frequency(ch.control_ch_num, band); + if (freq == 0) { + brcmf_err("Invalid frequency %d returned for channel %d, band %d. chanspec was %04x\n", + freq, ch.control_ch_num, ch.band, chanspec); + return -EINVAL; + } chandef->chan = ieee80211_get_channel(wiphy, freq); chandef->width = width; chandef->center_freq1 = ieee80211_channel_to_frequency(ch.chnum, band); + if (chandef->center_freq1 == 0) { + brcmf_err("Invalid frequency %d returned for channel %d, band %d. chanspec was %04x\n", + freq, ch.chnum, ch.band, chanspec); + return -EINVAL; + } chandef->center_freq2 = 0; return 0; @@ -5930,17 +5835,29 @@ static int brcmf_cfg80211_set_pmk(struct wiphy *wiphy, struct net_device *dev, const struct cfg80211_pmk_conf *conf) { struct brcmf_if *ifp; - + struct brcmf_pub *drvr; + int ret; brcmf_dbg(TRACE, "enter\n"); /* expect using firmware supplicant for 1X */ ifp = netdev_priv(dev); - if (WARN_ON(ifp->vif->profile.use_fwsup != BRCMF_PROFILE_FWSUP_1X)) + drvr = ifp->drvr; + if (WARN_ON((ifp->vif->profile.use_fwsup != BRCMF_PROFILE_FWSUP_1X) && + (ifp->vif->profile.use_fwsup != BRCMF_PROFILE_FWSUP_ROAM) && + (ifp->vif->profile.is_ft != true) && + (ifp->vif->profile.is_okc != true))) return -EINVAL; if (conf->pmk_len > BRCMF_WSEC_MAX_PSK_LEN) return -ERANGE; + if (ifp->vif->profile.is_okc) { + ret = brcmf_fil_iovar_data_set(ifp, "okc_info_pmk", conf->pmk, + conf->pmk_len); + if (ret < 0) + bphy_err(drvr, "okc_info_pmk iovar failed: ret=%d\n", + ret); + } return brcmf_set_pmk(ifp, conf->pmk, conf->pmk_len); } @@ -6399,6 +6316,46 @@ static s32 brcmf_get_assoc_ies(struct brcmf_cfg80211_info *cfg, return err; } +static bool brcmf_has_pmkid(const u8 *parse, u32 len) +{ + const struct brcmf_tlv *rsn_ie; + const u8 *ie; + u32 ie_len; + u32 offset; + u16 count; + + rsn_ie = brcmf_parse_tlvs(parse, len, WLAN_EID_RSN); + if (!rsn_ie) + goto done; + ie = (const u8 *)rsn_ie; + ie_len = rsn_ie->len + TLV_HDR_LEN; + /* Skip group data cipher suite */ + offset = TLV_HDR_LEN + WPA_IE_VERSION_LEN + WPA_IE_MIN_OUI_LEN; + if (offset + WPA_IE_SUITE_COUNT_LEN >= ie_len) + goto done; + /* Skip pairwise cipher suite(s) */ + count = ie[offset] + (ie[offset + 1] << 8); + offset += WPA_IE_SUITE_COUNT_LEN + (count * WPA_IE_MIN_OUI_LEN); + if (offset + WPA_IE_SUITE_COUNT_LEN >= ie_len) + goto done; + /* Skip auth key management suite(s) */ + count = ie[offset] + (ie[offset + 1] << 8); + offset += WPA_IE_SUITE_COUNT_LEN + (count * WPA_IE_MIN_OUI_LEN); + if (offset + RSN_CAP_LEN >= ie_len) + goto done; + /* Skip rsn capabilities */ + offset += RSN_CAP_LEN; + if (offset + RSN_PMKID_COUNT_LEN > ie_len) + goto done; + /* Extract PMKID count */ + count = ie[offset] + (ie[offset + 1] << 8); + if (count) + return true; + +done: + return false; +} + static s32 brcmf_bss_roaming_done(struct brcmf_cfg80211_info *cfg, struct net_device *ndev, @@ -6443,10 +6400,17 @@ brcmf_bss_roaming_done(struct brcmf_cfg80211_info *cfg, if (ch.band == BRCMU_CHAN_BAND_2G) band = wiphy->bands[NL80211_BAND_2GHZ]; - else + else if (ch.band == BRCMU_CHAN_BAND_5G) band = wiphy->bands[NL80211_BAND_5GHZ]; + else + band = wiphy->bands[NL80211_BAND_6GHZ]; freq = ieee80211_channel_to_frequency(ch.control_ch_num, band->band); + if (freq == 0) { + brcmf_err("Invalid frequency %d returned for channel %d, band %d. chanspec was %04x\n", + freq, ch.control_ch_num, ch.band, bi->chanspec); + goto done; + } notify_channel = ieee80211_get_channel(wiphy, freq); done: @@ -6462,11 +6426,16 @@ brcmf_bss_roaming_done(struct brcmf_cfg80211_info *cfg, cfg80211_roamed(ndev, &roam_info, GFP_KERNEL); brcmf_dbg(CONN, "Report roaming result\n"); - if (profile->use_fwsup == BRCMF_PROFILE_FWSUP_1X && profile->is_ft) { - cfg80211_port_authorized(ndev, profile->bssid, NULL, 0, GFP_KERNEL); + if (((profile->use_fwsup == BRCMF_PROFILE_FWSUP_1X || + profile->use_fwsup == BRCMF_PROFILE_FWSUP_ROAM) && + (brcmf_has_pmkid(roam_info.req_ie, roam_info.req_ie_len) || + profile->is_ft || profile->is_okc))) { + cfg80211_port_authorized(ndev, profile->bssid, NULL, 0, + GFP_KERNEL); brcmf_dbg(CONN, "Report port authorized\n"); } + clear_bit(BRCMF_VIF_STATUS_CONNECTING, &ifp->vif->sme_state); set_bit(BRCMF_VIF_STATUS_CONNECTED, &ifp->vif->sme_state); brcmf_dbg(TRACE, "Exit\n"); return err; @@ -6925,8 +6894,6 @@ static s32 brcmf_dongle_roam(struct brcmf_if *ifp) if (err) bphy_err(drvr, "WLC_SET_ROAM_TRIGGER error (%d)\n", err); - roam_delta[0] = cpu_to_le32(WL_ROAM_DELTA); - roam_delta[1] = cpu_to_le32(BRCM_BAND_ALL); err = brcmf_fil_cmd_data_set(ifp, BRCMF_C_SET_ROAM_DELTA, (void *)roam_delta, sizeof(roam_delta)); if (err) @@ -7019,15 +6986,34 @@ static int brcmf_construct_chaninfo(struct brcmf_cfg80211_info *cfg, goto fail_pbuf; } + /* Changing regulatory domain may change power limits upwards. + * To ensure that we correctly set the new band info, copy the original + * info first. + */ band = wiphy->bands[NL80211_BAND_2GHZ]; - if (band) + if (band) { + memcpy(band->channels, &__wl_2ghz_channels, + sizeof(__wl_2ghz_channels)); + band->n_channels = ARRAY_SIZE(__wl_2ghz_channels); for (i = 0; i < band->n_channels; i++) band->channels[i].flags = IEEE80211_CHAN_DISABLED; + } band = wiphy->bands[NL80211_BAND_5GHZ]; - if (band) + if (band) { + memcpy(band->channels, &__wl_5ghz_channels, + sizeof(__wl_5ghz_channels)); + band->n_channels = ARRAY_SIZE(__wl_5ghz_channels); for (i = 0; i < band->n_channels; i++) band->channels[i].flags = IEEE80211_CHAN_DISABLED; - + } + band = wiphy->bands[NL80211_BAND_6GHZ]; + if (band) { + memcpy(band->channels, &__wl_6ghz_channels, + sizeof(__wl_6ghz_channels)); + band->n_channels = ARRAY_SIZE(__wl_6ghz_channels); + for (i = 0; i < band->n_channels; i++) + band->channels[i].flags = IEEE80211_CHAN_DISABLED; + } total = le32_to_cpu(list->count); if (total > BRCMF_MAX_CHANSPEC_LIST) { bphy_err(drvr, "Invalid count of channel Spec. (%u)\n", @@ -7044,6 +7030,8 @@ static int brcmf_construct_chaninfo(struct brcmf_cfg80211_info *cfg, band = wiphy->bands[NL80211_BAND_2GHZ]; } else if (ch.band == BRCMU_CHAN_BAND_5G) { band = wiphy->bands[NL80211_BAND_5GHZ]; + } else if (ch.band == BRCMU_CHAN_BAND_6G) { + band = wiphy->bands[NL80211_BAND_6GHZ]; } else { bphy_err(drvr, "Invalid channel Spec. 0x%x.\n", ch.chspec); @@ -7065,6 +7053,7 @@ static int brcmf_construct_chaninfo(struct brcmf_cfg80211_info *cfg, break; } } + if (!channel) { /* It seems firmware supports some channel we never * considered. Something new in IEEE standard? @@ -7137,17 +7126,25 @@ static int brcmf_enable_bw40_2g(struct brcmf_cfg80211_info *cfg) struct brcmu_chan ch; u32 num_chan; int i, j; + s32 updown; /* verify support for bw_cap command */ - val = WLC_BAND_5G; + val = WLC_BAND_2G; err = brcmf_fil_iovar_int_query(ifp, "bw_cap", &val); - + brcmf_dbg(INFO, "Check bw_cap support:%d\n", err); if (!err) { + /* Setting the bw_cap is DOWN restricted. */ + updown = 0; + brcmf_fil_cmd_data_set(ifp, BRCMF_C_DOWN, &updown, sizeof(s32)); /* only set 2G bandwidth using bw_cap command */ band_bwcap.band = cpu_to_le32(WLC_BAND_2G); band_bwcap.bw_cap = cpu_to_le32(WLC_BW_CAP_40MHZ); err = brcmf_fil_iovar_data_set(ifp, "bw_cap", &band_bwcap, sizeof(band_bwcap)); + brcmf_dbg(INFO, "set bw_cap support:%d\n", err); + brcmf_c_set_joinpref_default(ifp); + updown = 1; + brcmf_fil_cmd_data_set(ifp, BRCMF_C_UP, &updown, sizeof(s32)); } else { brcmf_dbg(INFO, "fallback to mimo_bw_cap\n"); val = WLC_N_BW_40ALL; @@ -7209,7 +7206,7 @@ static int brcmf_enable_bw40_2g(struct brcmf_cfg80211_info *cfg) return err; } -static void brcmf_get_bwcap(struct brcmf_if *ifp, u32 bw_cap[]) +static void brcmf_get_bwcap(struct brcmf_if *ifp, u32 bw_cap[4], bool has_6g) { struct brcmf_pub *drvr = ifp->drvr; u32 band, mimo_bwcap; @@ -7217,17 +7214,29 @@ static void brcmf_get_bwcap(struct brcmf_if *ifp, u32 bw_cap[]) band = WLC_BAND_2G; err = brcmf_fil_iovar_int_query(ifp, "bw_cap", &band); - if (!err) { - bw_cap[NL80211_BAND_2GHZ] = band; - band = WLC_BAND_5G; - err = brcmf_fil_iovar_int_query(ifp, "bw_cap", &band); - if (!err) { - bw_cap[NL80211_BAND_5GHZ] = band; - return; - } - WARN_ON(1); + if (err) + goto fallback; + bw_cap[NL80211_BAND_2GHZ] = band; + band = WLC_BAND_5G; + err |= brcmf_fil_iovar_int_query(ifp, "bw_cap", &band); + if (err) + goto fallback; + bw_cap[NL80211_BAND_5GHZ] = band; + if (!has_6g) return; - } + band = WLC_BAND_6G; + err |= brcmf_fil_iovar_int_query(ifp, "bw_cap", &band); + /* Prior to the introduction of 6g, this function only + * did fallback in the case of 2g and 5g -failing. + * As mimo_bwcap does not have 6g bwcap info anyway, + * we keep that behavior. + */ + if (err) + return; + bw_cap[NL80211_BAND_6GHZ] = band; + return; +fallback: + brcmf_dbg(INFO, "fallback to mimo_bw_cap info\n"); err = brcmf_fil_iovar_int_get(ifp, "mimo_bw_cap", &mimo_bwcap); if (err) @@ -7251,8 +7260,11 @@ static void brcmf_get_bwcap(struct brcmf_if *ifp, u32 bw_cap[]) } static void brcmf_update_ht_cap(struct ieee80211_supported_band *band, - u32 bw_cap[2], u32 nchain) + u32 bw_cap[4], u32 nrxchain) { + /* Not supported in 6G band */ + if (band->band == NL80211_BAND_6GHZ) + return; band->ht_cap.ht_supported = true; if (bw_cap[band->band] & WLC_BW_40MHZ_BIT) { band->ht_cap.cap |= IEEE80211_HT_CAP_SGI_40; @@ -7262,32 +7274,49 @@ static void brcmf_update_ht_cap(struct ieee80211_supported_band *band, band->ht_cap.cap |= IEEE80211_HT_CAP_DSSSCCK40; band->ht_cap.ampdu_factor = IEEE80211_HT_MAX_AMPDU_64K; band->ht_cap.ampdu_density = IEEE80211_HT_MPDU_DENSITY_16; - memset(band->ht_cap.mcs.rx_mask, 0xff, nchain); + memset(band->ht_cap.mcs.rx_mask, 0xff, nrxchain); band->ht_cap.mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED; } -static __le16 brcmf_get_mcs_map(u32 nchain, enum ieee80211_vht_mcs_support supp) +static __le16 brcmf_get_mcs_map(u32 nstreams, + enum ieee80211_vht_mcs_support supp) { u16 mcs_map; int i; - for (i = 0, mcs_map = 0xFFFF; i < nchain; i++) + for (i = 0, mcs_map = 0xFFFF; i < nstreams; i++) mcs_map = (mcs_map << 2) | supp; return cpu_to_le16(mcs_map); } static void brcmf_update_vht_cap(struct ieee80211_supported_band *band, - u32 bw_cap[2], u32 nchain, u32 txstreams, - u32 txbf_bfe_cap, u32 txbf_bfr_cap) + u32 bw_cap[4], u32 txstreams, u32 rxstreams, + u32 txbf_bfe_cap, u32 txbf_bfr_cap, + u32 ldpc_cap, u32 stbc_rx, u32 stbc_tx) { __le16 mcs_map; - /* not allowed in 2.4G band */ - if (band->band == NL80211_BAND_2GHZ) + /* not allowed in 2.4G or 6G band */ + if (band->band == NL80211_BAND_2GHZ || band->band == NL80211_BAND_6GHZ) return; band->vht_cap.vht_supported = true; + band->vht_cap.vht_mcs.tx_highest = cpu_to_le16(433 * txstreams); + band->vht_cap.vht_mcs.rx_highest = cpu_to_le16(433 * rxstreams); + + band->vht_cap.cap |= IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN | + IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN; + + if (ldpc_cap) + band->vht_cap.cap |= IEEE80211_VHT_CAP_RXLDPC; + if (stbc_tx) + band->vht_cap.cap |= IEEE80211_VHT_CAP_TXSTBC; + + if (stbc_rx) + band->vht_cap.cap |= + (stbc_rx << IEEE80211_VHT_CAP_RXSTBC_SHIFT); + /* 80MHz is mandatory */ band->vht_cap.cap |= IEEE80211_VHT_CAP_SHORT_GI_80; if (bw_cap[band->band] & WLC_BW_160MHZ_BIT) { @@ -7295,8 +7324,10 @@ static void brcmf_update_vht_cap(struct ieee80211_supported_band *band, band->vht_cap.cap |= IEEE80211_VHT_CAP_SHORT_GI_160; } /* all support 256-QAM */ - mcs_map = brcmf_get_mcs_map(nchain, IEEE80211_VHT_MCS_SUPPORT_0_9); + mcs_map = brcmf_get_mcs_map(rxstreams, IEEE80211_VHT_MCS_SUPPORT_0_9); band->vht_cap.vht_mcs.rx_mcs_map = mcs_map; + mcs_map = brcmf_get_mcs_map(txstreams, IEEE80211_VHT_MCS_SUPPORT_0_9); + band->vht_cap.vht_mcs.tx_mcs_map = mcs_map; /* Beamforming support information */ @@ -7312,11 +7343,129 @@ static void brcmf_update_vht_cap(struct ieee80211_supported_band *band, if ((txbf_bfe_cap || txbf_bfr_cap) && (txstreams > 1)) { band->vht_cap.cap |= (2 << IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT); - band->vht_cap.cap |= ((txstreams - 1) << - IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT); + band->vht_cap.cap |= + ((txstreams - 1) + << IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT); band->vht_cap.cap |= IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB; } + /* AMPDU length limit, support max 1MB (2 ^ (13 + 7)) */ + band->vht_cap.cap |= + (7 << IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT); +} + +static void brcmf_update_he_cap(struct ieee80211_supported_band *band, + struct ieee80211_sband_iftype_data *data) +{ + int idx = 1; + struct ieee80211_sta_he_cap *he_cap = &data->he_cap; + struct ieee80211_he_cap_elem *he_cap_elem = &he_cap->he_cap_elem; + struct ieee80211_he_mcs_nss_supp *he_mcs = &he_cap->he_mcs_nss_supp; + struct ieee80211_he_6ghz_capa *he_6ghz_capa = &data->he_6ghz_capa; + + if (!data) { + brcmf_err("failed to allocate sdata\n"); + return; + } + + data->types_mask = BIT(NL80211_IFTYPE_STATION); + he_cap->has_he = true; + + /* HE MAC Capabilities Information */ + he_cap_elem->mac_cap_info[0] = IEEE80211_HE_MAC_CAP0_HTC_HE | + IEEE80211_HE_MAC_CAP0_TWT_REQ | + IEEE80211_HE_MAC_CAP0_TWT_RES; + + he_cap_elem->mac_cap_info[1] = + IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US | + IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US; + + he_cap_elem->mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_BSR | + IEEE80211_HE_MAC_CAP2_BCAST_TWT; + + he_cap_elem->mac_cap_info[3] = + IEEE80211_HE_MAC_CAP3_OMI_CONTROL | + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_1 | + IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED; + + he_cap_elem->mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU; + + /* HE PHY Capabilities Information */ + he_cap_elem->phy_cap_info[0] = + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; + ; + + he_cap_elem->phy_cap_info[1] = + IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD; + + he_cap_elem->phy_cap_info[2] = + IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | + IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO | + IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO; + + he_cap_elem->phy_cap_info[3] = + IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK | + IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2 | + IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM | + IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER; + + he_cap_elem->phy_cap_info[4] = + IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE | + IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_MASK | + IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4 | + IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8; + + he_cap_elem->phy_cap_info[5] = + IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK | + IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK | + IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2; + + he_cap_elem->phy_cap_info[6] = + IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU | + IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU | + IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMING_FB | + IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMING_PARTIAL_BW_FB | + IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB | + IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE | + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT; + + he_cap_elem->phy_cap_info[7] = + IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI | + IEEE80211_HE_PHY_CAP7_MAX_NC_1; + + he_cap_elem->phy_cap_info[8] = + IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI | + IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G | + IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU | + IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU; + + he_cap_elem->phy_cap_info[9] = + IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU | + IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU | + IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB | + IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB; + + /* HE Supported MCS and NSS Set */ + he_mcs->rx_mcs_80 = cpu_to_le16(0xfffa); + he_mcs->tx_mcs_80 = cpu_to_le16(0xfffa); + he_mcs->rx_mcs_160 = cpu_to_le16(0xfffa); + he_mcs->tx_mcs_160 = cpu_to_le16(0xfffa); + /* HE 6 GHz band capabilities */ + if (band->band == NL80211_BAND_6GHZ) { + u16 capa = 0; + + capa = FIELD_PREP(IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START, + IEEE80211_HT_MPDU_DENSITY_8) | + FIELD_PREP(IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP, + IEEE80211_VHT_MAX_AMPDU_1024K) | + FIELD_PREP(IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN, + IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454); + he_6ghz_capa->capa = cpu_to_le16(capa); + } + band->n_iftype_data = idx; + band->iftype_data = data; } static int brcmf_setup_wiphybands(struct brcmf_cfg80211_info *cfg) @@ -7326,26 +7475,49 @@ static int brcmf_setup_wiphybands(struct brcmf_cfg80211_info *cfg) struct wiphy *wiphy = cfg_to_wiphy(cfg); u32 nmode; u32 vhtmode = 0; - u32 bw_cap[2] = { WLC_BW_20MHZ_BIT, WLC_BW_20MHZ_BIT }; + /* 2GHZ, 5GHZ, 60GHZ, 6GHZ */ + u32 bw_cap[4] = { 0, 0, 0, 0 }; u32 rxchain; - u32 nchain; + u32 txchain; + u32 nrxchain; + u32 ntxchain; int err; s32 i; struct ieee80211_supported_band *band; u32 txstreams = 0; + u32 rxstreams = 0; u32 txbf_bfe_cap = 0; u32 txbf_bfr_cap = 0; + u8 he_enable; + struct brcmf_he_defcap he_cap; + u32 ldpc_cap = 0; + u32 stbc_rx = 0; + u32 stbc_tx = 0; (void)brcmf_fil_iovar_int_get(ifp, "vhtmode", &vhtmode); + (void)brcmf_fil_iovar_int_get(ifp, "ldpc_cap", &ldpc_cap); + (void)brcmf_fil_iovar_int_get(ifp, "stbc_rx", &stbc_rx); + (void)brcmf_fil_iovar_int_get(ifp, "stbc_tx", &stbc_tx); + err = brcmf_fil_xtlv_int8_get(ifp, "he", BRCMF_HE_CMD_ENABLE, + &he_enable); + if (!err && he_enable) { + brcmf_fil_xtlv_data_get(ifp, "he", BRCMF_HE_CMD_DEFCAP, &he_cap, + sizeof(he_cap)); + brcmf_dbg_hex_dump(BRCMF_INFO_ON(), he_cap.mac_cap, 6, + "default HE mac cap\n"); + brcmf_dbg_hex_dump(BRCMF_INFO_ON(), he_cap.phy_cap, 11, + "default HE phy cap\n"); + } err = brcmf_fil_iovar_int_get(ifp, "nmode", &nmode); if (err) { bphy_err(drvr, "nmode error (%d)\n", err); - } else { - brcmf_get_bwcap(ifp, bw_cap); } - brcmf_dbg(INFO, "nmode=%d, vhtmode=%d, bw_cap=(%d, %d)\n", + brcmf_get_bwcap(ifp, bw_cap, he_enable != 0); + brcmf_dbg(INFO, + "nmode=%d, vhtmode=%d, bw_cap=(%d, %d, %d), he_enable=%d\n", nmode, vhtmode, bw_cap[NL80211_BAND_2GHZ], - bw_cap[NL80211_BAND_5GHZ]); + bw_cap[NL80211_BAND_5GHZ], bw_cap[NL80211_BAND_6GHZ], + he_enable); err = brcmf_fil_iovar_int_get(ifp, "rxchain", &rxchain); if (err) { @@ -7355,12 +7527,31 @@ static int brcmf_setup_wiphybands(struct brcmf_cfg80211_info *cfg) else bphy_err(drvr, "rxchain error (%d)\n", err); - nchain = 1; + nrxchain = 1; + rxchain = 1; } else { - for (nchain = 0; rxchain; nchain++) + for (nrxchain = 0; rxchain; nrxchain++) rxchain = rxchain & (rxchain - 1); } - brcmf_dbg(INFO, "nchain=%d\n", nchain); + brcmf_dbg(INFO, "nrxchain=%d\n", nrxchain); + err = brcmf_fil_iovar_int_get(ifp, "txchain", &txchain); + if (err) { + /* rxchain unsupported by firmware of older chips */ + if (err == -EBADE) + bphy_info_once(drvr, "rxchain unsupported\n"); + else + bphy_err(drvr, "rxchain error (%d)\n", err); + + ntxchain = 1; + txchain = 1; + } else { + for (ntxchain = 0; txchain; ntxchain++) + txchain = txchain & (txchain - 1); + } + brcmf_dbg(INFO, "ntxchain=%d\n", ntxchain); + + wiphy->available_antennas_rx = nrxchain; + wiphy->available_antennas_tx = ntxchain; err = brcmf_construct_chaninfo(cfg, bw_cap); if (err) { @@ -7369,6 +7560,7 @@ static int brcmf_setup_wiphybands(struct brcmf_cfg80211_info *cfg) } if (vhtmode) { + (void)brcmf_fil_iovar_int_get(ifp, "rxstreams", &rxstreams); (void)brcmf_fil_iovar_int_get(ifp, "txstreams", &txstreams); (void)brcmf_fil_iovar_int_get(ifp, "txbf_bfe_cap", &txbf_bfe_cap); @@ -7382,10 +7574,13 @@ static int brcmf_setup_wiphybands(struct brcmf_cfg80211_info *cfg) continue; if (nmode) - brcmf_update_ht_cap(band, bw_cap, nchain); + brcmf_update_ht_cap(band, bw_cap, nrxchain); if (vhtmode) - brcmf_update_vht_cap(band, bw_cap, nchain, txstreams, - txbf_bfe_cap, txbf_bfr_cap); + brcmf_update_vht_cap(band, bw_cap, txstreams, rxstreams, + txbf_bfe_cap, txbf_bfr_cap, + ldpc_cap, stbc_rx, stbc_tx); + if (he_enable) + brcmf_update_he_cap(band, &sdata[band->band]); } return 0; @@ -7640,7 +7835,7 @@ static int brcmf_setup_wiphy(struct wiphy *wiphy, struct brcmf_if *ifp) struct ieee80211_supported_band *band; u16 max_interfaces = 0; bool gscan; - __le32 bandlist[3]; + __le32 bandlist[16]; u32 n_bands; int err, i; @@ -7708,6 +7903,13 @@ static int brcmf_setup_wiphy(struct wiphy *wiphy, struct brcmf_if *ifp) } if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_SAE_EXT)) wiphy->features |= NL80211_FEATURE_SAE; + + /* High accuracy and low power scans are always supported. */ + wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN); + wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_LOW_POWER_SCAN); + wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_LOW_SPAN_SCAN); + wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN; + wiphy->mgmt_stypes = brcmf_txrx_stypes; wiphy->max_remain_on_channel_duration = 5000; if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_PNO)) { @@ -7763,12 +7965,27 @@ static int brcmf_setup_wiphy(struct wiphy *wiphy, struct brcmf_if *ifp) band->n_channels = ARRAY_SIZE(__wl_5ghz_channels); wiphy->bands[NL80211_BAND_5GHZ] = band; } - } + if (bandlist[i] == cpu_to_le32(WLC_BAND_6G)) { + band = kmemdup(&__wl_band_6ghz, sizeof(__wl_band_6ghz), + GFP_KERNEL); + if (!band) + return -ENOMEM; + + band->channels = kmemdup(&__wl_6ghz_channels, + sizeof(__wl_6ghz_channels), + GFP_KERNEL); + if (!band->channels) { + kfree(band); + return -ENOMEM; + } + band->n_channels = ARRAY_SIZE(__wl_6ghz_channels); + wiphy->bands[NL80211_BAND_6GHZ] = band; + } + } if (wiphy->bands[NL80211_BAND_5GHZ] && brcmf_feat_is_enabled(ifp, BRCMF_FEAT_DOT11H)) - wiphy_ext_feature_set(wiphy, - NL80211_EXT_FEATURE_DFS_OFFLOAD); + wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_DFS_OFFLOAD); wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST); @@ -8267,9 +8484,17 @@ static void brcmf_cfg80211_reg_notifier(struct wiphy *wiphy, } err = brcmf_translate_country_code(ifp->drvr, req->alpha2, &ccreq); - if (err) - return; - + if (err) { + /* Because we ignore the default country code above, + * we will start out in our custom reg domain, but the chip + * may already be set to the right country. + * As such, we force the bands to be re-set the first + * time we try to set a country for real. + */ + if (err != -EAGAIN || !cfg->force_band_setup) + return; + } + cfg->force_band_setup = false; err = brcmf_fil_iovar_data_set(ifp, "country", &ccreq, sizeof(ccreq)); if (err) { bphy_err(drvr, "Firmware rejected country setting\n"); @@ -8298,6 +8523,10 @@ static void brcmf_free_wiphy(struct wiphy *wiphy) kfree(wiphy->bands[NL80211_BAND_5GHZ]->channels); kfree(wiphy->bands[NL80211_BAND_5GHZ]); } + if (wiphy->bands[NL80211_BAND_6GHZ]) { + kfree(wiphy->bands[NL80211_BAND_6GHZ]->channels); + kfree(wiphy->bands[NL80211_BAND_6GHZ]); + } #if IS_ENABLED(CONFIG_PM) if (wiphy->wowlan != &brcmf_wowlan_support) kfree(wiphy->wowlan); @@ -8332,6 +8561,7 @@ struct brcmf_cfg80211_info *brcmf_cfg80211_attach(struct brcmf_pub *drvr, cfg->pub = drvr; init_vif_event(&cfg->vif_event); INIT_LIST_HEAD(&cfg->vif_list); + cfg->force_band_setup = true; vif = brcmf_alloc_vif(cfg, NL80211_IFTYPE_STATION); if (IS_ERR(vif)) @@ -8389,18 +8619,21 @@ struct brcmf_cfg80211_info *brcmf_cfg80211_attach(struct brcmf_pub *drvr, if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_DUMP_OBSS)) ops->dump_survey = brcmf_cfg80211_dump_survey; - err = wiphy_register(wiphy); - if (err < 0) { - bphy_err(drvr, "Could not register wiphy device (%d)\n", err); - goto priv_out; - } - + /* We have to configure the bands before we register the wiphy device + * because it requires that band capabilities be correct. + */ err = brcmf_setup_wiphybands(cfg); if (err) { bphy_err(drvr, "Setting wiphy bands failed (%d)\n", err); goto wiphy_unreg_out; } + err = wiphy_register(wiphy); + if (err < 0) { + bphy_err(drvr, "Could not register wiphy device (%d)\n", err); + goto priv_out; + } + /* If cfg80211 didn't disable 40MHz HT CAP in wiphy_register(), * setup 40MHz in 2GHz band and enable OBSS scanning. */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h index 273c80f2d483a3..11f651ab9f4228 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h @@ -8,6 +8,7 @@ /* for brcmu_d11inf */ #include +#include #include "core.h" #include "fwil_types.h" @@ -127,7 +128,8 @@ enum brcmf_profile_fwsup { BRCMF_PROFILE_FWSUP_NONE, BRCMF_PROFILE_FWSUP_PSK, BRCMF_PROFILE_FWSUP_1X, - BRCMF_PROFILE_FWSUP_SAE + BRCMF_PROFILE_FWSUP_SAE, + BRCMF_PROFILE_FWSUP_ROAM }; /** @@ -172,6 +174,7 @@ struct brcmf_cfg80211_profile { enum brcmf_profile_fwsup use_fwsup; u16 use_fwauth; bool is_ft; + bool is_okc; }; /** @@ -350,6 +353,7 @@ struct brcmf_cfg80211_wowl { * @dongle_up: indicate whether dongle up or not. * @roam_on: on/off switch for dongle self-roaming. * @scan_tried: indicates if first scan attempted. + * @force_band_setup: indicates if we should force band setup * @dcmd_buf: dcmd buffer. * @extra_buf: mainly to grab assoc information. * @debugfsdir: debugfs folder for this device. @@ -380,6 +384,7 @@ struct brcmf_cfg80211_info { bool pwr_save; bool dongle_up; bool scan_tried; + bool force_band_setup; u8 *dcmd_buf; u8 *extra_buf; struct dentry *debugfsdir; @@ -409,6 +414,22 @@ struct brcmf_tlv { u8 data[]; }; +static inline enum nl80211_band fwil_band_to_nl80211(u16 band) +{ + switch (band) { + case WLC_BAND_2G: + return NL80211_BAND_2GHZ; + case WLC_BAND_5G: + return NL80211_BAND_5GHZ; + case WLC_BAND_6G: + return NL80211_BAND_6GHZ; + default: + WARN_ON(1); + break; + } + return 0; +} + static inline struct wiphy *cfg_to_wiphy(struct brcmf_cfg80211_info *cfg) { return cfg->wiphy; @@ -476,6 +497,8 @@ s32 brcmf_vif_set_mgmt_ie(struct brcmf_cfg80211_vif *vif, s32 pktflag, s32 brcmf_vif_clear_mgmt_ies(struct brcmf_cfg80211_vif *vif); u16 channel_to_chanspec(struct brcmu_d11inf *d11inf, struct ieee80211_channel *ch); +u16 chandef_to_chanspec(struct brcmu_d11inf *d11inf, + struct cfg80211_chan_def *ch); bool brcmf_get_vif_state_any(struct brcmf_cfg80211_info *cfg, unsigned long state); void brcmf_cfg80211_arm_vif_event(struct brcmf_cfg80211_info *cfg, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c index 4239f2b21e5423..75b6bfa28b6c29 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c @@ -162,6 +162,15 @@ struct sbconfig { #define SRCI_SRBSZ_SHIFT 0 #define SR_BSZ_BASE 14 +#define SYSMEM_SRCI_ROMNB_MASK 0x3e0 +#define SYSMEM_SRCI_ROMNB_SHIFT 5 +#define SYSMEM_SRCI_SRNB_MASK 0x1f +#define SYSMEM_SRCI_SRNB_SHIFT 0 +#define SYSMEM_SRCI_NEW_ROMNB_MASK 0xff000000 +#define SYSMEM_SRCI_NEW_ROMNB_SHIFT 24 +#define SYSMEM_SRCI_NEW_SRNB_MASK 0xff0000 +#define SYSMEM_SRCI_NEW_SRNB_SHIFT 16 + struct sbsocramregs { u32 coreinfo; u32 bwalloc; @@ -436,25 +445,11 @@ static void brcmf_chip_ai_resetcore(struct brcmf_core_priv *core, u32 prereset, { struct brcmf_chip_priv *ci; int count; - struct brcmf_core *d11core2 = NULL; - struct brcmf_core_priv *d11priv2 = NULL; ci = core->chip; - /* special handle two D11 cores reset */ - if (core->pub.id == BCMA_CORE_80211) { - d11core2 = brcmf_chip_get_d11core(&ci->pub, 1); - if (d11core2) { - brcmf_dbg(INFO, "found two d11 cores, reset both\n"); - d11priv2 = container_of(d11core2, - struct brcmf_core_priv, pub); - } - } - /* must disable first to work for arbitrary current core state */ brcmf_chip_ai_coredisable(core, prereset, reset); - if (d11priv2) - brcmf_chip_ai_coredisable(d11priv2, prereset, reset); count = 0; while (ci->ops->read32(ci->ctx, core->wrapbase + BCMA_RESET_CTL) & @@ -466,30 +461,9 @@ static void brcmf_chip_ai_resetcore(struct brcmf_core_priv *core, u32 prereset, usleep_range(40, 60); } - if (d11priv2) { - count = 0; - while (ci->ops->read32(ci->ctx, - d11priv2->wrapbase + BCMA_RESET_CTL) & - BCMA_RESET_CTL_RESET) { - ci->ops->write32(ci->ctx, - d11priv2->wrapbase + BCMA_RESET_CTL, - 0); - count++; - if (count > 50) - break; - usleep_range(40, 60); - } - } - ci->ops->write32(ci->ctx, core->wrapbase + BCMA_IOCTL, postreset | BCMA_IOCTL_CLK); ci->ops->read32(ci->ctx, core->wrapbase + BCMA_IOCTL); - - if (d11priv2) { - ci->ops->write32(ci->ctx, d11priv2->wrapbase + BCMA_IOCTL, - postreset | BCMA_IOCTL_CLK); - ci->ops->read32(ci->ctx, d11priv2->wrapbase + BCMA_IOCTL); - } } char *brcmf_chip_name(u32 id, u32 rev, char *buf, uint len) @@ -659,6 +633,7 @@ static u32 brcmf_chip_sysmem_ramsize(struct brcmf_core_priv *sysmem) u32 memsize = 0; u32 coreinfo; u32 idx; + u32 nrb; u32 nb; u32 banksize; @@ -666,10 +641,16 @@ static u32 brcmf_chip_sysmem_ramsize(struct brcmf_core_priv *sysmem) brcmf_chip_resetcore(&sysmem->pub, 0, 0, 0); coreinfo = brcmf_chip_core_read32(sysmem, SYSMEMREGOFFS(coreinfo)); - nb = (coreinfo & SRCI_SRNB_MASK) >> SRCI_SRNB_SHIFT; + if (sysmem->pub.rev >= 12) { + nrb = (coreinfo & SYSMEM_SRCI_NEW_ROMNB_MASK) >> SYSMEM_SRCI_NEW_ROMNB_SHIFT; + nb = (coreinfo & SYSMEM_SRCI_NEW_SRNB_MASK) >> SYSMEM_SRCI_NEW_SRNB_SHIFT; + } else { + nrb = (coreinfo & SYSMEM_SRCI_ROMNB_MASK) >> SYSMEM_SRCI_ROMNB_SHIFT; + nb = (coreinfo & SYSMEM_SRCI_SRNB_MASK) >> SYSMEM_SRCI_SRNB_SHIFT; + } for (idx = 0; idx < nb; idx++) { - brcmf_chip_socram_banksize(sysmem, idx, &banksize); + brcmf_chip_socram_banksize(sysmem, idx + nrb, &banksize); memsize += banksize; } @@ -731,6 +712,7 @@ static u32 brcmf_chip_tcm_rambase(struct brcmf_chip_priv *ci) case BRCM_CC_4366_CHIP_ID: case BRCM_CC_43664_CHIP_ID: case BRCM_CC_43666_CHIP_ID: + case BRCM_CC_4388_CHIP_ID: return 0x200000; case BRCM_CC_4355_CHIP_ID: case BRCM_CC_4359_CHIP_ID: @@ -1338,14 +1320,15 @@ static inline void brcmf_chip_ca7_set_passive(struct brcmf_chip_priv *chip) { struct brcmf_core *core; + int i; brcmf_chip_disable_arm(chip, BCMA_CORE_ARM_CA7); - core = brcmf_chip_get_core(&chip->pub, BCMA_CORE_80211); - brcmf_chip_resetcore(core, D11_BCMA_IOCTL_PHYRESET | - D11_BCMA_IOCTL_PHYCLOCKEN, - D11_BCMA_IOCTL_PHYCLOCKEN, - D11_BCMA_IOCTL_PHYCLOCKEN); + /* Disable the cores only and let the firmware enable them. */ + for (i = 0; (core = brcmf_chip_get_d11core(&chip->pub, i)); i++) + brcmf_chip_coredisable(core, D11_BCMA_IOCTL_PHYRESET | + D11_BCMA_IOCTL_PHYCLOCKEN, + D11_BCMA_IOCTL_PHYCLOCKEN); } static bool brcmf_chip_ca7_set_active(struct brcmf_chip_priv *chip, u32 rstvec) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c index 688f16c513192d..b80e0b4ad422ab 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c @@ -13,6 +13,7 @@ #include "core.h" #include "bus.h" #include "debug.h" +#include "fweh.h" #include "fwil.h" #include "fwil_types.h" #include "tracepoint.h" @@ -266,7 +267,6 @@ static int brcmf_c_process_cal_blob(struct brcmf_if *ifp) int brcmf_c_preinit_dcmds(struct brcmf_if *ifp) { struct brcmf_pub *drvr = ifp->drvr; - struct brcmf_fweh_info *fweh = drvr->fweh; u8 buf[BRCMF_DCMD_SMLEN]; struct brcmf_bus *bus; struct brcmf_rev_info_le revinfo; @@ -412,27 +412,6 @@ int brcmf_c_preinit_dcmds(struct brcmf_if *ifp) brcmf_c_set_joinpref_default(ifp); - /* Setup event_msgs, enable E_IF */ - err = brcmf_fil_iovar_data_get(ifp, "event_msgs", fweh->event_mask, - fweh->event_mask_len); - if (err) { - bphy_err(drvr, "Get event_msgs error (%d)\n", err); - goto done; - } - /* - * BRCMF_E_IF can safely be used to set the appropriate bit - * in the event_mask as the firmware event code is guaranteed - * to match the value of BRCMF_E_IF because it is old cruft - * that all vendors have. - */ - setbit(fweh->event_mask, BRCMF_E_IF); - err = brcmf_fil_iovar_data_set(ifp, "event_msgs", fweh->event_mask, - fweh->event_mask_len); - if (err) { - bphy_err(drvr, "Set event_msgs error (%d)\n", err); - goto done; - } - /* Setup default scan channel time */ err = brcmf_fil_cmd_int_set(ifp, BRCMF_C_SET_SCAN_CHANNEL_TIME, BRCMF_DEFAULT_SCAN_CHANNEL_TIME); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c index 862a0336a0b591..3ef91663863da8 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c @@ -1227,7 +1227,14 @@ static int brcmf_bus_started(struct brcmf_pub *drvr, struct cfg80211_ops *ops) if (ret < 0) goto fail; - brcmf_feat_attach(drvr); + ret = brcmf_feat_attach(drvr); + if (ret) + goto fail; + + /* Setup event_msgs, enable E_IF */ + ret = brcmf_fweh_init_events(ifp); + if (ret) + goto fail; ret = brcmf_proto_init_done(drvr); if (ret < 0) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h index 399b6810e394de..4b52a3aa855de8 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h @@ -97,6 +97,68 @@ struct brcmf_rev_info { u32 nvramrev; }; +struct brcmf_pno_info; +enum nl80211_band; +/** + * struct pno_struct_handler + */ +struct pno_struct_handler { + u8 version; + int (*pno_config)(struct brcmf_if *ifp, u32 scan_freq, u32 mscan, + u32 bestn); + u32 (*get_min_data_len)(void); + u32 (*get_result_count)(void *data); + u32 (*get_result_status)(void *data); + int (*validate_pfn_results)(void *data, u32 event_datalen); + u32 (*get_bucket_map)(void *data, int idx, struct brcmf_pno_info *pi); + int (*get_result_info)(void *data, int result_idx, + u8 (*ssid)[IEEE80211_MAX_SSID_LEN], u8 *ssid_len, + u8 *channel, enum nl80211_band *band); +}; + +struct cfg80211_scan_request; +struct scan_param_struct_handler { + u8 version; + void *(*get_struct_for_request)(struct brcmf_cfg80211_info *cfg, + u32 *struct_size, + struct cfg80211_scan_request *request); +}; + +struct cfg80211_ibss_params; +struct cfg80211_connect_params; + +/** + * struct join_param_struct_handler - Handler for different join parameter versions + * + * There are a number of different, incompatible structures and interface versions for join/extended join parameters + * We abstract away the actual structures used, so that code does not have to worry about filling in structs properly. + * + * This interface deliberately takes and returns opaque structures. + * + * @version - Interface version the firmware supports/uses + * @get_struct_for_ibss - Return a join parameter structure for a set of IBSS parameters. + * This structure can be used to join the passed BSS. + * @get_struct_for_connect - Return an extended join parameter structure for a set of connect + * parameters. This structure can be used to join the SSID specified in the parameters. + * @get_join_from_ext_join - When an extended join does not work, we fall back to a regular join. + * This function produces a join parameter struture from an extended join one. + */ +struct join_param_struct_handler { + u8 version; + /* This returns a join_param type struct */ + void *(*get_struct_for_ibss)(struct brcmf_cfg80211_info *cfg, + u32 *struct_size, + struct cfg80211_ibss_params *params); + /* This returns an ext_join_param type struct */ + void *(*get_struct_for_connect)(struct brcmf_cfg80211_info *cfg, + u32 *struct_size, + struct cfg80211_connect_params *params); + /* This returns the join param portion of an ext_join_param type struct. + * The memory returned is separately allocated from the passed-in struct. + */ + void *(*get_join_from_ext_join)(void *ext_join_param, u32 *struct_size); +}; + /* Common structure for module and instance linkage */ struct brcmf_pub { /* Linkage ponters */ @@ -145,6 +207,10 @@ struct brcmf_pub { u8 sta_mac_idx; const struct brcmf_fwvid_ops *vops; void *vdata; + u16 cnt_ver; + struct pno_struct_handler pno_handler; + struct scan_param_struct_handler scan_param_handler; + struct join_param_struct_handler join_param_handler; }; /* forward declarations */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.h index 9bb5f709d41a27..432d93ae8fb854 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.h @@ -85,6 +85,7 @@ do { \ #define BRCMF_FIL_ON() (brcmf_msg_level & BRCMF_FIL_VAL) #define BRCMF_FWCON_ON() (brcmf_msg_level & BRCMF_FWCON_VAL) #define BRCMF_SCAN_ON() (brcmf_msg_level & BRCMF_SCAN_VAL) +#define BRCMF_INFO_ON() (brcmf_msg_level & BRCMF_INFO_VAL) #else /* defined(DEBUG) || defined(CONFIG_BRCM_TRACING) */ @@ -104,6 +105,7 @@ do { \ #define BRCMF_FIL_ON() 0 #define BRCMF_FWCON_ON() 0 #define BRCMF_SCAN_ON() 0 +#define BRCMF_INFO_ON() 0 #endif /* defined(DEBUG) || defined(CONFIG_BRCM_TRACING) */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c index c3a602197662b7..abe7f6501e5ed0 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c @@ -24,6 +24,10 @@ static const struct brcmf_dmi_data acepc_t8_data = { BRCM_CC_4345_CHIP_ID, 6, "acepc-t8" }; +static const struct brcmf_dmi_data acer_a1_840_data = { + BRCM_CC_43340_CHIP_ID, 2, "acer-a1-840" +}; + /* The Chuwi Hi8 Pro uses the same Ampak AP6212 module as the Chuwi Vi8 Plus * and the nvram for the Vi8 Plus is already in linux-firmware, so use that. */ @@ -91,6 +95,16 @@ static const struct dmi_system_id dmi_platform_data[] = { }, .driver_data = (void *)&acepc_t8_data, }, + { + /* Acer Iconia One 8 A1-840 (non FHD version) */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "BayTrail"), + /* Above strings are too generic also match BIOS date */ + DMI_MATCH(DMI_BIOS_DATE, "04/01/2014"), + }, + .driver_data = (void *)&acer_a1_840_data, + }, { /* Chuwi Hi8 Pro with D2D3_Hi8Pro.233 BIOS */ .matches = { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c index 488364ef8ff2a1..d823ced048454a 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c @@ -16,9 +16,24 @@ #include "fwvid.h" #include "feature.h" #include "common.h" +#include "pno.h" +#include "scan_param.h" +#include "join_param.h" #define BRCMF_FW_UNSUPPORTED 23 +/* MIN branch version supporting join iovar versioning */ +#define MIN_JOINEXT_V1_FW_MAJOR 17u +/* Branch/es supporting join iovar versioning prior to + * MIN_JOINEXT_V1_FW_MAJOR + */ +#define MIN_JOINEXT_V1_BR2_FW_MAJOR 16 +#define MIN_JOINEXT_V1_BR2_FW_MINOR 1 + +#define MIN_JOINEXT_V1_BR1_FW_MAJOR 14 +#define MIN_JOINEXT_V1_BR1_FW_MINOR_2 2 +#define MIN_JOINEXT_V1_BR1_FW_MINOR_4 4 + /* * expand feature list to array of feature strings. */ @@ -45,6 +60,7 @@ static const struct brcmf_feat_fwcap brcmf_fwcap_map[] = { { BRCMF_FEAT_SAE, "sae " }, { BRCMF_FEAT_FWAUTH, "idauth" }, { BRCMF_FEAT_SAE_EXT, "sae_ext" }, + { BRCMF_FEAT_GCMP, "gcmp"} }; #ifdef DEBUG @@ -136,7 +152,7 @@ struct brcmf_feat_wlcfeat { static const struct brcmf_feat_wlcfeat brcmf_feat_wlcfeat_map[] = { { 12, 0, BIT(BRCMF_FEAT_PMKID_V2) }, - { 13, 0, BIT(BRCMF_FEAT_PMKID_V3) }, + { 13, 0, BIT(BRCMF_FEAT_PMKID_V3) } }; static void brcmf_feat_wlc_version_overrides(struct brcmf_pub *drv) @@ -286,9 +302,12 @@ static int brcmf_feat_fwcap_debugfs_read(struct seq_file *seq, void *data) return 0; } -void brcmf_feat_attach(struct brcmf_pub *drvr) +int brcmf_feat_attach(struct brcmf_pub *drvr) { struct brcmf_if *ifp = brcmf_get_ifp(drvr, 0); + struct brcmf_join_version_le join_ver; + struct brcmf_scan_version_le scan_ver; + struct brcmf_pno_param_v3_le pno_params; struct brcmf_pno_macaddr_le pfn_mac; struct brcmf_gscan_config gscan_cfg; u32 wowl_cap; @@ -331,6 +350,7 @@ void brcmf_feat_attach(struct brcmf_pub *drvr) brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_TDLS, "tdls_enable"); brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_MFP, "mfp"); brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_DUMP_OBSS, "dump_obss"); + brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_EVENT_MSGS_EXT, "event_msgs_ext"); pfn_mac.version = BRCMF_PFN_MACADDR_CFG_VER; err = brcmf_fil_iovar_data_get(ifp, "pfn_macaddr", &pfn_mac, @@ -339,13 +359,71 @@ void brcmf_feat_attach(struct brcmf_pub *drvr) ifp->drvr->feat_flags |= BIT(BRCMF_FEAT_SCAN_RANDOM_MAC); brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_FWSUP, "sup_wpa"); - brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_SCAN_V2, "scan_ver"); + + err = brcmf_fil_iovar_data_get(ifp, "join_ver", &join_ver, sizeof(join_ver)); + if (!err) { + u16 ver = le16_to_cpu(join_ver.join_ver_major); + err = brcmf_join_param_setup_for_version(drvr, ver); + } else { + /* Default to version 0, unless it is one of the firmware branches + * that doesn't have a join_ver iovar but are still version 1 */ + u8 version = 0; + struct brcmf_wlc_version_le ver; + err = brcmf_fil_iovar_data_get(ifp, "wlc_ver", &ver, + sizeof(ver)); + if (!err) { + u16 major = le16_to_cpu(ver.wlc_ver_major); + u16 minor = le16_to_cpu(ver.wlc_ver_minor); + if (((major == MIN_JOINEXT_V1_BR1_FW_MAJOR) && + ((minor == MIN_JOINEXT_V1_BR1_FW_MINOR_2) || + (minor == MIN_JOINEXT_V1_BR1_FW_MINOR_4))) || + ((major == MIN_JOINEXT_V1_BR2_FW_MAJOR) && + (minor >= MIN_JOINEXT_V1_BR2_FW_MINOR)) || + (major >= MIN_JOINEXT_V1_FW_MAJOR)) { + version = 1; + } + } + err = brcmf_join_param_setup_for_version(drvr, version); + } + if (err) { + bphy_err(drvr, "Error setting up join structure handler: %d\n", + err); + return err; + } + err = brcmf_fil_iovar_data_get(ifp, "scan_ver", &scan_ver, + sizeof(scan_ver)); + if (!err) { + u16 ver = le16_to_cpu(scan_ver.scan_ver_major); + err = brcmf_scan_param_setup_for_version(drvr, ver); + } else { + /* Default to version 1. */ + err = brcmf_scan_param_setup_for_version(drvr, 1); + } + if (err) { + bphy_err(drvr, "Error setting up scan structure handler: %d\n", + err); + return err; + } + /* See what version of PFN scan is supported*/ + err = brcmf_fil_iovar_data_get(ifp, "pno_set", &pno_params, + sizeof(pno_params)); + if (!err) { + err = brcmf_pno_setup_for_version( + drvr, le16_to_cpu(pno_params.version)); + } else { + /* Default to version 2, supported by all chips we support. */ + err = brcmf_pno_setup_for_version(drvr, 2); + } + if (err) { + bphy_err(drvr, "Error setting up escan structure handler: %d\n", + err); + return err; + } brcmf_feat_wlc_version_overrides(drvr); brcmf_feat_firmware_overrides(drvr); brcmf_fwvid_feat_attach(ifp); - if (drvr->settings->feature_disable) { brcmf_dbg(INFO, "Features: 0x%02x, disable: 0x%02x\n", ifp->drvr->feat_flags, @@ -365,6 +443,7 @@ void brcmf_feat_attach(struct brcmf_pub *drvr) /* no quirks */ break; } + return 0; } void brcmf_feat_debugfs_create(struct brcmf_pub *drvr) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h index 31f8695ca41765..be271ca0fca588 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h @@ -30,8 +30,12 @@ * SAE: simultaneous authentication of equals * FWAUTH: Firmware authenticator * DUMP_OBSS: Firmware has capable to dump obss info to support ACS - * SCAN_V2: Version 2 scan params * SAE_EXT: SAE authentication handled by user-space supplicant + * PMKID_V2: Version 2 PMKID + * PMKID_V3: Version 3 PMKID + * EVENT_MSGS_EXT: Event messages extension + * JOIN_V1: Version 1 join struct + * GCMP: GCMP Cipher suite support */ #define BRCMF_FEAT_LIST \ BRCMF_FEAT_DEF(MBSS) \ @@ -56,10 +60,11 @@ BRCMF_FEAT_DEF(SAE) \ BRCMF_FEAT_DEF(FWAUTH) \ BRCMF_FEAT_DEF(DUMP_OBSS) \ - BRCMF_FEAT_DEF(SCAN_V2) \ BRCMF_FEAT_DEF(PMKID_V2) \ BRCMF_FEAT_DEF(PMKID_V3) \ - BRCMF_FEAT_DEF(SAE_EXT) + BRCMF_FEAT_DEF(SAE_EXT) \ + BRCMF_FEAT_DEF(EVENT_MSGS_EXT) \ + BRCMF_FEAT_DEF(GCMP) /* * Quirks: @@ -97,8 +102,10 @@ enum brcmf_feat_quirk { * brcmf_feat_attach() - determine features and quirks. * * @drvr: driver instance. + * + * Return: 0 in case of success, error code otherwise. */ -void brcmf_feat_attach(struct brcmf_pub *drvr); +int brcmf_feat_attach(struct brcmf_pub *drvr); /** * brcmf_feat_debugfs_create() - create debugfs entries. diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c index c2d98ee6652f3a..09819d233af97e 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c @@ -11,8 +11,10 @@ #include "core.h" #include "debug.h" #include "tracepoint.h" +#include "feature.h" #include "fweh.h" #include "fwil.h" +#include "fwil_types.h" #include "proto.h" #include "bus.h" #include "fwvid.h" @@ -425,6 +427,67 @@ void brcmf_fweh_unregister(struct brcmf_pub *drvr, drvr->fweh->evt_handler[evt_handler_idx] = NULL; } +/** + * brcmf_fweh_init_events() - initialize event handling. + * + * @ifp: primary interface object. + */ +int brcmf_fweh_init_events(struct brcmf_if *ifp) +{ + struct brcmf_pub *drvr = ifp->drvr; + struct brcmf_eventmsgs_ext_le *eventmsgs; + size_t size = sizeof(*eventmsgs) + drvr->fweh->event_mask_len; + int err; + + eventmsgs = kzalloc(size, GFP_KERNEL); + if(!eventmsgs) + return -ENOMEM; + + eventmsgs->version = EVENTMSGS_VER; + eventmsgs->command = EVENTMSGS_NONE; + eventmsgs->len = drvr->fweh->event_mask_len; + eventmsgs->maxgetsize = drvr->fweh->event_mask_len; + + if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_EVENT_MSGS_EXT)) + err = brcmf_fil_iovar_data_get(ifp, "event_msgs_ext", + eventmsgs, size); + else + err = brcmf_fil_iovar_data_get(ifp, "event_msgs", + drvr->fweh->event_mask, + drvr->fweh->event_mask_len); + + if (err) { + bphy_err(drvr, "Get event_msgs error (%d)\n", err); + kfree(eventmsgs); + return err; + } + + brcmf_dbg(EVENT, "Event mask len: driver=%d fw=%d\n", + drvr->fweh->event_mask_len, eventmsgs->len); + + /* want to handle IF event as well */ + brcmf_dbg(EVENT, "enable event IF\n"); + setbit(eventmsgs->mask, BRCMF_E_IF); + + eventmsgs->version = EVENTMSGS_VER; + eventmsgs->command = EVENTMSGS_SET_MASK; + eventmsgs->len = drvr->fweh->event_mask_len; + + if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_EVENT_MSGS_EXT)) + err = brcmf_fil_iovar_data_set(ifp, "event_msgs_ext", + eventmsgs, size); + else + err = brcmf_fil_iovar_data_set(ifp, "event_msgs", + drvr->fweh->event_mask, + drvr->fweh->event_mask_len); + + if (err) + bphy_err(drvr, "Set event_msgs error (%d)\n", err); + + kfree(eventmsgs); + return err; +} + /** * brcmf_fweh_activate_events() - enables firmware events registered. * @@ -432,32 +495,47 @@ void brcmf_fweh_unregister(struct brcmf_pub *drvr, */ int brcmf_fweh_activate_events(struct brcmf_if *ifp) { - struct brcmf_fweh_info *fweh = ifp->drvr->fweh; - enum brcmf_fweh_event_code code; + struct brcmf_pub *drvr = ifp->drvr; + struct brcmf_eventmsgs_ext_le *eventmsgs; + size_t size = sizeof(*eventmsgs) + drvr->fweh->event_mask_len; int i, err; - memset(fweh->event_mask, 0, fweh->event_mask_len); - for (i = 0; i < fweh->num_event_codes; i++) { - if (fweh->evt_handler[i]) { - brcmf_fweh_map_fwevt_code(fweh, i, &code); + eventmsgs = kzalloc(size, GFP_KERNEL); + if(!eventmsgs) + return -ENOMEM; + + for (i = 0; i < drvr->fweh->num_event_codes; i++) { + if (drvr->fweh->evt_handler[i]) { brcmf_dbg(EVENT, "enable event %s\n", - brcmf_fweh_event_name(code)); - setbit(fweh->event_mask, i); + brcmf_fweh_event_name(i)); + setbit(eventmsgs->mask, i); } } /* want to handle IF event as well */ brcmf_dbg(EVENT, "enable event IF\n"); - setbit(fweh->event_mask, BRCMF_E_IF); + setbit(eventmsgs->mask, BRCMF_E_IF); + + eventmsgs->version = EVENTMSGS_VER; + eventmsgs->command = EVENTMSGS_SET_MASK; + eventmsgs->len = drvr->fweh->event_mask_len; /* allow per-vendor method to activate firmware events */ if (!brcmf_fwvid_activate_events(ifp)) return 0; - err = brcmf_fil_iovar_data_set(ifp, "event_msgs", fweh->event_mask, - fweh->event_mask_len); + if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_EVENT_MSGS_EXT)) + err = brcmf_fil_iovar_data_set(ifp, "event_msgs_ext", + eventmsgs, size); + else + err = brcmf_fil_iovar_data_set(ifp, "event_msgs", + drvr->fweh->event_mask, + drvr->fweh->event_mask_len); + if (err) - bphy_err(fweh->drvr, "Set event_msgs error (%d)\n", err); + bphy_err(drvr, "Set event_msgs error (%d)\n", err); + + kfree(eventmsgs); return err; } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h index e327dd58d29c95..53c4b58e6323cc 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h @@ -356,6 +356,7 @@ int brcmf_fweh_register(struct brcmf_pub *drvr, enum brcmf_fweh_event_code code, void *data)); void brcmf_fweh_unregister(struct brcmf_pub *drvr, enum brcmf_fweh_event_code code); +int brcmf_fweh_init_events(struct brcmf_if *ifp); int brcmf_fweh_activate_events(struct brcmf_if *ifp); void brcmf_fweh_process_event(struct brcmf_pub *drvr, struct brcmf_event *event_packet, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h index e74a23e11830c1..7b8f809cdc412d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h @@ -18,7 +18,8 @@ #define BRCMF_ARP_OL_HOST_AUTO_REPLY 0x00000004 #define BRCMF_ARP_OL_PEER_AUTO_REPLY 0x00000008 -#define BRCMF_BSS_INFO_VERSION 109 /* curr ver of brcmf_bss_info_le struct */ +#define BRCMF_BSS_INFO_MIN_VERSION 109 /* min ver of brcmf_bss_info_le struct */ +#define BRCMF_BSS_INFO_MAX_VERSION 112 /* max ver of brcmf_bss_info_le struct */ #define BRCMF_BSS_RSSI_ON_CHANNEL 0x0004 #define BRCMF_STA_BRCM 0x00000001 /* Running a Broadcom driver */ @@ -46,12 +47,10 @@ #define BRCMF_STA_DWDS_CAP 0x01000000 /* DWDS CAP */ #define BRCMF_STA_DWDS 0x02000000 /* DWDS active */ -/* size of brcmf_scan_params not including variable length array */ -#define BRCMF_SCAN_PARAMS_FIXED_SIZE 64 -#define BRCMF_SCAN_PARAMS_V2_FIXED_SIZE 72 - /* version of brcmf_scan_params structure */ #define BRCMF_SCAN_PARAMS_VERSION_V2 2 +#define BRCMF_SCAN_PARAMS_VERSION_V3 3 +#define BRCMF_SCAN_PARAMS_VERSION_V4 4 /* masks for channel and ssid count */ #define BRCMF_SCAN_PARAMS_COUNT_MASK 0x0000ffff @@ -62,16 +61,26 @@ #define BRCMF_SCANTYPE_ACTIVE 0 #define BRCMF_SCANTYPE_PASSIVE 1 +/* Additional scanning flags */ +#define BRCMF_SCANFLAGS_LOW_PRIO 0x2 +#define BRCMF_SCANFLAGS_LOW_POWER 0x1000 +#define BRCMF_SCANFLAGS_HIGH_ACCURACY 0x2000 +#define BRCMF_SCANFLAGS_LOW_SPAN 0x4000 + +/* scan ssid_type flags */ +#define BRCMF_SCANSSID_INC_RNR 0x02 /* Include RNR channels*/ + #define BRCMF_WSEC_MAX_PSK_LEN 32 #define BRCMF_WSEC_PASSPHRASE BIT(0) -#define BRCMF_WSEC_MAX_SAE_PASSWORD_LEN 128 +#define BRCMF_WSEC_MAX_SAE_PASSWORD_LEN 256 /* primary (ie tx) key */ #define BRCMF_PRIMARY_KEY (1 << 1) #define DOT11_BSSTYPE_ANY 2 #define BRCMF_ESCAN_REQ_VERSION 1 #define BRCMF_ESCAN_REQ_VERSION_V2 2 +#define BRCMF_ESCAN_REQ_VERSION_V3 3 #define BRCMF_MAXRATES_IN_SET 16 /* max # of rates in rateset */ @@ -320,29 +329,57 @@ struct brcmf_bss_info_le { __le16 beacon_period; /* units are Kusec */ __le16 capability; /* Capability information */ u8 SSID_len; - u8 SSID[32]; + u8 SSID[IEEE80211_MAX_SSID_LEN]; + u8 bcnflags; /* additional flags w.r.t. beacon */ struct { __le32 count; /* # rates in this set */ u8 rates[16]; /* rates in 500kbps units w/hi bit set if basic */ } rateset; /* supported rates */ __le16 chanspec; /* chanspec for bss */ __le16 atim_window; /* units are Kusec */ - u8 dtim_period; /* DTIM period */ + u8 dtim_period; /* DTIM period */ + u8 accessnet; /* from beacon interwork IE (if bcnflags) */ __le16 RSSI; /* receive signal strength (in dBm) */ s8 phy_noise; /* noise (in dBm) */ u8 n_cap; /* BSS is 802.11N Capable */ + u8 he_cap; /* BSS is he capable */ + u8 load; /* BSS Load from QBSS load IE if available */ /* 802.11N BSS Capabilities (based on HT_CAP_*): */ __le32 nbss_cap; u8 ctl_ch; /* 802.11N BSS control channel number */ - __le32 reserved32[1]; /* Reserved for expansion of BSS properties */ + u8 reserved1[3]; /* Reserved for expansion of BSS properties */ + __le16 vht_rxmcsmap; /* VHT rx mcs map (802.11ac IE, VHT_CAP_MCS_MAP_*) */ + __le16 vht_txmcsmap; /* VHT tx mcs map (802.11ac IE, VHT_CAP_MCS_MAP_*) */ u8 flags; /* flags */ - u8 reserved[3]; /* Reserved for expansion of BSS properties */ + u8 vht_cap; /* BSS is vht capable */ + u8 reserved2[2]; /* Reserved for expansion of BSS properties */ u8 basic_mcs[BRCMF_MCSSET_LEN]; /* 802.11N BSS required MCS set */ __le16 ie_offset; /* offset at which IEs start, from beginning */ + u8 reserved3[2]; /* Reserved for expansion of BSS properties */ __le32 ie_length; /* byte length of Information Elements */ __le16 SNR; /* average SNR of during frame reception */ + __le16 vht_mcsmap; /**< STA's Associated vhtmcsmap */ + __le16 vht_mcsmap_prop; /**< STA's Associated prop vhtmcsmap */ + __le16 vht_txmcsmap_prop; /**< prop VHT tx mcs prop */ + __le32 he_mcsmap; /**< STA's Associated hemcsmap */ + __le32 he_rxmcsmap; /**< HE rx mcs map (802.11ax IE, HE_CAP_MCS_MAP_*) */ + __le32 he_txmcsmap; /**< HE tx mcs map (802.11ax IE, HE_CAP_MCS_MAP_*) */ + __le32 timestamp[2]; /* Beacon Timestamp for FAKEAP req */ + /* V112 fields follow */ + u8 eht_cap; /* BSS is EHT capable */ + u8 reserved4[3]; /* Reserved for expansion of BSS properties */ + /* by the spec. it is maximum 16 streams hence all mcs code for all nss may not fit + * in a 32 bit mcs nss map but since this field only reflects the common mcs nss map + * between that of the peer and our device so it's probably ok to make it 32 bit and + * allow only a limited number of nss e.g. upto 8 of them in the map given the fact + * that our device probably won't exceed 4 streams anyway... + */ + __le32 eht_mcsmap; /* STA's associated EHT mcs code map */ + /* FIXME: change the following mcs code map to uint32 if all mcs+nss can fit in */ + u8 eht_rxmcsmap[6]; /* EHT rx mcs code map */ + u8 eht_txmcsmap[6]; /* EHT tx mcs code map */ /* Add new fields here */ /* variable length Information Elements */ }; @@ -366,23 +403,23 @@ struct brcmf_ssid8_le { }; struct brcmf_scan_params_le { - struct brcmf_ssid_le ssid_le; /* default: {0, ""} */ - u8 bssid[ETH_ALEN]; /* default: bcast */ - s8 bss_type; /* default: any, + struct brcmf_ssid_le ssid_le; /* default: {0, ""} */ + u8 bssid[ETH_ALEN]; /* default: bcast */ + s8 bss_type; /* default: any, * DOT11_BSSTYPE_ANY/INFRASTRUCTURE/INDEPENDENT */ - u8 scan_type; /* flags, 0 use default */ - __le32 nprobes; /* -1 use default, number of probes per channel */ - __le32 active_time; /* -1 use default, dwell time per channel for + u8 scan_type; /* flags, 0 use default */ + __le32 nprobes; /* -1 use default, number of probes per channel */ + __le32 active_time; /* -1 use default, dwell time per channel for * active scanning */ - __le32 passive_time; /* -1 use default, dwell time per channel + __le32 passive_time; /* -1 use default, dwell time per channel * for passive scanning */ __le32 home_time; /* -1 use default, dwell time for the * home channel between channel scans */ - __le32 channel_num; /* count of channels and ssids that follow + __le32 channel_num; /* count of channels and ssids that follow * * low half is count of channels in * channel_list, 0 means default (use all @@ -398,56 +435,125 @@ struct brcmf_scan_params_le { * fixed parameter portion is assumed, otherwise * ssid in the fixed portion is ignored */ - union { - __le16 padding; /* Reserve space for at least 1 entry for abort - * which uses an on stack brcmf_scan_params_le - */ - DECLARE_FLEX_ARRAY(__le16, channel_list); /* chanspecs */ - }; + __le16 channel_list[]; /* chanspecs */ }; struct brcmf_scan_params_v2_le { - __le16 version; /* structure version */ - __le16 length; /* structure length */ - struct brcmf_ssid_le ssid_le; /* default: {0, ""} */ - u8 bssid[ETH_ALEN]; /* default: bcast */ - s8 bss_type; /* default: any, - * DOT11_BSSTYPE_ANY/INFRASTRUCTURE/INDEPENDENT - */ - u8 pad; - __le32 scan_type; /* flags, 0 use default */ - __le32 nprobes; /* -1 use default, number of probes per channel */ - __le32 active_time; /* -1 use default, dwell time per channel for - * active scanning - */ - __le32 passive_time; /* -1 use default, dwell time per channel - * for passive scanning - */ - __le32 home_time; /* -1 use default, dwell time for the - * home channel between channel scans - */ - __le32 channel_num; /* count of channels and ssids that follow - * - * low half is count of channels in - * channel_list, 0 means default (use all - * available channels) - * - * high half is entries in struct brcmf_ssid - * array that follows channel_list, aligned for - * s32 (4 bytes) meaning an odd channel count - * implies a 2-byte pad between end of - * channel_list and first ssid - * - * if ssid count is zero, single ssid in the - * fixed parameter portion is assumed, otherwise - * ssid in the fixed portion is ignored - */ - union { - __le16 padding; /* Reserve space for at least 1 entry for abort - * which uses an on stack brcmf_scan_params_v2_le - */ - DECLARE_FLEX_ARRAY(__le16, channel_list); /* chanspecs */ - }; + __le16 version; /* structure version */ + __le16 length; /* structure length */ + struct brcmf_ssid_le ssid_le; /* default: {0, ""} */ + u8 bssid[ETH_ALEN]; /* default: bcast */ + s8 bss_type; /* default: any, + * DOT11_BSSTYPE_ANY/INFRASTRUCTURE/INDEPENDENT + */ + u8 PAD; + __le32 scan_type; /* flags, 0 use default */ + __le32 nprobes; /* -1 use default, number of probes per channel */ + __le32 active_time; /* -1 use default, dwell time per channel for + * active scanning + */ + __le32 passive_time; /* -1 use default, dwell time per channel + * for passive scanning + */ + __le32 home_time; /* -1 use default, dwell time for the + * home channel between channel scans + */ + __le32 channel_num; /* count of channels and ssids that follow + * + * low half is count of channels in + * channel_list, 0 means default (use all + * available channels) + * + * high half is entries in struct brcmf_ssid + * array that follows channel_list, aligned for + * s32 (4 bytes) meaning an odd channel count + * implies a 2-byte pad between end of + * channel_list and first ssid + * + * if ssid count is zero, single ssid in the + * fixed parameter portion is assumed, otherwise + * ssid in the fixed portion is ignored + */ + __le16 channel_list[]; /* chanspecs */ +}; + +struct brcmf_scan_params_v3_le { + __le16 version; /* structure version */ + __le16 length; /* structure length */ + struct brcmf_ssid_le ssid_le; /* default: {0, ""} */ + u8 bssid[ETH_ALEN]; /* default: bcast */ + s8 bss_type; /* default: any, + * DOT11_BSSTYPE_ANY/INFRASTRUCTURE/INDEPENDENT + */ + u8 ssid_type; /* short vs regular SSID */ + __le32 scan_type; /* flags, 0 use default */ + __le32 nprobes; /* -1 use default, number of probes per channel */ + __le32 active_time; /* -1 use default, dwell time per channel for + * active scanning + */ + __le32 passive_time; /* -1 use default, dwell time per channel + * for passive scanning + */ + __le32 home_time; /* -1 use default, dwell time for the + * home channel between channel scans + */ + __le32 channel_num; /* count of channels and ssids that follow + * + * low half is count of channels in + * channel_list, 0 means default (use all + * available channels) + * + * high half is entries in struct brcmf_ssid + * array that follows channel_list, aligned for + * s32 (4 bytes) meaning an odd channel count + * implies a 2-byte pad between end of + * channel_list and first ssid + * + * if ssid count is zero, single ssid in the + * fixed parameter portion is assumed, otherwise + * ssid in the fixed portion is ignored + */ + __le16 channel_list[]; /* chanspecs */ +}; + +struct brcmf_scan_params_v4_le { + __le16 version; /* structure version */ + __le16 length; /* structure length */ + struct brcmf_ssid_le ssid_le; /* default: {0, ""} */ + u8 bssid[ETH_ALEN]; /* default: bcast */ + s8 bss_type; /* default: any, + * DOT11_BSSTYPE_ANY/INFRASTRUCTURE/INDEPENDENT + */ + u8 ssid_type; /* short vs regular SSID */ + __le32 scan_type; /* flags, 0 use default */ + __le32 scan_type_ext; /* ext flags, 0 use default */ + __le32 nprobes; /* -1 use default, number of probes per channel */ + __le32 active_time; /* -1 use default, dwell time per channel for + * active scanning + */ + __le32 passive_time; /* -1 use default, dwell time per channel + * for passive scanning + */ + __le32 home_time; /* -1 use default, dwell time for the + * home channel between channel scans + */ + __le32 channel_num; /* count of channels and ssids that follow + * + * low half is count of channels in + * channel_list, 0 means default (use all + * available channels) + * + * high half is entries in struct brcmf_ssid + * array that follows channel_list, aligned for + * s32 (4 bytes) meaning an odd channel count + * implies a 2-byte pad between end of + * channel_list and first ssid + * + * if ssid count is zero, single ssid in the + * fixed parameter portion is assumed, otherwise + * ssid in the fixed portion is ignored + */ + __le16 channel_list[]; /* chanspecs */ }; struct brcmf_scan_results { @@ -464,6 +570,8 @@ struct brcmf_escan_params_le { union { struct brcmf_scan_params_le params_le; struct brcmf_scan_params_v2_le params_v2_le; + struct brcmf_scan_params_v3_le params_v3_le; + struct brcmf_scan_params_v4_le params_v4_le; }; }; @@ -482,11 +590,67 @@ struct brcmf_escan_result_le { struct brcmf_assoc_params_le { /* 00:00:00:00:00:00: broadcast scan */ u8 bssid[ETH_ALEN]; + /* 0: use chanspec_num, and the single bssid, + * otherwise count of chanspecs in chanspec_list + * AND paired bssids following chanspec_list + * also, chanspec_num has to be set to zero + * for bssid list to be used + */ + __le16 bssid_cnt; + /* 0: all available channels, otherwise count of chanspecs in + * chanspec_list */ + __le32 chanspec_num; + /* list of chanspecs */ + __le16 chanspec_list[]; +}; + +struct brcmf_assoc_params_v1_le { + __le16 version; + __le16 flags; + /* 00:00:00:00:00:00: broadcast scan */ + u8 bssid[ETH_ALEN]; + /* 0: use chanspec_num, and the single bssid, + * otherwise count of chanspecs in chanspec_list + * AND paired bssids following chanspec_list + * also, chanspec_num has to be set to zero + * for bssid list to be used + */ + __le16 bssid_cnt; /* 0: all available channels, otherwise count of chanspecs in * chanspec_list */ __le32 chanspec_num; /* list of chanspecs */ - __le16 chanspec_list[1]; + __le16 chanspec_list[]; +}; + +/* ML assoc and scan params */ +struct brcmf_ml_assoc_scan_params_v1_le { + /* whether to follow strictly ordered assoc ? */ + u8 ml_assoc_mode; + /* to identify whether ml scan needs to be triggered */ + u8 ml_scan_mode; + u8 pad[2]; +}; + +struct brcmf_assoc_params_v2_le { + __le16 version; + __le16 flags; + /* 00:00:00:00:00:00: broadcast scan */ + u8 bssid[ETH_ALEN]; + /* 0: use chanspec_num, and the single bssid, + * otherwise count of chanspecs in chanspec_list + * AND paired bssids following chanspec_list + * also, chanspec_num has to be set to zero + * for bssid list to be used + */ + __le16 bssid_cnt; + /* Multilink association and scan params */ + struct brcmf_ml_assoc_scan_params_v1_le ml_assoc_scan_params; + /* 0: all available channels, otherwise count of chanspecs in + * chanspec_list */ + __le32 chanspec_num; + /* list of chanspecs */ + __le16 chanspec_list[]; }; /** @@ -511,9 +675,19 @@ struct brcmf_join_params { struct brcmf_assoc_params_le params_le; }; +struct brcmf_join_params_v1 { + struct brcmf_ssid_le ssid_le; + struct brcmf_assoc_params_v1_le params_le; +}; +struct brcmf_join_params_v2 { + struct brcmf_ssid_le ssid_le; + struct brcmf_assoc_params_v2_le params_le; +}; + /* scan params for extended join */ struct brcmf_join_scan_params_le { u8 scan_type; /* 0 use default, active or passive scan */ + u8 PAD[3]; __le32 nprobes; /* -1 use default, nr of probes per channel */ __le32 active_time; /* -1 use default, dwell time per channel for * active scanning @@ -526,6 +700,23 @@ struct brcmf_join_scan_params_le { */ }; +/* scan params for extended join */ +struct brcmf_join_scan_params_v1_le { + u8 scan_type; /* 0 use default, active or passive scan */ + u8 ml_scan_mode; /* 0 scan ML channels in RNR, 1 scan only provided channels */ + u8 PAD[2]; + __le32 nprobes; /* -1 use default, nr of probes per channel */ + __le32 active_time; /* -1 use default, dwell time per channel for + * active scanning + */ + __le32 passive_time; /* -1 use default, dwell time per channel + * for passive scanning + */ + __le32 home_time; /* -1 use default, dwell time for the home + * channel between channel scans + */ +}; + /* extended join params */ struct brcmf_ext_join_params_le { struct brcmf_ssid_le ssid_le; /* {0, ""}: wildcard scan */ @@ -533,6 +724,24 @@ struct brcmf_ext_join_params_le { struct brcmf_assoc_params_le assoc_le; }; +/* extended join params */ +struct brcmf_ext_join_params_v1_le { + __le16 version; + u16 pad; + struct brcmf_ssid_le ssid_le; /* {0, ""}: wildcard scan */ + struct brcmf_join_scan_params_le scan_le; + struct brcmf_assoc_params_v1_le assoc_le; +}; + +/* extended join params v2 */ +struct brcmf_ext_join_params_v2_le { + __le16 version; + u16 pad; + struct brcmf_ssid_le ssid_le; /* {0, ""}: wildcard scan */ + struct brcmf_join_scan_params_v1_le scan_le; + struct brcmf_assoc_params_v2_le assoc_le; +}; + struct brcmf_wsec_key { u32 index; /* key index */ u32 len; /* key length */ @@ -580,11 +789,15 @@ struct brcmf_wsec_key_le { * @key_len: number of octets in key material. * @flags: key handling qualifiers. * @key: PMK key material. + * @opt_len: optional field length + * @opt_tlvs: optional fields in TLV format */ struct brcmf_wsec_pmk_le { __le16 key_len; __le16 flags; u8 key[BRCMF_WSEC_MAX_SAE_PASSWORD_LEN]; + __le16 opt_len; + u8 opt_tlvs[]; }; /** @@ -611,13 +824,17 @@ struct brcmf_channel_info_le { __le32 scan_channel; }; +#define BRCMF_MAX_ASSOC_OUI_NUM 6 +#define BRCMF_ASSOC_OUI_LEN 3 struct brcmf_sta_info_le { __le16 ver; /* version of this struct */ __le16 len; /* length in bytes of this structure */ __le16 cap; /* sta's advertised capabilities */ + u16 PAD; __le32 flags; /* flags defined below */ __le32 idle; /* time since data pkt rx'd from sta */ u8 ea[ETH_ALEN]; /* Station address */ + u16 PAD2; __le32 count; /* # rates in this set */ u8 rates[BRCMF_MAXRATES_IN_SET]; /* rates in 500kbps units */ /* w/hi bit set if basic */ @@ -649,6 +866,7 @@ struct brcmf_sta_info_le { __le16 aid; /* association ID */ __le16 ht_capabilities; /* advertised ht caps */ __le16 vht_flags; /* converted vht flags */ + u16 PAD3; __le32 tx_pkts_retry_cnt; /* # of frames where a retry was * exhausted. */ @@ -701,6 +919,13 @@ struct brcmf_sta_info_le { __le32 tx_rspec; /* Rate of last successful tx frame */ __le32 rx_rspec; /* Rate of last successful rx frame */ __le32 wnm_cap; /* wnm capabilities */ + __le16 he_flags; /* converted he flags */ + u16 PAD; + struct { + u8 count; + u8 oui[BRCMF_MAX_ASSOC_OUI_NUM][BRCMF_ASSOC_OUI_LEN]; + } vendor_oui; + u8 link_bw; } v7; }; }; @@ -833,6 +1058,30 @@ struct brcmf_wlc_version_le { __le16 wlc_ver_minor; }; +/** + * struct brcmf_join_version_le - join interface version + */ +struct brcmf_join_version_le { + __le16 version; /**< version of the structure */ + __le16 length; /**< length of the entire structure */ + + /* join interface version numbers */ + __le16 join_ver_major; /**< join interface major version number */ + u8 pad[2]; +}; +#define BRCMF_JOIN_VERSION_VERSION 1 + +/** + * struct brcmf_scan_version_le - scan interface version + */ +struct brcmf_scan_version_le { + __le16 version; + __le16 length; + __le16 scan_ver_major; +}; + +#define BRCMF_SCAN_VERSION_VERSION 1 + /** * struct brcmf_assoclist_le - request assoc list. * @@ -1009,6 +1258,46 @@ struct brcmf_pno_param_le { __le32 slow_freq; }; +/** + * struct brcmf_pno_param_le - PNO scan configuration parameters + * + * @version: PNO parameters version. + * @length: Length of PNO structure + * @scan_freq: scan frequency. + * @lost_network_timeout: #sec. to declare discovered network as lost. + * @flags: Bit field to control features of PFN such as sort criteria auto + * enable switch and background scan. + * @rssi_margin: Margin to avoid jitter for choosing a PFN based on RSSI sort + * criteria. + * @bestn: number of best networks in each scan. + * @mscan: number of scans recorded. + * @repeat: minimum number of scan intervals before scan frequency changes + * in adaptive scan. + * @exp: exponent of 2 for maximum scan interval. + * @slow_freq: slow scan period. + * @min_bound: min bound for scan time randomization + * @max_bound: max bound for scan time randomization + * @pfn_lp_scan_disable: unused + * @pfn_lp_scan_cnt: allow interleaving lp scan with hp scan + */ +struct brcmf_pno_param_v3_le { + __le16 version; + __le16 length; + __le32 scan_freq; + __le32 lost_network_timeout; + __le16 flags; + __le16 rssi_margin; + u8 bestn; + u8 mscan; + u8 repeat; + u8 exp; + __le32 slow_freq; + u8 min_bound; + u8 max_bound; + u8 pfn_lp_scan_disable; + u8 pfn_lp_scan_cnt; +}; + /** * struct brcmf_pno_config_le - PNO channel configuration. * @@ -1062,6 +1351,28 @@ struct brcmf_pno_net_info_le { __le16 timestamp; }; +/** + * struct brcmf_pno_net_info_v3_le - information per found network. + * + * @bssid: BSS network identifier. + * @chanspec: channel spec. + * @SSID_len: length of ssid. + * @SSID: ssid characters. + * @flags: flags + * @RSSI: receive signal strength (in dBm). + * @timestamp: age in seconds. + */ +struct brcmf_pno_net_info_v3_le { + u8 bssid[6]; + u16 chanspec; + u8 SSID_len; + u8 padding; + u16 flags; + u8 SSID[32]; + __le16 RSSI; + __le16 timestamp; +}; + /** * struct brcmf_pno_scanresults_le - result returned in PNO NET FOUND event. * @@ -1082,6 +1393,14 @@ struct brcmf_pno_scanresults_v2_le { __le32 scan_ch_bucket; }; +/* V2 and V3 structs are the same */ +struct brcmf_pno_scanresults_v3_le { + __le32 version; + __le32 status; + __le32 count; + __le32 scan_ch_bucket; +}; + /** * struct brcmf_pno_macaddr_le - to configure PNO macaddr randomization. * @@ -1236,4 +1555,141 @@ struct brcmf_mkeep_alive_pkt_le { u8 data[]; } __packed; +enum event_msgs_ext_command { + EVENTMSGS_NONE = 0, + EVENTMSGS_SET_BIT = 1, + EVENTMSGS_RESET_BIT = 2, + EVENTMSGS_SET_MASK = 3 +}; + +#define EVENTMSGS_VER 1 + +/** + * struct brcmf_eventmsgs_ext_le - new event message mask commands + * + * @version: EVENTMSGS_VER + * @command: one of enum event_msgs_ext_command + * @len: for set, the mask size from the application to the firmware. + * for get, the actual firmware mask size. + * @maxgetsize: for get, the max size that the application can read from + * the firmware. + */ +struct brcmf_eventmsgs_ext_le { + u8 version; + u8 command; + u8 len; + u8 maxgetsize; + u8 mask[]; +}; + +/* version of the brcmf_wl_wsec_info structure */ +#define BRCMF_WSEC_INFO_VER 1 + +/* tlv used to return wl_wsec_info properties */ +struct brcmf_wsec_info_tlv { + u16 type; + u16 len; /* data length */ + u8 data[1]; /* data follows */ +}; + +/* input/output data type for wsec_info iovar */ +struct brcmf_wsec_info { + u8 version; /* structure version */ + u8 pad[2]; + u8 num_tlvs; + struct brcmf_wsec_info_tlv tlvs[1]; /* tlv data follows */ +}; + +/* HE top level command IDs */ +enum { + BRCMF_HE_CMD_ENABLE = 0, + BRCMF_HE_CMD_FEATURES = 1, + BRCMF_HE_CMD_SR = 2, + BRCMF_HE_CMD_TESTBED = 3, + BRCMF_HE_CMD_BSR_SUPPORT = 4, + BRCMF_HE_CMD_BSSCOLOR = 5, + BRCMF_HE_CMD_PARTIAL_BSSCOLOR = 6, + BRCMF_HE_CMD_CAP = 7, + BRCMF_HE_CMD_OMI = 8, + BRCMF_HE_CMD_RANGE_EXT = 9, + BRCMF_HE_CMD_RTSDURTHRESH = 10, + BRCMF_HE_CMD_PEDURATION = 11, + BRCMF_HE_CMD_MUEDCA = 12, + BRCMF_HE_CMD_DYNFRAG = 13, + BRCMF_HE_CMD_PPET = 14, + BRCMF_HE_CMD_HTC = 15, + BRCMF_HE_CMD_AXMODE = 16, + BRCMF_HE_CMD_FRAGTX = 17, + BRCMF_HE_CMD_DEFCAP = 18, +}; + +#define BRCMF_HE_VER_1 1 + +struct brcmf_he_bsscolor { + u8 color; /* 1..63, on get returns currently in use color */ + u8 disabled; /* 0/1, 0 means disabled is false, so coloring is enabled */ + u8 switch_count; /* 0, immediate programming, 1 .. 255 beacon count down */ + u8 PAD; +}; + +struct brcmf_he_omi { + u8 peer[ETH_ALEN]; /* leave it all 0s' for non-AP */ + u8 rx_nss; /* 0..7 */ + u8 channel_width; /* 0:20, 1:40, 2:80, 3:160 */ + u8 ul_mu_disable; /* 0|1 */ + u8 tx_nsts; /* 0..7 */ + u8 er_su_disable; /* 0|1 */ + u8 dl_mumimo_resound; /* 0|1 */ + u8 ul_mu_data_disable; /* 0|1 */ + u8 tx_override; /* 0, only used for testbed AP */ + u8 PAD[2]; +}; + +struct brcmf_he_edca_v1 { + u8 aci_aifsn; + u8 ecw_min_max; + u8 muedca_timer; + u8 PAD; +}; + +#define BRCMF_AC_COUNT 4 +struct brcmf_he_muedca_v1 { + /* structure control */ + __le16 version; /* structure version */ + __le16 length; /* data length (starting after this field) */ + struct brcmf_he_edca_v1 ac_param_ap[BRCMF_AC_COUNT]; + struct brcmf_he_edca_v1 ac_param_sta[BRCMF_AC_COUNT]; +}; + +#define BRCMF_HE_SR_VER_1 1 + +#define SRC_PSR_DIS 0x01 +#define SRC_NON_SRG_OBSS_PD_SR_DIS 0x02 +#define SRC_NON_SRG_OFFSET_PRESENT 0x04 +#define SRC_SRG_INFORMATION_PRESENT 0x08 +#define SRC_HESIGA_SPATIAL_REUSE_VALUE15_ALLOWED 0x10 + +#define HE_SR_SRG_INFO_LEN 18 + +struct brcmf_he_sr_v1 { + /* structure control */ + __le16 version; /* structure version */ + __le16 length; /* data length (starting after this field) */ + u8 enabled; + u8 src; /* SR control, see above defines. */ + u8 non_srg_offset; /* Non-SRG Offset */ + u8 srg[HE_SR_SRG_INFO_LEN]; /* SRG Information */ +}; + +#define BRCMF_HE_DEFCAP_VER_1 1 + +struct brcmf_he_defcap { + __le16 version; /* structure version */ + __le16 length; /* data length (starting after this field) */ + u8 bsscfg_type; + u8 bsscfg_subtype; + u8 mac_cap[6]; + u8 phy_cap[11]; +}; + #endif /* FWIL_TYPES_H_ */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/interface_create.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/interface_create.c new file mode 100644 index 00000000000000..1f40ff8d632c25 --- /dev/null +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/interface_create.c @@ -0,0 +1,270 @@ +// SPDX-License-Identifier: ISC +/* + * Copyright (c) 2023 Daniel Berlin + */ + +/* This file handles firmware-side interface creation */ + +#include +#include +#include +#include +#include +#include + +#include +#include +#include "cfg80211.h" +#include "debug.h" +#include "fwil.h" +#include "proto.h" +#include "bus.h" +#include "common.h" +#include "interface_create.h" + +#define BRCMF_INTERFACE_CREATE_VER_1 1 +#define BRCMF_INTERFACE_CREATE_VER_2 2 +#define BRCMF_INTERFACE_CREATE_VER_3 3 +#define BRCMF_INTERFACE_CREATE_VER_MAX BRCMF_INTERFACE_CREATE_VER_3 + +/* These sets of flags specify whether to use various fields in the interface create structures */ + +/* This is only used with version 0 or 1 */ +#define BRCMF_INTERFACE_CREATE_STA (0 << 0) +#define BRCMF_INTERFACE_CREATE_AP (1 << 0) + +#define BRCMF_INTERFACE_MAC_DONT_USE (0 << 1) +#define BRCMF_INTERFACE_MAC_USE (1 << 1) + +#define BRCMF_INTERFACE_WLC_INDEX_DONT_USE (0 << 2) +#define BRCMF_INTERFACE_WLC_INDEX_USE (1 << 2) + +#define BRCMF_INTERFACE_IF_INDEX_DONT_USE (0 << 3) +#define BRCMF_INTERFACE_IF_INDEX_USE (1 << 3) + +#define BRCMF_INTERFACE_BSSID_DONT_USE (0 << 4) +#define BRCMF_INTERFACE_BSSID_USE (1 << 4) + +/* + * From revision >= 2 Bit 0 of flags field will not be used for STA or AP interface creation. + * "iftype" field shall be used for identifying the interface type. + */ +enum brcmf_interface_type { + BRCMF_INTERFACE_TYPE_STA = 0, + BRCMF_INTERFACE_TYPE_AP = 1, + /* The missing number here is deliberate */ + BRCMF_INTERFACE_TYPE_NAN = 3, + BRCMF_INTERFACE_TYPE_P2P_GO = 4, + BRCMF_INTERFACE_TYPE_P2P_GC = 5, + BRCMF_INTERFACE_TYPE_P2P_DISC = 6, + BRCMF_INTERFACE_TYPE_IBSS = 7, + BRCMF_INTERFACE_TYPE_MESH = 8 +}; + + +/* All sources treat these structures as being host endian. + * However, firmware treats it as little endian, so we do as well */ + +struct brcmf_interface_create_v1 { + __le16 ver; /* structure version */ + u8 pad1[2]; + __le32 flags; /* flags for operation */ + u8 mac_addr[ETH_ALEN]; /* MAC address */ + u8 pad2[2]; + __le32 wlc_index; /* optional for wlc index */ +}; + +struct brcmf_interface_create_v2 { + __le16 ver; /* structure version */ + u8 pad1[2]; + __le32 flags; /* flags for operation */ + u8 mac_addr[ETH_ALEN]; /* MAC address */ + u8 iftype; /* type of interface created */ + u8 pad2; + u32 wlc_index; /* optional for wlc index */ +}; + +struct brcmf_interface_create_v3 { + __le16 ver; /* structure version */ + __le16 len; /* length of structure + data */ + __le16 fixed_len; /* length of structure */ + u8 iftype; /* type of interface created */ + u8 wlc_index; /* optional for wlc index */ + __le32 flags; /* flags for operation */ + u8 mac_addr[ETH_ALEN]; /* MAC address */ + u8 bssid[ETH_ALEN]; /* optional for BSSID */ + u8 if_index; /* interface index request */ + u8 pad[3]; + u8 data[]; /* Optional for specific data */ +}; + +static int brcmf_get_first_free_bsscfgidx(struct brcmf_pub *drvr) +{ + int bsscfgidx; + + for (bsscfgidx = 0; bsscfgidx < BRCMF_MAX_IFS; bsscfgidx++) { + /* bsscfgidx 1 is reserved for legacy P2P */ + if (bsscfgidx == 1) + continue; + if (!drvr->iflist[bsscfgidx]) + return bsscfgidx; + } + + return -ENOMEM; +} + +static void brcmf_set_vif_sta_macaddr(struct brcmf_if *ifp, u8 *mac_addr) +{ + u8 mac_idx = ifp->drvr->sta_mac_idx; + + /* set difference MAC address with locally administered bit */ + memcpy(mac_addr, ifp->mac_addr, ETH_ALEN); + mac_addr[0] |= 0x02; + mac_addr[3] ^= mac_idx ? 0xC0 : 0xA0; + mac_idx++; + mac_idx = mac_idx % 2; + ifp->drvr->sta_mac_idx = mac_idx; +} + +static int brcmf_cfg80211_request_if_internal(struct brcmf_if *ifp, u32 version, + enum brcmf_interface_type if_type, + u8 *macaddr) +{ + switch (version) { + case BRCMF_INTERFACE_CREATE_VER_1: { + struct brcmf_interface_create_v1 iface_v1 = {}; + u32 flags = if_type; + + iface_v1.ver = cpu_to_le16(BRCMF_INTERFACE_CREATE_VER_1); + if (macaddr) { + flags |= BRCMF_INTERFACE_MAC_USE; + if (!is_zero_ether_addr(macaddr)) + memcpy(iface_v1.mac_addr, macaddr, ETH_ALEN); + else + brcmf_set_vif_sta_macaddr(ifp, + iface_v1.mac_addr); + } + iface_v1.flags = cpu_to_le32(flags); + return brcmf_fil_iovar_data_get(ifp, "interface_create", + &iface_v1, sizeof(iface_v1)); + } + case BRCMF_INTERFACE_CREATE_VER_2: { + struct brcmf_interface_create_v2 iface_v2 = {}; + u32 flags = 0; + + iface_v2.ver = cpu_to_le16(BRCMF_INTERFACE_CREATE_VER_2); + iface_v2.iftype = if_type; + if (macaddr) { + flags = BRCMF_INTERFACE_MAC_USE; + if (!is_zero_ether_addr(macaddr)) + memcpy(iface_v2.mac_addr, macaddr, ETH_ALEN); + else + brcmf_set_vif_sta_macaddr(ifp, + iface_v2.mac_addr); + } + iface_v2.flags = cpu_to_le32(flags); + return brcmf_fil_iovar_data_get(ifp, "interface_create", + &iface_v2, sizeof(iface_v2)); + } + case BRCMF_INTERFACE_CREATE_VER_3: { + struct brcmf_interface_create_v3 iface_v3 = {}; + u32 flags = 0; + + iface_v3.ver = cpu_to_le16(BRCMF_INTERFACE_CREATE_VER_3); + iface_v3.iftype = if_type; + iface_v3.len = cpu_to_le16(sizeof(iface_v3)); + iface_v3.fixed_len = cpu_to_le16(sizeof(iface_v3)); + if (macaddr) { + flags = BRCMF_INTERFACE_MAC_USE; + if (!is_zero_ether_addr(macaddr)) + memcpy(iface_v3.mac_addr, macaddr, ETH_ALEN); + else + brcmf_set_vif_sta_macaddr(ifp, + iface_v3.mac_addr); + } + iface_v3.flags = cpu_to_le32(flags); + return brcmf_fil_iovar_data_get(ifp, "interface_create", + &iface_v3, sizeof(iface_v3)); + } + default: + bphy_err(ifp->drvr, "Unknown interface create version:%d\n", + version); + return -EINVAL; + } +} +static int brcmf_cfg80211_request_if(struct brcmf_if *ifp, + enum brcmf_interface_type if_type, + u8 *macaddr) +{ + s32 err; + u32 iface_create_ver; + + /* Query the creation version, see if the firmware knows */ + iface_create_ver = 0; + err = brcmf_fil_bsscfg_int_query(ifp, "interface_create", + &iface_create_ver); + if (!err) { + err = brcmf_cfg80211_request_if_internal(ifp, iface_create_ver, + if_type, macaddr); + if (!err) { + brcmf_info("interface created (version %d)\n", + iface_create_ver); + } else { + bphy_err(ifp->drvr, + "failed to create interface (version %d):%d\n", + iface_create_ver, err); + } + return err; + } + /* Either version one or version two */ + err = brcmf_cfg80211_request_if_internal( + ifp, if_type, BRCMF_INTERFACE_CREATE_VER_2, macaddr); + if (!err) { + brcmf_info("interface created (version 2)\n"); + return 0; + } + err = brcmf_cfg80211_request_if_internal( + ifp, if_type, BRCMF_INTERFACE_CREATE_VER_1, macaddr); + if (!err) { + brcmf_info("interface created (version 1)\n"); + return 0; + } + bphy_err(ifp->drvr, + "interface creation failed, tried query, v2, v1: %d\n", err); + return -EINVAL; +} + +int brcmf_cfg80211_request_sta_if(struct brcmf_if *ifp, u8 *macaddr) +{ + return brcmf_cfg80211_request_if(ifp, BRCMF_INTERFACE_TYPE_STA, + macaddr); +} + +int brcmf_cfg80211_request_ap_if(struct brcmf_if *ifp) +{ + int err; + + err = brcmf_cfg80211_request_if(ifp, BRCMF_INTERFACE_TYPE_AP, NULL); + if (err) { + struct brcmf_mbss_ssid_le mbss_ssid_le; + int bsscfgidx; + + brcmf_info("Does not support interface_create (%d)\n", err); + memset(&mbss_ssid_le, 0, sizeof(mbss_ssid_le)); + bsscfgidx = brcmf_get_first_free_bsscfgidx(ifp->drvr); + if (bsscfgidx < 0) + return bsscfgidx; + + mbss_ssid_le.bsscfgidx = cpu_to_le32(bsscfgidx); + mbss_ssid_le.SSID_len = cpu_to_le32(5); + sprintf(mbss_ssid_le.SSID, "ssid%d", bsscfgidx); + + err = brcmf_fil_bsscfg_data_set(ifp, "bsscfg:ssid", + &mbss_ssid_le, + sizeof(mbss_ssid_le)); + + if (err < 0) + bphy_err(ifp->drvr, "setting ssid failed %d\n", err); + } + return err; +} diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/interface_create.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/interface_create.h new file mode 100644 index 00000000000000..669fa1508b67f6 --- /dev/null +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/interface_create.h @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: ISC +/* + * Copyright (c) 2023 Daniel Berlin + */ + +#ifndef _BRCMF_INTERFACE_CREATE_H_ +#define _BRCMF_INTERFACE_CREATE_H_ +#include "core.h" + +int brcmf_cfg80211_request_sta_if(struct brcmf_if *ifp, u8 *macaddr); +int brcmf_cfg80211_request_ap_if(struct brcmf_if *ifp); + +#endif /* _BRCMF_INTERFACE_CREATE_H_ */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/join_param.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/join_param.c new file mode 100644 index 00000000000000..4f026571c7e7eb --- /dev/null +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/join_param.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: ISC +/* + * Copyright (c) 2023 Daniel Berlin + */ +#include +#include + +#include "core.h" +#include "debug.h" +#include "fwil_types.h" +#include "cfg80211.h" +#include "join_param.h" + +/* These defaults are the same as found in the DHD drivers, and represent + * reasonable defaults for various scan dwell and probe times. */ +#define BRCMF_SCAN_JOIN_ACTIVE_DWELL_TIME_MS 320 +#define BRCMF_SCAN_JOIN_PASSIVE_DWELL_TIME_MS 400 +#define BRCMF_SCAN_JOIN_PROBE_INTERVAL_MS 20 + +/* Most of the actual structure fields we fill in are the same for various versions + * However, due to various incompatible changes and variants, the fields are not always + * in the same place. + * This makes for code duplication, so we try to commonize setting fields where it makes sense. + */ + +static void brcmf_joinscan_set_ssid(struct brcmf_ssid_le *ssid_le, + const u8 *ssid, u32 ssid_len) +{ + ssid_len = min_t(u32, ssid_len, IEEE80211_MAX_SSID_LEN); + ssid_le->SSID_len = cpu_to_le32(ssid_len); + memcpy(ssid_le->SSID, ssid, ssid_len); +} + +static void brcmf_joinscan_set_bssid(u8 out_bssid[6], const u8 *in_bssid) +{ + if (in_bssid) { + memcpy(out_bssid, in_bssid, ETH_ALEN); + } else { + eth_broadcast_addr(out_bssid); + } +} + +/* Create a single channel chanspec list from a wireless stack channel */ +static void brcmf_joinscan_set_single_chanspec_from_channel( + struct brcmf_cfg80211_info *cfg, struct ieee80211_channel *chan, + __le32 *chanspec_count, __le16 (*chanspec_list)[]) +{ + u16 chanspec = channel_to_chanspec(&cfg->d11inf, chan); + *chanspec_count = cpu_to_le32(1); + (*chanspec_list)[0] = cpu_to_le16(chanspec); +} + +/* Create a single channel chanspec list from a wireless stack chandef */ +static void brcmf_joinscan_set_single_chanspec_from_chandef( + struct brcmf_cfg80211_info *cfg, struct cfg80211_chan_def *chandef, + __le32 *chanspec_count, __le16 (*chanspec_list)[]) +{ + u16 chanspec = chandef_to_chanspec(&cfg->d11inf, chandef); + *chanspec_count = cpu_to_le32(1); + (*chanspec_list)[0] = cpu_to_le16(chanspec); +} + +static void *brcmf_get_struct_for_ibss_v0(struct brcmf_cfg80211_info *cfg, + u32 *struct_size, + struct cfg80211_ibss_params *params) +{ + struct brcmf_join_params *join_params; + + u32 join_params_size = struct_size(join_params, params_le.chanspec_list, + params->chandef.chan != NULL); + + *struct_size = join_params_size; + join_params = kzalloc(join_params_size, GFP_KERNEL); + if (!join_params) { + bphy_err(cfg, "Unable to allocate memory for join params\n"); + return NULL; + } + brcmf_joinscan_set_ssid(&join_params->ssid_le, params->ssid, + params->ssid_len); + brcmf_joinscan_set_bssid(join_params->params_le.bssid, params->bssid); + /* Channel */ + if (cfg->channel) { + brcmf_joinscan_set_single_chanspec_from_chandef( + cfg, ¶ms->chandef, + &join_params->params_le.chanspec_num, + &join_params->params_le.chanspec_list); + } + return join_params; +} + +static void * +brcmf_get_prepped_struct_for_ibss_v1(struct brcmf_cfg80211_info *cfg, + u32 *struct_size, + struct cfg80211_ibss_params *params) +{ + struct brcmf_join_params_v1 *join_params; + u32 join_params_size = struct_size(join_params, params_le.chanspec_list, + params->chandef.chan != NULL); + + *struct_size = join_params_size; + join_params = kzalloc(join_params_size, GFP_KERNEL); + if (!join_params) { + bphy_err(cfg, "Unable to allocate memory for join params\n"); + return NULL; + } + join_params->params_le.version = cpu_to_le16(1); + brcmf_joinscan_set_ssid(&join_params->ssid_le, params->ssid, + params->ssid_len); + brcmf_joinscan_set_bssid(join_params->params_le.bssid, params->bssid); + /* Channel */ + if (cfg->channel) { + brcmf_joinscan_set_single_chanspec_from_chandef( + cfg, ¶ms->chandef, + &join_params->params_le.chanspec_num, + &join_params->params_le.chanspec_list); + } + return join_params; +} + +static void +brcmf_joinscan_set_common_v0v1_params(struct brcmf_join_scan_params_le *scan_le, + bool have_channel) +{ + /* Set up join scan parameters */ + scan_le->scan_type = 0; + scan_le->home_time = cpu_to_le32(-1); + + if (have_channel) { + /* Increase dwell time to receive probe response or detect + * beacon from target AP at a noisy air only during connect + * command. + */ + scan_le->active_time = + cpu_to_le32(BRCMF_SCAN_JOIN_ACTIVE_DWELL_TIME_MS); + scan_le->passive_time = + cpu_to_le32(BRCMF_SCAN_JOIN_PASSIVE_DWELL_TIME_MS); + /* To sync with presence period of VSDB GO send probe request + * more frequently. Probe request will be stopped when it gets + * probe response from target AP/GO. + */ + scan_le->nprobes = + cpu_to_le32(BRCMF_SCAN_JOIN_ACTIVE_DWELL_TIME_MS / + BRCMF_SCAN_JOIN_PROBE_INTERVAL_MS); + } else { + scan_le->active_time = cpu_to_le32(-1); + scan_le->passive_time = cpu_to_le32(-1); + scan_le->nprobes = cpu_to_le32(-1); + } +} +static void * +brcmf_get_struct_for_connect_v0(struct brcmf_cfg80211_info *cfg, + u32 *struct_size, + struct cfg80211_connect_params *params) +{ + struct brcmf_ext_join_params_le *ext_v0; + u32 join_params_size = + struct_size(ext_v0, assoc_le.chanspec_list, cfg->channel != 0); + + *struct_size = join_params_size; + ext_v0 = kzalloc(join_params_size, GFP_KERNEL); + if (!ext_v0) { + bphy_err( + cfg, + "Could not allocate memory for extended join parameters\n"); + return NULL; + } + brcmf_joinscan_set_ssid(&ext_v0->ssid_le, params->ssid, + params->ssid_len); + brcmf_joinscan_set_common_v0v1_params(&ext_v0->scan_le, + cfg->channel != 0); + brcmf_joinscan_set_bssid(ext_v0->assoc_le.bssid, params->bssid); + if (cfg->channel) { + struct ieee80211_channel *chan = params->channel_hint ? + params->channel_hint : + params->channel; + brcmf_joinscan_set_single_chanspec_from_channel( + cfg, chan, &ext_v0->assoc_le.chanspec_num, + &ext_v0->assoc_le.chanspec_list); + } + return ext_v0; +} + +static void * +brcmf_get_struct_for_connect_v1(struct brcmf_cfg80211_info *cfg, + u32 *struct_size, + struct cfg80211_connect_params *params) +{ + struct brcmf_ext_join_params_v1_le *ext_v1; + u32 join_params_size = + struct_size(ext_v1, assoc_le.chanspec_list, cfg->channel != 0); + + *struct_size = join_params_size; + ext_v1 = kzalloc(join_params_size, GFP_KERNEL); + if (!ext_v1) { + bphy_err( + cfg, + "Could not allocate memory for extended join parameters\n"); + return NULL; + } + ext_v1->version = cpu_to_le16(1); + ext_v1->assoc_le.version = cpu_to_le16(1); + brcmf_joinscan_set_ssid(&ext_v1->ssid_le, params->ssid, + params->ssid_len); + brcmf_joinscan_set_common_v0v1_params(&ext_v1->scan_le, + cfg->channel != 0); + brcmf_joinscan_set_bssid(ext_v1->assoc_le.bssid, params->bssid); + if (cfg->channel) { + struct ieee80211_channel *chan = params->channel_hint ? + params->channel_hint : + params->channel; + brcmf_joinscan_set_single_chanspec_from_channel( + cfg, chan, &ext_v1->assoc_le.chanspec_num, + &ext_v1->assoc_le.chanspec_list); + } + return ext_v1; +} + +static void *brcmf_get_join_from_ext_join_v0(void *ext_join, u32 *struct_size) +{ + struct brcmf_ext_join_params_le *ext_join_v0 = + (struct brcmf_ext_join_params_le *)ext_join; + u32 chanspec_num = le32_to_cpu(ext_join_v0->assoc_le.chanspec_num); + struct brcmf_join_params *join_params; + u32 join_params_size = + struct_size(join_params, params_le.chanspec_list, chanspec_num); + u32 assoc_size = struct_size_t(struct brcmf_assoc_params_le, + chanspec_list, chanspec_num); + + *struct_size = join_params_size; + join_params = kzalloc(join_params_size, GFP_KERNEL); + if (!join_params) { + return NULL; + } + memcpy(&join_params->ssid_le, &ext_join_v0->ssid_le, + sizeof(ext_join_v0->ssid_le)); + memcpy(&join_params->params_le, &ext_join_v0->assoc_le, assoc_size); + + return join_params; +} + +static void *brcmf_get_join_from_ext_join_v1(void *ext_join, u32 *struct_size) +{ + struct brcmf_ext_join_params_v1_le *ext_join_v1 = + (struct brcmf_ext_join_params_v1_le *)ext_join; + u32 chanspec_num = le32_to_cpu(ext_join_v1->assoc_le.chanspec_num); + struct brcmf_join_params_v1 *join_params; + u32 join_params_size = + struct_size(join_params, params_le.chanspec_list, chanspec_num); + u32 assoc_size = struct_size_t(struct brcmf_assoc_params_le, + chanspec_list, chanspec_num); + + *struct_size = join_params_size; + join_params = kzalloc(join_params_size, GFP_KERNEL); + if (!join_params) { + return NULL; + } + memcpy(&join_params->ssid_le, &ext_join_v1->ssid_le, + sizeof(ext_join_v1->ssid_le)); + memcpy(&join_params->params_le, &ext_join_v1->assoc_le, assoc_size); + + return join_params; +} + +int brcmf_join_param_setup_for_version(struct brcmf_pub *drvr, u8 version) +{ + drvr->join_param_handler.version = version; + switch (version) { + case 0: + drvr->join_param_handler.get_struct_for_ibss = + brcmf_get_struct_for_ibss_v0; + drvr->join_param_handler.get_struct_for_connect = + brcmf_get_struct_for_connect_v0; + drvr->join_param_handler.get_join_from_ext_join = + brcmf_get_join_from_ext_join_v0; + break; + case 1: + drvr->join_param_handler.get_struct_for_ibss = + brcmf_get_prepped_struct_for_ibss_v1; + drvr->join_param_handler.get_struct_for_connect = + brcmf_get_struct_for_connect_v1; + drvr->join_param_handler.get_join_from_ext_join = + brcmf_get_join_from_ext_join_v1; + break; + default: + return -EINVAL; + } + return 0; +} diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/join_param.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/join_param.h new file mode 100644 index 00000000000000..f549fe2a740823 --- /dev/null +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/join_param.h @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: ISC +/* + * Copyright (c) 2023 Daniel Berlin + */ + +#ifndef _BRCMF_JOIN_PARAM_H +#define _BRCMF_JOIN_PARAM_H + +struct brcmf_pub; + +/** + * brcmf_join_param_setup_for_version() - Setup the driver to handle join structures + * + * There are a number of different structures and interface versions for join/extended join parameters + * This sets up the driver to handle a particular interface version. + * + * @drvr Driver structure to setup + * @ver Interface version + * Return: %0 if okay, error code otherwise + */ +int brcmf_join_param_setup_for_version(struct brcmf_pub *drvr, u8 ver); +#endif /* _BRCMF_JOIN_PARAM_H */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c index 45fbcbdc7d9e4b..0e41d618486d39 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c @@ -47,9 +47,35 @@ #define MSGBUF_TYPE_RX_CMPLT 0x12 #define MSGBUF_TYPE_LPBK_DMAXFER 0x13 #define MSGBUF_TYPE_LPBK_DMAXFER_CMPLT 0x14 +#define MSGBUF_TYPE_FLOW_RING_RESUME 0x15 +#define MSGBUF_TYPE_FLOW_RING_RESUME_CMPLT 0x16 +#define MSGBUF_TYPE_FLOW_RING_SUSPEND 0x17 +#define MSGBUF_TYPE_FLOW_RING_SUSPEND_CMPLT 0x18 +#define MSGBUF_TYPE_INFO_BUF_POST 0x19 +#define MSGBUF_TYPE_INFO_BUF_CMPLT 0x1A +#define MSGBUF_TYPE_H2D_RING_CREATE 0x1B +#define MSGBUF_TYPE_D2H_RING_CREATE 0x1C +#define MSGBUF_TYPE_H2D_RING_CREATE_CMPLT 0x1D +#define MSGBUF_TYPE_D2H_RING_CREATE_CMPLT 0x1E +#define MSGBUF_TYPE_H2D_RING_CONFIG 0x1F +#define MSGBUF_TYPE_D2H_RING_CONFIG 0x20 +#define MSGBUF_TYPE_H2D_RING_CONFIG_CMPLT 0x21 +#define MSGBUF_TYPE_D2H_RING_CONFIG_CMPLT 0x22 +#define MSGBUF_TYPE_H2D_MAILBOX_DATA 0x23 +#define MSGBUF_TYPE_D2H_MAILBOX_DATA 0x24 +#define MSGBUF_TYPE_TIMSTAMP_BUFPOST 0x25 +#define MSGBUF_TYPE_HOSTTIMSTAMP 0x26 +#define MSGBUF_TYPE_HOSTTIMSTAMP_CMPLT 0x27 +#define MSGBUF_TYPE_FIRMWARE_TIMESTAMP 0x28 +#define MSGBUF_TYPE_SNAPSHOT_UPLOAD 0x29 +#define MSGBUF_TYPE_SNAPSHOT_CMPLT 0x2A +#define MSGBUF_TYPE_H2D_RING_DELETE 0x2B +#define MSGBUF_TYPE_D2H_RING_DELETE 0x2C +#define MSGBUF_TYPE_H2D_RING_DELETE_CMPLT 0x2D +#define MSGBUF_TYPE_D2H_RING_DELETE_CMPLT 0x2E #define NR_TX_PKTIDS 2048 -#define NR_RX_PKTIDS 1024 +#define NR_RX_PKTIDS 2048 #define BRCMF_IOCTL_REQ_PKTID 0xFFFE @@ -218,6 +244,19 @@ struct msgbuf_flowring_flush_resp { __le32 rsvd0[3]; }; +struct msgbuf_h2d_mailbox_data { + struct msgbuf_common_hdr msg; + __le32 data; + __le32 rsvd0[7]; +}; + +struct msgbuf_d2h_mailbox_data { + struct msgbuf_common_hdr msg; + struct msgbuf_completion_hdr compl_hdr; + __le32 data; + __le32 rsvd0[2]; +}; + struct brcmf_msgbuf_work_item { struct list_head queue; u32 flowid; @@ -1285,6 +1324,16 @@ brcmf_msgbuf_process_flow_ring_delete_response(struct brcmf_msgbuf *msgbuf, } +static void brcmf_msgbuf_process_d2h_mailbox_data(struct brcmf_msgbuf *msgbuf, + void *buf) +{ + struct msgbuf_d2h_mailbox_data *d2h_mb_data = buf; + struct brcmf_pub *drvr = msgbuf->drvr; + + brcmf_bus_d2h_mb_rx(drvr->bus_if, le32_to_cpu(d2h_mb_data->data)); +} + + static void brcmf_msgbuf_process_msgtype(struct brcmf_msgbuf *msgbuf, void *buf) { struct brcmf_pub *drvr = msgbuf->drvr; @@ -1327,6 +1376,10 @@ static void brcmf_msgbuf_process_msgtype(struct brcmf_msgbuf *msgbuf, void *buf) brcmf_dbg(MSGBUF, "MSGBUF_TYPE_RX_CMPLT\n"); brcmf_msgbuf_process_rx_complete(msgbuf, buf); break; + case MSGBUF_TYPE_D2H_MAILBOX_DATA: + brcmf_dbg(MSGBUF, "MSGBUF_TYPE_D2H_MAILBOX_DATA\n"); + brcmf_msgbuf_process_d2h_mailbox_data(msgbuf, buf); + break; default: bphy_err(drvr, "Unsupported msgtype %d\n", msg->msgtype); break; @@ -1465,6 +1518,38 @@ void brcmf_msgbuf_delete_flowring(struct brcmf_pub *drvr, u16 flowid) } } + +int brcmf_msgbuf_h2d_mb_write(struct brcmf_pub *drvr, u32 data) +{ + struct brcmf_msgbuf *msgbuf = (struct brcmf_msgbuf *)drvr->proto->pd; + struct brcmf_commonring *commonring; + struct msgbuf_h2d_mailbox_data *request; + void *ret_ptr; + int err; + + commonring = msgbuf->commonrings[BRCMF_H2D_MSGRING_CONTROL_SUBMIT]; + brcmf_commonring_lock(commonring); + ret_ptr = brcmf_commonring_reserve_for_write(commonring); + if (!ret_ptr) { + bphy_err(drvr, "Failed to reserve space in commonring\n"); + brcmf_commonring_unlock(commonring); + return -ENOMEM; + } + + request = (struct msgbuf_h2d_mailbox_data *)ret_ptr; + request->msg.msgtype = MSGBUF_TYPE_H2D_MAILBOX_DATA; + request->msg.ifidx = -1; + request->msg.flags = 0; + request->msg.request_id = 0; + request->data = data; + + err = brcmf_commonring_write_complete(commonring); + brcmf_commonring_unlock(commonring); + + return err; +} + + #ifdef DEBUG static int brcmf_msgbuf_stats_read(struct seq_file *seq, void *data) { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.h index 6a849f4a94dd7f..0ed48cf13d93cf 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.h @@ -8,10 +8,10 @@ #ifdef CONFIG_BRCMFMAC_PROTO_MSGBUF #define BRCMF_H2D_MSGRING_CONTROL_SUBMIT_MAX_ITEM 64 -#define BRCMF_H2D_MSGRING_RXPOST_SUBMIT_MAX_ITEM 1024 +#define BRCMF_H2D_MSGRING_RXPOST_SUBMIT_MAX_ITEM 2048 #define BRCMF_D2H_MSGRING_CONTROL_COMPLETE_MAX_ITEM 64 #define BRCMF_D2H_MSGRING_TX_COMPLETE_MAX_ITEM 1024 -#define BRCMF_D2H_MSGRING_RX_COMPLETE_MAX_ITEM 1024 +#define BRCMF_D2H_MSGRING_RX_COMPLETE_MAX_ITEM 2048 #define BRCMF_H2D_TXFLOWRING_MAX_ITEM 512 #define BRCMF_H2D_MSGRING_CONTROL_SUBMIT_ITEMSIZE 40 @@ -32,6 +32,7 @@ int brcmf_proto_msgbuf_rx_trigger(struct device *dev); void brcmf_msgbuf_delete_flowring(struct brcmf_pub *drvr, u16 flowid); int brcmf_proto_msgbuf_attach(struct brcmf_pub *drvr); void brcmf_proto_msgbuf_detach(struct brcmf_pub *drvr); +int brcmf_msgbuf_h2d_mb_write(struct brcmf_pub *drvr, u32 data); #else static inline int brcmf_proto_msgbuf_attach(struct brcmf_pub *drvr) { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c index e1752a513c733d..06d2933162b26f 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c @@ -1784,8 +1784,8 @@ bool brcmf_p2p_send_action_frame(struct brcmf_if *ifp, /* do not configure anything. it will be */ /* sent with a default configuration */ } else { - bphy_err(drvr, "Unknown Frame: category 0x%x, action 0x%x\n", - category, action); + bphy_info_once(drvr, "Unknown Frame: category 0x%x, action 0x%x\n", + category, action); return false; } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 6327f4eca50078..9f11d555ade453 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -71,6 +71,8 @@ BRCMF_FW_CLM_DEF(4377B3, "brcmfmac4377b3-pcie"); BRCMF_FW_CLM_DEF(4378B1, "brcmfmac4378b1-pcie"); BRCMF_FW_CLM_DEF(4378B3, "brcmfmac4378b3-pcie"); BRCMF_FW_CLM_DEF(4387C2, "brcmfmac4387c2-pcie"); +BRCMF_FW_CLM_DEF(4388B0, "brcmfmac4388b0-pcie"); +BRCMF_FW_CLM_DEF(4388C0, "brcmfmac4388c0-pcie"); BRCMF_FW_CLM_DEF(54591, "brcmfmac54591-pcie"); /* firmware config files */ @@ -112,6 +114,8 @@ static const struct brcmf_firmware_mapping brcmf_pcie_fwnames[] = { BRCMF_FW_ENTRY(BRCM_CC_4378_CHIP_ID, 0x0000000F, 4378B1), /* revision ID 3 */ BRCMF_FW_ENTRY(BRCM_CC_4378_CHIP_ID, 0xFFFFFFE0, 4378B3), /* revision ID 5 */ BRCMF_FW_ENTRY(BRCM_CC_4387_CHIP_ID, 0xFFFFFFFF, 4387C2), /* revision ID 7 */ + BRCMF_FW_ENTRY(BRCM_CC_4388_CHIP_ID, 0x0000000F, 4388B0), + BRCMF_FW_ENTRY(BRCM_CC_4388_CHIP_ID, 0xFFFFFFF0, 4388C0), /* revision ID 4 */ }; #define BRCMF_PCIE_FW_UP_TIMEOUT 5000 /* msec */ @@ -219,11 +223,64 @@ static const struct brcmf_firmware_mapping brcmf_pcie_fwnames[] = { #define BRCMF_PCIE_SHARED_VERSION_MASK 0x00FF #define BRCMF_PCIE_SHARED_DMA_INDEX 0x10000 #define BRCMF_PCIE_SHARED_DMA_2B_IDX 0x100000 +#define BRCMF_PCIE_SHARED_USE_MAILBOX 0x2000000 +#define BRCMF_PCIE_SHARED_TIMESTAMP_DB0 0x8000000 #define BRCMF_PCIE_SHARED_HOSTRDY_DB1 0x10000000 +#define BRCMF_PCIE_SHARED_NO_OOB_DW 0x20000000 +#define BRCMF_PCIE_SHARED_INBAND_DS 0x40000000 +#define BRCMF_PCIE_SHARED_DAR 0x80000000 + +#define BRCMF_PCIE_SHARED2_EXTENDED_TRAP_DATA 0x1 +#define BRCMF_PCIE_SHARED2_TXSTATUS_METADATA 0x2 +#define BRCMF_PCIE_SHARED2_BT_LOGGING 0x4 +#define BRCMF_PCIE_SHARED2_SNAPSHOT_UPLOAD 0x8 +#define BRCMF_PCIE_SHARED2_SUBMIT_COUNT_WAR 0x10 +#define BRCMF_PCIE_SHARED2_FAST_DELETE_RING 0x20 +#define BRCMF_PCIE_SHARED2_EVTBUF_MAX_MASK 0xC0 +#define BRCMF_PCIE_SHARED2_PKT_TX_STATUS 0x100 +#define BRCMF_PCIE_SHARED2_FW_SMALL_MEMDUMP 0x200 +#define BRCMF_PCIE_SHARED2_FW_HC_ON_TRAP 0x400 +#define BRCMF_PCIE_SHARED2_HSCB 0x800 +#define BRCMF_PCIE_SHARED2_EDL_RING 0x1000 +#define BRCMF_PCIE_SHARED2_DEBUG_BUF_DEST 0x2000 +#define BRCMF_PCIE_SHARED2_PCIE_ENUM_RESET_FLR 0x4000 +#define BRCMF_PCIE_SHARED2_PKT_TIMESTAMP 0x8000 +#define BRCMF_PCIE_SHARED2_HP2P 0x10000 +#define BRCMF_PCIE_SHARED2_HWA 0x20000 +#define BRCMF_PCIE_SHARED2_TRAP_ON_HOST_DB7 0x40000 +#define BRCMF_PCIE_SHARED2_DURATION_SCALE 0x100000 +#define BRCMF_PCIE_SHARED2_D2H_D11_TX_STATUS 0x40000000 +#define BRCMF_PCIE_SHARED2_H2D_D11_TX_STATUS 0x80000000 #define BRCMF_PCIE_FLAGS_HTOD_SPLIT 0x4000 #define BRCMF_PCIE_FLAGS_DTOH_SPLIT 0x8000 +#define BRCMF_HOSTCAP_PCIEAPI_VERSION_MASK 0x000000FF +#define BRCMF_HOSTCAP_H2D_VALID_PHASE 0x00000100 +#define BRCMF_HOSTCAP_H2D_ENABLE_TRAP_ON_BADPHASE 0x00000200 +#define BRCMF_HOSTCAP_H2D_ENABLE_HOSTRDY 0x400 +#define BRCMF_HOSTCAP_DB0_TIMESTAMP 0x800 +#define BRCMF_HOSTCAP_DS_NO_OOB_DW 0x1000 +#define BRCMF_HOSTCAP_DS_INBAND_DW 0x2000 +#define BRCMF_HOSTCAP_H2D_IDMA 0x4000 +#define BRCMF_HOSTCAP_H2D_IFRM 0x8000 +#define BRCMF_HOSTCAP_H2D_DAR 0x10000 +#define BRCMF_HOSTCAP_EXTENDED_TRAP_DATA 0x20000 +#define BRCMF_HOSTCAP_TXSTATUS_METADATA 0x40000 +#define BRCMF_HOSTCAP_BT_LOGGING 0x80000 +#define BRCMF_HOSTCAP_SNAPSHOT_UPLOAD 0x100000 +#define BRCMF_HOSTCAP_FAST_DELETE_RING 0x200000 +#define BRCMF_HOSTCAP_PKT_TXSTATUS 0x400000 +#define BRCMF_HOSTCAP_UR_FW_NO_TRAP 0x800000 +#define BRCMF_HOSTCAP_HSCB 0x2000000 +#define BRCMF_HOSTCAP_EXT_TRAP_DBGBUF 0x4000000 +#define BRCMF_HOSTCAP_EDL_RING 0x10000000 +#define BRCMF_HOSTCAP_PKT_TIMESTAMP 0x20000000 +#define BRCMF_HOSTCAP_PKT_HP2P 0x40000000 +#define BRCMF_HOSTCAP_HWA 0x80000000 +#define BRCMF_HOSTCAP2_DURATION_SCALE_MASK 0x3F + +#define BRCMF_SHARED_FLAGS_OFFSET 0 #define BRCMF_SHARED_MAX_RXBUFPOST_OFFSET 34 #define BRCMF_SHARED_RING_BASE_OFFSET 52 #define BRCMF_SHARED_RX_DATAOFFSET_OFFSET 36 @@ -235,6 +292,11 @@ static const struct brcmf_firmware_mapping brcmf_pcie_fwnames[] = { #define BRCMF_SHARED_DMA_SCRATCH_ADDR_OFFSET 56 #define BRCMF_SHARED_DMA_RINGUPD_LEN_OFFSET 64 #define BRCMF_SHARED_DMA_RINGUPD_ADDR_OFFSET 68 +#define BRCMF_SHARED_FLAGS2_OFFSET 80 +#define BRCMF_SHARED_HOST_CAP_OFFSET 84 +#define BRCMF_SHARED_FLAGS3_OFFSET 108 +#define BRCMF_SHARED_HOST_CAP2_OFFSET 112 +#define BRCMF_SHARED_HOST_CAP3_OFFSET 116 #define BRCMF_RING_H2D_RING_COUNT_OFFSET 0 #define BRCMF_RING_D2H_RING_COUNT_OFFSET 1 @@ -280,6 +342,7 @@ static const struct brcmf_firmware_mapping brcmf_pcie_fwnames[] = { #define BRCMF_PCIE_CFGREG_PML1_SUB_CTRL1 0x248 #define BRCMF_PCIE_CFGREG_REG_BAR2_CONFIG 0x4E0 #define BRCMF_PCIE_CFGREG_REG_BAR3_CONFIG 0x4F4 +#define BRCMF_PCIE_CFGREG_TLCNTRL_5 0x814 #define BRCMF_PCIE_LINK_STATUS_CTRL_ASPM_ENAB 3 /* Magic number at a magic location to find RAM size */ @@ -299,6 +362,8 @@ struct brcmf_pcie_console { struct brcmf_pcie_shared_info { u32 tcm_base_address; u32 flags; + u32 flags2; + u32 flags3; struct brcmf_pcie_ringbuf *commonrings[BRCMF_NROF_COMMON_MSGRINGS]; struct brcmf_pcie_ringbuf *flowrings; u16 max_rxbufpost; @@ -315,6 +380,7 @@ struct brcmf_pcie_shared_info { void *ringupd; dma_addr_t ringupd_dmahandle; u8 version; + bool mb_via_ctl; }; #define BRCMF_OTP_MAX_PARAM_LEN 16 @@ -331,6 +397,7 @@ struct brcmf_pciedev_info { bool in_irq; struct pci_dev *pdev; char fw_name[BRCMF_FW_NAME_LEN]; + char sig_name[BRCMF_FW_NAME_LEN]; char nvram_name[BRCMF_FW_NAME_LEN]; char clm_name[BRCMF_FW_NAME_LEN]; char txcap_name[BRCMF_FW_NAME_LEN]; @@ -339,14 +406,16 @@ struct brcmf_pciedev_info { const struct brcmf_pcie_reginfo *reginfo; void __iomem *regs; void __iomem *tcm; - u32 ram_base; - u32 ram_size; + u32 fw_size; + bool skip_reset_vector; struct brcmf_chip *ci; u32 coreid; struct brcmf_pcie_shared_info shared; wait_queue_head_t mbdata_resp_wait; bool mbdata_completed; bool irq_allocated; + bool irq_ready; + bool have_msi; bool wowl_enabled; u8 dma_idx_sz; void *idxbuf; @@ -433,8 +502,6 @@ struct brcmf_pcie_reginfo { u32 intmask; u32 mailboxint; u32 mailboxmask; - u32 h2d_mailbox_0; - u32 h2d_mailbox_1; u32 int_d2h_db; u32 int_fn0; }; @@ -443,8 +510,6 @@ static const struct brcmf_pcie_reginfo brcmf_reginfo_default = { .intmask = BRCMF_PCIE_PCIE2REG_INTMASK, .mailboxint = BRCMF_PCIE_PCIE2REG_MAILBOXINT, .mailboxmask = BRCMF_PCIE_PCIE2REG_MAILBOXMASK, - .h2d_mailbox_0 = BRCMF_PCIE_PCIE2REG_H2D_MAILBOX_0, - .h2d_mailbox_1 = BRCMF_PCIE_PCIE2REG_H2D_MAILBOX_1, .int_d2h_db = BRCMF_PCIE_MB_INT_D2H_DB, .int_fn0 = BRCMF_PCIE_MB_INT_FN0, }; @@ -453,8 +518,6 @@ static const struct brcmf_pcie_reginfo brcmf_reginfo_64 = { .intmask = BRCMF_PCIE_64_PCIE2REG_INTMASK, .mailboxint = BRCMF_PCIE_64_PCIE2REG_MAILBOXINT, .mailboxmask = BRCMF_PCIE_64_PCIE2REG_MAILBOXMASK, - .h2d_mailbox_0 = BRCMF_PCIE_64_PCIE2REG_H2D_MAILBOX_0, - .h2d_mailbox_1 = BRCMF_PCIE_64_PCIE2REG_H2D_MAILBOX_1, .int_d2h_db = BRCMF_PCIE_64_MB_INT_D2H_DB, .int_fn0 = 0, }; @@ -493,6 +556,19 @@ brcmf_pcie_write_reg32(struct brcmf_pciedev_info *devinfo, u32 reg_offset, iowrite32(value, address); } +static u32 +brcmf_pcie_read_pcie32(struct brcmf_pciedev_info *devinfo, u32 reg_offset) +{ + return brcmf_pcie_read_reg32(devinfo, 0x2000 + reg_offset); +} + + +static void +brcmf_pcie_write_pcie32(struct brcmf_pciedev_info *devinfo, u32 reg_offset, + u32 value) +{ + brcmf_pcie_write_reg32(devinfo, 0x2000 + reg_offset, value); +} static u8 brcmf_pcie_read_tcm8(struct brcmf_pciedev_info *devinfo, u32 mem_offset) @@ -686,8 +762,30 @@ static void brcmf_pcie_reset_device(struct brcmf_pciedev_info *devinfo) /* Watchdog reset */ brcmf_pcie_select_core(devinfo, BCMA_CORE_CHIPCOMMON); - WRITECC32(devinfo, watchdog, 4); - msleep(100); + core = brcmf_chip_get_chipcommon(devinfo->ci); + + if (core->rev >= 65) { + u32 mask = CC_WD_SSRESET_PCIE_F0_EN; + + core = brcmf_chip_get_core(devinfo->ci, BCMA_CORE_PCIE2); + if (core->rev < 66) + mask |= CC_WD_SSRESET_PCIE_ALL_FN_EN; + + val = READCC32(devinfo, watchdog); + val &= ~CC_WD_ENABLE_MASK; + val |= mask; + WRITECC32(devinfo, watchdog, val); + val &= ~CC_WD_COUNTER_MASK; + val |= 4; + WRITECC32(devinfo, watchdog, val); + msleep(10); + val = READCC32(devinfo, intstatus); + val |= mask; + WRITECC32(devinfo, intstatus, val); + } else { + WRITECC32(devinfo, watchdog, 4); + msleep(100); + } /* Restore ASPM */ brcmf_pcie_select_core(devinfo, BCMA_CORE_PCIE2); @@ -697,14 +795,14 @@ static void brcmf_pcie_reset_device(struct brcmf_pciedev_info *devinfo) core = brcmf_chip_get_core(devinfo->ci, BCMA_CORE_PCIE2); if (core->rev <= 13) { for (i = 0; i < ARRAY_SIZE(cfg_offset); i++) { - brcmf_pcie_write_reg32(devinfo, + brcmf_pcie_write_pcie32(devinfo, BRCMF_PCIE_PCIE2REG_CONFIGADDR, cfg_offset[i]); - val = brcmf_pcie_read_reg32(devinfo, + val = brcmf_pcie_read_pcie32(devinfo, BRCMF_PCIE_PCIE2REG_CONFIGDATA); brcmf_dbg(PCIE, "config offset 0x%04x, value 0x%04x\n", cfg_offset[i], val); - brcmf_pcie_write_reg32(devinfo, + brcmf_pcie_write_pcie32(devinfo, BRCMF_PCIE_PCIE2REG_CONFIGDATA, val); } @@ -718,9 +816,9 @@ static void brcmf_pcie_attach(struct brcmf_pciedev_info *devinfo) /* BAR1 window may not be sized properly */ brcmf_pcie_select_core(devinfo, BCMA_CORE_PCIE2); - brcmf_pcie_write_reg32(devinfo, BRCMF_PCIE_PCIE2REG_CONFIGADDR, 0x4e0); - config = brcmf_pcie_read_reg32(devinfo, BRCMF_PCIE_PCIE2REG_CONFIGDATA); - brcmf_pcie_write_reg32(devinfo, BRCMF_PCIE_PCIE2REG_CONFIGDATA, config); + brcmf_pcie_write_pcie32(devinfo, BRCMF_PCIE_PCIE2REG_CONFIGADDR, 0x4e0); + config = brcmf_pcie_read_pcie32(devinfo, BRCMF_PCIE_PCIE2REG_CONFIGDATA); + brcmf_pcie_write_pcie32(devinfo, BRCMF_PCIE_PCIE2REG_CONFIGDATA, config); device_wakeup_enable(&devinfo->pdev->dev); } @@ -739,6 +837,21 @@ static int brcmf_pcie_enter_download_state(struct brcmf_pciedev_info *devinfo) brcmf_pcie_write_reg32(devinfo, BRCMF_PCIE_ARMCR4REG_BANKPDA, 0); } + + /* Ensure all IRQs are masked so the firmware doesn't get + * a hostready notification too early. + */ + + brcmf_pcie_write_pcie32(devinfo, devinfo->reginfo->mailboxmask, 0); + brcmf_pcie_write_pcie32(devinfo, devinfo->reginfo->mailboxint, + 0xffffffff); + + pci_write_config_dword(devinfo->pdev, BRCMF_PCIE_REG_INTMASK, 0); + + brcmf_pcie_write_pcie32(devinfo, BRCMF_PCIE_PCIE2REG_CONFIGADDR, + BRCMF_PCIE_CFGREG_TLCNTRL_5); + brcmf_pcie_write_pcie32(devinfo, BRCMF_PCIE_PCIE2REG_CONFIGDATA, + 0xffffffff); return 0; } @@ -769,6 +882,19 @@ brcmf_pcie_send_mb_data(struct brcmf_pciedev_info *devinfo, u32 htod_mb_data) u32 i; shared = &devinfo->shared; + + if (shared->mb_via_ctl) { + struct pci_dev *pdev = devinfo->pdev; + struct brcmf_bus *bus = dev_get_drvdata(&pdev->dev); + int ret; + + ret = brcmf_msgbuf_h2d_mb_write(bus->drvr, htod_mb_data); + if (ret < 0) + brcmf_err(bus, "Failed to send H2D mailbox data (%d)\n", + ret); + return ret; + } + addr = shared->htod_mb_data_addr; cur_htod_mb_data = brcmf_pcie_read_tcm32(devinfo, addr); @@ -796,8 +922,29 @@ brcmf_pcie_send_mb_data(struct brcmf_pciedev_info *devinfo, u32 htod_mb_data) return 0; } +static void brcmf_pcie_handle_mb_data(struct brcmf_pciedev_info *devinfo, u32 data) +{ + brcmf_dbg(PCIE, "D2H_MB_DATA: 0x%04x\n", data); + if (data & BRCMF_D2H_DEV_DS_ENTER_REQ) { + brcmf_dbg(PCIE, "D2H_MB_DATA: DEEP SLEEP REQ\n"); + brcmf_pcie_send_mb_data(devinfo, BRCMF_H2D_HOST_DS_ACK); + brcmf_dbg(PCIE, "D2H_MB_DATA: sent DEEP SLEEP ACK\n"); + } + if (data & BRCMF_D2H_DEV_DS_EXIT_NOTE) + brcmf_dbg(PCIE, "D2H_MB_DATA: DEEP SLEEP EXIT\n"); + if (data & BRCMF_D2H_DEV_D3_ACK) { + brcmf_dbg(PCIE, "D2H_MB_DATA: D3 ACK\n"); + devinfo->mbdata_completed = true; + wake_up(&devinfo->mbdata_resp_wait); + } + if (data & BRCMF_D2H_DEV_FWHALT) { + brcmf_dbg(PCIE, "D2H_MB_DATA: FW HALT\n"); + brcmf_fw_crashed(&devinfo->pdev->dev); + } +} -static void brcmf_pcie_handle_mb_data(struct brcmf_pciedev_info *devinfo) + +static void brcmf_pcie_poll_mb_data(struct brcmf_pciedev_info *devinfo) { struct brcmf_pcie_shared_info *shared; u32 addr; @@ -812,23 +959,16 @@ static void brcmf_pcie_handle_mb_data(struct brcmf_pciedev_info *devinfo) brcmf_pcie_write_tcm32(devinfo, addr, 0); - brcmf_dbg(PCIE, "D2H_MB_DATA: 0x%04x\n", dtoh_mb_data); - if (dtoh_mb_data & BRCMF_D2H_DEV_DS_ENTER_REQ) { - brcmf_dbg(PCIE, "D2H_MB_DATA: DEEP SLEEP REQ\n"); - brcmf_pcie_send_mb_data(devinfo, BRCMF_H2D_HOST_DS_ACK); - brcmf_dbg(PCIE, "D2H_MB_DATA: sent DEEP SLEEP ACK\n"); - } - if (dtoh_mb_data & BRCMF_D2H_DEV_DS_EXIT_NOTE) - brcmf_dbg(PCIE, "D2H_MB_DATA: DEEP SLEEP EXIT\n"); - if (dtoh_mb_data & BRCMF_D2H_DEV_D3_ACK) { - brcmf_dbg(PCIE, "D2H_MB_DATA: D3 ACK\n"); - devinfo->mbdata_completed = true; - wake_up(&devinfo->mbdata_resp_wait); - } - if (dtoh_mb_data & BRCMF_D2H_DEV_FWHALT) { - brcmf_dbg(PCIE, "D2H_MB_DATA: FW HALT\n"); - brcmf_fw_crashed(&devinfo->pdev->dev); - } + brcmf_pcie_handle_mb_data(devinfo, dtoh_mb_data); +} + + +static void brcmf_pcie_d2h_mb_rx(struct device *dev, u32 data) +{ + struct brcmf_bus *bus_if = dev_get_drvdata(dev); + struct brcmf_pciedev *buspub = bus_if->bus_priv.pcie; + + brcmf_pcie_handle_mb_data(buspub->devinfo, data); } @@ -907,33 +1047,45 @@ static void brcmf_pcie_bus_console_read(struct brcmf_pciedev_info *devinfo, static void brcmf_pcie_intr_disable(struct brcmf_pciedev_info *devinfo) { - brcmf_pcie_write_reg32(devinfo, devinfo->reginfo->mailboxmask, 0); + brcmf_pcie_write_pcie32(devinfo, devinfo->reginfo->mailboxmask, 0); + + devinfo->irq_ready = false; } static void brcmf_pcie_intr_enable(struct brcmf_pciedev_info *devinfo) { - brcmf_pcie_write_reg32(devinfo, devinfo->reginfo->mailboxmask, + brcmf_pcie_write_pcie32(devinfo, devinfo->reginfo->mailboxmask, devinfo->reginfo->int_d2h_db | devinfo->reginfo->int_fn0); + + devinfo->irq_ready = true; } static void brcmf_pcie_hostready(struct brcmf_pciedev_info *devinfo) { - if (devinfo->shared.flags & BRCMF_PCIE_SHARED_HOSTRDY_DB1) - brcmf_pcie_write_reg32(devinfo, - devinfo->reginfo->h2d_mailbox_1, 1); + if (devinfo->shared.flags & BRCMF_PCIE_SHARED_HOSTRDY_DB1) { + if (devinfo->shared.flags & BRCMF_PCIE_SHARED_DAR) + brcmf_pcie_write_pcie32(devinfo, BRCMF_PCIE_64_PCIE2REG_H2D_MAILBOX_1, 1); + else + brcmf_pcie_write_pcie32(devinfo, BRCMF_PCIE_PCIE2REG_H2D_MAILBOX_1, 1); + } } static irqreturn_t brcmf_pcie_quick_check_isr(int irq, void *arg) { struct brcmf_pciedev_info *devinfo = (struct brcmf_pciedev_info *)arg; - if (brcmf_pcie_read_reg32(devinfo, devinfo->reginfo->mailboxint)) { + if (brcmf_pcie_read_pcie32(devinfo, devinfo->reginfo->mailboxint)) { brcmf_pcie_intr_disable(devinfo); brcmf_dbg(PCIE, "Enter\n"); return IRQ_WAKE_THREAD; } + + /* mailboxint is cleared by the firmware in MSI mode */ + if (devinfo->have_msi) + return IRQ_WAKE_THREAD; + return IRQ_NONE; } @@ -944,19 +1096,19 @@ static irqreturn_t brcmf_pcie_isr_thread(int irq, void *arg) u32 status; devinfo->in_irq = true; - status = brcmf_pcie_read_reg32(devinfo, devinfo->reginfo->mailboxint); + status = brcmf_pcie_read_pcie32(devinfo, devinfo->reginfo->mailboxint); brcmf_dbg(PCIE, "Enter %x\n", status); if (status) { - brcmf_pcie_write_reg32(devinfo, devinfo->reginfo->mailboxint, + brcmf_pcie_write_pcie32(devinfo, devinfo->reginfo->mailboxint, status); if (status & devinfo->reginfo->int_fn0) - brcmf_pcie_handle_mb_data(devinfo); - if (status & devinfo->reginfo->int_d2h_db) { - if (devinfo->state == BRCMFMAC_PCIE_STATE_UP) - brcmf_proto_msgbuf_rx_trigger( - &devinfo->pdev->dev); - } + brcmf_pcie_poll_mb_data(devinfo); } + if (devinfo->have_msi || status & devinfo->reginfo->int_d2h_db) { + if (devinfo->state == BRCMFMAC_PCIE_STATE_UP && devinfo->irq_ready) + brcmf_proto_msgbuf_rx_trigger(&devinfo->pdev->dev); + } + brcmf_pcie_bus_console_read(devinfo, false); if (devinfo->state == BRCMFMAC_PCIE_STATE_UP) brcmf_pcie_intr_enable(devinfo); @@ -974,7 +1126,10 @@ static int brcmf_pcie_request_irq(struct brcmf_pciedev_info *devinfo) brcmf_dbg(PCIE, "Enter\n"); - pci_enable_msi(pdev); + devinfo->have_msi = pci_enable_msi(pdev) >= 0; + if (devinfo->have_msi) + brcmf_dbg(PCIE, "MSI enabled\n"); + if (request_threaded_irq(pdev->irq, brcmf_pcie_quick_check_isr, brcmf_pcie_isr_thread, IRQF_SHARED, "brcmf_pcie_intr", devinfo)) { @@ -1010,8 +1165,8 @@ static void brcmf_pcie_release_irq(struct brcmf_pciedev_info *devinfo) if (devinfo->in_irq) brcmf_err(bus, "Still in IRQ (processing) !!!\n"); - status = brcmf_pcie_read_reg32(devinfo, devinfo->reginfo->mailboxint); - brcmf_pcie_write_reg32(devinfo, devinfo->reginfo->mailboxint, status); + status = brcmf_pcie_read_pcie32(devinfo, devinfo->reginfo->mailboxint); + brcmf_pcie_write_pcie32(devinfo, devinfo->reginfo->mailboxint, status); devinfo->irq_allocated = false; } @@ -1063,7 +1218,10 @@ static int brcmf_pcie_ring_mb_ring_bell(void *ctx) brcmf_dbg(PCIE, "RING !\n"); /* Any arbitrary value will do, lets use 1 */ - brcmf_pcie_write_reg32(devinfo, devinfo->reginfo->h2d_mailbox_0, 1); + if (devinfo->shared.flags & BRCMF_PCIE_SHARED_DAR) + brcmf_pcie_write_pcie32(devinfo, BRCMF_PCIE_64_PCIE2REG_H2D_MAILBOX_0, 1); + else + brcmf_pcie_write_pcie32(devinfo, BRCMF_PCIE_PCIE2REG_H2D_MAILBOX_0, 1); return 0; } @@ -1589,6 +1747,7 @@ static const struct brcmf_bus_ops brcmf_pcie_bus_ops = { .get_blob = brcmf_pcie_get_blob, .reset = brcmf_pcie_reset, .debugfs_create = brcmf_pcie_debugfs_create, + .d2h_mb_rx = brcmf_pcie_d2h_mb_rx, }; @@ -1620,12 +1779,16 @@ brcmf_pcie_init_share_ram_info(struct brcmf_pciedev_info *devinfo, { struct brcmf_bus *bus = dev_get_drvdata(&devinfo->pdev->dev); struct brcmf_pcie_shared_info *shared; + u32 host_cap; + u32 host_cap2; u32 addr; shared = &devinfo->shared; shared->tcm_base_address = sharedram_addr; - shared->flags = brcmf_pcie_read_tcm32(devinfo, sharedram_addr); + shared->flags = brcmf_pcie_read_tcm32(devinfo, sharedram_addr + + BRCMF_SHARED_FLAGS_OFFSET); + shared->version = (u8)(shared->flags & BRCMF_PCIE_SHARED_VERSION_MASK); brcmf_dbg(PCIE, "PCIe protocol version %d\n", shared->version); if ((shared->version > BRCMF_PCIE_MAX_SHARED_VERSION) || @@ -1666,29 +1829,223 @@ brcmf_pcie_init_share_ram_info(struct brcmf_pciedev_info *devinfo, brcmf_pcie_bus_console_init(devinfo); brcmf_pcie_bus_console_read(devinfo, false); + /* Features added in revision 6 follow */ + if (shared->version < 6) + return 0; + + shared->flags2 = brcmf_pcie_read_tcm32(devinfo, sharedram_addr + + BRCMF_SHARED_FLAGS2_OFFSET); + shared->flags3 = brcmf_pcie_read_tcm32(devinfo, sharedram_addr + + BRCMF_SHARED_FLAGS3_OFFSET); + + /* Check which mailbox mechanism to use */ + if (!(shared->flags & BRCMF_PCIE_SHARED_USE_MAILBOX)) + shared->mb_via_ctl = true; + + /* Update host support flags */ + host_cap = shared->version; + host_cap2 = 0; + + if (shared->flags & BRCMF_PCIE_SHARED_HOSTRDY_DB1) + host_cap |= BRCMF_HOSTCAP_H2D_ENABLE_HOSTRDY; + + if (shared->flags & BRCMF_PCIE_SHARED_DAR) + host_cap |= BRCMF_HOSTCAP_H2D_DAR; + + /* Disable DS: this is not currently properly supported */ + host_cap |= BRCMF_HOSTCAP_DS_NO_OOB_DW; + + brcmf_pcie_write_tcm32(devinfo, sharedram_addr + + BRCMF_SHARED_HOST_CAP_OFFSET, host_cap); + brcmf_pcie_write_tcm32(devinfo, sharedram_addr + + BRCMF_SHARED_HOST_CAP2_OFFSET, host_cap2); + return 0; } -struct brcmf_random_seed_footer { +struct brcmf_rtlv_footer { __le32 length; __le32 magic; }; +/** struct brcmf_fw_memmap_region - start/end of memory regions for chip + */ +struct brcmf_fw_memmap_region { + u32 start; + u32 end; +}; + +/** struct brcmf_fw_memmap + * + * @reset_vec - Reset vector - read only + * @int_vec - copied from ram, jumps here on success + * @rom - bootloader at rom start + * @mmap - struct/memory map written by host + * @vstatus - verification status + * @fw - firmware + * @sig - firwmare signature + * @heap - region for heap allocations + * @stack - region for stack allocations + * @prng - PRNG data, may be 0 length + * @nvram - NVRAM data + */ +struct brcmf_fw_memmap { + struct brcmf_fw_memmap_region reset_vec; + struct brcmf_fw_memmap_region int_vec; + struct brcmf_fw_memmap_region rom; + struct brcmf_fw_memmap_region mmap; + struct brcmf_fw_memmap_region vstatus; + struct brcmf_fw_memmap_region fw; + struct brcmf_fw_memmap_region sig; + struct brcmf_fw_memmap_region heap; + struct brcmf_fw_memmap_region stack; + struct brcmf_fw_memmap_region prng; + struct brcmf_fw_memmap_region nvram; +}; + +#define BRCMF_BL_HEAP_START_GAP 0x1000 +#define BRCMF_BL_HEAP_SIZE 0x10000 #define BRCMF_RANDOM_SEED_MAGIC 0xfeedc0de #define BRCMF_RANDOM_SEED_LENGTH 0x100 +#define BRCMF_FW_SIG_MAGIC 0xfeedfe51 +#define BRCMF_NVRAM_SIG_MAGIC 0xfeedfe52 +#define BRCMF_MEMMAP_MAGIC 0xfeedfe53 +#define BRCMF_VSTATUS_MAGIC 0xfeedfe54 +#define BRCMF_VSTATUS_SIZE 0x28 +#define BRCMF_END_MAGIC 0xfeed0e2d -static noinline_for_stack void -brcmf_pcie_provide_random_bytes(struct brcmf_pciedev_info *devinfo, u32 address) +static int brcmf_alloc_rtlv(struct brcmf_pciedev_info *devinfo, u32 *address, u32 type, u32 length) { + struct brcmf_bus *bus = dev_get_drvdata(&devinfo->pdev->dev); + u32 fw_top = devinfo->ci->rambase + devinfo->fw_size; + u32 ram_start = ALIGN(fw_top + BRCMF_BL_HEAP_START_GAP, 4); + u32 ram_end = ram_start + BRCMF_BL_HEAP_SIZE; + u32 start_addr; + struct brcmf_rtlv_footer footer = { + .magic = type, + }; + + length = ALIGN(length, 4); + start_addr = *address - length - sizeof(struct brcmf_rtlv_footer); + + if (length > 0xffff || start_addr > *address || start_addr < ram_end) { + brcmf_err(bus, "failed to allocate 0x%x bytes for rTLV type 0x%x\n", + length, type); + return -ENOMEM; + } + + /* Random seed does not use the length check code */ + if (type == BRCMF_RANDOM_SEED_MAGIC) + footer.length = length; + else + footer.length = length | ((length ^ 0xffff) << 16); + + memcpy_toio(devinfo->tcm + *address - sizeof(struct brcmf_rtlv_footer), + &footer, sizeof(struct brcmf_rtlv_footer)); + + *address = start_addr; + + return 0; +} + +static noinline_for_stack int +brcmf_pcie_add_random_seed(struct brcmf_pciedev_info *devinfo, u32 *address) +{ + int err; u8 randbuf[BRCMF_RANDOM_SEED_LENGTH]; + err = brcmf_alloc_rtlv(devinfo, address, + BRCMF_RANDOM_SEED_MAGIC, BRCMF_RANDOM_SEED_LENGTH); + if (err) + return err; + + /* Some Apple chips/firmwares expect a buffer of random + * data to be present before NVRAM + */ + brcmf_dbg(PCIE, "Download random seed\n"); + get_random_bytes(randbuf, BRCMF_RANDOM_SEED_LENGTH); - memcpy_toio(devinfo->tcm + address, randbuf, BRCMF_RANDOM_SEED_LENGTH); + memcpy_toio(devinfo->tcm + *address, randbuf, BRCMF_RANDOM_SEED_LENGTH); + + return 0; +} + +static int brcmf_pcie_add_signature(struct brcmf_pciedev_info *devinfo, + u32 *address, const struct firmware *fwsig) +{ + int err; + struct brcmf_fw_memmap memmap; + + brcmf_dbg(PCIE, "Download firmware signature\n"); + + memset(&memmap, 0, sizeof(memmap)); + + memmap.sig.end = *address; + err = brcmf_alloc_rtlv(devinfo, address, BRCMF_FW_SIG_MAGIC, fwsig->size); + if (err) + return err; + memmap.sig.start = *address; + + memmap.vstatus.end = *address; + err = brcmf_alloc_rtlv(devinfo, address, BRCMF_VSTATUS_MAGIC, BRCMF_VSTATUS_SIZE); + if (err) + return err; + memmap.vstatus.start = *address; + + err = brcmf_alloc_rtlv(devinfo, address, BRCMF_MEMMAP_MAGIC, sizeof(memmap)); + if (err) + return err; + + memmap.fw.start = devinfo->ci->rambase; + memmap.fw.end = memmap.fw.start + devinfo->fw_size; + memmap.heap.start = ALIGN(memmap.fw.end + BRCMF_BL_HEAP_START_GAP, 4); + memmap.heap.end = memmap.heap.start + BRCMF_BL_HEAP_SIZE; + + if (memmap.heap.end > *address) + return -ENOMEM; + + memcpy_toio(devinfo->tcm + memmap.sig.start, fwsig->data, fwsig->size); + memset_io(devinfo->tcm + memmap.vstatus.start, 0, BRCMF_VSTATUS_SIZE); + memcpy_toio(devinfo->tcm + *address, &memmap, sizeof(memmap)); + + err = brcmf_alloc_rtlv(devinfo, address, BRCMF_END_MAGIC, 0); + if (err) + return err; + + devinfo->skip_reset_vector = true; + + return 0; +} + +static int brcmf_pcie_populate_footers(struct brcmf_pciedev_info *devinfo, + u32 *address, const struct firmware *fwsig) +{ + int err; + + /* We only do this for Apple firmwares. If any other + * production firmwares are found to need this, the condition + * needs to be adjusted. + */ + if (!devinfo->fwseed) + return 0; + + err = brcmf_pcie_add_random_seed(devinfo, address); + if (err) + return err; + + if (fwsig) { + err = brcmf_pcie_add_signature(devinfo, address, fwsig); + if (err) + return err; + } + + return 0; } static int brcmf_pcie_download_fw_nvram(struct brcmf_pciedev_info *devinfo, - const struct firmware *fw, void *nvram, - u32 nvram_len) + const struct firmware *fw, + const struct firmware *fwsig, + void *nvram, u32 nvram_len) { struct brcmf_bus *bus = dev_get_drvdata(&devinfo->pdev->dev); u32 sharedram_addr; @@ -1708,6 +2065,7 @@ static int brcmf_pcie_download_fw_nvram(struct brcmf_pciedev_info *devinfo, (void *)fw->data, fw->size); resetintr = get_unaligned_le32(fw->data); + devinfo->fw_size = fw->size; release_firmware(fw); /* reset last 4 bytes of RAM address. to be used for shared @@ -1715,37 +2073,31 @@ static int brcmf_pcie_download_fw_nvram(struct brcmf_pciedev_info *devinfo, */ brcmf_pcie_write_ram32(devinfo, devinfo->ci->ramsize - 4, 0); + address = devinfo->ci->rambase + devinfo->ci->ramsize; + if (nvram) { brcmf_dbg(PCIE, "Download NVRAM %s\n", devinfo->nvram_name); - address = devinfo->ci->rambase + devinfo->ci->ramsize - - nvram_len; + address -= nvram_len; memcpy_toio(devinfo->tcm + address, nvram, nvram_len); brcmf_fw_nvram_free(nvram); - if (devinfo->fwseed) { - size_t rand_len = BRCMF_RANDOM_SEED_LENGTH; - struct brcmf_random_seed_footer footer = { - .length = cpu_to_le32(rand_len), - .magic = cpu_to_le32(BRCMF_RANDOM_SEED_MAGIC), - }; - - /* Some chips/firmwares expect a buffer of random - * data to be present before NVRAM - */ - brcmf_dbg(PCIE, "Download random seed\n"); - - address -= sizeof(footer); - memcpy_toio(devinfo->tcm + address, &footer, - sizeof(footer)); - - address -= rand_len; - brcmf_pcie_provide_random_bytes(devinfo, address); - } + err = brcmf_pcie_populate_footers(devinfo, &address, fwsig); + if (err) + brcmf_err(bus, "failed to populate firmware footers err=%d\n", err); } else { brcmf_dbg(PCIE, "No matching NVRAM file found %s\n", devinfo->nvram_name); } + release_firmware(fwsig); + + /* Clear free TCM. This isn't really necessary, but it + * makes debugging memory dumps a lot easier since we + * don't get a bunch of junk filling up the free space. + */ + memset_io(devinfo->tcm + devinfo->ci->rambase + devinfo->fw_size, + 0, address - devinfo->fw_size - devinfo->ci->rambase); + sharedram_addr_written = brcmf_pcie_read_ram32(devinfo, devinfo->ci->ramsize - 4); @@ -1889,9 +2241,9 @@ static int brcmf_pcie_buscore_reset(void *ctx, struct brcmf_chip *chip) else reg = BRCMF_PCIE_PCIE2REG_MAILBOXINT; - val = brcmf_pcie_read_reg32(devinfo, reg); + val = brcmf_pcie_read_pcie32(devinfo, reg); if (val != 0xffffffff) - brcmf_pcie_write_reg32(devinfo, reg, val); + brcmf_pcie_write_pcie32(devinfo, reg, val); return 0; } @@ -1902,7 +2254,8 @@ static void brcmf_pcie_buscore_activate(void *ctx, struct brcmf_chip *chip, { struct brcmf_pciedev_info *devinfo = (struct brcmf_pciedev_info *)ctx; - brcmf_pcie_write_tcm32(devinfo, 0, rstvec); + if (!devinfo->skip_reset_vector) + brcmf_pcie_write_tcm32(devinfo, 0, rstvec); } @@ -2073,6 +2426,11 @@ static int brcmf_pcie_read_otp(struct brcmf_pciedev_info *devinfo) base = 0x113c; words = 0x170; break; + case BRCM_CC_4388_CHIP_ID: + coreid = BCMA_CORE_GCI; + base = 0x115c; + words = 0x150; + break; default: /* OTP not supported on this chip */ return 0; @@ -2131,11 +2489,12 @@ static int brcmf_pcie_read_otp(struct brcmf_pciedev_info *devinfo) #define BRCMF_PCIE_FW_NVRAM 1 #define BRCMF_PCIE_FW_CLM 2 #define BRCMF_PCIE_FW_TXCAP 3 +#define BRCMF_PCIE_FW_SIG 4 static void brcmf_pcie_setup(struct device *dev, int ret, struct brcmf_fw_request *fwreq) { - const struct firmware *fw; + const struct firmware *fw, *fwsig; void *nvram; struct brcmf_bus *bus; struct brcmf_pciedev *pcie_bus_dev; @@ -2154,6 +2513,7 @@ static void brcmf_pcie_setup(struct device *dev, int ret, brcmf_pcie_attach(devinfo); fw = fwreq->items[BRCMF_PCIE_FW_CODE].binary; + fwsig = fwreq->items[BRCMF_PCIE_FW_SIG].binary; nvram = fwreq->items[BRCMF_PCIE_FW_NVRAM].nv_data.data; nvram_len = fwreq->items[BRCMF_PCIE_FW_NVRAM].nv_data.len; devinfo->clm_fw = fwreq->items[BRCMF_PCIE_FW_CLM].binary; @@ -2164,6 +2524,7 @@ static void brcmf_pcie_setup(struct device *dev, int ret, if (ret) { brcmf_err(bus, "Failed to get RAM info\n"); release_firmware(fw); + release_firmware(fwsig); brcmf_fw_nvram_free(nvram); goto fail; } @@ -2175,7 +2536,15 @@ static void brcmf_pcie_setup(struct device *dev, int ret, */ brcmf_pcie_adjust_ramsize(devinfo, (u8 *)fw->data, fw->size); - ret = brcmf_pcie_download_fw_nvram(devinfo, fw, nvram, nvram_len); + /* Newer firmwares will signal firmware boot via MSI, so make sure we + * initialize that upfront. + */ + brcmf_pcie_select_core(devinfo, BCMA_CORE_PCIE2); + ret = brcmf_pcie_request_irq(devinfo); + if (ret) + goto fail; + + ret = brcmf_pcie_download_fw_nvram(devinfo, fw, fwsig, nvram, nvram_len); if (ret) goto fail; @@ -2190,9 +2559,6 @@ static void brcmf_pcie_setup(struct device *dev, int ret, goto fail; brcmf_pcie_select_core(devinfo, BCMA_CORE_PCIE2); - ret = brcmf_pcie_request_irq(devinfo); - if (ret) - goto fail; /* hook the commonrings in the bus structure. */ for (i = 0; i < BRCMF_NROF_COMMON_MSGRINGS; i++) @@ -2240,6 +2606,7 @@ brcmf_pcie_prepare_fw_request(struct brcmf_pciedev_info *devinfo) { ".txt", devinfo->nvram_name }, { ".clm_blob", devinfo->clm_name }, { ".txcap_blob", devinfo->txcap_name }, + { ".sig", devinfo->sig_name }, }; fwreq = brcmf_fw_alloc_request(devinfo->ci->chip, devinfo->ci->chiprev, @@ -2250,6 +2617,8 @@ brcmf_pcie_prepare_fw_request(struct brcmf_pciedev_info *devinfo) return NULL; fwreq->items[BRCMF_PCIE_FW_CODE].type = BRCMF_FW_TYPE_BINARY; + fwreq->items[BRCMF_PCIE_FW_SIG].type = BRCMF_FW_TYPE_BINARY; + fwreq->items[BRCMF_PCIE_FW_SIG].flags = BRCMF_FW_REQF_OPTIONAL; fwreq->items[BRCMF_PCIE_FW_NVRAM].type = BRCMF_FW_TYPE_NVRAM; fwreq->items[BRCMF_PCIE_FW_NVRAM].flags = BRCMF_FW_REQF_OPTIONAL; fwreq->items[BRCMF_PCIE_FW_CLM].type = BRCMF_FW_TYPE_BINARY; @@ -2668,12 +3037,13 @@ static int brcmf_pcie_pm_leave_D3(struct device *dev) brcmf_dbg(PCIE, "Enter, dev=%p, bus=%p\n", dev, bus); /* Check if device is still up and running, if so we are ready */ - if (brcmf_pcie_read_reg32(devinfo, devinfo->reginfo->intmask) != 0) { + if (brcmf_pcie_read_pcie32(devinfo, devinfo->reginfo->intmask) != 0) { brcmf_dbg(PCIE, "Try to wakeup device....\n"); + /* Set the device up, so we can write the MB data message in ring mode */ + devinfo->state = BRCMFMAC_PCIE_STATE_UP; if (brcmf_pcie_send_mb_data(devinfo, BRCMF_H2D_HOST_D0_INFORM)) goto cleanup; brcmf_dbg(PCIE, "Hot resume, continue....\n"); - devinfo->state = BRCMFMAC_PCIE_STATE_UP; brcmf_pcie_select_core(devinfo, BCMA_CORE_PCIE2); brcmf_bus_change_state(bus, BRCMF_BUS_UP); brcmf_pcie_intr_enable(devinfo); @@ -2683,6 +3053,7 @@ static int brcmf_pcie_pm_leave_D3(struct device *dev) } cleanup: + devinfo->state = BRCMFMAC_PCIE_STATE_DOWN; brcmf_chip_detach(devinfo->ci); devinfo->ci = NULL; pdev = devinfo->pdev; @@ -2750,6 +3121,7 @@ static const struct pci_device_id brcmf_pcie_devid_table[] = { BRCMF_PCIE_DEVICE(BRCM_PCIE_4377_DEVICE_ID, WCC_SEED), BRCMF_PCIE_DEVICE(BRCM_PCIE_4378_DEVICE_ID, WCC_SEED), BRCMF_PCIE_DEVICE(BRCM_PCIE_4387_DEVICE_ID, WCC_SEED), + BRCMF_PCIE_DEVICE(BRCM_PCIE_4388_DEVICE_ID, WCC_SEED), BRCMF_PCIE_DEVICE(BRCM_PCIE_43752_DEVICE_ID, WCC_SEED), BRCMF_PCIE_DEVICE(CY_PCIE_54591_DEVICE_ID, CYW), { /* end: all zeroes */ } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c index 05f66ab13bed6d..dbeeaef75b165a 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c @@ -12,8 +12,10 @@ #include "fwil_types.h" #include "cfg80211.h" #include "pno.h" +#include "feature.h" -#define BRCMF_PNO_VERSION 2 +#define BRCMF_PNO_VERSION_2 2 +#define BRCMF_PNO_VERSION_3 3 #define BRCMF_PNO_REPEAT 4 #define BRCMF_PNO_FREQ_EXPO_MAX 3 #define BRCMF_PNO_IMMEDIATE_SCAN_BIT 3 @@ -99,8 +101,62 @@ static int brcmf_pno_channel_config(struct brcmf_if *ifp, return brcmf_fil_iovar_data_set(ifp, "pfn_cfg", cfg, sizeof(*cfg)); } -static int brcmf_pno_config(struct brcmf_if *ifp, u32 scan_freq, - u32 mscan, u32 bestn) +static int brcmf_pno_config_v3(struct brcmf_if *ifp, u32 scan_freq, u32 mscan, + u32 bestn) +{ + struct brcmf_pub *drvr = ifp->drvr; + struct brcmf_pno_param_v3_le pfn_param; + u16 flags; + u32 pfnmem; + s32 err; + + memset(&pfn_param, 0, sizeof(pfn_param)); + pfn_param.version = cpu_to_le16(BRCMF_PNO_VERSION_3); + pfn_param.length = cpu_to_le16(sizeof(struct brcmf_pno_param_v3_le)); + + /* set extra pno params */ + flags = BIT(BRCMF_PNO_IMMEDIATE_SCAN_BIT) | + BIT(BRCMF_PNO_ENABLE_ADAPTSCAN_BIT); + pfn_param.repeat = BRCMF_PNO_REPEAT; + pfn_param.exp = BRCMF_PNO_FREQ_EXPO_MAX; + + /* set up pno scan fr */ + pfn_param.scan_freq = cpu_to_le32(scan_freq); + + if (mscan) { + pfnmem = bestn; + + /* set bestn in firmware */ + err = brcmf_fil_iovar_int_set(ifp, "pfnmem", pfnmem); + if (err < 0) { + bphy_err(drvr, "failed to set pfnmem\n"); + goto exit; + } + /* get max mscan which the firmware supports */ + err = brcmf_fil_iovar_int_get(ifp, "pfnmem", &pfnmem); + if (err < 0) { + bphy_err(drvr, "failed to get pfnmem\n"); + goto exit; + } + mscan = min_t(u32, mscan, pfnmem); + pfn_param.mscan = mscan; + pfn_param.bestn = bestn; + flags |= BIT(BRCMF_PNO_ENABLE_BD_SCAN_BIT); + brcmf_dbg(INFO, "mscan=%d, bestn=%d\n", mscan, bestn); + } + + pfn_param.flags = cpu_to_le16(flags); + err = brcmf_fil_iovar_data_set(ifp, "pfn_set", &pfn_param, + sizeof(pfn_param)); + if (err) + bphy_err(drvr, "pfn_set failed, err=%d\n", err); + +exit: + return err; +} + +static int brcmf_pno_config_v2(struct brcmf_if *ifp, u32 scan_freq, u32 mscan, + u32 bestn) { struct brcmf_pub *drvr = ifp->drvr; struct brcmf_pno_param_le pfn_param; @@ -109,7 +165,7 @@ static int brcmf_pno_config(struct brcmf_if *ifp, u32 scan_freq, s32 err; memset(&pfn_param, 0, sizeof(pfn_param)); - pfn_param.version = cpu_to_le32(BRCMF_PNO_VERSION); + pfn_param.version = cpu_to_le32(BRCMF_PNO_VERSION_2); /* set extra pno params */ flags = BIT(BRCMF_PNO_IMMEDIATE_SCAN_BIT) | @@ -152,6 +208,12 @@ static int brcmf_pno_config(struct brcmf_if *ifp, u32 scan_freq, return err; } +static int brcmf_pno_config(struct brcmf_if *ifp, u32 scan_freq, u32 mscan, + u32 bestn) +{ + return ifp->drvr->pno_handler.pno_config(ifp, scan_freq, mscan, bestn); +} + static int brcmf_pno_set_random(struct brcmf_if *ifp, struct brcmf_pno_info *pi) { struct brcmf_pub *drvr = ifp->drvr; @@ -275,7 +337,7 @@ static int brcmf_pno_get_bucket_channels(struct cfg80211_sched_scan_request *r, { u32 n_chan = le32_to_cpu(pno_cfg->channel_num); u16 chan; - int i, err = 0; + int i, err; for (i = 0; i < r->n_channels; i++) { if (n_chan >= BRCMF_NUMCHANNELS) { @@ -562,9 +624,82 @@ u64 brcmf_pno_find_reqid_by_bucket(struct brcmf_pno_info *pi, u32 bucket) return reqid; } -u32 brcmf_pno_get_bucket_map(struct brcmf_pno_info *pi, - struct brcmf_pno_net_info_le *ni) + +static struct brcmf_pno_net_info_le * +brcmf_get_netinfo_array(void *pfn_v1_data) +{ + struct brcmf_pno_scanresults_le *pfn_v1 = + (struct brcmf_pno_scanresults_le *)pfn_v1_data; + struct brcmf_pno_scanresults_v2_le *pfn_v2; + struct brcmf_pno_net_info_le *netinfo = NULL; + + switch (pfn_v1->version) { + default: + WARN_ON(1); + fallthrough; + case cpu_to_le32(1): + netinfo = (struct brcmf_pno_net_info_le *)(pfn_v1 + 1); + break; + case cpu_to_le32(2): + pfn_v2 = (struct brcmf_pno_scanresults_v2_le *)pfn_v1; + netinfo = (struct brcmf_pno_net_info_le *)(pfn_v2 + 1); + break; + case cpu_to_le32(3): + brcmf_err("Need to use brcmf_get_netinfo_v3_array\n"); + break; + } + + return netinfo; +} + +static struct brcmf_pno_net_info_v3_le * +brcmf_get_netinfo_v3_array(void*pfn_v3_data) +{ + struct brcmf_pno_scanresults_v3_le *pfn_v3 = + (struct brcmf_pno_scanresults_v3_le *)pfn_v3_data; + return (struct brcmf_pno_net_info_v3_le *) (pfn_v3 + 1); +} + +static u32 brcmf_pno_get_bucket_map(void *data, int idx, struct brcmf_pno_info *pi) +{ + + struct brcmf_pno_net_info_le *netinfo_start = + brcmf_get_netinfo_array(data); + struct brcmf_pno_net_info_le *ni = &netinfo_start[idx]; + struct cfg80211_sched_scan_request *req; + struct cfg80211_match_set *ms; + u32 bucket_map = 0; + int i, j; + + mutex_lock(&pi->req_lock); + for (i = 0; i < pi->n_reqs; i++) { + req = pi->reqs[i]; + + if (!req->n_match_sets) + continue; + for (j = 0; j < req->n_match_sets; j++) { + ms = &req->match_sets[j]; + if (ms->ssid.ssid_len == ni->SSID_len && + !memcmp(ms->ssid.ssid, ni->SSID, ni->SSID_len)) { + bucket_map |= BIT(i); + break; + } + if (is_valid_ether_addr(ms->bssid) && + !memcmp(ms->bssid, ni->bssid, ETH_ALEN)) { + bucket_map |= BIT(i); + break; + } + } + } + mutex_unlock(&pi->req_lock); + return bucket_map; +} + +static u32 brcmf_pno_get_bucket_map_v3(void *data, int idx, struct brcmf_pno_info *pi) { + struct brcmf_pno_net_info_v3_le *netinfo_v3_start = + brcmf_get_netinfo_v3_array(data); + struct brcmf_pno_net_info_v3_le *ni = &netinfo_v3_start[idx]; struct cfg80211_sched_scan_request *req; struct cfg80211_match_set *ms; u32 bucket_map = 0; @@ -593,3 +728,148 @@ u32 brcmf_pno_get_bucket_map(struct brcmf_pno_info *pi, mutex_unlock(&pi->req_lock); return bucket_map; } + +static u32 brcmf_pno_min_data_len(void) +{ + return sizeof(struct brcmf_pno_scanresults_le) + + sizeof(struct brcmf_pno_net_info_le); +} +static u32 brcmf_pno_min_data_len_v3(void) +{ + return sizeof(struct brcmf_pno_scanresults_v3_le) + + sizeof(struct brcmf_pno_net_info_v3_le); +} + +static int brcmf_pno_validate_pfn_results_v3(void *data, u32 eventlen) +{ + struct brcmf_pno_scanresults_v3_le *scanresult = + (struct brcmf_pno_scanresults_v3_le *)data; + struct brcmf_pno_net_info_v3_le *netinfo_v3_start = + brcmf_get_netinfo_v3_array(scanresult); + u32 datalen; + + if (!netinfo_v3_start) { + brcmf_err("did not get netinfo_v3 data\n"); + return -EINVAL; + } + datalen = eventlen - ((void *)netinfo_v3_start - (void *)data); + if (datalen < le32_to_cpu(scanresult->count) * sizeof(struct brcmf_pno_net_info_v3_le)) { + brcmf_err("insufficient event data\n"); + return -EINVAL; + } + return 0; +} + +static int brcmf_pno_validate_pfn_results(void *data, u32 eventlen) +{ + struct brcmf_pno_scanresults_le *scanresult = + (struct brcmf_pno_scanresults_le *)data; + struct brcmf_pno_net_info_le *netinfo_start = + brcmf_get_netinfo_array(scanresult); + u32 datalen; + + if (!netinfo_start) { + brcmf_err("did not get netinfo data\n"); + return -EINVAL; + } + datalen = eventlen - ((void *)netinfo_start - (void *)data); + if (datalen < le32_to_cpu(scanresult->count) * sizeof(struct brcmf_pno_net_info_le)) { + brcmf_err("insufficient event data\n"); + return -EINVAL; + } + return 0; +} + +static int brcmf_pno_get_result_info(void *data, int result_idx, + u8 (*ssid)[IEEE80211_MAX_SSID_LEN], + u8 *ssid_len, u8 *channel, + enum nl80211_band *band) +{ + struct brcmf_pno_scanresults_le *scanresult = + (struct brcmf_pno_scanresults_le *)data; + struct brcmf_pno_net_info_le *netinfo_start = + brcmf_get_netinfo_array(scanresult); + struct brcmf_pno_net_info_le *netinfo = &netinfo_start[result_idx]; + + *channel = netinfo->channel; + *band = netinfo->channel <= CH_MAX_2G_CHANNEL ? NL80211_BAND_2GHZ : + NL80211_BAND_5GHZ; + *ssid_len = netinfo->SSID_len; + if (netinfo->SSID_len > IEEE80211_MAX_SSID_LEN) + *ssid_len = IEEE80211_MAX_SSID_LEN; + memcpy(ssid, netinfo->SSID, *ssid_len); + + return 0; +} + +static int brcmf_pno_get_result_info_v3(void *data, int result_idx, + u8 (*ssid)[IEEE80211_MAX_SSID_LEN], + u8 *ssid_len, u8 *channel, + enum nl80211_band *band) +{ + struct brcmf_pno_scanresults_v3_le *scanresult = + (struct brcmf_pno_scanresults_v3_le *)data; + struct brcmf_pno_net_info_v3_le *netinfo_v3_start = + brcmf_get_netinfo_v3_array(scanresult); + struct brcmf_pno_net_info_v3_le *netinfo_v3 = + &netinfo_v3_start[result_idx]; + + *channel = CHSPEC_CHANNEL(netinfo_v3->chanspec); + *band = fwil_band_to_nl80211(CHSPEC_BAND(netinfo_v3->chanspec)); + *ssid_len = netinfo_v3->SSID_len; + if (netinfo_v3->SSID_len > IEEE80211_MAX_SSID_LEN) + *ssid_len = IEEE80211_MAX_SSID_LEN; + memcpy(ssid, netinfo_v3->SSID, *ssid_len); + + return 0; +} + +/* The count and status fields are in the same place for v1/2/3 */ +static u32 brcmf_pno_get_result_count_v123(void *data) +{ + struct brcmf_pno_scanresults_le *results = + (struct brcmf_pno_scanresults_le *)data; + return le32_to_cpu(results->count); +} +static u32 brcmf_pno_get_result_status_v123(void *data) +{ + struct brcmf_pno_scanresults_le *results = + (struct brcmf_pno_scanresults_le *)data; + return le32_to_cpu(results->status); +} + +int brcmf_pno_setup_for_version(struct brcmf_pub *drvr, u8 vers) +{ + /* The first supported version by this driver was version 2. + * The v2 functions handle version one structures if handed to them, + * but the config was always set to interface version 2. */ + switch (vers) { + case BRCMF_PNO_VERSION_2: { + drvr->pno_handler.version = BRCMF_PNO_VERSION_2; + drvr->pno_handler.pno_config = brcmf_pno_config_v2; + drvr->pno_handler.get_result_count = brcmf_pno_get_result_count_v123; + drvr->pno_handler.get_result_status = brcmf_pno_get_result_status_v123; + drvr->pno_handler.get_bucket_map = brcmf_pno_get_bucket_map; + drvr->pno_handler.get_min_data_len = brcmf_pno_min_data_len; + drvr->pno_handler.get_result_info = brcmf_pno_get_result_info; + drvr->pno_handler.validate_pfn_results = + brcmf_pno_validate_pfn_results; + break; + } + case BRCMF_PNO_VERSION_3: { + drvr->pno_handler.version = BRCMF_PNO_VERSION_3; + drvr->pno_handler.pno_config = brcmf_pno_config_v3; + drvr->pno_handler.get_result_count = brcmf_pno_get_result_count_v123; + drvr->pno_handler.get_result_status = brcmf_pno_get_result_status_v123; + drvr->pno_handler.get_bucket_map = brcmf_pno_get_bucket_map_v3; + drvr->pno_handler.get_min_data_len = brcmf_pno_min_data_len_v3; + drvr->pno_handler.get_result_info = brcmf_pno_get_result_info_v3; + drvr->pno_handler.validate_pfn_results = + brcmf_pno_validate_pfn_results_v3; + break; + } + default: + return -EINVAL; + } + return 0; +} diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.h index 25d406019ac340..0163c762f5385a 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.h @@ -61,12 +61,12 @@ void brcmf_pno_detach(struct brcmf_cfg80211_info *cfg); u64 brcmf_pno_find_reqid_by_bucket(struct brcmf_pno_info *pi, u32 bucket); /** - * brcmf_pno_get_bucket_map - determine bucket map for given netinfo. + * brcmf_pno_setup_for_version - setup our PNO handler for whatever version structures + * are supported by the chip * - * @pi: pno instance used. - * @netinfo: netinfo to compare with bucket configuration. + * @cfg: CFG to fill in. + * @vers: Version to use */ -u32 brcmf_pno_get_bucket_map(struct brcmf_pno_info *pi, - struct brcmf_pno_net_info_le *netinfo); +int brcmf_pno_setup_for_version(struct brcmf_pub *drvr, u8 vers); #endif /* _BRCMF_PNO_H */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/ratespec.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/ratespec.h new file mode 100644 index 00000000000000..37e722daab14d4 --- /dev/null +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/ratespec.h @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: ISC +/* + * Copyright (c) 2023 Daniel Berlin + */ + +#ifndef BRCMFMAC_RATESPEC_H +#define BRCMFMAC_RATESPEC_H +/* Rate spec. definitions */ +/* for BRCMF_RSPEC_ENCODING field >= BRCMF_RSPEC_ENCODING_HE, backward compatible */ + +/**< Legacy rate or MCS or MCS + NSS */ +#define BRCMF_RSPEC_RATE_MASK 0x000000FFu +/**< Tx chain expansion beyond Nsts */ +#define BRCMF_RSPEC_TXEXP_MASK 0x00000300u +#define BRCMF_RSPEC_TXEXP_SHIFT 8u +/* EHT GI indices */ +#define BRCMF_RSPEC_EHT_GI_MASK 0x00000C00u +#define BRCMF_RSPEC_EHT_GI_SHIFT 10u +/* HE GI indices */ +#define BRCMF_RSPEC_HE_GI_MASK 0x00000C00u +#define BRCMF_RSPEC_HE_GI_SHIFT 10u +/**< Range extension mask */ +#define BRCMF_RSPEC_ER_MASK 0x0000C000u +#define BRCMF_RSPEC_ER_SHIFT 14u +/**< Range extension tone config */ +#define BRCMF_RSPEC_ER_TONE_MASK 0x00004000u +#define BRCMF_RSPEC_ER_TONE_SHIFT 14u +/**< Range extension enable */ +#define BRCMF_RSPEC_ER_ENAB_MASK 0x00008000u +#define BRCMF_RSPEC_ER_ENAB_SHIFT 15u +/**< Bandwidth */ +#define BRCMF_RSPEC_BW_MASK 0x00070000u +#define BRCMF_RSPEC_BW_SHIFT 16u +/**< Dual Carrier Modulation */ +#define BRCMF_RSPEC_DCM 0x00080000u +#define BRCMF_RSPEC_DCM_SHIFT 19u +/**< STBC expansion, Nsts = 2 * Nss */ +#define BRCMF_RSPEC_STBC 0x00100000u +#define BRCMF_RSPEC_TXBF 0x00200000u +#define BRCMF_RSPEC_LDPC 0x00400000u +/* HT/VHT SGI indication */ +#define BRCMF_RSPEC_SGI 0x00800000u +/**< DSSS short preable - Encoding 0 */ +#define BRCMF_RSPEC_SHORT_PREAMBLE 0x00800000u +/**< Encoding of RSPEC_RATE field */ +#define BRCMF_RSPEC_ENCODING_MASK 0x07000000u +#define BRCMF_RSPEC_ENCODING_SHIFT 24u +#define BRCMF_RSPEC_OVERRIDE_RATE 0x40000000u /**< override rate only */ +#define BRCMF_RSPEC_OVERRIDE_MODE 0x80000000u /**< override both rate & mode */ + +/* ======== RSPEC_EHT_GI|RSPEC_SGI fields for EHT ======== */ +/* 11be Draft 0.4 Table 36-35:Common field for non-OFDMA transmission. + * Table 36-32 Common field for OFDMA transmission + */ +#define BRCMF_RSPEC_EHT_LTF_GI(rspec) \ + (((rspec) & BRCMF_RSPEC_EHT_GI_MASK) >> BRCMF_RSPEC_EHT_GI_SHIFT) +#define BRCMF_RSPEC_EHT_2x_LTF_GI_0_8us (0x0u) +#define BRCMF_RSPEC_EHT_2x_LTF_GI_1_6us (0x1u) +#define BRCMF_RSPEC_EHT_4x_LTF_GI_0_8us (0x2u) +#define BRCMF_RSPEC_EHT_4x_LTF_GI_3_2us (0x3u) +#define WL_EHT_GI_TO_RSPEC(gi) \ + ((u32)(((gi) << BRCMF_RSPEC_EHT_GI_SHIFT) & \ + BRCMF_RSPEC_EHT_GI_MASK)) +#define WL_EHT_GI_TO_RSPEC_SET(rspec, gi) \ + ((rspec & (~BRCMF_RSPEC_EHT_GI_MASK)) | WL_EHT_GI_TO_RSPEC(gi)) + +/* Macros for EHT LTF and GI */ +#define EHT_IS_2X_LTF(gi) \ + (((gi) == BRCMF_RSPEC_EHT_2x_LTF_GI_0_8us) || \ + ((gi) == BRCMF_RSPEC_EHT_2x_LTF_GI_1_6us)) +#define EHT_IS_4X_LTF(gi) \ + (((gi) == BRCMF_RSPEC_EHT_4x_LTF_GI_0_8us) || \ + ((gi) == BRCMF_RSPEC_EHT_4x_LTF_GI_3_2us)) + +#define EHT_IS_GI_0_8us(gi) \ + (((gi) == BRCMF_RSPEC_EHT_2x_LTF_GI_0_8us) || \ + ((gi) == BRCMF_RSPEC_EHT_4x_LTF_GI_0_8us)) +#define EHT_IS_GI_1_6us(gi) ((gi) == BRCMF_RSPEC_EHT_2x_LTF_GI_1_6us) +#define EHT_IS_GI_3_2us(gi) ((gi) == BRCMF_RSPEC_EHT_4x_LTF_GI_3_2us) + +/* ======== RSPEC_HE_GI|RSPEC_SGI fields for HE ======== */ + +/* GI for HE */ +#define BRCMF_RSPEC_HE_LTF_GI(rspec) \ + (((rspec) & BRCMF_RSPEC_HE_GI_MASK) >> BRCMF_RSPEC_HE_GI_SHIFT) +#define BRCMF_RSPEC_HE_1x_LTF_GI_0_8us (0x0u) +#define BRCMF_RSPEC_HE_2x_LTF_GI_0_8us (0x1u) +#define BRCMF_RSPEC_HE_2x_LTF_GI_1_6us (0x2u) +#define BRCMF_RSPEC_HE_4x_LTF_GI_3_2us (0x3u) +#define BRCMF_RSPEC_ISHEGI(rspec) \ + (RSPEC_HE_LTF_GI(rspec) > BRCMF_RSPEC_HE_1x_LTF_GI_0_8us) +#define HE_GI_TO_RSPEC(gi) \ + (((u32)(gi) << BRCMF_RSPEC_HE_GI_SHIFT) & BRCMF_RSPEC_HE_GI_MASK) +#define HE_GI_TO_RSPEC_SET(rspec, gi) \ + ((rspec & (~BRCMF_RSPEC_HE_GI_MASK)) | HE_GI_TO_RSPEC(gi)) + +/* Macros for HE LTF and GI */ +#define HE_IS_1X_LTF(gi) ((gi) == BRCMF_RSPEC_HE_1x_LTF_GI_0_8us) +#define HE_IS_2X_LTF(gi) \ + (((gi) == BRCMF_RSPEC_HE_2x_LTF_GI_0_8us) || \ + ((gi) == BRCMF_RSPEC_HE_2x_LTF_GI_1_6us)) +#define HE_IS_4X_LTF(gi) ((gi) == BRCMF_RSPEC_HE_4x_LTF_GI_3_2us) + +#define HE_IS_GI_0_8us(gi) \ + (((gi) == BRCMF_RSPEC_HE_1x_LTF_GI_0_8us) || \ + ((gi) == BRCMF_RSPEC_HE_2x_LTF_GI_0_8us)) +#define HE_IS_GI_1_6us(gi) ((gi) == BRCMF_RSPEC_HE_2x_LTF_GI_1_6us) +#define HE_IS_GI_3_2us(gi) ((gi) == BRCMF_RSPEC_HE_4x_LTF_GI_3_2us) + +/* RSPEC Macros for extracting and using HE-ER and DCM */ +#define BRCMF_RSPEC_HE_DCM(rspec) \ + (((rspec) & BRCMF_RSPEC_DCM) >> BRCMF_RSPEC_DCM_SHIFT) +#define BRCMF_RSPEC_HE_ER(rspec) \ + (((rspec) & BRCMF_RSPEC_ER_MASK) >> BRCMF_RSPEC_ER_SHIFT) +#define BRCMF_RSPEC_HE_ER_ENAB(rspec) \ + (((rspec) & BRCMF_RSPEC_ER_ENAB_MASK) >> BRCMF_RSPEC_ER_ENAB_SHIFT) +#define BRCMF_RSPEC_HE_ER_TONE(rspec) \ + (((rspec) & BRCMF_RSPEC_ER_TONE_MASK) >> BRCMF_RSPEC_ER_TONE_SHIFT) +/* ======== RSPEC_RATE field ======== */ + +/* Encoding 0 - legacy rate */ +/* DSSS, CCK, and OFDM rates in [500kbps] units */ +#define BRCMF_RSPEC_LEGACY_RATE_MASK 0x0000007F +#define WLC_RATE_1M 2 +#define WLC_RATE_2M 4 +#define WLC_RATE_5M5 11 +#define WLC_RATE_11M 22 +#define WLC_RATE_6M 12 +#define WLC_RATE_9M 18 +#define WLC_RATE_12M 24 +#define WLC_RATE_18M 36 +#define WLC_RATE_24M 48 +#define WLC_RATE_36M 72 +#define WLC_RATE_48M 96 +#define WLC_RATE_54M 108 + +/* Encoding 1 - HT MCS */ +/**< HT MCS value mask in rspec */ +#define BRCMF_RSPEC_HT_MCS_MASK 0x0000007F + +/* Encoding >= 2 */ +/* NSS & MCS values mask in rspec */ +#define BRCMF_RSPEC_NSS_MCS_MASK 0x000000FF +/* mimo MCS value mask in rspec */ +#define BRCMF_RSPEC_MCS_MASK 0x0000000F +/* mimo NSS value mask in rspec */ +#define BRCMF_RSPEC_NSS_MASK 0x000000F0 +/* mimo NSS value shift in rspec */ +#define BRCMF_RSPEC_NSS_SHIFT 4 + +/* Encoding 2 - VHT MCS + NSS */ +/**< VHT MCS value mask in rspec */ +#define BRCMF_RSPEC_VHT_MCS_MASK BRCMF_RSPEC_MCS_MASK +/**< VHT Nss value mask in rspec */ +#define BRCMF_RSPEC_VHT_NSS_MASK BRCMF_RSPEC_NSS_MASK +/**< VHT Nss value shift in rspec */ +#define BRCMF_RSPEC_VHT_NSS_SHIFT BRCMF_RSPEC_NSS_SHIFT + +/* Encoding 3 - HE MCS + NSS */ +/**< HE MCS value mask in rspec */ +#define BRCMF_RSPEC_HE_MCS_MASK BRCMF_RSPEC_MCS_MASK +/**< HE Nss value mask in rspec */ +#define BRCMF_RSPEC_HE_NSS_MASK BRCMF_RSPEC_NSS_MASK +/**< HE Nss value shift in rpsec */ +#define BRCMF_RSPEC_HE_NSS_SHIFT BRCMF_RSPEC_NSS_SHIFT + +#define BRCMF_RSPEC_HE_NSS_UNSPECIFIED 0xf + +/* Encoding 4 - EHT MCS + NSS */ +/**< EHT MCS value mask in rspec */ +#define BRCMF_RSPEC_EHT_MCS_MASK BRCMF_RSPEC_MCS_MASK +/**< EHT Nss value mask in rspec */ +#define BRCMF_RSPEC_EHT_NSS_MASK BRCMF_RSPEC_NSS_MASK +/**< EHT Nss value shift in rpsec */ +#define BRCMF_RSPEC_EHT_NSS_SHIFT BRCMF_RSPEC_NSS_SHIFT + +/* ======== RSPEC_BW field ======== */ + +#define BRCMF_RSPEC_BW_UNSPECIFIED 0u +#define BRCMF_RSPEC_BW_20MHZ 0x00010000u +#define BRCMF_RSPEC_BW_40MHZ 0x00020000u +#define BRCMF_RSPEC_BW_80MHZ 0x00030000u +#define BRCMF_RSPEC_BW_160MHZ 0x00040000u +#define BRCMF_RSPEC_BW_320MHZ 0x00060000u + +/* ======== RSPEC_ENCODING field ======== */ + +/* NOTE: Assuming the rate field is always NSS+MCS starting from VHT encoding! + * Modify/fix RSPEC_ISNSSMCS() macro if above condition changes any time. + */ +/**< Legacy rate is stored in RSPEC_RATE */ +#define BRCMF_RSPEC_ENCODE_RATE 0x00000000u +/**< HT MCS is stored in RSPEC_RATE */ +#define BRCMF_RSPEC_ENCODE_HT 0x01000000u +/**< VHT MCS and NSS are stored in RSPEC_RATE */ +#define BRCMF_RSPEC_ENCODE_VHT 0x02000000u +/**< HE MCS and NSS are stored in RSPEC_RATE */ +#define BRCMF_RSPEC_ENCODE_HE 0x03000000u +/**< EHT MCS and NSS are stored in RSPEC_RATE */ +#define BRCMF_RSPEC_ENCODE_EHT 0x04000000u + +/** + * =============================== + * Handy macros to parse rate spec + * =============================== + */ +#define BRCMF_RSPEC_BW(rspec) ((rspec) & BRCMF_RSPEC_BW_MASK) +#define BRCMF_RSPEC_IS20MHZ(rspec) (RSPEC_BW(rspec) == BRCMF_RSPEC_BW_20MHZ) +#define BRCMF_RSPEC_IS40MHZ(rspec) (RSPEC_BW(rspec) == BRCMF_RSPEC_BW_40MHZ) +#define BRCMF_RSPEC_IS80MHZ(rspec) (RSPEC_BW(rspec) == BRCMF_RSPEC_BW_80MHZ) +#define BRCMF_RSPEC_IS160MHZ(rspec) (RSPEC_BW(rspec) == BRCMF_RSPEC_BW_160MHZ) +#if defined(WL_BW320MHZ) +#define BRCMF_RSPEC_IS320MHZ(rspec) (RSPEC_BW(rspec) == BRCMF_RSPEC_BW_320MHZ) +#else +#define BRCMF_RSPEC_IS320MHZ(rspec) (FALSE) +#endif /* WL_BW320MHZ */ + +#define BRCMF_RSPEC_BW_GE(rspec, rspec_bw) (RSPEC_BW(rspec) >= rspec_bw) +#define BRCMF_RSPEC_BW_LE(rspec, rspec_bw) (RSPEC_BW(rspec) <= rspec_bw) +#define BRCMF_RSPEC_BW_GT(rspec, rspec_bw) (!RSPEC_BW_LE(rspec, rspec_bw)) +#define BRCMF_RSPEC_BW_LT(rspec, rspec_bw) (!RSPEC_BW_GE(rspec, rspec_bw)) + +#define BRCMF_RSPEC_ISSGI(rspec) (((rspec) & BRCMF_RSPEC_SGI) != 0) +#define BRCMF_RSPEC_ISLDPC(rspec) (((rspec) & BRCMF_RSPEC_LDPC) != 0) +#define BRCMF_RSPEC_ISSTBC(rspec) (((rspec) & BRCMF_RSPEC_STBC) != 0) +#define BRCMF_RSPEC_ISTXBF(rspec) (((rspec) & BRCMF_RSPEC_TXBF) != 0) + +#define BRCMF_RSPEC_TXEXP(rspec) \ + (((rspec) & BRCMF_RSPEC_TXEXP_MASK) >> BRCMF_RSPEC_TXEXP_SHIFT) + +#define BRCMF_RSPEC_ENCODE(rspec) \ + (((rspec) & BRCMF_RSPEC_ENCODING_MASK) >> BRCMF_RSPEC_ENCODING_SHIFT) +#define BRCMF_RSPEC_ISLEGACY(rspec) \ + (((rspec) & BRCMF_RSPEC_ENCODING_MASK) == BRCMF_RSPEC_ENCODE_RATE) + +#define BRCMF_RSPEC_ISHT(rspec) \ + (((rspec) & BRCMF_RSPEC_ENCODING_MASK) == BRCMF_RSPEC_ENCODE_HT) +#define BRCMF_RSPEC_ISVHT(rspec) \ + (((rspec) & BRCMF_RSPEC_ENCODING_MASK) == BRCMF_RSPEC_ENCODE_VHT) +#define BRCMF_RSPEC_ISHE(rspec) \ + (((rspec) & BRCMF_RSPEC_ENCODING_MASK) == BRCMF_RSPEC_ENCODE_HE) +#define BRCMF_RSPEC_ISEHT(rspec) \ + (((rspec) & BRCMF_RSPEC_ENCODING_MASK) == BRCMF_RSPEC_ENCODE_EHT) + +/* fast check if rate field is NSS+MCS format (starting from VHT ratespec) */ +#define BRCMF_RSPEC_ISVHTEXT(rspec) \ + (((rspec) & BRCMF_RSPEC_ENCODING_MASK) >= BRCMF_RSPEC_ENCODE_VHT) +/* fast check if rate field is NSS+MCS format (starting from HE ratespec) */ +#define BRCMF_RSPEC_ISHEEXT(rspec) \ + (((rspec) & BRCMF_RSPEC_ENCODING_MASK) >= BRCMF_RSPEC_ENCODE_HE) + +#endif /* BRCMFMAC_RATESPEC_H */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/scan_param.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/scan_param.c new file mode 100644 index 00000000000000..4f634509d25256 --- /dev/null +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/scan_param.c @@ -0,0 +1,446 @@ +// SPDX-License-Identifier: ISC +/* + * Copyright (c) 2023 Daniel Berlin + */ +#include +#include + +#include "core.h" +#include "debug.h" +#include "fwil_types.h" +#include "cfg80211.h" +#include "scan_param.h" + +static void brcmf_scan_param_set_defaults(u8 (*bssid)[ETH_ALEN], s8 *bss_type, __le32 *channel_num, + __le32 *nprobes, __le32 *active_time, + __le32 *passive_time, + __le32 *home_time) +{ + eth_broadcast_addr(*bssid); + *bss_type = DOT11_BSSTYPE_ANY; + *channel_num = 0; + *nprobes = cpu_to_le32(-1); + *active_time = cpu_to_le32(-1); + *passive_time = cpu_to_le32(-1); + *home_time = cpu_to_le32(-1); +} + +static void brcmf_scan_param_copy_chanspecs( + struct brcmf_cfg80211_info *cfg, __le16 (*dest_channels)[], + struct ieee80211_channel **in_channels, u32 n_channels) +{ + int i; + for (i = 0; i < n_channels; i++) { + u32 chanspec = + channel_to_chanspec(&cfg->d11inf, in_channels[i]); + brcmf_dbg(SCAN, "Chan : %d, Channel spec: %x\n", + in_channels[i]->hw_value, chanspec); + (*dest_channels)[i] = cpu_to_le16(chanspec); + } +} + +static void brcmf_scan_param_copy_ssids(char *dest_ssids, + struct cfg80211_ssid *in_ssids, + u32 n_ssids) +{ + int i; + for (i = 0; i < n_ssids; i++) { + struct brcmf_ssid_le ssid_le; + memset(&ssid_le, 0, sizeof(ssid_le)); + ssid_le.SSID_len = cpu_to_le32(in_ssids[i].ssid_len); + memcpy(ssid_le.SSID, in_ssids[i].ssid, in_ssids[i].ssid_len); + if (!ssid_le.SSID_len) + brcmf_dbg(SCAN, "%d: Broadcast scan\n", i); + else + brcmf_dbg(SCAN, "%d: scan for %.32s size=%d\n", i, + ssid_le.SSID, ssid_le.SSID_len); + memcpy(dest_ssids, &ssid_le, sizeof(ssid_le)); + dest_ssids += sizeof(ssid_le); + } +} + +/* The scan parameter structures have an array of SSID's that appears at the end in some cases. + * In these cases, the chan list is really the lower half of a pair, the upper half is a ssid number, + * and then after all of that there is an array of SSIDs */ +static u32 +brcmf_scan_param_tail_size(const struct cfg80211_scan_request *request, + u32 params_size) +{ + if (request != NULL) { + /* Allocate space for populating ssid upper half in struct */ + params_size += sizeof(u32) * ((request->n_channels + 1) / 2); + /* Allocate space for populating ssids in struct */ + params_size += sizeof(struct brcmf_ssid_le) * request->n_ssids; + } else { + params_size += sizeof(u16); + } + return params_size; +} + +static u32 brcmf_nl80211_scan_flags_to_scan_flags(u32 nl80211_flags) +{ + u32 scan_flags = 0; + if (nl80211_flags & NL80211_SCAN_FLAG_LOW_SPAN) { + scan_flags |= BRCMF_SCANFLAGS_LOW_SPAN; + brcmf_dbg(SCAN, "requested low span scan\n"); + } + if (nl80211_flags & NL80211_SCAN_FLAG_HIGH_ACCURACY) { + scan_flags |= BRCMF_SCANFLAGS_HIGH_ACCURACY; + brcmf_dbg(SCAN, "requested high accuracy scan\n"); + } + if (nl80211_flags & NL80211_SCAN_FLAG_LOW_POWER) { + scan_flags |= BRCMF_SCANFLAGS_LOW_POWER; + brcmf_dbg(SCAN, "requested low power scan\n"); + } + if (nl80211_flags & NL80211_SCAN_FLAG_LOW_PRIORITY) { + scan_flags |= BRCMF_SCANFLAGS_LOW_PRIO; + brcmf_dbg(SCAN, "requested low priority scan\n"); + } + return scan_flags; +} + +static void * +brcmf_scan_param_get_prepped_struct_v1(struct brcmf_cfg80211_info *cfg, + u32 *struct_size, + struct cfg80211_scan_request *request) +{ + u32 n_ssids; + u32 n_channels; + u32 params_size = sizeof(struct brcmf_scan_params_le); + u32 length; + struct brcmf_scan_params_le *params_le = NULL; + u8 scan_type = BRCMF_SCANTYPE_ACTIVE; + + length = offsetof(struct brcmf_scan_params_le, channel_list); + params_size = brcmf_scan_param_tail_size(request, params_size); + params_le = kzalloc(params_size, GFP_KERNEL); + if (!params_le) { + bphy_err(cfg, "Could not allocate scan params\n"); + return NULL; + } + brcmf_scan_param_set_defaults(¶ms_le->bssid, + ¶ms_le->bss_type, ¶ms_le->channel_num, + ¶ms_le->nprobes, ¶ms_le->active_time, + ¶ms_le->passive_time, ¶ms_le->home_time); + + /* Scan abort */ + if (!request) { + params_le->channel_num = cpu_to_le32(1); + params_le->channel_list[0] = cpu_to_le16(-1); + goto done; + } + + n_ssids = request->n_ssids; + n_channels = request->n_channels; + + /* Copy channel array if applicable */ + brcmf_dbg(SCAN, "### List of channelspecs to scan ### %d\n", + n_channels); + if (n_channels > 0) { + length += roundup(sizeof(u16) * n_channels, sizeof(u32)); + brcmf_scan_param_copy_chanspecs(cfg, ¶ms_le->channel_list, + request->channels, n_channels); + } else { + brcmf_dbg(SCAN, "Scanning all channels\n"); + } + + /* Copy ssid array if applicable */ + brcmf_dbg(SCAN, "### List of SSIDs to scan ### %d\n", n_ssids); + if (n_ssids > 0) { + s32 offset; + char *ptr; + + offset = + offsetof(struct brcmf_scan_params_le, channel_list) + + n_channels * sizeof(u16); + offset = roundup(offset, sizeof(u32)); + length += sizeof(struct brcmf_ssid_le) * n_ssids; + ptr = (char *)params_le + offset; + brcmf_scan_param_copy_ssids(ptr, request->ssids, n_ssids); + } else { + brcmf_dbg(SCAN, "Performing passive scan\n"); + scan_type = BRCMF_SCANTYPE_PASSIVE; + } + scan_type |= brcmf_nl80211_scan_flags_to_scan_flags(request->flags); + params_le->scan_type =scan_type; + /* Adding mask to channel numbers */ + params_le->channel_num = + cpu_to_le32((n_ssids << BRCMF_SCAN_PARAMS_NSSID_SHIFT) | + (n_channels & BRCMF_SCAN_PARAMS_COUNT_MASK)); +done: + *struct_size = length; + return params_le; +} + +static void * +brcmf_scan_param_get_prepped_struct_v2(struct brcmf_cfg80211_info *cfg, + u32 *struct_size, + struct cfg80211_scan_request *request) +{ + u32 n_ssids; + u32 n_channels; + u32 params_size = sizeof(struct brcmf_scan_params_v2_le); + u32 length; + struct brcmf_scan_params_v2_le *params_le = NULL; + u32 scan_type = BRCMF_SCANTYPE_ACTIVE; + + length = offsetof(struct brcmf_scan_params_v2_le, channel_list); + params_size = brcmf_scan_param_tail_size(request, params_size); + params_le = kzalloc(params_size, GFP_KERNEL); + if (!params_le) { + bphy_err(cfg, "Could not allocate scan params\n"); + return NULL; + } + params_le->version = cpu_to_le16(BRCMF_SCAN_PARAMS_VERSION_V2); + brcmf_scan_param_set_defaults(¶ms_le->bssid, + ¶ms_le->bss_type, ¶ms_le->channel_num, + ¶ms_le->nprobes, ¶ms_le->active_time, + ¶ms_le->passive_time, ¶ms_le->home_time); + + /* Scan abort */ + if (!request) { + length += sizeof(u16); + params_le->channel_num = cpu_to_le32(1); + params_le->channel_list[0] = cpu_to_le16(-1); + params_le->length = cpu_to_le16(length); + goto done; + } + + n_ssids = request->n_ssids; + n_channels = request->n_channels; + + /* Copy channel array if applicable */ + brcmf_dbg(SCAN, "### List of channelspecs to scan ### %d\n", + n_channels); + if (n_channels > 0) { + length += roundup(sizeof(u16) * n_channels, sizeof(u32)); + brcmf_scan_param_copy_chanspecs(cfg, ¶ms_le->channel_list, + request->channels, n_channels); + } else { + brcmf_dbg(SCAN, "Scanning all channels\n"); + } + + /* Copy ssid array if applicable */ + brcmf_dbg(SCAN, "### List of SSIDs to scan ### %d\n", n_ssids); + if (n_ssids > 0) { + s32 offset; + char *ptr; + + offset = + offsetof(struct brcmf_scan_params_v2_le, channel_list) + + n_channels * sizeof(u16); + offset = roundup(offset, sizeof(u32)); + length += sizeof(struct brcmf_ssid_le) * n_ssids; + ptr = (char *)params_le + offset; + brcmf_scan_param_copy_ssids(ptr, request->ssids, n_ssids); + + } else { + brcmf_dbg(SCAN, "Performing passive scan\n"); + scan_type = BRCMF_SCANTYPE_PASSIVE; + } + scan_type |= brcmf_nl80211_scan_flags_to_scan_flags(request->flags); + params_le->scan_type = cpu_to_le32(scan_type); + params_le->length = cpu_to_le16(length); + /* Adding mask to channel numbers */ + params_le->channel_num = + cpu_to_le32((n_ssids << BRCMF_SCAN_PARAMS_NSSID_SHIFT) | + (n_channels & BRCMF_SCAN_PARAMS_COUNT_MASK)); +done: + *struct_size = length; + return params_le; +} + +static void * +brcmf_scan_param_get_prepped_struct_v3(struct brcmf_cfg80211_info *cfg, + u32 *struct_size, + struct cfg80211_scan_request *request) +{ + u32 n_ssids; + u32 n_channels; + u32 params_size = sizeof(struct brcmf_scan_params_v3_le); + u32 length; + struct brcmf_scan_params_v3_le *params_le = NULL; + u32 scan_type = BRCMF_SCANTYPE_ACTIVE; + + length = offsetof(struct brcmf_scan_params_v3_le, channel_list); + params_size = brcmf_scan_param_tail_size(request, params_size); + params_le = kzalloc(params_size, GFP_KERNEL); + if (!params_le) { + bphy_err(cfg, "Could not allocate scan params\n"); + return NULL; + } + + params_le->version = cpu_to_le16(BRCMF_SCAN_PARAMS_VERSION_V3); + params_le->ssid_type = 0; + brcmf_scan_param_set_defaults(¶ms_le->bssid, + ¶ms_le->bss_type, ¶ms_le->channel_num, + ¶ms_le->nprobes, ¶ms_le->active_time, + ¶ms_le->passive_time, ¶ms_le->home_time); + + /* Scan abort */ + if (!request) { + length += sizeof(u16); + params_le->channel_num = cpu_to_le32(1); + params_le->channel_list[0] = cpu_to_le16(-1); + params_le->length = cpu_to_le16(length); + goto done; + } + + n_ssids = request->n_ssids; + n_channels = request->n_channels; + + /* Copy channel array if applicable */ + brcmf_dbg(SCAN, "### List of channelspecs to scan ### %d\n", + n_channels); + if (n_channels > 0) { + length += roundup(sizeof(u16) * n_channels, sizeof(u32)); + brcmf_scan_param_copy_chanspecs(cfg, ¶ms_le->channel_list, + request->channels, n_channels); + + } else { + brcmf_dbg(SCAN, "Scanning all channels\n"); + } + + /* Copy ssid array if applicable */ + brcmf_dbg(SCAN, "### List of SSIDs to scan ### %d\n", n_ssids); + if (n_ssids > 0) { + s32 offset; + char *ptr; + + offset = + offsetof(struct brcmf_scan_params_v3_le, channel_list) + + n_channels * sizeof(u16); + offset = roundup(offset, sizeof(u32)); + length += sizeof(struct brcmf_ssid_le) * n_ssids; + ptr = (char *)params_le + offset; + brcmf_scan_param_copy_ssids(ptr, request->ssids, n_ssids); + + } else { + brcmf_dbg(SCAN, "Performing passive scan\n"); + scan_type = BRCMF_SCANTYPE_PASSIVE; + } + scan_type |= brcmf_nl80211_scan_flags_to_scan_flags(request->flags); + params_le->scan_type = cpu_to_le32(scan_type); + params_le->length = cpu_to_le16(length); + params_le->channel_num = + cpu_to_le32((n_ssids << BRCMF_SCAN_PARAMS_NSSID_SHIFT) | + (n_channels & BRCMF_SCAN_PARAMS_COUNT_MASK)); + + /* Include RNR results if requested */ + if (request->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ) { + params_le->ssid_type |= BRCMF_SCANSSID_INC_RNR; + } + /* Adding mask to channel numbers */ +done: + *struct_size = length; + return params_le; +} + +static void * +brcmf_scan_param_get_prepped_struct_v4(struct brcmf_cfg80211_info *cfg, + u32 *struct_size, + struct cfg80211_scan_request *request) +{ + u32 n_ssids; + u32 n_channels; + u32 params_size = sizeof(struct brcmf_scan_params_v4_le); + u32 length; + struct brcmf_scan_params_v4_le *params_le = NULL; + u32 scan_type = BRCMF_SCANTYPE_ACTIVE; + + length = offsetof(struct brcmf_scan_params_v4_le, channel_list); + params_size = brcmf_scan_param_tail_size(request, params_size); + params_le = kzalloc(params_size, GFP_KERNEL); + if (!params_le) { + bphy_err(cfg, "Could not allocate scan params\n"); + return NULL; + } + params_le->version = cpu_to_le16(BRCMF_SCAN_PARAMS_VERSION_V4); + params_le->ssid_type = 0; + brcmf_scan_param_set_defaults(¶ms_le->bssid, + ¶ms_le->bss_type, ¶ms_le->channel_num, + ¶ms_le->nprobes, ¶ms_le->active_time, + ¶ms_le->passive_time, ¶ms_le->home_time); + + /* Scan abort */ + if (!request) { + length += sizeof(u16); + params_le->channel_num = cpu_to_le32(1); + params_le->channel_list[0] = cpu_to_le16(-1); + params_le->length = cpu_to_le16(length); + goto done; + } + + n_ssids = request->n_ssids; + n_channels = request->n_channels; + + /* Copy channel array if applicable */ + brcmf_dbg(SCAN, "### List of channelspecs to scan ### %d\n", + n_channels); + if (n_channels > 0) { + length += roundup(sizeof(u16) * n_channels, sizeof(u32)); + brcmf_scan_param_copy_chanspecs(cfg, ¶ms_le->channel_list, + request->channels, n_channels); + } else { + brcmf_dbg(SCAN, "Scanning all channels\n"); + } + + /* Copy ssid array if applicable */ + brcmf_dbg(SCAN, "### List of SSIDs to scan ### %d\n", n_ssids); + if (n_ssids > 0) { + s32 offset; + char *ptr; + + offset = + offsetof(struct brcmf_scan_params_v4_le, channel_list) + + n_channels * sizeof(u16); + offset = roundup(offset, sizeof(u32)); + length += sizeof(struct brcmf_ssid_le) * n_ssids; + ptr = (char *)params_le + offset; + brcmf_scan_param_copy_ssids(ptr, request->ssids, n_ssids); + } else { + brcmf_dbg(SCAN, "Performing passive scan\n"); + scan_type = BRCMF_SCANTYPE_PASSIVE; + } + scan_type |= brcmf_nl80211_scan_flags_to_scan_flags(request->flags); + params_le->scan_type = cpu_to_le32(scan_type); + params_le->length = cpu_to_le16(length); + /* Adding mask to channel numbers */ + params_le->channel_num = + cpu_to_le32((n_ssids << BRCMF_SCAN_PARAMS_NSSID_SHIFT) | + (n_channels & BRCMF_SCAN_PARAMS_COUNT_MASK)); + /* Include RNR results if requested */ + if (request->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ) { + params_le->ssid_type |= BRCMF_SCANSSID_INC_RNR; + } +done: + *struct_size = length; + return params_le; +} + +int brcmf_scan_param_setup_for_version(struct brcmf_pub *drvr, u8 version) +{ + drvr->scan_param_handler.version = version; + switch (version) { + case 1: { + drvr->scan_param_handler.get_struct_for_request = + brcmf_scan_param_get_prepped_struct_v1; + } break; + case 2: { + drvr->scan_param_handler.get_struct_for_request = + brcmf_scan_param_get_prepped_struct_v2; + } break; + case 3: { + drvr->scan_param_handler.get_struct_for_request = + brcmf_scan_param_get_prepped_struct_v3; + } break; + case 4: { + drvr->scan_param_handler.get_struct_for_request = + brcmf_scan_param_get_prepped_struct_v4; + + } break; + default: + return -EINVAL; + } + return 0; +} diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/scan_param.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/scan_param.h new file mode 100644 index 00000000000000..577de083c6e3cd --- /dev/null +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/scan_param.h @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: ISC +/* + * Copyright (c) 2023 Daniel Berlin + */ + +#ifndef _BRCMF_SCAN_PARAM_H +#define _BRCMF_SCAN_PARAM_H + +struct brcmf_pub; + +/** + * brcmf_scan_param_setup_for_version() - Setup the driver to handle join structures + * + * There are a number of different structures and interface versions for scanning info + * This sets up the driver to handle a particular interface version. + * + * @drvr Driver structure to setup + * @ver Interface version + * Return: %0 if okay, error code otherwise + */ +int brcmf_scan_param_setup_for_version(struct brcmf_pub *, u8 ver); +#endif /* _BRCMF_SCAN_PARAM_H */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmutil/d11.c b/drivers/net/wireless/broadcom/brcm80211/brcmutil/d11.c index 1e2b1e487eb76e..faf7eeeeb2d57e 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmutil/d11.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmutil/d11.c @@ -87,10 +87,20 @@ static void brcmu_d11ac_encchspec(struct brcmu_chan *ch) 0, d11ac_bw(ch->bw)); ch->chspec &= ~BRCMU_CHSPEC_D11AC_BND_MASK; - if (ch->chnum <= CH_MAX_2G_CHANNEL) - ch->chspec |= BRCMU_CHSPEC_D11AC_BND_2G; - else + switch (ch->band) { + case BRCMU_CHAN_BAND_6G: + ch->chspec |= BRCMU_CHSPEC_D11AC_BND_6G; + break; + case BRCMU_CHAN_BAND_5G: ch->chspec |= BRCMU_CHSPEC_D11AC_BND_5G; + break; + case BRCMU_CHAN_BAND_2G: + ch->chspec |= BRCMU_CHSPEC_D11AC_BND_2G; + break; + default: + WARN_ONCE(1, "Invalid band 0x%04x\n", ch->band); + break; + } } static void brcmu_d11n_decchspec(struct brcmu_chan *ch) @@ -117,7 +127,9 @@ static void brcmu_d11n_decchspec(struct brcmu_chan *ch) } break; default: - WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec); + WARN_ONCE(1, + "Invalid chanspec - unknown 11n bandwidth 0x%04x\n", + ch->chspec); break; } @@ -129,7 +141,8 @@ static void brcmu_d11n_decchspec(struct brcmu_chan *ch) ch->band = BRCMU_CHAN_BAND_2G; break; default: - WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec); + WARN_ONCE(1, "Invalid chanspec - unknown 11n band 0x%04x\n", + ch->chspec); break; } } @@ -156,7 +169,9 @@ static void brcmu_d11ac_decchspec(struct brcmu_chan *ch) ch->sb = BRCMU_CHAN_SB_U; ch->control_ch_num += CH_10MHZ_APART; } else { - WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec); + WARN_ONCE(1, + "Invalid chanspec - unknown 11ac channel distance 0x%04x\n", + ch->chspec); } break; case BRCMU_CHSPEC_D11AC_BW_80: @@ -177,7 +192,9 @@ static void brcmu_d11ac_decchspec(struct brcmu_chan *ch) ch->control_ch_num += CH_30MHZ_APART; break; default: - WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec); + WARN_ONCE(1, + "Invalid chanspec - unknown 11ac channel distance 0x%04x\n", + ch->chspec); break; } break; @@ -211,17 +228,24 @@ static void brcmu_d11ac_decchspec(struct brcmu_chan *ch) ch->control_ch_num += CH_70MHZ_APART; break; default: - WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec); + WARN_ONCE(1, + "Invalid chanspec - unknown 11ac channel distance 0x%04x\n", + ch->chspec); break; } break; case BRCMU_CHSPEC_D11AC_BW_8080: default: - WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec); + WARN_ONCE(1, + "Invalid chanspec - unknown 11ac channel bandwidth 0x%04x\n", + ch->chspec); break; } switch (ch->chspec & BRCMU_CHSPEC_D11AC_BND_MASK) { + case BRCMU_CHSPEC_D11AC_BND_6G: + ch->band = BRCMU_CHAN_BAND_6G; + break; case BRCMU_CHSPEC_D11AC_BND_5G: ch->band = BRCMU_CHAN_BAND_5G; break; @@ -229,7 +253,9 @@ static void brcmu_d11ac_decchspec(struct brcmu_chan *ch) ch->band = BRCMU_CHAN_BAND_2G; break; default: - WARN_ONCE(1, "Invalid chanspec 0x%04x\n", ch->chspec); + WARN_ONCE(1, + "Invalid chanspec - unknown 11ac channel band 0x%04x\n", + ch->chspec); break; } } diff --git a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h index df3b67ba4db290..f749337a06942e 100644 --- a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h +++ b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h @@ -57,6 +57,7 @@ #define BRCM_CC_4377_CHIP_ID 0x4377 #define BRCM_CC_4378_CHIP_ID 0x4378 #define BRCM_CC_4387_CHIP_ID 0x4387 +#define BRCM_CC_4388_CHIP_ID 0x4388 #define CY_CC_4373_CHIP_ID 0x4373 #define CY_CC_43012_CHIP_ID 43012 #define CY_CC_43439_CHIP_ID 43439 @@ -99,6 +100,7 @@ #define BRCM_PCIE_4377_DEVICE_ID 0x4488 #define BRCM_PCIE_4378_DEVICE_ID 0x4425 #define BRCM_PCIE_4387_DEVICE_ID 0x4433 +#define BRCM_PCIE_4388_DEVICE_ID 0x4434 #define CY_PCIE_54591_DEVICE_ID 0x4417 /* brcmsmac IDs */ diff --git a/drivers/net/wireless/broadcom/brcm80211/include/brcmu_d11.h b/drivers/net/wireless/broadcom/brcm80211/include/brcmu_d11.h index f6344023855c36..bb48b744206223 100644 --- a/drivers/net/wireless/broadcom/brcm80211/include/brcmu_d11.h +++ b/drivers/net/wireless/broadcom/brcm80211/include/brcmu_d11.h @@ -69,24 +69,44 @@ #define BRCMU_CHSPEC_D11AC_SB_UU BRCMU_CHSPEC_D11AC_SB_LUU #define BRCMU_CHSPEC_D11AC_SB_L BRCMU_CHSPEC_D11AC_SB_LLL #define BRCMU_CHSPEC_D11AC_SB_U BRCMU_CHSPEC_D11AC_SB_LLU +/* channel sideband indication for frequency >= 240MHz */ +#define BRCMU_CHSPEC_D11AC_320_SB_MASK 0x0780 +#define BRCMU_CHSPEC_D11AC_320_SB_SHIFT 7 +#define BRCMU_CHSPEC_D11AC_SB_LLLL 0x0000 +#define BRCMU_CHSPEC_D11AC_SB_LLLU 0x0080 +#define BRCMU_CHSPEC_D11AC_SB_LLUL 0x0100 +#define BRCMU_CHSPEC_D11AC_SB_LLUU 0x0180 +#define BRCMU_CHSPEC_D11AC_SB_LULL 0x0200 +#define BRCMU_CHSPEC_D11AC_SB_LULU 0x0280 +#define BRCMU_CHSPEC_D11AC_SB_LUUL 0x0300 +#define BRCMU_CHSPEC_D11AC_SB_LUUU 0x0380 +#define BRCMU_CHSPEC_D11AC_SB_ULLL 0x0400 +#define BRCMU_CHSPEC_D11AC_SB_ULLU 0x0480 +#define BRCMU_CHSPEC_D11AC_SB_ULUL 0x0500 +#define BRCMU_CHSPEC_D11AC_SB_ULUU 0x0580 +#define BRCMU_CHSPEC_D11AC_SB_UULL 0x0600 +#define BRCMU_CHSPEC_D11AC_SB_UULU 0x0680 +#define BRCMU_CHSPEC_D11AC_SB_UUUL 0x0700 +#define BRCMU_CHSPEC_D11AC_SB_UUUU 0x0780 #define BRCMU_CHSPEC_D11AC_BW_MASK 0x3800 #define BRCMU_CHSPEC_D11AC_BW_SHIFT 11 -#define BRCMU_CHSPEC_D11AC_BW_5 0x0000 -#define BRCMU_CHSPEC_D11AC_BW_10 0x0800 -#define BRCMU_CHSPEC_D11AC_BW_20 0x1000 -#define BRCMU_CHSPEC_D11AC_BW_40 0x1800 -#define BRCMU_CHSPEC_D11AC_BW_80 0x2000 -#define BRCMU_CHSPEC_D11AC_BW_160 0x2800 -#define BRCMU_CHSPEC_D11AC_BW_8080 0x3000 -#define BRCMU_CHSPEC_D11AC_BND_MASK 0xc000 -#define BRCMU_CHSPEC_D11AC_BND_SHIFT 14 -#define BRCMU_CHSPEC_D11AC_BND_2G 0x0000 -#define BRCMU_CHSPEC_D11AC_BND_3G 0x4000 -#define BRCMU_CHSPEC_D11AC_BND_4G 0x8000 -#define BRCMU_CHSPEC_D11AC_BND_5G 0xc000 +#define BRCMU_CHSPEC_D11AC_BW_10 0x0800 +#define BRCMU_CHSPEC_D11AC_BW_20 0x1000 +#define BRCMU_CHSPEC_D11AC_BW_40 0x1800 +#define BRCMU_CHSPEC_D11AC_BW_80 0x2000 +#define BRCMU_CHSPEC_D11AC_BW_160 0x2800 +#define BRCMU_CHSPEC_D11AC_BW_320 0x0000 +#define BRCMU_CHSPEC_D11AC_BW_8080 0x3000 +#define BRCMU_CHSPEC_D11AC_BND_MASK 0xc000 +#define BRCMU_CHSPEC_D11AC_BND_SHIFT 14 +#define BRCMU_CHSPEC_D11AC_BND_2G 0x0000 +#define BRCMU_CHSPEC_D11AC_BND_4G 0x8000 +#define BRCMU_CHSPEC_D11AC_BND_5G 0xc000 +#define BRCMU_CHSPEC_D11AC_BND_6G 0x4000 #define BRCMU_CHAN_BAND_2G 0 #define BRCMU_CHAN_BAND_5G 1 +#define BRCMU_CHAN_BAND_6G 2 enum brcmu_chan_bw { BRCMU_CHAN_BW_20, diff --git a/drivers/net/wireless/broadcom/brcm80211/include/brcmu_wifi.h b/drivers/net/wireless/broadcom/brcm80211/include/brcmu_wifi.h index 7552bdb91991ce..ef042beeb586f9 100644 --- a/drivers/net/wireless/broadcom/brcm80211/include/brcmu_wifi.h +++ b/drivers/net/wireless/broadcom/brcm80211/include/brcmu_wifi.h @@ -31,6 +31,7 @@ /* bandstate array indices */ #define BAND_2G_INDEX 0 /* wlc->bandstate[x] index */ #define BAND_5G_INDEX 1 /* wlc->bandstate[x] index */ +#define BAND_6G_INDEX 2 /* wlc->bandstate[x] index */ /* * max # supported channels. The max channel no is 216, this is that + 1 @@ -48,17 +49,22 @@ #define WL_CHANSPEC_CTL_SB_UPPER 0x0200 #define WL_CHANSPEC_CTL_SB_NONE 0x0300 -#define WL_CHANSPEC_BW_MASK 0x0C00 -#define WL_CHANSPEC_BW_SHIFT 10 +#define WL_CHANSPEC_BW_MASK 0x3800 +#define WL_CHANSPEC_BW_SHIFT 11 #define WL_CHANSPEC_BW_10 0x0400 #define WL_CHANSPEC_BW_20 0x0800 #define WL_CHANSPEC_BW_40 0x0C00 #define WL_CHANSPEC_BW_80 0x2000 - -#define WL_CHANSPEC_BAND_MASK 0xf000 -#define WL_CHANSPEC_BAND_SHIFT 12 -#define WL_CHANSPEC_BAND_5G 0x1000 -#define WL_CHANSPEC_BAND_2G 0x2000 +#define WL_CHANSPEC_BW_160 0x2800 +#define WL_CHANSPEC_BW_8080 0x3000 +#define WL_CHANSPEC_BW_320 0x0000 + +#define WL_CHANSPEC_BAND_MASK 0xc000 +#define WL_CHANSPEC_BAND_SHIFT 14 +#define WL_CHANSPEC_BAND_2G 0x0000 +#define WL_CHANSPEC_BAND_4G 0x8000 +#define WL_CHANSPEC_BAND_5G 0xc000 +#define WL_CHANSPEC_BAND_6G 0x4000 #define INVCHANSPEC 255 #define WL_CHAN_VALID_HW (1 << 0) /* valid with current HW */ @@ -93,6 +99,9 @@ #define WLC_BAND_5G 1 /* 5 Ghz */ #define WLC_BAND_2G 2 /* 2.4 Ghz */ #define WLC_BAND_ALL 3 /* all bands */ +#define WLC_BAND_6G 4 /* 6 Ghz */ + +#define WLC_AP_IOV_OP_MANUAL_AP_BSSCFG_CREATE 2 #define CHSPEC_CHANNEL(chspec) ((u8)((chspec) & WL_CHANSPEC_CHAN_MASK)) #define CHSPEC_BAND(chspec) ((chspec) & WL_CHANSPEC_BAND_MASK) @@ -112,6 +121,12 @@ #define CHSPEC_IS80(chspec) \ (((chspec) & WL_CHANSPEC_BW_MASK) == WL_CHANSPEC_BW_80) +#define CHSPEC_IS160(chspec) \ + (((chspec) & WL_CHANSPEC_BW_MASK) == WL_CHANSPEC_BW_160) + +#define CHSPEC_IS6G(chspec) \ + (((chspec) & WL_CHANSPEC_BAND_MASK) == WL_CHANSPEC_BAND_6G) + #define CHSPEC_IS5G(chspec) \ (((chspec) & WL_CHANSPEC_BAND_MASK) == WL_CHANSPEC_BAND_5G) @@ -200,6 +215,13 @@ static inline bool ac_bitmap_tst(u8 bitmap, int prec) #define CRYPTO_ALGO_AES_RESERVED1 5 #define CRYPTO_ALGO_AES_RESERVED2 6 #define CRYPTO_ALGO_NALG 7 +#define CRYPTO_ALGO_AES_GCM 14 /* 128 bit GCM */ +#define CRYPTO_ALGO_AES_CCM256 15 /* 256 bit CCM */ +#define CRYPTO_ALGO_AES_GCM256 16 /* 256 bit GCM */ +#define CRYPTO_ALGO_BIP_CMAC256 17 /* 256 bit BIP CMAC */ +#define CRYPTO_ALGO_BIP_GMAC 18 /* 128 bit BIP GMAC */ +#define CRYPTO_ALGO_BIP_GMAC256 19 /* 256 bit BIP GMAC */ + /* wireless security bitvec */ @@ -232,6 +254,13 @@ static inline bool ac_bitmap_tst(u8 bitmap, int prec) #define WPA2_AUTH_PSK_SHA256 0x8000 /* PSK with SHA256 key derivation */ #define WPA3_AUTH_SAE_PSK 0x40000 /* SAE with 4-way handshake */ +#define WPA3_AUTH_OWE 0x100000 /* OWE */ +#define WFA_AUTH_DPP 0x200000 /* WFA DPP AUTH */ +#define WPA3_AUTH_1X_SUITE_B_SHA384 0x400000 /* Suite B-192 SHA384 */ + + +#define WFA_OUI "\x50\x6F\x9A" /* WFA OUI */ +#define DPP_VER 0x1A /* WFA DPP v1.0 */ #define DOT11_DEFAULT_RTS_LEN 2347 #define DOT11_DEFAULT_FRAG_LEN 2346 diff --git a/drivers/net/wireless/broadcom/brcm80211/include/chipcommon.h b/drivers/net/wireless/broadcom/brcm80211/include/chipcommon.h index 0340bba968688f..5c3b8fb41194ae 100644 --- a/drivers/net/wireless/broadcom/brcm80211/include/chipcommon.h +++ b/drivers/net/wireless/broadcom/brcm80211/include/chipcommon.h @@ -302,6 +302,14 @@ struct chipcregs { #define PMU_RCTL_LOGIC_DISABLE_MASK (1 << 27) +/* watchdog */ +#define CC_WD_SSRESET_PCIE_F0_EN 0x10000000 +#define CC_WD_SSRESET_PCIE_F1_EN 0x20000000 +#define CC_WD_SSRESET_PCIE_F2_EN 0x40000000 +#define CC_WD_SSRESET_PCIE_ALL_FN_EN 0x80000000 +#define CC_WD_COUNTER_MASK 0x0fffffff +#define CC_WD_ENABLE_MASK 0xf0000000 + /* * Maximum delay for the PMU state transition in us. * This is an upper bound intended for spinwaits etc. diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index 607fcea6f4efc4..0f002ef261fccf 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -1599,7 +1599,7 @@ static void _iwl_op_mode_stop(struct iwl_drv *drv) */ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context) { - unsigned int min_core, max_core, loaded_core; + int min_core, max_core, loaded_core; struct iwl_drv *drv = context; struct iwl_fw *fw = &drv->fw; const struct iwl_ucode_header *ucode; @@ -1678,7 +1678,7 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context) if (loaded_core < min_core || loaded_core > max_core) { IWL_ERR(drv, "Driver unable to support your firmware API. " - "Driver supports FW core %u..%u, firmware is %u.\n", + "Driver supports FW core %d..%d, firmware is %d.\n", min_core, max_core, loaded_core); goto try_again; } diff --git a/drivers/net/wireless/intel/iwlwifi/mld/d3.c b/drivers/net/wireless/intel/iwlwifi/mld/d3.c index 1d4282a21f09e0..dd85be94433cc5 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/d3.c @@ -1794,6 +1794,10 @@ iwl_mld_send_proto_offload(struct iwl_mld *mld, u32 enabled = 0; cmd = kzalloc(hcmd.len[0], GFP_KERNEL); + if (!cmd) { + IWL_DEBUG_WOWLAN(mld, "Failed to allocate proto offload cmd\n"); + return -ENOMEM; + } #if IS_ENABLED(CONFIG_IPV6) struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif); diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.c b/drivers/net/wireless/intel/iwlwifi/mld/iface.c index ed379825a92361..240ce19996b347 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/iface.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.c @@ -55,8 +55,6 @@ void iwl_mld_cleanup_vif(void *data, u8 *mac, struct ieee80211_vif *vif) ieee80211_iter_keys(mld->hw, vif, iwl_mld_cleanup_keys_iter, NULL); - wiphy_delayed_work_cancel(mld->wiphy, &mld_vif->mlo_scan_start_wk); - CLEANUP_STRUCT(mld_vif); } diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c index 5725104a53bf03..2a7e7417d7d84f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c @@ -1755,6 +1755,8 @@ static int iwl_mld_move_sta_state_down(struct iwl_mld *mld, wiphy_work_cancel(mld->wiphy, &mld_vif->emlsr.unblock_tpt_wk); wiphy_delayed_work_cancel(mld->wiphy, &mld_vif->emlsr.check_tpt_wk); + wiphy_delayed_work_cancel(mld->wiphy, + &mld_vif->mlo_scan_start_wk); iwl_mld_reset_cca_40mhz_workaround(mld, vif); iwl_mld_smps_workaround(mld, vif, true); diff --git a/drivers/net/wireless/intel/iwlwifi/mld/ptp.c b/drivers/net/wireless/intel/iwlwifi/mld/ptp.c index ffeb37a7f830eb..231920425c066e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/ptp.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/ptp.c @@ -121,6 +121,12 @@ static int iwl_mld_ptp_gettime(struct ptp_clock_info *ptp, return 0; } +static int iwl_mld_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + return -EOPNOTSUPP; +} + static int iwl_mld_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct iwl_mld *mld = container_of(ptp, struct iwl_mld, @@ -279,6 +285,7 @@ void iwl_mld_ptp_init(struct iwl_mld *mld) mld->ptp_data.ptp_clock_info.owner = THIS_MODULE; mld->ptp_data.ptp_clock_info.gettime64 = iwl_mld_ptp_gettime; + mld->ptp_data.ptp_clock_info.settime64 = iwl_mld_ptp_settime; mld->ptp_data.ptp_clock_info.max_adj = 0x7fffffff; mld->ptp_data.ptp_clock_info.adjtime = iwl_mld_ptp_adjtime; mld->ptp_data.ptp_clock_info.adjfine = iwl_mld_ptp_adjfine; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 07f1a84c274efe..af1a45845999bb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2025 Intel Corporation + * Copyright (C) 2012-2014, 2018-2026 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -3239,6 +3239,8 @@ void iwl_mvm_fast_suspend(struct iwl_mvm *mvm) IWL_DEBUG_WOWLAN(mvm, "Starting fast suspend flow\n"); + iwl_mvm_pause_tcm(mvm, true); + mvm->fast_resume = true; set_bit(IWL_MVM_STATUS_IN_D3, &mvm->status); @@ -3295,6 +3297,8 @@ int iwl_mvm_fast_resume(struct iwl_mvm *mvm) mvm->trans->state = IWL_TRANS_NO_FW; } + iwl_mvm_resume_tcm(mvm); + out: clear_bit(IWL_MVM_STATUS_IN_D3, &mvm->status); mvm->fast_resume = false; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c b/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c index 06a4c9f74797a4..ad156b82eaa943 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c @@ -220,6 +220,12 @@ static int iwl_mvm_ptp_gettime(struct ptp_clock_info *ptp, return 0; } +static int iwl_mvm_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + return -EOPNOTSUPP; +} + static int iwl_mvm_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct iwl_mvm *mvm = container_of(ptp, struct iwl_mvm, @@ -281,6 +287,7 @@ void iwl_mvm_ptp_init(struct iwl_mvm *mvm) mvm->ptp_data.ptp_clock_info.adjfine = iwl_mvm_ptp_adjfine; mvm->ptp_data.ptp_clock_info.adjtime = iwl_mvm_ptp_adjtime; mvm->ptp_data.ptp_clock_info.gettime64 = iwl_mvm_ptp_gettime; + mvm->ptp_data.ptp_clock_info.settime64 = iwl_mvm_ptp_settime; mvm->ptp_data.scaled_freq = SCALE_FACTOR; /* Give a short 'friendly name' to identify the PHC clock */ diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c index 354c5ce6604550..f3397dc6c422ed 100644 --- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c +++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c @@ -825,7 +825,7 @@ void mwifiex_update_rxreor_flags(struct mwifiex_adapter *adapter, u8 flags) static void mwifiex_update_ampdu_rxwinsize(struct mwifiex_adapter *adapter, bool coex_flag) { - u8 i; + u8 i, j; u32 rx_win_size; struct mwifiex_private *priv; @@ -863,8 +863,8 @@ static void mwifiex_update_ampdu_rxwinsize(struct mwifiex_adapter *adapter, if (rx_win_size != priv->add_ba_param.rx_win_size) { if (!priv->media_connected) continue; - for (i = 0; i < MAX_NUM_TID; i++) - mwifiex_11n_delba(priv, i); + for (j = 0; j < MAX_NUM_TID; j++) + mwifiex_11n_delba(priv, j); } } } diff --git a/drivers/net/wireless/mediatek/mt76/eeprom.c b/drivers/net/wireless/mediatek/mt76/eeprom.c index a987c5e4eff6c6..6ce8e4af18fe53 100644 --- a/drivers/net/wireless/mediatek/mt76/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/eeprom.c @@ -253,6 +253,19 @@ mt76_get_of_array(struct device_node *np, char *name, size_t *len, int min) return prop->value; } +static const s8 * +mt76_get_of_array_s8(struct device_node *np, char *name, size_t *len, int min) +{ + struct property *prop = of_find_property(np, name, NULL); + + if (!prop || !prop->value || prop->length < min) + return NULL; + + *len = prop->length; + + return prop->value; +} + struct device_node * mt76_find_channel_node(struct device_node *np, struct ieee80211_channel *chan) { @@ -294,7 +307,7 @@ mt76_get_txs_delta(struct device_node *np, u8 nss) } static void -mt76_apply_array_limit(s8 *pwr, size_t pwr_len, const __be32 *data, +mt76_apply_array_limit(s8 *pwr, size_t pwr_len, const s8 *data, s8 target_power, s8 nss_delta, s8 *max_power) { int i; @@ -303,15 +316,14 @@ mt76_apply_array_limit(s8 *pwr, size_t pwr_len, const __be32 *data, return; for (i = 0; i < pwr_len; i++) { - pwr[i] = min_t(s8, target_power, - be32_to_cpu(data[i]) + nss_delta); + pwr[i] = min_t(s8, target_power, data[i] + nss_delta); *max_power = max(*max_power, pwr[i]); } } static void mt76_apply_multi_array_limit(s8 *pwr, size_t pwr_len, s8 pwr_num, - const __be32 *data, size_t len, s8 target_power, + const s8 *data, size_t len, s8 target_power, s8 nss_delta, s8 *max_power) { int i, cur; @@ -319,8 +331,7 @@ mt76_apply_multi_array_limit(s8 *pwr, size_t pwr_len, s8 pwr_num, if (!data) return; - len /= 4; - cur = be32_to_cpu(data[0]); + cur = data[0]; for (i = 0; i < pwr_num; i++) { if (len < pwr_len + 1) break; @@ -335,7 +346,7 @@ mt76_apply_multi_array_limit(s8 *pwr, size_t pwr_len, s8 pwr_num, if (!len) break; - cur = be32_to_cpu(data[0]); + cur = data[0]; } } @@ -346,7 +357,7 @@ s8 mt76_get_rate_power_limits(struct mt76_phy *phy, { struct mt76_dev *dev = phy->dev; struct device_node *np; - const __be32 *val; + const s8 *val; char name[16]; u32 mcs_rates = dev->drv->mcs_rates; u32 ru_rates = ARRAY_SIZE(dest->ru[0]); @@ -392,21 +403,21 @@ s8 mt76_get_rate_power_limits(struct mt76_phy *phy, txs_delta = mt76_get_txs_delta(np, hweight16(phy->chainmask)); - val = mt76_get_of_array(np, "rates-cck", &len, ARRAY_SIZE(dest->cck)); + val = mt76_get_of_array_s8(np, "rates-cck", &len, ARRAY_SIZE(dest->cck)); mt76_apply_array_limit(dest->cck, ARRAY_SIZE(dest->cck), val, target_power, txs_delta, &max_power); - val = mt76_get_of_array(np, "rates-ofdm", - &len, ARRAY_SIZE(dest->ofdm)); + val = mt76_get_of_array_s8(np, "rates-ofdm", + &len, ARRAY_SIZE(dest->ofdm)); mt76_apply_array_limit(dest->ofdm, ARRAY_SIZE(dest->ofdm), val, target_power, txs_delta, &max_power); - val = mt76_get_of_array(np, "rates-mcs", &len, mcs_rates + 1); + val = mt76_get_of_array_s8(np, "rates-mcs", &len, mcs_rates + 1); mt76_apply_multi_array_limit(dest->mcs[0], ARRAY_SIZE(dest->mcs[0]), ARRAY_SIZE(dest->mcs), val, len, target_power, txs_delta, &max_power); - val = mt76_get_of_array(np, "rates-ru", &len, ru_rates + 1); + val = mt76_get_of_array_s8(np, "rates-ru", &len, ru_rates + 1); mt76_apply_multi_array_limit(dest->ru[0], ARRAY_SIZE(dest->ru[0]), ARRAY_SIZE(dest->ru), val, len, target_power, txs_delta, &max_power); diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 5ceaf78c9ea064..5e75861bf6f990 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -847,8 +847,6 @@ void mt76_reset_device(struct mt76_dev *dev) } rcu_read_unlock(); - mt76_abort_scan(dev); - INIT_LIST_HEAD(&dev->wcid_list); INIT_LIST_HEAD(&dev->sta_poll_list); dev->vif_mask = 0; diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index e0d50b58cd0129..7753afa3d883d6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -1252,6 +1252,15 @@ static inline int mt76_wed_dma_setup(struct mt76_dev *dev, struct mt76_queue *q, #define mt76_dereference(p, dev) \ rcu_dereference_protected(p, lockdep_is_held(&(dev)->mutex)) +static inline struct mt76_dev *mt76_wed_to_dev(struct mtk_wed_device *wed) +{ +#ifdef CONFIG_NET_MEDIATEK_SOC_WED + if (wed->wlan.hif2) + return container_of(wed, struct mt76_dev, mmio.wed_hif2); +#endif /* CONFIG_NET_MEDIATEK_SOC_WED */ + return container_of(wed, struct mt76_dev, mmio.wed); +} + static inline struct mt76_wcid * __mt76_wcid_ptr(struct mt76_dev *dev, u16 idx) { diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c index 4064e193d4dec6..08ee2e861c4e21 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c @@ -874,8 +874,10 @@ mt7615_mcu_wtbl_sta_add(struct mt7615_phy *phy, struct ieee80211_vif *vif, wtbl_hdr = mt76_connac_mcu_alloc_wtbl_req(&dev->mt76, &msta->wcid, WTBL_RESET_AND_SET, NULL, &wskb); - if (IS_ERR(wtbl_hdr)) + if (IS_ERR(wtbl_hdr)) { + dev_kfree_skb(sskb); return PTR_ERR(wtbl_hdr); + } if (enable) { mt76_connac_mcu_wtbl_generic_tlv(&dev->mt76, wskb, vif, sta, diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c index 1c0d310146d63b..5caf818e828343 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c @@ -1451,6 +1451,8 @@ mt7915_mac_full_reset(struct mt7915_dev *dev) if (ext_phy) cancel_delayed_work_sync(&ext_phy->mac_work); + mt76_abort_scan(&dev->mt76); + mutex_lock(&dev->mt76.mutex); for (i = 0; i < 10; i++) { if (!mt7915_mac_restart(dev)) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index 86bd33b916a9de..edc1df3c071e56 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -646,10 +646,10 @@ int mt7921_run_firmware(struct mt792x_dev *dev) if (err) return err; - set_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state); err = mt7921_load_clc(dev, mt792x_ram_name(dev)); if (err) return err; + set_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state); return mt7921_mcu_fw_log_2_host(dev, 1); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index 8eda407e4135e0..c12b71b71cfc78 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -1003,10 +1003,10 @@ int mt7925_run_firmware(struct mt792x_dev *dev) if (err) return err; - set_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state); err = mt7925_load_clc(dev, mt792x_ram_name(dev)); if (err) return err; + set_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state); return mt7925_mcu_fw_log_2_host(dev, 1); } diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c index c0e56541a95476..9cad572c34a38a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c @@ -688,7 +688,6 @@ int mt792x_init_wiphy(struct ieee80211_hw *hw) ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS); ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW); ieee80211_hw_set(hw, CONNECTION_MONITOR); - ieee80211_hw_set(hw, NO_VIRTUAL_MONITOR); ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID); ieee80211_hw_set(hw, SUPPORTS_ONLY_HE_MULTI_BSSID); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c index 659015f93d3238..7ed2f21b0e6db4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c @@ -512,12 +512,15 @@ int mt7996_dma_rro_init(struct mt7996_dev *dev) if (ret) return ret; - /* We need to set cpu idx pointer before resetting the EMI - * queues. - */ - mdev->q_rx[MT_RXQ_RRO_RXDMAD_C].emi_cpu_idx = - &dev->wed_rro.emi_rings_cpu.ptr->ring[0].idx; - mt76_queue_reset(dev, &mdev->q_rx[MT_RXQ_RRO_RXDMAD_C], true); + if (!mtk_wed_device_active(&mdev->mmio.wed)) { + /* We need to set cpu idx pointer before resetting the + * EMI queues. + */ + mdev->q_rx[MT_RXQ_RRO_RXDMAD_C].emi_cpu_idx = + &dev->wed_rro.emi_rings_cpu.ptr->ring[0].idx; + mt76_queue_reset(dev, &mdev->q_rx[MT_RXQ_RRO_RXDMAD_C], + true); + } goto start_hw_rro; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c index 5e95a36b42d164..b136b9a6697690 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c @@ -959,9 +959,10 @@ static int mt7996_wed_rro_init(struct mt7996_dev *dev) MT7996_RRO_MSDU_PG_SIZE_PER_CR); } - if (dev->mt76.hwrro_mode == MT76_HWRRO_V3_1) { + if (!mtk_wed_device_active(&dev->mt76.mmio.wed) && + dev->mt76.hwrro_mode == MT76_HWRRO_V3_1) { ptr = dmam_alloc_coherent(dev->mt76.dma_dev, - sizeof(dev->wed_rro.emi_rings_cpu.ptr), + sizeof(*dev->wed_rro.emi_rings_cpu.ptr), &dev->wed_rro.emi_rings_cpu.phy_addr, GFP_KERNEL); if (!ptr) @@ -970,7 +971,7 @@ static int mt7996_wed_rro_init(struct mt7996_dev *dev) dev->wed_rro.emi_rings_cpu.ptr = ptr; ptr = dmam_alloc_coherent(dev->mt76.dma_dev, - sizeof(dev->wed_rro.emi_rings_dma.ptr), + sizeof(*dev->wed_rro.emi_rings_dma.ptr), &dev->wed_rro.emi_rings_dma.phy_addr, GFP_KERNEL); if (!ptr) @@ -1036,6 +1037,18 @@ static void mt7996_wed_rro_free(struct mt7996_dev *dev) dev->wed_rro.msdu_pg[i].phy_addr); } + if (dev->wed_rro.emi_rings_cpu.ptr) + dmam_free_coherent(dev->mt76.dma_dev, + sizeof(*dev->wed_rro.emi_rings_cpu.ptr), + dev->wed_rro.emi_rings_cpu.ptr, + dev->wed_rro.emi_rings_cpu.phy_addr); + + if (dev->wed_rro.emi_rings_dma.ptr) + dmam_free_coherent(dev->mt76.dma_dev, + sizeof(*dev->wed_rro.emi_rings_dma.ptr), + dev->wed_rro.emi_rings_dma.ptr, + dev->wed_rro.emi_rings_dma.phy_addr); + if (!dev->wed_rro.session.ptr) return; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 9501def3e0e3e2..502136691a69e4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -794,6 +794,7 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi, u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; __le16 fc = hdr->frame_control, sc = hdr->seq_ctrl; u16 seqno = le16_to_cpu(sc); + bool hw_bigtk = false; u8 fc_type, fc_stype; u32 val; @@ -819,7 +820,11 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi, info->flags & IEEE80211_TX_CTL_USE_MINRATE) val |= MT_TXD1_FIXED_RATE; - if (key && multicast && ieee80211_is_robust_mgmt_frame(skb)) { + if (is_mt7990(&dev->mt76) && ieee80211_is_beacon(fc) && + (wcid->hw_key_idx2 == 6 || wcid->hw_key_idx2 == 7)) + hw_bigtk = true; + + if ((key && multicast && ieee80211_is_robust_mgmt_frame(skb)) || hw_bigtk) { val |= MT_TXD1_BIP; txwi[3] &= ~cpu_to_le32(MT_TXD3_PROTECT_FRAME); } @@ -1681,8 +1686,7 @@ mt7996_msdu_page_get_from_cache(struct mt7996_dev *dev) if (!list_empty(&dev->wed_rro.page_cache)) { p = list_first_entry(&dev->wed_rro.page_cache, struct mt7996_msdu_page, list); - if (p) - list_del(&p->list); + list_del(&p->list); } spin_unlock(&dev->wed_rro.lock); @@ -2337,7 +2341,7 @@ mt7996_mac_restart(struct mt7996_dev *dev) if (!test_bit(MT76_STATE_RUNNING, &phy->mt76->state)) continue; - ret = mt7996_run(&dev->phy); + ret = mt7996_run(phy); if (ret) goto out; } @@ -2420,6 +2424,8 @@ mt7996_mac_full_reset(struct mt7996_dev *dev) mt7996_for_each_phy(dev, phy) cancel_delayed_work_sync(&phy->mt76->mac_work); + mt76_abort_scan(&dev->mt76); + mutex_lock(&dev->mt76.mutex); for (i = 0; i < 10; i++) { if (!mt7996_mac_restart(dev)) @@ -2854,6 +2860,8 @@ void mt7996_mac_sta_rc_work(struct work_struct *work) LIST_HEAD(list); u32 changed; + mutex_lock(&dev->mt76.mutex); + spin_lock_bh(&dev->mt76.sta_poll_lock); list_splice_init(&dev->sta_rc_list, &list); @@ -2886,6 +2894,8 @@ void mt7996_mac_sta_rc_work(struct work_struct *work) } spin_unlock_bh(&dev->mt76.sta_poll_lock); + + mutex_unlock(&dev->mt76.mutex); } void mt7996_mac_work(struct work_struct *work) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 581314368c5ba5..2ad52ae2c5f55c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -90,9 +90,11 @@ static void mt7996_stop(struct ieee80211_hw *hw, bool suspend) { } -static inline int get_free_idx(u32 mask, u8 start, u8 end) +static inline int get_free_idx(u64 mask, u8 start, u8 end) { - return ffs(~mask & GENMASK(end, start)); + if (~mask & GENMASK_ULL(end, start)) + return __ffs64(~mask & GENMASK_ULL(end, start)) + 1; + return 0; } static int get_omac_idx(enum nl80211_iftype type, u64 mask) @@ -247,12 +249,13 @@ mt7996_set_hw_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, else if (idx == *wcid_keyidx) *wcid_keyidx = -1; - if (cmd != SET_KEY && sta) + /* only do remove key for BIGTK */ + if (cmd != SET_KEY && !is_bigtk) return 0; mt76_wcid_key_setup(&dev->mt76, &msta_link->wcid, key); - err = mt7996_mcu_add_key(&dev->mt76, vif, key, + err = mt7996_mcu_add_key(&dev->mt76, link, key, MCU_WMWA_UNI_CMD(STA_REC_UPDATE), &msta_link->wcid, cmd); @@ -308,12 +311,6 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif, if (idx < 0) return -ENOSPC; - if (!dev->mld_idx_mask) { /* first link in the group */ - mvif->mld_group_idx = get_own_mld_idx(dev->mld_idx_mask, true); - mvif->mld_remap_idx = get_free_idx(dev->mld_remap_idx_mask, - 0, 15); - } - mld_idx = get_own_mld_idx(dev->mld_idx_mask, false); if (mld_idx < 0) return -ENOSPC; @@ -331,10 +328,6 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif, return ret; dev->mt76.vif_mask |= BIT_ULL(mlink->idx); - if (!dev->mld_idx_mask) { - dev->mld_idx_mask |= BIT_ULL(mvif->mld_group_idx); - dev->mld_remap_idx_mask |= BIT_ULL(mvif->mld_remap_idx); - } dev->mld_idx_mask |= BIT_ULL(link->mld_idx); phy->omac_mask |= BIT_ULL(mlink->omac_idx); @@ -343,6 +336,7 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif, INIT_LIST_HEAD(&msta_link->rc_list); msta_link->wcid.idx = idx; msta_link->wcid.link_id = link_conf->link_id; + msta_link->wcid.link_valid = ieee80211_vif_is_mld(vif); msta_link->wcid.tx_info |= MT_WCID_TX_INFO_SET; mt76_wcid_init(&msta_link->wcid, band_idx); @@ -376,7 +370,8 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif, ieee80211_iter_keys(mphy->hw, vif, mt7996_key_iter, &it); - if (mvif->mt76.deflink_id == IEEE80211_LINK_UNSPECIFIED) + if (!mlink->wcid->offchannel && + mvif->mt76.deflink_id == IEEE80211_LINK_UNSPECIFIED) mvif->mt76.deflink_id = link_conf->link_id; return 0; @@ -397,7 +392,8 @@ void mt7996_vif_link_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif, }; int idx = msta_link->wcid.idx; - ieee80211_iter_keys(mphy->hw, vif, mt7996_key_iter, &it); + if (!mlink->wcid->offchannel) + ieee80211_iter_keys(mphy->hw, vif, mt7996_key_iter, &it); mt7996_mcu_add_sta(dev, link_conf, NULL, link, NULL, CONN_STATE_DISCONNECT, false); @@ -407,7 +403,8 @@ void mt7996_vif_link_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif, rcu_assign_pointer(dev->mt76.wcid[idx], NULL); - if (mvif->mt76.deflink_id == link_conf->link_id) { + if (!mlink->wcid->offchannel && + mvif->mt76.deflink_id == link_conf->link_id) { struct ieee80211_bss_conf *iter; unsigned int link_id; @@ -423,11 +420,6 @@ void mt7996_vif_link_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif, dev->mt76.vif_mask &= ~BIT_ULL(mlink->idx); dev->mld_idx_mask &= ~BIT_ULL(link->mld_idx); phy->omac_mask &= ~BIT_ULL(mlink->omac_idx); - if (!(dev->mld_idx_mask & ~BIT_ULL(mvif->mld_group_idx))) { - /* last link */ - dev->mld_idx_mask &= ~BIT_ULL(mvif->mld_group_idx); - dev->mld_remap_idx_mask &= ~BIT_ULL(mvif->mld_remap_idx); - } spin_lock_bh(&dev->mt76.sta_poll_lock); if (!list_empty(&msta_link->wcid.poll_list)) @@ -665,8 +657,8 @@ mt7996_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, unsigned int link_id, u16 queue, const struct ieee80211_tx_queue_params *params) { - struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt7996_vif_link *mlink = mt7996_vif_link(dev, vif, link_id); + struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; + struct mt7996_vif_link_info *link_info = &mvif->link_info[link_id]; static const u8 mq_to_aci[] = { [IEEE80211_AC_VO] = 3, [IEEE80211_AC_VI] = 2, @@ -675,7 +667,7 @@ mt7996_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, }; /* firmware uses access class index */ - mlink->queue_params[mq_to_aci[queue]] = *params; + link_info->queue_params[mq_to_aci[queue]] = *params; /* no need to update right away, we'll get BSS_CHANGED_QOS */ return 0; @@ -984,6 +976,7 @@ mt7996_mac_sta_init_link(struct mt7996_dev *dev, msta_link->wcid.sta = 1; msta_link->wcid.idx = idx; msta_link->wcid.link_id = link_id; + msta_link->wcid.link_valid = !!sta->valid_links; msta_link->wcid.def_wcid = &msta->deflink.wcid; ewma_avg_signal_init(&msta_link->avg_ack_signal); @@ -1160,12 +1153,15 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif, unsigned long links = sta->valid_links; struct ieee80211_link_sta *link_sta; unsigned int link_id; + int err = 0; + + mutex_lock(&dev->mt76.mutex); for_each_sta_active_link(vif, sta, link_sta, link_id) { struct ieee80211_bss_conf *link_conf; struct mt7996_sta_link *msta_link; struct mt7996_vif_link *link; - int i, err; + int i; link_conf = link_conf_dereference_protected(vif, link_id); if (!link_conf) @@ -1185,12 +1181,12 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif, link, msta_link, CONN_STATE_CONNECT, true); if (err) - return err; + goto unlock; err = mt7996_mcu_add_rate_ctrl(dev, msta_link->sta, vif, link_id, false); if (err) - return err; + goto unlock; msta_link->wcid.tx_info |= MT_WCID_TX_INFO_SET; break; @@ -1199,28 +1195,30 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif, link, msta_link, CONN_STATE_PORT_SECURE, false); if (err) - return err; + goto unlock; break; case MT76_STA_EVENT_DISASSOC: for (i = 0; i < ARRAY_SIZE(msta_link->twt.flow); i++) mt7996_mac_twt_teardown_flow(dev, link, msta_link, i); - if (sta->mlo && links == BIT(link_id)) /* last link */ - mt7996_mcu_teardown_mld_sta(dev, link, - msta_link); - else + if (!sta->mlo) mt7996_mcu_add_sta(dev, link_conf, link_sta, link, msta_link, CONN_STATE_DISCONNECT, false); + else if (sta->mlo && links == BIT(link_id)) /* last link */ + mt7996_mcu_teardown_mld_sta(dev, link, + msta_link); msta_link->wcid.sta_disabled = 1; msta_link->wcid.sta = 0; links = links & ~BIT(link_id); break; } } +unlock: + mutex_unlock(&dev->mt76.mutex); - return 0; + return err; } static void @@ -1339,12 +1337,10 @@ static void mt7996_tx(struct ieee80211_hw *hw, } if (mvif) { - struct mt76_vif_link *mlink = &mvif->deflink.mt76; - - if (link_id < IEEE80211_LINK_UNSPECIFIED) - mlink = rcu_dereference(mvif->mt76.link[link_id]); + struct mt76_vif_link *mlink; - if (mlink->wcid) + mlink = rcu_dereference(mvif->mt76.link[link_id]); + if (mlink && mlink->wcid) wcid = mlink->wcid; if (mvif->mt76.roc_phy && @@ -1352,7 +1348,7 @@ static void mt7996_tx(struct ieee80211_hw *hw, mphy = mvif->mt76.roc_phy; if (mphy->roc_link) wcid = mphy->roc_link->wcid; - } else { + } else if (mlink) { mphy = mt76_vif_link_phy(mlink); } } @@ -1362,7 +1358,7 @@ static void mt7996_tx(struct ieee80211_hw *hw, goto unlock; } - if (msta && link_id < IEEE80211_LINK_UNSPECIFIED) { + if (msta) { struct mt7996_sta_link *msta_link; msta_link = rcu_dereference(msta->link[link_id]); @@ -2217,7 +2213,42 @@ mt7996_change_vif_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 old_links, u16 new_links, struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS]) { - return 0; + struct mt7996_dev *dev = mt7996_hw_dev(hw); + struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; + int ret = 0; + + mutex_lock(&dev->mt76.mutex); + + if (!old_links) { + int idx; + + idx = get_own_mld_idx(dev->mld_idx_mask, true); + if (idx < 0) { + ret = -ENOSPC; + goto out; + } + mvif->mld_group_idx = idx; + dev->mld_idx_mask |= BIT_ULL(mvif->mld_group_idx); + + idx = get_free_idx(dev->mld_remap_idx_mask, 0, 15) - 1; + if (idx < 0) { + ret = -ENOSPC; + goto out; + } + mvif->mld_remap_idx = idx; + dev->mld_remap_idx_mask |= BIT_ULL(mvif->mld_remap_idx); + } + + if (new_links) + goto out; + + dev->mld_idx_mask &= ~BIT_ULL(mvif->mld_group_idx); + dev->mld_remap_idx_mask &= ~BIT_ULL(mvif->mld_remap_idx); + +out: + mutex_unlock(&dev->mt76.mutex); + + return ret; } static void diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c index 0347ee0c2dd75d..5bde9959bbb99d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c @@ -1034,7 +1034,6 @@ mt7996_mcu_bss_basic_tlv(struct sk_buff *skb, struct mt76_connac_bss_basic_tlv *bss; u32 type = CONNECTION_INFRA_AP; u16 sta_wlan_idx = wlan_idx; - struct ieee80211_sta *sta; struct tlv *tlv; int idx; @@ -1045,14 +1044,18 @@ mt7996_mcu_bss_basic_tlv(struct sk_buff *skb, break; case NL80211_IFTYPE_STATION: if (enable) { + struct ieee80211_sta *sta; + rcu_read_lock(); - sta = ieee80211_find_sta(vif, vif->bss_conf.bssid); - /* TODO: enable BSS_INFO_UAPSD & BSS_INFO_PM */ + sta = ieee80211_find_sta(vif, link_conf->bssid); if (sta) { - struct mt76_wcid *wcid; + struct mt7996_sta *msta = (void *)sta->drv_priv; + struct mt7996_sta_link *msta_link; + int link_id = link_conf->link_id; - wcid = (struct mt76_wcid *)sta->drv_priv; - sta_wlan_idx = wcid->idx; + msta_link = rcu_dereference(msta->link[link_id]); + if (msta_link) + sta_wlan_idx = msta_link->wcid.idx; } rcu_read_unlock(); } @@ -1069,8 +1072,6 @@ mt7996_mcu_bss_basic_tlv(struct sk_buff *skb, tlv = mt7996_mcu_add_uni_tlv(skb, UNI_BSS_INFO_BASIC, sizeof(*bss)); bss = (struct mt76_connac_bss_basic_tlv *)tlv; - bss->bcn_interval = cpu_to_le16(link_conf->beacon_int); - bss->dtim_period = link_conf->dtim_period; bss->bmc_tx_wlan_idx = cpu_to_le16(wlan_idx); bss->sta_idx = cpu_to_le16(sta_wlan_idx); bss->conn_type = cpu_to_le32(type); @@ -1090,10 +1091,10 @@ mt7996_mcu_bss_basic_tlv(struct sk_buff *skb, memcpy(bss->bssid, link_conf->bssid, ETH_ALEN); bss->bcn_interval = cpu_to_le16(link_conf->beacon_int); - bss->dtim_period = vif->bss_conf.dtim_period; + bss->dtim_period = link_conf->dtim_period; bss->phymode = mt76_connac_get_phy_mode(phy, vif, chandef->chan->band, NULL); - bss->phymode_ext = mt76_connac_get_phy_mode_ext(phy, &vif->bss_conf, + bss->phymode_ext = mt76_connac_get_phy_mode_ext(phy, link_conf, chandef->chan->band); return 0; @@ -1822,8 +1823,8 @@ mt7996_mcu_sta_bfer_tlv(struct mt7996_dev *dev, struct sk_buff *skb, bf->ibf_nrow = tx_ant; if (link_sta->eht_cap.has_eht || link_sta->he_cap.has_he) - bf->ibf_timeout = is_mt7996(&dev->mt76) ? MT7996_IBF_TIMEOUT : - MT7992_IBF_TIMEOUT; + bf->ibf_timeout = is_mt7992(&dev->mt76) ? MT7992_IBF_TIMEOUT : + MT7996_IBF_TIMEOUT; else if (!ebf && link_sta->bandwidth <= IEEE80211_STA_RX_BW_40 && !bf->ncol) bf->ibf_timeout = MT7996_IBF_TIMEOUT_LEGACY; else @@ -2526,7 +2527,7 @@ int mt7996_mcu_teardown_mld_sta(struct mt7996_dev *dev, } static int -mt7996_mcu_sta_key_tlv(struct mt76_wcid *wcid, +mt7996_mcu_sta_key_tlv(struct mt76_dev *dev, struct mt76_wcid *wcid, struct sk_buff *skb, struct ieee80211_key_conf *key, enum set_key_cmd cmd) @@ -2538,7 +2539,10 @@ mt7996_mcu_sta_key_tlv(struct mt76_wcid *wcid, tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_KEY_V2, sizeof(*sec)); sec = (struct sta_rec_sec_uni *)tlv; - sec->add = 0; + /* due to connac3 FW design, we only do remove key for BIGTK; even for + * removal, the field should be filled with SET_KEY + */ + sec->add = SET_KEY; sec->n_cipher = 1; sec_key = &sec->key[0]; sec_key->wlan_idx = cpu_to_le16(wcid->idx); @@ -2578,29 +2582,33 @@ mt7996_mcu_sta_key_tlv(struct mt76_wcid *wcid, case WLAN_CIPHER_SUITE_BIP_GMAC_256: sec_key->cipher_id = MCU_CIPHER_BCN_PROT_GMAC_256; break; + case WLAN_CIPHER_SUITE_BIP_CMAC_256: + if (!is_mt7990(dev)) + return -EOPNOTSUPP; + sec_key->cipher_id = MCU_CIPHER_BCN_PROT_CMAC_256; + break; default: return -EOPNOTSUPP; } - sec_key->bcn_mode = BP_SW_MODE; + sec_key->bcn_mode = is_mt7990(dev) ? BP_HW_MODE : BP_SW_MODE; return 0; } -int mt7996_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif, +int mt7996_mcu_add_key(struct mt76_dev *dev, struct mt7996_vif_link *link, struct ieee80211_key_conf *key, int mcu_cmd, struct mt76_wcid *wcid, enum set_key_cmd cmd) { - struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv; struct sk_buff *skb; int ret; - skb = __mt76_connac_mcu_alloc_sta_req(dev, mvif, wcid, - MT7996_STA_UPDATE_MAX_SIZE); + skb = __mt76_connac_mcu_alloc_sta_req(dev, (struct mt76_vif_link *)link, + wcid, MT7996_STA_UPDATE_MAX_SIZE); if (IS_ERR(skb)) return PTR_ERR(skb); - ret = mt7996_mcu_sta_key_tlv(wcid, skb, key, cmd); + ret = mt7996_mcu_sta_key_tlv(dev, wcid, skb, key, cmd); if (ret) { dev_kfree_skb(skb); return ret; @@ -2720,12 +2728,18 @@ mt7996_mcu_beacon_mbss(struct sk_buff *rskb, struct sk_buff *skb, static void mt7996_mcu_beacon_cont(struct mt7996_dev *dev, struct ieee80211_bss_conf *link_conf, + struct mt7996_vif_link *link, struct sk_buff *rskb, struct sk_buff *skb, struct bss_bcn_content_tlv *bcn, struct ieee80211_mutable_offsets *offs) { - struct mt76_wcid *wcid = &dev->mt76.global_wcid; - u8 *buf; + u8 *buf, keyidx = link->msta_link.wcid.hw_key_idx2; + struct mt76_wcid *wcid; + + if (is_mt7990(&dev->mt76) && (keyidx == 6 || keyidx == 7)) + wcid = &link->msta_link.wcid; + else + wcid = &dev->mt76.global_wcid; bcn->pkt_len = cpu_to_le16(MT_TXD_SIZE + skb->len); bcn->tim_ie_pos = cpu_to_le16(offs->tim_offset); @@ -2800,7 +2814,7 @@ int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif, info = IEEE80211_SKB_CB(skb); info->hw_queue |= FIELD_PREP(MT_TX_HW_QUEUE_PHY, mlink->band_idx); - mt7996_mcu_beacon_cont(dev, link_conf, rskb, skb, bcn, &offs); + mt7996_mcu_beacon_cont(dev, link_conf, link, rskb, skb, bcn, &offs); if (link_conf->bssid_indicator) mt7996_mcu_beacon_mbss(rskb, skb, bcn, &offs); mt7996_mcu_beacon_cntdwn(rskb, skb, &offs, link_conf->csa_active); @@ -3414,6 +3428,9 @@ int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif, #define WMM_PARAM_SET (WMM_AIFS_SET | WMM_CW_MIN_SET | \ WMM_CW_MAX_SET | WMM_TXOP_SET) struct mt7996_vif_link *link = mt7996_vif_conf_link(dev, vif, link_conf); + struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv; + unsigned int link_id = link_conf->link_id; + struct mt7996_vif_link_info *link_info = &mvif->link_info[link_id]; struct { u8 bss_idx; u8 __rsv[3]; @@ -3431,7 +3448,7 @@ int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif, skb_put_data(skb, &hdr, sizeof(hdr)); for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - struct ieee80211_tx_queue_params *q = &link->queue_params[ac]; + struct ieee80211_tx_queue_params *q = &link_info->queue_params[ac]; struct edca *e; struct tlv *tlv; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c index d14b626ee51156..80db102ed809c3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c @@ -595,6 +595,7 @@ int mt7996_mmio_wed_init(struct mt7996_dev *dev, void *pdev_ptr, wed->wlan.nbuf = MT7996_HW_TOKEN_SIZE; wed->wlan.token_start = MT7996_TOKEN_SIZE - wed->wlan.nbuf; + wed->wlan.hif2 = hif2; wed->wlan.amsdu_max_subframes = 8; wed->wlan.amsdu_max_len = 1536; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h index 8ec2acdb331937..b942928c79e280 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h @@ -253,16 +253,21 @@ struct mt7996_vif_link { struct mt7996_sta_link msta_link; struct mt7996_phy *phy; - struct ieee80211_tx_queue_params queue_params[IEEE80211_NUM_ACS]; struct cfg80211_bitrate_mask bitrate_mask; u8 mld_idx; }; +struct mt7996_vif_link_info { + struct ieee80211_tx_queue_params queue_params[IEEE80211_NUM_ACS]; +}; + struct mt7996_vif { struct mt7996_vif_link deflink; /* must be first */ struct mt76_vif_data mt76; + struct mt7996_vif_link_info link_info[IEEE80211_MLD_MAX_NUM_LINKS]; + u8 mld_group_idx; u8 mld_remap_idx; }; @@ -781,7 +786,7 @@ void mt7996_memcpy_fromio(struct mt7996_dev *dev, void *buf, u32 offset, static inline u16 mt7996_rx_chainmask(struct mt7996_phy *phy) { - int max_nss = hweight8(phy->mt76->hw->wiphy->available_antennas_tx); + int max_nss = hweight16(phy->orig_antenna_mask); int cur_nss = hweight8(phy->mt76->antenna_mask); u16 tx_chainmask = phy->mt76->chainmask; @@ -843,7 +848,7 @@ void mt7996_update_channel(struct mt76_phy *mphy); int mt7996_init_debugfs(struct mt7996_dev *dev); void mt7996_debugfs_rx_fw_monitor(struct mt7996_dev *dev, const void *data, int len); bool mt7996_debugfs_rx_log(struct mt7996_dev *dev, const void *data, int len); -int mt7996_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif, +int mt7996_mcu_add_key(struct mt76_dev *dev, struct mt7996_vif_link *link, struct ieee80211_key_conf *key, int mcu_cmd, struct mt76_wcid *wcid, enum set_key_cmd cmd); int mt7996_mcu_bcn_prot_enable(struct mt7996_dev *dev, diff --git a/drivers/net/wireless/mediatek/mt76/wed.c b/drivers/net/wireless/mediatek/mt76/wed.c index 907a8e43e72ad1..fbd7e59c73aaf2 100644 --- a/drivers/net/wireless/mediatek/mt76/wed.c +++ b/drivers/net/wireless/mediatek/mt76/wed.c @@ -8,7 +8,7 @@ void mt76_wed_release_rx_buf(struct mtk_wed_device *wed) { - struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); + struct mt76_dev *dev = mt76_wed_to_dev(wed); int i; for (i = 0; i < dev->rx_token_size; i++) { @@ -31,8 +31,8 @@ EXPORT_SYMBOL_GPL(mt76_wed_release_rx_buf); #ifdef CONFIG_NET_MEDIATEK_SOC_WED u32 mt76_wed_init_rx_buf(struct mtk_wed_device *wed, int size) { - struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); struct mtk_wed_bm_desc *desc = wed->rx_buf_ring.desc; + struct mt76_dev *dev = mt76_wed_to_dev(wed); struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN]; struct mt76_txwi_cache *t = NULL; int i; @@ -80,7 +80,7 @@ EXPORT_SYMBOL_GPL(mt76_wed_init_rx_buf); int mt76_wed_offload_enable(struct mtk_wed_device *wed) { - struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); + struct mt76_dev *dev = mt76_wed_to_dev(wed); spin_lock_bh(&dev->token_lock); dev->token_size = wed->wlan.token_start; @@ -164,7 +164,7 @@ EXPORT_SYMBOL_GPL(mt76_wed_dma_setup); void mt76_wed_offload_disable(struct mtk_wed_device *wed) { - struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); + struct mt76_dev *dev = mt76_wed_to_dev(wed); spin_lock_bh(&dev->token_lock); dev->token_size = dev->drv->token_size; @@ -174,7 +174,7 @@ EXPORT_SYMBOL_GPL(mt76_wed_offload_disable); void mt76_wed_reset_complete(struct mtk_wed_device *wed) { - struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); + struct mt76_dev *dev = mt76_wed_to_dev(wed); complete(&dev->mmio.wed_reset_complete); } diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c b/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c index 2905baea62390d..070c0431c4821c 100644 --- a/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c +++ b/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c @@ -1023,9 +1023,6 @@ static int rtl8180_init_rx_ring(struct ieee80211_hw *dev) dma_addr_t *mapping; entry = priv->rx_ring + priv->rx_ring_sz*i; if (!skb) { - dma_free_coherent(&priv->pdev->dev, - priv->rx_ring_sz * 32, - priv->rx_ring, priv->rx_ring_dma); wiphy_err(dev->wiphy, "Cannot allocate RX skb\n"); return -ENOMEM; } @@ -1037,9 +1034,7 @@ static int rtl8180_init_rx_ring(struct ieee80211_hw *dev) if (dma_mapping_error(&priv->pdev->dev, *mapping)) { kfree_skb(skb); - dma_free_coherent(&priv->pdev->dev, - priv->rx_ring_sz * 32, - priv->rx_ring, priv->rx_ring_dma); + priv->rx_buf[i] = NULL; wiphy_err(dev->wiphy, "Cannot map DMA for RX skb\n"); return -ENOMEM; } @@ -1130,7 +1125,7 @@ static int rtl8180_start(struct ieee80211_hw *dev) ret = rtl8180_init_rx_ring(dev); if (ret) - return ret; + goto err_free_rings; for (i = 0; i < (dev->queues + 1); i++) if ((ret = rtl8180_init_tx_ring(dev, i, 16))) diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c index 0c5c66401daa6d..7aa2da0cd63cc8 100644 --- a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c +++ b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c @@ -338,14 +338,16 @@ static void rtl8187_rx_cb(struct urb *urb) spin_unlock_irqrestore(&priv->rx_queue.lock, f); skb_put(skb, urb->actual_length); - if (unlikely(urb->status)) { - dev_kfree_skb_irq(skb); - return; - } + if (unlikely(urb->status)) + goto free_skb; if (!priv->is_rtl8187b) { - struct rtl8187_rx_hdr *hdr = - (typeof(hdr))(skb_tail_pointer(skb) - sizeof(*hdr)); + struct rtl8187_rx_hdr *hdr; + + if (skb->len < sizeof(struct rtl8187_rx_hdr)) + goto free_skb; + + hdr = (typeof(hdr))(skb_tail_pointer(skb) - sizeof(*hdr)); flags = le32_to_cpu(hdr->flags); /* As with the RTL8187B below, the AGC is used to calculate * signal strength. In this case, the scaling @@ -355,8 +357,12 @@ static void rtl8187_rx_cb(struct urb *urb) rx_status.antenna = (hdr->signal >> 7) & 1; rx_status.mactime = le64_to_cpu(hdr->mac_time); } else { - struct rtl8187b_rx_hdr *hdr = - (typeof(hdr))(skb_tail_pointer(skb) - sizeof(*hdr)); + struct rtl8187b_rx_hdr *hdr; + + if (skb->len < sizeof(struct rtl8187b_rx_hdr)) + goto free_skb; + + hdr = (typeof(hdr))(skb_tail_pointer(skb) - sizeof(*hdr)); /* The Realtek datasheet for the RTL8187B shows that the RX * header contains the following quantities: signal quality, * RSSI, AGC, the received power in dB, and the measured SNR. @@ -409,6 +415,11 @@ static void rtl8187_rx_cb(struct urb *urb) skb_unlink(skb, &priv->rx_queue); dev_kfree_skb_irq(skb); } + return; + +free_skb: + dev_kfree_skb_irq(skb); + return; } static int rtl8187_init_urbs(struct ieee80211_hw *dev) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/core.c b/drivers/net/wireless/realtek/rtl8xxxu/core.c index 3ded5952729fc6..a17c1084931b0e 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/core.c @@ -1252,7 +1252,7 @@ void rtl8xxxu_gen1_config_channel(struct ieee80211_hw *hw) opmode &= ~BW_OPMODE_20MHZ; rtl8xxxu_write8(priv, REG_BW_OPMODE, opmode); rsr &= ~RSR_RSC_BANDWIDTH_40M; - if (sec_ch_above) + if (!sec_ch_above) rsr |= RSR_RSC_UPPER_SUB_CHANNEL; else rsr |= RSR_RSC_LOWER_SUB_CHANNEL; @@ -1321,9 +1321,8 @@ void rtl8xxxu_gen1_config_channel(struct ieee80211_hw *hw) for (i = RF_A; i < priv->rf_paths; i++) { val32 = rtl8xxxu_read_rfreg(priv, i, RF6052_REG_MODE_AG); - if (hw->conf.chandef.width == NL80211_CHAN_WIDTH_40) - val32 &= ~MODE_AG_CHANNEL_20MHZ; - else + val32 &= ~MODE_AG_BW_MASK; + if (hw->conf.chandef.width != NL80211_CHAN_WIDTH_40) val32 |= MODE_AG_CHANNEL_20MHZ; rtl8xxxu_write_rfreg(priv, i, RF6052_REG_MODE_AG, val32); } @@ -7928,6 +7927,7 @@ static int rtl8xxxu_probe(struct usb_interface *interface, goto err_set_intfdata; hw->vif_data_size = sizeof(struct rtl8xxxu_vif); + hw->sta_data_size = sizeof(struct rtl8xxxu_sta_info); hw->wiphy->max_scan_ssids = 1; hw->wiphy->max_scan_ie_len = IEEE80211_MAX_DATA_LEN; @@ -8136,6 +8136,9 @@ static const struct usb_device_id dev_table[] = { /* TP-Link TL-WN823N V2 */ {USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x0135, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192fu_fops}, +/* D-Link AN3U rev. A1 */ +{USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x3328, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192fu_fops}, #ifdef CONFIG_RTL8XXXU_UNTESTED /* Still supported by rtlwifi */ {USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x8176, 0xff, 0xff, 0xff), diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/trx.c index aa702ba7c9f540..d6c35e8d02a58c 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/trx.c @@ -511,7 +511,8 @@ void rtl92cu_tx_fill_desc(struct ieee80211_hw *hw, if (sta) { sta_entry = (struct rtl_sta_info *)sta->drv_priv; tid = ieee80211_get_tid(hdr); - agg_state = sta_entry->tids[tid].agg.agg_state; + if (tid < MAX_TID_COUNT) + agg_state = sta_entry->tids[tid].agg.agg_state; ampdu_density = sta->deflink.ht_cap.ampdu_density; } diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index fa0ed39cb1992a..d93d21656f26c8 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -2444,10 +2444,10 @@ void rtw_core_enable_beacon(struct rtw_dev *rtwdev, bool enable) if (enable) { rtw_write32_set(rtwdev, REG_BCN_CTRL, BIT_EN_BCN_FUNCTION); - rtw_write32_clr(rtwdev, REG_TXPAUSE, BIT_HIGH_QUEUE); + rtw_write8_clr(rtwdev, REG_TXPAUSE, BIT_HIGH_QUEUE); } else { rtw_write32_clr(rtwdev, REG_BCN_CTRL, BIT_EN_BCN_FUNCTION); - rtw_write32_set(rtwdev, REG_TXPAUSE, BIT_HIGH_QUEUE); + rtw_write8_set(rtwdev, REG_TXPAUSE, BIT_HIGH_QUEUE); } } diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822cu.c b/drivers/net/wireless/realtek/rtw88/rtw8822cu.c index 324fd5c8bfd440..755f76840b1210 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822cu.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8822cu.c @@ -21,6 +21,8 @@ static const struct usb_device_id rtw_8822cu_id_table[] = { .driver_info = (kernel_ulong_t)&(rtw8822c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(0x13b1, 0x0043, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)&(rtw8822c_hw_spec) }, /* Alpha - Alpha */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x3329, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8822c_hw_spec) }, /* D-Link AC13U rev. A1 */ {}, }; MODULE_DEVICE_TABLE(usb, rtw_8822cu_id_table); diff --git a/drivers/net/wireless/realtek/rtw88/sdio.c b/drivers/net/wireless/realtek/rtw88/sdio.c index 99d7c629eac6fb..e35de52d8eb430 100644 --- a/drivers/net/wireless/realtek/rtw88/sdio.c +++ b/drivers/net/wireless/realtek/rtw88/sdio.c @@ -144,8 +144,10 @@ static u32 rtw_sdio_to_io_address(struct rtw_dev *rtwdev, u32 addr, static bool rtw_sdio_use_direct_io(struct rtw_dev *rtwdev, u32 addr) { + bool might_indirect_under_power_off = rtwdev->chip->id == RTW_CHIP_TYPE_8822C; + if (!test_bit(RTW_FLAG_POWERON, rtwdev->flags) && - !rtw_sdio_is_bus_addr(addr)) + !rtw_sdio_is_bus_addr(addr) && might_indirect_under_power_off) return false; return !rtw_sdio_is_sdio30_supported(rtwdev) || diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c index 3dc7981c510fdb..a82df3814069cd 100644 --- a/drivers/net/wireless/realtek/rtw89/debug.c +++ b/drivers/net/wireless/realtek/rtw89/debug.c @@ -824,10 +824,6 @@ static ssize_t __print_txpwr_map(struct rtw89_dev *rtwdev, char *buf, size_t buf s8 *bufp, tmp; int ret; - bufp = vzalloc(map->addr_to - map->addr_from + 4); - if (!bufp) - return -ENOMEM; - if (path_num == 1) max_valid_addr = map->addr_to_1ss; else @@ -836,6 +832,10 @@ static ssize_t __print_txpwr_map(struct rtw89_dev *rtwdev, char *buf, size_t buf if (max_valid_addr == 0) return -EOPNOTSUPP; + bufp = vzalloc(map->addr_to - map->addr_from + 4); + if (!bufp) + return -ENOMEM; + for (addr = map->addr_from; addr <= max_valid_addr; addr += 4) { ret = rtw89_mac_txpwr_read32(rtwdev, RTW89_PHY_0, addr, &val); if (ret) diff --git a/drivers/net/wireless/realtek/rtw89/usb.c b/drivers/net/wireless/realtek/rtw89/usb.c index 6cf89aee252eda..512a46dd9d06a3 100644 --- a/drivers/net/wireless/realtek/rtw89/usb.c +++ b/drivers/net/wireless/realtek/rtw89/usb.c @@ -256,7 +256,7 @@ static int rtw89_usb_write_port(struct rtw89_dev *rtwdev, u8 ch_dma, int ret; if (test_bit(RTW89_FLAG_UNPLUGGED, rtwdev->flags)) - return 0; + return -ENODEV; urb = usb_alloc_urb(0, GFP_ATOMIC); if (!urb) @@ -305,8 +305,9 @@ static void rtw89_usb_ops_tx_kick_off(struct rtw89_dev *rtwdev, u8 txch) ret = rtw89_usb_write_port(rtwdev, txch, skb->data, skb->len, txcb); if (ret) { - rtw89_err(rtwdev, "write port txch %d failed: %d\n", - txch, ret); + if (ret != -ENODEV) + rtw89_err(rtwdev, "write port txch %d failed: %d\n", + txch, ret); skb_dequeue(&txcb->tx_ack_queue); kfree(txcb); @@ -410,8 +411,7 @@ static void rtw89_usb_rx_handler(struct work_struct *work) if (skb_queue_len(&rtwusb->rx_queue) >= RTW89_USB_MAX_RXQ_LEN) { rtw89_warn(rtwdev, "rx_queue overflow\n"); - dev_kfree_skb_any(rx_skb); - continue; + goto free_or_reuse; } memset(&desc_info, 0, sizeof(desc_info)); @@ -422,7 +422,7 @@ static void rtw89_usb_rx_handler(struct work_struct *work) rtw89_debug(rtwdev, RTW89_DBG_HCI, "failed to allocate RX skb of size %u\n", desc_info.pkt_size); - continue; + goto free_or_reuse; } pkt_offset = desc_info.offset + desc_info.rxd_len; @@ -432,6 +432,7 @@ static void rtw89_usb_rx_handler(struct work_struct *work) rtw89_core_rx(rtwdev, &desc_info, skb); +free_or_reuse: if (skb_queue_len(&rtwusb->rx_free_queue) >= RTW89_USB_RX_SKB_NUM) dev_kfree_skb_any(rx_skb); else diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index f3a853edfc11df..8c8e074a3a7056 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -2035,6 +2035,7 @@ int rsi_mac80211_attach(struct rsi_common *common) hw->queues = MAX_HW_QUEUES; hw->extra_tx_headroom = RSI_NEEDED_HEADROOM; + hw->vif_data_size = sizeof(struct vif_priv); hw->max_rates = 1; hw->max_rate_tries = MAX_RETRIES; diff --git a/drivers/net/wireless/st/cw1200/bh.c b/drivers/net/wireless/st/cw1200/bh.c index 3b4ded2ac801cc..37232ee2203755 100644 --- a/drivers/net/wireless/st/cw1200/bh.c +++ b/drivers/net/wireless/st/cw1200/bh.c @@ -317,10 +317,12 @@ static int cw1200_bh_rx_helper(struct cw1200_common *priv, if (wsm_id & 0x0400) { int rc = wsm_release_tx_buffer(priv, 1); - if (WARN_ON(rc < 0)) + if (WARN_ON(rc < 0)) { + dev_kfree_skb(skb_rx); return rc; - else if (rc > 0) + } else if (rc > 0) { *tx = 1; + } } /* cw1200_wsm_rx takes care on SKB livetime */ diff --git a/drivers/net/wireless/ti/wlcore/tx.c b/drivers/net/wireless/ti/wlcore/tx.c index 464587d16ab20d..f251627c24c6ea 100644 --- a/drivers/net/wireless/ti/wlcore/tx.c +++ b/drivers/net/wireless/ti/wlcore/tx.c @@ -207,6 +207,11 @@ static int wl1271_tx_allocate(struct wl1271 *wl, struct wl12xx_vif *wlvif, total_blocks = wlcore_hw_calc_tx_blocks(wl, total_len, spare_blocks); if (total_blocks <= wl->tx_blocks_available) { + if (skb_headroom(skb) < (total_len - skb->len) && + pskb_expand_head(skb, (total_len - skb->len), 0, GFP_ATOMIC)) { + wl1271_free_tx_id(wl, id); + return -EAGAIN; + } desc = skb_push(skb, total_len - skb->len); wlcore_hw_set_tx_desc_blocks(wl, desc, total_blocks, diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c index 5903d82e1ab1e8..2f263d89d2d692 100644 --- a/drivers/net/wireless/virtual/mac80211_hwsim.c +++ b/drivers/net/wireless/virtual/mac80211_hwsim.c @@ -4040,7 +4040,7 @@ mac80211_hwsim_nan_dw_start(struct hrtimer *timer) ieee80211_vif_to_wdev(data->nan_device_vif); if (data->nan_curr_dw_band == NL80211_BAND_5GHZ) - ch = ieee80211_get_channel(hw->wiphy, 5475); + ch = ieee80211_get_channel(hw->wiphy, 5745); else ch = ieee80211_get_channel(hw->wiphy, 2437); diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.c b/drivers/net/wwan/iosm/iosm_ipc_mux.c index fc928b298a9840..b846889fcb0997 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux.c @@ -456,6 +456,7 @@ void ipc_mux_deinit(struct iosm_mux *ipc_mux) struct sk_buff_head *free_list; union mux_msg mux_msg; struct sk_buff *skb; + int i; if (!ipc_mux->initialized) return; @@ -479,5 +480,10 @@ void ipc_mux_deinit(struct iosm_mux *ipc_mux) ipc_mux->channel->dl_pipe.is_open = false; } + if (ipc_mux->protocol != MUX_LITE) { + for (i = 0; i < IPC_MEM_MUX_IP_SESSION_ENTRIES; i++) + kfree(ipc_mux->ul_adb.pp_qlt[i]); + } + kfree(ipc_mux); } diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c index 2310493203d3c7..d9f10df03a5dba 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c @@ -395,6 +395,7 @@ static int t7xx_dpmaif_set_frag_to_skb(const struct dpmaif_rx_queue *rxq, struct sk_buff *skb) { unsigned long long data_bus_addr, data_base_addr; + struct skb_shared_info *shinfo = skb_shinfo(skb); struct device *dev = rxq->dpmaif_ctrl->dev; struct dpmaif_bat_page *page_info; unsigned int data_len; @@ -402,18 +403,22 @@ static int t7xx_dpmaif_set_frag_to_skb(const struct dpmaif_rx_queue *rxq, page_info = rxq->bat_frag->bat_skb; page_info += t7xx_normal_pit_bid(pkt_info); - dma_unmap_page(dev, page_info->data_bus_addr, page_info->data_len, DMA_FROM_DEVICE); if (!page_info->page) return -EINVAL; + if (shinfo->nr_frags >= MAX_SKB_FRAGS) + return -EINVAL; + + dma_unmap_page(dev, page_info->data_bus_addr, page_info->data_len, DMA_FROM_DEVICE); + data_bus_addr = le32_to_cpu(pkt_info->pd.data_addr_h); data_bus_addr = (data_bus_addr << 32) + le32_to_cpu(pkt_info->pd.data_addr_l); data_base_addr = page_info->data_bus_addr; data_offset = data_bus_addr - data_base_addr; data_offset += page_info->offset; data_len = FIELD_GET(PD_PIT_DATA_LEN, le32_to_cpu(pkt_info->header)); - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page_info->page, + skb_add_rx_frag(skb, shinfo->nr_frags, page_info->page, data_offset, data_len, page_info->data_len); page_info->page = NULL; diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index a78a25b872409a..61b547aab286a2 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -735,10 +735,11 @@ static void connect(struct backend_info *be) */ requested_num_queues = xenbus_read_unsigned(dev->otherend, "multi-queue-num-queues", 1); - if (requested_num_queues > xenvif_max_queues) { + if (requested_num_queues > xenvif_max_queues || + requested_num_queues == 0) { /* buggy or malicious guest */ xenbus_dev_fatal(dev, -EINVAL, - "guest requested %u queues, exceeding the maximum of %u.", + "guest requested %u queues, but valid range is 1 - %u.", requested_num_queues, xenvif_max_queues); return; } diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index ffd7367ce11945..018a80674f06ed 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -406,7 +406,7 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy) if (rc || (transferred != sizeof(cmd))) { nfc_err(&phy->udev->dev, "Reader power on cmd error %d\n", rc); - return rc; + return rc ?: -EINVAL; } rc = usb_submit_urb(phy->in_urb, GFP_KERNEL); diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c index 9ef8ef2d4363a8..b957fce83b7c88 100644 --- a/drivers/nfc/virtual_ncidev.c +++ b/drivers/nfc/virtual_ncidev.c @@ -125,10 +125,6 @@ static ssize_t virtual_ncidev_write(struct file *file, kfree_skb(skb); return -EFAULT; } - if (strnlen(skb->data, count) != count) { - kfree_skb(skb); - return -EINVAL; - } nci_recv_frame(vdev->ndev, skb); return count; diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index eb875e3db2e3b9..71d4bb25f7fdd1 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -1394,6 +1394,7 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) goto err2; } + mutex_init(&nt->link_event_lock); INIT_DELAYED_WORK(&nt->link_work, ntb_transport_link_work); INIT_WORK(&nt->link_cleanup, ntb_transport_link_cleanup_work); diff --git a/drivers/nvdimm/nd_virtio.c b/drivers/nvdimm/nd_virtio.c index c3f07be4aa22ad..af82385be7c6aa 100644 --- a/drivers/nvdimm/nd_virtio.c +++ b/drivers/nvdimm/nd_virtio.c @@ -44,6 +44,8 @@ static int virtio_pmem_flush(struct nd_region *nd_region) unsigned long flags; int err, err1; + guard(mutex)(&vpmem->flush_lock); + /* * Don't bother to submit the request to the device if the device is * not activated. @@ -53,7 +55,6 @@ static int virtio_pmem_flush(struct nd_region *nd_region) return -EIO; } - might_sleep(); req_data = kmalloc(sizeof(*req_data), GFP_KERNEL); if (!req_data) return -ENOMEM; diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c index 2396d19ce54969..77b1966619059c 100644 --- a/drivers/nvdimm/virtio_pmem.c +++ b/drivers/nvdimm/virtio_pmem.c @@ -64,6 +64,7 @@ static int virtio_pmem_probe(struct virtio_device *vdev) goto out_err; } + mutex_init(&vpmem->flush_lock); vpmem->vdev = vdev; vdev->priv = vpmem; err = init_vq(vpmem); diff --git a/drivers/nvdimm/virtio_pmem.h b/drivers/nvdimm/virtio_pmem.h index 0dddefe594c46a..f72cf17f9518fb 100644 --- a/drivers/nvdimm/virtio_pmem.h +++ b/drivers/nvdimm/virtio_pmem.h @@ -13,6 +13,7 @@ #include #include #include +#include #include struct virtio_pmem_request { @@ -35,6 +36,9 @@ struct virtio_pmem { /* Virtio pmem request queue */ struct virtqueue *req_vq; + /* Serialize flush requests to the device. */ + struct mutex flush_lock; + /* nvdimm bus registers virtio pmem device */ struct nvdimm_bus *nvdimm_bus; struct nvdimm_bus_descriptor nd_desc; diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index f35d3f71d14f32..ed8aa0298415b2 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -203,8 +203,20 @@ struct apple_nvme { int irq; spinlock_t lock; + + /* + * Delayed cache flush handling state + */ + struct nvme_ns *flush_ns; + unsigned long flush_interval; + unsigned long last_flush; + struct delayed_work flush_dwork; }; +unsigned int flush_interval = 1000; +module_param(flush_interval, uint, 0644); +MODULE_PARM_DESC(flush_interval, "Grace period in msecs between flushes"); + static_assert(sizeof(struct nvme_command) == 64); static_assert(sizeof(struct apple_nvmmu_tcb) == 128); @@ -762,6 +774,26 @@ static int apple_nvme_remove_sq(struct apple_nvme *anv) return nvme_submit_sync_cmd(anv->ctrl.admin_q, &c, NULL, 0); } +static bool apple_nvme_delayed_flush(struct apple_nvme *anv, struct nvme_ns *ns, + struct request *req) +{ + if (!anv->flush_interval || req_op(req) != REQ_OP_FLUSH) + return false; + if (delayed_work_pending(&anv->flush_dwork)) + return true; + if (time_before(jiffies, anv->last_flush + anv->flush_interval)) { + kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &anv->flush_dwork, + anv->flush_interval); + if (WARN_ON_ONCE(anv->flush_ns && anv->flush_ns != ns)) + goto out; + anv->flush_ns = ns; + return true; + } +out: + anv->last_flush = jiffies; + return false; +} + static blk_status_t apple_nvme_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -798,6 +830,11 @@ static blk_status_t apple_nvme_queue_rq(struct blk_mq_hw_ctx *hctx, nvme_start_request(req); + if (apple_nvme_delayed_flush(anv, ns, req)) { + blk_mq_complete_request(req); + return BLK_STS_OK; + } + if (anv->hw->has_lsq_nvmmu) apple_nvme_submit_cmd_t8103(q, cmnd); else @@ -1452,6 +1489,28 @@ static void devm_apple_nvme_mempool_destroy(void *data) mempool_destroy(data); } +static void apple_nvme_flush_work(struct work_struct *work) +{ + struct nvme_command c = { }; + struct apple_nvme *anv; + struct nvme_ns *ns; + int err; + + anv = container_of(work, struct apple_nvme, flush_dwork.work); + ns = anv->flush_ns; + if (WARN_ON_ONCE(!ns)) + return; + + c.common.opcode = nvme_cmd_flush; + c.common.nsid = cpu_to_le32(anv->flush_ns->head->ns_id); + err = nvme_submit_sync_cmd(ns->queue, &c, NULL, 0); + if (err) { + dev_err(anv->dev, "Deferred flush failed: %d\n", err); + } else { + anv->last_flush = jiffies; + } +} + static struct apple_nvme *apple_nvme_alloc(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1620,6 +1679,14 @@ static int apple_nvme_probe(struct platform_device *pdev) goto out_uninit_ctrl; } + if (flush_interval) { + anv->flush_interval = msecs_to_jiffies(flush_interval); + anv->flush_ns = NULL; + anv->last_flush = jiffies - anv->flush_interval; + } + + INIT_DELAYED_WORK(&anv->flush_dwork, apple_nvme_flush_work); + nvme_reset_ctrl(&anv->ctrl); async_schedule(apple_nvme_async_probe, anv); @@ -1657,6 +1724,7 @@ static void apple_nvme_shutdown(struct platform_device *pdev) { struct apple_nvme *anv = platform_get_drvdata(pdev); + flush_delayed_work(&anv->flush_dwork); apple_nvme_disable(anv, true); if (apple_rtkit_is_running(anv->rtk)) { apple_rtkit_shutdown(anv->rtk); @@ -1703,6 +1771,7 @@ static const struct apple_nvme_hw apple_nvme_t8103_hw = { static const struct of_device_id apple_nvme_of_match[] = { { .compatible = "apple,t8015-nvme-ans2", .data = &apple_nvme_t8015_hw }, + { .compatible = "apple,t8103-nvme-ans2", .data = &apple_nvme_t8103_hw }, { .compatible = "apple,nvme-ans2", .data = &apple_nvme_t8103_hw }, {}, }; diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index a01178caf15bb5..8f3ccb317e4de6 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -1122,7 +1122,7 @@ void nvme_auth_free(struct nvme_ctrl *ctrl) if (ctrl->dhchap_ctxs) { for (i = 0; i < ctrl_max_dhchaps(ctrl); i++) nvme_auth_free_dhchap(&ctrl->dhchap_ctxs[i]); - kfree(ctrl->dhchap_ctxs); + kvfree(ctrl->dhchap_ctxs); } if (ctrl->host_key) { nvme_auth_free_key(ctrl->host_key); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 2e58a7ce109052..55a8afd2efd503 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -592,7 +592,7 @@ bool nvmf_should_reconnect(struct nvme_ctrl *ctrl, int status) if (status > 0 && (status & NVME_STATUS_DNR)) return false; - if (status == -EKEYREJECTED) + if (status == -EKEYREJECTED || status == -ENOKEY) return false; if (ctrl->opts->max_reconnects == -1 || diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 2c903729b0b909..bf78faf1a4ffa6 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1468,14 +1468,14 @@ nvme_fc_match_disconn_ls(struct nvme_fc_rport *rport, { struct fcnvme_ls_disconnect_assoc_rqst *rqst = &lsop->rqstbuf->rq_dis_assoc; - struct nvme_fc_ctrl *ctrl, *ret = NULL; + struct nvme_fc_ctrl *ctrl, *tmp, *ret = NULL; struct nvmefc_ls_rcv_op *oldls = NULL; u64 association_id = be64_to_cpu(rqst->associd.association_id); unsigned long flags; spin_lock_irqsave(&rport->lock, flags); - list_for_each_entry(ctrl, &rport->ctrl_list, ctrl_list) { + list_for_each_entry_safe(ctrl, tmp, &rport->ctrl_list, ctrl_list) { if (!nvme_fc_ctrl_get(ctrl)) continue; spin_lock(&ctrl->lock); @@ -1488,7 +1488,9 @@ nvme_fc_match_disconn_ls(struct nvme_fc_rport *rport, if (ret) /* leave the ctrl get reference */ break; + spin_unlock_irqrestore(&rport->lock, flags); nvme_fc_ctrl_put(ctrl); + spin_lock_irqsave(&rport->lock, flags); } spin_unlock_irqrestore(&rport->lock, flags); @@ -3582,6 +3584,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ctrl->ctrl.opts = NULL; + if (ctrl->ctrl.admin_tagset) + nvme_remove_admin_tag_set(&ctrl->ctrl); /* initiate nvme ctrl ref counting teardown */ nvme_uninit_ctrl(&ctrl->ctrl); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 72fb675a696f49..391c854428d3e9 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -771,6 +771,32 @@ static void nvme_unmap_data(struct request *req) nvme_free_descriptors(req); } +static bool nvme_pci_prp_save_mapping(struct request *req, + struct device *dma_dev, + struct blk_dma_iter *iter) +{ + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + + if (dma_use_iova(&iod->dma_state) || !dma_need_unmap(dma_dev)) + return true; + + if (!iod->nr_dma_vecs) { + struct nvme_queue *nvmeq = req->mq_hctx->driver_data; + + iod->dma_vecs = mempool_alloc(nvmeq->dev->dmavec_mempool, + GFP_ATOMIC); + if (!iod->dma_vecs) { + iter->status = BLK_STS_RESOURCE; + return false; + } + } + + iod->dma_vecs[iod->nr_dma_vecs].addr = iter->addr; + iod->dma_vecs[iod->nr_dma_vecs].len = iter->len; + iod->nr_dma_vecs++; + return true; +} + static bool nvme_pci_prp_iter_next(struct request *req, struct device *dma_dev, struct blk_dma_iter *iter) { @@ -780,12 +806,7 @@ static bool nvme_pci_prp_iter_next(struct request *req, struct device *dma_dev, return true; if (!blk_rq_dma_map_iter_next(req, dma_dev, &iod->dma_state, iter)) return false; - if (!dma_use_iova(&iod->dma_state) && dma_need_unmap(dma_dev)) { - iod->dma_vecs[iod->nr_dma_vecs].addr = iter->addr; - iod->dma_vecs[iod->nr_dma_vecs].len = iter->len; - iod->nr_dma_vecs++; - } - return true; + return nvme_pci_prp_save_mapping(req, dma_dev, iter); } static blk_status_t nvme_pci_setup_data_prp(struct request *req, @@ -798,15 +819,8 @@ static blk_status_t nvme_pci_setup_data_prp(struct request *req, unsigned int prp_len, i; __le64 *prp_list; - if (!dma_use_iova(&iod->dma_state) && dma_need_unmap(nvmeq->dev->dev)) { - iod->dma_vecs = mempool_alloc(nvmeq->dev->dmavec_mempool, - GFP_ATOMIC); - if (!iod->dma_vecs) - return BLK_STS_RESOURCE; - iod->dma_vecs[0].addr = iter->addr; - iod->dma_vecs[0].len = iter->len; - iod->nr_dma_vecs = 1; - } + if (!nvme_pci_prp_save_mapping(req, nvmeq->dev->dev, iter)) + return iter->status; /* * PRP1 always points to the start of the DMA transfers. @@ -1148,6 +1162,7 @@ static blk_status_t nvme_prep_rq(struct request *req) iod->nr_descriptors = 0; iod->total_len = 0; iod->meta_total_len = 0; + iod->nr_dma_vecs = 0; ret = nvme_setup_cmd(req->q->queuedata, req); if (ret) @@ -1461,7 +1476,10 @@ static int nvme_pci_subsystem_reset(struct nvme_ctrl *ctrl) } writel(NVME_SUBSYS_RESET, dev->bar + NVME_REG_NSSR); - nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE); + + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING) || + !nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) + goto unlock; /* * Read controller status to flush the previous write and trigger a @@ -3917,6 +3935,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x1e49, 0x0041), /* ZHITAI TiPro7000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x1fa0, 0x2283), /* Wodposit WPBSNM8-256GTP */ + .driver_data = NVME_QUIRK_NO_SECONDARY_TEMP_THRESH, }, { PCI_DEVICE(0x025e, 0xf1ac), /* SOLIDIGM P44 pro SSDPFKKW020X7 */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0xc0a9, 0x540a), /* Crucial P2 */ diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 8d246b8ca604c5..0103815542d49f 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -180,9 +180,10 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts) static void nvmet_bio_done(struct bio *bio) { struct nvmet_req *req = bio->bi_private; + blk_status_t blk_status = bio->bi_status; - nvmet_req_complete(req, blk_to_nvme_status(req, bio->bi_status)); nvmet_req_bio_put(req, bio); + nvmet_req_complete(req, blk_to_nvme_status(req, blk_status)); } #ifdef CONFIG_BLK_DEV_INTEGRITY diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c index 2e78397a7373a7..9c5b0f78ce8dfc 100644 --- a/drivers/nvme/target/pci-epf.c +++ b/drivers/nvme/target/pci-epf.c @@ -2325,6 +2325,8 @@ static int nvmet_pci_epf_epc_init(struct pci_epf *epf) return ret; } + nvmet_pci_epf_init_dma(nvme_epf); + /* Set device ID, class, etc. */ epf->header->vendorid = ctrl->tctrl->subsys->vendor_id; epf->header->subsys_vendor_id = ctrl->tctrl->subsys->subsys_vendor_id; @@ -2422,8 +2424,6 @@ static int nvmet_pci_epf_bind(struct pci_epf *epf) if (ret) return ret; - nvmet_pci_epf_init_dma(nvme_epf); - return 0; } diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 470bf37e5a6372..5c8d17bcc49bd5 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -349,11 +349,14 @@ static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd) cmd->req.sg = NULL; } +static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue); + static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) { struct bio_vec *iov = cmd->iov; struct scatterlist *sg; u32 length, offset, sg_offset; + unsigned int sg_remaining; int nr_pages; length = cmd->pdu_len; @@ -361,9 +364,22 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) offset = cmd->rbytes_done; cmd->sg_idx = offset / PAGE_SIZE; sg_offset = offset % PAGE_SIZE; + if (!cmd->req.sg_cnt || cmd->sg_idx >= cmd->req.sg_cnt) { + nvmet_tcp_fatal_error(cmd->queue); + return; + } sg = &cmd->req.sg[cmd->sg_idx]; + sg_remaining = cmd->req.sg_cnt - cmd->sg_idx; while (length) { + if (!sg_remaining) { + nvmet_tcp_fatal_error(cmd->queue); + return; + } + if (!sg->length || sg->length <= sg_offset) { + nvmet_tcp_fatal_error(cmd->queue); + return; + } u32 iov_len = min_t(u32, length, sg->length - sg_offset); bvec_set_page(iov, sg_page(sg), iov_len, @@ -371,6 +387,7 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) length -= iov_len; sg = sg_next(sg); + sg_remaining--; iov++; sg_offset = 0; } @@ -982,6 +999,18 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len); goto err_proto; } + /* + * Ensure command data structures are initialized. We must check both + * cmd->req.sg and cmd->iov because they can have different NULL states: + * - Uninitialized commands: both NULL + * - READ commands: cmd->req.sg allocated, cmd->iov NULL + * - WRITE commands: both allocated + */ + if (unlikely(!cmd->req.sg || !cmd->iov)) { + pr_err("queue %d: H2CData PDU received for invalid command state (ttag %u)\n", + queue->idx, data->ttag); + goto err_proto; + } cmd->pdu_recv = 0; nvmet_tcp_build_pdu_iovec(cmd); queue->cmd = cmd; @@ -1992,14 +2021,13 @@ static void nvmet_tcp_listen_data_ready(struct sock *sk) trace_sk_data_ready(sk); + if (sk->sk_state != TCP_LISTEN) + return; + read_lock_bh(&sk->sk_callback_lock); port = sk->sk_user_data; - if (!port) - goto out; - - if (sk->sk_state == TCP_LISTEN) + if (port) queue_work(nvmet_wq, &port->accept_work); -out: read_unlock_bh(&sk->sk_callback_lock); } diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig index e0d88d3199c11a..11b098705ec629 100644 --- a/drivers/nvmem/Kconfig +++ b/drivers/nvmem/Kconfig @@ -30,7 +30,7 @@ source "drivers/nvmem/layouts/Kconfig" config NVMEM_AN8855_EFUSE tristate "Airoha AN8855 eFuse support" - depends on MFD_AIROHA_AN8855 || COMPILE_TEST + depends on COMPILE_TEST help Say y here to enable support for reading eFuses on Airoha AN8855 Switch. These are e.g. used to store factory programmed diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 387c88c5525954..19be16943ee66e 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -1618,12 +1618,14 @@ static void nvmem_shift_read_buffer_in_place(struct nvmem_cell_entry *cell, void *p = *b++ >> bit_offset; /* setup rest of the bytes if any */ - for (i = 1; i < cell->bytes; i++) { + for (i = 1; i < (cell->bytes - bytes_offset); i++) { /* Get bits from next byte and shift them towards msb */ *p++ |= *b << (BITS_PER_BYTE - bit_offset); *p = *b++ >> bit_offset; } + /* point to end of the buffer unused bits will be cleared */ + p = buf + cell->bytes - 1; } else if (p != b) { memmove(p, b, cell->bytes - bytes_offset); p += cell->bytes - 1; diff --git a/drivers/of/base.c b/drivers/of/base.c index 7043acd971a0fc..2fd27ea0310c5f 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1895,13 +1895,17 @@ void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)) end--; len = end - start; - if (kstrtoint(end, 10, &id) < 0) + if (kstrtoint(end, 10, &id) < 0) { + of_node_put(np); continue; + } /* Allocate an alias_prop with enough space for the stem */ ap = dt_alloc(sizeof(*ap) + len + 1, __alignof__(*ap)); - if (!ap) + if (!ap) { + of_node_put(np); continue; + } memset(ap, 0, sizeof(*ap) + len + 1); ap->alias = start; of_alias_add(ap, np, id, start, len); diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 0edd639898a63f..3851ce24458586 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -503,8 +503,8 @@ void __init early_init_fdt_scan_reserved_mem(void) if (!initial_boot_params) return; - fdt_scan_reserved_mem(); fdt_reserve_elfcorehdr(); + fdt_scan_reserved_mem(); /* Process header /memreserve/ fields */ for (n = 0; ; n++) { @@ -625,6 +625,47 @@ const void *__init of_get_flat_dt_prop(unsigned long node, const char *name, return fdt_getprop(initial_boot_params, node, name, size); } +const __be32 *__init of_flat_dt_get_addr_size_prop(unsigned long node, + const char *name, + int *entries) +{ + const __be32 *prop; + int len, elen = (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32); + + prop = of_get_flat_dt_prop(node, name, &len); + if (!prop || len % elen) { + *entries = 0; + return NULL; + } + + *entries = len / elen; + return prop; +} + +bool __init of_flat_dt_get_addr_size(unsigned long node, const char *name, + u64 *addr, u64 *size) +{ + const __be32 *prop; + int entries; + + prop = of_flat_dt_get_addr_size_prop(node, name, &entries); + if (!prop || entries != 1) + return false; + + of_flat_dt_read_addr_size(prop, 0, addr, size); + return true; +} + +void __init of_flat_dt_read_addr_size(const __be32 *prop, int entry_index, + u64 *addr, u64 *size) +{ + int entry_cells = dt_root_addr_cells + dt_root_size_cells; + prop += entry_cells * entry_index; + + *addr = dt_mem_next_cell(dt_root_addr_cells, &prop); + *size = dt_mem_next_cell(dt_root_size_cells, &prop); +} + /** * of_fdt_is_compatible - Return true if given node from the given blob has * compat in its compatible list @@ -812,21 +853,15 @@ static void __init early_init_dt_check_for_initrd(unsigned long node) */ static void __init early_init_dt_check_for_elfcorehdr(unsigned long node) { - const __be32 *prop; - int len; - if (!IS_ENABLED(CONFIG_CRASH_DUMP)) return; pr_debug("Looking for elfcorehdr property... "); - prop = of_get_flat_dt_prop(node, "linux,elfcorehdr", &len); - if (!prop || (len < (dt_root_addr_cells + dt_root_size_cells))) + if (!of_flat_dt_get_addr_size(node, "linux,elfcorehdr", + &elfcorehdr_addr, &elfcorehdr_size)) return; - elfcorehdr_addr = dt_mem_next_cell(dt_root_addr_cells, &prop); - elfcorehdr_size = dt_mem_next_cell(dt_root_size_cells, &prop); - pr_debug("elfcorehdr_start=0x%llx elfcorehdr_size=0x%llx\n", elfcorehdr_addr, elfcorehdr_size); } @@ -849,8 +884,9 @@ static unsigned long chosen_node_offset = -FDT_ERR_NOTFOUND; void __init early_init_dt_check_for_usable_mem_range(void) { struct memblock_region rgn[MAX_USABLE_RANGES] = {0}; - const __be32 *prop, *endp; + const __be32 *prop; int len, i; + u64 base, size; unsigned long node = chosen_node_offset; if ((long)node < 0) @@ -858,14 +894,17 @@ void __init early_init_dt_check_for_usable_mem_range(void) pr_debug("Looking for usable-memory-range property... "); - prop = of_get_flat_dt_prop(node, "linux,usable-memory-range", &len); - if (!prop || (len % (dt_root_addr_cells + dt_root_size_cells))) + prop = of_flat_dt_get_addr_size_prop(node, "linux,usable-memory-range", + &len); + if (!prop) return; - endp = prop + (len / sizeof(__be32)); - for (i = 0; i < MAX_USABLE_RANGES && prop < endp; i++) { - rgn[i].base = dt_mem_next_cell(dt_root_addr_cells, &prop); - rgn[i].size = dt_mem_next_cell(dt_root_size_cells, &prop); + len = min(len, MAX_USABLE_RANGES); + + for (i = 0; i < len; i++) { + of_flat_dt_read_addr_size(prop, i, &base, &size); + rgn[i].base = base; + rgn[i].size = size; pr_debug("cap_mem_regions[%d]: base=%pa, size=%pa\n", i, &rgn[i].base, &rgn[i].size); @@ -883,26 +922,18 @@ static void __init early_init_dt_check_kho(void) { unsigned long node = chosen_node_offset; u64 fdt_start, fdt_size, scratch_start, scratch_size; - const __be32 *p; - int l; if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER) || (long)node < 0) return; - p = of_get_flat_dt_prop(node, "linux,kho-fdt", &l); - if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32)) + if (!of_flat_dt_get_addr_size(node, "linux,kho-fdt", + &fdt_start, &fdt_size)) return; - fdt_start = dt_mem_next_cell(dt_root_addr_cells, &p); - fdt_size = dt_mem_next_cell(dt_root_addr_cells, &p); - - p = of_get_flat_dt_prop(node, "linux,kho-scratch", &l); - if (l != (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32)) + if (!of_flat_dt_get_addr_size(node, "linux,kho-scratch", + &scratch_start, &scratch_size)) return; - scratch_start = dt_mem_next_cell(dt_root_addr_cells, &p); - scratch_size = dt_mem_next_cell(dt_root_addr_cells, &p); - kho_populate(fdt_start, fdt_size, scratch_start, scratch_size); } diff --git a/drivers/of/of_kunit_helpers.c b/drivers/of/of_kunit_helpers.c index 7b3ed5a382aaa5..f6ed1af8b62aaf 100644 --- a/drivers/of/of_kunit_helpers.c +++ b/drivers/of/of_kunit_helpers.c @@ -18,8 +18,9 @@ */ void of_root_kunit_skip(struct kunit *test) { - if (IS_ENABLED(CONFIG_ARM64) && IS_ENABLED(CONFIG_ACPI) && !of_root) - kunit_skip(test, "arm64+acpi doesn't populate a root node"); + if ((IS_ENABLED(CONFIG_ARM64) || IS_ENABLED(CONFIG_RISCV)) && + IS_ENABLED(CONFIG_ACPI) && !of_root) + kunit_skip(test, "arm64/riscv+acpi doesn't populate a root node"); } EXPORT_SYMBOL_GPL(of_root_kunit_skip); diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 2e9ea751ed2df0..fe111d1ea73971 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -158,7 +158,7 @@ static int __init __reserved_mem_reserve_reg(unsigned long node, phys_addr_t base, size; int len; const __be32 *prop; - bool nomap; + bool nomap, default_cma; prop = of_get_flat_dt_prop(node, "reg", &len); if (!prop) @@ -171,6 +171,12 @@ static int __init __reserved_mem_reserve_reg(unsigned long node, } nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL; + default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL); + + if (default_cma && cma_skip_dt_default_reserved_mem()) { + pr_err("Skipping dt linux,cma-default for \"cma=\" kernel param.\n"); + return -EINVAL; + } while (len >= t_len) { base = dt_mem_next_cell(dt_root_addr_cells, &prop); @@ -230,12 +236,9 @@ static void __init __rmem_check_for_overlap(void); */ void __init fdt_scan_reserved_mem_reg_nodes(void) { - int t_len = (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32); const void *fdt = initial_boot_params; phys_addr_t base, size; - const __be32 *prop; int node, child; - int len; if (!fdt) return; @@ -256,29 +259,24 @@ void __init fdt_scan_reserved_mem_reg_nodes(void) fdt_for_each_subnode(child, fdt, node) { const char *uname; + bool default_cma = of_get_flat_dt_prop(child, "linux,cma-default", NULL); + u64 b, s; - prop = of_get_flat_dt_prop(child, "reg", &len); - if (!prop) - continue; if (!of_fdt_device_is_available(fdt, child)) continue; - - uname = fdt_get_name(fdt, child, NULL); - if (len && len % t_len != 0) { - pr_err("Reserved memory: invalid reg property in '%s', skipping node.\n", - uname); + if (default_cma && cma_skip_dt_default_reserved_mem()) continue; - } - if (len > t_len) - pr_warn("%s() ignores %d regions in node '%s'\n", - __func__, len / t_len - 1, uname); + if (!of_flat_dt_get_addr_size(child, "reg", &b, &s)) + continue; - base = dt_mem_next_cell(dt_root_addr_cells, &prop); - size = dt_mem_next_cell(dt_root_size_cells, &prop); + base = b; + size = s; - if (size) + if (size) { + uname = fdt_get_name(fdt, child, NULL); fdt_reserved_mem_save_node(child, uname, base, size); + } } /* check for overlapping reserved regions */ @@ -406,7 +404,7 @@ static int __init __reserved_mem_alloc_size(unsigned long node, const char *unam phys_addr_t base = 0, align = 0, size; int len; const __be32 *prop; - bool nomap; + bool nomap, default_cma; int ret; prop = of_get_flat_dt_prop(node, "size", &len); @@ -430,6 +428,12 @@ static int __init __reserved_mem_alloc_size(unsigned long node, const char *unam } nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL; + default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL); + + if (default_cma && cma_skip_dt_default_reserved_mem()) { + pr_err("Skipping dt linux,cma-default for \"cma=\" kernel param.\n"); + return -EINVAL; + } /* Need adjust the alignment to satisfy the CMA requirement */ if (IS_ENABLED(CONFIG_CMA) diff --git a/drivers/of/platform.c b/drivers/of/platform.c index f77cb19973a5d1..a6dca3a005aac9 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -569,7 +569,7 @@ static int __init of_platform_default_populate_init(void) node = of_find_node_by_path("/firmware"); if (node) { - of_platform_populate(node, NULL, NULL, NULL); + of_platform_default_populate(node, NULL, NULL); of_node_put(node); } diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 388e9ec2cccf83..9c184e93f50c67 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -804,11 +804,13 @@ static void __init of_unittest_property_copy(void) new = __of_prop_dup(&p1, GFP_KERNEL); unittest(new && propcmp(&p1, new), "empty property didn't copy correctly\n"); - __of_prop_free(new); + if (new) + __of_prop_free(new); new = __of_prop_dup(&p2, GFP_KERNEL); unittest(new && propcmp(&p2, new), "non-empty property didn't copy correctly\n"); - __of_prop_free(new); + if (new) + __of_prop_free(new); #endif } @@ -1985,7 +1987,6 @@ static void attach_node_and_children(struct device_node *np) */ static int __init unittest_data_add(void) { - void *unittest_data; void *unittest_data_align; struct device_node *unittest_data_node = NULL, *np; /* @@ -2004,7 +2005,7 @@ static int __init unittest_data_add(void) } /* creating copy */ - unittest_data = kmalloc(size + FDT_ALIGN_SIZE, GFP_KERNEL); + void *unittest_data __free(kfree) = kmalloc(size + FDT_ALIGN_SIZE, GFP_KERNEL); if (!unittest_data) return -ENOMEM; @@ -2014,12 +2015,10 @@ static int __init unittest_data_add(void) ret = of_fdt_unflatten_tree(unittest_data_align, NULL, &unittest_data_node); if (!ret) { pr_warn("%s: unflatten testcases tree failed\n", __func__); - kfree(unittest_data); return -ENODATA; } if (!unittest_data_node) { pr_warn("%s: testcases tree is empty\n", __func__); - kfree(unittest_data); return -ENODATA; } @@ -2038,7 +2037,6 @@ static int __init unittest_data_add(void) /* attach the sub-tree to live tree */ if (!of_root) { pr_warn("%s: no live tree to attach sub-tree\n", __func__); - kfree(unittest_data); rc = -ENODEV; goto unlock; } @@ -2059,6 +2057,8 @@ static int __init unittest_data_add(void) EXPECT_END(KERN_INFO, "Duplicate name in testcase-data, renamed to \"duplicate-name#1\""); + retain_and_null_ptr(unittest_data); + unlock: of_overlay_mutex_unlock(); diff --git a/drivers/opp/core.c b/drivers/opp/core.c index bba4f7daff8cb8..775d4a36f2f544 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -241,7 +241,7 @@ unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp) { if (IS_ERR_OR_NULL(opp) || !opp->available) { pr_err("%s: Invalid parameters\n", __func__); - return 0; + return U32_MAX; } return opp->level; diff --git a/drivers/parisc/gsc.c b/drivers/parisc/gsc.c index a0daaa548bc392..8ba778170447eb 100644 --- a/drivers/parisc/gsc.c +++ b/drivers/parisc/gsc.c @@ -154,7 +154,9 @@ static int gsc_set_affinity_irq(struct irq_data *d, const struct cpumask *dest, gsc_dev->eim = ((u32) gsc_dev->gsc_irq.txn_addr) | gsc_dev->gsc_irq.txn_data; /* switch IRQ's for devices below LASI/WAX to other CPU */ - gsc_writel(gsc_dev->eim, gsc_dev->hpa + OFFSET_IAR); + /* ASP chip (svers 0x70) does not support reprogramming */ + if (gsc_dev->gsc->id.sversion != 0x70) + gsc_writel(gsc_dev->eim, gsc_dev->hpa + OFFSET_IAR); irq_data_update_effective_affinity(d, &tmask); diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index f94f5d384362e5..47e466946bedb1 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -207,12 +207,6 @@ config PCI_P2PDMA P2P DMA transactions must be between devices behind the same root port. - Enabling this option will reduce the entropy of x86 KASLR memory - regions. For example - on a 46 bit system, the entropy goes down - from 16 bits to 15 bits. The actual reduction in entropy depends - on the physical address bits, on processor features, kernel config - (5 level page table) and physical memory present on the system. - If unsure, say N. config PCI_LABEL diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index f26aec6ff58899..9daf13ed3714e0 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -357,6 +357,9 @@ void pci_bus_add_device(struct pci_dev *dev) pci_proc_attach_device(dev); pci_bridge_d3_update(dev); + /* Save config space for error recoverability */ + pci_save_state(dev); + /* * If the PCI device is associated with a pwrctrl device with a * power supply, create a device link between the PCI device and diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index 41748d083b933d..31784cdb1b76e4 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -45,6 +45,7 @@ config PCIE_APPLE depends on ARCH_APPLE || COMPILE_TEST depends on OF depends on PCI_MSI + depends on PAGE_SIZE_16KB || COMPILE_TEST select PCI_HOST_COMMON select IRQ_MSI_LIB help @@ -259,12 +260,11 @@ config PCIE_RCAR_EP config PCI_RCAR_GEN2 bool "Renesas R-Car Gen2 Internal PCI controller" - depends on ARCH_RENESAS || COMPILE_TEST - depends on ARM + depends on (ARCH_RENESAS && ARM) || COMPILE_TEST help Say Y here if you want internal PCI support on R-Car Gen2 SoC. - There are 3 internal PCI controllers available with a single - built-in EHCI/OHCI host controller present on each one. + Each internal PCI controller contains a single built-in EHCI/OHCI + host controller. config PCIE_ROCKCHIP bool diff --git a/drivers/pci/controller/cadence/pcie-sg2042.c b/drivers/pci/controller/cadence/pcie-sg2042.c index a077b28d489494..0c50c74d03eeb2 100644 --- a/drivers/pci/controller/cadence/pcie-sg2042.c +++ b/drivers/pci/controller/cadence/pcie-sg2042.c @@ -74,15 +74,12 @@ static int sg2042_pcie_probe(struct platform_device *pdev) static void sg2042_pcie_remove(struct platform_device *pdev) { struct cdns_pcie *pcie = platform_get_drvdata(pdev); - struct device *dev = &pdev->dev; struct cdns_pcie_rc *rc; rc = container_of(pcie, struct cdns_pcie_rc, pcie); cdns_pcie_host_disable(rc); cdns_pcie_disable_phy(pcie); - - pm_runtime_disable(dev); } static int sg2042_pcie_suspend_noirq(struct device *dev) diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c index eb00aa38072201..25b8193ffbcf12 100644 --- a/drivers/pci/controller/dwc/pci-keystone.c +++ b/drivers/pci/controller/dwc/pci-keystone.c @@ -1337,6 +1337,8 @@ static int ks_pcie_probe(struct platform_device *pdev) break; default: dev_err(dev, "INVALID device type %d\n", mode); + ret = -EINVAL; + goto err_get_sync; } ks_pcie_enable_error_irq(ks_pcie); diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c index 787469d1b396d4..0694084f612b79 100644 --- a/drivers/pci/controller/dwc/pci-meson.c +++ b/drivers/pci/controller/dwc/pci-meson.c @@ -37,7 +37,6 @@ #define PCIE_CFG_STATUS17 0x44 #define PM_CURRENT_STATE(x) (((x) >> 7) & 0x1) -#define WAIT_LINKUP_TIMEOUT 4000 #define PORT_CLK_RATE 100000000UL #define MAX_PAYLOAD_SIZE 256 #define MAX_READ_REQ_SIZE 256 @@ -108,10 +107,22 @@ static int meson_pcie_get_mems(struct platform_device *pdev, struct meson_pcie *mp) { struct dw_pcie *pci = &mp->pci; + struct resource *res; - pci->dbi_base = devm_platform_ioremap_resource_byname(pdev, "elbi"); - if (IS_ERR(pci->dbi_base)) - return PTR_ERR(pci->dbi_base); + /* + * For the broken DTs that supply 'dbi' as 'elbi', parse the 'elbi' + * region and assign it to both 'pci->elbi_base' and 'pci->dbi_space' so + * that the DWC core can skip parsing both regions. + */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "elbi"); + if (res) { + pci->elbi_base = devm_pci_remap_cfg_resource(pci->dev, res); + if (IS_ERR(pci->elbi_base)) + return PTR_ERR(pci->elbi_base); + + pci->dbi_base = pci->elbi_base; + pci->dbi_phys_addr = res->start; + } mp->cfg_base = devm_platform_ioremap_resource_byname(pdev, "cfg"); if (IS_ERR(mp->cfg_base)) @@ -338,40 +349,10 @@ static struct pci_ops meson_pci_ops = { static bool meson_pcie_link_up(struct dw_pcie *pci) { struct meson_pcie *mp = to_meson_pcie(pci); - struct device *dev = pci->dev; - u32 speed_okay = 0; - u32 cnt = 0; - u32 state12, state17, smlh_up, ltssm_up, rdlh_up; - - do { - state12 = meson_cfg_readl(mp, PCIE_CFG_STATUS12); - state17 = meson_cfg_readl(mp, PCIE_CFG_STATUS17); - smlh_up = IS_SMLH_LINK_UP(state12); - rdlh_up = IS_RDLH_LINK_UP(state12); - ltssm_up = IS_LTSSM_UP(state12); - - if (PM_CURRENT_STATE(state17) < PCIE_GEN3) - speed_okay = 1; - - if (smlh_up) - dev_dbg(dev, "smlh_link_up is on\n"); - if (rdlh_up) - dev_dbg(dev, "rdlh_link_up is on\n"); - if (ltssm_up) - dev_dbg(dev, "ltssm_up is on\n"); - if (speed_okay) - dev_dbg(dev, "speed_okay\n"); - - if (smlh_up && rdlh_up && ltssm_up && speed_okay) - return true; - - cnt++; - - udelay(10); - } while (cnt < WAIT_LINKUP_TIMEOUT); - - dev_err(dev, "error: wait linkup timeout\n"); - return false; + u32 state12; + + state12 = meson_cfg_readl(mp, PCIE_CFG_STATUS12); + return IS_SMLH_LINK_UP(state12) && IS_RDLH_LINK_UP(state12); } static int meson_pcie_host_init(struct dw_pcie_rp *pp) diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index c644216995f69c..06eca858eb1b3c 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -168,11 +168,13 @@ int dw_pcie_get_resources(struct dw_pcie *pci) } /* ELBI is an optional resource */ - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "elbi"); - if (res) { - pci->elbi_base = devm_ioremap_resource(pci->dev, res); - if (IS_ERR(pci->elbi_base)) - return PTR_ERR(pci->elbi_base); + if (!pci->elbi_base) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "elbi"); + if (res) { + pci->elbi_base = devm_ioremap_resource(pci->dev, res); + if (IS_ERR(pci->elbi_base)) + return PTR_ERR(pci->elbi_base); + } } /* LLDD is supposed to manually switch the clocks and resets state */ diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index e995f692a1ecd1..24bfa5231923a1 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -97,7 +97,7 @@ #define PORT_LANE_SKEW_INSERT_MASK GENMASK(23, 0) #define PCIE_PORT_DEBUG0 0x728 -#define PORT_LOGIC_LTSSM_STATE_MASK 0x1f +#define PORT_LOGIC_LTSSM_STATE_MASK 0x3f #define PORT_LOGIC_LTSSM_STATE_L0 0x11 #define PCIE_PORT_DEBUG1 0x72C #define PCIE_PORT_DEBUG1_LINK_UP BIT(4) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index c48a20602d7fa4..6e820595ba32a9 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -1033,7 +1033,6 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie) writel(WR_NO_SNOOP_OVERRIDE_EN | RD_NO_SNOOP_OVERRIDE_EN, pcie->parf + PARF_NO_SNOOP_OVERRIDE); - qcom_pcie_clear_aspm_l0s(pcie->pci); qcom_pcie_clear_hpc(pcie->pci); return 0; @@ -1302,6 +1301,8 @@ static int qcom_pcie_host_init(struct dw_pcie_rp *pp) goto err_disable_phy; } + qcom_pcie_clear_aspm_l0s(pcie->pci); + qcom_ep_reset_deassert(pcie); if (pcie->cfg->ops->config_sid) { @@ -1450,6 +1451,7 @@ static const struct qcom_pcie_cfg cfg_2_1_0 = { static const struct qcom_pcie_cfg cfg_2_3_2 = { .ops = &ops_2_3_2, + .no_l0s = true, }; static const struct qcom_pcie_cfg cfg_2_3_3 = { diff --git a/drivers/pci/controller/dwc/pcie-sophgo.c b/drivers/pci/controller/dwc/pcie-sophgo.c index ad4baaa34ffa1d..044088898819e5 100644 --- a/drivers/pci/controller/dwc/pcie-sophgo.c +++ b/drivers/pci/controller/dwc/pcie-sophgo.c @@ -161,6 +161,22 @@ static void sophgo_pcie_msi_enable(struct dw_pcie_rp *pp) raw_spin_unlock_irqrestore(&pp->lock, flags); } +static void sophgo_pcie_disable_l0s_l1(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + u32 offset, val; + + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + + dw_pcie_dbi_ro_wr_en(pci); + + val = dw_pcie_readl_dbi(pci, PCI_EXP_LNKCAP + offset); + val &= ~(PCI_EXP_LNKCAP_ASPM_L0S | PCI_EXP_LNKCAP_ASPM_L1); + dw_pcie_writel_dbi(pci, PCI_EXP_LNKCAP + offset, val); + + dw_pcie_dbi_ro_wr_dis(pci); +} + static int sophgo_pcie_host_init(struct dw_pcie_rp *pp) { int irq; @@ -171,6 +187,8 @@ static int sophgo_pcie_host_init(struct dw_pcie_rp *pp) irq_set_chained_handler_and_data(irq, sophgo_pcie_intx_handler, pp); + sophgo_pcie_disable_l0s_l1(pp); + sophgo_pcie_msi_enable(pp); return 0; diff --git a/drivers/pci/controller/dwc/pcie-stm32-ep.c b/drivers/pci/controller/dwc/pcie-stm32-ep.c index 3400c7cd2d88a2..7d48038d576d90 100644 --- a/drivers/pci/controller/dwc/pcie-stm32-ep.c +++ b/drivers/pci/controller/dwc/pcie-stm32-ep.c @@ -37,36 +37,9 @@ static void stm32_pcie_ep_init(struct dw_pcie_ep *ep) dw_pcie_ep_reset_bar(pci, bar); } -static int stm32_pcie_enable_link(struct dw_pcie *pci) -{ - struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); - - regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, - STM32MP25_PCIECR_LTSSM_EN, - STM32MP25_PCIECR_LTSSM_EN); - - return dw_pcie_wait_for_link(pci); -} - -static void stm32_pcie_disable_link(struct dw_pcie *pci) -{ - struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); - - regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, STM32MP25_PCIECR_LTSSM_EN, 0); -} - static int stm32_pcie_start_link(struct dw_pcie *pci) { struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); - int ret; - - dev_dbg(pci->dev, "Enable link\n"); - - ret = stm32_pcie_enable_link(pci); - if (ret) { - dev_err(pci->dev, "PCIe cannot establish link: %d\n", ret); - return ret; - } enable_irq(stm32_pcie->perst_irq); @@ -77,11 +50,7 @@ static void stm32_pcie_stop_link(struct dw_pcie *pci) { struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); - dev_dbg(pci->dev, "Disable link\n"); - disable_irq(stm32_pcie->perst_irq); - - stm32_pcie_disable_link(pci); } static int stm32_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, @@ -152,6 +121,9 @@ static void stm32_pcie_perst_assert(struct dw_pcie *pci) dev_dbg(dev, "PERST asserted by host\n"); + regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_LTSSM_EN, 0); + pci_epc_deinit_notify(ep->epc); stm32_pcie_disable_resources(stm32_pcie); @@ -192,6 +164,11 @@ static void stm32_pcie_perst_deassert(struct dw_pcie *pci) pci_epc_init_notify(ep->epc); + /* Enable link training */ + regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_LTSSM_EN, + STM32MP25_PCIECR_LTSSM_EN); + return; err_disable_resources: @@ -237,6 +214,8 @@ static int stm32_add_pcie_ep(struct stm32_pcie *stm32_pcie, ep->ops = &stm32_pcie_ep_ops; + ep->page_size = stm32_pcie_epc_features.align; + ret = dw_pcie_ep_init(ep); if (ret) { dev_err(dev, "Failed to initialize ep: %d\n", ret); diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c index 0380d300adca6f..05c5dd47f32e72 100644 --- a/drivers/pci/controller/pcie-apple.c +++ b/drivers/pci/controller/pcie-apple.c @@ -33,6 +33,10 @@ #include "pci-host-common.h" +static int link_up_timeout = 500; +module_param(link_up_timeout, int, 0644); +MODULE_PARM_DESC(link_up_timeout, "PCIe link training timeout in milliseconds"); + /* T8103 (original M1) and related SoCs */ #define CORE_RC_PHYIF_CTL 0x00024 #define CORE_RC_PHYIF_CTL_RUN BIT(0) @@ -554,22 +558,105 @@ static u32 apple_pcie_rid2sid_write(struct apple_pcie_port *port, return readl_relaxed(port_rid2sid_addr(port, idx)); } +static int apple_pcie_setup_link(struct apple_pcie *pcie, + struct apple_pcie_port *port, + struct device_node *np) +{ +#define MAX_AUX_PERST 3 + struct gpio_desc *aux_reset[MAX_AUX_PERST] = { NULL }; + u32 num_aux_resets = 0; + struct gpio_desc *reset, *pwren = NULL; + u32 stat; + int ret; + + /* + * Assert PERST# and configure the pin as output. + * The Aquantia AQC113 10GB nic used desktop macs is sensitive to + * deasserting it without prior clock setup. + * Observed on M1 Max/Ultra Mac Studios under m1n1's hypervisor. + */ + reset = devm_fwnode_gpiod_get(pcie->dev, of_fwnode_handle(np), "reset", + GPIOD_OUT_HIGH, "PERST#"); + if (IS_ERR(reset)) + return PTR_ERR(reset); + // HACK: use additional "reset-gpios" until pci-pwrctrl gains PERST# support. + for (u32 idx = 0; idx < MAX_AUX_PERST; idx++) { + aux_reset[idx] = devm_fwnode_gpiod_get_index(pcie->dev, + of_fwnode_handle(np), + "reset", idx + 1, + GPIOD_OUT_HIGH, + "PERST#"); + if (IS_ERR(aux_reset[idx])) { + if (PTR_ERR(aux_reset[idx]) == -ENOENT) + break; + else + return PTR_ERR(aux_reset[idx]); + } + num_aux_resets++; + } + dev_info(pcie->dev, "Using %u auxiliary PERST#\n", num_aux_resets); + + pwren = devm_fwnode_gpiod_get(pcie->dev, of_fwnode_handle(np), "pwren", + GPIOD_ASIS, "PWREN"); + if (IS_ERR(pwren)) { + if (PTR_ERR(pwren) == -ENOENT) + pwren = NULL; + else + return PTR_ERR(pwren); + } + + rmw_set(PORT_APPCLK_EN, port->base + PORT_APPCLK); + + /* Assert PERST# before setting up the clock */ + gpiod_set_value_cansleep(reset, 1); + for (u32 idx = 0; idx < num_aux_resets; idx++) + gpiod_set_value_cansleep(aux_reset[idx], 1); + + /* Power on the device if required */ + gpiod_set_value_cansleep(pwren, 1); + + ret = apple_pcie_setup_refclk(pcie, port); + if (ret < 0) + return ret; + + /* + * The minimal Tperst-clk value is 100us (PCIe CEM r5.0, 2.9.2) + * If powering up, the minimal Tpvperl is 100ms + */ + if (pwren) + msleep(100); + else + usleep_range(100, 200); + + /* Deassert PERST# */ + rmw_set(PORT_PERST_OFF, port->base + pcie->hw->port_perst); + gpiod_set_value_cansleep(reset, 0); + for (u32 idx = 0; idx < num_aux_resets; idx++) + gpiod_set_value_cansleep(aux_reset[idx], 0); + + /* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */ + msleep(100); + + ret = readl_relaxed_poll_timeout(port->base + PORT_STATUS, stat, + stat & PORT_STATUS_READY, 100, 250000); + if (ret < 0) { + dev_err(pcie->dev, "port %pOF ready wait timeout\n", np); + return ret; + } + + return 0; +} + static int apple_pcie_setup_port(struct apple_pcie *pcie, struct device_node *np) { struct platform_device *platform = to_platform_device(pcie->dev); struct apple_pcie_port *port; - struct gpio_desc *reset; struct resource *res; char name[16]; - u32 stat, idx; + u32 link_stat, idx; int ret, i; - reset = devm_fwnode_gpiod_get(pcie->dev, of_fwnode_handle(np), "reset", - GPIOD_OUT_LOW, "PERST#"); - if (IS_ERR(reset)) - return PTR_ERR(reset); - port = devm_kzalloc(pcie->dev, sizeof(*port), GFP_KERNEL); if (!port) return -ENOMEM; @@ -605,30 +692,12 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, else port->phy = pcie->base + CORE_PHY_DEFAULT_BASE(port->idx); - rmw_set(PORT_APPCLK_EN, port->base + PORT_APPCLK); - - /* Assert PERST# before setting up the clock */ - gpiod_set_value_cansleep(reset, 1); - - ret = apple_pcie_setup_refclk(pcie, port); - if (ret < 0) - return ret; - - /* The minimal Tperst-clk value is 100us (PCIe CEM r5.0, 2.9.2) */ - usleep_range(100, 200); - - /* Deassert PERST# */ - rmw_set(PORT_PERST_OFF, port->base + pcie->hw->port_perst); - gpiod_set_value_cansleep(reset, 0); - - /* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */ - msleep(100); - - ret = readl_relaxed_poll_timeout(port->base + PORT_STATUS, stat, - stat & PORT_STATUS_READY, 100, 250000); - if (ret < 0) { - dev_err(pcie->dev, "port %pOF ready wait timeout\n", np); - return ret; + /* link might be already brought up by u-boot, skip setup then */ + link_stat = readl_relaxed(port->base + PORT_LINKSTS); + if (!(link_stat & PORT_LINKSTS_UP)) { + ret = apple_pcie_setup_link(pcie, port, np); + if (ret) + return ret; } if (pcie->hw->port_refclk) @@ -662,10 +731,21 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, ret = apple_pcie_port_register_irqs(port); WARN_ON(ret); - writel_relaxed(PORT_LTSSMCTL_START, port->base + PORT_LTSSMCTL); + link_stat = readl_relaxed(port->base + PORT_LINKSTS); + if (!(link_stat & PORT_LINKSTS_UP)) { + unsigned long timeout, left; + /* start link training */ + writel_relaxed(PORT_LTSSMCTL_START, port->base + PORT_LTSSMCTL); - if (!wait_for_completion_timeout(&pcie->event, HZ / 10)) - dev_warn(pcie->dev, "%pOF link didn't come up\n", np); + timeout = link_up_timeout * HZ / 1000; + left = wait_for_completion_timeout(&pcie->event, timeout); + if (!left) + dev_warn(pcie->dev, "%pOF link didn't come up\n", np); + else + dev_info(pcie->dev, "%pOF link up after %ldms\n", np, + (timeout - left) * 1000 / HZ); + + } return 0; } @@ -872,12 +952,46 @@ static const struct pci_ecam_ops apple_pcie_cfg_ecam_ops = { } }; +static int apple_pcie_probe_port(struct device_node *np) +{ + struct gpio_desc *gd; + + /* check whether the GPPIO pin exists but leave it as is */ + gd = fwnode_gpiod_get_index(of_fwnode_handle(np), "reset", 0, + GPIOD_ASIS, "PERST#"); + if (IS_ERR(gd)) + return PTR_ERR(gd); + + gpiod_put(gd); + + gd = fwnode_gpiod_get_index(of_fwnode_handle(np), "pwren", 0, + GPIOD_ASIS, "PWREN"); + if (IS_ERR(gd)) { + if (PTR_ERR(gd) != -ENOENT) + return PTR_ERR(gd); + } else { + gpiod_put(gd); + } + + return 0; +} + static int apple_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; + struct device_node *of_port; struct apple_pcie *pcie; int ret; + /* Check for probe dependencies for all ports first */ + for_each_available_child_of_node(dev->of_node, of_port) { + ret = apple_pcie_probe_port(of_port); + if (ret) { + of_node_put(of_port); + return dev_err_probe(dev, ret, "Port %pOF probe fail\n", of_port); + } + } + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); if (!pcie) return -ENOMEM; diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c index 9afbd02ded35ee..7e9b2f6a604a5a 100644 --- a/drivers/pci/controller/pcie-brcmstb.c +++ b/drivers/pci/controller/pcie-brcmstb.c @@ -48,7 +48,6 @@ #define PCIE_RC_CFG_PRIV1_LINK_CAPABILITY 0x04dc #define PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_MAX_LINK_WIDTH_MASK 0x1f0 -#define PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_ASPM_SUPPORT_MASK 0xc00 #define PCIE_RC_CFG_PRIV1_ROOT_CAP 0x4f8 #define PCIE_RC_CFG_PRIV1_ROOT_CAP_L1SS_MODE_MASK 0xf8 @@ -1075,7 +1074,7 @@ static int brcm_pcie_setup(struct brcm_pcie *pcie) void __iomem *base = pcie->base; struct pci_host_bridge *bridge; struct resource_entry *entry; - u32 tmp, burst, aspm_support, num_lanes, num_lanes_cap; + u32 tmp, burst, num_lanes, num_lanes_cap; u8 num_out_wins = 0; int num_inbound_wins = 0; int memc, ret; @@ -1175,12 +1174,9 @@ static int brcm_pcie_setup(struct brcm_pcie *pcie) /* Don't advertise L0s capability if 'aspm-no-l0s' */ - aspm_support = PCIE_LINK_STATE_L1; - if (!of_property_read_bool(pcie->np, "aspm-no-l0s")) - aspm_support |= PCIE_LINK_STATE_L0S; tmp = readl(base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY); - u32p_replace_bits(&tmp, aspm_support, - PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_ASPM_SUPPORT_MASK); + if (of_property_read_bool(pcie->np, "aspm-no-l0s")) + tmp &= ~PCI_EXP_LNKCAP_ASPM_L0S; writel(tmp, base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY); /* 'tmp' still holds the contents of PRIV1_LINK_CAPABILITY */ diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index 24cc30a2ab6c66..e0bf667c2b4c6c 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -575,8 +575,10 @@ static int mtk_pcie_init_irq_domain(struct mtk_pcie_port *port, if (IS_ENABLED(CONFIG_PCI_MSI)) { ret = mtk_pcie_allocate_msi_domains(port); - if (ret) + if (ret) { + irq_domain_remove(port->irq_domain); return ret; + } } return 0; diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c index 937ea6ae1ac486..4aa139abac16e8 100644 --- a/drivers/pci/controller/pcie-xilinx.c +++ b/drivers/pci/controller/pcie-xilinx.c @@ -302,9 +302,10 @@ static int xilinx_allocate_msi_domains(struct xilinx_pcie *pcie) return 0; } -static void xilinx_free_msi_domains(struct xilinx_pcie *pcie) +static void xilinx_free_irq_domains(struct xilinx_pcie *pcie) { irq_domain_remove(pcie->msi_domain); + irq_domain_remove(pcie->leg_domain); } /* INTx Functions */ @@ -480,8 +481,10 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie *pcie) phys_addr_t pa = ALIGN_DOWN(virt_to_phys(pcie), SZ_4K); ret = xilinx_allocate_msi_domains(pcie); - if (ret) + if (ret) { + irq_domain_remove(pcie->leg_domain); return ret; + } pcie_write(pcie, upper_32_bits(pa), XILINX_PCIE_REG_MSIBASE1); pcie_write(pcie, lower_32_bits(pa), XILINX_PCIE_REG_MSIBASE2); @@ -600,7 +603,7 @@ static int xilinx_pcie_probe(struct platform_device *pdev) err = pci_host_probe(bridge); if (err) - xilinx_free_msi_domains(pcie); + xilinx_free_irq_domains(pcie); return err; } diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index 31617772ad5165..b05e8db575c353 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -730,8 +730,9 @@ static void pci_epf_test_enable_doorbell(struct pci_epf_test *epf_test, if (bar < BAR_0) goto err_doorbell_cleanup; - ret = request_irq(epf->db_msg[0].virq, pci_epf_test_doorbell_handler, 0, - "pci-ep-test-doorbell", epf_test); + ret = request_threaded_irq(epf->db_msg[0].virq, NULL, + pci_epf_test_doorbell_handler, IRQF_ONESHOT, + "pci-ep-test-doorbell", epf_test); if (ret) { dev_err(&epf->dev, "Failed to request doorbell IRQ: %d\n", diff --git a/drivers/pci/endpoint/pci-ep-cfs.c b/drivers/pci/endpoint/pci-ep-cfs.c index ef50c82e647f4d..43feb6139fa36c 100644 --- a/drivers/pci/endpoint/pci-ep-cfs.c +++ b/drivers/pci/endpoint/pci-ep-cfs.c @@ -23,7 +23,6 @@ struct pci_epf_group { struct config_group group; struct config_group primary_epc_group; struct config_group secondary_epc_group; - struct delayed_work cfs_work; struct pci_epf *epf; int index; }; @@ -103,7 +102,7 @@ static struct config_group secondary_epc_group = &epf_group->secondary_epc_group; config_group_init_type_name(secondary_epc_group, "secondary", &pci_secondary_epc_type); - configfs_register_group(&epf_group->group, secondary_epc_group); + configfs_add_default_group(secondary_epc_group, &epf_group->group); return secondary_epc_group; } @@ -166,7 +165,7 @@ static struct config_group config_group_init_type_name(primary_epc_group, "primary", &pci_primary_epc_type); - configfs_register_group(&epf_group->group, primary_epc_group); + configfs_add_default_group(primary_epc_group, &epf_group->group); return primary_epc_group; } @@ -570,15 +569,13 @@ static void pci_ep_cfs_add_type_group(struct pci_epf_group *epf_group) return; } - configfs_register_group(&epf_group->group, group); + configfs_add_default_group(group, &epf_group->group); } -static void pci_epf_cfs_work(struct work_struct *work) +static void pci_epf_cfs_add_sub_groups(struct pci_epf_group *epf_group) { - struct pci_epf_group *epf_group; struct config_group *group; - epf_group = container_of(work, struct pci_epf_group, cfs_work.work); group = pci_ep_cfs_add_primary_group(epf_group); if (IS_ERR(group)) { pr_err("failed to create 'primary' EPC interface\n"); @@ -637,9 +634,7 @@ static struct config_group *pci_epf_make(struct config_group *group, kfree(epf_name); - INIT_DELAYED_WORK(&epf_group->cfs_work, pci_epf_cfs_work); - queue_delayed_work(system_wq, &epf_group->cfs_work, - msecs_to_jiffies(1)); + pci_epf_cfs_add_sub_groups(epf_group); return &epf_group->group; diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 78e108e47254ab..49e395eb013d38 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -147,11 +147,19 @@ static int p2pmem_alloc_mmap(struct file *filp, struct kobject *kobj, * we have just allocated the page no one else should be * using it. */ - VM_WARN_ON_ONCE_PAGE(!page_ref_count(page), page); + VM_WARN_ON_ONCE_PAGE(page_ref_count(page), page); set_page_count(page, 1); ret = vm_insert_page(vma, vaddr, page); if (ret) { gen_pool_free(p2pdma->pool, (uintptr_t)kaddr, len); + + /* + * Reset the page count. We don't use put_page() + * because we don't want to trigger the + * p2pdma_folio_free() path. + */ + set_page_count(page, 0); + percpu_ref_put(ref); return ret; } percpu_ref_get(ref); diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 9369377725fa03..0162acfb57896b 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -271,21 +271,6 @@ static acpi_status decode_type1_hpx_record(union acpi_object *record, return AE_OK; } -static bool pcie_root_rcb_set(struct pci_dev *dev) -{ - struct pci_dev *rp = pcie_find_root_port(dev); - u16 lnkctl; - - if (!rp) - return false; - - pcie_capability_read_word(rp, PCI_EXP_LNKCTL, &lnkctl); - if (lnkctl & PCI_EXP_LNKCTL_RCB) - return true; - - return false; -} - /* _HPX PCI Express Setting Record (Type 2) */ struct hpx_type2 { u32 revision; @@ -311,6 +296,7 @@ static void program_hpx_type2(struct pci_dev *dev, struct hpx_type2 *hpx) { int pos; u32 reg32; + const struct pci_host_bridge *host; if (!hpx) return; @@ -318,6 +304,15 @@ static void program_hpx_type2(struct pci_dev *dev, struct hpx_type2 *hpx) if (!pci_is_pcie(dev)) return; + host = pci_find_host_bridge(dev->bus); + + /* + * Only do the _HPX Type 2 programming if OS owns PCIe native + * hotplug but not AER. + */ + if (!host->native_pcie_hotplug || host->native_aer) + return; + if (hpx->revision > 1) { pci_warn(dev, "PCIe settings rev %d not supported\n", hpx->revision); @@ -325,33 +320,27 @@ static void program_hpx_type2(struct pci_dev *dev, struct hpx_type2 *hpx) } /* - * Don't allow _HPX to change MPS or MRRS settings. We manage - * those to make sure they're consistent with the rest of the - * platform. + * We only allow _HPX to program DEVCTL bits related to AER, namely + * PCI_EXP_DEVCTL_CERE, PCI_EXP_DEVCTL_NFERE, PCI_EXP_DEVCTL_FERE, + * and PCI_EXP_DEVCTL_URRE. + * + * The rest of DEVCTL is managed by the OS to make sure it's + * consistent with the rest of the platform. */ - hpx->pci_exp_devctl_and |= PCI_EXP_DEVCTL_PAYLOAD | - PCI_EXP_DEVCTL_READRQ; - hpx->pci_exp_devctl_or &= ~(PCI_EXP_DEVCTL_PAYLOAD | - PCI_EXP_DEVCTL_READRQ); + hpx->pci_exp_devctl_and |= ~PCI_EXP_AER_FLAGS; + hpx->pci_exp_devctl_or &= PCI_EXP_AER_FLAGS; /* Initialize Device Control Register */ pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL, ~hpx->pci_exp_devctl_and, hpx->pci_exp_devctl_or); - /* Initialize Link Control Register */ + /* Log if _HPX attempts to modify Link Control Register */ if (pcie_cap_has_lnkctl(dev)) { - - /* - * If the Root Port supports Read Completion Boundary of - * 128, set RCB to 128. Otherwise, clear it. - */ - hpx->pci_exp_lnkctl_and |= PCI_EXP_LNKCTL_RCB; - hpx->pci_exp_lnkctl_or &= ~PCI_EXP_LNKCTL_RCB; - if (pcie_root_rcb_set(dev)) - hpx->pci_exp_lnkctl_or |= PCI_EXP_LNKCTL_RCB; - - pcie_capability_clear_and_set_word(dev, PCI_EXP_LNKCTL, - ~hpx->pci_exp_lnkctl_and, hpx->pci_exp_lnkctl_or); + if (hpx->pci_exp_lnkctl_and != 0xffff || + hpx->pci_exp_lnkctl_or != 0) + pci_info(dev, "_HPX attempts Link Control setting (AND %#06x OR %#06x)\n", + hpx->pci_exp_lnkctl_and, + hpx->pci_exp_lnkctl_or); } /* Find Advanced Error Reporting Enhanced Capability */ diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 302d61783f6c04..327b21c48614db 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -629,6 +629,8 @@ static int pci_legacy_suspend(struct device *dev, pm_message_t state) struct pci_dev *pci_dev = to_pci_dev(dev); struct pci_driver *drv = pci_dev->driver; + pci_dev->state_saved = false; + if (drv && drv->suspend) { pci_power_t prev = pci_dev->current_state; int error; @@ -1036,6 +1038,8 @@ static int pci_pm_freeze(struct device *dev) if (!pm) { pci_pm_default_suspend(pci_dev); + if (!pm_runtime_suspended(dev)) + pci_dev->state_saved = false; return 0; } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index b14dd064006cca..82e323b5aaa25c 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1488,6 +1488,9 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state, bool || (state == PCI_D2 && !dev->d2_support)) return -EIO; + if (dev->current_state == state) + return 0; + pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); if (PCI_POSSIBLE_ERROR(pmcsr)) { pci_err(dev, "Unable to change power state from %s to %s, device inaccessible\n", @@ -1855,9 +1858,6 @@ static void pci_restore_rebar_state(struct pci_dev *pdev) */ void pci_restore_state(struct pci_dev *dev) { - if (!dev->state_saved) - return; - pci_restore_pcie_state(dev); pci_restore_pasid_state(dev); pci_restore_pri_state(dev); @@ -6717,7 +6717,7 @@ static void of_pci_bus_release_domain_nr(struct device *parent, int domain_nr) return; /* Release domain from IDA where it was allocated. */ - if (of_get_pci_domain_nr(parent->of_node) == domain_nr) + if (parent && of_get_pci_domain_nr(parent->of_node) == domain_nr) ida_free(&pci_domain_nr_static_ida, domain_nr); else ida_free(&pci_domain_nr_dynamic_ida, domain_nr); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 36f8c0985430a4..565acfcd7cdb14 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -88,6 +88,9 @@ struct pcie_tlp_log; #define PCI_BUS_BRIDGE_MEM_WINDOW 1 #define PCI_BUS_BRIDGE_PREF_MEM_WINDOW 2 +#define PCI_EXP_AER_FLAGS (PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \ + PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE) + extern const unsigned char pcie_link_speed[]; extern bool pci_early_dump; diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 0b5ed4722ac323..23bead9415fcd1 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -238,9 +238,6 @@ void pcie_ecrc_get_policy(char *str) } #endif /* CONFIG_PCIE_ECRC */ -#define PCI_EXP_AER_FLAGS (PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \ - PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE) - int pcie_aer_is_native(struct pci_dev *dev) { struct pci_host_bridge *host = pci_find_host_bridge(dev->bus); diff --git a/drivers/pci/pcie/portdrv.c b/drivers/pci/pcie/portdrv.c index d1b68c18444f80..a0991da4821363 100644 --- a/drivers/pci/pcie/portdrv.c +++ b/drivers/pci/pcie/portdrv.c @@ -557,10 +557,10 @@ static int pcie_port_remove_service(struct device *dev) pciedev = to_pcie_device(dev); driver = to_service_driver(dev->driver); - if (driver && driver->remove) { + if (driver && driver->remove) driver->remove(pciedev); - put_device(dev); - } + + put_device(dev); return 0; } @@ -760,7 +760,6 @@ static pci_ers_result_t pcie_portdrv_slot_reset(struct pci_dev *dev) device_for_each_child(&dev->dev, &off, pcie_port_device_iter); pci_restore_state(dev); - pci_save_state(dev); return PCI_ERS_RESULT_RECOVERED; } diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c index 65e4b008be00df..41d370f082ee41 100644 --- a/drivers/pci/pcie/ptm.c +++ b/drivers/pci/pcie/ptm.c @@ -519,8 +519,10 @@ struct pci_ptm_debugfs *pcie_ptm_create_debugfs(struct device *dev, void *pdata, return NULL; dirname = devm_kasprintf(dev, GFP_KERNEL, "pcie_ptm_%s", dev_name(dev)); - if (!dirname) + if (!dirname) { + kfree(ptm_debugfs); return NULL; + } ptm_debugfs->debugfs = debugfs_create_dir(dirname, NULL); ptm_debugfs->pdata = pdata; @@ -551,6 +553,7 @@ void pcie_ptm_destroy_debugfs(struct pci_ptm_debugfs *ptm_debugfs) mutex_destroy(&ptm_debugfs->lock); debugfs_remove_recursive(ptm_debugfs->debugfs); + kfree(ptm_debugfs); } EXPORT_SYMBOL_GPL(pcie_ptm_destroy_debugfs); #endif diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 9cd032dff31e57..7d4f0db5ac265a 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2251,7 +2251,8 @@ int pci_configure_extended_tags(struct pci_dev *dev, void *ign) u16 ctl; int ret; - if (!pci_is_pcie(dev)) + /* PCI_EXP_DEVCTL_EXT_TAG is RsvdP in VFs */ + if (!pci_is_pcie(dev) || dev->is_virtfn) return 0; ret = pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap); @@ -2380,6 +2381,37 @@ static void pci_configure_serr(struct pci_dev *dev) } } +static void pci_configure_rcb(struct pci_dev *dev) +{ + struct pci_dev *rp; + u16 rp_lnkctl; + + /* + * Per PCIe r7.0, sec 7.5.3.7, RCB is only meaningful in Root Ports + * (where it is read-only), Endpoints, and Bridges. It may only be + * set for Endpoints and Bridges if it is set in the Root Port. For + * Endpoints, it is 'RsvdP' for Virtual Functions. + */ + if (!pci_is_pcie(dev) || + pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT || + pci_pcie_type(dev) == PCI_EXP_TYPE_UPSTREAM || + pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM || + pci_pcie_type(dev) == PCI_EXP_TYPE_RC_EC || + dev->is_virtfn) + return; + + /* Root Port often not visible to virtualized guests */ + rp = pcie_find_root_port(dev); + if (!rp) + return; + + pcie_capability_read_word(rp, PCI_EXP_LNKCTL, &rp_lnkctl); + pcie_capability_clear_and_set_word(dev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_RCB, + (rp_lnkctl & PCI_EXP_LNKCTL_RCB) ? + PCI_EXP_LNKCTL_RCB : 0); +} + static void pci_configure_device(struct pci_dev *dev) { pci_configure_mps(dev); @@ -2389,6 +2421,7 @@ static void pci_configure_device(struct pci_dev *dev) pci_configure_aspm_l1ss(dev); pci_configure_eetlp_prefix(dev); pci_configure_serr(dev); + pci_configure_rcb(dev); pci_acpi_program_hp_params(dev); } diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index b9c252aa6fe08a..9e073321b2dd29 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5581,6 +5581,7 @@ static void quirk_no_ext_tags(struct pci_dev *pdev) pci_walk_bus(bridge->bus, pci_configure_extended_tags, NULL); } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_3WARE, 0x1004, quirk_no_ext_tags); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_3WARE, 0x1005, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0132, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0140, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0141, quirk_no_ext_tags); @@ -6188,6 +6189,10 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_PERICOM, 0x2303, pci_fixup_pericom_acs_store_forward); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_PERICOM, 0x2303, pci_fixup_pericom_acs_store_forward); +DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_PERICOM, 0xb404, + pci_fixup_pericom_acs_store_forward); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_PERICOM, 0xb404, + pci_fixup_pericom_acs_store_forward); static void nvidia_ion_ahci_fixup(struct pci_dev *pdev) { diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 3645f392a9fd3a..cc592ccff54247 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -221,14 +221,21 @@ static struct resource *pbus_select_window_for_type(struct pci_bus *bus, switch (iores_type) { case IORESOURCE_IO: - return pci_bus_resource_n(bus, PCI_BUS_BRIDGE_IO_WINDOW); + win = pci_bus_resource_n(bus, PCI_BUS_BRIDGE_IO_WINDOW); + if (win && (win->flags & IORESOURCE_IO)) + return win; + return NULL; case IORESOURCE_MEM: mmio = pci_bus_resource_n(bus, PCI_BUS_BRIDGE_MEM_WINDOW); mmio_pref = pci_bus_resource_n(bus, PCI_BUS_BRIDGE_PREF_MEM_WINDOW); - if (!(type & IORESOURCE_PREFETCH) || - !(mmio_pref->flags & IORESOURCE_MEM)) + if (mmio && !(mmio->flags & IORESOURCE_MEM)) + mmio = NULL; + if (mmio_pref && !(mmio_pref->flags & IORESOURCE_MEM)) + mmio_pref = NULL; + + if (!(type & IORESOURCE_PREFETCH) || !mmio_pref) return mmio; if ((type & IORESOURCE_MEM_64) || @@ -1066,16 +1073,13 @@ static resource_size_t calculate_memsize(resource_size_t size, resource_size_t min_size, resource_size_t add_size, resource_size_t children_add_size, - resource_size_t old_size, resource_size_t align) { if (size < min_size) size = min_size; - if (old_size == 1) - old_size = 0; size = max(size, add_size) + children_add_size; - return ALIGN(max(size, old_size), align); + return ALIGN(size, align); } resource_size_t __weak pcibios_window_alignment(struct pci_bus *bus, @@ -1223,66 +1227,43 @@ static inline resource_size_t calculate_mem_align(resource_size_t *aligns, return min_align; } -/** - * pbus_upstream_space_available - Check no upstream resource limits allocation - * @bus: The bus - * @res: The resource to help select the correct bridge window - * @size: The size required from the bridge window - * @align: Required alignment for the resource - * - * Check that @size can fit inside the upstream bridge resources that are - * already assigned. Select the upstream bridge window based on the type of - * @res. - * - * Return: %true if enough space is available on all assigned upstream +/* + * Calculate bridge window head alignment that leaves no gaps in between * resources. */ -static bool pbus_upstream_space_available(struct pci_bus *bus, - struct resource *res, - resource_size_t size, - resource_size_t align) -{ - struct resource_constraint constraint = { - .max = RESOURCE_SIZE_MAX, - .align = align, - }; - struct pci_bus *downstream = bus; - - while ((bus = bus->parent)) { - if (pci_is_root_bus(bus)) - break; +static resource_size_t calculate_head_align(resource_size_t *aligns, + int max_order) +{ + resource_size_t head_align = 1; + resource_size_t remainder = 0; + int order; - res = pbus_select_window(bus, res); - if (!res) - return false; - if (!res->parent) - continue; + /* Take the largest alignment as the starting point. */ + head_align <<= max_order + __ffs(SZ_1M); - if (resource_size(res) >= size) { - struct resource gap = {}; + for (order = max_order - 1; order >= 0; order--) { + resource_size_t align1 = 1; - if (find_resource_space(res, &gap, size, &constraint) == 0) { - gap.flags = res->flags; - pci_dbg(bus->self, - "Assigned bridge window %pR to %pR free space at %pR\n", - res, &bus->busn_res, &gap); - return true; - } - } + align1 <<= order + __ffs(SZ_1M); - if (bus->self) { - pci_info(bus->self, - "Assigned bridge window %pR to %pR cannot fit 0x%llx required for %s bridging to %pR\n", - res, &bus->busn_res, - (unsigned long long)size, - pci_name(downstream->self), - &downstream->busn_res); - } + /* + * Account smaller resources with alignment < max_order that + * could be used to fill head room if alignment less than + * max_order is used. + */ + remainder += aligns[order]; - return false; + /* + * Test if head fill is enough to satisfy the alignment of + * the larger resources after reducing the alignment. + */ + while ((head_align > align1) && (remainder >= head_align / 2)) { + head_align /= 2; + remainder -= head_align; + } } - return true; + return head_align; } /** @@ -1310,14 +1291,12 @@ static void pbus_size_mem(struct pci_bus *bus, unsigned long type, { struct pci_dev *dev; resource_size_t min_align, win_align, align, size, size0, size1 = 0; - resource_size_t aligns[28]; /* Alignments from 1MB to 128TB */ + resource_size_t aligns[28] = {}; /* Alignments from 1MB to 128TB */ int order, max_order; struct resource *b_res = pbus_select_window_for_type(bus, type); resource_size_t children_add_size = 0; resource_size_t children_add_align = 0; resource_size_t add_align = 0; - resource_size_t relaxed_align; - resource_size_t old_size; if (!b_res) return; @@ -1326,7 +1305,6 @@ static void pbus_size_mem(struct pci_bus *bus, unsigned long type, if (b_res->parent) return; - memset(aligns, 0, sizeof(aligns)); max_order = 0; size = 0; @@ -1371,12 +1349,8 @@ static void pbus_size_mem(struct pci_bus *bus, unsigned long type, continue; } size += max(r_size, align); - /* - * Exclude ranges with size > align from calculation of - * the alignment. - */ - if (r_size <= align) - aligns[order] += align; + + aligns[order] += align; if (order > max_order) max_order = order; @@ -1388,44 +1362,20 @@ static void pbus_size_mem(struct pci_bus *bus, unsigned long type, } } - old_size = resource_size(b_res); win_align = window_alignment(bus, b_res->flags); - min_align = calculate_mem_align(aligns, max_order); + min_align = calculate_head_align(aligns, max_order); min_align = max(min_align, win_align); - size0 = calculate_memsize(size, min_size, 0, 0, old_size, min_align); + size0 = calculate_memsize(size, min_size, 0, 0, win_align); if (size0) { resource_set_range(b_res, min_align, size0); b_res->flags &= ~IORESOURCE_DISABLED; } - if (bus->self && size0 && - !pbus_upstream_space_available(bus, b_res, size0, min_align)) { - relaxed_align = 1ULL << (max_order + __ffs(SZ_1M)); - relaxed_align = max(relaxed_align, win_align); - min_align = min(min_align, relaxed_align); - size0 = calculate_memsize(size, min_size, 0, 0, old_size, win_align); - resource_set_range(b_res, min_align, size0); - pci_info(bus->self, "bridge window %pR to %pR requires relaxed alignment rules\n", - b_res, &bus->busn_res); - } - if (realloc_head && (add_size > 0 || children_add_size > 0)) { add_align = max(min_align, add_align); size1 = calculate_memsize(size, min_size, add_size, children_add_size, - old_size, add_align); - - if (bus->self && size1 && - !pbus_upstream_space_available(bus, b_res, size1, add_align)) { - relaxed_align = 1ULL << (max_order + __ffs(SZ_1M)); - relaxed_align = max(relaxed_align, win_align); - min_align = min(min_align, relaxed_align); - size1 = calculate_memsize(size, min_size, add_size, children_add_size, - old_size, win_align); - pci_info(bus->self, - "bridge window %pR to %pR requires relaxed alignment rules\n", - b_res, &bus->busn_res); - } + win_align); } if (!size0 && !size1) { @@ -2504,6 +2454,11 @@ int pbus_reassign_bridge_resources(struct pci_bus *bus, struct resource *res) bridge = dev_res->dev; i = pci_resource_num(bridge, res); + if (res->parent) { + release_child_resources(res); + pci_release_resource(bridge, i); + } + restore_dev_resource(dev_res); pci_claim_resource(bridge, i); diff --git a/drivers/pci/vgaarb.c b/drivers/pci/vgaarb.c index 436fa7f4c3873b..baa242b1409930 100644 --- a/drivers/pci/vgaarb.c +++ b/drivers/pci/vgaarb.c @@ -652,13 +652,6 @@ static bool vga_is_boot_device(struct vga_device *vgadev) return true; } - /* - * Vgadev has neither IO nor MEM enabled. If we haven't found any - * other VGA devices, it is the best candidate so far. - */ - if (!boot_vga) - return true; - return false; } diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c index efa9b229e7012e..e0d4293f06f93f 100644 --- a/drivers/perf/arm_cspmu/arm_cspmu.c +++ b/drivers/perf/arm_cspmu/arm_cspmu.c @@ -1365,8 +1365,10 @@ void arm_cspmu_impl_unregister(const struct arm_cspmu_impl_match *impl_match) /* Unbind the driver from all matching backend devices. */ while ((dev = driver_find_device(&arm_cspmu_driver.driver, NULL, - match, arm_cspmu_match_device))) + match, arm_cspmu_match_device))) { device_release_driver(dev); + put_device(dev); + } mutex_lock(&arm_cspmu_lock); diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index fa50645feddadb..e4e4e63c64c42a 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -105,6 +105,8 @@ struct arm_spe_pmu { /* Keep track of our dynamic hotplug state */ static enum cpuhp_state arm_spe_pmu_online; +static void arm_spe_pmu_stop(struct perf_event *event, int flags); + enum arm_spe_pmu_buf_fault_action { SPE_PMU_BUF_FAULT_ACT_SPURIOUS, SPE_PMU_BUF_FAULT_ACT_FATAL, @@ -582,8 +584,8 @@ static u64 arm_spe_pmu_next_off(struct perf_output_handle *handle) return limit; } -static void arm_spe_perf_aux_output_begin(struct perf_output_handle *handle, - struct perf_event *event) +static int arm_spe_perf_aux_output_begin(struct perf_output_handle *handle, + struct perf_event *event) { u64 base, limit; struct arm_spe_pmu_buf *buf; @@ -597,7 +599,6 @@ static void arm_spe_perf_aux_output_begin(struct perf_output_handle *handle, /* Start a new aux session */ buf = perf_aux_output_begin(handle, event); if (!buf) { - event->hw.state |= PERF_HES_STOPPED; /* * We still need to clear the limit pointer, since the * profiler might only be disabled by virtue of a fault. @@ -617,6 +618,7 @@ static void arm_spe_perf_aux_output_begin(struct perf_output_handle *handle, out_write_limit: write_sysreg_s(limit, SYS_PMBLIMITR_EL1); + return (limit & PMBLIMITR_EL1_E) ? 0 : -EIO; } static void arm_spe_perf_aux_output_end(struct perf_output_handle *handle) @@ -756,7 +758,10 @@ static irqreturn_t arm_spe_pmu_irq_handler(int irq, void *dev) * when we get to it. */ if (!(handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)) { - arm_spe_perf_aux_output_begin(handle, event); + if (arm_spe_perf_aux_output_begin(handle, event)) { + arm_spe_pmu_stop(event, PERF_EF_UPDATE); + break; + } isb(); } break; @@ -851,9 +856,10 @@ static void arm_spe_pmu_start(struct perf_event *event, int flags) struct perf_output_handle *handle = this_cpu_ptr(spe_pmu->handle); hwc->state = 0; - arm_spe_perf_aux_output_begin(handle, event); - if (hwc->state) + if (arm_spe_perf_aux_output_begin(handle, event)) { + arm_spe_pmu_stop(event, 0); return; + } reg = arm_spe_event_to_pmsfcr(event); write_sysreg_s(reg, SYS_PMSFCR_EL1); diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig index 678dd0452f0aa0..2fb5e3b313effc 100644 --- a/drivers/phy/Kconfig +++ b/drivers/phy/Kconfig @@ -103,6 +103,7 @@ config PHY_NXP_PTN3222 source "drivers/phy/allwinner/Kconfig" source "drivers/phy/amlogic/Kconfig" +source "drivers/phy/apple/Kconfig" source "drivers/phy/broadcom/Kconfig" source "drivers/phy/cadence/Kconfig" source "drivers/phy/freescale/Kconfig" diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile index bfb27fb5a49428..eb84c3328d1062 100644 --- a/drivers/phy/Makefile +++ b/drivers/phy/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_PHY_AIROHA_PCIE) += phy-airoha-pcie.o obj-$(CONFIG_PHY_NXP_PTN3222) += phy-nxp-ptn3222.o obj-y += allwinner/ \ amlogic/ \ + apple/ \ broadcom/ \ cadence/ \ freescale/ \ diff --git a/drivers/phy/apple/Kconfig b/drivers/phy/apple/Kconfig new file mode 100644 index 00000000000000..8409b67f6d1ecb --- /dev/null +++ b/drivers/phy/apple/Kconfig @@ -0,0 +1,23 @@ +# SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause +config PHY_APPLE_ATC + tristate "Apple Type-C PHY" + depends on (ARM64 && ARCH_APPLE) || (COMPILE_TEST && !GENERIC_ATOMIC64) + depends on TYPEC + select GENERIC_PHY + select APPLE_TUNABLE + help + Enable this to add support for the Apple Type-C PHY found in + Apple Silicon M-series SoCs. This PHY supports USB2, + USB3, USB4, Thunderbolt, and DisplayPort. + + If M is selected the module will be called 'phy-apple-atc'. + +config PHY_APPLE_DPTX + tristate "Apple DPTX PHY" + depends on ARCH_APPLE || COMPILE_TEST + select GENERIC_PHY + help + Enable this to add support for the Apple DPTX PHY found on Apple SoCs + such as the M2. + This driver provides support for DisplayPort and is used on the + Mac mini (M2 and M2 Pro, 2023). diff --git a/drivers/phy/apple/Makefile b/drivers/phy/apple/Makefile new file mode 100644 index 00000000000000..b9e7bf3e4ac170 --- /dev/null +++ b/drivers/phy/apple/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause + +obj-$(CONFIG_PHY_APPLE_ATC) += phy-apple-atc.o +phy-apple-atc-y := atc.o + +obj-$(CONFIG_PHY_APPLE_DPTX) += phy-apple-dptx.o +phy-apple-dptx-y += dptx.o diff --git a/drivers/phy/apple/atc.c b/drivers/phy/apple/atc.c new file mode 100644 index 00000000000000..dc867f368b6874 --- /dev/null +++ b/drivers/phy/apple/atc.c @@ -0,0 +1,2295 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause +/* + * Apple Type-C PHY driver + * + * The Apple Type-C PHY (ATCPHY) is a combined PHY for USB 2.0, USB 3.x, + * USB4/Thunderbolt, and DisplayPort connectivity via Type-C ports found in + * Apple Silicon SoCs. + * + * The PHY handles muxing between these different protocols and also provides the + * reset controller for the attached DWC3 USB controller. + * + * No documentation for this PHY is available and its operation has been + * reverse engineered by observing the XNU's MMIO access using a thin hypervisor + * and correlating register access to XNU's very verbose debug output. Most + * register names comes from this debug output as well. + * + * In order to correctly setup the high speed lanes for the various modes + * calibration values copied from Apple's firmware by our bootloader m1n1 are + * required. Without these only USB2 operation is possible. + * + * Copyright (C) The Asahi Linux Contributors + * Author: Sven Peter + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define AUSPLL_FSM_CTRL 0x1014 + +#define AUSPLL_APB_CMD_OVERRIDE 0x2000 +#define AUSPLL_APB_CMD_OVERRIDE_REQ BIT(0) +#define AUSPLL_APB_CMD_OVERRIDE_ACK BIT(1) +#define AUSPLL_APB_CMD_OVERRIDE_UNK28 BIT(28) +#define AUSPLL_APB_CMD_OVERRIDE_CMD GENMASK(27, 3) + +#define AUSPLL_FREQ_DESC_A 0x2080 +#define AUSPLL_FD_FREQ_COUNT_TARGET GENMASK(9, 0) +#define AUSPLL_FD_FBDIVN_HALF BIT(10) +#define AUSPLL_FD_REV_DIVN GENMASK(13, 11) +#define AUSPLL_FD_KI_MAN GENMASK(17, 14) +#define AUSPLL_FD_KI_EXP GENMASK(21, 18) +#define AUSPLL_FD_KP_MAN GENMASK(25, 22) +#define AUSPLL_FD_KP_EXP GENMASK(29, 26) +#define AUSPLL_FD_KPKI_SCALE_HBW GENMASK(31, 30) + +#define AUSPLL_FREQ_DESC_B 0x2084 +#define AUSPLL_FD_FBDIVN_FRAC_DEN GENMASK(13, 0) +#define AUSPLL_FD_FBDIVN_FRAC_NUM GENMASK(27, 14) + +#define AUSPLL_FREQ_DESC_C 0x2088 +#define AUSPLL_FD_SDM_SSC_STEP GENMASK(7, 0) +#define AUSPLL_FD_SDM_SSC_EN BIT(8) +#define AUSPLL_FD_PCLK_DIV_SEL GENMASK(13, 9) +#define AUSPLL_FD_LFSDM_DIV GENMASK(15, 14) +#define AUSPLL_FD_LFCLK_CTRL GENMASK(19, 16) +#define AUSPLL_FD_VCLK_OP_DIVN GENMASK(21, 20) +#define AUSPLL_FD_VCLK_PRE_DIVN BIT(22) + +#define AUSPLL_DCO_EFUSE_SPARE 0x222c +#define AUSPLL_RODCO_ENCAP_EFUSE GENMASK(10, 9) +#define AUSPLL_RODCO_BIAS_ADJUST_EFUSE GENMASK(14, 12) + +#define AUSPLL_FRACN_CAN 0x22a4 +#define AUSPLL_DLL_START_CAPCODE GENMASK(18, 17) + +#define AUSPLL_CLKOUT_MASTER 0x2200 +#define AUSPLL_CLKOUT_MASTER_PCLK_DRVR_EN BIT(2) +#define AUSPLL_CLKOUT_MASTER_PCLK2_DRVR_EN BIT(4) +#define AUSPLL_CLKOUT_MASTER_REFBUFCLK_DRVR_EN BIT(6) + +#define AUSPLL_CLKOUT_DIV 0x2208 +#define AUSPLL_CLKOUT_PLLA_REFBUFCLK_DI GENMASK(20, 16) + +#define AUSPLL_BGR 0x2214 +#define AUSPLL_BGR_CTRL_AVAIL BIT(0) + +#define AUSPLL_CLKOUT_DTC_VREG 0x2220 +#define AUSPLL_DTC_VREG_ADJUST GENMASK(16, 14) +#define AUSPLL_DTC_VREG_BYPASS BIT(7) + +#define AUSPLL_FREQ_CFG 0x2224 +#define AUSPLL_FREQ_REFCLK GENMASK(1, 0) + +#define AUS_COMMON_SHIM_BLK_VREG 0x0a04 +#define AUS_VREG_TRIM GENMASK(6, 2) + +#define AUS_UNK_A20 0x0a20 +#define AUS_UNK_A20_TX_CAL_CODE GENMASK(23, 20) + +#define ACIOPHY_CMN_SHM_STS_REG0 0x0a74 +#define ACIOPHY_CMN_SHM_STS_REG0_CMD_READY BIT(0) + +#define CIO3PLL_CLK_CTRL 0x2a00 +#define CIO3PLL_CLK_PCLK_EN BIT(1) +#define CIO3PLL_CLK_REFCLK_EN BIT(5) + +#define CIO3PLL_DCO_NCTRL 0x2a38 +#define CIO3PLL_DCO_COARSEBIN_EFUSE0 GENMASK(6, 0) +#define CIO3PLL_DCO_COARSEBIN_EFUSE1 GENMASK(23, 17) + +#define CIO3PLL_FRACN_CAN 0x2aa4 +#define CIO3PLL_DLL_CAL_START_CAPCODE GENMASK(18, 17) + +#define CIO3PLL_DTC_VREG 0x2a20 +#define CIO3PLL_DTC_VREG_ADJUST GENMASK(16, 14) + +#define ACIOPHY_CFG0 0x08 +#define ACIOPHY_CFG0_COMMON_BIG_OV BIT(1) +#define ACIOPHY_CFG0_COMMON_SMALL_OV BIT(3) +#define ACIOPHY_CFG0_COMMON_CLAMP_OV BIT(5) +#define ACIOPHY_CFG0_RX_SMALL_OV GENMASK(9, 8) +#define ACIOPHY_CFG0_RX_BIG_OV GENMASK(13, 12) +#define ACIOPHY_CFG0_RX_CLAMP_OV GENMASK(17, 16) + +#define ACIOPHY_CROSSBAR 0x4c +#define ACIOPHY_CROSSBAR_PROTOCOL GENMASK(4, 0) +#define ACIOPHY_CROSSBAR_PROTOCOL_USB4 0x0 +#define ACIOPHY_CROSSBAR_PROTOCOL_USB4_SWAPPED 0x1 +#define ACIOPHY_CROSSBAR_PROTOCOL_USB3 0xa +#define ACIOPHY_CROSSBAR_PROTOCOL_USB3_SWAPPED 0xb +#define ACIOPHY_CROSSBAR_PROTOCOL_USB3_DP 0x10 +#define ACIOPHY_CROSSBAR_PROTOCOL_USB3_DP_SWAPPED 0x11 +#define ACIOPHY_CROSSBAR_PROTOCOL_DP 0x14 +#define ACIOPHY_CROSSBAR_DP_SINGLE_PMA GENMASK(16, 5) +#define ACIOPHY_CROSSBAR_DP_SINGLE_PMA_NONE 0x0000 +#define ACIOPHY_CROSSBAR_DP_SINGLE_PMA_UNK100 0x100 +#define ACIOPHY_CROSSBAR_DP_SINGLE_PMA_UNK008 0x008 +#define ACIOPHY_CROSSBAR_DP_BOTH_PMA BIT(17) + +#define ACIOPHY_LANE_MODE 0x48 +#define ACIOPHY_LANE_MODE_RX0 GENMASK(2, 0) +#define ACIOPHY_LANE_MODE_TX0 GENMASK(5, 3) +#define ACIOPHY_LANE_MODE_RX1 GENMASK(8, 6) +#define ACIOPHY_LANE_MODE_TX1 GENMASK(11, 9) + +enum atcphy_lane_mode { + ACIOPHY_LANE_MODE_USB4 = 0, + ACIOPHY_LANE_MODE_USB3 = 1, + ACIOPHY_LANE_MODE_DP = 2, + ACIOPHY_LANE_MODE_OFF = 3, +}; + +#define ACIOPHY_TOP_BIST_CIOPHY_CFG1 0x84 +#define ACIOPHY_TOP_BIST_CIOPHY_CFG1_CLK_EN BIT(27) +#define ACIOPHY_TOP_BIST_CIOPHY_CFG1_BIST_EN BIT(28) + +#define ACIOPHY_TOP_BIST_OV_CFG 0x8c +#define ACIOPHY_TOP_BIST_OV_CFG_LN0_RESET_N_OV BIT(13) +#define ACIOPHY_TOP_BIST_OV_CFG_LN0_PWR_DOWN_OV BIT(25) + +#define ACIOPHY_TOP_BIST_READ_CTRL 0x90 +#define ACIOPHY_TOP_BIST_READ_CTRL_LN0_PHY_STATUS_RE BIT(2) + +#define ACIOPHY_TOP_PHY_STAT 0x9c +#define ACIOPHY_TOP_PHY_STAT_LN0_UNK0 BIT(0) +#define ACIOPHY_TOP_PHY_STAT_LN0_UNK23 BIT(23) + +#define ACIOPHY_TOP_BIST_PHY_CFG0 0xa8 +#define ACIOPHY_TOP_BIST_PHY_CFG0_LN0_RESET_N BIT(0) + +#define ACIOPHY_TOP_BIST_PHY_CFG1 0xac +#define ACIOPHY_TOP_BIST_PHY_CFG1_LN0_PWR_DOWN GENMASK(13, 10) + +#define ACIOPHY_SLEEP_CTRL 0x1b0 +#define ACIOPHY_SLEEP_CTRL_TX_BIG_OV GENMASK(3, 2) +#define ACIOPHY_SLEEP_CTRL_TX_SMALL_OV GENMASK(7, 6) +#define ACIOPHY_SLEEP_CTRL_TX_CLAMP_OV GENMASK(11, 10) + +#define ACIOPHY_PLL_PCTL_FSM_CTRL1 0x1014 +#define ACIOPHY_PLL_APB_REQ_OV_SEL GENMASK(21, 13) +#define ACIOPHY_PLL_COMMON_CTRL 0x1028 +#define ACIOPHY_PLL_WAIT_FOR_CMN_READY_BEFORE_RESET_EXIT BIT(24) + +#define ATCPHY_POWER_CTRL 0x20000 +#define ATCPHY_POWER_STAT 0x20004 +#define ATCPHY_POWER_SLEEP_SMALL BIT(0) +#define ATCPHY_POWER_SLEEP_BIG BIT(1) +#define ATCPHY_POWER_CLAMP_EN BIT(2) +#define ATCPHY_POWER_APB_RESET_N BIT(3) +#define ATCPHY_POWER_PHY_RESET_N BIT(4) + +#define ATCPHY_MISC 0x20008 +#define ATCPHY_MISC_RESET_N BIT(0) +#define ATCPHY_MISC_LANE_SWAP BIT(2) + +#define ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0 0x7000 +#define DP_PMA_BYTECLK_RESET BIT(0) +#define DP_MAC_DIV20_CLK_SEL BIT(1) +#define DPTXPHY_PMA_LANE_RESET_N BIT(2) +#define DPTXPHY_PMA_LANE_RESET_N_OV BIT(3) +#define DPTX_PCLK1_SELECT GENMASK(6, 4) +#define DPTX_PCLK2_SELECT GENMASK(9, 7) +#define DPRX_PCLK_SELECT GENMASK(12, 10) +#define DPTX_PCLK1_ENABLE BIT(13) +#define DPTX_PCLK2_ENABLE BIT(14) +#define DPRX_PCLK_ENABLE BIT(15) + +#define ACIOPHY_DP_PCLK_STAT 0x7044 +#define ACIOPHY_AUSPLL_LOCK BIT(3) + +#define LN0_AUSPMA_RX_TOP 0x9000 +#define LN0_AUSPMA_RX_EQ 0xA000 +#define LN0_AUSPMA_RX_SHM 0xB000 +#define LN0_AUSPMA_TX_TOP 0xC000 +#define LN0_AUSPMA_TX_SHM 0xD000 + +#define LN1_AUSPMA_RX_TOP 0x10000 +#define LN1_AUSPMA_RX_EQ 0x11000 +#define LN1_AUSPMA_RX_SHM 0x12000 +#define LN1_AUSPMA_TX_TOP 0x13000 +#define LN1_AUSPMA_TX_SHM 0x14000 + +#define LN_AUSPMA_RX_TOP_PMAFSM 0x0010 +#define LN_AUSPMA_RX_TOP_PMAFSM_PCS_OV BIT(0) +#define LN_AUSPMA_RX_TOP_PMAFSM_PCS_REQ BIT(9) + +#define LN_AUSPMA_RX_TOP_TJ_CFG_RX_TXMODE 0x00F0 +#define LN_RX_TXMODE BIT(0) + +#define LN_AUSPMA_RX_SHM_TJ_RXA_CTLE_CTRL0 0x00 +#define LN_TX_CLK_EN BIT(20) +#define LN_TX_CLK_EN_OV BIT(21) + +#define LN_AUSPMA_RX_SHM_TJ_RXA_AFE_CTRL1 0x04 +#define LN_RX_DIV20_RESET_N_OV BIT(29) +#define LN_RX_DIV20_RESET_N BIT(30) + +#define LN_AUSPMA_RX_SHM_TJ_RXA_UNK_CTRL2 0x08 +#define LN_AUSPMA_RX_SHM_TJ_RXA_UNK_CTRL3 0x0C +#define LN_AUSPMA_RX_SHM_TJ_RXA_UNK_CTRL4 0x10 +#define LN_AUSPMA_RX_SHM_TJ_RXA_UNK_CTRL5 0x14 +#define LN_AUSPMA_RX_SHM_TJ_RXA_UNK_CTRL6 0x18 +#define LN_AUSPMA_RX_SHM_TJ_RXA_UNK_CTRL7 0x1C +#define LN_AUSPMA_RX_SHM_TJ_RXA_UNK_CTRL8 0x20 +#define LN_AUSPMA_RX_SHM_TJ_RXA_UNK_CTRL9 0x24 +#define LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL10 0x28 +#define LN_DTVREG_ADJUST GENMASK(31, 27) + +#define LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL11 0x2C +#define LN_DTVREG_BIG_EN BIT(23) +#define LN_DTVREG_BIG_EN_OV BIT(24) +#define LN_DTVREG_SML_EN BIT(25) +#define LN_DTVREG_SML_EN_OV BIT(26) + +#define LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL12 0x30 +#define LN_TX_BYTECLK_RESET_SYNC_CLR BIT(22) +#define LN_TX_BYTECLK_RESET_SYNC_CLR_OV BIT(23) +#define LN_TX_BYTECLK_RESET_SYNC_EN BIT(24) +#define LN_TX_BYTECLK_RESET_SYNC_EN_OV BIT(25) +#define LN_TX_HRCLK_SEL BIT(28) +#define LN_TX_HRCLK_SEL_OV BIT(29) +#define LN_TX_PBIAS_EN BIT(30) +#define LN_TX_PBIAS_EN_OV BIT(31) + +#define LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL13 0x34 +#define LN_TX_PRE_EN BIT(0) +#define LN_TX_PRE_EN_OV BIT(1) +#define LN_TX_PST1_EN BIT(2) +#define LN_TX_PST1_EN_OV BIT(3) +#define LN_DTVREG_ADJUST_OV BIT(15) + +#define LN_AUSPMA_RX_SHM_TJ_UNK_CTRL14A 0x38 +#define LN_AUSPMA_RX_SHM_TJ_UNK_CTRL14B 0x3C +#define LN_AUSPMA_RX_SHM_TJ_UNK_CTRL15A 0x40 +#define LN_AUSPMA_RX_SHM_TJ_UNK_CTRL15B 0x44 +#define LN_AUSPMA_RX_SHM_TJ_RXA_SAVOS_CTRL16 0x48 +#define LN_RXTERM_EN BIT(21) +#define LN_RXTERM_EN_OV BIT(22) +#define LN_RXTERM_PULLUP_LEAK_EN BIT(23) +#define LN_RXTERM_PULLUP_LEAK_EN_OV BIT(24) +#define LN_TX_CAL_CODE GENMASK(29, 25) +#define LN_TX_CAL_CODE_OV BIT(30) + +#define LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL17 0x4C +#define LN_TX_MARGIN GENMASK(19, 15) +#define LN_TX_MARGIN_OV BIT(20) +#define LN_TX_MARGIN_LSB BIT(21) +#define LN_TX_MARGIN_LSB_OV BIT(22) +#define LN_TX_MARGIN_P1 GENMASK(26, 23) +#define LN_TX_MARGIN_P1_OV BIT(27) +#define LN_TX_MARGIN_P1_LSB GENMASK(29, 28) +#define LN_TX_MARGIN_P1_LSB_OV BIT(30) + +#define LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL18 0x50 +#define LN_TX_P1_CODE GENMASK(3, 0) +#define LN_TX_P1_CODE_OV BIT(4) +#define LN_TX_P1_LSB_CODE GENMASK(6, 5) +#define LN_TX_P1_LSB_CODE_OV BIT(7) +#define LN_TX_MARGIN_PRE GENMASK(10, 8) +#define LN_TX_MARGIN_PRE_OV BIT(11) +#define LN_TX_MARGIN_PRE_LSB GENMASK(13, 12) +#define LN_TX_MARGIN_PRE_LSB_OV BIT(14) +#define LN_TX_PRE_LSB_CODE GENMASK(16, 15) +#define LN_TX_PRE_LSB_CODE_OV BIT(17) +#define LN_TX_PRE_CODE GENMASK(21, 18) +#define LN_TX_PRE_CODE_OV BIT(22) + +#define LN_AUSPMA_RX_SHM_TJ_RXA_TERM_CTRL19 0x54 +#define LN_TX_TEST_EN BIT(21) +#define LN_TX_TEST_EN_OV BIT(22) +#define LN_TX_EN BIT(23) +#define LN_TX_EN_OV BIT(24) +#define LN_TX_CLK_DLY_CTRL_TAPGEN GENMASK(27, 25) +#define LN_TX_CLK_DIV2_EN BIT(28) +#define LN_TX_CLK_DIV2_EN_OV BIT(29) +#define LN_TX_CLK_DIV2_RST BIT(30) +#define LN_TX_CLK_DIV2_RST_OV BIT(31) + +#define LN_AUSPMA_RX_SHM_TJ_RXA_UNK_CTRL20 0x58 +#define LN_AUSPMA_RX_SHM_TJ_RXA_UNK_CTRL21 0x5C +#define LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22 0x60 +#define LN_VREF_ADJUST_GRAY GENMASK(11, 7) +#define LN_VREF_ADJUST_GRAY_OV BIT(12) +#define LN_VREF_BIAS_SEL GENMASK(14, 13) +#define LN_VREF_BIAS_SEL_OV BIT(15) +#define LN_VREF_BOOST_EN BIT(16) +#define LN_VREF_BOOST_EN_OV BIT(17) +#define LN_VREF_EN BIT(18) +#define LN_VREF_EN_OV BIT(19) +#define LN_VREF_LPBKIN_DATA GENMASK(29, 28) +#define LN_VREF_TEST_RXLPBKDT_EN BIT(30) +#define LN_VREF_TEST_RXLPBKDT_EN_OV BIT(31) + +#define LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG0 0x00 +#define LN_BYTECLK_RESET_SYNC_EN_OV BIT(2) +#define LN_BYTECLK_RESET_SYNC_EN BIT(3) +#define LN_BYTECLK_RESET_SYNC_CLR_OV BIT(4) +#define LN_BYTECLK_RESET_SYNC_CLR BIT(5) +#define LN_BYTECLK_RESET_SYNC_SEL_OV BIT(6) + +#define LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG1 0x04 +#define LN_TXA_DIV2_EN_OV BIT(8) +#define LN_TXA_DIV2_EN BIT(9) +#define LN_TXA_DIV2_RESET_OV BIT(10) +#define LN_TXA_DIV2_RESET BIT(11) +#define LN_TXA_CLK_EN_OV BIT(22) +#define LN_TXA_CLK_EN BIT(23) + +#define LN_AUSPMA_TX_SHM_TXA_IMP_REG0 0x08 +#define LN_TXA_CAL_CTRL_OV BIT(0) +#define LN_TXA_CAL_CTRL GENMASK(18, 1) +#define LN_TXA_CAL_CTRL_BASE_OV BIT(19) +#define LN_TXA_CAL_CTRL_BASE GENMASK(23, 20) +#define LN_TXA_HIZ_OV BIT(29) +#define LN_TXA_HIZ BIT(30) + +#define LN_AUSPMA_TX_SHM_TXA_IMP_REG1 0x0C +#define LN_AUSPMA_TX_SHM_TXA_IMP_REG2 0x10 +#define LN_TXA_MARGIN_OV BIT(0) +#define LN_TXA_MARGIN GENMASK(18, 1) +#define LN_TXA_MARGIN_2R_OV BIT(19) +#define LN_TXA_MARGIN_2R BIT(20) + +#define LN_AUSPMA_TX_SHM_TXA_IMP_REG3 0x14 +#define LN_TXA_MARGIN_POST_OV BIT(0) +#define LN_TXA_MARGIN_POST GENMASK(10, 1) +#define LN_TXA_MARGIN_POST_2R_OV BIT(11) +#define LN_TXA_MARGIN_POST_2R BIT(12) +#define LN_TXA_MARGIN_POST_4R_OV BIT(13) +#define LN_TXA_MARGIN_POST_4R BIT(14) +#define LN_TXA_MARGIN_PRE_OV BIT(15) +#define LN_TXA_MARGIN_PRE GENMASK(21, 16) +#define LN_TXA_MARGIN_PRE_2R_OV BIT(22) +#define LN_TXA_MARGIN_PRE_2R BIT(23) +#define LN_TXA_MARGIN_PRE_4R_OV BIT(24) +#define LN_TXA_MARGIN_PRE_4R BIT(25) + +#define LN_AUSPMA_TX_SHM_TXA_UNK_REG0 0x18 +#define LN_AUSPMA_TX_SHM_TXA_UNK_REG1 0x1C +#define LN_AUSPMA_TX_SHM_TXA_UNK_REG2 0x20 + +#define LN_AUSPMA_TX_SHM_TXA_LDOCLK 0x24 +#define LN_LDOCLK_BYPASS_SML_OV BIT(8) +#define LN_LDOCLK_BYPASS_SML BIT(9) +#define LN_LDOCLK_BYPASS_BIG_OV BIT(10) +#define LN_LDOCLK_BYPASS_BIG BIT(11) +#define LN_LDOCLK_EN_SML_OV BIT(12) +#define LN_LDOCLK_EN_SML BIT(13) +#define LN_LDOCLK_EN_BIG_OV BIT(14) +#define LN_LDOCLK_EN_BIG BIT(15) + +/* LPDPTX registers */ +#define LPDPTX_AUX_CFG_BLK_AUX_CTRL 0x0000 +#define LPDPTX_BLK_AUX_CTRL_PWRDN BIT(4) +#define LPDPTX_BLK_AUX_RXOFFSET GENMASK(25, 22) + +#define LPDPTX_AUX_CFG_BLK_AUX_LDO_CTRL 0x0008 + +#define LPDPTX_AUX_CFG_BLK_AUX_MARGIN 0x000c +#define LPDPTX_MARGIN_RCAL_RXOFFSET_EN BIT(5) +#define LPDPTX_AUX_MARGIN_RCAL_TXSWING GENMASK(10, 6) + +#define LPDPTX_AUX_SHM_CFG_BLK_AUX_CTRL_REG0 0x0204 +#define LPDPTX_CFG_PMA_AUX_SEL_LF_DATA BIT(15) + +#define LPDPTX_AUX_SHM_CFG_BLK_AUX_CTRL_REG1 0x0208 +#define LPDPTX_CFG_PMA_PHYS_ADJ GENMASK(22, 20) +#define LPDPTX_CFG_PMA_PHYS_ADJ_OV BIT(19) + +#define LPDPTX_AUX_CONTROL 0x4000 +#define LPDPTX_AUX_PWN_DOWN 0x10 +#define LPDPTX_AUX_CLAMP_EN 0x04 +#define LPDPTX_SLEEP_B_BIG_IN 0x02 +#define LPDPTX_SLEEP_B_SML_IN 0x01 +#define LPDPTX_TXTERM_CODEMSB 0x400 +#define LPDPTX_TXTERM_CODE GENMASK(9, 5) + +/* pipehandler registers */ +#define PIPEHANDLER_OVERRIDE 0x00 +#define PIPEHANDLER_OVERRIDE_RXVALID BIT(0) +#define PIPEHANDLER_OVERRIDE_RXDETECT BIT(2) + +#define PIPEHANDLER_OVERRIDE_VALUES 0x04 +#define PIPEHANDLER_OVERRIDE_VAL_RXDETECT0 BIT(1) +#define PIPEHANDLER_OVERRIDE_VAL_RXDETECT1 BIT(2) +#define PIPEHANDLER_OVERRIDE_VAL_PHY_STATUS BIT(4) + +#define PIPEHANDLER_MUX_CTRL 0x0c +#define PIPEHANDLER_MUX_CTRL_CLK GENMASK(5, 3) +#define PIPEHANDLER_MUX_CTRL_DATA GENMASK(2, 0) +#define PIPEHANDLER_MUX_CTRL_CLK_OFF 0 +#define PIPEHANDLER_MUX_CTRL_CLK_USB3 1 +#define PIPEHANDLER_MUX_CTRL_CLK_USB4 2 +#define PIPEHANDLER_MUX_CTRL_CLK_DUMMY 4 + +#define PIPEHANDLER_MUX_CTRL_DATA_USB3 0 +#define PIPEHANDLER_MUX_CTRL_DATA_USB4 1 +#define PIPEHANDLER_MUX_CTRL_DATA_DUMMY 2 + +#define PIPEHANDLER_LOCK_REQ 0x10 +#define PIPEHANDLER_LOCK_ACK 0x14 +#define PIPEHANDLER_LOCK_EN BIT(0) + +#define PIPEHANDLER_AON_GEN 0x1C +#define PIPEHANDLER_AON_GEN_DWC3_FORCE_CLAMP_EN BIT(4) +#define PIPEHANDLER_AON_GEN_DWC3_RESET_N BIT(0) + +#define PIPEHANDLER_NONSELECTED_OVERRIDE 0x20 +#define PIPEHANDLER_NATIVE_RESET BIT(12) +#define PIPEHANDLER_DUMMY_PHY_EN BIT(15) +#define PIPEHANDLER_NATIVE_POWER_DOWN GENMASK(3, 0) + +#define PIPEHANDLER_LOCK_ACK_TIMEOUT_US 1000 + +/* USB2 PHY regs */ +#define USB2PHY_USBCTL 0x00 +#define USB2PHY_USBCTL_RUN 2 +#define USB2PHY_USBCTL_ISOLATION 4 + +#define USB2PHY_CTL 0x04 +#define USB2PHY_CTL_RESET BIT(0) +#define USB2PHY_CTL_PORT_RESET BIT(1) +#define USB2PHY_CTL_APB_RESET_N BIT(2) +#define USB2PHY_CTL_SIDDQ BIT(3) + +#define USB2PHY_SIG 0x08 +#define USB2PHY_SIG_VBUSDET_FORCE_VAL BIT(0) +#define USB2PHY_SIG_VBUSDET_FORCE_EN BIT(1) +#define USB2PHY_SIG_VBUSVLDEXT_FORCE_VAL BIT(2) +#define USB2PHY_SIG_VBUSVLDEXT_FORCE_EN BIT(3) +#define USB2PHY_SIG_HOST (7 << 12) + +#define USB2PHY_MISCTUNE 0x1c +#define USB2PHY_MISCTUNE_APBCLK_GATE_OFF BIT(29) +#define USB2PHY_MISCTUNE_REFCLK_GATE_OFF BIT(30) + +enum atcphy_dp_link_rate { + ATCPHY_DP_LINK_RATE_RBR, + ATCPHY_DP_LINK_RATE_HBR, + ATCPHY_DP_LINK_RATE_HBR2, + ATCPHY_DP_LINK_RATE_HBR3, +}; + +/** + * enum atcphy_pipehandler_state - States of the PIPE mux interface ("pipehandler") + * @ATCPHY_PIPEHANDLER_STATE_DUMMY: "Dummy PHY" (disables USB3, USB2 only) + * @ATCPHY_PIPEHANDLER_STATE_USB3: USB3 directly connected to the Type-C port + * @ATCPHY_PIPEHANDLER_STATE_USB4: USB3 tunneled via USB4/Thunderbolt + * + * DWC3's USB3 PIPE interface is connected to a multiplexer inside this PHY + * which can switch between a dummy state (which effectively disables any USB3 + * support and falls back to USB2 only operation via the separate ULPI interface), + * a USB3 state (for regular USB3 or USB3+DisplayPort operation) and a USB4 state + * (for USB3 tunneled via USB4/Thunderbolt). + */ +enum atcphy_pipehandler_state { + ATCPHY_PIPEHANDLER_STATE_DUMMY, + ATCPHY_PIPEHANDLER_STATE_USB3, + ATCPHY_PIPEHANDLER_STATE_USB4, +}; + +/** + * enum atcphy_mode - Operating modes of the PHY + * @APPLE_ATCPHY_MODE_OFF: all PHYs powered off + * @APPLE_ATCPHY_MODE_USB2: Nothing on the four SS lanes (i.e. USB2 only on D-/+) + * @APPLE_ATCPHY_MODE_USB3: USB3 on two lanes, nothing on the other two + * @APPLE_ATCPHY_MODE_USB3_DP: USB3 on two lanes and DisplayPort on the other two + * @APPLE_ATCPHY_MODE_TBT: Thunderbolt on all lanes + * @APPLE_ATCPHY_MODE_USB4: USB4 on all lanes + * @APPLE_ATCPHY_MODE_DP: DisplayPort on all lanes + */ +enum atcphy_mode { + APPLE_ATCPHY_MODE_OFF, + APPLE_ATCPHY_MODE_USB2, + APPLE_ATCPHY_MODE_USB3, + APPLE_ATCPHY_MODE_USB3_DP, + APPLE_ATCPHY_MODE_TBT, + APPLE_ATCPHY_MODE_USB4, + APPLE_ATCPHY_MODE_DP, +}; + +enum atcphy_lane { + APPLE_ATCPHY_LANE_0, + APPLE_ATCPHY_LANE_1, +}; + +/* Link rate configuration, field names are taken from XNU debug output or register names */ +struct atcphy_dp_link_rate_configuration { + u16 freqinit_count_target; + u16 fbdivn_frac_den; + u16 fbdivn_frac_num; + u16 pclk_div_sel; + u8 lfclk_ctrl; + u8 vclk_op_divn; + bool plla_clkout_vreg_bypass; + bool txa_ldoclk_bypass; + bool txa_div2_en; +}; + +/* Crossbar and lane configuration */ +struct atcphy_mode_configuration { + u32 crossbar; + u32 crossbar_dp_single_pma; + bool crossbar_dp_both_pma; + enum atcphy_lane_mode lane_mode[2]; + bool dp_lane[2]; + bool set_swap; +}; + +/** + * struct apple_atcphy - Apple Type-C PHY device struct + * @np: Device node pointer + * @dev: Device pointer + * @tunables: Firmware-provided tunable parameters + * @tunables.axi2af: AXI to AF interface tunables + * @tunables.common: Common tunables for all lanes + * @tunables.lane_usb3: USB3 lane-specific tunables + * @tunables.lane_dp: DisplayPort lane-specific tunables + * @tunables.lane_usb4: USB4 lane-specific tunables + * @mode: Current PHY operating mode + * @swap_lanes: True if lanes must be swapped due to cable orientation + * @dp_link_rate: DisplayPort link rate + * @pipehandler_up: True if the PIPE mux ("pipehandler") is set to USB3 or USB4 mode + * @regs: Memory-mapped registers + * @regs.core: Core registers + * @regs.axi2af: AXI to Apple Fabric interface registers + * @regs.usb2phy: USB2 PHY registers + * @regs.pipehandler: USB3 PIPE interface ("pipehandler") registers + * @regs.lpdptx: DisplayPort registers + * @res: Resources for memory-mapped registers, used to verify that tunables aren't out of bounds + * @res.core: Core register resource + * @res.axi2af: AXI to Apple Fabric interface resource + * @phys: PHY instances + * @phys.usb2: USB2 PHY instance + * @phys.usb3: USB3 PHY instance + * @phys.dp: DisplayPort PHY instance + * @phy_provider: PHY provider instance + * @rcdev: Reset controller device + * @sw: Type-C switch instance + * @mux: Type-C mux instance + * @lock: Mutex for synchronizing register access across PHY, Type-C switch/mux and reset controller + */ +struct apple_atcphy { + struct device_node *np; + struct device *dev; + + struct { + struct apple_tunable *axi2af; + struct apple_tunable *common[2]; + struct apple_tunable *lane_usb3[2]; + struct apple_tunable *lane_dp[2]; + struct apple_tunable *lane_usb4[2]; + } tunables; + + enum atcphy_mode mode; + bool swap_lanes; + int dp_link_rate; + bool pipehandler_up; + + struct { + void __iomem *core; + void __iomem *axi2af; + void __iomem *usb2phy; + void __iomem *pipehandler; + void __iomem *lpdptx; + } regs; + + struct { + struct resource *core; + struct resource *axi2af; + } res; + + struct { + struct phy *usb2; + struct phy *usb3; + struct phy *dp; + } phys; + struct phy_provider *phy_provider; + + struct reset_controller_dev rcdev; + + struct typec_switch *sw; + struct typec_mux *mux; + + struct mutex lock; +}; + +static const struct { + const struct atcphy_mode_configuration normal; + const struct atcphy_mode_configuration swapped; + bool enable_dp_aux; + enum atcphy_pipehandler_state pipehandler_state; +} atcphy_modes[] = { + [APPLE_ATCPHY_MODE_OFF] = { + .normal = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_USB3, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_NONE, + .crossbar_dp_both_pma = false, + .lane_mode = {ACIOPHY_LANE_MODE_OFF, ACIOPHY_LANE_MODE_OFF}, + .dp_lane = {false, false}, + .set_swap = false, + }, + .swapped = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_USB3_SWAPPED, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_NONE, + .crossbar_dp_both_pma = false, + .lane_mode = {ACIOPHY_LANE_MODE_OFF, ACIOPHY_LANE_MODE_OFF}, + .dp_lane = {false, false}, + .set_swap = false, /* doesn't matter since the SS lanes are off */ + }, + .enable_dp_aux = false, + .pipehandler_state = ATCPHY_PIPEHANDLER_STATE_DUMMY, + }, + [APPLE_ATCPHY_MODE_USB2] = { + .normal = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_USB3, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_NONE, + .crossbar_dp_both_pma = false, + .lane_mode = {ACIOPHY_LANE_MODE_OFF, ACIOPHY_LANE_MODE_OFF}, + .dp_lane = {false, false}, + .set_swap = false, + }, + .swapped = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_USB3_SWAPPED, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_NONE, + .crossbar_dp_both_pma = false, + .lane_mode = {ACIOPHY_LANE_MODE_OFF, ACIOPHY_LANE_MODE_OFF}, + .dp_lane = {false, false}, + .set_swap = false, /* doesn't matter since the SS lanes are off */ + }, + .enable_dp_aux = false, + .pipehandler_state = ATCPHY_PIPEHANDLER_STATE_DUMMY, + }, + [APPLE_ATCPHY_MODE_USB3] = { + /* + * Setting up the lanes as DP/USB3 is intentional here, USB3/USB3 does not work + * and isn't required since this PHY does not support 20GBps mode anyway. + * The only difference to APPLE_ATCPHY_MODE_USB3_DP is that DP Aux is not enabled. + */ + .normal = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_USB3_DP, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_UNK008, + .crossbar_dp_both_pma = false, + .lane_mode = {ACIOPHY_LANE_MODE_USB3, ACIOPHY_LANE_MODE_DP}, + .dp_lane = {false, true}, + .set_swap = false, + }, + .swapped = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_USB3_DP_SWAPPED, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_UNK008, + .crossbar_dp_both_pma = false, + .lane_mode = {ACIOPHY_LANE_MODE_DP, ACIOPHY_LANE_MODE_USB3}, + .dp_lane = {true, false}, + .set_swap = true, + }, + .enable_dp_aux = false, + .pipehandler_state = ATCPHY_PIPEHANDLER_STATE_USB3, + }, + [APPLE_ATCPHY_MODE_USB3_DP] = { + .normal = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_USB3_DP, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_UNK008, + .crossbar_dp_both_pma = false, + .lane_mode = {ACIOPHY_LANE_MODE_USB3, ACIOPHY_LANE_MODE_DP}, + .dp_lane = {false, true}, + .set_swap = false, + }, + .swapped = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_USB3_DP_SWAPPED, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_UNK008, + .crossbar_dp_both_pma = false, + .lane_mode = {ACIOPHY_LANE_MODE_DP, ACIOPHY_LANE_MODE_USB3}, + .dp_lane = {true, false}, + .set_swap = true, + }, + .enable_dp_aux = true, + .pipehandler_state = ATCPHY_PIPEHANDLER_STATE_USB3, + }, + [APPLE_ATCPHY_MODE_TBT] = { + .normal = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_USB4, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_NONE, + .crossbar_dp_both_pma = false, + .lane_mode = {ACIOPHY_LANE_MODE_USB4, ACIOPHY_LANE_MODE_USB4}, + .dp_lane = {false, false}, + .set_swap = false, + }, + .swapped = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_USB4_SWAPPED, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_NONE, + .crossbar_dp_both_pma = false, + .lane_mode = {ACIOPHY_LANE_MODE_USB4, ACIOPHY_LANE_MODE_USB4}, + .dp_lane = {false, false}, + .set_swap = false, /* intentionally false */ + }, + .enable_dp_aux = false, + .pipehandler_state = ATCPHY_PIPEHANDLER_STATE_DUMMY, + }, + [APPLE_ATCPHY_MODE_USB4] = { + .normal = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_USB4, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_NONE, + .crossbar_dp_both_pma = false, + .lane_mode = {ACIOPHY_LANE_MODE_USB4, ACIOPHY_LANE_MODE_USB4}, + .dp_lane = {false, false}, + .set_swap = false, + }, + .swapped = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_USB4_SWAPPED, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_NONE, + .crossbar_dp_both_pma = false, + .lane_mode = {ACIOPHY_LANE_MODE_USB4, ACIOPHY_LANE_MODE_USB4}, + .dp_lane = {false, false}, + .set_swap = false, /* intentionally false */ + }, + .enable_dp_aux = false, + .pipehandler_state = ATCPHY_PIPEHANDLER_STATE_USB4, + }, + [APPLE_ATCPHY_MODE_DP] = { + .normal = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_DP, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_UNK100, + .crossbar_dp_both_pma = true, + .lane_mode = {ACIOPHY_LANE_MODE_DP, ACIOPHY_LANE_MODE_DP}, + .dp_lane = {true, true}, + .set_swap = false, + }, + .swapped = { + .crossbar = ACIOPHY_CROSSBAR_PROTOCOL_DP, + .crossbar_dp_single_pma = ACIOPHY_CROSSBAR_DP_SINGLE_PMA_UNK008, + .crossbar_dp_both_pma = false, /* intentionally false */ + .lane_mode = {ACIOPHY_LANE_MODE_DP, ACIOPHY_LANE_MODE_DP}, + .dp_lane = {true, true}, + .set_swap = false, /* intentionally false */ + }, + .enable_dp_aux = true, + .pipehandler_state = ATCPHY_PIPEHANDLER_STATE_DUMMY, + }, +}; + +static const struct atcphy_dp_link_rate_configuration dp_lr_config[] = { + [ATCPHY_DP_LINK_RATE_RBR] = { + .freqinit_count_target = 0x21c, + .fbdivn_frac_den = 0x0, + .fbdivn_frac_num = 0x0, + .pclk_div_sel = 0x13, + .lfclk_ctrl = 0x5, + .vclk_op_divn = 0x2, + .plla_clkout_vreg_bypass = true, + .txa_ldoclk_bypass = true, + .txa_div2_en = true, + }, + [ATCPHY_DP_LINK_RATE_HBR] = { + .freqinit_count_target = 0x1c2, + .fbdivn_frac_den = 0x3ffe, + .fbdivn_frac_num = 0x1fff, + .pclk_div_sel = 0x9, + .lfclk_ctrl = 0x5, + .vclk_op_divn = 0x2, + .plla_clkout_vreg_bypass = true, + .txa_ldoclk_bypass = true, + .txa_div2_en = false, + }, + [ATCPHY_DP_LINK_RATE_HBR2] = { + .freqinit_count_target = 0x1c2, + .fbdivn_frac_den = 0x3ffe, + .fbdivn_frac_num = 0x1fff, + .pclk_div_sel = 0x4, + .lfclk_ctrl = 0x5, + .vclk_op_divn = 0x0, + .plla_clkout_vreg_bypass = true, + .txa_ldoclk_bypass = true, + .txa_div2_en = false, + }, + [ATCPHY_DP_LINK_RATE_HBR3] = { + .freqinit_count_target = 0x2a3, + .fbdivn_frac_den = 0x3ffc, + .fbdivn_frac_num = 0x2ffd, + .pclk_div_sel = 0x4, + .lfclk_ctrl = 0x6, + .vclk_op_divn = 0x0, + .plla_clkout_vreg_bypass = false, + .txa_ldoclk_bypass = false, + .txa_div2_en = false, + }, +}; + +static inline void mask32(void __iomem *reg, u32 mask, u32 set) +{ + u32 value = readl(reg); + + value &= ~mask; + value |= set; + writel(value, reg); +} + +static inline void core_mask32(struct apple_atcphy *atcphy, u32 reg, u32 mask, u32 set) +{ + mask32(atcphy->regs.core + reg, mask, set); +} + +static inline void set32(void __iomem *reg, u32 set) +{ + mask32(reg, 0, set); +} + +static inline void core_set32(struct apple_atcphy *atcphy, u32 reg, u32 set) +{ + core_mask32(atcphy, reg, 0, set); +} + +static inline void clear32(void __iomem *reg, u32 clear) +{ + mask32(reg, clear, 0); +} + +static inline void core_clear32(struct apple_atcphy *atcphy, u32 reg, u32 clear) +{ + core_mask32(atcphy, reg, clear, 0); +} + +static const struct atcphy_mode_configuration *atcphy_get_mode_config(struct apple_atcphy *atcphy, + enum atcphy_mode mode) +{ + if (atcphy->swap_lanes) + return &atcphy_modes[mode].swapped; + else + return &atcphy_modes[mode].normal; +} + +static void atcphy_apply_tunables(struct apple_atcphy *atcphy, enum atcphy_mode mode) +{ + const int lane0 = atcphy->swap_lanes ? 1 : 0; + const int lane1 = atcphy->swap_lanes ? 0 : 1; + + apple_tunable_apply(atcphy->regs.core, atcphy->tunables.common[0]); + apple_tunable_apply(atcphy->regs.axi2af, atcphy->tunables.axi2af); + apple_tunable_apply(atcphy->regs.core, atcphy->tunables.common[1]); + + switch (mode) { + /* + * USB 3.2 Gen 2x2 / SuperSpeed 20Gbps is not supported by this hardware and applying USB3 + * tunables to both lanes does not result in a working PHY configuration. Thus, both + * USB3-only and USB3/DP get the same tunable setup here. + */ + case APPLE_ATCPHY_MODE_USB3: + case APPLE_ATCPHY_MODE_USB3_DP: + apple_tunable_apply(atcphy->regs.core, atcphy->tunables.lane_usb3[lane0]); + apple_tunable_apply(atcphy->regs.core, atcphy->tunables.lane_dp[lane1]); + break; + + case APPLE_ATCPHY_MODE_DP: + apple_tunable_apply(atcphy->regs.core, atcphy->tunables.lane_dp[lane0]); + apple_tunable_apply(atcphy->regs.core, atcphy->tunables.lane_dp[lane1]); + break; + + /* + * Even though the various Thunderbolt versions and USB4 are different protocols they need + * the same tunables. The actual protocol-specific setup happens inside the Thunderbolt/USB4 + * native host interface. + */ + case APPLE_ATCPHY_MODE_TBT: + case APPLE_ATCPHY_MODE_USB4: + apple_tunable_apply(atcphy->regs.core, atcphy->tunables.lane_usb4[lane0]); + apple_tunable_apply(atcphy->regs.core, atcphy->tunables.lane_usb4[lane1]); + break; + + case APPLE_ATCPHY_MODE_OFF: + case APPLE_ATCPHY_MODE_USB2: + break; + } +} + +static int atcphy_pipehandler_lock(struct apple_atcphy *atcphy) +{ + int ret; + u32 reg; + + if (readl(atcphy->regs.pipehandler + PIPEHANDLER_LOCK_REQ) & PIPEHANDLER_LOCK_EN) { + dev_warn(atcphy->dev, "Pipehandler already locked\n"); + return 0; + } + + set32(atcphy->regs.pipehandler + PIPEHANDLER_LOCK_REQ, PIPEHANDLER_LOCK_EN); + + ret = readl_poll_timeout(atcphy->regs.pipehandler + PIPEHANDLER_LOCK_ACK, reg, + reg & PIPEHANDLER_LOCK_EN, 10, PIPEHANDLER_LOCK_ACK_TIMEOUT_US); + if (ret) { + clear32(atcphy->regs.pipehandler + PIPEHANDLER_LOCK_REQ, 1); + dev_warn(atcphy->dev, "Pipehandler lock not acked.\n"); + } + + return ret; +} + +static int atcphy_pipehandler_unlock(struct apple_atcphy *atcphy) +{ + int ret; + u32 reg; + + clear32(atcphy->regs.pipehandler + PIPEHANDLER_LOCK_REQ, PIPEHANDLER_LOCK_EN); + ret = readl_poll_timeout(atcphy->regs.pipehandler + PIPEHANDLER_LOCK_ACK, reg, + !(reg & PIPEHANDLER_LOCK_EN), 10, PIPEHANDLER_LOCK_ACK_TIMEOUT_US); + if (ret) + dev_warn(atcphy->dev, "Pipehandler lock release not acked.\n"); + + return ret; +} + +static int atcphy_pipehandler_check(struct apple_atcphy *atcphy) +{ + int ret; + + lockdep_assert_held(&atcphy->lock); + + if (readl(atcphy->regs.pipehandler + PIPEHANDLER_LOCK_ACK) & PIPEHANDLER_LOCK_EN) { + dev_warn(atcphy->dev, "Pipehandler already locked\n"); + + ret = atcphy_pipehandler_unlock(atcphy); + if (ret) { + dev_err(atcphy->dev, "Failed to unlock pipehandler\n"); + return ret; + } + } + + return 0; +} + +static int atcphy_configure_pipehandler_usb3(struct apple_atcphy *atcphy, bool host) +{ + int ret; + u32 reg; + + ret = atcphy_pipehandler_check(atcphy); + if (ret) + return ret; + + /* + * Only host mode requires this unknown BIST sequence to work correctly, possibly due to + * some hardware quirk. Guest mode breaks if we try to apply this sequence. + */ + if (host) { + /* Force disable link detection */ + clear32(atcphy->regs.pipehandler + PIPEHANDLER_OVERRIDE_VALUES, + PIPEHANDLER_OVERRIDE_VAL_RXDETECT0 | PIPEHANDLER_OVERRIDE_VAL_RXDETECT1); + set32(atcphy->regs.pipehandler + PIPEHANDLER_OVERRIDE, + PIPEHANDLER_OVERRIDE_RXVALID); + set32(atcphy->regs.pipehandler + PIPEHANDLER_OVERRIDE, + PIPEHANDLER_OVERRIDE_RXDETECT); + + ret = atcphy_pipehandler_lock(atcphy); + if (ret) { + dev_err(atcphy->dev, "Failed to lock pipehandler"); + return ret; + } + + /* BIST dance */ + core_set32(atcphy, ACIOPHY_TOP_BIST_PHY_CFG0, + ACIOPHY_TOP_BIST_PHY_CFG0_LN0_RESET_N); + core_set32(atcphy, ACIOPHY_TOP_BIST_OV_CFG, ACIOPHY_TOP_BIST_OV_CFG_LN0_RESET_N_OV); + ret = readl_poll_timeout(atcphy->regs.core + ACIOPHY_TOP_PHY_STAT, reg, + !(reg & ACIOPHY_TOP_PHY_STAT_LN0_UNK23), 10, 10000); + if (ret) + dev_warn(atcphy->dev, + "Timed out waiting for ACIOPHY_TOP_PHY_STAT_LN0_UNK23\n"); + + core_set32(atcphy, ACIOPHY_TOP_BIST_READ_CTRL, + ACIOPHY_TOP_BIST_READ_CTRL_LN0_PHY_STATUS_RE); + core_clear32(atcphy, ACIOPHY_TOP_BIST_READ_CTRL, + ACIOPHY_TOP_BIST_READ_CTRL_LN0_PHY_STATUS_RE); + + core_mask32(atcphy, ACIOPHY_TOP_BIST_PHY_CFG1, + ACIOPHY_TOP_BIST_PHY_CFG1_LN0_PWR_DOWN, + FIELD_PREP(ACIOPHY_TOP_BIST_PHY_CFG1_LN0_PWR_DOWN, 3)); + + core_set32(atcphy, ACIOPHY_TOP_BIST_OV_CFG, + ACIOPHY_TOP_BIST_OV_CFG_LN0_PWR_DOWN_OV); + core_set32(atcphy, ACIOPHY_TOP_BIST_CIOPHY_CFG1, + ACIOPHY_TOP_BIST_CIOPHY_CFG1_CLK_EN); + core_set32(atcphy, ACIOPHY_TOP_BIST_CIOPHY_CFG1, + ACIOPHY_TOP_BIST_CIOPHY_CFG1_BIST_EN); + writel(0, atcphy->regs.core + ACIOPHY_TOP_BIST_CIOPHY_CFG1); + + ret = readl_poll_timeout(atcphy->regs.core + ACIOPHY_TOP_PHY_STAT, reg, + (reg & ACIOPHY_TOP_PHY_STAT_LN0_UNK0), 10, 10000); + if (ret) + dev_warn(atcphy->dev, + "timed out waiting for ACIOPHY_TOP_PHY_STAT_LN0_UNK0\n"); + + ret = readl_poll_timeout(atcphy->regs.core + ACIOPHY_TOP_PHY_STAT, reg, + !(reg & ACIOPHY_TOP_PHY_STAT_LN0_UNK23), 10, 10000); + if (ret) + dev_warn(atcphy->dev, + "timed out waiting for ACIOPHY_TOP_PHY_STAT_LN0_UNK23\n"); + + /* Clear reset for non-selected USB3 PHY (?) */ + mask32(atcphy->regs.pipehandler + PIPEHANDLER_NONSELECTED_OVERRIDE, + PIPEHANDLER_NATIVE_POWER_DOWN, FIELD_PREP(PIPEHANDLER_NATIVE_POWER_DOWN, 3)); + clear32(atcphy->regs.pipehandler + PIPEHANDLER_NONSELECTED_OVERRIDE, + PIPEHANDLER_NATIVE_RESET); + + /* More BIST stuff (?) */ + writel(0, atcphy->regs.core + ACIOPHY_TOP_BIST_OV_CFG); + core_set32(atcphy, ACIOPHY_TOP_BIST_CIOPHY_CFG1, + ACIOPHY_TOP_BIST_CIOPHY_CFG1_CLK_EN); + core_set32(atcphy, ACIOPHY_TOP_BIST_CIOPHY_CFG1, + ACIOPHY_TOP_BIST_CIOPHY_CFG1_BIST_EN); + } + + /* Configure PIPE mux to USB3 PHY */ + mask32(atcphy->regs.pipehandler + PIPEHANDLER_MUX_CTRL, PIPEHANDLER_MUX_CTRL_CLK, + FIELD_PREP(PIPEHANDLER_MUX_CTRL_CLK, PIPEHANDLER_MUX_CTRL_CLK_OFF)); + udelay(10); + mask32(atcphy->regs.pipehandler + PIPEHANDLER_MUX_CTRL, PIPEHANDLER_MUX_CTRL_DATA, + FIELD_PREP(PIPEHANDLER_MUX_CTRL_DATA, PIPEHANDLER_MUX_CTRL_DATA_USB3)); + udelay(10); + mask32(atcphy->regs.pipehandler + PIPEHANDLER_MUX_CTRL, PIPEHANDLER_MUX_CTRL_CLK, + FIELD_PREP(PIPEHANDLER_MUX_CTRL_CLK, PIPEHANDLER_MUX_CTRL_CLK_USB3)); + udelay(10); + + /* Remove link detection override */ + clear32(atcphy->regs.pipehandler + PIPEHANDLER_OVERRIDE, PIPEHANDLER_OVERRIDE_RXVALID); + clear32(atcphy->regs.pipehandler + PIPEHANDLER_OVERRIDE, PIPEHANDLER_OVERRIDE_RXDETECT); + + /* Pipehandler was only locked when the BIST sequence was applied for host mode */ + if (host) { + ret = atcphy_pipehandler_unlock(atcphy); + if (ret) + dev_warn(atcphy->dev, "Failed to unlock pipehandler"); + } + + return 0; +} + +static int atcphy_configure_pipehandler_dummy(struct apple_atcphy *atcphy) +{ + int ret; + + ret = atcphy_pipehandler_check(atcphy); + if (ret) + return ret; + + /* Force disable link detection */ + clear32(atcphy->regs.pipehandler + PIPEHANDLER_OVERRIDE_VALUES, + PIPEHANDLER_OVERRIDE_VAL_RXDETECT0 | PIPEHANDLER_OVERRIDE_VAL_RXDETECT1); + set32(atcphy->regs.pipehandler + PIPEHANDLER_OVERRIDE, PIPEHANDLER_OVERRIDE_RXVALID); + set32(atcphy->regs.pipehandler + PIPEHANDLER_OVERRIDE, PIPEHANDLER_OVERRIDE_RXDETECT); + + ret = atcphy_pipehandler_lock(atcphy); + if (ret) + dev_warn(atcphy->dev, "Failed to lock pipehandler"); + + /* Switch to dummy PHY */ + mask32(atcphy->regs.pipehandler + PIPEHANDLER_MUX_CTRL, PIPEHANDLER_MUX_CTRL_CLK, + FIELD_PREP(PIPEHANDLER_MUX_CTRL_CLK, PIPEHANDLER_MUX_CTRL_CLK_OFF)); + udelay(10); + mask32(atcphy->regs.pipehandler + PIPEHANDLER_MUX_CTRL, PIPEHANDLER_MUX_CTRL_DATA, + FIELD_PREP(PIPEHANDLER_MUX_CTRL_DATA, PIPEHANDLER_MUX_CTRL_DATA_DUMMY)); + udelay(10); + mask32(atcphy->regs.pipehandler + PIPEHANDLER_MUX_CTRL, PIPEHANDLER_MUX_CTRL_CLK, + FIELD_PREP(PIPEHANDLER_MUX_CTRL_CLK, PIPEHANDLER_MUX_CTRL_CLK_DUMMY)); + udelay(10); + + ret = atcphy_pipehandler_unlock(atcphy); + if (ret) + dev_warn(atcphy->dev, "Failed to unlock pipehandler"); + + mask32(atcphy->regs.pipehandler + PIPEHANDLER_NONSELECTED_OVERRIDE, + PIPEHANDLER_NATIVE_POWER_DOWN, FIELD_PREP(PIPEHANDLER_NATIVE_POWER_DOWN, 2)); + set32(atcphy->regs.pipehandler + PIPEHANDLER_NONSELECTED_OVERRIDE, + PIPEHANDLER_NATIVE_RESET); + + return 0; +} + +static int atcphy_configure_pipehandler(struct apple_atcphy *atcphy, bool host) +{ + int ret; + + lockdep_assert_held(&atcphy->lock); + + switch (atcphy_modes[atcphy->mode].pipehandler_state) { + case ATCPHY_PIPEHANDLER_STATE_USB3: + ret = atcphy_configure_pipehandler_usb3(atcphy, host); + atcphy->pipehandler_up = true; + break; + case ATCPHY_PIPEHANDLER_STATE_USB4: + dev_warn(atcphy->dev, + "ATCPHY_PIPEHANDLER_STATE_USB4 not implemented; falling back to USB2\n"); + ret = atcphy_configure_pipehandler_dummy(atcphy); + atcphy->pipehandler_up = false; + break; + default: + ret = -EINVAL; + } + + return ret; +} + +static void atcphy_setup_pipehandler(struct apple_atcphy *atcphy) +{ + lockdep_assert_held(&atcphy->lock); + + mask32(atcphy->regs.pipehandler + PIPEHANDLER_MUX_CTRL, PIPEHANDLER_MUX_CTRL_CLK, + FIELD_PREP(PIPEHANDLER_MUX_CTRL_CLK, PIPEHANDLER_MUX_CTRL_CLK_OFF)); + udelay(10); + mask32(atcphy->regs.pipehandler + PIPEHANDLER_MUX_CTRL, PIPEHANDLER_MUX_CTRL_DATA, + FIELD_PREP(PIPEHANDLER_MUX_CTRL_DATA, PIPEHANDLER_MUX_CTRL_DATA_DUMMY)); + udelay(10); + mask32(atcphy->regs.pipehandler + PIPEHANDLER_MUX_CTRL, PIPEHANDLER_MUX_CTRL_CLK, + FIELD_PREP(PIPEHANDLER_MUX_CTRL_CLK, PIPEHANDLER_MUX_CTRL_CLK_DUMMY)); + udelay(10); +} + +static void atcphy_configure_lanes(struct apple_atcphy *atcphy, enum atcphy_mode mode) +{ + const struct atcphy_mode_configuration *mode_cfg = atcphy_get_mode_config(atcphy, mode); + + core_mask32(atcphy, ACIOPHY_LANE_MODE, ACIOPHY_LANE_MODE_RX0, + FIELD_PREP(ACIOPHY_LANE_MODE_RX0, mode_cfg->lane_mode[0])); + core_mask32(atcphy, ACIOPHY_LANE_MODE, ACIOPHY_LANE_MODE_TX0, + FIELD_PREP(ACIOPHY_LANE_MODE_TX0, mode_cfg->lane_mode[0])); + core_mask32(atcphy, ACIOPHY_LANE_MODE, ACIOPHY_LANE_MODE_RX1, + FIELD_PREP(ACIOPHY_LANE_MODE_RX1, mode_cfg->lane_mode[1])); + core_mask32(atcphy, ACIOPHY_LANE_MODE, ACIOPHY_LANE_MODE_TX1, + FIELD_PREP(ACIOPHY_LANE_MODE_TX1, mode_cfg->lane_mode[1])); + core_mask32(atcphy, ACIOPHY_CROSSBAR, ACIOPHY_CROSSBAR_PROTOCOL, + FIELD_PREP(ACIOPHY_CROSSBAR_PROTOCOL, mode_cfg->crossbar)); + + if (mode_cfg->set_swap) + core_set32(atcphy, ATCPHY_MISC, ATCPHY_MISC_LANE_SWAP); + else + core_clear32(atcphy, ATCPHY_MISC, ATCPHY_MISC_LANE_SWAP); + + core_mask32(atcphy, ACIOPHY_CROSSBAR, ACIOPHY_CROSSBAR_DP_SINGLE_PMA, + FIELD_PREP(ACIOPHY_CROSSBAR_DP_SINGLE_PMA, mode_cfg->crossbar_dp_single_pma)); + if (mode_cfg->crossbar_dp_both_pma) + core_set32(atcphy, ACIOPHY_CROSSBAR, ACIOPHY_CROSSBAR_DP_BOTH_PMA); + else + core_clear32(atcphy, ACIOPHY_CROSSBAR, ACIOPHY_CROSSBAR_DP_BOTH_PMA); + + if (mode_cfg->dp_lane[0]) { + core_set32(atcphy, LN0_AUSPMA_RX_TOP + LN_AUSPMA_RX_TOP_PMAFSM, + LN_AUSPMA_RX_TOP_PMAFSM_PCS_OV); + udelay(10); + core_clear32(atcphy, LN0_AUSPMA_RX_TOP + LN_AUSPMA_RX_TOP_PMAFSM, + LN_AUSPMA_RX_TOP_PMAFSM_PCS_REQ); + } else { + core_clear32(atcphy, LN0_AUSPMA_RX_TOP + LN_AUSPMA_RX_TOP_PMAFSM, + LN_AUSPMA_RX_TOP_PMAFSM_PCS_OV); + udelay(10); + } + + if (mode_cfg->dp_lane[1]) { + core_set32(atcphy, LN1_AUSPMA_RX_TOP + LN_AUSPMA_RX_TOP_PMAFSM, + LN_AUSPMA_RX_TOP_PMAFSM_PCS_OV); + udelay(10); + core_clear32(atcphy, LN1_AUSPMA_RX_TOP + LN_AUSPMA_RX_TOP_PMAFSM, + LN_AUSPMA_RX_TOP_PMAFSM_PCS_REQ); + } else { + core_clear32(atcphy, LN1_AUSPMA_RX_TOP + LN_AUSPMA_RX_TOP_PMAFSM, + LN_AUSPMA_RX_TOP_PMAFSM_PCS_OV); + udelay(10); + } +} + +static void atcphy_enable_dp_aux(struct apple_atcphy *atcphy) +{ + core_set32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DPTXPHY_PMA_LANE_RESET_N); + core_set32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DPTXPHY_PMA_LANE_RESET_N_OV); + + core_mask32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DPRX_PCLK_SELECT, + FIELD_PREP(DPRX_PCLK_SELECT, 1)); + core_set32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DPRX_PCLK_ENABLE); + + core_mask32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DPTX_PCLK1_SELECT, + FIELD_PREP(DPTX_PCLK1_SELECT, 1)); + core_set32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DPTX_PCLK1_ENABLE); + + core_mask32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DPTX_PCLK2_SELECT, + FIELD_PREP(DPTX_PCLK2_SELECT, 1)); + core_set32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DPTX_PCLK2_ENABLE); + + core_set32(atcphy, ACIOPHY_PLL_COMMON_CTRL, + ACIOPHY_PLL_WAIT_FOR_CMN_READY_BEFORE_RESET_EXIT); + + set32(atcphy->regs.lpdptx + LPDPTX_AUX_CONTROL, LPDPTX_AUX_CLAMP_EN); + set32(atcphy->regs.lpdptx + LPDPTX_AUX_CONTROL, LPDPTX_SLEEP_B_SML_IN); + udelay(10); + set32(atcphy->regs.lpdptx + LPDPTX_AUX_CONTROL, LPDPTX_SLEEP_B_BIG_IN); + udelay(10); + clear32(atcphy->regs.lpdptx + LPDPTX_AUX_CONTROL, LPDPTX_AUX_CLAMP_EN); + clear32(atcphy->regs.lpdptx + LPDPTX_AUX_CONTROL, LPDPTX_AUX_PWN_DOWN); + clear32(atcphy->regs.lpdptx + LPDPTX_AUX_CONTROL, LPDPTX_TXTERM_CODEMSB); + mask32(atcphy->regs.lpdptx + LPDPTX_AUX_CONTROL, LPDPTX_TXTERM_CODE, + FIELD_PREP(LPDPTX_TXTERM_CODE, 0x16)); + + set32(atcphy->regs.lpdptx + LPDPTX_AUX_CFG_BLK_AUX_LDO_CTRL, 0x1c00); + mask32(atcphy->regs.lpdptx + LPDPTX_AUX_SHM_CFG_BLK_AUX_CTRL_REG1, LPDPTX_CFG_PMA_PHYS_ADJ, + FIELD_PREP(LPDPTX_CFG_PMA_PHYS_ADJ, 5)); + set32(atcphy->regs.lpdptx + LPDPTX_AUX_SHM_CFG_BLK_AUX_CTRL_REG1, + LPDPTX_CFG_PMA_PHYS_ADJ_OV); + + clear32(atcphy->regs.lpdptx + LPDPTX_AUX_CFG_BLK_AUX_MARGIN, + LPDPTX_MARGIN_RCAL_RXOFFSET_EN); + + clear32(atcphy->regs.lpdptx + LPDPTX_AUX_CFG_BLK_AUX_CTRL, LPDPTX_BLK_AUX_CTRL_PWRDN); + set32(atcphy->regs.lpdptx + LPDPTX_AUX_SHM_CFG_BLK_AUX_CTRL_REG0, + LPDPTX_CFG_PMA_AUX_SEL_LF_DATA); + mask32(atcphy->regs.lpdptx + LPDPTX_AUX_CFG_BLK_AUX_CTRL, LPDPTX_BLK_AUX_RXOFFSET, + FIELD_PREP(LPDPTX_BLK_AUX_RXOFFSET, 3)); + + mask32(atcphy->regs.lpdptx + LPDPTX_AUX_CFG_BLK_AUX_MARGIN, LPDPTX_AUX_MARGIN_RCAL_TXSWING, + FIELD_PREP(LPDPTX_AUX_MARGIN_RCAL_TXSWING, 12)); + + atcphy->dp_link_rate = -1; +} + +static void atcphy_disable_dp_aux(struct apple_atcphy *atcphy) +{ + set32(atcphy->regs.lpdptx + LPDPTX_AUX_CONTROL, LPDPTX_AUX_PWN_DOWN); + set32(atcphy->regs.lpdptx + LPDPTX_AUX_CFG_BLK_AUX_CTRL, LPDPTX_BLK_AUX_CTRL_PWRDN); + set32(atcphy->regs.lpdptx + LPDPTX_AUX_CONTROL, LPDPTX_AUX_CLAMP_EN); + clear32(atcphy->regs.lpdptx + LPDPTX_AUX_CONTROL, LPDPTX_SLEEP_B_SML_IN); + udelay(10); + clear32(atcphy->regs.lpdptx + LPDPTX_AUX_CONTROL, LPDPTX_SLEEP_B_BIG_IN); + udelay(10); + + core_clear32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DPTXPHY_PMA_LANE_RESET_N); + core_clear32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DPRX_PCLK_ENABLE); + core_clear32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DPTX_PCLK1_ENABLE); + core_clear32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DPTX_PCLK2_ENABLE); +} + +static int atcphy_dp_configure_lane(struct apple_atcphy *atcphy, enum atcphy_lane lane, + const struct atcphy_dp_link_rate_configuration *cfg) +{ + void __iomem *tx_shm, *rx_shm, *rx_top; + unsigned int tx_cal_code; + + lockdep_assert_held(&atcphy->lock); + + switch (lane) { + case APPLE_ATCPHY_LANE_0: + tx_shm = atcphy->regs.core + LN0_AUSPMA_TX_SHM; + rx_shm = atcphy->regs.core + LN0_AUSPMA_RX_SHM; + rx_top = atcphy->regs.core + LN0_AUSPMA_RX_TOP; + break; + case APPLE_ATCPHY_LANE_1: + tx_shm = atcphy->regs.core + LN1_AUSPMA_TX_SHM; + rx_shm = atcphy->regs.core + LN1_AUSPMA_RX_SHM; + rx_top = atcphy->regs.core + LN1_AUSPMA_RX_TOP; + break; + default: + return -EINVAL; + } + + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_LDOCLK, LN_LDOCLK_EN_SML); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_LDOCLK, LN_LDOCLK_EN_SML_OV); + udelay(10); + + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_LDOCLK, LN_LDOCLK_EN_BIG); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_LDOCLK, LN_LDOCLK_EN_BIG_OV); + udelay(10); + + if (cfg->txa_ldoclk_bypass) { + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_LDOCLK, LN_LDOCLK_BYPASS_SML); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_LDOCLK, LN_LDOCLK_BYPASS_SML_OV); + udelay(10); + + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_LDOCLK, LN_LDOCLK_BYPASS_BIG); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_LDOCLK, LN_LDOCLK_BYPASS_BIG_OV); + udelay(10); + } else { + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_LDOCLK, LN_LDOCLK_BYPASS_SML); + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_LDOCLK, LN_LDOCLK_BYPASS_SML_OV); + udelay(10); + + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_LDOCLK, LN_LDOCLK_BYPASS_BIG); + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_LDOCLK, LN_LDOCLK_BYPASS_BIG_OV); + udelay(10); + } + + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG0, LN_BYTECLK_RESET_SYNC_SEL_OV); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG0, LN_BYTECLK_RESET_SYNC_EN); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG0, LN_BYTECLK_RESET_SYNC_EN_OV); + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG0, LN_BYTECLK_RESET_SYNC_CLR); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG0, LN_BYTECLK_RESET_SYNC_CLR_OV); + + if (cfg->txa_div2_en) + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG1, LN_TXA_DIV2_EN); + else + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG1, LN_TXA_DIV2_EN); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG1, LN_TXA_DIV2_EN_OV); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG1, LN_TXA_CLK_EN); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG1, LN_TXA_CLK_EN_OV); + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG1, LN_TXA_DIV2_RESET); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_CFG_MAIN_REG1, LN_TXA_DIV2_RESET_OV); + + mask32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG0, LN_TXA_CAL_CTRL_BASE, + FIELD_PREP(LN_TXA_CAL_CTRL_BASE, 0xf)); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG0, LN_TXA_CAL_CTRL_BASE_OV); + + tx_cal_code = FIELD_GET(AUS_UNK_A20_TX_CAL_CODE, readl(atcphy->regs.core + AUS_UNK_A20)); + mask32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG0, LN_TXA_CAL_CTRL, + FIELD_PREP(LN_TXA_CAL_CTRL, (1 << tx_cal_code) - 1)); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG0, LN_TXA_CAL_CTRL_OV); + + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG2, LN_TXA_MARGIN); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG2, LN_TXA_MARGIN_OV); + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG2, LN_TXA_MARGIN_2R); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG2, LN_TXA_MARGIN_2R_OV); + + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG3, LN_TXA_MARGIN_POST); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG3, LN_TXA_MARGIN_POST_OV); + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG3, LN_TXA_MARGIN_POST_2R); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG3, LN_TXA_MARGIN_POST_2R_OV); + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG3, LN_TXA_MARGIN_POST_4R); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG3, LN_TXA_MARGIN_POST_4R_OV); + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG3, LN_TXA_MARGIN_PRE); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG3, LN_TXA_MARGIN_PRE_OV); + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG3, LN_TXA_MARGIN_PRE_2R); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG3, LN_TXA_MARGIN_PRE_2R_OV); + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG3, LN_TXA_MARGIN_PRE_4R); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG3, LN_TXA_MARGIN_PRE_4R_OV); + + clear32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG0, LN_TXA_HIZ); + set32(tx_shm + LN_AUSPMA_TX_SHM_TXA_IMP_REG0, LN_TXA_HIZ_OV); + + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_AFE_CTRL1, LN_RX_DIV20_RESET_N); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_AFE_CTRL1, LN_RX_DIV20_RESET_N_OV); + udelay(10); + + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_AFE_CTRL1, LN_RX_DIV20_RESET_N); + + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL12, LN_TX_BYTECLK_RESET_SYNC_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL12, LN_TX_BYTECLK_RESET_SYNC_EN_OV); + + mask32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_SAVOS_CTRL16, LN_TX_CAL_CODE, + FIELD_PREP(LN_TX_CAL_CODE, tx_cal_code)); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_SAVOS_CTRL16, LN_TX_CAL_CODE_OV); + + mask32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TERM_CTRL19, LN_TX_CLK_DLY_CTRL_TAPGEN, + FIELD_PREP(LN_TX_CLK_DLY_CTRL_TAPGEN, 3)); + + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL10, LN_DTVREG_ADJUST); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL13, LN_DTVREG_ADJUST_OV); + + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_SAVOS_CTRL16, LN_RXTERM_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_SAVOS_CTRL16, LN_RXTERM_EN_OV); + + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TERM_CTRL19, LN_TX_TEST_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TERM_CTRL19, LN_TX_TEST_EN_OV); + + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22, LN_VREF_TEST_RXLPBKDT_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22, LN_VREF_TEST_RXLPBKDT_EN_OV); + mask32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22, LN_VREF_LPBKIN_DATA, + FIELD_PREP(LN_VREF_LPBKIN_DATA, 3)); + mask32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22, LN_VREF_BIAS_SEL, + FIELD_PREP(LN_VREF_BIAS_SEL, 2)); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22, LN_VREF_BIAS_SEL_OV); + mask32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22, LN_VREF_ADJUST_GRAY, + FIELD_PREP(LN_VREF_ADJUST_GRAY, 0x18)); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22, LN_VREF_ADJUST_GRAY_OV); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22, LN_VREF_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22, LN_VREF_EN_OV); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22, LN_VREF_BOOST_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22, LN_VREF_BOOST_EN_OV); + udelay(10); + + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22, LN_VREF_BOOST_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_VREF_CTRL22, LN_VREF_BOOST_EN_OV); + udelay(10); + + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL13, LN_TX_PRE_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL13, LN_TX_PRE_EN_OV); + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL13, LN_TX_PST1_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL13, LN_TX_PST1_EN_OV); + + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL12, LN_TX_PBIAS_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL12, LN_TX_PBIAS_EN_OV); + + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_SAVOS_CTRL16, LN_RXTERM_PULLUP_LEAK_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_SAVOS_CTRL16, LN_RXTERM_PULLUP_LEAK_EN_OV); + + set32(rx_top + LN_AUSPMA_RX_TOP_TJ_CFG_RX_TXMODE, LN_RX_TXMODE); + + if (cfg->txa_div2_en) + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TERM_CTRL19, LN_TX_CLK_DIV2_EN); + else + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TERM_CTRL19, LN_TX_CLK_DIV2_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TERM_CTRL19, LN_TX_CLK_DIV2_EN_OV); + + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TERM_CTRL19, LN_TX_CLK_DIV2_RST); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TERM_CTRL19, LN_TX_CLK_DIV2_RST_OV); + + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL12, LN_TX_HRCLK_SEL); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL12, LN_TX_HRCLK_SEL_OV); + + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL17, LN_TX_MARGIN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL17, LN_TX_MARGIN_OV); + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL17, LN_TX_MARGIN_LSB); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL17, LN_TX_MARGIN_LSB_OV); + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL17, LN_TX_MARGIN_P1); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL17, LN_TX_MARGIN_P1_OV); + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL17, LN_TX_MARGIN_P1_LSB); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL17, LN_TX_MARGIN_P1_LSB_OV); + + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL18, LN_TX_P1_CODE); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL18, LN_TX_P1_CODE_OV); + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL18, LN_TX_P1_LSB_CODE); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL18, LN_TX_P1_LSB_CODE_OV); + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL18, LN_TX_MARGIN_PRE); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL18, LN_TX_MARGIN_PRE_OV); + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL18, LN_TX_MARGIN_PRE_LSB); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL18, LN_TX_MARGIN_PRE_LSB_OV); + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL18, LN_TX_PRE_LSB_CODE); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL18, LN_TX_PRE_LSB_CODE_OV); + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL18, LN_TX_PRE_CODE); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TX_CTRL18, LN_TX_PRE_CODE_OV); + + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL11, LN_DTVREG_SML_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL11, LN_DTVREG_SML_EN_OV); + udelay(10); + + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL11, LN_DTVREG_BIG_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL11, LN_DTVREG_BIG_EN_OV); + udelay(10); + + mask32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL10, LN_DTVREG_ADJUST, + FIELD_PREP(LN_DTVREG_ADJUST, 0xa)); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL13, LN_DTVREG_ADJUST_OV); + udelay(10); + + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TERM_CTRL19, LN_TX_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_TERM_CTRL19, LN_TX_EN_OV); + udelay(10); + + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_CTLE_CTRL0, LN_TX_CLK_EN); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_CTLE_CTRL0, LN_TX_CLK_EN_OV); + + clear32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL12, LN_TX_BYTECLK_RESET_SYNC_CLR); + set32(rx_shm + LN_AUSPMA_RX_SHM_TJ_RXA_DFE_CTRL12, LN_TX_BYTECLK_RESET_SYNC_CLR_OV); + + return 0; +} + +static int atcphy_auspll_apb_command(struct apple_atcphy *atcphy, u32 command) +{ + int ret; + u32 reg; + + reg = readl(atcphy->regs.core + AUSPLL_APB_CMD_OVERRIDE); + reg &= ~AUSPLL_APB_CMD_OVERRIDE_CMD; + reg |= FIELD_PREP(AUSPLL_APB_CMD_OVERRIDE_CMD, command); + reg |= AUSPLL_APB_CMD_OVERRIDE_REQ; + reg |= AUSPLL_APB_CMD_OVERRIDE_UNK28; + writel(reg, atcphy->regs.core + AUSPLL_APB_CMD_OVERRIDE); + + ret = readl_poll_timeout(atcphy->regs.core + AUSPLL_APB_CMD_OVERRIDE, reg, + (reg & AUSPLL_APB_CMD_OVERRIDE_ACK), 10, 10000); + if (ret) + dev_warn(atcphy->dev, "AUSPLL APB command was not acked\n"); + + core_clear32(atcphy, AUSPLL_APB_CMD_OVERRIDE, AUSPLL_APB_CMD_OVERRIDE_REQ); + + return 0; +} + +static int atcphy_dp_configure(struct apple_atcphy *atcphy, enum atcphy_dp_link_rate lr) +{ + const struct atcphy_dp_link_rate_configuration *cfg; + const struct atcphy_mode_configuration *mode_cfg; + int ret; + u32 reg; + + guard(mutex)(&atcphy->lock); + mode_cfg = atcphy_get_mode_config(atcphy, atcphy->mode); + cfg = &dp_lr_config[lr]; + + if (atcphy->dp_link_rate == lr) + return 0; + + ret = readl_poll_timeout(atcphy->regs.core + ACIOPHY_CMN_SHM_STS_REG0, reg, + (reg & ACIOPHY_CMN_SHM_STS_REG0_CMD_READY), 10, 10000); + if (ret) { + dev_err(atcphy->dev, "ACIOPHY_CMN_SHM_STS_REG0_CMD_READY not set.\n"); + return ret; + } + + core_clear32(atcphy, AUSPLL_FREQ_CFG, AUSPLL_FREQ_REFCLK); + + core_mask32(atcphy, AUSPLL_FREQ_DESC_A, AUSPLL_FD_FREQ_COUNT_TARGET, + FIELD_PREP(AUSPLL_FD_FREQ_COUNT_TARGET, cfg->freqinit_count_target)); + core_clear32(atcphy, AUSPLL_FREQ_DESC_A, AUSPLL_FD_FBDIVN_HALF); + core_clear32(atcphy, AUSPLL_FREQ_DESC_A, AUSPLL_FD_REV_DIVN); + core_mask32(atcphy, AUSPLL_FREQ_DESC_A, AUSPLL_FD_KI_MAN, FIELD_PREP(AUSPLL_FD_KI_MAN, 8)); + core_mask32(atcphy, AUSPLL_FREQ_DESC_A, AUSPLL_FD_KI_EXP, FIELD_PREP(AUSPLL_FD_KI_EXP, 3)); + core_mask32(atcphy, AUSPLL_FREQ_DESC_A, AUSPLL_FD_KP_MAN, FIELD_PREP(AUSPLL_FD_KP_MAN, 8)); + core_mask32(atcphy, AUSPLL_FREQ_DESC_A, AUSPLL_FD_KP_EXP, FIELD_PREP(AUSPLL_FD_KP_EXP, 7)); + core_clear32(atcphy, AUSPLL_FREQ_DESC_A, AUSPLL_FD_KPKI_SCALE_HBW); + + core_mask32(atcphy, AUSPLL_FREQ_DESC_B, AUSPLL_FD_FBDIVN_FRAC_DEN, + FIELD_PREP(AUSPLL_FD_FBDIVN_FRAC_DEN, cfg->fbdivn_frac_den)); + core_mask32(atcphy, AUSPLL_FREQ_DESC_B, AUSPLL_FD_FBDIVN_FRAC_NUM, + FIELD_PREP(AUSPLL_FD_FBDIVN_FRAC_NUM, cfg->fbdivn_frac_num)); + + core_clear32(atcphy, AUSPLL_FREQ_DESC_C, AUSPLL_FD_SDM_SSC_STEP); + core_clear32(atcphy, AUSPLL_FREQ_DESC_C, AUSPLL_FD_SDM_SSC_EN); + core_mask32(atcphy, AUSPLL_FREQ_DESC_C, AUSPLL_FD_PCLK_DIV_SEL, + FIELD_PREP(AUSPLL_FD_PCLK_DIV_SEL, cfg->pclk_div_sel)); + core_mask32(atcphy, AUSPLL_FREQ_DESC_C, AUSPLL_FD_LFSDM_DIV, + FIELD_PREP(AUSPLL_FD_LFSDM_DIV, 1)); + core_mask32(atcphy, AUSPLL_FREQ_DESC_C, AUSPLL_FD_LFCLK_CTRL, + FIELD_PREP(AUSPLL_FD_LFCLK_CTRL, cfg->lfclk_ctrl)); + core_mask32(atcphy, AUSPLL_FREQ_DESC_C, AUSPLL_FD_VCLK_OP_DIVN, + FIELD_PREP(AUSPLL_FD_VCLK_OP_DIVN, cfg->vclk_op_divn)); + core_set32(atcphy, AUSPLL_FREQ_DESC_C, AUSPLL_FD_VCLK_PRE_DIVN); + + core_mask32(atcphy, AUSPLL_CLKOUT_DIV, AUSPLL_CLKOUT_PLLA_REFBUFCLK_DI, + FIELD_PREP(AUSPLL_CLKOUT_PLLA_REFBUFCLK_DI, 7)); + + if (cfg->plla_clkout_vreg_bypass) + core_set32(atcphy, AUSPLL_CLKOUT_DTC_VREG, AUSPLL_DTC_VREG_BYPASS); + else + core_clear32(atcphy, AUSPLL_CLKOUT_DTC_VREG, AUSPLL_DTC_VREG_BYPASS); + + core_set32(atcphy, AUSPLL_BGR, AUSPLL_BGR_CTRL_AVAIL); + + core_set32(atcphy, AUSPLL_CLKOUT_MASTER, AUSPLL_CLKOUT_MASTER_PCLK_DRVR_EN); + core_set32(atcphy, AUSPLL_CLKOUT_MASTER, AUSPLL_CLKOUT_MASTER_PCLK2_DRVR_EN); + core_set32(atcphy, AUSPLL_CLKOUT_MASTER, AUSPLL_CLKOUT_MASTER_REFBUFCLK_DRVR_EN); + + ret = atcphy_auspll_apb_command(atcphy, 0); + if (ret) + return ret; + + ret = readl_poll_timeout(atcphy->regs.core + ACIOPHY_DP_PCLK_STAT, reg, + (reg & ACIOPHY_AUSPLL_LOCK), 10, 10000); + if (ret) { + dev_err(atcphy->dev, "ACIOPHY_DP_PCLK did not lock.\n"); + return ret; + } + + ret = atcphy_auspll_apb_command(atcphy, 0x2800); + if (ret) + return ret; + + if (mode_cfg->dp_lane[0]) { + ret = atcphy_dp_configure_lane(atcphy, APPLE_ATCPHY_LANE_0, cfg); + if (ret) + return ret; + } + + if (mode_cfg->dp_lane[1]) { + ret = atcphy_dp_configure_lane(atcphy, APPLE_ATCPHY_LANE_1, cfg); + if (ret) + return ret; + } + + core_clear32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DP_PMA_BYTECLK_RESET); + core_clear32(atcphy, ACIOPHY_LANE_DP_CFG_BLK_TX_DP_CTRL0, DP_MAC_DIV20_CLK_SEL); + + atcphy->dp_link_rate = lr; + return 0; +} + +static void atcphy_usb2_power_off(struct apple_atcphy *atcphy) +{ + /* Disable the PHY, this clears USB2PHY_USBCTL_RUN */ + writel(USB2PHY_USBCTL_ISOLATION, atcphy->regs.usb2phy + USB2PHY_USBCTL); + udelay(10); + + /* Switch the PHY to low power mode */ + set32(atcphy->regs.usb2phy + USB2PHY_CTL, USB2PHY_CTL_SIDDQ); + udelay(10); + + /* Enable all resets */ + set32(atcphy->regs.usb2phy + USB2PHY_CTL, USB2PHY_CTL_PORT_RESET); + udelay(10); + set32(atcphy->regs.usb2phy + USB2PHY_CTL, USB2PHY_CTL_RESET); + udelay(10); + clear32(atcphy->regs.usb2phy + USB2PHY_CTL, USB2PHY_CTL_APB_RESET_N); + udelay(10); + set32(atcphy->regs.usb2phy + USB2PHY_MISCTUNE, USB2PHY_MISCTUNE_APBCLK_GATE_OFF); + set32(atcphy->regs.usb2phy + USB2PHY_MISCTUNE, USB2PHY_MISCTUNE_REFCLK_GATE_OFF); +} + +static int atcphy_power_off(struct apple_atcphy *atcphy) +{ + u32 reg; + int ret; + + atcphy_disable_dp_aux(atcphy); + + /* Enable all reset lines */ + core_clear32(atcphy, ATCPHY_POWER_CTRL, ATCPHY_POWER_PHY_RESET_N); + core_set32(atcphy, ATCPHY_POWER_CTRL, ATCPHY_POWER_CLAMP_EN); + core_clear32(atcphy, ATCPHY_MISC, ATCPHY_MISC_RESET_N | ATCPHY_MISC_LANE_SWAP); + core_clear32(atcphy, ATCPHY_POWER_CTRL, ATCPHY_POWER_APB_RESET_N); + + core_clear32(atcphy, ATCPHY_POWER_CTRL, ATCPHY_POWER_SLEEP_BIG); + ret = readl_poll_timeout(atcphy->regs.core + ATCPHY_POWER_STAT, reg, + !(reg & ATCPHY_POWER_SLEEP_BIG), 10, 1000); + if (ret) { + dev_err(atcphy->dev, "Failed to sleep atcphy \"big\"\n"); + return ret; + } + + core_clear32(atcphy, ATCPHY_POWER_CTRL, ATCPHY_POWER_SLEEP_SMALL); + ret = readl_poll_timeout(atcphy->regs.core + ATCPHY_POWER_STAT, reg, + !(reg & ATCPHY_POWER_SLEEP_SMALL), 10, 1000); + if (ret) { + dev_err(atcphy->dev, "Failed to sleep atcphy \"small\"\n"); + return ret; + } + + return 0; +} + +static void atcphy_usb2_power_on(struct apple_atcphy *atcphy) +{ + set32(atcphy->regs.usb2phy + USB2PHY_SIG, + USB2PHY_SIG_VBUSDET_FORCE_VAL | USB2PHY_SIG_VBUSDET_FORCE_EN | + USB2PHY_SIG_VBUSVLDEXT_FORCE_VAL | USB2PHY_SIG_VBUSVLDEXT_FORCE_EN); + udelay(10); + + /* Take the PHY out of its low power state */ + clear32(atcphy->regs.usb2phy + USB2PHY_CTL, USB2PHY_CTL_SIDDQ); + udelay(10); + + /* Release reset */ + clear32(atcphy->regs.usb2phy + USB2PHY_CTL, USB2PHY_CTL_RESET); + udelay(10); + clear32(atcphy->regs.usb2phy + USB2PHY_CTL, USB2PHY_CTL_PORT_RESET); + udelay(10); + set32(atcphy->regs.usb2phy + USB2PHY_CTL, USB2PHY_CTL_APB_RESET_N); + udelay(10); + clear32(atcphy->regs.usb2phy + USB2PHY_MISCTUNE, USB2PHY_MISCTUNE_APBCLK_GATE_OFF); + clear32(atcphy->regs.usb2phy + USB2PHY_MISCTUNE, USB2PHY_MISCTUNE_REFCLK_GATE_OFF); + + /* Enable the PHY */ + writel(USB2PHY_USBCTL_RUN, atcphy->regs.usb2phy + USB2PHY_USBCTL); +} + +static int atcphy_power_on(struct apple_atcphy *atcphy) +{ + u32 reg; + int ret; + + atcphy_usb2_power_on(atcphy); + + core_set32(atcphy, ATCPHY_MISC, ATCPHY_MISC_RESET_N); + + core_set32(atcphy, ATCPHY_POWER_CTRL, ATCPHY_POWER_SLEEP_SMALL); + ret = readl_poll_timeout(atcphy->regs.core + ATCPHY_POWER_STAT, reg, + reg & ATCPHY_POWER_SLEEP_SMALL, 100, 100000); + if (ret) { + dev_err(atcphy->dev, "failed to wakeup atcphy \"small\"\n"); + return ret; + } + + core_set32(atcphy, ATCPHY_POWER_CTRL, ATCPHY_POWER_SLEEP_BIG); + ret = readl_poll_timeout(atcphy->regs.core + ATCPHY_POWER_STAT, reg, + reg & ATCPHY_POWER_SLEEP_BIG, 100, 100000); + if (ret) { + dev_err(atcphy->dev, "failed to wakeup atcphy \"big\"\n"); + return ret; + } + + core_clear32(atcphy, ATCPHY_POWER_CTRL, ATCPHY_POWER_CLAMP_EN); + core_set32(atcphy, ATCPHY_POWER_CTRL, ATCPHY_POWER_APB_RESET_N); + + return 0; +} + +static int atcphy_configure(struct apple_atcphy *atcphy, enum atcphy_mode mode) +{ + int ret = 0; + + lockdep_assert_held(&atcphy->lock); + + if (mode == APPLE_ATCPHY_MODE_OFF) { + ret = atcphy_power_off(atcphy); + atcphy->mode = mode; + return ret; + } + + ret = atcphy_power_on(atcphy); + if (ret) + return ret; + + atcphy_apply_tunables(atcphy, mode); + + core_set32(atcphy, AUSPLL_FSM_CTRL, 0x1fe000); + core_set32(atcphy, AUSPLL_APB_CMD_OVERRIDE, AUSPLL_APB_CMD_OVERRIDE_UNK28); + + set32(atcphy->regs.core + ACIOPHY_CFG0, ACIOPHY_CFG0_COMMON_SMALL_OV); + udelay(10); + set32(atcphy->regs.core + ACIOPHY_CFG0, ACIOPHY_CFG0_COMMON_BIG_OV); + udelay(10); + set32(atcphy->regs.core + ACIOPHY_CFG0, ACIOPHY_CFG0_COMMON_CLAMP_OV); + udelay(10); + + mask32(atcphy->regs.core + ACIOPHY_SLEEP_CTRL, ACIOPHY_SLEEP_CTRL_TX_SMALL_OV, + FIELD_PREP(ACIOPHY_SLEEP_CTRL_TX_SMALL_OV, 3)); + udelay(10); + mask32(atcphy->regs.core + ACIOPHY_SLEEP_CTRL, ACIOPHY_SLEEP_CTRL_TX_BIG_OV, + FIELD_PREP(ACIOPHY_SLEEP_CTRL_TX_BIG_OV, 3)); + udelay(10); + mask32(atcphy->regs.core + ACIOPHY_SLEEP_CTRL, ACIOPHY_SLEEP_CTRL_TX_CLAMP_OV, + FIELD_PREP(ACIOPHY_SLEEP_CTRL_TX_CLAMP_OV, 3)); + udelay(10); + + mask32(atcphy->regs.core + ACIOPHY_CFG0, ACIOPHY_CFG0_RX_BIG_OV, + FIELD_PREP(ACIOPHY_CFG0_RX_BIG_OV, 3)); + udelay(10); + mask32(atcphy->regs.core + ACIOPHY_CFG0, ACIOPHY_CFG0_RX_SMALL_OV, + FIELD_PREP(ACIOPHY_CFG0_RX_SMALL_OV, 3)); + udelay(10); + mask32(atcphy->regs.core + ACIOPHY_CFG0, ACIOPHY_CFG0_RX_CLAMP_OV, + FIELD_PREP(ACIOPHY_CFG0_RX_CLAMP_OV, 3)); + udelay(10); + + /* Setup AUX channel if DP altmode is requested */ + if (atcphy_modes[mode].enable_dp_aux) + atcphy_enable_dp_aux(atcphy); + + /* Enable clocks and configure lanes */ + core_set32(atcphy, CIO3PLL_CLK_CTRL, CIO3PLL_CLK_PCLK_EN); + core_set32(atcphy, CIO3PLL_CLK_CTRL, CIO3PLL_CLK_REFCLK_EN); + atcphy_configure_lanes(atcphy, mode); + + /* Take the USB3 PHY out of reset */ + core_set32(atcphy, ATCPHY_POWER_CTRL, ATCPHY_POWER_PHY_RESET_N); + + atcphy->mode = mode; + + return 0; +} + +static int atcphy_usb2_set_mode(struct phy *phy, enum phy_mode mode, int submode) +{ + struct apple_atcphy *atcphy = phy_get_drvdata(phy); + + guard(mutex)(&atcphy->lock); + + switch (mode) { + case PHY_MODE_USB_HOST: + set32(atcphy->regs.usb2phy + USB2PHY_SIG, USB2PHY_SIG_HOST); + break; + case PHY_MODE_USB_DEVICE: + clear32(atcphy->regs.usb2phy + USB2PHY_SIG, USB2PHY_SIG_HOST); + break; + default: + return -EINVAL; + } + + return 0; +} + +static const struct phy_ops apple_atc_usb2_phy_ops = { + .owner = THIS_MODULE, + .set_mode = atcphy_usb2_set_mode, +}; + +static int atcphy_usb3_power_off(struct phy *phy) +{ + struct apple_atcphy *atcphy = phy_get_drvdata(phy); + int ret; + + guard(mutex)(&atcphy->lock); + + ret = atcphy_configure_pipehandler_dummy(atcphy); + if (ret) + dev_warn(atcphy->dev, "Failed to switch pipe to dummy: %d", ret); + + atcphy->pipehandler_up = false; + + if (atcphy->mode != APPLE_ATCPHY_MODE_OFF) + atcphy_configure(atcphy, APPLE_ATCPHY_MODE_OFF); + + return 0; +} + +static int atcphy_usb3_set_mode(struct phy *phy, enum phy_mode mode, int submode) +{ + struct apple_atcphy *atcphy = phy_get_drvdata(phy); + + guard(mutex)(&atcphy->lock); + + /* + * We may get multiple calls to set_mode (for host mode e.g. at least one from the dwc3 glue + * driver and then another one from the generic xhci code) but must only configure the + * PIPE handler once. + */ + if (atcphy->pipehandler_up) + return 0; + + switch (mode) { + case PHY_MODE_USB_HOST: + return atcphy_configure_pipehandler(atcphy, true); + case PHY_MODE_USB_DEVICE: + return atcphy_configure_pipehandler(atcphy, false); + default: + return -EINVAL; + } +} + +static const struct phy_ops apple_atc_usb3_phy_ops = { + .owner = THIS_MODULE, + .power_off = atcphy_usb3_power_off, + .set_mode = atcphy_usb3_set_mode, +}; + +static int atcphy_dpphy_set_mode(struct phy *phy, enum phy_mode mode, int submode) +{ + /* Nothing to do here since the setup already happened in mux_set */ + if (mode == PHY_MODE_DP && submode == 0) + return 0; + return -EINVAL; +} + +static int atcphy_dpphy_validate(struct phy *phy, enum phy_mode mode, int submode, + union phy_configure_opts *opts_) +{ + struct phy_configure_opts_dp *opts = &opts_->dp; + struct apple_atcphy *atcphy = phy_get_drvdata(phy); + + if (mode != PHY_MODE_DP) + return -EINVAL; + if (submode != 0) + return -EINVAL; + + switch (atcphy->mode) { + case APPLE_ATCPHY_MODE_USB3_DP: + opts->lanes = 2; + break; + case APPLE_ATCPHY_MODE_DP: + opts->lanes = 4; + break; + default: + opts->lanes = 0; + } + + return 0; +} + +static int atcphy_dpphy_configure(struct phy *phy, union phy_configure_opts *opts_) +{ + struct phy_configure_opts_dp *opts = &opts_->dp; + struct apple_atcphy *atcphy = phy_get_drvdata(phy); + enum atcphy_dp_link_rate link_rate; + + if (opts->set_voltages) + return -EINVAL; + if (opts->set_lanes) + return -EINVAL; + + if (opts->set_rate) { + switch (opts->link_rate) { + case 1620: + link_rate = ATCPHY_DP_LINK_RATE_RBR; + break; + case 2700: + link_rate = ATCPHY_DP_LINK_RATE_HBR; + break; + case 5400: + link_rate = ATCPHY_DP_LINK_RATE_HBR2; + break; + case 8100: + link_rate = ATCPHY_DP_LINK_RATE_HBR3; + break; + case 0: + return 0; + default: + dev_err(atcphy->dev, "Unsupported link rate: %d\n", opts->link_rate); + return -EINVAL; + } + + return atcphy_dp_configure(atcphy, link_rate); + } + + return 0; +} + +static const struct phy_ops apple_atc_dp_phy_ops = { + .owner = THIS_MODULE, + .configure = atcphy_dpphy_configure, + .validate = atcphy_dpphy_validate, + .set_mode = atcphy_dpphy_set_mode, +}; + +static struct phy *atcphy_xlate(struct device *dev, const struct of_phandle_args *args) +{ + struct apple_atcphy *atcphy = dev_get_drvdata(dev); + + switch (args->args[0]) { + case PHY_TYPE_USB2: + return atcphy->phys.usb2; + case PHY_TYPE_USB3: + return atcphy->phys.usb3; + case PHY_TYPE_DP: + return atcphy->phys.dp; + } + return ERR_PTR(-ENODEV); +} + +static int atcphy_probe_phy(struct apple_atcphy *atcphy) +{ + struct { + struct phy **phy; + const struct phy_ops *ops; + } phys[] = { + { &atcphy->phys.usb2, &apple_atc_usb2_phy_ops }, + { &atcphy->phys.usb3, &apple_atc_usb3_phy_ops }, + { &atcphy->phys.dp, &apple_atc_dp_phy_ops }, + }; + + for (int i = 0; i < ARRAY_SIZE(phys); i++) { + *phys[i].phy = devm_phy_create(atcphy->dev, NULL, phys[i].ops); + if (IS_ERR(*phys[i].phy)) + return PTR_ERR(*phys[i].phy); + phy_set_drvdata(*phys[i].phy, atcphy); + } + + atcphy->phy_provider = devm_of_phy_provider_register(atcphy->dev, atcphy_xlate); + if (IS_ERR(atcphy->phy_provider)) + return PTR_ERR(atcphy->phy_provider); + return 0; +} + +static void _atcphy_dwc3_reset_assert(struct apple_atcphy *atcphy) +{ + lockdep_assert_held(&atcphy->lock); + + clear32(atcphy->regs.pipehandler + PIPEHANDLER_AON_GEN, PIPEHANDLER_AON_GEN_DWC3_RESET_N); + set32(atcphy->regs.pipehandler + PIPEHANDLER_AON_GEN, + PIPEHANDLER_AON_GEN_DWC3_FORCE_CLAMP_EN); +} + +static int atcphy_dwc3_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) +{ + struct apple_atcphy *atcphy = container_of(rcdev, struct apple_atcphy, rcdev); + int ret; + + guard(mutex)(&atcphy->lock); + + _atcphy_dwc3_reset_assert(atcphy); + + if (atcphy->pipehandler_up) { + ret = atcphy_configure_pipehandler_dummy(atcphy); + if (ret) + dev_warn(atcphy->dev, "Failed to switch PIPE to dummy: %d\n", ret); + else + atcphy->pipehandler_up = false; + } + + atcphy_usb2_power_off(atcphy); + + return 0; +} + +static int atcphy_dwc3_reset_deassert(struct reset_controller_dev *rcdev, unsigned long id) +{ + struct apple_atcphy *atcphy = container_of(rcdev, struct apple_atcphy, rcdev); + + guard(mutex)(&atcphy->lock); + + clear32(atcphy->regs.pipehandler + PIPEHANDLER_AON_GEN, + PIPEHANDLER_AON_GEN_DWC3_FORCE_CLAMP_EN); + set32(atcphy->regs.pipehandler + PIPEHANDLER_AON_GEN, PIPEHANDLER_AON_GEN_DWC3_RESET_N); + + return 0; +} + +const struct reset_control_ops atcphy_dwc3_reset_ops = { + .assert = atcphy_dwc3_reset_assert, + .deassert = atcphy_dwc3_reset_deassert, +}; + +static int atcphy_reset_xlate(struct reset_controller_dev *rcdev, + const struct of_phandle_args *reset_spec) +{ + return 0; +} + +static int atcphy_probe_rcdev(struct apple_atcphy *atcphy) +{ + atcphy->rcdev.owner = THIS_MODULE; + atcphy->rcdev.nr_resets = 1; + atcphy->rcdev.ops = &atcphy_dwc3_reset_ops; + atcphy->rcdev.of_node = atcphy->dev->of_node; + atcphy->rcdev.of_reset_n_cells = 0; + atcphy->rcdev.of_xlate = atcphy_reset_xlate; + + return devm_reset_controller_register(atcphy->dev, &atcphy->rcdev); +} + +static int atcphy_sw_set(struct typec_switch_dev *sw, enum typec_orientation orientation) +{ + struct apple_atcphy *atcphy = typec_switch_get_drvdata(sw); + + guard(mutex)(&atcphy->lock); + + switch (orientation) { + case TYPEC_ORIENTATION_NONE: + break; + case TYPEC_ORIENTATION_NORMAL: + atcphy->swap_lanes = false; + break; + case TYPEC_ORIENTATION_REVERSE: + atcphy->swap_lanes = true; + break; + } + + return 0; +} + +static int atcphy_probe_switch(struct apple_atcphy *atcphy) +{ + struct typec_switch_desc sw_desc = { + .drvdata = atcphy, + .fwnode = atcphy->dev->fwnode, + .set = atcphy_sw_set, + }; + + return PTR_ERR_OR_ZERO(typec_switch_register(atcphy->dev, &sw_desc)); +} + +static int atcphy_mux_set(struct typec_mux_dev *mux, struct typec_mux_state *state) +{ + struct apple_atcphy *atcphy = typec_mux_get_drvdata(mux); + enum atcphy_mode target_mode; + + guard(mutex)(&atcphy->lock); + + if (state->mode == TYPEC_STATE_SAFE) { + target_mode = APPLE_ATCPHY_MODE_OFF; + } else if (state->mode == TYPEC_STATE_USB) { + target_mode = APPLE_ATCPHY_MODE_USB3; + } else if (!state->alt && state->mode == TYPEC_MODE_USB4) { + struct enter_usb_data *data = state->data; + u32 eudo_usb_mode = FIELD_GET(EUDO_USB_MODE_MASK, data->eudo); + + switch (eudo_usb_mode) { + case EUDO_USB_MODE_USB2: + target_mode = APPLE_ATCPHY_MODE_USB2; + break; + case EUDO_USB_MODE_USB3: + target_mode = APPLE_ATCPHY_MODE_USB3; + break; + case EUDO_USB_MODE_USB4: + target_mode = APPLE_ATCPHY_MODE_USB4; + break; + default: + dev_warn(atcphy->dev, "Unsupported EUDO USB mode: 0x%x.\n", eudo_usb_mode); + target_mode = APPLE_ATCPHY_MODE_OFF; + } + } else if (state->alt && state->alt->svid == USB_TYPEC_TBT_SID) { + target_mode = APPLE_ATCPHY_MODE_TBT; + } else if (state->alt && state->alt->svid == USB_TYPEC_DP_SID) { + switch (state->mode) { + case TYPEC_DP_STATE_C: + case TYPEC_DP_STATE_E: + target_mode = APPLE_ATCPHY_MODE_DP; + break; + case TYPEC_DP_STATE_D: + target_mode = APPLE_ATCPHY_MODE_USB3_DP; + break; + default: + dev_err(atcphy->dev, + "Unsupported DP pin assignment: 0x%lx, your connected device will not work.\n", + state->mode); + target_mode = APPLE_ATCPHY_MODE_OFF; + } + } else if (state->alt) { + dev_err(atcphy->dev, + "Unknown alternate mode SVID: 0x%x, your connected device will not work.\n", + state->alt->svid); + target_mode = APPLE_ATCPHY_MODE_OFF; + } else { + dev_err(atcphy->dev, "Unknown mode: 0x%lx, your connected device will not work.\n", + state->mode); + target_mode = APPLE_ATCPHY_MODE_OFF; + } + + if (atcphy->mode == target_mode) + return 0; + + /* + * If the pipehandler is still/already up here there's a bug somewhere so make sure to + * complain loudly. We can still try to switch modes and hope for the best though, + * in the worst case the hardware will fall back to USB2-only. + */ + WARN_ON_ONCE(atcphy->pipehandler_up); + return atcphy_configure(atcphy, target_mode); +} + +static int atcphy_probe_mux(struct apple_atcphy *atcphy) +{ + struct typec_mux_desc mux_desc = { + .drvdata = atcphy, + .fwnode = atcphy->dev->fwnode, + .set = atcphy_mux_set, + }; + + return PTR_ERR_OR_ZERO(typec_mux_register(atcphy->dev, &mux_desc)); +} + +static int atcphy_load_tunables(struct apple_atcphy *atcphy) +{ + struct { + const char *dt_name; + struct apple_tunable **tunable; + struct resource *res; + } tunables[] = { + { "apple,tunable-axi2af", &atcphy->tunables.axi2af, atcphy->res.axi2af }, + { "apple,tunable-common-a", &atcphy->tunables.common[0], atcphy->res.core }, + { "apple,tunable-common-b", &atcphy->tunables.common[1], atcphy->res.core }, + { "apple,tunable-lane0-usb", &atcphy->tunables.lane_usb3[0], atcphy->res.core }, + { "apple,tunable-lane1-usb", &atcphy->tunables.lane_usb3[1], atcphy->res.core }, + { "apple,tunable-lane0-cio", &atcphy->tunables.lane_usb4[0], atcphy->res.core }, + { "apple,tunable-lane1-cio", &atcphy->tunables.lane_usb4[1], atcphy->res.core }, + { "apple,tunable-lane0-dp", &atcphy->tunables.lane_dp[0], atcphy->res.core }, + { "apple,tunable-lane1-dp", &atcphy->tunables.lane_dp[1], atcphy->res.core }, + }; + + for (int i = 0; i < ARRAY_SIZE(tunables); i++) { + *tunables[i].tunable = devm_apple_tunable_parse( + atcphy->dev, atcphy->np, tunables[i].dt_name, tunables[i].res); + if (IS_ERR(*tunables[i].tunable)) { + dev_err(atcphy->dev, "Failed to read tunable %s: %ld\n", + tunables[i].dt_name, PTR_ERR(*tunables[i].tunable)); + return PTR_ERR(*tunables[i].tunable); + } + } + + return 0; +} + +static int atcphy_map_resources(struct platform_device *pdev, struct apple_atcphy *atcphy) +{ + struct { + const char *name; + void __iomem **addr; + struct resource **res; + } resources[] = { + { "core", &atcphy->regs.core, &atcphy->res.core }, + { "lpdptx", &atcphy->regs.lpdptx, NULL }, + { "axi2af", &atcphy->regs.axi2af, &atcphy->res.axi2af }, + { "usb2phy", &atcphy->regs.usb2phy, NULL }, + { "pipehandler", &atcphy->regs.pipehandler, NULL }, + }; + struct resource *res; + + for (int i = 0; i < ARRAY_SIZE(resources); i++) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, resources[i].name); + *resources[i].addr = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(resources[i].addr)) + return dev_err_probe(atcphy->dev, PTR_ERR(resources[i].addr), + "Unable to map %s regs", resources[i].name); + + if (resources[i].res) + *resources[i].res = res; + } + + return 0; +} + +static int atcphy_probe_finalize(struct apple_atcphy *atcphy) +{ + int ret; + + guard(mutex)(&atcphy->lock); + + /* Reset dwc3 on probe, let dwc3 (consumer) deassert it */ + _atcphy_dwc3_reset_assert(atcphy); + + /* Reset atcphy to clear any state potentially left by the bootloader */ + atcphy_usb2_power_off(atcphy); + atcphy_power_off(atcphy); + atcphy_setup_pipehandler(atcphy); + + ret = atcphy_probe_rcdev(atcphy); + if (ret) + return dev_err_probe(atcphy->dev, ret, "Probing rcdev failed"); + ret = atcphy_probe_mux(atcphy); + if (ret) + return dev_err_probe(atcphy->dev, ret, "Probing mux failed"); + ret = atcphy_probe_switch(atcphy); + if (ret) + return dev_err_probe(atcphy->dev, ret, "Probing switch failed"); + ret = atcphy_probe_phy(atcphy); + if (ret) + return dev_err_probe(atcphy->dev, ret, "Probing phy failed"); + + return 0; +} + +static int atcphy_probe(struct platform_device *pdev) +{ + struct apple_atcphy *atcphy; + struct device *dev = &pdev->dev; + int ret; + + atcphy = devm_kzalloc(&pdev->dev, sizeof(*atcphy), GFP_KERNEL); + if (!atcphy) + return -ENOMEM; + + atcphy->dev = dev; + atcphy->np = dev->of_node; + mutex_init(&atcphy->lock); + platform_set_drvdata(pdev, atcphy); + + ret = atcphy_map_resources(pdev, atcphy); + if (ret) + return ret; + ret = atcphy_load_tunables(atcphy); + if (ret) + return ret; + + atcphy->mode = APPLE_ATCPHY_MODE_OFF; + atcphy->pipehandler_up = false; + + return atcphy_probe_finalize(atcphy); +} + +static const struct of_device_id atcphy_match[] = { + { .compatible = "apple,t8103-atcphy" }, + {}, +}; +MODULE_DEVICE_TABLE(of, atcphy_match); + +static struct platform_driver atcphy_driver = { + .driver = { + .name = "phy-apple-atc", + .of_match_table = atcphy_match, + }, + .probe = atcphy_probe, +}; +module_platform_driver(atcphy_driver); + +MODULE_AUTHOR("Sven Peter "); +MODULE_DESCRIPTION("Apple Type-C PHY driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/phy/apple/dptx.c b/drivers/phy/apple/dptx.c new file mode 100644 index 00000000000000..f0df2d40a18023 --- /dev/null +++ b/drivers/phy/apple/dptx.c @@ -0,0 +1,690 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause +/* + * Apple dptx PHY driver + * + * Copyright (C) The Asahi Linux Contributors + * Author: Janne Grunau + * + * based on drivers/phy/apple/atc.c + * + * Copyright (C) The Asahi Linux Contributors + * Author: Sven Peter + */ + +#include "dptx.h" + +#include +#include "linux/of.h" +#include +#include +#include +#include +#include +#include +#include + +#define DPTX_MAX_LANES 4 +#define DPTX_LANE0_OFFSET 0x5000 +#define DPTX_LANE_STRIDE 0x1000 +#define DPTX_LANE_END (DPTX_LANE0_OFFSET + DPTX_MAX_LANES * DPTX_LANE_STRIDE) + +enum apple_dptx_type { + DPTX_PHY_T8112, + DPTX_PHY_T6020, +}; + +struct apple_dptx_phy_hw { + enum apple_dptx_type type; +}; + +struct apple_dptx_phy { + struct device *dev; + + struct apple_dptx_phy_hw hw; + + int dp_link_rate; + + struct { + void __iomem *core; + void __iomem *dptx; + } regs; + + struct phy *phy_dp; + struct phy_provider *phy_provider; + + struct mutex lock; + + // TODO: m1n1 port things to clean up + u32 active_lanes; +}; + + +static inline void mask32(void __iomem *reg, u32 mask, u32 set) +{ + u32 value = readl(reg); + value &= ~mask; + value |= set; + writel(value, reg); +} + +static inline void set32(void __iomem *reg, u32 set) +{ + mask32(reg, 0, set); +} + +static inline void clear32(void __iomem *reg, u32 clear) +{ + mask32(reg, clear, 0); +} + + +static int dptx_phy_set_active_lane_count(struct apple_dptx_phy *phy, u32 num_lanes) +{ + u32 l, ctrl; + + dev_dbg(phy->dev, "set_active_lane_count(%u)\n", num_lanes); + + if (num_lanes == 3 || num_lanes > DPTX_MAX_LANES) + return -1; + + ctrl = readl(phy->regs.dptx + 0x4000); + writel(ctrl, phy->regs.dptx + 0x4000); + + for (l = 0; l < num_lanes; l++) { + u64 offset = 0x5000 + 0x1000 * l; + readl(phy->regs.dptx + offset); + writel(0x100, phy->regs.dptx + offset); + } + for (; l < DPTX_MAX_LANES; l++) { + u64 offset = 0x5000 + 0x1000 * l; + readl(phy->regs.dptx + offset); + writel(0x300, phy->regs.dptx + offset); + } + for (l = 0; l < num_lanes; l++) { + u64 offset = 0x5000 + 0x1000 * l; + readl(phy->regs.dptx + offset); + writel(0x0, phy->regs.dptx + offset); + } + for (; l < DPTX_MAX_LANES; l++) { + u64 offset = 0x5000 + 0x1000 * l; + readl(phy->regs.dptx + offset); + writel(0x300, phy->regs.dptx + offset); + } + + if (num_lanes > 0) { + // clear32(phy->regs.dptx + 0x4000, 0x4000000); + ctrl = readl(phy->regs.dptx + 0x4000); + ctrl &= ~0x4000000; + writel(ctrl, phy->regs.dptx + 0x4000); + } + phy->active_lanes = num_lanes; + + return 0; +} + +static int dptx_phy_activate(struct apple_dptx_phy *phy, u32 dcp_index) +{ + u32 val_2014; + u32 val_4008; + u32 val_4408; + + dev_dbg(phy->dev, "activate(dcp:%u)\n", dcp_index); + + // MMIO: R.4 0x23c500010 (dptx-phy[1], offset 0x10) = 0x0 + // MMIO: W.4 0x23c500010 (dptx-phy[1], offset 0x10) = 0x0 + readl(phy->regs.core + 0x10); + writel(dcp_index, phy->regs.core + 0x10); + + // MMIO: R.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x444 + // MMIO: W.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x454 + set32(phy->regs.core + 0x48, 0x010); + // MMIO: R.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x454 + // MMIO: W.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x474 + set32(phy->regs.core + 0x48, 0x020); + // MMIO: R.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x474 + // MMIO: W.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x434 + clear32(phy->regs.core + 0x48, 0x040); + // MMIO: R.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x434 + // MMIO: W.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x534 + set32(phy->regs.core + 0x48, 0x100); + // MMIO: R.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x534 + // MMIO: W.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x734 + set32(phy->regs.core + 0x48, 0x200); + // MMIO: R.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x734 + // MMIO: W.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x334 + clear32(phy->regs.core + 0x48, 0x400); + // MMIO: R.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x334 + // MMIO: W.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x335 + set32(phy->regs.core + 0x48, 0x001); + // MMIO: R.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x335 + // MMIO: W.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x337 + set32(phy->regs.core + 0x48, 0x002); + // MMIO: R.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x337 + // MMIO: W.4 0x23c500048 (dptx-phy[1], offset 0x48) = 0x333 + clear32(phy->regs.core + 0x48, 0x004); + + // MMIO: R.4 0x23c542014 (dptx-phy[0], offset 0x2014) = 0x80a0c + val_2014 = readl(phy->regs.dptx + 0x2014); + // MMIO: W.4 0x23c542014 (dptx-phy[0], offset 0x2014) = 0x300a0c + writel((0x30 << 16) | (val_2014 & 0xffff), phy->regs.dptx + 0x2014); + + // MMIO: R.4 0x23c5420b8 (dptx-phy[0], offset 0x20b8) = 0x644800 + // MMIO: W.4 0x23c5420b8 (dptx-phy[0], offset 0x20b8) = 0x654800 + set32(phy->regs.dptx + 0x20b8, 0x010000); + + // MMIO: R.4 0x23c542220 (dptx-phy[0], offset 0x2220) = 0x11090a2 + // MMIO: W.4 0x23c542220 (dptx-phy[0], offset 0x2220) = 0x11090a0 + clear32(phy->regs.dptx + 0x2220, 0x0000002); + + // MMIO: R.4 0x23c54222c (dptx-phy[0], offset 0x222c) = 0x103003 + // MMIO: W.4 0x23c54222c (dptx-phy[0], offset 0x222c) = 0x103803 + set32(phy->regs.dptx + 0x222c, 0x000800); + // MMIO: R.4 0x23c54222c (dptx-phy[0], offset 0x222c) = 0x103803 + // MMIO: W.4 0x23c54222c (dptx-phy[0], offset 0x222c) = 0x103903 + set32(phy->regs.dptx + 0x222c, 0x000100); + + // MMIO: R.4 0x23c542230 (dptx-phy[0], offset 0x2230) = 0x2308804 + // MMIO: W.4 0x23c542230 (dptx-phy[0], offset 0x2230) = 0x2208804 + clear32(phy->regs.dptx + 0x2230, 0x0100000); + + // MMIO: R.4 0x23c542278 (dptx-phy[0], offset 0x2278) = 0x18300811 + // MMIO: W.4 0x23c542278 (dptx-phy[0], offset 0x2278) = 0x10300811 + clear32(phy->regs.dptx + 0x2278, 0x08000000); + + // MMIO: R.4 0x23c5422a4 (dptx-phy[0], offset 0x22a4) = 0x1044200 + // MMIO: W.4 0x23c5422a4 (dptx-phy[0], offset 0x22a4) = 0x1044201 + set32(phy->regs.dptx + 0x22a4, 0x0000001); + + // MMIO: R.4 0x23c544008 (dptx-phy[0], offset 0x4008) = 0x18030 + val_4008 = readl(phy->regs.dptx + 0x4008); + // MMIO: W.4 0x23c544008 (dptx-phy[0], offset 0x4008) = 0x30030 + writel((0x6 << 15) | (val_4008 & 0x7fff), phy->regs.dptx + 0x4008); + // MMIO: R.4 0x23c544008 (dptx-phy[0], offset 0x4008) = 0x30030 + // MMIO: W.4 0x23c544008 (dptx-phy[0], offset 0x4008) = 0x30010 + clear32(phy->regs.dptx + 0x4008, 0x00020); + + // MMIO: R.4 0x23c54420c (dptx-phy[0], offset 0x420c) = 0x88e3 + // MMIO: W.4 0x23c54420c (dptx-phy[0], offset 0x420c) = 0x88c3 + clear32(phy->regs.dptx + 0x420c, 0x0020); + + // MMIO: R.4 0x23c544600 (dptx-phy[0], offset 0x4600) = 0x0 + // MMIO: W.4 0x23c544600 (dptx-phy[0], offset 0x4600) = 0x8000000 + set32(phy->regs.dptx + 0x4600, 0x8000000); + + // MMIO: R.4 0x23c545040 (dptx-phy[0], offset 0x5040) = 0x21780 + // MMIO: W.4 0x23c545040 (dptx-phy[0], offset 0x5040) = 0x221780 + // MMIO: R.4 0x23c546040 (dptx-phy[0], offset 0x6040) = 0x21780 + // MMIO: W.4 0x23c546040 (dptx-phy[0], offset 0x6040) = 0x221780 + // MMIO: R.4 0x23c547040 (dptx-phy[0], offset 0x7040) = 0x21780 + // MMIO: W.4 0x23c547040 (dptx-phy[0], offset 0x7040) = 0x221780 + // MMIO: R.4 0x23c548040 (dptx-phy[0], offset 0x8040) = 0x21780 + // MMIO: W.4 0x23c548040 (dptx-phy[0], offset 0x8040) = 0x221780 + for (u32 loff = DPTX_LANE0_OFFSET; loff < DPTX_LANE_END; + loff += DPTX_LANE_STRIDE) + set32(phy->regs.dptx + loff + 0x40, 0x200000); + + // MMIO: R.4 0x23c545040 (dptx-phy[0], offset 0x5040) = 0x221780 + // MMIO: W.4 0x23c545040 (dptx-phy[0], offset 0x5040) = 0x2a1780 + // MMIO: R.4 0x23c546040 (dptx-phy[0], offset 0x6040) = 0x221780 + // MMIO: W.4 0x23c546040 (dptx-phy[0], offset 0x6040) = 0x2a1780 + // MMIO: R.4 0x23c547040 (dptx-phy[0], offset 0x7040) = 0x221780 + // MMIO: W.4 0x23c547040 (dptx-phy[0], offset 0x7040) = 0x2a1780 + // MMIO: R.4 0x23c548040 (dptx-phy[0], offset 0x8040) = 0x221780 + // MMIO: W.4 0x23c548040 (dptx-phy[0], offset 0x8040) = 0x2a1780 + for (u32 loff = DPTX_LANE0_OFFSET; loff < DPTX_LANE_END; + loff += DPTX_LANE_STRIDE) + set32(phy->regs.dptx + loff + 0x40, 0x080000); + + // MMIO: R.4 0x23c545244 (dptx-phy[0], offset 0x5244) = 0x18 + // MMIO: W.4 0x23c545244 (dptx-phy[0], offset 0x5244) = 0x8 + // MMIO: R.4 0x23c546244 (dptx-phy[0], offset 0x6244) = 0x18 + // MMIO: W.4 0x23c546244 (dptx-phy[0], offset 0x6244) = 0x8 + // MMIO: R.4 0x23c547244 (dptx-phy[0], offset 0x7244) = 0x18 + // MMIO: W.4 0x23c547244 (dptx-phy[0], offset 0x7244) = 0x8 + // MMIO: R.4 0x23c548244 (dptx-phy[0], offset 0x8244) = 0x18 + // MMIO: W.4 0x23c548244 (dptx-phy[0], offset 0x8244) = 0x8 + for (u32 loff = DPTX_LANE0_OFFSET; loff < DPTX_LANE_END; + loff += DPTX_LANE_STRIDE) + clear32(phy->regs.dptx + loff + 0x244, 0x10); + + // MMIO: R.4 0x23c542214 (dptx-phy[0], offset 0x2214) = 0x1e0 + // MMIO: W.4 0x23c542214 (dptx-phy[0], offset 0x2214) = 0x1e1 + set32(phy->regs.dptx + 0x2214, 0x001); + + // MMIO: R.4 0x23c542224 (dptx-phy[0], offset 0x2224) = 0x20086001 + // MMIO: W.4 0x23c542224 (dptx-phy[0], offset 0x2224) = 0x20086000 + clear32(phy->regs.dptx + 0x2224, 0x00000001); + + // MMIO: R.4 0x23c542200 (dptx-phy[0], offset 0x2200) = 0x2000 + // MMIO: W.4 0x23c542200 (dptx-phy[0], offset 0x2200) = 0x2002 + set32(phy->regs.dptx + 0x2200, 0x0002); + + // MMIO: R.4 0x23c541000 (dptx-phy[0], offset 0x1000) = 0xe0000003 + // MMIO: W.4 0x23c541000 (dptx-phy[0], offset 0x1000) = 0xe0000001 + clear32(phy->regs.dptx + 0x1000, 0x00000002); + + // MMIO: R.4 0x23c544004 (dptx-phy[0], offset 0x4004) = 0x41 + // MMIO: W.4 0x23c544004 (dptx-phy[0], offset 0x4004) = 0x49 + set32(phy->regs.dptx + 0x4004, 0x08); + + /* TODO: no idea what happens here, supposedly setting/clearing some bits */ + // MMIO: R.4 0x23c544404 (dptx-phy[0], offset 0x4404) = 0x555d444 + readl(phy->regs.dptx + 0x4404); + // MMIO: W.4 0x23c544404 (dptx-phy[0], offset 0x4404) = 0x555d444 + writel(0x555d444, phy->regs.dptx + 0x4404); + // MMIO: R.4 0x23c544404 (dptx-phy[0], offset 0x4404) = 0x555d444 + readl(phy->regs.dptx + 0x4404); + // MMIO: W.4 0x23c544404 (dptx-phy[0], offset 0x4404) = 0x555d444 + writel(0x555d444, phy->regs.dptx + 0x4404); + + dptx_phy_set_active_lane_count(phy, 0); + + // MMIO: R.4 0x23c544200 (dptx-phy[0], offset 0x4200) = 0x4002430 + // MMIO: W.4 0x23c544200 (dptx-phy[0], offset 0x4200) = 0x4002420 + clear32(phy->regs.dptx + 0x4200, 0x0000010); + + // MMIO: R.4 0x23c544600 (dptx-phy[0], offset 0x4600) = 0x8000000 + // MMIO: W.4 0x23c544600 (dptx-phy[0], offset 0x4600) = 0x8000000 + clear32(phy->regs.dptx + 0x4600, 0x0000001); + // MMIO: R.4 0x23c544600 (dptx-phy[0], offset 0x4600) = 0x8000000 + // MMIO: W.4 0x23c544600 (dptx-phy[0], offset 0x4600) = 0x8000001 + set32(phy->regs.dptx + 0x4600, 0x0000001); + // MMIO: R.4 0x23c544600 (dptx-phy[0], offset 0x4600) = 0x8000001 + // MMIO: W.4 0x23c544600 (dptx-phy[0], offset 0x4600) = 0x8000003 + set32(phy->regs.dptx + 0x4600, 0x0000002); + // MMIO: R.4 0x23c544600 (dptx-phy[0], offset 0x4600) = 0x8000043 + // MMIO: R.4 0x23c544600 (dptx-phy[0], offset 0x4600) = 0x8000043 + // MMIO: W.4 0x23c544600 (dptx-phy[0], offset 0x4600) = 0x8000041 + /* TODO: read first to check if the previous set(...,0x2) sticked? */ + readl(phy->regs.dptx + 0x4600); + clear32(phy->regs.dptx + 0x4600, 0x0000001); + + // MMIO: R.4 0x23c544408 (dptx-phy[0], offset 0x4408) = 0x482 + // MMIO: W.4 0x23c544408 (dptx-phy[0], offset 0x4408) = 0x482 + /* TODO: probably a set32 of an already set bit */ + val_4408 = readl(phy->regs.dptx + 0x4408); + if (val_4408 != 0x482 && val_4408 != 0x483) + dev_warn( + phy->dev, + "unexpected initial value at regs.dptx offset 0x4408: 0x%03x\n", + val_4408); + writel(val_4408, phy->regs.dptx + 0x4408); + // MMIO: R.4 0x23c544408 (dptx-phy[0], offset 0x4408) = 0x482 + // MMIO: W.4 0x23c544408 (dptx-phy[0], offset 0x4408) = 0x483 + set32(phy->regs.dptx + 0x4408, 0x001); + + return 0; +} + +static int dptx_phy_deactivate(struct apple_dptx_phy *phy) +{ + return 0; +} + +static int dptx_phy_set_link_rate(struct apple_dptx_phy *phy, u32 link_rate) +{ + u32 sts_1008, sts_1014, val_100c, val_20b0, val_20b4; + + dev_dbg(phy->dev, "set_link_rate(%u)\n", link_rate); + + // MMIO: R.4 0x23c544004 (dptx-phy[0], offset 0x4004) = 0x49 + // MMIO: W.4 0x23c544004 (dptx-phy[0], offset 0x4004) = 0x49 + set32(phy->regs.dptx + 0x4004, 0x08); + + // MMIO: R.4 0x23c544000 (dptx-phy[0], offset 0x4000) = 0x41021ac + // MMIO: W.4 0x23c544000 (dptx-phy[0], offset 0x4000) = 0x41021ac + clear32(phy->regs.dptx + 0x4000, 0x0000040); + + // MMIO: R.4 0x23c544004 (dptx-phy[0], offset 0x4004) = 0x49 + // MMIO: W.4 0x23c544004 (dptx-phy[0], offset 0x4004) = 0x41 + clear32(phy->regs.dptx + 0x4004, 0x08); + + // MMIO: R.4 0x23c544000 (dptx-phy[0], offset 0x4000) = 0x41021ac + // MMIO: W.4 0x23c544000 (dptx-phy[0], offset 0x4000) = 0x41021ac + clear32(phy->regs.dptx + 0x4000, 0x2000000); + // MMIO: R.4 0x23c544000 (dptx-phy[0], offset 0x4000) = 0x41021ac + // MMIO: W.4 0x23c544000 (dptx-phy[0], offset 0x4000) = 0x41021ac + set32(phy->regs.dptx + 0x4000, 0x1000000); + + // MMIO: R.4 0x23c542200 (dptx-phy[0], offset 0x2200) = 0x2002 + // MMIO: R.4 0x23c542200 (dptx-phy[0], offset 0x2200) = 0x2002 + // MMIO: W.4 0x23c542200 (dptx-phy[0], offset 0x2200) = 0x2000 + /* TODO: what is this read checking for? */ + readl(phy->regs.dptx + 0x2200); + clear32(phy->regs.dptx + 0x2200, 0x0002); + + // MMIO: R.4 0x23c54100c (dptx-phy[0], offset 0x100c) = 0xf000 + // MMIO: W.4 0x23c54100c (dptx-phy[0], offset 0x100c) = 0xf000 + // MMIO: R.4 0x23c54100c (dptx-phy[0], offset 0x100c) = 0xf000 + // MMIO: W.4 0x23c54100c (dptx-phy[0], offset 0x100c) = 0xf008 + /* TODO: what is the setting/clearing? */ + val_100c = readl(phy->regs.dptx + 0x100c); + writel(val_100c, phy->regs.dptx + 0x100c); + set32(phy->regs.dptx + 0x100c, 0x0008); + + // MMIO: R.4 0x23c541014 (dptx-phy[0], offset 0x1014) = 0x1 + sts_1014 = readl(phy->regs.dptx + 0x1014); + if (sts_1014 != 0x1) + dev_dbg(phy->dev, "unexpected?: dptx[0x1014]: %02x\n", sts_1014); + + // MMIO: R.4 0x23c54100c (dptx-phy[0], offset 0x100c) = 0xf008 + // MMIO: W.4 0x23c54100c (dptx-phy[0], offset 0x100c) = 0xf000 + clear32(phy->regs.dptx + 0x100c, 0x0008); + + // MMIO: R.4 0x23c541008 (dptx-phy[0], offset 0x1008) = 0x1 + sts_1008 = readl(phy->regs.dptx + 0x1008); + if (sts_1008 != 0x1) + dev_dbg(phy->dev, "unexpected?: dptx[0x1008]: %02x\n", sts_1008); + + // MMIO: R.4 0x23c542220 (dptx-phy[0], offset 0x2220) = 0x11090a0 + // MMIO: W.4 0x23c542220 (dptx-phy[0], offset 0x2220) = 0x1109020 + clear32(phy->regs.dptx + 0x2220, 0x0000080); + + // MMIO: R.4 0x23c5420b0 (dptx-phy[0], offset 0x20b0) = 0x1e0e01c2 + // MMIO: W.4 0x23c5420b0 (dptx-phy[0], offset 0x20b0) = 0x1e0e01c2 + val_20b0 = readl(phy->regs.dptx + 0x20b0); + /* TODO: what happens on dptx-phy */ + if (phy->hw.type == DPTX_PHY_T6020) + val_20b0 = (val_20b0 & ~0x3ff) | 0x2a3; + writel(val_20b0, phy->regs.dptx + 0x20b0); + + // MMIO: R.4 0x23c5420b4 (dptx-phy[0], offset 0x20b4) = 0x7fffffe + // MMIO: W.4 0x23c5420b4 (dptx-phy[0], offset 0x20b4) = 0x7fffffe + val_20b4 = readl(phy->regs.dptx + 0x20b4); + /* TODO: what happens on dptx-phy */ + if (phy->hw.type == DPTX_PHY_T6020) + val_20b4 = (val_20b4 | 0x4000000) & ~0x0008000; + writel(val_20b4, phy->regs.dptx + 0x20b4); + + // MMIO: R.4 0x23c5420b4 (dptx-phy[0], offset 0x20b4) = 0x7fffffe + // MMIO: W.4 0x23c5420b4 (dptx-phy[0], offset 0x20b4) = 0x7fffffe + val_20b4 = readl(phy->regs.dptx + 0x20b4); + /* TODO: what happens on dptx-phy */ + if (phy->hw.type == DPTX_PHY_T6020) + val_20b4 = (val_20b4 | 0x0000001) & ~0x0000004; + writel(val_20b4, phy->regs.dptx + 0x20b4); + + // MMIO: R.4 0x23c5420b8 (dptx-phy[0], offset 0x20b8) = 0x654800 + // MMIO: W.4 0x23c5420b8 (dptx-phy[0], offset 0x20b8) = 0x654800 + /* TODO: unclear */ + set32(phy->regs.dptx + 0x20b8, 0); + // MMIO: R.4 0x23c5420b8 (dptx-phy[0], offset 0x20b8) = 0x654800 + // MMIO: W.4 0x23c5420b8 (dptx-phy[0], offset 0x20b8) = 0x654800 + /* TODO: unclear */ + set32(phy->regs.dptx + 0x20b8, 0); + // MMIO: R.4 0x23c5420b8 (dptx-phy[0], offset 0x20b8) = 0x654800 + // MMIO: W.4 0x23c5420b8 (dptx-phy[0], offset 0x20b8) = 0x654800 + /* TODO: unclear */ + if (phy->hw.type == DPTX_PHY_T6020) + set32(phy->regs.dptx + 0x20b8, 0x010000); + else + set32(phy->regs.dptx + 0x20b8, 0); + // MMIO: R.4 0x23c5420b8 (dptx-phy[0], offset 0x20b8) = 0x654800 + // MMIO: W.4 0x23c5420b8 (dptx-phy[0], offset 0x20b8) = 0x454800 + clear32(phy->regs.dptx + 0x20b8, 0x200000); + + // MMIO: R.4 0x23c5420b8 (dptx-phy[0], offset 0x20b8) = 0x454800 + // MMIO: W.4 0x23c5420b8 (dptx-phy[0], offset 0x20b8) = 0x454800 + /* TODO: unclear */ + set32(phy->regs.dptx + 0x20b8, 0); + + // MMIO: R.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0x0 + // MMIO: W.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0x8 + // MMIO: R.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0x8 + // MMIO: W.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0xc + // MMIO: R.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0xc + // MMIO: W.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0x4000c + // MMIO: R.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0x4000c + // MMIO: W.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0xc + // MMIO: R.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0xc + // MMIO: W.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0x8000c + // MMIO: R.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0x8000c + // MMIO: W.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0xc + // MMIO: R.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0xc + // MMIO: W.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0x8 + // MMIO: R.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0x8 + // MMIO: W.4 0x23c5000a0 (dptx-phy[1], offset 0xa0) = 0x0 + set32(phy->regs.core + 0xa0, 0x8); + set32(phy->regs.core + 0xa0, 0x4); + set32(phy->regs.core + 0xa0, 0x40000); + clear32(phy->regs.core + 0xa0, 0x40000); + set32(phy->regs.core + 0xa0, 0x80000); + clear32(phy->regs.core + 0xa0, 0x80000); + clear32(phy->regs.core + 0xa0, 0x4); + clear32(phy->regs.core + 0xa0, 0x8); + + // MMIO: R.4 0x23c542000 (dptx-phy[0], offset 0x2000) = 0x2 + // MMIO: W.4 0x23c542000 (dptx-phy[0], offset 0x2000) = 0x2 + /* TODO: unclear */ + set32(phy->regs.dptx + 0x2000, 0x0); + + // MMIO: R.4 0x23c542018 (dptx-phy[0], offset 0x2018) = 0x0 + // MMIO: W.4 0x23c542018 (dptx-phy[0], offset 0x2018) = 0x0 + clear32(phy->regs.dptx + 0x2018, 0x0); + + // MMIO: R.4 0x23c54100c (dptx-phy[0], offset 0x100c) = 0xf000 + // MMIO: W.4 0x23c54100c (dptx-phy[0], offset 0x100c) = 0xf007 + set32(phy->regs.dptx + 0x100c, 0x0007); + // MMIO: R.4 0x23c54100c (dptx-phy[0], offset 0x100c) = 0xf007 + // MMIO: W.4 0x23c54100c (dptx-phy[0], offset 0x100c) = 0xf00f + set32(phy->regs.dptx + 0x100c, 0x0008); + + // MMIO: R.4 0x23c541014 (dptx-phy[0], offset 0x1014) = 0x38f + sts_1014 = readl(phy->regs.dptx + 0x1014); + if (sts_1014 != 0x38f) + dev_dbg(phy->dev, "unexpected?: dptx[0x1014]: %02x\n", sts_1014); + + // MMIO: R.4 0x23c54100c (dptx-phy[0], offset 0x100c) = 0xf00f + // MMIO: W.4 0x23c54100c (dptx-phy[0], offset 0x100c) = 0xf007 + clear32(phy->regs.dptx + 0x100c, 0x0008); + + // MMIO: R.4 0x23c541008 (dptx-phy[0], offset 0x1008) = 0x9 + sts_1008 = readl(phy->regs.dptx + 0x1008); + if (sts_1008 != 0x9) + dev_dbg(phy->dev, "unexpected?: dptx[0x1008]: %02x\n", sts_1008); + + // MMIO: R.4 0x23c542200 (dptx-phy[0], offset 0x2200) = 0x2000 + // MMIO: W.4 0x23c542200 (dptx-phy[0], offset 0x2200) = 0x2002 + set32(phy->regs.dptx + 0x2200, 0x0002); + + // MMIO: R.4 0x23c545010 (dptx-phy[0], offset 0x5010) = 0x18003000 + // MMIO: W.4 0x23c545010 (dptx-phy[0], offset 0x5010) = 0x18003000 + // MMIO: R.4 0x23c546010 (dptx-phy[0], offset 0x6010) = 0x18003000 + // MMIO: W.4 0x23c546010 (dptx-phy[0], offset 0x6010) = 0x18003000 + // MMIO: R.4 0x23c547010 (dptx-phy[0], offset 0x7010) = 0x18003000 + // MMIO: W.4 0x23c547010 (dptx-phy[0], offset 0x7010) = 0x18003000 + // MMIO: R.4 0x23c548010 (dptx-phy[0], offset 0x8010) = 0x18003000 + // MMIO: W.4 0x23c548010 (dptx-phy[0], offset 0x8010) = 0x18003000 + writel(0x18003000, phy->regs.dptx + 0x8010); + for (u32 loff = DPTX_LANE0_OFFSET; loff < DPTX_LANE_END; loff += DPTX_LANE_STRIDE) { + u32 val_l010 = readl(phy->regs.dptx + loff + 0x10); + writel(val_l010, phy->regs.dptx + loff + 0x10); + } + + // MMIO: R.4 0x23c544000 (dptx-phy[0], offset 0x4000) = 0x41021ac + // MMIO: W.4 0x23c544000 (dptx-phy[0], offset 0x4000) = 0x51021ac + set32(phy->regs.dptx + 0x4000, 0x1000000); + // MMIO: R.4 0x23c544000 (dptx-phy[0], offset 0x4000) = 0x51021ac + // MMIO: W.4 0x23c544000 (dptx-phy[0], offset 0x4000) = 0x71021ac + set32(phy->regs.dptx + 0x4000, 0x2000000); + + // MMIO: R.4 0x23c544004 (dptx-phy[0], offset 0x4004) = 0x41 + // MMIO: W.4 0x23c544004 (dptx-phy[0], offset 0x4004) = 0x49 + set32(phy->regs.dptx + 0x4004, 0x08); + + // MMIO: R.4 0x23c544000 (dptx-phy[0], offset 0x4000) = 0x71021ac + // MMIO: W.4 0x23c544000 (dptx-phy[0], offset 0x4000) = 0x71021ec + set32(phy->regs.dptx + 0x4000, 0x0000040); + + // MMIO: R.4 0x23c544004 (dptx-phy[0], offset 0x4004) = 0x49 + // MMIO: W.4 0x23c544004 (dptx-phy[0], offset 0x4004) = 0x48 + clear32(phy->regs.dptx + 0x4004, 0x01); + + return 0; +} + +static int dptx_phy_set_mode(struct phy *phy, enum phy_mode mode, int submode) +{ + struct apple_dptx_phy *dptx_phy = phy_get_drvdata(phy); + + switch (mode) { + case PHY_MODE_INVALID: + return dptx_phy_deactivate(dptx_phy); + case PHY_MODE_DP: + if (submode < 0 || submode > 5) + return -EINVAL; + return dptx_phy_activate(dptx_phy, submode); + default: + break; + } + + return -EINVAL; +} + +static int dptx_phy_validate(struct phy *phy, enum phy_mode mode, int submode, + union phy_configure_opts *opts_) +{ + struct phy_configure_opts_dp *opts = &opts_->dp; + + if (mode == PHY_MODE_INVALID) { + memset(opts, 0, sizeof(*opts)); + return 0; + } + + if (mode != PHY_MODE_DP) + return -EINVAL; + if (submode < 0 || submode > 5) + return -EINVAL; + + opts->lanes = 4; + opts->link_rate = 8100; + + for (int i = 0; i < 4; ++i) { + opts->voltage[i] = 3; + opts->pre[i] = 3; + } + + return 0; +} + +static int dptx_phy_configure(struct phy *phy, union phy_configure_opts *opts_) +{ + struct phy_configure_opts_dp *opts = &opts_->dp; + struct apple_dptx_phy *dptx_phy = phy_get_drvdata(phy); + enum dptx_phy_link_rate link_rate; + int ret = 0; + + if (opts->set_lanes) { + mutex_lock(&dptx_phy->lock); + ret = dptx_phy_set_active_lane_count(dptx_phy, opts->lanes); + mutex_unlock(&dptx_phy->lock); + } + + if (opts->set_rate) { + switch (opts->link_rate) { + case 1620: + link_rate = DPTX_PHY_LINK_RATE_RBR; + break; + case 2700: + link_rate = DPTX_PHY_LINK_RATE_HBR; + break; + case 5400: + link_rate = DPTX_PHY_LINK_RATE_HBR2; + break; + case 8100: + link_rate = DPTX_PHY_LINK_RATE_HBR3; + break; + case 0: + // TODO: disable! + return 0; + break; + default: + dev_err(dptx_phy->dev, "Unsupported link rate: %d\n", + opts->link_rate); + return -EINVAL; + } + + mutex_lock(&dptx_phy->lock); + ret = dptx_phy_set_link_rate(dptx_phy, link_rate); + mutex_unlock(&dptx_phy->lock); + } + + return ret; +} + +static const struct phy_ops apple_atc_dp_phy_ops = { + .owner = THIS_MODULE, + .configure = dptx_phy_configure, + .validate = dptx_phy_validate, + .set_mode = dptx_phy_set_mode, +}; + +static int dptx_phy_probe(struct platform_device *pdev) +{ + struct apple_dptx_phy *dptx_phy; + struct device *dev = &pdev->dev; + + dptx_phy = devm_kzalloc(dev, sizeof(*dptx_phy), GFP_KERNEL); + if (!dptx_phy) + return -ENOMEM; + + dptx_phy->dev = dev; + dptx_phy->hw = + *(struct apple_dptx_phy_hw *)of_device_get_match_data(dev); + platform_set_drvdata(pdev, dptx_phy); + + mutex_init(&dptx_phy->lock); + + dptx_phy->regs.core = + devm_platform_ioremap_resource_byname(pdev, "core"); + if (IS_ERR(dptx_phy->regs.core)) + return PTR_ERR(dptx_phy->regs.core); + dptx_phy->regs.dptx = + devm_platform_ioremap_resource_byname(pdev, "dptx"); + if (IS_ERR(dptx_phy->regs.dptx)) + return PTR_ERR(dptx_phy->regs.dptx); + + /* create phy */ + dptx_phy->phy_dp = + devm_phy_create(dptx_phy->dev, NULL, &apple_atc_dp_phy_ops); + if (IS_ERR(dptx_phy->phy_dp)) + return PTR_ERR(dptx_phy->phy_dp); + phy_set_drvdata(dptx_phy->phy_dp, dptx_phy); + + dptx_phy->phy_provider = + devm_of_phy_provider_register(dev, of_phy_simple_xlate); + if (IS_ERR(dptx_phy->phy_provider)) + return PTR_ERR(dptx_phy->phy_provider); + + return 0; +} + +static const struct apple_dptx_phy_hw apple_dptx_hw_t6020 = { + .type = DPTX_PHY_T6020, +}; + +static const struct apple_dptx_phy_hw apple_dptx_hw_t8112 = { + .type = DPTX_PHY_T8112, +}; + +static const struct of_device_id dptx_phy_match[] = { + { .compatible = "apple,t6020-dptx-phy", .data = &apple_dptx_hw_t6020 }, + { .compatible = "apple,t8112-dptx-phy", .data = &apple_dptx_hw_t8112 }, + {}, +}; +MODULE_DEVICE_TABLE(of, dptx_phy_match); + +static struct platform_driver dptx_phy_driver = { + .driver = { + .name = "phy-apple-dptx", + .of_match_table = dptx_phy_match, + }, + .probe = dptx_phy_probe, +}; + +module_platform_driver(dptx_phy_driver); + +MODULE_AUTHOR("Janne Grunau "); +MODULE_DESCRIPTION("Apple DP TX PHY driver"); + +MODULE_LICENSE("GPL"); diff --git a/drivers/phy/apple/dptx.h b/drivers/phy/apple/dptx.h new file mode 100644 index 00000000000000..2dd36d753eb357 --- /dev/null +++ b/drivers/phy/apple/dptx.h @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause +/* + * Apple DP TX PHY driver + * + * Copyright (C) The Asahi Linux Contributors + * Author: Janne Grunau + */ + +#ifndef PHY_APPLE_DPTX_H +#define PHY_APPLE_DPTX_H + +enum dptx_phy_link_rate { + DPTX_PHY_LINK_RATE_RBR, + DPTX_PHY_LINK_RATE_HBR, + DPTX_PHY_LINK_RATE_HBR2, + DPTX_PHY_LINK_RATE_HBR3, +}; +#endif /* PHY_APPLE_DPTX_H */ diff --git a/drivers/phy/broadcom/phy-bcm-ns-usb3.c b/drivers/phy/broadcom/phy-bcm-ns-usb3.c index 9f995e156f7559..6e56498d0644b3 100644 --- a/drivers/phy/broadcom/phy-bcm-ns-usb3.c +++ b/drivers/phy/broadcom/phy-bcm-ns-usb3.c @@ -203,7 +203,7 @@ static int bcm_ns_usb3_mdio_probe(struct mdio_device *mdiodev) usb3->dev = dev; usb3->mdiodev = mdiodev; - usb3->family = (enum bcm_ns_family)device_get_match_data(dev); + usb3->family = (unsigned long)device_get_match_data(dev); syscon_np = of_parse_phandle(dev->of_node, "usb3-dmp-syscon", 0); err = of_address_to_resource(syscon_np, 0, &res); diff --git a/drivers/phy/broadcom/phy-bcm63xx-usbh.c b/drivers/phy/broadcom/phy-bcm63xx-usbh.c index 647644de041bba..29fd6791bae642 100644 --- a/drivers/phy/broadcom/phy-bcm63xx-usbh.c +++ b/drivers/phy/broadcom/phy-bcm63xx-usbh.c @@ -375,7 +375,7 @@ static struct phy *bcm63xx_usbh_phy_xlate(struct device *dev, return of_phy_simple_xlate(dev, args); } -static int __init bcm63xx_usbh_phy_probe(struct platform_device *pdev) +static int bcm63xx_usbh_phy_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct bcm63xx_usbh_phy *usbh; @@ -432,7 +432,7 @@ static int __init bcm63xx_usbh_phy_probe(struct platform_device *pdev) return 0; } -static const struct of_device_id bcm63xx_usbh_phy_ids[] __initconst = { +static const struct of_device_id bcm63xx_usbh_phy_ids[] = { { .compatible = "brcm,bcm6318-usbh-phy", .data = &usbh_bcm6318 }, { .compatible = "brcm,bcm6328-usbh-phy", .data = &usbh_bcm6328 }, { .compatible = "brcm,bcm6358-usbh-phy", .data = &usbh_bcm6358 }, @@ -443,7 +443,7 @@ static const struct of_device_id bcm63xx_usbh_phy_ids[] __initconst = { }; MODULE_DEVICE_TABLE(of, bcm63xx_usbh_phy_ids); -static struct platform_driver bcm63xx_usbh_phy_driver __refdata = { +static struct platform_driver bcm63xx_usbh_phy_driver = { .driver = { .name = "bcm63xx-usbh-phy", .of_match_table = bcm63xx_usbh_phy_ids, diff --git a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c index 68fcc8114d750a..7f5600103a0019 100644 --- a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c +++ b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c @@ -89,7 +89,8 @@ static int imx8_pcie_phy_power_on(struct phy *phy) writel(imx8_phy->tx_deemph_gen2, imx8_phy->base + PCIE_PHY_TRSV_REG6); break; - case IMX8MP: /* Do nothing. */ + case IMX8MP: + reset_control_assert(imx8_phy->reset); break; } diff --git a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c index b94f242420fc73..f6cac4c049c431 100644 --- a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c +++ b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c @@ -124,8 +124,6 @@ struct imx8mq_usb_phy { static void tca_blk_orientation_set(struct tca_blk *tca, enum typec_orientation orientation); -#ifdef CONFIG_TYPEC - static int tca_blk_typec_switch_set(struct typec_switch_dev *sw, enum typec_orientation orientation) { @@ -173,18 +171,6 @@ static void tca_blk_put_typec_switch(struct typec_switch_dev *sw) typec_switch_unregister(sw); } -#else - -static struct typec_switch_dev *tca_blk_get_typec_switch(struct platform_device *pdev, - struct imx8mq_usb_phy *imx_phy) -{ - return NULL; -} - -static void tca_blk_put_typec_switch(struct typec_switch_dev *sw) {} - -#endif /* CONFIG_TYPEC */ - static void tca_blk_orientation_set(struct tca_blk *tca, enum typec_orientation orientation) { @@ -502,6 +488,7 @@ static void imx8m_phy_tune(struct imx8mq_usb_phy *imx_phy) if (imx_phy->pcs_tx_swing_full != PHY_TUNE_DEFAULT) { value = readl(imx_phy->base + PHY_CTRL5); + value &= ~PHY_CTRL5_PCS_TX_SWING_FULL_MASK; value |= FIELD_PREP(PHY_CTRL5_PCS_TX_SWING_FULL_MASK, imx_phy->pcs_tx_swing_full); writel(value, imx_phy->base + PHY_CTRL5); diff --git a/drivers/phy/freescale/phy-fsl-imx8qm-hsio.c b/drivers/phy/freescale/phy-fsl-imx8qm-hsio.c index 5dca93cd325c89..279b8ac7822df7 100644 --- a/drivers/phy/freescale/phy-fsl-imx8qm-hsio.c +++ b/drivers/phy/freescale/phy-fsl-imx8qm-hsio.c @@ -251,7 +251,7 @@ static void imx_hsio_configure_clk_pad(struct phy *phy) struct imx_hsio_lane *lane = phy_get_drvdata(phy); struct imx_hsio_priv *priv = lane->priv; - if (strncmp(priv->refclk_pad, "output", 6) == 0) { + if (priv->refclk_pad && strncmp(priv->refclk_pad, "output", 6) == 0) { pll = true; regmap_update_bits(priv->misc, HSIO_CTRL0, HSIO_IOB_A_0_TXOE | HSIO_IOB_A_0_M1M0_MASK, @@ -533,7 +533,7 @@ static struct phy *imx_hsio_xlate(struct device *dev, static int imx_hsio_probe(struct platform_device *pdev) { - int i; + int i, ret; void __iomem *off; struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; @@ -545,6 +545,9 @@ static int imx_hsio_probe(struct platform_device *pdev) return -ENOMEM; priv->dev = &pdev->dev; priv->drvdata = of_device_get_match_data(dev); + ret = devm_mutex_init(dev, &priv->lock); + if (ret) + return ret; /* Get HSIO configuration mode */ if (of_property_read_string(np, "fsl,hsio-cfg", &priv->hsio_cfg)) diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c index b5514a32ff8ff5..eb93015be841f5 100644 --- a/drivers/phy/qualcomm/phy-qcom-qusb2.c +++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c @@ -1093,29 +1093,29 @@ static int qusb2_phy_probe(struct platform_device *pdev) or->hsdisc_trim.override = true; } - pm_runtime_set_active(dev); - pm_runtime_enable(dev); + dev_set_drvdata(dev, qphy); + /* - * Prevent runtime pm from being ON by default. Users can enable - * it using power/control in sysfs. + * Enable runtime PM support, but forbid it by default. + * Users can allow it again via the power/control attribute in sysfs. */ + pm_runtime_set_active(dev); pm_runtime_forbid(dev); + ret = devm_pm_runtime_enable(dev); + if (ret) + return ret; generic_phy = devm_phy_create(dev, NULL, &qusb2_phy_gen_ops); if (IS_ERR(generic_phy)) { ret = PTR_ERR(generic_phy); dev_err(dev, "failed to create phy, %d\n", ret); - pm_runtime_disable(dev); return ret; } qphy->phy = generic_phy; - dev_set_drvdata(dev, qphy); phy_set_drvdata(generic_phy, qphy); phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); - if (IS_ERR(phy_provider)) - pm_runtime_disable(dev); return PTR_ERR_OR_ZERO(phy_provider); } diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c index 3f6b480e109229..a38ead7c8055d0 100644 --- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c +++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c @@ -134,7 +134,6 @@ struct rcar_gen3_chan { struct extcon_dev *extcon; struct rcar_gen3_phy rphys[NUM_OF_PHYS]; struct regulator *vbus; - struct reset_control *rstc; struct work_struct work; spinlock_t lock; /* protects access to hardware and driver data structure. */ enum usb_dr_mode dr_mode; @@ -771,21 +770,31 @@ static enum usb_dr_mode rcar_gen3_get_dr_mode(struct device_node *np) return candidate; } +static void rcar_gen3_reset_assert(void *data) +{ + reset_control_assert(data); +} + static int rcar_gen3_phy_usb2_init_bus(struct rcar_gen3_chan *channel) { struct device *dev = channel->dev; + struct reset_control *rstc; int ret; u32 val; - channel->rstc = devm_reset_control_array_get_shared(dev); - if (IS_ERR(channel->rstc)) - return PTR_ERR(channel->rstc); + rstc = devm_reset_control_array_get_shared(dev); + if (IS_ERR(rstc)) + return PTR_ERR(rstc); ret = pm_runtime_resume_and_get(dev); if (ret) return ret; - ret = reset_control_deassert(channel->rstc); + ret = reset_control_deassert(rstc); + if (ret) + goto rpm_put; + + ret = devm_add_action_or_reset(dev, rcar_gen3_reset_assert, rstc); if (ret) goto rpm_put; @@ -924,7 +933,6 @@ static void rcar_gen3_phy_usb2_remove(struct platform_device *pdev) if (channel->is_otg_channel) device_remove_file(&pdev->dev, &dev_attr_role); - reset_control_assert(channel->rstc); pm_runtime_disable(&pdev->dev); }; diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c index b0f23690ec3002..8f4c08e599aa22 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c @@ -821,17 +821,20 @@ static void rockchip_chg_detect_work(struct work_struct *work) container_of(work, struct rockchip_usb2phy_port, chg_work.work); struct rockchip_usb2phy *rphy = dev_get_drvdata(rport->phy->dev.parent); struct regmap *base = get_reg_base(rphy); - bool is_dcd, tmout, vout; + bool is_dcd, tmout, vout, vbus_attach; unsigned long delay; + vbus_attach = property_enabled(rphy->grf, &rport->port_cfg->utmi_bvalid); + dev_dbg(&rport->phy->dev, "chg detection work state = %d\n", rphy->chg_state); switch (rphy->chg_state) { case USB_CHG_STATE_UNDEFINED: - if (!rport->suspended) + if (!rport->suspended && !vbus_attach) rockchip_usb2phy_power_off(rport->phy); /* put the controller in non-driving mode */ - property_enable(base, &rphy->phy_cfg->chg_det.opmode, false); + if (!vbus_attach) + property_enable(base, &rphy->phy_cfg->chg_det.opmode, false); /* Start DCD processing stage 1 */ rockchip_chg_enable_dcd(rphy, true); rphy->chg_state = USB_CHG_STATE_WAIT_FOR_DCD; @@ -894,7 +897,8 @@ static void rockchip_chg_detect_work(struct work_struct *work) fallthrough; case USB_CHG_STATE_DETECTED: /* put the controller in normal mode */ - property_enable(base, &rphy->phy_cfg->chg_det.opmode, true); + if (!vbus_attach) + property_enable(base, &rphy->phy_cfg->chg_det.opmode, true); rockchip_usb2phy_otg_sm_work(&rport->otg_sm_work.work); dev_dbg(&rport->phy->dev, "charger = %s\n", chg_to_string(rphy->chg_type)); @@ -1491,7 +1495,7 @@ static int rockchip_usb2phy_probe(struct platform_device *pdev) rphy); if (ret) { dev_err_probe(rphy->dev, ret, "failed to request usb2phy irq handle\n"); - goto put_child; + return ret; } } diff --git a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c index a3ef19807b9ef4..7f8fc8e6d48905 100644 --- a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c +++ b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c @@ -21,6 +21,9 @@ #define REF_CLOCK_100MHz (100 * HZ_PER_MHZ) /* RK3528 COMBO PHY REG */ +#define RK3528_PHYREG5 0x14 +#define RK3528_PHYREG5_GATE_TX_PCK_SEL BIT(3) +#define RK3528_PHYREG5_GATE_TX_PCK_DLY_PLL_OFF BIT(3) #define RK3528_PHYREG6 0x18 #define RK3528_PHYREG6_PLL_KVCO GENMASK(12, 10) #define RK3528_PHYREG6_PLL_KVCO_VALUE 0x2 @@ -103,6 +106,10 @@ #define RK3568_PHYREG18 0x44 #define RK3568_PHYREG18_PLL_LOOP 0x32 +#define RK3568_PHYREG30 0x74 +#define RK3568_PHYREG30_GATE_TX_PCK_SEL BIT(7) +#define RK3568_PHYREG30_GATE_TX_PCK_DLY_PLL_OFF BIT(7) + #define RK3568_PHYREG32 0x7C #define RK3568_PHYREG32_SSC_MASK GENMASK(7, 4) #define RK3568_PHYREG32_SSC_DIR_MASK GENMASK(5, 4) @@ -504,6 +511,10 @@ static int rk3528_combphy_cfg(struct rockchip_combphy_priv *priv) case REF_CLOCK_100MHz: rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_100m, true); if (priv->type == PHY_TYPE_PCIE) { + /* Gate_tx_pck_sel length select for L1ss support */ + rockchip_combphy_updatel(priv, RK3528_PHYREG5_GATE_TX_PCK_SEL, + RK3528_PHYREG5_GATE_TX_PCK_DLY_PLL_OFF, RK3528_PHYREG5); + /* PLL KVCO tuning fine */ val = FIELD_PREP(RK3528_PHYREG6_PLL_KVCO, RK3528_PHYREG6_PLL_KVCO_VALUE); rockchip_combphy_updatel(priv, RK3528_PHYREG6_PLL_KVCO, val, @@ -657,6 +668,10 @@ static int rk3562_combphy_cfg(struct rockchip_combphy_priv *priv) case REF_CLOCK_100MHz: rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_100m, true); if (priv->type == PHY_TYPE_PCIE) { + /* Gate_tx_pck_sel length select for L1ss support */ + rockchip_combphy_updatel(priv, RK3568_PHYREG30_GATE_TX_PCK_SEL, + RK3568_PHYREG30_GATE_TX_PCK_DLY_PLL_OFF, + RK3568_PHYREG30); /* PLL KVCO tuning fine */ val = FIELD_PREP(RK3568_PHYREG33_PLL_KVCO_MASK, RK3568_PHYREG33_PLL_KVCO_VALUE); diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c index 01bbf668e05ef9..cafa618d70fdca 100644 --- a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c +++ b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c @@ -414,6 +414,8 @@ struct rk_hdptx_phy { static const struct ropll_config ropll_tmds_cfg[] = { { 594000000ULL, 124, 124, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0, 1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, }, + { 461101250ULL, 97, 97, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 71, 1, 53, 2, 6, + 35, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, }, { 371250000ULL, 155, 155, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0, 1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, }, { 297000000ULL, 124, 124, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 62, 1, 16, 5, 0, @@ -500,9 +502,7 @@ static const struct reg_sequence rk_hdtpx_common_cmn_init_seq[] = { REG_SEQ0(CMN_REG(0043), 0x00), REG_SEQ0(CMN_REG(0044), 0x46), REG_SEQ0(CMN_REG(0045), 0x24), - REG_SEQ0(CMN_REG(0046), 0xff), REG_SEQ0(CMN_REG(0047), 0x00), - REG_SEQ0(CMN_REG(0048), 0x44), REG_SEQ0(CMN_REG(0049), 0xfa), REG_SEQ0(CMN_REG(004a), 0x08), REG_SEQ0(CMN_REG(004b), 0x00), @@ -575,6 +575,8 @@ static const struct reg_sequence rk_hdtpx_tmds_cmn_init_seq[] = { REG_SEQ0(CMN_REG(0034), 0x00), REG_SEQ0(CMN_REG(003d), 0x40), REG_SEQ0(CMN_REG(0042), 0x78), + REG_SEQ0(CMN_REG(0046), 0xdd), + REG_SEQ0(CMN_REG(0048), 0x11), REG_SEQ0(CMN_REG(004e), 0x34), REG_SEQ0(CMN_REG(005c), 0x25), REG_SEQ0(CMN_REG(005e), 0x4f), @@ -668,13 +670,9 @@ static const struct reg_sequence rk_hdtpx_common_lane_init_seq[] = { static const struct reg_sequence rk_hdtpx_tmds_lane_init_seq[] = { REG_SEQ0(LANE_REG(0312), 0x00), - REG_SEQ0(LANE_REG(031e), 0x00), REG_SEQ0(LANE_REG(0412), 0x00), - REG_SEQ0(LANE_REG(041e), 0x00), REG_SEQ0(LANE_REG(0512), 0x00), - REG_SEQ0(LANE_REG(051e), 0x00), REG_SEQ0(LANE_REG(0612), 0x00), - REG_SEQ0(LANE_REG(061e), 0x08), REG_SEQ0(LANE_REG(0303), 0x2f), REG_SEQ0(LANE_REG(0403), 0x2f), REG_SEQ0(LANE_REG(0503), 0x2f), @@ -687,6 +685,11 @@ static const struct reg_sequence rk_hdtpx_tmds_lane_init_seq[] = { REG_SEQ0(LANE_REG(0406), 0x1c), REG_SEQ0(LANE_REG(0506), 0x1c), REG_SEQ0(LANE_REG(0606), 0x1c), + /* Keep Inter-Pair Skew in the limits */ + REG_SEQ0(LANE_REG(031e), 0x02), + REG_SEQ0(LANE_REG(041e), 0x02), + REG_SEQ0(LANE_REG(051e), 0x02), + REG_SEQ0(LANE_REG(061e), 0x0a), }; static struct tx_drv_ctrl tx_drv_ctrl_rbr[4][4] = { @@ -1037,7 +1040,8 @@ static int rk_hdptx_ropll_tmds_cmn_config(struct rk_hdptx_phy *hdptx) ret = rk_hdptx_post_enable_pll(hdptx); if (!ret) - hdptx->hw_rate = hdptx->hdmi_cfg.tmds_char_rate; + hdptx->hw_rate = DIV_ROUND_CLOSEST_ULL(hdptx->hdmi_cfg.tmds_char_rate * 8, + hdptx->hdmi_cfg.bpc); return ret; } @@ -1895,19 +1899,20 @@ static long rk_hdptx_phy_clk_round_rate(struct clk_hw *hw, unsigned long rate, * hence ensure rk_hdptx_phy_clk_set_rate() won't be invoked with * a different rate argument. */ - return hdptx->hdmi_cfg.tmds_char_rate; + return DIV_ROUND_CLOSEST_ULL(hdptx->hdmi_cfg.tmds_char_rate * 8, hdptx->hdmi_cfg.bpc); } static int rk_hdptx_phy_clk_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { struct rk_hdptx_phy *hdptx = to_rk_hdptx_phy(hw); + unsigned long long tmds_rate = DIV_ROUND_CLOSEST_ULL(rate * hdptx->hdmi_cfg.bpc, 8); /* Revert any unlikely TMDS char rate change since round_rate() */ - if (hdptx->hdmi_cfg.tmds_char_rate != rate) { - dev_warn(hdptx->dev, "Reverting unexpected rate change from %lu to %llu\n", - rate, hdptx->hdmi_cfg.tmds_char_rate); - hdptx->hdmi_cfg.tmds_char_rate = rate; + if (hdptx->hdmi_cfg.tmds_char_rate != tmds_rate) { + dev_warn(hdptx->dev, "Reverting unexpected rate change from %llu to %llu\n", + tmds_rate, hdptx->hdmi_cfg.tmds_char_rate); + hdptx->hdmi_cfg.tmds_char_rate = tmds_rate; } /* diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c index a88ba95bdc8f53..1c8bf80119f11e 100644 --- a/drivers/phy/samsung/phy-exynos5-usbdrd.c +++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c @@ -1823,7 +1823,7 @@ static int exynos5_usbdrd_orien_sw_set(struct typec_switch_dev *sw, phy_drd->orientation = orientation; } - clk_bulk_disable(phy_drd->drv_data->n_clks, phy_drd->clks); + clk_bulk_disable_unprepare(phy_drd->drv_data->n_clks, phy_drd->clks); return 0; } diff --git a/drivers/phy/st/phy-stm32-usbphyc.c b/drivers/phy/st/phy-stm32-usbphyc.c index 27fe92f73f3313..b44afbff8616ba 100644 --- a/drivers/phy/st/phy-stm32-usbphyc.c +++ b/drivers/phy/st/phy-stm32-usbphyc.c @@ -712,7 +712,7 @@ static int stm32_usbphyc_probe(struct platform_device *pdev) } ret = of_property_read_u32(child, "reg", &index); - if (ret || index > usbphyc->nphys) { + if (ret || index >= usbphyc->nphys) { dev_err(&phy->dev, "invalid reg property: %d\n", ret); if (!ret) ret = -EINVAL; diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c index e818f6c3980e6b..bec9616c4a2e0d 100644 --- a/drivers/phy/tegra/xusb-tegra186.c +++ b/drivers/phy/tegra/xusb-tegra186.c @@ -84,6 +84,7 @@ #define XUSB_PADCTL_USB2_BIAS_PAD_CTL0 0x284 #define BIAS_PAD_PD BIT(11) #define HS_SQUELCH_LEVEL(x) (((x) & 0x7) << 0) +#define HS_DISCON_LEVEL(x) (((x) & 0x7) << 3) #define XUSB_PADCTL_USB2_BIAS_PAD_CTL1 0x288 #define USB2_TRK_START_TIMER(x) (((x) & 0x7f) << 12) @@ -623,6 +624,8 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl) value &= ~BIAS_PAD_PD; value &= ~HS_SQUELCH_LEVEL(~0); value |= HS_SQUELCH_LEVEL(priv->calib.hs_squelch); + value &= ~HS_DISCON_LEVEL(~0); + value |= HS_DISCON_LEVEL(0x7); padctl_writel(padctl, value, XUSB_PADCTL_USB2_BIAS_PAD_CTL0); udelay(1); diff --git a/drivers/phy/ti/phy-da8xx-usb.c b/drivers/phy/ti/phy-da8xx-usb.c index 1d81a1e6ec6b6b..62fa6f89c0e61e 100644 --- a/drivers/phy/ti/phy-da8xx-usb.c +++ b/drivers/phy/ti/phy-da8xx-usb.c @@ -180,6 +180,7 @@ static int da8xx_usb_phy_probe(struct platform_device *pdev) struct da8xx_usb_phy_platform_data *pdata = dev->platform_data; struct device_node *node = dev->of_node; struct da8xx_usb_phy *d_phy; + int ret; d_phy = devm_kzalloc(dev, sizeof(*d_phy), GFP_KERNEL); if (!d_phy) @@ -233,8 +234,6 @@ static int da8xx_usb_phy_probe(struct platform_device *pdev) return PTR_ERR(d_phy->phy_provider); } } else { - int ret; - ret = phy_create_lookup(d_phy->usb11_phy, "usb-phy", "ohci-da8xx"); if (ret) @@ -249,7 +248,9 @@ static int da8xx_usb_phy_probe(struct platform_device *pdev) PHY_INIT_BITS, PHY_INIT_BITS); pm_runtime_set_active(dev); - devm_pm_runtime_enable(dev); + ret = devm_pm_runtime_enable(dev); + if (ret) + return ret; /* * Prevent runtime pm from being ON by default. Users can enable * it using power/control in sysfs. diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c index 50adabb867cb12..26209a89703a8a 100644 --- a/drivers/phy/ti/phy-gmii-sel.c +++ b/drivers/phy/ti/phy-gmii-sel.c @@ -512,7 +512,7 @@ static int phy_gmii_sel_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(base), "failed to get base memory resource\n"); - priv->regmap = regmap_init_mmio(dev, base, &phy_gmii_sel_regmap_cfg); + priv->regmap = devm_regmap_init_mmio(dev, base, &phy_gmii_sel_regmap_cfg); if (IS_ERR(priv->regmap)) return dev_err_probe(dev, PTR_ERR(priv->regmap), "Failed to get syscon\n"); diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8189.c b/drivers/pinctrl/mediatek/pinctrl-mt8189.c index f6a3e584588b0e..cd4cdff309a12b 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8189.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8189.c @@ -1642,7 +1642,7 @@ static const struct mtk_pin_reg_calc mt8189_reg_cals[PINCTRL_PIN_REG_MAX] = { }; static const char * const mt8189_pinctrl_register_base_names[] = { - "base", "lm", "rb0", "rb1", "bm0", "bm1", "bm2", "lt0", "lt1", "rt", + "base", "bm0", "bm1", "bm2", "lm", "lt0", "lt1", "rb0", "rb1", "rt", }; static const struct mtk_eint_hw mt8189_eint_hw = { diff --git a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c index d9e3a8d5932a82..f05d8261624a4e 100644 --- a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c +++ b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c @@ -725,8 +725,9 @@ static u32 aml_bank_pins(struct device_node *np) if (of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, 0, &of_args)) return 0; - else - return of_args.args[2]; + + of_node_put(of_args.np); + return of_args.args[2]; } static int aml_bank_number(struct device_node *np) @@ -736,8 +737,9 @@ static int aml_bank_number(struct device_node *np) if (of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, 0, &of_args)) return -EINVAL; - else - return of_args.args[1] >> 8; + + of_node_put(of_args.np); + return of_args.args[1] >> 8; } static unsigned int aml_count_pins(struct device_node *np) diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c index 18295b15ecd9dd..4507dc8b5563c0 100644 --- a/drivers/pinctrl/meson/pinctrl-meson.c +++ b/drivers/pinctrl/meson/pinctrl-meson.c @@ -619,7 +619,7 @@ static int meson_gpiolib_register(struct meson_pinctrl *pc) pc->chip.set = meson_gpio_set; pc->chip.base = -1; pc->chip.ngpio = pc->data->num_pins; - pc->chip.can_sleep = false; + pc->chip.can_sleep = true; ret = gpiochip_add_data(&pc->chip, pc); if (ret) { diff --git a/drivers/pinctrl/pinctrl-equilibrium.c b/drivers/pinctrl/pinctrl-equilibrium.c index 2d04829b29c997..48b55c5bf8d4fd 100644 --- a/drivers/pinctrl/pinctrl-equilibrium.c +++ b/drivers/pinctrl/pinctrl-equilibrium.c @@ -846,6 +846,7 @@ static int pinbank_init(struct device_node *np, bank->pin_base = spec.args[1]; bank->nr_pins = spec.args[2]; + of_node_put(spec.np); bank->aval_pinmap = readl(bank->membase + REG_AVAIL); bank->id = id; diff --git a/drivers/pinctrl/pinctrl-k230.c b/drivers/pinctrl/pinctrl-k230.c index d716f23d837f7a..20f7c0f70eb77c 100644 --- a/drivers/pinctrl/pinctrl-k230.c +++ b/drivers/pinctrl/pinctrl-k230.c @@ -65,6 +65,7 @@ struct k230_pmx_func { }; struct k230_pinctrl { + struct device *dev; struct pinctrl_desc pctl; struct pinctrl_dev *pctl_dev; struct regmap *regmap_base; @@ -470,7 +471,7 @@ static int k230_pinctrl_parse_groups(struct device_node *np, struct k230_pinctrl *info, unsigned int index) { - struct device *dev = info->pctl_dev->dev; + struct device *dev = info->dev; const __be32 *list; int size, i, ret; @@ -511,7 +512,7 @@ static int k230_pinctrl_parse_functions(struct device_node *np, struct k230_pinctrl *info, unsigned int index) { - struct device *dev = info->pctl_dev->dev; + struct device *dev = info->dev; struct k230_pmx_func *func; struct k230_pin_group *grp; static unsigned int idx, i; @@ -596,6 +597,8 @@ static int k230_pinctrl_probe(struct platform_device *pdev) if (!info) return -ENOMEM; + info->dev = dev; + pctl = &info->pctl; pctl->name = "k230-pinctrl"; diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index 7a68a6237649c1..f1cba3d2367a36 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -3184,10 +3184,9 @@ static int rockchip_pmx_set(struct pinctrl_dev *pctldev, unsigned selector, return 0; } -static int rockchip_pmx_gpio_set_direction(struct pinctrl_dev *pctldev, - struct pinctrl_gpio_range *range, - unsigned offset, - bool input) +static int rockchip_pmx_gpio_request_enable(struct pinctrl_dev *pctldev, + struct pinctrl_gpio_range *range, + unsigned int offset) { struct rockchip_pinctrl *info = pinctrl_dev_get_drvdata(pctldev); struct rockchip_pin_bank *bank; @@ -3201,7 +3200,7 @@ static const struct pinmux_ops rockchip_pmx_ops = { .get_function_name = rockchip_pmx_get_func_name, .get_function_groups = rockchip_pmx_get_groups, .set_mux = rockchip_pmx_set, - .gpio_set_direction = rockchip_pmx_gpio_set_direction, + .gpio_request_enable = rockchip_pmx_gpio_request_enable, }; /* diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index 6d580aa282ec98..d85e6c1f632186 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -485,7 +485,8 @@ static int pcs_pinconf_get(struct pinctrl_dev *pctldev, struct pcs_device *pcs = pinctrl_dev_get_drvdata(pctldev); struct pcs_function *func; enum pin_config_param param; - unsigned offset = 0, data = 0, i, j, ret; + unsigned offset = 0, data = 0, i, j; + int ret; ret = pcs_get_function(pctldev, pin, &func); if (ret) @@ -549,9 +550,9 @@ static int pcs_pinconf_set(struct pinctrl_dev *pctldev, { struct pcs_device *pcs = pinctrl_dev_get_drvdata(pctldev); struct pcs_function *func; - unsigned offset = 0, shift = 0, i, data, ret; + unsigned offset = 0, shift = 0, i, data; u32 arg; - int j; + int j, ret; enum pin_config_param param; ret = pcs_get_function(pctldev, pin, &func); @@ -1358,6 +1359,7 @@ static int pcs_add_gpio_func(struct device_node *node, struct pcs_device *pcs) } range = devm_kzalloc(pcs->dev, sizeof(*range), GFP_KERNEL); if (!range) { + of_node_put(gpiospec.np); ret = -ENOMEM; break; } @@ -1367,6 +1369,7 @@ static int pcs_add_gpio_func(struct device_node *node, struct pcs_device *pcs) mutex_lock(&pcs->mutex); list_add_tail(&range->node, &pcs->gpiofuncs); mutex_unlock(&pcs->mutex); + of_node_put(gpiospec.np); } return ret; } diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index c480e8b7850329..f56592411cf6d9 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -61,13 +61,14 @@ config PINCTRL_LPASS_LPI (Low Power Island) found on the Qualcomm Technologies Inc SoCs. config PINCTRL_SC7280_LPASS_LPI - tristate "Qualcomm Technologies Inc SC7280 LPASS LPI pin controller driver" + tristate "Qualcomm Technologies Inc SC7280 and SM8350 LPASS LPI pin controller driver" depends on ARM64 || COMPILE_TEST depends on PINCTRL_LPASS_LPI help This is the pinctrl, pinmux, pinconf and gpiolib driver for the Qualcomm Technologies Inc LPASS (Low Power Audio SubSystem) LPI - (Low Power Island) found on the Qualcomm Technologies Inc SC7280 platform. + (Low Power Island) found on the Qualcomm Technologies Inc SC7280 + and SM8350 platforms. config PINCTRL_SDM660_LPASS_LPI tristate "Qualcomm Technologies Inc SDM660 LPASS LPI pin controller driver" @@ -106,16 +107,6 @@ config PINCTRL_SM8250_LPASS_LPI Qualcomm Technologies Inc LPASS (Low Power Audio SubSystem) LPI (Low Power Island) found on the Qualcomm Technologies Inc SM8250 platform. -config PINCTRL_SM8350_LPASS_LPI - tristate "Qualcomm Technologies Inc SM8350 LPASS LPI pin controller driver" - depends on ARM64 || COMPILE_TEST - depends on PINCTRL_LPASS_LPI - help - This is the pinctrl, pinmux, pinconf and gpiolib driver for the - Qualcomm Technologies Inc LPASS (Low Power Audio SubSystem) LPI - (Low Power Island) found on the Qualcomm Technologies Inc SM8350 - platform. - config PINCTRL_SM8450_LPASS_LPI tristate "Qualcomm Technologies Inc SM8450 LPASS LPI pin controller driver" depends on ARM64 || COMPILE_TEST diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile index 567d3051e760dd..9d7ada203d4cbf 100644 --- a/drivers/pinctrl/qcom/Makefile +++ b/drivers/pinctrl/qcom/Makefile @@ -63,7 +63,6 @@ obj-$(CONFIG_PINCTRL_SM8150) += pinctrl-sm8150.o obj-$(CONFIG_PINCTRL_SM8250) += pinctrl-sm8250.o obj-$(CONFIG_PINCTRL_SM8250_LPASS_LPI) += pinctrl-sm8250-lpass-lpi.o obj-$(CONFIG_PINCTRL_SM8350) += pinctrl-sm8350.o -obj-$(CONFIG_PINCTRL_SM8350_LPASS_LPI) += pinctrl-sm8350-lpass-lpi.o obj-$(CONFIG_PINCTRL_SM8450) += pinctrl-sm8450.o obj-$(CONFIG_PINCTRL_SM8450_LPASS_LPI) += pinctrl-sm8450-lpass-lpi.o obj-$(CONFIG_PINCTRL_SM8550) += pinctrl-sm8550.o diff --git a/drivers/pinctrl/qcom/pinctrl-glymur.c b/drivers/pinctrl/qcom/pinctrl-glymur.c index 9913f98e953110..335005084b6bc8 100644 --- a/drivers/pinctrl/qcom/pinctrl-glymur.c +++ b/drivers/pinctrl/qcom/pinctrl-glymur.c @@ -1316,7 +1316,7 @@ static const char *const wcn_sw_ctrl_groups[] = { }; static const struct pinfunction glymur_functions[] = { - MSM_PIN_FUNCTION(gpio), + MSM_GPIO_PIN_FUNCTION(gpio), MSM_PIN_FUNCTION(resout_gpio_n), MSM_PIN_FUNCTION(aoss_cti), MSM_PIN_FUNCTION(asc_cci), @@ -1342,7 +1342,7 @@ static const struct pinfunction glymur_functions[] = { MSM_PIN_FUNCTION(edp0_hot), MSM_PIN_FUNCTION(edp0_lcd), MSM_PIN_FUNCTION(edp1_lcd), - MSM_PIN_FUNCTION(egpio), + MSM_GPIO_PIN_FUNCTION(egpio), MSM_PIN_FUNCTION(eusb_ac_en), MSM_PIN_FUNCTION(gcc_gp1), MSM_PIN_FUNCTION(gcc_gp2), @@ -1743,7 +1743,7 @@ static const struct msm_pinctrl_soc_data glymur_tlmm = { }; static const struct of_device_id glymur_tlmm_of_match[] = { - { .compatible = "qcom,glymur-tlmm", .data = &glymur_tlmm }, + { .compatible = "qcom,glymur-tlmm", }, { } }; diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c index 1c97ec44aa5ff7..76aed32962794e 100644 --- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c @@ -312,6 +312,22 @@ static const struct pinconf_ops lpi_gpio_pinconf_ops = { .pin_config_group_set = lpi_config_set, }; +static int lpi_gpio_get_direction(struct gpio_chip *chip, unsigned int pin) +{ + unsigned long config = pinconf_to_config_packed(PIN_CONFIG_LEVEL, 0); + struct lpi_pinctrl *state = gpiochip_get_data(chip); + unsigned long arg; + int ret; + + ret = lpi_config_get(state->ctrl, pin, &config); + if (ret) + return ret; + + arg = pinconf_to_config_argument(config); + + return arg ? GPIO_LINE_DIRECTION_OUT : GPIO_LINE_DIRECTION_IN; +} + static int lpi_gpio_direction_input(struct gpio_chip *chip, unsigned int pin) { struct lpi_pinctrl *state = gpiochip_get_data(chip); @@ -409,6 +425,7 @@ static void lpi_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) #endif static const struct gpio_chip lpi_gpio_template = { + .get_direction = lpi_gpio_get_direction, .direction_input = lpi_gpio_direction_input, .direction_output = lpi_gpio_direction_output, .get = lpi_gpio_get, @@ -498,7 +515,7 @@ int lpi_pinctrl_probe(struct platform_device *pdev) pctrl->chip.base = -1; pctrl->chip.ngpio = data->npins; pctrl->chip.label = dev_name(dev); - pctrl->chip.can_sleep = false; + pctrl->chip.can_sleep = true; mutex_init(&pctrl->lock); diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c index 1161f0a91a002a..750f410311a8fb 100644 --- a/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-sc7280-lpass-lpi.c @@ -131,6 +131,9 @@ static const struct of_device_id lpi_pinctrl_of_match[] = { { .compatible = "qcom,sc7280-lpass-lpi-pinctrl", .data = &sc7280_lpi_data, + }, { + .compatible = "qcom,sm8350-lpass-lpi-pinctrl", + .data = &sc7280_lpi_data, }, { } }; diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c index 64494a86490e2f..c27452eece3e6b 100644 --- a/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-sm8250-lpass-lpi.c @@ -73,7 +73,7 @@ static const char * const i2s1_ws_groups[] = { "gpio7" }; static const char * const i2s1_data_groups[] = { "gpio8", "gpio9" }; static const char * const wsa_swr_clk_groups[] = { "gpio10" }; static const char * const wsa_swr_data_groups[] = { "gpio11" }; -static const char * const i2s2_data_groups[] = { "gpio12", "gpio12" }; +static const char * const i2s2_data_groups[] = { "gpio12", "gpio13" }; static const struct lpi_pingroup sm8250_groups[] = { LPI_PINGROUP(0, 0, swr_tx_clk, qua_mi2s_sclk, _, _), diff --git a/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c deleted file mode 100644 index 7b146b4acfdf42..00000000000000 --- a/drivers/pinctrl/qcom/pinctrl-sm8350-lpass-lpi.c +++ /dev/null @@ -1,151 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2016-2019, The Linux Foundation. All rights reserved. - * Copyright (c) 2020-2023 Linaro Ltd. - */ - -#include -#include -#include - -#include "pinctrl-lpass-lpi.h" - -enum lpass_lpi_functions { - LPI_MUX_dmic1_clk, - LPI_MUX_dmic1_data, - LPI_MUX_dmic2_clk, - LPI_MUX_dmic2_data, - LPI_MUX_dmic3_clk, - LPI_MUX_dmic3_data, - LPI_MUX_i2s1_clk, - LPI_MUX_i2s1_data, - LPI_MUX_i2s1_ws, - LPI_MUX_i2s2_clk, - LPI_MUX_i2s2_data, - LPI_MUX_i2s2_ws, - LPI_MUX_qua_mi2s_data, - LPI_MUX_qua_mi2s_sclk, - LPI_MUX_qua_mi2s_ws, - LPI_MUX_swr_rx_clk, - LPI_MUX_swr_rx_data, - LPI_MUX_swr_tx_clk, - LPI_MUX_swr_tx_data, - LPI_MUX_wsa_swr_clk, - LPI_MUX_wsa_swr_data, - LPI_MUX_gpio, - LPI_MUX__, -}; - -static const struct pinctrl_pin_desc sm8350_lpi_pins[] = { - PINCTRL_PIN(0, "gpio0"), - PINCTRL_PIN(1, "gpio1"), - PINCTRL_PIN(2, "gpio2"), - PINCTRL_PIN(3, "gpio3"), - PINCTRL_PIN(4, "gpio4"), - PINCTRL_PIN(5, "gpio5"), - PINCTRL_PIN(6, "gpio6"), - PINCTRL_PIN(7, "gpio7"), - PINCTRL_PIN(8, "gpio8"), - PINCTRL_PIN(9, "gpio9"), - PINCTRL_PIN(10, "gpio10"), - PINCTRL_PIN(11, "gpio11"), - PINCTRL_PIN(12, "gpio12"), - PINCTRL_PIN(13, "gpio13"), - PINCTRL_PIN(14, "gpio14"), -}; - -static const char * const swr_tx_clk_groups[] = { "gpio0" }; -static const char * const swr_tx_data_groups[] = { "gpio1", "gpio2", "gpio5", "gpio14" }; -static const char * const swr_rx_clk_groups[] = { "gpio3" }; -static const char * const swr_rx_data_groups[] = { "gpio4", "gpio5" }; -static const char * const dmic1_clk_groups[] = { "gpio6" }; -static const char * const dmic1_data_groups[] = { "gpio7" }; -static const char * const dmic2_clk_groups[] = { "gpio8" }; -static const char * const dmic2_data_groups[] = { "gpio9" }; -static const char * const i2s2_clk_groups[] = { "gpio10" }; -static const char * const i2s2_ws_groups[] = { "gpio11" }; -static const char * const dmic3_clk_groups[] = { "gpio12" }; -static const char * const dmic3_data_groups[] = { "gpio13" }; -static const char * const qua_mi2s_sclk_groups[] = { "gpio0" }; -static const char * const qua_mi2s_ws_groups[] = { "gpio1" }; -static const char * const qua_mi2s_data_groups[] = { "gpio2", "gpio3", "gpio4" }; -static const char * const i2s1_clk_groups[] = { "gpio6" }; -static const char * const i2s1_ws_groups[] = { "gpio7" }; -static const char * const i2s1_data_groups[] = { "gpio8", "gpio9" }; -static const char * const wsa_swr_clk_groups[] = { "gpio10" }; -static const char * const wsa_swr_data_groups[] = { "gpio11" }; -static const char * const i2s2_data_groups[] = { "gpio12", "gpio12" }; - -static const struct lpi_pingroup sm8350_groups[] = { - LPI_PINGROUP(0, 0, swr_tx_clk, qua_mi2s_sclk, _, _), - LPI_PINGROUP(1, 2, swr_tx_data, qua_mi2s_ws, _, _), - LPI_PINGROUP(2, 4, swr_tx_data, qua_mi2s_data, _, _), - LPI_PINGROUP(3, 8, swr_rx_clk, qua_mi2s_data, _, _), - LPI_PINGROUP(4, 10, swr_rx_data, qua_mi2s_data, _, _), - LPI_PINGROUP(5, 12, swr_tx_data, swr_rx_data, _, _), - LPI_PINGROUP(6, LPI_NO_SLEW, dmic1_clk, i2s1_clk, _, _), - LPI_PINGROUP(7, LPI_NO_SLEW, dmic1_data, i2s1_ws, _, _), - LPI_PINGROUP(8, LPI_NO_SLEW, dmic2_clk, i2s1_data, _, _), - LPI_PINGROUP(9, LPI_NO_SLEW, dmic2_data, i2s1_data, _, _), - LPI_PINGROUP(10, 16, i2s2_clk, wsa_swr_clk, _, _), - LPI_PINGROUP(11, 18, i2s2_ws, wsa_swr_data, _, _), - LPI_PINGROUP(12, LPI_NO_SLEW, dmic3_clk, i2s2_data, _, _), - LPI_PINGROUP(13, LPI_NO_SLEW, dmic3_data, i2s2_data, _, _), - LPI_PINGROUP(14, 6, swr_tx_data, _, _, _), -}; - -static const struct lpi_function sm8350_functions[] = { - LPI_FUNCTION(dmic1_clk), - LPI_FUNCTION(dmic1_data), - LPI_FUNCTION(dmic2_clk), - LPI_FUNCTION(dmic2_data), - LPI_FUNCTION(dmic3_clk), - LPI_FUNCTION(dmic3_data), - LPI_FUNCTION(i2s1_clk), - LPI_FUNCTION(i2s1_data), - LPI_FUNCTION(i2s1_ws), - LPI_FUNCTION(i2s2_clk), - LPI_FUNCTION(i2s2_data), - LPI_FUNCTION(i2s2_ws), - LPI_FUNCTION(qua_mi2s_data), - LPI_FUNCTION(qua_mi2s_sclk), - LPI_FUNCTION(qua_mi2s_ws), - LPI_FUNCTION(swr_rx_clk), - LPI_FUNCTION(swr_rx_data), - LPI_FUNCTION(swr_tx_clk), - LPI_FUNCTION(swr_tx_data), - LPI_FUNCTION(wsa_swr_clk), - LPI_FUNCTION(wsa_swr_data), -}; - -static const struct lpi_pinctrl_variant_data sm8350_lpi_data = { - .pins = sm8350_lpi_pins, - .npins = ARRAY_SIZE(sm8350_lpi_pins), - .groups = sm8350_groups, - .ngroups = ARRAY_SIZE(sm8350_groups), - .functions = sm8350_functions, - .nfunctions = ARRAY_SIZE(sm8350_functions), -}; - -static const struct of_device_id lpi_pinctrl_of_match[] = { - { - .compatible = "qcom,sm8350-lpass-lpi-pinctrl", - .data = &sm8350_lpi_data, - }, - { } -}; -MODULE_DEVICE_TABLE(of, lpi_pinctrl_of_match); - -static struct platform_driver lpi_pinctrl_driver = { - .driver = { - .name = "qcom-sm8350-lpass-lpi-pinctrl", - .of_match_table = lpi_pinctrl_of_match, - }, - .probe = lpi_pinctrl_probe, - .remove = lpi_pinctrl_remove, -}; -module_platform_driver(lpi_pinctrl_driver); - -MODULE_AUTHOR("Krzysztof Kozlowski "); -MODULE_DESCRIPTION("QTI SM8350 LPI GPIO pin control driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index f524af6f586f4a..c2711b2de374dd 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -359,7 +359,7 @@ struct rzg2l_pinctrl { spinlock_t bitmap_lock; /* protect tint_slot bitmap */ unsigned int hwirq[RZG2L_TINT_MAX_INTERRUPT]; - spinlock_t lock; /* lock read/write registers */ + raw_spinlock_t lock; /* lock read/write registers */ struct mutex mutex; /* serialize adding groups and functions */ struct rzg2l_pinctrl_pin_settings *settings; @@ -543,7 +543,7 @@ static void rzg2l_pinctrl_set_pfc_mode(struct rzg2l_pinctrl *pctrl, unsigned long flags; u32 reg; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); /* Set pin to 'Non-use (Hi-Z input protection)' */ reg = readw(pctrl->base + PM(off)); @@ -567,7 +567,7 @@ static void rzg2l_pinctrl_set_pfc_mode(struct rzg2l_pinctrl *pctrl, pctrl->data->pwpr_pfc_lock_unlock(pctrl, true); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); }; static int rzg2l_pinctrl_set_mux(struct pinctrl_dev *pctldev, @@ -882,10 +882,10 @@ static void rzg2l_rmw_pin_config(struct rzg2l_pinctrl *pctrl, u32 offset, addr += 4; } - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); reg = readl(addr) & ~(mask << (bit * 8)); writel(reg | (val << (bit * 8)), addr); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } static int rzg2l_caps_to_pwr_reg(const struct rzg2l_register_offsets *regs, u32 caps) @@ -1121,7 +1121,7 @@ static int rzg2l_write_oen(struct rzg2l_pinctrl *pctrl, unsigned int _pin, u8 oe if (bit < 0) return -EINVAL; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); val = readb(pctrl->base + oen_offset); if (oen) val &= ~BIT(bit); @@ -1134,7 +1134,7 @@ static int rzg2l_write_oen(struct rzg2l_pinctrl *pctrl, unsigned int _pin, u8 oe writeb(val, pctrl->base + oen_offset); if (pctrl->data->hwcfg->oen_pwpr_lock) writeb(pwpr & ~PWPR_REGWE_B, pctrl->base + regs->pwpr); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); return 0; } @@ -1687,14 +1687,14 @@ static int rzg2l_gpio_request(struct gpio_chip *chip, unsigned int offset) if (ret) return ret; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); /* Select GPIO mode in PMC Register */ reg8 = readb(pctrl->base + PMC(off)); reg8 &= ~BIT(bit); pctrl->data->pmc_writeb(pctrl, reg8, PMC(off)); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); return 0; } @@ -1709,7 +1709,7 @@ static void rzg2l_gpio_set_direction(struct rzg2l_pinctrl *pctrl, u32 offset, unsigned long flags; u16 reg16; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); reg16 = readw(pctrl->base + PM(off)); reg16 &= ~(PM_MASK << (bit * 2)); @@ -1717,7 +1717,7 @@ static void rzg2l_gpio_set_direction(struct rzg2l_pinctrl *pctrl, u32 offset, reg16 |= (output ? PM_OUTPUT : PM_INPUT) << (bit * 2); writew(reg16, pctrl->base + PM(off)); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } static int rzg2l_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) @@ -1761,7 +1761,7 @@ static int rzg2l_gpio_set(struct gpio_chip *chip, unsigned int offset, unsigned long flags; u8 reg8; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); reg8 = readb(pctrl->base + P(off)); @@ -1770,7 +1770,7 @@ static int rzg2l_gpio_set(struct gpio_chip *chip, unsigned int offset, else writeb(reg8 & ~BIT(bit), pctrl->base + P(off)); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); return 0; } @@ -2429,14 +2429,13 @@ static int rzg2l_gpio_get_gpioint(unsigned int virq, struct rzg2l_pinctrl *pctrl return gpioint; } -static void rzg2l_gpio_irq_endisable(struct rzg2l_pinctrl *pctrl, - unsigned int hwirq, bool enable) +static void __rzg2l_gpio_irq_endisable(struct rzg2l_pinctrl *pctrl, + unsigned int hwirq, bool enable) { const struct pinctrl_pin_desc *pin_desc = &pctrl->desc.pins[hwirq]; u64 *pin_data = pin_desc->drv_data; u32 off = RZG2L_PIN_CFG_TO_PORT_OFFSET(*pin_data); u8 bit = RZG2L_PIN_ID_TO_PIN(hwirq); - unsigned long flags; void __iomem *addr; addr = pctrl->base + ISEL(off); @@ -2445,12 +2444,20 @@ static void rzg2l_gpio_irq_endisable(struct rzg2l_pinctrl *pctrl, addr += 4; } - spin_lock_irqsave(&pctrl->lock, flags); if (enable) writel(readl(addr) | BIT(bit * 8), addr); else writel(readl(addr) & ~BIT(bit * 8), addr); - spin_unlock_irqrestore(&pctrl->lock, flags); +} + +static void rzg2l_gpio_irq_endisable(struct rzg2l_pinctrl *pctrl, + unsigned int hwirq, bool enable) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&pctrl->lock, flags); + __rzg2l_gpio_irq_endisable(pctrl, hwirq, enable); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } static void rzg2l_gpio_irq_disable(struct irq_data *d) @@ -2462,15 +2469,25 @@ static void rzg2l_gpio_irq_disable(struct irq_data *d) gpiochip_disable_irq(gc, hwirq); } -static void rzg2l_gpio_irq_enable(struct irq_data *d) +static void __rzg2l_gpio_irq_enable(struct irq_data *d, bool lock) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct rzg2l_pinctrl *pctrl = container_of(gc, struct rzg2l_pinctrl, gpio_chip); unsigned int hwirq = irqd_to_hwirq(d); gpiochip_enable_irq(gc, hwirq); + if (lock) + rzg2l_gpio_irq_endisable(pctrl, hwirq, true); + else + __rzg2l_gpio_irq_endisable(pctrl, hwirq, true); irq_chip_enable_parent(d); } +static void rzg2l_gpio_irq_enable(struct irq_data *d) +{ + __rzg2l_gpio_irq_enable(d, true); +} + static int rzg2l_gpio_irq_set_type(struct irq_data *d, unsigned int type) { return irq_chip_set_type_parent(d, type); @@ -2616,11 +2633,11 @@ static void rzg2l_gpio_irq_restore(struct rzg2l_pinctrl *pctrl) * This has to be atomically executed to protect against a concurrent * interrupt. */ - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); ret = rzg2l_gpio_irq_set_type(data, irqd_get_trigger_type(data)); if (!ret && !irqd_irq_disabled(data)) - rzg2l_gpio_irq_enable(data); - spin_unlock_irqrestore(&pctrl->lock, flags); + __rzg2l_gpio_irq_enable(data, false); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); if (ret) dev_crit(pctrl->dev, "Failed to set IRQ type for virq=%u\n", virq); @@ -2950,7 +2967,7 @@ static int rzg2l_pinctrl_probe(struct platform_device *pdev) "failed to enable GPIO clk\n"); } - spin_lock_init(&pctrl->lock); + raw_spin_lock_init(&pctrl->lock); spin_lock_init(&pctrl->bitmap_lock); mutex_init(&pctrl->mutex); atomic_set(&pctrl->wakeup_path, 0); @@ -2993,7 +3010,11 @@ static void rzg2l_pinctrl_pm_setup_regs(struct rzg2l_pinctrl *pctrl, bool suspen * Now cache the registers or set them in the order suggested by * HW manual (section "Operation for GPIO Function"). */ - RZG2L_PCTRL_REG_ACCESS8(suspend, pctrl->base + PMC(off), cache->pmc[port]); + if (suspend) + RZG2L_PCTRL_REG_ACCESS8(suspend, pctrl->base + PMC(off), cache->pmc[port]); + else + pctrl->data->pmc_writeb(pctrl, cache->pmc[port], PMC(off)); + if (has_iolh) { RZG2L_PCTRL_REG_ACCESS32(suspend, pctrl->base + IOLH(off), cache->iolh[0][port]); @@ -3093,7 +3114,7 @@ static void rzg2l_pinctrl_pm_setup_pfc(struct rzg2l_pinctrl *pctrl) u32 nports = pctrl->data->n_port_pins / RZG2L_PINS_PER_PORT; unsigned long flags; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); pctrl->data->pwpr_pfc_lock_unlock(pctrl, false); /* Restore port registers. */ @@ -3138,7 +3159,7 @@ static void rzg2l_pinctrl_pm_setup_pfc(struct rzg2l_pinctrl *pctrl) } pctrl->data->pwpr_pfc_lock_unlock(pctrl, true); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } static int rzg2l_pinctrl_suspend_noirq(struct device *dev) @@ -3187,14 +3208,14 @@ static int rzg2l_pinctrl_resume_noirq(struct device *dev) writeb(cache->qspi, pctrl->base + QSPI); if (pctrl->data->hwcfg->oen_pwpr_lock) { - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); pwpr = readb(pctrl->base + regs->pwpr); writeb(pwpr | PWPR_REGWE_B, pctrl->base + regs->pwpr); } writeb(cache->oen, pctrl->base + pctrl->data->hwcfg->regs.oen); if (pctrl->data->hwcfg->oen_pwpr_lock) { writeb(pwpr & ~PWPR_REGWE_B, pctrl->base + regs->pwpr); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } for (u8 i = 0; i < 2; i++) { if (regs->sd_ch) diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index 3ebb468de830db..e73feb8ac90d16 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -1671,7 +1671,7 @@ int stm32_pctl_probe(struct platform_device *pdev) if (hwlock_id == -EPROBE_DEFER) return hwlock_id; } else { - pctl->hwlock = hwspin_lock_request_specific(hwlock_id); + pctl->hwlock = devm_hwspin_lock_request_specific(dev, hwlock_id); } spin_lock_init(&pctl->irqmux_lock); diff --git a/drivers/platform/chrome/cros_ec_ishtp.c b/drivers/platform/chrome/cros_ec_ishtp.c index 4e74e702c5a24d..3766cef81fe82e 100644 --- a/drivers/platform/chrome/cros_ec_ishtp.c +++ b/drivers/platform/chrome/cros_ec_ishtp.c @@ -667,6 +667,7 @@ static void cros_ec_ishtp_remove(struct ishtp_cl_device *cl_device) cancel_work_sync(&client_data->work_ishtp_reset); cancel_work_sync(&client_data->work_ec_evt); + cros_ec_unregister(client_data->ec_dev); cros_ish_deinit(cros_ish_cl); ishtp_put_device(cl_device); } diff --git a/drivers/platform/chrome/cros_ec_lightbar.c b/drivers/platform/chrome/cros_ec_lightbar.c index 87634f6921b78a..6b028615ee245b 100644 --- a/drivers/platform/chrome/cros_ec_lightbar.c +++ b/drivers/platform/chrome/cros_ec_lightbar.c @@ -119,7 +119,7 @@ static int get_lightbar_version(struct cros_ec_dev *ec, param = (struct ec_params_lightbar *)msg->data; param->cmd = LIGHTBAR_CMD_VERSION; msg->outsize = sizeof(param->cmd); - msg->result = sizeof(resp->version); + msg->insize = sizeof(resp->version); ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); if (ret < 0 && ret != -EINVAL) { ret = 0; diff --git a/drivers/platform/chrome/cros_typec_switch.c b/drivers/platform/chrome/cros_typec_switch.c index 8d7c34abb0a128..d8a28d4e51a85e 100644 --- a/drivers/platform/chrome/cros_typec_switch.c +++ b/drivers/platform/chrome/cros_typec_switch.c @@ -230,20 +230,20 @@ static int cros_typec_register_switches(struct cros_typec_switch_data *sdata) adev = to_acpi_device_node(fwnode); if (!adev) { - dev_err(fwnode->dev, "Couldn't get ACPI device handle\n"); + dev_err(dev, "Couldn't get ACPI device handle for %pfwP\n", fwnode); ret = -ENODEV; goto err_switch; } ret = acpi_evaluate_integer(adev->handle, "_ADR", NULL, &index); if (ACPI_FAILURE(ret)) { - dev_err(fwnode->dev, "_ADR wasn't evaluated\n"); + dev_err(dev, "_ADR wasn't evaluated for %pfwP\n", fwnode); ret = -ENODATA; goto err_switch; } if (index >= EC_USB_PD_MAX_PORTS) { - dev_err(fwnode->dev, "Invalid port index number: %llu\n", index); + dev_err(dev, "%pfwP: Invalid port index number: %llu\n", fwnode, index); ret = -EINVAL; goto err_switch; } diff --git a/drivers/platform/mellanox/mlx-platform.c b/drivers/platform/mellanox/mlx-platform.c index d0df18be93c76e..efd0c074ad9375 100644 --- a/drivers/platform/mellanox/mlx-platform.c +++ b/drivers/platform/mellanox/mlx-platform.c @@ -7381,7 +7381,7 @@ static int __init mlxplat_dmi_ng400_hi171_matched(const struct dmi_system_id *dm mlxplat_hotplug = &mlxplat_mlxcpld_ng800_hi171_data; mlxplat_hotplug->deferred_nr = mlxplat_msn21xx_channels[MLXPLAT_CPLD_GRP_CHNL_NUM - 1]; - mlxplat_led = &mlxplat_default_ng_led_data; + mlxplat_led = &mlxplat_xdr_led_data; mlxplat_regs_io = &mlxplat_default_ng_regs_io_data; mlxplat_fan = &mlxplat_xdr_fan_data; diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index 16a2fd9fdd9b81..5ec1ad4716967d 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -801,18 +801,18 @@ static const struct mlxbf_pmc_events mlxbf_pmc_llt_miss_events[] = { {11, "GDC_MISS_MACHINE_CHI_TXDAT"}, {12, "GDC_MISS_MACHINE_CHI_RXDAT"}, {13, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC0_0"}, - {14, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC0_1 "}, + {14, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC0_1"}, {15, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC0_2"}, - {16, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC0_3 "}, - {17, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_0 "}, - {18, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_1 "}, - {19, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_2 "}, - {20, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_3 "}, + {16, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC0_3"}, + {17, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_0"}, + {18, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_1"}, + {19, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_2"}, + {20, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC1_3"}, {21, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE0_0"}, {22, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE0_1"}, {23, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE0_2"}, {24, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE0_3"}, - {25, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE1_0 "}, + {25, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE1_0"}, {26, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE1_1"}, {27, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE1_2"}, {28, "GDC_MISS_MACHINE_G_FIFO_FF_EXEC_DONE1_3"}, diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c index 404e62ad293a98..ed285afaf9b0d7 100644 --- a/drivers/platform/x86/amd/pmc/pmc-quirks.c +++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c @@ -302,6 +302,13 @@ static const struct dmi_system_id fwbug_list[] = { DMI_MATCH(DMI_BOARD_NAME, "XxKK4NAx_XxSP4NAx"), } }, + { + .ident = "MECHREVO Wujie 15X Pro", + .driver_data = &quirk_spurious_8042, + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "WUJIE Series-X5SP4NAG"), + } + }, {} }; diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index bc544a4a5266ee..e787480f4df26b 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -314,6 +314,61 @@ int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev) return 0; } +static int amd_pmf_reinit_ta(struct amd_pmf_dev *pdev) +{ + bool status; + int ret, i; + + for (i = 0; i < ARRAY_SIZE(amd_pmf_ta_uuid); i++) { + ret = amd_pmf_tee_init(pdev, &amd_pmf_ta_uuid[i]); + if (ret) { + dev_err(pdev->dev, "TEE init failed for UUID[%d] ret: %d\n", i, ret); + return ret; + } + + ret = amd_pmf_start_policy_engine(pdev); + dev_dbg(pdev->dev, "start policy engine ret: %d (UUID idx: %d)\n", ret, i); + status = ret == TA_PMF_TYPE_SUCCESS; + if (status) + break; + amd_pmf_tee_deinit(pdev); + } + + return 0; +} + +static int amd_pmf_restore_handler(struct device *dev) +{ + struct amd_pmf_dev *pdev = dev_get_drvdata(dev); + int ret; + + if (pdev->buf) { + ret = amd_pmf_set_dram_addr(pdev, false); + if (ret) + return ret; + } + + if (pdev->smart_pc_enabled) + amd_pmf_reinit_ta(pdev); + + return 0; +} + +static int amd_pmf_freeze_handler(struct device *dev) +{ + struct amd_pmf_dev *pdev = dev_get_drvdata(dev); + + if (!pdev->smart_pc_enabled) + return 0; + + cancel_delayed_work_sync(&pdev->pb_work); + /* Clear all TEE resources */ + amd_pmf_tee_deinit(pdev); + pdev->session_id = 0; + + return 0; +} + static int amd_pmf_suspend_handler(struct device *dev) { struct amd_pmf_dev *pdev = dev_get_drvdata(dev); @@ -347,7 +402,12 @@ static int amd_pmf_resume_handler(struct device *dev) return 0; } -static DEFINE_SIMPLE_DEV_PM_OPS(amd_pmf_pm, amd_pmf_suspend_handler, amd_pmf_resume_handler); +static const struct dev_pm_ops amd_pmf_pm = { + .suspend = amd_pmf_suspend_handler, + .resume = amd_pmf_resume_handler, + .freeze = amd_pmf_freeze_handler, + .restore = amd_pmf_restore_handler, +}; static void amd_pmf_init_features(struct amd_pmf_dev *dev) { diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h index bd19f2a6bc786b..2da1885d879151 100644 --- a/drivers/platform/x86/amd/pmf/pmf.h +++ b/drivers/platform/x86/amd/pmf/pmf.h @@ -122,6 +122,12 @@ struct cookie_header { typedef void (*apmf_event_handler_t)(acpi_handle handle, u32 event, void *data); +static const uuid_t amd_pmf_ta_uuid[] __used = { UUID_INIT(0xd9b39bf2, 0x66bd, 0x4154, 0xaf, 0xb8, + 0x8a, 0xcc, 0x2b, 0x2b, 0x60, 0xd6), + UUID_INIT(0x6fd93b77, 0x3fb8, 0x524d, 0xb1, 0x2d, + 0xc5, 0x29, 0xb1, 0x3d, 0x85, 0x43), + }; + /* APTS PMF BIOS Interface */ struct amd_pmf_apts_output { u16 table_version; @@ -888,4 +894,8 @@ void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_tab void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in); int amd_pmf_invoke_cmd_enact(struct amd_pmf_dev *dev); +int amd_pmf_tee_init(struct amd_pmf_dev *dev, const uuid_t *uuid); +void amd_pmf_tee_deinit(struct amd_pmf_dev *dev); +int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev); + #endif /* PMF_H */ diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c index 6e8116bef4f6ab..9030459352375a 100644 --- a/drivers/platform/x86/amd/pmf/tee-if.c +++ b/drivers/platform/x86/amd/pmf/tee-if.c @@ -27,12 +27,6 @@ module_param(pb_side_load, bool, 0444); MODULE_PARM_DESC(pb_side_load, "Sideload policy binaries debug policy failures"); #endif -static const uuid_t amd_pmf_ta_uuid[] = { UUID_INIT(0xd9b39bf2, 0x66bd, 0x4154, 0xaf, 0xb8, 0x8a, - 0xcc, 0x2b, 0x2b, 0x60, 0xd6), - UUID_INIT(0x6fd93b77, 0x3fb8, 0x524d, 0xb1, 0x2d, 0xc5, - 0x29, 0xb1, 0x3d, 0x85, 0x43), - }; - static const char *amd_pmf_uevent_as_str(unsigned int state) { switch (state) { @@ -312,7 +306,7 @@ static void amd_pmf_invoke_cmd(struct work_struct *work) schedule_delayed_work(&dev->pb_work, msecs_to_jiffies(pb_actions_ms)); } -static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev) +int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev) { struct cookie_header *header; int res; @@ -468,7 +462,7 @@ static int amd_pmf_register_input_device(struct amd_pmf_dev *dev) return 0; } -static int amd_pmf_tee_init(struct amd_pmf_dev *dev, const uuid_t *uuid) +int amd_pmf_tee_init(struct amd_pmf_dev *dev, const uuid_t *uuid) { u32 size; int ret; @@ -516,7 +510,7 @@ static int amd_pmf_tee_init(struct amd_pmf_dev *dev, const uuid_t *uuid) return ret; } -static void amd_pmf_tee_deinit(struct amd_pmf_dev *dev) +void amd_pmf_tee_deinit(struct amd_pmf_dev *dev) { if (!dev->tee_ctx) return; diff --git a/drivers/platform/x86/amd/wbrf.c b/drivers/platform/x86/amd/wbrf.c index dd197b3aebe06a..0f58d252b620af 100644 --- a/drivers/platform/x86/amd/wbrf.c +++ b/drivers/platform/x86/amd/wbrf.c @@ -104,8 +104,10 @@ static int wbrf_record(struct acpi_device *adev, uint8_t action, struct wbrf_ran obj = acpi_evaluate_dsm(adev->handle, &wifi_acpi_dsm_guid, WBRF_REVISION, WBRF_RECORD, &argv4); - if (!obj) + if (!obj) { + kfree(tmp); return -EINVAL; + } if (obj->type != ACPI_TYPE_INTEGER) { ret = -EINVAL; diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index e72a2b5d158e9c..8e3300f5c2943a 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -1619,14 +1619,14 @@ static void do_kbd_led_set(struct led_classdev *led_cdev, int value) kbd_led_update(asus); } -static void kbd_led_set(struct led_classdev *led_cdev, - enum led_brightness value) +static int kbd_led_set(struct led_classdev *led_cdev, enum led_brightness value) { /* Prevent disabling keyboard backlight on module unregister */ if (led_cdev->flags & LED_UNREGISTERING) - return; + return 0; do_kbd_led_set(led_cdev, value); + return 0; } static void kbd_led_set_by_kbd(struct asus_wmi *asus, enum led_brightness value) @@ -1802,7 +1802,7 @@ static int asus_wmi_led_init(struct asus_wmi *asus) asus->kbd_led_wk = led_val; asus->kbd_led.name = "asus::kbd_backlight"; asus->kbd_led.flags = LED_BRIGHT_HW_CHANGED; - asus->kbd_led.brightness_set = kbd_led_set; + asus->kbd_led.brightness_set_blocking = kbd_led_set; asus->kbd_led.brightness_get = kbd_led_get; asus->kbd_led.max_brightness = 3; diff --git a/drivers/platform/x86/classmate-laptop.c b/drivers/platform/x86/classmate-laptop.c index 6b1b8e444e241c..74d3eb83f56a63 100644 --- a/drivers/platform/x86/classmate-laptop.c +++ b/drivers/platform/x86/classmate-laptop.c @@ -207,7 +207,12 @@ static ssize_t cmpc_accel_sensitivity_show_v4(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; return sysfs_emit(buf, "%d\n", accel->sensitivity); } @@ -224,7 +229,12 @@ static ssize_t cmpc_accel_sensitivity_store_v4(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; r = kstrtoul(buf, 0, &sensitivity); if (r) @@ -256,7 +266,12 @@ static ssize_t cmpc_accel_g_select_show_v4(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; return sysfs_emit(buf, "%d\n", accel->g_select); } @@ -273,7 +288,12 @@ static ssize_t cmpc_accel_g_select_store_v4(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; r = kstrtoul(buf, 0, &g_select); if (r) @@ -302,6 +322,8 @@ static int cmpc_accel_open_v4(struct input_dev *input) acpi = to_acpi_device(input->dev.parent); accel = dev_get_drvdata(&input->dev); + if (!accel) + return -ENXIO; cmpc_accel_set_sensitivity_v4(acpi->handle, accel->sensitivity); cmpc_accel_set_g_select_v4(acpi->handle, accel->g_select); @@ -549,7 +571,12 @@ static ssize_t cmpc_accel_sensitivity_show(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; return sysfs_emit(buf, "%d\n", accel->sensitivity); } @@ -566,7 +593,12 @@ static ssize_t cmpc_accel_sensitivity_store(struct device *dev, acpi = to_acpi_device(dev); inputdev = dev_get_drvdata(&acpi->dev); + if (!inputdev) + return -ENXIO; + accel = dev_get_drvdata(&inputdev->dev); + if (!accel) + return -ENXIO; r = kstrtoul(buf, 0, &sensitivity); if (r) diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c index fadf7aac6779f7..01af6dde9057f6 100644 --- a/drivers/platform/x86/dell/alienware-wmi-wmax.c +++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c @@ -89,6 +89,30 @@ static struct awcc_quirks generic_quirks = { static struct awcc_quirks empty_quirks; static const struct dmi_system_id awcc_dmi_table[] __initconst = { + { + .ident = "Alienware 16 Area-51", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware 16 Area-51"), + }, + .driver_data = &g_series_quirks, + }, + { + .ident = "Alienware 16X Aurora", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware 16X Aurora"), + }, + .driver_data = &g_series_quirks, + }, + { + .ident = "Alienware 18 Area-51", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware 18 Area-51"), + }, + .driver_data = &g_series_quirks, + }, { .ident = "Alienware 16 Aurora", .matches = { @@ -161,6 +185,14 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = { }, .driver_data = &generic_quirks, }, + { + .ident = "Alienware x16", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware x16"), + }, + .driver_data = &g_series_quirks, + }, { .ident = "Alienware x17", .matches = { diff --git a/drivers/platform/x86/dell/dell-lis3lv02d.c b/drivers/platform/x86/dell/dell-lis3lv02d.c index 77905a9ddde9dd..fe52bcd896f78f 100644 --- a/drivers/platform/x86/dell/dell-lis3lv02d.c +++ b/drivers/platform/x86/dell/dell-lis3lv02d.c @@ -44,6 +44,7 @@ static const struct dmi_system_id lis3lv02d_devices[] __initconst = { /* * Additional individual entries were added after verification. */ + DELL_LIS3LV02D_DMI_ENTRY("Latitude 5400", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Latitude 5480", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Latitude 5500", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Latitude E6330", 0x29), diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c index 5bfa7159f5bcd5..51e8977d3eb4a8 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c +++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c @@ -10,6 +10,8 @@ #include #include #include +#include +#include #include #include "bioscfg.h" #include "../../firmware_attributes_class.h" @@ -694,6 +696,11 @@ static int hp_init_bios_package_attribute(enum hp_wmi_data_type attr_type, return ret; } + if (!str_value || !str_value[0]) { + pr_debug("Ignoring attribute with empty name\n"); + goto pack_attr_exit; + } + /* All duplicate attributes found are ignored */ duplicate = kset_find_obj(temp_kset, str_value); if (duplicate) { @@ -781,6 +788,12 @@ static int hp_init_bios_buffer_attribute(enum hp_wmi_data_type attr_type, if (ret < 0) goto buff_attr_exit; + if (strlen(str) == 0) { + pr_debug("Ignoring attribute with empty name\n"); + ret = 0; + goto buff_attr_exit; + } + if (attr_type == HPWMI_PASSWORD_TYPE || attr_type == HPWMI_SECURE_PLATFORM_TYPE) temp_kset = bioscfg_drv.authentication_dir_kset; diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.h b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.h index 3166ef328ebae8..f1eec0e4ba075b 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.h +++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.h @@ -10,6 +10,7 @@ #include #include +#include #include #include #include @@ -56,14 +57,14 @@ enum mechanism_values { #define PASSWD_MECHANISM_TYPES "password" -#define HP_WMI_BIOS_GUID "5FB7F034-2C63-45e9-BE91-3D44E2C707E4" +#define HP_WMI_BIOS_GUID "5FB7F034-2C63-45E9-BE91-3D44E2C707E4" -#define HP_WMI_BIOS_STRING_GUID "988D08E3-68F4-4c35-AF3E-6A1B8106F83C" +#define HP_WMI_BIOS_STRING_GUID "988D08E3-68F4-4C35-AF3E-6A1B8106F83C" #define HP_WMI_BIOS_INTEGER_GUID "8232DE3D-663D-4327-A8F4-E293ADB9BF05" #define HP_WMI_BIOS_ENUMERATION_GUID "2D114B49-2DFB-4130-B8FE-4A3C09E75133" #define HP_WMI_BIOS_ORDERED_LIST_GUID "14EA9746-CE1F-4098-A0E0-7045CB4DA745" #define HP_WMI_BIOS_PASSWORD_GUID "322F2028-0F84-4901-988E-015176049E2D" -#define HP_WMI_SET_BIOS_SETTING_GUID "1F4C91EB-DC5C-460b-951D-C7CB9B4B8D5E" +#define HP_WMI_SET_BIOS_SETTING_GUID "1F4C91EB-DC5C-460B-951D-C7CB9B4B8D5E" enum hp_wmi_spm_commandtype { HPWMI_SECUREPLATFORM_GET_STATE = 0x10, @@ -285,8 +286,9 @@ enum hp_wmi_data_elements { { \ int i; \ \ - for (i = 0; i <= bioscfg_drv.type##_instances_count; i++) { \ - if (!strcmp(kobj->name, bioscfg_drv.type##_data[i].attr_name_kobj->name)) \ + for (i = 0; i < bioscfg_drv.type##_instances_count; i++) { \ + if (bioscfg_drv.type##_data[i].attr_name_kobj && \ + !strcmp(kobj->name, bioscfg_drv.type##_data[i].attr_name_kobj->name)) \ return i; \ } \ return -EIO; \ diff --git a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c index c50ad58805038e..f346aad8e9d895 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c @@ -207,7 +207,7 @@ static int hp_populate_enumeration_elements_from_package(union acpi_object *enum case PREREQUISITES: size = min_t(u32, enum_data->common.prerequisites_size, MAX_PREREQUISITES_SIZE); for (reqs = 0; reqs < size; reqs++) { - if (elem >= enum_obj_count) { + if (elem + reqs >= enum_obj_count) { pr_err("Error enum-objects package is too small\n"); return -EINVAL; } @@ -255,7 +255,7 @@ static int hp_populate_enumeration_elements_from_package(union acpi_object *enum for (pos_values = 0; pos_values < size && pos_values < MAX_VALUES_SIZE; pos_values++) { - if (elem >= enum_obj_count) { + if (elem + pos_values >= enum_obj_count) { pr_err("Error enum-objects package is too small\n"); return -EINVAL; } diff --git a/drivers/platform/x86/hp/hp-bioscfg/int-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/int-attributes.c index 6c7f4d5fa9cb9c..63b1fda2be4e20 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/int-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/int-attributes.c @@ -227,7 +227,7 @@ static int hp_populate_integer_elements_from_package(union acpi_object *integer_ size = min_t(u32, integer_data->common.prerequisites_size, MAX_PREREQUISITES_SIZE); for (reqs = 0; reqs < size; reqs++) { - if (elem >= integer_obj_count) { + if (elem + reqs >= integer_obj_count) { pr_err("Error elem-objects package is too small\n"); return -EINVAL; } diff --git a/drivers/platform/x86/hp/hp-bioscfg/order-list-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/order-list-attributes.c index c6e57bb9d8b74d..6a31f47ce3f5b7 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/order-list-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/order-list-attributes.c @@ -216,6 +216,11 @@ static int hp_populate_ordered_list_elements_from_package(union acpi_object *ord size = min_t(u32, ordered_list_data->common.prerequisites_size, MAX_PREREQUISITES_SIZE); for (reqs = 0; reqs < size; reqs++) { + if (elem + reqs >= order_obj_count) { + pr_err("Error elem-objects package is too small\n"); + return -EINVAL; + } + ret = hp_convert_hexstr_to_str(order_obj[elem + reqs].string.pointer, order_obj[elem + reqs].string.length, &str_value, &value_len); diff --git a/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c index 187b372123ed39..ec79d9d50377af 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c @@ -303,6 +303,11 @@ static int hp_populate_password_elements_from_package(union acpi_object *passwor MAX_PREREQUISITES_SIZE); for (reqs = 0; reqs < size; reqs++) { + if (elem + reqs >= password_obj_count) { + pr_err("Error elem-objects package is too small\n"); + return -EINVAL; + } + ret = hp_convert_hexstr_to_str(password_obj[elem + reqs].string.pointer, password_obj[elem + reqs].string.length, &str_value, &value_len); diff --git a/drivers/platform/x86/hp/hp-bioscfg/string-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/string-attributes.c index 27758b779b2d3c..7b885d25650c52 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/string-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/string-attributes.c @@ -217,7 +217,7 @@ static int hp_populate_string_elements_from_package(union acpi_object *string_ob MAX_PREREQUISITES_SIZE); for (reqs = 0; reqs < size; reqs++) { - if (elem >= string_obj_count) { + if (elem + reqs >= string_obj_count) { pr_err("Error elem-objects package is too small\n"); return -EINVAL; } diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index ad9d9f97960f2b..dfe45692c956a2 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -53,6 +53,66 @@ MODULE_ALIAS("wmi:5FB7F034-2C63-45E9-BE91-3D44E2C707E4"); #define zero_if_sup(tmp) (zero_insize_support?0:sizeof(tmp)) // use when zero insize is required +enum hp_thermal_profile_omen_v0 { + HP_OMEN_V0_THERMAL_PROFILE_DEFAULT = 0x00, + HP_OMEN_V0_THERMAL_PROFILE_PERFORMANCE = 0x01, + HP_OMEN_V0_THERMAL_PROFILE_COOL = 0x02, +}; + +enum hp_thermal_profile_omen_v1 { + HP_OMEN_V1_THERMAL_PROFILE_DEFAULT = 0x30, + HP_OMEN_V1_THERMAL_PROFILE_PERFORMANCE = 0x31, + HP_OMEN_V1_THERMAL_PROFILE_COOL = 0x50, +}; + +enum hp_thermal_profile_omen_flags { + HP_OMEN_EC_FLAGS_TURBO = 0x04, + HP_OMEN_EC_FLAGS_NOTIMER = 0x02, + HP_OMEN_EC_FLAGS_JUSTSET = 0x01, +}; + +enum hp_thermal_profile_victus { + HP_VICTUS_THERMAL_PROFILE_DEFAULT = 0x00, + HP_VICTUS_THERMAL_PROFILE_PERFORMANCE = 0x01, + HP_VICTUS_THERMAL_PROFILE_QUIET = 0x03, +}; + +enum hp_thermal_profile_victus_s { + HP_VICTUS_S_THERMAL_PROFILE_DEFAULT = 0x00, + HP_VICTUS_S_THERMAL_PROFILE_PERFORMANCE = 0x01, +}; + +enum hp_thermal_profile { + HP_THERMAL_PROFILE_PERFORMANCE = 0x00, + HP_THERMAL_PROFILE_DEFAULT = 0x01, + HP_THERMAL_PROFILE_COOL = 0x02, + HP_THERMAL_PROFILE_QUIET = 0x03, +}; + +struct thermal_profile_params { + u8 performance; + u8 balanced; + u8 low_power; +}; + +static const struct thermal_profile_params victus_s_thermal_params = { + .performance = HP_VICTUS_S_THERMAL_PROFILE_PERFORMANCE, + .balanced = HP_VICTUS_S_THERMAL_PROFILE_DEFAULT, + .low_power = HP_VICTUS_S_THERMAL_PROFILE_DEFAULT, +}; + +static const struct thermal_profile_params omen_v1_thermal_params = { + .performance = HP_OMEN_V1_THERMAL_PROFILE_PERFORMANCE, + .balanced = HP_OMEN_V1_THERMAL_PROFILE_DEFAULT, + .low_power = HP_OMEN_V1_THERMAL_PROFILE_DEFAULT, +}; + +/* + * A generic pointer for the currently-active board's thermal profile + * parameters. + */ +static struct thermal_profile_params *active_thermal_profile_params; + /* DMI board names of devices that should use the omen specific path for * thermal profiles. * This was obtained by taking a look in the windows omen command center @@ -93,12 +153,40 @@ static const char * const victus_thermal_profile_boards[] = { }; /* DMI Board names of Victus 16-r and Victus 16-s laptops */ -static const char * const victus_s_thermal_profile_boards[] = { - "8BBE", "8BD4", "8BD5", - "8C78", "8C99", "8C9C", - "8D41", +static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst = { + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BBE") }, + .driver_data = (void *)&victus_s_thermal_params, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BD4") }, + .driver_data = (void *)&victus_s_thermal_params, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BD5") }, + .driver_data = (void *)&victus_s_thermal_params, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "8C78") }, + .driver_data = (void *)&omen_v1_thermal_params, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "8C99") }, + .driver_data = (void *)&victus_s_thermal_params, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "8C9C") }, + .driver_data = (void *)&victus_s_thermal_params, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "8D41") }, + .driver_data = (void *)&victus_s_thermal_params, + }, + {}, }; +static bool is_victus_s_board; + enum hp_wmi_radio { HPWMI_WIFI = 0x0, HPWMI_BLUETOOTH = 0x1, @@ -219,42 +307,6 @@ enum hp_wireless2_bits { HPWMI_POWER_FW_OR_HW = HPWMI_POWER_BIOS | HPWMI_POWER_HARD, }; -enum hp_thermal_profile_omen_v0 { - HP_OMEN_V0_THERMAL_PROFILE_DEFAULT = 0x00, - HP_OMEN_V0_THERMAL_PROFILE_PERFORMANCE = 0x01, - HP_OMEN_V0_THERMAL_PROFILE_COOL = 0x02, -}; - -enum hp_thermal_profile_omen_v1 { - HP_OMEN_V1_THERMAL_PROFILE_DEFAULT = 0x30, - HP_OMEN_V1_THERMAL_PROFILE_PERFORMANCE = 0x31, - HP_OMEN_V1_THERMAL_PROFILE_COOL = 0x50, -}; - -enum hp_thermal_profile_omen_flags { - HP_OMEN_EC_FLAGS_TURBO = 0x04, - HP_OMEN_EC_FLAGS_NOTIMER = 0x02, - HP_OMEN_EC_FLAGS_JUSTSET = 0x01, -}; - -enum hp_thermal_profile_victus { - HP_VICTUS_THERMAL_PROFILE_DEFAULT = 0x00, - HP_VICTUS_THERMAL_PROFILE_PERFORMANCE = 0x01, - HP_VICTUS_THERMAL_PROFILE_QUIET = 0x03, -}; - -enum hp_thermal_profile_victus_s { - HP_VICTUS_S_THERMAL_PROFILE_DEFAULT = 0x00, - HP_VICTUS_S_THERMAL_PROFILE_PERFORMANCE = 0x01, -}; - -enum hp_thermal_profile { - HP_THERMAL_PROFILE_PERFORMANCE = 0x00, - HP_THERMAL_PROFILE_DEFAULT = 0x01, - HP_THERMAL_PROFILE_COOL = 0x02, - HP_THERMAL_PROFILE_QUIET = 0x03, -}; - #define IS_HWBLOCKED(x) ((x & HPWMI_POWER_FW_OR_HW) != HPWMI_POWER_FW_OR_HW) #define IS_SWBLOCKED(x) !(x & HPWMI_POWER_SOFT) @@ -1575,15 +1627,8 @@ static int platform_profile_victus_set_ec(enum platform_profile_option profile) static bool is_victus_s_thermal_profile(void) { - const char *board_name; - - board_name = dmi_get_system_info(DMI_BOARD_NAME); - if (!board_name) - return false; - - return match_string(victus_s_thermal_profile_boards, - ARRAY_SIZE(victus_s_thermal_profile_boards), - board_name) >= 0; + /* Initialised in driver init, hence safe to use here */ + return is_victus_s_board; } static int victus_s_gpu_thermal_profile_get(bool *ctgp_enable, @@ -1666,25 +1711,30 @@ static int victus_s_set_cpu_pl1_pl2(u8 pl1, u8 pl2) static int platform_profile_victus_s_set_ec(enum platform_profile_option profile) { + struct thermal_profile_params *params; bool gpu_ctgp_enable, gpu_ppab_enable; u8 gpu_dstate; /* Test shows 1 = 100%, 2 = 50%, 3 = 25%, 4 = 12.5% */ int err, tp; + params = active_thermal_profile_params; + if (!params) + return -ENODEV; + switch (profile) { case PLATFORM_PROFILE_PERFORMANCE: - tp = HP_VICTUS_S_THERMAL_PROFILE_PERFORMANCE; + tp = params->performance; gpu_ctgp_enable = true; gpu_ppab_enable = true; gpu_dstate = 1; break; case PLATFORM_PROFILE_BALANCED: - tp = HP_VICTUS_S_THERMAL_PROFILE_DEFAULT; + tp = params->balanced; gpu_ctgp_enable = false; gpu_ppab_enable = true; gpu_dstate = 1; break; case PLATFORM_PROFILE_LOW_POWER: - tp = HP_VICTUS_S_THERMAL_PROFILE_DEFAULT; + tp = params->low_power; gpu_ctgp_enable = false; gpu_ppab_enable = false; gpu_dstate = 1; @@ -2221,6 +2271,26 @@ static int hp_wmi_hwmon_init(void) return 0; } +static void __init setup_active_thermal_profile_params(void) +{ + const struct dmi_system_id *id; + + /* + * Currently only victus_s devices use the + * active_thermal_profile_params + */ + id = dmi_first_match(victus_s_thermal_profile_boards); + if (id) { + /* + * Marking this boolean is required to ensure that + * is_victus_s_thermal_profile() behaves like a valid + * wrapper. + */ + is_victus_s_board = true; + active_thermal_profile_params = id->driver_data; + } +} + static int __init hp_wmi_init(void) { int event_capable = wmi_has_guid(HPWMI_EVENT_GUID); @@ -2248,6 +2318,11 @@ static int __init hp_wmi_init(void) goto err_destroy_input; } + /* + * Setup active board's thermal profile parameters before + * starting platform driver probe. + */ + setup_active_thermal_profile_params(); err = platform_driver_probe(&hp_wmi_driver, hp_wmi_bios_setup); if (err) goto err_unregister_device; diff --git a/drivers/platform/x86/ibm_rtl.c b/drivers/platform/x86/ibm_rtl.c index 231b3790980170..139956168cf947 100644 --- a/drivers/platform/x86/ibm_rtl.c +++ b/drivers/platform/x86/ibm_rtl.c @@ -273,7 +273,7 @@ static int __init ibm_rtl_init(void) { /* search for the _RTL_ signature at the start of the table */ for (i = 0 ; i < ebda_size/sizeof(unsigned int); i++) { struct ibm_rtl_table __iomem * tmp; - tmp = (struct ibm_rtl_table __iomem *) (ebda_map+i); + tmp = (struct ibm_rtl_table __iomem *) (ebda_map + i*sizeof(unsigned int)); if ((readq(&tmp->signature) & RTL_MASK) == RTL_SIGNATURE) { phys_addr_t addr; unsigned int plen; diff --git a/drivers/platform/x86/intel/chtwc_int33fe.c b/drivers/platform/x86/intel/chtwc_int33fe.c index 29e8b5432f4c9e..d183aa53c318ba 100644 --- a/drivers/platform/x86/intel/chtwc_int33fe.c +++ b/drivers/platform/x86/intel/chtwc_int33fe.c @@ -77,7 +77,7 @@ static const struct software_node max17047_node = { * software node. */ static struct software_node_ref_args fusb302_mux_refs[] = { - { .node = NULL }, + SOFTWARE_NODE_REFERENCE(NULL), }; static const struct property_entry fusb302_properties[] = { @@ -190,11 +190,6 @@ static void cht_int33fe_remove_nodes(struct cht_int33fe_data *data) { software_node_unregister_node_group(node_group); - if (fusb302_mux_refs[0].node) { - fwnode_handle_put(software_node_fwnode(fusb302_mux_refs[0].node)); - fusb302_mux_refs[0].node = NULL; - } - if (data->dp) { data->dp->secondary = NULL; fwnode_handle_put(data->dp); @@ -202,7 +197,15 @@ static void cht_int33fe_remove_nodes(struct cht_int33fe_data *data) } } -static int cht_int33fe_add_nodes(struct cht_int33fe_data *data) +static void cht_int33fe_put_swnode(void *data) +{ + struct fwnode_handle *fwnode = data; + + fwnode_handle_put(fwnode); + fusb302_mux_refs[0] = SOFTWARE_NODE_REFERENCE(NULL); +} + +static int cht_int33fe_add_nodes(struct device *dev, struct cht_int33fe_data *data) { const struct software_node *mux_ref_node; int ret; @@ -212,17 +215,25 @@ static int cht_int33fe_add_nodes(struct cht_int33fe_data *data) * until the mux driver has created software node for the mux device. * It means we depend on the mux driver. This function will return * -EPROBE_DEFER until the mux device is registered. + * + * FIXME: the relevant software node exists in intel-xhci-usb-role-switch + * and - if exported - could be used to set up a static reference. */ mux_ref_node = software_node_find_by_name(NULL, "intel-xhci-usb-sw"); if (!mux_ref_node) return -EPROBE_DEFER; + ret = devm_add_action_or_reset(dev, cht_int33fe_put_swnode, + software_node_fwnode(mux_ref_node)); + if (ret) + return ret; + /* * Update node used in "usb-role-switch" property. Note that we * rely on software_node_register_node_group() to use the original * instance of properties instead of copying them. */ - fusb302_mux_refs[0].node = mux_ref_node; + fusb302_mux_refs[0] = SOFTWARE_NODE_REFERENCE(mux_ref_node); ret = software_node_register_node_group(node_group); if (ret) @@ -345,7 +356,7 @@ static int cht_int33fe_typec_probe(struct platform_device *pdev) return fusb302_irq; } - ret = cht_int33fe_add_nodes(data); + ret = cht_int33fe_add_nodes(dev, data); if (ret) return ret; diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index 9c07a7faf18fee..560cc063198e10 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -177,6 +177,18 @@ static const struct dmi_system_id dmi_vgbs_allow_list[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Elite Dragonfly G2 Notebook PC"), }, }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell Pro Rugged 10 Tablet RA00260"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell Pro Rugged 12 Tablet RA02260"), + }, + }, { } }; diff --git a/drivers/platform/x86/intel/int0002_vgpio.c b/drivers/platform/x86/intel/int0002_vgpio.c index 6f5629dc3f8dbc..562e8802564367 100644 --- a/drivers/platform/x86/intel/int0002_vgpio.c +++ b/drivers/platform/x86/intel/int0002_vgpio.c @@ -206,8 +206,8 @@ static int int0002_probe(struct platform_device *pdev) * FIXME: augment this if we managed to pull handling of shared * IRQs into gpiolib. */ - ret = devm_request_irq(dev, irq, int0002_irq, - IRQF_ONESHOT | IRQF_SHARED, "INT0002", chip); + ret = devm_request_irq(dev, irq, int0002_irq, IRQF_SHARED, "INT0002", + chip); if (ret) { dev_err(dev, "Error requesting IRQ %d: %d\n", irq, ret); return ret; diff --git a/drivers/platform/x86/intel/plr_tpmi.c b/drivers/platform/x86/intel/plr_tpmi.c index 58132da4774570..05727169f49c14 100644 --- a/drivers/platform/x86/intel/plr_tpmi.c +++ b/drivers/platform/x86/intel/plr_tpmi.c @@ -316,7 +316,7 @@ static int intel_plr_probe(struct auxiliary_device *auxdev, const struct auxilia snprintf(name, sizeof(name), "domain%d", i); dentry = debugfs_create_dir(name, plr->dbgfs_dir); - debugfs_create_file("status", 0444, dentry, &plr->die_info[i], + debugfs_create_file("status", 0644, dentry, &plr->die_info[i], &plr_status_fops); } diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h index f4dadb696a3142..d6818bd34768ec 100644 --- a/drivers/platform/x86/intel/pmc/core.h +++ b/drivers/platform/x86/intel/pmc/core.h @@ -282,7 +282,7 @@ enum ppfear_regs { /* Die C6 from PUNIT telemetry */ #define MTL_PMT_DMU_DIE_C6_OFFSET 15 #define MTL_PMT_DMU_GUID 0x1A067102 -#define ARL_PMT_DMU_GUID 0x1A06A000 +#define ARL_PMT_DMU_GUID 0x1A06A102 #define LNL_PMC_MMIO_REG_LEN 0x2708 #define LNL_PMC_LTR_OSSE 0x1B88 diff --git a/drivers/platform/x86/intel/pmt/discovery.c b/drivers/platform/x86/intel/pmt/discovery.c index 32713a194a550d..e500aa327d2374 100644 --- a/drivers/platform/x86/intel/pmt/discovery.c +++ b/drivers/platform/x86/intel/pmt/discovery.c @@ -503,8 +503,10 @@ static int pmt_features_discovery(struct pmt_features_priv *priv, ret = kobject_init_and_add(&feature->kobj, ktype, &priv->dev->kobj, "%s", pmt_feature_names[feature->id]); - if (ret) + if (ret) { + kobject_put(&feature->kobj); return ret; + } kobject_uevent(&feature->kobj, KOBJ_ADD); pmt_features_add_feat(feature); @@ -546,9 +548,9 @@ static int pmt_features_probe(struct auxiliary_device *auxdev, const struct auxi priv->dev = device_create(&intel_pmt_class, &auxdev->dev, MKDEV(0, 0), priv, "%s-%s", "features", dev_name(priv->parent)); if (IS_ERR(priv->dev)) - return dev_err_probe(priv->dev, PTR_ERR(priv->dev), + return dev_err_probe(&auxdev->dev, PTR_ERR(priv->dev), "Could not create %s-%s device node\n", - "features", dev_name(priv->dev)); + "features", dev_name(priv->parent)); /* Initialize each feature */ for (i = 0; i < ivdev->num_resources; i++) { diff --git a/drivers/platform/x86/intel/telemetry/debugfs.c b/drivers/platform/x86/intel/telemetry/debugfs.c index 70e5736c44c71a..189c61ff7ff0c0 100644 --- a/drivers/platform/x86/intel/telemetry/debugfs.c +++ b/drivers/platform/x86/intel/telemetry/debugfs.c @@ -449,7 +449,7 @@ static int telem_pss_states_show(struct seq_file *s, void *unused) for (index = 0; index < debugfs_conf->pss_ltr_evts; index++) { seq_printf(s, "%-32s\t%u\n", debugfs_conf->pss_ltr_data[index].name, - pss_s0ix_wakeup[index]); + pss_ltr_blkd[index]); } seq_puts(s, "\n--------------------------------------\n"); @@ -459,7 +459,7 @@ static int telem_pss_states_show(struct seq_file *s, void *unused) for (index = 0; index < debugfs_conf->pss_wakeup_evts; index++) { seq_printf(s, "%-32s\t%u\n", debugfs_conf->pss_wakeup[index].name, - pss_ltr_blkd[index]); + pss_s0ix_wakeup[index]); } return 0; diff --git a/drivers/platform/x86/intel/telemetry/pltdrv.c b/drivers/platform/x86/intel/telemetry/pltdrv.c index f23c170a55dc67..d9aa349f81e412 100644 --- a/drivers/platform/x86/intel/telemetry/pltdrv.c +++ b/drivers/platform/x86/intel/telemetry/pltdrv.c @@ -610,7 +610,7 @@ static int telemetry_setup(struct platform_device *pdev) /* Get telemetry Info */ events = (read_buf & TELEM_INFO_SRAMEVTS_MASK) >> TELEM_INFO_SRAMEVTS_SHIFT; - event_regs = read_buf & TELEM_INFO_SRAMEVTS_MASK; + event_regs = read_buf & TELEM_INFO_NENABLES_MASK; if ((events < TELEM_MAX_EVENTS_SRAM) || (event_regs < TELEM_MAX_EVENTS_SRAM)) { dev_err(&pdev->dev, "PSS:Insufficient Space for SRAM Trace\n"); diff --git a/drivers/platform/x86/lenovo/wmi-gamezone.c b/drivers/platform/x86/lenovo/wmi-gamezone.c index 0eb7fe8222f4ae..b26806b37d960f 100644 --- a/drivers/platform/x86/lenovo/wmi-gamezone.c +++ b/drivers/platform/x86/lenovo/wmi-gamezone.c @@ -274,8 +274,23 @@ static const struct dmi_system_id fwbug_list[] = { }, .driver_data = &quirk_no_extreme_bug, }, + { + .ident = "Legion Go 8ASP2", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Legion Go 8ASP2"), + }, + .driver_data = &quirk_no_extreme_bug, + }, + { + .ident = "Legion Go 8AHP2", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Legion Go 8AHP2"), + }, + .driver_data = &quirk_no_extreme_bug, + }, {}, - }; /** diff --git a/drivers/platform/x86/msi-laptop.c b/drivers/platform/x86/msi-laptop.c index c4b150fa093fef..ddef6b78d2fa9f 100644 --- a/drivers/platform/x86/msi-laptop.c +++ b/drivers/platform/x86/msi-laptop.c @@ -1130,6 +1130,9 @@ static void __exit msi_cleanup(void) sysfs_remove_group(&msipf_device->dev.kobj, &msipf_attribute_group); if (!quirks->old_ec_model && threeg_exists) device_remove_file(&msipf_device->dev, &dev_attr_threeg); + if (quirks->old_ec_model) + sysfs_remove_group(&msipf_device->dev.kobj, + &msipf_old_attribute_group); platform_device_unregister(msipf_device); platform_driver_unregister(&msipf_driver); backlight_device_unregister(msibl_device); diff --git a/drivers/platform/x86/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c index 255317e6fec881..937f1a5b78edfb 100644 --- a/drivers/platform/x86/panasonic-laptop.c +++ b/drivers/platform/x86/panasonic-laptop.c @@ -1089,7 +1089,7 @@ static int acpi_pcc_hotkey_add(struct acpi_device *device) PLATFORM_DEVID_NONE, NULL, 0); if (IS_ERR(pcc->platform)) { result = PTR_ERR(pcc->platform); - goto out_backlight; + goto out_sysfs; } result = device_create_file(&pcc->platform->dev, &dev_attr_cdpower); @@ -1105,6 +1105,8 @@ static int acpi_pcc_hotkey_add(struct acpi_device *device) out_platform: platform_device_unregister(pcc->platform); +out_sysfs: + sysfs_remove_group(&device->dev.kobj, &pcc_attr_group); out_backlight: backlight_device_unregister(pcc->backlight); out_input: diff --git a/drivers/platform/x86/samsung-galaxybook.c b/drivers/platform/x86/samsung-galaxybook.c index 3c13e13d488584..755cb82bdb606b 100644 --- a/drivers/platform/x86/samsung-galaxybook.c +++ b/drivers/platform/x86/samsung-galaxybook.c @@ -442,12 +442,13 @@ static int galaxybook_battery_ext_property_get(struct power_supply *psy, union power_supply_propval *val) { struct samsung_galaxybook *galaxybook = ext_data; + u8 value; int err; if (psp != POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD) return -EINVAL; - err = charge_control_end_threshold_acpi_get(galaxybook, (u8 *)&val->intval); + err = charge_control_end_threshold_acpi_get(galaxybook, &value); if (err) return err; @@ -455,8 +456,10 @@ static int galaxybook_battery_ext_property_get(struct power_supply *psy, * device stores "no end threshold" as 0 instead of 100; * if device has 0, report 100 */ - if (val->intval == 0) - val->intval = 100; + if (value == 0) + value = 100; + + val->intval = value; return 0; } diff --git a/drivers/platform/x86/toshiba_haps.c b/drivers/platform/x86/toshiba_haps.c index 03dfddeee0c0af..e9324bf16aea4b 100644 --- a/drivers/platform/x86/toshiba_haps.c +++ b/drivers/platform/x86/toshiba_haps.c @@ -183,7 +183,7 @@ static int toshiba_haps_add(struct acpi_device *acpi_dev) pr_info("Toshiba HDD Active Protection Sensor device\n"); - haps = kzalloc(sizeof(struct toshiba_haps_dev), GFP_KERNEL); + haps = devm_kzalloc(&acpi_dev->dev, sizeof(*haps), GFP_KERNEL); if (!haps) return -ENOMEM; diff --git a/drivers/pmdomain/apple/pmgr-pwrstate.c b/drivers/pmdomain/apple/pmgr-pwrstate.c index 82c33cf727a825..a92db8cf88bb90 100644 --- a/drivers/pmdomain/apple/pmgr-pwrstate.c +++ b/drivers/pmdomain/apple/pmgr-pwrstate.c @@ -21,7 +21,8 @@ #define APPLE_PMGR_AUTO_ENABLE BIT(28) #define APPLE_PMGR_PS_AUTO GENMASK(27, 24) #define APPLE_PMGR_PS_MIN GENMASK(19, 16) -#define APPLE_PMGR_PARENT_OFF BIT(11) +#define APPLE_PMGR_PS_RESET BIT(12) +#define APPLE_PMGR_BUSY BIT(11) #define APPLE_PMGR_DEV_DISABLE BIT(10) #define APPLE_PMGR_WAS_CLKGATED BIT(9) #define APPLE_PMGR_WAS_PWRGATED BIT(8) @@ -44,6 +45,9 @@ struct apple_pmgr_ps { struct regmap *regmap; u32 offset; u32 min_state; + bool force_disable; + bool force_reset; + bool externally_clocked; }; #define genpd_to_apple_pmgr_ps(_genpd) container_of(_genpd, struct apple_pmgr_ps, genpd) @@ -53,7 +57,7 @@ static int apple_pmgr_ps_set(struct generic_pm_domain *genpd, u32 pstate, bool a { int ret; struct apple_pmgr_ps *ps = genpd_to_apple_pmgr_ps(genpd); - u32 reg; + u32 reg, cur; ret = regmap_read(ps->regmap, ps->offset, ®); if (ret < 0) @@ -64,24 +68,57 @@ static int apple_pmgr_ps_set(struct generic_pm_domain *genpd, u32 pstate, bool a dev_err(ps->dev, "PS %s: powering off with RESET active\n", genpd->name); - reg &= ~(APPLE_PMGR_AUTO_ENABLE | APPLE_PMGR_FLAGS | APPLE_PMGR_PS_TARGET); + if (pstate != APPLE_PMGR_PS_ACTIVE && (ps->force_disable || ps->force_reset)) { + u32 reg_pre = reg & ~(APPLE_PMGR_AUTO_ENABLE | APPLE_PMGR_FLAGS); + + if (ps->force_disable) + reg_pre |= APPLE_PMGR_DEV_DISABLE; + if (ps->force_reset) + reg_pre |= APPLE_PMGR_PS_RESET; + + regmap_write(ps->regmap, ps->offset, reg_pre); + + ret = regmap_read_poll_timeout_atomic( + ps->regmap, ps->offset, cur, + (cur & (APPLE_PMGR_DEV_DISABLE | APPLE_PMGR_PS_RESET)) == + (reg_pre & (APPLE_PMGR_DEV_DISABLE | APPLE_PMGR_PS_RESET)), 1, + APPLE_PMGR_PS_SET_TIMEOUT); + + if (ret < 0) + dev_err(ps->dev, "PS %s: Failed to set reset/disable bits (now: 0x%x)\n", + genpd->name, reg); + } + + reg &= ~(APPLE_PMGR_DEV_DISABLE | APPLE_PMGR_PS_RESET | + APPLE_PMGR_AUTO_ENABLE | APPLE_PMGR_FLAGS | APPLE_PMGR_PS_TARGET); reg |= FIELD_PREP(APPLE_PMGR_PS_TARGET, pstate); dev_dbg(ps->dev, "PS %s: pwrstate = 0x%x: 0x%x\n", genpd->name, pstate, reg); regmap_write(ps->regmap, ps->offset, reg); - ret = regmap_read_poll_timeout_atomic( - ps->regmap, ps->offset, reg, - (FIELD_GET(APPLE_PMGR_PS_ACTUAL, reg) == pstate), 1, - APPLE_PMGR_PS_SET_TIMEOUT); + if (ps->externally_clocked && pstate == APPLE_PMGR_PS_ACTIVE) { + /* + * If this clock domain requires an external clock, then + * consider the "clock gated" state to be good enough. + */ + ret = regmap_read_poll_timeout_atomic( + ps->regmap, ps->offset, cur, + FIELD_GET(APPLE_PMGR_PS_ACTUAL, cur) >= APPLE_PMGR_PS_CLKGATE, 1, + APPLE_PMGR_PS_SET_TIMEOUT); + } else { + ret = regmap_read_poll_timeout_atomic( + ps->regmap, ps->offset, cur, + FIELD_GET(APPLE_PMGR_PS_ACTUAL, cur) == pstate, 1, + APPLE_PMGR_PS_SET_TIMEOUT); + } + if (ret < 0) dev_err(ps->dev, "PS %s: Failed to reach power state 0x%x (now: 0x%x)\n", genpd->name, pstate, reg); if (auto_enable) { /* Not all devices implement this; this is a no-op where not implemented. */ - reg &= ~APPLE_PMGR_FLAGS; reg |= APPLE_PMGR_AUTO_ENABLE; regmap_write(ps->regmap, ps->offset, reg); } @@ -234,6 +271,15 @@ static int apple_pmgr_ps_probe(struct platform_device *pdev) regmap_update_bits(regmap, ps->offset, APPLE_PMGR_FLAGS | APPLE_PMGR_PS_MIN, FIELD_PREP(APPLE_PMGR_PS_MIN, ps->min_state)); + if (of_property_read_bool(node, "apple,force-disable")) + ps->force_disable = true; + + if (of_property_read_bool(node, "apple,force-reset")) + ps->force_reset = true; + + if (of_property_read_bool(node, "apple,externally-clocked")) + ps->externally_clocked = true; + active = apple_pmgr_ps_is_active(ps); if (of_property_read_bool(node, "apple,always-on")) { ps->genpd.flags |= GENPD_FLAG_ALWAYS_ON; @@ -242,6 +288,8 @@ static int apple_pmgr_ps_probe(struct platform_device *pdev) /* Turn it on so pm_genpd_init does not fail */ active = apple_pmgr_ps_power_on(&ps->genpd) == 0; } + } else if (active) { + ps->genpd.flags |= GENPD_FLAG_DEFER_OFF | GENPD_FLAG_ACTIVE_WAKEUP; } /* Turn on auto-PM if the domain is already on */ diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c index 61c2277c9ce39f..c45006e7a880a4 100644 --- a/drivers/pmdomain/core.c +++ b/drivers/pmdomain/core.c @@ -7,6 +7,7 @@ #define pr_fmt(fmt) "PM: " fmt #include +#include #include #include #include @@ -188,6 +189,7 @@ static const struct genpd_lock_ops genpd_raw_spin_ops = { #define genpd_is_dev_name_fw(genpd) (genpd->flags & GENPD_FLAG_DEV_NAME_FW) #define genpd_is_no_sync_state(genpd) (genpd->flags & GENPD_FLAG_NO_SYNC_STATE) #define genpd_is_no_stay_on(genpd) (genpd->flags & GENPD_FLAG_NO_STAY_ON) +#define genpd_is_defer_off(genpd) (genpd->flags & GENPD_FLAG_DEFER_OFF) static inline bool irq_safe_dev_in_sleep_domain(struct device *dev, const struct generic_pm_domain *genpd) @@ -941,6 +943,27 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd) queue_work(pm_wq, &genpd->power_off_work); } +/** + * genpd_must_defer - Check whether the genpd cannot be safely powered off. + * @genpd: PM domain about to be powered down. + * @one_dev_probing: True if we are being called from RPM callbacks on a device that + * is probing, to allow poweroff if that device is the sole remaining consumer probing. + * + * Returns true if the @genpd has the GENPD_FLAG_DEFER_OFF flag and there + * are any consumer devices which either do not exist yet (only represented + * by fwlinks) or whose drivers have not probed yet. + */ +static bool genpd_must_defer(struct generic_pm_domain *genpd, bool one_dev_probing) +{ + if (genpd_is_defer_off(genpd) && genpd->has_provider) { + int absent = fw_devlink_count_absent_consumers(genpd->provider); + + if (absent > (one_dev_probing ? 1 : 0)) + return true; + } + return false; +} + /** * genpd_power_off - Remove power from a given PM domain. * @genpd: PM domain to power down. @@ -954,7 +977,7 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd) * have been powered down, remove power from @genpd. */ static void genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on, - unsigned int depth) + bool one_dev_probing, unsigned int depth) { struct pm_domain_data *pdd; struct gpd_link *link; @@ -1002,6 +1025,14 @@ static void genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on, if (not_suspended > 1 || (not_suspended == 1 && !one_dev_on)) return; + /* + * Do not allow PM domain to be powered off if it is marked + * as GENPD_FLAG_DEFER_OFF and there are consumer devices + * which have not probed yet. + */ + if (genpd_must_defer(genpd, one_dev_probing)) + return; + if (genpd->gov && genpd->gov->power_down_ok) { if (!genpd->gov->power_down_ok(&genpd->domain)) return; @@ -1027,7 +1058,7 @@ static void genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on, list_for_each_entry(link, &genpd->child_links, child_node) { genpd_sd_counter_dec(link->parent); genpd_lock_nested(link->parent, depth + 1); - genpd_power_off(link->parent, false, depth + 1); + genpd_power_off(link->parent, false, false, depth + 1); genpd_unlock(link->parent); } } @@ -1086,7 +1117,7 @@ static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth) child_node) { genpd_sd_counter_dec(link->parent); genpd_lock_nested(link->parent, depth + 1); - genpd_power_off(link->parent, false, depth + 1); + genpd_power_off(link->parent, false, false, depth + 1); genpd_unlock(link->parent); } @@ -1153,7 +1184,7 @@ static void genpd_power_off_work_fn(struct work_struct *work) genpd = container_of(work, struct generic_pm_domain, power_off_work); genpd_lock(genpd); - genpd_power_off(genpd, false, 0); + genpd_power_off(genpd, false, false, 0); genpd_unlock(genpd); } @@ -1218,6 +1249,7 @@ static int genpd_runtime_suspend(struct device *dev) struct generic_pm_domain_data *gpd_data = dev_gpd_data(dev); struct gpd_timing_data *td = gpd_data->td; bool runtime_pm = pm_runtime_enabled(dev); + bool probing = dev->links.status != DL_DEV_DRIVER_BOUND; ktime_t time_start = 0; s64 elapsed_ns; int ret; @@ -1272,7 +1304,7 @@ static int genpd_runtime_suspend(struct device *dev) return 0; genpd_lock(genpd); - genpd_power_off(genpd, true, 0); + genpd_power_off(genpd, true, probing, 0); gpd_data->rpm_pstate = genpd_drop_performance_state(dev); genpd_unlock(genpd); @@ -1293,6 +1325,7 @@ static int genpd_runtime_resume(struct device *dev) struct generic_pm_domain_data *gpd_data = dev_gpd_data(dev); struct gpd_timing_data *td = gpd_data->td; bool timed = td && pm_runtime_enabled(dev); + bool probing = dev->links.status != DL_DEV_DRIVER_BOUND; ktime_t time_start = 0; s64 elapsed_ns; int ret; @@ -1350,7 +1383,7 @@ static int genpd_runtime_resume(struct device *dev) err_poweroff: if (!pm_runtime_is_irq_safe(dev) || genpd_is_irq_safe(genpd)) { genpd_lock(genpd); - genpd_power_off(genpd, true, 0); + genpd_power_off(genpd, true, probing, 0); gpd_data->rpm_pstate = genpd_drop_performance_state(dev); genpd_unlock(genpd); } @@ -1418,6 +1451,9 @@ static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock, || atomic_read(&genpd->sd_count) > 0) return; + if (genpd_must_defer(genpd, false)) + return; + /* Check that the children are in their deepest (powered-off) state. */ list_for_each_entry(link, &genpd->parent_links, parent_node) { struct generic_pm_domain *child = link->child; @@ -2437,6 +2473,12 @@ int pm_genpd_init(struct generic_pm_domain *genpd, return -EINVAL; } + /* Deferred-off power domains should be powered on at initialization. */ + if (genpd_is_defer_off(genpd) && !genpd_status_on(genpd)) { + pr_warn("deferred-off PM domain %s is not on at init\n", genpd->name); + genpd->flags &= ~GENPD_FLAG_DEFER_OFF; + } + /* Multiple states but no governor doesn't make sense. */ if (!gov && genpd->state_count > 1) pr_warn("%s: no governor for states\n", genpd->name); @@ -3503,7 +3545,7 @@ void of_genpd_sync_state(struct device_node *np) if (genpd->provider == of_fwnode_handle(np)) { genpd_lock(genpd); genpd->stay_on = false; - genpd_power_off(genpd, false, 0); + genpd_power_off(genpd, false, false, 0); genpd_unlock(genpd); } } @@ -3531,7 +3573,7 @@ static void genpd_provider_sync_state(struct device *dev) case GENPD_SYNC_STATE_SIMPLE: genpd_lock(genpd); genpd->stay_on = false; - genpd_power_off(genpd, false, 0); + genpd_power_off(genpd, false, false, 0); genpd_unlock(genpd); break; diff --git a/drivers/pmdomain/imx/gpc.c b/drivers/pmdomain/imx/gpc.c index a34b260274f7bd..de695f1944ab31 100644 --- a/drivers/pmdomain/imx/gpc.c +++ b/drivers/pmdomain/imx/gpc.c @@ -402,13 +402,12 @@ static int imx_gpc_old_dt_init(struct device *dev, struct regmap *regmap, static int imx_gpc_probe(struct platform_device *pdev) { const struct imx_gpc_dt_data *of_id_data = device_get_match_data(&pdev->dev); - struct device_node *pgc_node; + struct device_node *pgc_node __free(device_node) + = of_get_child_by_name(pdev->dev.of_node, "pgc"); struct regmap *regmap; void __iomem *base; int ret; - pgc_node = of_get_child_by_name(pdev->dev.of_node, "pgc"); - /* bail out if DT too old and doesn't provide the necessary info */ if (!of_property_present(pdev->dev.of_node, "#power-domain-cells") && !pgc_node) diff --git a/drivers/pmdomain/imx/gpcv2.c b/drivers/pmdomain/imx/gpcv2.c index 105fcaf13a34c7..cff738e4d54622 100644 --- a/drivers/pmdomain/imx/gpcv2.c +++ b/drivers/pmdomain/imx/gpcv2.c @@ -165,13 +165,11 @@ #define IMX8M_VPU_HSK_PWRDNREQN BIT(5) #define IMX8M_DISP_HSK_PWRDNREQN BIT(4) -#define IMX8MM_GPUMIX_HSK_PWRDNACKN BIT(29) -#define IMX8MM_GPU_HSK_PWRDNACKN (BIT(27) | BIT(28)) +#define IMX8MM_GPU_HSK_PWRDNACKN GENMASK(29, 27) #define IMX8MM_VPUMIX_HSK_PWRDNACKN BIT(26) #define IMX8MM_DISPMIX_HSK_PWRDNACKN BIT(25) #define IMX8MM_HSIO_HSK_PWRDNACKN (BIT(23) | BIT(24)) -#define IMX8MM_GPUMIX_HSK_PWRDNREQN BIT(11) -#define IMX8MM_GPU_HSK_PWRDNREQN (BIT(9) | BIT(10)) +#define IMX8MM_GPU_HSK_PWRDNREQN GENMASK(11, 9) #define IMX8MM_VPUMIX_HSK_PWRDNREQN BIT(8) #define IMX8MM_DISPMIX_HSK_PWRDNREQN BIT(7) #define IMX8MM_HSIO_HSK_PWRDNREQN (BIT(5) | BIT(6)) @@ -794,8 +792,6 @@ static const struct imx_pgc_domain imx8mm_pgc_domains[] = { .bits = { .pxx = IMX8MM_GPUMIX_SW_Pxx_REQ, .map = IMX8MM_GPUMIX_A53_DOMAIN, - .hskreq = IMX8MM_GPUMIX_HSK_PWRDNREQN, - .hskack = IMX8MM_GPUMIX_HSK_PWRDNACKN, }, .pgc = BIT(IMX8MM_PGC_GPUMIX), .keep_clocks = true, diff --git a/drivers/pmdomain/imx/imx8m-blk-ctrl.c b/drivers/pmdomain/imx/imx8m-blk-ctrl.c index 5c83e5599f1ea6..19e992d2ee3b84 100644 --- a/drivers/pmdomain/imx/imx8m-blk-ctrl.c +++ b/drivers/pmdomain/imx/imx8m-blk-ctrl.c @@ -340,7 +340,7 @@ static void imx8m_blk_ctrl_remove(struct platform_device *pdev) of_genpd_del_provider(pdev->dev.of_node); - for (i = 0; bc->onecell_data.num_domains; i++) { + for (i = 0; i < bc->onecell_data.num_domains; i++) { struct imx8m_blk_ctrl_domain *domain = &bc->domains[i]; pm_genpd_remove(&domain->genpd); @@ -846,22 +846,25 @@ static int imx8mq_vpu_power_notifier(struct notifier_block *nb, return NOTIFY_OK; } +/* + * For i.MX8MQ, the ADB in the VPUMIX domain has no separate reset and clock + * enable bits, but is ungated and reset together with the VPUs. + * Resetting G1 or G2 separately may led to system hang. + * Remove the rst_mask and clk_mask from the domain data of G1 and G2, + * Let imx8mq_vpu_power_notifier() do really vpu reset. + */ static const struct imx8m_blk_ctrl_domain_data imx8mq_vpu_blk_ctl_domain_data[] = { [IMX8MQ_VPUBLK_PD_G1] = { .name = "vpublk-g1", .clk_names = (const char *[]){ "g1", }, .num_clks = 1, .gpc_name = "g1", - .rst_mask = BIT(1), - .clk_mask = BIT(1), }, [IMX8MQ_VPUBLK_PD_G2] = { .name = "vpublk-g2", .clk_names = (const char *[]){ "g2", }, .num_clks = 1, .gpc_name = "g2", - .rst_mask = BIT(0), - .clk_mask = BIT(0), }, }; diff --git a/drivers/pmdomain/imx/imx8mp-blk-ctrl.c b/drivers/pmdomain/imx/imx8mp-blk-ctrl.c index 34576be606e31a..8fc79f9723f07e 100644 --- a/drivers/pmdomain/imx/imx8mp-blk-ctrl.c +++ b/drivers/pmdomain/imx/imx8mp-blk-ctrl.c @@ -53,6 +53,7 @@ struct imx8mp_blk_ctrl_domain_data { const char * const *path_names; int num_paths; const char *gpc_name; + const unsigned int flags; }; #define DOMAIN_MAX_CLKS 3 @@ -65,6 +66,7 @@ struct imx8mp_blk_ctrl_domain { struct icc_bulk_data paths[DOMAIN_MAX_PATHS]; struct device *power_dev; struct imx8mp_blk_ctrl *bc; + struct notifier_block power_nb; int num_paths; int id; }; @@ -264,10 +266,12 @@ static const struct imx8mp_blk_ctrl_domain_data imx8mp_hsio_domain_data[] = { [IMX8MP_HSIOBLK_PD_USB_PHY1] = { .name = "hsioblk-usb-phy1", .gpc_name = "usb-phy1", + .flags = GENPD_FLAG_ACTIVE_WAKEUP, }, [IMX8MP_HSIOBLK_PD_USB_PHY2] = { .name = "hsioblk-usb-phy2", .gpc_name = "usb-phy2", + .flags = GENPD_FLAG_ACTIVE_WAKEUP, }, [IMX8MP_HSIOBLK_PD_PCIE] = { .name = "hsioblk-pcie", @@ -594,6 +598,20 @@ static int imx8mp_blk_ctrl_power_off(struct generic_pm_domain *genpd) return 0; } +static int imx8mp_blk_ctrl_gpc_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct imx8mp_blk_ctrl_domain *domain = + container_of(nb, struct imx8mp_blk_ctrl_domain, power_nb); + + if (action == GENPD_NOTIFY_PRE_OFF) { + if (domain->genpd.status == GENPD_STATE_ON) + return NOTIFY_BAD; + } + + return NOTIFY_OK; +} + static struct lock_class_key blk_ctrl_genpd_lock_class; static int imx8mp_blk_ctrl_probe(struct platform_device *pdev) @@ -698,15 +716,25 @@ static int imx8mp_blk_ctrl_probe(struct platform_device *pdev) goto cleanup_pds; } + domain->power_nb.notifier_call = imx8mp_blk_ctrl_gpc_notifier; + ret = dev_pm_genpd_add_notifier(domain->power_dev, &domain->power_nb); + if (ret) { + dev_err_probe(dev, ret, "failed to add power notifier\n"); + dev_pm_domain_detach(domain->power_dev, true); + goto cleanup_pds; + } + domain->genpd.name = data->name; domain->genpd.power_on = imx8mp_blk_ctrl_power_on; domain->genpd.power_off = imx8mp_blk_ctrl_power_off; + domain->genpd.flags = data->flags; domain->bc = bc; domain->id = i; ret = pm_genpd_init(&domain->genpd, NULL, true); if (ret) { dev_err_probe(dev, ret, "failed to init power domain\n"); + dev_pm_genpd_remove_notifier(domain->power_dev); dev_pm_domain_detach(domain->power_dev, true); goto cleanup_pds; } @@ -755,6 +783,7 @@ static int imx8mp_blk_ctrl_probe(struct platform_device *pdev) cleanup_pds: for (i--; i >= 0; i--) { pm_genpd_remove(&bc->domains[i].genpd); + dev_pm_genpd_remove_notifier(bc->domains[i].power_dev); dev_pm_domain_detach(bc->domains[i].power_dev, true); } @@ -774,6 +803,7 @@ static void imx8mp_blk_ctrl_remove(struct platform_device *pdev) struct imx8mp_blk_ctrl_domain *domain = &bc->domains[i]; pm_genpd_remove(&domain->genpd); + dev_pm_genpd_remove_notifier(domain->power_dev); dev_pm_domain_detach(domain->power_dev, true); } diff --git a/drivers/pmdomain/mediatek/mtk-pm-domains.c b/drivers/pmdomain/mediatek/mtk-pm-domains.c index 9c9323c8c93a70..269634bcd9a407 100644 --- a/drivers/pmdomain/mediatek/mtk-pm-domains.c +++ b/drivers/pmdomain/mediatek/mtk-pm-domains.c @@ -748,18 +748,6 @@ static void scpsys_domain_cleanup(struct scpsys *scpsys) } } -static struct device_node *scpsys_get_legacy_regmap(struct device_node *np, const char *pn) -{ - struct device_node *local_node; - - for_each_child_of_node(np, local_node) { - if (of_property_present(local_node, pn)) - return local_node; - } - - return NULL; -} - static int scpsys_get_bus_protection_legacy(struct device *dev, struct scpsys *scpsys) { const u8 bp_blocks[3] = { @@ -781,7 +769,8 @@ static int scpsys_get_bus_protection_legacy(struct device *dev, struct scpsys *s * this makes it then possible to allocate the array of bus_prot * regmaps and convert all to the new style handling. */ - node = scpsys_get_legacy_regmap(np, "mediatek,infracfg"); + of_node_get(np); + node = of_find_node_with_property(np, "mediatek,infracfg"); if (node) { regmap[0] = syscon_regmap_lookup_by_phandle(node, "mediatek,infracfg"); of_node_put(node); @@ -794,7 +783,8 @@ static int scpsys_get_bus_protection_legacy(struct device *dev, struct scpsys *s regmap[0] = NULL; } - node = scpsys_get_legacy_regmap(np, "mediatek,smi"); + of_node_get(np); + node = of_find_node_with_property(np, "mediatek,smi"); if (node) { smi_np = of_parse_phandle(node, "mediatek,smi", 0); of_node_put(node); @@ -812,7 +802,8 @@ static int scpsys_get_bus_protection_legacy(struct device *dev, struct scpsys *s regmap[1] = NULL; } - node = scpsys_get_legacy_regmap(np, "mediatek,infracfg-nao"); + of_node_get(np); + node = of_find_node_with_property(np, "mediatek,infracfg-nao"); if (node) { regmap[2] = syscon_regmap_lookup_by_phandle(node, "mediatek,infracfg-nao"); num_regmaps++; diff --git a/drivers/pmdomain/qcom/rpmhpd.c b/drivers/pmdomain/qcom/rpmhpd.c index 4faa8a25618621..4c3cbf3abc7504 100644 --- a/drivers/pmdomain/qcom/rpmhpd.c +++ b/drivers/pmdomain/qcom/rpmhpd.c @@ -246,6 +246,8 @@ static struct rpmhpd *sa8540p_rpmhpds[] = { [SC8280XP_MMCX_AO] = &mmcx_ao, [SC8280XP_MX] = &mx, [SC8280XP_MX_AO] = &mx_ao, + [SC8280XP_MXC] = &mxc, + [SC8280XP_MXC_AO] = &mxc_ao, [SC8280XP_NSP] = &nsp, }; @@ -675,6 +677,8 @@ static struct rpmhpd *sc8280xp_rpmhpds[] = { [SC8280XP_MMCX_AO] = &mmcx_ao, [SC8280XP_MX] = &mx, [SC8280XP_MX_AO] = &mx_ao, + [SC8280XP_MXC] = &mxc, + [SC8280XP_MXC_AO] = &mxc_ao, [SC8280XP_NSP] = &nsp, [SC8280XP_QPHY] = &qphy, }; diff --git a/drivers/pmdomain/qcom/rpmpd.c b/drivers/pmdomain/qcom/rpmpd.c index f8580ec0f73785..98ab4f9ea9bff4 100644 --- a/drivers/pmdomain/qcom/rpmpd.c +++ b/drivers/pmdomain/qcom/rpmpd.c @@ -1001,7 +1001,7 @@ static int rpmpd_aggregate_corner(struct rpmpd *pd) /* Clamp to the highest corner/level if sync_state isn't done yet */ if (!pd->state_synced) - this_active_corner = this_sleep_corner = pd->max_state - 1; + this_active_corner = this_sleep_corner = pd->max_state; else to_active_sleep(pd, pd->corner, &this_active_corner, &this_sleep_corner); diff --git a/drivers/pmdomain/rockchip/pm-domains.c b/drivers/pmdomain/rockchip/pm-domains.c index 1955c6d453e4f6..5baaa6beb21011 100644 --- a/drivers/pmdomain/rockchip/pm-domains.c +++ b/drivers/pmdomain/rockchip/pm-domains.c @@ -861,6 +861,16 @@ static int rockchip_pm_add_one_domain(struct rockchip_pmu *pmu, pd->genpd.name = pd->info->name; else pd->genpd.name = kbasename(node->full_name); + + /* + * power domain's needing a regulator should default to off, since + * the regulator state is unknown at probe time. Also the regulator + * state cannot be checked, since that usually requires IP needing + * (a different) power domain. + */ + if (pd->info->need_regulator) + rockchip_pd_power(pd, false); + pd->genpd.power_off = rockchip_pd_power_off; pd->genpd.power_on = rockchip_pd_power_on; pd->genpd.attach_dev = rockchip_pd_attach_dev; diff --git a/drivers/power/reset/macsmc-reboot.c b/drivers/power/reset/macsmc-reboot.c index e9702acdd366b0..94fcbf12fe3b93 100644 --- a/drivers/power/reset/macsmc-reboot.c +++ b/drivers/power/reset/macsmc-reboot.c @@ -205,6 +205,14 @@ static int macsmc_reboot_probe(struct platform_device *pdev) struct macsmc_reboot *reboot; int ret, i; + /* + * MFD will probe this device even without a node in the device tree, + * thus bail out early if the SMC on the current machines does not + * support reboot and has no node in the device tree. + */ + if (!pdev->dev.of_node) + return -ENODEV; + reboot = devm_kzalloc(&pdev->dev, sizeof(*reboot), GFP_KERNEL); if (!reboot) return -ENOMEM; diff --git a/drivers/power/reset/nvmem-reboot-mode.c b/drivers/power/reset/nvmem-reboot-mode.c index 41530b70cfc48c..d260715fccf67f 100644 --- a/drivers/power/reset/nvmem-reboot-mode.c +++ b/drivers/power/reset/nvmem-reboot-mode.c @@ -10,6 +10,7 @@ #include #include #include +#include struct nvmem_reboot_mode { struct reboot_mode_driver reboot; @@ -19,12 +20,22 @@ struct nvmem_reboot_mode { static int nvmem_reboot_mode_write(struct reboot_mode_driver *reboot, unsigned int magic) { - int ret; struct nvmem_reboot_mode *nvmem_rbm; + size_t buf_len; + void *buf; + int ret; nvmem_rbm = container_of(reboot, struct nvmem_reboot_mode, reboot); - ret = nvmem_cell_write(nvmem_rbm->cell, &magic, sizeof(magic)); + buf = nvmem_cell_read(nvmem_rbm->cell, &buf_len); + if (IS_ERR(buf)) + return PTR_ERR(buf); + kfree(buf); + + if (buf_len > sizeof(magic)) + return -EINVAL; + + ret = nvmem_cell_write(nvmem_rbm->cell, &magic, buf_len); if (ret < 0) dev_err(reboot->dev, "update reboot mode bits failed\n"); diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig index dca4be23ee7095..aa2a1119cb6b7e 100644 --- a/drivers/power/supply/Kconfig +++ b/drivers/power/supply/Kconfig @@ -1097,4 +1097,11 @@ config FUEL_GAUGE_MM8013 the state of charge, temperature, cycle count, actual and design capacity, etc. +config CHARGER_MACSMC + tristate "Apple SMC Charger / Battery support" + depends on MFD_MACSMC + help + Say Y here to enable support for the charger and battery controls on + Apple SMC controllers, as used on Apple Silicon Macs. + endif # POWER_SUPPLY diff --git a/drivers/power/supply/Makefile b/drivers/power/supply/Makefile index 99a820d38197cd..9a9b3bb54e4f0b 100644 --- a/drivers/power/supply/Makefile +++ b/drivers/power/supply/Makefile @@ -79,6 +79,7 @@ obj-$(CONFIG_CHARGER_GPIO) += gpio-charger.o obj-$(CONFIG_CHARGER_MANAGER) += charger-manager.o obj-$(CONFIG_CHARGER_LT3651) += lt3651-charger.o obj-$(CONFIG_CHARGER_LTC4162L) += ltc4162-l-charger.o +obj-$(CONFIG_CHARGER_MACSMC) += macsmc-power.o obj-$(CONFIG_CHARGER_MAX14577) += max14577_charger.o obj-$(CONFIG_CHARGER_DETECTOR_MAX14656) += max14656_charger_detector.o obj-$(CONFIG_CHARGER_MAX77650) += max77650-charger.o diff --git a/drivers/power/supply/ab8500_charger.c b/drivers/power/supply/ab8500_charger.c index 5f4537766e5b90..1813fbdfa1c1f6 100644 --- a/drivers/power/supply/ab8500_charger.c +++ b/drivers/power/supply/ab8500_charger.c @@ -3466,26 +3466,6 @@ static int ab8500_charger_probe(struct platform_device *pdev) return ret; } - /* Request interrupts */ - for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) { - irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name); - if (irq < 0) - return irq; - - ret = devm_request_threaded_irq(dev, - irq, NULL, ab8500_charger_irq[i].isr, - IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT, - ab8500_charger_irq[i].name, di); - - if (ret != 0) { - dev_err(dev, "failed to request %s IRQ %d: %d\n" - , ab8500_charger_irq[i].name, irq, ret); - return ret; - } - dev_dbg(dev, "Requested %s IRQ %d: %d\n", - ab8500_charger_irq[i].name, irq, ret); - } - /* initialize lock */ spin_lock_init(&di->usb_state.usb_lock); mutex_init(&di->usb_ipt_crnt_lock); @@ -3614,6 +3594,26 @@ static int ab8500_charger_probe(struct platform_device *pdev) return PTR_ERR(di->usb_chg.psy); } + /* Request interrupts */ + for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) { + irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name); + if (irq < 0) + return irq; + + ret = devm_request_threaded_irq(dev, + irq, NULL, ab8500_charger_irq[i].isr, + IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT, + ab8500_charger_irq[i].name, di); + + if (ret != 0) { + dev_err(dev, "failed to request %s IRQ %d: %d\n" + , ab8500_charger_irq[i].name, irq, ret); + return ret; + } + dev_dbg(dev, "Requested %s IRQ %d: %d\n", + ab8500_charger_irq[i].name, irq, ret); + } + /* * Check what battery we have, since we always have the USB * psy, use that as a handle. diff --git a/drivers/power/supply/act8945a_charger.c b/drivers/power/supply/act8945a_charger.c index 3901a02f326a55..9dec4486b1439a 100644 --- a/drivers/power/supply/act8945a_charger.c +++ b/drivers/power/supply/act8945a_charger.c @@ -597,14 +597,6 @@ static int act8945a_charger_probe(struct platform_device *pdev) return irq ?: -ENXIO; } - ret = devm_request_irq(&pdev->dev, irq, act8945a_status_changed, - IRQF_TRIGGER_FALLING, "act8945a_interrupt", - charger); - if (ret) { - dev_err(&pdev->dev, "failed to request nIRQ pin IRQ\n"); - return ret; - } - charger->desc.name = "act8945a-charger"; charger->desc.get_property = act8945a_charger_get_property; charger->desc.properties = act8945a_charger_props; @@ -625,6 +617,14 @@ static int act8945a_charger_probe(struct platform_device *pdev) return PTR_ERR(charger->psy); } + ret = devm_request_irq(&pdev->dev, irq, act8945a_status_changed, + IRQF_TRIGGER_FALLING, "act8945a_interrupt", + charger); + if (ret) { + dev_err(&pdev->dev, "failed to request nIRQ pin IRQ\n"); + return ret; + } + platform_set_drvdata(pdev, charger); INIT_WORK(&charger->work, act8945a_work); diff --git a/drivers/power/supply/apm_power.c b/drivers/power/supply/apm_power.c index 9236e007857860..9933cdc5c387a1 100644 --- a/drivers/power/supply/apm_power.c +++ b/drivers/power/supply/apm_power.c @@ -364,7 +364,8 @@ static int __init apm_battery_init(void) static void __exit apm_battery_exit(void) { - apm_get_power_status = NULL; + if (apm_get_power_status == apm_battery_apm_get_power_status) + apm_get_power_status = NULL; } module_init(apm_battery_init); diff --git a/drivers/power/supply/bq256xx_charger.c b/drivers/power/supply/bq256xx_charger.c index ae14162f017a9e..d3de4f8b80db1e 100644 --- a/drivers/power/supply/bq256xx_charger.c +++ b/drivers/power/supply/bq256xx_charger.c @@ -1741,6 +1741,12 @@ static int bq256xx_probe(struct i2c_client *client) usb_register_notifier(bq->usb3_phy, &bq->usb_nb); } + ret = bq256xx_power_supply_init(bq, &psy_cfg, dev); + if (ret) { + dev_err(dev, "Failed to register power supply\n"); + return ret; + } + if (client->irq) { ret = devm_request_threaded_irq(dev, client->irq, NULL, bq256xx_irq_handler_thread, @@ -1753,12 +1759,6 @@ static int bq256xx_probe(struct i2c_client *client) } } - ret = bq256xx_power_supply_init(bq, &psy_cfg, dev); - if (ret) { - dev_err(dev, "Failed to register power supply\n"); - return ret; - } - ret = bq256xx_hw_init(bq); if (ret) { dev_err(dev, "Cannot initialize the chip.\n"); diff --git a/drivers/power/supply/bq25980_charger.c b/drivers/power/supply/bq25980_charger.c index 723858d62d1414..73f06f09f134cd 100644 --- a/drivers/power/supply/bq25980_charger.c +++ b/drivers/power/supply/bq25980_charger.c @@ -1241,6 +1241,12 @@ static int bq25980_probe(struct i2c_client *client) return ret; } + ret = bq25980_power_supply_init(bq, dev); + if (ret) { + dev_err(dev, "Failed to register power supply\n"); + return ret; + } + if (client->irq) { ret = devm_request_threaded_irq(dev, client->irq, NULL, bq25980_irq_handler_thread, @@ -1251,12 +1257,6 @@ static int bq25980_probe(struct i2c_client *client) return ret; } - ret = bq25980_power_supply_init(bq, dev); - if (ret) { - dev_err(dev, "Failed to register power supply\n"); - return ret; - } - ret = bq25980_hw_init(bq); if (ret) { dev_err(dev, "Cannot initialize the chip.\n"); diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 19445e39651c71..45f0e39b8c2dd4 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1172,7 +1172,7 @@ static inline int bq27xxx_write(struct bq27xxx_device_info *di, int reg_index, return -EINVAL; if (!di->bus.write) - return -EPERM; + return -EOPNOTSUPP; ret = di->bus.write(di, di->regs[reg_index], value, single); if (ret < 0) @@ -1191,7 +1191,7 @@ static inline int bq27xxx_read_block(struct bq27xxx_device_info *di, int reg_ind return -EINVAL; if (!di->bus.read_bulk) - return -EPERM; + return -EOPNOTSUPP; ret = di->bus.read_bulk(di, di->regs[reg_index], data, len); if (ret < 0) @@ -1210,7 +1210,7 @@ static inline int bq27xxx_write_block(struct bq27xxx_device_info *di, int reg_in return -EINVAL; if (!di->bus.write_bulk) - return -EPERM; + return -EOPNOTSUPP; ret = di->bus.write_bulk(di, di->regs[reg_index], data, len); if (ret < 0) diff --git a/drivers/power/supply/cpcap-battery.c b/drivers/power/supply/cpcap-battery.c index 8106d1edcbc26a..507fdc1c866d56 100644 --- a/drivers/power/supply/cpcap-battery.c +++ b/drivers/power/supply/cpcap-battery.c @@ -1122,10 +1122,6 @@ static int cpcap_battery_probe(struct platform_device *pdev) platform_set_drvdata(pdev, ddata); - error = cpcap_battery_init_interrupts(pdev, ddata); - if (error) - return error; - error = cpcap_battery_init_iio(ddata); if (error) return error; @@ -1142,6 +1138,10 @@ static int cpcap_battery_probe(struct platform_device *pdev) return error; } + error = cpcap_battery_init_interrupts(pdev, ddata); + if (error) + return error; + atomic_set(&ddata->active, 1); error = cpcap_battery_calibrate(ddata); diff --git a/drivers/power/supply/cw2015_battery.c b/drivers/power/supply/cw2015_battery.c index 2263d5d3448fdf..0806abea2372fe 100644 --- a/drivers/power/supply/cw2015_battery.c +++ b/drivers/power/supply/cw2015_battery.c @@ -699,7 +699,13 @@ static int cw_bat_probe(struct i2c_client *client) if (!cw_bat->battery_workqueue) return -ENOMEM; - devm_delayed_work_autocancel(&client->dev, &cw_bat->battery_delay_work, cw_bat_work); + ret = devm_delayed_work_autocancel(&client->dev, &cw_bat->battery_delay_work, cw_bat_work); + if (ret) { + dev_err_probe(&client->dev, ret, + "Failed to register delayed work\n"); + return ret; + } + queue_delayed_work(cw_bat->battery_workqueue, &cw_bat->battery_delay_work, msecs_to_jiffies(10)); return 0; diff --git a/drivers/power/supply/goldfish_battery.c b/drivers/power/supply/goldfish_battery.c index 479195e35d734a..5aa24e4dc4455d 100644 --- a/drivers/power/supply/goldfish_battery.c +++ b/drivers/power/supply/goldfish_battery.c @@ -224,12 +224,6 @@ static int goldfish_battery_probe(struct platform_device *pdev) if (data->irq < 0) return -ENODEV; - ret = devm_request_irq(&pdev->dev, data->irq, - goldfish_battery_interrupt, - IRQF_SHARED, pdev->name, data); - if (ret) - return ret; - psy_cfg.drv_data = data; data->ac = devm_power_supply_register(&pdev->dev, @@ -244,6 +238,12 @@ static int goldfish_battery_probe(struct platform_device *pdev) if (IS_ERR(data->battery)) return PTR_ERR(data->battery); + ret = devm_request_irq(&pdev->dev, data->irq, + goldfish_battery_interrupt, + IRQF_SHARED, pdev->name, data); + if (ret) + return ret; + GOLDFISH_BATTERY_WRITE(data, BATTERY_INT_ENABLE, BATTERY_INT_MASK); return 0; } diff --git a/drivers/power/supply/macsmc-power.c b/drivers/power/supply/macsmc-power.c new file mode 100644 index 00000000000000..dc3ec5ef2b81cf --- /dev/null +++ b/drivers/power/supply/macsmc-power.c @@ -0,0 +1,1053 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Apple SMC Power/Battery Management + * Copyright The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define MAX_STRING_LENGTH 256 + +/* + * This number is not reported anywhere by SMC, but seems to be a good + * conversion factor for charge to energy across machines. We need this + * to convert in the driver, since if we don't userspace will try to do + * the conversion with a randomly guessed voltage and get it wrong. + * + * Ideally there would be a power supply prop to inform userspace of this + * number, but there isn't, only min/max. + */ +#define MACSMC_NOMINAL_CELL_VOLTAGE_MV 3800 + +struct macsmc_power { + struct device *dev; + struct apple_smc *smc; + struct power_supply_desc ac_desc; + struct power_supply_desc batt_desc; + + struct power_supply *batt; + char model_name[MAX_STRING_LENGTH]; + char serial_number[MAX_STRING_LENGTH]; + char mfg_date[MAX_STRING_LENGTH]; + + bool has_chwa; + bool has_chls; + bool has_ch0i; + bool has_ch0c; + bool has_chte; + + u8 num_cells; + int nominal_voltage_mv; + + struct power_supply *ac; + + struct notifier_block nb; + + struct work_struct critical_work; + bool shutdown_started; + + struct delayed_work dbg_log_work; +}; + +static int macsmc_log_power_set(const char *val, const struct kernel_param *kp); + +static const struct kernel_param_ops macsmc_log_power_ops = { + .set = macsmc_log_power_set, + .get = param_get_bool, +}; + +static bool log_power = false; +module_param_cb(log_power, &macsmc_log_power_ops, &log_power, 0644); +MODULE_PARM_DESC(log_power, "Periodically log power consumption for debugging"); + +#define POWER_LOG_INTERVAL (HZ) + +static struct macsmc_power *g_power; + +#define CHNC_BATTERY_FULL BIT(0) +#define CHNC_NO_CHARGER BIT(7) +#define CHNC_NOCHG_CH0C BIT(14) +#define CHNC_NOCHG_CH0B_CH0K BIT(15) +#define CHNC_BATTERY_FULL_2 BIT(18) +#define CHNC_BMS_BUSY BIT(23) +#define CHNC_CHLS_LIMIT BIT(24) +#define CHNC_NOAC_CH0J BIT(53) +#define CHNC_NOAC_CH0I BIT(54) + +#define CH0R_LOWER_FLAGS GENMASK(15, 0) +#define CH0R_NOAC_CH0I BIT(0) +#define CH0R_NOAC_DISCONNECTED BIT(4) +#define CH0R_NOAC_CH0J BIT(5) +#define CH0R_BMS_BUSY BIT(8) +#define CH0R_NOAC_CH0K BIT(9) +#define CH0R_NOAC_CHWA BIT(11) + +#define CH0X_CH0C BIT(0) +#define CH0X_CH0B BIT(1) + +#define ACSt_CAN_BOOT_AP BIT(2) +#define ACSt_CAN_BOOT_IBOOT BIT(1) + +#define CHWA_CHLS_FIXED_START_OFFSET 5 +#define CHLS_MIN_END_THRESHOLD 10 +#define CHLS_FORCE_DISCHARGE 0x100 +#define CHWA_FIXED_END_THRESHOLD 80 +#define CHWA_PROP_WRITE_THRESHOLD 95 + +#define FLT_EXP_BIAS 127 +#define FLT_EXP_MASK GENMASK(30, 23) +#define FLT_MANT_BIAS 23 +#define FLT_MANT_MASK GENMASK(22, 0) +#define FLT_SIGN_MASK BIT(31) +/* + * Many sensors report their data as IEEE-754 floats. No other SMC function uses + * them. + */ +static int apple_smc_read_f32_scaled(struct apple_smc *smc, smc_key key, + int *p, int scale) +{ + u32 fval; + u64 val; + int ret, exp; + + BUILD_BUG_ON(scale <= 0); + + ret = apple_smc_read_u32(smc, key, &fval); + if (ret < 0) + return ret; + + val = ((u64)((fval & FLT_MANT_MASK) | BIT(23))); + exp = ((fval >> 23) & 0xff) - FLT_EXP_BIAS - FLT_MANT_BIAS; + val *= scale; + + if (exp > 63) + val = U64_MAX; + else if (exp < -63) + val = 0; + else if (exp < 0) + val >>= -exp; + else if (exp != 0 && (val & ~((1UL << (64 - exp)) - 1))) /* overflow */ + val = U64_MAX; + else + val <<= exp; + + if (fval & FLT_SIGN_MASK) { + if (val > (-(s64)INT_MIN)) + *p = INT_MIN; + else + *p = -val; + } else { + if (val > INT_MAX) + *p = INT_MAX; + else + *p = val; + } + + return 0; +} + +static void macsmc_do_dbg(struct macsmc_power *power) +{ + int p_in = 0, p_sys = 0, p_3v8 = 0, p_mpmu = 0, p_spmu = 0, p_clvr = 0, p_cpu = 0; + s32 p_bat = 0; + s16 t_full = 0, t_empty = 0; + u8 charge = 0; + + apple_smc_read_f32_scaled(power->smc, SMC_KEY(PDTR), &p_in, 1000); + apple_smc_read_f32_scaled(power->smc, SMC_KEY(PSTR), &p_sys, 1000); + apple_smc_read_f32_scaled(power->smc, SMC_KEY(PMVR), &p_3v8, 1000); + apple_smc_read_f32_scaled(power->smc, SMC_KEY(PHPC), &p_cpu, 1000); + apple_smc_read_f32_scaled(power->smc, SMC_KEY(PSVR), &p_clvr, 1000); + apple_smc_read_f32_scaled(power->smc, SMC_KEY(PPMC), &p_mpmu, 1000); + apple_smc_read_f32_scaled(power->smc, SMC_KEY(PPSC), &p_spmu, 1000); + apple_smc_read_s32(power->smc, SMC_KEY(B0AP), &p_bat); + apple_smc_read_s16(power->smc, SMC_KEY(B0TE), &t_empty); + apple_smc_read_s16(power->smc, SMC_KEY(B0TF), &t_full); + apple_smc_read_u8(power->smc, SMC_KEY(BUIC), &charge); + +#define FD3(x) ((x) / 1000), abs((x) % 1000) + dev_info(power->dev, + "In %2d.%03dW Sys %2d.%03dW 3V8 %2d.%03dW MPMU %2d.%03dW SPMU %2d.%03dW " + "CLVR %2d.%03dW CPU %2d.%03dW Batt %2d.%03dW %d%% T%s %dm\n", + FD3(p_in), FD3(p_sys), FD3(p_3v8), FD3(p_mpmu), FD3(p_spmu), FD3(p_clvr), + FD3(p_cpu), FD3(p_bat), charge, + t_full >= 0 ? "full" : "empty", + t_full >= 0 ? t_full : t_empty); +#undef FD3 +} + +static int macsmc_battery_get_status(struct macsmc_power *power) +{ + u64 nocharge_flags; + u32 nopower_flags; + u16 ac_current; + int charge_limit = 0; + bool limited = false; + bool flag; + int ret; + + /* + * Note: there are fallbacks in case some of these SMC keys disappear in the future + * or are not present on some machines. We treat the absence of the CHCE/CHCC/BSFC/CHSC + * flags as an error, since they are quite fundamental and simple booleans. + */ + + /* + * If power input is inhibited, we are definitely discharging. + * However, if the only reason is the BMS is doing a balancing cycle, + * go ahead and ignore that one to avoid spooking users. + */ + ret = apple_smc_read_u32(power->smc, SMC_KEY(CH0R), &nopower_flags); + if (!ret && (nopower_flags & CH0R_LOWER_FLAGS & ~CH0R_BMS_BUSY)) + return POWER_SUPPLY_STATUS_DISCHARGING; + + /* If no charger is present, we are definitely discharging. */ + ret = apple_smc_read_flag(power->smc, SMC_KEY(CHCE), &flag); + if (ret < 0) + return ret; + if (!flag) + return POWER_SUPPLY_STATUS_DISCHARGING; + + /* If AC is not charge capable, we are definitely discharging. */ + ret = apple_smc_read_flag(power->smc, SMC_KEY(CHCC), &flag); + if (ret < 0) + return ret; + if (!flag) + return POWER_SUPPLY_STATUS_DISCHARGING; + + /* + * If the AC input current limit is tiny or 0, we are discharging no matter + * how much the BMS believes it can charge. + */ + ret = apple_smc_read_u16(power->smc, SMC_KEY(AC-i), &ac_current); + if (!ret && ac_current < 100) + return POWER_SUPPLY_STATUS_DISCHARGING; + + /* If the battery is full, report it as such. */ + ret = apple_smc_read_flag(power->smc, SMC_KEY(BSFC), &flag); + if (ret < 0) + return ret; + if (flag) + return POWER_SUPPLY_STATUS_FULL; + + /* + * If we have charge limits supported and enabled and the SoC is above + * the start threshold, that means we are not charging for that reason + * (if not charging). + */ + if (power->has_chls) { + u16 vu16; + + ret = apple_smc_read_u16(power->smc, SMC_KEY(CHLS), &vu16); + if (ret == sizeof(vu16) && (vu16 & 0xff) >= CHLS_MIN_END_THRESHOLD) + charge_limit = (vu16 & 0xff) - CHWA_CHLS_FIXED_START_OFFSET; + } else if (power->has_chwa) { + ret = apple_smc_read_flag(power->smc, SMC_KEY(CHWA), &flag); + if (ret == 0 && flag) + charge_limit = CHWA_FIXED_END_THRESHOLD - CHWA_CHLS_FIXED_START_OFFSET; + } + + if (charge_limit > 0) { + u8 buic = 0; + + if (apple_smc_read_u8(power->smc, SMC_KEY(BUIC), &buic) >= 0 && + buic >= charge_limit) + limited = true; + } + + /* If there are reasons we aren't charging... */ + ret = apple_smc_read_u64(power->smc, SMC_KEY(CHNC), &nocharge_flags); + if (!ret) { + /* Perhaps the battery is full after all */ + if (nocharge_flags & CHNC_BATTERY_FULL) + return POWER_SUPPLY_STATUS_FULL; + /* + * Or maybe the BMS is just busy doing something, if so call it charging anyway. + * But CHWA limits show up as this, so exclude those. + */ + else if (nocharge_flags == CHNC_BMS_BUSY && !limited) + return POWER_SUPPLY_STATUS_CHARGING; + /* If we have other reasons we aren't charging, say we aren't */ + else if (nocharge_flags) + return POWER_SUPPLY_STATUS_NOT_CHARGING; + /* Else we're either charging or about to charge */ + else + return POWER_SUPPLY_STATUS_CHARGING; + } + + /* As a fallback, use the system charging flag. */ + ret = apple_smc_read_flag(power->smc, SMC_KEY(CHSC), &flag); + if (ret < 0) + return ret; + if (!flag) + return POWER_SUPPLY_STATUS_NOT_CHARGING; + else + return POWER_SUPPLY_STATUS_CHARGING; +} + +static int macsmc_battery_get_charge_behaviour(struct macsmc_power *power) +{ + int ret; + u8 val8; + u8 chte_buf[4]; + + if (power->has_ch0i) { + /* CH0I returns a bitmask like the low byte of CH0R */ + ret = apple_smc_read_u8(power->smc, SMC_KEY(CH0I), &val8); + if (ret) + return ret; + if (val8 & CH0R_NOAC_CH0I) + return POWER_SUPPLY_CHARGE_BEHAVIOUR_FORCE_DISCHARGE; + } + + /* Prefer CHTE available in newer firmwares */ + if (power->has_chte) { + ret = apple_smc_read(power->smc, SMC_KEY(CHTE), chte_buf, 4); + if (ret < 0) + return ret; + + if (chte_buf[0] == 0x01) + return POWER_SUPPLY_CHARGE_BEHAVIOUR_INHIBIT_CHARGE; + + } else if (power->has_ch0c) { + /* CH0C returns a bitmask containing CH0B/CH0C flags */ + ret = apple_smc_read_u8(power->smc, SMC_KEY(CH0C), &val8); + if (ret) + return ret; + if (val8 & CH0X_CH0C) + return POWER_SUPPLY_CHARGE_BEHAVIOUR_INHIBIT_CHARGE; + } + + return POWER_SUPPLY_CHARGE_BEHAVIOUR_AUTO; +} + +static int macsmc_battery_set_charge_behaviour(struct macsmc_power *power, int val) +{ + int ret; + + /* + * apple_smc_write_u32 does weird things with endianess, + * so we write raw bytes to ensure correctness of CHTE + */ + u8 chte_inhibit[4] = {0x01, 0x00, 0x00, 0x00}; + u8 chte_auto[4] = {0x00, 0x00, 0x00, 0x00}; + + /* + * CH0I/CH0C/CHTE are "hard" controls that will allow the battery to run down to 0. + * CH0K/CH0B are "soft" controls that are reset to 0 when SOC drops below 50%; + * we don't expose these yet. + */ + + switch (val) { + case POWER_SUPPLY_CHARGE_BEHAVIOUR_AUTO: + if (power->has_ch0i) { + ret = apple_smc_write_u8(power->smc, SMC_KEY(CH0I), 0); + if (ret) + return ret; + } + + if (power->has_chte) { + ret = apple_smc_write(power->smc, SMC_KEY(CHTE), chte_auto, 4); + if (ret) + return ret; + } else if (power->has_ch0c) { + ret = apple_smc_write_u8(power->smc, SMC_KEY(CH0C), 0); + if (ret) + return ret; + } + break; + + case POWER_SUPPLY_CHARGE_BEHAVIOUR_INHIBIT_CHARGE: + if (power->has_ch0i) { + ret = apple_smc_write_u8(power->smc, SMC_KEY(CH0I), 0); + if (ret) + return ret; + } + + /* Prefer CHTE available in newer firmwares */ + if (power->has_chte) + return apple_smc_write(power->smc, SMC_KEY(CHTE), chte_inhibit, 4); + else if (power->has_ch0c) + return apple_smc_write_u8(power->smc, SMC_KEY(CH0C), 1); + else + return -EINVAL; + break; + + case POWER_SUPPLY_CHARGE_BEHAVIOUR_FORCE_DISCHARGE: + if (!power->has_ch0i) + return -EINVAL; + + /* Prefer CHTE available in newer firmwares */ + if (power->has_chte) { + ret = apple_smc_write(power->smc, SMC_KEY(CHTE), chte_auto, 4); + if (ret) + return ret; + } else if (power->has_ch0c) { + ret = apple_smc_write_u8(power->smc, SMC_KEY(CH0C), 0); + if (ret) + return ret; + } + + return apple_smc_write_u8(power->smc, SMC_KEY(CH0I), 1); + + default: + return -EINVAL; + } + + return 0; +} + +static int macsmc_battery_get_date(const char *s, int *out) +{ + if (!isdigit(s[0]) || !isdigit(s[1])) + return -ENOTSUPP; + + *out = (s[0] - '0') * 10 + s[1] - '0'; + return 0; +} + +static int macsmc_battery_get_capacity_level(struct macsmc_power *power) +{ + bool flag; + u32 val; + int ret; + + /* Check for emergency shutdown condition */ + if (apple_smc_read_u32(power->smc, SMC_KEY(BCF0), &val) >= 0 && val) + return POWER_SUPPLY_CAPACITY_LEVEL_CRITICAL; + + /* Check AC status for whether we could boot in this state */ + if (apple_smc_read_u32(power->smc, SMC_KEY(ACSt), &val) >= 0) { + if (!(val & ACSt_CAN_BOOT_IBOOT)) + return POWER_SUPPLY_CAPACITY_LEVEL_CRITICAL; + + if (!(val & ACSt_CAN_BOOT_AP)) + return POWER_SUPPLY_CAPACITY_LEVEL_LOW; + } + + /* Check battery full flag */ + ret = apple_smc_read_flag(power->smc, SMC_KEY(BSFC), &flag); + if (ret < 0) + return POWER_SUPPLY_CAPACITY_LEVEL_UNKNOWN; + if (flag) + return POWER_SUPPLY_CAPACITY_LEVEL_FULL; + else + return POWER_SUPPLY_CAPACITY_LEVEL_NORMAL; +} + +static int macsmc_battery_get_property(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) +{ + struct macsmc_power *power = power_supply_get_drvdata(psy); + int ret = 0; + u8 vu8; + u16 vu16; + s16 vs16; + s32 vs32; + s64 vs64; + bool flag; + + switch (psp) { + case POWER_SUPPLY_PROP_STATUS: + val->intval = macsmc_battery_get_status(power); + ret = val->intval < 0 ? val->intval : 0; + break; + case POWER_SUPPLY_PROP_PRESENT: + val->intval = 1; + break; + case POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR: + val->intval = macsmc_battery_get_charge_behaviour(power); + ret = val->intval < 0 ? val->intval : 0; + break; + case POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0TE), &vu16); + val->intval = vu16 == 0xffff ? 0 : vu16 * 60; + break; + case POWER_SUPPLY_PROP_TIME_TO_FULL_NOW: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0TF), &vu16); + val->intval = vu16 == 0xffff ? 0 : vu16 * 60; + break; + case POWER_SUPPLY_PROP_CAPACITY: + ret = apple_smc_read_u8(power->smc, SMC_KEY(BUIC), &vu8); + val->intval = vu8; + break; + case POWER_SUPPLY_PROP_CAPACITY_LEVEL: + val->intval = macsmc_battery_get_capacity_level(power); + ret = val->intval < 0 ? val->intval : 0; + break; + case POWER_SUPPLY_PROP_VOLTAGE_NOW: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0AV), &vu16); + val->intval = vu16 * 1000; + break; + case POWER_SUPPLY_PROP_CURRENT_NOW: + ret = apple_smc_read_s16(power->smc, SMC_KEY(B0AC), &vs16); + val->intval = vs16 * 1000; + break; + case POWER_SUPPLY_PROP_POWER_NOW: + ret = apple_smc_read_s32(power->smc, SMC_KEY(B0AP), &vs32); + val->intval = vs32 * 1000; + break; + case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: + ret = apple_smc_read_u16(power->smc, SMC_KEY(BITV), &vu16); + val->intval = vu16 * 1000; + break; + case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN: + /* + * Battery cell max voltage? BVV* seem to return per-cell voltages, + * BVV[NOP] are probably the max voltages for the 3 cells but we don't + * know what will happen if they ever change the number of cells. + * So go with BVVN and multiply by the cell count (BNCB). + * BVVL seems to be the per-cell limit adjusted dynamically. + * Guess: BVVL = Limit, BVVN = Nominal, and the other cells got filled + * in around nearby letters? + */ + ret = apple_smc_read_u16(power->smc, SMC_KEY(BVVN), &vu16); + val->intval = vu16 * 1000 * power->num_cells; + break; + case POWER_SUPPLY_PROP_VOLTAGE_MIN: + /* Lifetime min */ + ret = apple_smc_read_s16(power->smc, SMC_KEY(BLPM), &vs16); + val->intval = vs16 * 1000; + break; + case POWER_SUPPLY_PROP_VOLTAGE_MAX: + /* Lifetime max */ + ret = apple_smc_read_s16(power->smc, SMC_KEY(BLPX), &vs16); + val->intval = vs16 * 1000; + break; + case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0RC), &vu16); + val->intval = vu16 * 1000; + break; + case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0RI), &vu16); + val->intval = vu16 * 1000; + break; + case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0RV), &vu16); + val->intval = vu16 * 1000; + break; + case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0DC), &vu16); + val->intval = vu16 * 1000; + break; + case POWER_SUPPLY_PROP_CHARGE_FULL: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0FC), &vu16); + val->intval = vu16 * 1000; + break; + case POWER_SUPPLY_PROP_CHARGE_NOW: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0RM), &vu16); + val->intval = swab16(vu16) * 1000; + break; + case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0DC), &vu16); + val->intval = vu16 * power->nominal_voltage_mv; + break; + case POWER_SUPPLY_PROP_ENERGY_FULL: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0FC), &vu16); + val->intval = vu16 * power->nominal_voltage_mv; + break; + case POWER_SUPPLY_PROP_ENERGY_NOW: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0RM), &vu16); + val->intval = swab16(vu16) * power->nominal_voltage_mv; + break; + case POWER_SUPPLY_PROP_TEMP: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0AT), &vu16); + val->intval = vu16 - 2732; + break; + case POWER_SUPPLY_PROP_CHARGE_COUNTER: + ret = apple_smc_read_s64(power->smc, SMC_KEY(BAAC), &vs64); + val->intval = vs64; + break; + case POWER_SUPPLY_PROP_CYCLE_COUNT: + ret = apple_smc_read_u16(power->smc, SMC_KEY(B0CT), &vu16); + val->intval = vu16; + break; + case POWER_SUPPLY_PROP_SCOPE: + val->intval = POWER_SUPPLY_SCOPE_SYSTEM; + break; + case POWER_SUPPLY_PROP_HEALTH: + flag = false; + ret = apple_smc_read_flag(power->smc, SMC_KEY(BBAD), &flag); + val->intval = flag ? POWER_SUPPLY_HEALTH_DEAD : POWER_SUPPLY_HEALTH_GOOD; + break; + case POWER_SUPPLY_PROP_MODEL_NAME: + val->strval = power->model_name; + break; + case POWER_SUPPLY_PROP_SERIAL_NUMBER: + val->strval = power->serial_number; + break; + case POWER_SUPPLY_PROP_MANUFACTURE_YEAR: + ret = macsmc_battery_get_date(&power->mfg_date[0], &val->intval); + val->intval += 2000 - 8; /* -8 is a fixup for a firmware bug... */ + break; + case POWER_SUPPLY_PROP_MANUFACTURE_MONTH: + ret = macsmc_battery_get_date(&power->mfg_date[2], &val->intval); + break; + case POWER_SUPPLY_PROP_MANUFACTURE_DAY: + ret = macsmc_battery_get_date(&power->mfg_date[4], &val->intval); + break; + case POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD: + case POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD: + if (power->has_chls) { + ret = apple_smc_read_u16(power->smc, SMC_KEY(CHLS), &vu16); + val->intval = vu16 & 0xff; + if (val->intval < CHLS_MIN_END_THRESHOLD || val->intval >= 100) + val->intval = 100; + } else if (power->has_chwa) { + flag = false; + ret = apple_smc_read_flag(power->smc, SMC_KEY(CHWA), &flag); + val->intval = flag ? CHWA_FIXED_END_THRESHOLD : 100; + } else { + return -EINVAL; + } + if (psp == POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD && + ret >= 0 && val->intval < 100 && val->intval >= CHLS_MIN_END_THRESHOLD) + val->intval -= CHWA_CHLS_FIXED_START_OFFSET; + break; + default: + return -EINVAL; + } + + return ret; +} + +static int macsmc_battery_set_property(struct power_supply *psy, + enum power_supply_property psp, + const union power_supply_propval *val) +{ + struct macsmc_power *power = power_supply_get_drvdata(psy); + + switch (psp) { + case POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR: + return macsmc_battery_set_charge_behaviour(power, val->intval); + case POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD: + /* + * Ignore, we allow writes so userspace isn't confused but this is + * not configurable independently, it always is end - 5 or 100 depending + * on the end_threshold setting. + */ + return 0; + case POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD: + if (power->has_chls) { + u16 kval = 0; + /* TODO: Make CHLS_FORCE_DISCHARGE configurable */ + if (val->intval < CHLS_MIN_END_THRESHOLD) + kval = CHLS_FORCE_DISCHARGE | CHLS_MIN_END_THRESHOLD; + else if (val->intval < 100) + kval = CHLS_FORCE_DISCHARGE | (val->intval & 0xff); + return apple_smc_write_u16(power->smc, SMC_KEY(CHLS), kval); + } else if (power->has_chwa) { + return apple_smc_write_flag(power->smc, SMC_KEY(CHWA), + val->intval <= CHWA_PROP_WRITE_THRESHOLD); + } else { + return -EINVAL; + } + default: + return -EINVAL; + } +} + +static int macsmc_battery_property_is_writeable(struct power_supply *psy, + enum power_supply_property psp) +{ + struct macsmc_power *power = power_supply_get_drvdata(psy); + + switch (psp) { + case POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR: + return true; + case POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD: + case POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD: + return power->has_chwa || power->has_chls; + default: + return false; + } +} + +static const enum power_supply_property macsmc_battery_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_PRESENT, + POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR, + POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW, + POWER_SUPPLY_PROP_TIME_TO_FULL_NOW, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_CAPACITY_LEVEL, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_POWER_NOW, + POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN, + POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN, + POWER_SUPPLY_PROP_VOLTAGE_MIN, + POWER_SUPPLY_PROP_VOLTAGE_MAX, + POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT, + POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX, + POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE, + POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, + POWER_SUPPLY_PROP_CHARGE_FULL, + POWER_SUPPLY_PROP_CHARGE_NOW, + POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN, + POWER_SUPPLY_PROP_ENERGY_FULL, + POWER_SUPPLY_PROP_ENERGY_NOW, + POWER_SUPPLY_PROP_TEMP, + POWER_SUPPLY_PROP_CHARGE_COUNTER, + POWER_SUPPLY_PROP_CYCLE_COUNT, + POWER_SUPPLY_PROP_SCOPE, + POWER_SUPPLY_PROP_HEALTH, + POWER_SUPPLY_PROP_MODEL_NAME, + POWER_SUPPLY_PROP_SERIAL_NUMBER, + POWER_SUPPLY_PROP_MANUFACTURE_YEAR, + POWER_SUPPLY_PROP_MANUFACTURE_MONTH, + POWER_SUPPLY_PROP_MANUFACTURE_DAY, + POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD, + POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD +}; + +static const struct power_supply_desc macsmc_battery_desc = { + .name = "macsmc-battery", + .type = POWER_SUPPLY_TYPE_BATTERY, + .get_property = macsmc_battery_get_property, + .set_property = macsmc_battery_set_property, + .property_is_writeable = macsmc_battery_property_is_writeable, + .properties = macsmc_battery_props, + .num_properties = ARRAY_SIZE(macsmc_battery_props), + .charge_behaviours = BIT(POWER_SUPPLY_CHARGE_BEHAVIOUR_AUTO) + | BIT(POWER_SUPPLY_CHARGE_BEHAVIOUR_FORCE_DISCHARGE) + | BIT(POWER_SUPPLY_CHARGE_BEHAVIOUR_INHIBIT_CHARGE), +}; + +static int macsmc_ac_get_property(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) +{ + struct macsmc_power *power = power_supply_get_drvdata(psy); + int ret = 0; + u16 vu16; + u32 vu32; + + switch (psp) { + case POWER_SUPPLY_PROP_ONLINE: + ret = apple_smc_read_u32(power->smc, SMC_KEY(CHIS), &vu32); + val->intval = !!vu32; + break; + case POWER_SUPPLY_PROP_VOLTAGE_NOW: + ret = apple_smc_read_u16(power->smc, SMC_KEY(AC-n), &vu16); + val->intval = vu16 * 1000; + break; + case POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT: + ret = apple_smc_read_u16(power->smc, SMC_KEY(AC-i), &vu16); + val->intval = vu16 * 1000; + break; + case POWER_SUPPLY_PROP_INPUT_POWER_LIMIT: + ret = apple_smc_read_u32(power->smc, SMC_KEY(ACPW), &vu32); + val->intval = vu32 * 1000; + break; + default: + return -EINVAL; + } + + return ret; +} + +static enum power_supply_property macsmc_ac_props[] = { + POWER_SUPPLY_PROP_ONLINE, + POWER_SUPPLY_PROP_INPUT_POWER_LIMIT, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, +}; + +static const struct power_supply_desc macsmc_ac_desc = { + .name = "macsmc-ac", + .type = POWER_SUPPLY_TYPE_MAINS, + .get_property = macsmc_ac_get_property, + .properties = macsmc_ac_props, + .num_properties = ARRAY_SIZE(macsmc_ac_props), +}; + +static int macsmc_log_power_set(const char *val, const struct kernel_param *kp) +{ + int ret = param_set_bool(val, kp); + + if (ret < 0) + return ret; + + if (log_power && g_power) + schedule_delayed_work(&g_power->dbg_log_work, 0); + + return 0; +} + +static void macsmc_dbg_work(struct work_struct *wrk) +{ + struct macsmc_power *power = container_of(to_delayed_work(wrk), + struct macsmc_power, dbg_log_work); + + macsmc_do_dbg(power); + + if (log_power) + schedule_delayed_work(&power->dbg_log_work, POWER_LOG_INTERVAL); +} + +static void macsmc_power_critical_work(struct work_struct *wrk) +{ + struct macsmc_power *power = container_of(wrk, struct macsmc_power, critical_work); + int ret; + u32 bcf0; + u16 bitv, b0av; + + /* + * Check if the battery voltage is below the design voltage. If it is, + * we have a few seconds until the machine dies. Explicitly shut down, + * which at least gets the NVMe controller to flush its cache. + */ + if (apple_smc_read_u16(power->smc, SMC_KEY(BITV), &bitv) >= 0 && + apple_smc_read_u16(power->smc, SMC_KEY(B0AV), &b0av) >= 0 && + b0av < bitv) { + dev_crit(power->dev, "Emergency notification: Battery is critical\n"); + if (kernel_can_power_off()) + kernel_power_off(); + else /* Missing macsmc-reboot driver? In this state, this will not boot anyway. */ + kernel_restart("Battery is critical"); + } + + /* This spams once per second, so make sure we only trigger shutdown once. */ + if (power->shutdown_started) + return; + + /* Check for battery empty condition */ + ret = apple_smc_read_u32(power->smc, SMC_KEY(BCF0), &bcf0); + if (ret < 0) { + dev_err(power->dev, + "Emergency notification: Failed to read battery status\n"); + } else if (bcf0 == 0) { + dev_warn(power->dev, "Emergency notification: Battery status is OK?\n"); + return; + } else { + dev_warn(power->dev, "Emergency notification: Battery is empty\n"); + } + + power->shutdown_started = true; + + /* + * Attempt to trigger an orderly shutdown. At this point, we should have a few + * minutes of reserve capacity left, enough to do a clean shutdown. + */ + dev_warn(power->dev, "Shutting down in 10 seconds\n"); + ssleep(10); + + /* + * Don't force it; if this stalls or fails, the last-resort check above will + * trigger a hard shutdown when shutdown is truly imminent. + */ + orderly_poweroff(false); +} + +static int macsmc_power_event(struct notifier_block *nb, unsigned long event, void *data) +{ + struct macsmc_power *power = container_of(nb, struct macsmc_power, nb); + + if ((event & 0xffffff00) == 0x71010100) { + bool charging = (event & 0xff) != 0; + + dev_info(power->dev, "Charging: %d\n", charging); + power_supply_changed(power->batt); + power_supply_changed(power->ac); + + return NOTIFY_OK; + } else if (event == 0x71020000) { + schedule_work(&power->critical_work); + + return NOTIFY_OK; + } else if ((event & 0xffff0000) == 0x71060000) { + u8 changed_port = event >> 8; + u8 cur_port; + + /* Port charging state change? */ + if (apple_smc_read_u8(power->smc, SMC_KEY(AC-W), &cur_port) >= 0) { + dev_info(power->dev, "Port %d state change (charge port: %d)\n", + changed_port + 1, cur_port); + } + + power_supply_changed(power->batt); + power_supply_changed(power->ac); + + return NOTIFY_OK; + } else if ((event & 0xffff0000) == 0x71130000) { + u8 port_index = (event >> 8) & 0xff; + u8 status = event & 0xff; + + if (port_index == 0xff) + dev_info(power->dev, "Connector event: Disconnect (status 0x%02x)\n", + status); + else + dev_info(power->dev, "Connector event: Port %d (status 0x%02x)\n", + port_index + 1, status); + + power_supply_changed(power->batt); + power_supply_changed(power->ac); + + return NOTIFY_OK; + } else if ((event & 0xff000000) == 0x71000000) { + dev_info(power->dev, "Unknown charger event 0x%lx\n", event); + + return NOTIFY_OK; + } else if ((event & 0xffff0000) == 0x72010000) { + /* Button event handled by macsmc-hid, but let's do a debug print */ + if (log_power) + macsmc_do_dbg(power); + + return NOTIFY_OK; + } + + return NOTIFY_DONE; +} + +static int macsmc_power_probe(struct platform_device *pdev) +{ + struct apple_smc *smc = dev_get_drvdata(pdev->dev.parent); + struct power_supply_config psy_cfg = {}; + struct macsmc_power *power; + bool flag; + u8 val8; + u16 vu16; + u32 val32; + int ret; + + power = devm_kzalloc(&pdev->dev, sizeof(*power), GFP_KERNEL); + if (!power) + return -ENOMEM; + + power->dev = &pdev->dev; + power->smc = smc; + power->ac_desc = macsmc_ac_desc; + power->batt_desc = macsmc_battery_desc; + dev_set_drvdata(&pdev->dev, power); + + /* Ignore devices without a charger/battery */ + if (macsmc_battery_get_status(power) <= POWER_SUPPLY_STATUS_UNKNOWN) + return -ENODEV; + + /* Fetch string properties */ + apple_smc_read(smc, SMC_KEY(BMDN), power->model_name, sizeof(power->model_name) - 1); + apple_smc_read(smc, SMC_KEY(BMSN), power->serial_number, sizeof(power->serial_number) - 1); + apple_smc_read(smc, SMC_KEY(BMDT), power->mfg_date, sizeof(power->mfg_date) - 1); + + if (apple_smc_read_u32(power->smc, SMC_KEY(CHTE), &val32) >= 0) + power->has_chte = true; + + if (apple_smc_read_u8(power->smc, SMC_KEY(CH0C), &val8) >= 0) + power->has_ch0c = true; + + if (apple_smc_read_u8(power->smc, SMC_KEY(CH0I), &val8) >= 0) + power->has_ch0i = true; + + /* Turn off the "optimized battery charging" flags, in case macOS left them on */ + if (power->has_chte) + apple_smc_write_u32(power->smc, SMC_KEY(CHTE), 0); + else if (power->has_ch0c) + apple_smc_write_u8(power->smc, SMC_KEY(CH0C), 0); + + if (power->has_ch0i) + apple_smc_write_u8(power->smc, SMC_KEY(CH0I), 0); + + apple_smc_write_u8(power->smc, SMC_KEY(CH0K), 0); + apple_smc_write_u8(power->smc, SMC_KEY(CH0B), 0); + + power->batt_desc.charge_behaviours = BIT(POWER_SUPPLY_CHARGE_BEHAVIOUR_AUTO); + + /* Newer firmwares do not have force discharge, so check if it's supported */ + if (power->has_ch0i) + power->batt_desc.charge_behaviours |= BIT(POWER_SUPPLY_CHARGE_BEHAVIOUR_FORCE_DISCHARGE); + + /* Older firmware uses CH0C, and newer firmware uses CHTE, so check if at least one is present*/ + if (power->has_chte || power->has_ch0c) + power->batt_desc.charge_behaviours |= BIT(POWER_SUPPLY_CHARGE_BEHAVIOUR_INHIBIT_CHARGE); + + /* + * Prefer CHWA as the SMC firmware from iBoot-10151.1.1 is not compatible with + * this CHLS usage. + */ + if (apple_smc_read_flag(power->smc, SMC_KEY(CHWA), &flag) == 0) { + power->has_chwa = true; + } else if (apple_smc_read_u16(power->smc, SMC_KEY(CHLS), &vu16) >= 0) { + power->has_chls = true; + } else { + /* Remove the last 2 properties that control the charge threshold */ + power->batt_desc.num_properties -= 2; + } + + apple_smc_read_u8(power->smc, SMC_KEY(BNCB), &power->num_cells); + power->nominal_voltage_mv = MACSMC_NOMINAL_CELL_VOLTAGE_MV * power->num_cells; + + /* Doing one read of this flag enables critical shutdown notifications */ + apple_smc_read_u32(power->smc, SMC_KEY(BCF0), &val32); + + psy_cfg.drv_data = power; + power->batt = devm_power_supply_register(&pdev->dev, &power->batt_desc, &psy_cfg); + if (IS_ERR(power->batt)) { + dev_err(&pdev->dev, "Failed to register battery\n"); + ret = PTR_ERR(power->batt); + return ret; + } + + /* SMC firmware in macOS 15.4 dropped "AC-i" and "AC-n" (and all keys + * with lower case last letter) without obvious replacement. */ + if (apple_smc_read_u16(power->smc, SMC_KEY(AC-n), &vu16) < 0) + power->ac_desc.num_properties -= 2; + + power->ac = devm_power_supply_register(&pdev->dev, &power->ac_desc, &psy_cfg); + if (IS_ERR(power->ac)) { + dev_err(&pdev->dev, "Failed to register AC adapter\n"); + ret = PTR_ERR(power->ac); + return ret; + } + + power->nb.notifier_call = macsmc_power_event; + blocking_notifier_chain_register(&smc->event_handlers, &power->nb); + + INIT_WORK(&power->critical_work, macsmc_power_critical_work); + INIT_DELAYED_WORK(&power->dbg_log_work, macsmc_dbg_work); + + g_power = power; + + if (log_power) + schedule_delayed_work(&power->dbg_log_work, 0); + + return 0; +} + +static void macsmc_power_remove(struct platform_device *pdev) +{ + struct macsmc_power *power = dev_get_drvdata(&pdev->dev); + + cancel_work(&power->critical_work); + cancel_delayed_work(&power->dbg_log_work); + + g_power = NULL; + + blocking_notifier_chain_unregister(&power->smc->event_handlers, &power->nb); +} + +static struct platform_driver macsmc_power_driver = { + .driver = { + .name = "macsmc-power", + .owner = THIS_MODULE, + }, + .probe = macsmc_power_probe, + .remove = macsmc_power_remove, +}; +module_platform_driver(macsmc_power_driver); + +MODULE_LICENSE("Dual MIT/GPL"); +MODULE_DESCRIPTION("Apple SMC battery and power management driver"); +MODULE_AUTHOR("Hector Martin "); +MODULE_ALIAS("platform:macsmc-power"); diff --git a/drivers/power/supply/max17040_battery.c b/drivers/power/supply/max17040_battery.c index c1640bc6accd27..48453508688a49 100644 --- a/drivers/power/supply/max17040_battery.c +++ b/drivers/power/supply/max17040_battery.c @@ -388,6 +388,7 @@ static int max17040_get_property(struct power_supply *psy, union power_supply_propval *val) { struct max17040_chip *chip = power_supply_get_drvdata(psy); + int ret; switch (psp) { case POWER_SUPPLY_PROP_ONLINE: @@ -410,7 +411,10 @@ static int max17040_get_property(struct power_supply *psy, if (!chip->channel_temp) return -ENODATA; - iio_read_channel_processed(chip->channel_temp, &val->intval); + ret = iio_read_channel_processed(chip->channel_temp, &val->intval); + if (ret) + return ret; + val->intval /= 100; /* Convert from milli- to deci-degree */ break; diff --git a/drivers/power/supply/max77705_charger.c b/drivers/power/supply/max77705_charger.c index b1a227bf72e26f..1044bf58aeaca8 100644 --- a/drivers/power/supply/max77705_charger.c +++ b/drivers/power/supply/max77705_charger.c @@ -60,7 +60,7 @@ static const struct regmap_irq max77705_charger_irqs[] = { REGMAP_IRQ_REG_LINE(MAX77705_AICL_I, BITS_PER_BYTE), }; -static struct regmap_irq_chip max77705_charger_irq_chip = { +static const struct regmap_irq_chip max77705_charger_irq_chip = { .name = "max77705-charger", .status_base = MAX77705_CHG_REG_INT, .mask_base = MAX77705_CHG_REG_INT_MASK, @@ -567,6 +567,7 @@ static int max77705_charger_probe(struct i2c_client *i2c) { struct power_supply_config pscfg = {}; struct max77705_charger_data *chg; + struct regmap_irq_chip *chip_desc; struct device *dev; struct regmap_irq_chip_data *irq_data; int ret; @@ -580,6 +581,13 @@ static int max77705_charger_probe(struct i2c_client *i2c) chg->dev = dev; i2c_set_clientdata(i2c, chg); + chip_desc = devm_kmemdup(dev, &max77705_charger_irq_chip, + sizeof(max77705_charger_irq_chip), + GFP_KERNEL); + if (!chip_desc) + return -ENOMEM; + chip_desc->irq_drv_data = chg; + chg->regmap = devm_regmap_init_i2c(i2c, &max77705_chg_regmap_config); if (IS_ERR(chg->regmap)) return PTR_ERR(chg->regmap); @@ -599,11 +607,9 @@ static int max77705_charger_probe(struct i2c_client *i2c) if (IS_ERR(chg->psy_chg)) return PTR_ERR(chg->psy_chg); - max77705_charger_irq_chip.irq_drv_data = chg; ret = devm_regmap_add_irq_chip(chg->dev, chg->regmap, i2c->irq, IRQF_ONESHOT, 0, - &max77705_charger_irq_chip, - &irq_data); + chip_desc, &irq_data); if (ret) return dev_err_probe(dev, ret, "failed to add irq chip\n"); diff --git a/drivers/power/supply/pm8916_bms_vm.c b/drivers/power/supply/pm8916_bms_vm.c index 5120be086e6ffc..de5d571c03e212 100644 --- a/drivers/power/supply/pm8916_bms_vm.c +++ b/drivers/power/supply/pm8916_bms_vm.c @@ -167,15 +167,6 @@ static int pm8916_bms_vm_battery_probe(struct platform_device *pdev) if (ret < 0) return -EINVAL; - irq = platform_get_irq_byname(pdev, "fifo"); - if (irq < 0) - return irq; - - ret = devm_request_threaded_irq(dev, irq, NULL, pm8916_bms_vm_fifo_update_done_irq, - IRQF_ONESHOT, "pm8916_vm_bms", bat); - if (ret) - return ret; - ret = regmap_bulk_read(bat->regmap, bat->reg + PM8916_PERPH_TYPE, &tmp, 2); if (ret) goto comm_error; @@ -220,6 +211,15 @@ static int pm8916_bms_vm_battery_probe(struct platform_device *pdev) if (ret) return dev_err_probe(dev, ret, "Unable to get battery info\n"); + irq = platform_get_irq_byname(pdev, "fifo"); + if (irq < 0) + return irq; + + ret = devm_request_threaded_irq(dev, irq, NULL, pm8916_bms_vm_fifo_update_done_irq, + IRQF_ONESHOT, "pm8916_vm_bms", bat); + if (ret) + return ret; + platform_set_drvdata(pdev, bat); return 0; diff --git a/drivers/power/supply/pm8916_lbc.c b/drivers/power/supply/pm8916_lbc.c index c74b75b1b2676c..6b631012a7959a 100644 --- a/drivers/power/supply/pm8916_lbc.c +++ b/drivers/power/supply/pm8916_lbc.c @@ -274,15 +274,6 @@ static int pm8916_lbc_charger_probe(struct platform_device *pdev) return dev_err_probe(dev, -EINVAL, "Wrong amount of reg values: %d (4 expected)\n", len); - irq = platform_get_irq_byname(pdev, "usb_vbus"); - if (irq < 0) - return irq; - - ret = devm_request_threaded_irq(dev, irq, NULL, pm8916_lbc_charger_state_changed_irq, - IRQF_ONESHOT, "pm8916_lbc", chg); - if (ret) - return ret; - ret = device_property_read_u32_array(dev, "reg", chg->reg, len); if (ret) return ret; @@ -332,6 +323,10 @@ static int pm8916_lbc_charger_probe(struct platform_device *pdev) if (ret) return dev_err_probe(dev, ret, "Unable to get battery info\n"); + irq = platform_get_irq_byname(pdev, "usb_vbus"); + if (irq < 0) + return irq; + chg->edev = devm_extcon_dev_allocate(dev, pm8916_lbc_charger_cable); if (IS_ERR(chg->edev)) return PTR_ERR(chg->edev); @@ -340,6 +335,11 @@ static int pm8916_lbc_charger_probe(struct platform_device *pdev) if (ret < 0) return dev_err_probe(dev, ret, "failed to register extcon device\n"); + ret = devm_request_threaded_irq(dev, irq, NULL, pm8916_lbc_charger_state_changed_irq, + IRQF_ONESHOT, "pm8916_lbc", chg); + if (ret) + return ret; + ret = regmap_read(chg->regmap, chg->reg[LBC_USB] + PM8916_INT_RT_STS, &tmp); if (ret) goto comm_error; diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c index 3c2837ef346173..ff77dba29a3efc 100644 --- a/drivers/power/supply/qcom_battmgr.c +++ b/drivers/power/supply/qcom_battmgr.c @@ -257,6 +257,7 @@ struct qcom_battmgr_info { unsigned int capacity_warning; unsigned int cycle_count; unsigned int charge_count; + bool charge_ctrl_enable; unsigned int charge_ctrl_start; unsigned int charge_ctrl_end; char model_number[BATTMGR_STRING_LEN]; @@ -659,13 +660,13 @@ static int qcom_battmgr_bat_get_property(struct power_supply *psy, } static int qcom_battmgr_set_charge_control(struct qcom_battmgr *battmgr, - u32 target_soc, u32 delta_soc) + bool enable, u32 target_soc, u32 delta_soc) { struct qcom_battmgr_charge_ctrl_request request = { .hdr.owner = cpu_to_le32(PMIC_GLINK_OWNER_BATTMGR), .hdr.type = cpu_to_le32(PMIC_GLINK_REQ_RESP), .hdr.opcode = cpu_to_le32(BATTMGR_CHG_CTRL_LIMIT_EN), - .enable = cpu_to_le32(1), + .enable = cpu_to_le32(enable), .target_soc = cpu_to_le32(target_soc), .delta_soc = cpu_to_le32(delta_soc), }; @@ -677,13 +678,9 @@ static int qcom_battmgr_set_charge_start_threshold(struct qcom_battmgr *battmgr, { u32 target_soc, delta_soc; int ret; + bool enable = start_soc != 0; - if (start_soc < CHARGE_CTRL_START_THR_MIN || - start_soc > CHARGE_CTRL_START_THR_MAX) { - dev_err(battmgr->dev, "charge control start threshold exceed range: [%u - %u]\n", - CHARGE_CTRL_START_THR_MIN, CHARGE_CTRL_START_THR_MAX); - return -EINVAL; - } + start_soc = clamp(start_soc, CHARGE_CTRL_START_THR_MIN, CHARGE_CTRL_START_THR_MAX); /* * If the new start threshold is larger than the old end threshold, @@ -701,9 +698,10 @@ static int qcom_battmgr_set_charge_start_threshold(struct qcom_battmgr *battmgr, } mutex_lock(&battmgr->lock); - ret = qcom_battmgr_set_charge_control(battmgr, target_soc, delta_soc); + ret = qcom_battmgr_set_charge_control(battmgr, enable, target_soc, delta_soc); mutex_unlock(&battmgr->lock); if (!ret) { + battmgr->info.charge_ctrl_enable = enable; battmgr->info.charge_ctrl_start = start_soc; battmgr->info.charge_ctrl_end = target_soc; } @@ -715,19 +713,15 @@ static int qcom_battmgr_set_charge_end_threshold(struct qcom_battmgr *battmgr, i { u32 delta_soc = CHARGE_CTRL_DELTA_SOC; int ret; + bool enable = battmgr->info.charge_ctrl_enable; - if (end_soc < CHARGE_CTRL_END_THR_MIN || - end_soc > CHARGE_CTRL_END_THR_MAX) { - dev_err(battmgr->dev, "charge control end threshold exceed range: [%u - %u]\n", - CHARGE_CTRL_END_THR_MIN, CHARGE_CTRL_END_THR_MAX); - return -EINVAL; - } + end_soc = clamp(end_soc, CHARGE_CTRL_END_THR_MIN, CHARGE_CTRL_END_THR_MAX); if (battmgr->info.charge_ctrl_start && end_soc > battmgr->info.charge_ctrl_start) delta_soc = end_soc - battmgr->info.charge_ctrl_start; mutex_lock(&battmgr->lock); - ret = qcom_battmgr_set_charge_control(battmgr, end_soc, delta_soc); + ret = qcom_battmgr_set_charge_control(battmgr, enable, end_soc, delta_soc); mutex_unlock(&battmgr->lock); if (!ret) { battmgr->info.charge_ctrl_start = end_soc - delta_soc; @@ -1250,7 +1244,8 @@ static unsigned int qcom_battmgr_sc8280xp_parse_technology(const char *chemistry if ((!strncmp(chemistry, "LIO", BATTMGR_CHEMISTRY_LEN)) || (!strncmp(chemistry, "OOI", BATTMGR_CHEMISTRY_LEN))) return POWER_SUPPLY_TECHNOLOGY_LION; - if (!strncmp(chemistry, "LIP", BATTMGR_CHEMISTRY_LEN)) + if (!strncmp(chemistry, "LIP", BATTMGR_CHEMISTRY_LEN) || + !strncmp(chemistry, "LiP", BATTMGR_CHEMISTRY_LEN)) return POWER_SUPPLY_TECHNOLOGY_LIPO; pr_err("Unknown battery technology '%s'\n", chemistry); diff --git a/drivers/power/supply/rt5033_charger.c b/drivers/power/supply/rt5033_charger.c index 2fdc5843970754..de724f23e453b3 100644 --- a/drivers/power/supply/rt5033_charger.c +++ b/drivers/power/supply/rt5033_charger.c @@ -701,6 +701,8 @@ static int rt5033_charger_probe(struct platform_device *pdev) np_conn = of_parse_phandle(pdev->dev.of_node, "richtek,usb-connector", 0); np_edev = of_get_parent(np_conn); charger->edev = extcon_find_edev_by_node(np_edev); + of_node_put(np_edev); + of_node_put(np_conn); if (IS_ERR(charger->edev)) { dev_warn(charger->dev, "no extcon device found in device-tree\n"); goto out; diff --git a/drivers/power/supply/rt9455_charger.c b/drivers/power/supply/rt9455_charger.c index 1ffe7f02932f6d..5130d2395e88fa 100644 --- a/drivers/power/supply/rt9455_charger.c +++ b/drivers/power/supply/rt9455_charger.c @@ -1663,6 +1663,15 @@ static int rt9455_probe(struct i2c_client *client) rt9455_charger_config.supplied_to = rt9455_charger_supplied_to; rt9455_charger_config.num_supplicants = ARRAY_SIZE(rt9455_charger_supplied_to); + + info->charger = devm_power_supply_register(dev, &rt9455_charger_desc, + &rt9455_charger_config); + if (IS_ERR(info->charger)) { + dev_err(dev, "Failed to register charger\n"); + ret = PTR_ERR(info->charger); + goto put_usb_notifier; + } + ret = devm_request_threaded_irq(dev, client->irq, NULL, rt9455_irq_handler_thread, IRQF_TRIGGER_LOW | IRQF_ONESHOT, @@ -1678,14 +1687,6 @@ static int rt9455_probe(struct i2c_client *client) goto put_usb_notifier; } - info->charger = devm_power_supply_register(dev, &rt9455_charger_desc, - &rt9455_charger_config); - if (IS_ERR(info->charger)) { - dev_err(dev, "Failed to register charger\n"); - ret = PTR_ERR(info->charger); - goto put_usb_notifier; - } - return 0; put_usb_notifier: diff --git a/drivers/power/supply/rt9467-charger.c b/drivers/power/supply/rt9467-charger.c index fe773dd8b404f3..44c26fb37a775f 100644 --- a/drivers/power/supply/rt9467-charger.c +++ b/drivers/power/supply/rt9467-charger.c @@ -376,7 +376,7 @@ static int rt9467_set_value_from_ranges(struct rt9467_chg_data *data, if (rsel == RT9467_RANGE_VMIVR) { ret = linear_range_get_selector_high(range, value, &sel, &found); if (ret) - value = range->max_sel; + sel = range->max_sel; } else { linear_range_get_selector_within(range, value, &sel); } @@ -588,6 +588,10 @@ static int rt9467_run_aicl(struct rt9467_chg_data *data) aicl_vth = mivr_vth + RT9467_AICLVTH_GAP_uV; ret = rt9467_set_value_from_ranges(data, F_AICL_VTH, RT9467_RANGE_AICL_VTH, aicl_vth); + if (ret) { + dev_err(data->dev, "Failed to set AICL VTH\n"); + return ret; + } /* Trigger AICL function */ ret = regmap_field_write(data->rm_field[F_AICL_MEAS], 1); diff --git a/drivers/power/supply/sbs-battery.c b/drivers/power/supply/sbs-battery.c index 943c82ee978f40..43c48196c16741 100644 --- a/drivers/power/supply/sbs-battery.c +++ b/drivers/power/supply/sbs-battery.c @@ -1174,24 +1174,6 @@ static int sbs_probe(struct i2c_client *client) i2c_set_clientdata(client, chip); - if (!chip->gpio_detect) - goto skip_gpio; - - irq = gpiod_to_irq(chip->gpio_detect); - if (irq <= 0) { - dev_warn(&client->dev, "Failed to get gpio as irq: %d\n", irq); - goto skip_gpio; - } - - rc = devm_request_threaded_irq(&client->dev, irq, NULL, sbs_irq, - IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, - dev_name(&client->dev), chip); - if (rc) { - dev_warn(&client->dev, "Failed to request irq: %d\n", rc); - goto skip_gpio; - } - -skip_gpio: /* * Before we register, we might need to make sure we can actually talk * to the battery. @@ -1217,6 +1199,24 @@ static int sbs_probe(struct i2c_client *client) return dev_err_probe(&client->dev, PTR_ERR(chip->power_supply), "Failed to register power supply\n"); + if (!chip->gpio_detect) + goto out; + + irq = gpiod_to_irq(chip->gpio_detect); + if (irq <= 0) { + dev_warn(&client->dev, "Failed to get gpio as irq: %d\n", irq); + goto out; + } + + rc = devm_request_threaded_irq(&client->dev, irq, NULL, sbs_irq, + IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + dev_name(&client->dev), chip); + if (rc) { + dev_warn(&client->dev, "Failed to request irq: %d\n", rc); + goto out; + } + +out: dev_info(&client->dev, "%s: battery gas gauge device registered\n", client->name); diff --git a/drivers/power/supply/wm831x_power.c b/drivers/power/supply/wm831x_power.c index 6acdba7885ca57..78fa0573ef25c7 100644 --- a/drivers/power/supply/wm831x_power.c +++ b/drivers/power/supply/wm831x_power.c @@ -144,6 +144,7 @@ static int wm831x_usb_limit_change(struct notifier_block *nb, struct wm831x_power, usb_notify); unsigned int i, best; + int ret; /* Find the highest supported limit */ best = 0; @@ -156,8 +157,13 @@ static int wm831x_usb_limit_change(struct notifier_block *nb, dev_dbg(wm831x_power->wm831x->dev, "Limiting USB current to %umA", wm831x_usb_limits[best]); - wm831x_set_bits(wm831x_power->wm831x, WM831X_POWER_STATE, - WM831X_USB_ILIM_MASK, best); + ret = wm831x_set_bits(wm831x_power->wm831x, WM831X_POWER_STATE, + WM831X_USB_ILIM_MASK, best); + if (ret < 0) { + dev_err(wm831x_power->wm831x->dev, + "Failed to set USB current limit: %d\n", ret); + return ret; + } return 0; } diff --git a/drivers/power/supply/wm97xx_battery.c b/drivers/power/supply/wm97xx_battery.c index b3b0c37a9dd2d5..f00722c88c6fea 100644 --- a/drivers/power/supply/wm97xx_battery.c +++ b/drivers/power/supply/wm97xx_battery.c @@ -178,12 +178,6 @@ static int wm97xx_bat_probe(struct platform_device *dev) "failed to get charge GPIO\n"); if (charge_gpiod) { gpiod_set_consumer_name(charge_gpiod, "BATT CHRG"); - ret = request_irq(gpiod_to_irq(charge_gpiod), - wm97xx_chrg_irq, 0, - "AC Detect", dev); - if (ret) - return dev_err_probe(&dev->dev, ret, - "failed to request GPIO irq\n"); props++; /* POWER_SUPPLY_PROP_STATUS */ } @@ -199,10 +193,8 @@ static int wm97xx_bat_probe(struct platform_device *dev) props++; /* POWER_SUPPLY_PROP_VOLTAGE_MIN */ prop = kcalloc(props, sizeof(*prop), GFP_KERNEL); - if (!prop) { - ret = -ENOMEM; - goto err3; - } + if (!prop) + return -ENOMEM; prop[i++] = POWER_SUPPLY_PROP_PRESENT; if (charge_gpiod) @@ -236,15 +228,27 @@ static int wm97xx_bat_probe(struct platform_device *dev) schedule_work(&bat_work); } else { ret = PTR_ERR(bat_psy); - goto err4; + goto free; + } + + if (charge_gpiod) { + ret = request_irq(gpiod_to_irq(charge_gpiod), wm97xx_chrg_irq, + 0, "AC Detect", dev); + if (ret) { + dev_err_probe(&dev->dev, ret, + "failed to request GPIO irq\n"); + goto unregister; + } } return 0; -err4: + +unregister: + power_supply_unregister(bat_psy); + +free: kfree(prop); -err3: - if (charge_gpiod) - free_irq(gpiod_to_irq(charge_gpiod), dev); + return ret; } diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index c7e7f9bf531371..57bebd07c7d0df 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1284,6 +1284,9 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &rapl_defaults_spr_server), X86_MATCH_VFM(INTEL_LUNARLAKE_M, &rapl_defaults_core), X86_MATCH_VFM(INTEL_PANTHERLAKE_L, &rapl_defaults_core), + X86_MATCH_VFM(INTEL_WILDCATLAKE_L, &rapl_defaults_core), + X86_MATCH_VFM(INTEL_NOVALAKE, &rapl_defaults_core), + X86_MATCH_VFM(INTEL_NOVALAKE_L, &rapl_defaults_core), X86_MATCH_VFM(INTEL_ARROWLAKE_H, &rapl_defaults_core), X86_MATCH_VFM(INTEL_ARROWLAKE, &rapl_defaults_core), X86_MATCH_VFM(INTEL_ARROWLAKE_U, &rapl_defaults_core), diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c index 4ed06c71a3ac43..c6b9a7debc3545 100644 --- a/drivers/powercap/intel_rapl_msr.c +++ b/drivers/powercap/intel_rapl_msr.c @@ -151,6 +151,9 @@ static const struct x86_cpu_id pl4_support_ids[] = { X86_MATCH_VFM(INTEL_ARROWLAKE_U, NULL), X86_MATCH_VFM(INTEL_ARROWLAKE_H, NULL), X86_MATCH_VFM(INTEL_PANTHERLAKE_L, NULL), + X86_MATCH_VFM(INTEL_WILDCATLAKE_L, NULL), + X86_MATCH_VFM(INTEL_NOVALAKE, NULL), + X86_MATCH_VFM(INTEL_NOVALAKE_L, NULL), {} }; diff --git a/drivers/powercap/intel_rapl_tpmi.c b/drivers/powercap/intel_rapl_tpmi.c index 82201bf4685d44..34c0bd1edd61a3 100644 --- a/drivers/powercap/intel_rapl_tpmi.c +++ b/drivers/powercap/intel_rapl_tpmi.c @@ -157,7 +157,7 @@ static int parse_one_domain(struct tpmi_rapl_package *trp, u32 offset) tpmi_domain_flags = tpmi_domain_header >> 32 & 0xffff; if (tpmi_domain_version == TPMI_VERSION_INVALID) { - pr_warn(FW_BUG "Invalid version\n"); + pr_debug("Invalid version, other instances may be valid\n"); return -ENODEV; } diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c index 4112a009733826..1ff369880beb28 100644 --- a/drivers/powercap/powercap_sys.c +++ b/drivers/powercap/powercap_sys.c @@ -68,7 +68,7 @@ static ssize_t show_constraint_##_attr(struct device *dev, \ int id; \ struct powercap_zone_constraint *pconst;\ \ - if (!sscanf(dev_attr->attr.name, "constraint_%d_", &id)) \ + if (sscanf(dev_attr->attr.name, "constraint_%d_", &id) != 1) \ return -EINVAL; \ if (id >= power_zone->const_id_cnt) \ return -EINVAL; \ @@ -93,7 +93,7 @@ static ssize_t store_constraint_##_attr(struct device *dev,\ int id; \ struct powercap_zone_constraint *pconst;\ \ - if (!sscanf(dev_attr->attr.name, "constraint_%d_", &id)) \ + if (sscanf(dev_attr->attr.name, "constraint_%d_", &id) != 1) \ return -EINVAL; \ if (id >= power_zone->const_id_cnt) \ return -EINVAL; \ @@ -162,7 +162,7 @@ static ssize_t show_constraint_name(struct device *dev, ssize_t len = -ENODATA; struct powercap_zone_constraint *pconst; - if (!sscanf(dev_attr->attr.name, "constraint_%d_", &id)) + if (sscanf(dev_attr->attr.name, "constraint_%d_", &id) != 1) return -EINVAL; if (id >= power_zone->const_id_cnt) return -EINVAL; @@ -625,17 +625,23 @@ struct powercap_control_type *powercap_register_control_type( INIT_LIST_HEAD(&control_type->node); control_type->dev.class = &powercap_class; dev_set_name(&control_type->dev, "%s", name); - result = device_register(&control_type->dev); - if (result) { - put_device(&control_type->dev); - return ERR_PTR(result); - } idr_init(&control_type->idr); mutex_lock(&powercap_cntrl_list_lock); list_add_tail(&control_type->node, &powercap_cntrl_list); mutex_unlock(&powercap_cntrl_list_lock); + result = device_register(&control_type->dev); + if (result) { + mutex_lock(&powercap_cntrl_list_lock); + list_del(&control_type->node); + mutex_unlock(&powercap_cntrl_list_lock); + + idr_destroy(&control_type->idr); + put_device(&control_type->dev); + return ERR_PTR(result); + } + return control_type; } EXPORT_SYMBOL_GPL(powercap_register_control_type); diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index ea2ccf42e81441..462c91a034c8e6 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -2294,8 +2294,9 @@ static long pwm_cdev_ioctl(struct file *file, unsigned int cmd, unsigned long ar .duty_offset_ns = wf.duty_offset_ns, }; - return copy_to_user((struct pwmchip_waveform __user *)arg, - &cwf, sizeof(cwf)); + ret = copy_to_user((struct pwmchip_waveform __user *)arg, + &cwf, sizeof(cwf)); + return ret ? -EFAULT : 0; } case PWM_IOCTL_GETWF: @@ -2328,8 +2329,9 @@ static long pwm_cdev_ioctl(struct file *file, unsigned int cmd, unsigned long ar .duty_offset_ns = wf.duty_offset_ns, }; - return copy_to_user((struct pwmchip_waveform __user *)arg, - &cwf, sizeof(cwf)); + ret = copy_to_user((struct pwmchip_waveform __user *)arg, + &cwf, sizeof(cwf)); + return ret ? -EFAULT : 0; } case PWM_IOCTL_SETROUNDEDWF: @@ -2696,11 +2698,10 @@ static int pwm_seq_show(struct seq_file *s, void *v) { struct pwm_chip *chip = v; - seq_printf(s, "%s%d: %s/%s, %d PWM device%s\n", + seq_printf(s, "%s%u: %s/%s, npwm: %u\n", (char *)s->private, chip->id, pwmchip_parent(chip)->bus ? pwmchip_parent(chip)->bus->name : "no-bus", - dev_name(pwmchip_parent(chip)), chip->npwm, - (chip->npwm != 1) ? "s" : ""); + dev_name(pwmchip_parent(chip)), chip->npwm); pwm_dbg_show(chip, s); diff --git a/drivers/pwm/pwm-bcm2835.c b/drivers/pwm/pwm-bcm2835.c index 578e95e0296c65..532903da521fd0 100644 --- a/drivers/pwm/pwm-bcm2835.c +++ b/drivers/pwm/pwm-bcm2835.c @@ -34,29 +34,6 @@ static inline struct bcm2835_pwm *to_bcm2835_pwm(struct pwm_chip *chip) return pwmchip_get_drvdata(chip); } -static int bcm2835_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm) -{ - struct bcm2835_pwm *pc = to_bcm2835_pwm(chip); - u32 value; - - value = readl(pc->base + PWM_CONTROL); - value &= ~(PWM_CONTROL_MASK << PWM_CONTROL_SHIFT(pwm->hwpwm)); - value |= (PWM_MODE << PWM_CONTROL_SHIFT(pwm->hwpwm)); - writel(value, pc->base + PWM_CONTROL); - - return 0; -} - -static void bcm2835_pwm_free(struct pwm_chip *chip, struct pwm_device *pwm) -{ - struct bcm2835_pwm *pc = to_bcm2835_pwm(chip); - u32 value; - - value = readl(pc->base + PWM_CONTROL); - value &= ~(PWM_CONTROL_MASK << PWM_CONTROL_SHIFT(pwm->hwpwm)); - writel(value, pc->base + PWM_CONTROL); -} - static int bcm2835_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, const struct pwm_state *state) { @@ -102,6 +79,9 @@ static int bcm2835_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, /* set polarity */ val = readl(pc->base + PWM_CONTROL); + val &= ~(PWM_CONTROL_MASK << PWM_CONTROL_SHIFT(pwm->hwpwm)); + val |= PWM_MODE << PWM_CONTROL_SHIFT(pwm->hwpwm); + if (state->polarity == PWM_POLARITY_NORMAL) val &= ~(PWM_POLARITY << PWM_CONTROL_SHIFT(pwm->hwpwm)); else @@ -119,8 +99,6 @@ static int bcm2835_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, } static const struct pwm_ops bcm2835_pwm_ops = { - .request = bcm2835_pwm_request, - .free = bcm2835_pwm_free, .apply = bcm2835_pwm_apply, }; diff --git a/drivers/pwm/pwm-max7360.c b/drivers/pwm/pwm-max7360.c index ebf93a7aee5be4..31972bd00ebe95 100644 --- a/drivers/pwm/pwm-max7360.c +++ b/drivers/pwm/pwm-max7360.c @@ -153,6 +153,7 @@ static int max7360_pwm_read_waveform(struct pwm_chip *chip, } static const struct pwm_ops max7360_pwm_ops = { + .sizeof_wfhw = sizeof(struct max7360_pwm_waveform), .request = max7360_pwm_request, .round_waveform_tohw = max7360_pwm_round_waveform_tohw, .round_waveform_fromhw = max7360_pwm_round_waveform_fromhw, diff --git a/drivers/pwm/pwm-rzg2l-gpt.c b/drivers/pwm/pwm-rzg2l-gpt.c index 360c8bf3b19037..4856af080e8e9f 100644 --- a/drivers/pwm/pwm-rzg2l-gpt.c +++ b/drivers/pwm/pwm-rzg2l-gpt.c @@ -96,6 +96,11 @@ static inline unsigned int rzg2l_gpt_subchannel(unsigned int hwpwm) return hwpwm & 0x1; } +static inline unsigned int rzg2l_gpt_sibling(unsigned int hwpwm) +{ + return hwpwm ^ 0x1; +} + static void rzg2l_gpt_write(struct rzg2l_gpt_chip *rzg2l_gpt, u32 reg, u32 data) { writel(data, rzg2l_gpt->mmio + reg); @@ -271,10 +276,14 @@ static int rzg2l_gpt_config(struct pwm_chip *chip, struct pwm_device *pwm, * in use with different settings. */ if (rzg2l_gpt->channel_request_count[ch] > 1) { - if (period_ticks < rzg2l_gpt->period_ticks[ch]) - return -EBUSY; - else + u8 sibling_ch = rzg2l_gpt_sibling(pwm->hwpwm); + + if (rzg2l_gpt_is_ch_enabled(rzg2l_gpt, sibling_ch)) { + if (period_ticks < rzg2l_gpt->period_ticks[ch]) + return -EBUSY; + period_ticks = rzg2l_gpt->period_ticks[ch]; + } } prescale = rzg2l_gpt_calculate_prescale(rzg2l_gpt, period_ticks); diff --git a/drivers/pwm/pwm-tiehrpwm.c b/drivers/pwm/pwm-tiehrpwm.c index 7a86cb090f76f1..2533c95b0ba9d3 100644 --- a/drivers/pwm/pwm-tiehrpwm.c +++ b/drivers/pwm/pwm-tiehrpwm.c @@ -237,8 +237,6 @@ static int ehrpwm_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, if (period_cycles < 1) period_cycles = 1; - pm_runtime_get_sync(pwmchip_parent(chip)); - /* Update clock prescaler values */ ehrpwm_modify(pc->mmio_base, TBCTL, TBCTL_CLKDIV_MASK, tb_divval); @@ -290,8 +288,6 @@ static int ehrpwm_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, if (!(duty_cycles > period_cycles)) ehrpwm_write(pc->mmio_base, cmp_reg, duty_cycles); - pm_runtime_put_sync(pwmchip_parent(chip)); - return 0; } @@ -378,6 +374,8 @@ static int ehrpwm_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, int err; bool enabled = pwm->state.enabled; + guard(pm_runtime_active)(pwmchip_parent(chip)); + if (state->polarity != pwm->state.polarity) { if (enabled) { ehrpwm_pwm_disable(chip, pwm); diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c index ac0e132ccc3eb9..2a5b5a9fdcb36c 100644 --- a/drivers/ras/ras.c +++ b/drivers/ras/ras.c @@ -53,9 +53,45 @@ void log_non_standard_event(const guid_t *sec_type, const guid_t *fru_id, } EXPORT_SYMBOL_GPL(log_non_standard_event); -void log_arm_hw_error(struct cper_sec_proc_arm *err) +void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev) { - trace_arm_event(err); + struct cper_arm_err_info *err_info; + struct cper_arm_ctx_info *ctx_info; + u8 *ven_err_data; + u32 ctx_len = 0; + int n, sz, cpu; + s32 vsei_len; + u32 pei_len; + u8 *pei_err, *ctx_err; + + pei_len = sizeof(struct cper_arm_err_info) * err->err_info_num; + pei_err = (u8 *)(err + 1); + + err_info = (struct cper_arm_err_info *)(err + 1); + ctx_info = (struct cper_arm_ctx_info *)(err_info + err->err_info_num); + ctx_err = (u8 *)ctx_info; + + for (n = 0; n < err->context_info_num; n++) { + sz = sizeof(struct cper_arm_ctx_info) + ctx_info->size; + ctx_info = (struct cper_arm_ctx_info *)((long)ctx_info + sz); + ctx_len += sz; + } + + vsei_len = err->section_length - (sizeof(struct cper_sec_proc_arm) + pei_len + ctx_len); + if (vsei_len < 0) { + pr_warn(FW_BUG "section length: %d\n", err->section_length); + pr_warn(FW_BUG "section length is too small\n"); + pr_warn(FW_BUG "firmware-generated error record is incorrect\n"); + vsei_len = 0; + } + ven_err_data = (u8 *)ctx_info; + + cpu = GET_LOGICAL_INDEX(err->mpidr); + if (cpu < 0) + cpu = -1; + + trace_arm_event(err, pei_err, pei_len, ctx_err, ctx_len, + ven_err_data, (u32)vsei_len, sev, cpu); } static int __init ras_init(void) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index dd7b10e768c06c..17c60d9547dc50 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1431,6 +1431,33 @@ static int set_machine_constraints(struct regulator_dev *rdev) int ret = 0; const struct regulator_ops *ops = rdev->desc->ops; + /* + * If there is no mechanism for controlling the regulator then + * flag it as always_on so we don't end up duplicating checks + * for this so much. Note that we could control the state of + * a supply to control the output on a regulator that has no + * direct control. + */ + if (!rdev->ena_pin && !ops->enable) { + if (rdev->supply_name && !rdev->supply) + return -EPROBE_DEFER; + + if (rdev->supply) + rdev->constraints->always_on = + rdev->supply->rdev->constraints->always_on; + else + rdev->constraints->always_on = true; + } + + /* + * If we want to enable this regulator, make sure that we know the + * supplying regulator. + */ + if (rdev->constraints->always_on || rdev->constraints->boot_on) { + if (rdev->supply_name && !rdev->supply) + return -EPROBE_DEFER; + } + ret = machine_constraints_voltage(rdev, rdev->constraints); if (ret != 0) return ret; @@ -1596,35 +1623,15 @@ static int set_machine_constraints(struct regulator_dev *rdev) } } - /* - * If there is no mechanism for controlling the regulator then - * flag it as always_on so we don't end up duplicating checks - * for this so much. Note that we could control the state of - * a supply to control the output on a regulator that has no - * direct control. - */ - if (!rdev->ena_pin && !ops->enable) { - if (rdev->supply_name && !rdev->supply) - return -EPROBE_DEFER; - - if (rdev->supply) - rdev->constraints->always_on = - rdev->supply->rdev->constraints->always_on; - else - rdev->constraints->always_on = true; - } - /* If the constraints say the regulator should be on at this point * and we have control then make sure it is enabled. */ if (rdev->constraints->always_on || rdev->constraints->boot_on) { - /* If we want to enable this regulator, make sure that we know - * the supplying regulator. - */ - if (rdev->supply_name && !rdev->supply) - return -EPROBE_DEFER; + bool supply_enabled = false; - /* If supplying regulator has already been enabled, + /* We have ensured a potential supply has been resolved above. + * + * If supplying regulator has already been enabled, * it's not intended to have use_count increment * when rdev is only boot-on. */ @@ -1637,11 +1644,14 @@ static int set_machine_constraints(struct regulator_dev *rdev) rdev->supply = NULL; return ret; } + supply_enabled = true; } ret = _regulator_do_enable(rdev); if (ret < 0 && ret != -EINVAL) { rdev_err(rdev, "failed to enable: %pe\n", ERR_PTR(ret)); + if (supply_enabled) + regulator_disable(rdev->supply); return ret; } @@ -1942,6 +1952,7 @@ static void regulator_supply_alias(struct device **dev, const char **supply) { struct regulator_supply_alias *map; + mutex_lock(®ulator_list_mutex); map = regulator_find_supply_alias(*dev, *supply); if (map) { dev_dbg(*dev, "Mapping supply %s to %s,%s\n", @@ -1950,6 +1961,7 @@ static void regulator_supply_alias(struct device **dev, const char **supply) *dev = map->alias_dev; *supply = map->alias_supply; } + mutex_unlock(®ulator_list_mutex); } static int regulator_match(struct device *dev, const void *data) @@ -2492,22 +2504,26 @@ int regulator_register_supply_alias(struct device *dev, const char *id, const char *alias_id) { struct regulator_supply_alias *map; + struct regulator_supply_alias *new_map; - map = regulator_find_supply_alias(dev, id); - if (map) - return -EEXIST; - - map = kzalloc(sizeof(struct regulator_supply_alias), GFP_KERNEL); - if (!map) + new_map = kzalloc(sizeof(struct regulator_supply_alias), GFP_KERNEL); + if (!new_map) return -ENOMEM; - map->src_dev = dev; - map->src_supply = id; - map->alias_dev = alias_dev; - map->alias_supply = alias_id; - - list_add(&map->list, ®ulator_supply_alias_list); + mutex_lock(®ulator_list_mutex); + map = regulator_find_supply_alias(dev, id); + if (map) { + mutex_unlock(®ulator_list_mutex); + kfree(new_map); + return -EEXIST; + } + new_map->src_dev = dev; + new_map->src_supply = id; + new_map->alias_dev = alias_dev; + new_map->alias_supply = alias_id; + list_add(&new_map->list, ®ulator_supply_alias_list); + mutex_unlock(®ulator_list_mutex); pr_info("Adding alias for supply %s,%s -> %s,%s\n", id, dev_name(dev), alias_id, dev_name(alias_dev)); @@ -2527,11 +2543,13 @@ void regulator_unregister_supply_alias(struct device *dev, const char *id) { struct regulator_supply_alias *map; + mutex_lock(®ulator_list_mutex); map = regulator_find_supply_alias(dev, id); if (map) { list_del(&map->list); kfree(map); } + mutex_unlock(®ulator_list_mutex); } EXPORT_SYMBOL_GPL(regulator_unregister_supply_alias); diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c index a2d16e9abfb58d..254c0a8a455594 100644 --- a/drivers/regulator/fixed.c +++ b/drivers/regulator/fixed.c @@ -330,13 +330,10 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev) drvdata->dev = devm_regulator_register(&pdev->dev, &drvdata->desc, &cfg); - if (IS_ERR(drvdata->dev)) { - ret = dev_err_probe(&pdev->dev, PTR_ERR(drvdata->dev), - "Failed to register regulator: %ld\n", - PTR_ERR(drvdata->dev)); - gpiod_put(cfg.ena_gpiod); - return ret; - } + if (IS_ERR(drvdata->dev)) + return dev_err_probe(&pdev->dev, PTR_ERR(drvdata->dev), + "Failed to register regulator: %ld\n", + PTR_ERR(drvdata->dev)); platform_set_drvdata(pdev, drvdata); diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index 4be270f4d6c35a..91b96dbab328bd 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -1251,10 +1251,9 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) * to this signal (if SION bit is set in IOMUX). */ pca9450->sd_vsel_gpio = gpiod_get_optional(&ldo5->dev, "sd-vsel", GPIOD_IN); - if (IS_ERR(pca9450->sd_vsel_gpio)) { - dev_err(&i2c->dev, "Failed to get SD_VSEL GPIO\n"); - return ret; - } + if (IS_ERR(pca9450->sd_vsel_gpio)) + return dev_err_probe(&i2c->dev, PTR_ERR(pca9450->sd_vsel_gpio), + "Failed to get SD_VSEL GPIO\n"); pca9450->sd_vsel_fixed_low = of_property_read_bool(ldo5->dev.of_node, "nxp,sd-vsel-fixed-low"); diff --git a/drivers/regulator/spacemit-p1.c b/drivers/regulator/spacemit-p1.c index d437e6738ea1e3..2b585ba01a93d0 100644 --- a/drivers/regulator/spacemit-p1.c +++ b/drivers/regulator/spacemit-p1.c @@ -87,13 +87,13 @@ static const struct linear_range p1_ldo_ranges[] = { } #define P1_BUCK_DESC(_n) \ - P1_REG_DESC(BUCK, buck, _n, "vcc", 0x47, BUCK_MASK, 254, p1_buck_ranges) + P1_REG_DESC(BUCK, buck, _n, "vin", 0x47, BUCK_MASK, 255, p1_buck_ranges) #define P1_ALDO_DESC(_n) \ - P1_REG_DESC(ALDO, aldo, _n, "vcc", 0x5b, LDO_MASK, 117, p1_ldo_ranges) + P1_REG_DESC(ALDO, aldo, _n, "vin", 0x5b, LDO_MASK, 128, p1_ldo_ranges) #define P1_DLDO_DESC(_n) \ - P1_REG_DESC(DLDO, dldo, _n, "buck5", 0x67, LDO_MASK, 117, p1_ldo_ranges) + P1_REG_DESC(DLDO, dldo, _n, "buck5", 0x67, LDO_MASK, 128, p1_ldo_ranges) static const struct regulator_desc p1_regulator_desc[] = { P1_BUCK_DESC(1), diff --git a/drivers/remoteproc/imx_dsp_rproc.c b/drivers/remoteproc/imx_dsp_rproc.c index 6e78a01755c7bd..e61a08df113e4d 100644 --- a/drivers/remoteproc/imx_dsp_rproc.c +++ b/drivers/remoteproc/imx_dsp_rproc.c @@ -1026,9 +1026,11 @@ static int imx_dsp_rproc_load(struct rproc *rproc, const struct firmware *fw) * Clear buffers after pm rumtime for internal ocram is not * accessible if power and clock are not enabled. */ - list_for_each_entry(carveout, &rproc->carveouts, node) { - if (carveout->va) - memset(carveout->va, 0, carveout->len); + if (rproc->state == RPROC_OFFLINE) { + list_for_each_entry(carveout, &rproc->carveouts, node) { + if (carveout->va) + memset(carveout->va, 0, carveout->len); + } } ret = imx_dsp_rproc_elf_load_segments(rproc, fw); diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c index bb25221a4a8987..8424e6ea5569b9 100644 --- a/drivers/remoteproc/imx_rproc.c +++ b/drivers/remoteproc/imx_rproc.c @@ -1136,11 +1136,16 @@ static int imx_rproc_probe(struct platform_device *pdev) ret = rproc_add(rproc); if (ret) { dev_err(dev, "rproc_add failed\n"); - goto err_put_clk; + goto err_put_pm; } return 0; +err_put_pm: + if (dcfg->method == IMX_RPROC_SCU_API) { + pm_runtime_disable(dev); + pm_runtime_put_noidle(dev); + } err_put_clk: clk_disable_unprepare(priv->clk); err_put_scu: @@ -1160,7 +1165,7 @@ static void imx_rproc_remove(struct platform_device *pdev) if (priv->dcfg->method == IMX_RPROC_SCU_API) { pm_runtime_disable(priv->dev); - pm_runtime_put(priv->dev); + pm_runtime_put_noidle(priv->dev); } clk_disable_unprepare(priv->clk); rproc_del(rproc); diff --git a/drivers/remoteproc/qcom_q6v5_wcss.c b/drivers/remoteproc/qcom_q6v5_wcss.c index 07c88623f59785..23ec87827d4f81 100644 --- a/drivers/remoteproc/qcom_q6v5_wcss.c +++ b/drivers/remoteproc/qcom_q6v5_wcss.c @@ -85,7 +85,7 @@ #define TCSR_WCSS_CLK_MASK 0x1F #define TCSR_WCSS_CLK_ENABLE 0x14 -#define MAX_HALT_REG 3 +#define MAX_HALT_REG 4 enum { WCSS_IPQ8074, WCSS_QCS404, @@ -864,9 +864,9 @@ static int q6v5_wcss_init_mmio(struct q6v5_wcss *wcss, return -EINVAL; } - wcss->halt_q6 = halt_reg[0]; - wcss->halt_wcss = halt_reg[1]; - wcss->halt_nc = halt_reg[2]; + wcss->halt_q6 = halt_reg[1]; + wcss->halt_wcss = halt_reg[2]; + wcss->halt_nc = halt_reg[3]; return 0; } diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig index 78b7078478d46d..b3b9e0f9d8c485 100644 --- a/drivers/reset/Kconfig +++ b/drivers/reset/Kconfig @@ -150,7 +150,7 @@ config RESET_K210 config RESET_K230 tristate "Reset controller driver for Canaan Kendryte K230 SoC" depends on ARCH_CANAAN || COMPILE_TEST - depends on OF + default ARCH_CANAAN help Support for the Canaan Kendryte K230 RISC-V SoC reset controller. Say Y if you want to control reset signals provided by this diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c index 820a6ca5b1d7a6..3a15d9d108089f 100644 --- a/drivers/rpmsg/qcom_glink_native.c +++ b/drivers/rpmsg/qcom_glink_native.c @@ -1399,6 +1399,7 @@ static void qcom_glink_destroy_ept(struct rpmsg_endpoint *ept) { struct glink_channel *channel = to_glink_channel(ept); struct qcom_glink *glink = channel->glink; + struct rpmsg_channel_info chinfo; unsigned long flags; spin_lock_irqsave(&channel->recv_lock, flags); @@ -1406,6 +1407,13 @@ static void qcom_glink_destroy_ept(struct rpmsg_endpoint *ept) spin_unlock_irqrestore(&channel->recv_lock, flags); /* Decouple the potential rpdev from the channel */ + if (channel->rpdev) { + strscpy_pad(chinfo.name, channel->name, sizeof(chinfo.name)); + chinfo.src = RPMSG_ADDR_ANY; + chinfo.dst = RPMSG_ADDR_ANY; + + rpmsg_unregister_device(glink->dev, &chinfo); + } channel->rpdev = NULL; qcom_glink_send_close_req(glink, channel); diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 2933c41c77c88e..cf3fa1475ffd05 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -2074,6 +2074,17 @@ config RTC_DRV_WILCO_EC This can also be built as a module. If so, the module will be named "rtc_wilco_ec". +config RTC_DRV_MACSMC + tristate "Apple Mac System Management Controller RTC" + depends on MFD_MACSMC + help + If you say yes here you get support for RTC functions + inside Apple SPMI PMUs accessed through the SoC's + System Management Controller + + To compile this driver as a module, choose M here: the + module will be called rtc-macsmc. + config RTC_DRV_MSC313 tristate "MStar MSC313 RTC" depends on ARCH_MSTARV7 || COMPILE_TEST diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index 8221bda6e6dcab..0485b09caceba4 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -93,6 +93,7 @@ obj-$(CONFIG_RTC_DRV_M48T35) += rtc-m48t35.o obj-$(CONFIG_RTC_DRV_M48T59) += rtc-m48t59.o obj-$(CONFIG_RTC_DRV_M48T86) += rtc-m48t86.o obj-$(CONFIG_RTC_DRV_MA35D1) += rtc-ma35d1.o +obj-$(CONFIG_RTC_DRV_MACSMC) += rtc-macsmc.o obj-$(CONFIG_RTC_DRV_MAX31335) += rtc-max31335.o obj-$(CONFIG_RTC_DRV_MAX6900) += rtc-max6900.o obj-$(CONFIG_RTC_DRV_MAX6902) += rtc-max6902.o diff --git a/drivers/rtc/rtc-amlogic-a4.c b/drivers/rtc/rtc-amlogic-a4.c index 1928b29c10454d..d766055d958488 100644 --- a/drivers/rtc/rtc-amlogic-a4.c +++ b/drivers/rtc/rtc-amlogic-a4.c @@ -371,7 +371,7 @@ static int aml_rtc_probe(struct platform_device *pdev) } ret = devm_request_irq(dev, rtc->irq, aml_rtc_handler, - IRQF_ONESHOT, "aml-rtc alarm", rtc); + 0, "aml-rtc alarm", rtc); if (ret) { dev_err_probe(dev, ret, "IRQ%d request failed, ret = %d\n", rtc->irq, ret); @@ -390,7 +390,6 @@ static int aml_rtc_probe(struct platform_device *pdev) return 0; err_clk: - clk_disable_unprepare(rtc->sys_clk); device_init_wakeup(dev, false); return ret; @@ -423,9 +422,6 @@ static SIMPLE_DEV_PM_OPS(aml_rtc_pm_ops, static void aml_rtc_remove(struct platform_device *pdev) { - struct aml_rtc_data *rtc = dev_get_drvdata(&pdev->dev); - - clk_disable_unprepare(rtc->sys_clk); device_init_wakeup(&pdev->dev, false); } diff --git a/drivers/rtc/rtc-gamecube.c b/drivers/rtc/rtc-gamecube.c index c828bc8e05b9cc..045d5d45ab4b07 100644 --- a/drivers/rtc/rtc-gamecube.c +++ b/drivers/rtc/rtc-gamecube.c @@ -242,6 +242,10 @@ static int gamecube_rtc_read_offset_from_sram(struct priv *d) } hw_srnprot = ioremap(res.start, resource_size(&res)); + if (!hw_srnprot) { + pr_err("failed to ioremap hw_srnprot\n"); + return -ENOMEM; + } old = ioread32be(hw_srnprot); /* TODO: figure out why we use this magic constant. I obtained it by diff --git a/drivers/rtc/rtc-macsmc.c b/drivers/rtc/rtc-macsmc.c new file mode 100644 index 00000000000000..05e360277f630f --- /dev/null +++ b/drivers/rtc/rtc-macsmc.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Apple SMC RTC driver + * Copyright The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* 48-bit RTC */ +#define RTC_BYTES 6 +#define RTC_BITS (8 * RTC_BYTES) + +/* 32768 Hz clock */ +#define RTC_SEC_SHIFT 15 + +struct macsmc_rtc { + struct device *dev; + struct apple_smc *smc; + struct rtc_device *rtc_dev; + struct nvmem_cell *rtc_offset; +}; + +static int macsmc_rtc_get_time(struct device *dev, struct rtc_time *tm) +{ + struct macsmc_rtc *rtc = dev_get_drvdata(dev); + u64 ctr = 0, off = 0; + time64_t now; + void *p_off; + size_t len; + int ret; + + ret = apple_smc_read(rtc->smc, SMC_KEY(CLKM), &ctr, RTC_BYTES); + if (ret < 0) + return ret; + if (ret != RTC_BYTES) + return -EIO; + + p_off = nvmem_cell_read(rtc->rtc_offset, &len); + if (IS_ERR(p_off)) + return PTR_ERR(p_off); + if (len < RTC_BYTES) { + kfree(p_off); + return -EIO; + } + + memcpy(&off, p_off, RTC_BYTES); + kfree(p_off); + + /* Sign extend from 48 to 64 bits, then arithmetic shift right 15 bits to get seconds */ + now = sign_extend64(ctr + off, RTC_BITS - 1) >> RTC_SEC_SHIFT; + rtc_time64_to_tm(now, tm); + + return ret; +} + +static int macsmc_rtc_set_time(struct device *dev, struct rtc_time *tm) +{ + struct macsmc_rtc *rtc = dev_get_drvdata(dev); + u64 ctr = 0, off = 0; + int ret; + + ret = apple_smc_read(rtc->smc, SMC_KEY(CLKM), &ctr, RTC_BYTES); + if (ret < 0) + return ret; + if (ret != RTC_BYTES) + return -EIO; + + /* This sets the offset such that the set second begins now */ + off = (rtc_tm_to_time64(tm) << RTC_SEC_SHIFT) - ctr; + return nvmem_cell_write(rtc->rtc_offset, &off, RTC_BYTES); +} + +static const struct rtc_class_ops macsmc_rtc_ops = { + .read_time = macsmc_rtc_get_time, + .set_time = macsmc_rtc_set_time, +}; + +static int macsmc_rtc_probe(struct platform_device *pdev) +{ + struct apple_smc *smc = dev_get_drvdata(pdev->dev.parent); + struct macsmc_rtc *rtc; + + /* + * MFD will probe this device even without a node in the device tree, + * thus bail out early if the SMC on the current machines does not + * support RTC and has no node in the device tree. + */ + if (!pdev->dev.of_node) + return -ENODEV; + + rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL); + if (!rtc) + return -ENOMEM; + + rtc->dev = &pdev->dev; + rtc->smc = smc; + + rtc->rtc_offset = devm_nvmem_cell_get(&pdev->dev, "rtc_offset"); + if (IS_ERR(rtc->rtc_offset)) + return dev_err_probe(&pdev->dev, PTR_ERR(rtc->rtc_offset), + "Failed to get rtc_offset NVMEM cell\n"); + + rtc->rtc_dev = devm_rtc_allocate_device(&pdev->dev); + if (IS_ERR(rtc->rtc_dev)) + return PTR_ERR(rtc->rtc_dev); + + rtc->rtc_dev->ops = &macsmc_rtc_ops; + rtc->rtc_dev->range_min = S64_MIN >> (RTC_SEC_SHIFT + (64 - RTC_BITS)); + rtc->rtc_dev->range_max = S64_MAX >> (RTC_SEC_SHIFT + (64 - RTC_BITS)); + + platform_set_drvdata(pdev, rtc); + + return devm_rtc_register_device(rtc->rtc_dev); +} + +static const struct of_device_id macsmc_rtc_of_table[] = { + { .compatible = "apple,smc-rtc", }, + {} +}; +MODULE_DEVICE_TABLE(of, macsmc_rtc_of_table); + +static struct platform_driver macsmc_rtc_driver = { + .driver = { + .name = "macsmc-rtc", + .of_match_table = macsmc_rtc_of_table, + }, + .probe = macsmc_rtc_probe, +}; +module_platform_driver(macsmc_rtc_driver); + +MODULE_LICENSE("Dual MIT/GPL"); +MODULE_DESCRIPTION("Apple SMC RTC driver"); +MODULE_AUTHOR("Hector Martin "); diff --git a/drivers/rtc/rtc-max31335.c b/drivers/rtc/rtc-max31335.c index dfb5bad3a3691d..23b7bf16b4cd5d 100644 --- a/drivers/rtc/rtc-max31335.c +++ b/drivers/rtc/rtc-max31335.c @@ -391,10 +391,8 @@ static int max31335_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) if (ret) return ret; - ret = regmap_update_bits(max31335->regmap, max31335->chip->int_status_reg, - MAX31335_STATUS1_A1F, 0); - - return 0; + return regmap_update_bits(max31335->regmap, max31335->chip->int_status_reg, + MAX31335_STATUS1_A1F, 0); } static int max31335_alarm_irq_enable(struct device *dev, unsigned int enabled) diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 88fa17aea2ec84..ec0c62e5ef73b6 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -6150,6 +6150,7 @@ static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid struct dasd_copy_relation *copy; struct dasd_block *block; struct gendisk *gdp; + int rc; copy = device->copy; if (!copy) @@ -6184,6 +6185,13 @@ static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid /* swap blocklayer device link */ gdp = block->gdp; dasd_add_link_to_gendisk(gdp, secondary); + rc = device_move(disk_to_dev(gdp), &secondary->cdev->dev, DPM_ORDER_NONE); + if (rc) { + dev_err(&primary->cdev->dev, + "copy_pair_swap: moving blockdevice parent %s->%s failed (%d)\n", + dev_name(&primary->cdev->dev), + dev_name(&secondary->cdev->dev), rc); + } /* re-enable device */ dasd_device_remove_stop_bits(primary, DASD_STOPPED_PPRC); diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index be78a57f9bfdef..8a70596a55447c 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -236,7 +236,7 @@ struct subchannel *css_alloc_subchannel(struct subchannel_id schid, return sch; err: - kfree(sch); + put_device(&sch->dev); return ERR_PTR(ret); } diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 65f1a127cc3f6b..dfd5d0f61a70de 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -2484,15 +2484,15 @@ static int __init ap_module_init(void) { int rc; - rc = ap_debug_init(); - if (rc) - return rc; - if (!ap_instructions_available()) { pr_warn("The hardware system does not support AP instructions\n"); return -ENODEV; } + rc = ap_debug_init(); + if (rc) + return rc; + /* init ap_queue hashtable */ hash_init(ap_queues); diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c index ce953cbbd56403..64a7f645eaf49c 100644 --- a/drivers/s390/crypto/ap_card.c +++ b/drivers/s390/crypto/ap_card.c @@ -44,7 +44,7 @@ static ssize_t depth_show(struct device *dev, struct device_attribute *attr, { struct ap_card *ac = to_ap_card(dev); - return sysfs_emit(buf, "%d\n", ac->hwinfo.qd); + return sysfs_emit(buf, "%d\n", ac->hwinfo.qd + 1); } static DEVICE_ATTR_RO(depth); diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 8977866fab1bcd..42ffb22aa1e2e7 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -269,7 +269,7 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq) list_move_tail(&ap_msg->list, &aq->pendingq); aq->requestq_count--; aq->pendingq_count++; - if (aq->queue_count < aq->card->hwinfo.qd) { + if (aq->queue_count < aq->card->hwinfo.qd + 1) { aq->sm_state = AP_SM_STATE_WORKING; return AP_SM_WAIT_AGAIN; } diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c index adf3d91456064e..95f3620059f7dc 100644 --- a/drivers/scsi/aic94xx/aic94xx_init.c +++ b/drivers/scsi/aic94xx/aic94xx_init.c @@ -882,6 +882,9 @@ static void asd_pci_remove(struct pci_dev *dev) asd_disable_ints(asd_ha); + /* Ensure all scheduled tasklets complete before freeing resources */ + tasklet_kill(&asd_ha->seq.dl_tasklet); + asd_remove_dev_attrs(asd_ha); /* XXX more here as needed */ diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c index 4e899ec1477d46..b1cba986f0fbd3 100644 --- a/drivers/scsi/be2iscsi/be_mgmt.c +++ b/drivers/scsi/be2iscsi/be_mgmt.c @@ -1025,6 +1025,7 @@ unsigned int beiscsi_boot_get_sinfo(struct beiscsi_hba *phba) &nonemb_cmd->dma, GFP_KERNEL); if (!nonemb_cmd->va) { + free_mcc_wrb(ctrl, tag); mutex_unlock(&ctrl->mbox_lock); return 0; } diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c index ff9adfc0b332e2..bdfd0651667187 100644 --- a/drivers/scsi/bfa/bfad.c +++ b/drivers/scsi/bfa/bfad.c @@ -1528,7 +1528,6 @@ bfad_pci_slot_reset(struct pci_dev *pdev) goto out_disable_device; } - pci_save_state(pdev); pci_set_master(pdev); rc = dma_set_mask_and_coherent(&bfad->pcidev->dev, DMA_BIT_MASK(64)); diff --git a/drivers/scsi/csiostor/csio_init.c b/drivers/scsi/csiostor/csio_init.c index 79c8dafdd49ed2..db0c2174430ac2 100644 --- a/drivers/scsi/csiostor/csio_init.c +++ b/drivers/scsi/csiostor/csio_init.c @@ -1093,7 +1093,6 @@ csio_pci_slot_reset(struct pci_dev *pdev) pci_set_master(pdev); pci_restore_state(pdev); - pci_save_state(pdev); /* Bring HW s/m to ready state. * but don't resume IOs. diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c index 34bde6650fae0f..356a7c577ec3ef 100644 --- a/drivers/scsi/csiostor/csio_scsi.c +++ b/drivers/scsi/csiostor/csio_scsi.c @@ -2074,7 +2074,7 @@ csio_eh_lun_reset_handler(struct scsi_cmnd *cmnd) struct csio_scsi_level_data sld; if (!rn) - goto fail; + goto fail_ret; csio_dbg(hw, "Request to reset LUN:%llu (ssni:0x%x tgtid:%d)\n", cmnd->device->lun, rn->flowid, rn->scsi_id); @@ -2220,6 +2220,7 @@ csio_eh_lun_reset_handler(struct scsi_cmnd *cmnd) csio_put_scsi_ioreq_lock(hw, scsim, ioreq); fail: CSIO_INC_STATS(rn, n_lun_rst_fail); +fail_ret: return FAILED; } diff --git a/drivers/scsi/elx/efct/efct_driver.c b/drivers/scsi/elx/efct/efct_driver.c index 1bd42f7db1773d..528399f725d428 100644 --- a/drivers/scsi/elx/efct/efct_driver.c +++ b/drivers/scsi/elx/efct/efct_driver.c @@ -415,12 +415,6 @@ efct_intr_thread(int irq, void *handle) return IRQ_HANDLED; } -static irqreturn_t -efct_intr_msix(int irq, void *handle) -{ - return IRQ_WAKE_THREAD; -} - static int efct_setup_msix(struct efct *efct, u32 num_intrs) { @@ -450,7 +444,7 @@ efct_setup_msix(struct efct *efct, u32 num_intrs) intr_ctx->index = i; rc = request_threaded_irq(pci_irq_vector(efct->pci, i), - efct_intr_msix, efct_intr_thread, 0, + NULL, efct_intr_thread, IRQF_ONESHOT, EFCT_DRIVER_NAME, intr_ctx); if (rc) { dev_err(&efct->pci->dev, diff --git a/drivers/scsi/imm.c b/drivers/scsi/imm.c index 5c602c0577989f..45b0e33293a591 100644 --- a/drivers/scsi/imm.c +++ b/drivers/scsi/imm.c @@ -1260,6 +1260,7 @@ static void imm_detach(struct parport *pb) imm_struct *dev; list_for_each_entry(dev, &imm_hosts, list) { if (dev->dev->port == pb) { + disable_delayed_work_sync(&dev->imm_tq); list_del_init(&dev->list); scsi_remove_host(dev->host); scsi_host_put(dev->host); diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 44214884deaf50..dbd58a7e7bc1f3 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -61,8 +61,8 @@ #include #include #include +#include #include -#include #include #include #include @@ -7843,6 +7843,30 @@ static int ipr_dump_mailbox_wait(struct ipr_cmnd *ipr_cmd) return IPR_RC_JOB_RETURN; } +/** + * ipr_set_affinity_nobalance + * @ioa_cfg: ipr_ioa_cfg struct for an ipr device + * @flag: bool + * true: ensable "IRQ_NO_BALANCING" bit for msix interrupt + * false: disable "IRQ_NO_BALANCING" bit for msix interrupt + * Description: This function will be called to disable/enable + * "IRQ_NO_BALANCING" to avoid irqbalance daemon + * kicking in during adapter reset. + **/ +static void ipr_set_affinity_nobalance(struct ipr_ioa_cfg *ioa_cfg, bool flag) +{ + int irq, i; + + for (i = 0; i < ioa_cfg->nvectors; i++) { + irq = pci_irq_vector(ioa_cfg->pdev, i); + + if (flag) + irq_set_status_flags(irq, IRQ_NO_BALANCING); + else + irq_clear_status_flags(irq, IRQ_NO_BALANCING); + } +} + /** * ipr_reset_restore_cfg_space - Restore PCI config space. * @ipr_cmd: ipr command struct @@ -7859,7 +7883,6 @@ static int ipr_reset_restore_cfg_space(struct ipr_cmnd *ipr_cmd) struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg; ENTER; - ioa_cfg->pdev->state_saved = true; pci_restore_state(ioa_cfg->pdev); if (ipr_set_pcix_cmd_reg(ioa_cfg)) { @@ -7867,6 +7890,7 @@ static int ipr_reset_restore_cfg_space(struct ipr_cmnd *ipr_cmd) return IPR_RC_JOB_CONTINUE; } + ipr_set_affinity_nobalance(ioa_cfg, false); ipr_fail_all_ops(ioa_cfg); if (ioa_cfg->sis64) { @@ -7946,6 +7970,7 @@ static int ipr_reset_start_bist(struct ipr_cmnd *ipr_cmd) rc = pci_write_config_byte(ioa_cfg->pdev, PCI_BIST, PCI_BIST_START); if (rc == PCIBIOS_SUCCESSFUL) { + ipr_set_affinity_nobalance(ioa_cfg, true); ipr_cmd->job_step = ipr_reset_bist_done; ipr_reset_start_timer(ipr_cmd, IPR_WAIT_FOR_BIST_TIMEOUT); rc = IPR_RC_JOB_RETURN; diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h index 6706f2be8d274b..da5408c701cddf 100644 --- a/drivers/scsi/libsas/sas_internal.h +++ b/drivers/scsi/libsas/sas_internal.h @@ -145,20 +145,6 @@ static inline void sas_fail_probe(struct domain_device *dev, const char *func, i func, dev->parent ? "exp-attached" : "direct-attached", SAS_ADDR(dev->sas_addr), err); - - /* - * If the device probe failed, the expander phy attached address - * needs to be reset so that the phy will not be treated as flutter - * in the next revalidation - */ - if (dev->parent && !dev_is_expander(dev->dev_type)) { - struct sas_phy *phy = dev->phy; - struct domain_device *parent = dev->parent; - struct ex_phy *ex_phy = &parent->ex_dev.ex_phy[phy->number]; - - memset(ex_phy->attached_sas_addr, 0, SAS_ADDR_SIZE); - } - sas_unregister_dev(dev->port, dev); } diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index b71db7d7d747d2..c08237f04bce27 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -934,10 +934,15 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, /* Check to see if link went down during discovery */ if (lpfc_els_chk_latt(vport)) { /* One additional decrement on node reference count to - * trigger the release of the node + * trigger the release of the node. Make sure the ndlp + * is marked NLP_DROPPED. */ - if (!(ndlp->fc4_xpt_flags & SCSI_XPT_REGD)) + if (!test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag) && + !test_bit(NLP_DROPPED, &ndlp->nlp_flag) && + !(ndlp->fc4_xpt_flags & SCSI_XPT_REGD)) { + set_bit(NLP_DROPPED, &ndlp->nlp_flag); lpfc_nlp_put(ndlp); + } goto out; } @@ -995,9 +1000,10 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, IOERR_LOOP_OPEN_FAILURE))) lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, "2858 FLOGI Status:x%x/x%x TMO" - ":x%x Data x%lx x%x\n", + ":x%x Data x%lx x%x x%lx x%x\n", ulp_status, ulp_word4, tmo, - phba->hba_flag, phba->fcf.fcf_flag); + phba->hba_flag, phba->fcf.fcf_flag, + ndlp->nlp_flag, ndlp->fc4_xpt_flags); /* Check for retry */ if (lpfc_els_retry(phba, cmdiocb, rspiocb)) { @@ -1015,14 +1021,17 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, * reference to trigger node release. */ if (!test_bit(NLP_IN_DEV_LOSS, &ndlp->nlp_flag) && - !(ndlp->fc4_xpt_flags & SCSI_XPT_REGD)) + !test_bit(NLP_DROPPED, &ndlp->nlp_flag) && + !(ndlp->fc4_xpt_flags & SCSI_XPT_REGD)) { + set_bit(NLP_DROPPED, &ndlp->nlp_flag); lpfc_nlp_put(ndlp); + } lpfc_printf_vlog(vport, KERN_WARNING, LOG_ELS, "0150 FLOGI Status:x%x/x%x " - "xri x%x TMO:x%x refcnt %d\n", + "xri x%x iotag x%x TMO:x%x refcnt %d\n", ulp_status, ulp_word4, cmdiocb->sli4_xritag, - tmo, kref_read(&ndlp->kref)); + cmdiocb->iotag, tmo, kref_read(&ndlp->kref)); /* If this is not a loop open failure, bail out */ if (!(ulp_status == IOSTAT_LOCAL_REJECT && @@ -1279,6 +1288,19 @@ lpfc_issue_els_flogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, uint32_t tmo, did; int rc; + /* It's possible for lpfc to reissue a FLOGI on an ndlp that is marked + * NLP_DROPPED. This happens when the FLOGI completed with the XB bit + * set causing lpfc to reference the ndlp until the XRI_ABORTED CQE is + * issued. The time window for the XRI_ABORTED CQE can be as much as + * 2*2*RA_TOV allowing for ndlp reuse of this type when the link is + * cycling quickly. When true, restore the initial reference and remove + * the NLP_DROPPED flag as lpfc is retrying. + */ + if (test_and_clear_bit(NLP_DROPPED, &ndlp->nlp_flag)) { + if (!lpfc_nlp_get(ndlp)) + return 1; + } + cmdsize = (sizeof(uint32_t) + sizeof(struct serv_parm)); elsiocb = lpfc_prep_els_iocb(vport, 1, cmdsize, retry, ndlp, ndlp->nlp_DID, ELS_CMD_FLOGI); diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 43d246c5c049cb..717ae56c8e4bd9 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -424,6 +424,7 @@ lpfc_check_nlp_post_devloss(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) { if (test_and_clear_bit(NLP_IN_RECOV_POST_DEV_LOSS, &ndlp->save_flags)) { + clear_bit(NLP_DROPPED, &ndlp->nlp_flag); lpfc_nlp_get(ndlp); lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY | LOG_NODE, "8438 Devloss timeout reversed on DID x%x " @@ -566,7 +567,8 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) return fcf_inuse; } - lpfc_nlp_put(ndlp); + if (!test_and_set_bit(NLP_DROPPED, &ndlp->nlp_flag)) + lpfc_nlp_put(ndlp); return fcf_inuse; } diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index f206267d9ecdc1..065eb91de9c0f6 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -14434,12 +14434,6 @@ lpfc_io_slot_reset_s3(struct pci_dev *pdev) pci_restore_state(pdev); - /* - * As the new kernel behavior of pci_restore_state() API call clears - * device saved_state flag, need to save the restored state again. - */ - pci_save_state(pdev); - if (pdev->is_busmaster) pci_set_master(pdev); diff --git a/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h b/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h index b42933fcd42336..6561f98c3cb2da 100644 --- a/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h +++ b/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h @@ -166,6 +166,7 @@ struct mpi3_ioc_facts_data { #define MPI3_IOCFACTS_FLAGS_SIGNED_NVDATA_REQUIRED (0x00010000) #define MPI3_IOCFACTS_FLAGS_DMA_ADDRESS_WIDTH_MASK (0x0000ff00) #define MPI3_IOCFACTS_FLAGS_DMA_ADDRESS_WIDTH_SHIFT (8) +#define MPI3_IOCFACTS_FLAGS_MAX_REQ_PER_REPLY_QUEUE_LIMIT (0x00000040) #define MPI3_IOCFACTS_FLAGS_INITIAL_PORT_ENABLE_MASK (0x00000030) #define MPI3_IOCFACTS_FLAGS_INITIAL_PORT_ENABLE_SHIFT (4) #define MPI3_IOCFACTS_FLAGS_INITIAL_PORT_ENABLE_NOT_STARTED (0x00000000) diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h index 6742684e2990a7..31d68c151b2076 100644 --- a/drivers/scsi/mpi3mr/mpi3mr.h +++ b/drivers/scsi/mpi3mr/mpi3mr.h @@ -56,8 +56,8 @@ extern struct list_head mrioc_list; extern int prot_mask; extern atomic64_t event_counter; -#define MPI3MR_DRIVER_VERSION "8.15.0.5.50" -#define MPI3MR_DRIVER_RELDATE "12-August-2025" +#define MPI3MR_DRIVER_VERSION "8.15.0.5.51" +#define MPI3MR_DRIVER_RELDATE "18-November-2025" #define MPI3MR_DRIVER_NAME "mpi3mr" #define MPI3MR_DRIVER_LICENSE "GPL" diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index 8fe6e0bf342e25..8c4bb7169a87c3 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -3158,6 +3158,8 @@ static void mpi3mr_process_factsdata(struct mpi3mr_ioc *mrioc, mrioc->facts.dma_mask = (facts_flags & MPI3_IOCFACTS_FLAGS_DMA_ADDRESS_WIDTH_MASK) >> MPI3_IOCFACTS_FLAGS_DMA_ADDRESS_WIDTH_SHIFT; + mrioc->facts.max_req_limit = (facts_flags & + MPI3_IOCFACTS_FLAGS_MAX_REQ_PER_REPLY_QUEUE_LIMIT); mrioc->facts.protocol_flags = facts_data->protocol_flags; mrioc->facts.mpi_version = le32_to_cpu(facts_data->mpi_version.word); mrioc->facts.max_reqs = le16_to_cpu(facts_data->max_outstanding_requests); diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index b88633e1efe275..d4ca878d088697 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -1184,6 +1184,8 @@ static void mpi3mr_update_tgtdev(struct mpi3mr_ioc *mrioc, if (is_added == true) tgtdev->io_throttle_enabled = (flags & MPI3_DEVICE0_FLAGS_IO_THROTTLING_REQUIRED) ? 1 : 0; + if (!mrioc->sas_transport_enabled) + tgtdev->non_stl = 1; switch (flags & MPI3_DEVICE0_FLAGS_MAX_WRITE_SAME_MASK) { case MPI3_DEVICE0_FLAGS_MAX_WRITE_SAME_256_LB: @@ -4844,7 +4846,7 @@ static int mpi3mr_target_alloc(struct scsi_target *starget) spin_lock_irqsave(&mrioc->tgtdev_lock, flags); if (starget->channel == mrioc->scsi_device_channel) { tgt_dev = __mpi3mr_get_tgtdev_by_perst_id(mrioc, starget->id); - if (tgt_dev && !tgt_dev->is_hidden) { + if (tgt_dev && !tgt_dev->is_hidden && tgt_dev->non_stl) { scsi_tgt_priv_data->starget = starget; scsi_tgt_priv_data->dev_handle = tgt_dev->dev_handle; scsi_tgt_priv_data->perst_id = tgt_dev->perst_id; diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c index ccfc2d26dd3725..0798bfd0372e47 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -1546,8 +1546,9 @@ qla2x00_update_optrom(struct bsg_job *bsg_job) ha->optrom_buffer = NULL; ha->optrom_state = QLA_SWAITING; mutex_unlock(&ha->optrom_mutex); - bsg_job_done(bsg_job, bsg_reply->result, - bsg_reply->reply_payload_rcv_len); + if (!rval) + bsg_job_done(bsg_job, bsg_reply->result, + bsg_reply->reply_payload_rcv_len); return rval; } @@ -2612,8 +2613,9 @@ qla2x00_manage_host_stats(struct bsg_job *bsg_job) sizeof(struct ql_vnd_mng_host_stats_resp)); bsg_reply->result = DID_OK; - bsg_job_done(bsg_job, bsg_reply->result, - bsg_reply->reply_payload_rcv_len); + if (!ret) + bsg_job_done(bsg_job, bsg_reply->result, + bsg_reply->reply_payload_rcv_len); return ret; } @@ -2702,8 +2704,9 @@ qla2x00_get_host_stats(struct bsg_job *bsg_job) bsg_job->reply_payload.sg_cnt, data, response_len); bsg_reply->result = DID_OK; - bsg_job_done(bsg_job, bsg_reply->result, - bsg_reply->reply_payload_rcv_len); + if (!ret) + bsg_job_done(bsg_job, bsg_reply->result, + bsg_reply->reply_payload_rcv_len); kfree(data); host_stat_out: @@ -2802,8 +2805,9 @@ qla2x00_get_tgt_stats(struct bsg_job *bsg_job) bsg_job->reply_payload.sg_cnt, data, response_len); bsg_reply->result = DID_OK; - bsg_job_done(bsg_job, bsg_reply->result, - bsg_reply->reply_payload_rcv_len); + if (!ret) + bsg_job_done(bsg_job, bsg_reply->result, + bsg_reply->reply_payload_rcv_len); tgt_stat_out: kfree(data); @@ -2864,8 +2868,9 @@ qla2x00_manage_host_port(struct bsg_job *bsg_job) bsg_job->reply_payload.sg_cnt, &rsp_data, sizeof(struct ql_vnd_mng_host_port_resp)); bsg_reply->result = DID_OK; - bsg_job_done(bsg_job, bsg_reply->result, - bsg_reply->reply_payload_rcv_len); + if (!ret) + bsg_job_done(bsg_job, bsg_reply->result, + bsg_reply->reply_payload_rcv_len); return ret; } @@ -3240,7 +3245,8 @@ int qla2x00_mailbox_passthru(struct bsg_job *bsg_job) bsg_job->reply_len = sizeof(*bsg_job->reply); bsg_reply->result = DID_OK << 16; - bsg_job_done(bsg_job, bsg_reply->result, bsg_reply->reply_payload_rcv_len); + if (!ret) + bsg_job_done(bsg_job, bsg_reply->result, bsg_reply->reply_payload_rcv_len); kfree(req_data); diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index cb95b7b12051da..b3265952c4bed9 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -3503,7 +3503,6 @@ struct isp_operations { #define QLA_MSIX_RSP_Q 0x01 #define QLA_ATIO_VECTOR 0x02 #define QLA_MSIX_QPAIR_MULTIQ_RSP_Q 0x03 -#define QLA_MSIX_QPAIR_MULTIQ_RSP_Q_HS 0x04 #define QLA_MIDX_DEFAULT 0 #define QLA_MIDX_RSP_Q 1 diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index 145defc420f27a..55d531c19e6b22 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -766,7 +766,7 @@ extern int qla2x00_dfs_remove(scsi_qla_host_t *); /* Globa function prototypes for multi-q */ extern int qla25xx_request_irq(struct qla_hw_data *, struct qla_qpair *, - struct qla_msix_entry *, int); + struct qla_msix_entry *); extern int qla25xx_init_req_que(struct scsi_qla_host *, struct req_que *); extern int qla25xx_init_rsp_que(struct scsi_qla_host *, struct rsp_que *); extern int qla25xx_create_req_que(struct qla_hw_data *, uint16_t, uint8_t, diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index 51c7cea71f9022..880cd73feaca45 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -3266,9 +3266,6 @@ void qla_fab_scan_finish(scsi_qla_host_t *vha, srb_t *sp) atomic_read(&fcport->state) == FCS_ONLINE) || do_delete) { if (fcport->loop_id != FC_NO_LOOP_ID) { - if (fcport->flags & FCF_FCP2_DEVICE) - continue; - ql_log(ql_log_warn, vha, 0x20f0, "%s %d %8phC post del sess\n", __func__, __LINE__, @@ -3535,8 +3532,8 @@ int qla_fab_async_scan(scsi_qla_host_t *vha, srb_t *sp) if (vha->scan.scan_flags & SF_SCANNING) { spin_unlock_irqrestore(&vha->work_lock, flags); ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x2012, - "%s: scan active\n", __func__); - return rval; + "%s: scan active for sp:%p\n", __func__, sp); + goto done_free_sp; } vha->scan.scan_flags |= SF_SCANNING; if (!sp) @@ -3701,23 +3698,25 @@ int qla_fab_async_scan(scsi_qla_host_t *vha, srb_t *sp) return rval; done_free_sp: - if (sp->u.iocb_cmd.u.ctarg.req) { - dma_free_coherent(&vha->hw->pdev->dev, - sp->u.iocb_cmd.u.ctarg.req_allocated_size, - sp->u.iocb_cmd.u.ctarg.req, - sp->u.iocb_cmd.u.ctarg.req_dma); - sp->u.iocb_cmd.u.ctarg.req = NULL; - } - if (sp->u.iocb_cmd.u.ctarg.rsp) { - dma_free_coherent(&vha->hw->pdev->dev, - sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, - sp->u.iocb_cmd.u.ctarg.rsp, - sp->u.iocb_cmd.u.ctarg.rsp_dma); - sp->u.iocb_cmd.u.ctarg.rsp = NULL; - } + if (sp) { + if (sp->u.iocb_cmd.u.ctarg.req) { + dma_free_coherent(&vha->hw->pdev->dev, + sp->u.iocb_cmd.u.ctarg.req_allocated_size, + sp->u.iocb_cmd.u.ctarg.req, + sp->u.iocb_cmd.u.ctarg.req_dma); + sp->u.iocb_cmd.u.ctarg.req = NULL; + } + if (sp->u.iocb_cmd.u.ctarg.rsp) { + dma_free_coherent(&vha->hw->pdev->dev, + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, + sp->u.iocb_cmd.u.ctarg.rsp, + sp->u.iocb_cmd.u.ctarg.rsp_dma); + sp->u.iocb_cmd.u.ctarg.rsp = NULL; + } - /* ref: INIT */ - kref_put(&sp->cmd_kref, qla2x00_sp_release); + /* ref: INIT */ + kref_put(&sp->cmd_kref, qla2x00_sp_release); + } spin_lock_irqsave(&vha->work_lock, flags); vha->scan.scan_flags &= ~SF_SCANNING; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 6a2e1c7fd1251a..84f89445c74705 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1859,15 +1859,6 @@ void qla2x00_handle_rscn(scsi_qla_host_t *vha, struct event_arg *ea) case RSCN_PORT_ADDR: fcport = qla2x00_find_fcport_by_nportid(vha, &ea->id, 1); if (fcport) { - if (ql2xfc2target && - fcport->flags & FCF_FCP2_DEVICE && - atomic_read(&fcport->state) == FCS_ONLINE) { - ql_dbg(ql_dbg_disc, vha, 0x2115, - "Delaying session delete for FCP2 portid=%06x %8phC ", - fcport->d_id.b24, fcport->port_name); - return; - } - if (vha->hw->flags.edif_enabled && DBELL_ACTIVE(vha)) { /* * On ipsec start by remote port, Target port @@ -2471,8 +2462,23 @@ qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea) ea->sp->gen1, fcport->rscn_gen, ea->data[0], ea->data[1], ea->iop[0], ea->iop[1]); - if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) || - (fcport->fw_login_state == DSC_LS_PRLI_PEND)) { + if (fcport->fw_login_state == DSC_LS_PLOGI_PEND) { + ql_dbg(ql_dbg_disc, vha, 0x20ea, + "%s %d %8phC Remote is trying to login\n", + __func__, __LINE__, fcport->port_name); + /* + * If we get here, there is port thats already logged in, + * but it's state has not moved ahead. Recheck with FW on + * what state it is in and proceed ahead + */ + if (!N2N_TOPO(vha->hw)) { + fcport->fw_login_state = DSC_LS_PRLI_COMP; + qla24xx_post_gpdb_work(vha, fcport, 0); + } + return; + } + + if (fcport->fw_login_state == DSC_LS_PRLI_PEND) { ql_dbg(ql_dbg_disc, vha, 0x20ea, "%s %d %8phC Remote is trying to login\n", __func__, __LINE__, fcport->port_name); diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index c4c6b5c6658c07..608d2f36e7b4ff 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -878,6 +878,9 @@ qla27xx_copy_multiple_pkt(struct scsi_qla_host *vha, void **pkt, payload_size = sizeof(purex->els_frame_payload); } + if (total_bytes > sizeof(item->iocb.iocb)) + total_bytes = sizeof(item->iocb.iocb); + pending_bytes = total_bytes; no_bytes = (pending_bytes > payload_size) ? payload_size : pending_bytes; @@ -1163,6 +1166,10 @@ qla27xx_copy_fpin_pkt(struct scsi_qla_host *vha, void **pkt, total_bytes = (le16_to_cpu(purex->frame_size) & 0x0FFF) - PURX_ELS_HEADER_SIZE; + + if (total_bytes > sizeof(item->iocb.iocb)) + total_bytes = sizeof(item->iocb.iocb); + pending_bytes = total_bytes; entry_count = entry_count_remaining = purex->entry_count; no_bytes = (pending_bytes > sizeof(purex->els_frame_payload)) ? @@ -1669,13 +1676,28 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb) /* Port logout */ fcport = qla2x00_find_fcport_by_loopid(vha, mb[1]); - if (!fcport) + if (!fcport) { + ql_dbg(ql_dbg_async, vha, 0x5011, + "Could not find fcport:%04x %04x %04x\n", + mb[1], mb[2], mb[3]); break; - if (atomic_read(&fcport->state) != FCS_ONLINE) + } + + if (atomic_read(&fcport->state) != FCS_ONLINE) { + ql_dbg(ql_dbg_async, vha, 0x5012, + "Port state is not online State:0x%x \n", + atomic_read(&fcport->state)); + ql_dbg(ql_dbg_async, vha, 0x5012, + "Scheduling session for deletion \n"); + fcport->logout_on_delete = 0; + qlt_schedule_sess_for_deletion(fcport); break; + } + ql_dbg(ql_dbg_async, vha, 0x508a, "Marking port lost loopid=%04x portid=%06x.\n", fcport->loop_id, fcport->d_id.b24); + if (qla_ini_mode_enabled(vha)) { fcport->logout_on_delete = 0; qlt_schedule_sess_for_deletion(fcport); @@ -4467,32 +4489,6 @@ qla2xxx_msix_rsp_q(int irq, void *dev_id) return IRQ_HANDLED; } -irqreturn_t -qla2xxx_msix_rsp_q_hs(int irq, void *dev_id) -{ - struct qla_hw_data *ha; - struct qla_qpair *qpair; - struct device_reg_24xx __iomem *reg; - unsigned long flags; - - qpair = dev_id; - if (!qpair) { - ql_log(ql_log_info, NULL, 0x505b, - "%s: NULL response queue pointer.\n", __func__); - return IRQ_NONE; - } - ha = qpair->hw; - - reg = &ha->iobase->isp24; - spin_lock_irqsave(&ha->hardware_lock, flags); - wrt_reg_dword(®->hccr, HCCRX_CLR_RISC_INT); - spin_unlock_irqrestore(&ha->hardware_lock, flags); - - queue_work(ha->wq, &qpair->q_work); - - return IRQ_HANDLED; -} - /* Interrupt handling helpers. */ struct qla_init_msix_entry { @@ -4505,7 +4501,6 @@ static const struct qla_init_msix_entry msix_entries[] = { { "rsp_q", qla24xx_msix_rsp_q }, { "atio_q", qla83xx_msix_atio_q }, { "qpair_multiq", qla2xxx_msix_rsp_q }, - { "qpair_multiq_hs", qla2xxx_msix_rsp_q_hs }, }; static const struct qla_init_msix_entry qla82xx_msix_entries[] = { @@ -4792,9 +4787,10 @@ qla2x00_free_irqs(scsi_qla_host_t *vha) } int qla25xx_request_irq(struct qla_hw_data *ha, struct qla_qpair *qpair, - struct qla_msix_entry *msix, int vector_type) + struct qla_msix_entry *msix) { - const struct qla_init_msix_entry *intr = &msix_entries[vector_type]; + const struct qla_init_msix_entry *intr = + &msix_entries[QLA_MSIX_QPAIR_MULTIQ_RSP_Q]; scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev); int ret; diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 32eb0ce8b170d9..1f01576f044b8e 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -253,6 +253,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) /* Issue set host interrupt command to send cmd out. */ ha->flags.mbox_int = 0; clear_bit(MBX_INTERRUPT, &ha->mbx_cmd_flags); + reinit_completion(&ha->mbx_intr_comp); /* Unlock mbx registers and wait for interrupt */ ql_dbg(ql_dbg_mbx, vha, 0x100f, @@ -279,6 +280,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) "cmd=%x Timeout.\n", command); spin_lock_irqsave(&ha->hardware_lock, flags); clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags); + reinit_completion(&ha->mbx_intr_comp); spin_unlock_irqrestore(&ha->hardware_lock, flags); if (chip_reset != ha->chip_reset) { diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index 8b71ac0b1d9995..0abc47e72e0bf1 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -899,9 +899,7 @@ qla25xx_create_rsp_que(struct qla_hw_data *ha, uint16_t options, rsp->options, rsp->id, rsp->rsp_q_in, rsp->rsp_q_out); - ret = qla25xx_request_irq(ha, qpair, qpair->msix, - ha->flags.disable_msix_handshake ? - QLA_MSIX_QPAIR_MULTIQ_RSP_Q : QLA_MSIX_QPAIR_MULTIQ_RSP_Q_HS); + ret = qla25xx_request_irq(ha, qpair, qpair->msix); if (ret) goto que_failed; diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 316594aa40cc5a..42eb65a62f1f3c 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -1292,7 +1292,7 @@ void qla2xxx_process_purls_iocb(void **pkt, struct rsp_que **rsp) a.reason = FCNVME_RJT_RC_LOGIC; a.explanation = FCNVME_RJT_EXP_NONE; xmt_reject = true; - kfree(item); + qla24xx_free_purex_item(item); goto out; } diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 5ffd9458665274..59ca4adcb43154 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1182,7 +1182,8 @@ qla2x00_wait_for_hba_ready(scsi_qla_host_t *vha) while ((qla2x00_reset_active(vha) || ha->dpc_active || ha->flags.mbox_busy) || test_bit(FX00_RESET_RECOVERY, &vha->dpc_flags) || - test_bit(FX00_TARGET_SCAN, &vha->dpc_flags)) { + test_bit(FX00_TARGET_SCAN, &vha->dpc_flags) || + (vha->scan.scan_flags & SF_SCANNING)) { if (test_bit(UNLOADING, &base_vha->dpc_flags)) break; msleep(1000); @@ -1862,12 +1863,6 @@ __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res) for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) { sp = req->outstanding_cmds[cnt]; if (sp) { - if (qla2x00_chip_is_down(vha)) { - req->outstanding_cmds[cnt] = NULL; - sp->done(sp, res); - continue; - } - switch (sp->cmd_type) { case TYPE_SRB: qla2x00_abort_srb(qp, sp, res, &flags); @@ -1881,10 +1876,26 @@ __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res) continue; } cmd = (struct qla_tgt_cmd *)sp; - cmd->aborted = 1; + + if (cmd->sg_mapped) + qlt_unmap_sg(vha, cmd); + + if (cmd->state == QLA_TGT_STATE_NEED_DATA) { + cmd->aborted = 1; + cmd->write_data_transferred = 0; + cmd->state = QLA_TGT_STATE_DATA_IN; + ha->tgt.tgt_ops->handle_data(cmd); + } else { + ha->tgt.tgt_ops->free_cmd(cmd); + } break; case TYPE_TGT_TMCMD: - /* Skip task management functions. */ + /* + * Currently, only ABTS response gets on the + * outstanding_cmds[] + */ + ha->tgt.tgt_ops->free_mcmd( + (struct qla_tgt_mgmt_cmd *) sp); break; default: break; @@ -3444,13 +3455,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) ha->mqenable = 0; if (ha->mqenable) { - bool startit = false; - - if (QLA_TGT_MODE_ENABLED()) - startit = false; - - if (ql2x_ini_mode == QLA2XXX_INI_MODE_ENABLED) - startit = true; + bool startit = !!(host->active_mode & MODE_INITIATOR); /* Create start of day qpairs for Block MQ */ for (i = 0; i < ha->max_qpairs; i++) @@ -4484,7 +4489,7 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len, fail_elsrej: dma_pool_destroy(ha->purex_dma_pool); fail_flt: - dma_free_coherent(&ha->pdev->dev, SFP_DEV_SIZE, + dma_free_coherent(&ha->pdev->dev, sizeof(struct qla_flt_header) + FLT_REGIONS_SIZE, ha->flt, ha->flt_dma); fail_flt_buffer: @@ -7886,11 +7891,6 @@ qla2xxx_pci_slot_reset(struct pci_dev *pdev) pci_restore_state(pdev); - /* pci_restore_state() clears the saved_state flag of the device - * save restored state which resets saved_state flag - */ - pci_save_state(pdev); - if (ha->mem_only) rc = pci_enable_device_mem(pdev); else diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 1e81582085e384..4c6aff59fe3fb9 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -2443,7 +2443,7 @@ static int qlt_pci_map_calc_cnt(struct qla_tgt_prm *prm) return -1; } -static void qlt_unmap_sg(struct scsi_qla_host *vha, struct qla_tgt_cmd *cmd) +void qlt_unmap_sg(struct scsi_qla_host *vha, struct qla_tgt_cmd *cmd) { struct qla_hw_data *ha; struct qla_qpair *qpair; @@ -3773,9 +3773,6 @@ int qlt_abort_cmd(struct qla_tgt_cmd *cmd) spin_lock_irqsave(&cmd->cmd_lock, flags); if (cmd->aborted) { - if (cmd->sg_mapped) - qlt_unmap_sg(vha, cmd); - spin_unlock_irqrestore(&cmd->cmd_lock, flags); /* * It's normal to see 2 calls in this path: diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index 15a59c125c5324..c483966d0a8474 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -1058,6 +1058,7 @@ extern int qlt_abort_cmd(struct qla_tgt_cmd *); extern void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *); extern void qlt_free_mcmd(struct qla_tgt_mgmt_cmd *); extern void qlt_free_cmd(struct qla_tgt_cmd *cmd); +extern void qlt_unmap_sg(struct scsi_qla_host *vha, struct qla_tgt_cmd *cmd); extern void qlt_async_event(uint16_t, struct scsi_qla_host *, uint16_t *); extern void qlt_enable_vha(struct scsi_qla_host *); extern void qlt_vport_create(struct scsi_qla_host *, struct qla_hw_data *); diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index 83ff66f954e672..97329c97332f83 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -9796,11 +9796,6 @@ qla4xxx_pci_slot_reset(struct pci_dev *pdev) */ pci_restore_state(pdev); - /* pci_restore_state() clears the saved_state flag of the device - * save restored state which resets saved_state flag - */ - pci_save_state(pdev); - /* Initialize device or resume if in suspended state */ rc = pci_enable_device(pdev); if (rc) { diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index b2ab97be5db3d4..047d56d23beab4 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -7410,7 +7410,7 @@ MODULE_PARM_DESC(lbprz, MODULE_PARM_DESC(lbpu, "enable LBP, support UNMAP command (def=0)"); MODULE_PARM_DESC(lbpws, "enable LBP, support WRITE SAME(16) with UNMAP bit (def=0)"); MODULE_PARM_DESC(lbpws10, "enable LBP, support WRITE SAME(10) with UNMAP bit (def=0)"); -MODULE_PARM_DESC(atomic_write, "enable ATOMIC WRITE support, support WRITE ATOMIC(16) (def=0)"); +MODULE_PARM_DESC(atomic_wr, "enable ATOMIC WRITE support, support WRITE ATOMIC(16) (def=0)"); MODULE_PARM_DESC(lowest_aligned, "lowest aligned lba (def=0)"); MODULE_PARM_DESC(lun_format, "LUN format: 0->peripheral (def); 1 --> flat address method"); MODULE_PARM_DESC(max_luns, "number of LUNs per target to simulate(def=1)"); diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 1c13812a3f0358..2fd4ca96b3089d 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -282,11 +282,20 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head) { struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu); struct Scsi_Host *shost = scmd->device->host; - unsigned int busy = scsi_host_busy(shost); + unsigned int busy; unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); shost->host_failed++; + spin_unlock_irqrestore(shost->host_lock, flags); + /* + * The counting of busy requests needs to occur after adding to + * host_failed or after the lock acquire for adding to host_failed + * to prevent a race with host unbusy and missing an eh wakeup. + */ + busy = scsi_host_busy(shost); + + spin_lock_irqsave(shost->host_lock, flags); scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } @@ -1060,6 +1069,9 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, unsigned char *cmnd, int cmnd_size, unsigned sense_bytes) { struct scsi_device *sdev = scmd->device; +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct request *rq = scsi_cmd_to_rq(scmd); +#endif /* * We need saved copies of a number of fields - this is because @@ -1111,6 +1123,18 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, scmd->cmnd[1] = (scmd->cmnd[1] & 0x1f) | (sdev->lun << 5 & 0xe0); + /* + * Encryption must be disabled for the commands submitted by the error handler. + * Hence, clear the encryption context information. + */ +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + ses->rq_crypt_keyslot = rq->crypt_keyslot; + ses->rq_crypt_ctx = rq->crypt_ctx; + + rq->crypt_keyslot = NULL; + rq->crypt_ctx = NULL; +#endif + /* * Zero the sense buffer. The scsi spec mandates that any * untransferred sense data should be interpreted as being zero. @@ -1128,6 +1152,10 @@ EXPORT_SYMBOL(scsi_eh_prep_cmnd); */ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) { +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct request *rq = scsi_cmd_to_rq(scmd); +#endif + /* * Restore original data */ @@ -1140,6 +1168,11 @@ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) scmd->underflow = ses->underflow; scmd->prot_op = ses->prot_op; scmd->eh_eflags = ses->eh_eflags; + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + rq->crypt_keyslot = ses->rq_crypt_keyslot; + rq->crypt_ctx = ses->rq_crypt_ctx; +#endif } EXPORT_SYMBOL(scsi_eh_restore_cmnd); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index d7e42293b86455..7ddb73cd6d9fe5 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -376,6 +376,14 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd) rcu_read_lock(); __clear_bit(SCMD_STATE_INFLIGHT, &cmd->state); if (unlikely(scsi_host_in_recovery(shost))) { + /* + * Ensure the clear of SCMD_STATE_INFLIGHT is visible to + * other CPUs before counting busy requests. Otherwise, + * reordering can cause CPUs to race and miss an eh wakeup + * when no CPU sees all busy requests as done or timed out. + */ + smp_mb(); + unsigned int busy = scsi_host_busy(shost); spin_lock_irqsave(shost->host_lock, flags); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index b3af9b78fa123b..57fba34832ad11 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -731,6 +731,8 @@ sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf, sg_remove_request(sfp, srp); return -EFAULT; } + hp->duration = jiffies_to_msecs(jiffies); + if (hp->interface_id != 'S') { sg_remove_request(sfp, srp); return -ENOSYS; @@ -815,7 +817,6 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp, return -ENODEV; } - hp->duration = jiffies_to_msecs(jiffies); if (hp->interface_id != '\0' && /* v3 (or later) interface */ (SG_FLAG_Q_AT_TAIL & hp->flags)) at_head = 0; @@ -1338,9 +1339,6 @@ sg_rq_end_io(struct request *rq, blk_status_t status) "sg_cmd_done: pack_id=%d, res=0x%x\n", srp->header.pack_id, result)); srp->header.resid = resid; - ms = jiffies_to_msecs(jiffies); - srp->header.duration = (ms > srp->header.duration) ? - (ms - srp->header.duration) : 0; if (0 != result) { struct scsi_sense_hdr sshdr; @@ -1389,6 +1387,9 @@ sg_rq_end_io(struct request *rq, blk_status_t status) done = 0; } srp->done = done; + ms = jiffies_to_msecs(jiffies); + srp->header.duration = (ms > srp->header.duration) ? + (ms - srp->header.duration) : 0; write_unlock_irqrestore(&sfp->rq_list_lock, iflags); if (likely(done)) { @@ -2533,6 +2534,7 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp) const sg_io_hdr_t *hp; const char * cp; unsigned int ms; + unsigned int duration; k = 0; list_for_each_entry(fp, &sdp->sfds, sfd_siblings) { @@ -2570,13 +2572,17 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp) seq_printf(s, " id=%d blen=%d", srp->header.pack_id, blen); if (srp->done) - seq_printf(s, " dur=%d", hp->duration); + seq_printf(s, " dur=%u", hp->duration); else { ms = jiffies_to_msecs(jiffies); - seq_printf(s, " t_o/elap=%d/%d", + duration = READ_ONCE(hp->duration); + if (duration) + duration = (ms > duration ? + ms - duration : 0); + seq_printf(s, " t_o/elap=%u/%u", (new_interface ? hp->timeout : jiffies_to_msecs(fp->timeout)), - (ms > hp->duration ? ms - hp->duration : 0)); + duration); } seq_printf(s, "ms sgat=%d op=0x%02x\n", usg, (int) srp->data.cmd_opcode); diff --git a/drivers/scsi/sim710.c b/drivers/scsi/sim710.c index e519df68d603d5..70c75ab1453a16 100644 --- a/drivers/scsi/sim710.c +++ b/drivers/scsi/sim710.c @@ -133,6 +133,7 @@ static int sim710_probe_common(struct device *dev, unsigned long base_addr, out_put_host: scsi_host_put(host); out_release: + ioport_unmap(hostdata->base); release_region(base_addr, 64); out_free: kfree(hostdata); @@ -148,6 +149,7 @@ static int sim710_device_remove(struct device *dev) scsi_remove_host(host); NCR_700_release(host); + ioport_unmap(hostdata->base); kfree(hostdata); free_irq(host->irq, host); release_region(host->base, 64); diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index 03c97e60d36f63..5a6e1bb57e7c84 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -1241,7 +1241,8 @@ static inline int pqi_report_phys_luns(struct pqi_ctrl_info *ctrl_info, void **b dev_err(&ctrl_info->pci_dev->dev, "RPL returned unsupported data format %u\n", rpl_response_format); - return -EINVAL; + rc = -EINVAL; + goto out_free_rpl_list; } else { dev_warn(&ctrl_info->pci_dev->dev, "RPL returned extended format 2 instead of 4\n"); @@ -1253,8 +1254,10 @@ static inline int pqi_report_phys_luns(struct pqi_ctrl_info *ctrl_info, void **b rpl_16byte_wwid_list = kmalloc(struct_size(rpl_16byte_wwid_list, lun_entries, num_physicals), GFP_KERNEL); - if (!rpl_16byte_wwid_list) - return -ENOMEM; + if (!rpl_16byte_wwid_list) { + rc = -ENOMEM; + goto out_free_rpl_list; + } put_unaligned_be32(num_physicals * sizeof(struct report_phys_lun_16byte_wwid), &rpl_16byte_wwid_list->header.list_length); @@ -1275,6 +1278,10 @@ static inline int pqi_report_phys_luns(struct pqi_ctrl_info *ctrl_info, void **b *buffer = rpl_16byte_wwid_list; return 0; + +out_free_rpl_list: + kfree(rpl_list); + return rc; } static inline int pqi_report_logical_luns(struct pqi_ctrl_info *ctrl_info, void **buffer) @@ -6410,10 +6417,22 @@ static int pqi_device_reset(struct pqi_ctrl_info *ctrl_info, struct pqi_scsi_dev static int pqi_device_reset_handler(struct pqi_ctrl_info *ctrl_info, struct pqi_scsi_dev *device, u8 lun, struct scsi_cmnd *scmd, u8 scsi_opcode) { + unsigned long flags; int rc; mutex_lock(&ctrl_info->lun_reset_mutex); + spin_lock_irqsave(&ctrl_info->scsi_device_list_lock, flags); + if (pqi_find_scsi_dev(ctrl_info, device->bus, device->target, device->lun) == NULL) { + dev_warn(&ctrl_info->pci_dev->dev, + "skipping reset of scsi %d:%d:%d:%u, device has been removed\n", + ctrl_info->scsi_host->host_no, device->bus, device->target, device->lun); + spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags); + mutex_unlock(&ctrl_info->lun_reset_mutex); + return 0; + } + spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags); + dev_err(&ctrl_info->pci_dev->dev, "resetting scsi %d:%d:%d:%u SCSI cmd at %p due to cmd opcode 0x%02x\n", ctrl_info->scsi_host->host_no, device->bus, device->target, lun, scmd, scsi_opcode); @@ -6594,7 +6613,9 @@ static void pqi_sdev_destroy(struct scsi_device *sdev) { struct pqi_ctrl_info *ctrl_info; struct pqi_scsi_dev *device; + struct pqi_tmf_work *tmf_work; int mutex_acquired; + unsigned int lun; unsigned long flags; ctrl_info = shost_to_hba(sdev->host); @@ -6621,8 +6642,13 @@ static void pqi_sdev_destroy(struct scsi_device *sdev) mutex_unlock(&ctrl_info->scan_mutex); + for (lun = 0, tmf_work = device->tmf_work; lun < PQI_MAX_LUNS_PER_DEVICE; lun++, tmf_work++) + cancel_work_sync(&tmf_work->work_struct); + + mutex_lock(&ctrl_info->lun_reset_mutex); pqi_dev_info(ctrl_info, "removed", device); pqi_free_device(device); + mutex_unlock(&ctrl_info->lun_reset_mutex); } static int pqi_getpciinfo_ioctl(struct pqi_ctrl_info *ctrl_info, void __user *arg) @@ -10108,6 +10134,10 @@ static const struct pci_device_id pqi_pci_id_table[] = { PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f, 0x207d, 0x4240) }, + { + PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f, + 0x207d, 0x4840) + }, { PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f, PCI_VENDOR_ID_ADVANTECH, 0x8312) diff --git a/drivers/scsi/stex.c b/drivers/scsi/stex.c index d8ad02c2932058..e02f28e5a104e4 100644 --- a/drivers/scsi/stex.c +++ b/drivers/scsi/stex.c @@ -1844,6 +1844,7 @@ static int stex_probe(struct pci_dev *pdev, const struct pci_device_id *id) out_scsi_host_put: scsi_host_put(host); out_disable: + unregister_reboot_notifier(&stex_notifier); pci_disable_device(pdev); return err; diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 6e4112143c7689..b43d876747b76c 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1144,7 +1144,7 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device, * The current SCSI handling on the host side does * not correctly handle: * INQUIRY command with page code parameter set to 0x80 - * MODE_SENSE command with cmd[2] == 0x1c + * MODE_SENSE and MODE_SENSE_10 command with cmd[2] == 0x1c * MAINTENANCE_IN is not supported by HyperV FC passthrough * * Setup srb and scsi status so this won't be fatal. @@ -1154,6 +1154,7 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device, if ((stor_pkt->vm_srb.cdb[0] == INQUIRY) || (stor_pkt->vm_srb.cdb[0] == MODE_SENSE) || + (stor_pkt->vm_srb.cdb[0] == MODE_SENSE_10) || (stor_pkt->vm_srb.cdb[0] == MAINTENANCE_IN && hv_dev_is_fc(device))) { vstor_packet->vm_srb.scsi_status = 0; diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c index 005fa2ef100f52..0992ca35cef498 100644 --- a/drivers/slimbus/core.c +++ b/drivers/slimbus/core.c @@ -379,6 +379,8 @@ struct slim_device *slim_get_device(struct slim_controller *ctrl, sbdev = slim_alloc_device(ctrl, e_addr, NULL); if (!sbdev) return ERR_PTR(-ENOMEM); + + get_device(&sbdev->dev); } return sbdev; @@ -489,21 +491,24 @@ int slim_device_report_present(struct slim_controller *ctrl, if (ctrl->sched.clk_state != SLIM_CLK_ACTIVE) { dev_err(ctrl->dev, "slim ctrl not active,state:%d, ret:%d\n", ctrl->sched.clk_state, ret); - goto slimbus_not_active; + goto out_put_rpm; } sbdev = slim_get_device(ctrl, e_addr); - if (IS_ERR(sbdev)) - return -ENODEV; + if (IS_ERR(sbdev)) { + ret = -ENODEV; + goto out_put_rpm; + } if (sbdev->is_laddr_valid) { *laddr = sbdev->laddr; - return 0; + ret = 0; + } else { + ret = slim_device_alloc_laddr(sbdev, true); } - ret = slim_device_alloc_laddr(sbdev, true); - -slimbus_not_active: + put_device(&sbdev->dev); +out_put_rpm: pm_runtime_mark_last_busy(ctrl->dev); pm_runtime_put_autosuspend(ctrl->dev); return ret; diff --git a/drivers/soc/amlogic/meson-canvas.c b/drivers/soc/amlogic/meson-canvas.c index b6e06c4d2117f6..0711088da5dcd1 100644 --- a/drivers/soc/amlogic/meson-canvas.c +++ b/drivers/soc/amlogic/meson-canvas.c @@ -73,10 +73,9 @@ struct meson_canvas *meson_canvas_get(struct device *dev) * current state, this driver probe cannot return -EPROBE_DEFER */ canvas = dev_get_drvdata(&canvas_pdev->dev); - if (!canvas) { - put_device(&canvas_pdev->dev); + put_device(&canvas_pdev->dev); + if (!canvas) return ERR_PTR(-EINVAL); - } return canvas; } diff --git a/drivers/soc/apple/Kconfig b/drivers/soc/apple/Kconfig index ad67368892311b..c926f7705be671 100644 --- a/drivers/soc/apple/Kconfig +++ b/drivers/soc/apple/Kconfig @@ -4,6 +4,15 @@ if ARCH_APPLE || COMPILE_TEST menu "Apple SoC drivers" +config APPLE_DOCKCHANNEL + tristate "Apple DockChannel FIFO" + depends on ARCH_APPLE || COMPILE_TEST + help + DockChannel is a simple FIFO used on Apple SoCs for debug and inter-processor + communications. + + Say 'y' here if you have an Apple SoC. + config APPLE_MAILBOX tristate "Apple SoC mailboxes" depends on PM @@ -16,6 +25,18 @@ config APPLE_MAILBOX Say Y here if you have an Apple SoC. +config APPLE_PMGR_MISC + bool "Apple SoC PMGR miscellaneous support" + depends on PM + help + The PMGR block in Apple SoCs provides high-level power state + controls for SoC devices. This driver manages miscellaneous + power controls. + +config APPLE_TUNABLE + tristate + depends on ARCH_APPLE || COMPILE_TEST + config APPLE_RTKIT tristate "Apple RTKit co-processor IPC protocol" depends on APPLE_MAILBOX @@ -28,6 +49,19 @@ config APPLE_RTKIT Say 'y' here if you have an Apple SoC. +config APPLE_RTKIT_HELPER + tristate "Apple Generic RTKit helper co-processor" + depends on APPLE_RTKIT + depends on ARCH_APPLE || COMPILE_TEST + help + Apple SoCs such as the M1 come with various co-processors running + their proprietary RTKit operating system. This option enables support + for a generic co-processor that does not implement any additional + in-band communications. It can be used for testing purposes, or for + coprocessors such as MTP that communicate over a different interface. + + Say 'y' here if you have an Apple SoC. + config APPLE_SART tristate "Apple SART DMA address filter" depends on ARCH_APPLE || COMPILE_TEST @@ -38,6 +72,43 @@ config APPLE_SART Say 'y' here if you have an Apple SoC. +config RUST_APPLE_MAILBOX + bool + depends on PM + depends on RUST + select APPLE_MAILBOX + +config RUST_APPLE_RTKIT + bool + depends on PM + depends on RUST + select APPLE_RTKIT + +config APPLE_AOP + tristate "Apple \"Always-on\" Processor" + depends on ARCH_APPLE || COMPILE_TEST + depends on PM + depends on RUST + select RUST_APPLE_RTKIT + help + A co-processor persent on certain Apple SoCs controlling accelerometers, + gyros, ambient light sensors and microphones. Is not actually always on. + + Say 'y' here if you have an Apple laptop. + +config APPLE_SEP + tristate "Apple Secure Element Processor" + depends on ARCH_APPLE || COMPILE_TEST + depends on PM + depends on RUST + select RUST_APPLE_RTKIT + select RUST_APPLE_MAILBOX + help + A security co-processor persent on Apple SoCs, controlling transparent + disk encryption, secure boot, HDCP, biometric auth and probably more. + + Say 'y' here if you have an Apple SoC. + endmenu endif diff --git a/drivers/soc/apple/Makefile b/drivers/soc/apple/Makefile index 4d9ab8f3037b71..47f66719ee8a90 100644 --- a/drivers/soc/apple/Makefile +++ b/drivers/soc/apple/Makefile @@ -1,10 +1,25 @@ # SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_APPLE_DOCKCHANNEL) += apple-dockchannel.o +apple-dockchannel-y = dockchannel.o + obj-$(CONFIG_APPLE_MAILBOX) += apple-mailbox.o apple-mailbox-y = mailbox.o +obj-$(CONFIG_APPLE_PMGR_MISC) += apple-pmgr-misc.o + +obj-$(CONFIG_APPLE_TUNABLE) += apple-tunable.o +apple-tunable-y = tunable.o + obj-$(CONFIG_APPLE_RTKIT) += apple-rtkit.o apple-rtkit-y = rtkit.o rtkit-crashlog.o +obj-$(CONFIG_APPLE_RTKIT_HELPER) += apple-rtkit-helper.o +apple-rtkit-helper-y = rtkit-helper.o + obj-$(CONFIG_APPLE_SART) += apple-sart.o apple-sart-y = sart.o + +obj-$(CONFIG_APPLE_AOP) += aop.o + +obj-$(CONFIG_APPLE_SEP) += sep.o diff --git a/drivers/soc/apple/aop.rs b/drivers/soc/apple/aop.rs new file mode 100644 index 00000000000000..b73d05227f2ff3 --- /dev/null +++ b/drivers/soc/apple/aop.rs @@ -0,0 +1,990 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +#![recursion_limit = "2048"] + +//! Apple AOP driver +//! +//! Copyright (C) The Asahi Linux Contributors + +use core::{arch::asm, cmp, mem, ptr, slice}; + +use kernel::{ + bindings, c_str, device, + device::Core, + dma::{CoherentAllocation, Device, DmaMask}, + error::from_err_ptr, + io::mem::IoMem, + iosys_map::IoSysMapRef, + module_platform_driver, new_condvar, new_mutex, of, platform, + prelude::*, + soc::apple::aop::{from_fourcc, EPICService, FakehidListener, AOP}, + soc::apple::rtkit, + sync::{Arc, ArcBorrow, CondVar, Mutex}, + types::{ARef, ForeignOwnable}, + workqueue::{self, impl_has_work, new_work, Work, WorkItem}, +}; + +const AOP_MAX_CALLS: usize = 8; +const AOP_MMIO_SIZE: usize = 0x1e0000; +const ASC_MMIO_SIZE: usize = 0x4000; +const BOOTARGS_OFFSET: usize = 0x22c; +const BOOTARGS_SIZE: usize = 0x230; +const CPU_CONTROL: usize = 0x44; +const CPU_RUN: u32 = 0x1 << 4; +const AFK_ENDPOINT_START: u8 = 0x20; +const AFK_ENDPOINT_COUNT: u8 = 0xf; +const AFK_OPC_GET_BUF: u64 = 0x89; +const AFK_OPC_INIT: u64 = 0x80; +const AFK_OPC_INIT_RX: u64 = 0x8b; +const AFK_OPC_INIT_TX: u64 = 0x8a; +const AFK_OPC_INIT_UNK: u64 = 0x8c; +const AFK_OPC_SEND: u64 = 0xa2; +const AFK_OPC_START_ACK: u64 = 0x86; +const AFK_OPC_SHUTDOWN_ACK: u64 = 0xc1; +const AFK_OPC_RECV: u64 = 0x85; +const AFK_MSG_GET_BUF_ACK: u64 = 0xa1 << 48; +const AFK_MSG_INIT: u64 = AFK_OPC_INIT << 48; +const AFK_MSG_INIT_ACK: u64 = 0xa0 << 48; +const AFK_MSG_START: u64 = 0xa3 << 48; +const AFK_MSG_SHUTDOWN: u64 = 0xc0 << 48; +const AFK_RB_BLOCK_STEP: usize = 0x40; +const EPIC_TYPE_NOTIFY: u32 = 0; +const EPIC_CATEGORY_REPORT: u8 = 0x00; +const EPIC_CATEGORY_NOTIFY: u8 = 0x10; +const EPIC_CATEGORY_REPLY: u8 = 0x20; +const EPIC_SUBTYPE_STD_SERVICE: u16 = 0xc0; +const EPIC_SUBTYPE_FAKEHID_REPORT: u16 = 0xc4; +const EPIC_SUBTYPE_RETCODE: u16 = 0x84; +const EPIC_SUBTYPE_RETCODE_PAYLOAD: u16 = 0xa0; +const EPIC_SUBTYPE_STRING: u16 = 0x8a; +const QE_MAGIC1: u32 = from_fourcc(b" POI"); +const QE_MAGIC2: u32 = from_fourcc(b" POA"); + +fn align_up(v: usize, a: usize) -> usize { + (v + a - 1) & !(a - 1) +} + +#[inline(always)] +fn mem_sync() { + unsafe { + asm!("dsb sy"); + } +} + +#[repr(C, packed)] +#[derive(Clone, Copy, Default)] +struct QEHeader { + magic: u32, + size: u32, + channel: u32, + ty: u32, +} + +#[repr(C, packed)] +#[derive(Clone, Copy, Default)] +struct EPICHeader { + version: u8, + seq: u16, + _pad0: u8, + _unk0: u32, + timestamp: u64, + // Subheader + length: u32, + sub_version: u8, + category: u8, + subtype: u16, + tag: u16, + _unk1: u16, + _pad1: u64, + inline_len: u32, +} + +#[repr(C, packed)] +struct EPICServiceAnnounce { + name: [u8; 20], + _unk0: u32, + retcode: u32, + _unk1: u32, + channel: u32, + _unk2: u32, + _unk3: u32, +} + +#[pin_data] +struct FutureValue { + #[pin] + val: Mutex>, + #[pin] + completion: CondVar, +} + +impl FutureValue { + fn pin_init() -> impl PinInit> { + pin_init!( + FutureValue { + val <- new_mutex!(None), + completion <- new_condvar!() + } + ) + } + fn complete(&self, val: T) { + *self.val.lock() = Some(val); + self.completion.notify_all(); + } + fn wait(&self) -> T { + let mut ret_guard = self.val.lock(); + while ret_guard.is_none() { + self.completion.wait(&mut ret_guard); + } + ret_guard.take().unwrap() + } + fn reset(&self) { + *self.val.lock() = None; + } +} + +struct AFKRingBuffer { + offset: usize, + block_size: usize, + buf_size: usize, +} + +struct CallResult { + retcode: u32, + extra_data: Option>, +} + +struct AFKEndpoint { + index: u8, + iomem: Option>, + txbuf: Option, + rxbuf: Option, + seq: u16, + calls: [Option>>; AOP_MAX_CALLS], + call_returns: [Option>; AOP_MAX_CALLS], +} + +unsafe impl Send for AFKEndpoint {} + +impl AFKEndpoint { + fn new(index: u8) -> AFKEndpoint { + AFKEndpoint { + index, + iomem: None, + txbuf: None, + rxbuf: None, + seq: 0, + calls: [const { None }; AOP_MAX_CALLS], + call_returns: [const { None }; AOP_MAX_CALLS], + } + } + + fn start(&self, rtkit: &mut rtkit::RtKit) -> Result<()> { + rtkit.send_message(self.index, AFK_MSG_INIT) + } + + fn stop(&self, rtkit: &mut rtkit::RtKit) -> Result<()> { + rtkit.send_message(self.index, AFK_MSG_SHUTDOWN) + } + + fn recv_message( + &mut self, + client: ArcBorrow<'_, AopData>, + rtkit: &mut rtkit::RtKit, + msg: u64, + ) -> Result<()> { + let opc = msg >> 48; + match opc { + AFK_OPC_INIT => { + rtkit.send_message(self.index, AFK_MSG_INIT_ACK)?; + } + AFK_OPC_GET_BUF => { + self.recv_get_buf(client.dev.clone(), rtkit, msg)?; + } + AFK_OPC_INIT_UNK => {} // no-op + AFK_OPC_START_ACK => {} + AFK_OPC_INIT_RX => { + if self.rxbuf.is_some() { + dev_err!( + client.dev, + "Got InitRX message with existing rxbuf at endpoint {}", + self.index + ); + return Err(EIO); + } + self.rxbuf = Some(self.parse_ring_buf(msg)?); + if self.txbuf.is_some() { + rtkit.send_message(self.index, AFK_MSG_START)?; + } + } + AFK_OPC_INIT_TX => { + if self.txbuf.is_some() { + dev_err!( + client.dev, + "Got InitTX message with existing txbuf at endpoint {}", + self.index + ); + return Err(EIO); + } + self.txbuf = Some(self.parse_ring_buf(msg)?); + if self.rxbuf.is_some() { + rtkit.send_message(self.index, AFK_MSG_START)?; + } + } + AFK_OPC_RECV => { + self.recv_rb(client)?; + } + AFK_OPC_SHUTDOWN_ACK => { + client.shutdown_complete(); + } + _ => dev_err!( + client.dev, + "AFK endpoint {} got unknown message {}", + self.index, + msg + ), + } + Ok(()) + } + + fn parse_ring_buf(&self, msg: u64) -> Result { + let msg = msg as usize; + let size = ((msg >> 16) & 0xFFFF) * AFK_RB_BLOCK_STEP; + let offset = ((msg >> 32) & 0xFFFF) * AFK_RB_BLOCK_STEP; + let buf_size = self.iomem_read32(offset)? as usize; + let block_size = (size - buf_size) / 3; + Ok(AFKRingBuffer { + offset, + block_size, + buf_size, + }) + } + fn iomem_write32(&mut self, off: usize, data: u32) -> Result<()> { + let size = core::mem::size_of::(); + let data = data.to_le_bytes(); + let buf = unsafe { self.iomem.as_mut().ok_or(ENXIO)?.as_slice_mut(off, size)? }; + buf.copy_from_slice(&data); + Ok(()) + } + + fn iomem_read32(&self, off: usize) -> Result { + let size = core::mem::size_of::(); + let buf = unsafe { self.iomem.as_ref().ok_or(ENXIO)?.as_slice(off, size)? }; + Ok(u32::from_le_bytes(buf.try_into().unwrap())) + } + + fn memcpy_from_iomem(&self, off: usize, target: &mut [u8]) -> Result<()> { + // SAFETY: + // as_slice() checks that off and target.len() are whithin iomem's limits. + unsafe { + let src = self + .iomem + .as_ref() + .ok_or(ENXIO)? + .as_slice(off, target.len())?; + target.copy_from_slice(src); + } + Ok(()) + } + + fn memcpy_to_iomem(&mut self, off: usize, src: &[u8]) -> Result<()> { + // SAFETY: + // as_slice_mut() checks that off and src.len() are whithin iomem's limits. + unsafe { + let target = self + .iomem + .as_mut() + .ok_or(ENXIO)? + .as_slice_mut(off, src.len())?; + target.copy_from_slice(src); + } + Ok(()) + } + + fn recv_get_buf( + &mut self, + dev: ARef, + rtkit: &mut rtkit::RtKit, + msg: u64, + ) -> Result<()> { + let size = ((msg & 0xFFFF0000) >> 16) as usize * AFK_RB_BLOCK_STEP; + if self.iomem.is_some() { + dev_err!( + dev, + "Got GetBuf message with existing buffer on endpoint {}", + self.index + ); + return Err(EIO); + } + let iomem = dev.while_bound_with(|bound_dev| { + CoherentAllocation::::alloc_coherent(bound_dev, size, GFP_KERNEL) + })?; + rtkit.send_message(self.index, AFK_MSG_GET_BUF_ACK | iomem.dma_handle())?; + self.iomem = Some(iomem); + Ok(()) + } + + fn recv_rb(&mut self, client: ArcBorrow<'_, AopData>) -> Result<()> { + let (buf_offset, block_size, buf_size) = match self.rxbuf.as_ref() { + Some(b) => (b.offset, b.block_size, b.buf_size), + None => { + dev_err!( + client.dev, + "Got Recv message with no rxbuf at endpoint {}", + self.index + ); + return Err(EIO); + } + }; + let mut rptr = self.iomem_read32(buf_offset + block_size)? as usize; + let mut wptr = self.iomem_read32(buf_offset + block_size * 2)?; + mem_sync(); + let base = buf_offset + block_size * 3; + let mut msg_buf = KVec::new(); + const QEH_SIZE: usize = mem::size_of::(); + while wptr as usize != rptr { + let mut qeh_bytes = [0; QEH_SIZE]; + self.memcpy_from_iomem(base + rptr, &mut qeh_bytes)?; + let mut qeh = unsafe { &*(qeh_bytes.as_ptr() as *const QEHeader) }; + if qeh.magic != QE_MAGIC1 && qeh.magic != QE_MAGIC2 { + let magic = qeh.magic; + dev_err!( + client.dev, + "Invalid magic on ep {}, got {:x}", + self.index, + magic + ); + return Err(EIO); + } + if qeh.size as usize > (buf_size - rptr - QEH_SIZE) { + rptr = 0; + self.memcpy_from_iomem(base + rptr, &mut qeh_bytes)?; + qeh = unsafe { &*(qeh_bytes.as_ptr() as *const QEHeader) }; + + if qeh.magic != QE_MAGIC1 && qeh.magic != QE_MAGIC2 { + let magic = qeh.magic; + dev_err!( + client.dev, + "Invalid magic on ep {}, got {:x}", + self.index, + magic + ); + return Err(EIO); + } + } + msg_buf.resize(qeh.size as usize, 0, GFP_KERNEL)?; + self.memcpy_from_iomem(base + rptr + QEH_SIZE, &mut msg_buf)?; + let (hdr_bytes, msg) = msg_buf.split_at(mem::size_of::()); + let header = unsafe { &*(hdr_bytes.as_ptr() as *const EPICHeader) }; + self.handle_ipc(client, qeh, header, msg)?; + rptr = align_up(rptr + QEH_SIZE + qeh.size as usize, block_size) % buf_size; + mem_sync(); + self.iomem_write32(buf_offset + block_size, rptr as u32)?; + wptr = self.iomem_read32(buf_offset + block_size * 2)?; + mem_sync(); + } + Ok(()) + } + fn handle_ipc( + &mut self, + client: ArcBorrow<'_, AopData>, + qhdr: &QEHeader, + ehdr: &EPICHeader, + data: &[u8], + ) -> Result<()> { + let subtype = ehdr.subtype; + if ehdr.category == EPIC_CATEGORY_REPORT { + if subtype == EPIC_SUBTYPE_STD_SERVICE { + let announce = unsafe { &*(data.as_ptr() as *const EPICServiceAnnounce) }; + let chan = announce.channel; + let name_len = announce + .name + .iter() + .position(|x| *x == 0) + .unwrap_or(announce.name.len()); + return Into::>::into(client).register_service( + self, + chan, + &announce.name[..name_len], + ); + } else if subtype == EPIC_SUBTYPE_FAKEHID_REPORT { + return client.process_fakehid_report(self, qhdr.channel, data); + } else { + dev_err!( + client.dev, + "Unexpected EPIC report subtype {:x} on endpoint {}", + subtype, + self.index + ); + return Err(EIO); + } + } else if ehdr.category == EPIC_CATEGORY_REPLY { + if subtype == EPIC_SUBTYPE_RETCODE_PAYLOAD + || subtype == EPIC_SUBTYPE_RETCODE + || subtype == EPIC_SUBTYPE_STRING + { + if data.len() < mem::size_of::() { + dev_err!( + client.dev, + "Retcode data too short on endpoint {}", + self.index + ); + return Err(EIO); + } + let retcode = u32::from_ne_bytes(data[..4].try_into().unwrap()); + let tag = ehdr.tag as usize; + if tag == 0 || tag - 1 > self.calls.len() || self.calls[tag - 1].is_none() { + dev_err!( + client.dev, + "Got a retcode with invalid tag {:?} on endpoint {}", + tag, + self.index + ); + return Err(EIO); + } + let future = self.calls[tag - 1].take().unwrap(); + let extra_data = if let Some(mut ret) = self.call_returns[tag - 1].take() { + let len = cmp::min(data.len() - 4, ret.len()); + ret[..len].copy_from_slice(&data[4..(len + 4)]); + ret.truncate(len); + Some(ret) + } else { + None + }; + future.complete(CallResult { + retcode, + extra_data, + }); + + return Ok(()); + } else { + dev_err!( + client.dev, + "Unexpected EPIC reply subtype {:x} on endpoint {}", + subtype, + self.index + ); + return Err(EIO); + } + } + dev_err!( + client.dev, + "Unexpected EPIC category {:x} on endpoint {}", + ehdr.category, + self.index + ); + Err(EIO) + } + fn send_rb( + &mut self, + client: &AopData, + rtkit: &mut rtkit::RtKit, + channel: u32, + ty: u32, + header: &[u8], + data: &[u8], + ) -> Result<()> { + let (buf_offset, block_size, buf_size) = match self.txbuf.as_ref() { + Some(b) => (b.offset, b.block_size, b.buf_size), + None => { + dev_err!( + client.dev, + "Attempting to send message with no txbuf at endpoint {}", + self.index + ); + return Err(EIO); + } + }; + let base = buf_offset + block_size * 3; + mem_sync(); + let rptr = self.iomem_read32(buf_offset + block_size)? as usize; + let mut wptr = self.iomem_read32(buf_offset + block_size * 2)? as usize; + const QEH_SIZE: usize = mem::size_of::(); + if wptr < rptr && wptr + QEH_SIZE >= rptr { + dev_err!(client.dev, "Tx buffer full at endpoint {}", self.index); + return Err(EIO); + } + let payload_len = header.len() + data.len(); + let qeh = QEHeader { + magic: QE_MAGIC1, + size: payload_len as u32, + channel, + ty, + }; + let qeh_bytes = unsafe { + slice::from_raw_parts( + &qeh as *const QEHeader as *const u8, + mem::size_of::(), + ) + }; + self.memcpy_to_iomem(base + wptr, qeh_bytes)?; + if payload_len > buf_size - wptr - QEH_SIZE { + wptr = 0; + self.memcpy_to_iomem(base + wptr, qeh_bytes)?; + } + self.memcpy_to_iomem(base + wptr + QEH_SIZE, header)?; + self.memcpy_to_iomem(base + wptr + QEH_SIZE + header.len(), data)?; + wptr = align_up(wptr + QEH_SIZE + payload_len, block_size) % buf_size; + self.iomem_write32(buf_offset + block_size * 2, wptr as u32)?; + let msg = wptr as u64 | (AFK_OPC_SEND << 48); + rtkit.send_message(self.index, msg) + } + fn epic_notify( + &mut self, + client: &AopData, + rtkit: &mut rtkit::RtKit, + channel: u32, + subtype: u16, + data: &[u8], + ret: Option>, + ) -> Result>> { + let mut tag = 0; + for i in 0..self.calls.len() { + if self.calls[i].is_none() { + tag = i + 1; + break; + } + } + if tag == 0 { + dev_err!( + client.dev, + "Too many inflight calls on endpoint {}", + self.index + ); + return Err(EIO); + } + let call = Arc::pin_init(FutureValue::pin_init(), GFP_KERNEL)?; + let hdr = EPICHeader { + version: 2, + seq: self.seq, + length: data.len() as u32, + sub_version: 2, + category: EPIC_CATEGORY_NOTIFY, + subtype, + tag: tag as u16, + ..EPICHeader::default() + }; + self.call_returns[tag - 1] = ret; + self.send_rb( + client, + rtkit, + channel, + EPIC_TYPE_NOTIFY, + unsafe { + slice::from_raw_parts( + &hdr as *const EPICHeader as *const u8, + mem::size_of::(), + ) + }, + data, + )?; + self.seq = self.seq.wrapping_add(1); + self.calls[tag - 1] = Some(call.clone()); + Ok(call) + } +} + +struct ListenerEntry { + svc: EPICService, + listener: Arc, +} + +unsafe impl Send for ListenerEntry {} + +#[pin_data] +struct AopData { + dev: ARef, + #[pin] + rtkit: Mutex>>, + #[pin] + endpoints: [Mutex; AFK_ENDPOINT_COUNT as usize], + #[pin] + ep_shutdown: FutureValue<()>, + #[pin] + hid_listeners: Mutex>, + #[pin] + subdevices: Mutex>, +} + +unsafe impl Send for AopData {} +unsafe impl Sync for AopData {} + +#[pin_data] +struct AopServiceRegisterWork { + name: &'static CStr, + data: Arc, + service: EPICService, + #[pin] + work: Work, +} + +impl_has_work! { + impl HasWork for AopServiceRegisterWork { self.work } +} + +impl AopServiceRegisterWork { + fn new( + name: &'static CStr, + data: Arc, + service: EPICService, + ) -> Result>> { + KBox::pin_init( + pin_init!(AopServiceRegisterWork { + name, data, service, + work <- new_work!("AopServiceRegisterWork::work"), + }), + GFP_KERNEL, + ) + } +} + +impl WorkItem for AopServiceRegisterWork { + type Pointer = Pin>; + + fn run(this: Pin>) { + let fwnode = this + .data + .dev + .fwnode() + .and_then(|x| x.get_child_by_name(this.name)); + let info = bindings::platform_device_info { + parent: this.data.dev.as_raw(), + name: this.name.as_ptr() as *const _, + id: bindings::PLATFORM_DEVID_AUTO, + res: ptr::null_mut(), + num_res: 0, + data: &this.service as *const EPICService as *const _, + size_data: mem::size_of::(), + dma_mask: 0, + fwnode: fwnode.map(|x| x.as_raw()).unwrap_or(ptr::null_mut()), + properties: ptr::null_mut(), + of_node_reused: false, + }; + let pdev = unsafe { from_err_ptr(bindings::platform_device_register_full(&info)) }; + match pdev { + Err(e) => { + dev_err!( + this.data.dev, + "Failed to create device for service {:?}: {:?}", + this.name, + e + ); + } + Ok(pdev) => { + let res = this.data.subdevices.lock().push(pdev, GFP_KERNEL); + if res.is_err() { + dev_err!(this.data.dev, "Failed to store subdevice"); + } + } + } + } +} + +impl AopData { + fn new(dev: &platform::Device) -> Result> { + Arc::pin_init( + pin_init!( + AopData { + dev: dev.as_ref().into(), + rtkit <- new_mutex!(None), + endpoints <- pin_init::pin_init_array_from_fn(|i| { + new_mutex!(AFKEndpoint::new(AFK_ENDPOINT_START + i as u8)) + }), + ep_shutdown <- FutureValue::pin_init(), + hid_listeners <- new_mutex!(KVec::new()), + subdevices <- new_mutex!(KVec::new()), + } + ), + GFP_KERNEL, + ) + } + fn start(&self) -> Result<()> { + { + let mut guard = self.rtkit.lock(); + let rtk = guard.as_mut().unwrap(); + rtk.wake()?; + } + for ep in 0..AFK_ENDPOINT_COUNT { + let rtk_ep_num = AFK_ENDPOINT_START + ep; + let mut guard = self.rtkit.lock(); + let rtk = guard.as_mut().unwrap(); + if !rtk.has_endpoint(rtk_ep_num) { + continue; + } + rtk.start_endpoint(rtk_ep_num)?; + let ep_guard = self.endpoints[ep as usize].lock(); + ep_guard.start(rtk)?; + } + Ok(()) + } + fn register_service( + self: Arc, + ep: &mut AFKEndpoint, + channel: u32, + name: &[u8], + ) -> Result<()> { + let svc = EPICService { + channel, + endpoint: ep.index, + }; + let dev_name = match name { + b"aop-audio" => c_str!("audio"), + b"las" => c_str!("las"), + b"als" => c_str!("als"), + _ => { + return Ok(()); + } + }; + // probe can call back into us, run it with locks dropped. + let work = AopServiceRegisterWork::new(dev_name, self, svc)?; + workqueue::system().enqueue(work); + Ok(()) + } + + fn process_fakehid_report(&self, ep: &AFKEndpoint, ch: u32, data: &[u8]) -> Result<()> { + let guard = self.hid_listeners.lock(); + for entry in &*guard { + if entry.svc.endpoint == ep.index && entry.svc.channel == ch { + return entry.listener.process_fakehid_report(data); + } + } + Ok(()) + } + + fn shutdown_complete(&self) { + self.ep_shutdown.complete(()); + } + + fn stop(&self) -> Result<()> { + for ep in 0..AFK_ENDPOINT_COUNT { + { + let rtk_ep_num = AFK_ENDPOINT_START + ep; + let mut guard = self.rtkit.lock(); + let rtk = guard.as_mut().unwrap(); + if !rtk.has_endpoint(rtk_ep_num) { + continue; + } + let ep_guard = self.endpoints[ep as usize].lock(); + ep_guard.stop(rtk)?; + } + self.ep_shutdown.wait(); + self.ep_shutdown.reset(); + } + Ok(()) + } + + fn patch_bootargs( + &self, + aop_mmio: &IoMem, + patches: &[(u32, u64)], + ) -> Result<()> { + let offset = aop_mmio.read32_relaxed(BOOTARGS_OFFSET) as usize; + let size = aop_mmio.read32_relaxed(BOOTARGS_SIZE) as usize; + let mut arg_bytes = KVec::::from_elem(0, size, GFP_KERNEL)?; + aop_mmio.try_memcpy_fromio(&mut arg_bytes, offset)?; + let mut idx = 0; + while idx < size { + let key = u32::from_le_bytes(arg_bytes[idx..idx + 4].try_into().unwrap()); + let size = u32::from_le_bytes(arg_bytes[idx + 4..idx + 8].try_into().unwrap()) as usize; + idx += 8; + for (k, v) in patches.iter() { + if *k != key { + continue; + } + arg_bytes[idx..idx + size].copy_from_slice(&(*v as u64).to_le_bytes()[..size]); + break; + } + idx += size; + } + aop_mmio.try_memcpy_toio(offset, &arg_bytes) + } + + fn start_cpu(&self, asc_mmio: &IoMem) -> Result<()> { + let val = asc_mmio.read32_relaxed(CPU_CONTROL); + asc_mmio.write32_relaxed(val | CPU_RUN, CPU_CONTROL); + Ok(()) + } +} + +impl AOP for AopData { + fn epic_call(&self, svc: &EPICService, subtype: u16, msg_bytes: &[u8]) -> Result { + let ep_idx = svc.endpoint - AFK_ENDPOINT_START; + let call = { + let mut rtk_guard = self.rtkit.lock(); + let rtk = rtk_guard.as_mut().unwrap(); + let mut ep_guard = self.endpoints[ep_idx as usize].lock(); + ep_guard.epic_notify(self, rtk, svc.channel, subtype, msg_bytes, None)? + }; + Ok(call.wait().retcode) + } + fn epic_call_ret( + &self, + svc: &EPICService, + subtype: u16, + msg_bytes: &[u8], + ret_len: usize, + ) -> Result<(u32, KVec)> { + let ep_idx = svc.endpoint - AFK_ENDPOINT_START; + let call = { + let mut rtk_guard = self.rtkit.lock(); + let rtk = rtk_guard.as_mut().unwrap(); + let mut ep_guard = self.endpoints[ep_idx as usize].lock(); + let mut ret_buf = KVec::new(); + ret_buf.resize(ret_len, 0, GFP_KERNEL)?; + ep_guard.epic_notify(self, rtk, svc.channel, subtype, msg_bytes, Some(ret_buf))? + }; + let res = call.wait(); + Ok((res.retcode, res.extra_data.unwrap())) + } + fn add_fakehid_listener( + &self, + svc: EPICService, + listener: Arc, + ) -> Result<()> { + let mut guard = self.hid_listeners.lock(); + Ok(guard.push(ListenerEntry { svc, listener }, GFP_KERNEL)?) + } + fn remove_fakehid_listener(&self, svc: &EPICService) -> bool { + let mut guard = self.hid_listeners.lock(); + for i in 0..guard.len() { + if guard[i].svc == *svc { + guard.swap_remove(i); + return true; + } + } + false + } + fn remove(&self) { + if let Err(e) = self.stop() { + dev_err!(self.dev, "Failed to stop AOP {:?}", e); + } + *self.rtkit.lock() = None; + let guard = self.subdevices.lock(); + for pdev in &*guard { + unsafe { + bindings::platform_device_unregister(*pdev); + } + } + } +} + +struct NoBuffer; +impl rtkit::Buffer for NoBuffer { + fn iova(&self) -> Result { + unreachable!() + } + fn buf(&mut self) -> Result> { + unreachable!() + } +} + +#[vtable] +impl rtkit::Operations for AopData { + type Data = Arc; + type Buffer = NoBuffer; + + fn recv_message(data: ::Borrowed<'_>, ep: u8, msg: u64) { + let mut rtk = data.rtkit.lock(); + let mut ep_guard = data.endpoints[(ep - AFK_ENDPOINT_START) as usize].lock(); + let ret = ep_guard.recv_message(data, rtk.as_mut().unwrap(), msg); + if let Err(e) = ret { + dev_err!(data.dev, "Failed to handle rtkit message, error: {:?}", e); + } + } + + fn crashed(data: ::Borrowed<'_>, _crashlog: Option<&[u8]>) { + dev_err!(data.dev, "AOP firmware crashed"); + } +} + +#[repr(transparent)] +struct AopDriver(Arc); + +struct AopHwConfig { + ec0p: u64, + alig: u64, + aopt: u64, +} + +const HW_CFG_T8103: AopHwConfig = AopHwConfig { + ec0p: 0x020000, + aopt: 1, + alig: 128, +}; +const HW_CFG_T8112: AopHwConfig = AopHwConfig { + ec0p: 0x020000, + aopt: 0, + alig: 128, +}; +const HW_CFG_T6000: AopHwConfig = AopHwConfig { + ec0p: 0x020000, + aopt: 0, + alig: 64, +}; +const HW_CFG_T6020: AopHwConfig = AopHwConfig { + ec0p: 0x0100_00000000, + aopt: 0, + alig: 64, +}; + +kernel::of_device_table!( + OF_TABLE, + MODULE_OF_TABLE, + ::IdInfo, + [ + (of::DeviceId::new(c_str!("apple,t8103-aop")), &HW_CFG_T8103), + (of::DeviceId::new(c_str!("apple,t8112-aop")), &HW_CFG_T8112), + (of::DeviceId::new(c_str!("apple,t6000-aop")), &HW_CFG_T6000), + (of::DeviceId::new(c_str!("apple,t6020-aop")), &HW_CFG_T6020), + ] +); + +impl platform::Driver for AopDriver { + type IdInfo = &'static AopHwConfig; + + const OF_ID_TABLE: Option> = Some(&OF_TABLE); + + fn probe( + pdev: &platform::Device, + info: Option<&Self::IdInfo>, + ) -> Result>> { + let cfg = info.ok_or(ENODEV)?; + unsafe { pdev.dma_set_mask_and_coherent(DmaMask::new::<42>())? }; + let aop_req = pdev.io_request_by_index(0).ok_or(EINVAL)?; + let aop_mmio = KBox::pin_init(aop_req.iomap_sized::(), GFP_KERNEL)?; + let asc_req = pdev.io_request_by_index(1).ok_or(EINVAL)?; + let asc_mmio = KBox::pin_init(asc_req.iomap_sized::(), GFP_KERNEL)?; + let data = AopData::new(pdev)?; + let aop_mmio = aop_mmio.access(pdev.as_ref())?; + data.patch_bootargs( + aop_mmio, + &[ + (from_fourcc(b"EC0p"), cfg.ec0p), + (from_fourcc(b"nCal"), 0x0), + (from_fourcc(b"alig"), cfg.alig), + (from_fourcc(b"AOPt"), cfg.aopt), + ], + )?; + let rtkit = rtkit::RtKit::::new(pdev.as_ref(), None, 0, data.clone())?; + *data.rtkit.lock() = Some(rtkit); + let asc_mmio = asc_mmio.access(pdev.as_ref())?; + let _ = data.start_cpu(asc_mmio); + data.start()?; + let data = data as Arc; + Ok(KBox::pin(AopDriver(data), GFP_KERNEL)?) + } +} + +impl Drop for AopDriver { + fn drop(&mut self) { + self.0.remove(); + } +} + +unsafe impl Send for AopDriver {} + +module_platform_driver! { + type: AopDriver, + name: "apple_aop", + description: "AOP driver", + license: "Dual MIT/GPL", +} diff --git a/drivers/soc/apple/apple-pmgr-misc.c b/drivers/soc/apple/apple-pmgr-misc.c new file mode 100644 index 00000000000000..e768f34aacc586 --- /dev/null +++ b/drivers/soc/apple/apple-pmgr-misc.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Apple SoC PMGR device power state driver + * + * Copyright The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include +#include +#include + +#define APPLE_CLKGEN_PSTATE 0 +#define APPLE_CLKGEN_PSTATE_DESIRED GENMASK(3, 0) + +#define SYS_DEV_PSTATE_SUSPEND 1 + +enum sys_device { + DEV_FABRIC, + DEV_DCS, + DEV_MAX, +}; + +struct apple_pmgr_sys_device { + void __iomem *base; + u32 active_state; + u32 suspend_state; +}; + +struct apple_pmgr_misc { + struct device *dev; + struct apple_pmgr_sys_device devices[DEV_MAX]; +}; + +static void apple_pmgr_sys_dev_set_pstate(struct apple_pmgr_misc *misc, + enum sys_device dev, bool active) +{ + u32 pstate; + u32 val; + + if (!misc->devices[dev].base) + return; + + if (active) + pstate = misc->devices[dev].active_state; + else + pstate = misc->devices[dev].suspend_state; + + printk("set %d ps to pstate %d\n", dev, pstate); + + val = readl_relaxed(misc->devices[dev].base + APPLE_CLKGEN_PSTATE); + val &= ~APPLE_CLKGEN_PSTATE_DESIRED; + val |= FIELD_PREP(APPLE_CLKGEN_PSTATE_DESIRED, pstate); + writel_relaxed(val, misc->devices[dev].base); +} + +static int __maybe_unused apple_pmgr_misc_suspend_noirq(struct device *dev) +{ + struct apple_pmgr_misc *misc = dev_get_drvdata(dev); + int i; + + for (i = 0; i < DEV_MAX; i++) + apple_pmgr_sys_dev_set_pstate(misc, i, false); + + return 0; +} + +static int __maybe_unused apple_pmgr_misc_resume_noirq(struct device *dev) +{ + struct apple_pmgr_misc *misc = dev_get_drvdata(dev); + int i; + + for (i = 0; i < DEV_MAX; i++) + apple_pmgr_sys_dev_set_pstate(misc, i, true); + + return 0; +} + +static bool apple_pmgr_init_device(struct apple_pmgr_misc *misc, + enum sys_device dev, const char *device_name) +{ + void __iomem *base; + char name[32]; + u32 val; + + snprintf(name, sizeof(name), "%s-ps", device_name); + + base = devm_platform_ioremap_resource_byname( + to_platform_device(misc->dev), name); + if (!base) + return false; + + val = readl_relaxed(base + APPLE_CLKGEN_PSTATE); + + misc->devices[dev].base = base; + misc->devices[dev].active_state = + FIELD_GET(APPLE_CLKGEN_PSTATE_DESIRED, val); + misc->devices[dev].suspend_state = SYS_DEV_PSTATE_SUSPEND; + + snprintf(name, sizeof(name), "apple,%s-min-ps", device_name); + of_property_read_u32(misc->dev->of_node, name, + &misc->devices[dev].suspend_state); + + return true; +} + +static int apple_pmgr_misc_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct apple_pmgr_misc *misc; + int ret = -ENODEV; + + misc = devm_kzalloc(dev, sizeof(*misc), GFP_KERNEL); + if (!misc) + return -ENOMEM; + + misc->dev = dev; + + if (apple_pmgr_init_device(misc, DEV_FABRIC, "fabric")) + ret = 0; + + if (apple_pmgr_init_device(misc, DEV_DCS, "dcs")) + ret = 0; + + platform_set_drvdata(pdev, misc); + + return ret; +} + +static const struct of_device_id apple_pmgr_misc_of_match[] = { + { .compatible = "apple,t6000-pmgr-misc" }, + {} +}; + +MODULE_DEVICE_TABLE(of, apple_pmgr_misc_of_match); + +static const struct dev_pm_ops apple_pmgr_misc_pm_ops = { + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(apple_pmgr_misc_suspend_noirq, + apple_pmgr_misc_resume_noirq) +}; + +static struct platform_driver apple_pmgr_misc_driver = { + .probe = apple_pmgr_misc_probe, + .driver = { + .name = "apple-pmgr-misc", + .of_match_table = apple_pmgr_misc_of_match, + .pm = pm_ptr(&apple_pmgr_misc_pm_ops), + }, +}; + +MODULE_AUTHOR("Hector Martin "); +MODULE_DESCRIPTION("PMGR misc driver for Apple SoCs"); +MODULE_LICENSE("GPL v2"); + +module_platform_driver(apple_pmgr_misc_driver); diff --git a/drivers/soc/apple/dockchannel.c b/drivers/soc/apple/dockchannel.c new file mode 100644 index 00000000000000..8f67c639da4d20 --- /dev/null +++ b/drivers/soc/apple/dockchannel.c @@ -0,0 +1,405 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Apple DockChannel FIFO driver + * Copyright The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DOCKCHANNEL_MAX_IRQ 32 + +#define DOCKCHANNEL_TX_TIMEOUT_MS 1000 +#define DOCKCHANNEL_RX_TIMEOUT_MS 1000 + +#define IRQ_MASK 0x0 +#define IRQ_FLAG 0x4 + +#define IRQ_TX BIT(0) +#define IRQ_RX BIT(1) + +#define CONFIG_TX_THRESH 0x0 +#define CONFIG_RX_THRESH 0x4 + +#define DATA_TX8 0x4 +#define DATA_TX16 0x8 +#define DATA_TX24 0xc +#define DATA_TX32 0x10 +#define DATA_TX_FREE 0x14 +#define DATA_RX8 0x1c +#define DATA_RX16 0x20 +#define DATA_RX24 0x24 +#define DATA_RX32 0x28 +#define DATA_RX_COUNT 0x2c + +struct dockchannel { + struct device *dev; + int tx_irq; + int rx_irq; + + void __iomem *config_base; + void __iomem *data_base; + + u32 fifo_size; + bool awaiting; + struct completion tx_comp; + struct completion rx_comp; + + void *cookie; + void (*data_available)(void *cookie, size_t avail); +}; + +struct dockchannel_common { + struct device *dev; + struct irq_domain *domain; + int irq; + + void __iomem *irq_base; +}; + +/* Dockchannel FIFO functions */ + +static irqreturn_t dockchannel_tx_irq(int irq, void *data) +{ + struct dockchannel *dockchannel = data; + + disable_irq_nosync(irq); + complete(&dockchannel->tx_comp); + + return IRQ_HANDLED; +} + +static irqreturn_t dockchannel_rx_irq(int irq, void *data) +{ + struct dockchannel *dockchannel = data; + + disable_irq_nosync(irq); + + if (dockchannel->awaiting) { + return IRQ_WAKE_THREAD; + } else { + complete(&dockchannel->rx_comp); + return IRQ_HANDLED; + } +} + +static irqreturn_t dockchannel_rx_irq_thread(int irq, void *data) +{ + struct dockchannel *dockchannel = data; + size_t avail = readl_relaxed(dockchannel->data_base + DATA_RX_COUNT); + + dockchannel->awaiting = false; + dockchannel->data_available(dockchannel->cookie, avail); + + return IRQ_HANDLED; +} + +int dockchannel_send(struct dockchannel *dockchannel, const void *buf, size_t count) +{ + size_t left = count; + const u8 *p = buf; + + while (left > 0) { + size_t avail = readl_relaxed(dockchannel->data_base + DATA_TX_FREE); + size_t block = min(left, avail); + + if (avail == 0) { + size_t threshold = min((size_t)(dockchannel->fifo_size / 2), left); + + writel_relaxed(threshold, dockchannel->config_base + CONFIG_TX_THRESH); + reinit_completion(&dockchannel->tx_comp); + enable_irq(dockchannel->tx_irq); + + if (!wait_for_completion_timeout(&dockchannel->tx_comp, + msecs_to_jiffies(DOCKCHANNEL_TX_TIMEOUT_MS))) { + disable_irq(dockchannel->tx_irq); + return -ETIMEDOUT; + } + + continue; + } + + while (block >= 4) { + writel_relaxed(get_unaligned_le32(p), dockchannel->data_base + DATA_TX32); + p += 4; + left -= 4; + block -= 4; + } + while (block > 0) { + writeb_relaxed(*p++, dockchannel->data_base + DATA_TX8); + left--; + block--; + } + } + + return count; +} +EXPORT_SYMBOL(dockchannel_send); + +int dockchannel_recv(struct dockchannel *dockchannel, void *buf, size_t count) +{ + size_t left = count; + u8 *p = buf; + + while (left > 0) { + size_t avail = readl_relaxed(dockchannel->data_base + DATA_RX_COUNT); + size_t block = min(left, avail); + + if (avail == 0) { + size_t threshold = min((size_t)(dockchannel->fifo_size / 2), left); + + writel_relaxed(threshold, dockchannel->config_base + CONFIG_RX_THRESH); + reinit_completion(&dockchannel->rx_comp); + enable_irq(dockchannel->rx_irq); + + if (!wait_for_completion_timeout(&dockchannel->rx_comp, + msecs_to_jiffies(DOCKCHANNEL_RX_TIMEOUT_MS))) { + disable_irq(dockchannel->rx_irq); + return -ETIMEDOUT; + } + + continue; + } + + while (block >= 4) { + put_unaligned_le32(readl_relaxed(dockchannel->data_base + DATA_RX32), p); + p += 4; + left -= 4; + block -= 4; + } + while (block > 0) { + *p++ = readl_relaxed(dockchannel->data_base + DATA_RX8) >> 8; + left--; + block--; + } + } + + return count; +} +EXPORT_SYMBOL(dockchannel_recv); + +int dockchannel_await(struct dockchannel *dockchannel, + void (*callback)(void *cookie, size_t avail), + void *cookie, size_t count) +{ + size_t threshold = min((size_t)dockchannel->fifo_size, count); + + if (!count) { + dockchannel->awaiting = false; + disable_irq(dockchannel->rx_irq); + return 0; + } + + dockchannel->data_available = callback; + dockchannel->cookie = cookie; + dockchannel->awaiting = true; + writel_relaxed(threshold, dockchannel->config_base + CONFIG_RX_THRESH); + enable_irq(dockchannel->rx_irq); + + return threshold; +} +EXPORT_SYMBOL(dockchannel_await); + +struct dockchannel *dockchannel_init(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dockchannel *dockchannel; + int ret; + + dockchannel = devm_kzalloc(dev, sizeof(*dockchannel), GFP_KERNEL); + if (!dockchannel) + return ERR_PTR(-ENOMEM); + + dockchannel->dev = dev; + dockchannel->config_base = devm_platform_ioremap_resource_byname(pdev, "config"); + if (IS_ERR(dockchannel->config_base)) + return (__force void *)dockchannel->config_base; + + dockchannel->data_base = devm_platform_ioremap_resource_byname(pdev, "data"); + if (IS_ERR(dockchannel->data_base)) + return (__force void *)dockchannel->data_base; + + ret = of_property_read_u32(dev->of_node, "apple,fifo-size", &dockchannel->fifo_size); + if (ret) + return ERR_PTR(dev_err_probe(dev, ret, "Missing apple,fifo-size property")); + + init_completion(&dockchannel->tx_comp); + init_completion(&dockchannel->rx_comp); + + dockchannel->tx_irq = platform_get_irq_byname(pdev, "tx"); + if (dockchannel->tx_irq <= 0) { + return ERR_PTR(dev_err_probe(dev, dockchannel->tx_irq, + "Failed to get TX IRQ")); + } + + dockchannel->rx_irq = platform_get_irq_byname(pdev, "rx"); + if (dockchannel->rx_irq <= 0) { + return ERR_PTR(dev_err_probe(dev, dockchannel->rx_irq, + "Failed to get RX IRQ")); + } + + ret = devm_request_irq(dev, dockchannel->tx_irq, dockchannel_tx_irq, IRQF_NO_AUTOEN, + "apple-dockchannel-tx", dockchannel); + if (ret) + return ERR_PTR(dev_err_probe(dev, ret, "Failed to request TX IRQ")); + + ret = devm_request_threaded_irq(dev, dockchannel->rx_irq, dockchannel_rx_irq, + dockchannel_rx_irq_thread, IRQF_NO_AUTOEN, + "apple-dockchannel-rx", dockchannel); + if (ret) + return ERR_PTR(dev_err_probe(dev, ret, "Failed to request RX IRQ")); + + return dockchannel; +} +EXPORT_SYMBOL(dockchannel_init); + + +/* Dockchannel IRQchip */ + +static void dockchannel_irq(struct irq_desc *desc) +{ + unsigned int irq = irq_desc_get_irq(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + struct dockchannel_common *dcc = irq_get_handler_data(irq); + unsigned long flags = readl_relaxed(dcc->irq_base + IRQ_FLAG); + int bit; + + chained_irq_enter(chip, desc); + + for_each_set_bit(bit, &flags, DOCKCHANNEL_MAX_IRQ) + generic_handle_domain_irq(dcc->domain, bit); + + chained_irq_exit(chip, desc); +} + +static void dockchannel_irq_ack(struct irq_data *data) +{ + struct dockchannel_common *dcc = irq_data_get_irq_chip_data(data); + unsigned int hwirq = data->hwirq; + + writel_relaxed(BIT(hwirq), dcc->irq_base + IRQ_FLAG); +} + +static void dockchannel_irq_mask(struct irq_data *data) +{ + struct dockchannel_common *dcc = irq_data_get_irq_chip_data(data); + unsigned int hwirq = data->hwirq; + u32 val = readl_relaxed(dcc->irq_base + IRQ_MASK); + + writel_relaxed(val & ~BIT(hwirq), dcc->irq_base + IRQ_MASK); +} + +static void dockchannel_irq_unmask(struct irq_data *data) +{ + struct dockchannel_common *dcc = irq_data_get_irq_chip_data(data); + unsigned int hwirq = data->hwirq; + u32 val = readl_relaxed(dcc->irq_base + IRQ_MASK); + + writel_relaxed(val | BIT(hwirq), dcc->irq_base + IRQ_MASK); +} + +static const struct irq_chip dockchannel_irqchip = { + .name = "dockchannel-irqc", + .irq_ack = dockchannel_irq_ack, + .irq_mask = dockchannel_irq_mask, + .irq_unmask = dockchannel_irq_unmask, +}; + +static int dockchannel_irq_domain_map(struct irq_domain *d, unsigned int virq, + irq_hw_number_t hw) +{ + irq_set_chip_data(virq, d->host_data); + irq_set_chip_and_handler(virq, &dockchannel_irqchip, handle_level_irq); + + return 0; +} + +static const struct irq_domain_ops dockchannel_irq_domain_ops = { + .xlate = irq_domain_xlate_twocell, + .map = dockchannel_irq_domain_map, +}; + +static int dockchannel_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dockchannel_common *dcc; + struct device_node *child; + + dcc = devm_kzalloc(dev, sizeof(*dcc), GFP_KERNEL); + if (!dcc) + return -ENOMEM; + + dcc->dev = dev; + platform_set_drvdata(pdev, dcc); + + dcc->irq_base = devm_platform_ioremap_resource_byname(pdev, "irq"); + if (IS_ERR(dcc->irq_base)) + return PTR_ERR(dcc->irq_base); + + writel_relaxed(0, dcc->irq_base + IRQ_MASK); + writel_relaxed(~0, dcc->irq_base + IRQ_FLAG); + + dcc->domain = irq_domain_add_linear(dev->of_node, DOCKCHANNEL_MAX_IRQ, + &dockchannel_irq_domain_ops, dcc); + if (!dcc->domain) + return -ENOMEM; + + dcc->irq = platform_get_irq(pdev, 0); + if (dcc->irq <= 0) + return dev_err_probe(dev, dcc->irq, "Failed to get IRQ"); + + irq_set_handler_data(dcc->irq, dcc); + irq_set_chained_handler(dcc->irq, dockchannel_irq); + + devm_of_platform_populate(dev); + + return 0; +} + +static void dockchannel_remove(struct platform_device *pdev) +{ + struct dockchannel_common *dcc = platform_get_drvdata(pdev); + int hwirq; + + device_for_each_child(&pdev->dev, NULL, of_platform_device_destroy); + + irq_set_chained_handler_and_data(dcc->irq, NULL, NULL); + + for (hwirq = 0; hwirq < DOCKCHANNEL_MAX_IRQ; hwirq++) + irq_dispose_mapping(irq_find_mapping(dcc->domain, hwirq)); + + irq_domain_remove(dcc->domain); + + writel_relaxed(0, dcc->irq_base + IRQ_MASK); + writel_relaxed(~0, dcc->irq_base + IRQ_FLAG); +} + +static const struct of_device_id dockchannel_of_match[] = { + { .compatible = "apple,dockchannel" }, + {}, +}; +MODULE_DEVICE_TABLE(of, dockchannel_of_match); + +static struct platform_driver dockchannel_driver = { + .driver = { + .name = "dockchannel", + .of_match_table = dockchannel_of_match, + }, + .probe = dockchannel_probe, + .remove = dockchannel_remove, +}; +module_platform_driver(dockchannel_driver); + +MODULE_AUTHOR("Hector Martin "); +MODULE_LICENSE("Dual MIT/GPL"); +MODULE_DESCRIPTION("Apple DockChannel driver"); diff --git a/drivers/soc/apple/mailbox.c b/drivers/soc/apple/mailbox.c index 8f29108dc69ac9..330015eea2ebe4 100644 --- a/drivers/soc/apple/mailbox.c +++ b/drivers/soc/apple/mailbox.c @@ -28,9 +28,9 @@ #include #include #include +#include #include #include -#include "mailbox.h" #define APPLE_ASC_MBOX_CONTROL_FULL BIT(16) #define APPLE_ASC_MBOX_CONTROL_EMPTY BIT(17) @@ -302,11 +302,18 @@ struct apple_mbox *apple_mbox_get(struct device *dev, int index) return ERR_PTR(-EPROBE_DEFER); mbox = platform_get_drvdata(pdev); - if (!mbox) - return ERR_PTR(-EPROBE_DEFER); + if (!mbox) { + mbox = ERR_PTR(-EPROBE_DEFER); + goto out_put_pdev; + } + + if (!device_link_add(dev, &pdev->dev, DL_FLAG_AUTOREMOVE_CONSUMER)) { + mbox = ERR_PTR(-ENODEV); + goto out_put_pdev; + } - if (!device_link_add(dev, &pdev->dev, DL_FLAG_AUTOREMOVE_CONSUMER)) - return ERR_PTR(-ENODEV); +out_put_pdev: + put_device(&pdev->dev); return mbox; } diff --git a/drivers/soc/apple/rtkit-helper.c b/drivers/soc/apple/rtkit-helper.c new file mode 100644 index 00000000000000..080d083ed9bd2f --- /dev/null +++ b/drivers/soc/apple/rtkit-helper.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Apple Generic RTKit helper coprocessor + * Copyright The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define APPLE_ASC_CPU_CONTROL 0x44 +#define APPLE_ASC_CPU_CONTROL_RUN BIT(4) + +struct apple_rtkit_helper { + struct device *dev; + struct apple_rtkit *rtk; + + void __iomem *asc_base; + + struct resource *sram; + void __iomem *sram_base; +}; + +static int apple_rtkit_helper_shmem_setup(void *cookie, struct apple_rtkit_shmem *bfr) +{ + struct apple_rtkit_helper *helper = cookie; + struct resource res = { + .start = bfr->iova, + .end = bfr->iova + bfr->size - 1, + .name = "rtkit_map", + }; + + if (!bfr->iova) { + bfr->buffer = dma_alloc_coherent(helper->dev, bfr->size, + &bfr->iova, GFP_KERNEL); + if (!bfr->buffer) + return -ENOMEM; + return 0; + } + + if (!helper->sram) { + dev_err(helper->dev, + "RTKit buffer request with no SRAM region: %pR", &res); + return -EFAULT; + } + + res.flags = helper->sram->flags; + + if (res.end < res.start || !resource_contains(helper->sram, &res)) { + dev_err(helper->dev, + "RTKit buffer request outside SRAM region: %pR", &res); + return -EFAULT; + } + + bfr->iomem = helper->sram_base + (res.start - helper->sram->start); + bfr->is_mapped = true; + + return 0; +} + +static void apple_rtkit_helper_shmem_destroy(void *cookie, struct apple_rtkit_shmem *bfr) +{ + // no-op +} + +static const struct apple_rtkit_ops apple_rtkit_helper_ops = { + .shmem_setup = apple_rtkit_helper_shmem_setup, + .shmem_destroy = apple_rtkit_helper_shmem_destroy, +}; + +static int apple_rtkit_helper_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct apple_rtkit_helper *helper; + int ret; + + /* 44 bits for addresses in standard RTKit requests */ + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(44)); + if (ret) + return ret; + + helper = devm_kzalloc(dev, sizeof(*helper), GFP_KERNEL); + if (!helper) + return -ENOMEM; + + helper->dev = dev; + platform_set_drvdata(pdev, helper); + + helper->asc_base = devm_platform_ioremap_resource_byname(pdev, "asc"); + if (IS_ERR(helper->asc_base)) + return PTR_ERR(helper->asc_base); + + helper->sram = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sram"); + if (helper->sram) { + helper->sram_base = devm_ioremap_resource(dev, helper->sram); + if (IS_ERR(helper->sram_base)) + return dev_err_probe(dev, PTR_ERR(helper->sram_base), + "Failed to map SRAM region"); + } + + helper->rtk = + devm_apple_rtkit_init(dev, helper, NULL, 0, &apple_rtkit_helper_ops); + if (IS_ERR(helper->rtk)) + return dev_err_probe(dev, PTR_ERR(helper->rtk), + "Failed to intialize RTKit"); + + writel_relaxed(APPLE_ASC_CPU_CONTROL_RUN, + helper->asc_base + APPLE_ASC_CPU_CONTROL); + + /* Works for both wake and boot */ + ret = apple_rtkit_wake(helper->rtk); + if (ret != 0) + return dev_err_probe(dev, ret, "Failed to wake up coprocessor"); + + return 0; +} + +static void apple_rtkit_helper_remove(struct platform_device *pdev) +{ + struct apple_rtkit_helper *helper = platform_get_drvdata(pdev); + + if (apple_rtkit_is_running(helper->rtk)) + apple_rtkit_quiesce(helper->rtk); + + writel_relaxed(0, helper->asc_base + APPLE_ASC_CPU_CONTROL); +} + +static const struct of_device_id apple_rtkit_helper_of_match[] = { + { .compatible = "apple,rtk-helper-asc4" }, + {}, +}; +MODULE_DEVICE_TABLE(of, apple_rtkit_helper_of_match); + +static struct platform_driver apple_rtkit_helper_driver = { + .driver = { + .name = "rtkit-helper", + .of_match_table = apple_rtkit_helper_of_match, + }, + .probe = apple_rtkit_helper_probe, + .remove = apple_rtkit_helper_remove, +}; +module_platform_driver(apple_rtkit_helper_driver); + +MODULE_AUTHOR("Hector Martin "); +MODULE_LICENSE("Dual MIT/GPL"); +MODULE_DESCRIPTION("Apple RTKit helper driver"); diff --git a/drivers/soc/apple/rtkit-internal.h b/drivers/soc/apple/rtkit-internal.h index b8d5244678f010..c82065a8bf7b03 100644 --- a/drivers/soc/apple/rtkit-internal.h +++ b/drivers/soc/apple/rtkit-internal.h @@ -15,9 +15,9 @@ #include #include #include +#include #include #include -#include "mailbox.h" #define APPLE_RTKIT_APP_ENDPOINT_START 0x20 #define APPLE_RTKIT_MAX_ENDPOINTS 0x100 diff --git a/drivers/soc/apple/rtkit.c b/drivers/soc/apple/rtkit.c index b8d4da147d23f7..67a21b21a30d98 100644 --- a/drivers/soc/apple/rtkit.c +++ b/drivers/soc/apple/rtkit.c @@ -22,6 +22,7 @@ enum { APPLE_RTKIT_EP_DEBUG = 3, APPLE_RTKIT_EP_IOREPORT = 4, APPLE_RTKIT_EP_OSLOG = 8, + APPLE_RTKIT_EP_TRACEKIT = 0xa, }; #define APPLE_RTKIT_MGMT_TYPE GENMASK_ULL(59, 52) @@ -191,6 +192,7 @@ static void apple_rtkit_management_rx_epmap(struct apple_rtkit *rtk, u64 msg) case APPLE_RTKIT_EP_DEBUG: case APPLE_RTKIT_EP_IOREPORT: case APPLE_RTKIT_EP_OSLOG: + case APPLE_RTKIT_EP_TRACEKIT: dev_dbg(rtk->dev, "RTKit: Starting system endpoint 0x%02x\n", ep); apple_rtkit_start_ep(rtk, ep); @@ -361,7 +363,7 @@ static void apple_rtkit_memcpy(struct apple_rtkit *rtk, void *dst, static void apple_rtkit_crashlog_rx(struct apple_rtkit *rtk, u64 msg) { u8 type = FIELD_GET(APPLE_RTKIT_SYSLOG_TYPE, msg); - u8 *bfr; + u8 *bfr __free(kfree) = NULL; if (type != APPLE_RTKIT_CRASHLOG_CRASH) { dev_warn(rtk->dev, "RTKit: Unknown crashlog message: %llx\n", @@ -394,9 +396,7 @@ static void apple_rtkit_crashlog_rx(struct apple_rtkit *rtk, u64 msg) rtk->crashed = true; if (rtk->ops->crashed) - rtk->ops->crashed(rtk->cookie, bfr, rtk->crashlog_buffer.size); - - kfree(bfr); + rtk->ops->crashed(rtk->cookie, bfr, bfr ? rtk->crashlog_buffer.size : 0); } static void apple_rtkit_ioreport_rx(struct apple_rtkit *rtk, u64 msg) @@ -639,6 +639,12 @@ int apple_rtkit_poll(struct apple_rtkit *rtk) } EXPORT_SYMBOL_GPL(apple_rtkit_poll); +bool apple_rtkit_has_endpoint(struct apple_rtkit *rtk, u8 ep) +{ + return test_bit(ep, rtk->endpoints); +} +EXPORT_SYMBOL_GPL(apple_rtkit_has_endpoint); + int apple_rtkit_start_ep(struct apple_rtkit *rtk, u8 endpoint) { u64 msg; @@ -958,6 +964,12 @@ struct apple_rtkit *devm_apple_rtkit_init(struct device *dev, void *cookie, } EXPORT_SYMBOL_GPL(devm_apple_rtkit_init); +void devm_apple_rtkit_free(struct device *dev, struct apple_rtkit *rtk) +{ + devm_release_action(dev, apple_rtkit_free_wrapper, rtk); +} +EXPORT_SYMBOL_GPL(devm_apple_rtkit_free); + MODULE_LICENSE("Dual MIT/GPL"); MODULE_AUTHOR("Sven Peter "); MODULE_DESCRIPTION("Apple RTKit driver"); diff --git a/drivers/soc/apple/sep.rs b/drivers/soc/apple/sep.rs new file mode 100644 index 00000000000000..228310cc2ae822 --- /dev/null +++ b/drivers/soc/apple/sep.rs @@ -0,0 +1,353 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +#![recursion_limit = "2048"] + +//! Apple SEP driver +//! +//! Copyright (C) The Asahi Linux Contributors + +use core::sync::atomic::{AtomicBool, Ordering}; + +use kernel::{ + bindings, c_str, device, dma, module_platform_driver, new_mutex, of, platform, + prelude::*, + soc::apple::mailbox::{MailCallback, Mailbox, Message}, + sync::{Arc, Mutex}, + types::{ARef, ForeignOwnable}, + workqueue::{self, impl_has_work, new_work, Work, WorkItem}, +}; + +const SHMEM_SIZE: usize = 0x30000; +const MSG_BOOT_TZ0: u64 = 0x5; +const MSG_BOOT_IMG4: u64 = 0x6; +const MSG_SET_SHMEM: u64 = 0x18; +const MSG_BOOT_TZ0_ACK1: u64 = 0x69; +const MSG_BOOT_TZ0_ACK2: u64 = 0xD2; +const MSG_BOOT_IMG4_ACK: u64 = 0x6A; +const MSG_ADVERTISE_EP: u64 = 0; +const EP_DISCOVER: u64 = 0xFD; +const EP_SHMEM: u64 = 0xFE; +const EP_BOOT: u64 = 0xFF; + +const MSG_TYPE_SHIFT: u32 = 16; +const MSG_TYPE_MASK: u64 = 0xFF; +//const MSG_PARAM_SHIFT: u32 = 24; +//const MSG_PARAM_MASK: u64 = 0xFF; + +const MSG_EP_MASK: u64 = 0xFF; +const MSG_DATA_SHIFT: u32 = 32; + +const IOVA_SHIFT: u32 = 0xC; + +type ShMem = dma::CoherentAllocation; + +fn align_up(v: usize, a: usize) -> usize { + (v + a - 1) & !(a - 1) +} + +fn memcpy_to_iomem(iomem: &mut ShMem, off: usize, src: &[u8]) -> Result<()> { + // SAFETY: + // as_slice_mut() checks that off and src.len() are whithin iomem's limits. + // memcpy_to_iomem is only called from within probe() ansuring there are no + // concurrent read and write accesses to the same region while the slice is + // alive per as_slice_mut()'s requiremnts. + unsafe { + let target = iomem.as_slice_mut(off, src.len())?; + target.copy_from_slice(src); + } + Ok(()) +} + +fn build_shmem(dev: &platform::Device) -> Result { + let fwnode = dev.as_ref().fwnode().ok_or(EIO)?; + let mut iomem = + dma::CoherentAllocation::::alloc_coherent(dev.as_ref(), SHMEM_SIZE, GFP_KERNEL)?; + + let panic_offset = 0x4000; + let panic_size = 0x8000; + memcpy_to_iomem(&mut iomem, panic_offset, &1u32.to_le_bytes())?; + + let lpol_offset = panic_offset + panic_size; + let lpol_prop_name = c_str!("local-policy-manifest"); + let lpol_prop_size = fwnode.property_count_elem::(lpol_prop_name)?; + let lpol = fwnode + .property_read_array_vec(lpol_prop_name, lpol_prop_size)? + .required_by(dev.as_ref())?; + memcpy_to_iomem( + &mut iomem, + lpol_offset, + &(lpol_prop_size as u32).to_le_bytes(), + )?; + memcpy_to_iomem(&mut iomem, lpol_offset + 4, &lpol)?; + let lpol_size = align_up(lpol_prop_size + 4, 0x4000); + + let ibot_offset = lpol_offset + lpol_size; + let ibot_prop_name = c_str!("iboot-manifest"); + let ibot_prop_size = fwnode.property_count_elem::(ibot_prop_name)?; + let ibot = fwnode + .property_read_array_vec(ibot_prop_name, ibot_prop_size)? + .required_by(dev.as_ref())?; + memcpy_to_iomem( + &mut iomem, + ibot_offset, + &(ibot_prop_size as u32).to_le_bytes(), + )?; + memcpy_to_iomem(&mut iomem, ibot_offset + 4, &ibot)?; + let ibot_size = align_up(ibot_prop_size + 4, 0x4000); + + memcpy_to_iomem(&mut iomem, 0, b"CNIP")?; + memcpy_to_iomem(&mut iomem, 4, &(panic_size as u32).to_le_bytes())?; + memcpy_to_iomem(&mut iomem, 8, &(panic_offset as u32).to_le_bytes())?; + + memcpy_to_iomem(&mut iomem, 16, b"OPLA")?; + memcpy_to_iomem(&mut iomem, 16 + 4, &(lpol_size as u32).to_le_bytes())?; + memcpy_to_iomem(&mut iomem, 16 + 8, &(lpol_offset as u32).to_le_bytes())?; + + memcpy_to_iomem(&mut iomem, 32, b"IPIS")?; + memcpy_to_iomem(&mut iomem, 32 + 4, &(ibot_size as u32).to_le_bytes())?; + memcpy_to_iomem(&mut iomem, 32 + 8, &(ibot_offset as u32).to_le_bytes())?; + + memcpy_to_iomem(&mut iomem, 48, b"llun")?; + Ok(iomem) +} + +#[pin_data] +struct SepReceiveWork { + data: Arc, + msg: Message, + #[pin] + work: Work, +} + +impl_has_work! { + impl HasWork for SepReceiveWork { self.work } +} + +impl SepReceiveWork { + fn new(data: Arc, msg: Message) -> Result> { + Arc::pin_init( + pin_init!(SepReceiveWork { + data, + msg, + work <- new_work!("SepReceiveWork::work"), + }), + GFP_ATOMIC, + ) + } +} + +impl WorkItem for SepReceiveWork { + type Pointer = Arc; + + fn run(this: Arc) { + this.data.process_message(this.msg); + } +} + +struct FwRegionParams { + addr: u64, + size: usize, +} + +#[pin_data] +struct SepData { + dev: ARef, + #[pin] + mbox: Mutex>>, + shmem: ShMem, + region_params: FwRegionParams, + fw_mapped: AtomicBool, +} + +impl SepData { + fn new( + dev: &platform::Device, + region_params: FwRegionParams, + ) -> Result> { + Arc::pin_init( + try_pin_init!(SepData { + shmem: build_shmem(dev)?, + dev: ARef::::from(dev.as_ref()), + mbox <- new_mutex!(None), + region_params, + fw_mapped: AtomicBool::new(false), + }), + GFP_KERNEL, + ) + } + fn start(&self) -> Result<()> { + self.mbox.lock().as_ref().unwrap().send( + Message { + msg0: EP_BOOT | (MSG_BOOT_TZ0 << MSG_TYPE_SHIFT), + msg1: 0, + }, + false, + ) + } + fn load_fw_and_shmem(&self) -> Result<()> { + let fw_addr = unsafe { + let res = bindings::dma_map_resource( + self.dev.as_raw(), + self.region_params.addr, + self.region_params.size, + bindings::dma_data_direction_DMA_TO_DEVICE, + 0, + ); + if bindings::dma_mapping_error(self.dev.as_raw(), res) != 0 { + dev_err!(self.dev, "Failed to map firmware"); + return Err(ENOMEM); + } + self.fw_mapped.store(true, Ordering::Relaxed); + res >> IOVA_SHIFT + }; + let guard = self.mbox.lock(); + let mbox = guard.as_ref().unwrap(); + mbox.send( + Message { + msg0: EP_BOOT | (MSG_BOOT_IMG4 << MSG_TYPE_SHIFT) | (fw_addr << MSG_DATA_SHIFT), + msg1: 0, + }, + false, + )?; + let shm_addr = self.shmem.dma_handle() >> IOVA_SHIFT; + mbox.send( + Message { + msg0: EP_SHMEM | (MSG_SET_SHMEM << MSG_TYPE_SHIFT) | (shm_addr << MSG_DATA_SHIFT), + msg1: 0, + }, + false, + )?; + Ok(()) + } + fn process_boot_msg(&self, msg: Message) { + let ty = (msg.msg0 >> MSG_TYPE_SHIFT) & MSG_TYPE_MASK; + match ty { + MSG_BOOT_TZ0_ACK1 => {} + MSG_BOOT_TZ0_ACK2 => { + let res = self.load_fw_and_shmem(); + if let Err(e) = res { + dev_err!(self.dev, "Unable to load firmware: {:?}", e); + } + } + MSG_BOOT_IMG4_ACK => {} + _ => { + dev_err!(self.dev, "Unknown boot message type: {}", ty); + } + } + } + fn process_discover_msg(&self, msg: Message) { + let ty = (msg.msg0 >> MSG_TYPE_SHIFT) & MSG_TYPE_MASK; + //let data = (msg.msg0 >> MSG_DATA_SHIFT) as u32; + //let param = (msg.msg0 >> MSG_PARAM_SHIFT) & MSG_PARAM_MASK; + match ty { + MSG_ADVERTISE_EP => { + /*dev_info!( + self.dev, + "Got endpoint {:?} at {}", + core::str::from_utf8(&data.to_be_bytes()), + param + );*/ + } + _ => { + //dev_warn!(self.dev, "Unknown discovery message type: {}", ty); + } + } + } + fn process_message(&self, msg: Message) { + let ep = msg.msg0 & MSG_EP_MASK; + match ep { + EP_BOOT => self.process_boot_msg(msg), + EP_DISCOVER => self.process_discover_msg(msg), + _ => {} // dev_warn!(self.dev, "Message from unknown endpoint: {}", ep), + } + } + fn remove(&self) { + *self.mbox.lock() = None; + if self.fw_mapped.load(Ordering::Relaxed) { + unsafe { + bindings::dma_unmap_resource( + self.dev.as_raw(), + self.region_params.addr, + self.region_params.size, + bindings::dma_data_direction_DMA_TO_DEVICE, + 0, + ); + } + } + } +} + +impl MailCallback for SepData { + type Data = Arc; + fn recv_message(data: ::Borrowed<'_>, msg: Message) { + let work = SepReceiveWork::new(data.into(), msg); + if let Ok(work) = work { + let res = workqueue::system().enqueue(work); + if res.is_err() { + dev_err!( + data.dev, + "Unable to schedule work item for message {}", + msg.msg0 + ); + } + } else { + dev_err!( + data.dev, + "Unable to allocate work item for message {}", + msg.msg0 + ); + } + } +} + +unsafe impl Send for SepData {} +unsafe impl Sync for SepData {} + +struct SepDriver(Arc); + +kernel::of_device_table!( + OF_TABLE, + MODULE_OF_TABLE, + (), + [(of::DeviceId::new(c_str!("apple,sep")), ())] +); + +impl platform::Driver for SepDriver { + type IdInfo = (); + + const OF_ID_TABLE: Option> = Some(&OF_TABLE); + + fn probe( + pdev: &platform::Device, + _info: Option<&()>, + ) -> Result>> { + let of = pdev.as_ref().of_node().ok_or(EIO)?; + let res = of.reserved_mem_region_to_resource_byname(c_str!("sepfw"))?; + let data = SepData::new( + pdev, + FwRegionParams { + addr: res.start(), + size: res.size().try_into()?, + }, + )?; + *data.mbox.lock() = Some(Mailbox::new_byname( + pdev.as_ref(), + c_str!("mbox"), + data.clone(), + )?); + data.start()?; + Ok(KBox::pin(SepDriver(data), GFP_KERNEL)?) + } +} + +impl Drop for SepDriver { + fn drop(&mut self) { + self.0.remove(); + } +} + +module_platform_driver! { + type: SepDriver, + name: "apple_sep", + description: "Secure enclave processor stub driver", + license: "Dual MIT/GPL", +} diff --git a/drivers/soc/apple/tunable.c b/drivers/soc/apple/tunable.c new file mode 100644 index 00000000000000..6593238391715b --- /dev/null +++ b/drivers/soc/apple/tunable.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Apple Silicon hardware tunable support + * + * Each tunable is a list with each entry containing a offset into the MMIO + * region, a mask of bits to be cleared and a set of bits to be set. These + * tunables are passed along by the previous boot stages and vary from device + * to device such that they cannot be hardcoded in the individual drivers. + * + * Copyright (C) The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include + +struct apple_tunable *devm_apple_tunable_parse(struct device *dev, + struct device_node *np, + const char *name, + struct resource *res) +{ + struct apple_tunable *tunable; + struct property *prop; + const __be32 *p; + size_t sz; + int i; + + if (resource_size(res) < 4) + return ERR_PTR(-EINVAL); + + prop = of_find_property(np, name, NULL); + if (!prop) + return ERR_PTR(-ENOENT); + + if (prop->length % (3 * sizeof(u32))) + return ERR_PTR(-EINVAL); + sz = prop->length / (3 * sizeof(u32)); + + tunable = devm_kzalloc(dev, struct_size(tunable, values, sz), GFP_KERNEL); + if (!tunable) + return ERR_PTR(-ENOMEM); + tunable->sz = sz; + + for (i = 0, p = NULL; i < tunable->sz; ++i) { + p = of_prop_next_u32(prop, p, &tunable->values[i].offset); + p = of_prop_next_u32(prop, p, &tunable->values[i].mask); + p = of_prop_next_u32(prop, p, &tunable->values[i].value); + + /* Sanity checks to catch bugs in our bootloader */ + if (tunable->values[i].offset % 4) + return ERR_PTR(-EINVAL); + if (tunable->values[i].offset > (resource_size(res) - 4)) + return ERR_PTR(-EINVAL); + } + + return tunable; +} +EXPORT_SYMBOL(devm_apple_tunable_parse); + +void apple_tunable_apply(void __iomem *regs, struct apple_tunable *tunable) +{ + size_t i; + + for (i = 0; i < tunable->sz; ++i) { + u32 val, old_val; + + old_val = readl(regs + tunable->values[i].offset); + val = old_val & ~tunable->values[i].mask; + val |= tunable->values[i].value; + if (val != old_val) + writel(val, regs + tunable->values[i].offset); + } +} +EXPORT_SYMBOL(apple_tunable_apply); + +MODULE_LICENSE("Dual MIT/GPL"); +MODULE_AUTHOR("Sven Peter "); +MODULE_DESCRIPTION("Apple Silicon hardware tunable support"); diff --git a/drivers/soc/mediatek/mtk-svs.c b/drivers/soc/mediatek/mtk-svs.c index f45537546553ec..99edecb204f254 100644 --- a/drivers/soc/mediatek/mtk-svs.c +++ b/drivers/soc/mediatek/mtk-svs.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -789,7 +790,7 @@ static ssize_t svs_enable_debug_write(struct file *filp, struct svs_bank *svsb = file_inode(filp)->i_private; struct svs_platform *svsp = dev_get_drvdata(svsb->dev); int enabled, ret; - char *buf = NULL; + char *buf __free(kfree) = NULL; if (count >= PAGE_SIZE) return -EINVAL; @@ -807,8 +808,6 @@ static ssize_t svs_enable_debug_write(struct file *filp, svsb->mode_support = SVSB_MODE_ALL_DISABLE; } - kfree(buf); - return count; } diff --git a/drivers/soc/qcom/cmd-db.c b/drivers/soc/qcom/cmd-db.c index ae66c2623d250d..84a75d8c4b7020 100644 --- a/drivers/soc/qcom/cmd-db.c +++ b/drivers/soc/qcom/cmd-db.c @@ -349,15 +349,16 @@ static int cmd_db_dev_probe(struct platform_device *pdev) return -EINVAL; } - cmd_db_header = memremap(rmem->base, rmem->size, MEMREMAP_WC); - if (!cmd_db_header) { - ret = -ENOMEM; + cmd_db_header = devm_memremap(&pdev->dev, rmem->base, rmem->size, MEMREMAP_WC); + if (IS_ERR(cmd_db_header)) { + ret = PTR_ERR(cmd_db_header); cmd_db_header = NULL; return ret; } if (!cmd_db_magic_matches(cmd_db_header)) { dev_err(&pdev->dev, "Invalid Command DB Magic\n"); + cmd_db_header = NULL; return -EINVAL; } diff --git a/drivers/soc/qcom/ocmem.c b/drivers/soc/qcom/ocmem.c index 9c3bd37b6579d3..71130a2f62e9e6 100644 --- a/drivers/soc/qcom/ocmem.c +++ b/drivers/soc/qcom/ocmem.c @@ -202,9 +202,9 @@ struct ocmem *of_get_ocmem(struct device *dev) } ocmem = platform_get_drvdata(pdev); + put_device(&pdev->dev); if (!ocmem) { dev_err(dev, "Cannot get ocmem\n"); - put_device(&pdev->dev); return ERR_PTR(-ENODEV); } return ocmem; diff --git a/drivers/soc/qcom/qcom-pbs.c b/drivers/soc/qcom/qcom-pbs.c index 1cc5d045f9ddfe..06b4a596e27578 100644 --- a/drivers/soc/qcom/qcom-pbs.c +++ b/drivers/soc/qcom/qcom-pbs.c @@ -173,6 +173,8 @@ struct pbs_dev *get_pbs_client_device(struct device *dev) return ERR_PTR(-EINVAL); } + platform_device_put(pdev); + return pbs; } EXPORT_SYMBOL_GPL(get_pbs_client_device); diff --git a/drivers/soc/qcom/qcom_gsbi.c b/drivers/soc/qcom/qcom_gsbi.c index 8f1158e0c6313a..a25d1de592f060 100644 --- a/drivers/soc/qcom/qcom_gsbi.c +++ b/drivers/soc/qcom/qcom_gsbi.c @@ -212,13 +212,6 @@ static int gsbi_probe(struct platform_device *pdev) return of_platform_populate(node, NULL, NULL, &pdev->dev); } -static void gsbi_remove(struct platform_device *pdev) -{ - struct gsbi_info *gsbi = platform_get_drvdata(pdev); - - clk_disable_unprepare(gsbi->hclk); -} - static const struct of_device_id gsbi_dt_match[] = { { .compatible = "qcom,gsbi-v1.0.0", }, { }, @@ -232,7 +225,6 @@ static struct platform_driver gsbi_driver = { .of_match_table = gsbi_dt_match, }, .probe = gsbi_probe, - .remove = gsbi_remove, }; module_platform_driver(gsbi_driver); diff --git a/drivers/soc/qcom/smem.c b/drivers/soc/qcom/smem.c index c4c45f15dca4fb..39177aa5793adb 100644 --- a/drivers/soc/qcom/smem.c +++ b/drivers/soc/qcom/smem.c @@ -1190,7 +1190,7 @@ static int qcom_smem_probe(struct platform_device *pdev) return dev_err_probe(&pdev->dev, hwlock_id, "failed to retrieve hwlock\n"); - smem->hwlock = hwspin_lock_request_specific(hwlock_id); + smem->hwlock = devm_hwspin_lock_request_specific(&pdev->dev, hwlock_id); if (!smem->hwlock) return -ENXIO; @@ -1215,7 +1215,9 @@ static int qcom_smem_probe(struct platform_device *pdev) smem->item_count = qcom_smem_get_item_count(smem); break; case SMEM_GLOBAL_HEAP_VERSION: - qcom_smem_map_global(smem, size); + ret = qcom_smem_map_global(smem, size); + if (ret < 0) + return ret; smem->item_count = SMEM_ITEM_COUNT; break; default: @@ -1243,7 +1245,6 @@ static void qcom_smem_remove(struct platform_device *pdev) { platform_device_unregister(__smem->socinfo); - hwspin_lock_free(__smem->hwlock); __smem = NULL; } diff --git a/drivers/soc/renesas/r9a08g045-sysc.c b/drivers/soc/renesas/r9a08g045-sysc.c index 0504d4e6876169..03d653d5cde554 100644 --- a/drivers/soc/renesas/r9a08g045-sysc.c +++ b/drivers/soc/renesas/r9a08g045-sysc.c @@ -6,10 +6,29 @@ */ #include +#include #include #include "rz-sysc.h" +#define SYS_XSPI_MAP_STAADD_CS0 0x348 +#define SYS_XSPI_MAP_ENDADD_CS0 0x34c +#define SYS_XSPI_MAP_STAADD_CS1 0x350 +#define SYS_XSPI_MAP_ENDADD_CS1 0x354 +#define SYS_GETH0_CFG 0x380 +#define SYS_GETH1_CFG 0x390 +#define SYS_PCIE_CFG 0x3a0 +#define SYS_PCIE_MON 0x3a4 +#define SYS_PCIE_ERR_MON 0x3ac +#define SYS_PCIE_PHY 0x3b4 +#define SYS_I2C0_CFG 0x400 +#define SYS_I2C1_CFG 0x410 +#define SYS_I2C2_CFG 0x420 +#define SYS_I2C3_CFG 0x430 +#define SYS_I3C_CFG 0x440 +#define SYS_USB_PWRRDY 0xd70 +#define SYS_PCIE_RST_RSM_B 0xd74 + static const struct rz_sysc_soc_id_init_data rzg3s_sysc_soc_id_init_data __initconst = { .family = "RZ/G3S", .id = 0x85e0447, @@ -18,7 +37,57 @@ static const struct rz_sysc_soc_id_init_data rzg3s_sysc_soc_id_init_data __initc .specific_id_mask = GENMASK(27, 0), }; +static bool rzg3s_regmap_readable_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case SYS_XSPI_MAP_STAADD_CS0: + case SYS_XSPI_MAP_ENDADD_CS0: + case SYS_XSPI_MAP_STAADD_CS1: + case SYS_XSPI_MAP_ENDADD_CS1: + case SYS_GETH0_CFG: + case SYS_GETH1_CFG: + case SYS_PCIE_CFG: + case SYS_PCIE_MON: + case SYS_PCIE_ERR_MON: + case SYS_PCIE_PHY: + case SYS_I2C0_CFG: + case SYS_I2C1_CFG: + case SYS_I2C2_CFG: + case SYS_I2C3_CFG: + case SYS_I3C_CFG: + case SYS_USB_PWRRDY: + case SYS_PCIE_RST_RSM_B: + return true; + default: + return false; + } +} + +static bool rzg3s_regmap_writeable_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case SYS_XSPI_MAP_STAADD_CS0: + case SYS_XSPI_MAP_ENDADD_CS0: + case SYS_XSPI_MAP_STAADD_CS1: + case SYS_XSPI_MAP_ENDADD_CS1: + case SYS_PCIE_CFG: + case SYS_PCIE_PHY: + case SYS_I2C0_CFG: + case SYS_I2C1_CFG: + case SYS_I2C2_CFG: + case SYS_I2C3_CFG: + case SYS_I3C_CFG: + case SYS_USB_PWRRDY: + case SYS_PCIE_RST_RSM_B: + return true; + default: + return false; + } +} + const struct rz_sysc_init_data rzg3s_sysc_init_data __initconst = { .soc_id_init_data = &rzg3s_sysc_soc_id_init_data, + .readable_reg = rzg3s_regmap_readable_reg, + .writeable_reg = rzg3s_regmap_writeable_reg, .max_register = 0xe20, }; diff --git a/drivers/soc/renesas/r9a09g047-sys.c b/drivers/soc/renesas/r9a09g047-sys.c index 2e8426c0305049..e413b0eff9bfd4 100644 --- a/drivers/soc/renesas/r9a09g047-sys.c +++ b/drivers/soc/renesas/r9a09g047-sys.c @@ -29,6 +29,27 @@ #define SYS_LSI_PRR_CA55_DIS BIT(8) #define SYS_LSI_PRR_NPU_DIS BIT(1) +#define SYS_LSI_OTPTSU1TRMVAL0 0x330 +#define SYS_LSI_OTPTSU1TRMVAL1 0x334 +#define SYS_SPI_STAADDCS0 0x900 +#define SYS_SPI_ENDADDCS0 0x904 +#define SYS_SPI_STAADDCS1 0x908 +#define SYS_SPI_ENDADDCS1 0x90c +#define SYS_VSP_CLK 0xe00 +#define SYS_GBETH0_CFG 0xf00 +#define SYS_GBETH1_CFG 0xf04 +#define SYS_PCIE_INTX_CH0 0x1000 +#define SYS_PCIE_MSI1_CH0 0x1004 +#define SYS_PCIE_MSI2_CH0 0x1008 +#define SYS_PCIE_MSI3_CH0 0x100c +#define SYS_PCIE_MSI4_CH0 0x1010 +#define SYS_PCIE_MSI5_CH0 0x1014 +#define SYS_PCIE_PME_CH0 0x1018 +#define SYS_PCIE_ACK_CH0 0x101c +#define SYS_PCIE_MISC_CH0 0x1020 +#define SYS_PCIE_MODE_CH0 0x1024 +#define SYS_ADC_CFG 0x1600 + static void rzg3e_sys_print_id(struct device *dev, void __iomem *sysc_base, struct soc_device_attribute *soc_dev_attr) @@ -62,7 +83,65 @@ static const struct rz_sysc_soc_id_init_data rzg3e_sys_soc_id_init_data __initco .print_id = rzg3e_sys_print_id, }; +static bool rzg3e_regmap_readable_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case SYS_LSI_OTPTSU1TRMVAL0: + case SYS_LSI_OTPTSU1TRMVAL1: + case SYS_SPI_STAADDCS0: + case SYS_SPI_ENDADDCS0: + case SYS_SPI_STAADDCS1: + case SYS_SPI_ENDADDCS1: + case SYS_VSP_CLK: + case SYS_GBETH0_CFG: + case SYS_GBETH1_CFG: + case SYS_PCIE_INTX_CH0: + case SYS_PCIE_MSI1_CH0: + case SYS_PCIE_MSI2_CH0: + case SYS_PCIE_MSI3_CH0: + case SYS_PCIE_MSI4_CH0: + case SYS_PCIE_MSI5_CH0: + case SYS_PCIE_PME_CH0: + case SYS_PCIE_ACK_CH0: + case SYS_PCIE_MISC_CH0: + case SYS_PCIE_MODE_CH0: + case SYS_ADC_CFG: + return true; + default: + return false; + } +} + +static bool rzg3e_regmap_writeable_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case SYS_SPI_STAADDCS0: + case SYS_SPI_ENDADDCS0: + case SYS_SPI_STAADDCS1: + case SYS_SPI_ENDADDCS1: + case SYS_VSP_CLK: + case SYS_GBETH0_CFG: + case SYS_GBETH1_CFG: + case SYS_PCIE_INTX_CH0: + case SYS_PCIE_MSI1_CH0: + case SYS_PCIE_MSI2_CH0: + case SYS_PCIE_MSI3_CH0: + case SYS_PCIE_MSI4_CH0: + case SYS_PCIE_MSI5_CH0: + case SYS_PCIE_PME_CH0: + case SYS_PCIE_ACK_CH0: + case SYS_PCIE_MISC_CH0: + case SYS_PCIE_MODE_CH0: + case SYS_ADC_CFG: + return true; + default: + return false; + } +} + const struct rz_sysc_init_data rzg3e_sys_init_data = { .soc_id_init_data = &rzg3e_sys_soc_id_init_data, + .readable_reg = rzg3e_regmap_readable_reg, + .writeable_reg = rzg3e_regmap_writeable_reg, .max_register = 0x170c, }; diff --git a/drivers/soc/renesas/r9a09g056-sys.c b/drivers/soc/renesas/r9a09g056-sys.c index 3ad1422eba36e6..42f5eff291fd1f 100644 --- a/drivers/soc/renesas/r9a09g056-sys.c +++ b/drivers/soc/renesas/r9a09g056-sys.c @@ -34,6 +34,24 @@ #define SYS_RZV2N_FEATURE_C55 BIT(1) #define SYS_RZV2N_FEATURE_SEC BIT(2) +#define SYS_LSI_OTPTSU0TRMVAL0 0x320 +#define SYS_LSI_OTPTSU0TRMVAL1 0x324 +#define SYS_LSI_OTPTSU1TRMVAL0 0x330 +#define SYS_LSI_OTPTSU1TRMVAL1 0x334 +#define SYS_GBETH0_CFG 0xf00 +#define SYS_GBETH1_CFG 0xf04 +#define SYS_PCIE_INTX_CH0 0x1000 +#define SYS_PCIE_MSI1_CH0 0x1004 +#define SYS_PCIE_MSI2_CH0 0x1008 +#define SYS_PCIE_MSI3_CH0 0x100c +#define SYS_PCIE_MSI4_CH0 0x1010 +#define SYS_PCIE_MSI5_CH0 0x1014 +#define SYS_PCIE_PME_CH0 0x1018 +#define SYS_PCIE_ACK_CH0 0x101c +#define SYS_PCIE_MISC_CH0 0x1020 +#define SYS_PCIE_MODE_CH0 0x1024 +#define SYS_ADC_CFG 0x1600 + static void rzv2n_sys_print_id(struct device *dev, void __iomem *sysc_base, struct soc_device_attribute *soc_dev_attr) @@ -70,6 +88,57 @@ static const struct rz_sysc_soc_id_init_data rzv2n_sys_soc_id_init_data __initco .print_id = rzv2n_sys_print_id, }; +static bool rzv2n_regmap_readable_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case SYS_LSI_OTPTSU0TRMVAL0: + case SYS_LSI_OTPTSU0TRMVAL1: + case SYS_LSI_OTPTSU1TRMVAL0: + case SYS_LSI_OTPTSU1TRMVAL1: + case SYS_GBETH0_CFG: + case SYS_GBETH1_CFG: + case SYS_PCIE_INTX_CH0: + case SYS_PCIE_MSI1_CH0: + case SYS_PCIE_MSI2_CH0: + case SYS_PCIE_MSI3_CH0: + case SYS_PCIE_MSI4_CH0: + case SYS_PCIE_MSI5_CH0: + case SYS_PCIE_PME_CH0: + case SYS_PCIE_ACK_CH0: + case SYS_PCIE_MISC_CH0: + case SYS_PCIE_MODE_CH0: + case SYS_ADC_CFG: + return true; + default: + return false; + } +} + +static bool rzv2n_regmap_writeable_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case SYS_GBETH0_CFG: + case SYS_GBETH1_CFG: + case SYS_PCIE_INTX_CH0: + case SYS_PCIE_MSI1_CH0: + case SYS_PCIE_MSI2_CH0: + case SYS_PCIE_MSI3_CH0: + case SYS_PCIE_MSI4_CH0: + case SYS_PCIE_MSI5_CH0: + case SYS_PCIE_PME_CH0: + case SYS_PCIE_ACK_CH0: + case SYS_PCIE_MISC_CH0: + case SYS_PCIE_MODE_CH0: + case SYS_ADC_CFG: + return true; + default: + return false; + } +} + const struct rz_sysc_init_data rzv2n_sys_init_data = { .soc_id_init_data = &rzv2n_sys_soc_id_init_data, + .readable_reg = rzv2n_regmap_readable_reg, + .writeable_reg = rzv2n_regmap_writeable_reg, + .max_register = 0x170c, }; diff --git a/drivers/soc/renesas/r9a09g057-sys.c b/drivers/soc/renesas/r9a09g057-sys.c index e3390e7c7fe516..827c718ac7c545 100644 --- a/drivers/soc/renesas/r9a09g057-sys.c +++ b/drivers/soc/renesas/r9a09g057-sys.c @@ -29,6 +29,35 @@ #define SYS_LSI_PRR_GPU_DIS BIT(0) #define SYS_LSI_PRR_ISP_DIS BIT(4) +#define SYS_LSI_OTPTSU0TRMVAL0 0x320 +#define SYS_LSI_OTPTSU0TRMVAL1 0x324 +#define SYS_LSI_OTPTSU1TRMVAL0 0x330 +#define SYS_LSI_OTPTSU1TRMVAL1 0x334 +#define SYS_GBETH0_CFG 0xf00 +#define SYS_GBETH1_CFG 0xf04 +#define SYS_PCIE_INTX_CH0 0x1000 +#define SYS_PCIE_MSI1_CH0 0x1004 +#define SYS_PCIE_MSI2_CH0 0x1008 +#define SYS_PCIE_MSI3_CH0 0x100c +#define SYS_PCIE_MSI4_CH0 0x1010 +#define SYS_PCIE_MSI5_CH0 0x1014 +#define SYS_PCIE_PME_CH0 0x1018 +#define SYS_PCIE_ACK_CH0 0x101c +#define SYS_PCIE_MISC_CH0 0x1020 +#define SYS_PCIE_MODE_CH0 0x1024 +#define SYS_PCIE_INTX_CH1 0x1030 +#define SYS_PCIE_MSI1_CH1 0x1034 +#define SYS_PCIE_MSI2_CH1 0x1038 +#define SYS_PCIE_MSI3_CH1 0x103c +#define SYS_PCIE_MSI4_CH1 0x1040 +#define SYS_PCIE_MSI5_CH1 0x1044 +#define SYS_PCIE_PME_CH1 0x1048 +#define SYS_PCIE_ACK_CH1 0x104c +#define SYS_PCIE_MISC_CH1 0x1050 +#define SYS_PCIE_MODE_CH1 0x1054 +#define SYS_PCIE_MODE 0x1060 +#define SYS_ADC_CFG 0x1600 + static void rzv2h_sys_print_id(struct device *dev, void __iomem *sysc_base, struct soc_device_attribute *soc_dev_attr) @@ -62,7 +91,79 @@ static const struct rz_sysc_soc_id_init_data rzv2h_sys_soc_id_init_data __initco .print_id = rzv2h_sys_print_id, }; +static bool rzv2h_regmap_readable_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case SYS_LSI_OTPTSU0TRMVAL0: + case SYS_LSI_OTPTSU0TRMVAL1: + case SYS_LSI_OTPTSU1TRMVAL0: + case SYS_LSI_OTPTSU1TRMVAL1: + case SYS_GBETH0_CFG: + case SYS_GBETH1_CFG: + case SYS_PCIE_INTX_CH0: + case SYS_PCIE_MSI1_CH0: + case SYS_PCIE_MSI2_CH0: + case SYS_PCIE_MSI3_CH0: + case SYS_PCIE_MSI4_CH0: + case SYS_PCIE_MSI5_CH0: + case SYS_PCIE_PME_CH0: + case SYS_PCIE_ACK_CH0: + case SYS_PCIE_MISC_CH0: + case SYS_PCIE_MODE_CH0: + case SYS_PCIE_INTX_CH1: + case SYS_PCIE_MSI1_CH1: + case SYS_PCIE_MSI2_CH1: + case SYS_PCIE_MSI3_CH1: + case SYS_PCIE_MSI4_CH1: + case SYS_PCIE_MSI5_CH1: + case SYS_PCIE_PME_CH1: + case SYS_PCIE_ACK_CH1: + case SYS_PCIE_MISC_CH1: + case SYS_PCIE_MODE_CH1: + case SYS_PCIE_MODE: + case SYS_ADC_CFG: + return true; + default: + return false; + } +} + +static bool rzv2h_regmap_writeable_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case SYS_GBETH0_CFG: + case SYS_GBETH1_CFG: + case SYS_PCIE_INTX_CH0: + case SYS_PCIE_MSI1_CH0: + case SYS_PCIE_MSI2_CH0: + case SYS_PCIE_MSI3_CH0: + case SYS_PCIE_MSI4_CH0: + case SYS_PCIE_MSI5_CH0: + case SYS_PCIE_PME_CH0: + case SYS_PCIE_ACK_CH0: + case SYS_PCIE_MISC_CH0: + case SYS_PCIE_MODE_CH0: + case SYS_PCIE_INTX_CH1: + case SYS_PCIE_MSI1_CH1: + case SYS_PCIE_MSI2_CH1: + case SYS_PCIE_MSI3_CH1: + case SYS_PCIE_MSI4_CH1: + case SYS_PCIE_MSI5_CH1: + case SYS_PCIE_PME_CH1: + case SYS_PCIE_ACK_CH1: + case SYS_PCIE_MISC_CH1: + case SYS_PCIE_MODE_CH1: + case SYS_PCIE_MODE: + case SYS_ADC_CFG: + return true; + default: + return false; + } +} + const struct rz_sysc_init_data rzv2h_sys_init_data = { .soc_id_init_data = &rzv2h_sys_soc_id_init_data, + .readable_reg = rzv2h_regmap_readable_reg, + .writeable_reg = rzv2h_regmap_writeable_reg, .max_register = 0x170c, }; diff --git a/drivers/soc/renesas/rz-sysc.c b/drivers/soc/renesas/rz-sysc.c index 9f79e299e6f416..19c1e666279b75 100644 --- a/drivers/soc/renesas/rz-sysc.c +++ b/drivers/soc/renesas/rz-sysc.c @@ -140,6 +140,8 @@ static int rz_sysc_probe(struct platform_device *pdev) regmap_cfg->val_bits = 32; regmap_cfg->fast_io = true; regmap_cfg->max_register = data->max_register; + regmap_cfg->readable_reg = data->readable_reg; + regmap_cfg->writeable_reg = data->writeable_reg; regmap = devm_regmap_init_mmio(dev, sysc->base, regmap_cfg); if (IS_ERR(regmap)) diff --git a/drivers/soc/renesas/rz-sysc.h b/drivers/soc/renesas/rz-sysc.h index 8eec355d5d5620..88929bf21cb114 100644 --- a/drivers/soc/renesas/rz-sysc.h +++ b/drivers/soc/renesas/rz-sysc.h @@ -34,10 +34,14 @@ struct rz_sysc_soc_id_init_data { /** * struct rz_sysc_init_data - RZ SYSC initialization data * @soc_id_init_data: RZ SYSC SoC ID initialization data + * @writeable_reg: Regmap writeable register check function + * @readable_reg: Regmap readable register check function * @max_register: Maximum SYSC register offset to be used by the regmap config */ struct rz_sysc_init_data { const struct rz_sysc_soc_id_init_data *soc_id_init_data; + bool (*writeable_reg)(struct device *dev, unsigned int reg); + bool (*readable_reg)(struct device *dev, unsigned int reg); u32 max_register; }; diff --git a/drivers/soc/samsung/exynos-pmu.c b/drivers/soc/samsung/exynos-pmu.c index 22c50ca2aa79bf..f8fe1a5965ab47 100644 --- a/drivers/soc/samsung/exynos-pmu.c +++ b/drivers/soc/samsung/exynos-pmu.c @@ -346,6 +346,8 @@ struct regmap *exynos_get_pmu_regmap_by_phandle(struct device_node *np, if (!dev) return ERR_PTR(-EPROBE_DEFER); + put_device(dev); + return syscon_node_to_regmap(pmu_np); } EXPORT_SYMBOL_GPL(exynos_get_pmu_regmap_by_phandle); @@ -585,10 +587,6 @@ static int setup_cpuhp_and_cpuidle(struct device *dev) if (!pmu_context->in_cpuhp) return -ENOMEM; - raw_spin_lock_init(&pmu_context->cpupm_lock); - pmu_context->sys_inreboot = false; - pmu_context->sys_insuspend = false; - /* set PMU to power on */ for_each_online_cpu(cpu) gs101_cpuhp_pmu_online(cpu); @@ -657,6 +655,9 @@ static int exynos_pmu_probe(struct platform_device *pdev) pmu_context->pmureg = regmap; pmu_context->dev = dev; + raw_spin_lock_init(&pmu_context->cpupm_lock); + pmu_context->sys_inreboot = false; + pmu_context->sys_insuspend = false; if (pmu_context->pmu_data && pmu_context->pmu_data->pmu_cpuhp) { ret = setup_cpuhp_and_cpuidle(dev); diff --git a/drivers/soc/tegra/fuse/fuse-tegra.c b/drivers/soc/tegra/fuse/fuse-tegra.c index d276672838465c..74d2fedea71ca6 100644 --- a/drivers/soc/tegra/fuse/fuse-tegra.c +++ b/drivers/soc/tegra/fuse/fuse-tegra.c @@ -182,8 +182,6 @@ static int tegra_fuse_probe(struct platform_device *pdev) } fuse->soc->init(fuse); - tegra_fuse_print_sku_info(&tegra_sku_info); - tegra_soc_device_register(); err = tegra_fuse_add_lookups(fuse); if (err) diff --git a/drivers/soc/tegra/fuse/speedo-tegra210.c b/drivers/soc/tegra/fuse/speedo-tegra210.c index 695d0b7f9a8abe..a8cc3632977230 100644 --- a/drivers/soc/tegra/fuse/speedo-tegra210.c +++ b/drivers/soc/tegra/fuse/speedo-tegra210.c @@ -65,27 +65,51 @@ static void __init rev_sku_to_speedo_ids(struct tegra_sku_info *sku_info, sku_info->gpu_speedo_id = 0; *threshold = THRESHOLD_INDEX_0; - switch (sku) { - case 0x00: /* Engineering SKU */ - case 0x01: /* Engineering SKU */ - case 0x07: - case 0x17: - case 0x27: - if (speedo_rev >= 2) + if (sku_info->revision >= TEGRA_REVISION_A02) { + switch (sku) { + case 0x00: /* Engineering SKU */ + case 0x01: /* Engineering SKU */ + case 0x13: + sku_info->cpu_speedo_id = 5; + sku_info->gpu_speedo_id = 2; + break; + + case 0x07: + case 0x17: + case 0x1F: + sku_info->cpu_speedo_id = 7; + sku_info->gpu_speedo_id = 2; + break; + + case 0x27: + sku_info->cpu_speedo_id = 1; + sku_info->gpu_speedo_id = 2; + break; + + case 0x83: + sku_info->cpu_speedo_id = 3; + sku_info->gpu_speedo_id = 3; + break; + + case 0x87: + sku_info->cpu_speedo_id = 2; sku_info->gpu_speedo_id = 1; - break; - - case 0x13: - if (speedo_rev >= 2) - sku_info->gpu_speedo_id = 1; - - sku_info->cpu_speedo_id = 1; - break; - - default: + break; + + case 0x8F: + sku_info->cpu_speedo_id = 9; + sku_info->gpu_speedo_id = 2; + break; + + default: + pr_err("Tegra210: unknown revision 2 or newer SKU %#04x\n", sku); + /* Using the default for the error case */ + break; + } + } else if (sku == 0x00 || sku == 0x01 || sku == 0x07 || sku == 0x13 || sku == 0x17) { + sku_info->gpu_speedo_id = 1; + } else { pr_err("Tegra210: unknown SKU %#04x\n", sku); - /* Using the default for the error case */ - break; } } diff --git a/drivers/soundwire/Kconfig b/drivers/soundwire/Kconfig index ad56393e4c93b8..196a7daaabdb88 100644 --- a/drivers/soundwire/Kconfig +++ b/drivers/soundwire/Kconfig @@ -40,6 +40,7 @@ config SOUNDWIRE_INTEL select AUXILIARY_BUS depends on ACPI && SND_SOC depends on SND_SOC_SOF_HDA_MLINK || !SND_SOC_SOF_HDA_MLINK + depends on SND_HDA_CORE || !SND_HDA_ALIGNED_MMIO help SoundWire Intel Master driver. If you have an Intel platform which has a SoundWire Master then diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c index 91e70cb46fb575..5c67c13e57357d 100644 --- a/drivers/soundwire/bus_type.c +++ b/drivers/soundwire/bus_type.c @@ -105,7 +105,7 @@ static int sdw_drv_probe(struct device *dev) if (ret) return ret; - ret = ida_alloc_max(&slave->bus->slave_ida, SDW_FW_MAX_DEVICES, GFP_KERNEL); + ret = ida_alloc_max(&slave->bus->slave_ida, SDW_FW_MAX_DEVICES - 1, GFP_KERNEL); if (ret < 0) { dev_err(dev, "Failed to allocated ID: %d\n", ret); return ret; diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index 55675750182e3d..1872f9d54a5cc9 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -706,15 +706,6 @@ config SPI_MESON_SPIFC This enables master mode support for the SPIFC (SPI flash controller) available in Amlogic Meson SoCs. -config SPI_MICROCHIP_CORE - tristate "Microchip FPGA SPI controllers" - depends on SPI_MASTER - help - This enables the SPI driver for Microchip FPGA SPI controllers. - Say Y or M here if you want to use the "hard" controllers on - PolarFire SoC. - If built as a module, it will be called spi-microchip-core. - config SPI_MICROCHIP_CORE_QSPI tristate "Microchip FPGA QSPI controllers" depends on SPI_MASTER @@ -871,6 +862,16 @@ config SPI_PL022 controller. If you have an embedded system with an AMBA(R) bus and a PL022 controller, say Y or M here. +config SPI_POLARFIRE_SOC + + tristate "Microchip FPGA SPI controllers" + depends on SPI_MASTER && ARCH_MICROCHIP + help + This enables the SPI driver for Microchip FPGA SPI controllers. + Say Y or M here if you want to use the "hard" controllers on + PolarFire SoC. + If built as a module, it will be called spi-mpfs. + config SPI_PPC4xx tristate "PPC4xx SPI Controller" depends on PPC32 && 4xx diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile index 8ff74a13faaa88..1f7c06a3091d92 100644 --- a/drivers/spi/Makefile +++ b/drivers/spi/Makefile @@ -86,7 +86,6 @@ obj-$(CONFIG_SPI_LOONGSON_PLATFORM) += spi-loongson-plat.o obj-$(CONFIG_SPI_LP8841_RTC) += spi-lp8841-rtc.o obj-$(CONFIG_SPI_MESON_SPICC) += spi-meson-spicc.o obj-$(CONFIG_SPI_MESON_SPIFC) += spi-meson-spifc.o -obj-$(CONFIG_SPI_MICROCHIP_CORE) += spi-microchip-core.o obj-$(CONFIG_SPI_MICROCHIP_CORE_QSPI) += spi-microchip-core-qspi.o obj-$(CONFIG_SPI_MPC512x_PSC) += spi-mpc512x-psc.o obj-$(CONFIG_SPI_MPC52xx_PSC) += spi-mpc52xx-psc.o @@ -97,6 +96,7 @@ obj-$(CONFIG_SPI_MTK_NOR) += spi-mtk-nor.o obj-$(CONFIG_SPI_MTK_SNFI) += spi-mtk-snfi.o obj-$(CONFIG_SPI_MXIC) += spi-mxic.o obj-$(CONFIG_SPI_MXS) += spi-mxs.o +obj-$(CONFIG_SPI_POLARFIRE_SOC) += spi-mpfs.o obj-$(CONFIG_SPI_WPCM_FIU) += spi-wpcm-fiu.o obj-$(CONFIG_SPI_NPCM_FIU) += spi-npcm-fiu.o obj-$(CONFIG_SPI_NPCM_PSPI) += spi-npcm-pspi.o diff --git a/drivers/spi/spi-airoha-snfi.c b/drivers/spi/spi-airoha-snfi.c index b78163eaed61d4..20b5d469d519a0 100644 --- a/drivers/spi/spi-airoha-snfi.c +++ b/drivers/spi/spi-airoha-snfi.c @@ -1030,6 +1030,11 @@ static const struct spi_controller_mem_ops airoha_snand_mem_ops = { .dirmap_write = airoha_snand_dirmap_write, }; +static const struct spi_controller_mem_ops airoha_snand_nodma_mem_ops = { + .supports_op = airoha_snand_supports_op, + .exec_op = airoha_snand_exec_op, +}; + static int airoha_snand_setup(struct spi_device *spi) { struct airoha_snand_ctrl *as_ctrl; @@ -1104,7 +1109,9 @@ static int airoha_snand_probe(struct platform_device *pdev) struct airoha_snand_ctrl *as_ctrl; struct device *dev = &pdev->dev; struct spi_controller *ctrl; + bool dma_enable = true; void __iomem *base; + u32 sfc_strap; int err; ctrl = devm_spi_alloc_host(dev, sizeof(*as_ctrl)); @@ -1139,12 +1146,28 @@ static int airoha_snand_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(as_ctrl->spi_clk), "unable to get spi clk\n"); + if (device_is_compatible(dev, "airoha,en7523-snand")) { + err = regmap_read(as_ctrl->regmap_ctrl, + REG_SPI_CTRL_SFC_STRAP, &sfc_strap); + if (err) + return err; + + if (!(sfc_strap & 0x04)) { + dma_enable = false; + dev_warn(dev, "Detected booting in RESERVED mode (UART_TXD was short to GND).\n"); + dev_warn(dev, "This mode is known for incorrect DMA reading of some flashes.\n"); + dev_warn(dev, "Much slower PIO mode will be used to prevent flash data damage.\n"); + dev_warn(dev, "Unplug UART cable and power cycle board to get full performance.\n"); + } + } + err = dma_set_mask(as_ctrl->dev, DMA_BIT_MASK(32)); if (err) return err; ctrl->num_chipselect = 2; - ctrl->mem_ops = &airoha_snand_mem_ops; + ctrl->mem_ops = dma_enable ? &airoha_snand_mem_ops + : &airoha_snand_nodma_mem_ops; ctrl->bits_per_word_mask = SPI_BPW_MASK(8); ctrl->mode_bits = SPI_RX_DUAL; ctrl->setup = airoha_snand_setup; diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index af6d050da1c8ac..1cca9d87fbde4c 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -769,6 +769,7 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata, readl(reg_base + CQSPI_REG_INDIRECTRD); /* Flush posted write. */ while (remaining > 0) { + ret = 0; if (use_irq && !wait_for_completion_timeout(&cqspi->transfer_complete, msecs_to_jiffies(CQSPI_READ_TIMEOUT_MS))) @@ -781,6 +782,14 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata, if (cqspi->slow_sram) writel(0x0, reg_base + CQSPI_REG_IRQMASK); + /* + * Prevent lost interrupt and race condition by reinitializing early. + * A spurious wakeup and another wait cycle can occur here, + * which is preferable to waiting until timeout if interrupt is lost. + */ + if (use_irq) + reinit_completion(&cqspi->transfer_complete); + bytes_to_read = cqspi_get_rd_sram_level(cqspi); if (ret && bytes_to_read == 0) { @@ -813,7 +822,6 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata, } if (use_irq && remaining > 0) { - reinit_completion(&cqspi->transfer_complete); if (cqspi->slow_sram) writel(CQSPI_REG_IRQ_WATERMARK, reg_base + CQSPI_REG_IRQMASK); } @@ -2024,7 +2032,9 @@ static int cqspi_probe(struct platform_device *pdev) probe_reset_failed: if (cqspi->is_jh7110) cqspi_jh7110_disable_clk(pdev, cqspi); - clk_disable_unprepare(cqspi->clk); + + if (pm_runtime_get_sync(&pdev->dev) >= 0) + clk_disable_unprepare(cqspi->clk); probe_clk_failed: return ret; } diff --git a/drivers/spi/spi-ch341.c b/drivers/spi/spi-ch341.c index 46bc208f2d0509..79d2f9ab4ef037 100644 --- a/drivers/spi/spi-ch341.c +++ b/drivers/spi/spi-ch341.c @@ -78,7 +78,7 @@ static int ch341_transfer_one(struct spi_controller *host, ch341->tx_buf[0] = CH341A_CMD_SPI_STREAM; - memcpy(ch341->tx_buf + 1, trans->tx_buf, len); + memcpy(ch341->tx_buf + 1, trans->tx_buf, len - 1); ret = usb_bulk_msg(ch341->udev, ch341->write_pipe, ch341->tx_buf, len, NULL, CH341_DEFAULT_TIMEOUT); diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c index 2f2082652a1a28..481a7b28aacd3d 100644 --- a/drivers/spi/spi-fsl-spi.c +++ b/drivers/spi/spi-fsl-spi.c @@ -335,7 +335,7 @@ static int fsl_spi_prepare_message(struct spi_controller *ctlr, if (t->bits_per_word == 16 || t->bits_per_word == 32) t->bits_per_word = 8; /* pretend its 8 bits */ if (t->bits_per_word == 8 && t->len >= 256 && - (mpc8xxx_spi->flags & SPI_CPM1)) + !(t->len & 1) && (mpc8xxx_spi->flags & SPI_CPM1)) t->bits_per_word = 16; } } diff --git a/drivers/spi/spi-hisi-kunpeng.c b/drivers/spi/spi-hisi-kunpeng.c index dadf558dd9c0c6..80a1a15de0bc33 100644 --- a/drivers/spi/spi-hisi-kunpeng.c +++ b/drivers/spi/spi-hisi-kunpeng.c @@ -161,10 +161,8 @@ static const struct debugfs_reg32 hisi_spi_regs[] = { static int hisi_spi_debugfs_init(struct hisi_spi *hs) { char name[32]; + struct spi_controller *host = dev_get_drvdata(hs->dev); - struct spi_controller *host; - - host = container_of(hs->dev, struct spi_controller, dev); snprintf(name, 32, "hisi_spi%d", host->bus_num); hs->debugfs = debugfs_create_dir(name, NULL); if (IS_ERR(hs->debugfs)) diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c index b8c572394aac20..bce3d149bea180 100644 --- a/drivers/spi/spi-intel-pci.c +++ b/drivers/spi/spi-intel-pci.c @@ -81,6 +81,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0x54a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x5794), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x5825), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0x6e24), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7723), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7a24), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7aa4), (unsigned long)&cnl_info }, diff --git a/drivers/spi/spi-microchip-core.c b/drivers/spi/spi-mpfs.c similarity index 68% rename from drivers/spi/spi-microchip-core.c rename to drivers/spi/spi-mpfs.c index 9128b86c536603..7e9e64d8e6c813 100644 --- a/drivers/spi/spi-microchip-core.c +++ b/drivers/spi/spi-mpfs.c @@ -99,7 +99,7 @@ #define REG_CTRL2 (0x48) #define REG_FRAMESUP (0x50) -struct mchp_corespi { +struct mpfs_spi { void __iomem *regs; struct clk *clk; const u8 *tx_buf; @@ -113,34 +113,34 @@ struct mchp_corespi { int n_bytes; }; -static inline u32 mchp_corespi_read(struct mchp_corespi *spi, unsigned int reg) +static inline u32 mpfs_spi_read(struct mpfs_spi *spi, unsigned int reg) { return readl(spi->regs + reg); } -static inline void mchp_corespi_write(struct mchp_corespi *spi, unsigned int reg, u32 val) +static inline void mpfs_spi_write(struct mpfs_spi *spi, unsigned int reg, u32 val) { writel(val, spi->regs + reg); } -static inline void mchp_corespi_disable(struct mchp_corespi *spi) +static inline void mpfs_spi_disable(struct mpfs_spi *spi) { - u32 control = mchp_corespi_read(spi, REG_CONTROL); + u32 control = mpfs_spi_read(spi, REG_CONTROL); control &= ~CONTROL_ENABLE; - mchp_corespi_write(spi, REG_CONTROL, control); + mpfs_spi_write(spi, REG_CONTROL, control); } -static inline void mchp_corespi_read_fifo(struct mchp_corespi *spi, int fifo_max) +static inline void mpfs_spi_read_fifo(struct mpfs_spi *spi, int fifo_max) { for (int i = 0; i < fifo_max; i++) { u32 data; - while (mchp_corespi_read(spi, REG_STATUS) & STATUS_RXFIFO_EMPTY) + while (mpfs_spi_read(spi, REG_STATUS) & STATUS_RXFIFO_EMPTY) ; - data = mchp_corespi_read(spi, REG_RX_DATA); + data = mpfs_spi_read(spi, REG_RX_DATA); spi->rx_len -= spi->n_bytes; @@ -158,34 +158,34 @@ static inline void mchp_corespi_read_fifo(struct mchp_corespi *spi, int fifo_max } } -static void mchp_corespi_enable_ints(struct mchp_corespi *spi) +static void mpfs_spi_enable_ints(struct mpfs_spi *spi) { - u32 control = mchp_corespi_read(spi, REG_CONTROL); + u32 control = mpfs_spi_read(spi, REG_CONTROL); control |= INT_ENABLE_MASK; - mchp_corespi_write(spi, REG_CONTROL, control); + mpfs_spi_write(spi, REG_CONTROL, control); } -static void mchp_corespi_disable_ints(struct mchp_corespi *spi) +static void mpfs_spi_disable_ints(struct mpfs_spi *spi) { - u32 control = mchp_corespi_read(spi, REG_CONTROL); + u32 control = mpfs_spi_read(spi, REG_CONTROL); control &= ~INT_ENABLE_MASK; - mchp_corespi_write(spi, REG_CONTROL, control); + mpfs_spi_write(spi, REG_CONTROL, control); } -static inline void mchp_corespi_set_xfer_size(struct mchp_corespi *spi, int len) +static inline void mpfs_spi_set_xfer_size(struct mpfs_spi *spi, int len) { u32 control; u32 lenpart; - u32 frames = mchp_corespi_read(spi, REG_FRAMESUP); + u32 frames = mpfs_spi_read(spi, REG_FRAMESUP); /* * Writing to FRAMECNT in REG_CONTROL will reset the frame count, taking * a shortcut requires an explicit clear. */ if (frames == len) { - mchp_corespi_write(spi, REG_COMMAND, COMMAND_CLRFRAMECNT); + mpfs_spi_write(spi, REG_COMMAND, COMMAND_CLRFRAMECNT); return; } @@ -208,20 +208,20 @@ static inline void mchp_corespi_set_xfer_size(struct mchp_corespi *spi, int len) * that matches the documentation. */ lenpart = len & 0xffff; - control = mchp_corespi_read(spi, REG_CONTROL); + control = mpfs_spi_read(spi, REG_CONTROL); control &= ~CONTROL_FRAMECNT_MASK; control |= lenpart << CONTROL_FRAMECNT_SHIFT; - mchp_corespi_write(spi, REG_CONTROL, control); - mchp_corespi_write(spi, REG_FRAMESUP, len); + mpfs_spi_write(spi, REG_CONTROL, control); + mpfs_spi_write(spi, REG_FRAMESUP, len); } -static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi, int fifo_max) +static inline void mpfs_spi_write_fifo(struct mpfs_spi *spi, int fifo_max) { int i = 0; - mchp_corespi_set_xfer_size(spi, fifo_max); + mpfs_spi_set_xfer_size(spi, fifo_max); - while ((i < fifo_max) && !(mchp_corespi_read(spi, REG_STATUS) & STATUS_TXFIFO_FULL)) { + while ((i < fifo_max) && !(mpfs_spi_read(spi, REG_STATUS) & STATUS_TXFIFO_FULL)) { u32 word; if (spi->n_bytes == 4) @@ -231,7 +231,7 @@ static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi, int fifo_ma else word = spi->tx_buf ? *spi->tx_buf : 0xaa; - mchp_corespi_write(spi, REG_TX_DATA, word); + mpfs_spi_write(spi, REG_TX_DATA, word); if (spi->tx_buf) spi->tx_buf += spi->n_bytes; i++; @@ -240,9 +240,9 @@ static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi, int fifo_ma spi->tx_len -= i * spi->n_bytes; } -static inline void mchp_corespi_set_framesize(struct mchp_corespi *spi, int bt) +static inline void mpfs_spi_set_framesize(struct mpfs_spi *spi, int bt) { - u32 frame_size = mchp_corespi_read(spi, REG_FRAME_SIZE); + u32 frame_size = mpfs_spi_read(spi, REG_FRAME_SIZE); u32 control; if ((frame_size & FRAME_SIZE_MASK) == bt) @@ -252,25 +252,25 @@ static inline void mchp_corespi_set_framesize(struct mchp_corespi *spi, int bt) * Disable the SPI controller. Writes to the frame size have * no effect when the controller is enabled. */ - control = mchp_corespi_read(spi, REG_CONTROL); + control = mpfs_spi_read(spi, REG_CONTROL); control &= ~CONTROL_ENABLE; - mchp_corespi_write(spi, REG_CONTROL, control); + mpfs_spi_write(spi, REG_CONTROL, control); - mchp_corespi_write(spi, REG_FRAME_SIZE, bt); + mpfs_spi_write(spi, REG_FRAME_SIZE, bt); control |= CONTROL_ENABLE; - mchp_corespi_write(spi, REG_CONTROL, control); + mpfs_spi_write(spi, REG_CONTROL, control); } -static void mchp_corespi_set_cs(struct spi_device *spi, bool disable) +static void mpfs_spi_set_cs(struct spi_device *spi, bool disable) { u32 reg; - struct mchp_corespi *corespi = spi_controller_get_devdata(spi->controller); + struct mpfs_spi *mspi = spi_controller_get_devdata(spi->controller); - reg = mchp_corespi_read(corespi, REG_SLAVE_SELECT); + reg = mpfs_spi_read(mspi, REG_SLAVE_SELECT); reg &= ~BIT(spi_get_chipselect(spi, 0)); reg |= !disable << spi_get_chipselect(spi, 0); - corespi->pending_slave_select = reg; + mspi->pending_slave_select = reg; /* * Only deassert chip select immediately. Writing to some registers @@ -281,12 +281,12 @@ static void mchp_corespi_set_cs(struct spi_device *spi, bool disable) * doesn't see any spurious clock transitions whilst CS is enabled. */ if (((spi->mode & SPI_CS_HIGH) == 0) == disable) - mchp_corespi_write(corespi, REG_SLAVE_SELECT, reg); + mpfs_spi_write(mspi, REG_SLAVE_SELECT, reg); } -static int mchp_corespi_setup(struct spi_device *spi) +static int mpfs_spi_setup(struct spi_device *spi) { - struct mchp_corespi *corespi = spi_controller_get_devdata(spi->controller); + struct mpfs_spi *mspi = spi_controller_get_devdata(spi->controller); u32 reg; if (spi_is_csgpiod(spi)) @@ -298,21 +298,21 @@ static int mchp_corespi_setup(struct spi_device *spi) * driving their select line low. */ if (spi->mode & SPI_CS_HIGH) { - reg = mchp_corespi_read(corespi, REG_SLAVE_SELECT); + reg = mpfs_spi_read(mspi, REG_SLAVE_SELECT); reg |= BIT(spi_get_chipselect(spi, 0)); - corespi->pending_slave_select = reg; - mchp_corespi_write(corespi, REG_SLAVE_SELECT, reg); + mspi->pending_slave_select = reg; + mpfs_spi_write(mspi, REG_SLAVE_SELECT, reg); } return 0; } -static void mchp_corespi_init(struct spi_controller *host, struct mchp_corespi *spi) +static void mpfs_spi_init(struct spi_controller *host, struct mpfs_spi *spi) { unsigned long clk_hz; - u32 control = mchp_corespi_read(spi, REG_CONTROL); + u32 control = mpfs_spi_read(spi, REG_CONTROL); control &= ~CONTROL_ENABLE; - mchp_corespi_write(spi, REG_CONTROL, control); + mpfs_spi_write(spi, REG_CONTROL, control); control |= CONTROL_MASTER; control &= ~CONTROL_MODE_MASK; @@ -328,15 +328,15 @@ static void mchp_corespi_init(struct spi_controller *host, struct mchp_corespi * */ control |= CONTROL_SPS | CONTROL_BIGFIFO; - mchp_corespi_write(spi, REG_CONTROL, control); + mpfs_spi_write(spi, REG_CONTROL, control); - mchp_corespi_set_framesize(spi, DEFAULT_FRAMESIZE); + mpfs_spi_set_framesize(spi, DEFAULT_FRAMESIZE); /* max. possible spi clock rate is the apb clock rate */ clk_hz = clk_get_rate(spi->clk); host->max_speed_hz = clk_hz; - mchp_corespi_enable_ints(spi); + mpfs_spi_enable_ints(spi); /* * It is required to enable direct mode, otherwise control over the chip @@ -344,34 +344,34 @@ static void mchp_corespi_init(struct spi_controller *host, struct mchp_corespi * * can deal with active high targets. */ spi->pending_slave_select = SSELOUT | SSEL_DIRECT; - mchp_corespi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select); + mpfs_spi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select); - control = mchp_corespi_read(spi, REG_CONTROL); + control = mpfs_spi_read(spi, REG_CONTROL); control &= ~CONTROL_RESET; control |= CONTROL_ENABLE; - mchp_corespi_write(spi, REG_CONTROL, control); + mpfs_spi_write(spi, REG_CONTROL, control); } -static inline void mchp_corespi_set_clk_gen(struct mchp_corespi *spi) +static inline void mpfs_spi_set_clk_gen(struct mpfs_spi *spi) { u32 control; - control = mchp_corespi_read(spi, REG_CONTROL); + control = mpfs_spi_read(spi, REG_CONTROL); if (spi->clk_mode) control |= CONTROL_CLKMODE; else control &= ~CONTROL_CLKMODE; - mchp_corespi_write(spi, REG_CLK_GEN, spi->clk_gen); - mchp_corespi_write(spi, REG_CONTROL, control); + mpfs_spi_write(spi, REG_CLK_GEN, spi->clk_gen); + mpfs_spi_write(spi, REG_CONTROL, control); } -static inline void mchp_corespi_set_mode(struct mchp_corespi *spi, unsigned int mode) +static inline void mpfs_spi_set_mode(struct mpfs_spi *spi, unsigned int mode) { u32 mode_val; - u32 control = mchp_corespi_read(spi, REG_CONTROL); + u32 control = mpfs_spi_read(spi, REG_CONTROL); switch (mode & SPI_MODE_X_MASK) { case SPI_MODE_0: @@ -394,22 +394,22 @@ static inline void mchp_corespi_set_mode(struct mchp_corespi *spi, unsigned int */ control &= ~CONTROL_ENABLE; - mchp_corespi_write(spi, REG_CONTROL, control); + mpfs_spi_write(spi, REG_CONTROL, control); control &= ~(SPI_MODE_X_MASK << MODE_X_MASK_SHIFT); control |= mode_val; - mchp_corespi_write(spi, REG_CONTROL, control); + mpfs_spi_write(spi, REG_CONTROL, control); control |= CONTROL_ENABLE; - mchp_corespi_write(spi, REG_CONTROL, control); + mpfs_spi_write(spi, REG_CONTROL, control); } -static irqreturn_t mchp_corespi_interrupt(int irq, void *dev_id) +static irqreturn_t mpfs_spi_interrupt(int irq, void *dev_id) { struct spi_controller *host = dev_id; - struct mchp_corespi *spi = spi_controller_get_devdata(host); - u32 intfield = mchp_corespi_read(spi, REG_MIS) & 0xf; + struct mpfs_spi *spi = spi_controller_get_devdata(host); + u32 intfield = mpfs_spi_read(spi, REG_MIS) & 0xf; bool finalise = false; /* Interrupt line may be shared and not for us at all */ @@ -417,7 +417,7 @@ static irqreturn_t mchp_corespi_interrupt(int irq, void *dev_id) return IRQ_NONE; if (intfield & INT_RX_CHANNEL_OVERFLOW) { - mchp_corespi_write(spi, REG_INT_CLEAR, INT_RX_CHANNEL_OVERFLOW); + mpfs_spi_write(spi, REG_INT_CLEAR, INT_RX_CHANNEL_OVERFLOW); finalise = true; dev_err(&host->dev, "%s: RX OVERFLOW: rxlen: %d, txlen: %d\n", __func__, @@ -425,7 +425,7 @@ static irqreturn_t mchp_corespi_interrupt(int irq, void *dev_id) } if (intfield & INT_TX_CHANNEL_UNDERRUN) { - mchp_corespi_write(spi, REG_INT_CLEAR, INT_TX_CHANNEL_UNDERRUN); + mpfs_spi_write(spi, REG_INT_CLEAR, INT_TX_CHANNEL_UNDERRUN); finalise = true; dev_err(&host->dev, "%s: TX UNDERFLOW: rxlen: %d, txlen: %d\n", __func__, @@ -438,8 +438,8 @@ static irqreturn_t mchp_corespi_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static int mchp_corespi_calculate_clkgen(struct mchp_corespi *spi, - unsigned long target_hz) +static int mpfs_spi_calculate_clkgen(struct mpfs_spi *spi, + unsigned long target_hz) { unsigned long clk_hz, spi_hz, clk_gen; @@ -475,20 +475,20 @@ static int mchp_corespi_calculate_clkgen(struct mchp_corespi *spi, return 0; } -static int mchp_corespi_transfer_one(struct spi_controller *host, - struct spi_device *spi_dev, - struct spi_transfer *xfer) +static int mpfs_spi_transfer_one(struct spi_controller *host, + struct spi_device *spi_dev, + struct spi_transfer *xfer) { - struct mchp_corespi *spi = spi_controller_get_devdata(host); + struct mpfs_spi *spi = spi_controller_get_devdata(host); int ret; - ret = mchp_corespi_calculate_clkgen(spi, (unsigned long)xfer->speed_hz); + ret = mpfs_spi_calculate_clkgen(spi, (unsigned long)xfer->speed_hz); if (ret) { dev_err(&host->dev, "failed to set clk_gen for target %u Hz\n", xfer->speed_hz); return ret; } - mchp_corespi_set_clk_gen(spi); + mpfs_spi_set_clk_gen(spi); spi->tx_buf = xfer->tx_buf; spi->rx_buf = xfer->rx_buf; @@ -496,45 +496,46 @@ static int mchp_corespi_transfer_one(struct spi_controller *host, spi->rx_len = xfer->len; spi->n_bytes = roundup_pow_of_two(DIV_ROUND_UP(xfer->bits_per_word, BITS_PER_BYTE)); - mchp_corespi_set_framesize(spi, xfer->bits_per_word); + mpfs_spi_set_framesize(spi, xfer->bits_per_word); - mchp_corespi_write(spi, REG_COMMAND, COMMAND_RXFIFORST | COMMAND_TXFIFORST); + mpfs_spi_write(spi, REG_COMMAND, COMMAND_RXFIFORST | COMMAND_TXFIFORST); - mchp_corespi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select); + mpfs_spi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select); while (spi->tx_len) { int fifo_max = DIV_ROUND_UP(min(spi->tx_len, FIFO_DEPTH), spi->n_bytes); - mchp_corespi_write_fifo(spi, fifo_max); - mchp_corespi_read_fifo(spi, fifo_max); + mpfs_spi_write_fifo(spi, fifo_max); + mpfs_spi_read_fifo(spi, fifo_max); } spi_finalize_current_transfer(host); return 1; } -static int mchp_corespi_prepare_message(struct spi_controller *host, - struct spi_message *msg) +static int mpfs_spi_prepare_message(struct spi_controller *host, + struct spi_message *msg) { struct spi_device *spi_dev = msg->spi; - struct mchp_corespi *spi = spi_controller_get_devdata(host); + struct mpfs_spi *spi = spi_controller_get_devdata(host); - mchp_corespi_set_mode(spi, spi_dev->mode); + mpfs_spi_set_mode(spi, spi_dev->mode); return 0; } -static int mchp_corespi_probe(struct platform_device *pdev) +static int mpfs_spi_probe(struct platform_device *pdev) { struct spi_controller *host; - struct mchp_corespi *spi; + struct mpfs_spi *spi; struct resource *res; u32 num_cs; int ret = 0; host = devm_spi_alloc_host(&pdev->dev, sizeof(*spi)); if (!host) - return -ENOMEM; + return dev_err_probe(&pdev->dev, -ENOMEM, + "unable to allocate host for SPI controller\n"); platform_set_drvdata(pdev, host); @@ -544,11 +545,11 @@ static int mchp_corespi_probe(struct platform_device *pdev) host->num_chipselect = num_cs; host->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH; host->use_gpio_descriptors = true; - host->setup = mchp_corespi_setup; + host->setup = mpfs_spi_setup; host->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32); - host->transfer_one = mchp_corespi_transfer_one; - host->prepare_message = mchp_corespi_prepare_message; - host->set_cs = mchp_corespi_set_cs; + host->transfer_one = mpfs_spi_transfer_one; + host->prepare_message = mpfs_spi_prepare_message; + host->set_cs = mpfs_spi_set_cs; host->dev.of_node = pdev->dev.of_node; spi = spi_controller_get_devdata(host); @@ -561,7 +562,7 @@ static int mchp_corespi_probe(struct platform_device *pdev) if (spi->irq < 0) return spi->irq; - ret = devm_request_irq(&pdev->dev, spi->irq, mchp_corespi_interrupt, + ret = devm_request_irq(&pdev->dev, spi->irq, mpfs_spi_interrupt, IRQF_SHARED, dev_name(&pdev->dev), host); if (ret) return dev_err_probe(&pdev->dev, ret, @@ -572,11 +573,12 @@ static int mchp_corespi_probe(struct platform_device *pdev) return dev_err_probe(&pdev->dev, PTR_ERR(spi->clk), "could not get clk\n"); - mchp_corespi_init(host, spi); + mpfs_spi_init(host, spi); ret = devm_spi_register_controller(&pdev->dev, host); if (ret) { - mchp_corespi_disable(spi); + mpfs_spi_disable_ints(spi); + mpfs_spi_disable(spi); return dev_err_probe(&pdev->dev, ret, "unable to register host for SPI controller\n"); } @@ -586,13 +588,13 @@ static int mchp_corespi_probe(struct platform_device *pdev) return 0; } -static void mchp_corespi_remove(struct platform_device *pdev) +static void mpfs_spi_remove(struct platform_device *pdev) { struct spi_controller *host = platform_get_drvdata(pdev); - struct mchp_corespi *spi = spi_controller_get_devdata(host); + struct mpfs_spi *spi = spi_controller_get_devdata(host); - mchp_corespi_disable_ints(spi); - mchp_corespi_disable(spi); + mpfs_spi_disable_ints(spi); + mpfs_spi_disable(spi); } #define MICROCHIP_SPI_PM_OPS (NULL) @@ -602,23 +604,23 @@ static void mchp_corespi_remove(struct platform_device *pdev) */ #if defined(CONFIG_OF) -static const struct of_device_id mchp_corespi_dt_ids[] = { +static const struct of_device_id mpfs_spi_dt_ids[] = { { .compatible = "microchip,mpfs-spi" }, { /* sentinel */ } }; -MODULE_DEVICE_TABLE(of, mchp_corespi_dt_ids); +MODULE_DEVICE_TABLE(of, mpfs_spi_dt_ids); #endif -static struct platform_driver mchp_corespi_driver = { - .probe = mchp_corespi_probe, +static struct platform_driver mpfs_spi_driver = { + .probe = mpfs_spi_probe, .driver = { - .name = "microchip-corespi", + .name = "microchip-spi", .pm = MICROCHIP_SPI_PM_OPS, - .of_match_table = of_match_ptr(mchp_corespi_dt_ids), + .of_match_table = of_match_ptr(mpfs_spi_dt_ids), }, - .remove = mchp_corespi_remove, + .remove = mpfs_spi_remove, }; -module_platform_driver(mchp_corespi_driver); +module_platform_driver(mpfs_spi_driver); MODULE_DESCRIPTION("Microchip coreSPI SPI controller driver"); MODULE_AUTHOR("Daire McNamara "); MODULE_AUTHOR("Conor Dooley "); diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 4b40985af1eaf0..90e5813cfdc332 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -1320,7 +1320,7 @@ static int mtk_spi_probe(struct platform_device *pdev) ret = devm_request_threaded_irq(dev, irq, mtk_spi_interrupt, mtk_spi_interrupt_thread, - IRQF_TRIGGER_NONE, dev_name(dev), host); + IRQF_ONESHOT, dev_name(dev), host); if (ret) return dev_err_probe(dev, ret, "failed to register irq\n"); diff --git a/drivers/spi/spi-sg2044-nor.c b/drivers/spi/spi-sg2044-nor.c index af48b1fcda930f..37f1cfe10be460 100644 --- a/drivers/spi/spi-sg2044-nor.c +++ b/drivers/spi/spi-sg2044-nor.c @@ -42,6 +42,7 @@ #define SPIFMC_TRAN_CSR_TRAN_MODE_RX BIT(0) #define SPIFMC_TRAN_CSR_TRAN_MODE_TX BIT(1) #define SPIFMC_TRAN_CSR_FAST_MODE BIT(3) +#define SPIFMC_TRAN_CSR_BUS_WIDTH_MASK GENMASK(5, 4) #define SPIFMC_TRAN_CSR_BUS_WIDTH_1_BIT (0x00 << 4) #define SPIFMC_TRAN_CSR_BUS_WIDTH_2_BIT (0x01 << 4) #define SPIFMC_TRAN_CSR_BUS_WIDTH_4_BIT (0x02 << 4) @@ -122,8 +123,7 @@ static u32 sg2044_spifmc_init_reg(struct sg2044_spifmc *spifmc) reg = readl(spifmc->io_base + SPIFMC_TRAN_CSR); reg &= ~(SPIFMC_TRAN_CSR_TRAN_MODE_MASK | SPIFMC_TRAN_CSR_FAST_MODE | - SPIFMC_TRAN_CSR_BUS_WIDTH_2_BIT | - SPIFMC_TRAN_CSR_BUS_WIDTH_4_BIT | + SPIFMC_TRAN_CSR_BUS_WIDTH_MASK | SPIFMC_TRAN_CSR_DMA_EN | SPIFMC_TRAN_CSR_ADDR_BYTES_MASK | SPIFMC_TRAN_CSR_WITH_CMD | diff --git a/drivers/spi/spi-sprd-adi.c b/drivers/spi/spi-sprd-adi.c index 262c11d977ea35..f25b34a91756f4 100644 --- a/drivers/spi/spi-sprd-adi.c +++ b/drivers/spi/spi-sprd-adi.c @@ -528,7 +528,7 @@ static int sprd_adi_probe(struct platform_device *pdev) pdev->id = of_alias_get_id(np, "spi"); num_chipselect = of_get_child_count(np); - ctlr = spi_alloc_host(&pdev->dev, sizeof(struct sprd_adi)); + ctlr = devm_spi_alloc_host(&pdev->dev, sizeof(struct sprd_adi)); if (!ctlr) return -ENOMEM; @@ -536,10 +536,8 @@ static int sprd_adi_probe(struct platform_device *pdev) sadi = spi_controller_get_devdata(ctlr); sadi->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); - if (IS_ERR(sadi->base)) { - ret = PTR_ERR(sadi->base); - goto put_ctlr; - } + if (IS_ERR(sadi->base)) + return PTR_ERR(sadi->base); sadi->slave_vbase = (unsigned long)sadi->base + data->slave_offset; @@ -551,18 +549,15 @@ static int sprd_adi_probe(struct platform_device *pdev) if (ret > 0 || (IS_ENABLED(CONFIG_HWSPINLOCK) && ret == 0)) { sadi->hwlock = devm_hwspin_lock_request_specific(&pdev->dev, ret); - if (!sadi->hwlock) { - ret = -ENXIO; - goto put_ctlr; - } + if (!sadi->hwlock) + return -ENXIO; } else { switch (ret) { case -ENOENT: dev_info(&pdev->dev, "no hardware spinlock supplied\n"); break; default: - dev_err_probe(&pdev->dev, ret, "failed to find hwlock id\n"); - goto put_ctlr; + return dev_err_probe(&pdev->dev, ret, "failed to find hwlock id\n"); } } @@ -579,26 +574,18 @@ static int sprd_adi_probe(struct platform_device *pdev) ctlr->transfer_one = sprd_adi_transfer_one; ret = devm_spi_register_controller(&pdev->dev, ctlr); - if (ret) { - dev_err(&pdev->dev, "failed to register SPI controller\n"); - goto put_ctlr; - } + if (ret) + return dev_err_probe(&pdev->dev, ret, "failed to register SPI controller\n"); if (sadi->data->restart) { ret = devm_register_restart_handler(&pdev->dev, sadi->data->restart, sadi); - if (ret) { - dev_err(&pdev->dev, "can not register restart handler\n"); - goto put_ctlr; - } + if (ret) + return dev_err_probe(&pdev->dev, ret, "can not register restart handler\n"); } return 0; - -put_ctlr: - spi_controller_put(ctlr); - return ret; } static struct sprd_adi_data sc9860_data = { diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c index 795a8482c2c700..48fb11fea55f2d 100644 --- a/drivers/spi/spi-tegra114.c +++ b/drivers/spi/spi-tegra114.c @@ -978,11 +978,14 @@ static int tegra_spi_setup(struct spi_device *spi) if (spi_get_csgpiod(spi, 0)) gpiod_set_value(spi_get_csgpiod(spi, 0), 0); + /* Update default register to include CS polarity and SPI mode */ val = tspi->def_command1_reg; if (spi->mode & SPI_CS_HIGH) val &= ~SPI_CS_POL_INACTIVE(spi_get_chipselect(spi, 0)); else val |= SPI_CS_POL_INACTIVE(spi_get_chipselect(spi, 0)); + val &= ~SPI_CONTROL_MODE_MASK; + val |= SPI_MODE_SEL(spi->mode & 0x3); tspi->def_command1_reg = val; tegra_spi_writel(tspi, tspi->def_command1_reg, SPI_COMMAND1); spin_unlock_irqrestore(&tspi->lock, flags); diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c index fe452d03c1ee43..709669610840bc 100644 --- a/drivers/spi/spi-tegra20-slink.c +++ b/drivers/spi/spi-tegra20-slink.c @@ -1086,8 +1086,10 @@ static int tegra_slink_probe(struct platform_device *pdev) reset_control_deassert(tspi->rst); spi_irq = platform_get_irq(pdev, 0); - if (spi_irq < 0) - return spi_irq; + if (spi_irq < 0) { + ret = spi_irq; + goto exit_pm_put; + } tspi->irq = spi_irq; ret = request_threaded_irq(tspi->irq, tegra_slink_isr, tegra_slink_isr_thread, IRQF_ONESHOT, diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c index 3be7499db21ec4..83def82fe48c14 100644 --- a/drivers/spi/spi-tegra210-quad.c +++ b/drivers/spi/spi-tegra210-quad.c @@ -839,6 +839,7 @@ static u32 tegra_qspi_setup_transfer_one(struct spi_device *spi, struct spi_tran u32 command1, command2, speed = t->speed_hz; u8 bits_per_word = t->bits_per_word; u32 tx_tap = 0, rx_tap = 0; + unsigned long flags; int req_mode; if (!has_acpi_companion(tqspi->dev) && speed != tqspi->cur_speed) { @@ -846,10 +847,12 @@ static u32 tegra_qspi_setup_transfer_one(struct spi_device *spi, struct spi_tran tqspi->cur_speed = speed; } + spin_lock_irqsave(&tqspi->lock, flags); tqspi->cur_pos = 0; tqspi->cur_rx_pos = 0; tqspi->cur_tx_pos = 0; tqspi->curr_xfer = t; + spin_unlock_irqrestore(&tqspi->lock, flags); if (is_first_of_msg) { tegra_qspi_mask_clear_irq(tqspi); @@ -1024,8 +1027,10 @@ static void tegra_qspi_handle_error(struct tegra_qspi *tqspi) dev_err(tqspi->dev, "error in transfer, fifo status 0x%08x\n", tqspi->status_reg); tegra_qspi_dump_regs(tqspi); tegra_qspi_flush_fifos(tqspi, true); - if (device_reset(tqspi->dev) < 0) + if (device_reset(tqspi->dev) < 0) { dev_warn_once(tqspi->dev, "device reset failed\n"); + tegra_qspi_mask_clear_irq(tqspi); + } } static void tegra_qspi_transfer_end(struct spi_device *spi) @@ -1084,6 +1089,7 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi, u32 address_value = 0; u32 cmd_config = 0, addr_config = 0; u8 cmd_value = 0, val = 0; + unsigned long flags; /* Enable Combined sequence mode */ val = tegra_qspi_readl(tqspi, QSPI_GLOBAL_CONFIG); @@ -1176,9 +1182,11 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi, } /* Reset controller if timeout happens */ - if (device_reset(tqspi->dev) < 0) + if (device_reset(tqspi->dev) < 0) { dev_warn_once(tqspi->dev, "device reset failed\n"); + tegra_qspi_mask_clear_irq(tqspi); + } ret = -EIO; goto exit; } @@ -1200,11 +1208,17 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi, tegra_qspi_transfer_end(spi); spi_transfer_delay_exec(xfer); } + spin_lock_irqsave(&tqspi->lock, flags); + tqspi->curr_xfer = NULL; + spin_unlock_irqrestore(&tqspi->lock, flags); transfer_phase++; } ret = 0; exit: + spin_lock_irqsave(&tqspi->lock, flags); + tqspi->curr_xfer = NULL; + spin_unlock_irqrestore(&tqspi->lock, flags); msg->status = ret; return ret; @@ -1217,6 +1231,7 @@ static int tegra_qspi_non_combined_seq_xfer(struct tegra_qspi *tqspi, struct spi_transfer *transfer; bool is_first_msg = true; int ret = 0, val = 0; + unsigned long flags; msg->status = 0; msg->actual_length = 0; @@ -1290,6 +1305,10 @@ static int tegra_qspi_non_combined_seq_xfer(struct tegra_qspi *tqspi, msg->actual_length += xfer->len + dummy_bytes; complete_xfer: + spin_lock_irqsave(&tqspi->lock, flags); + tqspi->curr_xfer = NULL; + spin_unlock_irqrestore(&tqspi->lock, flags); + if (ret < 0) { tegra_qspi_transfer_end(spi); spi_transfer_delay_exec(xfer); @@ -1368,10 +1387,16 @@ static int tegra_qspi_transfer_one_message(struct spi_controller *host, static irqreturn_t handle_cpu_based_xfer(struct tegra_qspi *tqspi) { - struct spi_transfer *t = tqspi->curr_xfer; + struct spi_transfer *t; unsigned long flags; spin_lock_irqsave(&tqspi->lock, flags); + t = tqspi->curr_xfer; + + if (!t) { + spin_unlock_irqrestore(&tqspi->lock, flags); + return IRQ_HANDLED; + } if (tqspi->tx_status || tqspi->rx_status) { tegra_qspi_handle_error(tqspi); @@ -1395,13 +1420,14 @@ static irqreturn_t handle_cpu_based_xfer(struct tegra_qspi *tqspi) tegra_qspi_calculate_curr_xfer_param(tqspi, t); tegra_qspi_start_cpu_based_transfer(tqspi, t); exit: + tqspi->curr_xfer = NULL; spin_unlock_irqrestore(&tqspi->lock, flags); return IRQ_HANDLED; } static irqreturn_t handle_dma_based_xfer(struct tegra_qspi *tqspi) { - struct spi_transfer *t = tqspi->curr_xfer; + struct spi_transfer *t; unsigned int total_fifo_words; unsigned long flags; long wait_status; @@ -1440,6 +1466,12 @@ static irqreturn_t handle_dma_based_xfer(struct tegra_qspi *tqspi) } spin_lock_irqsave(&tqspi->lock, flags); + t = tqspi->curr_xfer; + + if (!t) { + spin_unlock_irqrestore(&tqspi->lock, flags); + return IRQ_HANDLED; + } if (num_errors) { tegra_qspi_dma_unmap_xfer(tqspi, t); @@ -1479,6 +1511,33 @@ static irqreturn_t handle_dma_based_xfer(struct tegra_qspi *tqspi) static irqreturn_t tegra_qspi_isr_thread(int irq, void *context_data) { struct tegra_qspi *tqspi = context_data; + unsigned long flags; + u32 status; + + /* + * Read transfer status to check if interrupt was triggered by transfer + * completion + */ + status = tegra_qspi_readl(tqspi, QSPI_TRANS_STATUS); + + /* + * Occasionally the IRQ thread takes a long time to wake up (usually + * when the CPU that it's running on is excessively busy) and we have + * already reached the timeout before and cleaned up the timed out + * transfer. Avoid any processing in that case and bail out early. + * + * If no transfer is in progress, check if this was a real interrupt + * that the timeout handler already processed, or a spurious one. + */ + spin_lock_irqsave(&tqspi->lock, flags); + if (!tqspi->curr_xfer) { + spin_unlock_irqrestore(&tqspi->lock, flags); + /* Spurious interrupt - transfer not ready */ + if (!(status & QSPI_RDY)) + return IRQ_NONE; + /* Real interrupt, already handled by timeout path */ + return IRQ_HANDLED; + } tqspi->status_reg = tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS); @@ -1489,7 +1548,14 @@ static irqreturn_t tegra_qspi_isr_thread(int irq, void *context_data) tqspi->rx_status = tqspi->status_reg & (QSPI_RX_FIFO_OVF | QSPI_RX_FIFO_UNF); tegra_qspi_mask_clear_irq(tqspi); + spin_unlock_irqrestore(&tqspi->lock, flags); + /* + * Lock is released here but handlers safely re-check curr_xfer under + * lock before dereferencing. + * DMA handler also needs to sleep in wait_for_completion_*(), which + * cannot be done while holding spinlock. + */ if (!tqspi->is_curr_dma_xfer) return handle_cpu_based_xfer(tqspi); diff --git a/drivers/spi/spi-wpcm-fiu.c b/drivers/spi/spi-wpcm-fiu.c index a9aee2a6c7dcbc..c47b56f0933f14 100644 --- a/drivers/spi/spi-wpcm-fiu.c +++ b/drivers/spi/spi-wpcm-fiu.c @@ -459,11 +459,11 @@ static int wpcm_fiu_probe(struct platform_device *pdev) res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "memory"); fiu->memory = devm_ioremap_resource(dev, res); - fiu->memory_size = min_t(size_t, resource_size(res), MAX_MEMORY_SIZE_TOTAL); if (IS_ERR(fiu->memory)) return dev_err_probe(dev, PTR_ERR(fiu->memory), "Failed to map flash memory window\n"); + fiu->memory_size = min_t(size_t, resource_size(res), MAX_MEMORY_SIZE_TOTAL); fiu->shm_regmap = syscon_regmap_lookup_by_phandle_optional(dev->of_node, "nuvoton,shm"); wpcm_fiu_hw_init(fiu); diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c index 697b3e8bb02356..87e3ee9d4f2aa5 100644 --- a/drivers/spmi/spmi-apple-controller.c +++ b/drivers/spmi/spmi-apple-controller.c @@ -149,6 +149,7 @@ static int apple_spmi_probe(struct platform_device *pdev) } static const struct of_device_id apple_spmi_match_table[] = { + { .compatible = "apple,t8103-spmi", }, { .compatible = "apple,spmi", }, {} }; diff --git a/drivers/staging/fbtft/fbtft-core.c b/drivers/staging/fbtft/fbtft-core.c index 9e7b84071174cf..8a5ccc8ae0a188 100644 --- a/drivers/staging/fbtft/fbtft-core.c +++ b/drivers/staging/fbtft/fbtft-core.c @@ -1171,8 +1171,8 @@ int fbtft_probe_common(struct fbtft_display *display, par->pdev = pdev; if (display->buswidth == 0) { - dev_err(dev, "buswidth is not set\n"); - return -EINVAL; + ret = dev_err_probe(dev, -EINVAL, "buswidth is not set\n"); + goto out_release; } /* write register functions */ diff --git a/drivers/staging/gpib/common/iblib.c b/drivers/staging/gpib/common/iblib.c index 7cbb6a467177da..b672dd6aad25f2 100644 --- a/drivers/staging/gpib/common/iblib.c +++ b/drivers/staging/gpib/common/iblib.c @@ -227,11 +227,10 @@ int ibonline(struct gpib_board *board) #ifndef CONFIG_NIOS2 board->autospoll_task = kthread_run(&autospoll_thread, board, "gpib%d_autospoll_kthread", board->minor); - retval = IS_ERR(board->autospoll_task); - if (retval) { + if (IS_ERR(board->autospoll_task)) { dev_err(board->gpib_dev, "failed to create autospoll thread\n"); board->interface->detach(board); - return retval; + return PTR_ERR(board->autospoll_task); } #endif board->online = 1; diff --git a/drivers/staging/gpib/ni_usb/ni_usb_gpib.c b/drivers/staging/gpib/ni_usb/ni_usb_gpib.c index 1f8412de9fa329..b6fddb437f5524 100644 --- a/drivers/staging/gpib/ni_usb/ni_usb_gpib.c +++ b/drivers/staging/gpib/ni_usb/ni_usb_gpib.c @@ -566,7 +566,7 @@ static int ni_usb_write_registers(struct ni_usb_priv *ni_priv, retval, bytes_read); ni_usb_dump_raw_block(in_data, bytes_read); kfree(in_data); - return retval; + return retval ?: -EINVAL; } mutex_unlock(&ni_priv->addressed_transfer_lock); @@ -1780,7 +1780,7 @@ static int ni_usb_setup_init(struct gpib_board *board, struct ni_usb_register *w i++; if (i > NUM_INIT_WRITES) { dev_err(&usb_dev->dev, "bug!, buffer overrun, i=%i\n", i); - return 0; + return -EINVAL; } return i; } @@ -1799,10 +1799,12 @@ static int ni_usb_init(struct gpib_board *board) return -ENOMEM; writes_len = ni_usb_setup_init(board, writes); - if (writes_len) - retval = ni_usb_write_registers(ni_priv, writes, writes_len, &ibsta); - else - return -EFAULT; + if (writes_len < 0) { + kfree(writes); + return writes_len; + } + + retval = ni_usb_write_registers(ni_priv, writes, writes_len, &ibsta); kfree(writes); if (retval) { dev_err(&usb_dev->dev, "register write failed, retval=%i\n", retval); diff --git a/drivers/staging/greybus/light.c b/drivers/staging/greybus/light.c index e509fdc715dbbf..38c233a706c483 100644 --- a/drivers/staging/greybus/light.c +++ b/drivers/staging/greybus/light.c @@ -1008,14 +1008,18 @@ static int gb_lights_light_config(struct gb_lights *glights, u8 id) if (!strlen(conf.name)) return -EINVAL; - light->channels_count = conf.channel_count; light->name = kstrndup(conf.name, NAMES_MAX, GFP_KERNEL); if (!light->name) return -ENOMEM; - light->channels = kcalloc(light->channels_count, + light->channels = kcalloc(conf.channel_count, sizeof(struct gb_channel), GFP_KERNEL); if (!light->channels) return -ENOMEM; + /* + * Publish channels_count only after channels allocation so cleanup + * doesn't walk a NULL channels pointer on allocation failure. + */ + light->channels_count = conf.channel_count; /* First we collect all the configurations for all channels */ for (i = 0; i < light->channels_count; i++) { diff --git a/drivers/staging/most/Kconfig b/drivers/staging/most/Kconfig index 6f420cbcdcfff6..e89658df6f124c 100644 --- a/drivers/staging/most/Kconfig +++ b/drivers/staging/most/Kconfig @@ -24,6 +24,4 @@ source "drivers/staging/most/video/Kconfig" source "drivers/staging/most/dim2/Kconfig" -source "drivers/staging/most/i2c/Kconfig" - endif diff --git a/drivers/staging/most/Makefile b/drivers/staging/most/Makefile index 8b3fc5a7af5148..e45084df7803a7 100644 --- a/drivers/staging/most/Makefile +++ b/drivers/staging/most/Makefile @@ -3,4 +3,3 @@ obj-$(CONFIG_MOST_NET) += net/ obj-$(CONFIG_MOST_VIDEO) += video/ obj-$(CONFIG_MOST_DIM2) += dim2/ -obj-$(CONFIG_MOST_I2C) += i2c/ diff --git a/drivers/staging/most/i2c/Kconfig b/drivers/staging/most/i2c/Kconfig deleted file mode 100644 index ff64283cbad18b..00000000000000 --- a/drivers/staging/most/i2c/Kconfig +++ /dev/null @@ -1,13 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# MOST I2C configuration -# - -config MOST_I2C - tristate "I2C" - depends on I2C - help - Say Y here if you want to connect via I2C to network transceiver. - - To compile this driver as a module, choose M here: the - module will be called most_i2c. diff --git a/drivers/staging/most/i2c/Makefile b/drivers/staging/most/i2c/Makefile deleted file mode 100644 index 71099dd0f85b9c..00000000000000 --- a/drivers/staging/most/i2c/Makefile +++ /dev/null @@ -1,4 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_MOST_I2C) += most_i2c.o - -most_i2c-objs := i2c.o diff --git a/drivers/staging/most/i2c/i2c.c b/drivers/staging/most/i2c/i2c.c deleted file mode 100644 index 184b2dd11fc34a..00000000000000 --- a/drivers/staging/most/i2c/i2c.c +++ /dev/null @@ -1,374 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * i2c.c - Hardware Dependent Module for I2C Interface - * - * Copyright (C) 2013-2015, Microchip Technology Germany II GmbH & Co. KG - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include - -enum { CH_RX, CH_TX, NUM_CHANNELS }; - -#define MAX_BUFFERS_CONTROL 32 -#define MAX_BUF_SIZE_CONTROL 256 - -/** - * list_first_mbo - get the first mbo from a list - * @ptr: the list head to take the mbo from. - */ -#define list_first_mbo(ptr) \ - list_first_entry(ptr, struct mbo, list) - -static unsigned int polling_rate; -module_param(polling_rate, uint, 0644); -MODULE_PARM_DESC(polling_rate, "Polling rate [Hz]. Default = 0 (use IRQ)"); - -struct hdm_i2c { - struct most_interface most_iface; - struct most_channel_capability capabilities[NUM_CHANNELS]; - struct i2c_client *client; - struct rx { - struct delayed_work dwork; - struct list_head list; - bool int_disabled; - unsigned int delay; - } rx; - char name[64]; -}; - -static inline struct hdm_i2c *to_hdm(struct most_interface *iface) -{ - return container_of(iface, struct hdm_i2c, most_iface); -} - -static irqreturn_t most_irq_handler(int, void *); -static void pending_rx_work(struct work_struct *); - -/** - * configure_channel - called from MOST core to configure a channel - * @most_iface: interface the channel belongs to - * @ch_idx: channel to be configured - * @channel_config: structure that holds the configuration information - * - * Return 0 on success, negative on failure. - * - * Receives configuration information from MOST core and initialize the - * corresponding channel. - */ -static int configure_channel(struct most_interface *most_iface, - int ch_idx, - struct most_channel_config *channel_config) -{ - int ret; - struct hdm_i2c *dev = to_hdm(most_iface); - unsigned int delay, pr; - - BUG_ON(ch_idx < 0 || ch_idx >= NUM_CHANNELS); - - if (channel_config->data_type != MOST_CH_CONTROL) { - pr_err("bad data type for channel %d\n", ch_idx); - return -EPERM; - } - - if (channel_config->direction != dev->capabilities[ch_idx].direction) { - pr_err("bad direction for channel %d\n", ch_idx); - return -EPERM; - } - - if (channel_config->direction == MOST_CH_RX) { - if (!polling_rate) { - if (dev->client->irq <= 0) { - pr_err("bad irq: %d\n", dev->client->irq); - return -ENOENT; - } - dev->rx.int_disabled = false; - ret = request_irq(dev->client->irq, most_irq_handler, 0, - dev->client->name, dev); - if (ret) { - pr_err("request_irq(%d) failed: %d\n", - dev->client->irq, ret); - return ret; - } - } else { - delay = msecs_to_jiffies(MSEC_PER_SEC / polling_rate); - dev->rx.delay = delay ? delay : 1; - pr = MSEC_PER_SEC / jiffies_to_msecs(dev->rx.delay); - pr_info("polling rate is %u Hz\n", pr); - } - } - - return 0; -} - -/** - * enqueue - called from MOST core to enqueue a buffer for data transfer - * @most_iface: intended interface - * @ch_idx: ID of the channel the buffer is intended for - * @mbo: pointer to the buffer object - * - * Return 0 on success, negative on failure. - * - * Transmit the data over I2C if it is a "write" request or push the buffer into - * list if it is an "read" request - */ -static int enqueue(struct most_interface *most_iface, - int ch_idx, struct mbo *mbo) -{ - struct hdm_i2c *dev = to_hdm(most_iface); - int ret; - - BUG_ON(ch_idx < 0 || ch_idx >= NUM_CHANNELS); - - if (ch_idx == CH_RX) { - /* RX */ - if (!polling_rate) - disable_irq(dev->client->irq); - cancel_delayed_work_sync(&dev->rx.dwork); - list_add_tail(&mbo->list, &dev->rx.list); - if (dev->rx.int_disabled || polling_rate) - pending_rx_work(&dev->rx.dwork.work); - if (!polling_rate) - enable_irq(dev->client->irq); - } else { - /* TX */ - ret = i2c_master_send(dev->client, mbo->virt_address, - mbo->buffer_length); - if (ret <= 0) { - mbo->processed_length = 0; - mbo->status = MBO_E_INVAL; - } else { - mbo->processed_length = mbo->buffer_length; - mbo->status = MBO_SUCCESS; - } - mbo->complete(mbo); - } - - return 0; -} - -/** - * poison_channel - called from MOST core to poison buffers of a channel - * @most_iface: pointer to the interface the channel to be poisoned belongs to - * @ch_idx: corresponding channel ID - * - * Return 0 on success, negative on failure. - * - * If channel direction is RX, complete the buffers in list with - * status MBO_E_CLOSE - */ -static int poison_channel(struct most_interface *most_iface, - int ch_idx) -{ - struct hdm_i2c *dev = to_hdm(most_iface); - struct mbo *mbo; - - BUG_ON(ch_idx < 0 || ch_idx >= NUM_CHANNELS); - - if (ch_idx == CH_RX) { - if (!polling_rate) - free_irq(dev->client->irq, dev); - cancel_delayed_work_sync(&dev->rx.dwork); - - while (!list_empty(&dev->rx.list)) { - mbo = list_first_mbo(&dev->rx.list); - list_del(&mbo->list); - - mbo->processed_length = 0; - mbo->status = MBO_E_CLOSE; - mbo->complete(mbo); - } - } - - return 0; -} - -static void do_rx_work(struct hdm_i2c *dev) -{ - struct mbo *mbo; - unsigned char msg[MAX_BUF_SIZE_CONTROL]; - int ret; - u16 pml, data_size; - - /* Read PML (2 bytes) */ - ret = i2c_master_recv(dev->client, msg, 2); - if (ret <= 0) { - pr_err("Failed to receive PML\n"); - return; - } - - pml = (msg[0] << 8) | msg[1]; - if (!pml) - return; - - data_size = pml + 2; - - /* Read the whole message, including PML */ - ret = i2c_master_recv(dev->client, msg, data_size); - if (ret <= 0) { - pr_err("Failed to receive a Port Message\n"); - return; - } - - mbo = list_first_mbo(&dev->rx.list); - list_del(&mbo->list); - - mbo->processed_length = min(data_size, mbo->buffer_length); - memcpy(mbo->virt_address, msg, mbo->processed_length); - mbo->status = MBO_SUCCESS; - mbo->complete(mbo); -} - -/** - * pending_rx_work - Read pending messages through I2C - * @work: definition of this work item - * - * Invoked by the Interrupt Service Routine, most_irq_handler() - */ -static void pending_rx_work(struct work_struct *work) -{ - struct hdm_i2c *dev = container_of(work, struct hdm_i2c, rx.dwork.work); - - if (list_empty(&dev->rx.list)) - return; - - do_rx_work(dev); - - if (polling_rate) { - schedule_delayed_work(&dev->rx.dwork, dev->rx.delay); - } else { - dev->rx.int_disabled = false; - enable_irq(dev->client->irq); - } -} - -/* - * most_irq_handler - Interrupt Service Routine - * @irq: irq number - * @_dev: private data - * - * Schedules a delayed work - * - * By default the interrupt line behavior is Active Low. Once an interrupt is - * generated by the device, until driver clears the interrupt (by reading - * the PMP message), device keeps the interrupt line in low state. Since i2c - * read is done in work queue, the interrupt line must be disabled temporarily - * to avoid ISR being called repeatedly. Re-enable the interrupt in workqueue, - * after reading the message. - * - * Note: If we use the interrupt line in Falling edge mode, there is a - * possibility to miss interrupts when ISR is getting executed. - * - */ -static irqreturn_t most_irq_handler(int irq, void *_dev) -{ - struct hdm_i2c *dev = _dev; - - disable_irq_nosync(irq); - dev->rx.int_disabled = true; - schedule_delayed_work(&dev->rx.dwork, 0); - - return IRQ_HANDLED; -} - -/* - * i2c_probe - i2c probe handler - * @client: i2c client device structure - * @id: i2c client device id - * - * Return 0 on success, negative on failure. - * - * Register the i2c client device as a MOST interface - */ -static int i2c_probe(struct i2c_client *client) -{ - struct hdm_i2c *dev; - int ret, i; - - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) - return -ENOMEM; - - /* ID format: i2c--
*/ - snprintf(dev->name, sizeof(dev->name), "i2c-%d-%04x", - client->adapter->nr, client->addr); - - for (i = 0; i < NUM_CHANNELS; i++) { - dev->capabilities[i].data_type = MOST_CH_CONTROL; - dev->capabilities[i].num_buffers_packet = MAX_BUFFERS_CONTROL; - dev->capabilities[i].buffer_size_packet = MAX_BUF_SIZE_CONTROL; - } - dev->capabilities[CH_RX].direction = MOST_CH_RX; - dev->capabilities[CH_RX].name_suffix = "rx"; - dev->capabilities[CH_TX].direction = MOST_CH_TX; - dev->capabilities[CH_TX].name_suffix = "tx"; - - dev->most_iface.interface = ITYPE_I2C; - dev->most_iface.description = dev->name; - dev->most_iface.num_channels = NUM_CHANNELS; - dev->most_iface.channel_vector = dev->capabilities; - dev->most_iface.configure = configure_channel; - dev->most_iface.enqueue = enqueue; - dev->most_iface.poison_channel = poison_channel; - - INIT_LIST_HEAD(&dev->rx.list); - - INIT_DELAYED_WORK(&dev->rx.dwork, pending_rx_work); - - dev->client = client; - i2c_set_clientdata(client, dev); - - ret = most_register_interface(&dev->most_iface); - if (ret) { - pr_err("Failed to register i2c as a MOST interface\n"); - kfree(dev); - return ret; - } - - return 0; -} - -/* - * i2c_remove - i2c remove handler - * @client: i2c client device structure - * - * Return 0 on success. - * - * Unregister the i2c client device as a MOST interface - */ -static void i2c_remove(struct i2c_client *client) -{ - struct hdm_i2c *dev = i2c_get_clientdata(client); - - most_deregister_interface(&dev->most_iface); - kfree(dev); -} - -static const struct i2c_device_id i2c_id[] = { - { "most_i2c" }, - { } /* Terminating entry */ -}; - -MODULE_DEVICE_TABLE(i2c, i2c_id); - -static struct i2c_driver i2c_driver = { - .driver = { - .name = "hdm_i2c", - }, - .probe = i2c_probe, - .remove = i2c_remove, - .id_table = i2c_id, -}; - -module_i2c_driver(i2c_driver); - -MODULE_AUTHOR("Andrey Shvetsov "); -MODULE_DESCRIPTION("I2C Hardware Dependent Module"); -MODULE_LICENSE("GPL"); diff --git a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c index 53d4c113b19c8c..df35c616e71ff0 100644 --- a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c +++ b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c @@ -140,22 +140,24 @@ u8 *rtw_get_ie(u8 *pbuf, signed int index, signed int *len, signed int limit) signed int tmp, i; u8 *p; - if (limit < 1) + if (limit < 2) return NULL; p = pbuf; i = 0; *len = 0; - while (1) { + while (i + 2 <= limit) { + tmp = *(p + 1); + if (i + 2 + tmp > limit) + break; + if (*p == index) { - *len = *(p + 1); + *len = tmp; return p; } - tmp = *(p + 1); + p += (tmp + 2); i += (tmp + 2); - if (i >= limit) - break; } return NULL; } diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c index a897c433d2b061..72eb48d554a35b 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c @@ -588,9 +588,11 @@ unsigned int OnBeacon(struct adapter *padapter, union recv_frame *precv_frame) p = rtw_get_ie(pframe + sizeof(struct ieee80211_hdr_3addr) + _BEACON_IE_OFFSET_, WLAN_EID_EXT_SUPP_RATES, &ielen, precv_frame->u.hdr.len - sizeof(struct ieee80211_hdr_3addr) - _BEACON_IE_OFFSET_); if (p && ielen > 0) { - if ((*(p + 1 + ielen) == 0x2D) && (*(p + 2 + ielen) != 0x2D)) - /* Invalid value 0x2D is detected in Extended Supported Rates (ESR) IE. Try to fix the IE length to avoid failed Beacon parsing. */ - *(p + 1) = ielen - 1; + if (p + 2 + ielen < pframe + len) { + if ((*(p + 1 + ielen) == 0x2D) && (*(p + 2 + ielen) != 0x2D)) + /* Invalid value 0x2D is detected in Extended Supported Rates (ESR) IE. Try to fix the IE length to avoid failed Beacon parsing. */ + *(p + 1) = ielen - 1; + } } if (pmlmeext->sitesurvey_res.state == SCAN_PROCESS) { @@ -1042,6 +1044,9 @@ unsigned int OnAssocReq(struct adapter *padapter, union recv_frame *precv_frame) status = WLAN_STATUS_CHALLENGE_FAIL; goto OnAssocReqFail; } else { + if (ie_len > sizeof(supportRate)) + ie_len = sizeof(supportRate); + memcpy(supportRate, p+2, ie_len); supportRateNum = ie_len; @@ -1049,7 +1054,7 @@ unsigned int OnAssocReq(struct adapter *padapter, union recv_frame *precv_frame) pkt_len - WLAN_HDR_A3_LEN - ie_offset); if (p) { - if (supportRateNum <= sizeof(supportRate)) { + if (supportRateNum + ie_len <= sizeof(supportRate)) { memcpy(supportRate+supportRateNum, p+2, ie_len); supportRateNum += ie_len; } diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 5e6cf34929b55b..c1888c42afdd5e 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -741,8 +741,11 @@ void iscsit_dec_session_usage_count(struct iscsit_session *sess) spin_lock_bh(&sess->session_usage_lock); sess->session_usage_count--; - if (!sess->session_usage_count && sess->session_waiting_on_uc) + if (!sess->session_usage_count && sess->session_waiting_on_uc) { + spin_unlock_bh(&sess->session_usage_lock); complete(&sess->session_waiting_on_uc_comp); + return; + } spin_unlock_bh(&sess->session_usage_lock); } @@ -810,8 +813,11 @@ void iscsit_dec_conn_usage_count(struct iscsit_conn *conn) spin_lock_bh(&conn->conn_usage_lock); conn->conn_usage_count--; - if (!conn->conn_usage_count && conn->conn_waiting_on_uc) + if (!conn->conn_usage_count && conn->conn_waiting_on_uc) { + spin_unlock_bh(&conn->conn_usage_lock); complete(&conn->conn_waiting_on_uc_comp); + return; + } spin_unlock_bh(&conn->conn_usage_lock); } diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c index 3b89b5a70331f6..ad03bf7929f8bb 100644 --- a/drivers/target/sbp/sbp_target.c +++ b/drivers/target/sbp/sbp_target.c @@ -1961,12 +1961,12 @@ static struct se_portal_group *sbp_make_tpg(struct se_wwn *wwn, container_of(wwn, struct sbp_tport, tport_wwn); struct sbp_tpg *tpg; - unsigned long tpgt; + u16 tpgt; int ret; if (strstr(name, "tpgt_") != name) return ERR_PTR(-EINVAL); - if (kstrtoul(name + 5, 10, &tpgt) || tpgt > UINT_MAX) + if (kstrtou16(name + 5, 10, &tpgt)) return ERR_PTR(-EINVAL); if (tport->tpg) { diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index b19acd662726d4..1bd28482e7cb3e 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -2772,7 +2772,6 @@ static ssize_t target_lu_gp_members_show(struct config_item *item, char *page) cur_len = snprintf(buf, LU_GROUP_NAME_BUF, "%s/%s\n", config_item_name(&hba->hba_group.cg_item), config_item_name(&dev->dev_group.cg_item)); - cur_len++; /* Extra byte for NULL terminator */ if ((cur_len + len) > PAGE_SIZE || cur_len > LU_GROUP_NAME_BUF) { pr_warn("Ran out of lu_gp_show_attr" diff --git a/drivers/target/target_core_stat.c b/drivers/target/target_core_stat.c index 6bdf2d8bd69422..4fdc307ea38bc8 100644 --- a/drivers/target/target_core_stat.c +++ b/drivers/target/target_core_stat.c @@ -282,7 +282,7 @@ static ssize_t target_stat_lu_num_cmds_show(struct config_item *item, struct se_device *dev = to_stat_lu_dev(item); struct se_dev_io_stats *stats; unsigned int cpu; - u32 cmds = 0; + u64 cmds = 0; for_each_possible_cpu(cpu) { stats = per_cpu_ptr(dev->stats, cpu); @@ -290,7 +290,7 @@ static ssize_t target_stat_lu_num_cmds_show(struct config_item *item, } /* scsiLuNumCommands */ - return snprintf(page, PAGE_SIZE, "%u\n", cmds); + return snprintf(page, PAGE_SIZE, "%llu\n", cmds); } static ssize_t target_stat_lu_read_mbytes_show(struct config_item *item, @@ -299,7 +299,7 @@ static ssize_t target_stat_lu_read_mbytes_show(struct config_item *item, struct se_device *dev = to_stat_lu_dev(item); struct se_dev_io_stats *stats; unsigned int cpu; - u32 bytes = 0; + u64 bytes = 0; for_each_possible_cpu(cpu) { stats = per_cpu_ptr(dev->stats, cpu); @@ -307,7 +307,7 @@ static ssize_t target_stat_lu_read_mbytes_show(struct config_item *item, } /* scsiLuReadMegaBytes */ - return snprintf(page, PAGE_SIZE, "%u\n", bytes >> 20); + return snprintf(page, PAGE_SIZE, "%llu\n", bytes >> 20); } static ssize_t target_stat_lu_write_mbytes_show(struct config_item *item, @@ -316,7 +316,7 @@ static ssize_t target_stat_lu_write_mbytes_show(struct config_item *item, struct se_device *dev = to_stat_lu_dev(item); struct se_dev_io_stats *stats; unsigned int cpu; - u32 bytes = 0; + u64 bytes = 0; for_each_possible_cpu(cpu) { stats = per_cpu_ptr(dev->stats, cpu); @@ -324,7 +324,7 @@ static ssize_t target_stat_lu_write_mbytes_show(struct config_item *item, } /* scsiLuWrittenMegaBytes */ - return snprintf(page, PAGE_SIZE, "%u\n", bytes >> 20); + return snprintf(page, PAGE_SIZE, "%llu\n", bytes >> 20); } static ssize_t target_stat_lu_resets_show(struct config_item *item, char *page) @@ -1044,7 +1044,7 @@ static ssize_t target_stat_auth_num_cmds_show(struct config_item *item, struct se_dev_entry *deve; unsigned int cpu; ssize_t ret; - u32 cmds = 0; + u64 cmds = 0; rcu_read_lock(); deve = target_nacl_find_deve(nacl, lacl->mapped_lun); @@ -1059,7 +1059,7 @@ static ssize_t target_stat_auth_num_cmds_show(struct config_item *item, } /* scsiAuthIntrOutCommands */ - ret = snprintf(page, PAGE_SIZE, "%u\n", cmds); + ret = snprintf(page, PAGE_SIZE, "%llu\n", cmds); rcu_read_unlock(); return ret; } @@ -1073,7 +1073,7 @@ static ssize_t target_stat_auth_read_mbytes_show(struct config_item *item, struct se_dev_entry *deve; unsigned int cpu; ssize_t ret; - u32 bytes = 0; + u64 bytes = 0; rcu_read_lock(); deve = target_nacl_find_deve(nacl, lacl->mapped_lun); @@ -1088,7 +1088,7 @@ static ssize_t target_stat_auth_read_mbytes_show(struct config_item *item, } /* scsiAuthIntrReadMegaBytes */ - ret = snprintf(page, PAGE_SIZE, "%u\n", bytes >> 20); + ret = snprintf(page, PAGE_SIZE, "%llu\n", bytes >> 20); rcu_read_unlock(); return ret; } @@ -1102,7 +1102,7 @@ static ssize_t target_stat_auth_write_mbytes_show(struct config_item *item, struct se_dev_entry *deve; unsigned int cpu; ssize_t ret; - u32 bytes = 0; + u64 bytes = 0; rcu_read_lock(); deve = target_nacl_find_deve(nacl, lacl->mapped_lun); @@ -1117,7 +1117,7 @@ static ssize_t target_stat_auth_write_mbytes_show(struct config_item *item, } /* scsiAuthIntrWrittenMegaBytes */ - ret = snprintf(page, PAGE_SIZE, "%u\n", bytes >> 20); + ret = snprintf(page, PAGE_SIZE, "%llu\n", bytes >> 20); rcu_read_unlock(); return ret; } diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 0a76bdfe552820..88544c911949c8 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1524,6 +1524,7 @@ target_cmd_init_cdb(struct se_cmd *cmd, unsigned char *cdb, gfp_t gfp) if (scsi_command_size(cdb) > sizeof(cmd->__t_task_cdb)) { cmd->t_task_cdb = kzalloc(scsi_command_size(cdb), gfp); if (!cmd->t_task_cdb) { + cmd->t_task_cdb = &cmd->__t_task_cdb[0]; pr_err("Unable to allocate cmd->t_task_cdb" " %u > sizeof(cmd->__t_task_cdb): %lu ops\n", scsi_command_size(cdb), diff --git a/drivers/thermal/intel/x86_pkg_temp_thermal.c b/drivers/thermal/intel/x86_pkg_temp_thermal.c index 3fc679b6f11b17..aab5f9fca9c33c 100644 --- a/drivers/thermal/intel/x86_pkg_temp_thermal.c +++ b/drivers/thermal/intel/x86_pkg_temp_thermal.c @@ -128,6 +128,9 @@ sys_set_trip_temp(struct thermal_zone_device *tzd, u32 l, h, mask, shift, intr; int tj_max, val, ret; + if (temp == THERMAL_TEMP_INVALID) + temp = 0; + tj_max = intel_tcc_get_tjmax(zonedev->cpu); if (tj_max < 0) return tj_max; diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index 1a51a4d240ff60..b6d0c92f5522bd 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -280,10 +280,10 @@ static bool thermal_of_cm_lookup(struct device_node *cm_np, struct cooling_spec *c) { for_each_child_of_node_scoped(cm_np, child) { - struct device_node *tr_np; int count, i; - tr_np = of_parse_phandle(child, "trip", 0); + struct device_node *tr_np __free(device_node) = + of_parse_phandle(child, "trip", 0); if (tr_np != trip->priv) continue; diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 152f914c599dc5..79c3dca94b5600 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -95,6 +95,11 @@ #define PCI_DEVICE_ID_MOXA_CP138E_A 0x1381 #define PCI_DEVICE_ID_MOXA_CP168EL_A 0x1683 +#define PCI_DEVICE_ID_ADDIDATA_CPCI7500 0x7003 +#define PCI_DEVICE_ID_ADDIDATA_CPCI7500_NG 0x7024 +#define PCI_DEVICE_ID_ADDIDATA_CPCI7420_NG 0x7025 +#define PCI_DEVICE_ID_ADDIDATA_CPCI7300_NG 0x7026 + /* Unknown vendors/cards - this should not be in linux/pci_ids.h */ #define PCI_SUBDEVICE_ID_UNKNOWN_0x1584 0x1584 #define PCI_SUBDEVICE_ID_UNKNOWN_0x1588 0x1588 @@ -1645,7 +1650,7 @@ static int pci_fintek_rs485_config(struct uart_port *port, struct ktermios *term } static const struct serial_rs485 pci_fintek_rs485_supported = { - .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND, + .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RTS_AFTER_SEND, /* F81504/508/512 does not support RTS delay before or after send */ }; @@ -5996,6 +6001,38 @@ static const struct pci_device_id serial_pci_tbl[] = { 0, pbn_ADDIDATA_PCIe_8_3906250 }, + { PCI_VENDOR_ID_ADDIDATA, + PCI_DEVICE_ID_ADDIDATA_CPCI7500, + PCI_ANY_ID, + PCI_ANY_ID, + 0, + 0, + pbn_b0_4_115200 }, + + { PCI_VENDOR_ID_ADDIDATA, + PCI_DEVICE_ID_ADDIDATA_CPCI7500_NG, + PCI_ANY_ID, + PCI_ANY_ID, + 0, + 0, + pbn_b0_4_115200 }, + + { PCI_VENDOR_ID_ADDIDATA, + PCI_DEVICE_ID_ADDIDATA_CPCI7420_NG, + PCI_ANY_ID, + PCI_ANY_ID, + 0, + 0, + pbn_b0_2_115200 }, + + { PCI_VENDOR_ID_ADDIDATA, + PCI_DEVICE_ID_ADDIDATA_CPCI7300_NG, + PCI_ANY_ID, + PCI_ANY_ID, + 0, + 0, + pbn_b0_1_115200 }, + { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9835, PCI_VENDOR_ID_IBM, 0x0299, 0, 0, pbn_b0_bt_2_115200 }, @@ -6178,7 +6215,6 @@ static pci_ers_result_t serial8250_io_slot_reset(struct pci_dev *dev) return PCI_ERS_RESULT_DISCONNECT; pci_restore_state(dev); - pci_save_state(dev); return PCI_ERS_RESULT_RECOVERED; } diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 282116765e6481..2b9c8b39d68f55 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -486,14 +486,14 @@ config SERIAL_IMX can enable its onboard serial port by enabling this option. config SERIAL_IMX_CONSOLE - tristate "Console on IMX serial port" + bool "Console on IMX serial port" depends on SERIAL_IMX select SERIAL_CORE_CONSOLE help If you have enabled the serial port on the Freescale IMX - CPU you can make it the console by answering Y/M to this option. + CPU you can make it the console by answering Y to this option. - Even if you say Y/M here, the currently visible virtual console + Even if you say Y here, the currently visible virtual console (/dev/tty0) will still be used as the system console by default, but you can alter that using a kernel command line option such as "console=ttymxc0". (Try "man bootparam" or see the documentation of @@ -671,7 +671,7 @@ config SERIAL_SH_SCI_EARLYCON default ARCH_RENESAS config SERIAL_SH_SCI_DMA - bool "DMA support" if EXPERT + bool "Support for DMA on SuperH SCI(F)" if EXPERT depends on SERIAL_SH_SCI && DMA_ENGINE default ARCH_RENESAS diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 500dfc009d03e8..90e2ea1e8afe5c 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -2697,8 +2697,22 @@ static void imx_uart_save_context(struct imx_port *sport) /* called with irq off */ static void imx_uart_enable_wakeup(struct imx_port *sport, bool on) { + struct tty_port *port = &sport->port.state->port; + struct device *tty_dev; + bool may_wake = false; u32 ucr3; + scoped_guard(tty_port_tty, port) { + struct tty_struct *tty = scoped_tty(); + + tty_dev = tty->dev; + may_wake = tty_dev && device_may_wakeup(tty_dev); + } + + /* only configure the wake register when device set as wakeup source */ + if (!may_wake) + return; + uart_port_lock_irq(&sport->port); ucr3 = imx_uart_readl(sport, UCR3); diff --git a/drivers/tty/serial/jsm/jsm_driver.c b/drivers/tty/serial/jsm/jsm_driver.c index 417a5b6bffc34d..8d21373cae573a 100644 --- a/drivers/tty/serial/jsm/jsm_driver.c +++ b/drivers/tty/serial/jsm/jsm_driver.c @@ -355,7 +355,6 @@ static void jsm_io_resume(struct pci_dev *pdev) struct jsm_board *brd = pci_get_drvdata(pdev); pci_restore_state(pdev); - pci_save_state(pdev); jsm_uart_port_init(brd); } diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c index 2fb58c626daf35..563688c507515d 100644 --- a/drivers/tty/serial/samsung_tty.c +++ b/drivers/tty/serial/samsung_tty.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -1298,30 +1299,49 @@ static int apple_s5l_serial_startup(struct uart_port *port) return ret; } +static int __maybe_unused s3c24xx_serial_runtime_suspend(struct device *dev) +{ + struct uart_port *port = dev_get_drvdata(dev); + struct s3c24xx_uart_port *ourport = to_ourport(port); + int timeout = 10000; + + while (--timeout && !s3c24xx_serial_txempty_nofifo(port)) + udelay(100); + + if (!IS_ERR(ourport->baudclk)) + clk_disable_unprepare(ourport->baudclk); + + clk_disable_unprepare(ourport->clk); + return 0; +}; + +static int __maybe_unused s3c24xx_serial_runtime_resume(struct device *dev) +{ + struct uart_port *port = dev_get_drvdata(dev); + struct s3c24xx_uart_port *ourport = to_ourport(port); + + clk_prepare_enable(ourport->clk); + + if (!IS_ERR(ourport->baudclk)) + clk_prepare_enable(ourport->baudclk); + return 0; +}; + static void s3c24xx_serial_pm(struct uart_port *port, unsigned int level, unsigned int old) { struct s3c24xx_uart_port *ourport = to_ourport(port); - int timeout = 10000; ourport->pm_level = level; switch (level) { - case 3: - while (--timeout && !s3c24xx_serial_txempty_nofifo(port)) - udelay(100); - - if (!IS_ERR(ourport->baudclk)) - clk_disable_unprepare(ourport->baudclk); - - clk_disable_unprepare(ourport->clk); + case UART_PM_STATE_OFF: + pm_runtime_mark_last_busy(port->dev); + pm_runtime_put_sync(port->dev); break; - case 0: - clk_prepare_enable(ourport->clk); - - if (!IS_ERR(ourport->baudclk)) - clk_prepare_enable(ourport->baudclk); + case UART_PM_STATE_ON: + pm_runtime_get_sync(port->dev); break; default: dev_err(port->dev, "s3c24xx_serial: unknown pm %d\n", level); @@ -2044,18 +2064,15 @@ static int s3c24xx_serial_probe(struct platform_device *pdev) } } + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + dev_dbg(&pdev->dev, "%s: adding port\n", __func__); uart_add_one_port(&s3c24xx_uart_drv, &ourport->port); platform_set_drvdata(pdev, &ourport->port); - /* - * Deactivate the clock enabled in s3c24xx_serial_init_port here, - * so that a potential re-enablement through the pm-callback overlaps - * and keeps the clock enabled in this case. - */ - clk_disable_unprepare(ourport->clk); - if (!IS_ERR(ourport->baudclk)) - clk_disable_unprepare(ourport->baudclk); + pm_runtime_put_sync(&pdev->dev); probe_index++; @@ -2065,26 +2082,40 @@ static int s3c24xx_serial_probe(struct platform_device *pdev) static void s3c24xx_serial_remove(struct platform_device *dev) { struct uart_port *port = s3c24xx_dev_to_port(&dev->dev); + struct s3c24xx_uart_port *ourport = to_ourport(port); - if (port) + if (port) { + pm_runtime_get_sync(&dev->dev); uart_remove_one_port(&s3c24xx_uart_drv, port); + clk_disable_unprepare(ourport->clk); + if (!IS_ERR(ourport->baudclk)) + clk_disable_unprepare(ourport->baudclk); + + pm_runtime_disable(&dev->dev); + pm_runtime_set_suspended(&dev->dev); + pm_runtime_put_noidle(&dev->dev); + } + uart_unregister_driver(&s3c24xx_uart_drv); } /* UART power management code */ -#ifdef CONFIG_PM_SLEEP -static int s3c24xx_serial_suspend(struct device *dev) + +static int __maybe_unused s3c24xx_serial_suspend(struct device *dev) { struct uart_port *port = s3c24xx_dev_to_port(dev); + if (!console_suspend_enabled && uart_console(port)) + device_set_wakeup_path(dev); + if (port) uart_suspend_port(&s3c24xx_uart_drv, port); return 0; } -static int s3c24xx_serial_resume(struct device *dev) +static int __maybe_unused s3c24xx_serial_resume(struct device *dev) { struct uart_port *port = s3c24xx_dev_to_port(dev); struct s3c24xx_uart_port *ourport = to_ourport(port); @@ -2104,7 +2135,7 @@ static int s3c24xx_serial_resume(struct device *dev) return 0; } -static int s3c24xx_serial_resume_noirq(struct device *dev) +static int __maybe_unused s3c24xx_serial_resume_noirq(struct device *dev) { struct uart_port *port = s3c24xx_dev_to_port(dev); struct s3c24xx_uart_port *ourport = to_ourport(port); @@ -2178,13 +2209,9 @@ static int s3c24xx_serial_resume_noirq(struct device *dev) static const struct dev_pm_ops s3c24xx_serial_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(s3c24xx_serial_suspend, s3c24xx_serial_resume) SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(NULL, s3c24xx_serial_resume_noirq) + SET_RUNTIME_PM_OPS(s3c24xx_serial_runtime_suspend, + s3c24xx_serial_runtime_resume, NULL) }; -#define SERIAL_SAMSUNG_PM_OPS (&s3c24xx_serial_pm_ops) - -#else /* !CONFIG_PM_SLEEP */ - -#define SERIAL_SAMSUNG_PM_OPS NULL -#endif /* CONFIG_PM_SLEEP */ /* Console code */ @@ -2672,7 +2699,7 @@ static struct platform_driver samsung_serial_driver = { .id_table = s3c24xx_serial_driver_ids, .driver = { .name = "samsung-uart", - .pm = SERIAL_SAMSUNG_PM_OPS, + .pm = &s3c24xx_serial_pm_ops, .of_match_table = of_match_ptr(s3c24xx_uart_dt_match), }, }; diff --git a/drivers/tty/serial/serial_base_bus.c b/drivers/tty/serial/serial_base_bus.c index 22749ab0428a7c..1e1ad28d83fcf7 100644 --- a/drivers/tty/serial/serial_base_bus.c +++ b/drivers/tty/serial/serial_base_bus.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include #include @@ -60,6 +60,7 @@ void serial_base_driver_unregister(struct device_driver *driver) driver_unregister(driver); } +/* On failure the caller must put device @dev with put_device() */ static int serial_base_device_init(struct uart_port *port, struct device *dev, struct device *parent_dev, @@ -73,7 +74,9 @@ static int serial_base_device_init(struct uart_port *port, dev->parent = parent_dev; dev->bus = &serial_base_bus_type; dev->release = release; - device_set_of_node_from_dev(dev, parent_dev); + dev->of_node_reused = true; + + device_set_node(dev, fwnode_handle_get(dev_fwnode(parent_dev))); if (!serial_base_initialized) { dev_dbg(port->dev, "uart_add_one_port() called before arch_initcall()?\n"); @@ -94,7 +97,7 @@ static void serial_base_ctrl_release(struct device *dev) { struct serial_ctrl_device *ctrl_dev = to_serial_base_ctrl_device(dev); - of_node_put(dev->of_node); + fwnode_handle_put(dev_fwnode(dev)); kfree(ctrl_dev); } @@ -142,7 +145,7 @@ static void serial_base_port_release(struct device *dev) { struct serial_port_device *port_dev = to_serial_base_port_device(dev); - of_node_put(dev->of_node); + fwnode_handle_put(dev_fwnode(dev)); kfree(port_dev); } diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 4757293ece8c65..26db27d06a8653 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -3102,6 +3102,12 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u if (uport->cons && uport->dev) of_console_check(uport->dev->of_node, uport->cons->name, uport->line); + /* + * TTY port has to be linked with the driver before register_console() + * in uart_configure_port(), because user-space could open the console + * immediately after. + */ + tty_port_link_device(port, drv->tty_driver, uport->line); uart_configure_port(drv, state, uport); port->console = uart_console(uport); diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 62bb62b82cbe58..d91b1fb69bebdf 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1024,8 +1024,16 @@ static int sci_handle_fifo_overrun(struct uart_port *port) status = s->ops->read_reg(port, s->params->overrun_reg); if (status & s->params->overrun_mask) { - status &= ~s->params->overrun_mask; - s->ops->write_reg(port, s->params->overrun_reg, status); + if (s->type == SCI_PORT_RSCI) { + /* + * All of the CFCLR_*C clearing bits match the corresponding + * CSR_*status bits. So, reuse the overrun mask for clearing. + */ + s->ops->clear_SCxSR(port, s->params->overrun_mask); + } else { + status &= ~s->params->overrun_mask; + s->ops->write_reg(port, s->params->overrun_reg, status); + } port->icount.overrun++; @@ -1732,7 +1740,7 @@ static void sci_dma_check_tx_occurred(struct sci_port *s) struct dma_tx_state state; enum dma_status status; - if (!s->chan_tx) + if (!s->chan_tx || s->cookie_tx <= 0) return; status = dmaengine_tx_status(s->chan_tx, s->cookie_tx, &state); diff --git a/drivers/tty/serial/sprd_serial.c b/drivers/tty/serial/sprd_serial.c index 8c9366321f8e73..092755f356836a 100644 --- a/drivers/tty/serial/sprd_serial.c +++ b/drivers/tty/serial/sprd_serial.c @@ -1133,6 +1133,9 @@ static int sprd_clk_init(struct uart_port *uport) clk_uart = devm_clk_get(uport->dev, "uart"); if (IS_ERR(clk_uart)) { + if (PTR_ERR(clk_uart) == -EPROBE_DEFER) + return -EPROBE_DEFER; + dev_warn(uport->dev, "uart%d can't get uart clock\n", uport->line); clk_uart = NULL; @@ -1140,6 +1143,9 @@ static int sprd_clk_init(struct uart_port *uport) clk_parent = devm_clk_get(uport->dev, "source"); if (IS_ERR(clk_parent)) { + if (PTR_ERR(clk_parent) == -EPROBE_DEFER) + return -EPROBE_DEFER; + dev_warn(uport->dev, "uart%d can't get source clock\n", uport->line); clk_parent = NULL; diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index a66b44d21fba25..a354326a4242a6 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -430,10 +430,17 @@ static void cdns_uart_handle_tx(void *dev_id) struct tty_port *tport = &port->state->port; unsigned int numbytes; unsigned char ch; + ktime_t rts_delay; if (kfifo_is_empty(&tport->xmit_fifo) || uart_tx_stopped(port)) { /* Disable the TX Empty interrupt */ writel(CDNS_UART_IXR_TXEMPTY, port->membase + CDNS_UART_IDR); + /* Set RTS line after delay */ + if (cdns_uart->port->rs485.flags & SER_RS485_ENABLED) { + cdns_uart->tx_timer.function = &cdns_rs485_rx_callback; + rts_delay = ns_to_ktime(cdns_calc_after_tx_delay(cdns_uart)); + hrtimer_start(&cdns_uart->tx_timer, rts_delay, HRTIMER_MODE_REL); + } return; } @@ -450,13 +457,6 @@ static void cdns_uart_handle_tx(void *dev_id) /* Enable the TX Empty interrupt */ writel(CDNS_UART_IXR_TXEMPTY, cdns_uart->port->membase + CDNS_UART_IER); - - if (cdns_uart->port->rs485.flags & SER_RS485_ENABLED && - (kfifo_is_empty(&tport->xmit_fifo) || uart_tx_stopped(port))) { - hrtimer_update_function(&cdns_uart->tx_timer, cdns_rs485_rx_callback); - hrtimer_start(&cdns_uart->tx_timer, - ns_to_ktime(cdns_calc_after_tx_delay(cdns_uart)), HRTIMER_MODE_REL); - } } /** diff --git a/drivers/ufs/core/ufshcd-priv.h b/drivers/ufs/core/ufshcd-priv.h index d0a2c963a27d37..1f0d38aa37f920 100644 --- a/drivers/ufs/core/ufshcd-priv.h +++ b/drivers/ufs/core/ufshcd-priv.h @@ -6,6 +6,8 @@ #include #include +void ufshcd_enable_intr(struct ufs_hba *hba, u32 intrs); + static inline bool ufshcd_is_user_access_allowed(struct ufs_hba *hba) { return !hba->shutting_down; diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index d6a060a7246186..022810b524e96b 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -3837,7 +3837,7 @@ int ufshcd_read_string_desc(struct ufs_hba *hba, u8 desc_index, str[ret++] = '\0'; } else { - str = kmemdup(uc_str, uc_str->len, GFP_KERNEL); + str = kmemdup(uc_str->uc, uc_str->len, GFP_KERNEL); if (!str) { ret = -ENOMEM; goto out; @@ -6498,6 +6498,11 @@ static void ufshcd_clk_scaling_suspend(struct ufs_hba *hba, bool suspend) static void ufshcd_err_handling_prepare(struct ufs_hba *hba) { + /* + * A WLUN resume failure could potentially lead to the HBA being + * runtime suspended, so take an extra reference on hba->dev. + */ + pm_runtime_get_sync(hba->dev); ufshcd_rpm_get_sync(hba); if (pm_runtime_status_suspended(&hba->ufs_device_wlun->sdev_gendev) || hba->is_sys_suspended) { @@ -6537,6 +6542,7 @@ static void ufshcd_err_handling_unprepare(struct ufs_hba *hba) if (ufshcd_is_clkscaling_supported(hba)) ufshcd_clk_scaling_suspend(hba, false); ufshcd_rpm_put(hba); + pm_runtime_put(hba->dev); } static inline bool ufshcd_err_handling_should_stop(struct ufs_hba *hba) @@ -6551,28 +6557,42 @@ static inline bool ufshcd_err_handling_should_stop(struct ufs_hba *hba) #ifdef CONFIG_PM static void ufshcd_recover_pm_error(struct ufs_hba *hba) { + struct scsi_target *starget = hba->ufs_device_wlun->sdev_target; struct Scsi_Host *shost = hba->host; struct scsi_device *sdev; struct request_queue *q; - int ret; + bool resume_sdev_queues = false; hba->is_sys_suspended = false; + /* - * Set RPM status of wlun device to RPM_ACTIVE, - * this also clears its runtime error. + * Ensure the parent's error status is cleared before proceeding + * to the child, as the parent must be active to activate the child. */ - ret = pm_runtime_set_active(&hba->ufs_device_wlun->sdev_gendev); + if (hba->dev->power.runtime_error) { + /* hba->dev has no functional parent thus simplily set RPM_ACTIVE */ + pm_runtime_set_active(hba->dev); + resume_sdev_queues = true; + } + + if (hba->ufs_device_wlun->sdev_gendev.power.runtime_error) { + /* + * starget, parent of wlun, might be suspended if wlun resume failed. + * Make sure parent is resumed before set child (wlun) active. + */ + pm_runtime_get_sync(&starget->dev); + pm_runtime_set_active(&hba->ufs_device_wlun->sdev_gendev); + pm_runtime_put_sync(&starget->dev); + resume_sdev_queues = true; + } - /* hba device might have a runtime error otherwise */ - if (ret) - ret = pm_runtime_set_active(hba->dev); /* * If wlun device had runtime error, we also need to resume those * consumer scsi devices in case any of them has failed to be * resumed due to supplier runtime resume failure. This is to unblock * blk_queue_enter in case there are bios waiting inside it. */ - if (!ret) { + if (resume_sdev_queues) { shost_for_each_device(sdev, shost) { q = sdev->request_queue; if (q->dev && (q->rpm_status == RPM_SUSPENDED || @@ -6670,19 +6690,22 @@ static void ufshcd_err_handler(struct work_struct *work) hba->saved_uic_err, hba->force_reset, ufshcd_is_link_broken(hba) ? "; link is broken" : ""); - /* - * Use ufshcd_rpm_get_noresume() here to safely perform link recovery - * even if an error occurs during runtime suspend or runtime resume. - * This avoids potential deadlocks that could happen if we tried to - * resume the device while a PM operation is already in progress. - */ - ufshcd_rpm_get_noresume(hba); - if (hba->pm_op_in_progress) { - ufshcd_link_recovery(hba); + if (hba->ufs_device_wlun) { + /* + * Use ufshcd_rpm_get_noresume() here to safely perform link + * recovery even if an error occurs during runtime suspend or + * runtime resume. This avoids potential deadlocks that could + * happen if we tried to resume the device while a PM operation + * is already in progress. + */ + ufshcd_rpm_get_noresume(hba); + if (hba->pm_op_in_progress) { + ufshcd_link_recovery(hba); + ufshcd_rpm_put(hba); + return; + } ufshcd_rpm_put(hba); - return; } - ufshcd_rpm_put(hba); down(&hba->host_sem); spin_lock_irqsave(hba->host->host_lock, flags); @@ -10220,7 +10243,7 @@ static int ufshcd_suspend(struct ufs_hba *hba) ret = ufshcd_setup_clocks(hba, false); if (ret) { ufshcd_enable_irq(hba); - return ret; + goto out; } if (ufshcd_is_clkgating_allowed(hba)) { hba->clk_gating.state = CLKS_OFF; @@ -10232,6 +10255,9 @@ static int ufshcd_suspend(struct ufs_hba *hba) /* Put the host controller in low power mode if possible */ ufshcd_hba_vreg_set_lpm(hba); ufshcd_pm_qos_update(hba, false); +out: + if (ret) + ufshcd_update_evt_hist(hba, UFS_EVT_SUSPEND_ERR, (u32)ret); return ret; } diff --git a/drivers/ufs/host/Kconfig b/drivers/ufs/host/Kconfig index 191fbd799ec5bc..48ee7e9b665efc 100644 --- a/drivers/ufs/host/Kconfig +++ b/drivers/ufs/host/Kconfig @@ -72,6 +72,7 @@ config SCSI_UFS_QCOM config SCSI_UFS_MEDIATEK tristate "Mediatek specific hooks to UFS controller platform driver" depends on SCSI_UFSHCD_PLATFORM && ARCH_MEDIATEK + depends on PM depends on RESET_CONTROLLER select PHY_MTK_UFS select RESET_TI_SYSCON diff --git a/drivers/ufs/host/ufs-mediatek.c b/drivers/ufs/host/ufs-mediatek.c index 758a393a9de1a2..3c63adca561d2b 100644 --- a/drivers/ufs/host/ufs-mediatek.c +++ b/drivers/ufs/host/ufs-mediatek.c @@ -2366,13 +2366,17 @@ static void ufs_mtk_remove(struct platform_device *pdev) ufshcd_pltfrm_remove(pdev); } -#ifdef CONFIG_PM_SLEEP static int ufs_mtk_system_suspend(struct device *dev) { struct ufs_hba *hba = dev_get_drvdata(dev); struct arm_smccc_res res; int ret; + if (hba->shutting_down) { + ret = -EBUSY; + goto out; + } + ret = ufshcd_system_suspend(dev); if (ret) goto out; @@ -2408,9 +2412,7 @@ static int ufs_mtk_system_resume(struct device *dev) return ret; } -#endif -#ifdef CONFIG_PM static int ufs_mtk_runtime_suspend(struct device *dev) { struct ufs_hba *hba = dev_get_drvdata(dev); @@ -2449,13 +2451,10 @@ static int ufs_mtk_runtime_resume(struct device *dev) return ufshcd_runtime_resume(dev); } -#endif static const struct dev_pm_ops ufs_mtk_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(ufs_mtk_system_suspend, - ufs_mtk_system_resume) - SET_RUNTIME_PM_OPS(ufs_mtk_runtime_suspend, - ufs_mtk_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(ufs_mtk_system_suspend, ufs_mtk_system_resume) + RUNTIME_PM_OPS(ufs_mtk_runtime_suspend, ufs_mtk_runtime_resume, NULL) .prepare = ufshcd_suspend_prepare, .complete = ufshcd_resume_complete, }; @@ -2465,7 +2464,7 @@ static struct platform_driver ufs_mtk_pltform = { .remove = ufs_mtk_remove, .driver = { .name = "ufshcd-mtk", - .pm = &ufs_mtk_pm_ops, + .pm = pm_ptr(&ufs_mtk_pm_ops), .of_match_table = ufs_mtk_of_match, }, }; diff --git a/drivers/ufs/host/ufs-rockchip.c b/drivers/ufs/host/ufs-rockchip.c index 8754085dd0ccf4..8cecb28cdce411 100644 --- a/drivers/ufs/host/ufs-rockchip.c +++ b/drivers/ufs/host/ufs-rockchip.c @@ -20,9 +20,17 @@ #include "ufshcd-pltfrm.h" #include "ufs-rockchip.h" +static void ufs_rockchip_controller_reset(struct ufs_rockchip_host *host) +{ + reset_control_assert(host->rst); + udelay(1); + reset_control_deassert(host->rst); +} + static int ufs_rockchip_hce_enable_notify(struct ufs_hba *hba, enum ufs_notify_change_status status) { + struct ufs_rockchip_host *host = ufshcd_get_variant(hba); int err = 0; if (status == POST_CHANGE) { @@ -37,6 +45,9 @@ static int ufs_rockchip_hce_enable_notify(struct ufs_hba *hba, return ufshcd_vops_phy_initialization(hba); } + /* PRE_CHANGE */ + ufs_rockchip_controller_reset(host); + return 0; } @@ -156,9 +167,7 @@ static int ufs_rockchip_common_init(struct ufs_hba *hba) return dev_err_probe(dev, PTR_ERR(host->rst), "failed to get reset control\n"); - reset_control_assert(host->rst); - udelay(1); - reset_control_deassert(host->rst); + ufs_rockchip_controller_reset(host); host->ref_out_clk = devm_clk_get_enabled(dev, "ref_out"); if (IS_ERR(host->ref_out_clk)) @@ -282,9 +291,7 @@ static int ufs_rockchip_runtime_resume(struct device *dev) return err; } - reset_control_assert(host->rst); - udelay(1); - reset_control_deassert(host->rst); + ufs_rockchip_controller_reset(host); return ufshcd_runtime_resume(dev); } diff --git a/drivers/uio/uio_fsl_elbc_gpcm.c b/drivers/uio/uio_fsl_elbc_gpcm.c index 81454c3e2484c8..338dd2aaabc871 100644 --- a/drivers/uio/uio_fsl_elbc_gpcm.c +++ b/drivers/uio/uio_fsl_elbc_gpcm.c @@ -384,6 +384,11 @@ static int uio_fsl_elbc_gpcm_probe(struct platform_device *pdev) /* set all UIO data */ info->mem[0].name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%pOFn", node); + if (!info->mem[0].name) { + ret = -ENODEV; + goto out_err3; + } + info->mem[0].addr = res.start; info->mem[0].size = resource_size(&res); info->mem[0].memtype = UIO_MEM_PHYS; @@ -423,6 +428,8 @@ static int uio_fsl_elbc_gpcm_probe(struct platform_device *pdev) out_err2: if (priv->shutdown) priv->shutdown(info, true); + +out_err3: iounmap(info->mem[0].internal_addr); return ret; } diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c index 1243a5cea91b52..f0e32227c0b791 100644 --- a/drivers/usb/cdns3/core.c +++ b/drivers/usb/cdns3/core.c @@ -551,7 +551,7 @@ int cdns_resume(struct cdns *cdns) } } - if (cdns->roles[cdns->role]->resume) + if (!role_changed && cdns->roles[cdns->role]->resume) cdns->roles[cdns->role]->resume(cdns, power_lost); return 0; diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index baf5bc844b6ffa..2bb1ceb9d621a3 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -1040,6 +1040,11 @@ int usb_get_bos_descriptor(struct usb_device *dev) __u8 cap_type; int ret; + if (dev->quirks & USB_QUIRK_NO_BOS) { + dev_dbg(ddev, "skipping BOS descriptor\n"); + return -ENOMSG; + } + bos = kzalloc(sizeof(*bos), GFP_KERNEL); if (!bos) return -ENOMEM; diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index d2b2787be4092e..6138468c67c472 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -2431,7 +2431,7 @@ int cdc_parse_cdc_header(struct usb_cdc_parsed_header *hdr, break; case USB_CDC_MBIM_EXTENDED_TYPE: if (elength < sizeof(struct usb_cdc_mbim_extended_desc)) - break; + goto next_desc; hdr->usb_cdc_mbim_extended_desc = (struct usb_cdc_mbim_extended_desc *)buffer; break; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 47f589c4104a39..c4d85089d19b13 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -450,6 +450,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0c45, 0x7056), .driver_info = USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* Elgato 4K X - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x0fd9, 0x009b), .driver_info = USB_QUIRK_NO_BOS }, + /* Sony Xperia XZ1 Compact (lilac) smartphone in fastboot mode */ { USB_DEVICE(0x0fce, 0x0dde), .driver_info = USB_QUIRK_NO_LPM }, diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index 3f83ecc9fc236e..ef0d7307703473 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -369,11 +369,11 @@ static void dwc2_driver_shutdown(struct platform_device *dev) { struct dwc2_hsotg *hsotg = platform_get_drvdata(dev); - dwc2_disable_global_interrupts(hsotg); - synchronize_irq(hsotg->irq); - - if (hsotg->ll_hw_enabled) + if (hsotg->ll_hw_enabled) { + dwc2_disable_global_interrupts(hsotg); + synchronize_irq(hsotg->irq); dwc2_lowlevel_hw_disable(hsotg); + } } /** @@ -649,9 +649,13 @@ static int dwc2_driver_probe(struct platform_device *dev) static int __maybe_unused dwc2_suspend(struct device *dev) { struct dwc2_hsotg *dwc2 = dev_get_drvdata(dev); - bool is_device_mode = dwc2_is_device_mode(dwc2); + bool is_device_mode; int ret = 0; + if (!dwc2->ll_hw_enabled) + return 0; + + is_device_mode = dwc2_is_device_mode(dwc2); if (is_device_mode) dwc2_hsotg_suspend(dwc2); @@ -728,6 +732,9 @@ static int __maybe_unused dwc2_resume(struct device *dev) struct dwc2_hsotg *dwc2 = dev_get_drvdata(dev); int ret = 0; + if (!dwc2->ll_hw_enabled) + return 0; + if (dwc2->phy_off_for_suspend && dwc2->ll_hw_enabled) { ret = __dwc2_lowlevel_hw_enable(dwc2); if (ret) diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig index 4925d15084f816..bf3e0463513100 100644 --- a/drivers/usb/dwc3/Kconfig +++ b/drivers/usb/dwc3/Kconfig @@ -200,4 +200,15 @@ config USB_DWC3_GENERIC_PLAT the dwc3 child node in the device tree. Say 'Y' or 'M' here if your platform integrates DWC3 in a similar way. +config USB_DWC3_APPLE + tristate "Apple Silicon DWC3 Platform Driver" + depends on OF && ARCH_APPLE + default USB_DWC3 + select USB_ROLE_SWITCH + help + Support Apple Silicon SoCs with DesignWare Core USB3 IP. + The DesignWare Core USB3 IP has to be used in dual-role + mode on these machines. + Say 'Y' or 'M' if you have such device. + endif diff --git a/drivers/usb/dwc3/Makefile b/drivers/usb/dwc3/Makefile index 96469e48ff9d18..89d46ab5006856 100644 --- a/drivers/usb/dwc3/Makefile +++ b/drivers/usb/dwc3/Makefile @@ -43,6 +43,7 @@ endif ## obj-$(CONFIG_USB_DWC3_AM62) += dwc3-am62.o +obj-$(CONFIG_USB_DWC3_APPLE) += dwc3-apple.o obj-$(CONFIG_USB_DWC3_OMAP) += dwc3-omap.o obj-$(CONFIG_USB_DWC3_EXYNOS) += dwc3-exynos.o obj-$(CONFIG_USB_DWC3_PCI) += dwc3-pci.o diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index c2ce2f5e60a19c..a103898d059439 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -133,6 +133,7 @@ void dwc3_enable_susphy(struct dwc3 *dwc, bool enable) dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(i), reg); } } +EXPORT_SYMBOL_GPL(dwc3_enable_susphy); void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy) { @@ -159,6 +160,7 @@ void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy) dwc->current_dr_role = mode; trace_dwc3_set_prtcap(mode); } +EXPORT_SYMBOL_GPL(dwc3_set_prtcap); static void __dwc3_set_mode(struct work_struct *work) { @@ -976,7 +978,7 @@ static void dwc3_clk_disable(struct dwc3 *dwc) clk_disable_unprepare(dwc->bus_clk); } -static void dwc3_core_exit(struct dwc3 *dwc) +void dwc3_core_exit(struct dwc3 *dwc) { dwc3_event_buffers_cleanup(dwc); dwc3_phy_power_off(dwc); @@ -984,6 +986,7 @@ static void dwc3_core_exit(struct dwc3 *dwc) dwc3_clk_disable(dwc); reset_control_assert(dwc->reset); } +EXPORT_SYMBOL_GPL(dwc3_core_exit); static bool dwc3_core_is_valid(struct dwc3 *dwc) { @@ -991,6 +994,8 @@ static bool dwc3_core_is_valid(struct dwc3 *dwc) reg = dwc3_readl(dwc->regs, DWC3_GSNPSID); dwc->ip = DWC3_GSNPS_ID(reg); + if (dwc->ip == DWC4_IP) + dwc->ip = DWC32_IP; /* This should read as U3 followed by revision number */ if (DWC3_IP_IS(DWC3)) { @@ -1329,7 +1334,7 @@ static void dwc3_config_threshold(struct dwc3 *dwc) * * Returns 0 on success otherwise negative errno. */ -static int dwc3_core_init(struct dwc3 *dwc) +int dwc3_core_init(struct dwc3 *dwc) { unsigned int hw_mode; u32 reg; @@ -1529,6 +1534,7 @@ static int dwc3_core_init(struct dwc3 *dwc) return ret; } +EXPORT_SYMBOL_GPL(dwc3_core_init); static int dwc3_core_get_phy(struct dwc3 *dwc) { @@ -1667,7 +1673,8 @@ static void dwc3_core_exit_mode(struct dwc3 *dwc) dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, true); } -static void dwc3_get_software_properties(struct dwc3 *dwc) +static void dwc3_get_software_properties(struct dwc3 *dwc, + const struct dwc3_properties *properties) { struct device *tmpdev; u16 gsbuscfg0_reqinfo; @@ -1675,6 +1682,12 @@ static void dwc3_get_software_properties(struct dwc3 *dwc) dwc->gsbuscfg0_reqinfo = DWC3_GSBUSCFG0_REQINFO_UNSPECIFIED; + if (properties->gsbuscfg0_reqinfo != + DWC3_GSBUSCFG0_REQINFO_UNSPECIFIED) { + dwc->gsbuscfg0_reqinfo = properties->gsbuscfg0_reqinfo; + return; + } + /* * Iterate over all parent nodes for finding swnode properties * and non-DT (non-ABI) properties. @@ -2207,7 +2220,7 @@ int dwc3_core_probe(const struct dwc3_probe_data *data) dwc3_get_properties(dwc); - dwc3_get_software_properties(dwc); + dwc3_get_software_properties(dwc, &data->properties); dwc->usb_psy = dwc3_get_usb_power_supply(dwc); if (IS_ERR(dwc->usb_psy)) @@ -2300,9 +2313,11 @@ int dwc3_core_probe(const struct dwc3_probe_data *data) dwc3_check_params(dwc); dwc3_debugfs_init(dwc); - ret = dwc3_core_init_mode(dwc); - if (ret) - goto err_exit_debugfs; + if (!data->skip_core_init_mode) { + ret = dwc3_core_init_mode(dwc); + if (ret) + goto err_exit_debugfs; + } pm_runtime_put(dev); @@ -2357,6 +2372,7 @@ static int dwc3_probe(struct platform_device *pdev) probe_data.dwc = dwc; probe_data.res = res; + probe_data.properties = DWC3_DEFAULT_PROPERTIES; return dwc3_core_probe(&probe_data); } diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index a5fc92c4ffa3bc..45757169b672fd 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1265,6 +1265,7 @@ struct dwc3 { #define DWC3_IP 0x5533 #define DWC31_IP 0x3331 #define DWC32_IP 0x3332 +#define DWC4_IP 0x3430 u32 revision; diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c index 4c91240eb4299a..589bbeb2745419 100644 --- a/drivers/usb/dwc3/drd.c +++ b/drivers/usb/dwc3/drd.c @@ -515,6 +515,7 @@ static int dwc3_setup_role_switch(struct dwc3 *dwc) dwc3_role_switch.set = dwc3_usb_role_switch_set; dwc3_role_switch.get = dwc3_usb_role_switch_get; dwc3_role_switch.driver_data = dwc; + dwc3_role_switch.allow_userspace_control = true; dwc->role_sw = usb_role_switch_register(dwc->dev, &dwc3_role_switch); if (IS_ERR(dwc->role_sw)) return PTR_ERR(dwc->role_sw); diff --git a/drivers/usb/dwc3/dwc3-apple.c b/drivers/usb/dwc3/dwc3-apple.c new file mode 100644 index 00000000000000..40c3ccfddb6702 --- /dev/null +++ b/drivers/usb/dwc3/dwc3-apple.c @@ -0,0 +1,523 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Apple Silicon DWC3 Glue driver + * Copyright (C) The Asahi Linux Contributors + * + * Based on: + * - dwc3-qcom.c Copyright (c) 2018, The Linux Foundation. All rights reserved. + * - dwc3-of-simple.c Copyright (c) 2015 Texas Instruments Incorporated - https://www.ti.com + */ + +#include +#include +#include +#include +#include + +#include "glue.h" + +/* + * This platform requires a very specific sequence of operations to bring up dwc3 and its USB3 PHY: + * + * 1) The PHY itself has to be brought up; for this we need to know the mode (USB3, + * USB3+DisplayPort, USB4, etc) and the lane orientation. This happens through typec_mux_set. + * 2) DWC3 has to be brought up but we must not touch the gadget area or start xhci yet. + * 3) The PHY bring-up has to be finalized and dwc3's PIPE interface has to be switched to the + * USB3 PHY, this is done inside phy_set_mode. + * 4) We can now initialize xhci or gadget mode. + * + * We can switch 1 and 2 but 3 has to happen after (1 and 2) and 4 has to happen after 3. + * + * And then to bring this all down again: + * + * 1) DWC3 has to exit host or gadget mode and must no longer touch those registers + * 2) The PHY has to switch dwc3's PIPE interface back to the dummy backend + * 3) The PHY itself can be shut down, this happens from typec_mux_set + * + * We also can't transition the PHY from one mode to another while dwc3 is up and running (this is + * slightly wrong, some transitions are possible, others aren't but because we have no documentation + * for this I'd rather play it safe). + * + * After both the PHY and dwc3 are initialized we will only ever see a single "new device connected" + * event. If we just keep them running only the first device plugged in will ever work. XHCI's port + * status register actually does show the correct state but no interrupt ever comes in. In gadget + * mode we don't even get a USBDisconnected event and everything looks like there's still something + * connected on the other end. + * This can be partially explained because the USB2 D+/D- lines are connected through a stateful + * eUSB2 repeater which in turn is controlled by a variant of the TI TPS6598x USB PD chip which + * resets the repeater out-of-band everytime the CC lines are (dis)connected. This then requires a + * PHY reset to make sure the PHY and the eUSB2 repeater state are synchronized again. + * + * And to make this all extra fun: If we get the order of some of this wrong either the port is just + * broken until a phy+dwc3 reset, or it's broken until a full SoC reset (likely because we can't + * reset some parts of the PHY), or some watchdog kicks in after a few seconds and forces a full SoC + * reset (mostly seen this with USB4/Thunderbolt but there's clearly some watchdog that hates + * invalid states). + * + * Hence there's really no good way to keep dwc3 fully up and running after we disconnect a cable + * because then we can't shut down the PHY anymore. And if we kept the PHY running in whatever mode + * it was until the next cable is connected we'd need to tear it all down and bring it back up again + * anyway to detect and use the next device. + * + * Instead, we just shut down everything when a cable is disconnected and transition to + * DWC3_APPLE_NO_CABLE. + * During initial probe we don't have any information about the connected cable and can't bring up + * the PHY properly and thus also can't fully bring up dwc3. Instead, we just keep everything off + * and defer the first dwc3 probe until we get the first cable connected event. Until then we stay + * in DWC3_APPLE_PROBE_PENDING. + * Once a cable is connected we then keep track of the controller mode here by transitioning to + * DWC3_APPLE_HOST or DWC3_APPLE_DEVICE. + */ +enum dwc3_apple_state { + DWC3_APPLE_PROBE_PENDING, /* Before first cable connection, dwc3_core_probe not called */ + DWC3_APPLE_NO_CABLE, /* No cable connected, dwc3 suspended after dwc3_core_exit */ + DWC3_APPLE_HOST, /* Cable connected, dwc3 in host mode */ + DWC3_APPLE_DEVICE, /* Cable connected, dwc3 in device mode */ +}; + +/** + * struct dwc3_apple - Apple-specific DWC3 USB controller + * @dwc: Core DWC3 structure + * @dev: Pointer to the device structure + * @mmio_resource: Resource to be passed to dwc3_core_probe + * @apple_regs: Apple-specific DWC3 registers + * @reset: Reset control + * @role_sw: USB role switch + * @lock: Mutex for synchronizing access + * @state: Current state of the controller, see documentation for the enum for details + */ +struct dwc3_apple { + struct dwc3 dwc; + + struct device *dev; + struct resource *mmio_resource; + void __iomem *apple_regs; + + struct reset_control *reset; + struct usb_role_switch *role_sw; + + struct mutex lock; + + enum dwc3_apple_state state; +}; + +#define to_dwc3_apple(d) container_of((d), struct dwc3_apple, dwc) + +/* + * Apple Silicon dwc3 vendor-specific registers + * + * These registers were identified by tracing XNU's memory access patterns and correlating them with + * debug output over serial to determine their names. We don't exactly know what these do but + * without these USB3 devices sometimes don't work. + */ +#define APPLE_DWC3_REGS_START 0xcd00 +#define APPLE_DWC3_REGS_END 0xcdff + +#define APPLE_DWC3_CIO_LFPS_OFFSET 0xcd38 +#define APPLE_DWC3_CIO_LFPS_OFFSET_VALUE 0xf800f80 + +#define APPLE_DWC3_CIO_BW_NGT_OFFSET 0xcd3c +#define APPLE_DWC3_CIO_BW_NGT_OFFSET_VALUE 0xfc00fc0 + +#define APPLE_DWC3_CIO_LINK_TIMER 0xcd40 +#define APPLE_DWC3_CIO_PENDING_HP_TIMER GENMASK(23, 16) +#define APPLE_DWC3_CIO_PENDING_HP_TIMER_VALUE 0x14 +#define APPLE_DWC3_CIO_PM_LC_TIMER GENMASK(15, 8) +#define APPLE_DWC3_CIO_PM_LC_TIMER_VALUE 0xa +#define APPLE_DWC3_CIO_PM_ENTRY_TIMER GENMASK(7, 0) +#define APPLE_DWC3_CIO_PM_ENTRY_TIMER_VALUE 0x10 + +static inline void dwc3_apple_writel(struct dwc3_apple *appledwc, u32 offset, u32 value) +{ + writel(value, appledwc->apple_regs + offset - APPLE_DWC3_REGS_START); +} + +static inline u32 dwc3_apple_readl(struct dwc3_apple *appledwc, u32 offset) +{ + return readl(appledwc->apple_regs + offset - APPLE_DWC3_REGS_START); +} + +static inline void dwc3_apple_mask(struct dwc3_apple *appledwc, u32 offset, u32 mask, u32 value) +{ + u32 reg; + + reg = dwc3_apple_readl(appledwc, offset); + reg &= ~mask; + reg |= value; + dwc3_apple_writel(appledwc, offset, reg); +} + +static void dwc3_apple_setup_cio(struct dwc3_apple *appledwc) +{ + dwc3_apple_writel(appledwc, APPLE_DWC3_CIO_LFPS_OFFSET, APPLE_DWC3_CIO_LFPS_OFFSET_VALUE); + dwc3_apple_writel(appledwc, APPLE_DWC3_CIO_BW_NGT_OFFSET, + APPLE_DWC3_CIO_BW_NGT_OFFSET_VALUE); + dwc3_apple_mask(appledwc, APPLE_DWC3_CIO_LINK_TIMER, APPLE_DWC3_CIO_PENDING_HP_TIMER, + FIELD_PREP(APPLE_DWC3_CIO_PENDING_HP_TIMER, + APPLE_DWC3_CIO_PENDING_HP_TIMER_VALUE)); + dwc3_apple_mask(appledwc, APPLE_DWC3_CIO_LINK_TIMER, APPLE_DWC3_CIO_PM_LC_TIMER, + FIELD_PREP(APPLE_DWC3_CIO_PM_LC_TIMER, APPLE_DWC3_CIO_PM_LC_TIMER_VALUE)); + dwc3_apple_mask(appledwc, APPLE_DWC3_CIO_LINK_TIMER, APPLE_DWC3_CIO_PM_ENTRY_TIMER, + FIELD_PREP(APPLE_DWC3_CIO_PM_ENTRY_TIMER, + APPLE_DWC3_CIO_PM_ENTRY_TIMER_VALUE)); +} + +static void dwc3_apple_set_ptrcap(struct dwc3_apple *appledwc, u32 mode) +{ + guard(spinlock_irqsave)(&appledwc->dwc.lock); + dwc3_set_prtcap(&appledwc->dwc, mode, false); +} + +static int dwc3_apple_core_probe(struct dwc3_apple *appledwc) +{ + struct dwc3_probe_data probe_data = {}; + int ret; + + lockdep_assert_held(&appledwc->lock); + WARN_ON_ONCE(appledwc->state != DWC3_APPLE_PROBE_PENDING); + + appledwc->dwc.dev = appledwc->dev; + probe_data.dwc = &appledwc->dwc; + probe_data.res = appledwc->mmio_resource; + probe_data.ignore_clocks_and_resets = true; + probe_data.skip_core_init_mode = true; + probe_data.properties = DWC3_DEFAULT_PROPERTIES; + + ret = dwc3_core_probe(&probe_data); + if (ret) + return ret; + + appledwc->state = DWC3_APPLE_NO_CABLE; + return 0; +} + +static int dwc3_apple_core_init(struct dwc3_apple *appledwc) +{ + int ret; + + lockdep_assert_held(&appledwc->lock); + + switch (appledwc->state) { + case DWC3_APPLE_PROBE_PENDING: + ret = dwc3_apple_core_probe(appledwc); + if (ret) + dev_err(appledwc->dev, "Failed to probe DWC3 Core, err=%d\n", ret); + break; + case DWC3_APPLE_NO_CABLE: + ret = dwc3_core_init(&appledwc->dwc); + if (ret) + dev_err(appledwc->dev, "Failed to initialize DWC3 Core, err=%d\n", ret); + break; + default: + /* Unreachable unless there's a bug in this driver */ + WARN_ON_ONCE(1); + ret = -EINVAL; + break; + } + + return ret; +} + +static int dwc3_apple_init(struct dwc3_apple *appledwc, enum dwc3_apple_state state) +{ + int ret, ret_reset; + + lockdep_assert_held(&appledwc->lock); + + /* + * The USB2 PHY on this platform must be configured for host or device mode while it is + * still powered off and before dwc3 tries to access it. Otherwise, the new configuration + * will sometimes only take affect after the *next* time dwc3 is brought up which causes + * the connected device to just not work. + * The USB3 PHY must be configured later after dwc3 has already been initialized. + */ + switch (state) { + case DWC3_APPLE_HOST: + phy_set_mode(appledwc->dwc.usb2_generic_phy[0], PHY_MODE_USB_HOST); + break; + case DWC3_APPLE_DEVICE: + phy_set_mode(appledwc->dwc.usb2_generic_phy[0], PHY_MODE_USB_DEVICE); + break; + default: + /* Unreachable unless there's a bug in this driver */ + return -EINVAL; + } + + ret = reset_control_deassert(appledwc->reset); + if (ret) { + dev_err(appledwc->dev, "Failed to deassert reset, err=%d\n", ret); + return ret; + } + + ret = dwc3_apple_core_init(appledwc); + if (ret) + goto reset_assert; + + /* + * Now that the core is initialized and already went through dwc3_core_soft_reset we can + * configure some unknown Apple-specific settings and then bring up xhci or gadget mode. + */ + dwc3_apple_setup_cio(appledwc); + + switch (state) { + case DWC3_APPLE_HOST: + appledwc->dwc.dr_mode = USB_DR_MODE_HOST; + dwc3_apple_set_ptrcap(appledwc, DWC3_GCTL_PRTCAP_HOST); + /* + * This platform requires SUSPHY to be enabled here already in order to properly + * configure the PHY and switch dwc3's PIPE interface to USB3 PHY. The USB2 PHY + * has already been configured to the correct mode earlier. + */ + dwc3_enable_susphy(&appledwc->dwc, true); + phy_set_mode(appledwc->dwc.usb3_generic_phy[0], PHY_MODE_USB_HOST); + ret = dwc3_host_init(&appledwc->dwc); + if (ret) { + dev_err(appledwc->dev, "Failed to initialize host, ret=%d\n", ret); + goto core_exit; + } + + break; + case DWC3_APPLE_DEVICE: + appledwc->dwc.dr_mode = USB_DR_MODE_PERIPHERAL; + dwc3_apple_set_ptrcap(appledwc, DWC3_GCTL_PRTCAP_DEVICE); + /* + * This platform requires SUSPHY to be enabled here already in order to properly + * configure the PHY and switch dwc3's PIPE interface to USB3 PHY. The USB2 PHY + * has already been configured to the correct mode earlier. + */ + dwc3_enable_susphy(&appledwc->dwc, true); + phy_set_mode(appledwc->dwc.usb3_generic_phy[0], PHY_MODE_USB_DEVICE); + ret = dwc3_gadget_init(&appledwc->dwc); + if (ret) { + dev_err(appledwc->dev, "Failed to initialize gadget, ret=%d\n", ret); + goto core_exit; + } + break; + default: + /* Unreachable unless there's a bug in this driver */ + WARN_ON_ONCE(1); + ret = -EINVAL; + goto core_exit; + } + + appledwc->state = state; + return 0; + +core_exit: + dwc3_core_exit(&appledwc->dwc); +reset_assert: + ret_reset = reset_control_assert(appledwc->reset); + if (ret_reset) + dev_warn(appledwc->dev, "Failed to assert reset, err=%d\n", ret_reset); + + return ret; +} + +static int dwc3_apple_exit(struct dwc3_apple *appledwc) +{ + int ret = 0; + + lockdep_assert_held(&appledwc->lock); + + switch (appledwc->state) { + case DWC3_APPLE_PROBE_PENDING: + case DWC3_APPLE_NO_CABLE: + /* Nothing to do if we're already off */ + return 0; + case DWC3_APPLE_DEVICE: + dwc3_gadget_exit(&appledwc->dwc); + break; + case DWC3_APPLE_HOST: + dwc3_host_exit(&appledwc->dwc); + break; + } + + /* + * This platform requires SUSPHY to be enabled in order to properly power down the PHY + * and switch dwc3's PIPE interface back to a dummy PHY (i.e. no USB3 support and USB2 via + * a different PHY connected through ULPI). + */ + dwc3_enable_susphy(&appledwc->dwc, true); + dwc3_core_exit(&appledwc->dwc); + appledwc->state = DWC3_APPLE_NO_CABLE; + + ret = reset_control_assert(appledwc->reset); + if (ret) { + dev_err(appledwc->dev, "Failed to assert reset, err=%d\n", ret); + return ret; + } + + return 0; +} + +static int dwc3_usb_role_switch_set(struct usb_role_switch *sw, enum usb_role role) +{ + struct dwc3_apple *appledwc = usb_role_switch_get_drvdata(sw); + int ret; + + guard(mutex)(&appledwc->lock); + + /* + * Skip role switches if appledwc is already in the desired state. The + * USB-C port controller on M2 and M1/M2 Pro/Max/Ultra devices issues + * additional interrupts which results in usb_role_switch_set_role() + * calls with the current role. + * Ignore those calls here to ensure the USB-C port controller and + * appledwc are in a consistent state. + * This matches the behaviour in __dwc3_set_mode(). + * Do no handle USB_ROLE_NONE for DWC3_APPLE_NO_CABLE and + * DWC3_APPLE_PROBE_PENDING since that is no-op anyway. + */ + if (appledwc->state == DWC3_APPLE_HOST && role == USB_ROLE_HOST) + return 0; + if (appledwc->state == DWC3_APPLE_DEVICE && role == USB_ROLE_DEVICE) + return 0; + + /* + * We need to tear all of dwc3 down and re-initialize it every time a cable is + * connected or disconnected or when the mode changes. See the documentation for enum + * dwc3_apple_state for details. + */ + ret = dwc3_apple_exit(appledwc); + if (ret) + return ret; + + switch (role) { + case USB_ROLE_NONE: + /* Nothing to do if no cable is connected */ + return 0; + case USB_ROLE_HOST: + return dwc3_apple_init(appledwc, DWC3_APPLE_HOST); + case USB_ROLE_DEVICE: + return dwc3_apple_init(appledwc, DWC3_APPLE_DEVICE); + default: + dev_err(appledwc->dev, "Invalid target role: %d\n", role); + return -EINVAL; + } +} + +static enum usb_role dwc3_usb_role_switch_get(struct usb_role_switch *sw) +{ + struct dwc3_apple *appledwc = usb_role_switch_get_drvdata(sw); + + guard(mutex)(&appledwc->lock); + + switch (appledwc->state) { + case DWC3_APPLE_HOST: + return USB_ROLE_HOST; + case DWC3_APPLE_DEVICE: + return USB_ROLE_DEVICE; + case DWC3_APPLE_NO_CABLE: + case DWC3_APPLE_PROBE_PENDING: + return USB_ROLE_NONE; + default: + /* Unreachable unless there's a bug in this driver */ + dev_err(appledwc->dev, "Invalid internal state: %d\n", appledwc->state); + return USB_ROLE_NONE; + } +} + +static int dwc3_apple_setup_role_switch(struct dwc3_apple *appledwc) +{ + struct usb_role_switch_desc dwc3_role_switch = { NULL }; + + dwc3_role_switch.fwnode = dev_fwnode(appledwc->dev); + dwc3_role_switch.set = dwc3_usb_role_switch_set; + dwc3_role_switch.get = dwc3_usb_role_switch_get; + dwc3_role_switch.driver_data = appledwc; + appledwc->role_sw = usb_role_switch_register(appledwc->dev, &dwc3_role_switch); + if (IS_ERR(appledwc->role_sw)) + return PTR_ERR(appledwc->role_sw); + + return 0; +} + +static int dwc3_apple_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dwc3_apple *appledwc; + int ret; + + appledwc = devm_kzalloc(&pdev->dev, sizeof(*appledwc), GFP_KERNEL); + if (!appledwc) + return -ENOMEM; + + appledwc->dev = &pdev->dev; + mutex_init(&appledwc->lock); + + appledwc->reset = devm_reset_control_get_exclusive(dev, NULL); + if (IS_ERR(appledwc->reset)) + return dev_err_probe(&pdev->dev, PTR_ERR(appledwc->reset), + "Failed to get reset control\n"); + + ret = reset_control_assert(appledwc->reset); + if (ret) { + dev_err(&pdev->dev, "Failed to assert reset, err=%d\n", ret); + return ret; + } + + appledwc->mmio_resource = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dwc3-core"); + if (!appledwc->mmio_resource) { + dev_err(dev, "Failed to get DWC3 MMIO\n"); + return -EINVAL; + } + + appledwc->apple_regs = devm_platform_ioremap_resource_byname(pdev, "dwc3-apple"); + if (IS_ERR(appledwc->apple_regs)) + return dev_err_probe(dev, PTR_ERR(appledwc->apple_regs), + "Failed to map Apple-specific MMIO\n"); + + /* + * On this platform, DWC3 can only be brought up after parts of the PHY have been + * initialized with knowledge of the target mode and cable orientation from typec_set_mux. + * Since this has not happened here we cannot setup DWC3 yet and instead defer this until + * the first cable is connected. See the documentation for enum dwc3_apple_state for + * details. + */ + appledwc->state = DWC3_APPLE_PROBE_PENDING; + ret = dwc3_apple_setup_role_switch(appledwc); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to setup role switch\n"); + + return 0; +} + +static void dwc3_apple_remove(struct platform_device *pdev) +{ + struct dwc3 *dwc = platform_get_drvdata(pdev); + struct dwc3_apple *appledwc = to_dwc3_apple(dwc); + + guard(mutex)(&appledwc->lock); + + usb_role_switch_unregister(appledwc->role_sw); + + /* + * If we're still in DWC3_APPLE_PROBE_PENDING we never got any cable connected event and + * dwc3_core_probe was never called and there's hence no need to call dwc3_core_remove. + * dwc3_apple_exit can be called unconditionally because it checks the state itself. + */ + dwc3_apple_exit(appledwc); + if (appledwc->state != DWC3_APPLE_PROBE_PENDING) + dwc3_core_remove(&appledwc->dwc); +} + +static const struct of_device_id dwc3_apple_of_match[] = { + { .compatible = "apple,t8103-dwc3" }, + {} +}; +MODULE_DEVICE_TABLE(of, dwc3_apple_of_match); + +static struct platform_driver dwc3_apple_driver = { + .probe = dwc3_apple_probe, + .remove = dwc3_apple_remove, + .driver = { + .name = "dwc3-apple", + .of_match_table = dwc3_apple_of_match, + }, +}; + +module_platform_driver(dwc3_apple_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Sven Peter "); +MODULE_DESCRIPTION("DesignWare DWC3 Apple Silicon Glue Driver"); diff --git a/drivers/usb/dwc3/dwc3-generic-plat.c b/drivers/usb/dwc3/dwc3-generic-plat.c index f8ad79c08c4e5c..e869c7de7bc848 100644 --- a/drivers/usb/dwc3/dwc3-generic-plat.c +++ b/drivers/usb/dwc3/dwc3-generic-plat.c @@ -29,6 +29,7 @@ static void dwc3_generic_reset_control_assert(void *data) static int dwc3_generic_probe(struct platform_device *pdev) { + const struct dwc3_properties *properties; struct dwc3_probe_data probe_data = {}; struct device *dev = &pdev->dev; struct dwc3_generic *dwc3g; @@ -75,6 +76,13 @@ static int dwc3_generic_probe(struct platform_device *pdev) probe_data.dwc = &dwc3g->dwc; probe_data.res = res; probe_data.ignore_clocks_and_resets = true; + + properties = of_device_get_match_data(dev); + if (properties) + probe_data.properties = *properties; + else + probe_data.properties = DWC3_DEFAULT_PROPERTIES; + ret = dwc3_core_probe(&probe_data); if (ret) return dev_err_probe(dev, ret, "failed to register DWC3 Core\n"); @@ -142,8 +150,13 @@ static const struct dev_pm_ops dwc3_generic_dev_pm_ops = { dwc3_generic_runtime_idle) }; +static const struct dwc3_properties fsl_ls1028_dwc3 = { + .gsbuscfg0_reqinfo = 0x2222, +}; + static const struct of_device_id dwc3_generic_of_match[] = { { .compatible = "spacemit,k1-dwc3", }, + { .compatible = "fsl,ls1028a-dwc3", &fsl_ls1028_dwc3}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, dwc3_generic_of_match); diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c index a4954a21be9301..c116143335d9f9 100644 --- a/drivers/usb/dwc3/dwc3-of-simple.c +++ b/drivers/usb/dwc3/dwc3-of-simple.c @@ -70,11 +70,11 @@ static int dwc3_of_simple_probe(struct platform_device *pdev) simple->num_clocks = ret; ret = clk_bulk_prepare_enable(simple->num_clocks, simple->clks); if (ret) - goto err_resetc_assert; + goto err_clk_put_all; ret = of_platform_populate(np, NULL, NULL, dev); if (ret) - goto err_clk_put; + goto err_clk_disable; pm_runtime_set_active(dev); pm_runtime_enable(dev); @@ -82,8 +82,9 @@ static int dwc3_of_simple_probe(struct platform_device *pdev) return 0; -err_clk_put: +err_clk_disable: clk_bulk_disable_unprepare(simple->num_clocks, simple->clks); +err_clk_put_all: clk_bulk_put_all(simple->num_clocks, simple->clks); err_resetc_assert: diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index ded2ca86670c0b..9ac75547820d97 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -704,6 +704,7 @@ static int dwc3_qcom_probe(struct platform_device *pdev) probe_data.dwc = &qcom->dwc; probe_data.res = &res; probe_data.ignore_clocks_and_resets = true; + probe_data.properties = DWC3_DEFAULT_PROPERTIES; ret = dwc3_core_probe(&probe_data); if (ret) { ret = dev_err_probe(dev, ret, "failed to register DWC3 Core\n"); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 5e4997f974ddde..5544e25a78536d 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4817,6 +4817,7 @@ int dwc3_gadget_init(struct dwc3 *dwc) err0: return ret; } +EXPORT_SYMBOL_GPL(dwc3_gadget_init); /* -------------------------------------------------------------------------- */ @@ -4825,7 +4826,7 @@ void dwc3_gadget_exit(struct dwc3 *dwc) if (!dwc->gadget) return; - dwc3_enable_susphy(dwc, false); + dwc3_enable_susphy(dwc, true); usb_del_gadget(dwc->gadget); dwc3_gadget_free_endpoints(dwc); usb_put_gadget(dwc->gadget); @@ -4835,6 +4836,7 @@ void dwc3_gadget_exit(struct dwc3 *dwc) dma_free_coherent(dwc->sysdev, sizeof(*dwc->ep0_trb) * 2, dwc->ep0_trb, dwc->ep0_trb_addr); } +EXPORT_SYMBOL_GPL(dwc3_gadget_exit); int dwc3_gadget_suspend(struct dwc3 *dwc) { diff --git a/drivers/usb/dwc3/glue.h b/drivers/usb/dwc3/glue.h index 2efd00e763be4f..df86e14cb706ca 100644 --- a/drivers/usb/dwc3/glue.h +++ b/drivers/usb/dwc3/glue.h @@ -9,22 +9,66 @@ #include #include "core.h" +/** + * dwc3_properties: DWC3 core properties + * @gsbuscfg0_reqinfo: Value to be programmed in the GSBUSCFG0.REQINFO field + */ +struct dwc3_properties { + u32 gsbuscfg0_reqinfo; +}; + +#define DWC3_DEFAULT_PROPERTIES ((struct dwc3_properties){ \ + .gsbuscfg0_reqinfo = DWC3_GSBUSCFG0_REQINFO_UNSPECIFIED, \ + }) + /** * dwc3_probe_data: Initialization parameters passed to dwc3_core_probe() * @dwc: Reference to dwc3 context structure * @res: resource for the DWC3 core mmio region * @ignore_clocks_and_resets: clocks and resets defined for the device should * be ignored by the DWC3 core, as they are managed by the glue + * @skip_core_init_mode: Skip the finial initialization of the target mode, as + * it must be managed by the glue + * @properties: dwc3 software manage properties */ struct dwc3_probe_data { struct dwc3 *dwc; struct resource *res; bool ignore_clocks_and_resets; + bool skip_core_init_mode; + struct dwc3_properties properties; }; +/** + * dwc3_core_probe - Initialize the core dwc3 driver + * @data: Initialization and configuration parameters for the controller + * + * Initializes the DesignWare USB3 core driver by setting up resources, + * registering interrupts, performing hardware setup, and preparing + * the controller for operation in the appropriate mode (host, gadget, + * or OTG). This is the main initialization function called by glue + * layer drivers to set up the core controller. + * + * Return: 0 on success, negative error code on failure + */ int dwc3_core_probe(const struct dwc3_probe_data *data); + +/** + * dwc3_core_remove - Deinitialize and remove the core dwc3 driver + * @dwc: Pointer to DWC3 controller context + * + * Cleans up resources and disables the dwc3 core driver. This should be called + * during driver removal or when the glue layer needs to shut down the + * controller completely. + */ void dwc3_core_remove(struct dwc3 *dwc); +/* + * The following callbacks are provided for glue drivers to call from their + * own pm callbacks provided in struct dev_pm_ops. Glue drivers can perform + * platform-specific work before or after calling these functions and delegate + * the core suspend/resume operations to the core driver. + */ int dwc3_runtime_suspend(struct dwc3 *dwc); int dwc3_runtime_resume(struct dwc3 *dwc); int dwc3_runtime_idle(struct dwc3 *dwc); @@ -33,4 +77,117 @@ int dwc3_pm_resume(struct dwc3 *dwc); void dwc3_pm_complete(struct dwc3 *dwc); int dwc3_pm_prepare(struct dwc3 *dwc); + +/* All of the following functions must only be used with skip_core_init_mode */ + +/** + * dwc3_core_init - Initialize DWC3 core hardware + * @dwc: Pointer to DWC3 controller context + * + * Configures and initializes the core hardware, usually done by dwc3_core_probe. + * This function is provided for platforms that use skip_core_init_mode and need + * to finalize the core initialization after some platform-specific setup. + * It must only be called when using skip_core_init_mode and before + * dwc3_host_init or dwc3_gadget_init. + * + * Return: 0 on success, negative error code on failure + */ +int dwc3_core_init(struct dwc3 *dwc); + +/** + * dwc3_core_exit - Shut down DWC3 core hardware + * @dwc: Pointer to DWC3 controller context + * + * Disables and cleans up the core hardware state. This is usually handled + * internally by dwc3 and must only be called when using skip_core_init_mode + * and only after dwc3_core_init. Afterwards, dwc3_core_init may be called + * again. + */ +void dwc3_core_exit(struct dwc3 *dwc); + +/** + * dwc3_host_init - Initialize host mode operation + * @dwc: Pointer to DWC3 controller context + * + * Initializes the controller for USB host mode operation, usually done by + * dwc3_core_probe or from within the dwc3 USB role switch callback. + * This function is provided for platforms that use skip_core_init_mode and need + * to finalize the host initialization after some platform-specific setup. + * It must not be called before dwc3_core_init or when skip_core_init_mode is + * not used. It must also not be called when gadget or host mode has already + * been initialized. + * + * Return: 0 on success, negative error code on failure + */ +int dwc3_host_init(struct dwc3 *dwc); + +/** + * dwc3_host_exit - Shut down host mode operation + * @dwc: Pointer to DWC3 controller context + * + * Disables and cleans up host mode resources, usually done by + * the dwc3 USB role switch callback before switching controller mode. + * It must only be called when skip_core_init_mode is used and only after + * dwc3_host_init. + */ +void dwc3_host_exit(struct dwc3 *dwc); + +/** + * dwc3_gadget_init - Initialize gadget mode operation + * @dwc: Pointer to DWC3 controller context + * + * Initializes the controller for USB gadget mode operation, usually done by + * dwc3_core_probe or from within the dwc3 USB role switch callback. This + * function is provided for platforms that use skip_core_init_mode and need to + * finalize the gadget initialization after some platform-specific setup. + * It must not be called before dwc3_core_init or when skip_core_init_mode is + * not used. It must also not be called when gadget or host mode has already + * been initialized. + * + * Return: 0 on success, negative error code on failure + */ +int dwc3_gadget_init(struct dwc3 *dwc); + +/** + * dwc3_gadget_exit - Shut down gadget mode operation + * @dwc: Pointer to DWC3 controller context + * + * Disables and cleans up gadget mode resources, usually done by + * the dwc3 USB role switch callback before switching controller mode. + * It must only be called when skip_core_init_mode is used and only after + * dwc3_gadget_init. + */ +void dwc3_gadget_exit(struct dwc3 *dwc); + +/** + * dwc3_enable_susphy - Control SUSPHY status for all USB ports + * @dwc: Pointer to DWC3 controller context + * @enable: True to enable SUSPHY, false to disable + * + * Enables or disables the USB3 PHY SUSPEND and USB2 PHY SUSPHY feature for + * all available ports. + * This is usually handled by the dwc3 core code and should only be used + * when skip_core_init_mode is used and the glue layer needs to manage SUSPHY + * settings itself, e.g., due to platform-specific requirements during mode + * switches. + */ +void dwc3_enable_susphy(struct dwc3 *dwc, bool enable); + +/** + * dwc3_set_prtcap - Set the USB controller PRTCAP mode + * @dwc: Pointer to DWC3 controller context + * @mode: Target mode, must be one of DWC3_GCTL_PRTCAP_{HOST,DEVICE,OTG} + * @ignore_susphy: If true, skip disabling the SUSPHY and keep the current state + * + * Updates PRTCAP of the controller and current_dr_role inside the dwc3 + * structure. For DRD controllers, this also disables SUSPHY unless explicitly + * told to skip via the ignore_susphy parameter. + * + * This is usually handled by the dwc3 core code and should only be used + * when skip_core_init_mode is used and the glue layer needs to manage mode + * transitions itself due to platform-specific requirements. It must be called + * with the correct mode before calling dwc3_host_init or dwc3_gadget_init. + */ +void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy); + #endif diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c index 1c513bf8002ec9..96b588bd08cdce 100644 --- a/drivers/usb/dwc3/host.c +++ b/drivers/usb/dwc3/host.c @@ -37,7 +37,10 @@ static void dwc3_power_off_all_roothub_ports(struct dwc3 *dwc) /* xhci regs are not mapped yet, do it temporarily here */ if (dwc->xhci_resources[0].start) { - xhci_regs = ioremap(dwc->xhci_resources[0].start, DWC3_XHCI_REGS_END); + if (dwc->xhci_resources[0].flags & IORESOURCE_MEM_NONPOSTED) + xhci_regs = ioremap_np(dwc->xhci_resources[0].start, DWC3_XHCI_REGS_END); + else + xhci_regs = ioremap(dwc->xhci_resources[0].start, DWC3_XHCI_REGS_END); if (!xhci_regs) { dev_err(dwc->dev, "Failed to ioremap xhci_regs\n"); return; @@ -217,13 +220,15 @@ int dwc3_host_init(struct dwc3 *dwc) platform_device_put(xhci); return ret; } +EXPORT_SYMBOL_GPL(dwc3_host_init); void dwc3_host_exit(struct dwc3 *dwc) { if (dwc->sys_wakeup) device_init_wakeup(&dwc->xhci->dev, false); - dwc3_enable_susphy(dwc, false); + dwc3_enable_susphy(dwc, true); platform_device_unregister(dwc->xhci); dwc->xhci = NULL; } +EXPORT_SYMBOL_GPL(dwc3_host_exit); diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c index aa6ab666741a95..a96476507d2fdf 100644 --- a/drivers/usb/gadget/function/f_uvc.c +++ b/drivers/usb/gadget/function/f_uvc.c @@ -362,6 +362,10 @@ uvc_function_set_alt(struct usb_function *f, unsigned interface, unsigned alt) return ret; usb_ep_enable(uvc->video.ep); + uvc->video.max_req_size = uvc->video.ep->maxpacket + * max_t(unsigned int, uvc->video.ep->maxburst, 1) + * (uvc->video.ep->mult); + memset(&v4l2_event, 0, sizeof(v4l2_event)); v4l2_event.type = UVC_EVENT_STREAMON; v4l2_event_queue(&uvc->vdev, &v4l2_event); diff --git a/drivers/usb/gadget/function/uvc.h b/drivers/usb/gadget/function/uvc.h index 9e79cbe5071579..676419a049762f 100644 --- a/drivers/usb/gadget/function/uvc.h +++ b/drivers/usb/gadget/function/uvc.h @@ -107,7 +107,7 @@ struct uvc_video { unsigned int width; unsigned int height; unsigned int imagesize; - unsigned int interval; + unsigned int interval; /* in 100ns units */ struct mutex mutex; /* protects frame parameters */ unsigned int uvc_num_requests; @@ -117,6 +117,7 @@ struct uvc_video { /* Requests */ bool is_enabled; /* tracks whether video stream is enabled */ unsigned int req_size; + unsigned int max_req_size; struct list_head ureqs; /* all uvc_requests allocated by uvc_video */ /* USB requests that the video pump thread can encode into */ diff --git a/drivers/usb/gadget/function/uvc_queue.c b/drivers/usb/gadget/function/uvc_queue.c index 9a1bbd79ff5af9..21d80322cb6148 100644 --- a/drivers/usb/gadget/function/uvc_queue.c +++ b/drivers/usb/gadget/function/uvc_queue.c @@ -86,10 +86,17 @@ static int uvc_buffer_prepare(struct vb2_buffer *vb) buf->bytesused = 0; } else { buf->bytesused = vb2_get_plane_payload(vb, 0); - buf->req_payload_size = - DIV_ROUND_UP(buf->bytesused + - (video->reqs_per_frame * UVCG_REQUEST_HEADER_LEN), - video->reqs_per_frame); + + if (video->reqs_per_frame != 0) { + buf->req_payload_size = + DIV_ROUND_UP(buf->bytesused + + (video->reqs_per_frame * UVCG_REQUEST_HEADER_LEN), + video->reqs_per_frame); + if (buf->req_payload_size > video->req_size) + buf->req_payload_size = video->req_size; + } else { + buf->req_payload_size = video->max_req_size; + } } return 0; diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c index fb77b0b2179017..9dc3af16e2f389 100644 --- a/drivers/usb/gadget/function/uvc_video.c +++ b/drivers/usb/gadget/function/uvc_video.c @@ -499,13 +499,11 @@ uvc_video_prep_requests(struct uvc_video *video) { struct uvc_device *uvc = container_of(video, struct uvc_device, video); struct usb_composite_dev *cdev = uvc->func.config->cdev; - unsigned int interval_duration = video->ep->desc->bInterval * 1250; + unsigned int interval_duration; unsigned int max_req_size, req_size, header_size; unsigned int nreq; - max_req_size = video->ep->maxpacket - * max_t(unsigned int, video->ep->maxburst, 1) - * (video->ep->mult); + max_req_size = video->max_req_size; if (!usb_endpoint_xfer_isoc(video->ep->desc)) { video->req_size = max_req_size; @@ -515,8 +513,11 @@ uvc_video_prep_requests(struct uvc_video *video) return; } + interval_duration = 2 << (video->ep->desc->bInterval - 1); if (cdev->gadget->speed < USB_SPEED_HIGH) - interval_duration = video->ep->desc->bInterval * 10000; + interval_duration *= 10000; + else + interval_duration *= 1250; nreq = DIV_ROUND_UP(video->interval, interval_duration); diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c index b71680c58de6c7..46f343ba48b3da 100644 --- a/drivers/usb/gadget/legacy/raw_gadget.c +++ b/drivers/usb/gadget/legacy/raw_gadget.c @@ -40,6 +40,7 @@ MODULE_LICENSE("GPL"); static DEFINE_IDA(driver_id_numbers); #define DRIVER_DRIVER_NAME_LENGTH_MAX 32 +#define USB_RAW_IO_LENGTH_MAX KMALLOC_MAX_SIZE #define RAW_EVENT_QUEUE_SIZE 16 @@ -667,6 +668,8 @@ static void *raw_alloc_io_data(struct usb_raw_ep_io *io, void __user *ptr, return ERR_PTR(-EINVAL); if (!usb_raw_io_flags_valid(io->flags)) return ERR_PTR(-EINVAL); + if (io->length > USB_RAW_IO_LENGTH_MAX) + return ERR_PTR(-EINVAL); if (get_from_user) data = memdup_user(ptr + sizeof(*io), io->length); else { diff --git a/drivers/usb/gadget/udc/bdc/bdc_core.c b/drivers/usb/gadget/udc/bdc/bdc_core.c index 5c3d8b64c0e76e..f47aac078f6be6 100644 --- a/drivers/usb/gadget/udc/bdc/bdc_core.c +++ b/drivers/usb/gadget/udc/bdc/bdc_core.c @@ -35,8 +35,8 @@ static int poll_oip(struct bdc *bdc, u32 usec) u32 status; int ret; - ret = readl_poll_timeout(bdc->regs + BDC_BDCSC, status, - (BDC_CSTS(status) != BDC_OIP), 10, usec); + ret = readl_poll_timeout_atomic(bdc->regs + BDC_BDCSC, status, + (BDC_CSTS(status) != BDC_OIP), 10, usec); if (ret) dev_err(bdc->dev, "operation timedout BDCSC: 0x%08x\n", status); else diff --git a/drivers/usb/gadget/udc/lpc32xx_udc.c b/drivers/usb/gadget/udc/lpc32xx_udc.c index 1a7d3c4f652fef..a962d4294fbec6 100644 --- a/drivers/usb/gadget/udc/lpc32xx_udc.c +++ b/drivers/usb/gadget/udc/lpc32xx_udc.c @@ -3020,7 +3020,7 @@ static int lpc32xx_udc_probe(struct platform_device *pdev) pdev->dev.dma_mask = &lpc32xx_usbd_dmamask; retval = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); if (retval) - return retval; + goto err_put_client; udc->board = &lpc32xx_usbddata; @@ -3038,28 +3038,32 @@ static int lpc32xx_udc_probe(struct platform_device *pdev) /* Get IRQs */ for (i = 0; i < 4; i++) { udc->udp_irq[i] = platform_get_irq(pdev, i); - if (udc->udp_irq[i] < 0) - return udc->udp_irq[i]; + if (udc->udp_irq[i] < 0) { + retval = udc->udp_irq[i]; + goto err_put_client; + } } udc->udp_baseaddr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(udc->udp_baseaddr)) { dev_err(udc->dev, "IO map failure\n"); - return PTR_ERR(udc->udp_baseaddr); + retval = PTR_ERR(udc->udp_baseaddr); + goto err_put_client; } /* Get USB device clock */ udc->usb_slv_clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(udc->usb_slv_clk)) { dev_err(udc->dev, "failed to acquire USB device clock\n"); - return PTR_ERR(udc->usb_slv_clk); + retval = PTR_ERR(udc->usb_slv_clk); + goto err_put_client; } /* Enable USB device clock */ retval = clk_prepare_enable(udc->usb_slv_clk); if (retval < 0) { dev_err(udc->dev, "failed to start USB device clock\n"); - return retval; + goto err_put_client; } /* Setup deferred workqueue data */ @@ -3162,6 +3166,9 @@ static int lpc32xx_udc_probe(struct platform_device *pdev) udc->udca_v_base, udc->udca_p_base); i2c_fail: clk_disable_unprepare(udc->usb_slv_clk); +err_put_client: + put_device(&udc->isp1301_i2c_client->dev); + dev_err(udc->dev, "%s probe failed, %d\n", driver_name, retval); return retval; @@ -3190,6 +3197,8 @@ static void lpc32xx_udc_remove(struct platform_device *pdev) udc->udca_v_base, udc->udca_p_base); clk_disable_unprepare(udc->usb_slv_clk); + + put_device(&udc->isp1301_i2c_client->dev); } #ifdef CONFIG_PM diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index 0c38fc37b6e66c..9d2007f448c049 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -1558,12 +1558,6 @@ static int __tegra_xudc_ep_set_halt(struct tegra_xudc_ep *ep, bool halt) return -ENOTSUPP; } - if (!!(xudc_readl(xudc, EP_HALT) & BIT(ep->index)) == halt) { - dev_dbg(xudc->dev, "EP %u already %s\n", ep->index, - halt ? "halted" : "not halted"); - return 0; - } - if (halt) { ep_halt(xudc, ep->index); } else { diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig index c4f17ce5c77b15..5f3ecce8398b39 100644 --- a/drivers/usb/host/Kconfig +++ b/drivers/usb/host/Kconfig @@ -51,6 +51,15 @@ config USB_XHCI_PCI_RENESAS installed on your system for this device to work. If unsure, say 'N'. +config USB_XHCI_PCI_ASMEDIA + bool "Support firmware loading for ASMedia xHCI controllers" + default USB_XHCI_PCI if ARCH_APPLE + depends on USB_XHCI_PCI + help + Say 'Y' to enable support for ASMedia xHCI controllers with + host-supplied firmware. These are usually present on Apple devices. + If unsure, say 'N'. + config USB_XHCI_PLATFORM tristate "Generic xHCI driver for a platform device" help diff --git a/drivers/usb/host/Makefile b/drivers/usb/host/Makefile index 4df946c05ba0ee..a197e0979f89bd 100644 --- a/drivers/usb/host/Makefile +++ b/drivers/usb/host/Makefile @@ -72,6 +72,8 @@ obj-$(CONFIG_USB_UHCI_HCD) += uhci-hcd.o obj-$(CONFIG_USB_FHCI_HCD) += fhci.o obj-$(CONFIG_USB_XHCI_HCD) += xhci-hcd.o obj-$(CONFIG_USB_XHCI_PCI) += xhci-pci.o +xhci-pci-y += xhci-pci-core.o +xhci-pci-$(CONFIG_USB_XHCI_PCI_ASMEDIA) += xhci-pci-asmedia.o obj-$(CONFIG_USB_XHCI_PCI_RENESAS) += xhci-pci-renesas.o obj-$(CONFIG_USB_XHCI_PLATFORM) += xhci-plat-hcd.o obj-$(CONFIG_USB_XHCI_HISTB) += xhci-histb.o diff --git a/drivers/usb/host/ohci-nxp.c b/drivers/usb/host/ohci-nxp.c index 24d5a1dc505604..509ca7d8d51380 100644 --- a/drivers/usb/host/ohci-nxp.c +++ b/drivers/usb/host/ohci-nxp.c @@ -223,6 +223,7 @@ static int ohci_hcd_nxp_probe(struct platform_device *pdev) fail_resource: usb_put_hcd(hcd); fail_disable: + put_device(&isp1301_i2c_client->dev); isp1301_i2c_client = NULL; return ret; } @@ -234,6 +235,7 @@ static void ohci_hcd_nxp_remove(struct platform_device *pdev) usb_remove_hcd(hcd); ohci_nxp_stop_hc(); usb_put_hcd(hcd); + put_device(&isp1301_i2c_client->dev); isp1301_i2c_client = NULL; } diff --git a/drivers/usb/host/ohci-platform.c b/drivers/usb/host/ohci-platform.c index f47ae12cde6a26..059621210d2c29 100644 --- a/drivers/usb/host/ohci-platform.c +++ b/drivers/usb/host/ohci-platform.c @@ -376,3 +376,4 @@ MODULE_DESCRIPTION(DRIVER_DESC); MODULE_AUTHOR("Hauke Mehrtens"); MODULE_AUTHOR("Alan Stern"); MODULE_LICENSE("GPL"); +MODULE_SOFTDEP("pre: ehci_platform"); diff --git a/drivers/usb/host/uhci-platform.c b/drivers/usb/host/uhci-platform.c index 62318291f5664c..be8cba0242892f 100644 --- a/drivers/usb/host/uhci-platform.c +++ b/drivers/usb/host/uhci-platform.c @@ -191,3 +191,4 @@ static struct platform_driver uhci_platform_driver = { .of_match_table = platform_uhci_ids, }, }; +MODULE_SOFTDEP("pre: ehci_platform"); diff --git a/drivers/usb/host/xhci-dbgtty.c b/drivers/usb/host/xhci-dbgtty.c index 57cdda4e09c8ea..90282e51e23ec0 100644 --- a/drivers/usb/host/xhci-dbgtty.c +++ b/drivers/usb/host/xhci-dbgtty.c @@ -554,7 +554,7 @@ static void xhci_dbc_tty_unregister_device(struct xhci_dbc *dbc) * Hang up the TTY. This wakes up any blocked * writers and causes subsequent writes to fail. */ - tty_vhangup(port->port.tty); + tty_port_tty_vhangup(&port->port); tty_unregister_device(dbc_tty_driver, port->minor); xhci_dbc_tty_exit_port(port); diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index b3a59ce1b3f41f..5e1442e91743da 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -1671,7 +1671,7 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf) * SS devices are only visible to roothub after link training completes. * Keep polling roothubs for a grace period after xHC start */ - if (xhci->run_graceperiod) { + if (hcd->speed >= HCD_USB3 && xhci->run_graceperiod) { if (time_before(jiffies, xhci->run_graceperiod)) status = 1; else diff --git a/drivers/usb/host/xhci-pci-asmedia.c b/drivers/usb/host/xhci-pci-asmedia.c new file mode 100644 index 00000000000000..d6b12f5c540296 --- /dev/null +++ b/drivers/usb/host/xhci-pci-asmedia.c @@ -0,0 +1,414 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * ASMedia xHCI firmware loader + * Copyright (C) The Asahi Linux Contributors + */ + +#include +#include +#include +#include +#include +#include + +#include "xhci.h" +#include "xhci-trace.h" +#include "xhci-pci.h" + +/* Configuration space registers */ +#define ASMT_CFG_CONTROL 0xe0 +#define ASMT_CFG_CONTROL_WRITE BIT(1) +#define ASMT_CFG_CONTROL_READ BIT(0) + +#define ASMT_CFG_SRAM_ADDR 0xe2 + +#define ASMT_CFG_SRAM_ACCESS 0xef +#define ASMT_CFG_SRAM_ACCESS_READ BIT(6) +#define ASMT_CFG_SRAM_ACCESS_ENABLE BIT(7) + +#define ASMT_CFG_DATA_READ0 0xf0 +#define ASMT_CFG_DATA_READ1 0xf4 + +#define ASMT_CFG_DATA_WRITE0 0xf8 +#define ASMT_CFG_DATA_WRITE1 0xfc + +#define ASMT_CMD_GET_FWVER 0x8000060840 +#define ASMT_FWVER_ROM 0x010250090816 + +/* BAR0 registers */ +#define ASMT_REG_ADDR 0x3000 + +#define ASMT_REG_WDATA 0x3004 +#define ASMT_REG_RDATA 0x3008 + +#define ASMT_REG_STATUS 0x3009 +#define ASMT_REG_STATUS_BUSY BIT(7) + +#define ASMT_REG_CODE_WDATA 0x3010 +#define ASMT_REG_CODE_RDATA 0x3018 + +#define ASMT_MMIO_CPU_MISC 0x500e +#define ASMT_MMIO_CPU_MISC_CODE_RAM_WR BIT(0) + +#define ASMT_MMIO_CPU_MODE_NEXT 0x5040 +#define ASMT_MMIO_CPU_MODE_CUR 0x5041 + +#define ASMT_MMIO_CPU_MODE_RAM BIT(0) +#define ASMT_MMIO_CPU_MODE_HALFSPEED BIT(1) + +#define ASMT_MMIO_CPU_EXEC_CTRL 0x5042 +#define ASMT_MMIO_CPU_EXEC_CTRL_RESET BIT(0) +#define ASMT_MMIO_CPU_EXEC_CTRL_HALT BIT(1) + +#define TIMEOUT_USEC 10000 +#define RESET_TIMEOUT_USEC 500000 + +static int asmedia_mbox_tx(struct pci_dev *pdev, u64 data) +{ + u8 op; + int ret, err; + + ret = read_poll_timeout(pci_read_config_byte, err, + err || !(op & ASMT_CFG_CONTROL_WRITE), + 1, TIMEOUT_USEC, false, pdev, ASMT_CFG_CONTROL, + &op); + if (ret) { + dev_err(&pdev->dev, + "Timed out on mailbox tx: 0x%llx\n", + data); + return ret; + } + if (err) + return err; + + pci_write_config_dword(pdev, ASMT_CFG_DATA_WRITE0, data); + pci_write_config_dword(pdev, ASMT_CFG_DATA_WRITE1, data >> 32); + pci_write_config_byte(pdev, ASMT_CFG_CONTROL, ASMT_CFG_CONTROL_WRITE); + + return 0; +} + +static int asmedia_mbox_rx(struct pci_dev *pdev, u64 *data) +{ + u8 op; + u32 low, high; + int ret, err; + + ret = read_poll_timeout(pci_read_config_byte, err, + err || (op & ASMT_CFG_CONTROL_READ), + 1, TIMEOUT_USEC, false, pdev, ASMT_CFG_CONTROL, + &op); + if (ret) { + dev_err(&pdev->dev, "Timed out on mailbox rx\n"); + return ret; + } + if (err) + return err; + + pci_read_config_dword(pdev, ASMT_CFG_DATA_READ0, &low); + pci_read_config_dword(pdev, ASMT_CFG_DATA_READ1, &high); + pci_write_config_byte(pdev, ASMT_CFG_CONTROL, ASMT_CFG_CONTROL_READ); + + *data = ((u64)high << 32) | low; + return 0; +} + +static int asmedia_get_fw_version(struct pci_dev *pdev, u64 *version) +{ + int err = 0; + u64 cmd; + + err = asmedia_mbox_tx(pdev, ASMT_CMD_GET_FWVER); + if (err) + return err; + err = asmedia_mbox_tx(pdev, 0); + if (err) + return err; + + err = asmedia_mbox_rx(pdev, &cmd); + if (err) + return err; + err = asmedia_mbox_rx(pdev, version); + if (err) + return err; + + if (cmd != ASMT_CMD_GET_FWVER) { + dev_err(&pdev->dev, "Unexpected reply command 0x%llx\n", cmd); + return -EIO; + } + + return 0; +} + +static bool asmedia_check_firmware(struct pci_dev *pdev) +{ + u64 fwver; + int ret; + + ret = asmedia_get_fw_version(pdev, &fwver); + if (ret) + return ret; + + dev_info(&pdev->dev, "Firmware version: 0x%llx\n", fwver); + + return fwver != ASMT_FWVER_ROM; +} + +static int asmedia_wait_reset(struct pci_dev *pdev) +{ + struct usb_hcd *hcd = dev_get_drvdata(&pdev->dev); + struct xhci_cap_regs __iomem *cap = hcd->regs; + struct xhci_op_regs __iomem *op; + u32 val; + int ret; + + op = hcd->regs + HC_LENGTH(readl(&cap->hc_capbase)); + + ret = readl_poll_timeout(&op->command, + val, !(val & CMD_RESET), + 1000, RESET_TIMEOUT_USEC); + + if (!ret) + return 0; + + dev_err(hcd->self.controller, "Reset timed out, trying to kick it\n"); + + pci_write_config_byte(pdev, ASMT_CFG_SRAM_ACCESS, + ASMT_CFG_SRAM_ACCESS_ENABLE); + + pci_write_config_byte(pdev, ASMT_CFG_SRAM_ACCESS, 0); + + ret = readl_poll_timeout(&op->command, + val, !(val & CMD_RESET), + 1000, RESET_TIMEOUT_USEC); + + if (ret) + dev_err(hcd->self.controller, "Reset timed out, giving up\n"); + + return ret; +} + +static int asmedia_read_reg(struct usb_hcd *hcd, u16 addr, u8 *val) { + void __iomem *regs = hcd->regs; + u8 status; + int ret; + + ret = readb_poll_timeout(regs + ASMT_REG_STATUS, status, + !(status & ASMT_REG_STATUS_BUSY), + 1000, TIMEOUT_USEC); + + if (ret) { + dev_err(hcd->self.controller, + "Read reg wait timed out ([%04x])\n", addr); + return ret; + } + + writew_relaxed(addr, regs + ASMT_REG_ADDR); + + ret = readb_poll_timeout(regs + ASMT_REG_STATUS, status, + !(status & ASMT_REG_STATUS_BUSY), + 1000, TIMEOUT_USEC); + + if (ret) { + dev_err(hcd->self.controller, + "Read reg addr timed out ([%04x])\n", addr); + return ret; + } + + *val = readb_relaxed(regs + ASMT_REG_RDATA); + return 0; +} + +static int asmedia_write_reg(struct usb_hcd *hcd, u16 addr, u8 data, bool wait) { + void __iomem *regs = hcd->regs; + u8 status, val; + int ret, err; + + writew_relaxed(addr, regs + ASMT_REG_ADDR); + + ret = readb_poll_timeout(regs + ASMT_REG_STATUS, status, + !(status & ASMT_REG_STATUS_BUSY), + 1000, TIMEOUT_USEC); + + if (ret) { + dev_err(hcd->self.controller, + "Write reg addr timed out ([%04x] = %02x)\n", + addr, data); + return ret; + } + + writeb_relaxed(data, regs + ASMT_REG_WDATA); + + ret = readb_poll_timeout(regs + ASMT_REG_STATUS, status, + !(status & ASMT_REG_STATUS_BUSY), + 1000, TIMEOUT_USEC); + + if (ret) { + dev_err(hcd->self.controller, + "Write reg data timed out ([%04x] = %02x)\n", + addr, data); + return ret; + } + + if (!wait) + return 0; + + ret = read_poll_timeout(asmedia_read_reg, err, err || val == data, + 0, TIMEOUT_USEC, false, hcd, addr, &val); + if (ret) { + dev_err(hcd->self.controller, + "Verify register timed out ([%04x] = %02x)\n", + addr, data); + return ret; + } + if (err) { + dev_err(hcd->self.controller, + "Verify register read error ([%04x] = %02x)\n", + addr, data); + return err; + } + + return 0; +} + +static int asmedia_load_fw(struct pci_dev *pdev, const struct firmware *fw) +{ + struct usb_hcd *hcd; + void __iomem *regs; + const u16 *fw_data = (const u16 *)fw->data; + u16 raddr; + u32 data; + size_t index = 0, addr = 0; + size_t words = fw->size >> 1; + int ret, err; + + hcd = dev_get_drvdata(&pdev->dev); + regs = hcd->regs; + + ret = asmedia_write_reg(hcd, ASMT_MMIO_CPU_MODE_NEXT, + ASMT_MMIO_CPU_MODE_HALFSPEED, false); + if (ret) + return ret; + + ret = asmedia_write_reg(hcd, ASMT_MMIO_CPU_EXEC_CTRL, + ASMT_MMIO_CPU_EXEC_CTRL_RESET, false); + if (ret) + return ret; + + ret = asmedia_wait_reset(pdev); + if (ret) { + dev_err(hcd->self.controller, "Failed pre-upload reset\n"); + return ret; + } + + ret = asmedia_write_reg(hcd, ASMT_MMIO_CPU_EXEC_CTRL, + ASMT_MMIO_CPU_EXEC_CTRL_HALT, false); + if (ret) + return ret; + + ret = asmedia_write_reg(hcd, ASMT_MMIO_CPU_MISC, + ASMT_MMIO_CPU_MISC_CODE_RAM_WR, true); + if (ret) + return ret; + + pci_write_config_byte(pdev, ASMT_CFG_SRAM_ACCESS, + ASMT_CFG_SRAM_ACCESS_ENABLE); + + /* The firmware upload is interleaved in 0x4000 word blocks */ + addr = index = 0; + while (index < words) { + data = fw_data[index]; + if ((index | 0x4000) < words) + data |= fw_data[index | 0x4000] << 16; + + pci_write_config_word(pdev, ASMT_CFG_SRAM_ADDR, + addr); + + writel_relaxed(data, regs + ASMT_REG_CODE_WDATA); + + ret = read_poll_timeout(pci_read_config_word, err, + err || (raddr != addr), + 1, TIMEOUT_USEC, false, pdev, + ASMT_CFG_SRAM_ADDR, &raddr); + if (ret) { + dev_err(hcd->self.controller, "Word write timed out\n"); + return ret; + } + if (err) + return err; + + if (++index & 0x4000) + index += 0x4000; + addr += 2; + } + + pci_write_config_byte(pdev, ASMT_CFG_SRAM_ACCESS, 0); + + ret = asmedia_write_reg(hcd, ASMT_MMIO_CPU_MISC, 0, true); + if (ret) + return ret; + + ret = asmedia_write_reg(hcd, ASMT_MMIO_CPU_MODE_NEXT, + ASMT_MMIO_CPU_MODE_RAM | + ASMT_MMIO_CPU_MODE_HALFSPEED, false); + if (ret) + return ret; + + ret = asmedia_write_reg(hcd, ASMT_MMIO_CPU_EXEC_CTRL, 0, false); + if (ret) + return ret; + + ret = asmedia_wait_reset(pdev); + if (ret) { + dev_err(hcd->self.controller, "Failed post-upload reset\n"); + return ret; + } + + return 0; +} + +int asmedia_xhci_check_request_fw(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + struct xhci_driver_data *driver_data = + (struct xhci_driver_data *)id->driver_data; + const char *fw_name = driver_data->firmware; + const struct firmware *fw; + int ret; + + /* Check if device has firmware, if so skip everything */ + ret = asmedia_check_firmware(pdev); + if (ret < 0) + return ret; + else if (ret == 1) + return 0; + + pci_dev_get(pdev); + ret = request_firmware(&fw, fw_name, &pdev->dev); + pci_dev_put(pdev); + if (ret) { + dev_err(&pdev->dev, "Could not load firmware %s: %d\n", + fw_name, ret); + return ret; + } + + ret = asmedia_load_fw(pdev, fw); + if (ret) { + dev_err(&pdev->dev, "Firmware upload failed: %d\n", ret); + goto err; + } + + ret = asmedia_check_firmware(pdev); + if (ret < 0) { + goto err; + } else if (ret != 1) { + dev_err(&pdev->dev, "Firmware version is too old after upload\n"); + ret = -EIO; + } else { + ret = 0; + } + +err: + release_firmware(fw); + return ret; +} diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci-core.c similarity index 97% rename from drivers/usb/host/xhci-pci.c rename to drivers/usb/host/xhci-pci-core.c index f67a4d9562046f..89bc33aa4ce991 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci-core.c @@ -569,6 +569,18 @@ static int xhci_pci_setup(struct usb_hcd *hcd) struct pci_dev *pdev = to_pci_dev(hcd->self.controller); int retval; u8 sbrn; + struct xhci_driver_data *driver_data; + const struct pci_device_id *id; + + id = pci_match_id(to_pci_driver(pdev->dev.driver)->id_table, pdev); + if (id && id->driver_data && usb_hcd_is_primary_hcd(hcd)) { + driver_data = (struct xhci_driver_data *)id->driver_data; + if (driver_data->quirks & XHCI_ASMEDIA_FW_QUIRK) { + retval = asmedia_xhci_check_request_fw(pdev, id); + if (retval < 0) + return retval; + } + } xhci = hcd_to_xhci(hcd); @@ -938,10 +950,19 @@ static void xhci_pci_shutdown(struct usb_hcd *hcd) pci_set_power_state(pdev, PCI_D3hot); } +#define ASMEDIA_APPLE_FW_NAME "asmedia/asm2214a-apple.bin" + /*-------------------------------------------------------------------------*/ +static const struct xhci_driver_data asmedia_data = { + .quirks = XHCI_ASMEDIA_FW_QUIRK, + .firmware = ASMEDIA_APPLE_FW_NAME, +}; /* PCI driver selection metadata; PCI hotplugging uses this */ static const struct pci_device_id pci_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_ASMEDIA, 0x2142), + .driver_data = (unsigned long)&asmedia_data, + }, /* handle any USB 3.0 xHCI controller */ { PCI_DEVICE_CLASS(PCI_CLASS_SERIAL_USB_XHCI, ~0), }, @@ -949,6 +970,10 @@ static const struct pci_device_id pci_ids[] = { }; MODULE_DEVICE_TABLE(pci, pci_ids); +#if IS_ENABLED(CONFIG_USB_XHCI_PCI_ASMEDIA) +MODULE_FIRMWARE(ASMEDIA_APPLE_FW_NAME); +#endif + /* pci driver glue; this is a "new style" PCI driver module */ static struct pci_driver xhci_pci_driver = { .name = hcd_name, diff --git a/drivers/usb/host/xhci-pci.h b/drivers/usb/host/xhci-pci.h index e87c7d9d76b8e2..452908d1c069ba 100644 --- a/drivers/usb/host/xhci-pci.h +++ b/drivers/usb/host/xhci-pci.h @@ -7,4 +7,22 @@ int xhci_pci_common_probe(struct pci_dev *dev, const struct pci_device_id *id); void xhci_pci_remove(struct pci_dev *dev); +struct xhci_driver_data { + u64 quirks; + const char *firmware; +}; + +#if IS_ENABLED(CONFIG_USB_XHCI_PCI_ASMEDIA) +int asmedia_xhci_check_request_fw(struct pci_dev *dev, + const struct pci_device_id *id); + +#else +static inline int asmedia_xhci_check_request_fw(struct pci_dev *dev, + const struct pci_device_id *id) +{ + return 0; +} + +#endif + #endif diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 5bdcf9ab2b99d7..25185552287c05 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -128,11 +128,11 @@ static void inc_td_cnt(struct urb *urb) urb_priv->num_tds_done++; } -static void trb_to_noop(union xhci_trb *trb, u32 noop_type) +static void trb_to_noop(union xhci_trb *trb, u32 noop_type, bool unchain_links) { if (trb_is_link(trb)) { - /* unchain chained link TRBs */ - trb->link.control &= cpu_to_le32(~TRB_CHAIN); + if (unchain_links) + trb->link.control &= cpu_to_le32(~TRB_CHAIN); } else { trb->generic.field[0] = 0; trb->generic.field[1] = 0; @@ -465,7 +465,7 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci, xhci_dbg(xhci, "Turn aborted command %p to no-op\n", i_cmd->command_trb); - trb_to_noop(i_cmd->command_trb, TRB_CMD_NOOP); + trb_to_noop(i_cmd->command_trb, TRB_CMD_NOOP, false); /* * caller waiting for completion is called when command @@ -797,13 +797,18 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci, * (The last TRB actually points to the ring enqueue pointer, which is not part * of this TD.) This is used to remove partially enqueued isoc TDs from a ring. */ -static void td_to_noop(struct xhci_td *td, bool flip_cycle) +static void td_to_noop(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, + struct xhci_td *td, bool flip_cycle) { + bool unchain_links; struct xhci_segment *seg = td->start_seg; union xhci_trb *trb = td->start_trb; + /* link TRBs should now be unchained, but some old HCs expect otherwise */ + unchain_links = !xhci_link_chain_quirk(xhci, ep->ring ? ep->ring->type : TYPE_STREAM); + while (1) { - trb_to_noop(trb, TRB_TR_NOOP); + trb_to_noop(trb, TRB_TR_NOOP, unchain_links); /* flip cycle if asked to */ if (flip_cycle && trb != td->start_trb && trb != td->end_trb) @@ -1091,16 +1096,16 @@ static int xhci_invalidate_cancelled_tds(struct xhci_virt_ep *ep) "Found multiple active URBs %p and %p in stream %u?\n", td->urb, cached_td->urb, td->urb->stream_id); - td_to_noop(cached_td, false); + td_to_noop(xhci, ep, cached_td, false); cached_td->cancel_status = TD_CLEARED; } - td_to_noop(td, false); + td_to_noop(xhci, ep, td, false); td->cancel_status = TD_CLEARING_CACHE; cached_td = td; break; } } else { - td_to_noop(td, false); + td_to_noop(xhci, ep, td, false); td->cancel_status = TD_CLEARED; } } @@ -1125,7 +1130,7 @@ static int xhci_invalidate_cancelled_tds(struct xhci_virt_ep *ep) continue; xhci_warn(xhci, "Failed to clear cancelled cached URB %p, mark clear anyway\n", td->urb); - td_to_noop(td, false); + td_to_noop(xhci, ep, td, false); td->cancel_status = TD_CLEARED; } } @@ -4273,7 +4278,7 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, */ urb_priv->td[0].end_trb = ep_ring->enqueue; /* Every TRB except the first & last will have its cycle bit flipped. */ - td_to_noop(&urb_priv->td[0], true); + td_to_noop(xhci, xep, &urb_priv->td[0], true); /* Reset the ring enqueue back to the first TRB and its cycle bit. */ ep_ring->enqueue = urb_priv->td[0].start_trb; diff --git a/drivers/usb/host/xhci-sideband.c b/drivers/usb/host/xhci-sideband.c index a85f62a73313ab..2bd77255032b97 100644 --- a/drivers/usb/host/xhci-sideband.c +++ b/drivers/usb/host/xhci-sideband.c @@ -210,7 +210,6 @@ xhci_sideband_remove_endpoint(struct xhci_sideband *sb, return -ENODEV; __xhci_sideband_remove_endpoint(sb, ep); - xhci_initialize_ring_info(ep->ring); return 0; } diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 5255b10028931c..c78bed0aa844ea 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1564,7 +1564,7 @@ static int tegra_xusb_setup_wakeup(struct platform_device *pdev, struct tegra_xu for (i = 0; i < tegra->soc->max_num_wakes; i++) { struct irq_data *data; - tegra->wake_irqs[i] = platform_get_irq(pdev, i + WAKE_IRQ_START_INDEX); + tegra->wake_irqs[i] = platform_get_irq_optional(pdev, i + WAKE_IRQ_START_INDEX); if (tegra->wake_irqs[i] < 0) break; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index a148a128012638..4161c8c7721dd9 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -2891,16 +2891,25 @@ int xhci_stop_endpoint_sync(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, int gfp_t gfp_flags) { struct xhci_command *command; + struct xhci_ep_ctx *ep_ctx; unsigned long flags; - int ret; + int ret = -ENODEV; command = xhci_alloc_command(xhci, true, gfp_flags); if (!command) return -ENOMEM; spin_lock_irqsave(&xhci->lock, flags); - ret = xhci_queue_stop_endpoint(xhci, command, ep->vdev->slot_id, - ep->ep_index, suspend); + + /* make sure endpoint exists and is running before stopping it */ + if (ep->ring) { + ep_ctx = xhci_get_ep_ctx(xhci, ep->vdev->out_ctx, ep->ep_index); + if (GET_EP_CTX_STATE(ep_ctx) == EP_STATE_RUNNING) + ret = xhci_queue_stop_endpoint(xhci, command, + ep->vdev->slot_id, + ep->ep_index, suspend); + } + if (ret < 0) { spin_unlock_irqrestore(&xhci->lock, flags); goto out; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 58a51f09cceb8f..78c71d99d104c4 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1645,6 +1645,7 @@ struct xhci_hcd { #define XHCI_CDNS_SCTX_QUIRK BIT_ULL(48) #define XHCI_ETRON_HOST BIT_ULL(49) #define XHCI_LIMIT_ENDPOINT_INTERVAL_9 BIT_ULL(50) +#define XHCI_ASMEDIA_FW_QUIRK BIT_ULL(51) unsigned int num_active_eps; unsigned int limit_active_eps; diff --git a/drivers/usb/misc/chaoskey.c b/drivers/usb/misc/chaoskey.c index 225863321dc479..45cff32656c6e3 100644 --- a/drivers/usb/misc/chaoskey.c +++ b/drivers/usb/misc/chaoskey.c @@ -444,9 +444,19 @@ static ssize_t chaoskey_read(struct file *file, goto bail; mutex_unlock(&dev->rng_lock); - result = mutex_lock_interruptible(&dev->lock); - if (result) - goto bail; + if (file->f_flags & O_NONBLOCK) { + result = mutex_trylock(&dev->lock); + if (result == 0) { + result = -EAGAIN; + goto bail; + } else { + result = 0; + } + } else { + result = mutex_lock_interruptible(&dev->lock); + if (result) + goto bail; + } if (dev->valid == dev->used) { result = _chaoskey_fill(dev); if (result < 0) { diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c index 40ac68e52cee73..e266a47c4d4833 100644 --- a/drivers/usb/phy/phy-fsl-usb.c +++ b/drivers/usb/phy/phy-fsl-usb.c @@ -988,6 +988,7 @@ static void fsl_otg_remove(struct platform_device *pdev) { struct fsl_usb2_platform_data *pdata = dev_get_platdata(&pdev->dev); + disable_delayed_work_sync(&fsl_otg_dev->otg_event); usb_remove_phy(&fsl_otg_dev->phy); free_irq(fsl_otg_dev->irq, fsl_otg_dev); diff --git a/drivers/usb/phy/phy-isp1301.c b/drivers/usb/phy/phy-isp1301.c index f9b5c411aee4e5..2940f0c84e1b77 100644 --- a/drivers/usb/phy/phy-isp1301.c +++ b/drivers/usb/phy/phy-isp1301.c @@ -149,7 +149,12 @@ struct i2c_client *isp1301_get_client(struct device_node *node) return client; /* non-DT: only one ISP1301 chip supported */ - return isp1301_i2c_client; + if (isp1301_i2c_client) { + get_device(&isp1301_i2c_client->dev); + return isp1301_i2c_client; + } + + return NULL; } EXPORT_SYMBOL_GPL(isp1301_get_client); diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c index e1435bc596622c..5a9b9353f343d5 100644 --- a/drivers/usb/phy/phy.c +++ b/drivers/usb/phy/phy.c @@ -646,6 +646,8 @@ int usb_add_phy(struct usb_phy *x, enum usb_phy_type type) return -EINVAL; } + INIT_LIST_HEAD(&x->head); + usb_charger_init(x); ret = usb_add_extcon(x); if (ret) @@ -696,6 +698,8 @@ int usb_add_phy_dev(struct usb_phy *x) return -EINVAL; } + INIT_LIST_HEAD(&x->head); + usb_charger_init(x); ret = usb_add_extcon(x); if (ret) diff --git a/drivers/usb/renesas_usbhs/pipe.c b/drivers/usb/renesas_usbhs/pipe.c index 75fff2e4cbc65f..56fc3ff5016fc7 100644 --- a/drivers/usb/renesas_usbhs/pipe.c +++ b/drivers/usb/renesas_usbhs/pipe.c @@ -713,11 +713,13 @@ struct usbhs_pipe *usbhs_pipe_malloc(struct usbhs_priv *priv, /* make sure pipe is not busy */ ret = usbhsp_pipe_barrier(pipe); if (ret < 0) { + usbhsp_put_pipe(pipe); dev_err(dev, "pipe setup failed %d\n", usbhs_pipe_number(pipe)); return NULL; } if (usbhsp_setup_pipecfg(pipe, is_host, dir_in, &pipecfg)) { + usbhsp_put_pipe(pipe); dev_err(dev, "can't setup pipe\n"); return NULL; } diff --git a/drivers/usb/serial/belkin_sa.c b/drivers/usb/serial/belkin_sa.c index 44f5b58beec922..aa6b4c4ad5ecbe 100644 --- a/drivers/usb/serial/belkin_sa.c +++ b/drivers/usb/serial/belkin_sa.c @@ -435,7 +435,7 @@ static int belkin_sa_tiocmset(struct tty_struct *tty, struct belkin_sa_private *priv = usb_get_serial_port_data(port); unsigned long control_state; unsigned long flags; - int retval; + int retval = 0; int rts = 0; int dtr = 0; @@ -452,26 +452,32 @@ static int belkin_sa_tiocmset(struct tty_struct *tty, } if (clear & TIOCM_RTS) { control_state &= ~TIOCM_RTS; - rts = 0; + rts = 1; } if (clear & TIOCM_DTR) { control_state &= ~TIOCM_DTR; - dtr = 0; + dtr = 1; } priv->control_state = control_state; spin_unlock_irqrestore(&priv->lock, flags); - retval = BSA_USB_CMD(BELKIN_SA_SET_RTS_REQUEST, rts); - if (retval < 0) { - dev_err(&port->dev, "Set RTS error %d\n", retval); - goto exit; + if (rts) { + retval = BSA_USB_CMD(BELKIN_SA_SET_RTS_REQUEST, + !!(control_state & TIOCM_RTS)); + if (retval < 0) { + dev_err(&port->dev, "Set RTS error %d\n", retval); + goto exit; + } } - retval = BSA_USB_CMD(BELKIN_SA_SET_DTR_REQUEST, dtr); - if (retval < 0) { - dev_err(&port->dev, "Set DTR error %d\n", retval); - goto exit; + if (dtr) { + retval = BSA_USB_CMD(BELKIN_SA_SET_DTR_REQUEST, + !!(control_state & TIOCM_DTR)); + if (retval < 0) { + dev_err(&port->dev, "Set DTR error %d\n", retval); + goto exit; + } } exit: return retval; diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index b37fa31f56943d..ceddfb1852e165 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -628,10 +628,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_IBS_PEDO_PID) }, { USB_DEVICE(FTDI_VID, FTDI_IBS_PROD_PID) }, { USB_DEVICE(FTDI_VID, FTDI_TAVIR_STK500_PID) }, - { USB_DEVICE(FTDI_VID, FTDI_TIAO_UMPA_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLXM_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, FTDI_TIAO_UMPA_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, FTDI_NT_ORIONLXM_PID, 1) }, { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLX_PLUS_PID) }, { USB_DEVICE(FTDI_VID, FTDI_NT_ORION_IO_PID) }, { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONMX_PID) }, @@ -842,24 +840,18 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_ELSTER_UNICOM_PID) }, { USB_DEVICE(FTDI_VID, FTDI_PROPOX_JTAGCABLEII_PID) }, { USB_DEVICE(FTDI_VID, FTDI_PROPOX_ISPCABLEIII_PID) }, - { USB_DEVICE(FTDI_VID, CYBER_CORTEX_AV_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, CYBER_CORTEX_AV_PID, 1) }, { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID, 1) }, { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID, 1) }, { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_TINY_PID, 1) }, { USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_TINY_H_PID, 1) }, - { USB_DEVICE(FIC_VID, FIC_NEO1973_DEBUG_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(FTDI_VID, FTDI_OOCDLINK_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(FTDI_VID, LMI_LM3S_DEVEL_BOARD_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(FTDI_VID, LMI_LM3S_EVAL_BOARD_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(FTDI_VID, LMI_LM3S_ICDI_BOARD_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(FTDI_VID, FTDI_TURTELIZER_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(FIC_VID, FIC_NEO1973_DEBUG_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, FTDI_OOCDLINK_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, LMI_LM3S_DEVEL_BOARD_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, LMI_LM3S_EVAL_BOARD_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, LMI_LM3S_ICDI_BOARD_PID, 1) }, + { USB_DEVICE(FTDI_VID, FTDI_AXE027_PID) }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, FTDI_TURTELIZER_PID, 1) }, { USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_USB60F) }, { USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_SCU18) }, { USB_DEVICE(FTDI_VID, FTDI_REU_TINY_PID) }, @@ -901,17 +893,14 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(ATMEL_VID, STK541_PID) }, { USB_DEVICE(DE_VID, STB_PID) }, { USB_DEVICE(DE_VID, WHT_PID) }, - { USB_DEVICE(ADI_VID, ADI_GNICE_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(ADI_VID, ADI_GNICEPLUS_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(ADI_VID, ADI_GNICE_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(ADI_VID, ADI_GNICEPLUS_PID, 1) }, { USB_DEVICE_AND_INTERFACE_INFO(MICROCHIP_VID, MICROCHIP_USB_BOARD_PID, USB_CLASS_VENDOR_SPEC, USB_SUBCLASS_VENDOR_SPEC, 0x00) }, { USB_DEVICE_INTERFACE_NUMBER(ACTEL_VID, MICROSEMI_ARROW_SF2PLUS_BOARD_PID, 2) }, { USB_DEVICE(JETI_VID, JETI_SPC1201_PID) }, - { USB_DEVICE(MARVELL_VID, MARVELL_SHEEVAPLUG_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(MARVELL_VID, MARVELL_SHEEVAPLUG_PID, 1) }, { USB_DEVICE(LARSENBRUSGAARD_VID, LB_ALTITRACK_PID) }, { USB_DEVICE(GN_OTOMETRICS_VID, AURICAL_USB_PID) }, { USB_DEVICE(FTDI_VID, PI_C865_PID) }, @@ -934,10 +923,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(PI_VID, PI_1016_PID) }, { USB_DEVICE(KONDO_VID, KONDO_USB_SERIAL_PID) }, { USB_DEVICE(BAYER_VID, BAYER_CONTOUR_CABLE_PID) }, - { USB_DEVICE(FTDI_VID, MARVELL_OPENRD_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(FTDI_VID, TI_XDS100V2_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, MARVELL_OPENRD_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, TI_XDS100V2_PID, 1) }, { USB_DEVICE(FTDI_VID, HAMEG_HO820_PID) }, { USB_DEVICE(FTDI_VID, HAMEG_HO720_PID) }, { USB_DEVICE(FTDI_VID, HAMEG_HO730_PID) }, @@ -946,18 +933,14 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, MJSG_SR_RADIO_PID) }, { USB_DEVICE(FTDI_VID, MJSG_HD_RADIO_PID) }, { USB_DEVICE(FTDI_VID, MJSG_XM_RADIO_PID) }, - { USB_DEVICE(FTDI_VID, XVERVE_SIGNALYZER_ST_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(FTDI_VID, XVERVE_SIGNALYZER_SLITE_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(FTDI_VID, XVERVE_SIGNALYZER_SH2_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, XVERVE_SIGNALYZER_ST_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, XVERVE_SIGNALYZER_SLITE_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, XVERVE_SIGNALYZER_SH2_PID, 1) }, { USB_DEVICE(FTDI_VID, XVERVE_SIGNALYZER_SH4_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(FTDI_VID, SEGWAY_RMP200_PID) }, { USB_DEVICE(FTDI_VID, ACCESIO_COM4SM_PID) }, - { USB_DEVICE(IONICS_VID, IONICS_PLUGCOMPUTER_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(IONICS_VID, IONICS_PLUGCOMPUTER_PID, 1) }, { USB_DEVICE(FTDI_VID, FTDI_CHAMSYS_24_MASTER_WING_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CHAMSYS_PC_WING_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CHAMSYS_USB_DMX_PID) }, @@ -972,15 +955,12 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_CINTERION_MC55I_PID) }, { USB_DEVICE(FTDI_VID, FTDI_FHE_PID) }, { USB_DEVICE(FTDI_VID, FTDI_DOTEC_PID) }, - { USB_DEVICE(QIHARDWARE_VID, MILKYMISTONE_JTAGSERIAL_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(ST_VID, ST_STMCLT_2232_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(QIHARDWARE_VID, MILKYMISTONE_JTAGSERIAL_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(ST_VID, ST_STMCLT_2232_PID, 1) }, { USB_DEVICE(ST_VID, ST_STMCLT_4232_PID), .driver_info = (kernel_ulong_t)&ftdi_stmclite_quirk }, { USB_DEVICE(FTDI_VID, FTDI_RF_R106) }, - { USB_DEVICE(FTDI_VID, FTDI_DISTORTEC_JTAG_LOCK_PICK_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, FTDI_DISTORTEC_JTAG_LOCK_PICK_PID, 1) }, { USB_DEVICE(FTDI_VID, FTDI_LUMEL_PD12_PID) }, /* Crucible Devices */ { USB_DEVICE(FTDI_VID, FTDI_CT_COMET_PID) }, @@ -1055,8 +1035,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(ICPDAS_VID, ICPDAS_I7561U_PID) }, { USB_DEVICE(ICPDAS_VID, ICPDAS_I7563U_PID) }, { USB_DEVICE(WICED_VID, WICED_USB20706V2_PID) }, - { USB_DEVICE(TI_VID, TI_CC3200_LAUNCHPAD_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(TI_VID, TI_CC3200_LAUNCHPAD_PID, 1) }, { USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_BT_USB_PID) }, { USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_WL_USB_PID) }, { USB_DEVICE(AIRBUS_DS_VID, AIRBUS_DS_P8GR) }, @@ -1076,10 +1055,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(UBLOX_VID, UBLOX_C099F9P_ODIN_PID) }, { USB_DEVICE_INTERFACE_NUMBER(UBLOX_VID, UBLOX_EVK_M101_PID, 2) }, /* FreeCalypso USB adapters */ - { USB_DEVICE(FTDI_VID, FTDI_FALCONIA_JTAG_BUF_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, - { USB_DEVICE(FTDI_VID, FTDI_FALCONIA_JTAG_UNBUF_PID), - .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, FTDI_FALCONIA_JTAG_BUF_PID, 1) }, + { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, FTDI_FALCONIA_JTAG_UNBUF_PID, 1) }, /* GMC devices */ { USB_DEVICE(GMC_VID, GMC_Z216C_PID) }, /* Altera USB Blaster 3 */ diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 2539b9e2f712c3..6c76cfebfd0e42 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -96,6 +96,8 @@ #define LMI_LM3S_EVAL_BOARD_PID 0xbcd9 #define LMI_LM3S_ICDI_BOARD_PID 0xbcda +#define FTDI_AXE027_PID 0xBD90 /* PICAXE AXE027 USB download cable */ + #define FTDI_TURTELIZER_PID 0xBDC8 /* JTAG/RS-232 adapter by egnite GmbH */ /* OpenDCC (www.opendcc.de) product id */ diff --git a/drivers/usb/serial/kobil_sct.c b/drivers/usb/serial/kobil_sct.c index 464433be203443..96ea571c436a71 100644 --- a/drivers/usb/serial/kobil_sct.c +++ b/drivers/usb/serial/kobil_sct.c @@ -418,7 +418,7 @@ static int kobil_tiocmset(struct tty_struct *tty, struct usb_serial_port *port = tty->driver_data; struct device *dev = &port->dev; struct kobil_private *priv; - int result; + int result = 0; int dtr = 0; int rts = 0; @@ -435,12 +435,12 @@ static int kobil_tiocmset(struct tty_struct *tty, if (set & TIOCM_DTR) dtr = 1; if (clear & TIOCM_RTS) - rts = 0; + rts = 1; if (clear & TIOCM_DTR) - dtr = 0; + dtr = 1; - if (priv->device_type == KOBIL_ADAPTER_B_PRODUCT_ID) { - if (dtr != 0) + if (dtr && priv->device_type == KOBIL_ADAPTER_B_PRODUCT_ID) { + if (set & TIOCM_DTR) dev_dbg(dev, "%s - Setting DTR\n", __func__); else dev_dbg(dev, "%s - Clearing DTR\n", __func__); @@ -448,13 +448,13 @@ static int kobil_tiocmset(struct tty_struct *tty, usb_sndctrlpipe(port->serial->dev, 0), SUSBCRequest_SetStatusLinesOrQueues, USB_TYPE_VENDOR | USB_RECIP_ENDPOINT | USB_DIR_OUT, - ((dtr != 0) ? SUSBCR_SSL_SETDTR : SUSBCR_SSL_CLRDTR), + ((set & TIOCM_DTR) ? SUSBCR_SSL_SETDTR : SUSBCR_SSL_CLRDTR), 0, NULL, 0, KOBIL_TIMEOUT); - } else { - if (rts != 0) + } else if (rts) { + if (set & TIOCM_RTS) dev_dbg(dev, "%s - Setting RTS\n", __func__); else dev_dbg(dev, "%s - Clearing RTS\n", __func__); @@ -462,7 +462,7 @@ static int kobil_tiocmset(struct tty_struct *tty, usb_sndctrlpipe(port->serial->dev, 0), SUSBCRequest_SetStatusLinesOrQueues, USB_TYPE_VENDOR | USB_RECIP_ENDPOINT | USB_DIR_OUT, - ((rts != 0) ? SUSBCR_SSL_SETRTS : SUSBCR_SSL_CLRRTS), + ((set & TIOCM_RTS) ? SUSBCR_SSL_SETRTS : SUSBCR_SSL_CLRRTS), 0, NULL, 0, diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index e9400727ad36eb..d4505a4264460b 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1401,12 +1401,16 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a0, 0xff), /* Telit FN20C04 (rmnet) */ .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a1, 0xff), /* Telit FN20C04 (RNDIS) */ + .driver_info = NCTRL(4) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a2, 0xff), /* Telit FN920C04 (MBIM) */ .driver_info = NCTRL(4) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a3, 0xff), /* Telit FN920C04 (ECM) */ .driver_info = NCTRL(4) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a4, 0xff), /* Telit FN20C04 (rmnet) */ .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a6, 0xff), /* Telit FN920C04 (RNDIS) */ + .driver_info = NCTRL(4) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a7, 0xff), /* Telit FN920C04 (MBIM) */ .driver_info = NCTRL(4) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a8, 0xff), /* Telit FN920C04 (ECM) */ @@ -1415,6 +1419,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10aa, 0xff), /* Telit FN920C04 (MBIM) */ .driver_info = NCTRL(3) | RSVD(4) | RSVD(5) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10ab, 0xff), /* Telit FN920C04 (RNDIS) */ + .driver_info = NCTRL(3) | RSVD(4) | RSVD(5) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b0, 0xff, 0xff, 0x30), /* Telit FE990B (rmnet) */ .driver_info = NCTRL(5) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b0, 0xff, 0xff, 0x40) }, @@ -1433,17 +1439,31 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b3, 0xff, 0xff, 0x60) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c0, 0xff), /* Telit FE910C04 (rmnet) */ .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c1, 0xff), /* Telit FE910C04 (RNDIS) */ + .driver_info = NCTRL(4) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c2, 0xff), /* Telit FE910C04 (MBIM) */ + .driver_info = NCTRL(4) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c3, 0xff), /* Telit FE910C04 (ECM) */ + .driver_info = NCTRL(4) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c4, 0xff), /* Telit FE910C04 (rmnet) */ .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c5, 0xff), /* Telit FE910C04 (RNDIS) */ + .driver_info = NCTRL(4) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c6, 0xff), /* Telit FE910C04 (MBIM) */ + .driver_info = NCTRL(4) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10c7, 0xff, 0xff, 0x30), /* Telit FE910C04 (ECM) */ + .driver_info = NCTRL(4) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10c7, 0xff, 0xff, 0x40) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c8, 0xff), /* Telit FE910C04 (rmnet) */ .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c9, 0xff), /* Telit FE910C04 (MBIM) */ + .driver_info = NCTRL(3) | RSVD(4) | RSVD(5) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10cb, 0xff), /* Telit FE910C04 (RNDIS) */ + .driver_info = NCTRL(3) | RSVD(4) | RSVD(5) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d0, 0xff, 0xff, 0x30), /* Telit FN990B (rmnet) */ .driver_info = NCTRL(5) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d0, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d0, 0xff, 0xff, 0x60) }, - { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10c7, 0xff, 0xff, 0x30), /* Telit FE910C04 (ECM) */ - .driver_info = NCTRL(4) }, - { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10c7, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d1, 0xff, 0xff, 0x30), /* Telit FN990B (MBIM) */ .driver_info = NCTRL(6) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d1, 0xff, 0xff, 0x40) }, @@ -1491,6 +1511,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1231, 0xff), /* Telit LE910Cx (RNDIS) */ .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x1250, 0xff, 0x00, 0x00) }, /* Telit LE910Cx (rmnet) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1252, 0xff) }, /* Telit LE910Cx (MBIM) */ { USB_DEVICE(TELIT_VENDOR_ID, 0x1260), .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE(TELIT_VENDOR_ID, 0x1261), @@ -2376,6 +2397,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0f0, 0xff), /* Foxconn T99W373 MBIM */ .driver_info = RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe123, 0xff), /* Foxconn T99W760 MBIM */ + .driver_info = RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe145, 0xff), /* Foxconn T99W651 RNDIS */ .driver_info = RSVD(5) | RSVD(6) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe15f, 0xff), /* Foxconn T99W709 */ diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 1477e31d776327..939a98c2d3f747 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -98,7 +98,7 @@ UNUSUAL_DEV(0x125f, 0xa94a, 0x0160, 0x0160, US_FL_NO_ATA_1X), /* Reported-by: Benjamin Tissoires */ -UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999, +UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x0309, "Initio Corporation", "INIC-3069", USB_SC_DEVICE, USB_PR_DEVICE, NULL, diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 1dcb77faf85d45..64627056045107 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -764,12 +764,16 @@ int dp_altmode_probe(struct typec_altmode *alt) if (!(DP_CAP_PIN_ASSIGN_DFP_D(port->vdo) & DP_CAP_PIN_ASSIGN_UFP_D(alt->vdo)) && !(DP_CAP_PIN_ASSIGN_UFP_D(port->vdo) & - DP_CAP_PIN_ASSIGN_DFP_D(alt->vdo))) + DP_CAP_PIN_ASSIGN_DFP_D(alt->vdo))) { + typec_altmode_put_plug(plug); return -ENODEV; + } dp = devm_kzalloc(&alt->dev, sizeof(*dp), GFP_KERNEL); - if (!dp) + if (!dp) { + typec_altmode_put_plug(plug); return -ENOMEM; + } INIT_WORK(&dp->work, dp_altmode_work); mutex_init(&dp->lock); diff --git a/drivers/usb/typec/tcpm/fusb302.c b/drivers/usb/typec/tcpm/fusb302.c index 870a71f953f6cd..19ff8217818e7e 100644 --- a/drivers/usb/typec/tcpm/fusb302.c +++ b/drivers/usb/typec/tcpm/fusb302.c @@ -1756,8 +1756,7 @@ static int fusb302_probe(struct i2c_client *client) } ret = request_irq(chip->gpio_int_n_irq, fusb302_irq_intn, - IRQF_ONESHOT | IRQF_TRIGGER_LOW, - "fsc_interrupt_int_n", chip); + IRQF_TRIGGER_LOW, "fsc_interrupt_int_n", chip); if (ret < 0) { dev_err(dev, "cannot request IRQ for GPIO Int_N, ret=%d", ret); goto tcpm_unregister_port; diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index cc78770509dbc6..37698204d48d25 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -7877,7 +7877,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) port->partner_desc.identity = &port->partner_ident; port->role_sw = fwnode_usb_role_switch_get(tcpc->fwnode); - if (!port->role_sw) + if (IS_ERR_OR_NULL(port->role_sw)) port->role_sw = usb_role_switch_get(port->dev); if (IS_ERR(port->role_sw)) { err = PTR_ERR(port->role_sw); diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 2b1049c9a6f3c4..923477105483b1 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -22,6 +22,8 @@ #include #include #include +#include +#include #include "tps6598x.h" #include "trace.h" @@ -47,6 +49,7 @@ #define TPS_REG_POWER_STATUS 0x3f #define TPS_REG_PD_STATUS 0x40 #define TPS_REG_RX_IDENTITY_SOP 0x48 +#define TPS_REG_TX_VDM 0x4d #define TPS_REG_CF_VID_STATUS 0x5e #define TPS_REG_DP_SID_STATUS 0x58 #define TPS_REG_INTEL_VID_STATUS 0x59 @@ -130,6 +133,7 @@ enum { TPS_MODE_BIST, TPS_MODE_DISC, TPS_MODE_PTCH, + CD_MODE_DBMA, }; static const char *const modes[] = { @@ -138,11 +142,14 @@ static const char *const modes[] = { [TPS_MODE_BIST] = "BIST", [TPS_MODE_DISC] = "DISC", [TPS_MODE_PTCH] = "PTCH", + [CD_MODE_DBMA] = "DBMa", }; /* Unrecognized commands will be replaced with "!CMD" */ #define INVALID_CMD(_cmd_) (_cmd_ == 0x444d4321) +#define TPS_VDMS_MAX_LEN (7 * 4 + 1) + struct tps6598x; struct tipd_data { @@ -168,6 +175,7 @@ struct tps6598x { struct regmap *regmap; struct mutex lock; /* device lock */ u8 i2c_protocol:1; + u8 cd321x_unlocked:1; struct gpio_desc *reset; struct typec_port *port; @@ -577,30 +585,36 @@ static bool cd321x_read_data_status(struct tps6598x *tps) int ret; ret = tps6598x_read_data_status(tps); - if (ret < 0) + if (!ret) return false; if (tps->data_status & TPS_DATA_STATUS_DP_CONNECTION) { ret = tps6598x_block_read(tps, TPS_REG_DP_SID_STATUS, &cd321x->dp_sid_status, sizeof(cd321x->dp_sid_status)); - if (ret) + if (ret) { dev_err(tps->dev, "Failed to read DP SID Status: %d\n", ret); + return false; + } } if (tps->data_status & TPS_DATA_STATUS_TBT_CONNECTION) { ret = tps6598x_block_read(tps, TPS_REG_INTEL_VID_STATUS, &cd321x->intel_vid_status, sizeof(cd321x->intel_vid_status)); - if (ret) + if (ret) { dev_err(tps->dev, "Failed to read Intel VID Status: %d\n", ret); + return false; + } } if (tps->data_status & CD321X_DATA_STATUS_USB4_CONNECTION) { ret = tps6598x_block_read(tps, TPS_REG_USB4_STATUS, &cd321x->usb4_status, sizeof(cd321x->usb4_status)); - if (ret) + if (ret) { dev_err(tps->dev, "Failed to read USB4 Status: %d\n", ret); + return false; + } } return true; @@ -1070,6 +1084,8 @@ static int tps6598x_check_mode(struct tps6598x *tps) return ret; case TPS_MODE_BIST: case TPS_MODE_DISC: + case CD_MODE_DBMA: + return ret; default: dev_err(tps->dev, "controller in unsupported mode \"%s\"\n", mode); @@ -1625,6 +1641,175 @@ static int tps6598x_apply_patch(struct tps6598x *tps) return ret; } + +static ssize_t lock_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + struct tps6598x *tps = i2c_get_clientdata(client); + + if (tps->cd321x_unlocked) + return sysfs_emit(buf, "unlocked\n"); + else + return sysfs_emit(buf, "locked\n"); +} +static DEVICE_ATTR_RO(lock); + +static ssize_t mode_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + struct tps6598x *tps = i2c_get_clientdata(client); + + int mode = tps6598x_check_mode(tps); + switch (mode) { + case TPS_MODE_APP ... CD_MODE_DBMA: + return sysfs_emit(buf, "%s\n", modes[mode]); + default: + return sysfs_emit(buf, "unkown\n"); + } +} +static DEVICE_ATTR_RO(mode); + +static ssize_t power_status_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + struct tps6598x *tps = i2c_get_clientdata(client); + + return sysfs_emit(buf, "0x%04hx\n", tps->pwr_status); +} +static DEVICE_ATTR_RO(power_status); + +/* this assumes cd321x has a customized UnlockCode */ +static ssize_t commad_lock(struct tps6598x *tps, const char *buf, size_t count) +{ + const char default_code[4] = { 0, 0, 0, 0 }; + int ret; + + if (count < 4) + return -EINVAL; + + ret = tps6598x_exec_cmd(tps, "LOCK", 4, buf, 0, NULL); + if (ret) + dev_err(tps->dev, "Unlock command failed: %d\n", ret); + else + /* Key 0 locks cd321x when UnlockCode is customized */ + tps->cd321x_unlocked = !!memcmp(buf, default_code, 4); + + return count; +} + +static ssize_t commad_dbma(struct tps6598x *tps, const char *buf, size_t count) +{ + int ret, mode; + bool enable; + + if (count < 1) + return -EINVAL; + + enable = buf[0] != 0; + + if (enable && !tps->cd321x_unlocked) + return -EINVAL; + + ret = tps6598x_exec_cmd(tps, "DBMa", 1, buf, 0, NULL); + if (ret) { + dev_err(tps->dev, "Failed to exec 'DBMa' command: %d\n", ret); + return ret; + } + + mode = tps6598x_check_mode(tps); + if (enable && mode != CD_MODE_DBMA) { + dev_err(tps->dev, "CD321x failed to enter \"DBMa\" mode\n"); + return -EIO; + } else if (!enable && mode != TPS_MODE_APP) { + dev_err(tps->dev, "CD321x failed to exit \"DBMa\" mode\n"); + return -EIO; + } + + return count; +} + +static ssize_t commad_vdms(struct tps6598x *tps, const char *buf, size_t count) +{ + int ret; + + if (count < 5 || ((count -1) % 4) != 0 || count > TPS_VDMS_MAX_LEN) + return -EINVAL; + + if (tps6598x_check_mode(tps) != CD_MODE_DBMA) + return -EIO; + + ret = tps6598x_exec_cmd_tmo(tps, "VDMs", count, buf, 0, NULL, 200, 200); + if (ret) { + dev_err(tps->dev, "Sending VDM failed: %d\n", ret); + return ret; + } + + return count; +} + +static ssize_t commad_devn(struct tps6598x *tps, const char *buf, size_t count) +{ + int ret; + + if (count < 4) + return -EINVAL; + + if (tps6598x_check_mode(tps) != CD_MODE_DBMA) + return -EIO; + + ret = tps6598x_exec_cmd(tps, "DVEn", 4, buf, 0, NULL); + if (ret) + dev_err(tps->dev, "Could not enter local serial mode: %d\n", + ret); + + return count; +} + +#define CMD_LEN 4 +static ssize_t command_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct i2c_client *client = to_i2c_client(dev); + struct tps6598x *tps = i2c_get_clientdata(client); + int ret; + + if (count < CMD_LEN) + return -EINVAL; + + if (memcmp(buf, "LOCK", CMD_LEN) == 0) + ret = commad_lock(tps, buf + 4, count - 4); + else if (memcmp(buf, "DBMa", CMD_LEN) == 0) + ret = commad_dbma(tps, buf + 4, count - 4); + else if (memcmp(buf, "VDMs", CMD_LEN) == 0) + ret = commad_vdms(tps, buf + 4, count - 4); + else if (memcmp(buf, "DEVn", CMD_LEN) == 0) + ret = commad_devn(tps, buf + 4, count - 4); + else + return -EINVAL; + + if (ret < 0) + return ret; + + return ret + CMD_LEN; +} +static DEVICE_ATTR_WO(command); + +static struct attribute *vdm_attrs[] = { + &dev_attr_lock.attr, + &dev_attr_mode.attr, + &dev_attr_power_status.attr, + &dev_attr_command.attr, + NULL, +}; + +static const struct attribute_group vdm_group = { + .name = "cd321x_vdm", + .attrs = vdm_attrs, +}; + static int cd321x_init(struct tps6598x *tps) { return 0; @@ -1695,6 +1880,7 @@ tps25750_register_port(struct tps6598x *tps, struct fwnode_handle *fwnode) typec_cap.data = ret; typec_cap.revision = USB_TYPEC_REV_1_3; typec_cap.pd_revision = 0x300; + typec_cap.orientation_aware = true; typec_cap.driver_data = tps; typec_cap.ops = &tps6598x_ops; typec_cap.fwnode = fwnode; @@ -1859,6 +2045,14 @@ static int tps6598x_probe(struct i2c_client *client) enable_irq_wake(client->irq); } + if (device_is_compatible(tps->dev, "apple,cd321x")) { + int err; + err = sysfs_create_group(&client->dev.kobj, &vdm_group); + if (err < 0) + dev_err(tps->dev, "Couldn't register sysfs group for " + "CD321x VDMs\n"); + } + return 0; err_disconnect: @@ -1882,6 +2076,9 @@ static void tps6598x_remove(struct i2c_client *client) { struct tps6598x *tps = i2c_get_clientdata(client); + if (device_is_compatible(tps->dev, "apple,cd321x")) + sysfs_remove_group(&client->dev.kobj, &vdm_group); + if (!client->irq) cancel_delayed_work_sync(&tps->wq_poll); else diff --git a/drivers/usb/typec/ucsi/Kconfig b/drivers/usb/typec/ucsi/Kconfig index 7fcb1e1de5d6d1..87dd992a4b9e9a 100644 --- a/drivers/usb/typec/ucsi/Kconfig +++ b/drivers/usb/typec/ucsi/Kconfig @@ -73,7 +73,6 @@ config CROS_EC_UCSI tristate "UCSI Driver for ChromeOS EC" depends on MFD_CROS_EC_DEV depends on CROS_USBPD_NOTIFY - depends on !EXTCON_TCSS_CROS_EC default MFD_CROS_EC_DEV help This driver enables UCSI support for a ChromeOS EC. The EC is @@ -96,6 +95,7 @@ config UCSI_LENOVO_YOGA_C630 config UCSI_HUAWEI_GAOKUN tristate "UCSI Interface Driver for Huawei Matebook E Go" depends on EC_HUAWEI_GAOKUN + depends on DRM || !DRM select DRM_AUX_HPD_BRIDGE if DRM_BRIDGE && OF help This driver enables UCSI support on the Huawei Matebook E Go tablet, diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 3f568f790f39b0..3995483a0aa097 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -1807,6 +1807,12 @@ static int ucsi_init(struct ucsi *ucsi) ret = -ENODEV; goto err_reset; } + /* Check if reserved bit set. This is out of spec but happens in buggy FW */ + if (ucsi->cap.num_connectors & 0x80) { + dev_warn(ucsi->dev, "UCSI: Invalid num_connectors %d. Likely buggy FW\n", + ucsi->cap.num_connectors); + ucsi->cap.num_connectors &= 0x7f; // clear bit and carry on + } /* Allocate the connectors. Released in ucsi_unregister() */ connector = kcalloc(ucsi->cap.num_connectors + 1, sizeof(*connector), GFP_KERNEL); diff --git a/drivers/usb/typec/ucsi/ucsi_huawei_gaokun.c b/drivers/usb/typec/ucsi/ucsi_huawei_gaokun.c index 7b5222081bbb54..c5965656babadd 100644 --- a/drivers/usb/typec/ucsi/ucsi_huawei_gaokun.c +++ b/drivers/usb/typec/ucsi/ucsi_huawei_gaokun.c @@ -196,6 +196,7 @@ static void gaokun_ucsi_connector_status(struct ucsi_connector *con) const struct ucsi_operations gaokun_ucsi_ops = { .read_version = gaokun_ucsi_read_version, .read_cci = gaokun_ucsi_read_cci, + .poll_cci = gaokun_ucsi_read_cci, .read_message_in = gaokun_ucsi_read_message_in, .sync_control = ucsi_sync_control_common, .async_control = gaokun_ucsi_async_control, @@ -502,6 +503,7 @@ static void gaokun_ucsi_remove(struct auxiliary_device *adev) { struct gaokun_ucsi *uec = auxiliary_get_drvdata(adev); + disable_delayed_work_sync(&uec->work); gaokun_ec_unregister_notify(uec->ec, &uec->nb); ucsi_unregister(uec->ucsi); ucsi_destroy(uec->ucsi); diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index 0d6c10a8490c0b..f7e405abe60849 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -831,15 +831,15 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag no_need_xmit: usb_hcd_unlink_urb_from_ep(hcd, urb); no_need_unlink: - spin_unlock_irqrestore(&vhci->lock, flags); if (!ret) { /* usb_hcd_giveback_urb() should be called with * irqs disabled */ - local_irq_disable(); + spin_unlock(&vhci->lock); usb_hcd_giveback_urb(hcd, urb, urb->status); - local_irq_enable(); + spin_lock(&vhci->lock); } + spin_unlock_irqrestore(&vhci->lock, flags); return ret; } diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index a7936bd1aabe17..ddaa1366704bb0 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1256,7 +1256,7 @@ static int query_virtqueues(struct mlx5_vdpa_net *ndev, int vq_idx = start_vq + i; if (cmd->err) { - mlx5_vdpa_err(mvdev, "query vq %d failed, err: %d\n", vq_idx, err); + mlx5_vdpa_err(mvdev, "query vq %d failed, err: %d\n", vq_idx, cmd->err); if (!err) err = cmd->err; continue; diff --git a/drivers/vdpa/octeon_ep/octep_vdpa_main.c b/drivers/vdpa/octeon_ep/octep_vdpa_main.c index 9e8d07078606f3..31a02e7fd7f279 100644 --- a/drivers/vdpa/octeon_ep/octep_vdpa_main.c +++ b/drivers/vdpa/octeon_ep/octep_vdpa_main.c @@ -736,6 +736,7 @@ static int octep_sriov_enable(struct pci_dev *pdev, int num_vfs) octep_vdpa_assign_barspace(vf_pdev, pdev, index); if (++index == num_vfs) { done = true; + pci_dev_put(vf_pdev); break; } } diff --git a/drivers/vdpa/pds/vdpa_dev.c b/drivers/vdpa/pds/vdpa_dev.c index 36f61cc96e2110..43426bd971acc9 100644 --- a/drivers/vdpa/pds/vdpa_dev.c +++ b/drivers/vdpa/pds/vdpa_dev.c @@ -51,7 +51,7 @@ static int pds_vdpa_register_event_handler(struct pds_vdpa_device *pdsv) err = pdsc_register_notify(nb); if (err) { nb->notifier_call = NULL; - dev_err(dev, "failed to register pds event handler: %ps\n", + dev_err(dev, "failed to register pds event handler: %pe\n", ERR_PTR(err)); return -EINVAL; } diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c index 480cac3a0c274f..8ceca24ac136c6 100644 --- a/drivers/vfio/device_cdev.c +++ b/drivers/vfio/device_cdev.c @@ -99,7 +99,7 @@ long vfio_df_ioctl_bind_iommufd(struct vfio_device_file *df, return ret; if (user_size < minsz) return -EINVAL; - ret = copy_struct_from_user(&bind, minsz, arg, user_size); + ret = copy_struct_from_user(&bind, sizeof(bind), arg, user_size); if (ret) return ret; diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c index fde33f54e99ec5..ed2ae035deb167 100644 --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c @@ -1169,9 +1169,32 @@ hisi_acc_vfio_pci_get_device_state(struct vfio_device *vdev, return 0; } +static void hisi_acc_vf_pci_reset_prepare(struct pci_dev *pdev) +{ + struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_drvdata(pdev); + struct hisi_qm *qm = hisi_acc_vdev->pf_qm; + struct device *dev = &qm->pdev->dev; + u32 delay = 0; + + /* All reset requests need to be queued for processing */ + while (test_and_set_bit(QM_RESETTING, &qm->misc_ctl)) { + msleep(1); + if (++delay > QM_RESET_WAIT_TIMEOUT) { + dev_err(dev, "reset prepare failed\n"); + return; + } + } + + hisi_acc_vdev->set_reset_flag = true; +} + static void hisi_acc_vf_pci_aer_reset_done(struct pci_dev *pdev) { struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_drvdata(pdev); + struct hisi_qm *qm = hisi_acc_vdev->pf_qm; + + if (hisi_acc_vdev->set_reset_flag) + clear_bit(QM_RESETTING, &qm->misc_ctl); if (hisi_acc_vdev->core_device.vdev.migration_flags != VFIO_MIGRATION_STOP_COPY) @@ -1564,6 +1587,7 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_migrn_ops = { .mmap = hisi_acc_vfio_pci_mmap, .request = vfio_pci_core_request, .match = vfio_pci_core_match, + .match_token_uuid = vfio_pci_core_match_token_uuid, .bind_iommufd = vfio_iommufd_physical_bind, .unbind_iommufd = vfio_iommufd_physical_unbind, .attach_ioas = vfio_iommufd_physical_attach_ioas, @@ -1689,6 +1713,7 @@ static const struct pci_device_id hisi_acc_vfio_pci_table[] = { MODULE_DEVICE_TABLE(pci, hisi_acc_vfio_pci_table); static const struct pci_error_handlers hisi_acc_vf_err_handlers = { + .reset_prepare = hisi_acc_vf_pci_reset_prepare, .reset_done = hisi_acc_vf_pci_aer_reset_done, .error_detected = vfio_pci_core_aer_err_detected, }; diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h index 91002ceeebc18a..6253fa074003ea 100644 --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h @@ -27,6 +27,7 @@ #define ERROR_CHECK_TIMEOUT 100 #define CHECK_DELAY_TIME 100 +#define QM_RESET_WAIT_TIMEOUT 60000 #define QM_SQC_VFT_BASE_SHIFT_V2 28 #define QM_SQC_VFT_BASE_MASK_V2 GENMASK(15, 0) @@ -110,6 +111,7 @@ struct hisi_acc_vf_migration_file { struct hisi_acc_vf_core_device { struct vfio_pci_core_device core_device; u8 match_done; + bool set_reset_flag; /* * io_base is only valid when dev_opened is true, * which is protected by open_mutex. diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index e346392b72f6ab..3dc3c2432b5e08 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -491,7 +491,7 @@ nvgrace_gpu_map_and_read(struct nvgrace_gpu_pci_core_device *nvdev, ret = vfio_pci_core_do_io_rw(&nvdev->core_device, false, nvdev->resmem.ioaddr, buf, offset, mem_count, - 0, 0, false); + 0, 0, false, VFIO_PCI_IO_WIDTH_8); } return ret; @@ -609,7 +609,7 @@ nvgrace_gpu_map_and_write(struct nvgrace_gpu_pci_core_device *nvdev, ret = vfio_pci_core_do_io_rw(&nvdev->core_device, false, nvdev->resmem.ioaddr, (char __user *)buf, pos, mem_count, - 0, 0, true); + 0, 0, true, VFIO_PCI_IO_WIDTH_8); } return ret; diff --git a/drivers/vfio/pci/pds/dirty.c b/drivers/vfio/pci/pds/dirty.c index 481992142f7901..4915a7c1c4916d 100644 --- a/drivers/vfio/pci/pds/dirty.c +++ b/drivers/vfio/pci/pds/dirty.c @@ -292,8 +292,11 @@ static int pds_vfio_dirty_enable(struct pds_vfio_pci_device *pds_vfio, len = num_ranges * sizeof(*region_info); node = interval_tree_iter_first(ranges, 0, ULONG_MAX); - if (!node) - return -EINVAL; + if (!node) { + err = -EINVAL; + goto out_free_region_info; + } + for (int i = 0; i < num_ranges; i++) { struct pds_lm_dirty_region_info *ri = ®ion_info[i]; u64 region_size = node->last - node->start + 1; diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 7dcf5439dedc9d..085373d71e9c24 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -41,6 +41,40 @@ static bool nointxmask; static bool disable_vga; static bool disable_idle_d3; +static void vfio_pci_eventfd_rcu_free(struct rcu_head *rcu) +{ + struct vfio_pci_eventfd *eventfd = + container_of(rcu, struct vfio_pci_eventfd, rcu); + + eventfd_ctx_put(eventfd->ctx); + kfree(eventfd); +} + +int vfio_pci_eventfd_replace_locked(struct vfio_pci_core_device *vdev, + struct vfio_pci_eventfd __rcu **peventfd, + struct eventfd_ctx *ctx) +{ + struct vfio_pci_eventfd *new = NULL; + struct vfio_pci_eventfd *old; + + lockdep_assert_held(&vdev->igate); + + if (ctx) { + new = kzalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); + if (!new) + return -ENOMEM; + + new->ctx = ctx; + } + + old = rcu_replace_pointer(*peventfd, new, + lockdep_is_held(&vdev->igate)); + if (old) + call_rcu(&old->rcu, vfio_pci_eventfd_rcu_free); + + return 0; +} + /* List of PF's that vfio_pci_core_sriov_configure() has been called on */ static DEFINE_MUTEX(vfio_pci_sriov_pfs_mutex); static LIST_HEAD(vfio_pci_sriov_pfs); @@ -555,6 +589,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_enable); void vfio_pci_core_disable(struct vfio_pci_core_device *vdev) { + struct pci_dev *bridge; struct pci_dev *pdev = vdev->pdev; struct vfio_pci_dummy_resource *dummy_res, *tmp; struct vfio_pci_ioeventfd *ioeventfd, *ioeventfd_tmp; @@ -661,12 +696,20 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev) * We can not use the "try" reset interface here, which will * overwrite the previously restored configuration information. */ - if (vdev->reset_works && pci_dev_trylock(pdev)) { - if (!__pci_reset_function_locked(pdev)) - vdev->needs_reset = false; - pci_dev_unlock(pdev); + if (vdev->reset_works) { + bridge = pci_upstream_bridge(pdev); + if (bridge && !pci_dev_trylock(bridge)) + goto out_restore_state; + if (pci_dev_trylock(pdev)) { + if (!__pci_reset_function_locked(pdev)) + vdev->needs_reset = false; + pci_dev_unlock(pdev); + } + if (bridge) + pci_dev_unlock(bridge); } +out_restore_state: pci_restore_state(pdev); out: pci_disable_device(pdev); @@ -696,14 +739,8 @@ void vfio_pci_core_close_device(struct vfio_device *core_vdev) vfio_pci_core_disable(vdev); mutex_lock(&vdev->igate); - if (vdev->err_trigger) { - eventfd_ctx_put(vdev->err_trigger); - vdev->err_trigger = NULL; - } - if (vdev->req_trigger) { - eventfd_ctx_put(vdev->req_trigger); - vdev->req_trigger = NULL; - } + vfio_pci_eventfd_replace_locked(vdev, &vdev->err_trigger, NULL); + vfio_pci_eventfd_replace_locked(vdev, &vdev->req_trigger, NULL); mutex_unlock(&vdev->igate); } EXPORT_SYMBOL_GPL(vfio_pci_core_close_device); @@ -1800,21 +1837,21 @@ void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count) struct vfio_pci_core_device *vdev = container_of(core_vdev, struct vfio_pci_core_device, vdev); struct pci_dev *pdev = vdev->pdev; + struct vfio_pci_eventfd *eventfd; - mutex_lock(&vdev->igate); - - if (vdev->req_trigger) { + rcu_read_lock(); + eventfd = rcu_dereference(vdev->req_trigger); + if (eventfd) { if (!(count % 10)) pci_notice_ratelimited(pdev, "Relaying device request to user (#%u)\n", count); - eventfd_signal(vdev->req_trigger); + eventfd_signal(eventfd->ctx); } else if (count == 0) { pci_warn(pdev, "No device request channel registered, blocked until released by user\n"); } - - mutex_unlock(&vdev->igate); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(vfio_pci_core_request); @@ -2227,13 +2264,13 @@ pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, pci_channel_state_t state) { struct vfio_pci_core_device *vdev = dev_get_drvdata(&pdev->dev); + struct vfio_pci_eventfd *eventfd; - mutex_lock(&vdev->igate); - - if (vdev->err_trigger) - eventfd_signal(vdev->err_trigger); - - mutex_unlock(&vdev->igate); + rcu_read_lock(); + eventfd = rcu_dereference(vdev->err_trigger); + if (eventfd) + eventfd_signal(eventfd->ctx); + rcu_read_unlock(); return PCI_ERS_RESULT_CAN_RECOVER; } diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 30d3e921cb0deb..c76e753b3cecd6 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -731,21 +731,27 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_core_device *vdev, return 0; } -static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx, +static int vfio_pci_set_ctx_trigger_single(struct vfio_pci_core_device *vdev, + struct vfio_pci_eventfd __rcu **peventfd, unsigned int count, uint32_t flags, void *data) { /* DATA_NONE/DATA_BOOL enables loopback testing */ if (flags & VFIO_IRQ_SET_DATA_NONE) { - if (*ctx) { - if (count) { - eventfd_signal(*ctx); - } else { - eventfd_ctx_put(*ctx); - *ctx = NULL; - } + struct vfio_pci_eventfd *eventfd; + + eventfd = rcu_dereference_protected(*peventfd, + lockdep_is_held(&vdev->igate)); + + if (!eventfd) + return -EINVAL; + + if (count) { + eventfd_signal(eventfd->ctx); return 0; } + + return vfio_pci_eventfd_replace_locked(vdev, peventfd, NULL); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { uint8_t trigger; @@ -753,8 +759,15 @@ static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx, return -EINVAL; trigger = *(uint8_t *)data; - if (trigger && *ctx) - eventfd_signal(*ctx); + + if (trigger) { + struct vfio_pci_eventfd *eventfd = + rcu_dereference_protected(*peventfd, + lockdep_is_held(&vdev->igate)); + + if (eventfd) + eventfd_signal(eventfd->ctx); + } return 0; } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { @@ -765,22 +778,23 @@ static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx, fd = *(int32_t *)data; if (fd == -1) { - if (*ctx) - eventfd_ctx_put(*ctx); - *ctx = NULL; + return vfio_pci_eventfd_replace_locked(vdev, + peventfd, NULL); } else if (fd >= 0) { struct eventfd_ctx *efdctx; + int ret; efdctx = eventfd_ctx_fdget(fd); if (IS_ERR(efdctx)) return PTR_ERR(efdctx); - if (*ctx) - eventfd_ctx_put(*ctx); + ret = vfio_pci_eventfd_replace_locked(vdev, + peventfd, efdctx); + if (ret) + eventfd_ctx_put(efdctx); - *ctx = efdctx; + return ret; } - return 0; } return -EINVAL; @@ -793,7 +807,7 @@ static int vfio_pci_set_err_trigger(struct vfio_pci_core_device *vdev, if (index != VFIO_PCI_ERR_IRQ_INDEX || start != 0 || count > 1) return -EINVAL; - return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger, + return vfio_pci_set_ctx_trigger_single(vdev, &vdev->err_trigger, count, flags, data); } @@ -804,7 +818,7 @@ static int vfio_pci_set_req_trigger(struct vfio_pci_core_device *vdev, if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count > 1) return -EINVAL; - return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger, + return vfio_pci_set_ctx_trigger_single(vdev, &vdev->req_trigger, count, flags, data); } diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h index a9972eacb2936b..97d992c063229d 100644 --- a/drivers/vfio/pci/vfio_pci_priv.h +++ b/drivers/vfio/pci/vfio_pci_priv.h @@ -26,6 +26,10 @@ struct vfio_pci_ioeventfd { bool vfio_pci_intx_mask(struct vfio_pci_core_device *vdev); void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev); +int vfio_pci_eventfd_replace_locked(struct vfio_pci_core_device *vdev, + struct vfio_pci_eventfd __rcu **peventfd, + struct eventfd_ctx *ctx); + int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev, uint32_t flags, unsigned index, unsigned start, unsigned count, void *data); diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index 6192788c8ba39f..25380b7dfe18a7 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -135,7 +135,8 @@ VFIO_IORDWR(64) ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, void __iomem *io, char __user *buf, loff_t off, size_t count, size_t x_start, - size_t x_end, bool iswrite) + size_t x_end, bool iswrite, + enum vfio_pci_io_width max_width) { ssize_t done = 0; int ret; @@ -150,20 +151,19 @@ ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, else fillable = 0; - if (fillable >= 8 && !(off % 8)) { + if (fillable >= 8 && !(off % 8) && max_width >= 8) { ret = vfio_pci_iordwr64(vdev, iswrite, test_mem, io, buf, off, &filled); if (ret) return ret; - } else - if (fillable >= 4 && !(off % 4)) { + } else if (fillable >= 4 && !(off % 4) && max_width >= 4) { ret = vfio_pci_iordwr32(vdev, iswrite, test_mem, io, buf, off, &filled); if (ret) return ret; - } else if (fillable >= 2 && !(off % 2)) { + } else if (fillable >= 2 && !(off % 2) && max_width >= 2) { ret = vfio_pci_iordwr16(vdev, iswrite, test_mem, io, buf, off, &filled); if (ret) @@ -234,6 +234,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, void __iomem *io; struct resource *res = &vdev->pdev->resource[bar]; ssize_t done; + enum vfio_pci_io_width max_width = VFIO_PCI_IO_WIDTH_8; if (pci_resource_start(pdev, bar)) end = pci_resource_len(pdev, bar); @@ -262,6 +263,16 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, if (!io) return -ENOMEM; x_end = end; + + /* + * Certain devices (e.g. Intel X710) don't support qword + * access to the ROM bar. Otherwise PCI AER errors might be + * triggered. + * + * Disable qword access to the ROM bar universally, which + * worked reliably for years before qword access is enabled. + */ + max_width = VFIO_PCI_IO_WIDTH_4; } else { int ret = vfio_pci_core_setup_barmap(vdev, bar); if (ret) { @@ -278,7 +289,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, } done = vfio_pci_core_do_io_rw(vdev, res->flags & IORESOURCE_MEM, io, buf, pos, - count, x_start, x_end, iswrite); + count, x_start, x_end, iswrite, max_width); if (done >= 0) *ppos += done; @@ -352,7 +363,7 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, * to the memory enable bit in the command register. */ done = vfio_pci_core_do_io_rw(vdev, false, iomem, buf, off, count, - 0, 0, iswrite); + 0, 0, iswrite, VFIO_PCI_IO_WIDTH_8); vga_put(vdev->pdev, rsrc); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 8f7f50acb6d63d..1e77c0482b849c 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -69,7 +69,7 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;" #define VHOST_DMA_IS_DONE(len) ((__force u32)(len) >= (__force u32)VHOST_DMA_DONE_LEN) -static const u64 vhost_net_features[VIRTIO_FEATURES_DWORDS] = { +static const u64 vhost_net_features[VIRTIO_FEATURES_U64S] = { VHOST_FEATURES | (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) | (1ULL << VIRTIO_NET_F_MRG_RXBUF) | @@ -1731,7 +1731,7 @@ static long vhost_net_set_owner(struct vhost_net *n) static long vhost_net_ioctl(struct file *f, unsigned int ioctl, unsigned long arg) { - u64 all_features[VIRTIO_FEATURES_DWORDS]; + u64 all_features[VIRTIO_FEATURES_U64S]; struct vhost_net *n = f->private_data; void __user *argp = (void __user *)arg; u64 __user *featurep = argp; @@ -1763,7 +1763,7 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl, /* Copy the net features, up to the user-provided buffer size */ argp += sizeof(u64); - copied = min(count, VIRTIO_FEATURES_DWORDS); + copied = min(count, (u64)VIRTIO_FEATURES_U64S); if (copy_to_user(argp, vhost_net_features, copied * sizeof(u64))) return -EFAULT; @@ -1778,13 +1778,13 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl, virtio_features_zero(all_features); argp += sizeof(u64); - copied = min(count, VIRTIO_FEATURES_DWORDS); + copied = min(count, (u64)VIRTIO_FEATURES_U64S); if (copy_from_user(all_features, argp, copied * sizeof(u64))) return -EFAULT; /* * Any feature specified by user-space above - * VIRTIO_FEATURES_MAX is not supported by definition. + * VIRTIO_FEATURES_BITS is not supported by definition. */ for (i = copied; i < count; ++i) { if (copy_from_user(&features, featurep + 1 + i, @@ -1794,7 +1794,7 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl, return -EOPNOTSUPP; } - for (i = 0; i < VIRTIO_FEATURES_DWORDS; i++) + for (i = 0; i < VIRTIO_FEATURES_U64S; i++) if (all_features[i] & ~vhost_net_features[i]) return -EOPNOTSUPP; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index a78226b37739d7..bccdc9eab267a7 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -804,11 +804,13 @@ static int vhost_kthread_worker_create(struct vhost_worker *worker, ret = vhost_attach_task_to_cgroups(worker); if (ret) - goto stop_worker; + goto free_id; worker->id = id; return 0; +free_id: + xa_erase(&dev->worker_xa, id); stop_worker: vhost_kthread_do_stop(worker); return ret; diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index ae01457ea2cdbb..78cc66fbb3dd66 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -64,14 +64,15 @@ static u32 vhost_transport_get_local_cid(void) return VHOST_VSOCK_DEFAULT_HOST_CID; } -/* Callers that dereference the return value must hold vhost_vsock_mutex or the - * RCU read lock. +/* Callers must be in an RCU read section or hold the vhost_vsock_mutex. + * The return value can only be dereferenced while within the section. */ static struct vhost_vsock *vhost_vsock_get(u32 guest_cid) { struct vhost_vsock *vsock; - hash_for_each_possible_rcu(vhost_vsock_hash, vsock, hash, guest_cid) { + hash_for_each_possible_rcu(vhost_vsock_hash, vsock, hash, guest_cid, + lockdep_is_held(&vhost_vsock_mutex)) { u32 other_cid = vsock->guest_cid; /* Skip instances that have no CID yet */ @@ -707,9 +708,15 @@ static void vhost_vsock_reset_orphans(struct sock *sk) * executing. */ + rcu_read_lock(); + /* If the peer is still valid, no need to reset connection */ - if (vhost_vsock_get(vsk->remote_addr.svm_cid)) + if (vhost_vsock_get(vsk->remote_addr.svm_cid)) { + rcu_read_unlock(); return; + } + + rcu_read_unlock(); /* If the close timeout is pending, let it expire. This avoids races * with the timeout callback. diff --git a/drivers/video/backlight/led_bl.c b/drivers/video/backlight/led_bl.c index efc5e380669aea..f7ab9b3607313c 100644 --- a/drivers/video/backlight/led_bl.c +++ b/drivers/video/backlight/led_bl.c @@ -210,6 +210,19 @@ static int led_bl_probe(struct platform_device *pdev) return PTR_ERR(priv->bl_dev); } + for (i = 0; i < priv->nb_leds; i++) { + struct device_link *link; + + link = device_link_add(&pdev->dev, priv->leds[i]->dev->parent, + DL_FLAG_AUTOREMOVE_CONSUMER); + if (!link) { + dev_err(&pdev->dev, "Failed to add devlink (consumer %s, supplier %s)\n", + dev_name(&pdev->dev), dev_name(priv->leds[i]->dev->parent)); + backlight_device_unregister(priv->bl_dev); + return -EINVAL; + } + } + for (i = 0; i < priv->nb_leds; i++) { mutex_lock(&priv->leds[i]->led_access); led_sysfs_disable(priv->leds[i]); diff --git a/drivers/video/backlight/qcom-wled.c b/drivers/video/backlight/qcom-wled.c index a63bb42c8f8b03..8054e4787725ef 100644 --- a/drivers/video/backlight/qcom-wled.c +++ b/drivers/video/backlight/qcom-wled.c @@ -1244,6 +1244,15 @@ static const struct wled_var_cfg wled4_ovp_cfg = { .size = ARRAY_SIZE(wled4_ovp_values), }; +static const u32 pmi8994_wled_ovp_values[] = { + 31000, 29500, 19400, 17800, +}; + +static const struct wled_var_cfg pmi8994_wled_ovp_cfg = { + .values = pmi8994_wled_ovp_values, + .size = ARRAY_SIZE(pmi8994_wled_ovp_values), +}; + static inline u32 wled5_ovp_values_fn(u32 idx) { /* @@ -1357,6 +1366,29 @@ static int wled_configure(struct wled *wled) }, }; + const struct wled_u32_opts pmi8994_wled_opts[] = { + { + .name = "qcom,current-boost-limit", + .val_ptr = &cfg->boost_i_limit, + .cfg = &wled4_boost_i_limit_cfg, + }, + { + .name = "qcom,current-limit-microamp", + .val_ptr = &cfg->string_i_limit, + .cfg = &wled4_string_i_limit_cfg, + }, + { + .name = "qcom,ovp-millivolt", + .val_ptr = &cfg->ovp, + .cfg = &pmi8994_wled_ovp_cfg, + }, + { + .name = "qcom,switching-freq", + .val_ptr = &cfg->switch_freq, + .cfg = &wled3_switch_freq_cfg, + }, + }; + const struct wled_u32_opts wled5_opts[] = { { .name = "qcom,current-boost-limit", @@ -1423,8 +1455,14 @@ static int wled_configure(struct wled *wled) break; case 4: - u32_opts = wled4_opts; - size = ARRAY_SIZE(wled4_opts); + if (of_device_is_compatible(dev->of_node, "qcom,pmi8950-wled") || + of_device_is_compatible(dev->of_node, "qcom,pmi8994-wled")) { + u32_opts = pmi8994_wled_opts; + size = ARRAY_SIZE(pmi8994_wled_opts); + } else { + u32_opts = wled4_opts; + size = ARRAY_SIZE(wled4_opts); + } *cfg = wled4_config_defaults; wled->wled_set_brightness = wled4_set_brightness; wled->wled_sync_toggle = wled3_sync_toggle; diff --git a/drivers/video/fbdev/au1200fb.c b/drivers/video/fbdev/au1200fb.c index ed770222660b51..685e629e7e1642 100644 --- a/drivers/video/fbdev/au1200fb.c +++ b/drivers/video/fbdev/au1200fb.c @@ -1724,8 +1724,10 @@ static int au1200fb_drv_probe(struct platform_device *dev) /* Now hook interrupt too */ irq = platform_get_irq(dev, 0); - if (irq < 0) - return irq; + if (irq < 0) { + ret = irq; + goto failed; + } ret = request_irq(irq, au1200fb_handle_irq, IRQF_SHARED, "lcd", (void *)dev); diff --git a/drivers/video/fbdev/gbefb.c b/drivers/video/fbdev/gbefb.c index 4c36a3e409bea9..cb6ff15a21dbff 100644 --- a/drivers/video/fbdev/gbefb.c +++ b/drivers/video/fbdev/gbefb.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -65,7 +66,7 @@ struct gbefb_par { static unsigned int gbe_mem_size = CONFIG_FB_GBE_MEM * 1024*1024; static void *gbe_mem; static dma_addr_t gbe_dma_addr; -static unsigned long gbe_mem_phys; +static phys_addr_t gbe_mem_phys; static struct { uint16_t *cpu; @@ -1183,7 +1184,7 @@ static int gbefb_probe(struct platform_device *p_dev) goto out_release_mem_region; } - gbe_mem_phys = (unsigned long) gbe_dma_addr; + gbe_mem_phys = dma_to_phys(&p_dev->dev, gbe_dma_addr); } par = info->par; diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c index b96a8a96bce8d1..e418eee825fb24 100644 --- a/drivers/video/fbdev/pxafb.c +++ b/drivers/video/fbdev/pxafb.c @@ -419,12 +419,12 @@ static int pxafb_adjust_timing(struct pxafb_info *fbi, var->yres = max_t(int, var->yres, MIN_YRES); if (!(fbi->lccr0 & LCCR0_LCDT)) { - clamp_val(var->hsync_len, 1, 64); - clamp_val(var->vsync_len, 1, 64); - clamp_val(var->left_margin, 1, 255); - clamp_val(var->right_margin, 1, 255); - clamp_val(var->upper_margin, 1, 255); - clamp_val(var->lower_margin, 1, 255); + var->hsync_len = clamp(var->hsync_len, 1, 64); + var->vsync_len = clamp(var->vsync_len, 1, 64); + var->left_margin = clamp(var->left_margin, 1, 255); + var->right_margin = clamp(var->right_margin, 1, 255); + var->upper_margin = clamp(var->upper_margin, 1, 255); + var->lower_margin = clamp(var->lower_margin, 1, 255); } /* make sure each line is aligned on word boundary */ diff --git a/drivers/video/fbdev/riva/riva_hw.c b/drivers/video/fbdev/riva/riva_hw.c index 8b829b7200642f..f292079566cfca 100644 --- a/drivers/video/fbdev/riva/riva_hw.c +++ b/drivers/video/fbdev/riva/riva_hw.c @@ -436,6 +436,9 @@ static char nv3_arb(nv3_fifo_info * res_info, nv3_sim_state * state, nv3_arb_in vmisses = 2; eburst_size = state->memory_width * 1; mburst_size = 32; + if (!state->mclk_khz) + return (0); + gns = 1000000 * (gmisses*state->mem_page_miss + state->mem_latency)/state->mclk_khz; ainfo->by_gfacc = gns*ainfo->gdrain_rate/1000000; ainfo->wcmocc = 0; diff --git a/drivers/video/fbdev/smscufx.c b/drivers/video/fbdev/smscufx.c index 5f0dd01fd83495..891ce7b76d637e 100644 --- a/drivers/video/fbdev/smscufx.c +++ b/drivers/video/fbdev/smscufx.c @@ -932,7 +932,6 @@ static int ufx_ops_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg) { struct ufx_data *dev = info->par; - struct dloarea *area = NULL; if (!atomic_read(&dev->usb_active)) return 0; @@ -947,6 +946,10 @@ static int ufx_ops_ioctl(struct fb_info *info, unsigned int cmd, /* TODO: Help propose a standard fb.h ioctl to report mmap damage */ if (cmd == UFX_IOCTL_REPORT_DAMAGE) { + struct dloarea *area __free(kfree) = kmalloc(sizeof(*area), GFP_KERNEL); + if (!area) + return -ENOMEM; + /* If we have a damage-aware client, turn fb_defio "off" * To avoid perf imact of unnecessary page fault handling. * Done by resetting the delay for this fb_info to a very @@ -956,7 +959,8 @@ static int ufx_ops_ioctl(struct fb_info *info, unsigned int cmd, if (info->fbdefio) info->fbdefio->delay = UFX_DEFIO_WRITE_DISABLE; - area = (struct dloarea *)arg; + if (copy_from_user(area, (u8 __user *)arg, sizeof(*area))) + return -EFAULT; if (area->x < 0) area->x = 0; diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c index aa6cc0a8151ac0..83dd31fa1fab53 100644 --- a/drivers/video/fbdev/ssd1307fb.c +++ b/drivers/video/fbdev/ssd1307fb.c @@ -680,7 +680,7 @@ static int ssd1307fb_probe(struct i2c_client *client) if (!ssd1307fb_defio) { dev_err(dev, "Couldn't allocate deferred io.\n"); ret = -ENOMEM; - goto fb_alloc_error; + goto fb_defio_error; } ssd1307fb_defio->delay = HZ / refreshrate; @@ -757,6 +757,8 @@ static int ssd1307fb_probe(struct i2c_client *client) regulator_disable(par->vbat_reg); reset_oled_error: fb_deferred_io_cleanup(info); +fb_defio_error: + __free_pages(vmem, get_order(vmem_size)); fb_alloc_error: framebuffer_release(info); return ret; diff --git a/drivers/video/fbdev/tcx.c b/drivers/video/fbdev/tcx.c index f9a0085ad72bf7..ca9e84e8d86052 100644 --- a/drivers/video/fbdev/tcx.c +++ b/drivers/video/fbdev/tcx.c @@ -428,7 +428,7 @@ static int tcx_probe(struct platform_device *op) j = i; break; } - par->mmap_map[i].poff = op->resource[j].start; + par->mmap_map[i].poff = op->resource[j].start - info->fix.smem_start; } info->fbops = &tcx_ops; diff --git a/drivers/video/of_display_timing.c b/drivers/video/of_display_timing.c index bebd371c6b93ea..a4cd446ac5a59f 100644 --- a/drivers/video/of_display_timing.c +++ b/drivers/video/of_display_timing.c @@ -195,7 +195,7 @@ struct display_timings *of_get_display_timings(const struct device_node *np) disp->num_timings = 0; disp->native_mode = 0; - for_each_child_of_node(timings_np, entry) { + for_each_child_of_node_scoped(timings_np, child) { struct display_timing *dt; int r; @@ -206,7 +206,7 @@ struct display_timings *of_get_display_timings(const struct device_node *np) goto timingfail; } - r = of_parse_display_timing(entry, dt); + r = of_parse_display_timing(child, dt); if (r) { /* * to not encourage wrong devicetrees, fail in case of @@ -218,7 +218,7 @@ struct display_timings *of_get_display_timings(const struct device_node *np) goto timingfail; } - if (native_mode == entry) + if (native_mode == child) disp->native_mode = disp->num_timings; disp->timings[disp->num_timings] = dt; diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index a09eb4d62f82df..5bdc6b82b30b48 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -53,7 +53,7 @@ static ssize_t features_show(struct device *_d, /* We actually represent this as a bitstring, as it could be * arbitrary length in future. */ - for (i = 0; i < VIRTIO_FEATURES_MAX; i++) + for (i = 0; i < VIRTIO_FEATURES_BITS; i++) len += sysfs_emit_at(buf, len, "%c", __virtio_test_bit(dev, i) ? '1' : '0'); len += sysfs_emit_at(buf, len, "\n"); @@ -272,8 +272,8 @@ static int virtio_dev_probe(struct device *_d) int err, i; struct virtio_device *dev = dev_to_virtio(_d); struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); - u64 device_features[VIRTIO_FEATURES_DWORDS]; - u64 driver_features[VIRTIO_FEATURES_DWORDS]; + u64 device_features[VIRTIO_FEATURES_U64S]; + u64 driver_features[VIRTIO_FEATURES_U64S]; u64 driver_features_legacy; /* We have a driver! */ @@ -286,7 +286,7 @@ static int virtio_dev_probe(struct device *_d) virtio_features_zero(driver_features); for (i = 0; i < drv->feature_table_size; i++) { unsigned int f = drv->feature_table[i]; - if (!WARN_ON_ONCE(f >= VIRTIO_FEATURES_MAX)) + if (!WARN_ON_ONCE(f >= VIRTIO_FEATURES_BITS)) virtio_features_set_bit(driver_features, f); } @@ -303,7 +303,7 @@ static int virtio_dev_probe(struct device *_d) } if (virtio_features_test_bit(device_features, VIRTIO_F_VERSION_1)) { - for (i = 0; i < VIRTIO_FEATURES_DWORDS; ++i) + for (i = 0; i < VIRTIO_FEATURES_U64S; ++i) dev->features_array[i] = driver_features[i] & device_features[i]; } else { @@ -325,7 +325,7 @@ static int virtio_dev_probe(struct device *_d) goto err; if (drv->validate) { - u64 features[VIRTIO_FEATURES_DWORDS]; + u64 features[VIRTIO_FEATURES_U64S]; virtio_features_copy(features, dev->features_array); err = drv->validate(dev); diff --git a/drivers/virtio/virtio_debug.c b/drivers/virtio/virtio_debug.c index d58713ddf2e587..ccf1955a1183ab 100644 --- a/drivers/virtio/virtio_debug.c +++ b/drivers/virtio/virtio_debug.c @@ -8,12 +8,12 @@ static struct dentry *virtio_debugfs_dir; static int virtio_debug_device_features_show(struct seq_file *s, void *data) { - u64 device_features[VIRTIO_FEATURES_DWORDS]; + u64 device_features[VIRTIO_FEATURES_U64S]; struct virtio_device *dev = s->private; unsigned int i; virtio_get_features(dev, device_features); - for (i = 0; i < VIRTIO_FEATURES_MAX; i++) { + for (i = 0; i < VIRTIO_FEATURES_BITS; i++) { if (virtio_features_test_bit(device_features, i)) seq_printf(s, "%u\n", i); } @@ -26,7 +26,7 @@ static int virtio_debug_filter_features_show(struct seq_file *s, void *data) struct virtio_device *dev = s->private; unsigned int i; - for (i = 0; i < VIRTIO_FEATURES_MAX; i++) { + for (i = 0; i < VIRTIO_FEATURES_BITS; i++) { if (virtio_features_test_bit(dev->debugfs_filter_features, i)) seq_printf(s, "%u\n", i); } @@ -50,7 +50,7 @@ static int virtio_debug_filter_feature_add(void *data, u64 val) { struct virtio_device *dev = data; - if (val >= VIRTIO_FEATURES_MAX) + if (val >= VIRTIO_FEATURES_BITS) return -EINVAL; virtio_features_set_bit(dev->debugfs_filter_features, val); @@ -64,7 +64,7 @@ static int virtio_debug_filter_feature_del(void *data, u64 val) { struct virtio_device *dev = data; - if (val >= VIRTIO_FEATURES_MAX) + if (val >= VIRTIO_FEATURES_BITS) return -EINVAL; virtio_features_clear_bit(dev->debugfs_filter_features, val); diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c index 9e503b7a58d813..413a8c35346380 100644 --- a/drivers/virtio/virtio_pci_modern_dev.c +++ b/drivers/virtio/virtio_pci_modern_dev.c @@ -401,7 +401,7 @@ void vp_modern_get_extended_features(struct virtio_pci_modern_device *mdev, int i; virtio_features_zero(features); - for (i = 0; i < VIRTIO_FEATURES_WORDS; i++) { + for (i = 0; i < VIRTIO_FEATURES_BITS / 32; i++) { u64 cur; vp_iowrite32(i, &cfg->device_feature_select); @@ -427,7 +427,7 @@ vp_modern_get_driver_extended_features(struct virtio_pci_modern_device *mdev, int i; virtio_features_zero(features); - for (i = 0; i < VIRTIO_FEATURES_WORDS; i++) { + for (i = 0; i < VIRTIO_FEATURES_BITS / 32; i++) { u64 cur; vp_iowrite32(i, &cfg->guest_feature_select); @@ -448,7 +448,7 @@ void vp_modern_set_extended_features(struct virtio_pci_modern_device *mdev, struct virtio_pci_common_cfg __iomem *cfg = mdev->common; int i; - for (i = 0; i < VIRTIO_FEATURES_WORDS; i++) { + for (i = 0; i < VIRTIO_FEATURES_BITS / 32; i++) { u32 cur = features[i >> 1] >> (32 * (i & 1)); vp_iowrite32(i, &cfg->guest_feature_select); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 7b6205253b46b3..ddab6895967171 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -3166,6 +3166,7 @@ EXPORT_SYMBOL_GPL(virtqueue_map_alloc_coherent); * @vdev: the virtio device we are talking to * @map: metadata for performing mapping * @size: the size of the buffer + * @vaddr: the virtual address that needs to be freed * @map_handle: the mapped address that needs to be freed * */ @@ -3190,7 +3191,7 @@ EXPORT_SYMBOL_GPL(virtqueue_map_free_coherent); * @dir: mapping direction * @attrs: mapping attributes * - * Returns mapped address. Caller should check that by virtqueue_mapping_error(). + * Returns mapped address. Caller should check that by virtqueue_map_mapping_error(). */ dma_addr_t virtqueue_map_page_attrs(const struct virtqueue *_vq, struct page *page, @@ -3249,7 +3250,7 @@ EXPORT_SYMBOL_GPL(virtqueue_unmap_page_attrs); * The caller calls this to do dma mapping in advance. The DMA address can be * passed to this _vq when it is in pre-mapped mode. * - * return mapped address. Caller should check that by virtqueue_mapping_error(). + * return mapped address. Caller should check that by virtqueue_map_mapping_error(). */ dma_addr_t virtqueue_map_single_attrs(const struct virtqueue *_vq, void *ptr, size_t size, @@ -3299,7 +3300,7 @@ void virtqueue_unmap_single_attrs(const struct virtqueue *_vq, EXPORT_SYMBOL_GPL(virtqueue_unmap_single_attrs); /** - * virtqueue_mapping_error - check dma address + * virtqueue_map_mapping_error - check dma address * @_vq: the struct virtqueue we're talking about. * @addr: DMA address * diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index f9a29045eca0de..0a801f67b59962 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -80,7 +80,7 @@ static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status) { struct vdpa_device *vdpa = vd_get_vdpa(vdev); - return vdpa_set_status(vdpa, status); + vdpa_set_status(vdpa, status); } static void virtio_vdpa_reset(struct virtio_device *vdev) diff --git a/drivers/w1/slaves/w1_therm.c b/drivers/w1/slaves/w1_therm.c index 9ccedb3264fb2a..832e3da94b203a 100644 --- a/drivers/w1/slaves/w1_therm.c +++ b/drivers/w1/slaves/w1_therm.c @@ -1836,53 +1836,35 @@ static ssize_t alarms_store(struct device *device, struct w1_slave *sl = dev_to_w1_slave(device); struct therm_info info; u8 new_config_register[3]; /* array of data to be written */ - int temp, ret; - char *token = NULL; + long long temp; + int ret = 0; s8 tl, th; /* 1 byte per value + temp ring order */ - char *p_args, *orig; - - p_args = orig = kmalloc(size, GFP_KERNEL); - /* Safe string copys as buf is const */ - if (!p_args) { - dev_warn(device, - "%s: error unable to allocate memory %d\n", - __func__, -ENOMEM); - return size; - } - strcpy(p_args, buf); - - /* Split string using space char */ - token = strsep(&p_args, " "); - - if (!token) { - dev_info(device, - "%s: error parsing args %d\n", __func__, -EINVAL); - goto free_m; - } - - /* Convert 1st entry to int */ - ret = kstrtoint (token, 10, &temp); + const char *p = buf; + char *endp; + + temp = simple_strtoll(p, &endp, 10); + if (p == endp || *endp != ' ') + ret = -EINVAL; + else if (temp < INT_MIN || temp > INT_MAX) + ret = -ERANGE; if (ret) { dev_info(device, "%s: error parsing args %d\n", __func__, ret); - goto free_m; + return size; } tl = int_to_short(temp); - /* Split string using space char */ - token = strsep(&p_args, " "); - if (!token) { - dev_info(device, - "%s: error parsing args %d\n", __func__, -EINVAL); - goto free_m; - } - /* Convert 2nd entry to int */ - ret = kstrtoint (token, 10, &temp); + p = endp + 1; + temp = simple_strtoll(p, &endp, 10); + if (p == endp) + ret = -EINVAL; + else if (temp < INT_MIN || temp > INT_MAX) + ret = -ERANGE; if (ret) { dev_info(device, "%s: error parsing args %d\n", __func__, ret); - goto free_m; + return size; } /* Prepare to cast to short by eliminating out of range values */ @@ -1905,7 +1887,7 @@ static ssize_t alarms_store(struct device *device, dev_info(device, "%s: error reading from the slave device %d\n", __func__, ret); - goto free_m; + return size; } /* Write data in the device RAM */ @@ -1913,7 +1895,7 @@ static ssize_t alarms_store(struct device *device, dev_info(device, "%s: Device not supported by the driver %d\n", __func__, -ENODEV); - goto free_m; + return size; } ret = SLAVE_SPECIFIC_FUNC(sl)->write_data(sl, new_config_register); @@ -1922,10 +1904,6 @@ static ssize_t alarms_store(struct device *device, "%s: error writing to the slave device %d\n", __func__, ret); -free_m: - /* free allocated memory */ - kfree(orig); - return size; } diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index d0474a0532ec1f..47e5a3f38ca339 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -758,8 +758,6 @@ int w1_attach_slave_device(struct w1_master *dev, struct w1_reg_num *rn) if (err < 0) { dev_err(&dev->dev, "%s: Attaching %s failed.\n", __func__, sl->name); - dev->slave_count--; - w1_family_put(sl->family); atomic_dec(&sl->master->refcnt); kfree(sl); return err; diff --git a/drivers/watchdog/apple_wdt.c b/drivers/watchdog/apple_wdt.c index 66a158f67a712b..6b9b0f9b05cedf 100644 --- a/drivers/watchdog/apple_wdt.c +++ b/drivers/watchdog/apple_wdt.c @@ -218,6 +218,7 @@ static int apple_wdt_suspend(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(apple_wdt_pm_ops, apple_wdt_suspend, apple_wdt_resume); static const struct of_device_id apple_wdt_of_match[] = { + { .compatible = "apple,t8103-wdt" }, { .compatible = "apple,wdt" }, {}, }; diff --git a/drivers/watchdog/starfive-wdt.c b/drivers/watchdog/starfive-wdt.c index 355918d62f63d5..af55adc4a3c69b 100644 --- a/drivers/watchdog/starfive-wdt.c +++ b/drivers/watchdog/starfive-wdt.c @@ -446,7 +446,7 @@ static int starfive_wdt_probe(struct platform_device *pdev) platform_set_drvdata(pdev, wdt); pm_runtime_enable(&pdev->dev); if (pm_runtime_enabled(&pdev->dev)) { - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) return ret; } else { @@ -500,12 +500,14 @@ static int starfive_wdt_probe(struct platform_device *pdev) if (pm_runtime_enabled(&pdev->dev)) { ret = pm_runtime_put_sync(&pdev->dev); if (ret) - goto err_exit; + goto err_unregister_wdt; } } return 0; +err_unregister_wdt: + watchdog_unregister_device(&wdt->wdd); err_exit: starfive_wdt_disable_clock(wdt); pm_runtime_disable(&pdev->dev); diff --git a/drivers/watchdog/via_wdt.c b/drivers/watchdog/via_wdt.c index d647923d68fede..f5557639265184 100644 --- a/drivers/watchdog/via_wdt.c +++ b/drivers/watchdog/via_wdt.c @@ -165,6 +165,7 @@ static int wdt_probe(struct pci_dev *pdev, dev_err(&pdev->dev, "cannot enable PCI device\n"); return -ENODEV; } + wdt_res.name = "via_wdt"; /* * Allocate a MMIO region which contains watchdog control register diff --git a/drivers/watchdog/wdat_wdt.c b/drivers/watchdog/wdat_wdt.c index 650fdc7996e1c2..dd3c2d69c9df12 100644 --- a/drivers/watchdog/wdat_wdt.c +++ b/drivers/watchdog/wdat_wdt.c @@ -326,19 +326,27 @@ static int wdat_wdt_probe(struct platform_device *pdev) return -ENODEV; wdat = devm_kzalloc(dev, sizeof(*wdat), GFP_KERNEL); - if (!wdat) - return -ENOMEM; + if (!wdat) { + ret = -ENOMEM; + goto out_put_table; + } regs = devm_kcalloc(dev, pdev->num_resources, sizeof(*regs), GFP_KERNEL); - if (!regs) - return -ENOMEM; + if (!regs) { + ret = -ENOMEM; + goto out_put_table; + } /* WDAT specification wants to have >= 1ms period */ - if (tbl->timer_period < 1) - return -EINVAL; - if (tbl->min_count > tbl->max_count) - return -EINVAL; + if (tbl->timer_period < 1) { + ret = -EINVAL; + goto out_put_table; + } + if (tbl->min_count > tbl->max_count) { + ret = -EINVAL; + goto out_put_table; + } wdat->period = tbl->timer_period; wdat->wdd.min_timeout = DIV_ROUND_UP(wdat->period * tbl->min_count, 1000); @@ -355,15 +363,20 @@ static int wdat_wdt_probe(struct platform_device *pdev) res = &pdev->resource[i]; if (resource_type(res) == IORESOURCE_MEM) { reg = devm_ioremap_resource(dev, res); - if (IS_ERR(reg)) - return PTR_ERR(reg); + if (IS_ERR(reg)) { + ret = PTR_ERR(reg); + goto out_put_table; + } } else if (resource_type(res) == IORESOURCE_IO) { reg = devm_ioport_map(dev, res->start, 1); - if (!reg) - return -ENOMEM; + if (!reg) { + ret = -ENOMEM; + goto out_put_table; + } } else { dev_err(dev, "Unsupported resource\n"); - return -EINVAL; + ret = -EINVAL; + goto out_put_table; } regs[i] = reg; @@ -385,8 +398,10 @@ static int wdat_wdt_probe(struct platform_device *pdev) } instr = devm_kzalloc(dev, sizeof(*instr), GFP_KERNEL); - if (!instr) - return -ENOMEM; + if (!instr) { + ret = -ENOMEM; + goto out_put_table; + } INIT_LIST_HEAD(&instr->node); instr->entry = entries[i]; @@ -417,7 +432,8 @@ static int wdat_wdt_probe(struct platform_device *pdev) if (!instr->reg) { dev_err(dev, "I/O resource not found\n"); - return -EINVAL; + ret = -EINVAL; + goto out_put_table; } instructions = wdat->instructions[action]; @@ -425,8 +441,10 @@ static int wdat_wdt_probe(struct platform_device *pdev) instructions = devm_kzalloc(dev, sizeof(*instructions), GFP_KERNEL); - if (!instructions) - return -ENOMEM; + if (!instructions) { + ret = -ENOMEM; + goto out_put_table; + } INIT_LIST_HEAD(instructions); wdat->instructions[action] = instructions; @@ -443,7 +461,7 @@ static int wdat_wdt_probe(struct platform_device *pdev) ret = wdat_wdt_enable_reboot(wdat); if (ret) - return ret; + goto out_put_table; platform_set_drvdata(pdev, wdat); @@ -460,12 +478,16 @@ static int wdat_wdt_probe(struct platform_device *pdev) ret = wdat_wdt_set_timeout(&wdat->wdd, timeout); if (ret) - return ret; + goto out_put_table; watchdog_set_nowayout(&wdat->wdd, nowayout); watchdog_stop_on_reboot(&wdat->wdd); watchdog_stop_on_unregister(&wdat->wdd); - return devm_watchdog_register_device(dev, &wdat->wdd); + ret = devm_watchdog_register_device(dev, &wdat->wdd); + +out_put_table: + acpi_put_table((struct acpi_table_header *)tbl); + return ret; } static int wdat_wdt_suspend_noirq(struct device *dev) diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 49c3f992639435..8c44a25a7d2b95 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -724,6 +724,7 @@ static int __init balloon_add_regions(void) static int __init balloon_init(void) { struct task_struct *task; + unsigned long current_pages; int rc; if (!xen_domain()) @@ -731,12 +732,18 @@ static int __init balloon_init(void) pr_info("Initialising balloon driver\n"); - if (xen_released_pages >= get_num_physpages()) { - WARN(1, "Released pages underflow current target"); - return -ERANGE; + if (xen_pv_domain()) { + if (xen_released_pages >= xen_start_info->nr_pages) + goto underflow; + current_pages = min(xen_start_info->nr_pages - + xen_released_pages, max_pfn); + } else { + if (xen_unpopulated_pages >= get_num_physpages()) + goto underflow; + current_pages = get_num_physpages() - xen_unpopulated_pages; } - balloon_stats.current_pages = get_num_physpages() - xen_released_pages; + balloon_stats.current_pages = current_pages; balloon_stats.target_pages = balloon_stats.current_pages; balloon_stats.balloon_low = 0; balloon_stats.balloon_high = 0; @@ -767,6 +774,10 @@ static int __init balloon_init(void) xen_balloon_init(); return 0; + + underflow: + WARN(1, "Released pages underflow current target"); + return -ERANGE; } subsys_initcall(balloon_init); diff --git a/drivers/xen/grant-dma-ops.c b/drivers/xen/grant-dma-ops.c index 29257d2639dbf0..43a918c498c6c7 100644 --- a/drivers/xen/grant-dma-ops.c +++ b/drivers/xen/grant-dma-ops.c @@ -362,7 +362,8 @@ static int xen_grant_init_backend_domid(struct device *dev, if (np) { ret = xen_dt_grant_init_backend_domid(dev, np, backend_domid); of_node_put(np); - } else if (IS_ENABLED(CONFIG_XEN_VIRTIO_FORCE_GRANT) || xen_pv_domain()) { + } else if (!xen_initial_domain() && + (IS_ENABLED(CONFIG_XEN_VIRTIO_FORCE_GRANT) || xen_pv_domain())) { dev_info(dev, "Using dom0 as backend\n"); *backend_domid = 0; ret = 0; diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c index d6fc2aefe2646b..1dc0b495c8e597 100644 --- a/drivers/xen/unpopulated-alloc.c +++ b/drivers/xen/unpopulated-alloc.c @@ -18,6 +18,9 @@ static unsigned int list_count; static struct resource *target_resource; +/* Pages to subtract from the memory count when setting balloon target. */ +unsigned long xen_unpopulated_pages __initdata; + /* * If arch is not happy with system "iomem_resource" being used for * the region allocation it can provide it's own view by creating specific diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 0c51edfd13dcdf..7d5117e5efe0e9 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1262,6 +1262,7 @@ static void scsiback_remove(struct xenbus_device *dev) gnttab_page_cache_shrink(&info->free_pages, 0); dev_set_drvdata(&dev->dev, NULL); + kfree(info); } static int scsiback_probe(struct xenbus_device *dev, diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index a020a8f00a1ac0..bde3ffb0e319a5 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -101,7 +101,7 @@ int v9fs_show_options(struct seq_file *m, struct dentry *root) struct v9fs_session_info *v9ses = root->d_sb->s_fs_info; if (v9ses->debug) - seq_printf(m, ",debug=%x", v9ses->debug); + seq_printf(m, ",debug=%#x", v9ses->debug); if (!uid_eq(v9ses->dfltuid, V9FS_DEFUID)) seq_printf(m, ",dfltuid=%u", from_kuid_munged(&init_user_ns, v9ses->dfltuid)); @@ -117,7 +117,7 @@ int v9fs_show_options(struct seq_file *m, struct dentry *root) if (v9ses->nodev) seq_puts(m, ",nodevmap"); if (v9ses->cache) - seq_printf(m, ",cache=%x", v9ses->cache); + seq_printf(m, ",cache=%#x", v9ses->cache); #ifdef CONFIG_9P_FSCACHE if (v9ses->cachetag && (v9ses->cache & CACHE_FSCACHE)) seq_printf(m, ",cachetag=%s", v9ses->cachetag); diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index eb0b083da269b4..d1db03093d4c3c 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -43,14 +43,18 @@ int v9fs_file_open(struct inode *inode, struct file *file) struct v9fs_session_info *v9ses; struct p9_fid *fid; int omode; + int o_append; p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, file); v9ses = v9fs_inode2v9ses(inode); - if (v9fs_proto_dotl(v9ses)) + if (v9fs_proto_dotl(v9ses)) { omode = v9fs_open_to_dotl_flags(file->f_flags); - else + o_append = P9_DOTL_APPEND; + } else { omode = v9fs_uflags2omode(file->f_flags, v9fs_proto_dotu(v9ses)); + o_append = P9_OAPPEND; + } fid = file->private_data; if (!fid) { fid = v9fs_fid_clone(file_dentry(file)); @@ -58,9 +62,10 @@ int v9fs_file_open(struct inode *inode, struct file *file) return PTR_ERR(fid); if ((v9ses->cache & CACHE_WRITEBACK) && (omode & P9_OWRITE)) { - int writeback_omode = (omode & ~P9_OWRITE) | P9_ORDWR; + int writeback_omode = (omode & ~(P9_OWRITE | o_append)) | P9_ORDWR; p9_debug(P9_DEBUG_CACHE, "write-only file with writeback enabled, try opening O_RDWR\n"); + err = p9_client_open(fid, writeback_omode); if (err < 0) { p9_debug(P9_DEBUG_CACHE, "could not open O_RDWR, disabling caches\n"); diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index d0c77ec31b1dd6..0f3189a0a516af 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -786,7 +786,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, p9_omode = v9fs_uflags2omode(flags, v9fs_proto_dotu(v9ses)); if ((v9ses->cache & CACHE_WRITEBACK) && (p9_omode & P9_OWRITE)) { - p9_omode = (p9_omode & ~P9_OWRITE) | P9_ORDWR; + p9_omode = (p9_omode & ~(P9_OWRITE | P9_OAPPEND)) | P9_ORDWR; p9_debug(P9_DEBUG_CACHE, "write-only file with writeback enabled, creating w/ O_RDWR\n"); } @@ -1393,4 +1393,3 @@ static const struct inode_operations v9fs_symlink_inode_operations = { .getattr = v9fs_vfs_getattr, .setattr = v9fs_vfs_setattr, }; - diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index be297e33546889..6312b3590f7438 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -282,7 +282,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, } if ((v9ses->cache & CACHE_WRITEBACK) && (p9_omode & P9_OWRITE)) { - p9_omode = (p9_omode & ~P9_OWRITE) | P9_ORDWR; + p9_omode = (p9_omode & ~(P9_OWRITE | P9_DOTL_APPEND)) | P9_ORDWR; p9_debug(P9_DEBUG_CACHE, "write-only file with writeback enabled, creating w/ O_RDWR\n"); } diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h index 99b3ced12805bb..78721412951c5a 100644 --- a/fs/btrfs/accessors.h +++ b/fs/btrfs/accessors.h @@ -12,6 +12,7 @@ #include #include #include +#include "fs.h" #include "extent_io.h" struct extent_buffer; diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index 21df48e6c4fa20..7d8aaa019c8ce6 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -41,13 +41,17 @@ static bool bbio_has_ordered_extent(const struct btrfs_bio *bbio) * Initialize a btrfs_bio structure. This skips the embedded bio itself as it * is already initialized by the block layer. */ -void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_fs_info *fs_info, +void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_inode *inode, u64 file_offset, btrfs_bio_end_io_t end_io, void *private) { + /* @inode parameter is mandatory. */ + ASSERT(inode); + memset(bbio, 0, offsetof(struct btrfs_bio, bio)); - bbio->fs_info = fs_info; + bbio->inode = inode; bbio->end_io = end_io; bbio->private = private; + bbio->file_offset = file_offset; atomic_set(&bbio->pending_ios, 1); WRITE_ONCE(bbio->status, BLK_STS_OK); } @@ -60,7 +64,7 @@ void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_fs_info *fs_info, * a mempool. */ struct btrfs_bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf, - struct btrfs_fs_info *fs_info, + struct btrfs_inode *inode, u64 file_offset, btrfs_bio_end_io_t end_io, void *private) { struct btrfs_bio *bbio; @@ -68,7 +72,7 @@ struct btrfs_bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf, bio = bio_alloc_bioset(NULL, nr_vecs, opf, GFP_NOFS, &btrfs_bioset); bbio = btrfs_bio(bio); - btrfs_bio_init(bbio, fs_info, end_io, private); + btrfs_bio_init(bbio, inode, file_offset, end_io, private); return bbio; } @@ -85,9 +89,7 @@ static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info, return ERR_CAST(bio); bbio = btrfs_bio(bio); - btrfs_bio_init(bbio, fs_info, NULL, orig_bbio); - bbio->inode = orig_bbio->inode; - bbio->file_offset = orig_bbio->file_offset; + btrfs_bio_init(bbio, orig_bbio->inode, orig_bbio->file_offset, NULL, orig_bbio); orig_bbio->file_offset += map_length; if (bbio_has_ordered_extent(bbio)) { refcount_inc(&orig_bbio->ordered->refs); @@ -100,6 +102,12 @@ static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info, void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status) { + /* Make sure we're already in task context. */ + ASSERT(in_task()); + + if (bbio->async_csum) + wait_for_completion(&bbio->csum_done); + bbio->bio.bi_status = status; if (bbio->bio.bi_pool == &btrfs_clone_bioset) { struct btrfs_bio *orig_bbio = bbio->private; @@ -244,9 +252,8 @@ static struct btrfs_failed_bio *repair_one_sector(struct btrfs_bio *failed_bbio, bio_add_folio_nofail(repair_bio, folio, sectorsize, foff); repair_bbio = btrfs_bio(repair_bio); - btrfs_bio_init(repair_bbio, fs_info, NULL, fbio); - repair_bbio->inode = failed_bbio->inode; - repair_bbio->file_offset = failed_bbio->file_offset + bio_offset; + btrfs_bio_init(repair_bbio, failed_bbio->inode, failed_bbio->file_offset + bio_offset, + NULL, fbio); mirror = next_repair_mirror(fbio, failed_bbio->mirror_num); btrfs_debug(fs_info, "submitting repair read to mirror %d", mirror); @@ -317,36 +324,35 @@ static struct workqueue_struct *btrfs_end_io_wq(const struct btrfs_fs_info *fs_i return fs_info->endio_workers; } -static void btrfs_end_bio_work(struct work_struct *work) +static void simple_end_io_work(struct work_struct *work) { struct btrfs_bio *bbio = container_of(work, struct btrfs_bio, end_io_work); + struct bio *bio = &bbio->bio; - /* Metadata reads are checked and repaired by the submitter. */ - if (is_data_bbio(bbio)) - btrfs_check_read_bio(bbio, bbio->bio.bi_private); - else - btrfs_bio_end_io(bbio, bbio->bio.bi_status); + if (bio_op(bio) == REQ_OP_READ) { + /* Metadata reads are checked and repaired by the submitter. */ + if (is_data_bbio(bbio)) + return btrfs_check_read_bio(bbio, bbio->bio.bi_private); + return btrfs_bio_end_io(bbio, bbio->bio.bi_status); + } + if (bio_is_zone_append(bio) && !bio->bi_status) + btrfs_record_physical_zoned(bbio); + btrfs_bio_end_io(bbio, bbio->bio.bi_status); } static void btrfs_simple_end_io(struct bio *bio) { struct btrfs_bio *bbio = btrfs_bio(bio); struct btrfs_device *dev = bio->bi_private; - struct btrfs_fs_info *fs_info = bbio->fs_info; + struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info; btrfs_bio_counter_dec(fs_info); if (bio->bi_status) btrfs_log_dev_io_error(bio, dev); - if (bio_op(bio) == REQ_OP_READ) { - INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work); - queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work); - } else { - if (bio_is_zone_append(bio) && !bio->bi_status) - btrfs_record_physical_zoned(bbio); - btrfs_bio_end_io(bbio, bbio->bio.bi_status); - } + INIT_WORK(&bbio->end_io_work, simple_end_io_work); + queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work); } static void btrfs_raid56_end_io(struct bio *bio) @@ -354,6 +360,9 @@ static void btrfs_raid56_end_io(struct bio *bio) struct btrfs_io_context *bioc = bio->bi_private; struct btrfs_bio *bbio = btrfs_bio(bio); + /* RAID56 endio is always handled in workqueue. */ + ASSERT(in_task()); + btrfs_bio_counter_dec(bioc->fs_info); bbio->mirror_num = bioc->mirror_num; if (bio_op(bio) == REQ_OP_READ && is_data_bbio(bbio)) @@ -364,11 +373,12 @@ static void btrfs_raid56_end_io(struct bio *bio) btrfs_put_bioc(bioc); } -static void btrfs_orig_write_end_io(struct bio *bio) +static void orig_write_end_io_work(struct work_struct *work) { + struct btrfs_bio *bbio = container_of(work, struct btrfs_bio, end_io_work); + struct bio *bio = &bbio->bio; struct btrfs_io_stripe *stripe = bio->bi_private; struct btrfs_io_context *bioc = stripe->bioc; - struct btrfs_bio *bbio = btrfs_bio(bio); btrfs_bio_counter_dec(bioc->fs_info); @@ -393,8 +403,18 @@ static void btrfs_orig_write_end_io(struct bio *bio) btrfs_put_bioc(bioc); } -static void btrfs_clone_write_end_io(struct bio *bio) +static void btrfs_orig_write_end_io(struct bio *bio) +{ + struct btrfs_bio *bbio = btrfs_bio(bio); + + INIT_WORK(&bbio->end_io_work, orig_write_end_io_work); + queue_work(btrfs_end_io_wq(bbio->inode->root->fs_info, bio), &bbio->end_io_work); +} + +static void clone_write_end_io_work(struct work_struct *work) { + struct btrfs_bio *bbio = container_of(work, struct btrfs_bio, end_io_work); + struct bio *bio = &bbio->bio; struct btrfs_io_stripe *stripe = bio->bi_private; if (bio->bi_status) { @@ -409,8 +429,18 @@ static void btrfs_clone_write_end_io(struct bio *bio) bio_put(bio); } +static void btrfs_clone_write_end_io(struct bio *bio) +{ + struct btrfs_bio *bbio = btrfs_bio(bio); + + INIT_WORK(&bbio->end_io_work, clone_write_end_io_work); + queue_work(btrfs_end_io_wq(bbio->inode->root->fs_info, bio), &bbio->end_io_work); +} + static void btrfs_submit_dev_bio(struct btrfs_device *dev, struct bio *bio) { + u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; + if (!dev || !dev->bdev || test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) || (btrfs_op(bio) == BTRFS_MAP_WRITE && @@ -425,12 +455,13 @@ static void btrfs_submit_dev_bio(struct btrfs_device *dev, struct bio *bio) * For zone append writing, bi_sector must point the beginning of the * zone */ - if (bio_op(bio) == REQ_OP_ZONE_APPEND) { - u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; + if (btrfs_bio(bio)->can_use_append && btrfs_dev_is_sequential(dev, physical)) { u64 zone_start = round_down(physical, dev->fs_info->zone_size); ASSERT(btrfs_dev_is_sequential(dev, physical)); bio->bi_iter.bi_sector = zone_start >> SECTOR_SHIFT; + bio->bi_opf &= ~REQ_OP_WRITE; + bio->bi_opf |= REQ_OP_ZONE_APPEND; } btrfs_debug(dev->fs_info, "%s: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u", @@ -455,6 +486,7 @@ static void btrfs_submit_dev_bio(struct btrfs_device *dev, struct bio *bio) static void btrfs_submit_mirrored_bio(struct btrfs_io_context *bioc, int dev_nr) { struct bio *orig_bio = bioc->orig_bio, *bio; + struct btrfs_bio *orig_bbio = btrfs_bio(orig_bio); ASSERT(bio_op(orig_bio) != REQ_OP_READ); @@ -463,8 +495,11 @@ static void btrfs_submit_mirrored_bio(struct btrfs_io_context *bioc, int dev_nr) bio = orig_bio; bio->bi_end_io = btrfs_orig_write_end_io; } else { - bio = bio_alloc_clone(NULL, orig_bio, GFP_NOFS, &fs_bio_set); + /* We need to use endio_work to run end_io in task context. */ + bio = bio_alloc_clone(NULL, orig_bio, GFP_NOFS, &btrfs_bioset); bio_inc_remaining(orig_bio); + btrfs_bio_init(btrfs_bio(bio), orig_bbio->inode, + orig_bbio->file_offset, NULL, NULL); bio->bi_end_io = btrfs_clone_write_end_io; } @@ -509,7 +544,11 @@ static int btrfs_bio_csum(struct btrfs_bio *bbio) { if (bbio->bio.bi_opf & REQ_META) return btree_csum_one_bio(bbio); - return btrfs_csum_one_bio(bbio); +#ifdef CONFIG_BTRFS_EXPERIMENTAL + return btrfs_csum_one_bio(bbio, true); +#else + return btrfs_csum_one_bio(bbio, false); +#endif } /* @@ -581,20 +620,25 @@ static void run_one_async_done(struct btrfs_work *work, bool do_free) static bool should_async_write(struct btrfs_bio *bbio) { + struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info; bool auto_csum_mode = true; #ifdef CONFIG_BTRFS_EXPERIMENTAL - struct btrfs_fs_devices *fs_devices = bbio->fs_info->fs_devices; + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; enum btrfs_offload_csum_mode csum_mode = READ_ONCE(fs_devices->offload_csum_mode); - if (csum_mode == BTRFS_OFFLOAD_CSUM_FORCE_OFF) - return false; - - auto_csum_mode = (csum_mode == BTRFS_OFFLOAD_CSUM_AUTO); + if (csum_mode == BTRFS_OFFLOAD_CSUM_FORCE_ON) + return true; + /* + * Write bios will calculate checksum and submit bio at the same time. + * Unless explicitly required don't offload serial csum calculate and bio + * submit into a workqueue. + */ + return false; #endif /* Submit synchronously if the checksum implementation is fast. */ - if (auto_csum_mode && test_bit(BTRFS_FS_CSUM_IMPL_FAST, &bbio->fs_info->flags)) + if (auto_csum_mode && test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags)) return false; /* @@ -605,7 +649,7 @@ static bool should_async_write(struct btrfs_bio *bbio) return false; /* Zoned devices require I/O to be submitted in order. */ - if ((bbio->bio.bi_opf & REQ_META) && btrfs_is_zoned(bbio->fs_info)) + if ((bbio->bio.bi_opf & REQ_META) && btrfs_is_zoned(fs_info)) return false; return true; @@ -620,7 +664,7 @@ static bool btrfs_wq_submit_bio(struct btrfs_bio *bbio, struct btrfs_io_context *bioc, struct btrfs_io_stripe *smap, int mirror_num) { - struct btrfs_fs_info *fs_info = bbio->fs_info; + struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info; struct async_submit_bio *async; async = kmalloc(sizeof(*async), GFP_NOFS); @@ -639,11 +683,12 @@ static bool btrfs_wq_submit_bio(struct btrfs_bio *bbio, static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) { + struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info; unsigned int nr_segs; int sector_offset; - map_length = min(map_length, bbio->fs_info->max_zone_append_size); - sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits, + map_length = min(map_length, fs_info->max_zone_append_size); + sector_offset = bio_split_rw_at(&bbio->bio, &fs_info->limits, &nr_segs, map_length); if (sector_offset) { /* @@ -651,7 +696,7 @@ static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) * sectorsize and thus cause unaligned I/Os. Fix that by * always rounding down to the nearest boundary. */ - return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, bbio->fs_info->sectorsize); + return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, fs_info->sectorsize); } return map_length; } @@ -659,18 +704,17 @@ static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) { struct btrfs_inode *inode = bbio->inode; - struct btrfs_fs_info *fs_info = bbio->fs_info; + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct bio *bio = &bbio->bio; u64 logical = bio->bi_iter.bi_sector << SECTOR_SHIFT; u64 length = bio->bi_iter.bi_size; u64 map_length = length; - bool use_append = btrfs_use_zone_append(bbio); struct btrfs_io_context *bioc = NULL; struct btrfs_io_stripe smap; blk_status_t status; int ret; - if (!bbio->inode || btrfs_is_data_reloc_root(inode->root)) + if (bbio->is_scrub || btrfs_is_data_reloc_root(inode->root)) smap.rst_search_commit_root = true; else smap.rst_search_commit_root = false; @@ -684,8 +728,10 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) goto end_bbio; } + bbio->can_use_append = btrfs_use_zone_append(bbio); + map_length = min(map_length, length); - if (use_append) + if (bbio->can_use_append) map_length = btrfs_append_map_length(bbio, map_length); if (map_length < length) { @@ -714,11 +760,6 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) } if (btrfs_op(bio) == BTRFS_MAP_WRITE) { - if (use_append) { - bio->bi_opf &= ~REQ_OP_WRITE; - bio->bi_opf |= REQ_OP_ZONE_APPEND; - } - if (is_data_bbio(bbio) && bioc && bioc->use_rst) { /* * No locking for the list update, as we only add to @@ -734,7 +775,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) * Csum items for reloc roots have already been cloned at this * point, so they are handled as part of the no-checksum case. */ - if (inode && !(inode->flags & BTRFS_INODE_NODATASUM) && + if (!(inode->flags & BTRFS_INODE_NODATASUM) && !test_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state) && !btrfs_is_data_reloc_root(inode->root)) { if (should_async_write(bbio) && @@ -745,7 +786,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) status = errno_to_blk_status(ret); if (status) goto fail; - } else if (use_append || + } else if (bbio->can_use_append || (btrfs_is_zoned(fs_info) && inode && inode->flags & BTRFS_INODE_NODATASUM)) { ret = btrfs_alloc_dummy_sum(bbio); @@ -782,7 +823,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) static void assert_bbio_alignment(struct btrfs_bio *bbio) { #ifdef CONFIG_BTRFS_ASSERT - struct btrfs_fs_info *fs_info = bbio->fs_info; + struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info; struct bio_vec bvec; struct bvec_iter iter; const u32 blocksize = fs_info->sectorsize; @@ -885,16 +926,16 @@ int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, */ void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_replace) { - struct btrfs_fs_info *fs_info = bbio->fs_info; + struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info; u64 logical = bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT; u64 length = bbio->bio.bi_iter.bi_size; struct btrfs_io_stripe smap = { 0 }; int ret; - ASSERT(fs_info); ASSERT(mirror_num > 0); ASSERT(btrfs_op(&bbio->bio) == BTRFS_MAP_WRITE); - ASSERT(!bbio->inode); + ASSERT(!is_data_inode(bbio->inode)); + ASSERT(bbio->is_scrub); btrfs_bio_counter_inc_blocked(fs_info); ret = btrfs_map_repair_block(fs_info, &smap, logical, length, mirror_num); diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h index 00883aea55d70f..69fe54f564fcb1 100644 --- a/fs/btrfs/bio.h +++ b/fs/btrfs/bio.h @@ -34,7 +34,10 @@ typedef void (*btrfs_bio_end_io_t)(struct btrfs_bio *bbio); struct btrfs_bio { /* * Inode and offset into it that this I/O operates on. - * Only set for data I/O. + * + * If the inode is a data one, csum verification and read-repair + * will be done automatically. + * If the inode is a metadata one, everything is handled by the caller. */ struct btrfs_inode *inode; u64 file_offset; @@ -60,6 +63,9 @@ struct btrfs_bio { struct { struct btrfs_ordered_extent *ordered; struct btrfs_ordered_sum *sums; + struct work_struct csum_work; + struct completion csum_done; + struct bvec_iter csum_saved_iter; u64 orig_physical; }; @@ -76,14 +82,24 @@ struct btrfs_bio { atomic_t pending_ios; struct work_struct end_io_work; - /* File system that this I/O operates on. */ - struct btrfs_fs_info *fs_info; - /* Save the first error status of split bio. */ blk_status_t status; /* Use the commit root to look up csums (data read bio only). */ bool csum_search_commit_root; + + /* + * Since scrub will reuse btree inode, we need this flag to distinguish + * scrub bios. + */ + bool is_scrub; + + /* Whether the csum generation for data write is async. */ + bool async_csum; + + /* Whether the bio is written using zone append. */ + bool can_use_append; + /* * This member must come last, bio_alloc_bioset will allocate enough * bytes for entire btrfs_bio but relies on bio being last. @@ -99,10 +115,10 @@ static inline struct btrfs_bio *btrfs_bio(struct bio *bio) int __init btrfs_bioset_init(void); void __cold btrfs_bioset_exit(void); -void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_fs_info *fs_info, +void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_inode *inode, u64 file_offset, btrfs_bio_end_io_t end_io, void *private); struct btrfs_bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf, - struct btrfs_fs_info *fs_info, + struct btrfs_inode *inode, u64 file_offset, btrfs_bio_end_io_t end_io, void *private); void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 5322ef2ae015e8..f7f6d8cb33114f 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -3681,6 +3681,14 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) return ret; } +static void btrfs_maybe_reset_size_class(struct btrfs_block_group *bg) +{ + lockdep_assert_held(&bg->lock); + if (btrfs_block_group_should_use_size_class(bg) && + bg->used == 0 && bg->reserved == 0) + bg->size_class = BTRFS_BG_SZ_NONE; +} + int btrfs_update_block_group(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, bool alloc) { @@ -3745,6 +3753,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, old_val -= num_bytes; cache->used = old_val; cache->pinned += num_bytes; + btrfs_maybe_reset_size_class(cache); btrfs_space_info_update_bytes_pinned(space_info, num_bytes); space_info->bytes_used -= num_bytes; space_info->disk_used -= num_bytes * factor; @@ -3836,7 +3845,7 @@ int btrfs_add_reserved_bytes(struct btrfs_block_group *cache, * that happens. */ if (num_bytes < ram_bytes) - btrfs_try_granting_tickets(cache->fs_info, space_info); + btrfs_try_granting_tickets(space_info); out: spin_unlock(&cache->lock); spin_unlock(&space_info->lock); @@ -3859,22 +3868,26 @@ void btrfs_free_reserved_bytes(struct btrfs_block_group *cache, u64 num_bytes, bool is_delalloc) { struct btrfs_space_info *space_info = cache->space_info; + bool bg_ro; spin_lock(&space_info->lock); spin_lock(&cache->lock); - if (cache->ro) + bg_ro = cache->ro; + cache->reserved -= num_bytes; + btrfs_maybe_reset_size_class(cache); + if (is_delalloc) + cache->delalloc_bytes -= num_bytes; + spin_unlock(&cache->lock); + + if (bg_ro) space_info->bytes_readonly += num_bytes; else if (btrfs_is_zoned(cache->fs_info)) space_info->bytes_zone_unusable += num_bytes; - cache->reserved -= num_bytes; + space_info->bytes_reserved -= num_bytes; space_info->max_extent_size = 0; - if (is_delalloc) - cache->delalloc_bytes -= num_bytes; - spin_unlock(&cache->lock); - - btrfs_try_granting_tickets(cache->fs_info, space_info); + btrfs_try_granting_tickets(space_info); spin_unlock(&space_info->lock); } @@ -4215,7 +4228,7 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, mutex_unlock(&fs_info->chunk_mutex); } else { /* Proceed with allocation */ - space_info->chunk_alloc = 1; + space_info->chunk_alloc = true; wait_for_alloc = false; spin_unlock(&space_info->lock); } @@ -4264,7 +4277,7 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, spin_lock(&space_info->lock); if (ret < 0) { if (ret == -ENOSPC) - space_info->full = 1; + space_info->full = true; else goto out; } else { @@ -4274,7 +4287,7 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, space_info->force_alloc = CHUNK_ALLOC_NO_FORCE; out: - space_info->chunk_alloc = 0; + space_info->chunk_alloc = false; spin_unlock(&space_info->lock); mutex_unlock(&fs_info->chunk_mutex); diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index 5ad6de738aee01..fc378d2038a2d2 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -278,10 +278,11 @@ u64 btrfs_block_rsv_release(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *target = NULL; /* - * If we are a delayed block reserve then push to the global rsv, - * otherwise dump into the global delayed reserve if it is not full. + * If we are a delayed refs block reserve then push to the global + * reserve, otherwise dump into the global delayed refs reserve if it is + * not full. */ - if (block_rsv->type == BTRFS_BLOCK_RSV_DELOPS) + if (block_rsv->type == BTRFS_BLOCK_RSV_DELREFS) target = global_rsv; else if (block_rsv != global_rsv && !btrfs_block_rsv_full(delayed_rsv)) target = delayed_rsv; @@ -387,7 +388,7 @@ void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info) num_bytes = block_rsv->reserved - block_rsv->size; btrfs_space_info_update_bytes_may_use(sinfo, -num_bytes); block_rsv->reserved = block_rsv->size; - btrfs_try_granting_tickets(fs_info, sinfo); + btrfs_try_granting_tickets(sinfo); } block_rsv->full = (block_rsv->reserved == block_rsv->size); diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index af373d50a901f2..a66ca5531b5c57 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -18,20 +18,20 @@ #include #include #include +#include "ctree.h" #include "block-rsv.h" #include "extent_map.h" -#include "extent_io.h" #include "extent-io-tree.h" -#include "ordered-data.h" -#include "delayed-inode.h" -struct extent_state; struct posix_acl; struct iov_iter; struct writeback_control; struct btrfs_root; struct btrfs_fs_info; struct btrfs_trans_handle; +struct btrfs_bio; +struct btrfs_file_extent; +struct btrfs_delayed_node; /* * Since we search a directory based on f_pos (struct dir_context::pos) we have diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index bacad18357b338..8c3899832a1aa1 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -67,9 +67,7 @@ static struct compressed_bio *alloc_compressed_bio(struct btrfs_inode *inode, bbio = btrfs_bio(bio_alloc_bioset(NULL, BTRFS_MAX_COMPRESSED_PAGES, op, GFP_NOFS, &btrfs_compressed_bioset)); - btrfs_bio_init(bbio, inode->root->fs_info, end_io, NULL); - bbio->inode = inode; - bbio->file_offset = start; + btrfs_bio_init(bbio, inode, start, end_io, NULL); return to_compressed_bio(bbio); } @@ -354,7 +352,7 @@ static void end_bbio_compressed_write(struct btrfs_bio *bbio) static void btrfs_add_compressed_bio_folios(struct compressed_bio *cb) { - struct btrfs_fs_info *fs_info = cb->bbio.fs_info; + struct btrfs_fs_info *fs_info = cb->bbio.inode->root->fs_info; struct bio *bio = &cb->bbio.bio; u32 offset = 0; diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index eba188a9e3bb58..062ebd9c2d32d1 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -14,14 +14,12 @@ #include #include "bio.h" #include "fs.h" -#include "messages.h" +#include "btrfs_inode.h" struct address_space; -struct page; struct inode; struct btrfs_inode; struct btrfs_ordered_extent; -struct btrfs_bio; /* * We want to make sure that amount of RAM required to uncompress an extent is @@ -77,7 +75,7 @@ struct compressed_bio { static inline struct btrfs_fs_info *cb_to_fs_info(const struct compressed_bio *cb) { - return cb->bbio.fs_info; + return cb->bbio.inode->root->fs_info; } /* @range_end must be exclusive. */ diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 561658aca018b4..6e053caa6e101b 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -4566,9 +4566,9 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, if (btrfs_header_nritems(leaf) == 0) { path->slots[1] = slot; ret = btrfs_del_leaf(trans, root, path, leaf); + free_extent_buffer(leaf); if (ret < 0) return ret; - free_extent_buffer(leaf); ret = 0; } else { /* if we're still in the path, make sure diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index fe70b593c7cd9d..16dd11c4853130 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -17,9 +17,7 @@ #include #include #include "locking.h" -#include "fs.h" #include "accessors.h" -#include "extent-io-tree.h" struct extent_buffer; struct btrfs_block_rsv; diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c index 7b277934f66f92..a4cc1bc6356227 100644 --- a/fs/btrfs/defrag.c +++ b/fs/btrfs/defrag.c @@ -15,6 +15,7 @@ #include "defrag.h" #include "file-item.h" #include "super.h" +#include "compression.h" static struct kmem_cache *btrfs_inode_defrag_cachep; diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 3df7b9d7fbe8d3..59b489d7e4b588 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -152,37 +152,39 @@ static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node( return ERR_PTR(-ENOMEM); btrfs_init_delayed_node(node, root, ino); + /* Cached in the inode and can be accessed. */ + refcount_set(&node->refs, 2); + btrfs_delayed_node_ref_tracker_alloc(node, tracker, GFP_NOFS); + btrfs_delayed_node_ref_tracker_alloc(node, &node->inode_cache_tracker, GFP_NOFS); + /* Allocate and reserve the slot, from now it can return a NULL from xa_load(). */ ret = xa_reserve(&root->delayed_nodes, ino, GFP_NOFS); - if (ret == -ENOMEM) { - btrfs_delayed_node_ref_tracker_dir_exit(node); - kmem_cache_free(delayed_node_cache, node); - return ERR_PTR(-ENOMEM); - } + if (ret == -ENOMEM) + goto cleanup; + xa_lock(&root->delayed_nodes); ptr = xa_load(&root->delayed_nodes, ino); if (ptr) { /* Somebody inserted it, go back and read it. */ xa_unlock(&root->delayed_nodes); - btrfs_delayed_node_ref_tracker_dir_exit(node); - kmem_cache_free(delayed_node_cache, node); - node = NULL; - goto again; + goto cleanup; } ptr = __xa_store(&root->delayed_nodes, ino, node, GFP_ATOMIC); ASSERT(xa_err(ptr) != -EINVAL); ASSERT(xa_err(ptr) != -ENOMEM); ASSERT(ptr == NULL); - - /* Cached in the inode and can be accessed. */ - refcount_set(&node->refs, 2); - btrfs_delayed_node_ref_tracker_alloc(node, tracker, GFP_ATOMIC); - btrfs_delayed_node_ref_tracker_alloc(node, &node->inode_cache_tracker, GFP_ATOMIC); - btrfs_inode->delayed_node = node; xa_unlock(&root->delayed_nodes); return node; +cleanup: + btrfs_delayed_node_ref_tracker_free(node, tracker); + btrfs_delayed_node_ref_tracker_free(node, &node->inode_cache_tracker); + btrfs_delayed_node_ref_tracker_dir_exit(node); + kmem_cache_free(delayed_node_cache, node); + if (ret) + return ERR_PTR(ret); + goto again; } /* diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 481802efaa1436..f8fc26272f76c5 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -798,9 +798,13 @@ static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref, } /* - * helper function to actually insert a head node into the rbtree. - * this does all the dirty work in terms of maintaining the correct - * overall modification count. + * Helper function to actually insert a head node into the xarray. This does all + * the dirty work in terms of maintaining the correct overall modification + * count. + * + * The caller is responsible for calling kfree() on @qrecord. More specifically, + * if this function reports that it did not insert it as noted in + * @qrecord_inserted_ret, then it's safe to call kfree() on it. * * Returns an error pointer in case of an error. */ @@ -814,7 +818,14 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_root *delayed_refs; const unsigned long index = (head_ref->bytenr >> fs_info->sectorsize_bits); - bool qrecord_inserted = false; + + /* + * If 'qrecord_inserted_ret' is provided, then the first thing we need + * to do is to initialize it to false just in case we have an exit + * before trying to insert the record. + */ + if (qrecord_inserted_ret) + *qrecord_inserted_ret = false; delayed_refs = &trans->transaction->delayed_refs; lockdep_assert_held(&delayed_refs->lock); @@ -833,6 +844,12 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, /* Record qgroup extent info if provided */ if (qrecord) { + /* + * Setting 'qrecord' but not 'qrecord_inserted_ret' will likely + * result in a memory leakage. + */ + ASSERT(qrecord_inserted_ret != NULL); + int ret; ret = btrfs_qgroup_trace_extent_nolock(fs_info, delayed_refs, qrecord, @@ -840,12 +857,10 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, if (ret) { /* Clean up if insertion fails or item exists. */ xa_release(&delayed_refs->dirty_extents, index); - /* Caller responsible for freeing qrecord on error. */ if (ret < 0) return ERR_PTR(ret); - kfree(qrecord); - } else { - qrecord_inserted = true; + } else if (qrecord_inserted_ret) { + *qrecord_inserted_ret = true; } } @@ -888,8 +903,6 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, delayed_refs->num_heads++; delayed_refs->num_heads_ready++; } - if (qrecord_inserted_ret) - *qrecord_inserted_ret = qrecord_inserted; return head_ref; } @@ -1049,6 +1062,14 @@ static int add_delayed_ref(struct btrfs_trans_handle *trans, xa_release(&delayed_refs->head_refs, index); spin_unlock(&delayed_refs->lock); ret = PTR_ERR(new_head_ref); + + /* + * It's only safe to call kfree() on 'qrecord' if + * add_delayed_ref_head() has _not_ inserted it for + * tracing. Otherwise we need to handle this here. + */ + if (!qrecord_reserved || qrecord_inserted) + goto free_head_ref; goto free_record; } head_ref = new_head_ref; @@ -1071,6 +1092,8 @@ static int add_delayed_ref(struct btrfs_trans_handle *trans, if (qrecord_inserted) return btrfs_qgroup_trace_extent_post(trans, record, generic_ref->bytenr); + + kfree(record); return 0; free_record: diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 69863e398e223f..77e1bcb2a74bf1 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -9,6 +9,7 @@ #include "transaction.h" #include "accessors.h" #include "dir-item.h" +#include "delayed-inode.h" /* * insert a name into a directory, doing overflow properly if there is a hash diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c index 802d4dbe5b3817..e29ea28ce90b9a 100644 --- a/fs/btrfs/direct-io.c +++ b/fs/btrfs/direct-io.c @@ -10,6 +10,8 @@ #include "fs.h" #include "transaction.h" #include "volumes.h" +#include "bio.h" +#include "ordered-data.h" struct btrfs_dio_data { ssize_t submitted; @@ -713,10 +715,8 @@ static void btrfs_dio_submit_io(const struct iomap_iter *iter, struct bio *bio, container_of(bbio, struct btrfs_dio_private, bbio); struct btrfs_dio_data *dio_data = iter->private; - btrfs_bio_init(bbio, BTRFS_I(iter->inode)->root->fs_info, + btrfs_bio_init(bbio, BTRFS_I(iter->inode), file_offset, btrfs_dio_end_io, bio->bi_private); - bbio->inode = BTRFS_I(iter->inode); - bbio->file_offset = file_offset; dip->file_offset = file_offset; dip->bytes = bio->bi_iter.bi_size; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 0aa7e5d1b05f6c..3fd5d6a27d4c0e 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -50,6 +50,7 @@ #include "relocation.h" #include "scrub.h" #include "super.h" +#include "delayed-inode.h" #define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\ BTRFS_HEADER_FLAG_RELOC |\ @@ -490,28 +491,6 @@ static int btree_migrate_folio(struct address_space *mapping, #define btree_migrate_folio NULL #endif -static int btree_writepages(struct address_space *mapping, - struct writeback_control *wbc) -{ - int ret; - - if (wbc->sync_mode == WB_SYNC_NONE) { - struct btrfs_fs_info *fs_info; - - if (wbc->for_kupdate) - return 0; - - fs_info = inode_to_fs_info(mapping->host); - /* this is a bit racy, but that's ok */ - ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes, - BTRFS_DIRTY_METADATA_THRESH, - fs_info->dirty_metadata_batch); - if (ret < 0) - return 0; - } - return btree_write_cache_pages(mapping, wbc); -} - static bool btree_release_folio(struct folio *folio, gfp_t gfp_flags) { if (folio_test_writeback(folio) || folio_test_dirty(folio)) @@ -1666,7 +1645,7 @@ static void backup_super_roots(struct btrfs_fs_info *info) btrfs_set_backup_chunk_root_level(root_backup, btrfs_header_level(info->chunk_root->node)); - if (!btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE)) { + if (!btrfs_fs_incompat(info, EXTENT_TREE_V2)) { struct btrfs_root *extent_root = btrfs_extent_root(info, 0); struct btrfs_root *csum_root = btrfs_csum_root(info, 0); @@ -3270,6 +3249,15 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount) return 0; } +static bool fs_is_full_ro(const struct btrfs_fs_info *fs_info) +{ + if (!sb_rdonly(fs_info->sb)) + return false; + if (unlikely(fs_info->mount_opt & BTRFS_MOUNT_FULL_RO_MASK)) + return true; + return false; +} + int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices) { u32 sectorsize; @@ -3378,6 +3366,10 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR) WRITE_ONCE(fs_info->fs_error, -EUCLEAN); + /* If the fs has any rescue options, no transaction is allowed. */ + if (fs_is_full_ro(fs_info)) + WRITE_ONCE(fs_info->fs_error, -EROFS); + /* Set up fs_info before parsing mount options */ nodesize = btrfs_super_nodesize(disk_super); sectorsize = btrfs_super_sectorsize(disk_super); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 57920f2c6fe4ef..5320da83d0cf8e 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -9,7 +9,8 @@ #include #include #include "ctree.h" -#include "fs.h" +#include "bio.h" +#include "ordered-data.h" struct block_device; struct super_block; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index dc4ca98c37800a..01337e3f2879c7 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -40,6 +40,7 @@ #include "orphan.h" #include "tree-checker.h" #include "raid-stripe-tree.h" +#include "delayed-inode.h" #undef SCRAMBLE_DELAYED_REFS diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 23273d0e6f2245..c3524401ff03eb 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -518,7 +518,7 @@ static void end_folio_read(struct folio *folio, bool uptodate, u64 start, u32 le */ static void end_bbio_data_write(struct btrfs_bio *bbio) { - struct btrfs_fs_info *fs_info = bbio->fs_info; + struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info; struct bio *bio = &bbio->bio; int error = blk_status_to_errno(bio->bi_status); struct folio_iter fi; @@ -574,7 +574,7 @@ static void begin_folio_read(struct btrfs_fs_info *fs_info, struct folio *folio) */ static void end_bbio_data_read(struct btrfs_bio *bbio) { - struct btrfs_fs_info *fs_info = bbio->fs_info; + struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info; struct bio *bio = &bbio->bio; struct folio_iter fi; @@ -739,12 +739,10 @@ static void alloc_new_bio(struct btrfs_inode *inode, struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_bio *bbio; - bbio = btrfs_bio_alloc(BIO_MAX_VECS, bio_ctrl->opf, fs_info, - bio_ctrl->end_io_func, NULL); + bbio = btrfs_bio_alloc(BIO_MAX_VECS, bio_ctrl->opf, inode, + file_offset, bio_ctrl->end_io_func, NULL); bbio->bio.bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT; bbio->bio.bi_write_hint = inode->vfs_inode.i_write_hint; - bbio->inode = inode; - bbio->file_offset = file_offset; bio_ctrl->bbio = bbio; bio_ctrl->len_to_oe_boundary = U32_MAX; bio_ctrl->next_file_offset = file_offset; @@ -1691,14 +1689,15 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, unsigned long range_bitmap = 0; bool submitted_io = false; int found_error = 0; + const u64 end = start + len; const u64 folio_start = folio_pos(folio); + const u64 folio_end = folio_start + folio_size(folio); const unsigned int blocks_per_folio = btrfs_blocks_per_folio(fs_info, folio); u64 cur; int bit; int ret = 0; - ASSERT(start >= folio_start && - start + len <= folio_start + folio_size(folio)); + ASSERT(start >= folio_start && end <= folio_end); ret = btrfs_writepage_cow_fixup(folio); if (ret == -EAGAIN) { @@ -1714,7 +1713,7 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, return ret; } - for (cur = start; cur < start + len; cur += fs_info->sectorsize) + for (cur = start; cur < end; cur += fs_info->sectorsize) set_bit((cur - folio_start) >> fs_info->sectorsize_bits, &range_bitmap); bitmap_and(&bio_ctrl->submit_bitmap, &bio_ctrl->submit_bitmap, &range_bitmap, blocks_per_folio); @@ -1725,8 +1724,25 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, cur = folio_pos(folio) + (bit << fs_info->sectorsize_bits); if (cur >= i_size) { + struct btrfs_ordered_extent *ordered; + unsigned long flags; + + ordered = btrfs_lookup_first_ordered_range(inode, cur, + fs_info->sectorsize); + /* + * We have just run delalloc before getting here, so + * there must be an ordered extent. + */ + ASSERT(ordered != NULL); + spin_lock_irqsave(&inode->ordered_tree_lock, flags); + set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags); + ordered->truncated_len = min(ordered->truncated_len, + cur - ordered->file_offset); + spin_unlock_irqrestore(&inode->ordered_tree_lock, flags); + btrfs_put_ordered_extent(ordered); + btrfs_mark_ordered_io_finished(inode, folio, cur, - start + len - cur, true); + fs_info->sectorsize, true); /* * This range is beyond i_size, thus we don't need to * bother writing back. @@ -1735,9 +1751,8 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, * writeback the sectors with subpage dirty bits, * causing writeback without ordered extent. */ - btrfs_folio_clear_dirty(fs_info, folio, cur, - start + len - cur); - break; + btrfs_folio_clear_dirty(fs_info, folio, cur, fs_info->sectorsize); + continue; } ret = submit_one_sector(inode, folio, cur, bio_ctrl, i_size); if (unlikely(ret < 0)) { @@ -2206,12 +2221,11 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb, bbio = btrfs_bio_alloc(INLINE_EXTENT_BUFFER_PAGES, REQ_OP_WRITE | REQ_META | wbc_to_write_flags(wbc), - eb->fs_info, end_bbio_meta_write, eb); + BTRFS_I(fs_info->btree_inode), eb->start, + end_bbio_meta_write, eb); bbio->bio.bi_iter.bi_sector = eb->start >> SECTOR_SHIFT; bio_set_dev(&bbio->bio, fs_info->fs_devices->latest_dev->bdev); wbc_init_bio(wbc, &bbio->bio); - bbio->inode = BTRFS_I(eb->fs_info->btree_inode); - bbio->file_offset = eb->start; for (int i = 0; i < num_extent_folios(eb); i++) { struct folio *folio = eb->folios[i]; u64 range_start = max_t(u64, eb->start, folio_pos(folio)); @@ -2272,8 +2286,7 @@ void btrfs_btree_wait_writeback_range(struct btrfs_fs_info *fs_info, u64 start, } } -int btree_write_cache_pages(struct address_space *mapping, - struct writeback_control *wbc) +int btree_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct btrfs_eb_write_context ctx = { .wbc = wbc }; struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host); @@ -3826,6 +3839,7 @@ static void end_bbio_meta_read(struct btrfs_bio *bbio) int read_extent_buffer_pages_nowait(struct extent_buffer *eb, int mirror_num, const struct btrfs_tree_parent_check *check) { + struct btrfs_fs_info *fs_info = eb->fs_info; struct btrfs_bio *bbio; if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) @@ -3859,11 +3873,9 @@ int read_extent_buffer_pages_nowait(struct extent_buffer *eb, int mirror_num, refcount_inc(&eb->refs); bbio = btrfs_bio_alloc(INLINE_EXTENT_BUFFER_PAGES, - REQ_OP_READ | REQ_META, eb->fs_info, - end_bbio_meta_read, eb); + REQ_OP_READ | REQ_META, BTRFS_I(fs_info->btree_inode), + eb->start, end_bbio_meta_read, eb); bbio->bio.bi_iter.bi_sector = eb->start >> SECTOR_SHIFT; - bbio->inode = BTRFS_I(eb->fs_info->btree_inode); - bbio->file_offset = eb->start; memcpy(&bbio->parent_check, check, sizeof(*check)); for (int i = 0; i < num_extent_folios(eb); i++) { struct folio *folio = eb->folios[i]; diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 5fcbfe44218c44..73571d5d3d5ad9 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -12,7 +12,6 @@ #include #include #include -#include "compression.h" #include "messages.h" #include "ulist.h" #include "misc.h" @@ -238,8 +237,7 @@ void extent_write_locked_range(struct inode *inode, const struct folio *locked_f u64 start, u64 end, struct writeback_control *wbc, bool pages_dirty); int btrfs_writepages(struct address_space *mapping, struct writeback_control *wbc); -int btree_write_cache_pages(struct address_space *mapping, - struct writeback_control *wbc); +int btree_writepages(struct address_space *mapping, struct writeback_control *wbc); void btrfs_btree_wait_writeback_range(struct btrfs_fs_info *fs_info, u64 start, u64 end); void btrfs_readahead(struct readahead_control *rac); int set_folio_extent_mapped(struct folio *folio); diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h index d4b81ee4d97bdb..6f685f3c932721 100644 --- a/fs/btrfs/extent_map.h +++ b/fs/btrfs/extent_map.h @@ -8,8 +8,7 @@ #include #include #include -#include "misc.h" -#include "compression.h" +#include "fs.h" struct btrfs_inode; struct btrfs_fs_info; diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index a42e6d54e7cd74..4b7c40f05e8f9e 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -18,6 +18,7 @@ #include "fs.h" #include "accessors.h" #include "file-item.h" +#include "volumes.h" #define __MAX_CSUM_ITEMS(r, size) ((unsigned long)(((BTRFS_LEAF_DATA_SIZE(r) - \ sizeof(struct btrfs_item) * 2) / \ @@ -764,21 +765,46 @@ int btrfs_lookup_csums_bitmap(struct btrfs_root *root, struct btrfs_path *path, return ret; } +static void csum_one_bio(struct btrfs_bio *bbio, struct bvec_iter *src) +{ + struct btrfs_inode *inode = bbio->inode; + struct btrfs_fs_info *fs_info = inode->root->fs_info; + SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); + struct bio *bio = &bbio->bio; + struct btrfs_ordered_sum *sums = bbio->sums; + struct bvec_iter iter = *src; + phys_addr_t paddr; + const u32 blocksize = fs_info->sectorsize; + int index = 0; + + shash->tfm = fs_info->csum_shash; + + btrfs_bio_for_each_block(paddr, bio, &iter, blocksize) { + btrfs_calculate_block_csum(fs_info, paddr, sums->sums + index); + index += fs_info->csum_size; + } +} + +static void csum_one_bio_work(struct work_struct *work) +{ + struct btrfs_bio *bbio = container_of(work, struct btrfs_bio, csum_work); + + ASSERT(btrfs_op(&bbio->bio) == BTRFS_MAP_WRITE); + ASSERT(bbio->async_csum == true); + csum_one_bio(bbio, &bbio->csum_saved_iter); + complete(&bbio->csum_done); +} + /* * Calculate checksums of the data contained inside a bio. */ -int btrfs_csum_one_bio(struct btrfs_bio *bbio) +int btrfs_csum_one_bio(struct btrfs_bio *bbio, bool async) { struct btrfs_ordered_extent *ordered = bbio->ordered; struct btrfs_inode *inode = bbio->inode; struct btrfs_fs_info *fs_info = inode->root->fs_info; - SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); struct bio *bio = &bbio->bio; struct btrfs_ordered_sum *sums; - struct bvec_iter iter = bio->bi_iter; - phys_addr_t paddr; - const u32 blocksize = fs_info->sectorsize; - int index; unsigned nofs_flag; nofs_flag = memalloc_nofs_save(); @@ -789,21 +815,21 @@ int btrfs_csum_one_bio(struct btrfs_bio *bbio) if (!sums) return -ENOMEM; + sums->logical = bio->bi_iter.bi_sector << SECTOR_SHIFT; sums->len = bio->bi_iter.bi_size; INIT_LIST_HEAD(&sums->list); - - sums->logical = bio->bi_iter.bi_sector << SECTOR_SHIFT; - index = 0; - - shash->tfm = fs_info->csum_shash; - - btrfs_bio_for_each_block(paddr, bio, &iter, blocksize) { - btrfs_calculate_block_csum(fs_info, paddr, sums->sums + index); - index += fs_info->csum_size; - } - bbio->sums = sums; btrfs_add_ordered_sum(ordered, sums); + + if (!async) { + csum_one_bio(bbio, &bbio->bio.bi_iter); + return 0; + } + init_completion(&bbio->csum_done); + bbio->async_csum = true; + bbio->csum_saved_iter = bbio->bio.bi_iter; + INIT_WORK(&bbio->csum_work, csum_one_bio_work); + schedule_work(&bbio->csum_work); return 0; } diff --git a/fs/btrfs/file-item.h b/fs/btrfs/file-item.h index 63216c43676def..5645c5e3abdb79 100644 --- a/fs/btrfs/file-item.h +++ b/fs/btrfs/file-item.h @@ -7,7 +7,7 @@ #include #include #include "ctree.h" -#include "accessors.h" +#include "ordered-data.h" struct extent_map; struct btrfs_file_extent_item; @@ -64,7 +64,7 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans, int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_ordered_sum *sums); -int btrfs_csum_one_bio(struct btrfs_bio *bbio); +int btrfs_csum_one_bio(struct btrfs_bio *bbio, bool async); int btrfs_alloc_dummy_sum(struct btrfs_bio *bbio); int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, struct list_head *list, int search_commit, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index fa82def46e3952..0fee45d35a5f83 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2018,13 +2018,14 @@ static vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf) else btrfs_delalloc_release_space(inode, data_reserved, page_start, reserved_space, true); - extent_changeset_free(data_reserved); out_noreserve: if (only_release_metadata) btrfs_check_nocow_unlock(inode); sb_end_pagefault(inode->vfs_inode.i_sb); + extent_changeset_free(data_reserved); + if (ret < 0) return vmf_error(ret); diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index 814bbc9417d2a2..37aa8d141a83d8 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -250,6 +250,14 @@ enum { BTRFS_MOUNT_REF_TRACKER = (1ULL << 33), }; +/* These mount options require a full read-only fs, no new transaction is allowed. */ +#define BTRFS_MOUNT_FULL_RO_MASK \ + (BTRFS_MOUNT_NOLOGREPLAY | \ + BTRFS_MOUNT_IGNOREBADROOTS | \ + BTRFS_MOUNT_IGNOREDATACSUMS | \ + BTRFS_MOUNT_IGNOREMETACSUMS | \ + BTRFS_MOUNT_IGNORESUPERFLAGS) + /* * Compat flags that we support. If any incompat flags are set other than the * ones specified below then we will fail to mount diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6282911e536f08..47e762856521d3 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -71,6 +71,7 @@ #include "backref.h" #include "raid-stripe-tree.h" #include "fiemap.h" +#include "delayed-inode.h" #define COW_FILE_RANGE_KEEP_LOCKED (1UL << 0) #define COW_FILE_RANGE_NO_INLINE (1UL << 1) @@ -256,6 +257,7 @@ static void print_data_reloc_error(const struct btrfs_inode *inode, u64 file_off if (ret < 0) { btrfs_err_rl(fs_info, "failed to lookup extent item for logical %llu: %d", logical, ret); + btrfs_release_path(&path); return; } eb = path.nodes[0]; @@ -613,19 +615,22 @@ static noinline int __cow_file_range_inline(struct btrfs_inode *inode, struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; - struct btrfs_trans_handle *trans; + struct btrfs_trans_handle *trans = NULL; u64 data_len = (compressed_size ?: size); int ret; struct btrfs_path *path; path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + ret = -ENOMEM; + goto out; + } trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { - btrfs_free_path(path); - return PTR_ERR(trans); + ret = PTR_ERR(trans); + trans = NULL; + goto out; } trans->block_rsv = &inode->block_rsv; @@ -669,10 +674,15 @@ static noinline int __cow_file_range_inline(struct btrfs_inode *inode, * it won't count as data extent, free them directly here. * And at reserve time, it's always aligned to page size, so * just free one page here. + * + * If we fallback to non-inline (ret == 1) due to -ENOSPC, then we need + * to keep the data reservation. */ - btrfs_qgroup_free_data(inode, NULL, 0, fs_info->sectorsize, NULL); + if (ret <= 0) + btrfs_qgroup_free_data(inode, NULL, 0, fs_info->sectorsize, NULL); btrfs_free_path(path); - btrfs_end_transaction(trans); + if (trans) + btrfs_end_transaction(trans); return ret; } @@ -3975,11 +3985,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path btrfs_set_inode_mapping_order(inode); cache_index: - ret = btrfs_init_file_extent_tree(inode); - if (ret) - goto out; - btrfs_inode_set_file_extent_range(inode, 0, - round_up(i_size_read(vfs_inode), fs_info->sectorsize)); /* * If we were modified in the current generation and evicted from memory * and then re-read we need to do a full sync since we don't have any @@ -4066,6 +4071,20 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path btrfs_ino(inode), btrfs_root_id(root), ret); } + /* + * We don't need the path anymore, so release it to avoid holding a read + * lock on a leaf while calling btrfs_init_file_extent_tree(), which can + * allocate memory that triggers reclaim (GFP_KERNEL) and cause a locking + * dependency. + */ + btrfs_release_path(path); + + ret = btrfs_init_file_extent_tree(inode); + if (ret) + goto out; + btrfs_inode_set_file_extent_range(inode, 0, + round_up(i_size_read(vfs_inode), fs_info->sectorsize)); + if (!maybe_acls) cache_no_acl(vfs_inode); @@ -4098,6 +4117,15 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path return 0; out: + /* + * We may have a read locked leaf and iget_failed() triggers inode + * eviction which needs to release the delayed inode and that needs + * to lock the delayed inode's mutex. This can cause a ABBA deadlock + * with a task running delayed items, as that require first locking + * the delayed inode's mutex and then modifying its subvolume btree. + * So release the path before iget_failed(). + */ + btrfs_release_path(path); iget_failed(vfs_inode); return ret; } @@ -9395,7 +9423,6 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, u64 disk_bytenr, u64 disk_io_size, struct page **pages, void *uring_ctx) { - struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_encoded_read_private *priv, sync_priv; struct completion sync_reads; unsigned long i = 0; @@ -9420,10 +9447,9 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, priv->status = 0; priv->uring_ctx = uring_ctx; - bbio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ, fs_info, + bbio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ, inode, 0, btrfs_encoded_read_endio, priv); bbio->bio.bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT; - bbio->inode = inode; do { size_t bytes = min_t(u64, disk_io_size, PAGE_SIZE); @@ -9432,10 +9458,9 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, refcount_inc(&priv->pending_refs); btrfs_submit_bbio(bbio, 0); - bbio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ, fs_info, + bbio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ, inode, 0, btrfs_encoded_read_endio, priv); bbio->bio.bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT; - bbio->inode = inode; continue; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8cb7d5a462ef79..9a34d6530658e5 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1913,10 +1913,8 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, ret = inode_permission(idmap, &temp_inode->vfs_inode, MAY_READ | MAY_EXEC); iput(&temp_inode->vfs_inode); - if (ret) { - ret = -EACCES; + if (ret) goto out_put; - } if (key.offset == upper_limit) break; diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 2829f20d7bb59d..8a8aa6ed405bd4 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -1098,8 +1098,9 @@ struct btrfs_ordered_extent *btrfs_lookup_first_ordered_range( struct rb_node *prev; struct rb_node *next; struct btrfs_ordered_extent *entry = NULL; + unsigned long flags; - spin_lock_irq(&inode->ordered_tree_lock); + spin_lock_irqsave(&inode->ordered_tree_lock, flags); node = inode->ordered_tree.rb_node; /* * Here we don't want to use tree_search() which will use tree->last @@ -1154,7 +1155,7 @@ struct btrfs_ordered_extent *btrfs_lookup_first_ordered_range( trace_btrfs_ordered_extent_lookup_first_range(inode, entry); } - spin_unlock_irq(&inode->ordered_tree_lock); + spin_unlock_irqrestore(&inode->ordered_tree_lock, flags); return entry; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 31ad8580322a6e..302bb3ecf39a32 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1157,11 +1157,14 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, } if (ret > 0) { /* - * Shouldn't happen, but in case it does we - * don't need to do the btrfs_next_item, just - * continue. + * Shouldn't happen because the key should still + * be there (return 0), but in case it does it + * means we have reached the end of the tree - + * there are no more leaves with items that have + * a key greater than or equals to @found_key, + * so just stop the search loop. */ - continue; + break; } } ret = btrfs_next_item(tree_root, path); @@ -1627,8 +1630,10 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, if (ret < 0 && ret != -ENOENT) goto out; ret2 = del_qgroup_relation_item(trans, dst, src); - if (ret2 < 0 && ret2 != -ENOENT) + if (ret2 < 0 && ret2 != -ENOENT) { + ret = ret2; goto out; + } /* At least one deletion succeeded, return 0 */ if (!ret || !ret2) @@ -3244,9 +3249,15 @@ static int qgroup_snapshot_quick_inherit(struct btrfs_fs_info *fs_info, { struct btrfs_qgroup *src; struct btrfs_qgroup *parent; + struct btrfs_qgroup *qgroup; struct btrfs_qgroup_list *list; + LIST_HEAD(qgroup_list); + const u32 nodesize = fs_info->nodesize; int nr_parents = 0; + if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_FULL) + return 0; + src = find_qgroup_rb(fs_info, srcid); if (!src) return -ENOENT; @@ -3281,8 +3292,19 @@ static int qgroup_snapshot_quick_inherit(struct btrfs_fs_info *fs_info, if (parent->excl != parent->rfer) return 1; - parent->excl += fs_info->nodesize; - parent->rfer += fs_info->nodesize; + qgroup_iterator_add(&qgroup_list, parent); + list_for_each_entry(qgroup, &qgroup_list, iterator) { + qgroup->rfer += nodesize; + qgroup->rfer_cmpr += nodesize; + qgroup->excl += nodesize; + qgroup->excl_cmpr += nodesize; + qgroup_dirty(fs_info, qgroup); + + /* Append parent qgroups to @qgroup_list. */ + list_for_each_entry(list, &qgroup->groups, next_group) + qgroup_iterator_add(&qgroup_list, list->group); + } + qgroup_iterator_clean(&qgroup_list); return 0; } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index ba20d9286a340c..747e2c748376a3 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -929,10 +929,11 @@ static int calc_next_mirror(int mirror, int num_copies) static void scrub_bio_add_sector(struct btrfs_bio *bbio, struct scrub_stripe *stripe, int sector_nr) { + struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info; void *kaddr = scrub_stripe_get_kaddr(stripe, sector_nr); int ret; - ret = bio_add_page(&bbio->bio, virt_to_page(kaddr), bbio->fs_info->sectorsize, + ret = bio_add_page(&bbio->bio, virt_to_page(kaddr), fs_info->sectorsize, offset_in_page(kaddr)); /* * Caller should ensure the bbio has enough size. @@ -942,7 +943,21 @@ static void scrub_bio_add_sector(struct btrfs_bio *bbio, struct scrub_stripe *st * to create the minimal amount of bio vectors, for fs block size < page * size cases. */ - ASSERT(ret == bbio->fs_info->sectorsize); + ASSERT(ret == fs_info->sectorsize); +} + +static struct btrfs_bio *alloc_scrub_bbio(struct btrfs_fs_info *fs_info, + unsigned int nr_vecs, blk_opf_t opf, + u64 logical, + btrfs_bio_end_io_t end_io, void *private) +{ + struct btrfs_bio *bbio; + + bbio = btrfs_bio_alloc(nr_vecs, opf, BTRFS_I(fs_info->btree_inode), + logical, end_io, private); + bbio->is_scrub = true; + bbio->bio.bi_iter.bi_sector = logical >> SECTOR_SHIFT; + return bbio; } static void scrub_stripe_submit_repair_read(struct scrub_stripe *stripe, @@ -968,12 +983,10 @@ static void scrub_stripe_submit_repair_read(struct scrub_stripe *stripe, bbio = NULL; } - if (!bbio) { - bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_READ, - fs_info, scrub_repair_read_endio, stripe); - bbio->bio.bi_iter.bi_sector = (stripe->logical + - (i << fs_info->sectorsize_bits)) >> SECTOR_SHIFT; - } + if (!bbio) + bbio = alloc_scrub_bbio(fs_info, stripe->nr_sectors, REQ_OP_READ, + stripe->logical + (i << fs_info->sectorsize_bits), + scrub_repair_read_endio, stripe); scrub_bio_add_sector(bbio, stripe, i); } @@ -1352,13 +1365,10 @@ static void scrub_write_sectors(struct scrub_ctx *sctx, struct scrub_stripe *str scrub_submit_write_bio(sctx, stripe, bbio, dev_replace); bbio = NULL; } - if (!bbio) { - bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_WRITE, - fs_info, scrub_write_endio, stripe); - bbio->bio.bi_iter.bi_sector = (stripe->logical + - (sector_nr << fs_info->sectorsize_bits)) >> - SECTOR_SHIFT; - } + if (!bbio) + bbio = alloc_scrub_bbio(fs_info, stripe->nr_sectors, REQ_OP_WRITE, + stripe->logical + (sector_nr << fs_info->sectorsize_bits), + scrub_write_endio, stripe); scrub_bio_add_sector(bbio, stripe, sector_nr); } if (bbio) @@ -1849,9 +1859,8 @@ static void scrub_submit_extent_sector_read(struct scrub_stripe *stripe) continue; } - bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_READ, - fs_info, scrub_read_endio, stripe); - bbio->bio.bi_iter.bi_sector = logical >> SECTOR_SHIFT; + bbio = alloc_scrub_bbio(fs_info, stripe->nr_sectors, REQ_OP_READ, + logical, scrub_read_endio, stripe); } scrub_bio_add_sector(bbio, stripe, i); @@ -1888,10 +1897,8 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx, return; } - bbio = btrfs_bio_alloc(BTRFS_STRIPE_LEN >> min_folio_shift, REQ_OP_READ, fs_info, - scrub_read_endio, stripe); - - bbio->bio.bi_iter.bi_sector = stripe->logical >> SECTOR_SHIFT; + bbio = alloc_scrub_bbio(fs_info, BTRFS_STRIPE_LEN >> min_folio_shift, REQ_OP_READ, + stripe->logical, scrub_read_endio, stripe); /* Read the whole range inside the chunk boundary. */ for (unsigned int cur = 0; cur < nr_sectors; cur++) scrub_bio_add_sector(bbio, stripe, cur); @@ -2230,9 +2237,9 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx, bio_put(bio); btrfs_bio_counter_dec(fs_info); +out: btrfs_release_path(&extent_path); btrfs_release_path(&csum_path); -out: return ret; } @@ -3039,6 +3046,10 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, unsigned int nofs_flag; bool need_commit = false; + /* Set the basic fallback @last_physical before we got a sctx. */ + if (progress) + progress->last_physical = start; + if (btrfs_fs_closing(fs_info)) return -EAGAIN; @@ -3057,6 +3068,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, sctx = scrub_setup_ctx(fs_info, is_dev_replace); if (IS_ERR(sctx)) return PTR_ERR(sctx); + sctx->stat.last_physical = start; ret = scrub_workers_get(fs_info); if (ret) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 96a030d28e0910..9012ce7a742f49 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6399,6 +6399,8 @@ static int range_is_hole_in_parent(struct send_ctx *sctx, extent_end = btrfs_file_extent_end(path); if (extent_end <= start) goto next; + if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) + return 0; if (btrfs_file_extent_disk_bytenr(leaf, fi) == 0) { search_start = extent_end; goto next; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 97452fb5d29b02..474ed47095ba7d 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -15,6 +15,7 @@ #include "accessors.h" #include "extent-tree.h" #include "zoned.h" +#include "delayed-inode.h" /* * HOW DOES SPACE RESERVATION WORK @@ -192,7 +193,7 @@ void btrfs_clear_space_info_full(struct btrfs_fs_info *info) struct btrfs_space_info *found; list_for_each_entry(found, head, list) - found->full = 0; + found->full = false; } /* @@ -305,18 +306,22 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) 0); if (ret) - return ret; + goto out_free; } ret = btrfs_sysfs_add_space_info_type(info, space_info); if (ret) - return ret; + goto out_free; list_add(&space_info->list, &info->space_info); if (flags & BTRFS_BLOCK_GROUP_DATA) info->data_sinfo = space_info; return ret; + +out_free: + kfree(space_info); + return ret; } int btrfs_init_space_info(struct btrfs_fs_info *fs_info) @@ -372,8 +377,8 @@ void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, space_info->bytes_readonly += block_group->bytes_super; btrfs_space_info_update_bytes_zone_unusable(space_info, block_group->zone_unusable); if (block_group->length > 0) - space_info->full = 0; - btrfs_try_granting_tickets(info, space_info); + space_info->full = false; + btrfs_try_granting_tickets(space_info); spin_unlock(&space_info->lock); block_group->space_info = space_info; @@ -523,9 +528,9 @@ static void remove_ticket(struct btrfs_space_info *space_info, * This is for space we already have accounted in space_info->bytes_may_use, so * basically when we're returning space from block_rsv's. */ -void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info) +void btrfs_try_granting_tickets(struct btrfs_space_info *space_info) { + struct btrfs_fs_info *fs_info = space_info->fs_info; struct list_head *head; enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_NO_FLUSH; @@ -1124,7 +1129,7 @@ static bool maybe_fail_all_tickets(struct btrfs_fs_info *fs_info, * the list. */ if (!aborted) - btrfs_try_granting_tickets(fs_info, space_info); + btrfs_try_granting_tickets(space_info); } return (tickets_id != space_info->tickets_id); } @@ -1146,7 +1151,7 @@ static void do_async_reclaim_metadata_space(struct btrfs_space_info *space_info) spin_lock(&space_info->lock); to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info); if (!to_reclaim) { - space_info->flush = 0; + space_info->flush = false; spin_unlock(&space_info->lock); return; } @@ -1158,7 +1163,7 @@ static void do_async_reclaim_metadata_space(struct btrfs_space_info *space_info) flush_space(fs_info, space_info, to_reclaim, flush_state, false); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { - space_info->flush = 0; + space_info->flush = false; spin_unlock(&space_info->lock); return; } @@ -1201,7 +1206,7 @@ static void do_async_reclaim_metadata_space(struct btrfs_space_info *space_info) flush_state = FLUSH_DELAYED_ITEMS_NR; commit_cycles--; } else { - space_info->flush = 0; + space_info->flush = false; } } else { flush_state = FLUSH_DELAYED_ITEMS_NR; @@ -1383,7 +1388,7 @@ static void do_async_reclaim_data_space(struct btrfs_space_info *space_info) spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { - space_info->flush = 0; + space_info->flush = false; spin_unlock(&space_info->lock); return; } @@ -1394,7 +1399,7 @@ static void do_async_reclaim_data_space(struct btrfs_space_info *space_info) flush_space(fs_info, space_info, U64_MAX, ALLOC_CHUNK_FORCE, false); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { - space_info->flush = 0; + space_info->flush = false; spin_unlock(&space_info->lock); return; } @@ -1411,7 +1416,7 @@ static void do_async_reclaim_data_space(struct btrfs_space_info *space_info) data_flush_states[flush_state], false); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { - space_info->flush = 0; + space_info->flush = false; spin_unlock(&space_info->lock); return; } @@ -1428,7 +1433,7 @@ static void do_async_reclaim_data_space(struct btrfs_space_info *space_info) if (maybe_fail_all_tickets(fs_info, space_info)) flush_state = 0; else - space_info->flush = 0; + space_info->flush = false; } else { flush_state = 0; } @@ -1444,7 +1449,7 @@ static void do_async_reclaim_data_space(struct btrfs_space_info *space_info) aborted_fs: maybe_fail_all_tickets(fs_info, space_info); - space_info->flush = 0; + space_info->flush = false; spin_unlock(&space_info->lock); } @@ -1544,7 +1549,7 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, * ticket in front of a smaller ticket that can now be satisfied with * the available space. */ - btrfs_try_granting_tickets(fs_info, space_info); + btrfs_try_granting_tickets(space_info); spin_unlock(&space_info->lock); } @@ -1572,7 +1577,7 @@ static void priority_reclaim_data_space(struct btrfs_fs_info *fs_info, ticket->error = -ENOSPC; remove_ticket(space_info, ticket); - btrfs_try_granting_tickets(fs_info, space_info); + btrfs_try_granting_tickets(space_info); spin_unlock(&space_info->lock); } @@ -1825,7 +1830,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, */ maybe_clamp_preempt(fs_info, space_info); - space_info->flush = 1; + space_info->flush = true; trace_btrfs_trigger_flush(fs_info, space_info->flags, orig_bytes, flush, @@ -2195,5 +2200,5 @@ void btrfs_return_free_space(struct btrfs_space_info *space_info, u64 len) grant: /* Add to any tickets we may have. */ if (len) - btrfs_try_granting_tickets(fs_info, space_info); + btrfs_try_granting_tickets(space_info); } diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index 679f22efb4073f..596a1e923ddfe9 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -142,11 +142,11 @@ struct btrfs_space_info { flushing. The value is >> clamp, so turns out to be a 2^clamp divisor. */ - unsigned int full:1; /* indicates that we cannot allocate any more + bool full; /* indicates that we cannot allocate any more chunks for this space */ - unsigned int chunk_alloc:1; /* set if we are allocating a chunk */ + bool chunk_alloc; /* set if we are allocating a chunk */ - unsigned int flush:1; /* set if we are trying to make space */ + bool flush; /* set if we are trying to make space */ unsigned int force_alloc; /* set if we need to force a chunk alloc for this space */ @@ -283,8 +283,7 @@ int btrfs_reserve_metadata_bytes(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 orig_bytes, enum btrfs_reserve_flush_enum flush); -void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info); +void btrfs_try_granting_tickets(struct btrfs_space_info *space_info); int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, const struct btrfs_space_info *space_info, u64 bytes, enum btrfs_reserve_flush_enum flush); @@ -295,7 +294,7 @@ static inline void btrfs_space_info_free_bytes_may_use( { spin_lock(&space_info->lock); btrfs_space_info_update_bytes_may_use(space_info, -num_bytes); - btrfs_try_granting_tickets(space_info->fs_info, space_info); + btrfs_try_granting_tickets(space_info); spin_unlock(&space_info->lock); } int btrfs_reserve_data_bytes(struct btrfs_space_info *space_info, u64 bytes, diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h index ad0552db7c7dcb..d81a0ade559fd1 100644 --- a/fs/btrfs/subpage.h +++ b/fs/btrfs/subpage.h @@ -7,7 +7,6 @@ #include #include #include "btrfs_inode.h" -#include "fs.h" struct address_space; struct folio; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 430e7419349c9a..c40944ca7b948f 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -736,14 +736,12 @@ bool btrfs_check_options(const struct btrfs_fs_info *info, */ void btrfs_set_free_space_cache_settings(struct btrfs_fs_info *fs_info) { - if (fs_info->sectorsize < PAGE_SIZE) { + if (fs_info->sectorsize < PAGE_SIZE && btrfs_test_opt(fs_info, SPACE_CACHE)) { + btrfs_info(fs_info, + "forcing free space tree for sector size %u with page size %lu", + fs_info->sectorsize, PAGE_SIZE); btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE); - if (!btrfs_test_opt(fs_info, FREE_SPACE_TREE)) { - btrfs_info(fs_info, - "forcing free space tree for sector size %u with page size %lu", - fs_info->sectorsize, PAGE_SIZE); - btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE); - } + btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE); } /* diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 89ae0c7a610aa5..089712b15d603a 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -32,6 +32,8 @@ #include "ioctl.h" #include "relocation.h" #include "scrub.h" +#include "ordered-data.h" +#include "delayed-inode.h" static struct kmem_cache *btrfs_trans_handle_cachep; @@ -518,13 +520,14 @@ static inline int is_transaction_blocked(struct btrfs_transaction *trans) * when this is done, it is safe to start a new transaction, but the current * transaction might not be fully on disk. */ -static void wait_current_trans(struct btrfs_fs_info *fs_info) +static void wait_current_trans(struct btrfs_fs_info *fs_info, unsigned int type) { struct btrfs_transaction *cur_trans; spin_lock(&fs_info->trans_lock); cur_trans = fs_info->running_transaction; - if (cur_trans && is_transaction_blocked(cur_trans)) { + if (cur_trans && is_transaction_blocked(cur_trans) && + (btrfs_blocked_trans_types[cur_trans->state] & type)) { refcount_inc(&cur_trans->use_count); spin_unlock(&fs_info->trans_lock); @@ -699,12 +702,12 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, sb_start_intwrite(fs_info->sb); if (may_wait_transaction(fs_info, type)) - wait_current_trans(fs_info); + wait_current_trans(fs_info, type); do { ret = join_transaction(fs_info, type); if (ret == -EBUSY) { - wait_current_trans(fs_info); + wait_current_trans(fs_info, type); if (unlikely(type == TRANS_ATTACH || type == TRANS_JOIN_NOSTART)) ret = -ENOENT; @@ -723,7 +726,7 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, h->type = type; INIT_LIST_HEAD(&h->new_bgs); - btrfs_init_metadata_block_rsv(fs_info, &h->delayed_rsv, BTRFS_BLOCK_RSV_DELOPS); + btrfs_init_metadata_block_rsv(fs_info, &h->delayed_rsv, BTRFS_BLOCK_RSV_DELREFS); smp_mb(); if (cur_trans->state >= TRANS_STATE_COMMIT_START && @@ -1001,7 +1004,7 @@ int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid) void btrfs_throttle(struct btrfs_fs_info *fs_info) { - wait_current_trans(fs_info); + wait_current_trans(fs_info, TRANS_START); } bool btrfs_should_end_transaction(struct btrfs_trans_handle *trans) @@ -2481,13 +2484,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) list_add_tail(&fs_info->chunk_root->dirty_list, &cur_trans->switch_commits); - if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) { - btrfs_set_root_node(&fs_info->block_group_root->root_item, - fs_info->block_group_root->node); - list_add_tail(&fs_info->block_group_root->dirty_list, - &cur_trans->switch_commits); - } - switch_commit_roots(trans); ASSERT(list_empty(&cur_trans->dirty_bgs)); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 9f7c777af6356c..18ef069197e5ba 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -14,10 +14,6 @@ #include #include "btrfs_inode.h" #include "delayed-ref.h" -#include "extent-io-tree.h" -#include "block-rsv.h" -#include "messages.h" -#include "misc.h" struct dentry; struct inode; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 30f3c3b849c143..6c5db73c3e85f1 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -29,6 +29,7 @@ #include "orphan.h" #include "print-tree.h" #include "tree-checker.h" +#include "delayed-inode.h" #define MAX_CONFLICT_INODES 10 @@ -189,7 +190,7 @@ static void do_abort_log_replay(struct walk_control *wc, const char *function, btrfs_abort_transaction(wc->trans, error); - if (wc->subvol_path->nodes[0]) { + if (wc->subvol_path && wc->subvol_path->nodes[0]) { btrfs_crit(fs_info, "subvolume (root %llu) leaf currently being processed:", btrfs_root_id(wc->root)); @@ -2800,7 +2801,7 @@ static int replay_one_buffer(struct extent_buffer *eb, nritems = btrfs_header_nritems(eb); for (wc->log_slot = 0; wc->log_slot < nritems; wc->log_slot++) { - struct btrfs_inode_item *inode_item; + struct btrfs_inode_item *inode_item = NULL; btrfs_item_key_to_cpu(eb, &wc->log_key, wc->log_slot); @@ -5872,14 +5873,6 @@ static int log_new_dir_dentries(struct btrfs_trans_handle *trans, struct btrfs_inode *curr_inode = start_inode; int ret = 0; - /* - * If we are logging a new name, as part of a link or rename operation, - * don't bother logging new dentries, as we just want to log the names - * of an inode and that any new parents exist. - */ - if (ctx->logging_new_name) - return 0; - path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -6058,6 +6051,33 @@ static int conflicting_inode_is_dir(struct btrfs_root *root, u64 ino, return ret; } +static bool can_log_conflicting_inode(const struct btrfs_trans_handle *trans, + const struct btrfs_inode *inode) +{ + if (!S_ISDIR(inode->vfs_inode.i_mode)) + return true; + + if (inode->last_unlink_trans < trans->transid) + return true; + + /* + * If this is a directory and its unlink_trans is not from a past + * transaction then we must fallback to a transaction commit in order + * to avoid getting a directory with 2 hard links after log replay. + * + * This happens if a directory A is renamed, moved from one parent + * directory to another one, a new file is created in the old parent + * directory with the old name of our directory A, the new file is + * fsynced, then we moved the new file to some other parent directory + * and fsync again the new file. This results in a log tree where we + * logged that directory A existed, with the INODE_REF item for the + * new location but without having logged its old parent inode, so + * that on log replay we add a new link for the new location but the + * old link remains, resulting in a link count of 2. + */ + return false; +} + static int add_conflicting_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, @@ -6161,6 +6181,11 @@ static int add_conflicting_inode(struct btrfs_trans_handle *trans, return 0; } + if (!can_log_conflicting_inode(trans, inode)) { + btrfs_add_delayed_iput(inode); + return BTRFS_LOG_FORCE_COMMIT; + } + btrfs_add_delayed_iput(inode); ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS); @@ -6225,6 +6250,12 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans, break; } + if (!can_log_conflicting_inode(trans, inode)) { + btrfs_add_delayed_iput(inode); + ret = BTRFS_LOG_FORCE_COMMIT; + break; + } + /* * Always log the directory, we cannot make this * conditional on need_log_inode() because the directory @@ -6318,10 +6349,8 @@ static int copy_inode_items_to_log(struct btrfs_trans_handle *trans, * and no keys greater than that, so bail out. */ break; - } else if ((min_key->type == BTRFS_INODE_REF_KEY || - min_key->type == BTRFS_INODE_EXTREF_KEY) && - (inode->generation == trans->transid || - ctx->logging_conflict_inodes)) { + } else if (min_key->type == BTRFS_INODE_REF_KEY || + min_key->type == BTRFS_INODE_EXTREF_KEY) { u64 other_ino = 0; u64 other_parent = 0; diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index dc313e6bb2faa1..4f149d7d4fdee1 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -8,8 +8,7 @@ #include #include -#include "messages.h" -#include "ctree.h" +#include #include "transaction.h" struct inode; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2bec544d8ba300..645bf98a9571b5 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1365,7 +1365,9 @@ struct btrfs_super_block *btrfs_read_disk_super(struct block_device *bdev, (bytenr + BTRFS_SUPER_INFO_SIZE) >> PAGE_SHIFT); } + filemap_invalidate_lock(mapping); page = read_cache_page_gfp(mapping, bytenr >> PAGE_SHIFT, GFP_NOFS); + filemap_invalidate_unlock(mapping); if (IS_ERR(page)) return ERR_CAST(page); @@ -1504,30 +1506,158 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, } /* - * Try to find a chunk that intersects [start, start + len] range and when one - * such is found, record the end of it in *start + * Find the first pending extent intersecting a range. + * + * @device: the device to search + * @start: start of the range to check + * @len: length of the range to check + * @pending_start: output pointer for the start of the found pending extent + * @pending_end: output pointer for the end of the found pending extent (inclusive) + * + * Search for a pending chunk allocation that intersects the half-open range + * [start, start + len). + * + * Return: true if a pending extent was found, false otherwise. + * If the return value is true, store the first pending extent in + * [*pending_start, *pending_end]. Otherwise, the two output variables + * may still be modified, to something outside the range and should not + * be used. */ -static bool contains_pending_extent(struct btrfs_device *device, u64 *start, - u64 len) +static bool first_pending_extent(struct btrfs_device *device, u64 start, u64 len, + u64 *pending_start, u64 *pending_end) { - u64 physical_start, physical_end; - lockdep_assert_held(&device->fs_info->chunk_mutex); - if (btrfs_find_first_extent_bit(&device->alloc_state, *start, - &physical_start, &physical_end, + if (btrfs_find_first_extent_bit(&device->alloc_state, start, + pending_start, pending_end, CHUNK_ALLOCATED, NULL)) { - if (in_range(physical_start, *start, len) || - in_range(*start, physical_start, - physical_end + 1 - physical_start)) { - *start = physical_end + 1; + if (in_range(*pending_start, start, len) || + in_range(start, *pending_start, *pending_end + 1 - *pending_start)) { return true; } } return false; } +/* + * Find the first real hole accounting for pending extents. + * + * @device: the device containing the candidate hole + * @start: input/output pointer for the hole start position + * @len: input/output pointer for the hole length + * @min_hole_size: the size of hole we are looking for + * + * Given a potential hole specified by [*start, *start + *len), check for pending + * chunk allocations within that range. If pending extents are found, the hole is + * adjusted to represent the first true free space that is large enough when + * accounting for pending chunks. + * + * Note that this function must handle various cases involving non consecutive + * pending extents. + * + * Returns: true if a suitable hole was found and false otherwise. + * If the return value is true, then *start and *len are set to represent the hole. + * If the return value is false, then *start is set to the largest hole we + * found and *len is set to its length. + * If there are no holes at all, then *start is set to the end of the range and + * *len is set to 0. + */ +static bool find_hole_in_pending_extents(struct btrfs_device *device, u64 *start, + u64 *len, u64 min_hole_size) +{ + u64 pending_start, pending_end; + u64 end; + u64 max_hole_start = 0; + u64 max_hole_len = 0; + + lockdep_assert_held(&device->fs_info->chunk_mutex); + + if (*len == 0) + return false; + + end = *start + *len - 1; + + /* + * Loop until we either see a large enough hole or check every pending + * extent overlapping the candidate hole. + * At every hole that we observe, record it if it is the new max. + * At the end of the iteration, set the output variables to the max hole. + */ + while (true) { + if (first_pending_extent(device, *start, *len, &pending_start, &pending_end)) { + /* + * Case 1: the pending extent overlaps the start of + * candidate hole. That means the true hole is after the + * pending extent, but we need to find the next pending + * extent to properly size the hole. In the next loop, + * we will reduce to case 2 or 3. + * e.g., + * + * |----pending A----| real hole |----pending B----| + * | candidate hole | + * *start end + */ + if (pending_start <= *start) { + *start = pending_end + 1; + goto next; + } + /* + * Case 2: The pending extent starts after *start (and overlaps + * [*start, end), so the first hole just goes up to the start + * of the pending extent. + * e.g., + * + * | real hole |----pending A----| + * | candidate hole | + * *start end + */ + *len = pending_start - *start; + if (*len > max_hole_len) { + max_hole_start = *start; + max_hole_len = *len; + } + if (*len >= min_hole_size) + break; + /* + * If the hole wasn't big enough, then we advance past + * the pending extent and keep looking. + */ + *start = pending_end + 1; + goto next; + } else { + /* + * Case 3: There is no pending extent overlapping the + * range [*start, *start + *len - 1], so the only remaining + * hole is the remaining range. + * e.g., + * + * | candidate hole | + * | real hole | + * *start end + */ + + if (*len > max_hole_len) { + max_hole_start = *start; + max_hole_len = *len; + } + break; + } +next: + if (*start > end) + break; + *len = end - *start + 1; + } + if (max_hole_len) { + *start = max_hole_start; + *len = max_hole_len; + } else { + *start = end + 1; + *len = 0; + } + return max_hole_len >= min_hole_size; +} + static u64 dev_extent_search_start(struct btrfs_device *device) { switch (device->fs_devices->chunk_alloc_policy) { @@ -1592,59 +1722,57 @@ static bool dev_extent_hole_check_zoned(struct btrfs_device *device, } /* - * Check if specified hole is suitable for allocation. + * Validate and adjust a hole for chunk allocation + * + * @device: the device containing the candidate hole + * @hole_start: input/output pointer for the hole start position + * @hole_size: input/output pointer for the hole size + * @num_bytes: minimum allocation size required * - * @device: the device which we have the hole - * @hole_start: starting position of the hole - * @hole_size: the size of the hole - * @num_bytes: the size of the free space that we need + * Check if the specified hole is suitable for allocation and adjust it if + * necessary. The hole may be modified to skip over pending chunk allocations + * and to satisfy stricter zoned requirements on zoned filesystems. * - * This function may modify @hole_start and @hole_size to reflect the suitable - * position for allocation. Returns 1 if hole position is updated, 0 otherwise. + * For regular (non-zoned) allocation, if the hole after adjustment is smaller + * than @num_bytes, the search continues past additional pending extents until + * either a sufficiently large hole is found or no more pending extents exist. + * + * Return: true if a suitable hole was found and false otherwise. + * If the return value is true, then *hole_start and *hole_size are set to + * represent the hole we found. + * If the return value is false, then *hole_start is set to the largest + * hole we found and *hole_size is set to its length. + * If there are no holes at all, then *hole_start is set to the end of the range + * and *hole_size is set to 0. */ static bool dev_extent_hole_check(struct btrfs_device *device, u64 *hole_start, u64 *hole_size, u64 num_bytes) { - bool changed = false; - u64 hole_end = *hole_start + *hole_size; + bool found = false; + const u64 hole_end = *hole_start + *hole_size - 1; - for (;;) { - /* - * Check before we set max_hole_start, otherwise we could end up - * sending back this offset anyway. - */ - if (contains_pending_extent(device, hole_start, *hole_size)) { - if (hole_end >= *hole_start) - *hole_size = hole_end - *hole_start; - else - *hole_size = 0; - changed = true; - } + ASSERT(*hole_size > 0); - switch (device->fs_devices->chunk_alloc_policy) { - default: - btrfs_warn_unknown_chunk_allocation(device->fs_devices->chunk_alloc_policy); - fallthrough; - case BTRFS_CHUNK_ALLOC_REGULAR: - /* No extra check */ - break; - case BTRFS_CHUNK_ALLOC_ZONED: - if (dev_extent_hole_check_zoned(device, hole_start, - hole_size, num_bytes)) { - changed = true; - /* - * The changed hole can contain pending extent. - * Loop again to check that. - */ - continue; - } - break; - } +again: + *hole_size = hole_end - *hole_start + 1; + found = find_hole_in_pending_extents(device, hole_start, hole_size, num_bytes); + if (!found) + return found; + ASSERT(*hole_size >= num_bytes); + switch (device->fs_devices->chunk_alloc_policy) { + default: + btrfs_warn_unknown_chunk_allocation(device->fs_devices->chunk_alloc_policy); + fallthrough; + case BTRFS_CHUNK_ALLOC_REGULAR: + return found; + case BTRFS_CHUNK_ALLOC_ZONED: + if (dev_extent_hole_check_zoned(device, hole_start, hole_size, num_bytes)) + goto again; break; } - return changed; + return found; } /* @@ -1703,7 +1831,7 @@ static int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, ret = -ENOMEM; goto out; } -again: + if (search_start >= search_end || test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { ret = -ENOSPC; @@ -1790,11 +1918,7 @@ static int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, */ if (search_end > search_start) { hole_size = search_end - search_start; - if (dev_extent_hole_check(device, &search_start, &hole_size, - num_bytes)) { - btrfs_release_path(path); - goto again; - } + dev_extent_hole_check(device, &search_start, &hole_size, num_bytes); if (hole_size > max_hole_size) { max_hole_start = search_start; @@ -4880,6 +5004,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size) u64 diff; u64 start; u64 free_diff = 0; + u64 pending_start, pending_end; new_size = round_down(new_size, fs_info->sectorsize); start = new_size; @@ -4925,7 +5050,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size) * in-memory chunks are synced to disk so that the loop below sees them * and relocates them accordingly. */ - if (contains_pending_extent(device, &start, diff)) { + if (first_pending_extent(device, start, diff, &pending_start, &pending_end)) { mutex_unlock(&fs_info->chunk_mutex); ret = btrfs_commit_transaction(trans); if (ret) @@ -7178,6 +7303,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info, fs_devices->seeding = true; fs_devices->opened = 1; + list_add(&fs_devices->seed_list, &fs_info->fs_devices->seed_list); return fs_devices; } diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 6caba8be7c845c..10ed48d4a84665 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -139,6 +139,7 @@ static int copy_data_into_buffer(struct address_space *mapping, data_in = kmap_local_folio(folio, offset); memcpy(workspace->buf + cur - filepos, data_in, copy_length); kunmap_local(data_in); + folio_put(folio); cur += copy_length; } return 0; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index d1db7fa1fe583a..3afc9c0c222878 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1809,14 +1809,14 @@ bool btrfs_use_zone_append(struct btrfs_bio *bbio) { u64 start = (bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT); struct btrfs_inode *inode = bbio->inode; - struct btrfs_fs_info *fs_info = bbio->fs_info; + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_block_group *cache; bool ret = false; if (!btrfs_is_zoned(fs_info)) return false; - if (!inode || !is_data_inode(inode)) + if (!is_data_inode(inode)) return false; if (btrfs_op(&bbio->bio) != BTRFS_MAP_WRITE) diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index 17c5656580dd97..2b807a02d1a8a8 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -15,7 +15,6 @@ #include "disk-io.h" #include "block-group.h" #include "btrfs_inode.h" -#include "fs.h" struct block_device; struct extent_buffer; diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c index 7026e794813ca1..de823a50af9c5c 100644 --- a/fs/ceph/crypto.c +++ b/fs/ceph/crypto.c @@ -219,12 +219,13 @@ static struct inode *parse_longname(const struct inode *parent, struct ceph_vino vino = { .snap = CEPH_NOSNAP }; char *name_end, *inode_number; int ret = -EIO; - /* NUL-terminate */ - char *str __free(kfree) = kmemdup_nul(name, *name_len, GFP_KERNEL); + /* Snapshot name must start with an underscore */ + if (*name_len <= 0 || name[0] != '_') + return ERR_PTR(-EIO); + /* Skip initial '_' and NUL-terminate */ + char *str __free(kfree) = kmemdup_nul(name + 1, *name_len - 1, GFP_KERNEL); if (!str) return ERR_PTR(-ENOMEM); - /* Skip initial '_' */ - str++; name_end = strrchr(str, '_'); if (!name_end) { doutc(cl, "failed to parse long snapshot name: %s\n", str); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 1740047aef0f9a..f3d146b869436b 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -5655,7 +5655,7 @@ static int ceph_mds_auth_match(struct ceph_mds_client *mdsc, u32 caller_uid = from_kuid(&init_user_ns, cred->fsuid); u32 caller_gid = from_kgid(&init_user_ns, cred->fsgid); struct ceph_client *cl = mdsc->fsc->client; - const char *fs_name = mdsc->fsc->mount_options->mds_namespace; + const char *fs_name = mdsc->mdsmap->m_fs_name; const char *spath = mdsc->fsc->mount_options->server_path; bool gid_matched = false; u32 gid, tlen, len; @@ -5663,7 +5663,8 @@ static int ceph_mds_auth_match(struct ceph_mds_client *mdsc, doutc(cl, "fsname check fs_name=%s match.fs_name=%s\n", fs_name, auth->match.fs_name ? auth->match.fs_name : ""); - if (auth->match.fs_name && strcmp(auth->match.fs_name, fs_name)) { + + if (!ceph_namespace_match(auth->match.fs_name, fs_name)) { /* fsname mismatch, try next one */ return 0; } diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 2c7b151a7c95cc..b228e5ecfb926d 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -353,22 +353,33 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, __decode_and_drop_type(p, end, u8, bad_ext); } if (mdsmap_ev >= 8) { - u32 fsname_len; + size_t fsname_len; + /* enabled */ ceph_decode_8_safe(p, end, m->m_enabled, bad_ext); + /* fs_name */ - ceph_decode_32_safe(p, end, fsname_len, bad_ext); + m->m_fs_name = ceph_extract_encoded_string(p, end, + &fsname_len, + GFP_NOFS); + if (IS_ERR(m->m_fs_name)) { + m->m_fs_name = NULL; + goto nomem; + } /* validate fsname against mds_namespace */ - if (!namespace_equals(mdsc->fsc->mount_options, *p, + if (!namespace_equals(mdsc->fsc->mount_options, m->m_fs_name, fsname_len)) { - pr_warn_client(cl, "fsname %*pE doesn't match mds_namespace %s\n", - (int)fsname_len, (char *)*p, + pr_warn_client(cl, "fsname %s doesn't match mds_namespace %s\n", + m->m_fs_name, mdsc->fsc->mount_options->mds_namespace); goto bad; } - /* skip fsname after validation */ - ceph_decode_skip_n(p, end, fsname_len, bad); + } else { + m->m_enabled = false; + m->m_fs_name = kstrdup(CEPH_OLD_FS_NAME, GFP_NOFS); + if (!m->m_fs_name) + goto nomem; } /* damaged */ if (mdsmap_ev >= 9) { @@ -430,6 +441,7 @@ void ceph_mdsmap_destroy(struct ceph_mdsmap *m) kfree(m->m_info); } kfree(m->m_data_pg_pools); + kfree(m->m_fs_name); kfree(m); } diff --git a/fs/ceph/mdsmap.h b/fs/ceph/mdsmap.h index 1f2171dd01bfa3..d48d07c3516d44 100644 --- a/fs/ceph/mdsmap.h +++ b/fs/ceph/mdsmap.h @@ -45,6 +45,7 @@ struct ceph_mdsmap { bool m_enabled; bool m_damaged; int m_num_laggy; + char *m_fs_name; }; static inline struct ceph_entity_addr * diff --git a/fs/ceph/super.h b/fs/ceph/super.h index a1f781c46b41d3..29a980e22dc26c 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -104,14 +104,26 @@ struct ceph_mount_options { struct fscrypt_dummy_policy dummy_enc_policy; }; +#define CEPH_NAMESPACE_WILDCARD "*" + +static inline bool ceph_namespace_match(const char *pattern, + const char *target) +{ + if (!pattern || !pattern[0] || + !strcmp(pattern, CEPH_NAMESPACE_WILDCARD)) + return true; + + return !strcmp(pattern, target); +} + /* * Check if the mds namespace in ceph_mount_options matches * the passed in namespace string. First time match (when * ->mds_namespace is NULL) is treated specially, since * ->mds_namespace needs to be initialized by the caller. */ -static inline int namespace_equals(struct ceph_mount_options *fsopt, - const char *namespace, size_t len) +static inline bool namespace_equals(struct ceph_mount_options *fsopt, + const char *namespace, size_t len) { return !(fsopt->mds_namespace && (strlen(fsopt->mds_namespace) != len || diff --git a/fs/efivarfs/vars.c b/fs/efivarfs/vars.c index 6edc10958ecf55..70e13db260dba0 100644 --- a/fs/efivarfs/vars.c +++ b/fs/efivarfs/vars.c @@ -552,7 +552,7 @@ int efivar_entry_get(struct efivar_entry *entry, u32 *attributes, err = __efivar_entry_get(entry, attributes, size, data); efivar_unlock(); - return 0; + return err; } /** diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index b7b3432a9882e0..5b77ee8cc99f4d 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -10,6 +10,7 @@ struct erofs_fileio_rq { struct bio bio; struct kiocb iocb; struct super_block *sb; + refcount_t ref; }; struct erofs_fileio { @@ -24,32 +25,29 @@ static void erofs_fileio_ki_complete(struct kiocb *iocb, long ret) container_of(iocb, struct erofs_fileio_rq, iocb); struct folio_iter fi; - if (ret > 0) { - if (ret != rq->bio.bi_iter.bi_size) { - bio_advance(&rq->bio, ret); - zero_fill_bio(&rq->bio); - } - ret = 0; + if (ret >= 0 && ret != rq->bio.bi_iter.bi_size) { + bio_advance(&rq->bio, ret); + zero_fill_bio(&rq->bio); } - if (rq->bio.bi_end_io) { - if (ret < 0 && !rq->bio.bi_status) - rq->bio.bi_status = errno_to_blk_status(ret); - rq->bio.bi_end_io(&rq->bio); - } else { + if (!rq->bio.bi_end_io) { bio_for_each_folio_all(fi, &rq->bio) { DBG_BUGON(folio_test_uptodate(fi.folio)); - erofs_onlinefolio_end(fi.folio, ret, false); + erofs_onlinefolio_end(fi.folio, ret < 0, false); } + } else if (ret < 0 && !rq->bio.bi_status) { + rq->bio.bi_status = errno_to_blk_status(ret); } + bio_endio(&rq->bio); bio_uninit(&rq->bio); - kfree(rq); + if (refcount_dec_and_test(&rq->ref)) + kfree(rq); } static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq) { const struct cred *old_cred; struct iov_iter iter; - int ret; + ssize_t ret; if (!rq) return; @@ -66,6 +64,8 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq) revert_creds(old_cred); if (ret != -EIOCBQUEUED) erofs_fileio_ki_complete(&rq->iocb, ret); + if (refcount_dec_and_test(&rq->ref)) + kfree(rq); } static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev) @@ -76,6 +76,7 @@ static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev) bio_init(&rq->bio, NULL, rq->bvecs, ARRAY_SIZE(rq->bvecs), REQ_OP_READ); rq->iocb.ki_filp = mdev->m_dif->file; rq->sb = mdev->m_sb; + refcount_set(&rq->ref, 2); return rq; } diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 362acf828279fc..7a346e20f7b7aa 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -185,7 +185,7 @@ static void erofs_fscache_bio_endio(void *priv, ssize_t transferred_or_error) if (IS_ERR_VALUE(transferred_or_error)) io->bio.bi_status = errno_to_blk_status(transferred_or_error); - io->bio.bi_end_io(&io->bio); + bio_endio(&io->bio); BUILD_BUG_ON(offsetof(struct erofs_fscache_bio, io) != 0); erofs_fscache_io_put(&io->io); } @@ -216,7 +216,7 @@ void erofs_fscache_submit_bio(struct bio *bio) if (!ret) return; bio->bi_status = errno_to_blk_status(ret); - bio->bi_end_io(bio); + bio_endio(bio); } static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio) diff --git a/fs/erofs/super.c b/fs/erofs/super.c index f3f8d8c066e4e6..5136cda5972a98 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -174,15 +174,15 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, if (!erofs_is_fileio_mode(sbi)) { dif->dax_dev = fs_dax_get_by_bdev(file_bdev(file), &dif->dax_part_off, NULL, NULL); - if (!dif->dax_dev && test_opt(&sbi->opt, DAX_ALWAYS)) { - erofs_info(sb, "DAX unsupported by %s. Turning off DAX.", - dif->path); - clear_opt(&sbi->opt, DAX_ALWAYS); - } } else if (!S_ISREG(file_inode(file)->i_mode)) { fput(file); return -EINVAL; } + if (!dif->dax_dev && test_opt(&sbi->opt, DAX_ALWAYS)) { + erofs_info(sb, "DAX unsupported by %s. Turning off DAX.", + dif->path); + clear_opt(&sbi->opt, DAX_ALWAYS); + } dif->file = file; } @@ -215,13 +215,13 @@ static int erofs_scan_devices(struct super_block *sb, ondisk_extradevs, sbi->devs->extra_devices); return -EINVAL; } - if (!ondisk_extradevs) { - if (test_opt(&sbi->opt, DAX_ALWAYS) && !sbi->dif0.dax_dev) { - erofs_info(sb, "DAX unsupported by block device. Turning off DAX."); - clear_opt(&sbi->opt, DAX_ALWAYS); - } - return 0; + + if (test_opt(&sbi->opt, DAX_ALWAYS) && !sbi->dif0.dax_dev) { + erofs_info(sb, "DAX unsupported by block device. Turning off DAX."); + clear_opt(&sbi->opt, DAX_ALWAYS); } + if (!ondisk_extradevs) + return 0; if (!sbi->devs->extra_devices && !erofs_is_fscache_mode(sb)) sbi->devs->flatdev = true; @@ -639,6 +639,29 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) sbi->blkszbits = PAGE_SHIFT; if (!sb->s_bdev) { + /* + * (File-backed mounts) EROFS claims it's safe to nest other + * fs contexts (including its own) due to self-controlled RO + * accesses/contexts and no side-effect changes that need to + * context save & restore so it can reuse the current thread + * context. + * However, we still need to prevent kernel stack overflow due + * to filesystem nesting: just ensure that s_stack_depth is 0 + * to disallow mounting EROFS on stacked filesystems. + * Note: s_stack_depth is not incremented here for now, since + * EROFS is the only fs supporting file-backed mounts for now. + * It MUST change if another fs plans to support them, which + * may also require adjusting FILESYSTEM_MAX_STACK_DEPTH. + */ + if (erofs_is_fileio_mode(sbi)) { + inode = file_inode(sbi->dif0.file); + if ((inode->i_sb->s_op == &erofs_sops && + !inode->i_sb->s_bdev) || + inode->i_sb->s_stack_depth) { + erofs_err(sb, "file-backed mounts cannot be applied to stacked fses"); + return -ENOTBLK; + } + } sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index bc80cfe482f73b..98e44570841a3d 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -805,14 +805,26 @@ static int z_erofs_pcluster_begin(struct z_erofs_frontend *fe) struct erofs_map_blocks *map = &fe->map; struct super_block *sb = fe->inode->i_sb; struct z_erofs_pcluster *pcl = NULL; - void *ptr; + void *ptr = NULL; int ret; DBG_BUGON(fe->pcl); /* must be Z_EROFS_PCLUSTER_TAIL or pointed to previous pcluster */ DBG_BUGON(!fe->head); - if (!(map->m_flags & EROFS_MAP_META)) { + if (map->m_flags & EROFS_MAP_META) { + ret = erofs_init_metabuf(&map->buf, sb, + erofs_inode_in_metabox(fe->inode)); + if (ret) + return ret; + ptr = erofs_bread(&map->buf, map->m_pa, false); + if (IS_ERR(ptr)) { + erofs_err(sb, "failed to read inline data %pe @ pa %llu of nid %llu", + ptr, map->m_pa, EROFS_I(fe->inode)->nid); + return PTR_ERR(ptr); + } + ptr = map->buf.page; + } else { while (1) { rcu_read_lock(); pcl = xa_load(&EROFS_SB(sb)->managed_pslots, map->m_pa); @@ -852,18 +864,8 @@ static int z_erofs_pcluster_begin(struct z_erofs_frontend *fe) /* bind cache first when cached decompression is preferred */ z_erofs_bind_cache(fe); } else { - ret = erofs_init_metabuf(&map->buf, sb, - erofs_inode_in_metabox(fe->inode)); - if (ret) - return ret; - ptr = erofs_bread(&map->buf, map->m_pa, false); - if (IS_ERR(ptr)) { - ret = PTR_ERR(ptr); - erofs_err(sb, "failed to get inline folio %d", ret); - return ret; - } - folio_get(page_folio(map->buf.page)); - WRITE_ONCE(fe->pcl->compressed_bvecs[0].page, map->buf.page); + folio_get(page_folio((struct page *)ptr)); + WRITE_ONCE(fe->pcl->compressed_bvecs[0].page, ptr); fe->pcl->pageofs_in = map->m_pa & ~PAGE_MASK; fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE; } @@ -1262,17 +1264,17 @@ static int z_erofs_parse_in_bvecs(struct z_erofs_backend *be, bool *overlapped) return err; } -static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err) +static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, bool eio) { struct erofs_sb_info *const sbi = EROFS_SB(be->sb); struct z_erofs_pcluster *pcl = be->pcl; unsigned int pclusterpages = z_erofs_pclusterpages(pcl); const struct z_erofs_decompressor *decomp = z_erofs_decomp[pcl->algorithmformat]; - int i, j, jtop, err2; + bool try_free = true; + int i, j, jtop, err2, err = eio ? -EIO : 0; struct page *page; bool overlapped; - bool try_free = true; mutex_lock(&pcl->lock); be->nr_pages = PAGE_ALIGN(pcl->length + pcl->pageofs_out) >> PAGE_SHIFT; @@ -1400,12 +1402,12 @@ static int z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io, .pcl = io->head, }; struct z_erofs_pcluster *next; - int err = io->eio ? -EIO : 0; + int err = 0; for (; be.pcl != Z_EROFS_PCLUSTER_TAIL; be.pcl = next) { DBG_BUGON(!be.pcl); next = READ_ONCE(be.pcl->next); - err = z_erofs_decompress_pcluster(&be, err) ?: err; + err = z_erofs_decompress_pcluster(&be, io->eio) ?: err; } return err; } diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index 2d2d510f2372cb..0b6466b3490a06 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -106,7 +106,7 @@ static int exfat_allocate_bitmap(struct super_block *sb, (PAGE_SHIFT - sb->s_blocksize_bits); for (i = 0; i < sbi->map_sectors; i++) { /* Trigger the next readahead in advance. */ - if (0 == (i % max_ra_count)) { + if (max_ra_count && 0 == (i % max_ra_count)) { blk_start_plug(&plug); for (j = i; j < min(max_ra_count, sbi->map_sectors - i) + i; j++) sb_breadahead(sb, sector + j); diff --git a/fs/exfat/file.c b/fs/exfat/file.c index adc37b4d7fc2d0..536c8078f0c192 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -25,6 +25,8 @@ static int exfat_cont_expand(struct inode *inode, loff_t size) struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_chain clu; + truncate_pagecache(inode, i_size_read(inode)); + ret = inode_newsize_ok(inode, size); if (ret) return ret; @@ -639,6 +641,9 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter) inode_lock(inode); + if (pos > i_size_read(inode)) + truncate_pagecache(inode, i_size_read(inode)); + valid_size = ei->valid_size; ret = generic_write_checks(iocb, iter); diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 745dce29ddb532..dfe957493d49ee 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -645,16 +645,6 @@ static int exfat_find(struct inode *dir, const struct qstr *qname, info->valid_size = le64_to_cpu(ep2->dentry.stream.valid_size); info->size = le64_to_cpu(ep2->dentry.stream.size); - if (info->valid_size < 0) { - exfat_fs_error(sb, "data valid size is invalid(%lld)", info->valid_size); - return -EIO; - } - - if (unlikely(EXFAT_B_TO_CLU_ROUND_UP(info->size, sbi) > sbi->used_clusters)) { - exfat_fs_error(sb, "data size is invalid(%lld)", info->size); - return -EIO; - } - info->start_clu = le32_to_cpu(ep2->dentry.stream.start_clu); if (!is_valid_cluster(sbi, info->start_clu) && info->size) { exfat_warn(sb, "start_clu is invalid cluster(0x%x)", @@ -692,6 +682,16 @@ static int exfat_find(struct inode *dir, const struct qstr *qname, 0); exfat_put_dentry_set(&es, false); + if (info->valid_size < 0) { + exfat_fs_error(sb, "data valid size is invalid(%lld)", info->valid_size); + return -EIO; + } + + if (unlikely(EXFAT_B_TO_CLU_ROUND_UP(info->size, sbi) > sbi->used_clusters)) { + exfat_fs_error(sb, "data size is invalid(%lld)", info->size); + return -EIO; + } + if (ei->start_clu == EXFAT_FREE_CLUSTER) { exfat_fs_error(sb, "non-zero size file starts with zero cluster (size : %llu, p_dir : %u, entry : 0x%08x)", diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 74d451f732c732..581754001128b7 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -813,10 +813,21 @@ static int exfat_init_fs_context(struct fs_context *fc) ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); - sbi->options.fs_uid = current_uid(); - sbi->options.fs_gid = current_gid(); - sbi->options.fs_fmask = current->fs->umask; - sbi->options.fs_dmask = current->fs->umask; + if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE && fc->root) { + struct super_block *sb = fc->root->d_sb; + struct exfat_mount_options *cur_opts = &EXFAT_SB(sb)->options; + + sbi->options.fs_uid = cur_opts->fs_uid; + sbi->options.fs_gid = cur_opts->fs_gid; + sbi->options.fs_fmask = cur_opts->fs_fmask; + sbi->options.fs_dmask = cur_opts->fs_dmask; + } else { + sbi->options.fs_uid = current_uid(); + sbi->options.fs_gid = current_gid(); + sbi->options.fs_fmask = current->fs->umask; + sbi->options.fs_dmask = current->fs->umask; + } + sbi->options.allow_utime = -1; sbi->options.errors = EXFAT_ERRORS_RO; exfat_set_iocharset(&sbi->options, exfat_default_iocharset); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 57087da6c7bee8..933297251f66a4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1771,6 +1771,10 @@ struct ext4_sb_info { * Main fast commit lock. This lock protects accesses to the * following fields: * ei->i_fc_list, s_fc_dentry_q, s_fc_q, s_fc_bytes, s_fc_bh. + * + * s_fc_lock can be taken from reclaim context (inode eviction) and is + * thus reclaim unsafe. Use ext4_fc_lock()/ext4_fc_unlock() helpers + * when acquiring / releasing the lock. */ struct mutex s_fc_lock; struct buffer_head *s_fc_bh; @@ -1815,6 +1819,18 @@ static inline void ext4_writepages_up_write(struct super_block *sb, int ctx) percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem); } +static inline int ext4_fc_lock(struct super_block *sb) +{ + mutex_lock(&EXT4_SB(sb)->s_fc_lock); + return memalloc_nofs_save(); +} + +static inline void ext4_fc_unlock(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + mutex_unlock(&EXT4_SB(sb)->s_fc_lock); +} + static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index ca5499e9412b07..ae7f2d6b32e32e 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -43,8 +43,13 @@ #define EXT4_EXT_MARK_UNWRIT1 0x2 /* mark first half unwritten */ #define EXT4_EXT_MARK_UNWRIT2 0x4 /* mark second half unwritten */ -#define EXT4_EXT_DATA_VALID1 0x8 /* first half contains valid data */ -#define EXT4_EXT_DATA_VALID2 0x10 /* second half contains valid data */ +/* first half contains valid data */ +#define EXT4_EXT_DATA_ENTIRE_VALID1 0x8 /* has entirely valid data */ +#define EXT4_EXT_DATA_PARTIAL_VALID1 0x10 /* has partially valid data */ +#define EXT4_EXT_DATA_VALID1 (EXT4_EXT_DATA_ENTIRE_VALID1 | \ + EXT4_EXT_DATA_PARTIAL_VALID1) + +#define EXT4_EXT_DATA_VALID2 0x20 /* second half contains valid data */ static __le32 ext4_extent_block_csum(struct inode *inode, struct ext4_extent_header *eh) @@ -3190,8 +3195,12 @@ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, unsigned int ee_len, depth; int err = 0; - BUG_ON((split_flag & (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)) == - (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)); + BUG_ON((split_flag & EXT4_EXT_DATA_VALID1) == EXT4_EXT_DATA_VALID1); + BUG_ON((split_flag & EXT4_EXT_DATA_VALID1) && + (split_flag & EXT4_EXT_DATA_VALID2)); + + /* Do not cache extents that are in the process of being modified. */ + flags |= EXT4_EX_NOCACHE; ext_debug(inode, "logical block %llu\n", (unsigned long long)split); @@ -3258,7 +3267,7 @@ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, err = PTR_ERR(path); if (err != -ENOSPC && err != -EDQUOT && err != -ENOMEM) - return path; + goto out_path; /* * Get a new path to try to zeroout or fix the extent length. @@ -3272,7 +3281,7 @@ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, if (IS_ERR(path)) { EXT4_ERROR_INODE(inode, "Failed split extent on %u, err %ld", split, PTR_ERR(path)); - return path; + goto out_path; } depth = ext_depth(inode); ex = path[depth].p_ext; @@ -3304,6 +3313,23 @@ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, } if (!err) { + /* + * The first half contains partially valid data, the + * splitting of this extent has not been completed, fix + * extent length and ext4_split_extent() split will the + * first half again. + */ + if (split_flag & EXT4_EXT_DATA_PARTIAL_VALID1) { + /* + * Drop extent cache to prevent stale unwritten + * extents remaining after zeroing out. + */ + ext4_es_remove_extent(inode, + le32_to_cpu(zero_ex.ee_block), + ext4_ext_get_actual_len(&zero_ex)); + goto fix_extent_len; + } + /* update the extent length and mark as initialized */ ex->ee_len = cpu_to_le16(ee_len); ext4_ext_try_to_merge(handle, inode, path, ex); @@ -3332,6 +3358,10 @@ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, ext4_free_ext_path(path); path = ERR_PTR(err); } +out_path: + if (IS_ERR(path)) + /* Remove all remaining potentially stale extents. */ + ext4_es_remove_extent(inode, ee_block, ee_len); ext4_ext_show_leaf(inode, path); return path; } @@ -3366,6 +3396,9 @@ static struct ext4_ext_path *ext4_split_extent(handle_t *handle, ee_len = ext4_ext_get_actual_len(ex); unwritten = ext4_ext_is_unwritten(ex); + /* Do not cache extents that are in the process of being modified. */ + flags |= EXT4_EX_NOCACHE; + if (map->m_lblk + map->m_len < ee_block + ee_len) { split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT; flags1 = flags | EXT4_GET_BLOCKS_PRE_IO; @@ -3373,7 +3406,9 @@ static struct ext4_ext_path *ext4_split_extent(handle_t *handle, split_flag1 |= EXT4_EXT_MARK_UNWRIT1 | EXT4_EXT_MARK_UNWRIT2; if (split_flag & EXT4_EXT_DATA_VALID2) - split_flag1 |= EXT4_EXT_DATA_VALID1; + split_flag1 |= map->m_lblk > ee_block ? + EXT4_EXT_DATA_PARTIAL_VALID1 : + EXT4_EXT_DATA_ENTIRE_VALID1; path = ext4_split_extent_at(handle, inode, path, map->m_lblk + map->m_len, split_flag1, flags1); if (IS_ERR(path)) @@ -3732,7 +3767,7 @@ static struct ext4_ext_path *ext4_split_convert_extents(handle_t *handle, /* Convert to unwritten */ if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) { - split_flag |= EXT4_EXT_DATA_VALID1; + split_flag |= EXT4_EXT_DATA_ENTIRE_VALID1; /* Convert to initialized */ } else if (flags & EXT4_GET_BLOCKS_CONVERT) { split_flag |= ee_block + ee_len <= eof_block ? @@ -5375,7 +5410,8 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, if (!extent) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) *iterator); - return -EFSCORRUPTED; + ret = -EFSCORRUPTED; + goto out; } if (SHIFT == SHIFT_LEFT && *iterator > le32_to_cpu(extent->ee_block)) { diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index fa66b08de9994e..5bd57d7f921b9a 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -231,16 +231,16 @@ static bool ext4_fc_disabled(struct super_block *sb) void ext4_fc_del(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_fc_dentry_update *fc_dentry; wait_queue_head_t *wq; + int alloc_ctx; if (ext4_fc_disabled(inode->i_sb)) return; - mutex_lock(&sbi->s_fc_lock); + alloc_ctx = ext4_fc_lock(inode->i_sb); if (list_empty(&ei->i_fc_list) && list_empty(&ei->i_fc_dilist)) { - mutex_unlock(&sbi->s_fc_lock); + ext4_fc_unlock(inode->i_sb, alloc_ctx); return; } @@ -275,9 +275,9 @@ void ext4_fc_del(struct inode *inode) #endif prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); if (ext4_test_inode_state(inode, EXT4_STATE_FC_FLUSHING_DATA)) { - mutex_unlock(&sbi->s_fc_lock); + ext4_fc_unlock(inode->i_sb, alloc_ctx); schedule(); - mutex_lock(&sbi->s_fc_lock); + alloc_ctx = ext4_fc_lock(inode->i_sb); } finish_wait(wq, &wait.wq_entry); } @@ -288,7 +288,7 @@ void ext4_fc_del(struct inode *inode) * dentry create references, since it is not needed to log it anyways. */ if (list_empty(&ei->i_fc_dilist)) { - mutex_unlock(&sbi->s_fc_lock); + ext4_fc_unlock(inode->i_sb, alloc_ctx); return; } @@ -298,7 +298,7 @@ void ext4_fc_del(struct inode *inode) list_del_init(&fc_dentry->fcd_dilist); WARN_ON(!list_empty(&ei->i_fc_dilist)); - mutex_unlock(&sbi->s_fc_lock); + ext4_fc_unlock(inode->i_sb, alloc_ctx); release_dentry_name_snapshot(&fc_dentry->fcd_name); kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry); @@ -315,6 +315,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handl tid_t tid; bool has_transaction = true; bool is_ineligible; + int alloc_ctx; if (ext4_fc_disabled(sb)) return; @@ -329,12 +330,12 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handl has_transaction = false; read_unlock(&sbi->s_journal->j_state_lock); } - mutex_lock(&sbi->s_fc_lock); + alloc_ctx = ext4_fc_lock(sb); is_ineligible = ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); if (has_transaction && (!is_ineligible || tid_gt(tid, sbi->s_fc_ineligible_tid))) sbi->s_fc_ineligible_tid = tid; ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); - mutex_unlock(&sbi->s_fc_lock); + ext4_fc_unlock(sb, alloc_ctx); WARN_ON(reason >= EXT4_FC_REASON_MAX); sbi->s_fc_stats.fc_ineligible_reason_count[reason]++; } @@ -358,6 +359,7 @@ static int ext4_fc_track_template( struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); tid_t tid = 0; + int alloc_ctx; int ret; tid = handle->h_transaction->t_tid; @@ -373,14 +375,14 @@ static int ext4_fc_track_template( if (!enqueue) return ret; - mutex_lock(&sbi->s_fc_lock); + alloc_ctx = ext4_fc_lock(inode->i_sb); if (list_empty(&EXT4_I(inode)->i_fc_list)) list_add_tail(&EXT4_I(inode)->i_fc_list, (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING || sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING) ? &sbi->s_fc_q[FC_Q_STAGING] : &sbi->s_fc_q[FC_Q_MAIN]); - mutex_unlock(&sbi->s_fc_lock); + ext4_fc_unlock(inode->i_sb, alloc_ctx); return ret; } @@ -402,6 +404,7 @@ static int __track_dentry_update(handle_t *handle, struct inode *inode, struct inode *dir = dentry->d_parent->d_inode; struct super_block *sb = inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); + int alloc_ctx; spin_unlock(&ei->i_fc_lock); @@ -425,7 +428,7 @@ static int __track_dentry_update(handle_t *handle, struct inode *inode, take_dentry_name_snapshot(&node->fcd_name, dentry); INIT_LIST_HEAD(&node->fcd_dilist); INIT_LIST_HEAD(&node->fcd_list); - mutex_lock(&sbi->s_fc_lock); + alloc_ctx = ext4_fc_lock(sb); if (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING || sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING) list_add_tail(&node->fcd_list, @@ -446,7 +449,7 @@ static int __track_dentry_update(handle_t *handle, struct inode *inode, WARN_ON(!list_empty(&ei->i_fc_dilist)); list_add_tail(&node->fcd_dilist, &ei->i_fc_dilist); } - mutex_unlock(&sbi->s_fc_lock); + ext4_fc_unlock(sb, alloc_ctx); spin_lock(&ei->i_fc_lock); return 0; @@ -1046,18 +1049,19 @@ static int ext4_fc_perform_commit(journal_t *journal) struct blk_plug plug; int ret = 0; u32 crc = 0; + int alloc_ctx; /* * Step 1: Mark all inodes on s_fc_q[MAIN] with * EXT4_STATE_FC_FLUSHING_DATA. This prevents these inodes from being * freed until the data flush is over. */ - mutex_lock(&sbi->s_fc_lock); + alloc_ctx = ext4_fc_lock(sb); list_for_each_entry(iter, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { ext4_set_inode_state(&iter->vfs_inode, EXT4_STATE_FC_FLUSHING_DATA); } - mutex_unlock(&sbi->s_fc_lock); + ext4_fc_unlock(sb, alloc_ctx); /* Step 2: Flush data for all the eligible inodes. */ ret = ext4_fc_flush_data(journal); @@ -1067,7 +1071,7 @@ static int ext4_fc_perform_commit(journal_t *journal) * any error from step 2. This ensures that waiters waiting on * EXT4_STATE_FC_FLUSHING_DATA can resume. */ - mutex_lock(&sbi->s_fc_lock); + alloc_ctx = ext4_fc_lock(sb); list_for_each_entry(iter, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { ext4_clear_inode_state(&iter->vfs_inode, EXT4_STATE_FC_FLUSHING_DATA); @@ -1084,7 +1088,7 @@ static int ext4_fc_perform_commit(journal_t *journal) * prepare_to_wait() in ext4_fc_del(). */ smp_mb(); - mutex_unlock(&sbi->s_fc_lock); + ext4_fc_unlock(sb, alloc_ctx); /* * If we encountered error in Step 2, return it now after clearing @@ -1101,12 +1105,12 @@ static int ext4_fc_perform_commit(journal_t *journal) * previous handles are now drained. We now mark the inodes on the * commit queue as being committed. */ - mutex_lock(&sbi->s_fc_lock); + alloc_ctx = ext4_fc_lock(sb); list_for_each_entry(iter, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { ext4_set_inode_state(&iter->vfs_inode, EXT4_STATE_FC_COMMITTING); } - mutex_unlock(&sbi->s_fc_lock); + ext4_fc_unlock(sb, alloc_ctx); jbd2_journal_unlock_updates(journal); /* @@ -1117,6 +1121,7 @@ static int ext4_fc_perform_commit(journal_t *journal) blkdev_issue_flush(journal->j_fs_dev); blk_start_plug(&plug); + alloc_ctx = ext4_fc_lock(sb); /* Step 6: Write fast commit blocks to disk. */ if (sbi->s_fc_bytes == 0) { /* @@ -1134,7 +1139,6 @@ static int ext4_fc_perform_commit(journal_t *journal) } /* Step 6.2: Now write all the dentry updates. */ - mutex_lock(&sbi->s_fc_lock); ret = ext4_fc_commit_dentry_updates(journal, &crc); if (ret) goto out; @@ -1156,7 +1160,7 @@ static int ext4_fc_perform_commit(journal_t *journal) ret = ext4_fc_write_tail(sb, crc); out: - mutex_unlock(&sbi->s_fc_lock); + ext4_fc_unlock(sb, alloc_ctx); blk_finish_plug(&plug); return ret; } @@ -1290,6 +1294,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid) struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *ei; struct ext4_fc_dentry_update *fc_dentry; + int alloc_ctx; if (full && sbi->s_fc_bh) sbi->s_fc_bh = NULL; @@ -1297,7 +1302,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid) trace_ext4_fc_cleanup(journal, full, tid); jbd2_fc_release_bufs(journal); - mutex_lock(&sbi->s_fc_lock); + alloc_ctx = ext4_fc_lock(sb); while (!list_empty(&sbi->s_fc_q[FC_Q_MAIN])) { ei = list_first_entry(&sbi->s_fc_q[FC_Q_MAIN], struct ext4_inode_info, @@ -1356,7 +1361,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid) if (full) sbi->s_fc_bytes = 0; - mutex_unlock(&sbi->s_fc_lock); + ext4_fc_unlock(sb, alloc_ctx); trace_ext4_fc_stats(sb); } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index ba4fd9aba1c14d..b20a1bf866abed 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1293,7 +1293,6 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap, ei->i_csum_seed = ext4_chksum(csum, (__u8 *)&gen, sizeof(gen)); } - ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ ext4_set_inode_state(inode, EXT4_STATE_NEW); ei->i_extra_isize = sbi->s_want_extra_isize; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 1b094a4f386632..1f6bc05593df16 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -418,7 +418,12 @@ static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode, return -ENOSPC; ext4_write_lock_xattr(inode, &no_expand); - + /* + * ei->i_inline_size may have changed since the initial check + * if other xattrs were added. Recalculate to ensure + * ext4_update_inline_data() validates against current capacity. + */ + (void) ext4_find_inline_data_nolock(inode); if (ei->i_inline_off) ret = ext4_update_inline_data(handle, inode, len); else @@ -446,9 +451,13 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle, if (!ei->i_inline_off) return 0; + down_write(&ei->i_data_sem); + error = ext4_get_inode_loc(inode, &is.iloc); - if (error) + if (error) { + up_write(&ei->i_data_sem); return error; + } error = ext4_xattr_ibody_find(inode, &i, &is); if (error) @@ -487,6 +496,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle, brelse(is.iloc.bh); if (error == -ENODATA) error = 0; + up_write(&ei->i_data_sem); return error; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e99306a8f47ce7..5fbe1a2ab81c39 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5288,7 +5288,6 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ei->i_projid = make_kprojid(&init_user_ns, i_projid); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); - ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ ei->i_inline_off = 0; ei->i_dir_start_lookup = 0; ei->i_dtime = le32_to_cpu(raw_inode->i_dtime); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index a93a7baae990cc..3dec26c939fde7 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -1394,6 +1394,10 @@ static int ext4_ioctl_set_tune_sb(struct file *filp, if (copy_from_user(¶ms, in, sizeof(params))) return -EFAULT; + if (strnlen(params.mount_opts, sizeof(params.mount_opts)) == + sizeof(params.mount_opts)) + return -E2BIG; + if ((params.set_flags & ~TUNE_OPS_SUPPORTED) != 0) return -EOPNOTSUPP; diff --git a/fs/ext4/mballoc-test.c b/fs/ext4/mballoc-test.c index a9416b20ff64c9..4abb40d4561ce3 100644 --- a/fs/ext4/mballoc-test.c +++ b/fs/ext4/mballoc-test.c @@ -567,7 +567,7 @@ test_mark_diskspace_used_range(struct kunit *test, bitmap = mbt_ctx_bitmap(sb, TEST_GOAL_GROUP); memset(bitmap, 0, sb->s_blocksize); - ret = ext4_mb_mark_diskspace_used(ac, NULL, 0); + ret = ext4_mb_mark_diskspace_used(ac, NULL); KUNIT_ASSERT_EQ(test, ret, 0); max = EXT4_CLUSTERS_PER_GROUP(sb); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 9087183602e44e..412289e5c0afee 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -682,6 +682,24 @@ do { \ } \ } while (0) +/* + * Perform buddy integrity check with the following steps: + * + * 1. Top-down validation (from highest order down to order 1, excluding order-0 bitmap): + * For each pair of adjacent orders, if a higher-order bit is set (indicating a free block), + * at most one of the two corresponding lower-order bits may be clear (free). + * + * 2. Order-0 (bitmap) validation, performed on bit pairs: + * - If either bit in a pair is set (1, allocated), then all corresponding higher-order bits + * must not be free (0). + * - If both bits in a pair are clear (0, free), then exactly one of the corresponding + * higher-order bits must be free (0). + * + * 3. Preallocation (pa) list validation: + * For each preallocated block (pa) in the group: + * - Verify that pa_pstart falls within the bounds of this block group. + * - Ensure the corresponding bit(s) in the order-0 bitmap are marked as allocated (1). + */ static void __mb_check_buddy(struct ext4_buddy *e4b, char *file, const char *function, int line) { @@ -723,15 +741,6 @@ static void __mb_check_buddy(struct ext4_buddy *e4b, char *file, continue; } - /* both bits in buddy2 must be 1 */ - MB_CHECK_ASSERT(mb_test_bit(i << 1, buddy2)); - MB_CHECK_ASSERT(mb_test_bit((i << 1) + 1, buddy2)); - - for (j = 0; j < (1 << order); j++) { - k = (i * (1 << order)) + j; - MB_CHECK_ASSERT( - !mb_test_bit(k, e4b->bd_bitmap)); - } count++; } MB_CHECK_ASSERT(e4b->bd_info->bb_counters[order] == count); @@ -747,15 +756,21 @@ static void __mb_check_buddy(struct ext4_buddy *e4b, char *file, fragments++; fstart = i; } - continue; + } else { + fstart = -1; } - fstart = -1; - /* check used bits only */ - for (j = 0; j < e4b->bd_blkbits + 1; j++) { - buddy2 = mb_find_buddy(e4b, j, &max2); - k = i >> j; - MB_CHECK_ASSERT(k < max2); - MB_CHECK_ASSERT(mb_test_bit(k, buddy2)); + if (!(i & 1)) { + int in_use, zero_bit_count = 0; + + in_use = mb_test_bit(i, buddy) || mb_test_bit(i + 1, buddy); + for (j = 1; j < e4b->bd_blkbits + 2; j++) { + buddy2 = mb_find_buddy(e4b, j, &max2); + k = i >> j; + MB_CHECK_ASSERT(k < max2); + if (!mb_test_bit(k, buddy2)) + zero_bit_count++; + } + MB_CHECK_ASSERT(zero_bit_count == !in_use); } } MB_CHECK_ASSERT(!EXT4_MB_GRP_NEED_INIT(e4b->bd_info)); @@ -768,6 +783,8 @@ static void __mb_check_buddy(struct ext4_buddy *e4b, char *file, ext4_group_t groupnr; struct ext4_prealloc_space *pa; pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); + if (!pa->pa_len) + continue; ext4_get_group_no_and_offset(sb, pa->pa_pstart, &groupnr, &k); MB_CHECK_ASSERT(groupnr == e4b->bd_group); for (i = 0; i < pa->pa_len; i++) @@ -875,6 +892,21 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) } } +static ext4_group_t ext4_get_allocation_groups_count( + struct ext4_allocation_context *ac) +{ + ext4_group_t ngroups = ext4_get_groups_count(ac->ac_sb); + + /* non-extent files are limited to low blocks/groups */ + if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS))) + ngroups = EXT4_SB(ac->ac_sb)->s_blockfile_groups; + + /* Pairs with smp_wmb() in ext4_update_super() */ + smp_rmb(); + + return ngroups; +} + static int ext4_mb_scan_groups_xa_range(struct ext4_allocation_context *ac, struct xarray *xa, ext4_group_t start, ext4_group_t end) @@ -882,7 +914,7 @@ static int ext4_mb_scan_groups_xa_range(struct ext4_allocation_context *ac, struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); enum criteria cr = ac->ac_criteria; - ext4_group_t ngroups = ext4_get_groups_count(sb); + ext4_group_t ngroups = ext4_get_allocation_groups_count(ac); unsigned long group = start; struct ext4_group_info *grp; @@ -934,7 +966,7 @@ static int ext4_mb_scan_groups_p2_aligned(struct ext4_allocation_context *ac, ext4_group_t start, end; start = group; - end = ext4_get_groups_count(ac->ac_sb); + end = ext4_get_allocation_groups_count(ac); wrap_around: for (i = ac->ac_2order; i < MB_NUM_ORDERS(ac->ac_sb); i++) { ret = ext4_mb_scan_groups_largest_free_order_range(ac, i, @@ -984,7 +1016,7 @@ static int ext4_mb_scan_groups_goal_fast(struct ext4_allocation_context *ac, ext4_group_t start, end; start = group; - end = ext4_get_groups_count(ac->ac_sb); + end = ext4_get_allocation_groups_count(ac); wrap_around: i = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); for (; i < MB_NUM_ORDERS(ac->ac_sb); i++) { @@ -1066,7 +1098,7 @@ static int ext4_mb_scan_groups_best_avail(struct ext4_allocation_context *ac, min_order = fls(ac->ac_o_ex.fe_len); start = group; - end = ext4_get_groups_count(ac->ac_sb); + end = ext4_get_allocation_groups_count(ac); wrap_around: for (i = order; i >= min_order; i--) { int frag_order; @@ -1116,8 +1148,6 @@ static inline int should_optimize_scan(struct ext4_allocation_context *ac) return 0; if (ac->ac_criteria >= CR_GOAL_LEN_SLOW) return 0; - if (!ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) - return 0; return 1; } @@ -1165,11 +1195,7 @@ static int ext4_mb_scan_groups(struct ext4_allocation_context *ac) int ret = 0; ext4_group_t start; struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); - ext4_group_t ngroups = ext4_get_groups_count(ac->ac_sb); - - /* non-extent files are limited to low blocks/groups */ - if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS))) - ngroups = sbi->s_blockfile_groups; + ext4_group_t ngroups = ext4_get_allocation_groups_count(ac); /* searching for the right group start from the goal value specified */ start = ac->ac_g_ex.fe_group; @@ -1695,16 +1721,17 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, /* Avoid locking the folio in the fast path ... */ folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_ACCESSED, 0); - if (IS_ERR(folio) || !folio_test_uptodate(folio)) { + if (IS_ERR(folio) || !folio_test_uptodate(folio) || folio_test_locked(folio)) { + /* + * folio_test_locked is employed to detect ongoing folio + * migrations, since concurrent migrations can lead to + * bitmap inconsistency. And if we are not uptodate that + * implies somebody just created the folio but is yet to + * initialize it. We can drop the folio reference and + * try to get the folio with lock in both cases to avoid + * concurrency. + */ if (!IS_ERR(folio)) - /* - * drop the folio reference and try - * to get the folio with lock. If we - * are not uptodate that implies - * somebody just created the folio but - * is yet to initialize it. So - * wait for it to initialize. - */ folio_put(folio); folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); @@ -1746,7 +1773,7 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, poff = block % blocks_per_page; folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_ACCESSED, 0); - if (IS_ERR(folio) || !folio_test_uptodate(folio)) { + if (IS_ERR(folio) || !folio_test_uptodate(folio) || folio_test_locked(folio)) { if (!IS_ERR(folio)) folio_put(folio); folio = __filemap_get_folio(inode->i_mapping, pnum, @@ -4163,8 +4190,7 @@ ext4_mb_mark_context(handle_t *handle, struct super_block *sb, bool state, * Returns 0 if success or error code */ static noinline_for_stack int -ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, - handle_t *handle, unsigned int reserv_clstrs) +ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, handle_t *handle) { struct ext4_group_desc *gdp; struct ext4_sb_info *sbi; @@ -4219,13 +4245,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, BUG_ON(changed != ac->ac_b_ex.fe_len); #endif percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len); - /* - * Now reduce the dirty block count also. Should not go negative - */ - if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED)) - /* release all the reserved blocks if non delalloc */ - percpu_counter_sub(&sbi->s_dirtyclusters_counter, - reserv_clstrs); return err; } @@ -6310,7 +6329,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, ext4_mb_pa_put_free(ac); } if (likely(ac->ac_status == AC_STATUS_FOUND)) { - *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs); + *errp = ext4_mb_mark_diskspace_used(ac, handle); if (*errp) { ext4_discard_allocated_blocks(ac); goto errout; @@ -6341,12 +6360,9 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, out: if (inquota && ar->len < inquota) dquot_free_block(ar->inode, EXT4_C2B(sbi, inquota - ar->len)); - if (!ar->len) { - if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) - /* release all the reserved blocks if non delalloc */ - percpu_counter_sub(&sbi->s_dirtyclusters_counter, - reserv_clstrs); - } + /* release any reserved blocks */ + if (reserv_clstrs) + percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); trace_ext4_allocate_blocks(ar, (unsigned long long)block); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 4b091c21908fda..0f4b7c89edd398 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -485,7 +485,7 @@ mext_check_arguments(struct inode *orig_inode, return -ETXTBSY; } - if (ext4_is_quota_file(orig_inode) && ext4_is_quota_file(donor_inode)) { + if (ext4_is_quota_file(orig_inode) || ext4_is_quota_file(donor_inode)) { ext4_debug("ext4 move extent: The argument files should not be quota files [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EOPNOTSUPP; diff --git a/fs/ext4/orphan.c b/fs/ext4/orphan.c index 82d5e750145559..fb57bba0d19d1e 100644 --- a/fs/ext4/orphan.c +++ b/fs/ext4/orphan.c @@ -8,6 +8,8 @@ #include "ext4.h" #include "ext4_jbd2.h" +#define EXT4_MAX_ORPHAN_FILE_BLOCKS 512 + static int ext4_orphan_file_add(handle_t *handle, struct inode *inode) { int i, j, start; @@ -588,7 +590,7 @@ int ext4_init_orphan_info(struct super_block *sb) * consuming absurd amounts of memory when pinning blocks of orphan * file in memory. */ - if (inode->i_size > 8 << 20) { + if (inode->i_size > (EXT4_MAX_ORPHAN_FILE_BLOCKS << inode->i_blkbits)) { ext4_msg(sb, KERN_ERR, "orphan file too big: %llu", (unsigned long long)inode->i_size); ret = -EFSCORRUPTED; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 33e7c08c9529c3..4ef5590c73fdad 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1396,6 +1396,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) inode_set_iversion(&ei->vfs_inode, 1); ei->i_flags = 0; + ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ spin_lock_init(&ei->i_raw_lock); ei->i_prealloc_node = RB_ROOT; atomic_set(&ei->i_prealloc_active, 0); @@ -2475,7 +2476,7 @@ static int parse_apply_sb_mount_options(struct super_block *sb, struct ext4_fs_context *m_ctx) { struct ext4_sb_info *sbi = EXT4_SB(sb); - char s_mount_opts[65]; + char s_mount_opts[64]; struct ext4_fs_context *s_ctx = NULL; struct fs_context *fc = NULL; int ret = -ENOMEM; @@ -2483,7 +2484,8 @@ static int parse_apply_sb_mount_options(struct super_block *sb, if (!sbi->s_es->s_mount_opts[0]) return 0; - strscpy_pad(s_mount_opts, sbi->s_es->s_mount_opts); + if (strscpy_pad(s_mount_opts, sbi->s_es->s_mount_opts) < 0) + return -E2BIG; fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL); if (!fc) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index ce7253b3f54996..4ed8ddf2a60b31 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1037,6 +1037,7 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, ext4_error_inode(ea_inode, __func__, __LINE__, 0, "EA inode %lu ref wraparound: ref_count=%lld ref_change=%d", ea_inode->i_ino, ref_count, ref_change); + brelse(iloc.bh); ret = -EFSCORRUPTED; goto out; } @@ -1174,7 +1175,11 @@ ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent, if (block_csum) end = (void *)bh->b_data + bh->b_size; else { - ext4_get_inode_loc(parent, &iloc); + err = ext4_get_inode_loc(parent, &iloc); + if (err) { + EXT4_ERROR_INODE(parent, "parent inode loc (error %d)", err); + return; + } end = (void *)ext4_raw_inode(&iloc) + EXT4_SB(parent->i_sb)->s_inode_size; } diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 6ad8d3bc6df7a8..811bfe38e5c09a 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -759,10 +759,7 @@ void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task) ret = -EFSCORRUPTED; /* Avoid f2fs_commit_super in irq context */ - if (!in_task) - f2fs_handle_error_async(sbi, ERROR_FAIL_DECOMPRESSION); - else - f2fs_handle_error(sbi, ERROR_FAIL_DECOMPRESSION); + f2fs_handle_error(sbi, ERROR_FAIL_DECOMPRESSION); goto out_release; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 775aa4f63aa303..3ac0ecbf3ced38 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -151,6 +151,12 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task) } dec_page_count(F2FS_F_SB(folio), __read_io_type(folio)); + + if (F2FS_F_SB(folio)->node_inode && is_node_folio(folio) && + f2fs_sanity_check_node_footer(F2FS_F_SB(folio), + folio, folio->index, NODE_TYPE_REGULAR, true)) + bio->bi_status = BLK_STS_IOERR; + folio_end_read(folio, bio->bi_status == BLK_STS_OK); } @@ -352,18 +358,27 @@ static void f2fs_write_end_io(struct bio *bio) STOP_CP_REASON_WRITE_FAIL); } - f2fs_bug_on(sbi, is_node_folio(folio) && - folio->index != nid_of_node(folio)); + if (is_node_folio(folio)) { + f2fs_sanity_check_node_footer(sbi, folio, + folio->index, NODE_TYPE_REGULAR, true); + f2fs_bug_on(sbi, folio->index != nid_of_node(folio)); + } dec_page_count(sbi, type); + + /* + * we should access sbi before folio_end_writeback() to + * avoid racing w/ kill_f2fs_super() + */ + if (type == F2FS_WB_CP_DATA && !get_pages(sbi, type) && + wq_has_sleeper(&sbi->cp_wait)) + wake_up(&sbi->cp_wait); + if (f2fs_in_warm_node_list(sbi, folio)) f2fs_del_fsync_node_entry(sbi, folio); folio_clear_f2fs_gcing(folio); folio_end_writeback(folio); } - if (!get_pages(sbi, F2FS_WB_CP_DATA) && - wq_has_sleeper(&sbi->cp_wait)) - wake_up(&sbi->cp_wait); bio_put(bio); } @@ -1793,7 +1808,8 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int flag) return err; } -bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len) +static bool __f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len, + bool check_first) { struct f2fs_map_blocks map; block_t last_lblk; @@ -1815,10 +1831,17 @@ bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len) if (err || map.m_len == 0) return false; map.m_lblk += map.m_len; + if (check_first) + break; } return true; } +bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len) +{ + return __f2fs_overwrite_io(inode, pos, len, false); +} + static int f2fs_xattr_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo) { @@ -3224,6 +3247,19 @@ static inline bool __should_serialize_io(struct inode *inode, return false; } +static inline void account_writeback(struct inode *inode, bool inc) +{ + if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + return; + + f2fs_down_read(&F2FS_I(inode)->i_sem); + if (inc) + atomic_inc(&F2FS_I(inode)->writeback); + else + atomic_dec(&F2FS_I(inode)->writeback); + f2fs_up_read(&F2FS_I(inode)->i_sem); +} + static int __f2fs_write_data_pages(struct address_space *mapping, struct writeback_control *wbc, enum iostat_type io_type) @@ -3269,10 +3305,14 @@ static int __f2fs_write_data_pages(struct address_space *mapping, locked = true; } + account_writeback(inode, true); + blk_start_plug(&plug); ret = f2fs_write_cache_pages(mapping, wbc, io_type); blk_finish_plug(&plug); + account_writeback(inode, false); + if (locked) mutex_unlock(&sbi->writepages); @@ -3916,6 +3956,7 @@ static int check_swap_activate(struct swap_info_struct *sis, while (cur_lblock < last_lblock && cur_lblock < sis->max) { struct f2fs_map_blocks map; + bool last_extent = false; retry: cond_resched(); @@ -3941,11 +3982,10 @@ static int check_swap_activate(struct swap_info_struct *sis, pblock = map.m_pblk; nr_pblocks = map.m_len; - if ((pblock - SM_I(sbi)->main_blkaddr) % blks_per_sec || - nr_pblocks % blks_per_sec || - f2fs_is_sequential_zone_area(sbi, pblock)) { - bool last_extent = false; - + if (!last_extent && + ((pblock - SM_I(sbi)->main_blkaddr) % blks_per_sec || + nr_pblocks % blks_per_sec || + f2fs_is_sequential_zone_area(sbi, pblock))) { not_aligned++; nr_pblocks = roundup(nr_pblocks, blks_per_sec); @@ -3966,8 +4006,8 @@ static int check_swap_activate(struct swap_info_struct *sis, goto out; } - if (!last_extent) - goto retry; + /* lookup block mapping info after block migration */ + goto retry; } if (cur_lblock + nr_pblocks >= sis->max) @@ -4168,7 +4208,7 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, * f2fs_map_lock and f2fs_balance_fs are not necessary. */ if ((flags & IOMAP_WRITE) && - !f2fs_overwrite_io(inode, offset, length)) + !__f2fs_overwrite_io(inode, offset, length, true)) map.m_may_create = true; err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_DIO); diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 33e09c453c7033..0ed84cc065a7ed 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -808,7 +808,7 @@ static void __update_extent_tree_range(struct inode *inode, } goto out_read_extent_cache; update_age_extent_cache: - if (!tei->last_blocks) + if (tei->last_blocks == F2FS_EXTENT_AGE_INVALID) goto out_read_extent_cache; __set_extent_info(&ei, fofs, len, 0, false, @@ -912,7 +912,7 @@ static int __get_new_block_age(struct inode *inode, struct extent_info *ei, cur_age = cur_blocks - tei.last_blocks; else /* allocated_data_blocks overflow */ - cur_age = ULLONG_MAX - tei.last_blocks + cur_blocks; + cur_age = (ULLONG_MAX - 1) - tei.last_blocks + cur_blocks; if (tei.age) ei->age = __calculate_block_age(sbi, cur_age, tei.age); @@ -1114,6 +1114,7 @@ void f2fs_update_age_extent_cache_range(struct dnode_of_data *dn, struct extent_info ei = { .fofs = fofs, .len = len, + .last_blocks = F2FS_EXTENT_AGE_INVALID, }; if (!__may_extent_tree(dn->inode, EX_BLOCK_AGE)) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 5b4e9548a231f3..123c50f6619ae4 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -245,6 +245,7 @@ struct f2fs_mount_info { #define F2FS_FEATURE_COMPRESSION 0x00002000 #define F2FS_FEATURE_RO 0x00004000 #define F2FS_FEATURE_DEVICE_ALIAS 0x00008000 +#define F2FS_FEATURE_PACKED_SSA 0x00010000 #define __F2FS_HAS_FEATURE(raw_super, mask) \ ((raw_super->feature & cpu_to_le32(mask)) != 0) @@ -507,13 +508,25 @@ struct fsync_inode_entry { #define nats_in_cursum(jnl) (le16_to_cpu((jnl)->n_nats)) #define sits_in_cursum(jnl) (le16_to_cpu((jnl)->n_sits)) -#define nat_in_journal(jnl, i) ((jnl)->nat_j.entries[i].ne) -#define nid_in_journal(jnl, i) ((jnl)->nat_j.entries[i].nid) -#define sit_in_journal(jnl, i) ((jnl)->sit_j.entries[i].se) -#define segno_in_journal(jnl, i) ((jnl)->sit_j.entries[i].segno) - -#define MAX_NAT_JENTRIES(jnl) (NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl)) -#define MAX_SIT_JENTRIES(jnl) (SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl)) +#define nat_in_journal(jnl, i) \ + (((struct nat_journal_entry *)(jnl)->nat_j.entries)[i].ne) +#define nid_in_journal(jnl, i) \ + (((struct nat_journal_entry *)(jnl)->nat_j.entries)[i].nid) +#define sit_in_journal(jnl, i) \ + (((struct sit_journal_entry *)(jnl)->sit_j.entries)[i].se) +#define segno_in_journal(jnl, i) \ + (((struct sit_journal_entry *)(jnl)->sit_j.entries)[i].segno) + +#define sum_entries(sum) ((struct f2fs_summary *)(sum)) +#define sum_journal(sbi, sum) \ + ((struct f2fs_journal *)((char *)(sum) + \ + ((sbi)->entries_in_sum * sizeof(struct f2fs_summary)))) +#define sum_footer(sbi, sum) \ + ((struct summary_footer *)((char *)(sum) + (sbi)->sum_blocksize - \ + sizeof(struct summary_footer))) + +#define MAX_NAT_JENTRIES(sbi, jnl) ((sbi)->nat_journal_entries - nats_in_cursum(jnl)) +#define MAX_SIT_JENTRIES(sbi, jnl) ((sbi)->sit_journal_entries - sits_in_cursum(jnl)) static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i) { @@ -531,14 +544,6 @@ static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i) return before; } -static inline bool __has_cursum_space(struct f2fs_journal *journal, - int size, int type) -{ - if (type == NAT_JOURNAL) - return size <= MAX_NAT_JENTRIES(journal); - return size <= MAX_SIT_JENTRIES(journal); -} - /* for inline stuff */ #define DEF_INLINE_RESERVED_SIZE 1 static inline int get_extra_isize(struct inode *inode); @@ -707,6 +712,12 @@ enum extent_type { NR_EXTENT_CACHES, }; +/* + * Reserved value to mark invalid age extents, hence valid block range + * from 0 to ULLONG_MAX-1 + */ +#define F2FS_EXTENT_AGE_INVALID ULLONG_MAX + struct extent_info { unsigned int fofs; /* start offset in a file */ unsigned int len; /* length of the extent */ @@ -947,6 +958,7 @@ struct f2fs_inode_info { unsigned char i_compress_level; /* compress level (lz4hc,zstd) */ unsigned char i_compress_flag; /* compress flag */ unsigned int i_cluster_size; /* cluster size */ + atomic_t writeback; /* count # of writeback thread */ unsigned int atomic_write_cnt; loff_t original_i_size; /* original i_size before atomic write */ @@ -1504,6 +1516,15 @@ enum f2fs_lookup_mode { LOOKUP_AUTO, }; +/* For node type in __get_node_folio() */ +enum node_type { + NODE_TYPE_REGULAR, + NODE_TYPE_INODE, + NODE_TYPE_XATTR, + NODE_TYPE_NON_INODE, +}; + + static inline int f2fs_test_bit(unsigned int nr, char *addr); static inline void f2fs_set_bit(unsigned int nr, char *addr); static inline void f2fs_clear_bit(unsigned int nr, char *addr); @@ -1742,6 +1763,15 @@ struct f2fs_sb_info { bool readdir_ra; /* readahead inode in readdir */ u64 max_io_bytes; /* max io bytes to merge IOs */ + /* variable summary block units */ + unsigned int sum_blocksize; /* sum block size */ + unsigned int sums_per_block; /* sum block count per block */ + unsigned int entries_in_sum; /* entry count in sum block */ + unsigned int sum_entry_size; /* total entry size in sum block */ + unsigned int sum_journal_size; /* journal size in sum block */ + unsigned int nat_journal_entries; /* nat journal entry count in the journal */ + unsigned int sit_journal_entries; /* sit journal entry count in the journal */ + block_t user_block_count; /* # of user blocks */ block_t total_valid_block_count; /* # of valid blocks */ block_t discard_blks; /* discard command candidats */ @@ -1884,9 +1914,6 @@ struct f2fs_sb_info { spinlock_t error_lock; /* protect errors/stop_reason array */ bool error_dirty; /* errors of sb is dirty */ - struct kmem_cache *inline_xattr_slab; /* inline xattr entry */ - unsigned int inline_xattr_slab_size; /* default inline xattr slab size */ - /* For reclaimed segs statistics per each GC mode */ unsigned int gc_segment_mode; /* GC state for reclaimed segments */ unsigned int gc_reclaimed_segs[MAX_GC_MODE]; /* Reclaimed segs for each mode */ @@ -2794,6 +2821,14 @@ static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi) return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum); } +static inline bool __has_cursum_space(struct f2fs_sb_info *sbi, + struct f2fs_journal *journal, int size, int type) +{ + if (type == NAT_JOURNAL) + return size <= MAX_NAT_JENTRIES(sbi, journal); + return size <= MAX_SIT_JENTRIES(sbi, journal); +} + extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync); static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, struct inode *inode, bool is_inode) @@ -3810,7 +3845,6 @@ void f2fs_quota_off_umount(struct super_block *sb); void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag); void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason); void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error); -void f2fs_handle_error_async(struct f2fs_sb_info *sbi, unsigned char error); int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover); int f2fs_sync_fs(struct super_block *sb, int sync); int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi); @@ -3849,6 +3883,9 @@ struct folio *f2fs_new_node_folio(struct dnode_of_data *dn, unsigned int ofs); void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid); struct folio *f2fs_get_node_folio(struct f2fs_sb_info *sbi, pgoff_t nid, enum node_type node_type); +int f2fs_sanity_check_node_footer(struct f2fs_sb_info *sbi, + struct folio *folio, pgoff_t nid, + enum node_type ntype, bool in_irq); struct folio *f2fs_get_inode_folio(struct f2fs_sb_info *sbi, pgoff_t ino); struct folio *f2fs_get_xnode_folio(struct f2fs_sb_info *sbi, pgoff_t xnid); int f2fs_move_node_folio(struct folio *node_folio, int gc_type); @@ -3948,7 +3985,8 @@ void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, block_t len); void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk); void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk); -int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, +int f2fs_lookup_journal_in_cursum(struct f2fs_sb_info *sbi, + struct f2fs_journal *journal, int type, unsigned int val, int alloc); void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); int f2fs_check_and_fix_write_pointer(struct f2fs_sb_info *sbi); @@ -4674,7 +4712,7 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode) f2fs_up_write(&fi->i_sem); return true; } - if (f2fs_is_mmap_file(inode) || + if (f2fs_is_mmap_file(inode) || atomic_read(&fi->writeback) || (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))) { f2fs_up_write(&fi->i_sem); return false; @@ -4710,6 +4748,7 @@ F2FS_FEATURE_FUNCS(casefold, CASEFOLD); F2FS_FEATURE_FUNCS(compression, COMPRESSION); F2FS_FEATURE_FUNCS(readonly, RO); F2FS_FEATURE_FUNCS(device_alias, DEVICE_ALIAS); +F2FS_FEATURE_FUNCS(packed_ssa, PACKED_SSA); #ifdef CONFIG_BLK_DEV_ZONED static inline bool f2fs_zone_is_seq(struct f2fs_sb_info *sbi, int devi, diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index ffa045b39c01de..6d42e2d28861ce 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1654,8 +1654,11 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, f2fs_set_data_blkaddr(dn, NEW_ADDR); } - f2fs_update_read_extent_cache_range(dn, start, 0, index - start); - f2fs_update_age_extent_cache_range(dn, start, index - start); + if (index > start) { + f2fs_update_read_extent_cache_range(dn, start, 0, + index - start); + f2fs_update_age_extent_cache_range(dn, start, index - start); + } return ret; } @@ -2125,8 +2128,9 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) f2fs_down_write(&fi->i_sem); if (!f2fs_may_compress(inode) || - (S_ISREG(inode->i_mode) && - F2FS_HAS_BLOCKS(inode))) { + atomic_read(&fi->writeback) || + (S_ISREG(inode->i_mode) && + F2FS_HAS_BLOCKS(inode))) { f2fs_up_write(&fi->i_sem); return -EINVAL; } diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index a7708cf80c04ed..9d2f4f22fd3963 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -38,13 +38,14 @@ static int gc_thread_func(void *data) struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO, .should_migrate_blocks = false, - .err_gc_skipped = false }; + .err_gc_skipped = false, + .one_time = false }; wait_ms = gc_th->min_sleep_time; set_freezable(); do { - bool sync_mode, foreground = false; + bool sync_mode, foreground = false, gc_boost = false; wait_event_freezable_timeout(*wq, kthread_should_stop() || @@ -52,8 +53,12 @@ static int gc_thread_func(void *data) gc_th->gc_wake, msecs_to_jiffies(wait_ms)); - if (test_opt(sbi, GC_MERGE) && waitqueue_active(fggc_wq)) + if (test_opt(sbi, GC_MERGE) && waitqueue_active(fggc_wq)) { foreground = true; + gc_control.one_time = false; + } else if (f2fs_sb_has_blkzoned(sbi)) { + gc_control.one_time = true; + } /* give it a try one time */ if (gc_th->gc_wake) @@ -81,8 +86,6 @@ static int gc_thread_func(void *data) continue; } - gc_control.one_time = false; - /* * [GC triggering condition] * 0. GC is not conducted currently. @@ -132,7 +135,7 @@ static int gc_thread_func(void *data) if (need_to_boost_gc(sbi)) { decrease_sleep_time(gc_th, &wait_ms); if (f2fs_sb_has_blkzoned(sbi)) - gc_control.one_time = true; + gc_boost = true; } else { increase_sleep_time(gc_th, &wait_ms); } @@ -141,7 +144,7 @@ static int gc_thread_func(void *data) FOREGROUND : BACKGROUND); sync_mode = (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_SYNC) || - (gc_control.one_time && gc_th->boost_gc_greedy); + (gc_boost && gc_th->boost_gc_greedy); /* foreground GC was been triggered via f2fs_balance_fs() */ if (foreground && !f2fs_sb_has_blkzoned(sbi)) @@ -771,7 +774,7 @@ int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result, { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); struct sit_info *sm = SIT_I(sbi); - struct victim_sel_policy p; + struct victim_sel_policy p = {0}; unsigned int secno, last_victim; unsigned int last_segment; unsigned int nsearched; @@ -1729,7 +1732,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ? SUM_TYPE_DATA : SUM_TYPE_NODE; unsigned char data_type = (type == SUM_TYPE_DATA) ? DATA : NODE; - int submitted = 0; + int submitted = 0, sum_blk_cnt; if (__is_large_section(sbi)) { sec_end_segno = rounddown(end_segno, SEGS_PER_SEC(sbi)); @@ -1763,22 +1766,28 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, sanity_check_seg_type(sbi, get_seg_entry(sbi, segno)->type); + segno = rounddown(segno, sbi->sums_per_block); + sum_blk_cnt = DIV_ROUND_UP(end_segno - segno, sbi->sums_per_block); /* readahead multi ssa blocks those have contiguous address */ if (__is_large_section(sbi)) f2fs_ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), - end_segno - segno, META_SSA, true); + sum_blk_cnt, META_SSA, true); /* reference all summary page */ while (segno < end_segno) { - struct folio *sum_folio = f2fs_get_sum_folio(sbi, segno++); + struct folio *sum_folio = f2fs_get_sum_folio(sbi, segno); + + segno += sbi->sums_per_block; if (IS_ERR(sum_folio)) { int err = PTR_ERR(sum_folio); - end_segno = segno - 1; - for (segno = start_segno; segno < end_segno; segno++) { + end_segno = segno - sbi->sums_per_block; + segno = rounddown(start_segno, sbi->sums_per_block); + while (segno < end_segno) { sum_folio = filemap_get_folio(META_MAPPING(sbi), GET_SUM_BLOCK(sbi, segno)); folio_put_refs(sum_folio, 2); + segno += sbi->sums_per_block; } return err; } @@ -1787,68 +1796,84 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, blk_start_plug(&plug); - for (segno = start_segno; segno < end_segno; segno++) { - struct f2fs_summary_block *sum; + segno = start_segno; + while (segno < end_segno) { + unsigned int cur_segno; /* find segment summary of victim */ struct folio *sum_folio = filemap_get_folio(META_MAPPING(sbi), GET_SUM_BLOCK(sbi, segno)); + unsigned int block_end_segno = rounddown(segno, sbi->sums_per_block) + + sbi->sums_per_block; + + if (block_end_segno > end_segno) + block_end_segno = end_segno; if (is_cursec(sbi, GET_SEC_FROM_SEG(sbi, segno))) { f2fs_err(sbi, "%s: segment %u is used by log", __func__, segno); f2fs_bug_on(sbi, 1); - goto skip; + goto next_block; } - if (get_valid_blocks(sbi, segno, false) == 0) - goto freed; - if (gc_type == BG_GC && __is_large_section(sbi) && - migrated >= sbi->migration_granularity) - goto skip; if (!folio_test_uptodate(sum_folio) || unlikely(f2fs_cp_error(sbi))) - goto skip; + goto next_block; - sum = folio_address(sum_folio); - if (type != GET_SUM_TYPE((&sum->footer))) { - f2fs_err(sbi, "Inconsistent segment (%u) type [%d, %d] in SIT and SSA", - segno, type, GET_SUM_TYPE((&sum->footer))); - f2fs_stop_checkpoint(sbi, false, - STOP_CP_REASON_CORRUPTED_SUMMARY); - goto skip; - } + for (cur_segno = segno; cur_segno < block_end_segno; + cur_segno++) { + struct f2fs_summary_block *sum; - /* - * this is to avoid deadlock: - * - lock_page(sum_page) - f2fs_replace_block - * - check_valid_map() - down_write(sentry_lock) - * - down_read(sentry_lock) - change_curseg() - * - lock_page(sum_page) - */ - if (type == SUM_TYPE_NODE) - submitted += gc_node_segment(sbi, sum->entries, segno, - gc_type); - else - submitted += gc_data_segment(sbi, sum->entries, gc_list, - segno, gc_type, - force_migrate); + if (get_valid_blocks(sbi, cur_segno, false) == 0) + goto freed; + if (gc_type == BG_GC && __is_large_section(sbi) && + migrated >= sbi->migration_granularity) + continue; - stat_inc_gc_seg_count(sbi, data_type, gc_type); - sbi->gc_reclaimed_segs[sbi->gc_mode]++; - migrated++; + sum = SUM_BLK_PAGE_ADDR(sbi, sum_folio, cur_segno); + if (type != GET_SUM_TYPE(sum_footer(sbi, sum))) { + f2fs_err(sbi, "Inconsistent segment (%u) type " + "[%d, %d] in SSA and SIT", + cur_segno, type, + GET_SUM_TYPE( + sum_footer(sbi, sum))); + f2fs_stop_checkpoint(sbi, false, + STOP_CP_REASON_CORRUPTED_SUMMARY); + continue; + } -freed: - if (gc_type == FG_GC && - get_valid_blocks(sbi, segno, false) == 0) - seg_freed++; + /* + * this is to avoid deadlock: + * - lock_page(sum_page) - f2fs_replace_block + * - check_valid_map() - down_write(sentry_lock) + * - down_read(sentry_lock) - change_curseg() + * - lock_page(sum_page) + */ + if (type == SUM_TYPE_NODE) + submitted += gc_node_segment(sbi, sum->entries, + cur_segno, gc_type); + else + submitted += gc_data_segment(sbi, sum->entries, + gc_list, cur_segno, + gc_type, force_migrate); - if (__is_large_section(sbi)) - sbi->next_victim_seg[gc_type] = - (segno + 1 < sec_end_segno) ? - segno + 1 : NULL_SEGNO; -skip: + stat_inc_gc_seg_count(sbi, data_type, gc_type); + sbi->gc_reclaimed_segs[sbi->gc_mode]++; + migrated++; + +freed: + if (gc_type == FG_GC && + get_valid_blocks(sbi, cur_segno, false) == 0) + seg_freed++; + + if (__is_large_section(sbi)) + sbi->next_victim_seg[gc_type] = + (cur_segno + 1 < sec_end_segno) ? + cur_segno + 1 : NULL_SEGNO; + } +next_block: folio_put_refs(sum_folio, 2); + segno = block_end_segno; } if (submitted) @@ -2069,6 +2094,7 @@ int f2fs_gc_range(struct f2fs_sb_info *sbi, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + stat_inc_gc_call_count(sbi, FOREGROUND); for (segno = start_seg; segno <= end_seg; segno += SEGS_PER_SEC(sbi)) { struct gc_inode_list gc_list = { .ilist = LIST_HEAD_INIT(gc_list.ilist), diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index b882771e469971..712479b7b93d78 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -1053,9 +1053,11 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, if (whiteout) { set_inode_flag(whiteout, FI_INC_LINK); err = f2fs_add_link(old_dentry, whiteout); - if (err) + if (err) { + d_invalidate(old_dentry); + d_invalidate(new_dentry); goto put_out_dir; - + } spin_lock(&whiteout->i_lock); whiteout->i_state &= ~I_LINKABLE; spin_unlock(&whiteout->i_lock); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 482a362f262543..591fcdf3ba77b9 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -606,7 +606,7 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, goto retry; } - i = f2fs_lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0); + i = f2fs_lookup_journal_in_cursum(sbi, journal, NAT_JOURNAL, nid, 0); if (i >= 0) { ne = nat_in_journal(journal, i); node_info_from_raw_nat(ni, &ne); @@ -1500,9 +1500,9 @@ void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) f2fs_folio_put(afolio, err ? true : false); } -static int sanity_check_node_footer(struct f2fs_sb_info *sbi, +int f2fs_sanity_check_node_footer(struct f2fs_sb_info *sbi, struct folio *folio, pgoff_t nid, - enum node_type ntype) + enum node_type ntype, bool in_irq) { if (unlikely(nid != nid_of_node(folio))) goto out_err; @@ -1527,12 +1527,13 @@ static int sanity_check_node_footer(struct f2fs_sb_info *sbi, goto out_err; return 0; out_err: - f2fs_warn(sbi, "inconsistent node block, node_type:%d, nid:%lu, " - "node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]", - ntype, nid, nid_of_node(folio), ino_of_node(folio), - ofs_of_node(folio), cpver_of_node(folio), - next_blkaddr_of_node(folio)); set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn_ratelimited(sbi, "inconsistent node block, node_type:%d, nid:%lu, " + "node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]", + ntype, nid, nid_of_node(folio), ino_of_node(folio), + ofs_of_node(folio), cpver_of_node(folio), + next_blkaddr_of_node(folio)); + f2fs_handle_error(sbi, ERROR_INCONSISTENT_FOOTER); return -EFSCORRUPTED; } @@ -1578,7 +1579,7 @@ static struct folio *__get_node_folio(struct f2fs_sb_info *sbi, pgoff_t nid, goto out_err; } page_hit: - err = sanity_check_node_footer(sbi, folio, nid, ntype); + err = f2fs_sanity_check_node_footer(sbi, folio, nid, ntype, false); if (!err) return folio; out_err: @@ -1751,7 +1752,12 @@ static bool __write_node_folio(struct folio *folio, bool atomic, bool *submitted /* get old block addr of this node page */ nid = nid_of_node(folio); - f2fs_bug_on(sbi, folio->index != nid); + + if (f2fs_sanity_check_node_footer(sbi, folio, nid, + NODE_TYPE_REGULAR, false)) { + f2fs_handle_critical_error(sbi, STOP_CP_REASON_CORRUPTED_NID); + goto redirty_out; + } if (f2fs_get_node_info(sbi, nid, &ni, !do_balance)) goto redirty_out; @@ -1774,8 +1780,13 @@ static bool __write_node_folio(struct folio *folio, bool atomic, bool *submitted goto redirty_out; } - if (atomic && !test_opt(sbi, NOBARRIER)) - fio.op_flags |= REQ_PREFLUSH | REQ_FUA; + if (atomic) { + if (!test_opt(sbi, NOBARRIER)) + fio.op_flags |= REQ_PREFLUSH | REQ_FUA; + if (IS_INODE(folio)) + set_dentry_mark(folio, + f2fs_need_dentry_mark(sbi, ino_of_node(folio))); + } /* should add to global list before clearing PAGECACHE status */ if (f2fs_in_warm_node_list(sbi, folio)) { @@ -1916,8 +1927,9 @@ int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, if (is_inode_flag_set(inode, FI_DIRTY_INODE)) f2fs_update_inode(inode, folio); - set_dentry_mark(folio, - f2fs_need_dentry_mark(sbi, ino)); + if (!atomic) + set_dentry_mark(folio, + f2fs_need_dentry_mark(sbi, ino)); } /* may be written by other thread */ if (!folio_test_dirty(folio)) @@ -2937,7 +2949,7 @@ int f2fs_restore_node_summary(struct f2fs_sb_info *sbi, /* scan the node segment */ last_offset = BLKS_PER_SEG(sbi); addr = START_BLOCK(sbi, segno); - sum_entry = &sum->entries[0]; + sum_entry = sum_entries(sum); for (i = 0; i < last_offset; i += nrpages, addr += nrpages) { nrpages = bio_max_segs(last_offset - i); @@ -3078,7 +3090,7 @@ static int __flush_nat_entry_set(struct f2fs_sb_info *sbi, * #2, flush nat entries to nat page. */ if (enabled_nat_bits(sbi, cpc) || - !__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL)) + !__has_cursum_space(sbi, journal, set->entry_cnt, NAT_JOURNAL)) to_journal = false; if (to_journal) { @@ -3101,7 +3113,7 @@ static int __flush_nat_entry_set(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, nat_get_blkaddr(ne) == NEW_ADDR); if (to_journal) { - offset = f2fs_lookup_journal_in_cursum(journal, + offset = f2fs_lookup_journal_in_cursum(sbi, journal, NAT_JOURNAL, nid, 1); f2fs_bug_on(sbi, offset < 0); raw_ne = &nat_in_journal(journal, offset); @@ -3172,7 +3184,7 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) * into nat entry set. */ if (enabled_nat_bits(sbi, cpc) || - !__has_cursum_space(journal, + !__has_cursum_space(sbi, journal, nm_i->nat_cnt[DIRTY_NAT], NAT_JOURNAL)) remove_nats_in_journal(sbi); @@ -3183,7 +3195,7 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) set_idx = setvec[found - 1]->set + 1; for (idx = 0; idx < found; idx++) __adjust_nat_entry_set(setvec[idx], &sets, - MAX_NAT_JENTRIES(journal)); + MAX_NAT_JENTRIES(sbi, journal)); } /* flush dirty nats in nat entry set */ diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 9cb8dcf8d41760..824ac9f0e6e42a 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -52,14 +52,6 @@ enum { IS_PREALLOC, /* nat entry is preallocated */ }; -/* For node type in __get_node_folio() */ -enum node_type { - NODE_TYPE_REGULAR, - NODE_TYPE_INODE, - NODE_TYPE_XATTR, - NODE_TYPE_NON_INODE, -}; - /* * For node information */ diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 215e442db72c82..06674e694b271e 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -399,7 +399,7 @@ static int sanity_check_node_chain(struct f2fs_sb_info *sbi, block_t blkaddr, } static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, - bool check_only) + bool check_only, bool *new_inode) { struct curseg_info *curseg; block_t blkaddr, blkaddr_fast; @@ -447,16 +447,19 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, quota_inode = true; } - /* - * CP | dnode(F) | inode(DF) - * For this case, we should not give up now. - */ entry = add_fsync_inode(sbi, head, ino_of_node(folio), quota_inode); if (IS_ERR(entry)) { err = PTR_ERR(entry); - if (err == -ENOENT) + /* + * CP | dnode(F) | inode(DF) + * For this case, we should not give up now. + */ + if (err == -ENOENT) { + if (check_only) + *new_inode = true; goto next; + } f2fs_folio_put(folio, true); break; } @@ -511,7 +514,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, struct curseg_info *curseg = CURSEG_I(sbi, i); if (curseg->segno == segno) { - sum = curseg->sum_blk->entries[blkoff]; + sum = sum_entries(curseg->sum_blk)[blkoff]; goto got_it; } } @@ -519,8 +522,8 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, sum_folio = f2fs_get_sum_folio(sbi, segno); if (IS_ERR(sum_folio)) return PTR_ERR(sum_folio); - sum_node = folio_address(sum_folio); - sum = sum_node->entries[blkoff]; + sum_node = SUM_BLK_PAGE_ADDR(sbi, sum_folio, segno); + sum = sum_entries(sum_node)[blkoff]; f2fs_folio_put(sum_folio, true); got_it: /* Use the locked dnode page and inode */ @@ -875,6 +878,7 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) int ret = 0; unsigned long s_flags = sbi->sb->s_flags; bool need_writecp = false; + bool new_inode = false; f2fs_notice(sbi, "f2fs_recover_fsync_data: recovery fsync data, " "check_only: %d", check_only); @@ -890,8 +894,8 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) f2fs_down_write(&sbi->cp_global_sem); /* step #1: find fsynced inode numbers */ - err = find_fsync_dnodes(sbi, &inode_list, check_only); - if (err || list_empty(&inode_list)) + err = find_fsync_dnodes(sbi, &inode_list, check_only, &new_inode); + if (err < 0 || (list_empty(&inode_list) && (!check_only || !new_inode))) goto skip; if (check_only) { diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index b45eace879d74b..23b94a8fd843de 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -2689,12 +2689,12 @@ int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) valid_sum_count += f2fs_curseg_valid_blocks(sbi, i); } - sum_in_page = (PAGE_SIZE - 2 * SUM_JOURNAL_SIZE - + sum_in_page = (sbi->blocksize - 2 * sbi->sum_journal_size - SUM_FOOTER_SIZE) / SUMMARY_SIZE; if (valid_sum_count <= sum_in_page) return 1; else if ((valid_sum_count - sum_in_page) <= - (PAGE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE) + (sbi->blocksize - SUM_FOOTER_SIZE) / SUMMARY_SIZE) return 2; return 3; } @@ -2712,7 +2712,15 @@ struct folio *f2fs_get_sum_folio(struct f2fs_sb_info *sbi, unsigned int segno) void f2fs_update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr) { - struct folio *folio = f2fs_grab_meta_folio(sbi, blk_addr); + struct folio *folio; + + if (!f2fs_sb_has_packed_ssa(sbi)) + folio = f2fs_grab_meta_folio(sbi, blk_addr); + else + folio = f2fs_get_meta_folio_retry(sbi, blk_addr); + + if (IS_ERR(folio)) + return; memcpy(folio_address(folio), src, PAGE_SIZE); folio_mark_dirty(folio); @@ -2720,9 +2728,22 @@ void f2fs_update_meta_page(struct f2fs_sb_info *sbi, } static void write_sum_page(struct f2fs_sb_info *sbi, - struct f2fs_summary_block *sum_blk, block_t blk_addr) + struct f2fs_summary_block *sum_blk, unsigned int segno) { - f2fs_update_meta_page(sbi, (void *)sum_blk, blk_addr); + struct folio *folio; + + if (!f2fs_sb_has_packed_ssa(sbi)) + return f2fs_update_meta_page(sbi, (void *)sum_blk, + GET_SUM_BLOCK(sbi, segno)); + + folio = f2fs_get_sum_folio(sbi, segno); + if (IS_ERR(folio)) + return; + + memcpy(SUM_BLK_PAGE_ADDR(sbi, folio, segno), sum_blk, + sbi->sum_blocksize); + folio_mark_dirty(folio); + f2fs_folio_put(folio, true); } static void write_current_sum_page(struct f2fs_sb_info *sbi, @@ -2739,11 +2760,11 @@ static void write_current_sum_page(struct f2fs_sb_info *sbi, mutex_lock(&curseg->curseg_mutex); down_read(&curseg->journal_rwsem); - memcpy(&dst->journal, curseg->journal, SUM_JOURNAL_SIZE); + memcpy(sum_journal(sbi, dst), curseg->journal, sbi->sum_journal_size); up_read(&curseg->journal_rwsem); - memcpy(dst->entries, src->entries, SUM_ENTRY_SIZE); - memcpy(&dst->footer, &src->footer, SUM_FOOTER_SIZE); + memcpy(sum_entries(dst), sum_entries(src), sbi->sum_entry_size); + memcpy(sum_footer(sbi, dst), sum_footer(sbi, src), SUM_FOOTER_SIZE); mutex_unlock(&curseg->curseg_mutex); @@ -2916,7 +2937,7 @@ static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified) curseg->next_blkoff = 0; curseg->next_segno = NULL_SEGNO; - sum_footer = &(curseg->sum_blk->footer); + sum_footer = sum_footer(sbi, curseg->sum_blk); memset(sum_footer, 0, sizeof(struct summary_footer)); sanity_check_seg_type(sbi, seg_type); @@ -2987,7 +3008,7 @@ static int new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec) int ret; if (curseg->inited) - write_sum_page(sbi, curseg->sum_blk, GET_SUM_BLOCK(sbi, segno)); + write_sum_page(sbi, curseg->sum_blk, segno); segno = __get_next_segno(sbi, type); ret = get_new_segment(sbi, &segno, new_sec, pinning); @@ -3046,7 +3067,7 @@ static int change_curseg(struct f2fs_sb_info *sbi, int type) struct folio *sum_folio; if (curseg->inited) - write_sum_page(sbi, curseg->sum_blk, GET_SUM_BLOCK(sbi, curseg->segno)); + write_sum_page(sbi, curseg->sum_blk, curseg->segno); __set_test_and_inuse(sbi, new_segno); @@ -3062,11 +3083,11 @@ static int change_curseg(struct f2fs_sb_info *sbi, int type) sum_folio = f2fs_get_sum_folio(sbi, new_segno); if (IS_ERR(sum_folio)) { /* GC won't be able to use stale summary pages by cp_error */ - memset(curseg->sum_blk, 0, SUM_ENTRY_SIZE); + memset(curseg->sum_blk, 0, sbi->sum_entry_size); return PTR_ERR(sum_folio); } - sum_node = folio_address(sum_folio); - memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE); + sum_node = SUM_BLK_PAGE_ADDR(sbi, sum_folio, new_segno); + memcpy(curseg->sum_blk, sum_node, sbi->sum_entry_size); f2fs_folio_put(sum_folio, true); return 0; } @@ -3154,8 +3175,7 @@ static void __f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi, int type) goto out; if (get_valid_blocks(sbi, curseg->segno, false)) { - write_sum_page(sbi, curseg->sum_blk, - GET_SUM_BLOCK(sbi, curseg->segno)); + write_sum_page(sbi, curseg->sum_blk, curseg->segno); } else { mutex_lock(&DIRTY_I(sbi)->seglist_lock); __set_test_and_free(sbi, curseg->segno, true); @@ -3799,7 +3819,7 @@ int f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct folio *folio, f2fs_wait_discard_bio(sbi, *new_blkaddr); - curseg->sum_blk->entries[curseg->next_blkoff] = *sum; + sum_entries(curseg->sum_blk)[curseg->next_blkoff] = *sum; if (curseg->alloc_type == SSR) { curseg->next_blkoff = f2fs_find_next_ssr_block(sbi, curseg); } else { @@ -3833,8 +3853,7 @@ int f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct folio *folio, if (segment_full) { if (type == CURSEG_COLD_DATA_PINNED && !((curseg->segno + 1) % sbi->segs_per_sec)) { - write_sum_page(sbi, curseg->sum_blk, - GET_SUM_BLOCK(sbi, curseg->segno)); + write_sum_page(sbi, curseg->sum_blk, curseg->segno); reset_curseg_fields(curseg); goto skip_new_segment; } @@ -3863,8 +3882,13 @@ int f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct folio *folio, locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); locate_dirty_segment(sbi, GET_SEGNO(sbi, *new_blkaddr)); - if (IS_DATASEG(curseg->seg_type)) - atomic64_inc(&sbi->allocated_data_blocks); + if (IS_DATASEG(curseg->seg_type)) { + unsigned long long new_val; + + new_val = atomic64_inc_return(&sbi->allocated_data_blocks); + if (unlikely(new_val == ULLONG_MAX)) + atomic64_set(&sbi->allocated_data_blocks, 0); + } up_write(&sit_i->sentry_lock); @@ -4164,7 +4188,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, } curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr); - curseg->sum_blk->entries[curseg->next_blkoff] = *sum; + sum_entries(curseg->sum_blk)[curseg->next_blkoff] = *sum; if (!recover_curseg || recover_newaddr) { if (!from_gc) @@ -4284,12 +4308,12 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi) /* Step 1: restore nat cache */ seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA); - memcpy(seg_i->journal, kaddr, SUM_JOURNAL_SIZE); + memcpy(seg_i->journal, kaddr, sbi->sum_journal_size); /* Step 2: restore sit cache */ seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA); - memcpy(seg_i->journal, kaddr + SUM_JOURNAL_SIZE, SUM_JOURNAL_SIZE); - offset = 2 * SUM_JOURNAL_SIZE; + memcpy(seg_i->journal, kaddr + sbi->sum_journal_size, sbi->sum_journal_size); + offset = 2 * sbi->sum_journal_size; /* Step 3: restore summary entries */ for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { @@ -4311,9 +4335,9 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi) struct f2fs_summary *s; s = (struct f2fs_summary *)(kaddr + offset); - seg_i->sum_blk->entries[j] = *s; + sum_entries(seg_i->sum_blk)[j] = *s; offset += SUMMARY_SIZE; - if (offset + SUMMARY_SIZE <= PAGE_SIZE - + if (offset + SUMMARY_SIZE <= sbi->blocksize - SUM_FOOTER_SIZE) continue; @@ -4369,7 +4393,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) if (IS_NODESEG(type)) { if (__exist_node_summaries(sbi)) { - struct f2fs_summary *ns = &sum->entries[0]; + struct f2fs_summary *ns = sum_entries(sum); int i; for (i = 0; i < BLKS_PER_SEG(sbi); i++, ns++) { @@ -4389,11 +4413,13 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) /* update journal info */ down_write(&curseg->journal_rwsem); - memcpy(curseg->journal, &sum->journal, SUM_JOURNAL_SIZE); + memcpy(curseg->journal, sum_journal(sbi, sum), sbi->sum_journal_size); up_write(&curseg->journal_rwsem); - memcpy(curseg->sum_blk->entries, sum->entries, SUM_ENTRY_SIZE); - memcpy(&curseg->sum_blk->footer, &sum->footer, SUM_FOOTER_SIZE); + memcpy(sum_entries(curseg->sum_blk), sum_entries(sum), + sbi->sum_entry_size); + memcpy(sum_footer(sbi, curseg->sum_blk), sum_footer(sbi, sum), + SUM_FOOTER_SIZE); curseg->next_segno = segno; reset_curseg(sbi, type, 0); curseg->alloc_type = ckpt->alloc_type[type]; @@ -4437,8 +4463,8 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) } /* sanity check for summary blocks */ - if (nats_in_cursum(nat_j) > NAT_JOURNAL_ENTRIES || - sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES) { + if (nats_in_cursum(nat_j) > sbi->nat_journal_entries || + sits_in_cursum(sit_j) > sbi->sit_journal_entries) { f2fs_err(sbi, "invalid journal entries nats %u sits %u", nats_in_cursum(nat_j), sits_in_cursum(sit_j)); return -EINVAL; @@ -4462,13 +4488,13 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr) /* Step 1: write nat cache */ seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA); - memcpy(kaddr, seg_i->journal, SUM_JOURNAL_SIZE); - written_size += SUM_JOURNAL_SIZE; + memcpy(kaddr, seg_i->journal, sbi->sum_journal_size); + written_size += sbi->sum_journal_size; /* Step 2: write sit cache */ seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA); - memcpy(kaddr + written_size, seg_i->journal, SUM_JOURNAL_SIZE); - written_size += SUM_JOURNAL_SIZE; + memcpy(kaddr + written_size, seg_i->journal, sbi->sum_journal_size); + written_size += sbi->sum_journal_size; /* Step 3: write summary entries */ for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { @@ -4481,10 +4507,10 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr) written_size = 0; } summary = (struct f2fs_summary *)(kaddr + written_size); - *summary = seg_i->sum_blk->entries[j]; + *summary = sum_entries(seg_i->sum_blk)[j]; written_size += SUMMARY_SIZE; - if (written_size + SUMMARY_SIZE <= PAGE_SIZE - + if (written_size + SUMMARY_SIZE <= sbi->blocksize - SUM_FOOTER_SIZE) continue; @@ -4526,8 +4552,9 @@ void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk) write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE); } -int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, - unsigned int val, int alloc) +int f2fs_lookup_journal_in_cursum(struct f2fs_sb_info *sbi, + struct f2fs_journal *journal, int type, + unsigned int val, int alloc) { int i; @@ -4536,13 +4563,13 @@ int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, if (le32_to_cpu(nid_in_journal(journal, i)) == val) return i; } - if (alloc && __has_cursum_space(journal, 1, NAT_JOURNAL)) + if (alloc && __has_cursum_space(sbi, journal, 1, NAT_JOURNAL)) return update_nats_in_cursum(journal, 1); } else if (type == SIT_JOURNAL) { for (i = 0; i < sits_in_cursum(journal); i++) if (le32_to_cpu(segno_in_journal(journal, i)) == val) return i; - if (alloc && __has_cursum_space(journal, 1, SIT_JOURNAL)) + if (alloc && __has_cursum_space(sbi, journal, 1, SIT_JOURNAL)) return update_sits_in_cursum(journal, 1); } return -1; @@ -4690,8 +4717,8 @@ void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) * entries, remove all entries from journal and add and account * them in sit entry set. */ - if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL) || - !to_journal) + if (!__has_cursum_space(sbi, journal, + sit_i->dirty_sentries, SIT_JOURNAL) || !to_journal) remove_sits_in_journal(sbi); /* @@ -4708,7 +4735,8 @@ void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned int segno = start_segno; if (to_journal && - !__has_cursum_space(journal, ses->entry_cnt, SIT_JOURNAL)) + !__has_cursum_space(sbi, journal, ses->entry_cnt, + SIT_JOURNAL)) to_journal = false; if (to_journal) { @@ -4736,7 +4764,7 @@ void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) } if (to_journal) { - offset = f2fs_lookup_journal_in_cursum(journal, + offset = f2fs_lookup_journal_in_cursum(sbi, journal, SIT_JOURNAL, segno, 1); f2fs_bug_on(sbi, offset < 0); segno_in_journal(journal, offset) = @@ -4943,12 +4971,13 @@ static int build_curseg(struct f2fs_sb_info *sbi) for (i = 0; i < NO_CHECK_TYPE; i++) { mutex_init(&array[i].curseg_mutex); - array[i].sum_blk = f2fs_kzalloc(sbi, PAGE_SIZE, GFP_KERNEL); + array[i].sum_blk = f2fs_kzalloc(sbi, sbi->sum_blocksize, + GFP_KERNEL); if (!array[i].sum_blk) return -ENOMEM; init_rwsem(&array[i].journal_rwsem); array[i].journal = f2fs_kzalloc(sbi, - sizeof(struct f2fs_journal), GFP_KERNEL); + sbi->sum_journal_size, GFP_KERNEL); if (!array[i].journal) return -ENOMEM; array[i].seg_type = log_type_to_seg_type(i); diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 1ce2c8abaf4888..d05d133c89aff8 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -85,8 +85,11 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi, #define GET_ZONE_FROM_SEG(sbi, segno) \ GET_ZONE_FROM_SEC(sbi, GET_SEC_FROM_SEG(sbi, segno)) -#define GET_SUM_BLOCK(sbi, segno) \ - ((sbi)->sm_info->ssa_blkaddr + (segno)) +#define GET_SUM_BLOCK(sbi, segno) \ + (SM_I(sbi)->ssa_blkaddr + (segno / (sbi)->sums_per_block)) +#define GET_SUM_BLKOFF(sbi, segno) (segno % (sbi)->sums_per_block) +#define SUM_BLK_PAGE_ADDR(sbi, folio, segno) \ + (folio_address(folio) + GET_SUM_BLKOFF(sbi, segno) * (sbi)->sum_blocksize) #define GET_SUM_TYPE(footer) ((footer)->entry_type) #define SET_SUM_TYPE(footer, type) ((footer)->entry_type = (type)) @@ -603,10 +606,12 @@ static inline int reserved_sections(struct f2fs_sb_info *sbi) static inline unsigned int get_left_section_blocks(struct f2fs_sb_info *sbi, enum log_type type, unsigned int segno) { - if (f2fs_lfs_mode(sbi) && __is_large_section(sbi)) - return CAP_BLKS_PER_SEC(sbi) - SEGS_TO_BLKS(sbi, - (segno - GET_START_SEG_FROM_SEC(sbi, segno))) - + if (f2fs_lfs_mode(sbi)) { + unsigned int used_blocks = __is_large_section(sbi) ? SEGS_TO_BLKS(sbi, + (segno - GET_START_SEG_FROM_SEC(sbi, segno))) : 0; + return CAP_BLKS_PER_SEC(sbi) - used_blocks - CURSEG_I(sbi, type)->next_blkoff; + } return CAP_BLKS_PER_SEC(sbi) - get_ckpt_valid_blocks(sbi, segno, true); } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index db7afb8064115c..907f632193abf0 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1759,6 +1759,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) atomic_set(&fi->dirty_pages, 0); atomic_set(&fi->i_compr_blocks, 0); atomic_set(&fi->open_count, 0); + atomic_set(&fi->writeback, 0); init_f2fs_rwsem(&fi->i_sem); spin_lock_init(&fi->i_size_lock); INIT_LIST_HEAD(&fi->dirty_list); @@ -1988,14 +1989,6 @@ static void f2fs_put_super(struct super_block *sb) truncate_inode_pages_final(META_MAPPING(sbi)); } - for (i = 0; i < NR_COUNT_TYPE; i++) { - if (!get_pages(sbi, i)) - continue; - f2fs_err(sbi, "detect filesystem reference count leak during " - "umount, type: %d, count: %lld", i, get_pages(sbi, i)); - f2fs_bug_on(sbi, 1); - } - f2fs_bug_on(sbi, sbi->fsync_node_num); f2fs_destroy_compress_inode(sbi); @@ -2006,6 +1999,15 @@ static void f2fs_put_super(struct super_block *sb) iput(sbi->meta_inode); sbi->meta_inode = NULL; + /* Should check the page counts after dropping all node/meta pages */ + for (i = 0; i < NR_COUNT_TYPE; i++) { + if (!get_pages(sbi, i)) + continue; + f2fs_err(sbi, "detect filesystem reference count leak during " + "umount, type: %d, count: %lld", i, get_pages(sbi, i)); + f2fs_bug_on(sbi, 1); + } + /* * iput() can update stat information, if f2fs_write_checkpoint() * above failed with error. @@ -2026,7 +2028,6 @@ static void f2fs_put_super(struct super_block *sb) kfree(sbi->raw_super); f2fs_destroy_page_array_cache(sbi); - f2fs_destroy_xattr_caches(sbi); #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) kfree(F2FS_OPTION(sbi).s_qf_names[i]); @@ -2632,10 +2633,11 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) return err; } -static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi) +static int f2fs_enable_checkpoint(struct f2fs_sb_info *sbi) { unsigned int nr_pages = get_pages(sbi, F2FS_DIRTY_DATA) / 16; long long start, writeback, end; + int ret; f2fs_info(sbi, "f2fs_enable_checkpoint() starts, meta: %lld, node: %lld, data: %lld", get_pages(sbi, F2FS_DIRTY_META), @@ -2669,7 +2671,9 @@ static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi) set_sbi_flag(sbi, SBI_IS_DIRTY); f2fs_up_write(&sbi->gc_lock); - f2fs_sync_fs(sbi->sb, 1); + ret = f2fs_sync_fs(sbi->sb, 1); + if (ret) + f2fs_err(sbi, "%s sync_fs failed, ret: %d", __func__, ret); /* Let's ensure there's no pending checkpoint anymore */ f2fs_flush_ckpt_thread(sbi); @@ -2679,6 +2683,7 @@ static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi) f2fs_info(sbi, "f2fs_enable_checkpoint() finishes, writeback:%llu, sync:%llu", ktime_ms_delta(writeback, start), ktime_ms_delta(end, writeback)); + return ret; } static int __f2fs_remount(struct fs_context *fc, struct super_block *sb) @@ -2892,7 +2897,9 @@ static int __f2fs_remount(struct fs_context *fc, struct super_block *sb) goto restore_discard; need_enable_checkpoint = true; } else { - f2fs_enable_checkpoint(sbi); + err = f2fs_enable_checkpoint(sbi); + if (err) + goto restore_discard; need_disable_checkpoint = true; } } @@ -2935,7 +2942,8 @@ static int __f2fs_remount(struct fs_context *fc, struct super_block *sb) return 0; restore_checkpoint: if (need_enable_checkpoint) { - f2fs_enable_checkpoint(sbi); + if (f2fs_enable_checkpoint(sbi)) + f2fs_warn(sbi, "checkpoint has not been enabled"); } else if (need_disable_checkpoint) { if (f2fs_disable_checkpoint(sbi)) f2fs_warn(sbi, "checkpoint has not been disabled"); @@ -4261,6 +4269,18 @@ static void init_sb_info(struct f2fs_sb_info *sbi) spin_lock_init(&sbi->gc_remaining_trials_lock); atomic64_set(&sbi->current_atomic_write, 0); + sbi->sum_blocksize = f2fs_sb_has_packed_ssa(sbi) ? + 4096 : sbi->blocksize; + sbi->sums_per_block = sbi->blocksize / sbi->sum_blocksize; + sbi->entries_in_sum = sbi->sum_blocksize / 8; + sbi->sum_entry_size = SUMMARY_SIZE * sbi->entries_in_sum; + sbi->sum_journal_size = sbi->sum_blocksize - SUM_FOOTER_SIZE - + sbi->sum_entry_size; + sbi->nat_journal_entries = (sbi->sum_journal_size - 2) / + sizeof(struct nat_journal_entry); + sbi->sit_journal_entries = (sbi->sum_journal_size - 2) / + sizeof(struct sit_journal_entry); + sbi->dir_level = DEF_DIR_LEVEL; sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL; sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL; @@ -4544,48 +4564,7 @@ void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag) spin_unlock_irqrestore(&sbi->error_lock, flags); } -static bool f2fs_update_errors(struct f2fs_sb_info *sbi) -{ - unsigned long flags; - bool need_update = false; - - spin_lock_irqsave(&sbi->error_lock, flags); - if (sbi->error_dirty) { - memcpy(F2FS_RAW_SUPER(sbi)->s_errors, sbi->errors, - MAX_F2FS_ERRORS); - sbi->error_dirty = false; - need_update = true; - } - spin_unlock_irqrestore(&sbi->error_lock, flags); - - return need_update; -} - -static void f2fs_record_errors(struct f2fs_sb_info *sbi, unsigned char error) -{ - int err; - - f2fs_down_write(&sbi->sb_lock); - - if (!f2fs_update_errors(sbi)) - goto out_unlock; - - err = f2fs_commit_super(sbi, false); - if (err) - f2fs_err_ratelimited(sbi, - "f2fs_commit_super fails to record errors:%u, err:%d", - error, err); -out_unlock: - f2fs_up_write(&sbi->sb_lock); -} - void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error) -{ - f2fs_save_errors(sbi, error); - f2fs_record_errors(sbi, error); -} - -void f2fs_handle_error_async(struct f2fs_sb_info *sbi, unsigned char error) { f2fs_save_errors(sbi, error); @@ -5015,13 +4994,9 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) if (err) goto free_iostat; - /* init per sbi slab cache */ - err = f2fs_init_xattr_caches(sbi); - if (err) - goto free_percpu; err = f2fs_init_page_array_cache(sbi); if (err) - goto free_xattr_cache; + goto free_percpu; /* get an inode for meta space */ sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi)); @@ -5226,11 +5201,15 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) } } else { err = f2fs_recover_fsync_data(sbi, true); - - if (!f2fs_readonly(sb) && err > 0) { - err = -EINVAL; - f2fs_err(sbi, "Need to recover fsync data"); - goto free_meta; + if (err > 0) { + if (!f2fs_readonly(sb)) { + f2fs_err(sbi, "Need to recover fsync data"); + err = -EINVAL; + goto free_meta; + } else { + f2fs_info(sbi, "drop all fsynced data"); + err = 0; + } } } @@ -5257,13 +5236,12 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) if (err) goto sync_free_meta; - if (test_opt(sbi, DISABLE_CHECKPOINT)) { + if (test_opt(sbi, DISABLE_CHECKPOINT)) err = f2fs_disable_checkpoint(sbi); - if (err) - goto sync_free_meta; - } else if (is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)) { - f2fs_enable_checkpoint(sbi); - } + else if (is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)) + err = f2fs_enable_checkpoint(sbi); + if (err) + goto sync_free_meta; /* * If filesystem is not mounted as read-only then @@ -5350,8 +5328,6 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) sbi->meta_inode = NULL; free_page_array_cache: f2fs_destroy_page_array_cache(sbi); -free_xattr_cache: - f2fs_destroy_xattr_caches(sbi); free_percpu: destroy_percpu_info(sbi); free_iostat: @@ -5554,10 +5530,15 @@ static int __init init_f2fs_fs(void) err = f2fs_create_casefold_cache(); if (err) goto free_compress_cache; - err = register_filesystem(&f2fs_fs_type); + err = f2fs_init_xattr_cache(); if (err) goto free_casefold_cache; + err = register_filesystem(&f2fs_fs_type); + if (err) + goto free_xattr_cache; return 0; +free_xattr_cache: + f2fs_destroy_xattr_cache(); free_casefold_cache: f2fs_destroy_casefold_cache(); free_compress_cache: @@ -5598,6 +5579,7 @@ static int __init init_f2fs_fs(void) static void __exit exit_f2fs_fs(void) { unregister_filesystem(&f2fs_fs_type); + f2fs_destroy_xattr_cache(); f2fs_destroy_casefold_cache(); f2fs_destroy_compress_cache(); f2fs_destroy_compress_mempool(); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 6d2a4fba68a29f..c6fa8f74b91c2c 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -58,6 +58,7 @@ struct f2fs_attr { const char *buf, size_t len); int struct_type; int offset; + int size; int id; }; @@ -235,6 +236,9 @@ static ssize_t features_show(struct f2fs_attr *a, if (f2fs_sb_has_compression(sbi)) len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "compression"); + if (f2fs_sb_has_packed_ssa(sbi)) + len += sysfs_emit_at(buf, len, "%s%s", + len ? ", " : "", "packed_ssa"); len += sysfs_emit_at(buf, len, "%s%s", len ? ", " : "", "pin_file"); len += sysfs_emit_at(buf, len, "\n"); @@ -341,11 +345,30 @@ static ssize_t main_blkaddr_show(struct f2fs_attr *a, (unsigned long long)MAIN_BLKADDR(sbi)); } +static ssize_t __sbi_show_value(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf, + unsigned char *value) +{ + switch (a->size) { + case 1: + return sysfs_emit(buf, "%u\n", *(u8 *)value); + case 2: + return sysfs_emit(buf, "%u\n", *(u16 *)value); + case 4: + return sysfs_emit(buf, "%u\n", *(u32 *)value); + case 8: + return sysfs_emit(buf, "%llu\n", *(u64 *)value); + default: + f2fs_bug_on(sbi, 1); + return sysfs_emit(buf, + "show sysfs node value with wrong type\n"); + } +} + static ssize_t f2fs_sbi_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { unsigned char *ptr = NULL; - unsigned int *ui; ptr = __struct_ptr(sbi, a->struct_type); if (!ptr) @@ -425,9 +448,30 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a, atomic_read(&sbi->cp_call_count[BACKGROUND])); #endif - ui = (unsigned int *)(ptr + a->offset); + return __sbi_show_value(a, sbi, buf, ptr + a->offset); +} - return sysfs_emit(buf, "%u\n", *ui); +static void __sbi_store_value(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, + unsigned char *ui, unsigned long value) +{ + switch (a->size) { + case 1: + *(u8 *)ui = value; + break; + case 2: + *(u16 *)ui = value; + break; + case 4: + *(u32 *)ui = value; + break; + case 8: + *(u64 *)ui = value; + break; + default: + f2fs_bug_on(sbi, 1); + f2fs_err(sbi, "store sysfs node value with wrong type"); + } } static ssize_t __sbi_store(struct f2fs_attr *a, @@ -746,7 +790,7 @@ static ssize_t __sbi_store(struct f2fs_attr *a, return count; } - if (!strcmp(a->attr.name, "gc_pin_file_threshold")) { + if (!strcmp(a->attr.name, "gc_pin_file_thresh")) { if (t > MAX_GC_FAILED_PINNED_FILES) return -EINVAL; sbi->gc_pin_file_threshold = t; @@ -903,7 +947,7 @@ static ssize_t __sbi_store(struct f2fs_attr *a, return count; } - *ui = (unsigned int)t; + __sbi_store_value(a, sbi, ptr + a->offset, t); return count; } @@ -1050,24 +1094,27 @@ static struct f2fs_attr f2fs_attr_sb_##_name = { \ .id = F2FS_FEATURE_##_feat, \ } -#define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \ +#define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset, _size) \ static struct f2fs_attr f2fs_attr_##_name = { \ .attr = {.name = __stringify(_name), .mode = _mode }, \ .show = _show, \ .store = _store, \ .struct_type = _struct_type, \ - .offset = _offset \ + .offset = _offset, \ + .size = _size \ } #define F2FS_RO_ATTR(struct_type, struct_name, name, elname) \ F2FS_ATTR_OFFSET(struct_type, name, 0444, \ f2fs_sbi_show, NULL, \ - offsetof(struct struct_name, elname)) + offsetof(struct struct_name, elname), \ + sizeof_field(struct struct_name, elname)) #define F2FS_RW_ATTR(struct_type, struct_name, name, elname) \ F2FS_ATTR_OFFSET(struct_type, name, 0644, \ f2fs_sbi_show, f2fs_sbi_store, \ - offsetof(struct struct_name, elname)) + offsetof(struct struct_name, elname), \ + sizeof_field(struct struct_name, elname)) #define F2FS_GENERAL_RO_ATTR(name) \ static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL) @@ -1296,6 +1343,7 @@ F2FS_FEATURE_RO_ATTR(pin_file); #ifdef CONFIG_UNICODE F2FS_FEATURE_RO_ATTR(linear_lookup); #endif +F2FS_FEATURE_RO_ATTR(packed_ssa); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -1455,6 +1503,7 @@ static struct attribute *f2fs_feat_attrs[] = { #ifdef CONFIG_UNICODE BASE_ATTR_LIST(linear_lookup), #endif + BASE_ATTR_LIST(packed_ssa), NULL, }; ATTRIBUTE_GROUPS(f2fs_feat); @@ -1490,6 +1539,7 @@ F2FS_SB_FEATURE_RO_ATTR(casefold, CASEFOLD); F2FS_SB_FEATURE_RO_ATTR(compression, COMPRESSION); F2FS_SB_FEATURE_RO_ATTR(readonly, RO); F2FS_SB_FEATURE_RO_ATTR(device_alias, DEVICE_ALIAS); +F2FS_SB_FEATURE_RO_ATTR(packed_ssa, PACKED_SSA); static struct attribute *f2fs_sb_feat_attrs[] = { ATTR_LIST(sb_encryption), @@ -1507,6 +1557,7 @@ static struct attribute *f2fs_sb_feat_attrs[] = { ATTR_LIST(sb_compression), ATTR_LIST(sb_readonly), ATTR_LIST(sb_device_alias), + ATTR_LIST(sb_packed_ssa), NULL, }; ATTRIBUTE_GROUPS(f2fs_sb_feat); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 58632a2b66136c..b4e5c406632f81 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -23,11 +23,12 @@ #include "xattr.h" #include "segment.h" +static struct kmem_cache *inline_xattr_slab; static void *xattr_alloc(struct f2fs_sb_info *sbi, int size, bool *is_inline) { - if (likely(size == sbi->inline_xattr_slab_size)) { + if (likely(size == DEFAULT_XATTR_SLAB_SIZE)) { *is_inline = true; - return f2fs_kmem_cache_alloc(sbi->inline_xattr_slab, + return f2fs_kmem_cache_alloc(inline_xattr_slab, GFP_F2FS_ZERO, false, sbi); } *is_inline = false; @@ -38,7 +39,7 @@ static void xattr_free(struct f2fs_sb_info *sbi, void *xattr_addr, bool is_inline) { if (is_inline) - kmem_cache_free(sbi->inline_xattr_slab, xattr_addr); + kmem_cache_free(inline_xattr_slab, xattr_addr); else kfree(xattr_addr); } @@ -830,25 +831,14 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, return err; } -int f2fs_init_xattr_caches(struct f2fs_sb_info *sbi) +int __init f2fs_init_xattr_cache(void) { - dev_t dev = sbi->sb->s_bdev->bd_dev; - char slab_name[32]; - - sprintf(slab_name, "f2fs_xattr_entry-%u:%u", MAJOR(dev), MINOR(dev)); - - sbi->inline_xattr_slab_size = F2FS_OPTION(sbi).inline_xattr_size * - sizeof(__le32) + XATTR_PADDING_SIZE; - - sbi->inline_xattr_slab = f2fs_kmem_cache_create(slab_name, - sbi->inline_xattr_slab_size); - if (!sbi->inline_xattr_slab) - return -ENOMEM; - - return 0; + inline_xattr_slab = f2fs_kmem_cache_create("f2fs_xattr_entry", + DEFAULT_XATTR_SLAB_SIZE); + return inline_xattr_slab ? 0 : -ENOMEM; } -void f2fs_destroy_xattr_caches(struct f2fs_sb_info *sbi) +void f2fs_destroy_xattr_cache(void) { - kmem_cache_destroy(sbi->inline_xattr_slab); -} + kmem_cache_destroy(inline_xattr_slab); +} \ No newline at end of file diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 4fc0b2305fbd80..bce3d93e4755b5 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -89,6 +89,8 @@ struct f2fs_xattr_entry { F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - \ DEF_INLINE_RESERVED_SIZE - \ MIN_INLINE_DENTRY_SIZE / sizeof(__le32)) +#define DEFAULT_XATTR_SLAB_SIZE (DEFAULT_INLINE_XATTR_ADDRS * \ + sizeof(__le32) + XATTR_PADDING_SIZE) /* * On-disk structure of f2fs_xattr @@ -132,8 +134,8 @@ int f2fs_setxattr(struct inode *, int, const char *, const void *, int f2fs_getxattr(struct inode *, int, const char *, void *, size_t, struct folio *); ssize_t f2fs_listxattr(struct dentry *, char *, size_t); -int f2fs_init_xattr_caches(struct f2fs_sb_info *); -void f2fs_destroy_xattr_caches(struct f2fs_sb_info *); +int __init f2fs_init_xattr_cache(void); +void f2fs_destroy_xattr_cache(void); #else #define f2fs_xattr_handlers NULL @@ -150,8 +152,8 @@ static inline int f2fs_getxattr(struct inode *inode, int index, { return -EOPNOTSUPP; } -static inline int f2fs_init_xattr_caches(struct f2fs_sb_info *sbi) { return 0; } -static inline void f2fs_destroy_xattr_caches(struct f2fs_sb_info *sbi) { } +static inline int __init f2fs_init_xattr_cache(void) { return 0; } +static inline void f2fs_destroy_xattr_cache(void) { } #endif #ifdef CONFIG_F2FS_FS_SECURITY diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index 0b920ee40a7f9f..262ec1b790b560 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -325,7 +325,12 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry) err = fat_remove_entries(dir, &sinfo); /* and releases bh */ if (err) goto out; - drop_nlink(dir); + if (dir->i_nlink >= 3) + drop_nlink(dir); + else { + fat_fs_error(sb, "parent dir link count too low (%u)", + dir->i_nlink); + } clear_nlink(inode); fat_truncate_time(inode, NULL, S_CTIME); diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 5dbc4cbb8fce3d..47ff083cfc7e66 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -803,7 +803,12 @@ static int vfat_rmdir(struct inode *dir, struct dentry *dentry) err = fat_remove_entries(dir, &sinfo); /* and releases bh */ if (err) goto out; - drop_nlink(dir); + if (dir->i_nlink >= 3) + drop_nlink(dir); + else { + fat_fs_error(sb, "parent dir link count too low (%u)", + dir->i_nlink); + } clear_nlink(inode); fat_truncate_time(inode, NULL, S_ATIME|S_MTIME); diff --git a/fs/file_table.c b/fs/file_table.c index cd4a3db4659ac4..34244fccf2edf0 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -176,6 +176,11 @@ static int init_file(struct file *f, int flags, const struct cred *cred) f->f_flags = flags; f->f_mode = OPEN_FMODE(flags); + /* + * Disable permission and pre-content events for all files by default. + * They may be enabled later by fsnotify_open_perm_and_set_mode(). + */ + file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM); f->f_op = NULL; f->f_mapping = NULL; @@ -197,11 +202,6 @@ static int init_file(struct file *f, int flags, const struct cred *cred) * refcount bumps we should reinitialize the reused file first. */ file_ref_init(&f->f_ref, 1); - /* - * Disable permission and pre-content events for all files by default. - * They may be enabled later by fsnotify_open_perm_and_set_mode(). - */ - file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM); return 0; } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 2b35e80037feed..21b6adee03dfb8 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2471,7 +2471,8 @@ static void wakeup_dirtytime_writeback(struct work_struct *w) wb_wakeup(wb); } rcu_read_unlock(); - schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); + if (dirtytime_expire_interval) + schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); } static int dirtytime_interval_handler(const struct ctl_table *table, int write, @@ -2480,8 +2481,12 @@ static int dirtytime_interval_handler(const struct ctl_table *table, int write, int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (ret == 0 && write) - mod_delayed_work(system_percpu_wq, &dirtytime_work, 0); + if (ret == 0 && write) { + if (dirtytime_expire_interval) + mod_delayed_work(system_percpu_wq, &dirtytime_work, 0); + else + cancel_delayed_work_sync(&dirtytime_work); + } return ret; } @@ -2498,7 +2503,8 @@ static const struct ctl_table vm_fs_writeback_table[] = { static int __init start_dirtytime_writeback(void) { - schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); + if (dirtytime_expire_interval) + schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); register_sysctl_init("vm", vm_fs_writeback_table); return 0; } @@ -2729,8 +2735,13 @@ static void wait_sb_inodes(struct super_block *sb) * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. + * + * If the mapping does not have data integrity semantics, + * there's no need to wait for the writeout to complete, as the + * mapping cannot guarantee that data is persistently stored. */ - if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) + if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK) || + mapping_no_data_integrity(mapping)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); diff --git a/fs/fs_struct.c b/fs/fs_struct.c index 28be762ac1c637..a0b40ad5e7423e 100644 --- a/fs/fs_struct.c +++ b/fs/fs_struct.c @@ -6,6 +6,7 @@ #include #include #include +#include #include "internal.h" /* diff --git a/fs/fuse/control.c b/fs/fuse/control.c index bb407705603c29..5247df896c5d01 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -205,8 +205,7 @@ static const struct file_operations fuse_conn_congestion_threshold_ops = { static struct dentry *fuse_ctl_add_dentry(struct dentry *parent, struct fuse_conn *fc, - const char *name, - int mode, int nlink, + const char *name, int mode, const struct inode_operations *iop, const struct file_operations *fop) { @@ -232,7 +231,10 @@ static struct dentry *fuse_ctl_add_dentry(struct dentry *parent, if (iop) inode->i_op = iop; inode->i_fop = fop; - set_nlink(inode, nlink); + if (S_ISDIR(mode)) { + inc_nlink(d_inode(parent)); + inc_nlink(inode); + } inode->i_private = fc; d_add(dentry, inode); @@ -252,22 +254,21 @@ int fuse_ctl_add_conn(struct fuse_conn *fc) return 0; parent = fuse_control_sb->s_root; - inc_nlink(d_inode(parent)); sprintf(name, "%u", fc->dev); - parent = fuse_ctl_add_dentry(parent, fc, name, S_IFDIR | 0500, 2, + parent = fuse_ctl_add_dentry(parent, fc, name, S_IFDIR | 0500, &simple_dir_inode_operations, &simple_dir_operations); if (!parent) goto err; - if (!fuse_ctl_add_dentry(parent, fc, "waiting", S_IFREG | 0400, 1, + if (!fuse_ctl_add_dentry(parent, fc, "waiting", S_IFREG | 0400, NULL, &fuse_ctl_waiting_ops) || - !fuse_ctl_add_dentry(parent, fc, "abort", S_IFREG | 0200, 1, + !fuse_ctl_add_dentry(parent, fc, "abort", S_IFREG | 0200, NULL, &fuse_ctl_abort_ops) || !fuse_ctl_add_dentry(parent, fc, "max_background", S_IFREG | 0600, - 1, NULL, &fuse_conn_max_background_ops) || + NULL, &fuse_conn_max_background_ops) || !fuse_ctl_add_dentry(parent, fc, "congestion_threshold", - S_IFREG | 0600, 1, NULL, + S_IFREG | 0600, NULL, &fuse_conn_congestion_threshold_ops)) goto err; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 132f38619d7072..49b18d7accb399 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -846,7 +846,7 @@ void fuse_copy_init(struct fuse_copy_state *cs, bool write, } /* Unmap and put previous page of userspace buffer */ -static void fuse_copy_finish(struct fuse_copy_state *cs) +void fuse_copy_finish(struct fuse_copy_state *cs) { if (cs->currbuf) { struct pipe_buffer *buf = cs->currbuf; diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c index f6b12aebb8bbe7..f0846694822ddf 100644 --- a/fs/fuse/dev_uring.c +++ b/fs/fuse/dev_uring.c @@ -86,6 +86,7 @@ static void fuse_uring_req_end(struct fuse_ring_ent *ent, struct fuse_req *req, lockdep_assert_not_held(&queue->lock); spin_lock(&queue->lock); ent->fuse_req = NULL; + list_del_init(&req->list); if (test_bit(FR_BACKGROUND, &req->flags)) { queue->active_background--; spin_lock(&fc->bg_lock); @@ -598,7 +599,9 @@ static int fuse_uring_copy_from_ring(struct fuse_ring *ring, cs.is_uring = true; cs.req = req; - return fuse_copy_out_args(&cs, args, ring_in_out.payload_sz); + err = fuse_copy_out_args(&cs, args, ring_in_out.payload_sz); + fuse_copy_finish(&cs); + return err; } /* @@ -649,6 +652,7 @@ static int fuse_uring_args_to_ring(struct fuse_ring *ring, struct fuse_req *req, /* copy the payload */ err = fuse_copy_args(&cs, num_args, args->in_pages, (struct fuse_arg *)in_args, 0); + fuse_copy_finish(&cs); if (err) { pr_info_ratelimited("%s fuse_copy_args failed\n", __func__); return err; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index f1ef77a0be05bb..37620fdd02055e 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -110,7 +110,9 @@ static void fuse_file_put(struct fuse_file *ff, bool sync) fuse_file_io_release(ff, ra->inode); if (!args) { - /* Do nothing when server does not implement 'open' */ + /* Do nothing when server does not implement 'opendir' */ + } else if (args->opcode == FUSE_RELEASE && ff->fm->fc->no_open) { + fuse_release_end(ff->fm, args, 0); } else if (sync) { fuse_simple_request(ff->fm, args); fuse_release_end(ff->fm, args, 0); @@ -131,8 +133,17 @@ struct fuse_file *fuse_file_open(struct fuse_mount *fm, u64 nodeid, struct fuse_file *ff; int opcode = isdir ? FUSE_OPENDIR : FUSE_OPEN; bool open = isdir ? !fc->no_opendir : !fc->no_open; + bool release = !isdir || open; - ff = fuse_file_alloc(fm, open); + /* + * ff->args->release_args still needs to be allocated (so we can hold an + * inode reference while there are pending inflight file operations when + * ->release() is called, see fuse_prepare_release()) even if + * fc->no_open is set else it becomes possible for reclaim to deadlock + * if while servicing the readahead request the server triggers reclaim + * and reclaim evicts the inode of the file being read ahead. + */ + ff = fuse_file_alloc(fm, release); if (!ff) return ERR_PTR(-ENOMEM); @@ -152,13 +163,14 @@ struct fuse_file *fuse_file_open(struct fuse_mount *fm, u64 nodeid, fuse_file_free(ff); return ERR_PTR(err); } else { - /* No release needed */ - kfree(ff->args); - ff->args = NULL; - if (isdir) + if (isdir) { + /* No release needed */ + kfree(ff->args); + ff->args = NULL; fc->no_opendir = 1; - else + } else { fc->no_open = 1; + } } } @@ -1607,7 +1619,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, if (!ia) return -ENOMEM; - if (fopen_direct_io && fc->direct_io_allow_mmap) { + if (fopen_direct_io) { res = filemap_write_and_wait_range(mapping, pos, pos + count - 1); if (res) { fuse_io_free(ia); @@ -1681,6 +1693,15 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, if (res > 0) *ppos = pos; + if (res > 0 && write && fopen_direct_io) { + /* + * As in generic_file_direct_write(), invalidate after the + * write, to invalidate read-ahead cache that may have competed + * with the write. + */ + invalidate_inode_pages2_range(mapping, idx_from, idx_to); + } + return res > 0 ? res : err; } EXPORT_SYMBOL_GPL(fuse_direct_io); @@ -3125,8 +3146,10 @@ void fuse_init_file_inode(struct inode *inode, unsigned int flags) inode->i_fop = &fuse_file_operations; inode->i_data.a_ops = &fuse_file_aops; - if (fc->writeback_cache) + if (fc->writeback_cache) { mapping_set_writeback_may_deadlock_on_reclaim(&inode->i_data); + mapping_set_no_data_integrity(&inode->i_data); + } INIT_LIST_HEAD(&fi->write_files); INIT_LIST_HEAD(&fi->queued_writes); diff --git a/fs/fuse/fuse_dev_i.h b/fs/fuse/fuse_dev_i.h index 6e8373f970409e..134bf44aff0d39 100644 --- a/fs/fuse/fuse_dev_i.h +++ b/fs/fuse/fuse_dev_i.h @@ -62,6 +62,7 @@ void fuse_dev_end_requests(struct list_head *head); void fuse_copy_init(struct fuse_copy_state *cs, bool write, struct iov_iter *iter); +void fuse_copy_finish(struct fuse_copy_state *cs); int fuse_copy_args(struct fuse_copy_state *cs, unsigned int numargs, unsigned int argpages, struct fuse_arg *args, int zeroing); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 131091520de6be..fdcac8e3f2ba26 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1127,10 +1127,18 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, goto out_unlock; break; default: - goto out_unlock; + goto out; } ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap, &mp); + if (ret) + goto out_unlock; + +out: + if (iomap->type == IOMAP_INLINE) { + iomap->private = metapath_dibh(&mp); + get_bh(iomap->private); + } out_unlock: release_metapath(&mp); @@ -1144,6 +1152,9 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length, struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); + if (iomap->private) + brelse(iomap->private); + switch (flags & (IOMAP_WRITE | IOMAP_ZERO)) { case IOMAP_WRITE: if (flags & IOMAP_DIRECT) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index b677c0e6b9ab30..7aec6cfdfd91de 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1211,10 +1211,13 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, mapping = gfs2_glock2aspace(gl); if (mapping) { + gfp_t gfp_mask; + mapping->a_ops = &gfs2_meta_aops; mapping->host = sdp->sd_inode; mapping->flags = 0; - mapping_set_gfp_mask(mapping, GFP_NOFS); + gfp_mask = mapping_gfp_mask(sdp->sd_inode->i_mapping); + mapping_set_gfp_mask(mapping, gfp_mask); mapping->i_private_data = NULL; mapping->writeback_index = 0; } @@ -1351,31 +1354,45 @@ static int glocks_pending(unsigned int num_gh, struct gfs2_holder *ghs) * gfs2_glock_async_wait - wait on multiple asynchronous glock acquisitions * @num_gh: the number of holders in the array * @ghs: the glock holder array + * @retries: number of retries attempted so far * * Returns: 0 on success, meaning all glocks have been granted and are held. * -ESTALE if the request timed out, meaning all glocks were released, * and the caller should retry the operation. */ -int gfs2_glock_async_wait(unsigned int num_gh, struct gfs2_holder *ghs) +int gfs2_glock_async_wait(unsigned int num_gh, struct gfs2_holder *ghs, + unsigned int retries) { struct gfs2_sbd *sdp = ghs[0].gh_gl->gl_name.ln_sbd; - int i, ret = 0, timeout = 0; unsigned long start_time = jiffies; + int i, ret = 0; + long timeout; might_sleep(); - /* - * Total up the (minimum hold time * 2) of all glocks and use that to - * determine the max amount of time we should wait. - */ - for (i = 0; i < num_gh; i++) - timeout += ghs[i].gh_gl->gl_hold_time << 1; - if (!wait_event_timeout(sdp->sd_async_glock_wait, + timeout = GL_GLOCK_MIN_HOLD; + if (retries) { + unsigned int max_shift; + long incr; + + /* Add a random delay and increase the timeout exponentially. */ + max_shift = BITS_PER_LONG - 2 - __fls(GL_GLOCK_HOLD_INCR); + incr = min(GL_GLOCK_HOLD_INCR << min(retries - 1, max_shift), + 10 * HZ - GL_GLOCK_MIN_HOLD); + schedule_timeout_interruptible(get_random_long() % (incr / 3)); + if (signal_pending(current)) + goto interrupted; + timeout += (incr / 3) + get_random_long() % (incr / 3); + } + + if (!wait_event_interruptible_timeout(sdp->sd_async_glock_wait, !glocks_pending(num_gh, ghs), timeout)) { ret = -ESTALE; /* request timed out. */ goto out; } + if (signal_pending(current)) + goto interrupted; for (i = 0; i < num_gh; i++) { struct gfs2_holder *gh = &ghs[i]; @@ -1399,6 +1416,10 @@ int gfs2_glock_async_wait(unsigned int num_gh, struct gfs2_holder *ghs) } } return ret; + +interrupted: + ret = -EINTR; + goto out; } /** diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index d041b922b45e3b..2d4fd1a2bbbb87 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -204,7 +204,8 @@ int gfs2_glock_poll(struct gfs2_holder *gh); int gfs2_instantiate(struct gfs2_holder *gh); int gfs2_glock_holder_ready(struct gfs2_holder *gh); int gfs2_glock_wait(struct gfs2_holder *gh); -int gfs2_glock_async_wait(unsigned int num_gh, struct gfs2_holder *ghs); +int gfs2_glock_async_wait(unsigned int num_gh, struct gfs2_holder *ghs, + unsigned int retries); void gfs2_glock_dq(struct gfs2_holder *gh); void gfs2_glock_dq_wait(struct gfs2_holder *gh); void gfs2_glock_dq_uninit(struct gfs2_holder *gh); diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 0c0a80b3bacab2..0c68ab4432b08a 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -630,8 +630,7 @@ static void iopen_go_callback(struct gfs2_glock *gl, bool remote) struct gfs2_inode *ip = gl->gl_object; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - if (!remote || sb_rdonly(sdp->sd_vfs) || - test_bit(SDF_KILL, &sdp->sd_flags)) + if (!remote || test_bit(SDF_KILL, &sdp->sd_flags)) return; if (gl->gl_demote_state == LM_ST_UNLOCKED && diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 8a7ed80d9f2d6e..63d9fe74643441 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -89,6 +89,19 @@ static int iget_set(struct inode *inode, void *opaque) return 0; } +void gfs2_setup_inode(struct inode *inode) +{ + gfp_t gfp_mask; + + /* + * Ensure all page cache allocations are done from GFP_NOFS context to + * prevent direct reclaim recursion back into the filesystem and blowing + * stacks or deadlocking. + */ + gfp_mask = mapping_gfp_mask(inode->i_mapping); + mapping_set_gfp_mask(inode->i_mapping, gfp_mask & ~__GFP_FS); +} + /** * gfs2_inode_lookup - Lookup an inode * @sb: The super block @@ -132,6 +145,7 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, struct gfs2_glock *io_gl; int extra_flags = 0; + gfs2_setup_inode(inode); error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); if (unlikely(error)) @@ -752,6 +766,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = -ENOMEM; if (!inode) goto fail_gunlock; + gfs2_setup_inode(inode); ip = GFS2_I(inode); error = posix_acl_create(dir, &mode, &default_acl, &acl); @@ -1480,7 +1495,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, unsigned int num_gh; int dir_rename = 0; struct gfs2_diradd da = { .nr_blocks = 0, .save_loc = 0, }; - unsigned int x; + unsigned int retries = 0, x; int error; gfs2_holder_mark_uninitialized(&r_gh); @@ -1530,12 +1545,17 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, num_gh++; } +again: for (x = 0; x < num_gh; x++) { error = gfs2_glock_nq(ghs + x); if (error) goto out_gunlock; } - error = gfs2_glock_async_wait(num_gh, ghs); + error = gfs2_glock_async_wait(num_gh, ghs, retries); + if (error == -ESTALE) { + retries++; + goto again; + } if (error) goto out_gunlock; @@ -1724,7 +1744,7 @@ static int gfs2_exchange(struct inode *odir, struct dentry *odentry, struct gfs2_sbd *sdp = GFS2_SB(odir); struct gfs2_holder ghs[4], r_gh; unsigned int num_gh; - unsigned int x; + unsigned int retries = 0, x; umode_t old_mode = oip->i_inode.i_mode; umode_t new_mode = nip->i_inode.i_mode; int error; @@ -1768,13 +1788,18 @@ static int gfs2_exchange(struct inode *odir, struct dentry *odentry, gfs2_holder_init(nip->i_gl, LM_ST_EXCLUSIVE, GL_ASYNC, ghs + num_gh); num_gh++; +again: for (x = 0; x < num_gh; x++) { error = gfs2_glock_nq(ghs + x); if (error) goto out_gunlock; } - error = gfs2_glock_async_wait(num_gh, ghs); + error = gfs2_glock_async_wait(num_gh, ghs, retries); + if (error == -ESTALE) { + retries++; + goto again; + } if (error) goto out_gunlock; diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index e43f08eb26e729..2fcd96dd136139 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -86,6 +86,7 @@ static inline int gfs2_check_internal_file_size(struct inode *inode, return -EIO; } +void gfs2_setup_inode(struct inode *inode); struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, u64 no_addr, u64 no_formal_ino, unsigned int blktype); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index aa15183f9a168e..1a2db8053da04c 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1183,7 +1183,7 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc) mapping = gfs2_aspace(sdp); mapping->a_ops = &gfs2_rgrp_aops; - mapping_set_gfp_mask(mapping, GFP_NOFS); + gfs2_setup_inode(sdp->sd_inode); error = init_names(sdp, silent); if (error) diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 2298e06797ac38..898fc3937b4497 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -334,6 +334,7 @@ static void qd_put(struct gfs2_quota_data *qd) lockref_mark_dead(&qd->qd_lockref); spin_unlock(&qd->qd_lockref.lock); + list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru); gfs2_qd_dispose(qd); return; } @@ -1616,7 +1617,7 @@ int gfs2_quotad(void *data) t = min(quotad_timeo, statfs_timeo); - t = wait_event_freezable_timeout(sdp->sd_quota_wait, + t -= wait_event_freezable_timeout(sdp->sd_quota_wait, sdp->sd_statfs_force_sync || gfs2_withdrawing_or_withdrawn(sdp) || kthread_should_stop(), diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 644b2d1e72769e..54c6f2098f01ef 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -749,9 +749,7 @@ static int gfs2_freeze_super(struct super_block *sb, enum freeze_holder who, break; } - error = gfs2_do_thaw(sdp, who, freeze_owner); - if (error) - goto out; + (void)gfs2_do_thaw(sdp, who, freeze_owner); if (error == -EBUSY) fs_err(sdp, "waiting for recovery before freeze\n"); diff --git a/fs/hfs/catalog.c b/fs/hfs/catalog.c index caebabb6642f16..b80ba40e387761 100644 --- a/fs/hfs/catalog.c +++ b/fs/hfs/catalog.c @@ -322,9 +322,9 @@ int hfs_correct_next_unused_CNID(struct super_block *sb, u32 cnid) } } + node_id = node->prev; hfs_bnode_put(node); - node_id = node->prev; } while (node_id >= leaf_head); return -ENOENT; diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index 53f3fae6021797..f28cd24dee8425 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -92,7 +92,7 @@ int hfs_mdb_get(struct super_block *sb) /* See if this is an HFS filesystem */ bh = sb_bread512(sb, part_start + HFS_MDB_BLK, mdb); if (!bh) - goto out; + return -EIO; if (mdb->drSigWord == cpu_to_be16(HFS_SUPER_MAGIC)) break; @@ -102,13 +102,14 @@ int hfs_mdb_get(struct super_block *sb) * (should do this only for cdrom/loop though) */ if (hfs_part_find(sb, &part_start, &part_size)) - goto out; + return -EIO; } HFS_SB(sb)->alloc_blksz = size = be32_to_cpu(mdb->drAlBlkSiz); if (!size || (size & (HFS_SECTOR_SIZE - 1))) { pr_err("bad allocation block size %d\n", size); - goto out_bh; + brelse(bh); + return -EIO; } size = min(HFS_SB(sb)->alloc_blksz, (u32)PAGE_SIZE); @@ -125,14 +126,16 @@ int hfs_mdb_get(struct super_block *sb) brelse(bh); if (!sb_set_blocksize(sb, size)) { pr_err("unable to set blocksize to %u\n", size); - goto out; + return -EIO; } bh = sb_bread512(sb, part_start + HFS_MDB_BLK, mdb); if (!bh) - goto out; - if (mdb->drSigWord != cpu_to_be16(HFS_SUPER_MAGIC)) - goto out_bh; + return -EIO; + if (mdb->drSigWord != cpu_to_be16(HFS_SUPER_MAGIC)) { + brelse(bh); + return -EIO; + } HFS_SB(sb)->mdb_bh = bh; HFS_SB(sb)->mdb = mdb; @@ -174,7 +177,7 @@ int hfs_mdb_get(struct super_block *sb) HFS_SB(sb)->bitmap = kzalloc(8192, GFP_KERNEL); if (!HFS_SB(sb)->bitmap) - goto out; + return -EIO; /* read in the bitmap */ block = be16_to_cpu(mdb->drVBMSt) + part_start; @@ -185,7 +188,7 @@ int hfs_mdb_get(struct super_block *sb) bh = sb_bread(sb, off >> sb->s_blocksize_bits); if (!bh) { pr_err("unable to read volume bitmap\n"); - goto out; + return -EIO; } off2 = off & (sb->s_blocksize - 1); len = min((int)sb->s_blocksize - off2, size); @@ -199,12 +202,12 @@ int hfs_mdb_get(struct super_block *sb) HFS_SB(sb)->ext_tree = hfs_btree_open(sb, HFS_EXT_CNID, hfs_ext_keycmp); if (!HFS_SB(sb)->ext_tree) { pr_err("unable to open extent tree\n"); - goto out; + return -EIO; } HFS_SB(sb)->cat_tree = hfs_btree_open(sb, HFS_CAT_CNID, hfs_cat_keycmp); if (!HFS_SB(sb)->cat_tree) { pr_err("unable to open catalog tree\n"); - goto out; + return -EIO; } attrib = mdb->drAtrb; @@ -229,12 +232,6 @@ int hfs_mdb_get(struct super_block *sb) } return 0; - -out_bh: - brelse(bh); -out: - hfs_mdb_put(sb); - return -EIO; } /* @@ -359,8 +356,6 @@ void hfs_mdb_close(struct super_block *sb) * Release the resources associated with the in-core MDB. */ void hfs_mdb_put(struct super_block *sb) { - if (!HFS_SB(sb)) - return; /* free the B-trees */ hfs_btree_close(HFS_SB(sb)->ext_tree); hfs_btree_close(HFS_SB(sb)->cat_tree); @@ -373,6 +368,4 @@ void hfs_mdb_put(struct super_block *sb) unload_nls(HFS_SB(sb)->nls_disk); kfree(HFS_SB(sb)->bitmap); - kfree(HFS_SB(sb)); - sb->s_fs_info = NULL; } diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 47f50fa555a457..df289cbdd4e85b 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -431,10 +431,18 @@ static int hfs_init_fs_context(struct fs_context *fc) return 0; } +static void hfs_kill_super(struct super_block *sb) +{ + struct hfs_sb_info *hsb = HFS_SB(sb); + + kill_block_super(sb); + kfree(hsb); +} + static struct file_system_type hfs_fs_type = { .owner = THIS_MODULE, .name = "hfs", - .kill_sb = kill_block_super, + .kill_sb = hfs_kill_super, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = hfs_init_fs_context, }; diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c index 63e652ad1e0def..8e60e04c427bd2 100644 --- a/fs/hfsplus/bnode.c +++ b/fs/hfsplus/bnode.c @@ -481,6 +481,7 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) tree->node_hash[hash] = node; tree->node_hash_cnt++; } else { + hfs_bnode_get(node2); spin_unlock(&tree->hash_lock); kfree(node); wait_event(node2->lock_wq, @@ -628,7 +629,7 @@ struct hfs_bnode *hfs_bnode_create(struct hfs_btree *tree, u32 num) if (node) { pr_crit("new node %u already hashed?\n", num); WARN_ON(1); - return node; + return ERR_PTR(-EEXIST); } node = __hfs_bnode_create(tree, num); if (!node) @@ -704,6 +705,5 @@ bool hfs_bnode_need_zeroout(struct hfs_btree *tree) struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); const u32 volume_attr = be32_to_cpu(sbi->s_vhdr->attributes); - return tree->cnid == HFSPLUS_CAT_CNID && - volume_attr & HFSPLUS_VOL_UNUSED_NODE_FIX; + return volume_attr & HFSPLUS_VOL_UNUSED_NODE_FIX; } diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 1b3e27a0d5e038..cadf0b5f93422e 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -552,8 +552,13 @@ static int hfsplus_rename(struct mnt_idmap *idmap, res = hfsplus_rename_cat((u32)(unsigned long)old_dentry->d_fsdata, old_dir, &old_dentry->d_name, new_dir, &new_dentry->d_name); - if (!res) + if (!res) { new_dentry->d_fsdata = old_dentry->d_fsdata; + + res = hfsplus_cat_write_inode(old_dir); + if (!res) + res = hfsplus_cat_write_inode(new_dir); + } return res; } diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 89e8b19c127b0a..de801942ae4713 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -477,6 +477,8 @@ int hfs_part_find(struct super_block *sb, sector_t *part_start, /* super.c */ struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino); void hfsplus_mark_mdb_dirty(struct super_block *sb); +void hfsplus_prepare_volume_header_for_commit(struct hfsplus_vh *vhdr); +int hfsplus_commit_superblock(struct super_block *sb); /* tables.c */ extern u16 hfsplus_case_fold_table[]; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index b51a411ecd2376..7ae6745ca7ae12 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -180,13 +180,29 @@ const struct dentry_operations hfsplus_dentry_operations = { .d_compare = hfsplus_compare_dentry, }; -static void hfsplus_get_perms(struct inode *inode, - struct hfsplus_perm *perms, int dir) +static int hfsplus_get_perms(struct inode *inode, + struct hfsplus_perm *perms, int dir) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb); u16 mode; mode = be16_to_cpu(perms->mode); + if (dir) { + if (mode && !S_ISDIR(mode)) + goto bad_type; + } else if (mode) { + switch (mode & S_IFMT) { + case S_IFREG: + case S_IFLNK: + case S_IFCHR: + case S_IFBLK: + case S_IFIFO: + case S_IFSOCK: + break; + default: + goto bad_type; + } + } i_uid_write(inode, be32_to_cpu(perms->owner)); if ((test_bit(HFSPLUS_SB_UID, &sbi->flags)) || (!i_uid_read(inode) && !mode)) @@ -212,6 +228,10 @@ static void hfsplus_get_perms(struct inode *inode, inode->i_flags |= S_APPEND; else inode->i_flags &= ~S_APPEND; + return 0; +bad_type: + pr_err("invalid file type 0%04o for inode %lu\n", mode, inode->i_ino); + return -EIO; } static int hfsplus_file_open(struct inode *inode, struct file *file) @@ -305,6 +325,7 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, struct inode *inode = file->f_mapping->host; struct hfsplus_inode_info *hip = HFSPLUS_I(inode); struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb); + struct hfsplus_vh *vhdr = sbi->s_vhdr; int error = 0, error2; error = file_write_and_wait_range(file, start, end); @@ -348,6 +369,14 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, error = error2; } + mutex_lock(&sbi->vh_mutex); + hfsplus_prepare_volume_header_for_commit(vhdr); + mutex_unlock(&sbi->vh_mutex); + + error2 = hfsplus_commit_superblock(inode->i_sb); + if (!error) + error = error2; + if (!test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags)) blkdev_issue_flush(inode->i_sb->s_bdev); @@ -516,7 +545,9 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) } hfs_bnode_read(fd->bnode, &entry, fd->entryoffset, sizeof(struct hfsplus_cat_folder)); - hfsplus_get_perms(inode, &folder->permissions, 1); + res = hfsplus_get_perms(inode, &folder->permissions, 1); + if (res) + goto out; set_nlink(inode, 1); inode->i_size = 2 + be32_to_cpu(folder->valence); inode_set_atime_to_ts(inode, hfsp_mt2ut(folder->access_date)); @@ -545,7 +576,9 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) hfsplus_inode_read_fork(inode, HFSPLUS_IS_RSRC(inode) ? &file->rsrc_fork : &file->data_fork); - hfsplus_get_perms(inode, &file->permissions, 0); + res = hfsplus_get_perms(inode, &file->permissions, 0); + if (res) + goto out; set_nlink(inode, 1); if (S_ISREG(inode->i_mode)) { if (file->permissions.dev) diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 16bc4abc67e08f..67a7a2a093476d 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -187,40 +187,15 @@ static void hfsplus_evict_inode(struct inode *inode) } } -static int hfsplus_sync_fs(struct super_block *sb, int wait) +int hfsplus_commit_superblock(struct super_block *sb) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); struct hfsplus_vh *vhdr = sbi->s_vhdr; int write_backup = 0; - int error, error2; - - if (!wait) - return 0; + int error = 0, error2; hfs_dbg("starting...\n"); - /* - * Explicitly write out the special metadata inodes. - * - * While these special inodes are marked as hashed and written - * out peridocically by the flusher threads we redirty them - * during writeout of normal inodes, and thus the life lock - * prevents us from getting the latest state to disk. - */ - error = filemap_write_and_wait(sbi->cat_tree->inode->i_mapping); - error2 = filemap_write_and_wait(sbi->ext_tree->inode->i_mapping); - if (!error) - error = error2; - if (sbi->attr_tree) { - error2 = - filemap_write_and_wait(sbi->attr_tree->inode->i_mapping); - if (!error) - error = error2; - } - error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping); - if (!error) - error = error2; - mutex_lock(&sbi->vh_mutex); mutex_lock(&sbi->alloc_mutex); vhdr->free_blocks = cpu_to_be32(sbi->free_blocks); @@ -249,11 +224,52 @@ static int hfsplus_sync_fs(struct super_block *sb, int wait) sbi->part_start + sbi->sect_count - 2, sbi->s_backup_vhdr_buf, NULL, REQ_OP_WRITE); if (!error) - error2 = error; + error = error2; out: mutex_unlock(&sbi->alloc_mutex); mutex_unlock(&sbi->vh_mutex); + hfs_dbg("finished: err %d\n", error); + + return error; +} + +static int hfsplus_sync_fs(struct super_block *sb, int wait) +{ + struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); + int error, error2; + + if (!wait) + return 0; + + hfs_dbg("starting...\n"); + + /* + * Explicitly write out the special metadata inodes. + * + * While these special inodes are marked as hashed and written + * out peridocically by the flusher threads we redirty them + * during writeout of normal inodes, and thus the life lock + * prevents us from getting the latest state to disk. + */ + error = filemap_write_and_wait(sbi->cat_tree->inode->i_mapping); + error2 = filemap_write_and_wait(sbi->ext_tree->inode->i_mapping); + if (!error) + error = error2; + if (sbi->attr_tree) { + error2 = + filemap_write_and_wait(sbi->attr_tree->inode->i_mapping); + if (!error) + error = error2; + } + error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping); + if (!error) + error = error2; + + error2 = hfsplus_commit_superblock(sb); + if (!error) + error = error2; + if (!test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags)) blkdev_issue_flush(sb->s_bdev); @@ -395,6 +411,15 @@ static const struct super_operations hfsplus_sops = { .show_options = hfsplus_show_options, }; +void hfsplus_prepare_volume_header_for_commit(struct hfsplus_vh *vhdr) +{ + vhdr->last_mount_vers = cpu_to_be32(HFSP_MOUNT_VERSION); + vhdr->modify_date = hfsp_now2mt(); + be32_add_cpu(&vhdr->write_count, 1); + vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT); + vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT); +} + static int hfsplus_fill_super(struct super_block *sb, struct fs_context *fc) { struct hfsplus_vh *vhdr; @@ -562,11 +587,7 @@ static int hfsplus_fill_super(struct super_block *sb, struct fs_context *fc) * H+LX == hfsplusutils, H+Lx == this driver, H+lx is unused * all three are registered with Apple for our use */ - vhdr->last_mount_vers = cpu_to_be32(HFSP_MOUNT_VERSION); - vhdr->modify_date = hfsp_now2mt(); - be32_add_cpu(&vhdr->write_count, 1); - vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT); - vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT); + hfsplus_prepare_volume_header_for_commit(vhdr); hfsplus_sync_fs(sb, 1); if (!sbi->hidden_dir) { diff --git a/fs/inode.c b/fs/inode.c index cff1d3af0d5772..2c55ec49b02397 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2322,42 +2322,40 @@ struct timespec64 current_time(struct inode *inode) } EXPORT_SYMBOL(current_time); -static int inode_needs_update_time(struct inode *inode) +static int file_update_time_flags(struct file *file, unsigned int flags) { + struct inode *inode = file_inode(file); struct timespec64 now, ts; - int sync_it = 0; + int sync_mode = 0; + int ret = 0; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) return 0; + if (unlikely(file->f_mode & FMODE_NOCMTIME)) + return 0; now = current_time(inode); ts = inode_get_mtime(inode); if (!timespec64_equal(&ts, &now)) - sync_it |= S_MTIME; - + sync_mode |= S_MTIME; ts = inode_get_ctime(inode); if (!timespec64_equal(&ts, &now)) - sync_it |= S_CTIME; - + sync_mode |= S_CTIME; if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode)) - sync_it |= S_VERSION; - - return sync_it; -} + sync_mode |= S_VERSION; -static int __file_update_time(struct file *file, int sync_mode) -{ - int ret = 0; - struct inode *inode = file_inode(file); + if (!sync_mode) + return 0; - /* try to update time settings */ - if (!mnt_get_write_access_file(file)) { - ret = inode_update_time(inode, sync_mode); - mnt_put_write_access_file(file); - } + if (flags & IOCB_NOWAIT) + return -EAGAIN; + if (mnt_get_write_access_file(file)) + return 0; + ret = inode_update_time(inode, sync_mode); + mnt_put_write_access_file(file); return ret; } @@ -2377,14 +2375,7 @@ static int __file_update_time(struct file *file, int sync_mode) */ int file_update_time(struct file *file) { - int ret; - struct inode *inode = file_inode(file); - - ret = inode_needs_update_time(inode); - if (ret <= 0) - return ret; - - return __file_update_time(file, ret); + return file_update_time_flags(file, 0); } EXPORT_SYMBOL(file_update_time); @@ -2406,7 +2397,6 @@ EXPORT_SYMBOL(file_update_time); static int file_modified_flags(struct file *file, int flags) { int ret; - struct inode *inode = file_inode(file); /* * Clear the security bits if the process is not being run by root. @@ -2415,17 +2405,7 @@ static int file_modified_flags(struct file *file, int flags) ret = file_remove_privs_flags(file, flags); if (ret) return ret; - - if (unlikely(file->f_mode & FMODE_NOCMTIME)) - return 0; - - ret = inode_needs_update_time(inode); - if (ret <= 0) - return ret; - if (flags & IOCB_NOWAIT) - return -EAGAIN; - - return __file_update_time(file, ret); + return file_update_time_flags(file, flags); } /** diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 8b847a1e27f13e..c0fa6acf19375b 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -217,6 +217,22 @@ static void ifs_free(struct folio *folio) kfree(ifs); } +/* + * Calculate how many bytes to truncate based off the number of blocks to + * truncate and the end position to start truncating from. + */ +static size_t iomap_bytes_to_truncate(loff_t end_pos, unsigned block_bits, + unsigned blocks_truncated) +{ + unsigned block_size = 1 << block_bits; + unsigned block_offset = end_pos & (block_size - 1); + + if (!block_offset) + return blocks_truncated << block_bits; + + return ((blocks_truncated - 1) << block_bits) + block_offset; +} + /* * Calculate the range inside the folio that we actually need to read. */ @@ -240,22 +256,30 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, * to avoid reading in already uptodate ranges. */ if (ifs) { - unsigned int i; + unsigned int i, blocks_skipped; /* move forward for each leading block marked uptodate */ - for (i = first; i <= last; i++) { + for (i = first; i <= last; i++) if (!ifs_block_is_uptodate(ifs, i)) break; - *pos += block_size; - poff += block_size; - plen -= block_size; - first++; + + blocks_skipped = i - first; + if (blocks_skipped) { + unsigned long block_offset = *pos & (block_size - 1); + unsigned bytes_skipped = + (blocks_skipped << block_bits) - block_offset; + + *pos += bytes_skipped; + poff += bytes_skipped; + plen -= bytes_skipped; } + first = i; /* truncate len if we find any trailing uptodate block(s) */ while (++i <= last) { if (ifs_block_is_uptodate(ifs, i)) { - plen -= (last - i + 1) * block_size; + plen -= iomap_bytes_to_truncate(*pos + plen, + block_bits, last - i + 1); last = i - 1; break; } @@ -271,7 +295,8 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, unsigned end = offset_in_folio(folio, isize - 1) >> block_bits; if (first <= end && last > end) - plen -= (last - end) * block_size; + plen -= iomap_bytes_to_truncate(*pos + plen, block_bits, + last - end); } *offp = poff; diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 5d5d63efbd5767..e73c71f39bd45f 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -179,7 +179,18 @@ static void iomap_dio_done(struct iomap_dio *dio) WRITE_ONCE(dio->submit.waiter, NULL); blk_wake_io_task(waiter); - } else if (dio->flags & IOMAP_DIO_INLINE_COMP) { + return; + } + + /* + * Always run error completions in user context. These are not + * performance critical and some code relies on taking sleeping locks + * for error handling. + */ + if (dio->error) + dio->flags &= ~IOMAP_DIO_INLINE_COMP; + + if (dio->flags & IOMAP_DIO_INLINE_COMP) { WRITE_ONCE(iocb->private, NULL); iomap_dio_complete_work(&dio->aio.work); } else if (dio->flags & IOMAP_DIO_CALLER_COMP) { @@ -418,9 +429,13 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS); do { size_t n; - if (dio->error) { - iov_iter_revert(dio->submit.iter, copied); - copied = ret = 0; + + /* + * If completions already occurred and reported errors, give up now and + * don't bother submitting more bios. + */ + if (unlikely(data_race(dio->error))) { + ret = 0; goto out; } @@ -717,12 +732,12 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, } goto out_free_dio; } + } - if (!wait_for_completion && !inode->i_sb->s_dio_done_wq) { - ret = sb_init_dio_done_wq(inode->i_sb); - if (ret < 0) - goto out_free_dio; - } + if (!wait_for_completion && !inode->i_sb->s_dio_done_wq) { + ret = sb_init_dio_done_wq(inode->i_sb); + if (ret < 0) + goto out_free_dio; } inode_dio_begin(inode); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index d480b94117cd77..d02fc04e60d08e 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1521,7 +1521,6 @@ static journal_t *journal_init_common(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int blocksize) { - static struct lock_class_key jbd2_trans_commit_key; journal_t *journal; int err; int n; @@ -1530,6 +1529,7 @@ static journal_t *journal_init_common(struct block_device *bdev, if (!journal) return ERR_PTR(-ENOMEM); + lockdep_register_key(&journal->jbd2_trans_commit_key); journal->j_blocksize = blocksize; journal->j_dev = bdev; journal->j_fs_dev = fs_dev; @@ -1560,7 +1560,7 @@ static journal_t *journal_init_common(struct block_device *bdev, journal->j_max_batch_time = 15000; /* 15ms */ atomic_set(&journal->j_reserved_credits, 0); lockdep_init_map(&journal->j_trans_commit_map, "jbd2_handle", - &jbd2_trans_commit_key, 0); + &journal->jbd2_trans_commit_key, 0); /* The journal is marked for error until we succeed with recovery! */ journal->j_flags = JBD2_ABORT; @@ -1611,6 +1611,7 @@ static journal_t *journal_init_common(struct block_device *bdev, kfree(journal->j_wbuf); jbd2_journal_destroy_revoke(journal); journal_fail_superblock(journal); + lockdep_unregister_key(&journal->jbd2_trans_commit_key); kfree(journal); return ERR_PTR(err); } @@ -2187,6 +2188,7 @@ int jbd2_journal_destroy(journal_t *journal) jbd2_journal_destroy_revoke(journal); kfree(journal->j_fc_wbuf); kfree(journal->j_wbuf); + lockdep_unregister_key(&journal->jbd2_trans_commit_key); kfree(journal); return err; @@ -2349,6 +2351,12 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, sb->s_feature_compat |= cpu_to_be32(compat); sb->s_feature_ro_compat |= cpu_to_be32(ro); sb->s_feature_incompat |= cpu_to_be32(incompat); + /* + * Update the checksum now so that it is valid even for read-only + * filesystems where jbd2_write_superblock() doesn't get called. + */ + if (jbd2_journal_has_csum_v2or3(journal)) + sb->s_checksum = jbd2_superblock_csum(sb); unlock_buffer(journal->j_sb_buffer); jbd2_journal_init_transaction_limits(journal); @@ -2378,9 +2386,17 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat, sb = journal->j_superblock; + lock_buffer(journal->j_sb_buffer); sb->s_feature_compat &= ~cpu_to_be32(compat); sb->s_feature_ro_compat &= ~cpu_to_be32(ro); sb->s_feature_incompat &= ~cpu_to_be32(incompat); + /* + * Update the checksum now so that it is valid even for read-only + * filesystems where jbd2_write_superblock() doesn't get called. + */ + if (jbd2_journal_has_csum_v2or3(journal)) + sb->s_checksum = jbd2_superblock_csum(sb); + unlock_buffer(journal->j_sb_buffer); jbd2_journal_init_transaction_limits(journal); } EXPORT_SYMBOL(jbd2_journal_clear_features); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 3e510564de6ee8..653ee540c4a1b7 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -441,7 +441,7 @@ static int start_this_handle(journal_t *journal, handle_t *handle, read_unlock(&journal->j_state_lock); current->journal_info = handle; - rwsem_acquire_read(&journal->j_trans_commit_map, 0, 0, _THIS_IP_); + rwsem_acquire_read(&journal->j_trans_commit_map, 0, 1, _THIS_IP_); jbd2_journal_free_transaction(new_transaction); /* * Ensure that no allocations done while the transaction is open are @@ -1284,14 +1284,23 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) * committing transaction's lists, but it HAS to be in Forget state in * that case: the transaction must have deleted the buffer for it to be * reused here. + * In the case of file system data inconsistency, for example, if the + * block bitmap of a referenced block is not set, it can lead to the + * situation where a block being committed is allocated and used again. + * As a result, the following condition will not be satisfied, so here + * we directly trigger a JBD abort instead of immediately invoking + * bugon. */ spin_lock(&jh->b_state_lock); - J_ASSERT_JH(jh, (jh->b_transaction == transaction || - jh->b_transaction == NULL || - (jh->b_transaction == journal->j_committing_transaction && - jh->b_jlist == BJ_Forget))); + if (!(jh->b_transaction == transaction || jh->b_transaction == NULL || + (jh->b_transaction == journal->j_committing_transaction && + jh->b_jlist == BJ_Forget)) || jh->b_next_transaction != NULL) { + err = -EROFS; + spin_unlock(&jh->b_state_lock); + jbd2_journal_abort(journal, err); + goto out; + } - J_ASSERT_JH(jh, jh->b_next_transaction == NULL); J_ASSERT_JH(jh, buffer_locked(jh2bh(jh))); if (jh->b_transaction == NULL) { diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index 0ab83bb7bbdf9a..9ab3f2fc61d176 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -2903,7 +2903,7 @@ int jfs_readdir(struct file *file, struct dir_context *ctx) stbl = DT_GETSTBL(p); for (i = index; i < p->header.nextindex; i++) { - if (stbl[i] < 0 || stbl[i] >= DTPAGEMAXSLOT) { + if (stbl[i] < 0) { jfs_err("JFS: Invalid stbl[%d] = %d for inode %ld, block = %lld", i, stbl[i], (long)ip->i_ino, (long long)bn); free_page(dirent_buf); @@ -3108,7 +3108,7 @@ static int dtReadFirst(struct inode *ip, struct btstack * btstack) /* get the leftmost entry */ stbl = DT_GETSTBL(p); - if (stbl[0] < 0 || stbl[0] >= DTPAGEMAXSLOT) { + if (stbl[0] < 0) { DT_PUTPAGE(mp); jfs_error(ip->i_sb, "stbl[0] out of bound\n"); return -EIO; diff --git a/fs/libfs.c b/fs/libfs.c index ce8c496a6940ac..6be233c787fd8c 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -346,22 +346,22 @@ void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry) * User space expects the directory offset value of the replaced * (new) directory entry to be unchanged after a rename. * - * Returns zero on success, a negative errno value on failure. + * Caller must have grabbed a slot for new_dentry in the maple_tree + * associated with new_dir, even if dentry is negative. */ -int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) +void simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) { struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir); struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir); long new_offset = dentry2offset(new_dentry); - simple_offset_remove(old_ctx, old_dentry); + if (WARN_ON(!new_offset)) + return; - if (new_offset) { - offset_set(new_dentry, 0); - return simple_offset_replace(new_ctx, old_dentry, new_offset); - } - return simple_offset_add(new_ctx, old_dentry); + simple_offset_remove(old_ctx, old_dentry); + offset_set(new_dentry, 0); + WARN_ON(simple_offset_replace(new_ctx, old_dentry, new_offset)); } /** @@ -388,31 +388,23 @@ int simple_offset_rename_exchange(struct inode *old_dir, long new_index = dentry2offset(new_dentry); int ret; - simple_offset_remove(old_ctx, old_dentry); - simple_offset_remove(new_ctx, new_dentry); + if (WARN_ON(!old_index || !new_index)) + return -EINVAL; - ret = simple_offset_replace(new_ctx, old_dentry, new_index); - if (ret) - goto out_restore; + ret = mtree_store(&new_ctx->mt, new_index, old_dentry, GFP_KERNEL); + if (WARN_ON(ret)) + return ret; - ret = simple_offset_replace(old_ctx, new_dentry, old_index); - if (ret) { - simple_offset_remove(new_ctx, old_dentry); - goto out_restore; + ret = mtree_store(&old_ctx->mt, old_index, new_dentry, GFP_KERNEL); + if (WARN_ON(ret)) { + mtree_store(&new_ctx->mt, new_index, new_dentry, GFP_KERNEL); + return ret; } - ret = simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); - if (ret) { - simple_offset_remove(new_ctx, old_dentry); - simple_offset_remove(old_ctx, new_dentry); - goto out_restore; - } + offset_set(old_dentry, new_index); + offset_set(new_dentry, old_index); + simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); return 0; - -out_restore: - (void)simple_offset_replace(old_ctx, old_dentry, old_index); - (void)simple_offset_replace(new_ctx, new_dentry, new_index); - return ret; } /** diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 109e5caae8c704..4b6f18d977343d 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -97,7 +97,6 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; - struct nlm_lockowner *test_owner; __be32 rc = rpc_success; dprintk("lockd: TEST4 called\n"); @@ -107,7 +106,6 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file))) return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success; - test_owner = argp->lock.fl.c.flc_owner; /* Now check for conflicting locks */ resp->status = nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock); @@ -116,7 +114,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) else dprintk("lockd: TEST4 status %d\n", ntohl(resp->status)); - nlmsvc_put_lockowner(test_owner); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rc; diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index a31dc9588eb807..d66e8285159996 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -627,7 +627,13 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, } mode = lock_to_openmode(&lock->fl); - error = vfs_test_lock(file->f_file[mode], &lock->fl); + locks_init_lock(&conflock->fl); + /* vfs_test_lock only uses start, end, and owner, but tests flc_file */ + conflock->fl.c.flc_file = lock->fl.c.flc_file; + conflock->fl.fl_start = lock->fl.fl_start; + conflock->fl.fl_end = lock->fl.fl_end; + conflock->fl.c.flc_owner = lock->fl.c.flc_owner; + error = vfs_test_lock(file->f_file[mode], &conflock->fl); if (error) { /* We can't currently deal with deferred test requests */ if (error == FILE_LOCK_DEFERRED) @@ -637,22 +643,19 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, goto out; } - if (lock->fl.c.flc_type == F_UNLCK) { + if (conflock->fl.c.flc_type == F_UNLCK) { ret = nlm_granted; goto out; } dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n", - lock->fl.c.flc_type, (long long)lock->fl.fl_start, - (long long)lock->fl.fl_end); + conflock->fl.c.flc_type, (long long)conflock->fl.fl_start, + (long long)conflock->fl.fl_end); conflock->caller = "somehost"; /* FIXME */ conflock->len = strlen(conflock->caller); conflock->oh.len = 0; /* don't return OH info */ - conflock->svid = lock->fl.c.flc_pid; - conflock->fl.c.flc_type = lock->fl.c.flc_type; - conflock->fl.fl_start = lock->fl.fl_start; - conflock->fl.fl_end = lock->fl.fl_end; - locks_release_private(&lock->fl); + conflock->svid = conflock->fl.c.flc_pid; + locks_release_private(&conflock->fl); ret = nlm_lck_denied; out: diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index f53d5177f26732..5817ef272332d9 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -117,7 +117,6 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; - struct nlm_lockowner *test_owner; __be32 rc = rpc_success; dprintk("lockd: TEST called\n"); @@ -127,8 +126,6 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file))) return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success; - test_owner = argp->lock.fl.c.flc_owner; - /* Now check for conflicting locks */ resp->status = cast_status(nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock)); @@ -138,7 +135,7 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) dprintk("lockd: TEST status %d vers %d\n", ntohl(resp->status), rqstp->rq_vers); - nlmsvc_put_lockowner(test_owner); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rc; diff --git a/fs/locks.c b/fs/locks.c index 04a3f0e2072461..bf5e0d05a02691 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2185,13 +2185,21 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) /** * vfs_test_lock - test file byte range lock * @filp: The file to test lock for - * @fl: The lock to test; also used to hold result + * @fl: The byte-range in the file to test; also used to hold result * + * On entry, @fl does not contain a lock, but identifies a range (fl_start, fl_end) + * in the file (c.flc_file), and an owner (c.flc_owner) for whom existing locks + * should be ignored. c.flc_type and c.flc_flags are ignored. + * Both fl_lmops and fl_ops in @fl must be NULL. * Returns -ERRNO on failure. Indicates presence of conflicting lock by - * setting conf->fl_type to something other than F_UNLCK. + * setting fl->fl_type to something other than F_UNLCK. + * + * If vfs_test_lock() does find a lock and return it, the caller must + * use locks_free_lock() or locks_release_private() on the returned lock. */ int vfs_test_lock(struct file *filp, struct file_lock *fl) { + WARN_ON_ONCE(fl->fl_ops || fl->fl_lmops); WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, F_GETLK, fl); diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index a95e7aadafd072..7a0ffa675fb17a 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -137,7 +137,7 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, rreq->front_folio_order = order; fsize = PAGE_SIZE << order; fpos = folio_pos(folio); - fend = umin(fpos + fsize, rreq->i_size); + fend = fpos + fsize; trace_netfs_collect_folio(rreq, folio, fend, collected_to); diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c index fc9c3e0d34d813..29489a23a22093 100644 --- a/fs/netfs/write_retry.c +++ b/fs/netfs/write_retry.c @@ -98,7 +98,6 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, subreq->start = start; subreq->len = len; __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - subreq->retry_count++; trace_netfs_sreq(subreq, netfs_sreq_trace_retry); /* Renegotiate max_len (wsize) */ diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index ab76120705e206..134d7f760a33a6 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -417,8 +417,10 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, d->map = bl_map_simple; d->pr_key = v->scsi.pr_key; - if (d->len == 0) - return -ENODEV; + if (d->len == 0) { + error = -ENODEV; + goto out_blkdev_put; + } ops = bdev->bd_disk->fops->pr_ops; if (!ops) { diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 54699299d5b168..2aaea9c98c2cd0 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -784,10 +784,18 @@ static int nfs_init_server(struct nfs_server *server, server->fattr_valid = NFS_ATTR_FATTR_V4; } - if (ctx->rsize) + if (ctx->bsize) { + server->bsize = ctx->bsize; + server->automount_inherit |= NFS_AUTOMOUNT_INHERIT_BSIZE; + } + if (ctx->rsize) { server->rsize = nfs_io_size(ctx->rsize, clp->cl_proto); - if (ctx->wsize) + server->automount_inherit |= NFS_AUTOMOUNT_INHERIT_RSIZE; + } + if (ctx->wsize) { server->wsize = nfs_io_size(ctx->wsize, clp->cl_proto); + server->automount_inherit |= NFS_AUTOMOUNT_INHERIT_WSIZE; + } server->acregmin = ctx->acregmin * HZ; server->acregmax = ctx->acregmax * HZ; @@ -977,8 +985,13 @@ EXPORT_SYMBOL_GPL(nfs_probe_server); void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *source) { target->flags = source->flags; - target->rsize = source->rsize; - target->wsize = source->wsize; + target->automount_inherit = source->automount_inherit; + if (source->automount_inherit & NFS_AUTOMOUNT_INHERIT_BSIZE) + target->bsize = source->bsize; + if (source->automount_inherit & NFS_AUTOMOUNT_INHERIT_RSIZE) + target->rsize = source->rsize; + if (source->automount_inherit & NFS_AUTOMOUNT_INHERIT_WSIZE) + target->wsize = source->wsize; target->acregmin = source->acregmin; target->acregmax = source->acregmax; target->acdirmin = source->acdirmin; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index ea9f6ca8f30fa2..a653a401b79701 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -72,7 +72,7 @@ const struct address_space_operations nfs_dir_aops = { .free_folio = nfs_readdir_clear_array, }; -#define NFS_INIT_DTSIZE PAGE_SIZE +#define NFS_INIT_DTSIZE SZ_64K static struct nfs_open_dir_context * alloc_nfs_open_dir_context(struct inode *dir) @@ -83,7 +83,7 @@ alloc_nfs_open_dir_context(struct inode *dir) ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); if (ctx != NULL) { ctx->attr_gencount = nfsi->attr_gencount; - ctx->dtsize = NFS_INIT_DTSIZE; + ctx->dtsize = min(NFS_SERVER(dir)->dtsize, NFS_INIT_DTSIZE); spin_lock(&dir->i_lock); if (list_empty(&nfsi->open_files) && (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER)) @@ -789,16 +789,17 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry, goto out; } + nfs_set_verifier(dentry, dir_verifier); inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr); alias = d_splice_alias(inode, dentry); d_lookup_done(dentry); if (alias) { if (IS_ERR(alias)) goto out; + nfs_set_verifier(alias, dir_verifier); dput(dentry); dentry = alias; } - nfs_set_verifier(dentry, dir_verifier); trace_nfs_readdir_lookup(d_inode(parent), dentry, 0); out: dput(dentry); @@ -1894,13 +1895,15 @@ static int nfs_dentry_delete(const struct dentry *dentry) } /* Ensure that we revalidate inode->i_nlink */ -static void nfs_drop_nlink(struct inode *inode) +static void nfs_drop_nlink(struct inode *inode, unsigned long gencount) { + struct nfs_inode *nfsi = NFS_I(inode); + spin_lock(&inode->i_lock); /* drop the inode if we're reasonably sure this is the last link */ - if (inode->i_nlink > 0) + if (inode->i_nlink > 0 && gencount == nfsi->attr_gencount) drop_nlink(inode); - NFS_I(inode)->attr_gencount = nfs_inc_attr_generation_counter(); + nfsi->attr_gencount = nfs_inc_attr_generation_counter(); nfs_set_cache_invalid( inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_NLINK); @@ -1914,8 +1917,9 @@ static void nfs_drop_nlink(struct inode *inode) static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode) { if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { + unsigned long gencount = READ_ONCE(NFS_I(inode)->attr_gencount); nfs_complete_unlink(dentry, inode); - nfs_drop_nlink(inode); + nfs_drop_nlink(inode, gencount); } iput(inode); } @@ -1991,13 +1995,14 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in nfs_lookup_advise_force_readdirplus(dir, flags); no_entry: + nfs_set_verifier(dentry, dir_verifier); res = d_splice_alias(inode, dentry); if (res != NULL) { if (IS_ERR(res)) goto out; + nfs_set_verifier(res, dir_verifier); dentry = res; } - nfs_set_verifier(dentry, dir_verifier); out: trace_nfs_lookup_exit(dir, dentry, flags, PTR_ERR_OR_ZERO(res)); nfs_free_fattr(fattr); @@ -2139,12 +2144,12 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, d_drop(dentry); switch (err) { case -ENOENT: - d_splice_alias(NULL, dentry); if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) dir_verifier = inode_peek_iversion_raw(dir); else dir_verifier = nfs_save_change_attribute(dir); nfs_set_verifier(dentry, dir_verifier); + d_splice_alias(NULL, dentry); break; case -EISDIR: case -ENOTDIR: @@ -2507,9 +2512,11 @@ static int nfs_safe_remove(struct dentry *dentry) trace_nfs_remove_enter(dir, dentry); if (inode != NULL) { + unsigned long gencount = READ_ONCE(NFS_I(inode)->attr_gencount); + error = NFS_PROTO(dir)->remove(dir, dentry); if (error == 0) - nfs_drop_nlink(inode); + nfs_drop_nlink(inode, gencount); } else error = NFS_PROTO(dir)->remove(dir, dentry); if (error == -ENOENT) @@ -2709,6 +2716,7 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); + unsigned long new_gencount = 0; struct dentry *dentry = NULL; struct rpc_task *task; bool must_unblock = false; @@ -2761,6 +2769,7 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, } else { block_revalidate(new_dentry); must_unblock = true; + new_gencount = NFS_I(new_inode)->attr_gencount; spin_unlock(&new_dentry->d_lock); } @@ -2800,7 +2809,7 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, new_dir, new_dentry, error); if (!error) { if (new_inode != NULL) - nfs_drop_nlink(new_inode); + nfs_drop_nlink(new_inode, new_gencount); /* * The d_move() should be here instead of in an async RPC completion * handler because we need the proper locks to move the dentry. If diff --git a/fs/nfs/file.c b/fs/nfs/file.c index d020aab40c64eb..d1c138a416cfb5 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -511,7 +511,8 @@ static bool nfs_release_folio(struct folio *folio, gfp_t gfp) if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL || current_is_kswapd() || current_is_kcompactd()) return false; - if (nfs_wb_folio(folio->mapping->host, folio) < 0) + if (nfs_wb_folio_reclaim(folio->mapping->host, folio) < 0 || + folio_test_private(folio)) return false; } return nfs_fscache_release_folio(folio, gfp); diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index c55ea8fa3bfa57..c2d8a13a9dbdd7 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -103,7 +103,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, sizeof(struct nfs4_ff_ds_version), gfp_flags); if (!ds_versions) - goto out_scratch; + goto out_err_drain_dsaddrs; for (i = 0; i < version_count; i++) { /* 20 = version(4) + minor_version(4) + rsize(4) + wsize(4) + diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 13ad70fc00d84b..8c2bfcc323e02f 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -716,7 +716,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, { struct inode *inode = d_inode(dentry); struct nfs_fattr *fattr; - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int error = 0; kuid_t task_uid = current_fsuid(); kuid_t owner_uid = inode->i_uid; @@ -727,6 +727,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) attr->ia_valid &= ~ATTR_MODE; + if (S_ISREG(inode->i_mode)) + nfs_file_block_o_direct(NFS_I(inode)); + + oldsize = i_size_read(inode); if (attr->ia_valid & ATTR_SIZE) { BUG_ON(!S_ISREG(inode->i_mode)); @@ -774,10 +778,8 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, trace_nfs_setattr_enter(inode); /* Write all dirty data */ - if (S_ISREG(inode->i_mode)) { - nfs_file_block_o_direct(NFS_I(inode)); + if (S_ISREG(inode->i_mode)) nfs_sync_inode(inode); - } fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 2ecd38e1d17a80..2e596244799f39 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -13,7 +13,7 @@ #include #include -#define NFS_SB_MASK (SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS) +#define NFS_SB_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS) extern const struct export_operations nfs_export_ops; @@ -152,7 +152,6 @@ struct nfs_fs_context { struct super_block *sb; struct dentry *dentry; struct nfs_fattr *fattr; - unsigned int inherited_bsize; } clone_data; }; diff --git a/fs/nfs/io.c b/fs/nfs/io.c index d275b0a250bf3b..8337f0ae852d42 100644 --- a/fs/nfs/io.c +++ b/fs/nfs/io.c @@ -84,6 +84,7 @@ nfs_start_io_write(struct inode *inode) nfs_file_block_o_direct(NFS_I(inode)); return err; } +EXPORT_SYMBOL_GPL(nfs_start_io_write); /** * nfs_end_io_write - declare that the buffered write operation is done @@ -97,6 +98,7 @@ nfs_end_io_write(struct inode *inode) { up_write(&inode->i_rwsem); } +EXPORT_SYMBOL_GPL(nfs_end_io_write); /* Call with exclusively locked inode->i_rwsem */ static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode) diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index 656976b4f42ce6..358d686d2ae330 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -43,8 +43,8 @@ struct nfs_local_kiocb { size_t end_len; short int end_iter_index; atomic_t n_iters; + struct iov_iter iters[NFSLOCAL_MAX_IOS]; bool iter_is_dio_aligned[NFSLOCAL_MAX_IOS]; - struct iov_iter iters[NFSLOCAL_MAX_IOS] ____cacheline_aligned; /* End mostly DIO-specific members */ }; @@ -58,6 +58,11 @@ struct nfs_local_fsync_ctx { static bool localio_enabled __read_mostly = true; module_param(localio_enabled, bool, 0644); +static int nfs_local_do_read(struct nfs_local_kiocb *iocb, + const struct rpc_call_ops *call_ops); +static int nfs_local_do_write(struct nfs_local_kiocb *iocb, + const struct rpc_call_ops *call_ops); + static inline bool nfs_client_is_local(const struct nfs_client *clp) { return !!rcu_access_pointer(clp->cl_uuid.net); @@ -286,6 +291,18 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, } EXPORT_SYMBOL_GPL(nfs_local_open_fh); +/* + * Ensure all page cache allocations are done from GFP_NOFS context to + * prevent direct reclaim recursion back into NFS via nfs_writepages. + */ +static void +nfs_local_mapping_set_gfp_nofs_context(struct address_space *m) +{ + gfp_t gfp_mask = mapping_gfp_mask(m); + + mapping_set_gfp_mask(m, (gfp_mask & ~(__GFP_FS))); +} + static void nfs_local_iocb_free(struct nfs_local_kiocb *iocb) { @@ -310,6 +327,7 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr, return NULL; } + nfs_local_mapping_set_gfp_nofs_context(file->f_mapping); init_sync_kiocb(&iocb->kiocb, file); iocb->hdr = hdr; @@ -339,8 +357,6 @@ nfs_is_local_dio_possible(struct nfs_local_kiocb *iocb, int rw, if (unlikely(!nf_dio_mem_align || !nf_dio_offset_align)) return false; - if (unlikely(nf_dio_offset_align > PAGE_SIZE)) - return false; if (unlikely(len < nf_dio_offset_align)) return false; @@ -463,6 +479,8 @@ nfs_local_iters_init(struct nfs_local_kiocb *iocb, int rw) v = 0; total = hdr->args.count; base = hdr->args.pgbase; + pagevec += base >> PAGE_SHIFT; + base &= ~PAGE_MASK; while (total && v < hdr->page_array.npages) { len = min_t(size_t, total, PAGE_SIZE - base); bvec_set_page(&iocb->bvec[v], *pagevec, len, base); @@ -542,13 +560,50 @@ nfs_local_iocb_release(struct nfs_local_kiocb *iocb) nfs_local_iocb_free(iocb); } -static void -nfs_local_pgio_release(struct nfs_local_kiocb *iocb) +static void nfs_local_pgio_restart(struct nfs_local_kiocb *iocb, + struct nfs_pgio_header *hdr) +{ + int status = 0; + + iocb->kiocb.ki_pos = hdr->args.offset; + iocb->kiocb.ki_flags &= ~(IOCB_DSYNC | IOCB_SYNC | IOCB_DIRECT); + iocb->kiocb.ki_complete = NULL; + iocb->aio_complete_work = NULL; + iocb->end_iter_index = -1; + + switch (hdr->rw_mode) { + case FMODE_READ: + nfs_local_iters_init(iocb, ITER_DEST); + status = nfs_local_do_read(iocb, hdr->task.tk_ops); + break; + case FMODE_WRITE: + nfs_local_iters_init(iocb, ITER_SOURCE); + status = nfs_local_do_write(iocb, hdr->task.tk_ops); + break; + default: + status = -EOPNOTSUPP; + } + + if (status != 0) { + nfs_local_iocb_release(iocb); + hdr->task.tk_status = status; + nfs_local_hdr_release(hdr, hdr->task.tk_ops); + } +} + +static void nfs_local_pgio_release(struct nfs_local_kiocb *iocb) { struct nfs_pgio_header *hdr = iocb->hdr; + struct rpc_task *task = &hdr->task; - nfs_local_iocb_release(iocb); - nfs_local_hdr_release(hdr, hdr->task.tk_ops); + task->tk_action = NULL; + task->tk_ops->rpc_call_done(task, hdr); + + if (task->tk_action == NULL) { + nfs_local_iocb_release(iocb); + task->tk_ops->rpc_release(hdr); + } else + nfs_local_pgio_restart(iocb, hdr); } /* @@ -625,8 +680,6 @@ static void nfs_local_call_read(struct work_struct *work) ssize_t status; int n_iters; - save_cred = override_creds(filp->f_cred); - n_iters = atomic_read(&iocb->n_iters); for (int i = 0; i < n_iters ; i++) { if (iocb->iter_is_dio_aligned[i]) { @@ -639,7 +692,10 @@ static void nfs_local_call_read(struct work_struct *work) } else iocb->kiocb.ki_flags &= ~IOCB_DIRECT; + save_cred = override_creds(filp->f_cred); status = filp->f_op->read_iter(&iocb->kiocb, &iocb->iters[i]); + revert_creds(save_cred); + if (status != -EIOCBQUEUED) { if (unlikely(status >= 0 && status < iocb->iters[i].count)) force_done = true; /* Partial read */ @@ -649,8 +705,6 @@ static void nfs_local_call_read(struct work_struct *work) } } } - - revert_creds(save_cred); } static int @@ -777,19 +831,7 @@ static void nfs_local_write_done(struct nfs_local_kiocb *iocb) pr_info_ratelimited("nfs: Unexpected direct I/O write alignment failure\n"); } - /* Handle short writes as if they are ENOSPC */ - status = hdr->res.count; - if (status > 0 && status < hdr->args.count) { - hdr->mds_offset += status; - hdr->args.offset += status; - hdr->args.pgbase += status; - hdr->args.count -= status; - nfs_set_pgio_error(hdr, -ENOSPC, hdr->args.offset); - status = -ENOSPC; - /* record -ENOSPC in terms of nfs_local_pgio_done */ - (void) nfs_local_pgio_done(iocb, status, true); - } - if (hdr->task.tk_status < 0) + if (status < 0) nfs_reset_boot_verifier(hdr->inode); } @@ -832,7 +874,6 @@ static void nfs_local_call_write(struct work_struct *work) int n_iters; current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO; - save_cred = override_creds(filp->f_cred); file_start_write(filp); n_iters = atomic_read(&iocb->n_iters); @@ -847,7 +888,10 @@ static void nfs_local_call_write(struct work_struct *work) } else iocb->kiocb.ki_flags &= ~IOCB_DIRECT; + save_cred = override_creds(filp->f_cred); status = filp->f_op->write_iter(&iocb->kiocb, &iocb->iters[i]); + revert_creds(save_cred); + if (status != -EIOCBQUEUED) { if (unlikely(status >= 0 && status < iocb->iters[i].count)) force_done = true; /* Partial write */ @@ -859,7 +903,6 @@ static void nfs_local_call_write(struct work_struct *work) } file_end_write(filp); - revert_creds(save_cred); current->flags = old_flags; } @@ -952,8 +995,6 @@ int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio, } if (status != 0) { - if (status == -EAGAIN) - nfs_localio_disable_client(clp); nfs_local_iocb_release(iocb); hdr->task.tk_status = status; nfs_local_hdr_release(hdr, call_ops); @@ -980,6 +1021,8 @@ nfs_local_run_commit(struct file *filp, struct nfs_commit_data *data) end = LLONG_MAX; } + nfs_local_mapping_set_gfp_nofs_context(filp->f_mapping); + dprintk("%s: commit %llu - %llu\n", __func__, start, end); return vfs_fsync_range(filp, start, end, 0); } @@ -1021,17 +1064,22 @@ nfs_local_fsync_ctx_free(struct nfs_local_fsync_ctx *ctx) static void nfs_local_fsync_work(struct work_struct *work) { + unsigned long old_flags = current->flags; struct nfs_local_fsync_ctx *ctx; int status; ctx = container_of(work, struct nfs_local_fsync_ctx, work); + current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO; + status = nfs_local_run_commit(nfs_to->nfsd_file_file(ctx->localio), ctx->data); nfs_local_commit_done(ctx->data, status); if (ctx->done != NULL) complete(ctx->done); nfs_local_fsync_ctx_free(ctx); + + current->flags = old_flags; } static struct nfs_local_fsync_ctx * @@ -1055,7 +1103,7 @@ int nfs_local_commit(struct nfsd_file *localio, { struct nfs_local_fsync_ctx *ctx; - ctx = nfs_local_fsync_ctx_alloc(data, localio, GFP_KERNEL); + ctx = nfs_local_fsync_ctx_alloc(data, localio, GFP_NOIO); if (!ctx) { nfs_local_commit_done(data, -ENOMEM); nfs_local_release_commit_data(localio, data, call_ops); @@ -1067,10 +1115,10 @@ int nfs_local_commit(struct nfsd_file *localio, if (how & FLUSH_SYNC) { DECLARE_COMPLETION_ONSTACK(done); ctx->done = &done; - queue_work(nfsiod_workqueue, &ctx->work); + queue_work(nfslocaliod_workqueue, &ctx->work); wait_for_completion(&done); } else - queue_work(nfsiod_workqueue, &ctx->work); + queue_work(nfslocaliod_workqueue, &ctx->work); return 0; } diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 5a4d193da1a98b..af9be0c5f51630 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -149,6 +149,7 @@ struct vfsmount *nfs_d_automount(struct path *path) struct vfsmount *mnt = ERR_PTR(-ENOMEM); struct nfs_server *server = NFS_SB(path->dentry->d_sb); struct nfs_client *client = server->nfs_client; + unsigned long s_flags = path->dentry->d_sb->s_flags; int timeout = READ_ONCE(nfs_mountpoint_expiry_timeout); int ret; @@ -169,11 +170,21 @@ struct vfsmount *nfs_d_automount(struct path *path) if (!ctx->clone_data.fattr) goto out_fc; + if (fc->cred != server->cred) { + put_cred(fc->cred); + fc->cred = get_cred(server->cred); + } + if (fc->net_ns != client->cl_net) { put_net(fc->net_ns); fc->net_ns = get_net(client->cl_net); } + /* Inherit the flags covered by NFS_SB_MASK */ + fc->sb_flags_mask |= NFS_SB_MASK; + fc->sb_flags &= ~NFS_SB_MASK; + fc->sb_flags |= s_flags & NFS_SB_MASK; + /* for submounts we want the same server; referrals will reassign */ memcpy(&ctx->nfs_server._address, &client->cl_addr, client->cl_addrlen); ctx->nfs_server.addrlen = client->cl_addrlen; @@ -184,6 +195,10 @@ struct vfsmount *nfs_d_automount(struct path *path) ctx->nfs_mod = client->cl_nfs_mod; get_nfs_version(ctx->nfs_mod); + /* Inherit block sizes if they were specified as mount parameters */ + if (server->automount_inherit & NFS_AUTOMOUNT_INHERIT_BSIZE) + ctx->bsize = server->bsize; + ret = client->rpc_ops->submount(fc, server); if (ret < 0) { mnt = ERR_PTR(ret); @@ -283,7 +298,6 @@ int nfs_do_submount(struct fs_context *fc) return -ENOMEM; ctx->internal = true; - ctx->clone_data.inherited_bsize = ctx->clone_data.sb->s_blocksize_bits; p = nfs_devname(dentry, buffer, 4096); if (IS_ERR(p)) { diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index d537fb0c230e8b..c08520828708bf 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -114,7 +114,6 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, exception.inode = inode; exception.state = lock->open_context->state; - nfs_file_block_o_direct(NFS_I(inode)); err = nfs_sync_inode(inode); if (err) goto out; @@ -138,13 +137,17 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE], }; struct inode *inode = file_inode(filep); - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int err; if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; + + oldsize = i_size_read(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); @@ -155,7 +158,7 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) NFS_SERVER(inode)->caps &= ~(NFS_CAP_ALLOCATE | NFS_CAP_ZERO_RANGE); - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -170,7 +173,9 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) if (!nfs_server_capable(inode, NFS_CAP_DEALLOCATE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; err = nfs42_proc_fallocate(&msg, filep, offset, len); if (err == 0) @@ -179,7 +184,7 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) NFS_SERVER(inode)->caps &= ~(NFS_CAP_DEALLOCATE | NFS_CAP_ZERO_RANGE); - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -189,14 +194,17 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ZERO_RANGE], }; struct inode *inode = file_inode(filep); - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int err; if (!nfs_server_capable(inode, NFS_CAP_ZERO_RANGE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; + oldsize = i_size_read(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); if (err == 0) { nfs_truncate_last_folio(inode->i_mapping, oldsize, @@ -205,7 +213,7 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) } else if (err == -EOPNOTSUPP) NFS_SERVER(inode)->caps &= ~NFS_CAP_ZERO_RANGE; - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -416,7 +424,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, struct nfs_server *src_server = NFS_SERVER(src_inode); loff_t pos_src = args->src_pos; loff_t pos_dst = args->dst_pos; - loff_t oldsize_dst = i_size_read(dst_inode); + loff_t oldsize_dst; size_t count = args->count; ssize_t status; @@ -461,6 +469,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, &src_lock->open_context->state->flags); set_bit(NFS_CLNT_DST_SSC_COPY_STATE, &dst_lock->open_context->state->flags); + oldsize_dst = i_size_read(dst_inode); status = nfs4_call_sync(dst_server->client, dst_server, &msg, &args->seq_args, &res->seq_res, 0); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 3a4baed993c96f..4ff0e9dd1145e2 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -1174,10 +1174,20 @@ static int nfs4_init_server(struct nfs_server *server, struct fs_context *fc) if (error < 0) return error; - if (ctx->rsize) - server->rsize = nfs_io_size(ctx->rsize, server->nfs_client->cl_proto); - if (ctx->wsize) - server->wsize = nfs_io_size(ctx->wsize, server->nfs_client->cl_proto); + if (ctx->bsize) { + server->bsize = ctx->bsize; + server->automount_inherit |= NFS_AUTOMOUNT_INHERIT_BSIZE; + } + if (ctx->rsize) { + server->rsize = + nfs_io_size(ctx->rsize, server->nfs_client->cl_proto); + server->automount_inherit |= NFS_AUTOMOUNT_INHERIT_RSIZE; + } + if (ctx->wsize) { + server->wsize = + nfs_io_size(ctx->wsize, server->nfs_client->cl_proto); + server->automount_inherit |= NFS_AUTOMOUNT_INHERIT_WSIZE; + } server->acregmin = ctx->acregmin * HZ; server->acregmax = ctx->acregmax * HZ; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 93c6ce04332b89..3745c59f0af25f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1780,8 +1780,17 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state, if (nfs_stateid_is_sequential(state, stateid)) break; - if (status) - break; + if (status) { + if (nfs4_stateid_match_other(stateid, &state->open_stateid) && + !nfs4_stateid_is_newer(stateid, &state->open_stateid)) { + trace_nfs4_open_stateid_update_skip(state->inode, + stateid, status); + return; + } else { + break; + } + } + /* Rely on seqids for serialisation with NFSv4.0 */ if (!nfs4_has_session(NFS_SERVER(state->inode)->nfs_client)) break; @@ -3174,18 +3183,6 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, if (opendata->o_res.rflags & NFS4_OPEN_RESULT_PRESERVE_UNLINKED) set_bit(NFS_INO_PRESERVE_UNLINKED, &NFS_I(state->inode)->flags); - dentry = opendata->dentry; - if (d_really_is_negative(dentry)) { - struct dentry *alias; - d_drop(dentry); - alias = d_splice_alias(igrab(state->inode), dentry); - /* d_splice_alias() can't fail here - it's a non-directory */ - if (alias) { - dput(ctx->dentry); - ctx->dentry = dentry = alias; - } - } - switch(opendata->o_arg.claim) { default: break; @@ -3196,7 +3193,20 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, break; if (opendata->o_res.delegation.type != 0) dir_verifier = nfs_save_change_attribute(dir); - nfs_set_verifier(dentry, dir_verifier); + } + + dentry = opendata->dentry; + nfs_set_verifier(dentry, dir_verifier); + if (d_really_is_negative(dentry)) { + struct dentry *alias; + d_drop(dentry); + alias = d_splice_alias(igrab(state->inode), dentry); + /* d_splice_alias() can't fail here - it's a non-directory */ + if (alias) { + dput(ctx->dentry); + nfs_set_verifier(alias, dir_verifier); + ctx->dentry = dentry = alias; + } } /* Parse layoutget results before we check for access */ @@ -3884,8 +3894,8 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) calldata->res.seqid = calldata->arg.seqid; calldata->res.server = server; calldata->res.lr_ret = -NFS4ERR_NOMATCHING_LAYOUT; - calldata->lr.roc = pnfs_roc(state->inode, - &calldata->lr.arg, &calldata->lr.res, msg.rpc_cred); + calldata->lr.roc = pnfs_roc(state->inode, &calldata->lr.arg, + &calldata->lr.res, msg.rpc_cred, wait); if (calldata->lr.roc) { calldata->arg.lr_args = &calldata->lr.arg; calldata->res.lr_res = &calldata->lr.res; @@ -6936,7 +6946,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, data->inode = nfs_igrab_and_active(inode); if (data->inode || issync) { data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, - cred); + cred, issync); if (data->lr.roc) { data->args.lr_args = &data->lr.arg; data->res.lr_res = &data->lr.res; diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 9776d220cec33f..6285128e631a5a 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -1353,6 +1353,7 @@ DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_setattr); DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_delegreturn); DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_open_stateid_update); DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_open_stateid_update_wait); +DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_open_stateid_update_skip); DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_close_stateid_update_wait); DECLARE_EVENT_CLASS(nfs4_getattr_event, diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 6ce55e8e6b67c0..9f9ce4a565ea68 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -1062,6 +1062,9 @@ DECLARE_EVENT_CLASS(nfs_folio_event_done, DEFINE_NFS_FOLIO_EVENT(nfs_aop_readpage); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_aop_readpage_done); +DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio_reclaim); +DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_reclaim_done); + DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_done); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index a3135b5af7eeca..b3cb5ee9d821ef 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -463,7 +463,9 @@ pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, }; struct pnfs_layout_segment *lseg, *next; - set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); + if (test_and_set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) + return !list_empty(&lo->plh_segs); + clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(lo->plh_inode)->flags); list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) pnfs_clear_lseg_state(lseg, lseg_list); pnfs_clear_layoutreturn_info(lo); @@ -1532,10 +1534,9 @@ static int pnfs_layout_return_on_reboot(struct pnfs_layout_hdr *lo) PNFS_FL_LAYOUTRETURN_PRIVILEGED); } -bool pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred) +bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, const struct cred *cred, + bool sync) { struct nfs_inode *nfsi = NFS_I(ino); struct nfs_open_context *ctx; @@ -1546,7 +1547,7 @@ bool pnfs_roc(struct inode *ino, nfs4_stateid stateid; enum pnfs_iomode iomode = 0; bool layoutreturn = false, roc = false; - bool skip_read = false; + bool skip_read; if (!nfs_have_layout(ino)) return false; @@ -1559,20 +1560,14 @@ bool pnfs_roc(struct inode *ino, lo = NULL; goto out_noroc; } - pnfs_get_layout_hdr(lo); - if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { - spin_unlock(&ino->i_lock); - rcu_read_unlock(); - wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, - TASK_UNINTERRUPTIBLE); - pnfs_put_layout_hdr(lo); - goto retry; - } /* no roc if we hold a delegation */ + skip_read = false; if (nfs4_check_delegation(ino, FMODE_READ)) { - if (nfs4_check_delegation(ino, FMODE_WRITE)) + if (nfs4_check_delegation(ino, FMODE_WRITE)) { + lo = NULL; goto out_noroc; + } skip_read = true; } @@ -1581,12 +1576,43 @@ bool pnfs_roc(struct inode *ino, if (state == NULL) continue; /* Don't return layout if there is open file state */ - if (state->state & FMODE_WRITE) + if (state->state & FMODE_WRITE) { + lo = NULL; goto out_noroc; + } if (state->state & FMODE_READ) skip_read = true; } + if (skip_read) { + bool writes = false; + + list_for_each_entry(lseg, &lo->plh_segs, pls_list) { + if (lseg->pls_range.iomode != IOMODE_READ) { + writes = true; + break; + } + } + if (!writes) { + lo = NULL; + goto out_noroc; + } + } + + pnfs_get_layout_hdr(lo); + if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { + if (!sync) { + pnfs_set_plh_return_info( + lo, skip_read ? IOMODE_RW : IOMODE_ANY, 0); + goto out_noroc; + } + spin_unlock(&ino->i_lock); + rcu_read_unlock(); + wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, + TASK_UNINTERRUPTIBLE); + pnfs_put_layout_hdr(lo); + goto retry; + } list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) { if (skip_read && lseg->pls_range.iomode == IOMODE_READ) @@ -1626,7 +1652,7 @@ bool pnfs_roc(struct inode *ino, out_noroc: spin_unlock(&ino->i_lock); rcu_read_unlock(); - pnfs_layoutcommit_inode(ino, true); + pnfs_layoutcommit_inode(ino, sync); if (roc) { struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld; if (ld->prepare_layoutreturn) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 91ff877185c8af..3db8f13d8fe4e5 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -303,10 +303,9 @@ int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, u32 seq); int pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, struct list_head *lseg_list); -bool pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred); +bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, const struct cred *cred, + bool sync); int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp, struct nfs4_layoutreturn_res **respp, int *ret); void pnfs_roc_release(struct nfs4_layoutreturn_args *args, @@ -773,12 +772,10 @@ pnfs_layoutcommit_outstanding(struct inode *inode) return false; } - -static inline bool -pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred) +static inline bool pnfs_roc(struct inode *ino, + struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, + const struct cred *cred, bool sync) { return false; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 72dee6f3050e67..57d372db03b936 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1051,16 +1051,6 @@ int nfs_reconfigure(struct fs_context *fc) sync_filesystem(sb); - /* - * The SB_RDONLY flag has been removed from the superblock during - * mounts to prevent interference between different filesystems. - * Similarly, it is also necessary to ignore the SB_RDONLY flag - * during reconfiguration; otherwise, it may also result in the - * creation of redundant superblocks when mounting a directory with - * different rw and ro flags multiple times. - */ - fc->sb_flags_mask &= ~SB_RDONLY; - /* * Userspace mount programs that send binary options generally send * them populated with default values. We have no way to know which @@ -1101,8 +1091,9 @@ static void nfs_fill_super(struct super_block *sb, struct nfs_fs_context *ctx) sb->s_blocksize = 0; sb->s_xattr = server->nfs_client->cl_nfs_mod->xattr; sb->s_op = server->nfs_client->cl_nfs_mod->sops; - if (ctx->bsize) - sb->s_blocksize = nfs_block_size(ctx->bsize, &sb->s_blocksize_bits); + if (server->bsize) + sb->s_blocksize = + nfs_block_size(server->bsize, &sb->s_blocksize_bits); switch (server->nfs_client->rpc_ops->version) { case 2: @@ -1318,26 +1309,13 @@ int nfs_get_tree_common(struct fs_context *fc) if (IS_ERR(server)) return PTR_ERR(server); - /* - * When NFS_MOUNT_UNSHARED is not set, NFS forces the sharing of a - * superblock among each filesystem that mounts sub-directories - * belonging to a single exported root path. - * To prevent interference between different filesystems, the - * SB_RDONLY flag should be removed from the superblock. - */ if (server->flags & NFS_MOUNT_UNSHARED) compare_super = NULL; - else - fc->sb_flags &= ~SB_RDONLY; /* -o noac implies -o sync */ if (server->flags & NFS_MOUNT_NOAC) fc->sb_flags |= SB_SYNCHRONOUS; - if (ctx->clone_data.sb) - if (ctx->clone_data.sb->s_flags & SB_SYNCHRONOUS) - fc->sb_flags |= SB_SYNCHRONOUS; - /* Get a superblock - note that we may end up sharing one that already exists */ fc->s_fs_info = server; s = sget_fc(fc, compare_super, nfs_set_super); @@ -1361,13 +1339,8 @@ int nfs_get_tree_common(struct fs_context *fc) } if (!s->s_root) { - unsigned bsize = ctx->clone_data.inherited_bsize; /* initial superblock/root creation */ nfs_fill_super(s, ctx); - if (bsize) { - s->s_blocksize_bits = bsize; - s->s_blocksize = 1U << bsize; - } error = nfs_get_cache_cookie(s, ctx); if (error < 0) goto error_splat_super; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 336c510f375020..bf412455e8edff 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -2024,6 +2024,39 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio) return ret; } +/** + * nfs_wb_folio_reclaim - Write back all requests on one page + * @inode: pointer to page + * @folio: pointer to folio + * + * Assumes that the folio has been locked by the caller + */ +int nfs_wb_folio_reclaim(struct inode *inode, struct folio *folio) +{ + loff_t range_start = folio_pos(folio); + size_t len = folio_size(folio); + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0, + .range_start = range_start, + .range_end = range_start + len - 1, + .for_sync = 1, + }; + int ret; + + if (folio_test_writeback(folio)) + return -EBUSY; + if (folio_clear_dirty_for_io(folio)) { + trace_nfs_writeback_folio_reclaim(inode, range_start, len); + ret = nfs_writepage_locked(folio, &wbc); + trace_nfs_writeback_folio_reclaim_done(inode, range_start, len, + ret); + return ret; + } + nfs_commit_inode(inode, 0); + return 0; +} + /** * nfs_wb_folio - Write back all requests on one page * @inode: pointer to page diff --git a/fs/nfs_common/common.c b/fs/nfs_common/common.c index af09aed09fd279..0778743ae2c2c2 100644 --- a/fs/nfs_common/common.c +++ b/fs/nfs_common/common.c @@ -17,7 +17,6 @@ static const struct { { NFSERR_NOENT, -ENOENT }, { NFSERR_IO, -EIO }, { NFSERR_NXIO, -ENXIO }, -/* { NFSERR_EAGAIN, -EAGAIN }, */ { NFSERR_ACCES, -EACCES }, { NFSERR_EXIST, -EEXIST }, { NFSERR_XDEV, -EXDEV }, diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index fde5539cf6a690..e9512c34c9dcf7 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -23,6 +23,7 @@ nfsd4_block_proc_layoutget(struct svc_rqst *rqstp, struct inode *inode, { struct nfsd4_layout_seg *seg = &args->lg_seg; struct super_block *sb = inode->i_sb; + u64 length; u32 block_size = i_blocksize(inode); struct pnfs_block_extent *bex; struct iomap iomap; @@ -56,7 +57,8 @@ nfsd4_block_proc_layoutget(struct svc_rqst *rqstp, struct inode *inode, goto out_error; } - if (iomap.length < args->lg_minlength) { + length = iomap.offset + iomap.length - seg->offset; + if (length < args->lg_minlength) { dprintk("pnfsd: extent smaller than minlength\n"); goto out_layoutunavailable; } @@ -342,7 +344,8 @@ nfsd4_scsi_fence_client(struct nfs4_layout_stateid *ls, struct nfsd_file *file) struct block_device *bdev = file->nf_file->f_path.mnt->mnt_sb->s_bdev; bdev->bd_disk->fops->pr_ops->pr_preempt(bdev, NFSD_MDS_PR_KEY, - nfsd4_scsi_pr_key(clp), 0, true); + nfsd4_scsi_pr_key(clp), + PR_EXCLUSIVE_ACCESS_REG_ONLY, true); } const struct nfsd4_layout_ops scsi_layout_ops = { diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 9d55512d0cc97f..2a1499f2ad196a 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -1024,7 +1024,7 @@ exp_rootfh(struct net *net, struct auth_domain *clp, char *name, { struct svc_export *exp; struct path path; - struct inode *inode; + struct inode *inode __maybe_unused; struct svc_fh fh; int err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 3e2d0fde80a7ce..fe8338735e7cc5 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -66,6 +66,8 @@ struct nfsd_net { struct lock_manager nfsd4_manager; bool grace_ended; + bool grace_end_forced; + bool client_tracking_active; time64_t boot_time; struct dentry *nfsd_client_dir; diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 5fb202acb0fd00..0ac538c7618009 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -45,7 +45,7 @@ static __be32 nfsacld_proc_getacl(struct svc_rqst *rqstp) inode = d_inode(fh->fh_dentry); if (argp->mask & ~NFS_ACL_MASK) { - resp->status = nfserr_inval; + resp->status = nfserr_io; goto out; } resp->mask = argp->mask; diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index 8cca1329f3485c..b5b3d45979c9b3 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -643,13 +643,31 @@ static __be32 encode_name_from_id(struct xdr_stream *xdr, return idmap_id_to_name(xdr, rqstp, type, id); } -__be32 -nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen, - kuid_t *uid) +/** + * nfsd_map_name_to_uid - Map user@domain to local UID + * @rqstp: RPC execution context + * @name: user@domain name to be mapped + * @namelen: length of name, in bytes + * @uid: OUT: mapped local UID value + * + * Returns nfs_ok on success or an NFSv4 status code on failure. + */ +__be32 nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, + size_t namelen, kuid_t *uid) { __be32 status; u32 id = -1; + /* + * The idmap lookup below triggers an upcall that invokes + * cache_check(). RQ_USEDEFERRAL must be clear to prevent + * cache_check() from setting RQ_DROPME via svc_defer(). + * NFSv4 servers are not permitted to drop requests. Also + * RQ_DROPME will force NFSv4.1 session slot processing to + * be skipped. + */ + WARN_ON_ONCE(test_bit(RQ_USEDEFERRAL, &rqstp->rq_flags)); + if (name == NULL || namelen == 0) return nfserr_inval; @@ -660,13 +678,31 @@ nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen, return status; } -__be32 -nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen, - kgid_t *gid) +/** + * nfsd_map_name_to_gid - Map user@domain to local GID + * @rqstp: RPC execution context + * @name: user@domain name to be mapped + * @namelen: length of name, in bytes + * @gid: OUT: mapped local GID value + * + * Returns nfs_ok on success or an NFSv4 status code on failure. + */ +__be32 nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, + size_t namelen, kgid_t *gid) { __be32 status; u32 id = -1; + /* + * The idmap lookup below triggers an upcall that invokes + * cache_check(). RQ_USEDEFERRAL must be clear to prevent + * cache_check() from setting RQ_DROPME via svc_defer(). + * NFSv4 servers are not permitted to drop requests. Also + * RQ_DROPME will force NFSv4.1 session slot processing to + * be skipped. + */ + WARN_ON_ONCE(test_bit(RQ_USEDEFERRAL, &rqstp->rq_flags)); + if (name == NULL || namelen == 0) return nfserr_inval; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 7f7e6bb23a90d9..8dada7ef97cb17 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1506,7 +1506,7 @@ static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr, (schedule_timeout(20*HZ) == 0)) { finish_wait(&nn->nfsd_ssc_waitq, &wait); kfree(work); - return nfserr_eagain; + return nfserr_jukebox; } finish_wait(&nn->nfsd_ssc_waitq, &wait); goto try_again; @@ -2995,8 +2995,6 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) BUG_ON(cstate->replay_owner); out: cstate->status = status; - /* Reset deferral mechanism for RPC deferrals */ - set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); return rpc_success; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8a696050021741..740c40eb5b3669 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -84,7 +84,7 @@ static u64 current_sessionid = 1; /* forward declarations */ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner); static void nfs4_free_ol_stateid(struct nfs4_stid *stid); -void nfsd4_end_grace(struct nfsd_net *nn); +static void nfsd4_end_grace(struct nfsd_net *nn); static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); static void nfsd4_file_hash_remove(struct nfs4_file *fi); static void deleg_reaper(struct nfsd_net *nn); @@ -1218,13 +1218,15 @@ static void put_deleg_file(struct nfs4_file *fp) if (nf) nfsd_file_put(nf); - if (rnf) + if (rnf) { + nfsd_file_put(rnf); nfs4_file_put_access(fp, NFS4_SHARE_ACCESS_READ); + } } static void nfsd4_finalize_deleg_timestamps(struct nfs4_delegation *dp, struct file *f) { - struct iattr ia = { .ia_valid = ATTR_ATIME | ATTR_CTIME | ATTR_MTIME }; + struct iattr ia = { .ia_valid = ATTR_ATIME | ATTR_CTIME | ATTR_MTIME | ATTR_DELEG }; struct inode *inode = file_inode(f); int ret; @@ -1757,7 +1759,7 @@ static struct nfs4_stid *find_one_sb_stid(struct nfs4_client *clp, /** * nfsd4_revoke_states - revoke all nfsv4 states associated with given filesystem - * @net: used to identify instance of nfsd (there is one per net namespace) + * @nn: used to identify instance of nfsd (there is one per net namespace) * @sb: super_block used to identify target filesystem * * All nfs4 states (open, lock, delegation, layout) held by the server instance @@ -1769,16 +1771,15 @@ static struct nfs4_stid *find_one_sb_stid(struct nfs4_client *clp, * The clients which own the states will subsequently being notified that the * states have been "admin-revoked". */ -void nfsd4_revoke_states(struct net *net, struct super_block *sb) +void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb) { - struct nfsd_net *nn = net_generic(net, nfsd_net_id); unsigned int idhashval; unsigned int sc_types; sc_types = SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG | SC_TYPE_LAYOUT; spin_lock(&nn->client_lock); - for (idhashval = 0; idhashval < CLIENT_HASH_MASK; idhashval++) { + for (idhashval = 0; idhashval < CLIENT_HASH_SIZE; idhashval++) { struct list_head *head = &nn->conf_id_hashtbl[idhashval]; struct nfs4_client *clp; retry: @@ -3097,8 +3098,10 @@ static int client_states_open(struct inode *inode, struct file *file) return -ENXIO; ret = seq_open(file, &states_seq_ops); - if (ret) + if (ret) { + drop_client(clp); return ret; + } s = file->private_data; s->private = clp; return 0; @@ -6253,10 +6256,14 @@ nfsd4_add_rdaccess_to_wrdeleg(struct svc_rqst *rqstp, struct nfsd4_open *open, fp = stp->st_stid.sc_file; spin_lock(&fp->fi_lock); __nfs4_file_get_access(fp, NFS4_SHARE_ACCESS_READ); - fp = stp->st_stid.sc_file; - fp->fi_fds[O_RDONLY] = nf; - fp->fi_rdeleg_file = nf; + if (!fp->fi_fds[O_RDONLY]) { + fp->fi_fds[O_RDONLY] = nf; + nf = NULL; + } + fp->fi_rdeleg_file = nfsd_file_get(fp->fi_fds[O_RDONLY]); spin_unlock(&fp->fi_lock); + if (nf) + nfsd_file_put(nf); } return true; } @@ -6589,7 +6596,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfs_ok; } -void +static void nfsd4_end_grace(struct nfsd_net *nn) { /* do nothing if grace period already ended */ @@ -6622,6 +6629,33 @@ nfsd4_end_grace(struct nfsd_net *nn) */ } +/** + * nfsd4_force_end_grace - forcibly end the NFSv4 grace period + * @nn: network namespace for the server instance to be updated + * + * Forces bypass of normal grace period completion, then schedules + * the laundromat to end the grace period immediately. Does not wait + * for the grace period to fully terminate before returning. + * + * Return values: + * %true: Grace termination schedule + * %false: No action was taken + */ +bool nfsd4_force_end_grace(struct nfsd_net *nn) +{ + if (!nn->client_tracking_ops) + return false; + spin_lock(&nn->client_lock); + if (nn->grace_ended || !nn->client_tracking_active) { + spin_unlock(&nn->client_lock); + return false; + } + WRITE_ONCE(nn->grace_end_forced, true); + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + spin_unlock(&nn->client_lock); + return true; +} + /* * If we've waited a lease period but there are still clients trying to * reclaim, wait a little longer to give them a chance to finish. @@ -6631,6 +6665,8 @@ static bool clients_still_reclaiming(struct nfsd_net *nn) time64_t double_grace_period_end = nn->boot_time + 2 * nn->nfsd4_lease; + if (READ_ONCE(nn->grace_end_forced)) + return false; if (nn->track_reclaim_completes && atomic_read(&nn->nr_reclaim_complete) == nn->reclaim_str_hashtbl_size) @@ -8934,6 +8970,8 @@ static int nfs4_state_create_net(struct net *net) nn->unconf_name_tree = RB_ROOT; nn->boot_time = ktime_get_real_seconds(); nn->grace_ended = false; + nn->grace_end_forced = false; + nn->client_tracking_active = false; nn->nfsd4_manager.block_opens = true; INIT_LIST_HEAD(&nn->nfsd4_manager.list); INIT_LIST_HEAD(&nn->client_lru); @@ -9014,6 +9052,10 @@ nfs4_state_start_net(struct net *net) return ret; locks_start_grace(net, &nn->nfsd4_manager); nfsd4_client_tracking_init(net); + /* safe for laundromat to run now */ + spin_lock(&nn->client_lock); + nn->client_tracking_active = true; + spin_unlock(&nn->client_lock); if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0) goto skip_grace; printk(KERN_INFO "NFSD: starting %lld-second grace period (net %x)\n", @@ -9062,6 +9104,9 @@ nfs4_state_shutdown_net(struct net *net) shrinker_free(nn->nfsd_client_shrinker); cancel_work_sync(&nn->nfsd_shrinker_work); + spin_lock(&nn->client_lock); + nn->client_tracking_active = false; + spin_unlock(&nn->client_lock); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 67bb9c0b9fcb18..5f046d5be4a6e2 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3375,6 +3375,11 @@ static __be32 nfsd4_encode_fattr4_suppattr_exclcreat(struct xdr_stream *xdr, u32 supp[3]; memcpy(supp, nfsd_suppattrs[resp->cstate.minorversion], sizeof(supp)); + if (!IS_POSIXACL(d_inode(args->dentry))) + supp[0] &= ~FATTR4_WORD0_ACL; + if (!args->contextsupport) + supp[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + supp[0] &= NFSD_SUPPATTR_EXCLCREAT_WORD0; supp[1] &= NFSD_SUPPATTR_EXCLCREAT_WORD1; supp[2] &= NFSD_SUPPATTR_EXCLCREAT_WORD2; @@ -5996,6 +6001,22 @@ nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) args->ops = args->iops; args->rqstp = rqstp; + /* + * NFSv4 operation decoders can invoke svc cache lookups + * that trigger svc_defer() when RQ_USEDEFERRAL is set, + * setting RQ_DROPME. This creates two problems: + * + * 1. Non-idempotency: Compounds make it too hard to avoid + * problems if a request is deferred and replayed. + * + * 2. Session slot leakage (NFSv4.1+): If RQ_DROPME is set + * during decode but SEQUENCE executes successfully, the + * session slot will be marked INUSE. The request is then + * dropped before encoding, so the slot is never released, + * rendering it permanently unusable by the client. + */ + clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); + return nfsd4_decode_compound(args); } diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 2b79129703d54b..8cbfb9dc3abb7f 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -259,6 +259,7 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) struct path path; char *fo_path; int error; + struct nfsd_net *nn; /* sanity check */ if (size == 0) @@ -285,7 +286,13 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) * 3. Is that directory the root of an exported file system? */ error = nlmsvc_unlock_all_by_sb(path.dentry->d_sb); - nfsd4_revoke_states(netns(file), path.dentry->d_sb); + mutex_lock(&nfsd_mutex); + nn = net_generic(netns(file), nfsd_net_id); + if (nn->nfsd_serv) + nfsd4_revoke_states(nn, path.dentry->d_sb); + else + error = -EINVAL; + mutex_unlock(&nfsd_mutex); path_put(&path); return error; @@ -1082,10 +1089,9 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) case 'Y': case 'y': case '1': - if (!nn->nfsd_serv) + if (!nfsd4_force_end_grace(nn)) return -EBUSY; trace_nfsd_end_grace(netns(file)); - nfsd4_end_grace(nn); break; default: return -EINVAL; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index b752433c3c2c43..8cecccdaf9ee5b 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -232,7 +232,6 @@ void nfsd_lockd_shutdown(void); #define nfserr_noent cpu_to_be32(NFSERR_NOENT) #define nfserr_io cpu_to_be32(NFSERR_IO) #define nfserr_nxio cpu_to_be32(NFSERR_NXIO) -#define nfserr_eagain cpu_to_be32(NFSERR_EAGAIN) #define nfserr_acces cpu_to_be32(NFSERR_ACCES) #define nfserr_exist cpu_to_be32(NFSERR_EXIST) #define nfserr_xdev cpu_to_be32(NFSERR_XDEV) @@ -547,8 +546,14 @@ static inline bool nfsd_attrs_supported(u32 minorversion, const u32 *bmval) #define NFSD_SUPPATTR_EXCLCREAT_WORD1 \ (NFSD_WRITEABLE_ATTRS_WORD1 & \ ~(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET)) +/* + * The FATTR4_WORD2_TIME_DELEG attributes are not to be allowed for + * OPEN(create) with EXCLUSIVE4_1. It doesn't make sense to set a + * delegated timestamp on a new file. + */ #define NFSD_SUPPATTR_EXCLCREAT_WORD2 \ - NFSD_WRITEABLE_ATTRS_WORD2 + (NFSD_WRITEABLE_ATTRS_WORD2 & \ + ~(FATTR4_WORD2_TIME_DELEG_ACCESS | FATTR4_WORD2_TIME_DELEG_MODIFY)) extern int nfsd4_is_junction(struct dentry *dentry); extern int register_cld_notifier(void); diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 8f71f5748c75b6..906a6725789008 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -33,7 +33,7 @@ static __be32 nfsd_map_status(__be32 status) break; case nfserr_symlink: case nfserr_wrong_type: - status = nfserr_inval; + status = nfserr_io; break; } return status; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 7057ddd7a0a873..fcb47f344e32f0 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -424,26 +424,26 @@ static void nfsd_shutdown_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - if (!nn->nfsd_net_up) - return; - - percpu_ref_kill_and_confirm(&nn->nfsd_net_ref, nfsd_net_done); - wait_for_completion(&nn->nfsd_net_confirm_done); - - nfsd_export_flush(net); - nfs4_state_shutdown_net(net); - nfsd_reply_cache_shutdown(nn); - nfsd_file_cache_shutdown_net(net); - if (nn->lockd_up) { - lockd_down(net); - nn->lockd_up = false; + if (nn->nfsd_net_up) { + percpu_ref_kill_and_confirm(&nn->nfsd_net_ref, nfsd_net_done); + wait_for_completion(&nn->nfsd_net_confirm_done); + + nfsd_export_flush(net); + nfs4_state_shutdown_net(net); + nfsd_reply_cache_shutdown(nn); + nfsd_file_cache_shutdown_net(net); + if (nn->lockd_up) { + lockd_down(net); + nn->lockd_up = false; + } + wait_for_completion(&nn->nfsd_net_free_done); } - wait_for_completion(&nn->nfsd_net_free_done); percpu_ref_exit(&nn->nfsd_net_ref); + if (nn->nfsd_net_up) + nfsd_shutdown_generic(); nn->nfsd_net_up = false; - nfsd_shutdown_generic(); } static DEFINE_SPINLOCK(nfsd_notifier_lock); @@ -633,12 +633,15 @@ int nfsd_create_serv(struct net *net) serv = svc_create_pooled(nfsd_programs, ARRAY_SIZE(nfsd_programs), &nn->nfsd_svcstats, nfsd_max_blksize, nfsd); - if (serv == NULL) + if (serv == NULL) { + percpu_ref_exit(&nn->nfsd_net_ref); return -ENOMEM; + } error = svc_bind(serv, net); if (error < 0) { svc_destroy(&serv); + percpu_ref_exit(&nn->nfsd_net_ref); return error; } spin_lock(&nfsd_notifier_lock); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 1e736f4024263f..c75bf3abec40ad 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -841,15 +841,15 @@ static inline void get_nfs4_file(struct nfs4_file *fi) struct nfsd_file *find_any_file(struct nfs4_file *f); #ifdef CONFIG_NFSD_V4 -void nfsd4_revoke_states(struct net *net, struct super_block *sb); +void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb); #else -static inline void nfsd4_revoke_states(struct net *net, struct super_block *sb) +static inline void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb) { } #endif /* grace period management */ -void nfsd4_end_grace(struct nfsd_net *nn); +bool nfsd4_force_end_grace(struct nfsd_net *nn); /* nfs4recover operations */ extern int nfsd4_client_tracking_init(struct net *net); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 9cb20d4aeab159..e32a5fcd6ac851 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1228,8 +1228,18 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, stable = NFS_UNSTABLE; init_sync_kiocb(&kiocb, file); kiocb.ki_pos = offset; - if (stable && !fhp->fh_use_wgather) - kiocb.ki_flags |= IOCB_DSYNC; + if (likely(!fhp->fh_use_wgather)) { + switch (stable) { + case NFS_FILE_SYNC: + /* persist data and timestamps */ + kiocb.ki_flags |= IOCB_DSYNC | IOCB_SYNC; + break; + case NFS_DATA_SYNC: + /* persist data only */ + kiocb.ki_flags |= IOCB_DSYNC; + break; + } + } nvecs = xdr_buf_to_bvec(rqstp->rq_bvec, rqstp->rq_maxpages, payload); iov_iter_bvec(&iter, ITER_SOURCE, rqstp->rq_bvec, nvecs, *cnt); @@ -2673,8 +2683,8 @@ nfsd_permission(struct svc_cred *cred, struct svc_export *exp, /* Allow read access to binaries even when mode 111 */ if (err == -EACCES && S_ISREG(inode->i_mode) && - (acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE) || - acc == (NFSD_MAY_READ | NFSD_MAY_READ_IF_EXEC))) + (((acc & NFSD_MAY_MASK) == NFSD_MAY_READ) && + (acc & (NFSD_MAY_OWNER_OVERRIDE | NFSD_MAY_READ_IF_EXEC)))) err = inode_permission(&nop_mnt_idmap, inode, MAY_EXEC); return err? nfserrno(err) : 0; diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 0c0292611c6de3..9652c1de53ec13 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -67,7 +67,8 @@ static inline bool nfsd_attrs_valid(struct nfsd_attrs *attrs) struct iattr *iap = attrs->na_iattr; return (iap->ia_valid || (attrs->na_seclabel && - attrs->na_seclabel->len)); + attrs->na_seclabel->len) || + attrs->na_pacl || attrs->na_dpacl); } __be32 nfserrno (int errno); diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 330f269abedf5d..71ee217eb072cf 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -1093,6 +1093,9 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range) else end_block = start_block + len - 1; + if (end_block < nilfs->ns_first_data_block) + goto out; + segnum = nilfs_get_segnum_of_block(nilfs, start_block); segnum_end = nilfs_get_segnum_of_block(nilfs, end_block); @@ -1191,6 +1194,7 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range) out_sem: up_read(&NILFS_MDT(sufile)->mi_sem); +out: range->len = ndiscarded << nilfs->ns_blocksize_bits; return ret; } diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c index 18d597e49a194e..a5c3a9f1b8dc59 100644 --- a/fs/nls/nls_base.c +++ b/fs/nls/nls_base.c @@ -67,19 +67,22 @@ int utf8_to_utf32(const u8 *s, int inlen, unicode_t *pu) l &= t->lmask; if (l < t->lval || l > UNICODE_MAX || (l & SURROGATE_MASK) == SURROGATE_PAIR) - return -1; + return -EILSEQ; + *pu = (unicode_t) l; return nc; } if (inlen <= nc) - return -1; + return -EOVERFLOW; + s++; c = (*s ^ 0x80) & 0xFF; if (c & 0xC0) - return -1; + return -EILSEQ; + l = (l << 6) | c; } - return -1; + return -EILSEQ; } EXPORT_SYMBOL(utf8_to_utf32); @@ -94,7 +97,7 @@ int utf32_to_utf8(unicode_t u, u8 *s, int maxout) l = u; if (l > UNICODE_MAX || (l & SURROGATE_MASK) == SURROGATE_PAIR) - return -1; + return -EILSEQ; nc = 0; for (t = utf8_table; t->cmask && maxout; t++, maxout--) { @@ -110,7 +113,7 @@ int utf32_to_utf8(unicode_t u, u8 *s, int maxout) return nc; } } - return -1; + return -EOVERFLOW; } EXPORT_SYMBOL(utf32_to_utf8); @@ -217,8 +220,16 @@ int utf16s_to_utf8s(const wchar_t *pwcs, int inlen, enum utf16_endian endian, inlen--; } size = utf32_to_utf8(u, op, maxout); - if (size == -1) { - /* Ignore character and move on */ + if (size < 0) { + if (size == -EILSEQ) { + /* Ignore character and move on */ + continue; + } + /* + * Stop filling the buffer with data once a character + * does not fit anymore. + */ + break; } else { op += size; maxout -= size; diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 46bfc543f9467c..63dd44931989d4 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -270,8 +270,15 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, /* * Include parent/name in notification either if some notification * groups require parent info or the parent is interested in this event. + * The parent interest in ACCESS/MODIFY events does not apply to special + * files, where read/write are not on the filesystem of the parent and + * events can provide an undesirable side-channel for information + * exfiltration. */ - parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS; + parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS && + !(data_type == FSNOTIFY_EVENT_PATH && + d_is_special(dentry) && + (mask & (FS_ACCESS | FS_MODIFY))); if (parent_needed || parent_interested) { /* When notifying parent, child should be passed as data */ WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type)); diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 4c90ec2fa2eae0..cd7aaeef45fe9a 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -930,7 +930,7 @@ static int ntfs_get_frame_pages(struct address_space *mapping, pgoff_t index, folio = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, - gfp_mask); + gfp_mask | __GFP_ZERO); if (IS_ERR(folio)) { while (npages--) { folio = page_folio(pages[npages]); @@ -1012,8 +1012,12 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from) goto out; if (lcn == SPARSE_LCN) { - ni->i_valid = valid = - frame_vbo + ((u64)clen << sbi->cluster_bits); + valid = frame_vbo + ((u64)clen << sbi->cluster_bits); + if (ni->i_valid == valid) { + err = -EINVAL; + goto out; + } + ni->i_valid = valid; continue; } @@ -1375,6 +1379,18 @@ static ssize_t ntfs_file_splice_write(struct pipe_inode_info *pipe, return iter_file_splice_write(pipe, file, ppos, len, flags); } +/* + * ntfs_file_fsync - file_operations::fsync + */ +static int ntfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) +{ + struct inode *inode = file_inode(file); + if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) + return -EIO; + + return generic_file_fsync(file, start, end, datasync); +} + // clang-format off const struct inode_operations ntfs_file_inode_operations = { .getattr = ntfs_getattr, @@ -1397,7 +1413,7 @@ const struct file_operations ntfs_file_operations = { .splice_write = ntfs_file_splice_write, .mmap_prepare = ntfs_file_mmap_prepare, .open = ntfs_file_open, - .fsync = generic_file_fsync, + .fsync = ntfs_file_fsync, .fallocate = ntfs_fallocate, .release = ntfs_file_release, }; diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 8f9fe1d7a69081..295f6936a3e588 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -325,8 +325,10 @@ bool ni_add_subrecord(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi) mi_get_ref(&ni->mi, &m->mrec->parent_ref); - ni_add_mi(ni, m); - *mi = m; + *mi = ni_ins_mi(ni, &ni->mi_tree, m->rno, &m->node); + if (*mi != m) + mi_put(m); + return true; } @@ -1015,9 +1017,9 @@ static int ni_ins_attr_ext(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le, out2: ni_remove_mi(ni, mi); - mi_put(mi); out1: + mi_put(mi); ntfs_mark_rec_free(sbi, rno, is_mft); out: @@ -2020,6 +2022,29 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo, return err; } +static struct page *ntfs_lock_new_page(struct address_space *mapping, + pgoff_t index, gfp_t gfp) +{ + struct folio *folio = __filemap_get_folio(mapping, index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); + struct page *page; + + if (IS_ERR(folio)) + return ERR_CAST(folio); + + if (!folio_test_uptodate(folio)) + return folio_file_page(folio, index); + + /* Use a temporary page to avoid data corruption */ + folio_unlock(folio); + folio_put(folio); + page = alloc_page(gfp); + if (!page) + return ERR_PTR(-ENOMEM); + __SetPageLocked(page); + return page; +} + /* * ni_readpage_cmpr * @@ -2074,9 +2099,9 @@ int ni_readpage_cmpr(struct ntfs_inode *ni, struct folio *folio) if (i == idx) continue; - pg = find_or_create_page(mapping, index, gfp_mask); - if (!pg) { - err = -ENOMEM; + pg = ntfs_lock_new_page(mapping, index, gfp_mask); + if (IS_ERR(pg)) { + err = PTR_ERR(pg); goto out1; } pages[i] = pg; @@ -2175,13 +2200,13 @@ int ni_decompress_file(struct ntfs_inode *ni) for (i = 0; i < pages_per_frame; i++, index++) { struct page *pg; - pg = find_or_create_page(mapping, index, gfp_mask); - if (!pg) { + pg = ntfs_lock_new_page(mapping, index, gfp_mask); + if (IS_ERR(pg)) { while (i--) { unlock_page(pages[i]); put_page(pages[i]); } - err = -ENOMEM; + err = PTR_ERR(pg); goto out; } pages[i] = pg; diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 38934e6978ecec..28bd611f580d9c 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -3429,6 +3429,9 @@ static int do_action(struct ntfs_log *log, struct OPEN_ATTR_ENRTY *oe, e1 = Add2Ptr(attr, le16_to_cpu(lrh->attr_off)); esize = le16_to_cpu(e1->size); + if (PtrOffset(e1, Add2Ptr(hdr, used)) < esize) + goto dirty_vol; + e2 = Add2Ptr(e1, esize); memmove(e1, e2, PtrOffset(e2, Add2Ptr(hdr, used))); diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index c7a2f191254dad..5ae910e9ecbda4 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -1349,7 +1349,14 @@ int ntfs_get_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, } if (buffer_locked(bh)) __wait_on_buffer(bh); - set_buffer_uptodate(bh); + + lock_buffer(bh); + if (!buffer_uptodate(bh)) + { + memset(bh->b_data, 0, blocksize); + set_buffer_uptodate(bh); + } + unlock_buffer(bh); } else { bh = ntfs_bread(sb, block); if (!bh) { diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 3959f23c487a2c..164fd63dff40d6 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -472,6 +472,7 @@ static struct inode *ntfs_read_mft(struct inode *inode, /* Records in $Extend are not a files or general directories. */ inode->i_op = &ntfs_file_inode_operations; mode = S_IFREG; + init_rwsem(&ni->file.run_lock); } else { err = -EINVAL; goto out; @@ -1278,7 +1279,7 @@ int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, fa |= FILE_ATTRIBUTE_READONLY; /* Allocate PATH_MAX bytes. */ - new_de = __getname(); + new_de = kmem_cache_zalloc(names_cachep, GFP_KERNEL); if (!new_de) { err = -ENOMEM; goto out1; @@ -1719,7 +1720,7 @@ int ntfs_link_inode(struct inode *inode, struct dentry *dentry) struct NTFS_DE *de; /* Allocate PATH_MAX bytes. */ - de = __getname(); + de = kmem_cache_zalloc(names_cachep, GFP_KERNEL); if (!de) return -ENOMEM; @@ -1757,7 +1758,7 @@ int ntfs_unlink_inode(struct inode *dir, const struct dentry *dentry) return -EINVAL; /* Allocate PATH_MAX bytes. */ - de = __getname(); + de = kmem_cache_zalloc(names_cachep, GFP_KERNEL); if (!de) return -ENOMEM; diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 630128716ea739..2649fbe16669de 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -979,11 +979,12 @@ static inline __le64 kernel2nt(const struct timespec64 *ts) */ static inline void nt2kernel(const __le64 tm, struct timespec64 *ts) { - u64 t = le64_to_cpu(tm) - _100ns2seconds * SecondsToStartOf1970; + s32 t32; + /* use signed 64 bit to support timestamps prior to epoch. xfstest 258. */ + s64 t = le64_to_cpu(tm) - _100ns2seconds * SecondsToStartOf1970; - // WARNING: do_div changes its first argument(!) - ts->tv_nsec = do_div(t, _100ns2seconds) * 100; - ts->tv_sec = t; + ts->tv_sec = div_s64_rem(t, _100ns2seconds, &t32); + ts->tv_nsec = t32 * 100; } static inline struct ntfs_sb_info *ntfs_sb(struct super_block *sb) diff --git a/fs/ntfs3/run.c b/fs/ntfs3/run.c index 88550085f74575..5df55e4adbb114 100644 --- a/fs/ntfs3/run.c +++ b/fs/ntfs3/run.c @@ -984,8 +984,12 @@ int run_unpack(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, if (!dlcn) return -EINVAL; - if (check_add_overflow(prev_lcn, dlcn, &lcn)) + /* Check special combination: 0 + SPARSE_LCN64. */ + if (!prev_lcn && dlcn == SPARSE_LCN64) { + lcn = SPARSE_LCN64; + } else if (check_add_overflow(prev_lcn, dlcn, &lcn)) { return -EINVAL; + } prev_lcn = lcn; } else { /* The size of 'dlcn' can't be > 8. */ diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index ddff94c091b8c6..e6c0908e27c299 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -933,6 +933,11 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, sbi->volume.blocks = dev_size >> PAGE_SHIFT; + /* Set dummy blocksize to read boot_block. */ + if (!sb_min_blocksize(sb, PAGE_SIZE)) { + return -EINVAL; + } + read_boot: bh = ntfs_bread(sb, boot_block); if (!bh) diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 162711cc5b201f..a0ced11e0c24ab 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -3654,7 +3654,6 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path, * So we use the new rightmost path. */ ocfs2_mv_path(right_path, left_path); - left_path = NULL; } else ocfs2_complete_edge_insert(handle, left_path, right_path, subtree_index); diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index fcc89856ab95b6..0a0a96054bfecb 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -201,13 +201,15 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags, static int ocfs2_dinode_has_extents(struct ocfs2_dinode *di) { /* inodes flagged with other stuff in id2 */ - if (di->i_flags & (OCFS2_SUPER_BLOCK_FL | OCFS2_LOCAL_ALLOC_FL | - OCFS2_CHAIN_FL | OCFS2_DEALLOC_FL)) + if (le32_to_cpu(di->i_flags) & + (OCFS2_SUPER_BLOCK_FL | OCFS2_LOCAL_ALLOC_FL | OCFS2_CHAIN_FL | + OCFS2_DEALLOC_FL)) return 0; /* i_flags doesn't indicate when id2 is a fast symlink */ - if (S_ISLNK(di->i_mode) && di->i_size && di->i_clusters == 0) + if (S_ISLNK(le16_to_cpu(di->i_mode)) && le64_to_cpu(di->i_size) && + !le32_to_cpu(di->i_clusters)) return 0; - if (di->i_dyn_features & OCFS2_INLINE_DATA_FL) + if (le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) return 0; return 1; diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 10923bf7c8b841..26e150c5f25eb0 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -98,7 +98,13 @@ static int __ocfs2_move_extent(handle_t *handle, rec = &el->l_recs[index]; - BUG_ON(ext_flags != rec->e_flags); + if (ext_flags != rec->e_flags) { + ret = ocfs2_error(inode->i_sb, + "Inode %llu has corrupted extent %d with flags 0x%x at cpos %u\n", + (unsigned long long)ino, index, rec->e_flags, cpos); + goto out; + } + /* * after moving/defraging to new location, the extent is not going * to be refcounted anymore. diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 6ac4dcd54588cf..e93fc842bb2038 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -1992,6 +1992,16 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac, } cl = (struct ocfs2_chain_list *) &fe->id2.i_chain; + if (!le16_to_cpu(cl->cl_next_free_rec) || + le16_to_cpu(cl->cl_next_free_rec) > le16_to_cpu(cl->cl_count)) { + status = ocfs2_error(ac->ac_inode->i_sb, + "Chain allocator dinode %llu has invalid next " + "free chain record %u, but only %u total\n", + (unsigned long long)le64_to_cpu(fe->i_blkno), + le16_to_cpu(cl->cl_next_free_rec), + le16_to_cpu(cl->cl_count)); + goto bail; + } victim = ocfs2_find_victim_chain(cl); ac->ac_chain = victim; diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 1e9792cc557b8d..3c27e7a16f94b1 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -761,7 +761,7 @@ static bool ovl_fill_real(struct dir_context *ctx, const char *name, struct dir_context *orig_ctx = rdt->orig_ctx; bool res; - if (rdt->parent_ino && strcmp(name, "..") == 0) { + if (rdt->parent_ino && namelen == 2 && !strncmp(name, "..", 2)) { ino = rdt->parent_ino; } else if (rdt->cache) { struct ovl_cache_entry *p; diff --git a/fs/pidfs.c b/fs/pidfs.c index 0ef5b47d796a26..34987fcdd9a87e 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -306,6 +306,8 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) const struct cred *c; __u64 mask; + BUILD_BUG_ON(sizeof(struct pidfd_info) != PIDFD_INFO_SIZE_VER1); + if (!uinfo) return -EINVAL; if (usize < PIDFD_INFO_SIZE_VER0) @@ -319,7 +321,7 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) * namespace hierarchy. */ if (!pid_in_current_pidns(pid)) - return -ESRCH; + return -EREMOTE; attr = READ_ONCE(pid->attr); if (mask & PIDFD_INFO_EXIT) { diff --git a/fs/proc/array.c b/fs/proc/array.c index 2ae63189091e02..038d4b57127fef 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -529,7 +529,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, } sid = task_session_nr_ns(task, ns); - ppid = task_tgid_nr_ns(task->real_parent, ns); + ppid = task_ppid_nr_ns(task, ns); pgid = task_pgrp_nr_ns(task, ns); unlock_task_sighand(task, &flags); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index fc35a0543f0191..2ee152a318f50f 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -656,6 +656,7 @@ static int do_procmap_query(struct mm_struct *mm, void __user *uarg) struct proc_maps_locking_ctx lock_ctx = { .mm = mm }; struct procmap_query karg; struct vm_area_struct *vma; + struct file *vm_file = NULL; const char *name = NULL; char build_id_buf[BUILD_ID_SIZE_MAX], *name_buf = NULL; __u64 usize; @@ -727,21 +728,6 @@ static int do_procmap_query(struct mm_struct *mm, void __user *uarg) karg.inode = 0; } - if (karg.build_id_size) { - __u32 build_id_sz; - - err = build_id_parse(vma, build_id_buf, &build_id_sz); - if (err) { - karg.build_id_size = 0; - } else { - if (karg.build_id_size < build_id_sz) { - err = -ENAMETOOLONG; - goto out; - } - karg.build_id_size = build_id_sz; - } - } - if (karg.vma_name_size) { size_t name_buf_sz = min_t(size_t, PATH_MAX, karg.vma_name_size); const struct path *path; @@ -775,10 +761,34 @@ static int do_procmap_query(struct mm_struct *mm, void __user *uarg) karg.vma_name_size = name_sz; } + if (karg.build_id_size && vma->vm_file) + vm_file = get_file(vma->vm_file); + /* unlock vma or mmap_lock, and put mm_struct before copying data to user */ query_vma_teardown(&lock_ctx); mmput(mm); + if (karg.build_id_size) { + __u32 build_id_sz; + + if (vm_file) + err = build_id_parse_file(vm_file, build_id_buf, &build_id_sz); + else + err = -ENOENT; + if (err) { + karg.build_id_size = 0; + } else { + if (karg.build_id_size < build_id_sz) { + err = -ENAMETOOLONG; + goto out; + } + karg.build_id_size = build_id_sz; + } + } + + if (vm_file) + fput(vm_file); + if (karg.vma_name_size && copy_to_user(u64_to_user_ptr(karg.vma_name_addr), name, karg.vma_name_size)) { kfree(name_buf); @@ -798,6 +808,8 @@ static int do_procmap_query(struct mm_struct *mm, void __user *uarg) out: query_vma_teardown(&lock_ctx); mmput(mm); + if (vm_file) + fput(vm_file); kfree(name_buf); return err; } diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index f1848cdd6d3485..c9eaacdec37e48 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -298,6 +298,17 @@ void persistent_ram_save_old(struct persistent_ram_zone *prz) if (!size) return; + /* + * If the existing buffer is differently sized, free it so a new + * one is allocated. This can happen when persistent_ram_save_old() + * is called early in boot and later for a timer-triggered + * survivable crash when the crash dumps don't match in size + * (which would be extremely unlikely given kmsg buffers usually + * exceed prz buffer sizes). + */ + if (prz->old_log && prz->old_log_size != size) + persistent_ram_free_old(prz); + if (!prz->old_log) { persistent_ram_ecc_old(prz); prz->old_log = kvzalloc(size, GFP_KERNEL); diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 7c2b75a4448528..de4379a9c79208 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -899,6 +899,7 @@ static struct super_block *quotactl_block(const char __user *special, int cmd) sb_start_write(sb); sb_end_write(sb); put_super(sb); + cond_resched(); goto retry; } return sb; diff --git a/fs/readdir.c b/fs/readdir.c index 7764b863897888..73707b6816e9aa 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -316,6 +316,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, struct getdents_callback buf = { .ctx.actor = filldir, .ctx.count = count, + .ctx.dt_flags_mask = FILLDIR_FLAG_NOINTR, .current_dir = dirent }; int error; @@ -400,6 +401,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, struct getdents_callback64 buf = { .ctx.actor = filldir64, .ctx.count = count, + .ctx.dt_flags_mask = FILLDIR_FLAG_NOINTR, .current_dir = dirent }; int error; @@ -569,6 +571,7 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, struct compat_getdents_callback buf = { .ctx.actor = compat_filldir, .ctx.count = count, + .ctx.dt_flags_mask = FILLDIR_FLAG_NOINTR, .current_dir = dirent, }; int error; diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 0addcc849ff2ca..e83f9b78d7a16e 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -458,7 +458,10 @@ static int romfs_fill_super(struct super_block *sb, struct fs_context *fc) #ifdef CONFIG_BLOCK if (!sb->s_mtd) { - sb_set_blocksize(sb, ROMBSIZE); + if (!sb_set_blocksize(sb, ROMBSIZE)) { + errorf(fc, "romfs: unable to set blocksize\n"); + return -EINVAL; + } } else { sb->s_blocksize = ROMBSIZE; sb->s_blocksize_bits = blksize_bits(ROMBSIZE); diff --git a/fs/smb/client/cached_dir.h b/fs/smb/client/cached_dir.h index 1e383db7c33743..5091bf45345e81 100644 --- a/fs/smb/client/cached_dir.h +++ b/fs/smb/client/cached_dir.h @@ -36,10 +36,10 @@ struct cached_fid { struct list_head entry; struct cached_fids *cfids; const char *path; - bool has_lease:1; - bool is_open:1; - bool on_list:1; - bool file_all_info_is_valid:1; + bool has_lease; + bool is_open; + bool on_list; + bool file_all_info_is_valid; unsigned long time; /* jiffies of when lease was taken */ unsigned long last_access_time; /* jiffies of when last accessed */ struct kref refcount; diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index dcc50a2bfa4b23..bfc9b1ea76fac9 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1374,7 +1374,7 @@ cifs_readv_callback(struct mid_q_entry *mid) } else { size_t trans = rdata->subreq.transferred + rdata->got_bytes; if (trans < rdata->subreq.len && - rdata->subreq.start + trans == ictx->remote_i_size) { + rdata->subreq.start + trans >= ictx->remote_i_size) { rdata->result = 0; __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); } else if (rdata->got_bytes > 0) { diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 2a0d8b87bd8ea8..d8bd3cdc535df7 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -1080,6 +1080,8 @@ static int smb3_reconfigure(struct fs_context *fc) rc = smb3_sync_session_ctx_passwords(cifs_sb, ses); if (rc) { mutex_unlock(&ses->session_mutex); + kfree_sensitive(new_password); + kfree_sensitive(new_password2); return rc; } diff --git a/fs/smb/client/nterr.h b/fs/smb/client/nterr.h index 180602c22355e1..09263c91d07a48 100644 --- a/fs/smb/client/nterr.h +++ b/fs/smb/client/nterr.h @@ -41,10 +41,10 @@ extern const struct nt_err_code_struct nt_errs[]; #define NT_STATUS_MEDIA_CHANGED 0x8000001c #define NT_STATUS_END_OF_MEDIA 0x8000001e #define NT_STATUS_MEDIA_CHECK 0x80000020 -#define NT_STATUS_NO_DATA_DETECTED 0x8000001c +#define NT_STATUS_NO_DATA_DETECTED 0x80000022 #define NT_STATUS_STOPPED_ON_SYMLINK 0x8000002d #define NT_STATUS_DEVICE_REQUIRES_CLEANING 0x80000288 -#define NT_STATUS_DEVICE_DOOR_OPEN 0x80000288 +#define NT_STATUS_DEVICE_DOOR_OPEN 0x80000289 #define NT_STATUS_UNSUCCESSFUL 0xC0000000 | 0x0001 #define NT_STATUS_NOT_IMPLEMENTED 0xC0000000 | 0x0002 #define NT_STATUS_INVALID_INFO_CLASS 0xC0000000 | 0x0003 @@ -70,7 +70,7 @@ extern const struct nt_err_code_struct nt_errs[]; #define NT_STATUS_NO_MEMORY 0xC0000000 | 0x0017 #define NT_STATUS_CONFLICTING_ADDRESSES 0xC0000000 | 0x0018 #define NT_STATUS_NOT_MAPPED_VIEW 0xC0000000 | 0x0019 -#define NT_STATUS_UNABLE_TO_FREE_VM 0x80000000 | 0x001a +#define NT_STATUS_UNABLE_TO_FREE_VM 0xC0000000 | 0x001a #define NT_STATUS_UNABLE_TO_DELETE_SECTION 0xC0000000 | 0x001b #define NT_STATUS_INVALID_SYSTEM_SERVICE 0xC0000000 | 0x001c #define NT_STATUS_ILLEGAL_INSTRUCTION 0xC0000000 | 0x001d diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index a7f6292388306c..e6cdf2efc7f4f4 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -177,6 +177,9 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, &err_iov, &err_buftype); if (rc == -EACCES && retry_without_read_attributes) { + free_rsp_buf(err_buftype, err_iov.iov_base); + memset(&err_iov, 0, sizeof(err_iov)); + err_buftype = CIFS_NO_BUFFER; oparms->desired_access &= ~FILE_READ_ATTRIBUTES; rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, &err_iov, &err_buftype); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 8b4a4573e9c372..e661d40213eabc 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4629,7 +4629,7 @@ smb2_readv_callback(struct mid_q_entry *mid) } else { size_t trans = rdata->subreq.transferred + rdata->got_bytes; if (trans < rdata->subreq.len && - rdata->subreq.start + trans == ictx->remote_i_size) { + rdata->subreq.start + trans >= ictx->remote_i_size) { __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; } diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index c6c428c2e08ddb..c8cef098d48065 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -7,6 +7,7 @@ #include #include #include +#define __SMBDIRECT_SOCKET_DISCONNECT(__sc) smbd_disconnect_rdma_connection(__sc) #include "../common/smbdirect/smbdirect_pdu.h" #include "smbdirect.h" #include "cifs_debug.h" @@ -34,6 +35,10 @@ static void enqueue_reassembly( static struct smbdirect_recv_io *_get_first_reassembly( struct smbdirect_socket *sc); +static int smbd_post_send(struct smbdirect_socket *sc, + struct smbdirect_send_batch *batch, + struct smbdirect_send_io *request); + static int smbd_post_recv( struct smbdirect_socket *sc, struct smbdirect_recv_io *response); @@ -96,8 +101,23 @@ int smbd_send_credit_target = 255; /* The maximum single message size can be sent to remote peer */ int smbd_max_send_size = 1364; -/* The maximum fragmented upper-layer payload receive size supported */ -int smbd_max_fragmented_recv_size = 1024 * 1024; +/* + * The maximum fragmented upper-layer payload receive size supported + * + * Assume max_payload_per_credit is + * smbd_max_receive_size - 24 = 1340 + * + * The maximum number would be + * smbd_receive_credit_max * max_payload_per_credit + * + * 1340 * 255 = 341700 (0x536C4) + * + * The minimum value from the spec is 131072 (0x20000) + * + * For now we use the logic we used in ksmbd before: + * (1364 * 255) / 2 = 173910 (0x2A756) + */ +int smbd_max_fragmented_recv_size = (1364 * 255) / 2; /* The maximum single-message size which can be received */ int smbd_max_receive_size = 1364; @@ -186,6 +206,9 @@ static void smbd_disconnect_rdma_work(struct work_struct *work) struct smbdirect_socket *sc = container_of(work, struct smbdirect_socket, disconnect_work); + if (sc->first_error == 0) + sc->first_error = -ECONNABORTED; + /* * make sure this and other work is not queued again * but here we don't block and avoid @@ -197,9 +220,6 @@ static void smbd_disconnect_rdma_work(struct work_struct *work) disable_work(&sc->idle.immediate_work); disable_delayed_work(&sc->idle.timer_work); - if (sc->first_error == 0) - sc->first_error = -ECONNABORTED; - switch (sc->status) { case SMBDIRECT_SOCKET_NEGOTIATE_NEEDED: case SMBDIRECT_SOCKET_NEGOTIATE_RUNNING: @@ -242,6 +262,9 @@ static void smbd_disconnect_rdma_work(struct work_struct *work) static void smbd_disconnect_rdma_connection(struct smbdirect_socket *sc) { + if (sc->first_error == 0) + sc->first_error = -ECONNABORTED; + /* * make sure other work (than disconnect_work) is * not queued again but here we don't block and avoid @@ -252,9 +275,6 @@ static void smbd_disconnect_rdma_connection(struct smbdirect_socket *sc) disable_work(&sc->idle.immediate_work); disable_delayed_work(&sc->idle.timer_work); - if (sc->first_error == 0) - sc->first_error = -ECONNABORTED; - switch (sc->status) { case SMBDIRECT_SOCKET_RESOLVE_ADDR_FAILED: case SMBDIRECT_SOCKET_RESOLVE_ROUTE_FAILED: @@ -322,27 +342,27 @@ static int smbd_conn_upcall( switch (event->event) { case RDMA_CM_EVENT_ADDR_RESOLVED: - WARN_ON_ONCE(sc->status != SMBDIRECT_SOCKET_RESOLVE_ADDR_RUNNING); + if (SMBDIRECT_CHECK_STATUS_DISCONNECT(sc, SMBDIRECT_SOCKET_RESOLVE_ADDR_RUNNING)) + break; sc->status = SMBDIRECT_SOCKET_RESOLVE_ROUTE_NEEDED; wake_up(&sc->status_wait); break; case RDMA_CM_EVENT_ROUTE_RESOLVED: - WARN_ON_ONCE(sc->status != SMBDIRECT_SOCKET_RESOLVE_ROUTE_RUNNING); + if (SMBDIRECT_CHECK_STATUS_DISCONNECT(sc, SMBDIRECT_SOCKET_RESOLVE_ROUTE_RUNNING)) + break; sc->status = SMBDIRECT_SOCKET_RDMA_CONNECT_NEEDED; wake_up(&sc->status_wait); break; case RDMA_CM_EVENT_ADDR_ERROR: log_rdma_event(ERR, "connecting failed event=%s\n", event_name); - WARN_ON_ONCE(sc->status != SMBDIRECT_SOCKET_RESOLVE_ADDR_RUNNING); sc->status = SMBDIRECT_SOCKET_RESOLVE_ADDR_FAILED; smbd_disconnect_rdma_work(&sc->disconnect_work); break; case RDMA_CM_EVENT_ROUTE_ERROR: log_rdma_event(ERR, "connecting failed event=%s\n", event_name); - WARN_ON_ONCE(sc->status != SMBDIRECT_SOCKET_RESOLVE_ROUTE_RUNNING); sc->status = SMBDIRECT_SOCKET_RESOLVE_ROUTE_FAILED; smbd_disconnect_rdma_work(&sc->disconnect_work); break; @@ -428,7 +448,8 @@ static int smbd_conn_upcall( min_t(u8, sp->responder_resources, peer_responder_resources); - WARN_ON_ONCE(sc->status != SMBDIRECT_SOCKET_RDMA_CONNECT_RUNNING); + if (SMBDIRECT_CHECK_STATUS_DISCONNECT(sc, SMBDIRECT_SOCKET_RDMA_CONNECT_RUNNING)) + break; sc->status = SMBDIRECT_SOCKET_NEGOTIATE_NEEDED; wake_up(&sc->status_wait); break; @@ -437,7 +458,6 @@ static int smbd_conn_upcall( case RDMA_CM_EVENT_UNREACHABLE: case RDMA_CM_EVENT_REJECTED: log_rdma_event(ERR, "connecting failed event=%s\n", event_name); - WARN_ON_ONCE(sc->status != SMBDIRECT_SOCKET_RDMA_CONNECT_RUNNING); sc->status = SMBDIRECT_SOCKET_RDMA_CONNECT_FAILED; smbd_disconnect_rdma_work(&sc->disconnect_work); break; @@ -492,27 +512,103 @@ static inline void *smbdirect_recv_io_payload(struct smbdirect_recv_io *response return (void *)response->packet; } +static struct smbdirect_send_io *smbd_alloc_send_io(struct smbdirect_socket *sc) +{ + struct smbdirect_send_io *msg; + + msg = mempool_alloc(sc->send_io.mem.pool, GFP_KERNEL); + if (!msg) + return ERR_PTR(-ENOMEM); + msg->socket = sc; + INIT_LIST_HEAD(&msg->sibling_list); + msg->num_sge = 0; + + return msg; +} + +static void smbd_free_send_io(struct smbdirect_send_io *msg) +{ + struct smbdirect_socket *sc = msg->socket; + size_t i; + + /* + * The list needs to be empty! + * The caller should take care of it. + */ + WARN_ON_ONCE(!list_empty(&msg->sibling_list)); + + /* + * Note we call ib_dma_unmap_page(), even if some sges are mapped using + * ib_dma_map_single(). + * + * The difference between _single() and _page() only matters for the + * ib_dma_map_*() case. + * + * For the ib_dma_unmap_*() case it does not matter as both take the + * dma_addr_t and dma_unmap_single_attrs() is just an alias to + * dma_unmap_page_attrs(). + */ + for (i = 0; i < msg->num_sge; i++) + ib_dma_unmap_page(sc->ib.dev, + msg->sge[i].addr, + msg->sge[i].length, + DMA_TO_DEVICE); + + mempool_free(msg, sc->send_io.mem.pool); +} + /* Called when a RDMA send is done */ static void send_done(struct ib_cq *cq, struct ib_wc *wc) { - int i; struct smbdirect_send_io *request = container_of(wc->wr_cqe, struct smbdirect_send_io, cqe); struct smbdirect_socket *sc = request->socket; + struct smbdirect_send_io *sibling, *next; int lcredits = 0; log_rdma_send(INFO, "smbdirect_send_io 0x%p completed wc->status=%s\n", request, ib_wc_status_msg(wc->status)); - for (i = 0; i < request->num_sge; i++) - ib_dma_unmap_single(sc->ib.dev, - request->sge[i].addr, - request->sge[i].length, - DMA_TO_DEVICE); - mempool_free(request, sc->send_io.mem.pool); + if (unlikely(!(request->wr.send_flags & IB_SEND_SIGNALED))) { + /* + * This happens when smbdirect_send_io is a sibling + * before the final message, it is signaled on + * error anyway, so we need to skip + * smbdirect_connection_free_send_io here, + * otherwise is will destroy the memory + * of the siblings too, which will cause + * use after free problems for the others + * triggered from ib_drain_qp(). + */ + if (wc->status != IB_WC_SUCCESS) + goto skip_free; + + /* + * This should not happen! + * But we better just close the + * connection... + */ + log_rdma_send(ERR, + "unexpected send completion wc->status=%s (%d) wc->opcode=%d\n", + ib_wc_status_msg(wc->status), wc->status, wc->opcode); + smbd_disconnect_rdma_connection(sc); + return; + } + + /* + * Free possible siblings and then the main send_io + */ + list_for_each_entry_safe(sibling, next, &request->sibling_list, sibling_list) { + list_del_init(&sibling->sibling_list); + smbd_free_send_io(sibling); + lcredits += 1; + } + /* Note this frees wc->wr_cqe, but not wc */ + smbd_free_send_io(request); lcredits += 1; if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_SEND) { +skip_free: if (wc->status != IB_WC_WR_FLUSH_ERR) log_rdma_send(ERR, "wc->status=%s wc->opcode=%d\n", ib_wc_status_msg(wc->status), wc->opcode); @@ -607,6 +703,7 @@ static bool process_negotiation_response( sp->max_frmr_depth * PAGE_SIZE); sp->max_frmr_depth = sp->max_read_write_size / PAGE_SIZE; + atomic_set(&sc->send_io.bcredits.count, 1); sc->recv_io.expected = SMBDIRECT_EXPECT_DATA_TRANSFER; return true; } @@ -617,6 +714,7 @@ static void smbd_post_send_credits(struct work_struct *work) struct smbdirect_recv_io *response; struct smbdirect_socket *sc = container_of(work, struct smbdirect_socket, recv_io.posted.refill_work); + int posted = 0; if (sc->status != SMBDIRECT_SOCKET_CONNECTED) { return; @@ -639,9 +737,21 @@ static void smbd_post_send_credits(struct work_struct *work) } atomic_inc(&sc->recv_io.posted.count); + posted += 1; } } + atomic_add(posted, &sc->recv_io.credits.available); + + /* + * If the last send credit is waiting for credits + * it can grant we need to wake it up + */ + if (posted && + atomic_read(&sc->send_io.bcredits.count) == 0 && + atomic_read(&sc->send_io.credits.count) == 0) + wake_up(&sc->send_io.credits.wait_queue); + /* Promptly send an immediate packet as defined in [MS-SMBD] 3.1.1.1 */ if (atomic_read(&sc->recv_io.credits.count) < sc->recv_io.credits.target - 1) { @@ -658,6 +768,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) container_of(wc->wr_cqe, struct smbdirect_recv_io, cqe); struct smbdirect_socket *sc = response->socket; struct smbdirect_socket_parameters *sp = &sc->parameters; + int current_recv_credits; u16 old_recv_credit_target; u32 data_offset = 0; u32 data_length = 0; @@ -699,7 +810,8 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) negotiate_done = process_negotiation_response(response, wc->byte_len); put_receive_buffer(sc, response); - WARN_ON_ONCE(sc->status != SMBDIRECT_SOCKET_NEGOTIATE_RUNNING); + if (SMBDIRECT_CHECK_STATUS_WARN(sc, SMBDIRECT_SOCKET_NEGOTIATE_RUNNING)) + negotiate_done = false; if (!negotiate_done) { sc->status = SMBDIRECT_SOCKET_NEGOTIATE_FAILED; smbd_disconnect_rdma_connection(sc); @@ -741,7 +853,8 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) } atomic_dec(&sc->recv_io.posted.count); - atomic_dec(&sc->recv_io.credits.count); + current_recv_credits = atomic_dec_return(&sc->recv_io.credits.count); + old_recv_credit_target = sc->recv_io.credits.target; sc->recv_io.credits.target = le16_to_cpu(data_transfer->credits_requested); @@ -777,7 +890,8 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) * reassembly queue and wake up the reading thread */ if (data_length) { - if (sc->recv_io.credits.target > old_recv_credit_target) + if (current_recv_credits <= (sc->recv_io.credits.target / 4) || + sc->recv_io.credits.target > old_recv_credit_target) queue_work(sc->workqueue, &sc->recv_io.posted.refill_work); enqueue_reassembly(sc, response, data_length); @@ -953,16 +1067,13 @@ static int smbd_ia_open( static int smbd_post_send_negotiate_req(struct smbdirect_socket *sc) { struct smbdirect_socket_parameters *sp = &sc->parameters; - struct ib_send_wr send_wr; - int rc = -ENOMEM; + int rc; struct smbdirect_send_io *request; struct smbdirect_negotiate_req *packet; - request = mempool_alloc(sc->send_io.mem.pool, GFP_KERNEL); - if (!request) - return rc; - - request->socket = sc; + request = smbd_alloc_send_io(sc); + if (IS_ERR(request)) + return PTR_ERR(request); packet = smbdirect_send_io_payload(request); packet->min_version = cpu_to_le16(SMBDIRECT_V1); @@ -974,7 +1085,6 @@ static int smbd_post_send_negotiate_req(struct smbdirect_socket *sc) packet->max_fragmented_size = cpu_to_le32(sp->max_fragmented_recv_size); - request->num_sge = 1; request->sge[0].addr = ib_dma_map_single( sc->ib.dev, (void *)packet, sizeof(*packet), DMA_TO_DEVICE); @@ -982,42 +1092,20 @@ static int smbd_post_send_negotiate_req(struct smbdirect_socket *sc) rc = -EIO; goto dma_mapping_failed; } + request->num_sge = 1; request->sge[0].length = sizeof(*packet); request->sge[0].lkey = sc->ib.pd->local_dma_lkey; - ib_dma_sync_single_for_device( - sc->ib.dev, request->sge[0].addr, - request->sge[0].length, DMA_TO_DEVICE); - - request->cqe.done = send_done; - - send_wr.next = NULL; - send_wr.wr_cqe = &request->cqe; - send_wr.sg_list = request->sge; - send_wr.num_sge = request->num_sge; - send_wr.opcode = IB_WR_SEND; - send_wr.send_flags = IB_SEND_SIGNALED; - - log_rdma_send(INFO, "sge addr=0x%llx length=%u lkey=0x%x\n", - request->sge[0].addr, - request->sge[0].length, request->sge[0].lkey); - - atomic_inc(&sc->send_io.pending.count); - rc = ib_post_send(sc->ib.qp, &send_wr, NULL); + rc = smbd_post_send(sc, NULL, request); if (!rc) return 0; - /* if we reach here, post send failed */ - log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc); - atomic_dec(&sc->send_io.pending.count); - ib_dma_unmap_single(sc->ib.dev, request->sge[0].addr, - request->sge[0].length, DMA_TO_DEVICE); - - smbd_disconnect_rdma_connection(sc); + if (rc == -EAGAIN) + rc = -EIO; dma_mapping_failed: - mempool_free(request, sc->send_io.mem.pool); + smbd_free_send_io(request); return rc; } @@ -1031,19 +1119,38 @@ static int smbd_post_send_negotiate_req(struct smbdirect_socket *sc) */ static int manage_credits_prior_sending(struct smbdirect_socket *sc) { + int missing; + int available; int new_credits; if (atomic_read(&sc->recv_io.credits.count) >= sc->recv_io.credits.target) return 0; - new_credits = atomic_read(&sc->recv_io.posted.count); - if (new_credits == 0) + missing = (int)sc->recv_io.credits.target - atomic_read(&sc->recv_io.credits.count); + available = atomic_xchg(&sc->recv_io.credits.available, 0); + new_credits = (u16)min3(U16_MAX, missing, available); + if (new_credits <= 0) { + /* + * If credits are available, but not granted + * we need to re-add them again. + */ + if (available) + atomic_add(available, &sc->recv_io.credits.available); return 0; + } - new_credits -= atomic_read(&sc->recv_io.credits.count); - if (new_credits <= 0) - return 0; + if (new_credits < available) { + /* + * Readd the remaining available again. + */ + available -= new_credits; + atomic_add(available, &sc->recv_io.credits.available); + } + /* + * Remember we granted the credits + */ + atomic_add(new_credits, &sc->recv_io.credits.count); return new_credits; } @@ -1073,12 +1180,27 @@ static int manage_keep_alive_before_sending(struct smbdirect_socket *sc) return 0; } +static int smbd_ib_post_send(struct smbdirect_socket *sc, + struct ib_send_wr *wr) +{ + int ret; + + atomic_inc(&sc->send_io.pending.count); + ret = ib_post_send(sc->ib.qp, wr, NULL); + if (ret) { + pr_err("failed to post send: %d\n", ret); + smbd_disconnect_rdma_connection(sc); + ret = -EAGAIN; + } + return ret; +} + /* Post the send request */ static int smbd_post_send(struct smbdirect_socket *sc, - struct smbdirect_send_io *request) + struct smbdirect_send_batch *batch, + struct smbdirect_send_io *request) { - struct ib_send_wr send_wr; - int rc, i; + int i; for (i = 0; i < request->num_sge; i++) { log_rdma_send(INFO, @@ -1092,79 +1214,245 @@ static int smbd_post_send(struct smbdirect_socket *sc, } request->cqe.done = send_done; + request->wr.next = NULL; + request->wr.sg_list = request->sge; + request->wr.num_sge = request->num_sge; + request->wr.opcode = IB_WR_SEND; + + if (batch) { + request->wr.wr_cqe = NULL; + request->wr.send_flags = 0; + if (!list_empty(&batch->msg_list)) { + struct smbdirect_send_io *last; + + last = list_last_entry(&batch->msg_list, + struct smbdirect_send_io, + sibling_list); + last->wr.next = &request->wr; + } + list_add_tail(&request->sibling_list, &batch->msg_list); + batch->wr_cnt++; + return 0; + } - send_wr.next = NULL; - send_wr.wr_cqe = &request->cqe; - send_wr.sg_list = request->sge; - send_wr.num_sge = request->num_sge; - send_wr.opcode = IB_WR_SEND; - send_wr.send_flags = IB_SEND_SIGNALED; + request->wr.wr_cqe = &request->cqe; + request->wr.send_flags = IB_SEND_SIGNALED; + return smbd_ib_post_send(sc, &request->wr); +} - rc = ib_post_send(sc->ib.qp, &send_wr, NULL); - if (rc) { - log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc); - smbd_disconnect_rdma_connection(sc); - rc = -EAGAIN; +static void smbd_send_batch_init(struct smbdirect_send_batch *batch, + bool need_invalidate_rkey, + unsigned int remote_key) +{ + INIT_LIST_HEAD(&batch->msg_list); + batch->wr_cnt = 0; + batch->need_invalidate_rkey = need_invalidate_rkey; + batch->remote_key = remote_key; + batch->credit = 0; +} + +static int smbd_send_batch_flush(struct smbdirect_socket *sc, + struct smbdirect_send_batch *batch, + bool is_last) +{ + struct smbdirect_send_io *first, *last; + int ret = 0; + + if (list_empty(&batch->msg_list)) + goto release_credit; + + first = list_first_entry(&batch->msg_list, + struct smbdirect_send_io, + sibling_list); + last = list_last_entry(&batch->msg_list, + struct smbdirect_send_io, + sibling_list); + + if (batch->need_invalidate_rkey) { + first->wr.opcode = IB_WR_SEND_WITH_INV; + first->wr.ex.invalidate_rkey = batch->remote_key; + batch->need_invalidate_rkey = false; + batch->remote_key = 0; } - return rc; + last->wr.send_flags = IB_SEND_SIGNALED; + last->wr.wr_cqe = &last->cqe; + + /* + * Remove last from batch->msg_list + * and splice the rest of batch->msg_list + * to last->sibling_list. + * + * batch->msg_list is a valid empty list + * at the end. + */ + list_del_init(&last->sibling_list); + list_splice_tail_init(&batch->msg_list, &last->sibling_list); + batch->wr_cnt = 0; + + ret = smbd_ib_post_send(sc, &first->wr); + if (ret) { + struct smbdirect_send_io *sibling, *next; + + list_for_each_entry_safe(sibling, next, &last->sibling_list, sibling_list) { + list_del_init(&sibling->sibling_list); + smbd_free_send_io(sibling); + } + smbd_free_send_io(last); + } + +release_credit: + if (is_last && !ret && batch->credit) { + atomic_add(batch->credit, &sc->send_io.bcredits.count); + batch->credit = 0; + wake_up(&sc->send_io.bcredits.wait_queue); + } + + return ret; +} + +static int wait_for_credits(struct smbdirect_socket *sc, + wait_queue_head_t *waitq, atomic_t *total_credits, + int needed) +{ + int ret; + + do { + if (atomic_sub_return(needed, total_credits) >= 0) + return 0; + + atomic_add(needed, total_credits); + ret = wait_event_interruptible(*waitq, + atomic_read(total_credits) >= needed || + sc->status != SMBDIRECT_SOCKET_CONNECTED); + + if (sc->status != SMBDIRECT_SOCKET_CONNECTED) + return -ENOTCONN; + else if (ret < 0) + return ret; + } while (true); +} + +static int wait_for_send_bcredit(struct smbdirect_socket *sc, + struct smbdirect_send_batch *batch) +{ + int ret; + + if (batch->credit) + return 0; + + ret = wait_for_credits(sc, + &sc->send_io.bcredits.wait_queue, + &sc->send_io.bcredits.count, + 1); + if (ret) + return ret; + + batch->credit = 1; + return 0; +} + +static int wait_for_send_lcredit(struct smbdirect_socket *sc, + struct smbdirect_send_batch *batch) +{ + if (batch && (atomic_read(&sc->send_io.lcredits.count) <= 1)) { + int ret; + + ret = smbd_send_batch_flush(sc, batch, false); + if (ret) + return ret; + } + + return wait_for_credits(sc, + &sc->send_io.lcredits.wait_queue, + &sc->send_io.lcredits.count, + 1); +} + +static int wait_for_send_credits(struct smbdirect_socket *sc, + struct smbdirect_send_batch *batch) +{ + if (batch && + (batch->wr_cnt >= 16 || atomic_read(&sc->send_io.credits.count) <= 1)) { + int ret; + + ret = smbd_send_batch_flush(sc, batch, false); + if (ret) + return ret; + } + + return wait_for_credits(sc, + &sc->send_io.credits.wait_queue, + &sc->send_io.credits.count, + 1); } static int smbd_post_send_iter(struct smbdirect_socket *sc, + struct smbdirect_send_batch *batch, struct iov_iter *iter, int *_remaining_data_length) { struct smbdirect_socket_parameters *sp = &sc->parameters; - int i, rc; + int rc; int header_length; int data_length; struct smbdirect_send_io *request; struct smbdirect_data_transfer *packet; int new_credits = 0; + struct smbdirect_send_batch _batch; -wait_lcredit: - /* Wait for local send credits */ - rc = wait_event_interruptible(sc->send_io.lcredits.wait_queue, - atomic_read(&sc->send_io.lcredits.count) > 0 || - sc->status != SMBDIRECT_SOCKET_CONNECTED); - if (rc) - goto err_wait_lcredit; + if (!batch) { + smbd_send_batch_init(&_batch, false, 0); + batch = &_batch; + } - if (sc->status != SMBDIRECT_SOCKET_CONNECTED) { - log_outgoing(ERR, "disconnected not sending on wait_credit\n"); + rc = wait_for_send_bcredit(sc, batch); + if (rc) { + log_outgoing(ERR, "disconnected not sending on wait_bcredit\n"); rc = -EAGAIN; - goto err_wait_lcredit; - } - if (unlikely(atomic_dec_return(&sc->send_io.lcredits.count) < 0)) { - atomic_inc(&sc->send_io.lcredits.count); - goto wait_lcredit; + goto err_wait_bcredit; } -wait_credit: - /* Wait for send credits. A SMBD packet needs one credit */ - rc = wait_event_interruptible(sc->send_io.credits.wait_queue, - atomic_read(&sc->send_io.credits.count) > 0 || - sc->status != SMBDIRECT_SOCKET_CONNECTED); - if (rc) - goto err_wait_credit; + rc = wait_for_send_lcredit(sc, batch); + if (rc) { + log_outgoing(ERR, "disconnected not sending on wait_lcredit\n"); + rc = -EAGAIN; + goto err_wait_lcredit; + } - if (sc->status != SMBDIRECT_SOCKET_CONNECTED) { + rc = wait_for_send_credits(sc, batch); + if (rc) { log_outgoing(ERR, "disconnected not sending on wait_credit\n"); rc = -EAGAIN; goto err_wait_credit; } - if (unlikely(atomic_dec_return(&sc->send_io.credits.count) < 0)) { - atomic_inc(&sc->send_io.credits.count); - goto wait_credit; + + new_credits = manage_credits_prior_sending(sc); + if (new_credits == 0 && + atomic_read(&sc->send_io.credits.count) == 0 && + atomic_read(&sc->recv_io.credits.count) == 0) { + queue_work(sc->workqueue, &sc->recv_io.posted.refill_work); + rc = wait_event_interruptible(sc->send_io.credits.wait_queue, + atomic_read(&sc->send_io.credits.count) >= 1 || + atomic_read(&sc->recv_io.credits.available) >= 1 || + sc->status != SMBDIRECT_SOCKET_CONNECTED); + if (sc->status != SMBDIRECT_SOCKET_CONNECTED) + rc = -ENOTCONN; + if (rc < 0) { + log_outgoing(ERR, "disconnected not sending on last credit\n"); + rc = -EAGAIN; + goto err_wait_credit; + } + + new_credits = manage_credits_prior_sending(sc); } - request = mempool_alloc(sc->send_io.mem.pool, GFP_KERNEL); - if (!request) { - rc = -ENOMEM; + request = smbd_alloc_send_io(sc); + if (IS_ERR(request)) { + rc = PTR_ERR(request); goto err_alloc; } - request->socket = sc; memset(request->sge, 0, sizeof(request->sge)); /* Map the packet to DMA */ @@ -1213,9 +1501,6 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc, /* Fill in the packet header */ packet->credits_requested = cpu_to_le16(sp->send_credit_target); - - new_credits = manage_credits_prior_sending(sc); - atomic_add(new_credits, &sc->recv_io.credits.count); packet->credits_granted = cpu_to_le16(new_credits); packet->flags = 0; @@ -1238,32 +1523,18 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc, le32_to_cpu(packet->data_length), le32_to_cpu(packet->remaining_data_length)); - /* - * Now that we got a local and a remote credit - * we add us as pending - */ - atomic_inc(&sc->send_io.pending.count); - - rc = smbd_post_send(sc, request); - if (!rc) - return 0; - - if (atomic_dec_and_test(&sc->send_io.pending.count)) - wake_up(&sc->send_io.pending.zero_wait_queue); + rc = smbd_post_send(sc, batch, request); + if (!rc) { + if (batch != &_batch) + return 0; - wake_up(&sc->send_io.pending.dec_wait_queue); + rc = smbd_send_batch_flush(sc, batch, true); + if (!rc) + return 0; + } err_dma: - for (i = 0; i < request->num_sge; i++) - if (request->sge[i].addr) - ib_dma_unmap_single(sc->ib.dev, - request->sge[i].addr, - request->sge[i].length, - DMA_TO_DEVICE); - mempool_free(request, sc->send_io.mem.pool); - - /* roll back the granted receive credits */ - atomic_sub(new_credits, &sc->recv_io.credits.count); + smbd_free_send_io(request); err_alloc: atomic_inc(&sc->send_io.credits.count); @@ -1274,6 +1545,11 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc, wake_up(&sc->send_io.lcredits.wait_queue); err_wait_lcredit: + atomic_add(batch->credit, &sc->send_io.bcredits.count); + batch->credit = 0; + wake_up(&sc->send_io.bcredits.wait_queue); + +err_wait_bcredit: return rc; } @@ -1287,10 +1563,11 @@ static int smbd_post_send_empty(struct smbdirect_socket *sc) int remaining_data_length = 0; sc->statistics.send_empty++; - return smbd_post_send_iter(sc, NULL, &remaining_data_length); + return smbd_post_send_iter(sc, NULL, NULL, &remaining_data_length); } static int smbd_post_send_full_iter(struct smbdirect_socket *sc, + struct smbdirect_send_batch *batch, struct iov_iter *iter, int *_remaining_data_length) { @@ -1303,7 +1580,7 @@ static int smbd_post_send_full_iter(struct smbdirect_socket *sc, */ while (iov_iter_count(iter) > 0) { - rc = smbd_post_send_iter(sc, iter, _remaining_data_length); + rc = smbd_post_send_iter(sc, batch, iter, _remaining_data_length); if (rc < 0) break; } @@ -2225,8 +2502,10 @@ int smbd_send(struct TCP_Server_Info *server, struct smbdirect_socket_parameters *sp = &sc->parameters; struct smb_rqst *rqst; struct iov_iter iter; + struct smbdirect_send_batch batch; unsigned int remaining_data_length, klen; int rc, i, rqst_idx; + int error = 0; if (sc->status != SMBDIRECT_SOCKET_CONNECTED) return -EAGAIN; @@ -2251,6 +2530,7 @@ int smbd_send(struct TCP_Server_Info *server, num_rqst, remaining_data_length); rqst_idx = 0; + smbd_send_batch_init(&batch, false, 0); do { rqst = &rqst_array[rqst_idx]; @@ -2269,20 +2549,28 @@ int smbd_send(struct TCP_Server_Info *server, klen += rqst->rq_iov[i].iov_len; iov_iter_kvec(&iter, ITER_SOURCE, rqst->rq_iov, rqst->rq_nvec, klen); - rc = smbd_post_send_full_iter(sc, &iter, &remaining_data_length); - if (rc < 0) + rc = smbd_post_send_full_iter(sc, &batch, &iter, &remaining_data_length); + if (rc < 0) { + error = rc; break; + } if (iov_iter_count(&rqst->rq_iter) > 0) { /* And then the data pages if there are any */ - rc = smbd_post_send_full_iter(sc, &rqst->rq_iter, + rc = smbd_post_send_full_iter(sc, &batch, &rqst->rq_iter, &remaining_data_length); - if (rc < 0) + if (rc < 0) { + error = rc; break; + } } } while (++rqst_idx < num_rqst); + rc = smbd_send_batch_flush(sc, &batch, true); + if (unlikely(!rc && error)) + rc = error; + /* * As an optimization, we don't wait for individual I/O to finish * before sending the next one. diff --git a/fs/smb/common/smbdirect/smbdirect_socket.h b/fs/smb/common/smbdirect/smbdirect_socket.h index ee5a90d691c898..ca22b7c2d3a7fe 100644 --- a/fs/smb/common/smbdirect/smbdirect_socket.h +++ b/fs/smb/common/smbdirect/smbdirect_socket.h @@ -74,6 +74,19 @@ const char *smbdirect_socket_status_string(enum smbdirect_socket_status status) return ""; } +/* + * This can be used with %1pe to print errors as strings or '0' + * And it avoids warnings like: warn: passing zero to 'ERR_PTR' + * from smatch -p=kernel --pedantic + */ +static __always_inline +const void * __must_check SMBDIRECT_DEBUG_ERR_PTR(long error) +{ + if (error == 0) + return NULL; + return ERR_PTR(error); +} + enum smbdirect_keepalive_status { SMBDIRECT_KEEPALIVE_NONE, SMBDIRECT_KEEPALIVE_PENDING, @@ -141,6 +154,17 @@ struct smbdirect_socket { mempool_t *pool; } mem; + /* + * This is a coordination for smbdirect_send_batch. + * + * There's only one possible credit, which means + * only one instance is running at a time. + */ + struct { + atomic_t count; + wait_queue_head_t wait_queue; + } bcredits; + /* * The local credit state for ib_post_send() */ @@ -218,6 +242,7 @@ struct smbdirect_socket { */ struct { u16 target; + atomic_t available; atomic_t count; } credits; @@ -345,6 +370,9 @@ static __always_inline void smbdirect_socket_init(struct smbdirect_socket *sc) INIT_DELAYED_WORK(&sc->idle.timer_work, __smbdirect_socket_disabled_work); disable_delayed_work_sync(&sc->idle.timer_work); + atomic_set(&sc->send_io.bcredits.count, 0); + init_waitqueue_head(&sc->send_io.bcredits.wait_queue); + atomic_set(&sc->send_io.lcredits.count, 0); init_waitqueue_head(&sc->send_io.lcredits.wait_queue); @@ -362,6 +390,7 @@ static __always_inline void smbdirect_socket_init(struct smbdirect_socket *sc) INIT_WORK(&sc->recv_io.posted.refill_work, __smbdirect_socket_disabled_work); disable_work_sync(&sc->recv_io.posted.refill_work); + atomic_set(&sc->recv_io.credits.available, 0); atomic_set(&sc->recv_io.credits.count, 0); INIT_LIST_HEAD(&sc->recv_io.reassembly.list); @@ -381,6 +410,44 @@ static __always_inline void smbdirect_socket_init(struct smbdirect_socket *sc) init_waitqueue_head(&sc->mr_io.cleanup.wait_queue); } +#define __SMBDIRECT_CHECK_STATUS_FAILED(__sc, __expected_status, __error_cmd, __unexpected_cmd) ({ \ + bool __failed = false; \ + if (unlikely((__sc)->first_error)) { \ + __failed = true; \ + __error_cmd \ + } else if (unlikely((__sc)->status != (__expected_status))) { \ + __failed = true; \ + __unexpected_cmd \ + } \ + __failed; \ +}) + +#define __SMBDIRECT_CHECK_STATUS_WARN(__sc, __expected_status, __unexpected_cmd) \ + __SMBDIRECT_CHECK_STATUS_FAILED(__sc, __expected_status, \ + , \ + { \ + const struct sockaddr_storage *__src = NULL; \ + const struct sockaddr_storage *__dst = NULL; \ + if ((__sc)->rdma.cm_id) { \ + __src = &(__sc)->rdma.cm_id->route.addr.src_addr; \ + __dst = &(__sc)->rdma.cm_id->route.addr.dst_addr; \ + } \ + WARN_ONCE(1, \ + "expected[%s] != %s first_error=%1pe local=%pISpsfc remote=%pISpsfc\n", \ + smbdirect_socket_status_string(__expected_status), \ + smbdirect_socket_status_string((__sc)->status), \ + SMBDIRECT_DEBUG_ERR_PTR((__sc)->first_error), \ + __src, __dst); \ + __unexpected_cmd \ + }) + +#define SMBDIRECT_CHECK_STATUS_WARN(__sc, __expected_status) \ + __SMBDIRECT_CHECK_STATUS_WARN(__sc, __expected_status, /* nothing */) + +#define SMBDIRECT_CHECK_STATUS_DISCONNECT(__sc, __expected_status) \ + __SMBDIRECT_CHECK_STATUS_WARN(__sc, __expected_status, \ + __SMBDIRECT_SOCKET_DISCONNECT(__sc);) + struct smbdirect_send_io { struct smbdirect_socket *socket; struct ib_cqe cqe; @@ -420,6 +487,8 @@ struct smbdirect_send_batch { */ bool need_invalidate_rkey; u32 remote_key; + + int credit; }; struct smbdirect_recv_io { diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c index ecfc5750867124..d3483d9c757c79 100644 --- a/fs/smb/server/mgmt/tree_connect.c +++ b/fs/smb/server/mgmt/tree_connect.c @@ -78,7 +78,6 @@ ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name) tree_conn->t_state = TREE_NEW; status.tree_conn = tree_conn; atomic_set(&tree_conn->refcount, 1); - init_waitqueue_head(&tree_conn->refcount_q); ret = xa_err(xa_store(&sess->tree_conns, tree_conn->id, tree_conn, KSMBD_DEFAULT_GFP)); @@ -100,14 +99,8 @@ ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name) void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon) { - /* - * Checking waitqueue to releasing tree connect on - * tree disconnect. waitqueue_active is safe because it - * uses atomic operation for condition. - */ - if (!atomic_dec_return(&tcon->refcount) && - waitqueue_active(&tcon->refcount_q)) - wake_up(&tcon->refcount_q); + if (atomic_dec_and_test(&tcon->refcount)) + kfree(tcon); } int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, @@ -119,14 +112,11 @@ int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, xa_erase(&sess->tree_conns, tree_conn->id); write_unlock(&sess->tree_conns_lock); - if (!atomic_dec_and_test(&tree_conn->refcount)) - wait_event(tree_conn->refcount_q, - atomic_read(&tree_conn->refcount) == 0); - ret = ksmbd_ipc_tree_disconnect_request(sess->id, tree_conn->id); ksmbd_release_tree_conn_id(sess, tree_conn->id); ksmbd_share_config_put(tree_conn->share_conf); - kfree(tree_conn); + if (atomic_dec_and_test(&tree_conn->refcount)) + kfree(tree_conn); return ret; } diff --git a/fs/smb/server/mgmt/tree_connect.h b/fs/smb/server/mgmt/tree_connect.h index a42cdd05104114..f0023d86716f25 100644 --- a/fs/smb/server/mgmt/tree_connect.h +++ b/fs/smb/server/mgmt/tree_connect.h @@ -33,7 +33,6 @@ struct ksmbd_tree_connect { int maximal_access; bool posix_extensions; atomic_t refcount; - wait_queue_head_t refcount_q; unsigned int t_state; }; diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index 1c181ef9992957..26cb87625f1c6b 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -32,12 +32,14 @@ static void free_channel_list(struct ksmbd_session *sess) struct channel *chann; unsigned long index; + down_write(&sess->chann_lock); xa_for_each(&sess->ksmbd_chann_list, index, chann) { xa_erase(&sess->ksmbd_chann_list, index); kfree(chann); } xa_destroy(&sess->ksmbd_chann_list); + up_write(&sess->chann_lock); } static void __session_rpc_close(struct ksmbd_session *sess, @@ -220,7 +222,9 @@ static int ksmbd_chann_del(struct ksmbd_conn *conn, struct ksmbd_session *sess) { struct channel *chann; + down_write(&sess->chann_lock); chann = xa_erase(&sess->ksmbd_chann_list, (long)conn); + up_write(&sess->chann_lock); if (!chann) return -ENOENT; @@ -325,8 +329,10 @@ struct ksmbd_session *ksmbd_session_lookup_all(struct ksmbd_conn *conn, sess = ksmbd_session_lookup(conn, id); if (!sess && conn->binding) sess = ksmbd_session_lookup_slowpath(id); - if (sess && sess->state != SMB2_SESSION_VALID) + if (sess && sess->state != SMB2_SESSION_VALID) { + ksmbd_user_session_put(sess); sess = NULL; + } return sess; } @@ -452,6 +458,7 @@ static struct ksmbd_session *__session_create(int protocol) rwlock_init(&sess->tree_conns_lock); atomic_set(&sess->refcnt, 2); init_rwsem(&sess->rpc_lock); + init_rwsem(&sess->chann_lock); ret = __init_smb2_session(sess); if (ret) diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index c5749d6ec7151c..cba7f688f6b577 100644 --- a/fs/smb/server/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h @@ -49,6 +49,7 @@ struct ksmbd_session { char sess_key[CIFS_KEY_SIZE]; struct hlist_node hlist; + struct rw_semaphore chann_lock; struct xarray ksmbd_chann_list; struct xarray tree_conns; struct ida tree_conn_ida; diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 40420544cc25a2..ef7a24e31f506f 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -126,21 +126,21 @@ static int __process_request(struct ksmbd_work *work, struct ksmbd_conn *conn, andx_again: if (command >= conn->max_cmds) { conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER); - return SERVER_HANDLER_CONTINUE; + return SERVER_HANDLER_ABORT; } cmds = &conn->cmds[command]; if (!cmds->proc) { ksmbd_debug(SMB, "*** not implemented yet cmd = %x\n", command); conn->ops->set_rsp_status(work, STATUS_NOT_IMPLEMENTED); - return SERVER_HANDLER_CONTINUE; + return SERVER_HANDLER_ABORT; } if (work->sess && conn->ops->is_sign_req(work, command)) { ret = conn->ops->check_sign_req(work); if (!ret) { conn->ops->set_rsp_status(work, STATUS_ACCESS_DENIED); - return SERVER_HANDLER_CONTINUE; + return SERVER_HANDLER_ABORT; } } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index f901ae18e68adf..bf8c4805943672 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -79,7 +79,13 @@ static inline bool check_session_id(struct ksmbd_conn *conn, u64 id) struct channel *lookup_chann_list(struct ksmbd_session *sess, struct ksmbd_conn *conn) { - return xa_load(&sess->ksmbd_chann_list, (long)conn); + struct channel *chann; + + down_read(&sess->chann_lock); + chann = xa_load(&sess->ksmbd_chann_list, (long)conn); + up_read(&sess->chann_lock); + + return chann; } /** @@ -1563,8 +1569,10 @@ static int ntlm_authenticate(struct ksmbd_work *work, return -ENOMEM; chann->conn = conn; + down_write(&sess->chann_lock); old = xa_store(&sess->ksmbd_chann_list, (long)conn, chann, KSMBD_DEFAULT_GFP); + up_write(&sess->chann_lock); if (xa_is_err(old)) { kfree(chann); return xa_err(old); @@ -1661,8 +1669,10 @@ static int krb5_authenticate(struct ksmbd_work *work, return -ENOMEM; chann->conn = conn; + down_write(&sess->chann_lock); old = xa_store(&sess->ksmbd_chann_list, (long)conn, chann, KSMBD_DEFAULT_GFP); + up_write(&sess->chann_lock); if (xa_is_err(old)) { kfree(chann); return xa_err(old); @@ -2200,7 +2210,6 @@ int smb2_tree_disconnect(struct ksmbd_work *work) goto err_out; } - WARN_ON_ONCE(atomic_dec_and_test(&tcon->refcount)); tcon->t_state = TREE_DISCONNECTED; write_unlock(&sess->tree_conns_lock); @@ -2210,8 +2219,6 @@ int smb2_tree_disconnect(struct ksmbd_work *work) goto err_out; } - work->tcon = NULL; - rsp->StructureSize = cpu_to_le16(4); err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_tree_disconnect_rsp)); @@ -2294,7 +2301,7 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work) { struct smb2_create_rsp *rsp; struct smb2_create_req *req; - int id; + int id = -1; int err; char *name; @@ -2351,6 +2358,9 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work) break; } + if (id >= 0) + ksmbd_session_rpc_close(work->sess, id); + if (!IS_ERR(name)) kfree(name); @@ -2376,7 +2386,7 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, int rc = 0; unsigned int next = 0; - if (buf_len < sizeof(struct smb2_ea_info) + eabuf->EaNameLength + + if (buf_len < sizeof(struct smb2_ea_info) + eabuf->EaNameLength + 1 + le16_to_cpu(eabuf->EaValueLength)) return -EINVAL; @@ -2453,7 +2463,7 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, break; } - if (buf_len < sizeof(struct smb2_ea_info) + eabuf->EaNameLength + + if (buf_len < sizeof(struct smb2_ea_info) + eabuf->EaNameLength + 1 + le16_to_cpu(eabuf->EaValueLength)) { rc = -EINVAL; break; @@ -2822,6 +2832,7 @@ static int parse_durable_handle_context(struct ksmbd_work *work, SMB2_CLIENT_GUID_SIZE)) { if (!(req->hdr.Flags & SMB2_FLAGS_REPLAY_OPERATION)) { err = -ENOEXEC; + ksmbd_put_durable_fd(dh_info->fp); goto out; } @@ -3019,10 +3030,10 @@ int smb2_open(struct ksmbd_work *work) file_info = FILE_OPENED; rc = ksmbd_vfs_getattr(&fp->filp->f_path, &stat); + ksmbd_put_durable_fd(fp); if (rc) goto err_out2; - ksmbd_put_durable_fd(fp); goto reconnected_fp; } } else if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) @@ -4936,8 +4947,10 @@ static int get_file_all_info(struct ksmbd_work *work, ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); - if (ret) + if (ret) { + kfree(filename); return ret; + } ksmbd_debug(SMB, "filename = %s\n", filename); delete_pending = ksmbd_inode_pending_delete(fp); @@ -8164,7 +8177,7 @@ int smb2_ioctl(struct ksmbd_work *work) id = req->VolatileFileId; if (req->Flags != cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL)) { - rsp->hdr.Status = STATUS_NOT_SUPPORTED; + ret = -EOPNOTSUPP; goto out; } @@ -8184,8 +8197,9 @@ int smb2_ioctl(struct ksmbd_work *work) case FSCTL_DFS_GET_REFERRALS: case FSCTL_DFS_GET_REFERRALS_EX: /* Not support DFS yet */ + ret = -EOPNOTSUPP; rsp->hdr.Status = STATUS_FS_DRIVER_REQUIRED; - goto out; + goto out2; case FSCTL_CREATE_OR_GET_OBJECT_ID: { struct file_object_buf_type1_ioctl_rsp *obj_buf; @@ -8475,8 +8489,10 @@ int smb2_ioctl(struct ksmbd_work *work) rsp->hdr.Status = STATUS_BUFFER_TOO_SMALL; else if (ret < 0 || rsp->hdr.Status == 0) rsp->hdr.Status = STATUS_INVALID_PARAMETER; + +out2: smb2_set_err_rsp(work); - return 0; + return ret; } /** diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 2c08cccfa6809f..2dbabe2d800554 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -553,12 +553,16 @@ static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle up_write(&ipc_msg_table_lock); ret = ipc_msg_send(msg); - if (ret) + if (ret) { + down_write(&ipc_msg_table_lock); goto out; + } ret = wait_event_interruptible_timeout(entry.wait, entry.response != NULL, IPC_WAIT_TIMEOUT); + + down_write(&ipc_msg_table_lock); if (entry.response) { ret = ipc_validate_msg(&entry); if (ret) { @@ -567,7 +571,6 @@ static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle } } out: - down_write(&ipc_msg_table_lock); hash_del(&entry.ipc_table_hlist); up_write(&ipc_msg_table_lock); return entry.response; diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index e2be9a49615461..4e74934e1f2778 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -19,6 +19,8 @@ #include #include +#define __SMBDIRECT_SOCKET_DISCONNECT(__sc) smb_direct_disconnect_rdma_connection(__sc) + #include "glob.h" #include "connection.h" #include "smb_common.h" @@ -219,6 +221,7 @@ static void smb_direct_disconnect_wake_up_all(struct smbdirect_socket *sc) * in order to notice the broken connection. */ wake_up_all(&sc->status_wait); + wake_up_all(&sc->send_io.bcredits.wait_queue); wake_up_all(&sc->send_io.lcredits.wait_queue); wake_up_all(&sc->send_io.credits.wait_queue); wake_up_all(&sc->send_io.pending.zero_wait_queue); @@ -231,6 +234,9 @@ static void smb_direct_disconnect_rdma_work(struct work_struct *work) struct smbdirect_socket *sc = container_of(work, struct smbdirect_socket, disconnect_work); + if (sc->first_error == 0) + sc->first_error = -ECONNABORTED; + /* * make sure this and other work is not queued again * but here we don't block and avoid @@ -241,9 +247,6 @@ static void smb_direct_disconnect_rdma_work(struct work_struct *work) disable_delayed_work(&sc->idle.timer_work); disable_work(&sc->idle.immediate_work); - if (sc->first_error == 0) - sc->first_error = -ECONNABORTED; - switch (sc->status) { case SMBDIRECT_SOCKET_NEGOTIATE_NEEDED: case SMBDIRECT_SOCKET_NEGOTIATE_RUNNING: @@ -287,6 +290,9 @@ static void smb_direct_disconnect_rdma_work(struct work_struct *work) static void smb_direct_disconnect_rdma_connection(struct smbdirect_socket *sc) { + if (sc->first_error == 0) + sc->first_error = -ECONNABORTED; + /* * make sure other work (than disconnect_work) is * not queued again but here we don't block and avoid @@ -296,9 +302,6 @@ smb_direct_disconnect_rdma_connection(struct smbdirect_socket *sc) disable_work(&sc->idle.immediate_work); disable_delayed_work(&sc->idle.timer_work); - if (sc->first_error == 0) - sc->first_error = -ECONNABORTED; - switch (sc->status) { case SMBDIRECT_SOCKET_RESOLVE_ADDR_FAILED: case SMBDIRECT_SOCKET_RESOLVE_ROUTE_FAILED: @@ -639,7 +642,18 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) return; } sc->recv_io.reassembly.full_packet_received = true; - WARN_ON_ONCE(sc->status != SMBDIRECT_SOCKET_NEGOTIATE_NEEDED); + /* + * Some drivers (at least mlx5_ib) might post a + * recv completion before RDMA_CM_EVENT_ESTABLISHED, + * we need to adjust our expectation in that case. + */ + if (!sc->first_error && sc->status == SMBDIRECT_SOCKET_RDMA_CONNECT_RUNNING) + sc->status = SMBDIRECT_SOCKET_NEGOTIATE_NEEDED; + if (SMBDIRECT_CHECK_STATUS_WARN(sc, SMBDIRECT_SOCKET_NEGOTIATE_NEEDED)) { + put_recvmsg(sc, recvmsg); + smb_direct_disconnect_rdma_connection(sc); + return; + } sc->status = SMBDIRECT_SOCKET_NEGOTIATE_RUNNING; enqueue_reassembly(sc, recvmsg, 0); wake_up(&sc->status_wait); @@ -648,6 +662,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) struct smbdirect_data_transfer *data_transfer = (struct smbdirect_data_transfer *)recvmsg->packet; u32 remaining_data_length, data_offset, data_length; + int current_recv_credits; u16 old_recv_credit_target; if (wc->byte_len < @@ -686,7 +701,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) } atomic_dec(&sc->recv_io.posted.count); - atomic_dec(&sc->recv_io.credits.count); + current_recv_credits = atomic_dec_return(&sc->recv_io.credits.count); old_recv_credit_target = sc->recv_io.credits.target; sc->recv_io.credits.target = @@ -706,7 +721,8 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) wake_up(&sc->send_io.credits.wait_queue); if (data_length) { - if (sc->recv_io.credits.target > old_recv_credit_target) + if (current_recv_credits <= (sc->recv_io.credits.target / 4) || + sc->recv_io.credits.target > old_recv_credit_target) queue_work(sc->workqueue, &sc->recv_io.posted.refill_work); enqueue_reassembly(sc, recvmsg, (int)data_length); @@ -913,6 +929,17 @@ static void smb_direct_post_recv_credits(struct work_struct *work) } } + atomic_add(credits, &sc->recv_io.credits.available); + + /* + * If the last send credit is waiting for credits + * it can grant we need to wake it up + */ + if (credits && + atomic_read(&sc->send_io.bcredits.count) == 0 && + atomic_read(&sc->send_io.credits.count) == 0) + wake_up(&sc->send_io.credits.wait_queue); + if (credits) queue_work(sc->workqueue, &sc->idle.immediate_work); } @@ -930,6 +957,31 @@ static void send_done(struct ib_cq *cq, struct ib_wc *wc) ib_wc_status_msg(wc->status), wc->status, wc->opcode); + if (unlikely(!(sendmsg->wr.send_flags & IB_SEND_SIGNALED))) { + /* + * This happens when smbdirect_send_io is a sibling + * before the final message, it is signaled on + * error anyway, so we need to skip + * smbdirect_connection_free_send_io here, + * otherwise is will destroy the memory + * of the siblings too, which will cause + * use after free problems for the others + * triggered from ib_drain_qp(). + */ + if (wc->status != IB_WC_SUCCESS) + goto skip_free; + + /* + * This should not happen! + * But we better just close the + * connection... + */ + pr_err("unexpected send completion wc->status=%s (%d) wc->opcode=%d\n", + ib_wc_status_msg(wc->status), wc->status, wc->opcode); + smb_direct_disconnect_rdma_connection(sc); + return; + } + /* * Free possible siblings and then the main send_io */ @@ -943,6 +995,7 @@ static void send_done(struct ib_cq *cq, struct ib_wc *wc) lcredits += 1; if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_SEND) { +skip_free: pr_err("Send error. status='%s (%d)', opcode=%d\n", ib_wc_status_msg(wc->status), wc->status, wc->opcode); @@ -959,19 +1012,37 @@ static void send_done(struct ib_cq *cq, struct ib_wc *wc) static int manage_credits_prior_sending(struct smbdirect_socket *sc) { + int missing; + int available; int new_credits; if (atomic_read(&sc->recv_io.credits.count) >= sc->recv_io.credits.target) return 0; - new_credits = atomic_read(&sc->recv_io.posted.count); - if (new_credits == 0) + missing = (int)sc->recv_io.credits.target - atomic_read(&sc->recv_io.credits.count); + available = atomic_xchg(&sc->recv_io.credits.available, 0); + new_credits = (u16)min3(U16_MAX, missing, available); + if (new_credits <= 0) { + /* + * If credits are available, but not granted + * we need to re-add them again. + */ + if (available) + atomic_add(available, &sc->recv_io.credits.available); return 0; + } - new_credits -= atomic_read(&sc->recv_io.credits.count); - if (new_credits <= 0) - return 0; + if (new_credits < available) { + /* + * Readd the remaining available again. + */ + available -= new_credits; + atomic_add(available, &sc->recv_io.credits.available); + } + /* + * Remember we granted the credits + */ atomic_add(new_credits, &sc->recv_io.credits.count); return new_credits; } @@ -1015,6 +1086,7 @@ static void smb_direct_send_ctx_init(struct smbdirect_send_batch *send_ctx, send_ctx->wr_cnt = 0; send_ctx->need_invalidate_rkey = need_invalidate_rkey; send_ctx->remote_key = remote_key; + send_ctx->credit = 0; } static int smb_direct_flush_send_list(struct smbdirect_socket *sc, @@ -1022,10 +1094,10 @@ static int smb_direct_flush_send_list(struct smbdirect_socket *sc, bool is_last) { struct smbdirect_send_io *first, *last; - int ret; + int ret = 0; if (list_empty(&send_ctx->msg_list)) - return 0; + goto release_credit; first = list_first_entry(&send_ctx->msg_list, struct smbdirect_send_io, @@ -1067,6 +1139,13 @@ static int smb_direct_flush_send_list(struct smbdirect_socket *sc, smb_direct_free_sendmsg(sc, last); } +release_credit: + if (is_last && !ret && send_ctx->credit) { + atomic_add(send_ctx->credit, &sc->send_io.bcredits.count); + send_ctx->credit = 0; + wake_up(&sc->send_io.bcredits.wait_queue); + } + return ret; } @@ -1092,6 +1171,25 @@ static int wait_for_credits(struct smbdirect_socket *sc, } while (true); } +static int wait_for_send_bcredit(struct smbdirect_socket *sc, + struct smbdirect_send_batch *send_ctx) +{ + int ret; + + if (send_ctx->credit) + return 0; + + ret = wait_for_credits(sc, + &sc->send_io.bcredits.wait_queue, + &sc->send_io.bcredits.count, + 1); + if (ret) + return ret; + + send_ctx->credit = 1; + return 0; +} + static int wait_for_send_lcredit(struct smbdirect_socket *sc, struct smbdirect_send_batch *send_ctx) { @@ -1141,6 +1239,7 @@ static int calc_rw_credits(struct smbdirect_socket *sc, static int smb_direct_create_header(struct smbdirect_socket *sc, int size, int remaining_data_length, + int new_credits, struct smbdirect_send_io **sendmsg_out) { struct smbdirect_socket_parameters *sp = &sc->parameters; @@ -1156,7 +1255,7 @@ static int smb_direct_create_header(struct smbdirect_socket *sc, /* Fill in the packet header */ packet = (struct smbdirect_data_transfer *)sendmsg->packet; packet->credits_requested = cpu_to_le16(sp->send_credit_target); - packet->credits_granted = cpu_to_le16(manage_credits_prior_sending(sc)); + packet->credits_granted = cpu_to_le16(new_credits); packet->flags = 0; if (manage_keep_alive_before_sending(sc)) @@ -1238,14 +1337,12 @@ static int get_sg_list(void *buf, int size, struct scatterlist *sg_list, int nen static int get_mapped_sg_list(struct ib_device *device, void *buf, int size, struct scatterlist *sg_list, int nentries, - enum dma_data_direction dir) + enum dma_data_direction dir, int *npages) { - int npages; - - npages = get_sg_list(buf, size, sg_list, nentries); - if (npages < 0) + *npages = get_sg_list(buf, size, sg_list, nentries); + if (*npages < 0) return -EINVAL; - return ib_dma_map_sg(device, sg_list, npages, dir); + return ib_dma_map_sg(device, sg_list, *npages, dir); } static int post_sendmsg(struct smbdirect_socket *sc, @@ -1295,6 +1392,17 @@ static int smb_direct_post_send_data(struct smbdirect_socket *sc, struct smbdirect_send_io *msg; int data_length; struct scatterlist sg[SMBDIRECT_SEND_IO_MAX_SGE - 1]; + struct smbdirect_send_batch _send_ctx; + int new_credits; + + if (!send_ctx) { + smb_direct_send_ctx_init(&_send_ctx, false, 0); + send_ctx = &_send_ctx; + } + + ret = wait_for_send_bcredit(sc, send_ctx); + if (ret) + goto bcredit_failed; ret = wait_for_send_lcredit(sc, send_ctx); if (ret) @@ -1304,24 +1412,42 @@ static int smb_direct_post_send_data(struct smbdirect_socket *sc, if (ret) goto credit_failed; + new_credits = manage_credits_prior_sending(sc); + if (new_credits == 0 && + atomic_read(&sc->send_io.credits.count) == 0 && + atomic_read(&sc->recv_io.credits.count) == 0) { + queue_work(sc->workqueue, &sc->recv_io.posted.refill_work); + ret = wait_event_interruptible(sc->send_io.credits.wait_queue, + atomic_read(&sc->send_io.credits.count) >= 1 || + atomic_read(&sc->recv_io.credits.available) >= 1 || + sc->status != SMBDIRECT_SOCKET_CONNECTED); + if (sc->status != SMBDIRECT_SOCKET_CONNECTED) + ret = -ENOTCONN; + if (ret < 0) + goto credit_failed; + + new_credits = manage_credits_prior_sending(sc); + } + data_length = 0; for (i = 0; i < niov; i++) data_length += iov[i].iov_len; ret = smb_direct_create_header(sc, data_length, remaining_data_length, - &msg); + new_credits, &msg); if (ret) goto header_failed; for (i = 0; i < niov; i++) { struct ib_sge *sge; int sg_cnt; + int npages; sg_init_table(sg, SMBDIRECT_SEND_IO_MAX_SGE - 1); sg_cnt = get_mapped_sg_list(sc->ib.dev, iov[i].iov_base, iov[i].iov_len, sg, SMBDIRECT_SEND_IO_MAX_SGE - 1, - DMA_TO_DEVICE); + DMA_TO_DEVICE, &npages); if (sg_cnt <= 0) { pr_err("failed to map buffer\n"); ret = -ENOMEM; @@ -1329,7 +1455,7 @@ static int smb_direct_post_send_data(struct smbdirect_socket *sc, } else if (sg_cnt + msg->num_sge > SMBDIRECT_SEND_IO_MAX_SGE) { pr_err("buffer not fitted into sges\n"); ret = -E2BIG; - ib_dma_unmap_sg(sc->ib.dev, sg, sg_cnt, + ib_dma_unmap_sg(sc->ib.dev, sg, npages, DMA_TO_DEVICE); goto err; } @@ -1346,6 +1472,13 @@ static int smb_direct_post_send_data(struct smbdirect_socket *sc, ret = post_sendmsg(sc, send_ctx, msg); if (ret) goto err; + + if (send_ctx == &_send_ctx) { + ret = smb_direct_flush_send_list(sc, send_ctx, true); + if (ret) + goto err; + } + return 0; err: smb_direct_free_sendmsg(sc, msg); @@ -1354,6 +1487,9 @@ static int smb_direct_post_send_data(struct smbdirect_socket *sc, credit_failed: atomic_inc(&sc->send_io.lcredits.count); lcredit_failed: + atomic_add(send_ctx->credit, &sc->send_io.bcredits.count); + send_ctx->credit = 0; +bcredit_failed: return ret; } @@ -1725,7 +1861,18 @@ static int smb_direct_cm_handler(struct rdma_cm_id *cm_id, switch (event->event) { case RDMA_CM_EVENT_ESTABLISHED: { - WARN_ON_ONCE(sc->status != SMBDIRECT_SOCKET_RDMA_CONNECT_RUNNING); + /* + * Some drivers (at least mlx5_ib) might post a + * recv completion before RDMA_CM_EVENT_ESTABLISHED, + * we need to adjust our expectation in that case. + * + * As we already started the negotiation, we just + * ignore RDMA_CM_EVENT_ESTABLISHED here. + */ + if (!sc->first_error && sc->status > SMBDIRECT_SOCKET_RDMA_CONNECT_RUNNING) + break; + if (SMBDIRECT_CHECK_STATUS_DISCONNECT(sc, SMBDIRECT_SOCKET_RDMA_CONNECT_RUNNING)) + break; sc->status = SMBDIRECT_SOCKET_NEGOTIATE_NEEDED; wake_up(&sc->status_wait); break; @@ -1804,6 +1951,7 @@ static int smb_direct_send_negotiate_response(struct smbdirect_socket *sc, resp->max_fragmented_size = cpu_to_le32(sp->max_fragmented_recv_size); + atomic_set(&sc->send_io.bcredits.count, 1); sc->recv_io.expected = SMBDIRECT_EXPECT_DATA_TRANSFER; sc->status = SMBDIRECT_SOCKET_CONNECTED; } diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index d2e391c29464e7..48cbb04ad41a2f 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -41,6 +41,7 @@ static const struct ksmbd_transport_ops ksmbd_tcp_transport_ops; static void tcp_stop_kthread(struct task_struct *kthread); static struct interface *alloc_iface(char *ifname); +static void ksmbd_tcp_disconnect(struct ksmbd_transport *t); #define KSMBD_TRANS(t) (&(t)->transport) #define TCP_TRANS(t) ((struct tcp_transport *)container_of(t, \ @@ -216,7 +217,7 @@ static int ksmbd_tcp_new_connection(struct socket *client_sk) if (IS_ERR(handler)) { pr_err("cannot start conn thread\n"); rc = PTR_ERR(handler); - free_transport(t); + ksmbd_tcp_disconnect(KSMBD_TRANS(t)); } return rc; } diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 891ed2dc2b7351..90e693e4e41497 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -324,6 +324,9 @@ static int check_lock_range(struct file *filp, loff_t start, loff_t end, struct file_lock_context *ctx = locks_inode_context(file_inode(filp)); int error = 0; + if (start == end) + return 0; + if (!ctx || list_empty_careful(&ctx->flc_posix)) return 0; @@ -828,7 +831,7 @@ int ksmbd_vfs_truncate(struct ksmbd_work *work, if (size < inode->i_size) { err = check_lock_range(filp, size, inode->i_size - 1, WRITE); - } else { + } else if (size > inode->i_size) { err = check_lock_range(filp, inode->i_size, size - 1, WRITE); } diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index dfed6fce890498..6ef116585af645 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -112,40 +112,62 @@ int ksmbd_query_inode_status(struct dentry *dentry) read_lock(&inode_hash_lock); ci = __ksmbd_inode_lookup(dentry); - if (ci) { - ret = KSMBD_INODE_STATUS_OK; - if (ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)) - ret = KSMBD_INODE_STATUS_PENDING_DELETE; - atomic_dec(&ci->m_count); - } read_unlock(&inode_hash_lock); + if (!ci) + return ret; + + down_read(&ci->m_lock); + if (ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)) + ret = KSMBD_INODE_STATUS_PENDING_DELETE; + else + ret = KSMBD_INODE_STATUS_OK; + up_read(&ci->m_lock); + + atomic_dec(&ci->m_count); return ret; } bool ksmbd_inode_pending_delete(struct ksmbd_file *fp) { - return (fp->f_ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)); + struct ksmbd_inode *ci = fp->f_ci; + int ret; + + down_read(&ci->m_lock); + ret = (ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)); + up_read(&ci->m_lock); + + return ret; } void ksmbd_set_inode_pending_delete(struct ksmbd_file *fp) { - fp->f_ci->m_flags |= S_DEL_PENDING; + struct ksmbd_inode *ci = fp->f_ci; + + down_write(&ci->m_lock); + ci->m_flags |= S_DEL_PENDING; + up_write(&ci->m_lock); } void ksmbd_clear_inode_pending_delete(struct ksmbd_file *fp) { - fp->f_ci->m_flags &= ~S_DEL_PENDING; + struct ksmbd_inode *ci = fp->f_ci; + + down_write(&ci->m_lock); + ci->m_flags &= ~S_DEL_PENDING; + up_write(&ci->m_lock); } void ksmbd_fd_set_delete_on_close(struct ksmbd_file *fp, int file_info) { - if (ksmbd_stream_fd(fp)) { - fp->f_ci->m_flags |= S_DEL_ON_CLS_STREAM; - return; - } + struct ksmbd_inode *ci = fp->f_ci; - fp->f_ci->m_flags |= S_DEL_ON_CLS; + down_write(&ci->m_lock); + if (ksmbd_stream_fd(fp)) + ci->m_flags |= S_DEL_ON_CLS_STREAM; + else + ci->m_flags |= S_DEL_ON_CLS; + up_write(&ci->m_lock); } static void ksmbd_inode_hash(struct ksmbd_inode *ci) @@ -257,27 +279,41 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) struct file *filp; filp = fp->filp; - if (ksmbd_stream_fd(fp) && (ci->m_flags & S_DEL_ON_CLS_STREAM)) { - ci->m_flags &= ~S_DEL_ON_CLS_STREAM; - err = ksmbd_vfs_remove_xattr(file_mnt_idmap(filp), - &filp->f_path, - fp->stream.name, - true); - if (err) - pr_err("remove xattr failed : %s\n", - fp->stream.name); + + if (ksmbd_stream_fd(fp)) { + bool remove_stream_xattr = false; + + down_write(&ci->m_lock); + if (ci->m_flags & S_DEL_ON_CLS_STREAM) { + ci->m_flags &= ~S_DEL_ON_CLS_STREAM; + remove_stream_xattr = true; + } + up_write(&ci->m_lock); + + if (remove_stream_xattr) { + err = ksmbd_vfs_remove_xattr(file_mnt_idmap(filp), + &filp->f_path, + fp->stream.name, + true); + if (err) + pr_err("remove xattr failed : %s\n", + fp->stream.name); + } } if (atomic_dec_and_test(&ci->m_count)) { + bool do_unlink = false; + down_write(&ci->m_lock); if (ci->m_flags & (S_DEL_ON_CLS | S_DEL_PENDING)) { ci->m_flags &= ~(S_DEL_ON_CLS | S_DEL_PENDING); - up_write(&ci->m_lock); - ksmbd_vfs_unlink(filp); - down_write(&ci->m_lock); + do_unlink = true; } up_write(&ci->m_lock); + if (do_unlink) + ksmbd_vfs_unlink(filp); + ksmbd_inode_free(ci); } } diff --git a/fs/super.c b/fs/super.c index 277b84e5c27913..4c79f170ac0d27 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1188,7 +1188,7 @@ static void filesystems_freeze_callback(struct super_block *sb, void *freeze_all if (!sb->s_op->freeze_fs && !sb->s_op->freeze_super) return; - if (freeze_all_ptr && !(sb->s_type->fs_flags & FS_POWER_FREEZE)) + if (!freeze_all_ptr && !(sb->s_type->fs_flags & FS_POWER_FREEZE)) return; if (!get_active_super(sb)) diff --git a/fs/tests/exec_kunit.c b/fs/tests/exec_kunit.c index 7c77d039680bbe..f412d1a0f6bba9 100644 --- a/fs/tests/exec_kunit.c +++ b/fs/tests/exec_kunit.c @@ -87,9 +87,6 @@ static const struct bprm_stack_limits_result bprm_stack_limits_results[] = { .argc = 0, .envc = ARG_MAX / sizeof(void *) - 1 }, .expected_argmin = ULONG_MAX - sizeof(void *) }, /* Raising rlim_stack / 4 to _STK_LIM / 4 * 3 will see more space. */ - { { .p = ULONG_MAX, .rlim_stack.rlim_cur = 4 * (_STK_LIM / 4 * 3), - .argc = 0, .envc = 0 }, - .expected_argmin = ULONG_MAX - (_STK_LIM / 4 * 3) + sizeof(void *) }, { { .p = ULONG_MAX, .rlim_stack.rlim_cur = 4 * (_STK_LIM / 4 * 3), .argc = 0, .envc = 0 }, .expected_argmin = ULONG_MAX - (_STK_LIM / 4 * 3) + sizeof(void *) }, @@ -103,9 +100,6 @@ static const struct bprm_stack_limits_result bprm_stack_limits_results[] = { { { .p = ULONG_MAX, .rlim_stack.rlim_cur = 4 * _STK_LIM, .argc = 0, .envc = 0 }, .expected_argmin = ULONG_MAX - (_STK_LIM / 4 * 3) + sizeof(void *) }, - { { .p = ULONG_MAX, .rlim_stack.rlim_cur = 4 * _STK_LIM, - .argc = 0, .envc = 0 }, - .expected_argmin = ULONG_MAX - (_STK_LIM / 4 * 3) + sizeof(void *) }, }; static void exec_test_bprm_stack_limits(struct kunit *test) diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 8705c77a9e75a1..93c231601c8e23 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -757,7 +757,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry const struct eventfs_entry *entries, int size, void *data) { - struct dentry *dentry = tracefs_start_creating(name, parent); + struct dentry *dentry; struct eventfs_root_inode *rei; struct eventfs_inode *ei; struct tracefs_inode *ti; @@ -768,6 +768,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry if (security_locked_down(LOCKDOWN_TRACEFS)) return NULL; + dentry = tracefs_start_creating(name, parent); if (IS_ERR(dentry)) return ERR_CAST(dentry); diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index d97295eaebe631..c19d6d713780ca 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -848,15 +848,16 @@ xfs_ialloc_ag_alloc( * invalid inode records, such as records that start at agbno 0 * or extend beyond the AG. * - * Set min agbno to the first aligned, non-zero agbno and max to - * the last aligned agbno that is at least one full chunk from - * the end of the AG. + * Set min agbno to the first chunk aligned, non-zero agbno and + * max to one less than the last chunk aligned agbno from the + * end of the AG. We subtract 1 from max so that the cluster + * allocation alignment takes over and allows allocation within + * the last full inode chunk in the AG. */ args.min_agbno = args.mp->m_sb.sb_inoalignmt; args.max_agbno = round_down(xfs_ag_block_count(args.mp, pag_agno(pag)), - args.mp->m_sb.sb_inoalignmt) - - igeo->ialloc_blks; + args.mp->m_sb.sb_inoalignmt) - 1; error = xfs_alloc_vextent_near_bno(&args, xfs_agbno_to_fsb(pag, diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index cdd16dd805d77c..94c272a2ae2622 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -301,6 +301,21 @@ xfs_validate_rt_geometry( sbp->sb_rbmblocks != xfs_expected_rbmblocks(sbp)) return false; + if (xfs_sb_is_v5(sbp) && + (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) { + uint32_t mod; + + /* + * Zoned RT devices must be aligned to the RT group size, + * because garbage collection assumes that all zones have the + * same size to avoid insane complexity if that weren't the + * case. + */ + div_u64_rem(sbp->sb_rextents, sbp->sb_rgextents, &mod); + if (mod) + return false; + } + return true; } diff --git a/fs/xfs/scrub/attr_repair.c b/fs/xfs/scrub/attr_repair.c index c7eb94069cafcd..09d63aa10314b0 100644 --- a/fs/xfs/scrub/attr_repair.c +++ b/fs/xfs/scrub/attr_repair.c @@ -333,7 +333,6 @@ xrep_xattr_salvage_remote_attr( .attr_filter = ent->flags & XFS_ATTR_NSP_ONDISK_MASK, .namelen = rentry->namelen, .name = rentry->name, - .value = ab->value, .valuelen = be32_to_cpu(rentry->valuelen), }; unsigned int namesize; @@ -363,6 +362,7 @@ xrep_xattr_salvage_remote_attr( error = -EDEADLOCK; if (error) return error; + args.value = ab->value; /* Look up the remote value and stash it for reconstruction. */ error = xfs_attr3_leaf_getvalue(leaf_bp, &args); diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index cd6f0ff382a7c8..acade92c5fce1a 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -370,12 +370,15 @@ xchk_btree_check_block_owner( { xfs_agnumber_t agno; xfs_agblock_t agbno; + bool is_bnobt, is_rmapbt; bool init_sa; int error = 0; if (!bs->cur) return 0; + is_bnobt = xfs_btree_is_bno(bs->cur->bc_ops); + is_rmapbt = xfs_btree_is_rmap(bs->cur->bc_ops); agno = xfs_daddr_to_agno(bs->cur->bc_mp, daddr); agbno = xfs_daddr_to_agbno(bs->cur->bc_mp, daddr); @@ -398,11 +401,11 @@ xchk_btree_check_block_owner( * have to nullify it (to shut down further block owner checks) if * self-xref encounters problems. */ - if (!bs->sc->sa.bno_cur && xfs_btree_is_bno(bs->cur->bc_ops)) + if (!bs->sc->sa.bno_cur && is_bnobt) bs->cur = NULL; xchk_xref_is_only_owned_by(bs->sc, agbno, 1, bs->oinfo); - if (!bs->sc->sa.rmap_cur && xfs_btree_is_rmap(bs->cur->bc_ops)) + if (!bs->sc->sa.rmap_cur && is_rmapbt) bs->cur = NULL; out_free: diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c index c3a593319bee71..e8fa326ac995bc 100644 --- a/fs/xfs/xfs_attr_item.c +++ b/fs/xfs/xfs_attr_item.c @@ -737,7 +737,7 @@ xfs_attr_recover_work( struct xfs_attri_log_item *attrip = ATTRI_ITEM(lip); struct xfs_attr_intent *attr; struct xfs_mount *mp = lip->li_log->l_mp; - struct xfs_inode *ip; + struct xfs_inode *ip = NULL; struct xfs_da_args *args; struct xfs_trans *tp; struct xfs_trans_res resv; diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 8d85b5eee44441..f4c5be67826e22 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -896,6 +896,7 @@ xfs_buf_item_init( map_size = DIV_ROUND_UP(chunks, NBWORD); if (map_size > XFS_BLF_DATAMAP_SIZE) { + xfs_buf_item_free_format(bip); kmem_cache_free(xfs_buf_item_cache, bip); xfs_err(mp, "buffer item dirty bitmap (%u uints) too small to reflect %u bytes!", diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 23ba84ec919a4d..18a19947bbdbac 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1318,7 +1318,7 @@ xfs_qm_quotacheck_dqadjust( error = xfs_dquot_attach_buf(NULL, dqp); if (error) - return error; + goto out_unlock; trace_xfs_dqadjust(dqp); @@ -1348,8 +1348,9 @@ xfs_qm_quotacheck_dqadjust( } dqp->q_flags |= XFS_DQFLAG_DIRTY; +out_unlock: xfs_qm_dqput(dqp); - return 0; + return error; } /* diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 6907e871fa1511..59fad43063a781 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -126,7 +126,7 @@ xfs_rtcopy_summary( error = 0; out: xfs_rtbuf_cache_relse(oargs); - return 0; + return error; } /* * Mark an extent specified by start and len allocated. @@ -1255,12 +1255,10 @@ xfs_growfs_check_rtgeom( min_logfsbs = min_t(xfs_extlen_t, xfs_log_calc_minimum_size(nmp), nmp->m_rsumblocks * 2); - kfree(nmp); - trace_xfs_growfs_check_rtgeom(mp, min_logfsbs); if (min_logfsbs > mp->m_sb.sb_logblocks) - return -EINVAL; + goto out_inval; if (xfs_has_zoned(mp)) { uint32_t gblocks = mp->m_groups[XG_TYPE_RTG].blocks; @@ -1268,16 +1266,20 @@ xfs_growfs_check_rtgeom( if (rextsize != 1) return -EINVAL; - div_u64_rem(mp->m_sb.sb_rblocks, gblocks, &rem); + div_u64_rem(nmp->m_sb.sb_rblocks, gblocks, &rem); if (rem) { xfs_warn(mp, "new RT volume size (%lld) not aligned to RT group size (%d)", - mp->m_sb.sb_rblocks, gblocks); - return -EINVAL; + nmp->m_sb.sb_rblocks, gblocks); + goto out_inval; } } + kfree(nmp); return 0; +out_inval: + kfree(nmp); + return -EINVAL; } /* diff --git a/include/acpi/pcc.h b/include/acpi/pcc.h index 9af3b502f83952..840bfc95bae332 100644 --- a/include/acpi/pcc.h +++ b/include/acpi/pcc.h @@ -17,35 +17,6 @@ struct pcc_mbox_chan { u32 latency; u32 max_access_rate; u16 min_turnaround_time; - - /* Set to true to indicate that the mailbox should manage - * writing the dat to the shared buffer. This differs from - * the case where the drivesr are writing to the buffer and - * using send_data only to ring the doorbell. If this flag - * is set, then the void * data parameter of send_data must - * point to a kernel-memory buffer formatted in accordance with - * the PCC specification. - * - * The active buffer management will include reading the - * notify_on_completion flag, and will then - * call mbox_chan_txdone when the acknowledgment interrupt is - * received. - */ - bool manage_writes; - - /* Optional callback that allows the driver - * to allocate the memory used for receiving - * messages. The return value is the location - * inside the buffer where the mailbox should write the data. - */ - void *(*rx_alloc)(struct mbox_client *cl, int size); -}; - -struct pcc_header { - u32 signature; - u32 flags; - u32 length; - u32 command; }; /* Generic Communications Channel Shared Memory Region */ diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 64ba6bc807d982..b89c7e3a20474f 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -124,10 +124,12 @@ static inline unsigned int hv_repcomp(u64 status) /* * Rep hypercalls. Callers of this functions are supposed to ensure that - * rep_count and varhead_size comply with Hyper-V hypercall definition. + * rep_count, varhead_size, and rep_start comply with Hyper-V hypercall + * definition. */ -static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, - void *input, void *output) +static inline u64 hv_do_rep_hypercall_ex(u16 code, u16 rep_count, + u16 varhead_size, u16 rep_start, + void *input, void *output) { u64 control = code; u64 status; @@ -135,6 +137,7 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, control |= (u64)varhead_size << HV_HYPERCALL_VARHEAD_OFFSET; control |= (u64)rep_count << HV_HYPERCALL_REP_COMP_OFFSET; + control |= (u64)rep_start << HV_HYPERCALL_REP_START_OFFSET; do { status = hv_do_hypercall(control, input, output); @@ -152,6 +155,14 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, return status; } +/* For the typical case where rep_start is 0 */ +static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, + void *input, void *output) +{ + return hv_do_rep_hypercall_ex(code, rep_count, varhead_size, 0, + input, output); +} + /* Generate the guest OS identifier as described in the Hyper-V TLFS */ static inline u64 hv_generate_guest_id(u64 kernel_version) { diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index 3c8ec3bfea4478..b9d2a7c79b93a1 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -28,6 +28,8 @@ static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm) return NULL; } + ptdesc_set_kernel(ptdesc); + return ptdesc_address(ptdesc); } #define __pte_alloc_one_kernel(...) alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__)) @@ -146,6 +148,10 @@ static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long ad pagetable_free(ptdesc); return NULL; } + + if (mm == &init_mm) + ptdesc_set_kernel(ptdesc); + return ptdesc_address(ptdesc); } #define pmd_alloc_one(...) alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__)) @@ -179,6 +185,10 @@ static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long return NULL; pagetable_pud_ctor(ptdesc); + + if (mm == &init_mm) + ptdesc_set_kernel(ptdesc); + return ptdesc_address(ptdesc); } #define __pud_alloc_one(...) alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__)) @@ -233,6 +243,10 @@ static inline p4d_t *__p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long return NULL; pagetable_p4d_ctor(ptdesc); + + if (mm == &init_mm) + ptdesc_set_kernel(ptdesc); + return ptdesc_address(ptdesc); } #define __p4d_alloc_one(...) alloc_hooks(__p4d_alloc_one_noprof(__VA_ARGS__)) @@ -277,6 +291,10 @@ static inline pgd_t *__pgd_alloc_noprof(struct mm_struct *mm, unsigned int order return NULL; pagetable_pgd_ctor(ptdesc); + + if (mm == &init_mm) + ptdesc_set_kernel(ptdesc); + return ptdesc_address(ptdesc); } #define __pgd_alloc(...) alloc_hooks(__pgd_alloc_noprof(__VA_ARGS__)) diff --git a/include/asm-generic/rqspinlock.h b/include/asm-generic/rqspinlock.h index 6d4244d643df32..5c5cf2f7fc395a 100644 --- a/include/asm-generic/rqspinlock.h +++ b/include/asm-generic/rqspinlock.h @@ -129,8 +129,8 @@ static __always_inline void release_held_lock_entry(void) * for lock B * release_held_lock_entry * - * try_cmpxchg_acquire for lock A * grab_held_lock_entry + * try_cmpxchg_acquire for lock A * * Lack of any ordering means reordering may occur such that dec, inc * are done before entry is overwritten. This permits a remote lock @@ -139,13 +139,8 @@ static __always_inline void release_held_lock_entry(void) * CPU holds a lock it is attempting to acquire, leading to false ABBA * diagnosis). * - * In case of unlock, we will always do a release on the lock word after - * releasing the entry, ensuring that other CPUs cannot hold the lock - * (and make conclusions about deadlocks) until the entry has been - * cleared on the local CPU, preventing any anomalies. Reordering is - * still possible there, but a remote CPU cannot observe a lock in our - * table which it is already holding, since visibility entails our - * release store for the said lock has not retired. + * The case of unlock is treated differently due to NMI reentrancy, see + * comments in res_spin_unlock. * * In theory we don't have a problem if the dec and WRITE_ONCE above get * reordered with each other, we either notice an empty NULL entry on @@ -175,16 +170,28 @@ static __always_inline int res_spin_lock(rqspinlock_t *lock) { int val = 0; - if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) { - grab_held_lock_entry(lock); + /* + * Grab the deadlock detection entry before doing the cmpxchg, so that + * reentrancy due to NMIs between the succeeding cmpxchg and creation of + * held lock entry can correctly detect an acquisition attempt in the + * interrupted context. + * + * cmpxchg lock A + * + * res_spin_lock(A) --> missed AA, leads to timeout + * + * grab_held_lock_entry(A) + */ + grab_held_lock_entry(lock); + + if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) return 0; - } return resilient_queued_spin_lock_slowpath(lock, val); } #else -#define res_spin_lock(lock) resilient_tas_spin_lock(lock) +#define res_spin_lock(lock) ({ grab_held_lock_entry(lock); resilient_tas_spin_lock(lock); }) #endif /* CONFIG_QUEUED_SPINLOCKS */ @@ -192,28 +199,25 @@ static __always_inline void res_spin_unlock(rqspinlock_t *lock) { struct rqspinlock_held *rqh = this_cpu_ptr(&rqspinlock_held_locks); - if (unlikely(rqh->cnt > RES_NR_HELD)) - goto unlock; - WRITE_ONCE(rqh->locks[rqh->cnt - 1], NULL); -unlock: /* - * Release barrier, ensures correct ordering. See release_held_lock_entry - * for details. Perform release store instead of queued_spin_unlock, - * since we use this function for test-and-set fallback as well. When we - * have CONFIG_QUEUED_SPINLOCKS=n, we clear the full 4-byte lockword. + * Release barrier, ensures correct ordering. Perform release store + * instead of queued_spin_unlock, since we use this function for the TAS + * fallback as well. When we have CONFIG_QUEUED_SPINLOCKS=n, we clear + * the full 4-byte lockword. * - * Like release_held_lock_entry, we can do the release before the dec. - * We simply care about not seeing the 'lock' in our table from a remote - * CPU once the lock has been released, which doesn't rely on the dec. + * Perform the smp_store_release before clearing the lock entry so that + * NMIs landing in the unlock path can correctly detect AA issues. The + * opposite order shown below may lead to missed AA checks: * - * Unlike smp_wmb(), release is not a two way fence, hence it is - * possible for a inc to move up and reorder with our clearing of the - * entry. This isn't a problem however, as for a misdiagnosis of ABBA, - * the remote CPU needs to hold this lock, which won't be released until - * the store below is done, which would ensure the entry is overwritten - * to NULL, etc. + * WRITE_ONCE(rqh->locks[rqh->cnt - 1], NULL) + * + * res_spin_lock(A) --> missed AA, leads to timeout + * + * smp_store_release(A->locked, 0) */ smp_store_release(&lock->locked, 0); + if (likely(rqh->cnt <= RES_NR_HELD)) + WRITE_ONCE(rqh->locks[rqh->cnt - 1], NULL); this_cpu_dec(rqspinlock_held_locks.cnt); } diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 1fff717cae510d..4d679d2a206b46 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -46,7 +46,8 @@ * * The mmu_gather API consists of: * - * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_finish_mmu() + * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_gather_mmu_vma() / + * tlb_finish_mmu() * * start and finish a mmu_gather * @@ -364,6 +365,20 @@ struct mmu_gather { unsigned int vma_huge : 1; unsigned int vma_pfn : 1; + /* + * Did we unshare (unmap) any shared page tables? For now only + * used for hugetlb PMD table sharing. + */ + unsigned int unshared_tables : 1; + + /* + * Did we unshare any page tables such that they are now exclusive + * and could get reused+modified by the new owner? When setting this + * flag, "unshared_tables" will be set as well. For now only used + * for hugetlb PMD table sharing. + */ + unsigned int fully_unshared_tables : 1; + unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER @@ -400,6 +415,7 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; + tlb->unshared_tables = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an @@ -484,7 +500,7 @@ static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) * these bits. */ if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds || - tlb->cleared_puds || tlb->cleared_p4ds)) + tlb->cleared_puds || tlb->cleared_p4ds || tlb->unshared_tables)) return; tlb_flush(tlb); @@ -773,6 +789,63 @@ static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) } #endif +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void tlb_unshare_pmd_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt, + unsigned long addr) +{ + /* + * The caller must make sure that concurrent unsharing + exclusive + * reuse is impossible until tlb_flush_unshared_tables() was called. + */ + VM_WARN_ON_ONCE(!ptdesc_pmd_is_shared(pt)); + ptdesc_pmd_pts_dec(pt); + + /* Clearing a PUD pointing at a PMD table with PMD leaves. */ + tlb_flush_pmd_range(tlb, addr & PUD_MASK, PUD_SIZE); + + /* + * If the page table is now exclusively owned, we fully unshared + * a page table. + */ + if (!ptdesc_pmd_is_shared(pt)) + tlb->fully_unshared_tables = true; + tlb->unshared_tables = true; +} + +static inline void tlb_flush_unshared_tables(struct mmu_gather *tlb) +{ + /* + * As soon as the caller drops locks to allow for reuse of + * previously-shared tables, these tables could get modified and + * even reused outside of hugetlb context, so we have to make sure that + * any page table walkers (incl. TLB, GUP-fast) are aware of that + * change. + * + * Even if we are not fully unsharing a PMD table, we must + * flush the TLB for the unsharer now. + */ + if (tlb->unshared_tables) + tlb_flush_mmu_tlbonly(tlb); + + /* + * Similarly, we must make sure that concurrent GUP-fast will not + * walk previously-shared page tables that are getting modified+reused + * elsewhere. So broadcast an IPI to wait for any concurrent GUP-fast. + * + * We only perform this when we are the last sharer of a page table, + * as the IPI will reach all CPUs: any GUP-fast. + * + * Note that on configs where tlb_remove_table_sync_one() is a NOP, + * the expectation is that the tlb_flush_mmu_tlbonly() would have issued + * required IPIs already for us. + */ + if (tlb->fully_unshared_tables) { + tlb_remove_table_sync_one(); + tlb->fully_unshared_tables = false; + } +} +#endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ + #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h index 83d14376ff2bc8..f485454e3955c3 100644 --- a/include/crypto/scatterwalk.h +++ b/include/crypto/scatterwalk.h @@ -227,6 +227,34 @@ static inline void scatterwalk_done_src(struct scatter_walk *walk, scatterwalk_advance(walk, nbytes); } +/* + * Flush the dcache of any pages that overlap the region + * [offset, offset + nbytes) relative to base_page. + * + * This should be called only when ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE, to ensure + * that all relevant code (including the call to sg_page() in the caller, if + * applicable) gets fully optimized out when !ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE. + */ +static inline void __scatterwalk_flush_dcache_pages(struct page *base_page, + unsigned int offset, + unsigned int nbytes) +{ + unsigned int num_pages; + + base_page += offset / PAGE_SIZE; + offset %= PAGE_SIZE; + + /* + * This is an overflow-safe version of + * num_pages = DIV_ROUND_UP(offset + nbytes, PAGE_SIZE). + */ + num_pages = nbytes / PAGE_SIZE; + num_pages += DIV_ROUND_UP(offset + (nbytes % PAGE_SIZE), PAGE_SIZE); + + for (unsigned int i = 0; i < num_pages; i++) + flush_dcache_page(base_page + i); +} + /** * scatterwalk_done_dst() - Finish one step of a walk of destination scatterlist * @walk: the scatter_walk @@ -240,27 +268,9 @@ static inline void scatterwalk_done_dst(struct scatter_walk *walk, unsigned int nbytes) { scatterwalk_unmap(walk); - /* - * Explicitly check ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE instead of just - * relying on flush_dcache_page() being a no-op when not implemented, - * since otherwise the BUG_ON in sg_page() does not get optimized out. - * This also avoids having to consider whether the loop would get - * reliably optimized out or not. - */ - if (ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE) { - struct page *base_page; - unsigned int offset; - int start, end, i; - - base_page = sg_page(walk->sg); - offset = walk->offset; - start = offset >> PAGE_SHIFT; - end = start + (nbytes >> PAGE_SHIFT); - end += (offset_in_page(offset) + offset_in_page(nbytes) + - PAGE_SIZE - 1) >> PAGE_SHIFT; - for (i = start; i < end; i++) - flush_dcache_page(base_page + i); - } + if (ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE) + __scatterwalk_flush_dcache_pages(sg_page(walk->sg), + walk->offset, nbytes); scatterwalk_advance(walk, nbytes); } diff --git a/include/drm/bridge/dw_hdmi_qp.h b/include/drm/bridge/dw_hdmi_qp.h index e9be6d507ad9cd..8955450663e530 100644 --- a/include/drm/bridge/dw_hdmi_qp.h +++ b/include/drm/bridge/dw_hdmi_qp.h @@ -28,5 +28,6 @@ struct dw_hdmi_qp_plat_data { struct dw_hdmi_qp *dw_hdmi_qp_bind(struct platform_device *pdev, struct drm_encoder *encoder, const struct dw_hdmi_qp_plat_data *plat_data); +void dw_hdmi_qp_suspend(struct device *dev, struct dw_hdmi_qp *hdmi); void dw_hdmi_qp_resume(struct device *dev, struct dw_hdmi_qp *hdmi); #endif /* __DW_HDMI_QP__ */ diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h index 53382fe93537bb..e154ee4f0696c0 100644 --- a/include/drm/drm_atomic_helper.h +++ b/include/drm/drm_atomic_helper.h @@ -60,6 +60,12 @@ int drm_atomic_helper_check_plane_state(struct drm_plane_state *plane_state, int drm_atomic_helper_check_planes(struct drm_device *dev, struct drm_atomic_state *state); int drm_atomic_helper_check_crtc_primary_plane(struct drm_crtc_state *crtc_state); +void drm_atomic_helper_commit_encoder_bridge_disable(struct drm_device *dev, + struct drm_atomic_state *state); +void drm_atomic_helper_commit_crtc_disable(struct drm_device *dev, + struct drm_atomic_state *state); +void drm_atomic_helper_commit_encoder_bridge_post_disable(struct drm_device *dev, + struct drm_atomic_state *state); int drm_atomic_helper_check(struct drm_device *dev, struct drm_atomic_state *state); void drm_atomic_helper_commit_tail(struct drm_atomic_state *state); @@ -89,8 +95,24 @@ drm_atomic_helper_update_legacy_modeset_state(struct drm_device *dev, void drm_atomic_helper_calc_timestamping_constants(struct drm_atomic_state *state); +void drm_atomic_helper_commit_crtc_set_mode(struct drm_device *dev, + struct drm_atomic_state *state); + void drm_atomic_helper_commit_modeset_disables(struct drm_device *dev, struct drm_atomic_state *state); + +void drm_atomic_helper_commit_writebacks(struct drm_device *dev, + struct drm_atomic_state *state); + +void drm_atomic_helper_commit_encoder_bridge_pre_enable(struct drm_device *dev, + struct drm_atomic_state *state); + +void drm_atomic_helper_commit_crtc_enable(struct drm_device *dev, + struct drm_atomic_state *state); + +void drm_atomic_helper_commit_encoder_bridge_enable(struct drm_device *dev, + struct drm_atomic_state *state); + void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev, struct drm_atomic_state *old_state); diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 76e05930f50e00..57d9a3c0621246 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -176,33 +176,17 @@ struct drm_bridge_funcs { /** * @disable: * - * The @disable callback should disable the bridge. + * This callback should disable the bridge. It is called right before + * the preceding element in the display pipe is disabled. If the + * preceding element is a bridge this means it's called before that + * bridge's @disable vfunc. If the preceding element is a &drm_encoder + * it's called right before the &drm_encoder_helper_funcs.disable, + * &drm_encoder_helper_funcs.prepare or &drm_encoder_helper_funcs.dpms + * hook. * * The bridge can assume that the display pipe (i.e. clocks and timing * signals) feeding it is still running when this callback is called. * - * - * If the preceding element is a &drm_bridge, then this is called before - * that bridge is disabled via one of: - * - * - &drm_bridge_funcs.disable - * - &drm_bridge_funcs.atomic_disable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called before the encoder is disabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_disable - * - &drm_encoder_helper_funcs.prepare - * - &drm_encoder_helper_funcs.disable - * - &drm_encoder_helper_funcs.dpms - * - * and the CRTC is disabled via one of: - * - * - &drm_crtc_helper_funcs.prepare - * - &drm_crtc_helper_funcs.atomic_disable - * - &drm_crtc_helper_funcs.disable - * - &drm_crtc_helper_funcs.dpms. - * * The @disable callback is optional. * * NOTE: @@ -215,34 +199,17 @@ struct drm_bridge_funcs { /** * @post_disable: * - * The bridge must assume that the display pipe (i.e. clocks and timing - * signals) feeding this bridge is no longer running when the - * @post_disable is called. + * This callback should disable the bridge. It is called right after the + * preceding element in the display pipe is disabled. If the preceding + * element is a bridge this means it's called after that bridge's + * @post_disable function. If the preceding element is a &drm_encoder + * it's called right after the encoder's + * &drm_encoder_helper_funcs.disable, &drm_encoder_helper_funcs.prepare + * or &drm_encoder_helper_funcs.dpms hook. * - * This callback should perform all the actions required by the hardware - * after it has stopped receiving signals from the preceding element. - * - * If the preceding element is a &drm_bridge, then this is called after - * that bridge is post-disabled (unless marked otherwise by the - * @pre_enable_prev_first flag) via one of: - * - * - &drm_bridge_funcs.post_disable - * - &drm_bridge_funcs.atomic_post_disable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called after the encoder is disabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_disable - * - &drm_encoder_helper_funcs.prepare - * - &drm_encoder_helper_funcs.disable - * - &drm_encoder_helper_funcs.dpms - * - * and the CRTC is disabled via one of: - * - * - &drm_crtc_helper_funcs.prepare - * - &drm_crtc_helper_funcs.atomic_disable - * - &drm_crtc_helper_funcs.disable - * - &drm_crtc_helper_funcs.dpms + * The bridge must assume that the display pipe (i.e. clocks and timing + * signals) feeding it is no longer running when this callback is + * called. * * The @post_disable callback is optional. * @@ -285,30 +252,18 @@ struct drm_bridge_funcs { /** * @pre_enable: * - * The display pipe (i.e. clocks and timing signals) feeding this bridge - * will not yet be running when the @pre_enable is called. - * - * This callback should perform all the necessary actions to prepare the - * bridge to accept signals from the preceding element. - * - * If the preceding element is a &drm_bridge, then this is called before - * that bridge is pre-enabled (unless marked otherwise by - * @pre_enable_prev_first flag) via one of: - * - * - &drm_bridge_funcs.pre_enable - * - &drm_bridge_funcs.atomic_pre_enable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called before the CRTC is enabled via one of: - * - * - &drm_crtc_helper_funcs.atomic_enable - * - &drm_crtc_helper_funcs.commit - * - * and the encoder is enabled via one of: + * This callback should enable the bridge. It is called right before + * the preceding element in the display pipe is enabled. If the + * preceding element is a bridge this means it's called before that + * bridge's @pre_enable function. If the preceding element is a + * &drm_encoder it's called right before the encoder's + * &drm_encoder_helper_funcs.enable, &drm_encoder_helper_funcs.commit or + * &drm_encoder_helper_funcs.dpms hook. * - * - &drm_encoder_helper_funcs.atomic_enable - * - &drm_encoder_helper_funcs.enable - * - &drm_encoder_helper_funcs.commit + * The display pipe (i.e. clocks and timing signals) feeding this bridge + * will not yet be running when this callback is called. The bridge must + * not enable the display link feeding the next bridge in the chain (if + * there is one) when this callback is called. * * The @pre_enable callback is optional. * @@ -322,31 +277,19 @@ struct drm_bridge_funcs { /** * @enable: * - * The @enable callback should enable the bridge. + * This callback should enable the bridge. It is called right after + * the preceding element in the display pipe is enabled. If the + * preceding element is a bridge this means it's called after that + * bridge's @enable function. If the preceding element is a + * &drm_encoder it's called right after the encoder's + * &drm_encoder_helper_funcs.enable, &drm_encoder_helper_funcs.commit or + * &drm_encoder_helper_funcs.dpms hook. * * The bridge can assume that the display pipe (i.e. clocks and timing * signals) feeding it is running when this callback is called. This * callback must enable the display link feeding the next bridge in the * chain if there is one. * - * If the preceding element is a &drm_bridge, then this is called after - * that bridge is enabled via one of: - * - * - &drm_bridge_funcs.enable - * - &drm_bridge_funcs.atomic_enable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called after the CRTC is enabled via one of: - * - * - &drm_crtc_helper_funcs.atomic_enable - * - &drm_crtc_helper_funcs.commit - * - * and the encoder is enabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_enable - * - &drm_encoder_helper_funcs.enable - * - drm_encoder_helper_funcs.commit - * * The @enable callback is optional. * * NOTE: @@ -359,30 +302,17 @@ struct drm_bridge_funcs { /** * @atomic_pre_enable: * - * The display pipe (i.e. clocks and timing signals) feeding this bridge - * will not yet be running when the @atomic_pre_enable is called. - * - * This callback should perform all the necessary actions to prepare the - * bridge to accept signals from the preceding element. - * - * If the preceding element is a &drm_bridge, then this is called before - * that bridge is pre-enabled (unless marked otherwise by - * @pre_enable_prev_first flag) via one of: - * - * - &drm_bridge_funcs.pre_enable - * - &drm_bridge_funcs.atomic_pre_enable + * This callback should enable the bridge. It is called right before + * the preceding element in the display pipe is enabled. If the + * preceding element is a bridge this means it's called before that + * bridge's @atomic_pre_enable or @pre_enable function. If the preceding + * element is a &drm_encoder it's called right before the encoder's + * &drm_encoder_helper_funcs.atomic_enable hook. * - * If the preceding element of the bridge is a display controller, then - * this callback is called before the CRTC is enabled via one of: - * - * - &drm_crtc_helper_funcs.atomic_enable - * - &drm_crtc_helper_funcs.commit - * - * and the encoder is enabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_enable - * - &drm_encoder_helper_funcs.enable - * - &drm_encoder_helper_funcs.commit + * The display pipe (i.e. clocks and timing signals) feeding this bridge + * will not yet be running when this callback is called. The bridge must + * not enable the display link feeding the next bridge in the chain (if + * there is one) when this callback is called. * * The @atomic_pre_enable callback is optional. */ @@ -392,31 +322,18 @@ struct drm_bridge_funcs { /** * @atomic_enable: * - * The @atomic_enable callback should enable the bridge. + * This callback should enable the bridge. It is called right after + * the preceding element in the display pipe is enabled. If the + * preceding element is a bridge this means it's called after that + * bridge's @atomic_enable or @enable function. If the preceding element + * is a &drm_encoder it's called right after the encoder's + * &drm_encoder_helper_funcs.atomic_enable hook. * * The bridge can assume that the display pipe (i.e. clocks and timing * signals) feeding it is running when this callback is called. This * callback must enable the display link feeding the next bridge in the * chain if there is one. * - * If the preceding element is a &drm_bridge, then this is called after - * that bridge is enabled via one of: - * - * - &drm_bridge_funcs.enable - * - &drm_bridge_funcs.atomic_enable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called after the CRTC is enabled via one of: - * - * - &drm_crtc_helper_funcs.atomic_enable - * - &drm_crtc_helper_funcs.commit - * - * and the encoder is enabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_enable - * - &drm_encoder_helper_funcs.enable - * - drm_encoder_helper_funcs.commit - * * The @atomic_enable callback is optional. */ void (*atomic_enable)(struct drm_bridge *bridge, @@ -424,32 +341,16 @@ struct drm_bridge_funcs { /** * @atomic_disable: * - * The @atomic_disable callback should disable the bridge. + * This callback should disable the bridge. It is called right before + * the preceding element in the display pipe is disabled. If the + * preceding element is a bridge this means it's called before that + * bridge's @atomic_disable or @disable vfunc. If the preceding element + * is a &drm_encoder it's called right before the + * &drm_encoder_helper_funcs.atomic_disable hook. * * The bridge can assume that the display pipe (i.e. clocks and timing * signals) feeding it is still running when this callback is called. * - * If the preceding element is a &drm_bridge, then this is called before - * that bridge is disabled via one of: - * - * - &drm_bridge_funcs.disable - * - &drm_bridge_funcs.atomic_disable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called before the encoder is disabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_disable - * - &drm_encoder_helper_funcs.prepare - * - &drm_encoder_helper_funcs.disable - * - &drm_encoder_helper_funcs.dpms - * - * and the CRTC is disabled via one of: - * - * - &drm_crtc_helper_funcs.prepare - * - &drm_crtc_helper_funcs.atomic_disable - * - &drm_crtc_helper_funcs.disable - * - &drm_crtc_helper_funcs.dpms. - * * The @atomic_disable callback is optional. */ void (*atomic_disable)(struct drm_bridge *bridge, @@ -458,34 +359,16 @@ struct drm_bridge_funcs { /** * @atomic_post_disable: * - * The bridge must assume that the display pipe (i.e. clocks and timing - * signals) feeding this bridge is no longer running when the - * @atomic_post_disable is called. - * - * This callback should perform all the actions required by the hardware - * after it has stopped receiving signals from the preceding element. + * This callback should disable the bridge. It is called right after the + * preceding element in the display pipe is disabled. If the preceding + * element is a bridge this means it's called after that bridge's + * @atomic_post_disable or @post_disable function. If the preceding + * element is a &drm_encoder it's called right after the encoder's + * &drm_encoder_helper_funcs.atomic_disable hook. * - * If the preceding element is a &drm_bridge, then this is called after - * that bridge is post-disabled (unless marked otherwise by the - * @pre_enable_prev_first flag) via one of: - * - * - &drm_bridge_funcs.post_disable - * - &drm_bridge_funcs.atomic_post_disable - * - * If the preceding element of the bridge is a display controller, then - * this callback is called after the encoder is disabled via one of: - * - * - &drm_encoder_helper_funcs.atomic_disable - * - &drm_encoder_helper_funcs.prepare - * - &drm_encoder_helper_funcs.disable - * - &drm_encoder_helper_funcs.dpms - * - * and the CRTC is disabled via one of: - * - * - &drm_crtc_helper_funcs.prepare - * - &drm_crtc_helper_funcs.atomic_disable - * - &drm_crtc_helper_funcs.disable - * - &drm_crtc_helper_funcs.dpms + * The bridge must assume that the display pipe (i.e. clocks and timing + * signals) feeding it is no longer running when this callback is + * called. * * The @atomic_post_disable callback is optional. */ diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h index 04afd7c21a82e9..c2e05a28125224 100644 --- a/include/drm/drm_buddy.h +++ b/include/drm/drm_buddy.h @@ -10,6 +10,7 @@ #include #include #include +#include #include @@ -44,7 +45,11 @@ struct drm_buddy_block { * a list, if so desired. As soon as the block is freed with * drm_buddy_free* ownership is given back to the mm. */ - struct list_head link; + union { + struct rb_node rb; + struct list_head link; + }; + struct list_head tmp_link; }; @@ -59,7 +64,7 @@ struct drm_buddy_block { */ struct drm_buddy { /* Maintain a free list for each order. */ - struct list_head *free_list; + struct rb_root **free_trees; /* * Maintain explicit binary tree(s) to track the allocation of the @@ -85,7 +90,7 @@ struct drm_buddy { }; static inline u64 -drm_buddy_block_offset(struct drm_buddy_block *block) +drm_buddy_block_offset(const struct drm_buddy_block *block) { return block->header & DRM_BUDDY_HEADER_OFFSET; } diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index 3d1aecfec9b2a4..04f7a7f1f10826 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -340,6 +340,12 @@ struct drm_edid_ident { const char *name; }; +#define DRM_EDID_IDENT_INIT(_vend_chr_0, _vend_chr_1, _vend_chr_2, _product_id, _name) \ +{ \ + .panel_id = drm_edid_encode_panel_id(_vend_chr_0, _vend_chr_1, _vend_chr_2, _product_id), \ + .name = _name, \ +} + #define EDID_PRODUCT_ID(e) ((e)->prod_code[0] | ((e)->prod_code[1] << 8)) /* Short Audio Descriptor */ diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h index 92f5db84b9c22e..589f7bfe7506eb 100644 --- a/include/drm/drm_gem_shmem_helper.h +++ b/include/drm/drm_gem_shmem_helper.h @@ -107,10 +107,12 @@ struct drm_gem_shmem_object { #define to_drm_gem_shmem_obj(obj) \ container_of(obj, struct drm_gem_shmem_object, base) +int drm_gem_shmem_init(struct drm_device *dev, struct drm_gem_shmem_object *shmem, size_t size); struct drm_gem_shmem_object *drm_gem_shmem_create(struct drm_device *dev, size_t size); struct drm_gem_shmem_object *drm_gem_shmem_create_with_mnt(struct drm_device *dev, size_t size, struct vfsmount *gemfs); +void drm_gem_shmem_release(struct drm_gem_shmem_object *shmem); void drm_gem_shmem_free(struct drm_gem_shmem_object *shmem); void drm_gem_shmem_put_pages_locked(struct drm_gem_shmem_object *shmem); diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h index 476990e761f869..75c48345677b0f 100644 --- a/include/drm/drm_gpuvm.h +++ b/include/drm/drm_gpuvm.h @@ -27,6 +27,7 @@ #include #include +#include #include #include @@ -56,10 +57,19 @@ enum drm_gpuva_flags { */ DRM_GPUVA_SPARSE = (1 << 1), + /** + * @DRM_GPUVA_REPEAT: + * + * Flag indicating that the &drm_gpuva is a mapping of a GEM + * object with a certain range that is repeated multiple times to + * fill the virtual address range. + */ + DRM_GPUVA_REPEAT = (1 << 2), + /** * @DRM_GPUVA_USERBITS: user defined bits */ - DRM_GPUVA_USERBITS = (1 << 2), + DRM_GPUVA_USERBITS = (1 << 3), }; /** @@ -111,6 +121,18 @@ struct drm_gpuva { */ u64 offset; + /* + * @gem.range: the range of the GEM that is mapped + * + * When dealing with normal mappings, this must be zero. + * When flags has DRM_GPUVA_REPEAT set, this field must be + * smaller than va.range and va.range must be a multiple of + * gem.range. + * This is a u32 not a u64 because we expect repeated mappings + * to be pointing to relatively small portions of a GEM object. + */ + u32 range; + /** * @gem.obj: the mapped &drm_gem_object */ @@ -152,6 +174,7 @@ void drm_gpuva_remove(struct drm_gpuva *va); void drm_gpuva_link(struct drm_gpuva *va, struct drm_gpuvm_bo *vm_bo); void drm_gpuva_unlink(struct drm_gpuva *va); +void drm_gpuva_unlink_defer(struct drm_gpuva *va); struct drm_gpuva *drm_gpuva_find(struct drm_gpuvm *gpuvm, u64 addr, u64 range); @@ -331,6 +354,11 @@ struct drm_gpuvm { */ spinlock_t lock; } evict; + + /** + * @bo_defer: structure holding vm_bos that need to be destroyed + */ + struct llist_head bo_defer; }; void drm_gpuvm_init(struct drm_gpuvm *gpuvm, const char *name, @@ -714,6 +742,12 @@ struct drm_gpuvm_bo { * &drm_gpuvms evict list. */ struct list_head evict; + + /** + * @list.entry.bo_defer: List entry to attach to + * the &drm_gpuvms bo_defer list. + */ + struct llist_node bo_defer; } entry; } list; }; @@ -746,6 +780,9 @@ drm_gpuvm_bo_get(struct drm_gpuvm_bo *vm_bo) bool drm_gpuvm_bo_put(struct drm_gpuvm_bo *vm_bo); +bool drm_gpuvm_bo_put_deferred(struct drm_gpuvm_bo *vm_bo); +void drm_gpuvm_bo_deferred_cleanup(struct drm_gpuvm *gpuvm); + struct drm_gpuvm_bo * drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm, struct drm_gem_object *obj); @@ -866,11 +903,27 @@ struct drm_gpuva_op_map { */ u64 offset; + /* + * @gem.range: the range of the GEM that is mapped + * + * When dealing with normal mappings, this must be zero. + * When flags has DRM_GPUVA_REPEAT set, it must be a multiple + * of va.range. This is a u32 not a u64 because we expect + * repeated mappings to be pointing to a relatively small + * portion of a GEM object. + */ + u32 range; + /** * @gem.obj: the &drm_gem_object to map */ struct drm_gem_object *obj; } gem; + + /** + * @flags: requested flags for the &drm_gpuva for this mapping + */ + enum drm_gpuva_flags flags; }; /** @@ -1107,6 +1160,7 @@ void drm_gpuva_ops_free(struct drm_gpuvm *gpuvm, static inline void drm_gpuva_init_from_op(struct drm_gpuva *va, struct drm_gpuva_op_map *op) { + va->flags = op->flags; va->va.addr = op->va.addr; va->va.range = op->va.range; va->gem.obj = op->gem.obj; @@ -1232,6 +1286,16 @@ struct drm_gpuvm_ops { * used. */ int (*sm_step_unmap)(struct drm_gpuva_op *op, void *priv); + + /** + * @sm_can_merge_flags: called during &drm_gpuvm_sm_map + * + * This callback is called to determine whether two va ranges can be merged, + * based on their flags. + * + * If NULL, va ranges can only be merged if their flags are equal. + */ + bool (*sm_can_merge_flags)(enum drm_gpuva_flags a, enum drm_gpuva_flags b); }; int drm_gpuvm_sm_map(struct drm_gpuvm *gpuvm, void *priv, @@ -1239,6 +1303,7 @@ int drm_gpuvm_sm_map(struct drm_gpuvm *gpuvm, void *priv, int drm_gpuvm_sm_unmap(struct drm_gpuvm *gpuvm, void *priv, u64 addr, u64 range); +int drm_gpuvm_bo_unmap(struct drm_gpuvm_bo *bo, void *priv); int drm_gpuvm_sm_map_exec_lock(struct drm_gpuvm *gpuvm, struct drm_exec *exec, unsigned int num_fences, diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h index f6e7e234c08926..eb29e5309f0ab6 100644 --- a/include/drm/drm_pagemap.h +++ b/include/drm/drm_pagemap.h @@ -8,6 +8,7 @@ #define NR_PAGES(order) (1U << (order)) +struct dma_fence; struct drm_pagemap; struct drm_pagemap_zdd; struct device; @@ -174,6 +175,8 @@ struct drm_pagemap_devmem_ops { * @pages: Pointer to array of device memory pages (destination) * @pagemap_addr: Pointer to array of DMA information (source) * @npages: Number of pages to copy + * @pre_migrate_fence: dma-fence to wait for before migration start. + * May be NULL. * * Copy pages to device memory. If the order of a @pagemap_addr entry * is greater than 0, the entry is populated but subsequent entries @@ -183,13 +186,16 @@ struct drm_pagemap_devmem_ops { */ int (*copy_to_devmem)(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages); + unsigned long npages, + struct dma_fence *pre_migrate_fence); /** * @copy_to_ram: Copy to system RAM (required for migration) * @pages: Pointer to array of device memory pages (source) * @pagemap_addr: Pointer to array of DMA information (destination) * @npages: Number of pages to copy + * @pre_migrate_fence: dma-fence to wait for before migration start. + * May be NULL. * * Copy pages to system RAM. If the order of a @pagemap_addr entry * is greater than 0, the entry is populated but subsequent entries @@ -199,9 +205,23 @@ struct drm_pagemap_devmem_ops { */ int (*copy_to_ram)(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages); + unsigned long npages, + struct dma_fence *pre_migrate_fence); }; +#if IS_ENABLED(CONFIG_ZONE_DEVICE) + +struct drm_pagemap *drm_pagemap_page_to_dpagemap(struct page *page); + +#else + +static inline struct drm_pagemap *drm_pagemap_page_to_dpagemap(struct page *page) +{ + return NULL; +} + +#endif /* IS_ENABLED(CONFIG_ZONE_DEVICE) */ + /** * struct drm_pagemap_devmem - Structure representing a GPU SVM device memory allocation * @@ -212,6 +232,8 @@ struct drm_pagemap_devmem_ops { * @dpagemap: The struct drm_pagemap of the pages this allocation belongs to. * @size: Size of device memory allocation * @timeslice_expiration: Timeslice expiration in jiffies + * @pre_migrate_fence: Fence to wait for or pipeline behind before migration starts. + * (May be NULL). */ struct drm_pagemap_devmem { struct device *dev; @@ -221,8 +243,11 @@ struct drm_pagemap_devmem { struct drm_pagemap *dpagemap; size_t size; u64 timeslice_expiration; + struct dma_fence *pre_migrate_fence; }; +#if IS_ENABLED(CONFIG_ZONE_DEVICE) + int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation, struct mm_struct *mm, unsigned long start, unsigned long end, @@ -233,16 +258,17 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation); const struct dev_pagemap_ops *drm_pagemap_pagemap_ops_get(void); -struct drm_pagemap *drm_pagemap_page_to_dpagemap(struct page *page); - void drm_pagemap_devmem_init(struct drm_pagemap_devmem *devmem_allocation, struct device *dev, struct mm_struct *mm, const struct drm_pagemap_devmem_ops *ops, - struct drm_pagemap *dpagemap, size_t size); + struct drm_pagemap *dpagemap, size_t size, + struct dma_fence *pre_migrate_fence); int drm_pagemap_populate_mm(struct drm_pagemap *dpagemap, unsigned long start, unsigned long end, struct mm_struct *mm, unsigned long timeslice_ms); +#endif /* IS_ENABLED(CONFIG_ZONE_DEVICE) */ + #endif diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 323a505e6e6ae0..71349c5779425a 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -301,6 +301,11 @@ struct drm_sched_fence { * @lock: the lock used by the scheduled and the finished fences. */ spinlock_t lock; + /** + * @sched_name: the name of the scheduler that owns this fence. We + * keep a copy here since fences can outlive their scheduler. + */ + char sched_name[16]; /** * @owner: job owner for debugging */ diff --git a/include/drm/intel/intel_lb_mei_interface.h b/include/drm/intel/intel_lb_mei_interface.h index d65be2cba2ab9f..0850738a30fc75 100644 --- a/include/drm/intel/intel_lb_mei_interface.h +++ b/include/drm/intel/intel_lb_mei_interface.h @@ -53,7 +53,8 @@ enum intel_lb_status { */ struct intel_lb_component_ops { /** - * push_payload - Sends a payload to the authentication firmware + * @push_payload: Sends a payload to the authentication firmware + * * @dev: Device struct corresponding to the mei device * @type: Payload type (see &enum intel_lb_type) * @flags: Payload flags bitmap (e.g. %INTEL_LB_FLAGS_IS_PERSISTENT) diff --git a/include/dt-bindings/clock/qcom,mmcc-sdm660.h b/include/dt-bindings/clock/qcom,mmcc-sdm660.h index f9dbc21cb5c7cf..ee2a89dae72dc5 100644 --- a/include/dt-bindings/clock/qcom,mmcc-sdm660.h +++ b/include/dt-bindings/clock/qcom,mmcc-sdm660.h @@ -157,6 +157,7 @@ #define BIMC_SMMU_GDSC 7 #define CAMSS_MICRO_BCR 0 +#define MDSS_BCR 1 #endif diff --git a/include/dt-bindings/power/qcom,rpmhpd.h b/include/dt-bindings/power/qcom,rpmhpd.h index 73cceb88953f70..269b73ff866a8f 100644 --- a/include/dt-bindings/power/qcom,rpmhpd.h +++ b/include/dt-bindings/power/qcom,rpmhpd.h @@ -261,5 +261,6 @@ #define SC8280XP_NSP 13 #define SC8280XP_QPHY 14 #define SC8280XP_XO 15 +#define SC8280XP_MXC_AO 16 #endif diff --git a/include/kunit/run-in-irq-context.h b/include/kunit/run-in-irq-context.h index 108e96433ea45b..c89b1b1b12dd58 100644 --- a/include/kunit/run-in-irq-context.h +++ b/include/kunit/run-in-irq-context.h @@ -20,8 +20,8 @@ struct kunit_irq_test_state { bool task_func_reported_failure; bool hardirq_func_reported_failure; bool softirq_func_reported_failure; - unsigned long hardirq_func_calls; - unsigned long softirq_func_calls; + atomic_t hardirq_func_calls; + atomic_t softirq_func_calls; struct hrtimer timer; struct work_struct bh_work; }; @@ -32,7 +32,7 @@ static enum hrtimer_restart kunit_irq_test_timer_func(struct hrtimer *timer) container_of(timer, typeof(*state), timer); WARN_ON_ONCE(!in_hardirq()); - state->hardirq_func_calls++; + atomic_inc(&state->hardirq_func_calls); if (!state->func(state->test_specific_state)) state->hardirq_func_reported_failure = true; @@ -48,7 +48,7 @@ static void kunit_irq_test_bh_work_func(struct work_struct *work) container_of(work, typeof(*state), bh_work); WARN_ON_ONCE(!in_serving_softirq()); - state->softirq_func_calls++; + atomic_inc(&state->softirq_func_calls); if (!state->func(state->test_specific_state)) state->softirq_func_reported_failure = true; @@ -59,7 +59,10 @@ static void kunit_irq_test_bh_work_func(struct work_struct *work) * hardirq context concurrently, and reports a failure to KUnit if any * invocation of @func in any context returns false. @func is passed * @test_specific_state as its argument. At most 3 invocations of @func will - * run concurrently: one in each of task, softirq, and hardirq context. + * run concurrently: one in each of task, softirq, and hardirq context. @func + * will continue running until either @max_iterations calls have been made (so + * long as at least one each runs in task, softirq, and hardirq contexts), or + * one second has passed. * * The main purpose of this interrupt context testing is to validate fallback * code paths that run in contexts where the normal code path cannot be used, @@ -85,6 +88,8 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *), .test_specific_state = test_specific_state, }; unsigned long end_jiffies; + int hardirq_calls, softirq_calls; + bool allctx = false; /* * Set up a hrtimer (the way we access hardirq context) and a work @@ -94,14 +99,25 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *), CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); INIT_WORK_ONSTACK(&state.bh_work, kunit_irq_test_bh_work_func); - /* Run for up to max_iterations or 1 second, whichever comes first. */ + /* + * Run for up to max_iterations (including at least one task, softirq, + * and hardirq), or 1 second, whichever comes first. + */ end_jiffies = jiffies + HZ; hrtimer_start(&state.timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL, HRTIMER_MODE_REL_HARD); - for (int i = 0; i < max_iterations && !time_after(jiffies, end_jiffies); - i++) { + for (int task_calls = 0, calls = 0; + ((calls < max_iterations) || !allctx) && + !time_after(jiffies, end_jiffies); + task_calls++) { if (!func(test_specific_state)) state.task_func_reported_failure = true; + + hardirq_calls = atomic_read(&state.hardirq_func_calls); + softirq_calls = atomic_read(&state.softirq_func_calls); + calls = task_calls + hardirq_calls + softirq_calls; + allctx = (task_calls > 0) && (hardirq_calls > 0) && + (softirq_calls > 0); } /* Cancel the timer and work. */ @@ -109,21 +125,18 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *), flush_work(&state.bh_work); /* Sanity check: the timer and BH functions should have been run. */ - KUNIT_EXPECT_GT_MSG(test, state.hardirq_func_calls, 0, + KUNIT_EXPECT_GT_MSG(test, atomic_read(&state.hardirq_func_calls), 0, "Timer function was not called"); - KUNIT_EXPECT_GT_MSG(test, state.softirq_func_calls, 0, + KUNIT_EXPECT_GT_MSG(test, atomic_read(&state.softirq_func_calls), 0, "BH work function was not called"); - /* Check for incorrect hash values reported from any context. */ - KUNIT_EXPECT_FALSE_MSG( - test, state.task_func_reported_failure, - "Incorrect hash values reported from task context"); - KUNIT_EXPECT_FALSE_MSG( - test, state.hardirq_func_reported_failure, - "Incorrect hash values reported from hardirq context"); - KUNIT_EXPECT_FALSE_MSG( - test, state.softirq_func_reported_failure, - "Incorrect hash values reported from softirq context"); + /* Check for failure reported from any context. */ + KUNIT_EXPECT_FALSE_MSG(test, state.task_func_reported_failure, + "Failure reported from task context"); + KUNIT_EXPECT_FALSE_MSG(test, state.hardirq_func_reported_failure, + "Failure reported from hardirq context"); + KUNIT_EXPECT_FALSE_MSG(test, state.softirq_func_reported_failure, + "Failure reported from softirq context"); } #endif /* _KUNIT_RUN_IN_IRQ_CONTEXT_H */ diff --git a/include/linux/audit.h b/include/linux/audit.h index 536f8ee8da818c..b8d8029c6c480c 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -128,12 +128,6 @@ enum audit_nfcfgop { extern int __init audit_register_class(int class, unsigned *list); extern int audit_classify_syscall(int abi, unsigned syscall); extern int audit_classify_arch(int arch); -/* only for compat system calls */ -extern unsigned compat_write_class[]; -extern unsigned compat_read_class[]; -extern unsigned compat_dir_class[]; -extern unsigned compat_chattr_class[]; -extern unsigned compat_signal_class[]; /* audit_names->type values */ #define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ diff --git a/include/linux/audit_arch.h b/include/linux/audit_arch.h index 0e34d673ef1712..2b8153791e6a5d 100644 --- a/include/linux/audit_arch.h +++ b/include/linux/audit_arch.h @@ -23,4 +23,11 @@ enum auditsc_class_t { extern int audit_classify_compat_syscall(int abi, unsigned syscall); +/* only for compat system calls */ +extern unsigned compat_write_class[]; +extern unsigned compat_read_class[]; +extern unsigned compat_dir_class[]; +extern unsigned compat_chattr_class[]; +extern unsigned compat_signal_class[]; + #endif diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 44c30183ecc344..4e2e3aed32f5f7 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -469,10 +469,7 @@ static inline bool op_is_discard(blk_opf_t op) } /* - * Check if a bio or request operation is a zone management operation, with - * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case - * due to its different handling in the block layer and device response in - * case of command failure. + * Check if a bio or request operation is a zone management operation. */ static inline bool op_is_zone_mgmt(enum req_op op) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 70b671a9a7f775..59e54550a053f9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -485,7 +485,7 @@ struct request_queue { */ unsigned long queue_flags; - unsigned int rq_timeout; + unsigned int __data_racy rq_timeout; unsigned int queue_depth; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d808253f2e945d..e2dd3a6d495afd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -3200,6 +3200,11 @@ static inline void bpf_prog_report_arena_violation(bool write, unsigned long add } #endif /* CONFIG_BPF_SYSCALL */ +static inline bool bpf_net_capable(void) +{ + return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); +} + static __always_inline int bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) { diff --git a/include/linux/bpf_mprog.h b/include/linux/bpf_mprog.h index 929225f7b09594..0b9f4caeeb0a32 100644 --- a/include/linux/bpf_mprog.h +++ b/include/linux/bpf_mprog.h @@ -340,4 +340,14 @@ static inline bool bpf_mprog_supported(enum bpf_prog_type type) return false; } } + +static inline bool bpf_mprog_detach_empty(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_SCHED_CLS: + return bpf_net_capable(); + default: + return false; + } +} #endif /* __BPF_MPROG_H */ diff --git a/include/linux/buildid.h b/include/linux/buildid.h index 014a88c410739e..5e0a14866cc185 100644 --- a/include/linux/buildid.h +++ b/include/linux/buildid.h @@ -7,7 +7,10 @@ #define BUILD_ID_SIZE_MAX 20 struct vm_area_struct; +struct file; + int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size); +int build_id_parse_file(struct file *file, unsigned char *build_id, __u32 *size); int build_id_parse_nofault(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size); int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size); diff --git a/include/linux/capability.h b/include/linux/capability.h index 1fb08922552c79..37db92b3d6f89e 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -203,6 +203,12 @@ static inline bool checkpoint_restore_ns_capable(struct user_namespace *ns) ns_capable(ns, CAP_SYS_ADMIN); } +static inline bool checkpoint_restore_ns_capable_noaudit(struct user_namespace *ns) +{ + return ns_capable_noaudit(ns, CAP_CHECKPOINT_RESTORE) || + ns_capable_noaudit(ns, CAP_SYS_ADMIN); +} + /* audit system wants to get cap info from files as well */ int get_vfs_caps_from_disk(struct mnt_idmap *idmap, const struct dentry *dentry, diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index c7f2c63b3bc3fb..08e5dbe15ca444 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -31,6 +31,12 @@ #define CEPH_INO_CEPH 2 /* hidden .ceph dir */ #define CEPH_INO_GLOBAL_SNAPREALM 3 /* global dummy snaprealm */ +/* + * name for "old" CephFS file systems, + * see ceph.git e2b151d009640114b2565c901d6f41f6cd5ec652 + */ +#define CEPH_OLD_FS_NAME "cephfs" + /* arbitrary limit on max # of monitors (cluster of 3 is typical) */ #define CEPH_MAX_MON 31 diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index 2573585b7f068a..19c7e475d3a4d9 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -290,15 +290,16 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ class_##_name##_t var __cleanup(class_##_name##_destructor) = \ class_##_name##_constructor -#define scoped_class(_name, var, args) \ - for (CLASS(_name, var)(args); \ - __guard_ptr(_name)(&var) || !__is_cond_ptr(_name); \ - ({ goto _label; })) \ - if (0) { \ -_label: \ - break; \ +#define __scoped_class(_name, var, _label, args...) \ + for (CLASS(_name, var)(args); ; ({ goto _label; })) \ + if (0) { \ +_label: \ + break; \ } else +#define scoped_class(_name, var, args...) \ + __scoped_class(_name, var, __UNIQUE_ID(label), args) + /* * DEFINE_GUARD(name, type, lock, unlock): * trivial wrapper around DEFINE_CLASS() above specifically diff --git a/include/linux/clk.h b/include/linux/clk.h index b607482ca77e98..64ff118ffb1a1d 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -228,6 +228,23 @@ int devm_clk_rate_exclusive_get(struct device *dev, struct clk *clk); */ void clk_rate_exclusive_put(struct clk *clk); +/** + * clk_save_context - save clock context for poweroff + * + * Saves the context of the clock register for powerstates in which the + * contents of the registers will be lost. Occurs deep within the suspend + * code so locking is not necessary. + */ +int clk_save_context(void); + +/** + * clk_restore_context - restore clock context after poweroff + * + * This occurs with all clocks enabled. Occurs deep within the resume code + * so locking is not necessary. + */ +void clk_restore_context(void); + #else static inline int clk_notifier_register(struct clk *clk, @@ -293,6 +310,13 @@ static inline int devm_clk_rate_exclusive_get(struct device *dev, struct clk *cl static inline void clk_rate_exclusive_put(struct clk *clk) {} +static inline int clk_save_context(void) +{ + return 0; +} + +static inline void clk_restore_context(void) {} + #endif #ifdef CONFIG_HAVE_CLK_PREPARE @@ -933,23 +957,6 @@ struct clk *clk_get_parent(struct clk *clk); */ struct clk *clk_get_sys(const char *dev_id, const char *con_id); -/** - * clk_save_context - save clock context for poweroff - * - * Saves the context of the clock register for powerstates in which the - * contents of the registers will be lost. Occurs deep within the suspend - * code so locking is not necessary. - */ -int clk_save_context(void); - -/** - * clk_restore_context - restore clock context after poweroff - * - * This occurs with all clocks enabled. Occurs deep within the resume code - * so locking is not necessary. - */ -void clk_restore_context(void); - #else /* !CONFIG_HAVE_CLK */ static inline struct clk *clk_get(struct device *dev, const char *id) @@ -1129,13 +1136,6 @@ static inline struct clk *clk_get_sys(const char *dev_id, const char *con_id) return NULL; } -static inline int clk_save_context(void) -{ - return 0; -} - -static inline void clk_restore_context(void) {} - #endif /* clk_prepare_enable helps cases using clk_enable in non-atomic context. */ diff --git a/include/linux/cma.h b/include/linux/cma.h index 62d9c1cf632652..2e6931735880bd 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -57,6 +57,15 @@ extern bool cma_intersects(struct cma *cma, unsigned long start, unsigned long e extern void cma_reserve_pages_on_error(struct cma *cma); +#ifdef CONFIG_DMA_CMA +extern bool cma_skip_dt_default_reserved_mem(void); +#else +static inline bool cma_skip_dt_default_reserved_mem(void) +{ + return false; +} +#endif + #ifdef CONFIG_CMA struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp); bool cma_free_folio(struct cma *cma, const struct folio *folio); diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 0a1b9598940d05..8128a445f04808 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -13,6 +13,19 @@ #ifndef __ASSEMBLY__ +/* + * C23 introduces "auto" as a standard way to define type-inferred + * variables, but "auto" has been a (useless) keyword even since K&R C, + * so it has always been "namespace reserved." + * + * Until at some future time we require C23 support, we need the gcc + * extension __auto_type, but there is no reason to put that elsewhere + * in the source code. + */ +#if __STDC_VERSION__ < 202311L +# define auto __auto_type +#endif + /* * Skipped when running bindgen due to a libclang issue; * see https://github.com/rust-lang/rust-bindgen/issues/2244. diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 6de59ce8ef8ca4..fafc9ec13f9f43 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -251,15 +251,11 @@ struct coresight_trace_id_map { * by @coresight_ops. * @access: Device i/o access abstraction for this device. * @dev: The device entity associated to this component. - * @mode: This tracer's mode, i.e sysFS, Perf or disabled. This is - * actually an 'enum cs_mode', but is stored in an atomic type. - * This is always accessed through local_read() and local_set(), - * but wherever it's done from within the Coresight device's lock, - * a non-atomic read would also work. This is the main point of - * synchronisation between code happening inside the sysfs mode's - * coresight_mutex and outside when running in Perf mode. A compare - * and exchange swap is done to atomically claim one mode or the - * other. + * @mode: The device mode, i.e sysFS, Perf or disabled. This is actually + * an 'enum cs_mode' but stored in an atomic type. Access is always + * through atomic APIs, ensuring SMP-safe synchronisation between + * racing from sysFS and Perf mode. A compare-and-exchange + * operation is done to atomically claim one mode or the other. * @refcnt: keep track of what is in use. Only access this outside of the * device's spinlock when the coresight_mutex held and mode == * CS_MODE_SYSFS. Otherwise it must be accessed from inside the @@ -288,7 +284,7 @@ struct coresight_device { const struct coresight_ops *ops; struct csdev_access access; struct device dev; - local_t mode; + atomic_t mode; int refcnt; bool orphan; /* sink specific fields */ @@ -332,12 +328,14 @@ static struct coresight_dev_list (var) = { \ /** * struct coresight_path - data needed by enable/disable path - * @path_list: path from source to sink. - * @trace_id: trace_id of the whole path. + * @path_list: path from source to sink. + * @trace_id: trace_id of the whole path. + * @handle: handle of the aux_event. */ struct coresight_path { - struct list_head path_list; - u8 trace_id; + struct list_head path_list; + u8 trace_id; + struct perf_output_handle *handle; }; enum cs_mode { @@ -621,13 +619,14 @@ static inline bool coresight_is_percpu_sink(struct coresight_device *csdev) static inline bool coresight_take_mode(struct coresight_device *csdev, enum cs_mode new_mode) { - return local_cmpxchg(&csdev->mode, CS_MODE_DISABLED, new_mode) == - CS_MODE_DISABLED; + int curr = CS_MODE_DISABLED; + + return atomic_try_cmpxchg_acquire(&csdev->mode, &curr, new_mode); } static inline enum cs_mode coresight_get_mode(struct coresight_device *csdev) { - return local_read(&csdev->mode); + return atomic_read_acquire(&csdev->mode); } static inline void coresight_set_mode(struct coresight_device *csdev, @@ -643,7 +642,7 @@ static inline void coresight_set_mode(struct coresight_device *csdev, WARN(new_mode != CS_MODE_DISABLED && current_mode != CS_MODE_DISABLED && current_mode != new_mode, "Device already in use\n"); - local_set(&csdev->mode, new_mode); + atomic_set_release(&csdev->mode, new_mode); } struct coresight_device *coresight_register(struct coresight_desc *desc); diff --git a/include/linux/cper.h b/include/linux/cper.h index 0ed60a91eca9d6..5b1236d8c65bb7 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -297,11 +297,11 @@ enum { #define CPER_ARM_INFO_FLAGS_PROPAGATED BIT(2) #define CPER_ARM_INFO_FLAGS_OVERFLOW BIT(3) -#define CPER_ARM_CACHE_ERROR 0 -#define CPER_ARM_TLB_ERROR 1 -#define CPER_ARM_BUS_ERROR 2 -#define CPER_ARM_VENDOR_ERROR 3 -#define CPER_ARM_MAX_TYPE CPER_ARM_VENDOR_ERROR +#define CPER_ARM_ERR_TYPE_MASK GENMASK(4,1) +#define CPER_ARM_CACHE_ERROR BIT(1) +#define CPER_ARM_TLB_ERROR BIT(2) +#define CPER_ARM_BUS_ERROR BIT(3) +#define CPER_ARM_VENDOR_ERROR BIT(4) #define CPER_ARM_ERR_VALID_TRANSACTION_TYPE BIT(0) #define CPER_ARM_ERR_VALID_OPERATION_TYPE BIT(1) @@ -588,6 +588,8 @@ const char *cper_mem_err_type_str(unsigned int); const char *cper_mem_err_status_str(u64 status); void cper_print_bits(const char *prefix, unsigned int bits, const char * const strs[], unsigned int strs_size); +int cper_bits_to_str(char *buf, int buf_size, unsigned long bits, + const char * const strs[], unsigned int strs_size); void cper_mem_err_pack(const struct cper_sec_mem_err *, struct cper_mem_err_compact *); const char *cper_mem_err_unpack(struct trace_seq *, diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h index 7b44b41d0a20d4..f0dc03d94ca2cd 100644 --- a/include/linux/crash_reserve.h +++ b/include/linux/crash_reserve.h @@ -32,6 +32,12 @@ int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, void __init reserve_crashkernel_cma(unsigned long long cma_size); #ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION +#ifndef arch_add_crash_res_to_iomem +static inline bool arch_add_crash_res_to_iomem(void) +{ + return true; +} +#endif #ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE #define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) #endif diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h index 0864773a57e8fe..822085bc2d202c 100644 --- a/include/linux/device_cgroup.h +++ b/include/linux/device_cgroup.h @@ -21,7 +21,7 @@ static inline int devcgroup_inode_permission(struct inode *inode, int mask) if (likely(!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode))) return 0; - if (likely(!inode->i_rdev)) + if (!inode->i_rdev) return 0; if (S_ISBLK(inode->i_mode)) diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 2ceda49c609fb7..aa36a0d1d9df6a 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -90,7 +90,7 @@ */ #define DMA_MAPPING_ERROR (~(dma_addr_t)0) -#define DMA_BIT_MASK(n) GENMASK_ULL(n - 1, 0) +#define DMA_BIT_MASK(n) GENMASK_ULL((n) - 1, 0) struct dma_iova_state { dma_addr_t addr; diff --git a/include/linux/dpll.h b/include/linux/dpll.h index 25be745bf41f1d..562f520b23c277 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -163,6 +163,7 @@ struct dpll_pin_properties { u32 freq_supported_num; struct dpll_pin_frequency *freq_supported; struct dpll_pin_phase_adjust_range phase_range; + u32 phase_gran; }; #if IS_ENABLED(CONFIG_DPLL) diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 61d50571ad88ac..ce2db5447d2214 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -18,7 +18,7 @@ * @power: The power consumed at this level (by 1 CPU or by a registered * device). It can be a total power: static and dynamic. * @cost: The cost coefficient associated with this level, used during - * energy calculation. Equal to: power * max_frequency / frequency + * energy calculation. Equal to: 10 * power * max_frequency / frequency * @flags: see "em_perf_state flags" description below. */ struct em_perf_state { diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 6afb4a13b81d65..dc41722fcc9dde 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -441,10 +441,8 @@ struct f2fs_sit_block { * from node's page's beginning to get a data block address. * ex) data_blkaddr = (block_t)(nodepage_start_address + ofs_in_node) */ -#define ENTRIES_IN_SUM (F2FS_BLKSIZE / 8) #define SUMMARY_SIZE (7) /* sizeof(struct f2fs_summary) */ #define SUM_FOOTER_SIZE (5) /* sizeof(struct summary_footer) */ -#define SUM_ENTRY_SIZE (SUMMARY_SIZE * ENTRIES_IN_SUM) /* a summary entry for a block in a segment */ struct f2fs_summary { @@ -467,22 +465,6 @@ struct summary_footer { __le32 check_sum; /* summary checksum */ } __packed; -#define SUM_JOURNAL_SIZE (F2FS_BLKSIZE - SUM_FOOTER_SIZE -\ - SUM_ENTRY_SIZE) -#define NAT_JOURNAL_ENTRIES ((SUM_JOURNAL_SIZE - 2) /\ - sizeof(struct nat_journal_entry)) -#define NAT_JOURNAL_RESERVED ((SUM_JOURNAL_SIZE - 2) %\ - sizeof(struct nat_journal_entry)) -#define SIT_JOURNAL_ENTRIES ((SUM_JOURNAL_SIZE - 2) /\ - sizeof(struct sit_journal_entry)) -#define SIT_JOURNAL_RESERVED ((SUM_JOURNAL_SIZE - 2) %\ - sizeof(struct sit_journal_entry)) - -/* Reserved area should make size of f2fs_extra_info equals to - * that of nat_journal and sit_journal. - */ -#define EXTRA_INFO_RESERVED (SUM_JOURNAL_SIZE - 2 - 8) - /* * frequently updated NAT/SIT entries can be stored in the spare area in * summary blocks @@ -497,9 +479,16 @@ struct nat_journal_entry { struct f2fs_nat_entry ne; } __packed; +/* + * The nat_journal structure is a placeholder whose actual size varies depending + * on the use of packed_ssa. Therefore, it must always be accessed only through + * specific sets of macros and fields, and size calculations should use + * size-related macros instead of sizeof(). + * Relevant macros: sbi->nat_journal_entries, nat_in_journal(), + * nid_in_journal(), MAX_NAT_JENTRIES(). + */ struct nat_journal { - struct nat_journal_entry entries[NAT_JOURNAL_ENTRIES]; - __u8 reserved[NAT_JOURNAL_RESERVED]; + struct nat_journal_entry entries[0]; } __packed; struct sit_journal_entry { @@ -507,14 +496,21 @@ struct sit_journal_entry { struct f2fs_sit_entry se; } __packed; +/* + * The sit_journal structure is a placeholder whose actual size varies depending + * on the use of packed_ssa. Therefore, it must always be accessed only through + * specific sets of macros and fields, and size calculations should use + * size-related macros instead of sizeof(). + * Relevant macros: sbi->sit_journal_entries, sit_in_journal(), + * segno_in_journal(), MAX_SIT_JENTRIES(). + */ struct sit_journal { - struct sit_journal_entry entries[SIT_JOURNAL_ENTRIES]; - __u8 reserved[SIT_JOURNAL_RESERVED]; + struct sit_journal_entry entries[0]; } __packed; struct f2fs_extra_info { __le64 kbytes_written; - __u8 reserved[EXTRA_INFO_RESERVED]; + __u8 reserved[]; } __packed; struct f2fs_journal { @@ -530,11 +526,33 @@ struct f2fs_journal { }; } __packed; -/* Block-sized summary block structure */ +/* + * Block-sized summary block structure + * + * The f2fs_summary_block structure is a placeholder whose actual size varies + * depending on the use of packed_ssa. Therefore, it must always be accessed + * only through specific sets of macros and fields, and size calculations should + * use size-related macros instead of sizeof(). + * Relevant macros: sbi->sum_blocksize, sbi->entries_in_sum, + * sbi->sum_entry_size, sum_entries(), sum_journal(), sum_footer(). + * + * Summary Block Layout + * + * +-----------------------+ <--- Block Start + * | struct f2fs_summary | + * | entries[0] | + * | ... | + * | entries[N-1] | + * +-----------------------+ + * | struct f2fs_journal | + * +-----------------------+ + * | struct summary_footer | + * +-----------------------+ <--- Block End + */ struct f2fs_summary_block { - struct f2fs_summary entries[ENTRIES_IN_SUM]; - struct f2fs_journal journal; - struct summary_footer footer; + struct f2fs_summary entries[0]; + // struct f2fs_journal journal; + // struct summary_footer footer; } __packed; /* diff --git a/include/linux/filter.h b/include/linux/filter.h index 973233b82dc1fd..cf7a0bce1bb6d8 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -712,11 +712,13 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, ret = dfunc(ctx, prog->insnsi, prog->bpf_func); duration = sched_clock() - start; - stats = this_cpu_ptr(prog->stats); - flags = u64_stats_update_begin_irqsave(&stats->syncp); - u64_stats_inc(&stats->cnt); - u64_stats_add(&stats->nsecs, duration); - u64_stats_update_end_irqrestore(&stats->syncp, flags); + if (likely(prog->stats)) { + stats = this_cpu_ptr(prog->stats); + flags = u64_stats_update_begin_irqsave(&stats->syncp); + u64_stats_inc(&stats->cnt); + u64_stats_add(&stats->nsecs, duration); + u64_stats_update_end_irqrestore(&stats->syncp, flags); + } } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); } @@ -1373,24 +1375,13 @@ static inline bool bpf_jit_kallsyms_enabled(void) return false; } -int __bpf_address_lookup(unsigned long addr, unsigned long *size, - unsigned long *off, char *sym); +int bpf_address_lookup(unsigned long addr, unsigned long *size, + unsigned long *off, char *sym); bool is_bpf_text_address(unsigned long addr); int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); struct bpf_prog *bpf_prog_ksym_find(unsigned long addr); -static inline int -bpf_address_lookup(unsigned long addr, unsigned long *size, - unsigned long *off, char **modname, char *sym) -{ - int ret = __bpf_address_lookup(addr, size, off, sym); - - if (ret && modname) - *modname = NULL; - return ret; -} - void bpf_prog_kallsyms_add(struct bpf_prog *fp); void bpf_prog_kallsyms_del(struct bpf_prog *fp); @@ -1429,8 +1420,8 @@ static inline bool bpf_jit_kallsyms_enabled(void) } static inline int -__bpf_address_lookup(unsigned long addr, unsigned long *size, - unsigned long *off, char *sym) +bpf_address_lookup(unsigned long addr, unsigned long *size, + unsigned long *off, char *sym) { return 0; } @@ -1451,13 +1442,6 @@ static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) return NULL; } -static inline int -bpf_address_lookup(unsigned long addr, unsigned long *size, - unsigned long *off, char **modname, char *sym) -{ - return 0; -} - static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp) { } diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index a66eb7624730c4..69959032f8f51e 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -188,8 +188,8 @@ struct cs_dsp { #ifdef CONFIG_DEBUG_FS struct dentry *debugfs_root; - char *wmfw_file_name; - char *bin_file_name; + const char *wmfw_file_name; + const char *bin_file_name; #endif }; diff --git a/include/linux/firmware/qcom/qcom_tzmem.h b/include/linux/firmware/qcom/qcom_tzmem.h index 48ac0e5454c7fc..23173e0c3dddd1 100644 --- a/include/linux/firmware/qcom/qcom_tzmem.h +++ b/include/linux/firmware/qcom/qcom_tzmem.h @@ -17,11 +17,20 @@ struct qcom_tzmem_pool; * enum qcom_tzmem_policy - Policy for pool growth. */ enum qcom_tzmem_policy { - /**< Static pool, never grow above initial size. */ + /** + * @QCOM_TZMEM_POLICY_STATIC: Static pool, + * never grow above initial size. + */ QCOM_TZMEM_POLICY_STATIC = 1, - /**< When out of memory, add increment * current size of memory. */ + /** + * @QCOM_TZMEM_POLICY_MULTIPLIER: When out of memory, + * add increment * current size of memory. + */ QCOM_TZMEM_POLICY_MULTIPLIER, - /**< When out of memory add as much as is needed until max_size. */ + /** + * @QCOM_TZMEM_POLICY_ON_DEMAND: When out of memory + * add as much as is needed until max_size. + */ QCOM_TZMEM_POLICY_ON_DEMAND, }; diff --git a/include/linux/fs.h b/include/linux/fs.h index dd3b57cfadeeb4..3e965c77fa1b16 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2207,6 +2207,8 @@ struct dir_context { * INT_MAX unlimited */ int count; + /* @actor supports these flags in d_type high bits */ + unsigned int dt_flags_mask; }; /* If OR-ed with d_type, pending signals are not checked */ @@ -3676,7 +3678,7 @@ struct offset_ctx { void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); -int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, +void simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, @@ -3985,7 +3987,9 @@ static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { - return ctx->actor(ctx, name, namelen, ctx->pos, ino, type); + unsigned int dt_mask = S_DT_MASK | ctx->dt_flags_mask; + + return ctx->actor(ctx, name, namelen, ctx->pos, ino, type & dt_mask); } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 07f8c309e43273..9cc60e2506af16 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -87,11 +87,13 @@ struct ftrace_hash; defined(CONFIG_DYNAMIC_FTRACE) int ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, - unsigned long *off, char **modname, char *sym); + unsigned long *off, char **modname, + const unsigned char **modbuildid, char *sym); #else static inline int ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, - unsigned long *off, char **modname, char *sym) + unsigned long *off, char **modname, + const unsigned char **modbuildid, char *sym) { return 0; } diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 097be89487bf5c..53e46648131d91 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -229,5 +229,6 @@ int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup, void fwnode_links_purge(struct fwnode_handle *fwnode); void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode); bool fw_devlink_is_strict(void); +int fw_devlink_count_absent_consumers(struct fwnode_handle *fwnode); #endif diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 0bd581003cd5df..60de63e46b33dd 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -44,6 +44,7 @@ struct gen_pool; * @nr: The number of zeroed bits we're looking for * @data: optional additional data used by the callback * @pool: the pool being allocated from + * @start_addr: start address of memory chunk */ typedef unsigned long (*genpool_algo_t)(unsigned long *map, unsigned long size, diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 623bee335383ef..b155929af5b110 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -387,7 +387,7 @@ extern void free_pages(unsigned long addr, unsigned int order); #define free_page(addr) free_pages((addr), 0) void page_alloc_init_cpuhp(void); -int decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp); +bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); diff --git a/include/linux/hid.h b/include/linux/hid.h index a4ddb94e3ee563..8c6d3124c20c9c 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -625,7 +625,9 @@ struct hid_input { enum hid_type { HID_TYPE_OTHER = 0, HID_TYPE_USBMOUSE, - HID_TYPE_USBNONE + HID_TYPE_USBNONE, + HID_TYPE_SPI_KEYBOARD, + HID_TYPE_SPI_MOUSE, }; enum hid_battery_status { @@ -786,6 +788,8 @@ struct hid_descriptor { .bus = BUS_BLUETOOTH, .vendor = (ven), .product = (prod) #define HID_I2C_DEVICE(ven, prod) \ .bus = BUS_I2C, .vendor = (ven), .product = (prod) +#define HID_SPI_DEVICE(ven, prod) \ + .bus = BUS_SPI, .vendor = (ven), .product = (prod) #define HID_REPORT_ID(rep) \ .report_type = (rep) diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index c4690e365ade90..4cf418a41fe438 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -444,12 +444,16 @@ struct hisi_qp_ops { int (*fill_sqe)(void *sqe, void *q_parm, void *d_parm); }; +struct instance_backlog { + struct list_head list; + spinlock_t lock; +}; + struct hisi_qp { u32 qp_id; u16 sq_depth; u16 cq_depth; u8 alg_type; - u8 req_type; struct qm_dma qdma; void *sqe; @@ -459,7 +463,6 @@ struct hisi_qp { struct hisi_qp_status qp_status; struct hisi_qp_ops *hw_ops; - void *qp_ctx; void (*req_cb)(struct hisi_qp *qp, void *data); void (*event_cb)(struct hisi_qp *qp); @@ -468,6 +471,10 @@ struct hisi_qp { bool is_in_kernel; u16 pasid; struct uacce_queue *uacce_q; + + spinlock_t qp_lock; + struct instance_backlog backlog; + const void **msg; }; static inline int vfs_num_set(const char *val, const struct kernel_param *kp) @@ -572,7 +579,7 @@ struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev, void hisi_acc_free_sgl_pool(struct device *dev, struct hisi_acc_sgl_pool *pool); int hisi_qm_alloc_qps_node(struct hisi_qm_list *qm_list, int qp_num, - u8 alg_type, int node, struct hisi_qp **qps); + u8 *alg_type, int node, struct hisi_qp **qps); void hisi_qm_free_qps(struct hisi_qp **qps, int qp_num); void hisi_qm_dev_shutdown(struct pci_dev *pdev); void hisi_qm_wait_task_finish(struct hisi_qm *qm, struct hisi_qm_list *qm_list); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 71ac78b9f834f6..240cbc67648090 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -369,10 +369,8 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order); int min_order_for_split(struct folio *folio); int split_folio_to_list(struct folio *folio, struct list_head *list); -bool uniform_split_supported(struct folio *folio, unsigned int new_order, - bool warns); -bool non_uniform_split_supported(struct folio *folio, unsigned int new_order, - bool warns); +bool folio_split_supported(struct folio *folio, unsigned int new_order, + bool uniform_split, bool warns); int folio_split(struct folio *folio, unsigned int new_order, struct page *page, struct list_head *list); /* @@ -392,7 +390,7 @@ int folio_split(struct folio *folio, unsigned int new_order, struct page *page, static inline int try_folio_split_to_order(struct folio *folio, struct page *page, unsigned int new_order) { - if (!non_uniform_split_supported(folio, new_order, /* warns= */ false)) + if (!folio_split_supported(folio, new_order, false, /* warns= */ false)) return split_huge_page_to_list_to_order(&folio->page, NULL, new_order); return folio_split(folio, new_order, page, NULL); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8e63e46b8e1f0e..6fc7934eafa116 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -241,8 +241,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep); +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); @@ -302,13 +303,17 @@ static inline struct address_space *hugetlb_folio_mapping_lock_write( return NULL; } -static inline int huge_pmd_unshare(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline int huge_pmd_unshare(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } +static inline void huge_pmd_unshare_flush(struct mmu_gather *tlb, + struct vm_area_struct *vma) +{ +} + static inline void adjust_range_if_pmd_sharing_possible( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) @@ -1323,7 +1328,7 @@ static inline __init void hugetlb_cma_reserve(int order) #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline bool hugetlb_pmd_shared(pte_t *pte) { - return page_count(virt_to_page(pte)) > 1; + return ptdesc_pmd_is_shared(virt_to_ptdesc(pte)); } #else static inline bool hugetlb_pmd_shared(pte_t *pte) diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index b424555753b11f..b77bc55a4cf356 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -15,6 +15,7 @@ #include #include #include +#include /** * struct hwrng - Hardware Random Number Generator driver @@ -48,6 +49,7 @@ struct hwrng { /* internal. */ struct list_head list; struct kref ref; + struct work_struct cleanup_work; struct completion cleanup_done; struct completion dying; }; diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index ddff9102f63329..1f4679092e69d4 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -3594,8 +3594,8 @@ enum ieee80211_statuscode { WLAN_STATUS_DENIED_WITH_SUGGESTED_BAND_AND_CHANNEL = 99, WLAN_STATUS_DENIED_DUE_TO_SPECTRUM_MANAGEMENT = 103, /* 802.11ai */ - WLAN_STATUS_FILS_AUTHENTICATION_FAILURE = 108, - WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 109, + WLAN_STATUS_FILS_AUTHENTICATION_FAILURE = 112, + WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 113, WLAN_STATUS_SAE_HASH_TO_ELEMENT = 126, WLAN_STATUS_SAE_PK = 127, WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING = 133, diff --git a/include/linux/if_hsr.h b/include/linux/if_hsr.h index d7941fd8803295..f4cf2dd36d193d 100644 --- a/include/linux/if_hsr.h +++ b/include/linux/if_hsr.h @@ -43,6 +43,8 @@ extern bool is_hsr_master(struct net_device *dev); extern int hsr_get_version(struct net_device *dev, enum hsr_version *ver); struct net_device *hsr_get_port_ndev(struct net_device *ndev, enum hsr_port_type pt); +int hsr_get_port_type(struct net_device *hsr_dev, struct net_device *dev, + enum hsr_port_type *type); #else static inline bool is_hsr_master(struct net_device *dev) { @@ -59,6 +61,13 @@ static inline struct net_device *hsr_get_port_ndev(struct net_device *ndev, { return ERR_PTR(-EINVAL); } + +static inline int hsr_get_port_type(struct net_device *hsr_dev, + struct net_device *dev, + enum hsr_port_type *type) +{ + return -EINVAL; +} #endif /* CONFIG_HSR */ #endif /*_LINUX_IF_HSR_H_*/ diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 4247497f3f8bd4..b87841a355f802 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -14,6 +14,7 @@ * @mlock: lock used to prevent simultaneous device state changes * @mlock_key: lockdep class for iio_dev lock * @info_exist_lock: lock to prevent use during removal + * @info_exist_key: lockdep class for info_exist lock * @trig_readonly: mark the current trigger immutable * @event_interface: event chrdevs associated with interrupt lines * @attached_buffers: array of buffers statically attached by the driver @@ -47,6 +48,7 @@ struct iio_dev_opaque { struct mutex mlock; struct lock_class_key mlock_key; struct mutex info_exist_lock; + struct lock_class_key info_exist_key; bool trig_readonly; struct iio_event_interface *event_interface; struct iio_buffer **attached_buffers; diff --git a/include/linux/input/adp5589.h b/include/linux/input/adp5589.h deleted file mode 100644 index 0e4742c8c81e3c..00000000000000 --- a/include/linux/input/adp5589.h +++ /dev/null @@ -1,180 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Analog Devices ADP5589/ADP5585 I/O Expander and QWERTY Keypad Controller - * - * Copyright 2010-2011 Analog Devices Inc. - */ - -#ifndef _ADP5589_H -#define _ADP5589_H - -/* - * ADP5589 specific GPI and Keymap defines - */ - -#define ADP5589_KEYMAPSIZE 88 - -#define ADP5589_GPI_PIN_ROW0 97 -#define ADP5589_GPI_PIN_ROW1 98 -#define ADP5589_GPI_PIN_ROW2 99 -#define ADP5589_GPI_PIN_ROW3 100 -#define ADP5589_GPI_PIN_ROW4 101 -#define ADP5589_GPI_PIN_ROW5 102 -#define ADP5589_GPI_PIN_ROW6 103 -#define ADP5589_GPI_PIN_ROW7 104 -#define ADP5589_GPI_PIN_COL0 105 -#define ADP5589_GPI_PIN_COL1 106 -#define ADP5589_GPI_PIN_COL2 107 -#define ADP5589_GPI_PIN_COL3 108 -#define ADP5589_GPI_PIN_COL4 109 -#define ADP5589_GPI_PIN_COL5 110 -#define ADP5589_GPI_PIN_COL6 111 -#define ADP5589_GPI_PIN_COL7 112 -#define ADP5589_GPI_PIN_COL8 113 -#define ADP5589_GPI_PIN_COL9 114 -#define ADP5589_GPI_PIN_COL10 115 -#define GPI_LOGIC1 116 -#define GPI_LOGIC2 117 - -#define ADP5589_GPI_PIN_ROW_BASE ADP5589_GPI_PIN_ROW0 -#define ADP5589_GPI_PIN_ROW_END ADP5589_GPI_PIN_ROW7 -#define ADP5589_GPI_PIN_COL_BASE ADP5589_GPI_PIN_COL0 -#define ADP5589_GPI_PIN_COL_END ADP5589_GPI_PIN_COL10 - -#define ADP5589_GPI_PIN_BASE ADP5589_GPI_PIN_ROW_BASE -#define ADP5589_GPI_PIN_END ADP5589_GPI_PIN_COL_END - -#define ADP5589_GPIMAPSIZE_MAX (ADP5589_GPI_PIN_END - ADP5589_GPI_PIN_BASE + 1) - -/* - * ADP5585 specific GPI and Keymap defines - */ - -#define ADP5585_KEYMAPSIZE 30 - -#define ADP5585_GPI_PIN_ROW0 37 -#define ADP5585_GPI_PIN_ROW1 38 -#define ADP5585_GPI_PIN_ROW2 39 -#define ADP5585_GPI_PIN_ROW3 40 -#define ADP5585_GPI_PIN_ROW4 41 -#define ADP5585_GPI_PIN_ROW5 42 -#define ADP5585_GPI_PIN_COL0 43 -#define ADP5585_GPI_PIN_COL1 44 -#define ADP5585_GPI_PIN_COL2 45 -#define ADP5585_GPI_PIN_COL3 46 -#define ADP5585_GPI_PIN_COL4 47 -#define GPI_LOGIC 48 - -#define ADP5585_GPI_PIN_ROW_BASE ADP5585_GPI_PIN_ROW0 -#define ADP5585_GPI_PIN_ROW_END ADP5585_GPI_PIN_ROW5 -#define ADP5585_GPI_PIN_COL_BASE ADP5585_GPI_PIN_COL0 -#define ADP5585_GPI_PIN_COL_END ADP5585_GPI_PIN_COL4 - -#define ADP5585_GPI_PIN_BASE ADP5585_GPI_PIN_ROW_BASE -#define ADP5585_GPI_PIN_END ADP5585_GPI_PIN_COL_END - -#define ADP5585_GPIMAPSIZE_MAX (ADP5585_GPI_PIN_END - ADP5585_GPI_PIN_BASE + 1) - -struct adp5589_gpi_map { - unsigned short pin; - unsigned short sw_evt; -}; - -/* scan_cycle_time */ -#define ADP5589_SCAN_CYCLE_10ms 0 -#define ADP5589_SCAN_CYCLE_20ms 1 -#define ADP5589_SCAN_CYCLE_30ms 2 -#define ADP5589_SCAN_CYCLE_40ms 3 - -/* RESET_CFG */ -#define RESET_PULSE_WIDTH_500us 0 -#define RESET_PULSE_WIDTH_1ms 1 -#define RESET_PULSE_WIDTH_2ms 2 -#define RESET_PULSE_WIDTH_10ms 3 - -#define RESET_TRIG_TIME_0ms (0 << 2) -#define RESET_TRIG_TIME_1000ms (1 << 2) -#define RESET_TRIG_TIME_1500ms (2 << 2) -#define RESET_TRIG_TIME_2000ms (3 << 2) -#define RESET_TRIG_TIME_2500ms (4 << 2) -#define RESET_TRIG_TIME_3000ms (5 << 2) -#define RESET_TRIG_TIME_3500ms (6 << 2) -#define RESET_TRIG_TIME_4000ms (7 << 2) - -#define RESET_PASSTHRU_EN (1 << 5) -#define RESET1_POL_HIGH (1 << 6) -#define RESET1_POL_LOW (0 << 6) -#define RESET2_POL_HIGH (1 << 7) -#define RESET2_POL_LOW (0 << 7) - -/* ADP5589 Mask Bits: - * C C C C C C C C C C C | R R R R R R R R - * 1 9 8 7 6 5 4 3 2 1 0 | 7 6 5 4 3 2 1 0 - * 0 - * ---------------- BIT ------------------ - * 1 1 1 1 1 1 1 1 1 0 0 | 0 0 0 0 0 0 0 0 - * 8 7 6 5 4 3 2 1 0 9 8 | 7 6 5 4 3 2 1 0 - */ - -#define ADP_ROW(x) (1 << (x)) -#define ADP_COL(x) (1 << (x + 8)) -#define ADP5589_ROW_MASK 0xFF -#define ADP5589_COL_MASK 0xFF -#define ADP5589_COL_SHIFT 8 -#define ADP5589_MAX_ROW_NUM 7 -#define ADP5589_MAX_COL_NUM 10 - -/* ADP5585 Mask Bits: - * C C C C C | R R R R R R - * 4 3 2 1 0 | 5 4 3 2 1 0 - * - * ---- BIT -- ----------- - * 1 0 0 0 0 | 0 0 0 0 0 0 - * 0 9 8 7 6 | 5 4 3 2 1 0 - */ - -#define ADP5585_ROW_MASK 0x3F -#define ADP5585_COL_MASK 0x1F -#define ADP5585_ROW_SHIFT 0 -#define ADP5585_COL_SHIFT 6 -#define ADP5585_MAX_ROW_NUM 5 -#define ADP5585_MAX_COL_NUM 4 - -#define ADP5585_ROW(x) (1 << ((x) & ADP5585_ROW_MASK)) -#define ADP5585_COL(x) (1 << (((x) & ADP5585_COL_MASK) + ADP5585_COL_SHIFT)) - -/* Put one of these structures in i2c_board_info platform_data */ - -struct adp5589_kpad_platform_data { - unsigned keypad_en_mask; /* Keypad (Rows/Columns) enable mask */ - const unsigned short *keymap; /* Pointer to keymap */ - unsigned short keymapsize; /* Keymap size */ - bool repeat; /* Enable key repeat */ - bool en_keylock; /* Enable key lock feature (ADP5589 only)*/ - unsigned char unlock_key1; /* Unlock Key 1 (ADP5589 only) */ - unsigned char unlock_key2; /* Unlock Key 2 (ADP5589 only) */ - unsigned char unlock_timer; /* Time in seconds [0..7] between the two unlock keys 0=disable (ADP5589 only) */ - unsigned char scan_cycle_time; /* Time between consecutive scan cycles */ - unsigned char reset_cfg; /* Reset config */ - unsigned short reset1_key_1; /* Reset Key 1 */ - unsigned short reset1_key_2; /* Reset Key 2 */ - unsigned short reset1_key_3; /* Reset Key 3 */ - unsigned short reset2_key_1; /* Reset Key 1 */ - unsigned short reset2_key_2; /* Reset Key 2 */ - unsigned debounce_dis_mask; /* Disable debounce mask */ - unsigned pull_dis_mask; /* Disable all pull resistors mask */ - unsigned pullup_en_100k; /* Pull-Up 100k Enable Mask */ - unsigned pullup_en_300k; /* Pull-Up 300k Enable Mask */ - unsigned pulldown_en_300k; /* Pull-Down 300k Enable Mask */ - const struct adp5589_gpi_map *gpimap; - unsigned short gpimapsize; - const struct adp5589_gpio_platform_data *gpio_data; -}; - -struct i2c_client; /* forward declaration */ - -struct adp5589_gpio_platform_data { - int gpio_start; /* GPIO Chip base # */ -}; - -#endif diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index dfbf7d9d7bb5a8..b235fd84f47804 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -87,6 +87,8 @@ bool ishtp_wait_resume(struct ishtp_device *dev); ishtp_print_log ishtp_trace_callback(struct ishtp_cl_device *cl_device); /* Get device pointer of PCI device for DMA acces */ struct device *ishtp_get_pci_device(struct ishtp_cl_device *cl_device); +/* Get the ISHTP workqueue */ +struct workqueue_struct *ishtp_get_workqueue(struct ishtp_cl_device *cl_device); struct ishtp_cl *ishtp_cl_allocate(struct ishtp_cl_device *cl_device); void ishtp_cl_free(struct ishtp_cl *cl); diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 51b6484c049345..8f1166bc3b1cef 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -215,7 +215,7 @@ static inline int __must_check devm_request_irq(struct device *dev, unsigned int irq, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id) { - return devm_request_threaded_irq(dev, irq, handler, NULL, irqflags, + return devm_request_threaded_irq(dev, irq, handler, NULL, irqflags | IRQF_COND_ONESHOT, devname, dev_id); } diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 8a823c6f2b4a88..9800b3c8a597ae 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -178,7 +178,7 @@ struct io_pgtable_cfg { } arm_mali_lpae_cfg; struct { - u64 ttbr[4]; + void *ttbr[4]; u32 n_ttbrs; u32 n_levels; } apple_dart_cfg; diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index c2ea6280901dca..b4d8aca3e78604 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -439,6 +439,9 @@ struct io_ring_ctx { struct list_head defer_list; unsigned nr_drained; + /* protected by ->completion_lock */ + unsigned nr_req_allocated; + #ifdef CONFIG_NET_RX_BUSY_POLL struct list_head napi_list; /* track busy poll napi_id */ spinlock_t napi_lock; /* napi_list lock */ @@ -451,10 +454,6 @@ struct io_ring_ctx { DECLARE_HASHTABLE(napi_ht, 4); #endif - /* protected by ->completion_lock */ - unsigned evfd_last_cq_tail; - unsigned nr_req_allocated; - /* * Protection for resize vs mmap races - both the mmap and resize * side will need to grab this lock, to prevent either side from diff --git a/include/linux/iommu.h b/include/linux/iommu.h index c30d12e16473df..602cf6dbc65264 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -289,12 +289,18 @@ enum iommu_resv_type { IOMMU_RESV_MSI, /* Software-managed MSI translation window */ IOMMU_RESV_SW_MSI, + /* + * Memory regions which must be mapped with the specified mapping + * at all times. + */ + IOMMU_RESV_TRANSLATED, }; /** * struct iommu_resv_region - descriptor for a reserved memory region * @list: Linked list pointers * @start: System physical start address of the region + * @start: Device virtual start address of the region for IOMMU_RESV_TRANSLATED * @length: Length of the region in bytes * @prot: IOMMU Protection flags (READ/WRITE/...) * @type: Type of the reserved region @@ -303,6 +309,7 @@ enum iommu_resv_type { struct iommu_resv_region { struct list_head list; phys_addr_t start; + dma_addr_t dva; size_t length; int prot; enum iommu_resv_type type; @@ -837,6 +844,7 @@ struct iommu_fault_param { * @pci_32bit_workaround: Limit DMA allocations to 32-bit IOVAs * @require_direct: device requires IOMMU_RESV_DIRECT regions * @shadow_on_flush: IOTLB flushes are used to sync shadow tables + * @require_translated: device requires IOMMU_RESV_TRANSLATED regions * * TODO: migrate other per device data pointers under iommu_dev_data, e.g. * struct iommu_group *iommu_group; @@ -852,6 +860,7 @@ struct dev_iommu { u32 pci_32bit_workaround:1; u32 require_direct:1; u32 shadow_on_flush:1; + u32 require_translated:1; }; int iommu_device_register(struct iommu_device *iommu, @@ -936,6 +945,9 @@ extern bool iommu_default_passthrough(void); extern struct iommu_resv_region * iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot, enum iommu_resv_type type, gfp_t gfp); +extern struct iommu_resv_region * +iommu_alloc_resv_region_tr(phys_addr_t start, dma_addr_t dva_start, size_t length, + int prot, enum iommu_resv_type type, gfp_t gfp); extern int iommu_get_group_resv_regions(struct iommu_group *group, struct list_head *head); @@ -1134,7 +1146,9 @@ struct iommu_sva { struct iommu_mm_data { u32 pasid; + struct mm_struct *mm; struct list_head sva_domains; + struct list_head mm_list_elm; }; int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode); @@ -1615,6 +1629,7 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm); void iommu_sva_unbind_device(struct iommu_sva *handle); u32 iommu_sva_get_pasid(struct iommu_sva *handle); +void iommu_sva_invalidate_kva_range(unsigned long start, unsigned long end); #else static inline struct iommu_sva * iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) @@ -1639,6 +1654,7 @@ static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm) } static inline void mm_pasid_drop(struct mm_struct *mm) {} +static inline void iommu_sva_invalidate_kva_range(unsigned long start, unsigned long end) {} #endif /* CONFIG_IOMMU_SVA */ #ifdef CONFIG_IOMMU_IOPF diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h index d643c7c87822e1..ba1ed42f8a1c29 100644 --- a/include/linux/irq-entry-common.h +++ b/include/linux/irq-entry-common.h @@ -253,11 +253,11 @@ static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs) static __always_inline void exit_to_user_mode(void) { instrumentation_begin(); + unwind_reset_info(); trace_hardirqs_on_prepare(); lockdep_hardirqs_on_prepare(); instrumentation_end(); - unwind_reset_info(); user_enter_irqoff(); arch_exit_to_user_mode(); lockdep_hardirqs_on(CALLER_ADDR0); diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index d5e6024cb2a8c1..bc4ddacd6ddc17 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -17,12 +17,18 @@ #include #include +typedef int (*platform_irq_probe_t)(struct platform_device *, struct device_node *); + /* Undefined on purpose */ extern of_irq_init_cb_t typecheck_irq_init_cb; +extern platform_irq_probe_t typecheck_irq_probe; #define typecheck_irq_init_cb(fn) \ (__typecheck(typecheck_irq_init_cb, &fn) ? fn : fn) +#define typecheck_irq_probe(fn) \ + (__typecheck(typecheck_irq_probe, &fn) ? fn : fn) + /* * This macro must be used by the different irqchip drivers to declare * the association between their DT compatible string and their @@ -42,7 +48,7 @@ extern int platform_irqchip_probe(struct platform_device *pdev); static const struct of_device_id drv_name##_irqchip_match_table[] = { #define IRQCHIP_MATCH(compat, fn) { .compatible = compat, \ - .data = typecheck_irq_init_cb(fn), }, + .data = typecheck_irq_probe(fn), }, #define IRQCHIP_PLATFORM_DRIVER_END(drv_name, ...) \ diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 43b9297fe8a75e..f5eaf76198f377 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1253,6 +1253,12 @@ struct journal_s */ struct lockdep_map j_trans_commit_map; #endif + /** + * @jbd2_trans_commit_key: + * + * "struct lock_class_key" for @j_trans_commit_map + */ + struct lock_class_key jbd2_trans_commit_key; /** * @j_fc_cleanup_callback: diff --git a/include/linux/kasan.h b/include/linux/kasan.h index d12e1a5f5a9af8..864472c9bfc971 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -28,6 +28,7 @@ typedef unsigned int __bitwise kasan_vmalloc_flags_t; #define KASAN_VMALLOC_INIT ((__force kasan_vmalloc_flags_t)0x01u) #define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u) #define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u) +#define KASAN_VMALLOC_KEEP_TAG ((__force kasan_vmalloc_flags_t)0x08u) #define KASAN_VMALLOC_PAGE_RANGE 0x1 /* Apply exsiting page range */ #define KASAN_VMALLOC_TLB_FLUSH 0x2 /* TLB flush */ @@ -614,6 +615,27 @@ static __always_inline void kasan_poison_vmalloc(const void *start, __kasan_poison_vmalloc(start, size); } +void __kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, + kasan_vmalloc_flags_t flags); +static __always_inline void +kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, + kasan_vmalloc_flags_t flags) +{ + if (kasan_enabled()) + __kasan_unpoison_vmap_areas(vms, nr_vms, flags); +} + +void __kasan_vrealloc(const void *start, unsigned long old_size, + unsigned long new_size); + +static __always_inline void kasan_vrealloc(const void *start, + unsigned long old_size, + unsigned long new_size) +{ + if (kasan_enabled()) + __kasan_vrealloc(start, old_size, new_size); +} + #else /* CONFIG_KASAN_VMALLOC */ static inline void kasan_populate_early_vm_area_shadow(void *start, @@ -638,6 +660,14 @@ static inline void *kasan_unpoison_vmalloc(const void *start, static inline void kasan_poison_vmalloc(const void *start, unsigned long size) { } +static __always_inline void +kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, + kasan_vmalloc_flags_t flags) +{ } + +static inline void kasan_vrealloc(const void *start, unsigned long old_size, + unsigned long new_size) { } + #endif /* CONFIG_KASAN_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index ff7e231b0485a9..8a22bc9b8c6c85 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -530,7 +530,7 @@ extern bool kexec_file_dbg_print; #define kexec_dprintk(fmt, arg...) \ do { if (kexec_file_dbg_print) pr_info(fmt, ##arg); } while (0) -extern void *kimage_map_segment(struct kimage *image, unsigned long addr, unsigned long size); +extern void *kimage_map_segment(struct kimage *image, int idx); extern void kimage_unmap_segment(void *buffer); #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; @@ -540,7 +540,7 @@ static inline void __crash_kexec(struct pt_regs *regs) { } static inline void crash_kexec(struct pt_regs *regs) { } static inline int kexec_should_crash(struct task_struct *p) { return 0; } static inline int kexec_crash_loaded(void) { return 0; } -static inline void *kimage_map_segment(struct kimage *image, unsigned long addr, unsigned long size) +static inline void *kimage_map_segment(struct kimage *image, int idx) { return NULL; } static inline void kimage_unmap_segment(void *buffer) { } #define kexec_in_progress false diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 0ad1ddbb8b996a..e5822f6e7f2794 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -211,6 +211,7 @@ struct kmem_obj_info; * __kfence_obj_info() - fill kmem_obj_info struct * @kpp: kmem_obj_info to be filled * @object: the object + * @slab: the slab * * Return: * * false - not a KFENCE object diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 067538fc4d5855..c982694c987b96 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -17,7 +17,7 @@ #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, vm_flags_t *vm_flags); -vm_flags_t ksm_vma_flags(const struct mm_struct *mm, const struct file *file, +vm_flags_t ksm_vma_flags(struct mm_struct *mm, const struct file *file, vm_flags_t vm_flags); int ksm_enable_merge_any(struct mm_struct *mm); int ksm_disable_merge_any(struct mm_struct *mm); @@ -103,7 +103,7 @@ bool ksm_process_mergeable(struct mm_struct *mm); #else /* !CONFIG_KSM */ -static inline vm_flags_t ksm_vma_flags(const struct mm_struct *mm, +static inline vm_flags_t ksm_vma_flags(struct mm_struct *mm, const struct file *file, vm_flags_t vm_flags) { return vm_flags; diff --git a/include/linux/leds-expresswire.h b/include/linux/leds-expresswire.h index a422921f4159f2..7f8c4795f69fa0 100644 --- a/include/linux/leds-expresswire.h +++ b/include/linux/leds-expresswire.h @@ -30,9 +30,6 @@ struct expresswire_common_props { void expresswire_power_off(struct expresswire_common_props *props); void expresswire_enable(struct expresswire_common_props *props); -void expresswire_start(struct expresswire_common_props *props); -void expresswire_end(struct expresswire_common_props *props); -void expresswire_set_bit(struct expresswire_common_props *props, bool bit); void expresswire_write_u8(struct expresswire_common_props *props, u8 val); #endif /* _LEDS_EXPRESSWIRE_H */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 7a98de1cc995c2..3b8bdea8516d04 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -899,6 +899,9 @@ struct ata_port { u64 qc_active; int nr_active_links; /* #links with active qcs */ + struct work_struct deferred_qc_work; + struct ata_queued_cmd *deferred_qc; + struct ata_link link; /* host default link */ struct ata_link *slave_link; /* see ata_slave_link_init() */ diff --git a/include/linux/memory_ordering_model.h b/include/linux/memory_ordering_model.h new file mode 100644 index 00000000000000..267a12ca66307e --- /dev/null +++ b/include/linux/memory_ordering_model.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MEMORY_ORDERING_MODEL_H +#define __ASM_MEMORY_ORDERING_MODEL_H + +/* Arch hooks to implement the PR_{GET_SET}_MEM_MODEL prctls */ + +struct task_struct; +int arch_prctl_mem_model_get(struct task_struct *t); +int arch_prctl_mem_model_set(struct task_struct *t, unsigned long val); + +#endif diff --git a/include/linux/mfd/macsmc.h b/include/linux/mfd/macsmc.h index 6b13f01a85924f..f6f80c33b5cf79 100644 --- a/include/linux/mfd/macsmc.h +++ b/include/linux/mfd/macsmc.h @@ -41,6 +41,7 @@ typedef u32 smc_key; */ #define SMC_KEY(s) (smc_key)(_SMC_KEY(#s)) #define _SMC_KEY(s) (((s)[0] << 24) | ((s)[1] << 16) | ((s)[2] << 8) | (s)[3]) +#define __SMC_KEY(a, b, c, d) (((u32)(a) << 24) | ((u32)(b) << 16) | ((u32)(c) << 8) | ((u32)(d))) #define APPLE_SMC_READABLE BIT(7) #define APPLE_SMC_WRITABLE BIT(6) diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h index 5f70d3b5d1b1a4..097ef4dfcdac8c 100644 --- a/include/linux/mfd/wm8350/core.h +++ b/include/linux/mfd/wm8350/core.h @@ -667,7 +667,7 @@ static inline int wm8350_register_irq(struct wm8350 *wm8350, int irq, return -ENODEV; return request_threaded_irq(irq + wm8350->irq_base, NULL, - handler, flags, name, data); + handler, flags | IRQF_ONESHOT, name, data); } static inline void wm8350_free_irq(struct wm8350 *wm8350, int irq, void *data) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5405ca1038f9ea..85c2b3d358ec1e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1274,12 +1274,12 @@ static inline bool mlx5_rl_is_supported(struct mlx5_core_dev *dev) static inline int mlx5_core_is_mp_slave(struct mlx5_core_dev *dev) { return MLX5_CAP_GEN(dev, affiliate_nic_vport_criteria) && - MLX5_CAP_GEN(dev, num_vhca_ports) <= 1; + MLX5_CAP_GEN_MAX(dev, num_vhca_ports) <= 1; } static inline int mlx5_core_is_mp_master(struct mlx5_core_dev *dev) { - return MLX5_CAP_GEN(dev, num_vhca_ports) > 1; + return MLX5_CAP_GEN_MAX(dev, num_vhca_ports) > 1; } static inline int mlx5_core_mp_enabled(struct mlx5_core_dev *dev) diff --git a/include/linux/mm.h b/include/linux/mm.h index 7c79b3369b82c9..86b60c2a981579 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2272,10 +2272,10 @@ static inline int folio_expected_ref_count(const struct folio *folio) if (WARN_ON_ONCE(page_has_type(&folio->page) && !folio_test_hugetlb(folio))) return 0; - if (folio_test_anon(folio)) { - /* One reference per page from the swapcache. */ - ref_count += folio_test_swapcache(folio) << order; - } else { + /* One reference per page from the swapcache. */ + ref_count += folio_test_swapcache(folio) << order; + + if (!folio_test_anon(folio)) { /* One reference per page from the pagecache. */ ref_count += !!folio->mapping << order; /* One reference from PG_private. */ @@ -2947,6 +2947,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a #endif /* CONFIG_MMU */ enum pt_flags { + PT_kernel = PG_referenced, PT_reserved = PG_reserved, /* High bits are used for zone/node/section */ }; @@ -2972,6 +2973,46 @@ static inline bool pagetable_is_reserved(struct ptdesc *pt) return test_bit(PT_reserved, &pt->pt_flags.f); } +/** + * ptdesc_set_kernel - Mark a ptdesc used to map the kernel + * @ptdesc: The ptdesc to be marked + * + * Kernel page tables often need special handling. Set a flag so that + * the handling code knows this ptdesc will not be used for userspace. + */ +static inline void ptdesc_set_kernel(struct ptdesc *ptdesc) +{ + set_bit(PT_kernel, &ptdesc->pt_flags.f); +} + +/** + * ptdesc_clear_kernel - Mark a ptdesc as no longer used to map the kernel + * @ptdesc: The ptdesc to be unmarked + * + * Use when the ptdesc is no longer used to map the kernel and no longer + * needs special handling. + */ +static inline void ptdesc_clear_kernel(struct ptdesc *ptdesc) +{ + /* + * Note: the 'PG_referenced' bit does not strictly need to be + * cleared before freeing the page. But this is nice for + * symmetry. + */ + clear_bit(PT_kernel, &ptdesc->pt_flags.f); +} + +/** + * ptdesc_test_kernel - Check if a ptdesc is used to map the kernel + * @ptdesc: The ptdesc being tested + * + * Call to tell if the ptdesc used to map the kernel. + */ +static inline bool ptdesc_test_kernel(const struct ptdesc *ptdesc) +{ + return test_bit(PT_kernel, &ptdesc->pt_flags.f); +} + /** * pagetable_alloc - Allocate pagetables * @gfp: GFP flags @@ -2990,6 +3031,21 @@ static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int orde } #define pagetable_alloc(...) alloc_hooks(pagetable_alloc_noprof(__VA_ARGS__)) +static inline void __pagetable_free(struct ptdesc *pt) +{ + struct page *page = ptdesc_page(pt); + + __free_pages(page, compound_order(page)); +} + +#ifdef CONFIG_ASYNC_KERNEL_PGTABLE_FREE +void pagetable_free_kernel(struct ptdesc *pt); +#else +static inline void pagetable_free_kernel(struct ptdesc *pt) +{ + __pagetable_free(pt); +} +#endif /** * pagetable_free - Free pagetables * @pt: The page table descriptor @@ -2999,9 +3055,12 @@ static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int orde */ static inline void pagetable_free(struct ptdesc *pt) { - struct page *page = ptdesc_page(pt); - - __free_pages(page, compound_order(page)); + if (ptdesc_test_kernel(pt)) { + ptdesc_clear_kernel(pt); + pagetable_free_kernel(pt); + } else { + __pagetable_free(pt); + } } #if defined(CONFIG_SPLIT_PTE_PTLOCKS) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 90e5790c318f02..8b1045c51e0a68 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1490,6 +1490,7 @@ static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumas struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); +void tlb_gather_mmu_vma(struct mmu_gather *tlb, struct vm_area_struct *vma); extern void tlb_finish_mmu(struct mmu_gather *tlb); struct vm_fault; diff --git a/include/linux/module.h b/include/linux/module.h index e135cc79aceeaf..4decae2b167551 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -747,6 +747,15 @@ static inline void __module_get(struct module *module) __mod ? __mod->name : "kernel"; \ }) +static inline const unsigned char *module_buildid(struct module *mod) +{ +#ifdef CONFIG_STACKTRACE_BUILD_ID + return mod->build_id; +#else + return NULL; +#endif +} + /* Dereference module function descriptor */ void *dereference_module_function_descriptor(struct module *mod, void *ptr); diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 927c10d7876958..1c741145e49717 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -287,7 +287,7 @@ struct spinand_device; /** * struct spinand_id - SPI NAND id structure - * @data: buffer containing the id bytes. Currently 4 bytes large, but can + * @data: buffer containing the id bytes. Currently 5 bytes large, but can * be extended if required * @len: ID length */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d1a687444b275d..c6c04cd0a6816a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3401,6 +3401,7 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *netdev_get_by_index(struct net *net, int ifindex, netdevice_tracker *tracker, gfp_t gfp); +struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex); struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp); struct net_device *netdev_get_by_flags_rcu(struct net *net, netdevice_tracker *tracker, @@ -5298,7 +5299,8 @@ netdev_features_t netdev_increment_features(netdev_features_t all, static inline netdev_features_t netdev_add_tso_features(netdev_features_t features, netdev_features_t mask) { - return netdev_increment_features(features, NETIF_F_ALL_TSO, mask); + return netdev_increment_features(features, NETIF_F_ALL_TSO | + NETIF_F_ALL_FOR_ALL, mask); } int __netdev_update_features(struct net_device *dev); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c585939b6cd60f..2cf490a3a239bf 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -636,6 +636,7 @@ extern int nfs_update_folio(struct file *file, struct folio *folio, extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_folio(struct inode *inode, struct folio *folio); +extern int nfs_wb_folio_reclaim(struct inode *inode, struct folio *folio); int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index d30c0245031c07..30ac384e011a45 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -172,6 +172,11 @@ struct nfs_server { #define NFS_MOUNT_FORCE_RDIRPLUS 0x20000000 #define NFS_MOUNT_NETUNREACH_FATAL 0x40000000 + unsigned int automount_inherit; /* Properties inherited by automount */ +#define NFS_AUTOMOUNT_INHERIT_BSIZE 0x0001 +#define NFS_AUTOMOUNT_INHERIT_RSIZE 0x0002 +#define NFS_AUTOMOUNT_INHERIT_WSIZE 0x0004 + unsigned int caps; /* server capabilities */ __u64 fattr_valid; /* Valid attributes */ unsigned int rsize; /* read size */ diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h index f5b68b8abb5433..71a5e28344d119 100644 --- a/include/linux/ns_common.h +++ b/include/linux/ns_common.h @@ -119,6 +119,17 @@ void __ns_common_free(struct ns_common *ns); struct user_namespace *: CLONE_NEWUSER, \ struct uts_namespace *: CLONE_NEWUTS) +#define NS_COMMON_INIT(nsname, refs) \ +{ \ + .ns_type = ns_common_type(&nsname), \ + .ns_id = 0, \ + .inum = ns_init_inum(&nsname), \ + .ops = to_ns_operations(&nsname), \ + .stashed = NULL, \ + .__ns_ref = REFCOUNT_INIT(refs), \ + .ns_list_node = LIST_HEAD_INIT(nsname.ns.ns_list_node), \ +} + #define ns_common_init(__ns) \ __ns_common_init(to_ns_common(__ns), \ ns_common_type(__ns), \ diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index b8d6c0c208760a..51dadbaa3d63a3 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -55,6 +55,15 @@ extern int of_get_flat_dt_subnode_by_name(unsigned long node, const char *uname); extern const void *of_get_flat_dt_prop(unsigned long node, const char *name, int *size); + +extern const __be32 *of_flat_dt_get_addr_size_prop(unsigned long node, + const char *name, + int *entries); +extern bool of_flat_dt_get_addr_size(unsigned long node, const char *name, + u64 *addr, u64 *size); +extern void of_flat_dt_read_addr_size(const __be32 *prop, int entry_index, + u64 *addr, u64 *size); + extern int of_flat_dt_is_compatible(unsigned long node, const char *name); extern unsigned long of_get_flat_dt_root(void); extern uint32_t of_get_flat_dt_phandle(unsigned long node); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 09b581c1d878d3..e3534d573ebc42 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -213,6 +213,7 @@ enum mapping_flags { AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, AS_KERNEL_FILE = 10, /* mapping for a fake kernel file that shouldn't account usage to user cgroups */ + AS_NO_DATA_INTEGRITY = 11, /* no data integrity guarantees */ /* Bits 16-25 are used for FOLIO_ORDER */ AS_FOLIO_ORDER_BITS = 5, AS_FOLIO_ORDER_MIN = 16, @@ -348,6 +349,16 @@ static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct addres return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } +static inline void mapping_set_no_data_integrity(struct address_space *mapping) +{ + set_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); +} + +static inline bool mapping_no_data_integrity(const struct address_space *mapping) +{ + return test_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); +} + static inline gfp_t mapping_gfp_mask(const struct address_space *mapping) { return mapping->gfp_mask; diff --git a/include/linux/phy.h b/include/linux/phy.h index 3c7634482356e2..0bc00a4cceb241 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1813,6 +1813,9 @@ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev) return phydev->is_pseudo_fixed_link; } +phy_interface_t phy_fix_phy_mode_for_mac_delays(phy_interface_t interface, + bool mac_txid, bool mac_rxid); + int phy_save_page(struct phy_device *phydev); int phy_select_page(struct phy_device *phydev, int page); int phy_restore_page(struct phy_device *phydev, int oldpage, int ret); diff --git a/include/linux/platform_data/lp855x.h b/include/linux/platform_data/lp855x.h index ab222dd05bbc25..3b4a891acefe93 100644 --- a/include/linux/platform_data/lp855x.h +++ b/include/linux/platform_data/lp855x.h @@ -124,12 +124,12 @@ struct lp855x_rom_data { }; /** - * struct lp855x_platform_data + * struct lp855x_platform_data - lp855 platform-specific data * @name : Backlight driver name. If it is not defined, default name is set. * @device_control : value of DEVICE CONTROL register * @initial_brightness : initial value of backlight brightness * @period_ns : platform specific pwm period value. unit is nano. - Only valid when mode is PWM_BASED. + * Only valid when mode is PWM_BASED. * @size_program : total size of lp855x_rom_data * @rom_data : list of new eeprom/eprom registers */ diff --git a/include/linux/platform_data/x86/intel_pmc_ipc.h b/include/linux/platform_data/x86/intel_pmc_ipc.h index 1d34435b70016a..85ea381e4a2752 100644 --- a/include/linux/platform_data/x86/intel_pmc_ipc.h +++ b/include/linux/platform_data/x86/intel_pmc_ipc.h @@ -9,6 +9,7 @@ #ifndef INTEL_PMC_IPC_H #define INTEL_PMC_IPC_H #include +#include #define IPC_SOC_REGISTER_ACCESS 0xAA #define IPC_SOC_SUB_CMD_READ 0x00 @@ -48,7 +49,6 @@ static inline int intel_pmc_ipc(struct pmc_ipc_cmd *ipc_cmd, struct pmc_ipc_rbuf {.type = ACPI_TYPE_INTEGER,}, }; struct acpi_object_list arg_list = { PMC_IPCS_PARAM_COUNT, params }; - union acpi_object *obj; int status; if (!ipc_cmd || !rbuf) @@ -72,7 +72,7 @@ static inline int intel_pmc_ipc(struct pmc_ipc_cmd *ipc_cmd, struct pmc_ipc_rbuf if (ACPI_FAILURE(status)) return -ENODEV; - obj = buffer.pointer; + union acpi_object *obj __free(kfree) = buffer.pointer; if (obj && obj->type == ACPI_TYPE_PACKAGE && obj->package.count == VALID_IPC_RESPONSE) { diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index f67a2cb7d78148..dca6784d0547bc 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -121,6 +121,13 @@ struct dev_pm_domain_list { * powered-off until the ->sync_state() callback is * invoked. This flag informs genpd to allow a * power-off without waiting for ->sync_state(). + * GENPD_FLAG_DEFER_OFF: Defer powerdown if there are any consumer + * device fwlinks indicating that some consumer + * devices have not yet probed. This is useful + * for power domains which are active at boot and + * must not be shut down until all consumers + * complete their probe sequence. + */ #define GENPD_FLAG_PM_CLK (1U << 0) #define GENPD_FLAG_IRQ_SAFE (1U << 1) @@ -133,6 +140,7 @@ struct dev_pm_domain_list { #define GENPD_FLAG_DEV_NAME_FW (1U << 8) #define GENPD_FLAG_NO_SYNC_STATE (1U << 9) #define GENPD_FLAG_NO_STAY_ON (1U << 10) +#define GENPD_FLAG_DEFER_OFF (1U << 11) enum gpd_status { GENPD_STATE_ON = 0, /* PM domain is on */ diff --git a/include/linux/psp.h b/include/linux/psp.h index 92e60aeef21e13..b337dcce1e9916 100644 --- a/include/linux/psp.h +++ b/include/linux/psp.h @@ -18,6 +18,7 @@ * and should include an appropriate local definition in their source file. */ #define PSP_CMDRESP_STS GENMASK(15, 0) +#define PSP_TEE_STS_RING_BUSY 0x0000000d /* Ring already initialized */ #define PSP_CMDRESP_CMD GENMASK(23, 16) #define PSP_CMDRESP_RESERVED GENMASK(29, 24) #define PSP_CMDRESP_RECOVERY BIT(30) diff --git a/include/linux/ras.h b/include/linux/ras.h index a64182bc72ad3f..468941bfe855f6 100644 --- a/include/linux/ras.h +++ b/include/linux/ras.h @@ -24,8 +24,7 @@ int __init parse_cec_param(char *str); void log_non_standard_event(const guid_t *sec_type, const guid_t *fru_id, const char *fru_text, const u8 sev, const u8 *err, const u32 len); -void log_arm_hw_error(struct cper_sec_proc_arm *err); - +void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev); #else static inline void log_non_standard_event(const guid_t *sec_type, @@ -33,7 +32,7 @@ log_non_standard_event(const guid_t *sec_type, const u8 sev, const u8 *err, const u32 len) { return; } static inline void -log_arm_hw_error(struct cper_sec_proc_arm *err) { return; } +log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev) { return; } #endif struct atl_err { @@ -53,4 +52,15 @@ static inline unsigned long amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err) { return -EINVAL; } #endif /* CONFIG_AMD_ATL */ +#if defined(CONFIG_ARM) || defined(CONFIG_ARM64) +#include +/* + * Include ARM-specific SMP header which provides a function mapping mpidr to + * CPU logical index. + */ +#define GET_LOGICAL_INDEX(mpidr) get_logical_index(mpidr & MPIDR_HWID_BITMASK) +#else +#define GET_LOGICAL_INDEX(mpidr) -EINVAL +#endif /* CONFIG_ARM || CONFIG_ARM64 */ + #endif /* __RAS_H__ */ diff --git a/include/linux/reset.h b/include/linux/reset.h index 840d75d172f623..44f9e3415f92c9 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -2,6 +2,7 @@ #ifndef _LINUX_RESET_H_ #define _LINUX_RESET_H_ +#include #include #include #include diff --git a/include/linux/sched.h b/include/linux/sched.h index b469878de25c8a..6ad294330c0b6e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1798,6 +1798,11 @@ static __always_inline bool is_percpu_thread(void) (current->nr_cpus_allowed == 1); } +static __always_inline bool is_user_task(struct task_struct *task) +{ + return task->mm && !(task->flags & (PF_KTHREAD | PF_USER_WORKER)); +} + /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 0232d983b71539..a3094379b5790e 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -323,6 +323,7 @@ static inline void might_alloc(gfp_t gfp_mask) /** * memalloc_flags_save - Add a PF_* flag to current->flags, save old value + * @flags: Flags to add. * * This allows PF_* flags to be conveniently added, irrespective of current * value, and then the old version restored with memalloc_flags_restore(). diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index bbcfdf12aa6e57..45c0022b91ced3 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -92,6 +92,9 @@ struct sched_domain { unsigned int nr_balance_failed; /* initialise to 0 */ /* idle_balance() stats */ + unsigned int newidle_call; + unsigned int newidle_success; + unsigned int newidle_ratio; u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a7cc3d1f4fd111..50f127451dc65e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4301,6 +4301,18 @@ skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) skb_headlen(skb), buffer); } +/* Variant of skb_header_pointer() where @offset is user-controlled + * and potentially negative. + */ +static inline void * __must_check +skb_header_pointer_careful(const struct sk_buff *skb, int offset, + int len, void *buffer) +{ + if (unlikely(offset < 0 && -offset > skb_headroom(skb))) + return NULL; + return skb_header_pointer(skb, offset, len, buffer); +} + static inline void * __must_check skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len) { diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 49847888c287ab..829b281d6c9c27 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -97,6 +97,8 @@ struct sk_psock { struct sk_buff_head ingress_skb; struct list_head ingress_msg; spinlock_t ingress_lock; + /** @msg_tot_len: Total bytes queued in ingress_msg list. */ + u32 msg_tot_len; unsigned long state; struct list_head link; spinlock_t link_lock; @@ -141,6 +143,8 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); +int __sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, + int len, int flags, int *copied_from_self); bool sk_msg_is_readable(struct sock *sk); static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes) @@ -319,6 +323,27 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } +static inline u32 sk_psock_get_msg_len_nolock(struct sk_psock *psock) +{ + /* Used by ioctl to read msg_tot_len only; lock-free for performance */ + return READ_ONCE(psock->msg_tot_len); +} + +static inline void sk_psock_msg_len_add_locked(struct sk_psock *psock, int diff) +{ + /* Use WRITE_ONCE to ensure correct read in sk_psock_get_msg_len_nolock(). + * ingress_lock should be held to prevent concurrent updates to msg_tot_len + */ + WRITE_ONCE(psock->msg_tot_len, psock->msg_tot_len + diff); +} + +static inline void sk_psock_msg_len_add(struct sk_psock *psock, int diff) +{ + spin_lock_bh(&psock->ingress_lock); + sk_psock_msg_len_add_locked(psock, diff); + spin_unlock_bh(&psock->ingress_lock); +} + static inline bool sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { @@ -327,6 +352,7 @@ static inline bool sk_psock_queue_msg(struct sk_psock *psock, spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { list_add_tail(&msg->list, &psock->ingress_msg); + sk_psock_msg_len_add_locked(psock, msg->sg.size); ret = true; } else { sk_msg_free(psock->sk, msg); @@ -343,18 +369,25 @@ static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock) spin_lock_bh(&psock->ingress_lock); msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list); - if (msg) + if (msg) { list_del(&msg->list); + sk_psock_msg_len_add_locked(psock, -msg->sg.size); + } spin_unlock_bh(&psock->ingress_lock); return msg; } +static inline struct sk_msg *sk_psock_peek_msg_locked(struct sk_psock *psock) +{ + return list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list); +} + static inline struct sk_msg *sk_psock_peek_msg(struct sk_psock *psock) { struct sk_msg *msg; spin_lock_bh(&psock->ingress_lock); - msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list); + msg = sk_psock_peek_msg_locked(psock); spin_unlock_bh(&psock->ingress_lock); return msg; } @@ -521,6 +554,39 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) return !!psock->saved_data_ready; } +/* for tcp only, sk is locked */ +static inline ssize_t sk_psock_msg_inq(struct sock *sk) +{ + struct sk_psock *psock; + ssize_t inq = 0; + + psock = sk_psock_get(sk); + if (likely(psock)) { + inq = sk_psock_get_msg_len_nolock(psock); + sk_psock_put(sk, psock); + } + return inq; +} + +/* for udp only, sk is not locked */ +static inline ssize_t sk_msg_first_len(struct sock *sk) +{ + struct sk_psock *psock; + struct sk_msg *msg; + ssize_t inq = 0; + + psock = sk_psock_get(sk); + if (likely(psock)) { + spin_lock_bh(&psock->ingress_lock); + msg = sk_psock_peek_msg_locked(psock); + if (msg) + inq = msg->sg.size; + spin_unlock_bh(&psock->ingress_lock); + sk_psock_put(sk, psock); + } + return inq; +} + #if IS_ENABLED(CONFIG_NET_SOCK_MSG) #define BPF_F_STRPARSER (1UL << 1) diff --git a/include/linux/slab.h b/include/linux/slab.h index cf443f064a667e..2482992248dc9c 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -1150,10 +1150,17 @@ static inline void kvfree_rcu_barrier(void) rcu_barrier(); } +static inline void kvfree_rcu_barrier_on_cache(struct kmem_cache *s) +{ + rcu_barrier(); +} + static inline void kfree_rcu_scheduler_running(void) { } #else void kvfree_rcu_barrier(void); +void kvfree_rcu_barrier_on_cache(struct kmem_cache *s); + void kfree_rcu_scheduler_running(void); #endif diff --git a/include/linux/soc/airoha/airoha_offload.h b/include/linux/soc/airoha/airoha_offload.h index 6f66eb339b3fc6..0e82f1f4d36c4a 100644 --- a/include/linux/soc/airoha/airoha_offload.h +++ b/include/linux/soc/airoha/airoha_offload.h @@ -51,8 +51,8 @@ static inline void airoha_ppe_put_dev(struct airoha_ppe_dev *dev) { } -static inline int airoha_ppe_setup_tc_block_cb(struct airoha_ppe_dev *dev, - void *type_data) +static inline int airoha_ppe_dev_setup_tc_block_cb(struct airoha_ppe_dev *dev, + void *type_data) { return -EOPNOTSUPP; } @@ -70,12 +70,12 @@ static inline void airoha_ppe_dev_check_skb(struct airoha_ppe_dev *dev, #define NPU_RX1_DESC_NUM 512 /* CTRL */ -#define NPU_RX_DMA_DESC_LAST_MASK BIT(29) -#define NPU_RX_DMA_DESC_LEN_MASK GENMASK(28, 15) -#define NPU_RX_DMA_DESC_CUR_LEN_MASK GENMASK(14, 1) +#define NPU_RX_DMA_DESC_LAST_MASK BIT(27) +#define NPU_RX_DMA_DESC_LEN_MASK GENMASK(26, 14) +#define NPU_RX_DMA_DESC_CUR_LEN_MASK GENMASK(13, 1) #define NPU_RX_DMA_DESC_DONE_MASK BIT(0) /* INFO */ -#define NPU_RX_DMA_PKT_COUNT_MASK GENMASK(31, 28) +#define NPU_RX_DMA_PKT_COUNT_MASK GENMASK(31, 29) #define NPU_RX_DMA_PKT_ID_MASK GENMASK(28, 26) #define NPU_RX_DMA_SRC_PORT_MASK GENMASK(25, 21) #define NPU_RX_DMA_CRSN_MASK GENMASK(20, 16) diff --git a/include/linux/soc/apple/dockchannel.h b/include/linux/soc/apple/dockchannel.h new file mode 100644 index 00000000000000..0b7093935ddf47 --- /dev/null +++ b/include/linux/soc/apple/dockchannel.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ +/* + * Apple Dockchannel devices + * Copyright (C) The Asahi Linux Contributors + */ +#ifndef _LINUX_APPLE_DOCKCHANNEL_H_ +#define _LINUX_APPLE_DOCKCHANNEL_H_ + +#include +#include +#include + +#if IS_ENABLED(CONFIG_APPLE_DOCKCHANNEL) + +struct dockchannel; + +struct dockchannel *dockchannel_init(struct platform_device *pdev); + +int dockchannel_send(struct dockchannel *dockchannel, const void *buf, size_t count); +int dockchannel_recv(struct dockchannel *dockchannel, void *buf, size_t count); +int dockchannel_await(struct dockchannel *dockchannel, + void (*callback)(void *cookie, size_t avail), + void *cookie, size_t count); + +#endif +#endif diff --git a/drivers/soc/apple/mailbox.h b/include/linux/soc/apple/mailbox.h similarity index 100% rename from drivers/soc/apple/mailbox.h rename to include/linux/soc/apple/mailbox.h diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h index 736f530180179b..22e1d3bb35ef0c 100644 --- a/include/linux/soc/apple/rtkit.h +++ b/include/linux/soc/apple/rtkit.h @@ -78,6 +78,13 @@ struct apple_rtkit; struct apple_rtkit *devm_apple_rtkit_init(struct device *dev, void *cookie, const char *mbox_name, int mbox_idx, const struct apple_rtkit_ops *ops); +/* + * Frees internal RTKit state allocated by devm_apple_rtkit_init(). + * + * @dev: Pointer to the device node this coprocessor is assocated with + * @rtk: Internal RTKit state initialized by devm_apple_rtkit_init() + */ +void devm_apple_rtkit_free(struct device *dev, struct apple_rtkit *rtk); /* * Non-devm version of devm_apple_rtkit_init. Must be freed with @@ -172,4 +179,12 @@ int apple_rtkit_send_message(struct apple_rtkit *rtk, u8 ep, u64 message, */ int apple_rtkit_poll(struct apple_rtkit *rtk); +/* + * Checks if an endpoint with a given index exists + * + * @rtk: RTKit reference + * @ep: endpoint to check for + */ +bool apple_rtkit_has_endpoint(struct apple_rtkit *rtk, u8 ep); + #endif /* _LINUX_APPLE_RTKIT_H_ */ diff --git a/include/linux/soc/apple/tunable.h b/include/linux/soc/apple/tunable.h new file mode 100644 index 00000000000000..531ca814cd0235 --- /dev/null +++ b/include/linux/soc/apple/tunable.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ +/* + * Apple Silicon hardware tunable support + * + * Each tunable is a list with each entry containing a offset into the MMIO + * region, a mask of bits to be cleared and a set of bits to be set. These + * tunables are passed along by the previous boot stages and vary from device + * to device such that they cannot be hardcoded in the individual drivers. + * + * Copyright (C) The Asahi Linux Contributors + */ + +#ifndef _LINUX_SOC_APPLE_TUNABLE_H_ +#define _LINUX_SOC_APPLE_TUNABLE_H_ + +#include +#include + +/** + * Struct to store an Apple Silicon hardware tunable. + * + * Each tunable is a list with each entry containing a offset into the MMIO + * region, a mask of bits to be cleared and a set of bits to be set. These + * tunables are passed along by the previous boot stages and vary from device + * to device such that they cannot be hardcoded in the individual drivers. + * + * @param sz Number of [offset, mask, value] tuples stored in values. + * @param values [offset, mask, value] array. + */ +struct apple_tunable { + size_t sz; + struct { + u32 offset; + u32 mask; + u32 value; + } values[] __counted_by(sz); +}; + +/** + * Parse an array of hardware tunables from the device tree. + * + * @dev: Device node used for devm_kzalloc internally. + * @np: Device node which contains the tunable array. + * @name: Name of the device tree property which contains the tunables. + * @res: Resource to which the tunables will be applied, used for bound checking + * + * @return: devres allocated struct on success or PTR_ERR on failure. + */ +struct apple_tunable *devm_apple_tunable_parse(struct device *dev, + struct device_node *np, + const char *name, + struct resource *res); + +/** + * Apply a previously loaded hardware tunable. + * + * @param regs: MMIO to which the tunable will be applied. + * @param tunable: Pointer to the tunable. + */ +void apple_tunable_apply(void __iomem *regs, struct apple_tunable *tunable); + +#endif diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index c4ff6bab176db1..3fa93bd650044b 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -154,6 +154,7 @@ struct mtk_wed_device { bool wcid_512; bool hw_rro; bool msi; + bool hif2; u16 token_start; unsigned int nbuf; diff --git a/include/linux/soc/qcom/ubwc.h b/include/linux/soc/qcom/ubwc.h index 1ed8b1b16bc90b..d9dfc9edc1b2f3 100644 --- a/include/linux/soc/qcom/ubwc.h +++ b/include/linux/soc/qcom/ubwc.h @@ -8,6 +8,7 @@ #define __QCOM_UBWC_H__ #include +#include #include struct qcom_ubwc_cfg_data { diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index fa1318bac06c44..151c81c560c8c4 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -171,7 +171,13 @@ struct dwmac4_addrs { u32 mtl_low_cred_offset; }; -#define STMMAC_FLAG_HAS_INTEGRATED_PCS BIT(0) +enum dwmac_core_type { + DWMAC_CORE_MAC100, + DWMAC_CORE_GMAC, + DWMAC_CORE_GMAC4, + DWMAC_CORE_XGMAC, +}; + #define STMMAC_FLAG_SPH_DISABLE BIT(1) #define STMMAC_FLAG_USE_PHY_WOL BIT(2) #define STMMAC_FLAG_HAS_SUN8I BIT(3) @@ -187,6 +193,7 @@ struct dwmac4_addrs { #define STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY BIT(13) struct plat_stmmacenet_data { + enum dwmac_core_type core_type; int bus_id; int phy_addr; /* MAC ----- optional PCS ----- SerDes ----- optional PHY ----- Media @@ -220,7 +227,6 @@ struct plat_stmmacenet_data { struct stmmac_dma_cfg *dma_cfg; struct stmmac_safety_feature_cfg *safety_feat_cfg; int clk_csr; - int has_gmac; int enh_desc; int tx_coe; int rx_coe; @@ -283,10 +289,8 @@ struct plat_stmmacenet_data { struct reset_control *stmmac_rst; struct reset_control *stmmac_ahb_rst; struct stmmac_axi *axi; - int has_gmac4; int rss_en; int mac_port_sel_speed; - int has_xgmac; u8 vlan_fail_q; struct pci_dev *pdev; int int_snapshot_num; diff --git a/include/linux/sunrpc/xdrgen/_builtins.h b/include/linux/sunrpc/xdrgen/_builtins.h index 66ca3ece951ab9..a5ab75d2db0446 100644 --- a/include/linux/sunrpc/xdrgen/_builtins.h +++ b/include/linux/sunrpc/xdrgen/_builtins.h @@ -188,12 +188,10 @@ xdrgen_decode_string(struct xdr_stream *xdr, string *ptr, u32 maxlen) return false; if (unlikely(maxlen && len > maxlen)) return false; - if (len != 0) { - p = xdr_inline_decode(xdr, len); - if (unlikely(!p)) - return false; - ptr->data = (unsigned char *)p; - } + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + return false; + ptr->data = (unsigned char *)p; ptr->len = len; return true; } @@ -219,12 +217,10 @@ xdrgen_decode_opaque(struct xdr_stream *xdr, opaque *ptr, u32 maxlen) return false; if (unlikely(maxlen && len > maxlen)) return false; - if (len != 0) { - p = xdr_inline_decode(xdr, len); - if (unlikely(!p)) - return false; - ptr->data = (u8 *)p; - } + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + return false; + ptr->data = (u8 *)p; ptr->len = len; return true; } diff --git a/include/linux/textsearch.h b/include/linux/textsearch.h index 6673e4d4ac2e1b..4933777404d618 100644 --- a/include/linux/textsearch.h +++ b/include/linux/textsearch.h @@ -35,6 +35,7 @@ struct ts_state * @get_pattern: return head of pattern * @get_pattern_len: return length of pattern * @owner: module reference to algorithm + * @list: list to search */ struct ts_ops { diff --git a/include/linux/tpm.h b/include/linux/tpm.h index dc0338a783f370..5d5c926a71119d 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -26,7 +26,9 @@ #include #define TPM_DIGEST_SIZE 20 /* Max TPM v1.2 PCR size */ -#define TPM_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE + +#define TPM2_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE +#define TPM2_MAX_PCR_BANKS 8 struct tpm_chip; struct trusted_key_payload; @@ -68,7 +70,7 @@ enum tpm2_curves { struct tpm_digest { u16 alg_id; - u8 digest[TPM_MAX_DIGEST_SIZE]; + u8 digest[TPM2_MAX_DIGEST_SIZE]; } __packed; struct tpm_bank_info { @@ -189,7 +191,7 @@ struct tpm_chip { unsigned int groups_cnt; u32 nr_allocated_banks; - struct tpm_bank_info *allocated_banks; + struct tpm_bank_info allocated_banks[TPM2_MAX_PCR_BANKS]; #ifdef CONFIG_ACPI acpi_handle acpi_dev_handle; char ppi_version[TPM_PPI_VERSION_LEN + 1]; @@ -524,8 +526,8 @@ static inline struct tpm2_auth *tpm2_chip_auth(struct tpm_chip *chip) #endif } -void tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf, - u32 handle, u8 *name); +int tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf, + u32 handle, u8 *name); void tpm_buf_append_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf, u8 attributes, u8 *passphrase, int passphraselen); @@ -558,7 +560,7 @@ static inline void tpm_buf_append_hmac_session_opt(struct tpm_chip *chip, #ifdef CONFIG_TCG_TPM2_HMAC int tpm2_start_auth_session(struct tpm_chip *chip); -void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf); +int tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf); int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf, int rc); void tpm2_end_auth_session(struct tpm_chip *chip); @@ -572,10 +574,13 @@ static inline int tpm2_start_auth_session(struct tpm_chip *chip) static inline void tpm2_end_auth_session(struct tpm_chip *chip) { } -static inline void tpm_buf_fill_hmac_session(struct tpm_chip *chip, - struct tpm_buf *buf) + +static inline int tpm_buf_fill_hmac_session(struct tpm_chip *chip, + struct tpm_buf *buf) { + return 0; } + static inline int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf, int rc) diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index ae04054a1be360..e6ca052b2a85a7 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -34,6 +34,13 @@ enum { TRACE_INTERNAL_SIRQ_BIT, TRACE_INTERNAL_TRANSITION_BIT, + /* Internal event use recursion bits */ + TRACE_INTERNAL_EVENT_BIT, + TRACE_INTERNAL_EVENT_NMI_BIT, + TRACE_INTERNAL_EVENT_IRQ_BIT, + TRACE_INTERNAL_EVENT_SIRQ_BIT, + TRACE_INTERNAL_EVENT_TRANSITION_BIT, + TRACE_BRANCH_BIT, /* * Abuse of the trace_recursion. @@ -58,6 +65,8 @@ enum { #define TRACE_LIST_START TRACE_INTERNAL_BIT +#define TRACE_EVENT_START TRACE_INTERNAL_EVENT_BIT + #define TRACE_CONTEXT_MASK ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) /* diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 457879938fc198..3366090a86bd2f 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -89,6 +89,11 @@ static inline void u64_stats_add(u64_stats_t *p, unsigned long val) local64_add(val, &p->v); } +static inline void u64_stats_sub(u64_stats_t *p, s64 val) +{ + local64_sub(val, &p->v); +} + static inline void u64_stats_inc(u64_stats_t *p) { local64_inc(&p->v); @@ -130,6 +135,11 @@ static inline void u64_stats_add(u64_stats_t *p, unsigned long val) p->v += val; } +static inline void u64_stats_sub(u64_stats_t *p, s64 val) +{ + p->v -= val; +} + static inline void u64_stats_inc(u64_stats_t *p) { p->v++; diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 59409c1fc3dee7..2f7bd2fdc6164b 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -75,4 +75,7 @@ /* short SET_ADDRESS request timeout */ #define USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT BIT(16) +/* skip BOS descriptor request */ +#define USB_QUIRK_NO_BOS BIT(17) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index f541044e42a2ad..7aa29428982aa5 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -27,6 +28,11 @@ struct vfio_pci_core_device; struct vfio_pci_region; +struct vfio_pci_eventfd { + struct eventfd_ctx *ctx; + struct rcu_head rcu; +}; + struct vfio_pci_regops { ssize_t (*rw)(struct vfio_pci_core_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite); @@ -83,8 +89,8 @@ struct vfio_pci_core_device { struct pci_saved_state *pci_saved_state; struct pci_saved_state *pm_save; int ioeventfds_nr; - struct eventfd_ctx *err_trigger; - struct eventfd_ctx *req_trigger; + struct vfio_pci_eventfd __rcu *err_trigger; + struct vfio_pci_eventfd __rcu *req_trigger; struct eventfd_ctx *pm_wake_eventfd_ctx; struct list_head dummy_resources_list; struct mutex ioeventfds_lock; @@ -96,6 +102,13 @@ struct vfio_pci_core_device { struct rw_semaphore memory_lock; }; +enum vfio_pci_io_width { + VFIO_PCI_IO_WIDTH_1 = 1, + VFIO_PCI_IO_WIDTH_2 = 2, + VFIO_PCI_IO_WIDTH_4 = 4, + VFIO_PCI_IO_WIDTH_8 = 8, +}; + /* Will be exported for vfio pci drivers usage */ int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev, unsigned int type, unsigned int subtype, @@ -133,7 +146,8 @@ pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, void __iomem *io, char __user *buf, loff_t off, size_t count, size_t x_start, - size_t x_end, bool iswrite); + size_t x_end, bool iswrite, + enum vfio_pci_io_width max_width); bool vfio_pci_core_range_intersect_range(loff_t buf_start, size_t buf_cnt, loff_t reg_start, size_t reg_cnt, loff_t *buf_offset, diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 96c66126c0741c..132a474e59140a 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -177,7 +177,7 @@ struct virtio_device { union virtio_map vmap; #ifdef CONFIG_VIRTIO_DEBUG struct dentry *debugfs_dir; - u64 debugfs_filter_features[VIRTIO_FEATURES_DWORDS]; + u64 debugfs_filter_features[VIRTIO_FEATURES_U64S]; #endif }; diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 16001e9f9b391e..69f84ea85d71a0 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -24,7 +24,7 @@ typedef void vq_callback_t(struct virtqueue *); * a virtqueue unused by the driver. * @callback: A callback to invoke on a used buffer notification. * NULL for a virtqueue that does not need a callback. - * @ctx: A flag to indicate to maintain an extra context per virtqueue. + * @ctx: whether to maintain an extra context per virtqueue. */ struct virtqueue_info { const char *name; @@ -80,13 +80,13 @@ struct virtqueue_info { * Returns the first 64 feature bits. * @get_extended_features: * vdev: the virtio_device - * Returns the first VIRTIO_FEATURES_MAX feature bits (all we currently + * Returns the first VIRTIO_FEATURES_BITS feature bits (all we currently * need). * @finalize_features: confirm what device features we'll be using. * vdev: the virtio_device * This sends the driver feature bits to the device: it can change * the dev->feature bits if it wants. - * Note that despite the name this can be called any number of + * Note that despite the name this can be called any number of * times. * Returns 0 on success or error status * @bus_name: return the bus name associated with the device (optional) @@ -141,8 +141,8 @@ struct virtio_config_ops { /** * struct virtio_map_ops - operations for mapping buffer for a virtio device - * Note: For transport that has its own mapping logic it must - * implements all of the operations + * Note: For a transport that has its own mapping logic it must + * implement all of the operations * @map_page: map a buffer to the device * map: metadata for performing mapping * page: the page that will be mapped by the device @@ -150,7 +150,7 @@ struct virtio_config_ops { * size: the buffer size * dir: mapping direction * attrs: mapping attributes - * Returns: the mapped address + * Returns the mapped address * @unmap_page: unmap a buffer from the device * map: device specific mapping map * map_handle: the mapped address @@ -172,23 +172,23 @@ struct virtio_config_ops { * size: the size of the buffer * map_handle: the mapping address to sync * gfp: allocation flag (GFP_XXX) - * Returns: virtual address of the allocated buffer + * Returns virtual address of the allocated buffer * @free: free a coherent buffer mapping * map: metadata for performing mapping * size: the size of the buffer * vaddr: virtual address of the buffer - * map_handle: the mapping address to sync + * map_handle: the mapping address that needs to be freed * attrs: unmapping attributes * @need_sync: if the buffer needs synchronization * map: metadata for performing mapping * map_handle: the mapped address - * Returns: whether the buffer needs synchronization + * Returns whether the buffer needs synchronization * @mapping_error: if the mapping address is error * map: metadata for performing mapping * map_handle: the mapped address * @max_mapping_size: get the maximum buffer size that can be mapped * map: metadata for performing mapping - * Returns: the maximum buffer size that can be mapped + * Returns the maximum buffer size that can be mapped */ struct virtio_map_ops { dma_addr_t (*map_page)(union virtio_map map, struct page *page, @@ -362,7 +362,7 @@ void virtio_device_ready(struct virtio_device *dev) * specific set_status() method. * * A well behaved device will only notify a virtqueue after - * DRIVER_OK, this means the device should "see" the coherenct + * DRIVER_OK, this means the device should "see" the coherent * memory write that set vq->broken as false which is done by * the driver when it sees DRIVER_OK, then the following * driver's vring_interrupt() will see vq->broken as false so @@ -384,7 +384,7 @@ const char *virtio_bus_name(struct virtio_device *vdev) * @vq: the virtqueue * @cpu_mask: the cpu mask * - * Pay attention the function are best-effort: the affinity hint may not be set + * Note that this function is best-effort: the affinity hint may not be set * due to config support, irq type and sharing. * */ diff --git a/include/linux/virtio_features.h b/include/linux/virtio_features.h index f748f2f87de8d3..ea2ad8717882e0 100644 --- a/include/linux/virtio_features.h +++ b/include/linux/virtio_features.h @@ -4,15 +4,16 @@ #include -#define VIRTIO_FEATURES_DWORDS 2 -#define VIRTIO_FEATURES_MAX (VIRTIO_FEATURES_DWORDS * 64) -#define VIRTIO_FEATURES_WORDS (VIRTIO_FEATURES_DWORDS * 2) +#define VIRTIO_FEATURES_U64S 2 +#define VIRTIO_FEATURES_BITS (VIRTIO_FEATURES_U64S * 64) + #define VIRTIO_BIT(b) BIT_ULL((b) & 0x3f) -#define VIRTIO_DWORD(b) ((b) >> 6) +#define VIRTIO_U64(b) ((b) >> 6) + #define VIRTIO_DECLARE_FEATURES(name) \ union { \ u64 name; \ - u64 name##_array[VIRTIO_FEATURES_DWORDS];\ + u64 name##_array[VIRTIO_FEATURES_U64S];\ } static inline bool virtio_features_chk_bit(unsigned int bit) @@ -22,9 +23,9 @@ static inline bool virtio_features_chk_bit(unsigned int bit) * Don't care returning the correct value: the build * will fail before any bad features access */ - BUILD_BUG_ON(bit >= VIRTIO_FEATURES_MAX); + BUILD_BUG_ON(bit >= VIRTIO_FEATURES_BITS); } else { - if (WARN_ON_ONCE(bit >= VIRTIO_FEATURES_MAX)) + if (WARN_ON_ONCE(bit >= VIRTIO_FEATURES_BITS)) return false; } return true; @@ -34,26 +35,26 @@ static inline bool virtio_features_test_bit(const u64 *features, unsigned int bit) { return virtio_features_chk_bit(bit) && - !!(features[VIRTIO_DWORD(bit)] & VIRTIO_BIT(bit)); + !!(features[VIRTIO_U64(bit)] & VIRTIO_BIT(bit)); } static inline void virtio_features_set_bit(u64 *features, unsigned int bit) { if (virtio_features_chk_bit(bit)) - features[VIRTIO_DWORD(bit)] |= VIRTIO_BIT(bit); + features[VIRTIO_U64(bit)] |= VIRTIO_BIT(bit); } static inline void virtio_features_clear_bit(u64 *features, unsigned int bit) { if (virtio_features_chk_bit(bit)) - features[VIRTIO_DWORD(bit)] &= ~VIRTIO_BIT(bit); + features[VIRTIO_U64(bit)] &= ~VIRTIO_BIT(bit); } static inline void virtio_features_zero(u64 *features) { - memset(features, 0, sizeof(features[0]) * VIRTIO_FEATURES_DWORDS); + memset(features, 0, sizeof(features[0]) * VIRTIO_FEATURES_U64S); } static inline void virtio_features_from_u64(u64 *features, u64 from) @@ -66,7 +67,7 @@ static inline bool virtio_features_equal(const u64 *f1, const u64 *f2) { int i; - for (i = 0; i < VIRTIO_FEATURES_DWORDS; ++i) + for (i = 0; i < VIRTIO_FEATURES_U64S; ++i) if (f1[i] != f2[i]) return false; return true; @@ -74,14 +75,14 @@ static inline bool virtio_features_equal(const u64 *f1, const u64 *f2) static inline void virtio_features_copy(u64 *to, const u64 *from) { - memcpy(to, from, sizeof(to[0]) * VIRTIO_FEATURES_DWORDS); + memcpy(to, from, sizeof(to[0]) * VIRTIO_FEATURES_U64S); } static inline void virtio_features_andnot(u64 *to, const u64 *f1, const u64 *f2) { int i; - for (i = 0; i < VIRTIO_FEATURES_DWORDS; i++) + for (i = 0; i < VIRTIO_FEATURES_U64S; i++) to[i] = f1[i] & ~f2[i]; } diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index 48bc12d1045bd5..9a3f2fc53bd659 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -107,7 +107,7 @@ void vp_modern_set_extended_features(struct virtio_pci_modern_device *mdev, static inline u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev) { - u64 features_array[VIRTIO_FEATURES_DWORDS]; + u64 features_array[VIRTIO_FEATURES_U64S]; vp_modern_get_extended_features(mdev, features_array); return features_array[0]; @@ -116,11 +116,11 @@ vp_modern_get_features(struct virtio_pci_modern_device *mdev) static inline u64 vp_modern_get_driver_features(struct virtio_pci_modern_device *mdev) { - u64 features_array[VIRTIO_FEATURES_DWORDS]; + u64 features_array[VIRTIO_FEATURES_U64S]; int i; vp_modern_get_driver_extended_features(mdev, features_array); - for (i = 1; i < VIRTIO_FEATURES_DWORDS; ++i) + for (i = 1; i < VIRTIO_FEATURES_U64S; ++i) WARN_ON_ONCE(features_array[i]); return features_array[0]; } @@ -128,7 +128,7 @@ vp_modern_get_driver_features(struct virtio_pci_modern_device *mdev) static inline void vp_modern_set_features(struct virtio_pci_modern_device *mdev, u64 features) { - u64 features_array[VIRTIO_FEATURES_DWORDS]; + u64 features_array[VIRTIO_FEATURES_U64S]; virtio_features_from_u64(features_array, features); vp_modern_set_extended_features(mdev, features_array); diff --git a/include/linux/xarray.h b/include/linux/xarray.h index be850174e802e6..64f2a5e06cebcc 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -563,6 +563,8 @@ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); +void *__xa_cmpxchg_raw(struct xarray *, unsigned long index, void *old, + void *entry, gfp_t); int __must_check __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); int __must_check __xa_alloc(struct xarray *, u32 *id, void *entry, diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h index 09c6164577ccf4..500f81f399dfaa 100644 --- a/include/media/v4l2-mem2mem.h +++ b/include/media/v4l2-mem2mem.h @@ -192,8 +192,7 @@ void v4l2_m2m_try_schedule(struct v4l2_m2m_ctx *m2m_ctx); * other instances to take control of the device. * * This function has to be called only after &v4l2_m2m_ops->device_run - * callback has been called on the driver. To prevent recursion, it should - * not be called directly from the &v4l2_m2m_ops->device_run callback though. + * callback has been called on the driver. */ void v4l2_m2m_job_finish(struct v4l2_m2m_dev *m2m_dev, struct v4l2_m2m_ctx *m2m_ctx); diff --git a/include/net/bonding.h b/include/net/bonding.h index 49edc7da05867f..46207840355709 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -521,13 +521,14 @@ static inline int bond_is_ip6_target_ok(struct in6_addr *addr) static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond, struct slave *slave) { + unsigned long tmp, ret = READ_ONCE(slave->target_last_arp_rx[0]); int i = 1; - unsigned long ret = slave->target_last_arp_rx[0]; - - for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++) - if (time_before(slave->target_last_arp_rx[i], ret)) - ret = slave->target_last_arp_rx[i]; + for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++) { + tmp = READ_ONCE(slave->target_last_arp_rx[i]); + if (time_before(tmp, ret)) + ret = tmp; + } return ret; } @@ -537,7 +538,7 @@ static inline unsigned long slave_last_rx(struct bonding *bond, if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL) return slave_oldest_target_arp_rx(bond, slave); - return slave->last_rx; + return READ_ONCE(slave->last_rx); } static inline void slave_update_last_tx(struct slave *slave) diff --git a/include/net/dsa.h b/include/net/dsa.h index d73ea08800660e..5cb456bf46394b 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -298,6 +298,7 @@ struct dsa_port { struct devlink_port devlink_port; struct phylink *pl; struct phylink_config pl_config; + netdevice_tracker conduit_tracker; struct dsa_lag *lag; struct net_device *hsr_dev; diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index ea32393464a291..827b87a95dab3f 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -51,11 +51,25 @@ static inline __u8 INET_ECN_encapsulate(__u8 outer, __u8 inner) return outer; } +/* Apply either ECT(0) or ECT(1) */ +static inline void __INET_ECN_xmit(struct sock *sk, bool use_ect_1) +{ + __u8 ect = use_ect_1 ? INET_ECN_ECT_1 : INET_ECN_ECT_0; + + /* Mask the complete byte in case the connection alternates between + * ECT(0) and ECT(1). + */ + inet_sk(sk)->tos &= ~INET_ECN_MASK; + inet_sk(sk)->tos |= ect; + if (inet6_sk(sk)) { + inet6_sk(sk)->tclass &= ~INET_ECN_MASK; + inet6_sk(sk)->tclass |= ect; + } +} + static inline void INET_ECN_xmit(struct sock *sk) { - inet_sk(sk)->tos |= INET_ECN_ECT_0; - if (inet6_sk(sk) != NULL) - inet6_sk(sk)->tclass |= INET_ECN_ECT_0; + __INET_ECN_xmit(sk, false); } static inline void INET_ECN_dontxmit(struct sock *sk) diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 0eccd9c3a883fb..365925c9d26286 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -123,27 +123,15 @@ void inet_frags_fini(struct inet_frags *); int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net); -static inline void fqdir_pre_exit(struct fqdir *fqdir) -{ - /* Prevent creation of new frags. - * Pairs with READ_ONCE() in inet_frag_find(). - */ - WRITE_ONCE(fqdir->high_thresh, 0); - - /* Pairs with READ_ONCE() in inet_frag_kill(), ip_expire() - * and ip6frag_expire_frag_queue(). - */ - WRITE_ONCE(fqdir->dead, true); -} +void fqdir_pre_exit(struct fqdir *fqdir); void fqdir_exit(struct fqdir *fqdir); void inet_frag_kill(struct inet_frag_queue *q, int *refs); void inet_frag_destroy(struct inet_frag_queue *q); struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key); -/* Free all skbs in the queue; return the sum of their truesizes. */ -unsigned int inet_frag_rbtree_purge(struct rb_root *root, - enum skb_drop_reason reason); +void inet_frag_queue_flush(struct inet_frag_queue *q, + enum skb_drop_reason reason); static inline void inet_frag_putn(struct inet_frag_queue *q, int refs) { diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index ecae35512b9b44..4021e6a73e32b8 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -19,6 +19,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_IPV6) #include @@ -372,7 +373,17 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4, fl4->flowi4_flags = flow_flags; } -int ip_tunnel_init(struct net_device *dev); +int __ip_tunnel_init(struct net_device *dev); +#define ip_tunnel_init(DEV) \ +({ \ + struct net_device *__dev = (DEV); \ + int __res = __ip_tunnel_init(__dev); \ + \ + if (!__res) \ + netdev_lockdep_set_classes(__dev);\ + __res; \ +}) + void ip_tunnel_uninit(struct net_device *dev); void ip_tunnel_dellink(struct net_device *dev, struct list_head *head); struct net *ip_tunnel_get_link_net(const struct net_device *dev); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 2ccdf85f34f164..f0936df7567e3d 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1280,12 +1280,15 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, static inline int ip6_sock_set_v6only(struct sock *sk) { - if (inet_sk(sk)->inet_num) - return -EINVAL; + int ret = 0; + lock_sock(sk); - sk->sk_ipv6only = true; + if (inet_sk(sk)->inet_num) + ret = -EINVAL; + else + sk->sk_ipv6only = true; release_sock(sk); - return 0; + return ret; } static inline void ip6_sock_set_recverr(struct sock *sk) diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 38ef66826939ee..41d9fc6965f9a0 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -69,9 +69,6 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) int refs = 1; rcu_read_lock(); - /* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */ - if (READ_ONCE(fq->q.fqdir->dead)) - goto out_rcu_unlock; spin_lock(&fq->q.lock); if (fq->q.flags & INET_FRAG_COMPLETE) @@ -80,6 +77,12 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) fq->q.flags |= INET_FRAG_DROP; inet_frag_kill(&fq->q, &refs); + /* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */ + if (READ_ONCE(fq->q.fqdir->dead)) { + inet_frag_queue_flush(&fq->q, 0); + goto out; + } + dev = dev_get_by_index_rcu(net, fq->iif); if (!dev) goto out; diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index 1b58b5b91ff6a4..cf0166520cf338 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -13,20 +13,20 @@ struct nf_conncount_list { u32 last_gc; /* jiffies at most recent gc */ struct list_head head; /* connections with the same filtering key */ unsigned int count; /* length of list */ + unsigned int last_gc_count; /* length of list at most recent gc */ }; struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int keylen); void nf_conncount_destroy(struct net *net, struct nf_conncount_data *data); -unsigned int nf_conncount_count(struct net *net, - struct nf_conncount_data *data, - const u32 *key, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone); +unsigned int nf_conncount_count_skb(struct net *net, + const struct sk_buff *skb, + u16 l3num, + struct nf_conncount_data *data, + const u32 *key); -int nf_conncount_add(struct net *net, struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone); +int nf_conncount_add_skb(struct net *net, const struct sk_buff *skb, + u16 l3num, struct nf_conncount_list *list); void nf_conncount_list_init(struct nf_conncount_list *list); diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 4aeffddb75861e..45eb26b2e95b37 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -6,11 +6,13 @@ #include #include #include +#include #include /* Each queued (to userspace) skbuff has one of these. */ struct nf_queue_entry { struct list_head list; + struct rhash_head hash_node; struct sk_buff *skb; unsigned int id; unsigned int hook_index; /* index in hook_entries->hook[] */ @@ -19,7 +21,9 @@ struct nf_queue_entry { struct net_device *physout; #endif struct nf_hook_state state; + bool nf_ct_is_unconfirmed; u16 size; /* sizeof(entry) + saved route keys */ + u16 queue_num; /* extra space to store route keys */ }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index fab7dc73f738cb..05f57ba6224476 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -278,6 +278,8 @@ struct nft_userdata { unsigned char data[]; }; +#define NFT_SET_ELEM_INTERNAL_LAST 0x1 + /* placeholder structure for opaque set element backend representation. */ struct nft_elem_priv { }; @@ -287,6 +289,7 @@ struct nft_elem_priv { }; * @key: element key * @key_end: closing element key * @data: element data + * @flags: flags * @priv: element private data and extensions */ struct nft_set_elem { @@ -302,6 +305,7 @@ struct nft_set_elem { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } data; + u32 flags; struct nft_elem_priv *priv; }; @@ -452,6 +456,7 @@ struct nft_set_ext; * @init: initialize private data of new set instance * @destroy: destroy private data of set instance * @gc_init: initialize garbage collection + * @abort_skip_removal: skip removal of elements from abort path * @elemsize: element private size * * Operations lookup, update and delete have simpler interfaces, are faster @@ -509,6 +514,7 @@ struct nft_set_ops { const struct nft_set *set); void (*gc_init)(const struct nft_set *set); + bool abort_skip_removal; unsigned int elemsize; }; @@ -1091,6 +1097,29 @@ struct nft_rule_blob { __attribute__((aligned(__alignof__(struct nft_rule_dp)))); }; +enum nft_chain_types { + NFT_CHAIN_T_DEFAULT = 0, + NFT_CHAIN_T_ROUTE, + NFT_CHAIN_T_NAT, + NFT_CHAIN_T_MAX +}; + +/** + * struct nft_chain_validate_state - validation state + * + * If a chain is encountered again during table validation it is + * possible to avoid revalidation provided the calling context is + * compatible. This structure stores relevant calling context of + * previous validations. + * + * @hook_mask: the hook numbers and locations the chain is linked to + * @depth: the deepest call chain level the chain is linked to + */ +struct nft_chain_validate_state { + u8 hook_mask[NFT_CHAIN_T_MAX]; + u8 depth; +}; + /** * struct nft_chain - nf_tables chain * @@ -1109,6 +1138,7 @@ struct nft_rule_blob { * @udlen: user data length * @udata: user data in the chain * @blob_next: rule blob pointer to the next in the chain + * @vstate: validation state */ struct nft_chain { struct nft_rule_blob __rcu *blob_gen_0; @@ -1128,9 +1158,10 @@ struct nft_chain { /* Only used during control plane commit phase: */ struct nft_rule_blob *blob_next; + struct nft_chain_validate_state vstate; }; -int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); +int nft_chain_validate(const struct nft_ctx *ctx, struct nft_chain *chain); int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv); @@ -1138,13 +1169,6 @@ int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); -enum nft_chain_types { - NFT_CHAIN_T_DEFAULT = 0, - NFT_CHAIN_T_ROUTE, - NFT_CHAIN_T_NAT, - NFT_CHAIN_T_MAX -}; - /** * struct nft_chain_type - nf_tables chain type info * diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 34eb3aecb3f21c..62166da0455481 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -87,6 +87,12 @@ struct netns_ipv4 { int sysctl_tcp_rmem[3]; __cacheline_group_end(netns_ipv4_read_rx); + /* ICMP rate limiter hot cache line. */ + __cacheline_group_begin_aligned(icmp); + atomic_t icmp_global_credit; + u32 icmp_global_stamp; + __cacheline_group_end_aligned(icmp); + struct inet_timewait_death_row tcp_death_row; struct udp_table *udp_table; @@ -139,8 +145,7 @@ struct netns_ipv4 { int sysctl_icmp_ratemask; int sysctl_icmp_msgs_per_sec; int sysctl_icmp_msgs_burst; - atomic_t icmp_global_credit; - u32 icmp_global_stamp; + u32 ip_rt_min_pmtu; int ip_rt_mtu_expires; int ip_rt_min_advmss; diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 127e6c7d910dcb..c54df042db6be2 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -219,6 +219,8 @@ static inline void nfc_free_device(struct nfc_dev *dev) int nfc_register_device(struct nfc_dev *dev); +void nfc_unregister_rfkill(struct nfc_dev *dev); +void nfc_remove_device(struct nfc_dev *dev); void nfc_unregister_device(struct nfc_dev *dev); /** diff --git a/include/net/tcp.h b/include/net/tcp.h index ab20f549b8f914..3c84d95cdba813 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1190,7 +1190,15 @@ enum tcp_ca_ack_event_flags { #define TCP_CONG_NON_RESTRICTED BIT(0) /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN BIT(1) -#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN) +/* Require successfully negotiated AccECN capability */ +#define TCP_CONG_NEEDS_ACCECN BIT(2) +/* Use ECT(1) instead of ECT(0) while the CA is uninitialized */ +#define TCP_CONG_ECT_1_NEGOTIATION BIT(3) +/* Cannot fallback to RFC3168 during AccECN negotiation */ +#define TCP_CONG_NO_FALLBACK_RFC3168 BIT(4) +#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN | \ + TCP_CONG_NEEDS_ACCECN | TCP_CONG_ECT_1_NEGOTIATION | \ + TCP_CONG_NO_FALLBACK_RFC3168) union tcp_cc_info; @@ -1322,6 +1330,27 @@ static inline bool tcp_ca_needs_ecn(const struct sock *sk) return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; } +static inline bool tcp_ca_needs_accecn(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ACCECN; +} + +static inline bool tcp_ca_ect_1_negotiation(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_ECT_1_NEGOTIATION; +} + +static inline bool tcp_ca_no_fallback_rfc3168(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_NO_FALLBACK_RFC3168; +} + static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index f13e5cd2b1ac3c..a709fb1756eb75 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -31,6 +31,12 @@ enum tcp_accecn_option { TCP_ACCECN_OPTION_FULL = 2, }; +/* Apply either ECT(0) or ECT(1) based on TCP_CONG_ECT_1_NEGOTIATION flag */ +static inline void INET_ECN_xmit_ect_1_negotiation(struct sock *sk) +{ + __INET_ECN_xmit(sk, tcp_ca_ect_1_negotiation(sk)); +} + static inline void tcp_ecn_queue_cwr(struct tcp_sock *tp) { /* Do not set CWR if in AccECN mode! */ @@ -467,6 +473,26 @@ static inline u8 tcp_accecn_option_init(const struct sk_buff *skb, return TCP_ACCECN_OPT_COUNTER_SEEN; } +static inline void tcp_ecn_rcv_synack_accecn(struct sock *sk, + const struct sk_buff *skb, u8 dsf) +{ + struct tcp_sock *tp = tcp_sk(sk); + + tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); + tp->syn_ect_rcv = dsf & INET_ECN_MASK; + /* Demand Accurate ECN option in response to the SYN on the SYN/ACK + * and the TCP server will try to send one more packet with an AccECN + * Option at a later point during the connection. + */ + if (tp->rx_opt.accecn && + tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) { + u8 saw_opt = tcp_accecn_option_init(skb, tp->rx_opt.accecn); + + tcp_accecn_saw_opt_fail_recv(tp, saw_opt); + tp->accecn_opt_demand = 2; + } +} + /* See Table 2 of the AccECN draft */ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb, const struct tcphdr *th, u8 ip_dsfield) @@ -489,32 +515,32 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); break; case 0x1: - case 0x5: /* +========+========+============+=============+ * | A | B | SYN/ACK | Feedback | * | | | B->A | Mode of A | * | | | AE CWR ECE | | * +========+========+============+=============+ - * | AccECN | Nonce | 1 0 1 | (Reserved) | * | AccECN | ECN | 0 0 1 | Classic ECN | * | Nonce | AccECN | 0 0 1 | Classic ECN | * | ECN | AccECN | 0 0 1 | Classic ECN | * +========+========+============+=============+ */ - if (tcp_ecn_mode_pending(tp)) - /* Downgrade from AccECN, or requested initially */ + if (tcp_ca_no_fallback_rfc3168(sk)) + tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); + else tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168); break; - default: - tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); - tp->syn_ect_rcv = ip_dsfield & INET_ECN_MASK; - if (tp->rx_opt.accecn && - tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) { - u8 saw_opt = tcp_accecn_option_init(skb, tp->rx_opt.accecn); - - tcp_accecn_saw_opt_fail_recv(tp, saw_opt); - tp->accecn_opt_demand = 2; + case 0x5: + if (tcp_ecn_mode_pending(tp)) { + tcp_ecn_rcv_synack_accecn(sk, skb, ip_dsfield); + if (INET_ECN_is_ce(ip_dsfield)) { + tp->received_ce++; + tp->received_ce_pending++; + } } + break; + default: + tcp_ecn_rcv_synack_accecn(sk, skb, ip_dsfield); if (INET_ECN_is_ce(ip_dsfield) && tcp_accecn_validate_syn_feedback(sk, ace, tp->syn_ect_snt)) { @@ -525,9 +551,11 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb } } -static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th, +static inline void tcp_ecn_rcv_syn(struct sock *sk, const struct tcphdr *th, const struct sk_buff *skb) { + struct tcp_sock *tp = tcp_sk(sk); + if (tcp_ecn_mode_pending(tp)) { if (!tcp_accecn_syn_requested(th)) { /* Downgrade to classic ECN feedback */ @@ -539,7 +567,8 @@ static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th, tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); } } - if (tcp_ecn_mode_rfc3168(tp) && (!th->ece || !th->cwr)) + if (tcp_ecn_mode_rfc3168(tp) && + (!th->ece || !th->cwr || tcp_ca_no_fallback_rfc3168(sk))) tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); } @@ -561,7 +590,7 @@ static inline void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; else if (tcp_ca_needs_ecn(sk) || tcp_bpf_ca_needs_ecn(sk)) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); if (tp->ecn_flags & TCP_ECN_MODE_ACCECN) { TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ACE; @@ -579,7 +608,8 @@ static inline void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) bool use_ecn, use_accecn; u8 tcp_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn); - use_accecn = tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ACCECN; + use_accecn = tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ACCECN || + tcp_ca_needs_accecn(sk); use_ecn = tcp_ecn == TCP_ECN_IN_ECN_OUT_ECN || tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ECN || tcp_ca_needs_ecn(sk) || bpf_needs_ecn || use_accecn; @@ -595,7 +625,7 @@ static inline void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) if (use_ecn) { if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; if (use_accecn) { diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index c8cd0f00c8454a..c9f0b1018bcce0 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -168,11 +168,25 @@ TRACE_EVENT(mc_event, * This event is generated when hardware detects an ARM processor error * has occurred. UEFI 2.6 spec section N.2.4.4. */ +#define APEIL "ARM Processor Err Info data len" +#define APEID "ARM Processor Err Info raw data" +#define APECIL "ARM Processor Err Context Info data len" +#define APECID "ARM Processor Err Context Info raw data" +#define VSEIL "Vendor Specific Err Info data len" +#define VSEID "Vendor Specific Err Info raw data" TRACE_EVENT(arm_event, - TP_PROTO(const struct cper_sec_proc_arm *proc), + TP_PROTO(const struct cper_sec_proc_arm *proc, + const u8 *pei_err, + const u32 pei_len, + const u8 *ctx_err, + const u32 ctx_len, + const u8 *oem, + const u32 oem_len, + u8 sev, + int cpu), - TP_ARGS(proc), + TP_ARGS(proc, pei_err, pei_len, ctx_err, ctx_len, oem, oem_len, sev, cpu), TP_STRUCT__entry( __field(u64, mpidr) @@ -180,6 +194,14 @@ TRACE_EVENT(arm_event, __field(u32, running_state) __field(u32, psci_state) __field(u8, affinity) + __field(u32, pei_len) + __dynamic_array(u8, pei_buf, pei_len) + __field(u32, ctx_len) + __dynamic_array(u8, ctx_buf, ctx_len) + __field(u32, oem_len) + __dynamic_array(u8, oem_buf, oem_len) + __field(u8, sev) + __field(int, cpu) ), TP_fast_assign( @@ -199,12 +221,29 @@ TRACE_EVENT(arm_event, __entry->running_state = ~0; __entry->psci_state = ~0; } + __entry->pei_len = pei_len; + memcpy(__get_dynamic_array(pei_buf), pei_err, pei_len); + __entry->ctx_len = ctx_len; + memcpy(__get_dynamic_array(ctx_buf), ctx_err, ctx_len); + __entry->oem_len = oem_len; + memcpy(__get_dynamic_array(oem_buf), oem, oem_len); + __entry->sev = sev; + __entry->cpu = cpu; ), - TP_printk("affinity level: %d; MPIDR: %016llx; MIDR: %016llx; " - "running state: %d; PSCI state: %d", + TP_printk("cpu: %d; error: %d; affinity level: %d; MPIDR: %016llx; MIDR: %016llx; " + "running state: %d; PSCI state: %d; " + "%s: %d; %s: %s; %s: %d; %s: %s; %s: %d; %s: %s", + __entry->cpu, + __entry->sev, __entry->affinity, __entry->mpidr, __entry->midr, - __entry->running_state, __entry->psci_state) + __entry->running_state, __entry->psci_state, + APEIL, __entry->pei_len, APEID, + __print_hex(__get_dynamic_array(pei_buf), __entry->pei_len), + APECIL, __entry->ctx_len, APECID, + __print_hex(__get_dynamic_array(ctx_buf), __entry->ctx_len), + VSEIL, __entry->oem_len, VSEID, + __print_hex(__get_dynamic_array(oem_buf), __entry->oem_len)) ); /* diff --git a/include/rdma/rw.h b/include/rdma/rw.h index d606cac482338b..9a8f4b76ce588d 100644 --- a/include/rdma/rw.h +++ b/include/rdma/rw.h @@ -66,6 +66,8 @@ int rdma_rw_ctx_post(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u32 port_num, unsigned int rdma_rw_mr_factor(struct ib_device *device, u32 port_num, unsigned int maxpages); +unsigned int rdma_rw_max_send_wr(struct ib_device *dev, u32 port_num, + unsigned int max_rdma_ctxs, u32 create_flags); void rdma_rw_init_qp(struct ib_device *dev, struct ib_qp_init_attr *attr); int rdma_rw_init_mrs(struct ib_qp *qp, struct ib_qp_init_attr *attr); void rdma_rw_cleanup_mrs(struct ib_qp *qp); diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h index 1ae08e81339fac..15679be90c5c3d 100644 --- a/include/scsi/scsi_eh.h +++ b/include/scsi/scsi_eh.h @@ -41,6 +41,12 @@ struct scsi_eh_save { unsigned char cmnd[32]; struct scsi_data_buffer sdb; struct scatterlist sense_sgl; + + /* struct request fields */ +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct bio_crypt_ctx *rq_crypt_ctx; + struct blk_crypto_keyslot *rq_crypt_keyslot; +#endif }; extern void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, diff --git a/include/sound/control.h b/include/sound/control.h index e07f6b960641ff..9be6546bf787de 100644 --- a/include/sound/control.h +++ b/include/sound/control.h @@ -14,9 +14,12 @@ #define snd_kcontrol_chip(kcontrol) ((kcontrol)->private_data) struct snd_kcontrol; +struct snd_ctl_file; typedef int (snd_kcontrol_info_t) (struct snd_kcontrol * kcontrol, struct snd_ctl_elem_info * uinfo); typedef int (snd_kcontrol_get_t) (struct snd_kcontrol * kcontrol, struct snd_ctl_elem_value * ucontrol); typedef int (snd_kcontrol_put_t) (struct snd_kcontrol * kcontrol, struct snd_ctl_elem_value * ucontrol); +typedef int (snd_kcontrol_lock_t) (struct snd_kcontrol * kcontrol, struct snd_ctl_file *owner); +typedef void (snd_kcontrol_unlock_t) (struct snd_kcontrol * kcontrol); typedef int (snd_kcontrol_tlv_rw_t)(struct snd_kcontrol *kcontrol, int op_flag, /* SNDRV_CTL_TLV_OP_XXX */ unsigned int size, @@ -55,6 +58,8 @@ struct snd_kcontrol_new { snd_kcontrol_info_t *info; snd_kcontrol_get_t *get; snd_kcontrol_put_t *put; + snd_kcontrol_lock_t *lock; + snd_kcontrol_unlock_t *unlock; union { snd_kcontrol_tlv_rw_t *c; const unsigned int *p; @@ -74,6 +79,8 @@ struct snd_kcontrol { snd_kcontrol_info_t *info; snd_kcontrol_get_t *get; snd_kcontrol_put_t *put; + snd_kcontrol_lock_t *lock; + snd_kcontrol_unlock_t *unlock; union { snd_kcontrol_tlv_rw_t *c; const unsigned int *p; diff --git a/include/sound/cs42l42.h b/include/sound/cs42l42.h index 1bd8eee54f6665..b3657965d49109 100644 --- a/include/sound/cs42l42.h +++ b/include/sound/cs42l42.h @@ -62,6 +62,10 @@ #define CS42L42_INTERNAL_FS_MASK (1 << CS42L42_INTERNAL_FS_SHIFT) #define CS42L42_SFTRAMP_RATE (CS42L42_PAGE_10 + 0x0A) +#define CS42L42_SFTRAMP_ASR_RATE_MASK GENMASK(7, 4) +#define CS42L42_SFTRAMP_ASR_RATE_SHIFT 4 +#define CS42L42_SFTRAMP_DSR_RATE_MASK GENMASK(3, 0) +#define CS42L42_SFTRAMP_DSR_RATE_SHIFT 0 #define CS42L42_SLOW_START_ENABLE (CS42L42_PAGE_10 + 0x0B) #define CS42L42_SLOW_START_EN_MASK GENMASK(6, 4) #define CS42L42_SLOW_START_EN_SHIFT 4 diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 58fd6e84f9613f..a0c987c9bd1fee 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -1073,6 +1073,7 @@ int snd_interval_ranges(struct snd_interval *i, unsigned int count, int snd_interval_ratnum(struct snd_interval *i, unsigned int rats_count, const struct snd_ratnum *rats, unsigned int *nump, unsigned int *denp); +int snd_interval_rate_bits(struct snd_interval *i, unsigned int rate_bits); void _snd_pcm_hw_params_any(struct snd_pcm_hw_params *params); void _snd_pcm_hw_param_setempty(struct snd_pcm_hw_params *params, snd_pcm_hw_param_t var); @@ -1402,7 +1403,7 @@ int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_s #define snd_pcm_lib_mmap_iomem NULL #endif -void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime); +int snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime); /** * snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer diff --git a/include/sound/sdca_function.h b/include/sound/sdca_function.h index ea68856e4c8c44..86fd74146c33d8 100644 --- a/include/sound/sdca_function.h +++ b/include/sound/sdca_function.h @@ -771,6 +771,7 @@ struct sdca_control { u8 layers; bool deferrable; + bool is_volatile; bool has_default; bool has_fixed; }; diff --git a/include/sound/soc-card.h b/include/sound/soc-card.h index ecc02e955279fd..ef46cac97d9968 100644 --- a/include/sound/soc-card.h +++ b/include/sound/soc-card.h @@ -44,7 +44,7 @@ int snd_soc_card_resume_post(struct snd_soc_card *card); int snd_soc_card_probe(struct snd_soc_card *card); int snd_soc_card_late_probe(struct snd_soc_card *card); -void snd_soc_card_fixup_controls(struct snd_soc_card *card); +int snd_soc_card_fixup_controls(struct snd_soc_card *card); int snd_soc_card_remove(struct snd_soc_card *card); int snd_soc_card_set_bias_level(struct snd_soc_card *card, diff --git a/include/sound/soc.h b/include/sound/soc.h index ddc508ff7b9be1..b5c91f4a5db3c9 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -561,8 +561,14 @@ int snd_soc_get_volsw_sx(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol); int snd_soc_put_volsw_sx(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol); +bool snd_soc_control_matches(struct snd_kcontrol *kcontrol, + const char *pattern); int snd_soc_limit_volume(struct snd_soc_card *card, const char *name, int max); +int snd_soc_deactivate_kctl(struct snd_soc_card *card, + const char *name, int active); +int snd_soc_set_enum_kctl(struct snd_soc_card *card, + const char *name, const char *strval); int snd_soc_bytes_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo); int snd_soc_bytes_get(struct snd_kcontrol *kcontrol, @@ -989,7 +995,7 @@ struct snd_soc_card { int (*probe)(struct snd_soc_card *card); int (*late_probe)(struct snd_soc_card *card); - void (*fixup_controls)(struct snd_soc_card *card); + int (*fixup_controls)(struct snd_soc_card *card); int (*remove)(struct snd_soc_card *card); /* the pre and post PM functions are used to do any PM work before and @@ -1225,6 +1231,7 @@ struct soc_mixer_control { unsigned int sign_bit; unsigned int invert:1; unsigned int autodisable:1; + unsigned int sdca_q78:1; #ifdef CONFIG_SND_SOC_TOPOLOGY struct snd_soc_dobj dobj; #endif diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h index 0fbcdb15c74b54..29d15ba65f04d3 100644 --- a/include/sound/tas2781.h +++ b/include/sound/tas2781.h @@ -197,7 +197,6 @@ struct tasdevice_priv { struct acoustic_data acou_data; #endif struct tasdevice_fw *fmw; - struct gpio_desc *speaker_id; struct gpio_desc *reset; struct mutex codec_lock; struct regmap *regmap; @@ -215,6 +214,7 @@ struct tasdevice_priv { unsigned int magic_num; unsigned int chip_id; unsigned int sysclk; + int speaker_id; int irq; int cur_prog; diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index c4d9116904aa0f..27e1f9d5f0c6cd 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -671,9 +671,9 @@ struct se_lun_acl { }; struct se_dev_entry_io_stats { - u32 total_cmds; - u32 read_bytes; - u32 write_bytes; + u64 total_cmds; + u64 read_bytes; + u64 write_bytes; }; struct se_dev_entry { @@ -806,9 +806,9 @@ struct se_device_queue { }; struct se_dev_io_stats { - u32 total_cmds; - u32 read_bytes; - u32 write_bytes; + u64 total_cmds; + u64 read_bytes; + u64 write_bytes; }; struct se_device { diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 7e418f065b945a..125bdc166bfed7 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -224,7 +224,8 @@ DECLARE_EVENT_CLASS(btrfs__inode, __entry->generation = BTRFS_I(inode)->generation; __entry->last_trans = BTRFS_I(inode)->last_trans; __entry->logged_trans = BTRFS_I(inode)->logged_trans; - __entry->root_objectid = btrfs_root_id(BTRFS_I(inode)->root); + __entry->root_objectid = BTRFS_I(inode)->root ? + btrfs_root_id(BTRFS_I(inode)->root) : 0; ), TP_printk_btrfs("root=%llu(%s) gen=%llu ino=%llu blocks=%llu " diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h index b3fef140ae155b..33e99e792f1aa2 100644 --- a/include/trace/events/dma.h +++ b/include/trace/events/dma.h @@ -275,6 +275,8 @@ TRACE_EVENT(dma_free_sgt, sizeof(u64), sizeof(u64))) ); +#define DMA_TRACE_MAX_ENTRIES 128 + TRACE_EVENT(dma_map_sg, TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, int ents, enum dma_data_direction dir, unsigned long attrs), @@ -282,9 +284,12 @@ TRACE_EVENT(dma_map_sg, TP_STRUCT__entry( __string(device, dev_name(dev)) - __dynamic_array(u64, phys_addrs, nents) - __dynamic_array(u64, dma_addrs, ents) - __dynamic_array(unsigned int, lengths, ents) + __field(int, full_nents) + __field(int, full_ents) + __field(bool, truncated) + __dynamic_array(u64, phys_addrs, min(nents, DMA_TRACE_MAX_ENTRIES)) + __dynamic_array(u64, dma_addrs, min(ents, DMA_TRACE_MAX_ENTRIES)) + __dynamic_array(unsigned int, lengths, min(ents, DMA_TRACE_MAX_ENTRIES)) __field(enum dma_data_direction, dir) __field(unsigned long, attrs) ), @@ -292,11 +297,16 @@ TRACE_EVENT(dma_map_sg, TP_fast_assign( struct scatterlist *sg; int i; + int traced_nents = min_t(int, nents, DMA_TRACE_MAX_ENTRIES); + int traced_ents = min_t(int, ents, DMA_TRACE_MAX_ENTRIES); __assign_str(device); - for_each_sg(sgl, sg, nents, i) + __entry->full_nents = nents; + __entry->full_ents = ents; + __entry->truncated = (nents > DMA_TRACE_MAX_ENTRIES) || (ents > DMA_TRACE_MAX_ENTRIES); + for_each_sg(sgl, sg, traced_nents, i) ((u64 *)__get_dynamic_array(phys_addrs))[i] = sg_phys(sg); - for_each_sg(sgl, sg, ents, i) { + for_each_sg(sgl, sg, traced_ents, i) { ((u64 *)__get_dynamic_array(dma_addrs))[i] = sg_dma_address(sg); ((unsigned int *)__get_dynamic_array(lengths))[i] = @@ -306,9 +316,12 @@ TRACE_EVENT(dma_map_sg, __entry->attrs = attrs; ), - TP_printk("%s dir=%s dma_addrs=%s sizes=%s phys_addrs=%s attrs=%s", + TP_printk("%s dir=%s nents=%d/%d ents=%d/%d%s dma_addrs=%s sizes=%s phys_addrs=%s attrs=%s", __get_str(device), decode_dma_data_direction(__entry->dir), + min_t(int, __entry->full_nents, DMA_TRACE_MAX_ENTRIES), __entry->full_nents, + min_t(int, __entry->full_ents, DMA_TRACE_MAX_ENTRIES), __entry->full_ents, + __entry->truncated ? " [TRUNCATED]" : "", __print_array(__get_dynamic_array(dma_addrs), __get_dynamic_array_len(dma_addrs) / sizeof(u64), sizeof(u64)), diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index de6f6d25767c6e..869f97c9bf733e 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -322,6 +322,7 @@ EM(rxrpc_call_put_kernel, "PUT kernel ") \ EM(rxrpc_call_put_poke, "PUT poke ") \ EM(rxrpc_call_put_recvmsg, "PUT recvmsg ") \ + EM(rxrpc_call_put_recvmsg_peek_nowait, "PUT peek-nwt") \ EM(rxrpc_call_put_release_recvmsg_q, "PUT rls-rcmq") \ EM(rxrpc_call_put_release_sock, "PUT rls-sock") \ EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ @@ -340,6 +341,9 @@ EM(rxrpc_call_see_input, "SEE input ") \ EM(rxrpc_call_see_notify_released, "SEE nfy-rlsd") \ EM(rxrpc_call_see_recvmsg, "SEE recvmsg ") \ + EM(rxrpc_call_see_recvmsg_requeue, "SEE recv-rqu") \ + EM(rxrpc_call_see_recvmsg_requeue_first, "SEE recv-rqF") \ + EM(rxrpc_call_see_recvmsg_requeue_move, "SEE recv-rqM") \ EM(rxrpc_call_see_release, "SEE release ") \ EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ EM(rxrpc_call_see_waiting_call, "SEE q-conn ") \ diff --git a/include/trace/events/tlb.h b/include/trace/events/tlb.h index b4d8e7dc38f880..fb836951168564 100644 --- a/include/trace/events/tlb.h +++ b/include/trace/events/tlb.h @@ -12,8 +12,9 @@ EM( TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" ) \ EM( TLB_REMOTE_SHOOTDOWN, "remote shootdown" ) \ EM( TLB_LOCAL_SHOOTDOWN, "local shootdown" ) \ - EM( TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" ) \ - EMe( TLB_REMOTE_SEND_IPI, "remote ipi send" ) + EM( TLB_LOCAL_MM_SHOOTDOWN, "local MM shootdown" ) \ + EM( TLB_REMOTE_SEND_IPI, "remote IPI send" ) \ + EMe( TLB_REMOTE_WRONG_CPU, "remote wrong CPU" ) /* * First define the enums in TLB_FLUSH_REASON to be exported to userspace diff --git a/include/trace/misc/nfs.h b/include/trace/misc/nfs.h index c82233e950ac06..a394b4d38e18fa 100644 --- a/include/trace/misc/nfs.h +++ b/include/trace/misc/nfs.h @@ -16,7 +16,6 @@ TRACE_DEFINE_ENUM(NFSERR_PERM); TRACE_DEFINE_ENUM(NFSERR_NOENT); TRACE_DEFINE_ENUM(NFSERR_IO); TRACE_DEFINE_ENUM(NFSERR_NXIO); -TRACE_DEFINE_ENUM(NFSERR_EAGAIN); TRACE_DEFINE_ENUM(NFSERR_ACCES); TRACE_DEFINE_ENUM(NFSERR_EXIST); TRACE_DEFINE_ENUM(NFSERR_XDEV); @@ -52,7 +51,6 @@ TRACE_DEFINE_ENUM(NFSERR_JUKEBOX); { NFSERR_NXIO, "NXIO" }, \ { ECHILD, "CHILD" }, \ { ETIMEDOUT, "TIMEDOUT" }, \ - { NFSERR_EAGAIN, "AGAIN" }, \ { NFSERR_ACCES, "ACCES" }, \ { NFSERR_EXIST, "EXIST" }, \ { NFSERR_XDEV, "XDEV" }, \ diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 517489a7ec60aa..400555a8af187f 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -1459,6 +1459,7 @@ struct drm_xe_exec { /** @exec_queue_id: Exec queue ID for the batch buffer */ __u32 exec_queue_id; +#define DRM_XE_MAX_SYNCS 1024 /** @num_syncs: Amount of struct drm_xe_sync in array. */ __u32 num_syncs; diff --git a/include/uapi/linux/comedi.h b/include/uapi/linux/comedi.h index 7314e5ee0a1e8d..798ec9a39e1298 100644 --- a/include/uapi/linux/comedi.h +++ b/include/uapi/linux/comedi.h @@ -640,7 +640,7 @@ struct comedi_chaninfo { /** * struct comedi_rangeinfo - used to retrieve the range table for a channel - * @range_type: Encodes subdevice index (bits 27:24), channel index + * @range_type: Encodes subdevice index (bits 31:24), channel index * (bits 23:16) and range table length (bits 15:0). * @range_ptr: Pointer to array of @struct comedi_krange to be filled * in with the range table for the channel or subdevice. diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index ab1725a954d749..69d35570ac4f12 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -251,6 +251,7 @@ enum dpll_a_pin { DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED, DPLL_A_PIN_ESYNC_PULSE, DPLL_A_PIN_REFERENCE_SYNC, + DPLL_A_PIN_PHASE_ADJUST_GRAN, __DPLL_A_PIN_MAX, DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1) diff --git a/include/uapi/linux/ext4.h b/include/uapi/linux/ext4.h index 411dcc1e4a35c8..9c683991c32f96 100644 --- a/include/uapi/linux/ext4.h +++ b/include/uapi/linux/ext4.h @@ -139,7 +139,7 @@ struct ext4_tune_sb_params { __u32 clear_feature_incompat_mask; __u32 clear_feature_ro_compat_mask; __u8 mount_opts[64]; - __u8 pad[64]; + __u8 pad[68]; }; #define EXT4_TUNE_FL_ERRORS_BEHAVIOR 0x00000001 diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 87cfab874e2415..49e9b4e98c8b4b 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -40,6 +40,7 @@ #define MPTCP_PM_ADDR_FLAG_FULLMESH _BITUL(3) #define MPTCP_PM_ADDR_FLAG_IMPLICIT _BITUL(4) #define MPTCP_PM_ADDR_FLAG_LAMINAR _BITUL(5) +#define MPTCP_PM_ADDR_FLAGS_MASK GENMASK(5, 0) struct mptcp_info { __u8 mptcpi_subflows; diff --git a/include/uapi/linux/nfs.h b/include/uapi/linux/nfs.h index f356f2ba381428..e629c495353456 100644 --- a/include/uapi/linux/nfs.h +++ b/include/uapi/linux/nfs.h @@ -49,14 +49,13 @@ NFSERR_NOENT = 2, /* v2 v3 v4 */ NFSERR_IO = 5, /* v2 v3 v4 */ NFSERR_NXIO = 6, /* v2 v3 v4 */ - NFSERR_EAGAIN = 11, /* v2 v3 */ NFSERR_ACCES = 13, /* v2 v3 v4 */ NFSERR_EXIST = 17, /* v2 v3 v4 */ NFSERR_XDEV = 18, /* v3 v4 */ NFSERR_NODEV = 19, /* v2 v3 v4 */ NFSERR_NOTDIR = 20, /* v2 v3 v4 */ NFSERR_ISDIR = 21, /* v2 v3 v4 */ - NFSERR_INVAL = 22, /* v2 v3 v4 */ + NFSERR_INVAL = 22, /* v3 v4 */ NFSERR_FBIG = 27, /* v2 v3 v4 */ NFSERR_NOSPC = 28, /* v2 v3 v4 */ NFSERR_ROFS = 30, /* v2 v3 v4 */ diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 957db425d459a1..6ccbabd9a68d81 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -28,6 +28,7 @@ #define PIDFD_INFO_COREDUMP (1UL << 4) /* Only returned if requested. */ #define PIDFD_INFO_SIZE_VER0 64 /* sizeof first published struct */ +#define PIDFD_INFO_SIZE_VER1 72 /* sizeof second published struct */ /* * Values for @coredump_mask in pidfd_info. diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 51c4e8c82b1e98..d58fce1f4ffafb 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -6,6 +6,11 @@ /* Values to pass as first argument to prctl() */ +#define PR_GET_MEM_MODEL 0x6d4d444c +#define PR_SET_MEM_MODEL 0x4d4d444c +# define PR_SET_MEM_MODEL_DEFAULT 0 +# define PR_SET_MEM_MODEL_TSO 1 + #define PR_SET_PDEATHSIG 1 /* Second arg is a signal */ #define PR_GET_PDEATHSIG 2 /* Second arg is a ptr to return the signal */ diff --git a/include/uapi/rdma/irdma-abi.h b/include/uapi/rdma/irdma-abi.h index f7788d33376b83..36f20802bcc849 100644 --- a/include/uapi/rdma/irdma-abi.h +++ b/include/uapi/rdma/irdma-abi.h @@ -57,8 +57,8 @@ struct irdma_alloc_ucontext_resp { __u8 rsvd2; __aligned_u64 comp_mask; __u16 min_hw_wq_size; + __u8 revd3[2]; __u32 max_hw_srq_quanta; - __u8 rsvd3[2]; }; struct irdma_alloc_pd_resp { diff --git a/include/uapi/rdma/rdma_user_cm.h b/include/uapi/rdma/rdma_user_cm.h index 5ded174687ee04..838f8d46025603 100644 --- a/include/uapi/rdma/rdma_user_cm.h +++ b/include/uapi/rdma/rdma_user_cm.h @@ -192,6 +192,7 @@ struct rdma_ucm_query_path_resp { struct rdma_ucm_query_ib_service_resp { __u32 num_service_recs; + __u32 reserved; struct ib_user_service_rec recs[]; }; @@ -354,7 +355,7 @@ enum { #define RDMA_USER_CM_IB_SERVICE_NAME_SIZE 64 struct rdma_ucm_ib_service { - __u64 service_id; + __aligned_u64 service_id; __u8 service_name[RDMA_USER_CM_IB_SERVICE_NAME_SIZE]; __u32 flags; __u32 reserved; @@ -362,6 +363,7 @@ struct rdma_ucm_ib_service { struct rdma_ucm_resolve_ib_service { __u32 id; + __u32 reserved; struct rdma_ucm_ib_service ibs; }; diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 5a049eeaeccea5..d3ce75ba938a84 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -60,7 +60,7 @@ struct snd_cea_861_aud_if { unsigned char db2_sf_ss; /* sample frequency and size */ unsigned char db3; /* not used, all zeros */ unsigned char db4_ca; /* channel allocation code */ - unsigned char db5_dminh_lsv; /* downmix inhibit & level-shit values */ + unsigned char db5_dminh_lsv; /* downmix inhibit & level-shift values */ }; /**************************************************************************** diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index 0f95576bf1f6ca..17fe07dac6a7e3 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1302,7 +1302,6 @@ static inline void ufshcd_rmwl(struct ufs_hba *hba, u32 mask, u32 val, u32 reg) void ufshcd_enable_irq(struct ufs_hba *hba); void ufshcd_disable_irq(struct ufs_hba *hba); -void ufshcd_enable_intr(struct ufs_hba *hba, u32 intrs); int ufshcd_alloc_host(struct device *, struct ufs_hba **); int ufshcd_hba_enable(struct ufs_hba *hba); int ufshcd_init(struct ufs_hba *, void __iomem *, unsigned int); @@ -1351,17 +1350,13 @@ static inline void *ufshcd_get_variant(struct ufs_hba *hba) return hba->priv; } -#ifdef CONFIG_PM extern int ufshcd_runtime_suspend(struct device *dev); extern int ufshcd_runtime_resume(struct device *dev); -#endif -#ifdef CONFIG_PM_SLEEP extern int ufshcd_system_suspend(struct device *dev); extern int ufshcd_system_resume(struct device *dev); extern int ufshcd_system_freeze(struct device *dev); extern int ufshcd_system_thaw(struct device *dev); extern int ufshcd_system_restore(struct device *dev); -#endif extern int ufshcd_dme_reset(struct ufs_hba *hba); extern int ufshcd_dme_enable(struct ufs_hba *hba); diff --git a/include/xen/xen.h b/include/xen/xen.h index 61854e3f283776..f280c5dcf92369 100644 --- a/include/xen/xen.h +++ b/include/xen/xen.h @@ -69,11 +69,13 @@ extern u64 xen_saved_max_mem_size; #endif #ifdef CONFIG_XEN_UNPOPULATED_ALLOC +extern unsigned long xen_unpopulated_pages; int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages); void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages); #include int arch_xen_unpopulated_init(struct resource **res); #else +#define xen_unpopulated_pages 0UL #include static inline int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages) diff --git a/io_uring/cancel.h b/io_uring/cancel.h index 43e9bb74e9d19a..eaa4069e258c9b 100644 --- a/io_uring/cancel.h +++ b/io_uring/cancel.h @@ -6,10 +6,8 @@ struct io_cancel_data { struct io_ring_ctx *ctx; - union { - u64 data; - struct file *file; - }; + u64 data; + struct file *file; u8 opcode; u32 flags; int seq; diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index 294c75a8a3bdbc..3585ad8308504a 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -65,7 +65,7 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) unsigned int cq_head = READ_ONCE(r->cq.head); unsigned int cq_tail = READ_ONCE(r->cq.tail); unsigned int sq_shift = 0; - unsigned int sq_entries; + unsigned int cq_entries, sq_entries; int sq_pid = -1, sq_cpu = -1; u64 sq_total_time = 0, sq_work_time = 0; unsigned int i; @@ -119,9 +119,11 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) } } seq_printf(m, "\n"); + cond_resched(); } seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head); - while (cq_head < cq_tail) { + cq_entries = min(cq_tail - cq_head, ctx->cq_entries); + for (i = 0; i < cq_entries; i++) { struct io_uring_cqe *cqe; bool cqe32 = false; @@ -136,8 +138,11 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) cqe->big_cqe[0], cqe->big_cqe[1]); seq_printf(m, "\n"); cq_head++; - if (cqe32) + if (cqe32) { cq_head++; + i++; + } + cond_resched(); } if (ctx->flags & IORING_SETUP_SQPOLL) { diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 1d03b2fc4b2594..49a9c914b4e97d 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -34,6 +34,7 @@ enum { enum { IO_WQ_BIT_EXIT = 0, /* wq exiting */ + IO_WQ_BIT_EXIT_ON_IDLE = 1, /* allow all workers to exit on idle */ }; enum { @@ -598,9 +599,9 @@ static void io_worker_handle_work(struct io_wq_acct *acct, __releases(&acct->lock) { struct io_wq *wq = worker->wq; - bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state); do { + bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state); struct io_wq_work *work; /* @@ -706,9 +707,13 @@ static int io_wq_worker(void *data) raw_spin_lock(&acct->workers_lock); /* * Last sleep timed out. Exit if we're not the last worker, - * or if someone modified our affinity. + * or if someone modified our affinity. If wq is marked + * idle-exit, drop the worker as well. This is used to avoid + * keeping io-wq workers around for tasks that no longer have + * any active io_uring instances. */ - if (last_timeout && (exit_mask || acct->nr_workers > 1)) { + if ((last_timeout && (exit_mask || acct->nr_workers > 1)) || + test_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state)) { acct->nr_workers--; raw_spin_unlock(&acct->workers_lock); __set_current_state(TASK_RUNNING); @@ -951,11 +956,11 @@ static bool io_wq_for_each_worker(struct io_wq *wq, void *data) { for (int i = 0; i < IO_WQ_ACCT_NR; i++) { - if (!io_acct_for_each_worker(&wq->acct[i], func, data)) - return false; + if (io_acct_for_each_worker(&wq->acct[i], func, data)) + return true; } - return true; + return false; } static bool io_wq_worker_wake(struct io_worker *worker, void *data) @@ -965,6 +970,24 @@ static bool io_wq_worker_wake(struct io_worker *worker, void *data) return false; } +void io_wq_set_exit_on_idle(struct io_wq *wq, bool enable) +{ + if (!wq->task) + return; + + if (!enable) { + clear_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state); + return; + } + + if (test_and_set_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state)) + return; + + rcu_read_lock(); + io_wq_for_each_worker(wq, io_wq_worker_wake, NULL); + rcu_read_unlock(); +} + static void io_run_cancel(struct io_wq_work *work, struct io_wq *wq) { do { diff --git a/io_uring/io-wq.h b/io_uring/io-wq.h index 774abab54732ef..94b14742b70328 100644 --- a/io_uring/io-wq.h +++ b/io_uring/io-wq.h @@ -41,6 +41,7 @@ struct io_wq_data { struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data); void io_wq_exit_start(struct io_wq *wq); void io_wq_put_and_exit(struct io_wq *wq); +void io_wq_set_exit_on_idle(struct io_wq *wq, bool enable); void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); void io_wq_hash_work(struct io_wq_work *work, void *val); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 02339b74ba8d4e..65af47b9135b84 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -148,7 +148,7 @@ static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, static void io_queue_sqe(struct io_kiocb *req, unsigned int extra_flags); static void __io_req_caches_free(struct io_ring_ctx *ctx); -static __read_mostly DEFINE_STATIC_KEY_FALSE(io_key_has_sqarray); +static __read_mostly DEFINE_STATIC_KEY_DEFERRED_FALSE(io_key_has_sqarray, HZ); struct kmem_cache *req_cachep; static struct workqueue_struct *iou_wq __ro_after_init; @@ -897,7 +897,7 @@ static __cold bool io_cqe_overflow_locked(struct io_ring_ctx *ctx, { struct io_overflow_cqe *ocqe; - ocqe = io_alloc_ocqe(ctx, cqe, big_cqe, GFP_ATOMIC); + ocqe = io_alloc_ocqe(ctx, cqe, big_cqe, GFP_NOWAIT); return io_cqring_add_overflow(ctx, ocqe); } @@ -2390,7 +2390,7 @@ static bool io_get_sqe(struct io_ring_ctx *ctx, const struct io_uring_sqe **sqe) unsigned mask = ctx->sq_entries - 1; unsigned head = ctx->cached_sq_head++ & mask; - if (static_branch_unlikely(&io_key_has_sqarray) && + if (static_branch_unlikely(&io_key_has_sqarray.key) && (!(ctx->flags & IORING_SETUP_NO_SQARRAY))) { head = READ_ONCE(ctx->sq_array[head]); if (unlikely(head >= ctx->sq_entries)) { @@ -2551,6 +2551,9 @@ static enum hrtimer_restart io_cqring_min_timer_wakeup(struct hrtimer *timer) goto out_wake; } + /* any generated CQE posted past this time should wake us up */ + iowq->cq_tail = iowq->cq_min_tail; + hrtimer_update_function(&iowq->t, io_cqring_timer_wakeup); hrtimer_set_expires(timer, iowq->timeout); return HRTIMER_RESTART; @@ -2866,7 +2869,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_rings_free(ctx); if (!(ctx->flags & IORING_SETUP_NO_SQARRAY)) - static_branch_dec(&io_key_has_sqarray); + static_branch_slow_dec_deferred(&io_key_has_sqarray); percpu_ref_exit(&ctx->refs); free_uid(ctx->user); @@ -3014,12 +3017,12 @@ static __cold void io_ring_exit_work(struct work_struct *work) mutex_unlock(&ctx->uring_lock); } - if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) - io_move_task_work_from_local(ctx); - /* The SQPOLL thread never reaches this path */ - while (io_uring_try_cancel_requests(ctx, NULL, true, false)) + do { + if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) + io_move_task_work_from_local(ctx); cond_resched(); + } while (io_uring_try_cancel_requests(ctx, NULL, true, false)); if (ctx->sq_data) { struct io_sq_data *sqd = ctx->sq_data; @@ -3487,7 +3490,11 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, ctx = file->private_data; ret = -EBADFD; - if (unlikely(ctx->flags & IORING_SETUP_R_DISABLED)) + /* + * Keep IORING_SETUP_R_DISABLED check before submitter_task load + * in io_uring_add_tctx_node() -> __io_uring_add_tctx_node_from_submit() + */ + if (unlikely(smp_load_acquire(&ctx->flags) & IORING_SETUP_R_DISABLED)) goto out; /* @@ -3623,10 +3630,6 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, if (!(ctx->flags & IORING_SETUP_NO_SQARRAY)) ctx->sq_array = (u32 *)((char *)rings + sq_array_offset); - rings->sq_ring_mask = p->sq_entries - 1; - rings->cq_ring_mask = p->cq_entries - 1; - rings->sq_ring_entries = p->sq_entries; - rings->cq_ring_entries = p->cq_entries; if (p->flags & IORING_SETUP_SQE128) size = array_size(2 * sizeof(struct io_uring_sqe), p->sq_entries); @@ -3649,6 +3652,12 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, return ret; } ctx->sq_sqes = io_region_get_ptr(&ctx->sq_region); + + memset(rings, 0, sizeof(*rings)); + WRITE_ONCE(rings->sq_ring_mask, ctx->sq_entries - 1); + WRITE_ONCE(rings->cq_ring_mask, ctx->cq_entries - 1); + WRITE_ONCE(rings->sq_ring_entries, ctx->sq_entries); + WRITE_ONCE(rings->cq_ring_entries, ctx->cq_entries); return 0; } @@ -3808,7 +3817,7 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, ctx->clock_offset = 0; if (!(ctx->flags & IORING_SETUP_NO_SQARRAY)) - static_branch_inc(&io_key_has_sqarray); + static_branch_deferred_inc(&io_key_has_sqarray); if ((ctx->flags & IORING_SETUP_DEFER_TASKRUN) && !(ctx->flags & IORING_SETUP_IOPOLL) && diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index a727e020fe036f..308ef71bcb286e 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -44,7 +44,7 @@ static bool io_kbuf_inc_commit(struct io_buffer_list *bl, int len) buf_len -= this_len; /* Stop looping for invalid buffer length of 0 */ if (buf_len || !this_len) { - buf->addr += this_len; + buf->addr = READ_ONCE(buf->addr) + this_len; buf->len = buf_len; return false; } @@ -198,9 +198,9 @@ static struct io_br_sel io_ring_buffer_select(struct io_kiocb *req, size_t *len, if (*len == 0 || *len > buf_len) *len = buf_len; req->flags |= REQ_F_BUFFER_RING | REQ_F_BUFFERS_COMMIT; - req->buf_index = buf->bid; + req->buf_index = READ_ONCE(buf->bid); sel.buf_list = bl; - sel.addr = u64_to_user_ptr(buf->addr); + sel.addr = u64_to_user_ptr(READ_ONCE(buf->addr)); if (io_should_commit(req, issue_flags)) { io_kbuf_commit(req, sel.buf_list, *len, 1); @@ -280,7 +280,7 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, if (!arg->max_len) arg->max_len = INT_MAX; - req->buf_index = buf->bid; + req->buf_index = READ_ONCE(buf->bid); do { u32 len = READ_ONCE(buf->len); @@ -295,7 +295,7 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, } } - iov->iov_base = u64_to_user_ptr(buf->addr); + iov->iov_base = u64_to_user_ptr(READ_ONCE(buf->addr)); iov->iov_len = len; iov++; @@ -669,8 +669,9 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) bl->buf_ring = br; if (reg.flags & IOU_PBUF_RING_INC) bl->flags |= IOBL_INC; - io_buffer_add_list(ctx, bl, reg.bgid); - return 0; + ret = io_buffer_add_list(ctx, bl, reg.bgid); + if (!ret) + return 0; fail: io_free_region(ctx, &bl->region); kfree(bl); diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 5e5b94236d7204..bce74a8b64c6eb 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -124,7 +124,11 @@ static int __io_msg_ring_data(struct io_ring_ctx *target_ctx, return -EINVAL; if (!(msg->flags & IORING_MSG_RING_FLAGS_PASS) && msg->dst_fd) return -EINVAL; - if (target_ctx->flags & IORING_SETUP_R_DISABLED) + /* + * Keep IORING_SETUP_R_DISABLED check before submitter_task load + * in io_msg_data_remote() -> io_msg_remote_post() + */ + if (smp_load_acquire(&target_ctx->flags) & IORING_SETUP_R_DISABLED) return -EBADFD; if (io_msg_need_remote(target_ctx)) @@ -244,7 +248,11 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) return -EINVAL; if (target_ctx == ctx) return -EINVAL; - if (target_ctx->flags & IORING_SETUP_R_DISABLED) + /* + * Keep IORING_SETUP_R_DISABLED check before submitter_task load + * in io_msg_fd_remote() + */ + if (smp_load_acquire(&target_ctx->flags) & IORING_SETUP_R_DISABLED) return -EBADFD; if (!msg->src_file) { int ret = io_msg_grab_file(req, issue_flags); diff --git a/io_uring/openclose.c b/io_uring/openclose.c index bfeb91b31bba51..15dde9bd6ff670 100644 --- a/io_uring/openclose.c +++ b/io_uring/openclose.c @@ -73,13 +73,13 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe open->filename = NULL; return ret; } + req->flags |= REQ_F_NEED_CLEANUP; open->file_slot = READ_ONCE(sqe->file_index); if (open->file_slot && (open->how.flags & O_CLOEXEC)) return -EINVAL; open->nofile = rlimit(RLIMIT_NOFILE); - req->flags |= REQ_F_NEED_CLEANUP; if (io_openat_force_async(open)) req->flags |= REQ_F_FORCE_ASYNC; return 0; diff --git a/io_uring/poll.c b/io_uring/poll.c index b9681d0f9f1314..0d5bb90d47433b 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -936,12 +936,17 @@ int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags) ret2 = io_poll_add(preq, issue_flags & ~IO_URING_F_UNLOCKED); /* successfully updated, don't complete poll request */ - if (!ret2 || ret2 == -EIOCBQUEUED) + if (ret2 == IOU_ISSUE_SKIP_COMPLETE) goto out; + /* request completed as part of the update, complete it */ + else if (ret2 == IOU_COMPLETE) + goto complete; } - req_set_fail(preq); io_req_set_res(preq, -ECANCELED, 0); +complete: + if (preq->cqe.res < 0) + req_set_fail(preq); preq->io_task_work.func = io_req_task_complete; io_req_task_work_add(preq); out: diff --git a/io_uring/register.c b/io_uring/register.c index d189b266b8ccec..db53e664348d74 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -193,7 +193,8 @@ static int io_register_enable_rings(struct io_ring_ctx *ctx) if (ctx->restrictions.registered) ctx->restricted = 1; - ctx->flags &= ~IORING_SETUP_R_DISABLED; + /* Keep submitter_task store before clearing IORING_SETUP_R_DISABLED */ + smp_store_release(&ctx->flags, ctx->flags & ~IORING_SETUP_R_DISABLED); if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait)) wake_up(&ctx->sq_data->wait); return 0; diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 0010c499249060..44442bf4827e47 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -1057,6 +1057,7 @@ static int io_import_kbuf(int ddir, struct iov_iter *iter, if (count < imu->len) { const struct bio_vec *bvec = iter->bvec; + len += iter->iov_offset; while (len > bvec->bv_len) { len -= bvec->bv_len; bvec++; @@ -1184,12 +1185,16 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx return -EBUSY; nbufs = src_ctx->buf_table.nr; + if (!nbufs) + return -ENXIO; if (!arg->nr) arg->nr = nbufs; else if (arg->nr > nbufs) return -EINVAL; else if (arg->nr > IORING_MAX_REG_BUFFERS) return -EINVAL; + if (check_add_overflow(arg->nr, arg->src_off, &off) || off > nbufs) + return -EOVERFLOW; if (check_add_overflow(arg->nr, arg->dst_off, &nbufs)) return -EOVERFLOW; if (nbufs > IORING_MAX_REG_BUFFERS) @@ -1199,7 +1204,7 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx if (ret) return ret; - /* Fill entries in data from dst that won't overlap with src */ + /* Copy original dst nodes from before the cloned range */ for (i = 0; i < min(arg->dst_off, ctx->buf_table.nr); i++) { struct io_rsrc_node *src_node = ctx->buf_table.nodes[i]; @@ -1209,21 +1214,6 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx } } - ret = -ENXIO; - nbufs = src_ctx->buf_table.nr; - if (!nbufs) - goto out_free; - ret = -EINVAL; - if (!arg->nr) - arg->nr = nbufs; - else if (arg->nr > nbufs) - goto out_free; - ret = -EOVERFLOW; - if (check_add_overflow(arg->nr, arg->src_off, &off)) - goto out_free; - if (off > nbufs) - goto out_free; - off = arg->dst_off; i = arg->src_off; nr = arg->nr; @@ -1236,8 +1226,8 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx } else { dst_node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER); if (!dst_node) { - ret = -ENOMEM; - goto out_free; + io_rsrc_data_free(ctx, &data); + return -ENOMEM; } refcount_inc(&src_node->buf->refs); @@ -1247,6 +1237,16 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx i++; } + /* Copy original dst nodes from after the cloned range */ + for (i = nbufs; i < ctx->buf_table.nr; i++) { + struct io_rsrc_node *node = ctx->buf_table.nodes[i]; + + if (node) { + data.nodes[i] = node; + node->refs++; + } + } + /* * If asked for replace, put the old table. data->nodes[] holds both * old and new nodes at this point. @@ -1263,10 +1263,6 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx WARN_ON_ONCE(ctx->buf_table.nr); ctx->buf_table = data; return 0; - -out_free: - io_rsrc_data_free(ctx, &data); - return ret; } /* diff --git a/io_uring/rw.c b/io_uring/rw.c index abe68ba9c9dc85..d7388a4a3ea5e0 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -144,19 +144,22 @@ static inline int io_import_rw_buffer(int rw, struct io_kiocb *req, return 0; } -static void io_rw_recycle(struct io_kiocb *req, unsigned int issue_flags) +static bool io_rw_recycle(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_rw *rw = req->async_data; if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) - return; + return false; io_alloc_cache_vec_kasan(&rw->vec); if (rw->vec.nr > IO_VEC_CACHE_SOFT_CAP) io_vec_free(&rw->vec); - if (io_alloc_cache_put(&req->ctx->rw_cache, rw)) + if (io_alloc_cache_put(&req->ctx->rw_cache, rw)) { io_req_async_data_clear(req, 0); + return true; + } + return false; } static void io_req_rw_cleanup(struct io_kiocb *req, unsigned int issue_flags) @@ -190,7 +193,11 @@ static void io_req_rw_cleanup(struct io_kiocb *req, unsigned int issue_flags) */ if (!(req->flags & (REQ_F_REISSUE | REQ_F_REFCOUNT))) { req->flags &= ~REQ_F_NEED_CLEANUP; - io_rw_recycle(req, issue_flags); + if (!io_rw_recycle(req, issue_flags)) { + struct io_async_rw *rw = req->async_data; + + io_vec_free(&rw->vec); + } } } diff --git a/io_uring/sync.c b/io_uring/sync.c index cea2d381ffd2a4..ab7fa1cd7dd639 100644 --- a/io_uring/sync.c +++ b/io_uring/sync.c @@ -62,6 +62,8 @@ int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EINVAL; sync->off = READ_ONCE(sqe->off); + if (sync->off < 0) + return -EINVAL; sync->len = READ_ONCE(sqe->len); req->flags |= REQ_F_FORCE_ASYNC; return 0; diff --git a/io_uring/tctx.c b/io_uring/tctx.c index 5b66755579c08f..03c278aa58120f 100644 --- a/io_uring/tctx.c +++ b/io_uring/tctx.c @@ -122,6 +122,14 @@ int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) return ret; } } + + /* + * Re-activate io-wq keepalive on any new io_uring usage. The wq may have + * been marked for idle-exit when the task temporarily had no active + * io_uring instances. + */ + if (tctx->io_wq) + io_wq_set_exit_on_idle(tctx->io_wq, false); if (!xa_load(&tctx->xa, (unsigned long)ctx)) { node = kmalloc(sizeof(*node), GFP_KERNEL); if (!node) @@ -183,6 +191,9 @@ __cold void io_uring_del_tctx_node(unsigned long index) if (tctx->last == node->ctx) tctx->last = NULL; kfree(node); + + if (xa_empty(&tctx->xa) && tctx->io_wq) + io_wq_set_exit_on_idle(tctx->io_wq, true); } __cold void io_uring_clean_tctx(struct io_uring_task *tctx) diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index b1b723222cdb81..03396769c775dc 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -196,6 +196,7 @@ static int io_import_umem(struct io_zcrx_ifq *ifq, GFP_KERNEL_ACCOUNT); if (ret) { unpin_user_pages(pages, nr_pages); + kvfree(pages); return ret; } @@ -599,29 +600,30 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx, if (ret) goto err; - ifq->netdev = netdev_get_by_index(current->nsproxy->net_ns, reg.if_idx, - &ifq->netdev_tracker, GFP_KERNEL); + ifq->netdev = netdev_get_by_index_lock(current->nsproxy->net_ns, reg.if_idx); if (!ifq->netdev) { ret = -ENODEV; goto err; } + netdev_hold(ifq->netdev, &ifq->netdev_tracker, GFP_KERNEL); ifq->dev = netdev_queue_get_dma_dev(ifq->netdev, reg.if_rxq); if (!ifq->dev) { ret = -EOPNOTSUPP; - goto err; + goto netdev_put_unlock; } get_device(ifq->dev); ret = io_zcrx_create_area(ifq, &area); if (ret) - goto err; + goto netdev_put_unlock; mp_param.mp_ops = &io_uring_pp_zc_ops; mp_param.mp_priv = ifq; - ret = net_mp_open_rxq(ifq->netdev, reg.if_rxq, &mp_param); + ret = __net_mp_open_rxq(ifq->netdev, reg.if_rxq, &mp_param, NULL); if (ret) - goto err; + goto netdev_put_unlock; + netdev_unlock(ifq->netdev); ifq->if_rxq = reg.if_rxq; reg.zcrx_id = id; @@ -640,6 +642,9 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx, goto err; } return 0; +netdev_put_unlock: + netdev_put(ifq->netdev, &ifq->netdev_tracker); + netdev_unlock(ifq->netdev); err: scoped_guard(mutex, &ctx->mmap_lock) xa_erase(&ctx->zcrx_ctxs, id); diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 15b17e86e198cf..9b087ebeb643b7 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -214,7 +214,7 @@ static int ipc_permissions(struct ctl_table_header *head, const struct ctl_table if (((table->data == &ns->ids[IPC_SEM_IDS].next_id) || (table->data == &ns->ids[IPC_MSG_IDS].next_id) || (table->data == &ns->ids[IPC_SHM_IDS].next_id)) && - checkpoint_restore_ns_capable(ns->user_ns)) + checkpoint_restore_ns_capable_noaudit(ns->user_ns)) mode = 0666; else #endif diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index d595fe512498cc..c2278f392e9320 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -713,8 +713,8 @@ static struct bpf_ksym *bpf_ksym_find(unsigned long addr) return n ? container_of(n, struct bpf_ksym, tnode) : NULL; } -int __bpf_address_lookup(unsigned long addr, unsigned long *size, - unsigned long *off, char *sym) +int bpf_address_lookup(unsigned long addr, unsigned long *size, + unsigned long *off, char *sym) { struct bpf_ksym *ksym; int ret = 0; diff --git a/kernel/bpf/dmabuf_iter.c b/kernel/bpf/dmabuf_iter.c index 4dd7ef7c145ca7..cd500248abd959 100644 --- a/kernel/bpf/dmabuf_iter.c +++ b/kernel/bpf/dmabuf_iter.c @@ -6,10 +6,33 @@ #include #include +struct dmabuf_iter_priv { + /* + * If this pointer is non-NULL, the buffer's refcount is elevated to + * prevent destruction between stop/start. If reading is not resumed and + * start is never called again, then dmabuf_iter_seq_fini drops the + * reference when the iterator is released. + */ + struct dma_buf *dmabuf; +}; + static void *dmabuf_iter_seq_start(struct seq_file *seq, loff_t *pos) { - if (*pos) - return NULL; + struct dmabuf_iter_priv *p = seq->private; + + if (*pos) { + struct dma_buf *dmabuf = p->dmabuf; + + if (!dmabuf) + return NULL; + + /* + * Always resume from where we stopped, regardless of the value + * of pos. + */ + p->dmabuf = NULL; + return dmabuf; + } return dma_buf_iter_begin(); } @@ -54,8 +77,11 @@ static void dmabuf_iter_seq_stop(struct seq_file *seq, void *v) { struct dma_buf *dmabuf = v; - if (dmabuf) - dma_buf_put(dmabuf); + if (dmabuf) { + struct dmabuf_iter_priv *p = seq->private; + + p->dmabuf = dmabuf; + } } static const struct seq_operations dmabuf_iter_seq_ops = { @@ -71,11 +97,27 @@ static void bpf_iter_dmabuf_show_fdinfo(const struct bpf_iter_aux_info *aux, seq_puts(seq, "dmabuf iter\n"); } +static int dmabuf_iter_seq_init(void *priv, struct bpf_iter_aux_info *aux) +{ + struct dmabuf_iter_priv *p = (struct dmabuf_iter_priv *)priv; + + p->dmabuf = NULL; + return 0; +} + +static void dmabuf_iter_seq_fini(void *priv) +{ + struct dmabuf_iter_priv *p = (struct dmabuf_iter_priv *)priv; + + if (p->dmabuf) + dma_buf_put(p->dmabuf); +} + static const struct bpf_iter_seq_info dmabuf_iter_seq_info = { .seq_ops = &dmabuf_iter_seq_ops, - .init_seq_private = NULL, - .fini_seq_private = NULL, - .seq_priv_size = 0, + .init_seq_private = dmabuf_iter_seq_init, + .fini_seq_private = dmabuf_iter_seq_fini, + .seq_priv_size = sizeof(struct dmabuf_iter_priv), }; static struct bpf_iter_reg bpf_dmabuf_reg_info = { diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index c2fcd0cd51e51b..e7721f0776c722 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -947,15 +947,21 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, void *value, bool onallcpus) { + void *ptr; + if (!onallcpus) { /* copy true value_size bytes */ - copy_map_value(&htab->map, this_cpu_ptr(pptr), value); + ptr = this_cpu_ptr(pptr); + copy_map_value(&htab->map, ptr, value); + bpf_obj_free_fields(htab->map.record, ptr); } else { u32 size = round_up(htab->map.value_size, 8); int off = 0, cpu; for_each_possible_cpu(cpu) { - copy_map_value_long(&htab->map, per_cpu_ptr(pptr, cpu), value + off); + ptr = per_cpu_ptr(pptr, cpu); + copy_map_value_long(&htab->map, ptr, value + off); + bpf_obj_free_fields(htab->map.record, ptr); off += size; } } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index e4007fea49091c..68da6dcfb4bb7c 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -777,9 +777,11 @@ int bpf_try_get_buffers(struct bpf_bprintf_buffers **bufs) { int nest_level; + preempt_disable(); nest_level = this_cpu_inc_return(bpf_bprintf_nest_level); if (WARN_ON_ONCE(nest_level > MAX_BPRINTF_NEST_LEVEL)) { this_cpu_dec(bpf_bprintf_nest_level); + preempt_enable(); return -EBUSY; } *bufs = this_cpu_ptr(&bpf_bprintf_bufs[nest_level - 1]); @@ -792,6 +794,7 @@ void bpf_put_buffers(void) if (WARN_ON_ONCE(this_cpu_read(bpf_bprintf_nest_level) == 0)) return; this_cpu_dec(bpf_bprintf_nest_level); + preempt_enable(); } void bpf_bprintf_cleanup(struct bpf_bprintf_data *data) @@ -1077,7 +1080,7 @@ const struct bpf_func_proto bpf_snprintf_proto = { .func = bpf_snprintf, .gpl_only = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM_OR_NULL, + .arg1_type = ARG_PTR_TO_MEM_OR_NULL | MEM_WRITE, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_CONST_STR, .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, diff --git a/kernel/bpf/rqspinlock.c b/kernel/bpf/rqspinlock.c index a00561b1d3e515..c0c93a0f5af636 100644 --- a/kernel/bpf/rqspinlock.c +++ b/kernel/bpf/rqspinlock.c @@ -89,15 +89,14 @@ struct rqspinlock_timeout { DEFINE_PER_CPU_ALIGNED(struct rqspinlock_held, rqspinlock_held_locks); EXPORT_SYMBOL_GPL(rqspinlock_held_locks); -static bool is_lock_released(rqspinlock_t *lock, u32 mask, struct rqspinlock_timeout *ts) +static bool is_lock_released(rqspinlock_t *lock, u32 mask) { if (!(atomic_read_acquire(&lock->val) & (mask))) return true; return false; } -static noinline int check_deadlock_AA(rqspinlock_t *lock, u32 mask, - struct rqspinlock_timeout *ts) +static noinline int check_deadlock_AA(rqspinlock_t *lock) { struct rqspinlock_held *rqh = this_cpu_ptr(&rqspinlock_held_locks); int cnt = min(RES_NR_HELD, rqh->cnt); @@ -118,8 +117,7 @@ static noinline int check_deadlock_AA(rqspinlock_t *lock, u32 mask, * more locks, which reduce to ABBA). This is not exhaustive, and we rely on * timeouts as the final line of defense. */ -static noinline int check_deadlock_ABBA(rqspinlock_t *lock, u32 mask, - struct rqspinlock_timeout *ts) +static noinline int check_deadlock_ABBA(rqspinlock_t *lock, u32 mask) { struct rqspinlock_held *rqh = this_cpu_ptr(&rqspinlock_held_locks); int rqh_cnt = min(RES_NR_HELD, rqh->cnt); @@ -142,7 +140,7 @@ static noinline int check_deadlock_ABBA(rqspinlock_t *lock, u32 mask, * Let's ensure to break out of this loop if the lock is available for * us to potentially acquire. */ - if (is_lock_released(lock, mask, ts)) + if (is_lock_released(lock, mask)) return 0; /* @@ -198,15 +196,14 @@ static noinline int check_deadlock_ABBA(rqspinlock_t *lock, u32 mask, return 0; } -static noinline int check_deadlock(rqspinlock_t *lock, u32 mask, - struct rqspinlock_timeout *ts) +static noinline int check_deadlock(rqspinlock_t *lock, u32 mask) { int ret; - ret = check_deadlock_AA(lock, mask, ts); + ret = check_deadlock_AA(lock); if (ret) return ret; - ret = check_deadlock_ABBA(lock, mask, ts); + ret = check_deadlock_ABBA(lock, mask); if (ret) return ret; @@ -234,7 +231,7 @@ static noinline int check_timeout(rqspinlock_t *lock, u32 mask, */ if (prev + NSEC_PER_MSEC < time) { ts->cur = time; - return check_deadlock(lock, mask, ts); + return check_deadlock(lock, mask); } return 0; @@ -278,7 +275,12 @@ int __lockfunc resilient_tas_spin_lock(rqspinlock_t *lock) int val, ret = 0; RES_INIT_TIMEOUT(ts); - grab_held_lock_entry(lock); + /* + * We are either called directly from res_spin_lock after grabbing the + * deadlock detection entry when queued spinlocks are disabled, or from + * resilient_queued_spin_lock_slowpath after grabbing the deadlock + * detection entry. No need to obtain it here. + */ /* * Since the waiting loop's time is dependent on the amount of @@ -400,10 +402,7 @@ int __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val) goto queue; } - /* - * Grab an entry in the held locks array, to enable deadlock detection. - */ - grab_held_lock_entry(lock); + /* Deadlock detection entry already held after failing fast path. */ /* * We're pending, wait for the owner to go away. @@ -451,11 +450,7 @@ int __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val) */ queue: lockevent_inc(lock_slowpath); - /* - * Grab deadlock detection entry for the queue path. - */ - grab_held_lock_entry(lock); - + /* Deadlock detection entry already held after failing fast path. */ node = this_cpu_ptr(&rqnodes[0].mcs); idx = node->count++; tail = encode_tail(smp_processor_id(), idx); @@ -471,7 +466,7 @@ int __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val) * any MCS node. This is not the most elegant solution, but is * simple enough. */ - if (unlikely(idx >= _Q_MAX_NODES || in_nmi())) { + if (unlikely(idx >= _Q_MAX_NODES || (in_nmi() && idx > 0))) { lockevent_inc(lock_no_node); RES_RESET_TIMEOUT(ts, RES_DEF_TIMEOUT); while (!queued_spin_trylock(lock)) { diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 4d53cdd1374cf7..2365541c81dd14 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -42,6 +42,28 @@ static inline int stack_map_data_size(struct bpf_map *map) sizeof(struct bpf_stack_build_id) : sizeof(u64); } +/** + * stack_map_calculate_max_depth - Calculate maximum allowed stack trace depth + * @size: Size of the buffer/map value in bytes + * @elem_size: Size of each stack trace element + * @flags: BPF stack trace flags (BPF_F_USER_STACK, BPF_F_USER_BUILD_ID, ...) + * + * Return: Maximum number of stack trace entries that can be safely stored + */ +static u32 stack_map_calculate_max_depth(u32 size, u32 elem_size, u64 flags) +{ + u32 skip = flags & BPF_F_SKIP_FIELD_MASK; + u32 max_depth; + u32 curr_sysctl_max_stack = READ_ONCE(sysctl_perf_event_max_stack); + + max_depth = size / elem_size; + max_depth += skip; + if (max_depth > curr_sysctl_max_stack) + return curr_sysctl_max_stack; + + return max_depth; +} + static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) { u64 elem_size = sizeof(struct stack_map_bucket) + @@ -229,8 +251,8 @@ static long __bpf_get_stackid(struct bpf_map *map, { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); struct stack_map_bucket *bucket, *new_bucket, *old_bucket; + u32 hash, id, trace_nr, trace_len, i, max_depth; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; - u32 hash, id, trace_nr, trace_len, i; bool user = flags & BPF_F_USER_STACK; u64 *ips; bool hash_matches; @@ -239,7 +261,8 @@ static long __bpf_get_stackid(struct bpf_map *map, /* skipping more than usable stack trace */ return -EFAULT; - trace_nr = trace->nr - skip; + max_depth = stack_map_calculate_max_depth(map->value_size, stack_map_data_size(map), flags); + trace_nr = min_t(u32, trace->nr - skip, max_depth - skip); trace_len = trace_nr * sizeof(u64); ips = trace->ip + skip; hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); @@ -300,20 +323,17 @@ static long __bpf_get_stackid(struct bpf_map *map, BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, u64, flags) { - u32 max_depth = map->value_size / stack_map_data_size(map); - u32 skip = flags & BPF_F_SKIP_FIELD_MASK; + u32 elem_size = stack_map_data_size(map); bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; bool kernel = !user; + u32 max_depth; if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) return -EINVAL; - max_depth += skip; - if (max_depth > sysctl_perf_event_max_stack) - max_depth = sysctl_perf_event_max_stack; - + max_depth = stack_map_calculate_max_depth(map->value_size, elem_size, flags); trace = get_perf_callchain(regs, kernel, user, max_depth, false, false); @@ -371,15 +391,11 @@ BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx, return -EFAULT; nr_kernel = count_kernel_ip(trace); + __u64 nr = trace->nr; /* save original */ if (kernel) { - __u64 nr = trace->nr; - trace->nr = nr_kernel; ret = __bpf_get_stackid(map, trace, flags); - - /* restore nr */ - trace->nr = nr; } else { /* user */ u64 skip = flags & BPF_F_SKIP_FIELD_MASK; @@ -390,6 +406,10 @@ BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx, flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip; ret = __bpf_get_stackid(map, trace, flags); } + + /* restore nr */ + trace->nr = nr; + return ret; } @@ -406,7 +426,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, struct perf_callchain_entry *trace_in, void *buf, u32 size, u64 flags, bool may_fault) { - u32 trace_nr, copy_len, elem_size, num_elem, max_depth; + u32 trace_nr, copy_len, elem_size, max_depth; bool user_build_id = flags & BPF_F_USER_BUILD_ID; bool crosstask = task && task != current; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; @@ -438,21 +458,20 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, goto clear; } - num_elem = size / elem_size; - max_depth = num_elem + skip; - if (sysctl_perf_event_max_stack < max_depth) - max_depth = sysctl_perf_event_max_stack; + max_depth = stack_map_calculate_max_depth(size, elem_size, flags); if (may_fault) rcu_read_lock(); /* need RCU for perf's callchain below */ - if (trace_in) + if (trace_in) { trace = trace_in; - else if (kernel && task) + trace->nr = min_t(u32, trace->nr, max_depth); + } else if (kernel && task) { trace = get_callchain_entry_for_task(task, max_depth); - else + } else { trace = get_perf_callchain(regs, kernel, user, max_depth, crosstask, false); + } if (unlikely(!trace) || trace->nr < skip) { if (may_fault) @@ -461,7 +480,6 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, } trace_nr = trace->nr - skip; - trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem; copy_len = trace_nr * elem_size; ips = trace->ip + skip; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8a129746bd6cc7..586ece78f783ad 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1365,11 +1365,6 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token, return ret; } -static bool bpf_net_capable(void) -{ - return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); -} - #define BPF_MAP_CREATE_LAST_FIELD excl_prog_hash_size /* called via syscall */ static int map_create(union bpf_attr *attr, bpfptr_t uattr) @@ -1585,7 +1580,8 @@ static int map_create(union bpf_attr *attr, bpfptr_t uattr) goto free_map; } } else if (attr->excl_prog_hash_size) { - return -EINVAL; + err = -EINVAL; + goto free_map; } err = security_bpf_map_create(map, attr, token, uattr.is_kernel); @@ -2462,6 +2458,9 @@ void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog) struct bpf_prog_stats *stats; unsigned int flags; + if (unlikely(!prog->stats)) + return; + stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->misses); @@ -2826,6 +2825,13 @@ static int bpf_prog_verify_signature(struct bpf_prog *prog, union bpf_attr *attr void *sig; int err = 0; + /* + * Don't attempt to use kmalloc_large or vmalloc for signatures. + * Practical signature for BPF program should be below this limit. + */ + if (attr->signature_size > KMALLOC_MAX_CACHE_SIZE) + return -EINVAL; + if (system_keyring_id_check(attr->keyring_id) == 0) key = bpf_lookup_system_key(attr->keyring_id); else @@ -4550,6 +4556,8 @@ static int bpf_prog_detach(const union bpf_attr *attr) prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); + } else if (!bpf_mprog_detach_empty(ptype)) { + return -EPERM; } } else if (is_cgroup_prog_type(ptype, 0, false)) { if (attr->attach_flags || attr->relative_fd) @@ -5295,6 +5303,9 @@ static int bpf_map_get_info_by_fd(struct file *file, if (info.hash_size != SHA256_DIGEST_SIZE) return -EINVAL; + if (!READ_ONCE(map->frozen)) + return -EPERM; + err = map->ops->map_get_hash(map, SHA256_DIGEST_SIZE, map->sha); if (err != 0) return err; @@ -6392,7 +6403,7 @@ static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { .func = bpf_kallsyms_lookup_name, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index f2cb0b09709330..04104397c432ea 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -220,7 +220,9 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr) } if (tr->func.ftrace_managed) { - ftrace_set_filter_ip(tr->fops, (unsigned long)ip, 0, 1); + ret = ftrace_set_filter_ip(tr->fops, (unsigned long)ip, 0, 1); + if (ret) + return ret; ret = register_ftrace_direct(tr->fops, (long)new_addr); } else { ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fbe4bb91c564ae..c4fa2268dbbc57 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -515,6 +515,7 @@ static bool is_callback_calling_kfunc(u32 btf_id); static bool is_bpf_throw_kfunc(struct bpf_insn *insn); static bool is_bpf_wq_set_callback_impl_kfunc(u32 btf_id); +static bool is_task_work_add_kfunc(u32 func_id); static bool is_sync_callback_calling_function(enum bpf_func_id func_id) { @@ -547,6 +548,21 @@ static bool is_async_callback_calling_insn(struct bpf_insn *insn) (bpf_pseudo_kfunc_call(insn) && is_async_callback_calling_kfunc(insn->imm)); } +static bool is_async_cb_sleepable(struct bpf_verifier_env *env, struct bpf_insn *insn) +{ + /* bpf_timer callbacks are never sleepable. */ + if (bpf_helper_call(insn) && insn->imm == BPF_FUNC_timer_set_callback) + return false; + + /* bpf_wq and bpf_task_work callbacks are always sleepable. */ + if (bpf_pseudo_kfunc_call(insn) && insn->off == 0 && + (is_bpf_wq_set_callback_impl_kfunc(insn->imm) || is_task_work_add_kfunc(insn->imm))) + return true; + + verifier_bug(env, "unhandled async callback in is_async_cb_sleepable"); + return false; +} + static bool is_may_goto_insn(struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_JCOND) && insn->src_reg == BPF_MAY_GOTO; @@ -4392,6 +4408,11 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, bt_reg_mask(bt)); return -EFAULT; } + if (insn->src_reg == BPF_REG_0 && insn->imm == BPF_FUNC_tail_call + && subseq_idx - idx != 1) { + if (bt_subprog_enter(bt)) + return -EFAULT; + } } else if (opcode == BPF_EXIT) { bool r0_precise; @@ -5826,8 +5847,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, static bool in_sleepable(struct bpf_verifier_env *env) { - return env->prog->sleepable || - (env->cur_state && env->cur_state->in_sleepable); + return env->cur_state->in_sleepable; } /* The non-sleepable programs and sleepable programs with explicit bpf_rcu_read_lock() @@ -8464,6 +8484,9 @@ static int check_map_field_pointer(struct bpf_verifier_env *env, u32 regno, case BPF_TASK_WORK: field_off = map->record->task_work_off; break; + case BPF_WORKQUEUE: + field_off = map->record->wq_off; + break; default: verifier_bug(env, "unsupported BTF field type: %s\n", struct_name); return -EINVAL; @@ -8505,13 +8528,17 @@ static int process_wq_func(struct bpf_verifier_env *env, int regno, { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; struct bpf_map *map = reg->map_ptr; - u64 val = reg->var_off.value; + int err; - if (map->record->wq_off != val + reg->off) { - verbose(env, "off %lld doesn't point to 'struct bpf_wq' that is at %d\n", - val + reg->off, map->record->wq_off); - return -EINVAL; + err = check_map_field_pointer(env, regno, BPF_WORKQUEUE); + if (err) + return err; + + if (meta->map.ptr) { + verifier_bug(env, "Two map pointers in a bpf_wq helper"); + return -EFAULT; } + meta->map.uid = reg->map_uid; meta->map.ptr = map; return 0; @@ -10368,8 +10395,6 @@ typedef int (*set_callee_state_fn)(struct bpf_verifier_env *env, struct bpf_func_state *callee, int insn_idx); -static bool is_task_work_add_kfunc(u32 func_id); - static int set_callee_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx); @@ -10588,8 +10613,7 @@ static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *ins env->subprog_info[subprog].is_async_cb = true; async_cb = push_async_cb(env, env->subprog_info[subprog].start, insn_idx, subprog, - is_bpf_wq_set_callback_impl_kfunc(insn->imm) || - is_task_work_add_kfunc(insn->imm)); + is_async_cb_sleepable(env, insn)); if (!async_cb) return -EFAULT; callee = async_cb->frame[0]; @@ -10976,6 +11000,10 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) bool in_callback_fn; int err; + err = bpf_update_live_stack(env); + if (err) + return err; + callee = state->frame[state->curframe]; r0 = &callee->regs[BPF_REG_0]; if (r0->type == PTR_TO_STACK) { @@ -11428,7 +11456,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } - if (in_sleepable(env) && is_storage_get_function(func_id)) + if (is_storage_get_function(func_id)) env->insn_aux_data[insn_idx].storage_get_func_atomic = true; } @@ -11439,7 +11467,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } - if (in_sleepable(env) && is_storage_get_function(func_id)) + if (is_storage_get_function(func_id)) env->insn_aux_data[insn_idx].storage_get_func_atomic = true; } @@ -11450,10 +11478,17 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } - if (in_sleepable(env) && is_storage_get_function(func_id)) + if (is_storage_get_function(func_id)) env->insn_aux_data[insn_idx].storage_get_func_atomic = true; } + /* + * Non-sleepable contexts in sleepable programs (e.g., timer callbacks) + * are atomic and must use GFP_ATOMIC for storage_get helpers. + */ + if (!in_sleepable(env) && is_storage_get_function(func_id)) + env->insn_aux_data[insn_idx].storage_get_func_atomic = true; + meta.func_id = func_id; /* check args */ for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { @@ -11886,6 +11921,25 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn env->prog->call_get_func_ip = true; } + if (func_id == BPF_FUNC_tail_call) { + if (env->cur_state->curframe) { + struct bpf_verifier_state *branch; + + mark_reg_scratched(env, BPF_REG_0); + branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false); + if (IS_ERR(branch)) + return PTR_ERR(branch); + clear_all_pkt_pointers(env); + mark_reg_unknown(env, regs, BPF_REG_0); + err = prepare_func_exit(env, &env->insn_idx); + if (err) + return err; + env->insn_idx--; + } else { + changes_data = false; + } + } + if (changes_data) clear_all_pkt_pointers(env); return 0; @@ -16661,6 +16715,7 @@ static void sync_linked_regs(struct bpf_verifier_state *vstate, struct bpf_reg_s } else { s32 saved_subreg_def = reg->subreg_def; s32 saved_off = reg->off; + u32 saved_id = reg->id; fake_reg.type = SCALAR_VALUE; __mark_reg_known(&fake_reg, (s32)reg->off - (s32)known_reg->off); @@ -16668,10 +16723,11 @@ static void sync_linked_regs(struct bpf_verifier_state *vstate, struct bpf_reg_s /* reg = known_reg; reg += delta */ copy_register_state(reg, known_reg); /* - * Must preserve off, id and add_const flag, + * Must preserve off, id and subreg_def flag, * otherwise another sync_linked_regs() will be incorrect. */ reg->off = saved_off; + reg->id = saved_id; reg->subreg_def = saved_subreg_def; scalar32_min_max_add(reg, &fake_reg); @@ -19784,9 +19840,6 @@ static int process_bpf_exit_full(struct bpf_verifier_env *env, return PROCESS_BPF_EXIT; if (env->cur_state->curframe) { - err = bpf_update_live_stack(env); - if (err) - return err; /* exit from nested function */ err = prepare_func_exit(env, &env->insn_idx); if (err) @@ -20096,17 +20149,19 @@ static int do_check(struct bpf_verifier_env *env) * may skip a nospec patched-in after the jump. This can * currently never happen because nospec_result is only * used for the write-ops - * `*(size*)(dst_reg+off)=src_reg|imm32` which must - * never skip the following insn. Still, add a warning - * to document this in case nospec_result is used - * elsewhere in the future. + * `*(size*)(dst_reg+off)=src_reg|imm32` and helper + * calls. These must never skip the following insn + * (i.e., bpf_insn_successors()'s opcode_info.can_jump + * is false). Still, add a warning to document this in + * case nospec_result is used elsewhere in the future. * * All non-branch instructions have a single * fall-through edge. For these, nospec_result should * already work. */ - if (verifier_bug_if(BPF_CLASS(insn->code) == BPF_JMP || - BPF_CLASS(insn->code) == BPF_JMP32, env, + if (verifier_bug_if((BPF_CLASS(insn->code) == BPF_JMP || + BPF_CLASS(insn->code) == BPF_JMP32) && + BPF_OP(insn->code) != BPF_CALL, env, "speculation barrier after jump instruction may not have the desired effect")) return -EFAULT; process_bpf_exit: @@ -20164,29 +20219,29 @@ static int find_btf_percpu_datasec(struct btf *btf) } /* - * Add btf to the used_btfs array and return the index. (If the btf was - * already added, then just return the index.) Upon successful insertion - * increase btf refcnt, and, if present, also refcount the corresponding - * kernel module. + * Add btf to the env->used_btfs array. If needed, refcount the + * corresponding kernel module. To simplify caller's logic + * in case of error or if btf was added before the function + * decreases the btf refcount. */ static int __add_used_btf(struct bpf_verifier_env *env, struct btf *btf) { struct btf_mod_pair *btf_mod; + int ret = 0; int i; /* check whether we recorded this BTF (and maybe module) already */ for (i = 0; i < env->used_btf_cnt; i++) if (env->used_btfs[i].btf == btf) - return i; + goto ret_put; if (env->used_btf_cnt >= MAX_USED_BTFS) { verbose(env, "The total number of btfs per program has reached the limit of %u\n", MAX_USED_BTFS); - return -E2BIG; + ret = -E2BIG; + goto ret_put; } - btf_get(btf); - btf_mod = &env->used_btfs[env->used_btf_cnt]; btf_mod->btf = btf; btf_mod->module = NULL; @@ -20195,12 +20250,18 @@ static int __add_used_btf(struct bpf_verifier_env *env, struct btf *btf) if (btf_is_module(btf)) { btf_mod->module = btf_try_get_module(btf); if (!btf_mod->module) { - btf_put(btf); - return -ENXIO; + ret = -ENXIO; + goto ret_put; } } - return env->used_btf_cnt++; + env->used_btf_cnt++; + return 0; + +ret_put: + /* Either error or this BTF was already added */ + btf_put(btf); + return ret; } /* replace pseudo btf_id with kernel symbol address */ @@ -20297,9 +20358,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, btf_fd = insn[1].imm; if (btf_fd) { - CLASS(fd, f)(btf_fd); - - btf = __btf_get_by_fd(f); + btf = btf_get_by_fd(btf_fd); if (IS_ERR(btf)) { verbose(env, "invalid module BTF object FD specified.\n"); return -EINVAL; @@ -20309,17 +20368,17 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n"); return -EINVAL; } + btf_get(btf_vmlinux); btf = btf_vmlinux; } err = __check_pseudo_btf_id(env, insn, aux, btf); - if (err) + if (err) { + btf_put(btf); return err; + } - err = __add_used_btf(env, btf); - if (err < 0) - return err; - return 0; + return __add_used_btf(env, btf); } static bool is_tracing_prog_type(enum bpf_prog_type type) @@ -22485,8 +22544,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) } if (is_storage_get_function(insn->imm)) { - if (!in_sleepable(env) || - env->insn_aux_data[i + delta].storage_get_func_atomic) + if (env->insn_aux_data[i + delta].storage_get_func_atomic) insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_ATOMIC); else insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_KERNEL); @@ -23156,6 +23214,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) state->curframe = 0; state->speculative = false; state->branches = 1; + state->in_sleepable = env->prog->sleepable; state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL_ACCOUNT); if (!state->frame[0]) { kfree(state); @@ -24041,10 +24100,8 @@ static int add_fd_from_fd_array(struct bpf_verifier_env *env, int fd) btf = __btf_get_by_fd(f); if (!IS_ERR(btf)) { - err = __add_used_btf(env, btf); - if (err < 0) - return err; - return 0; + btf_get(btf); + return __add_used_btf(env, btf); } verbose(env, "fd %d is not pointing to valid bpf_map or btf\n", fd); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 52468d2c178a3e..1245418cc8b3bd 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -352,6 +352,15 @@ static inline bool is_in_v2_mode(void) (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE); } +static inline bool cpuset_is_populated(struct cpuset *cs) +{ + lockdep_assert_held(&cpuset_mutex); + + /* Cpusets in the process of attaching should be considered as populated */ + return cgroup_is_populated(cs->css.cgroup) || + cs->attach_in_progress; +} + /** * partition_is_populated - check if partition has tasks * @cs: partition root to be checked @@ -364,21 +373,31 @@ static inline bool is_in_v2_mode(void) static inline bool partition_is_populated(struct cpuset *cs, struct cpuset *excluded_child) { - struct cgroup_subsys_state *css; - struct cpuset *child; + struct cpuset *cp; + struct cgroup_subsys_state *pos_css; - if (cs->css.cgroup->nr_populated_csets) + /* + * We cannot call cs_is_populated(cs) directly, as + * nr_populated_domain_children may include populated + * csets from descendants that are partitions. + */ + if (cs->css.cgroup->nr_populated_csets || + cs->attach_in_progress) return true; if (!excluded_child && !cs->nr_subparts) - return cgroup_is_populated(cs->css.cgroup); + return cpuset_is_populated(cs); rcu_read_lock(); - cpuset_for_each_child(child, css, cs) { - if (child == excluded_child) + cpuset_for_each_descendant_pre(cp, pos_css, cs) { + if (cp == cs || cp == excluded_child) continue; - if (is_partition_valid(child)) + + if (is_partition_valid(cp)) { + pos_css = css_rightmost_descendant(pos_css); continue; - if (cgroup_is_populated(child->css.cgroup)) { + } + + if (cpuset_is_populated(cp)) { rcu_read_unlock(); return true; } @@ -663,7 +682,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) * be changed to have empty cpus_allowed or mems_allowed. */ ret = -ENOSPC; - if ((cgroup_is_populated(cur->css.cgroup) || cur->attach_in_progress)) { + if (cpuset_is_populated(cur)) { if (!cpumask_empty(cur->cpus_allowed) && cpumask_empty(trial->cpus_allowed)) goto out; @@ -1581,7 +1600,14 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp) bool isolcpus_updated; WARN_ON_ONCE(!is_remote_partition(cs)); - WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus)); + /* + * When a CPU is offlined, top_cpuset may end up with no available CPUs, + * which should clear subpartitions_cpus. We should not emit a warning for this + * scenario: the hierarchy is updated from top to bottom, so subpartitions_cpus + * may already be cleared when disabling the partition. + */ + WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus) && + !cpumask_empty(subpartitions_cpus)); spin_lock_irq(&callback_lock); list_del_init(&cs->remote_sibling); @@ -3908,8 +3934,9 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) if (remote || (is_partition_valid(cs) && is_partition_valid(parent))) compute_partition_effective_cpumask(cs, &new_cpus); - if (remote && cpumask_empty(&new_cpus) && - partition_is_populated(cs, NULL)) { + if (remote && (cpumask_empty(subpartitions_cpus) || + (cpumask_empty(&new_cpus) && + partition_is_populated(cs, NULL)))) { cs->prs_err = PERR_HOTPLUG; remote_partition_disable(cs, tmp); compute_effective_cpumask(&new_cpus, cs, parent); @@ -3922,9 +3949,12 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) * 1) empty effective cpus but not valid empty partition. * 2) parent is invalid or doesn't grant any cpus to child * partitions. + * 3) subpartitions_cpus is empty. */ - if (is_local_partition(cs) && (!is_partition_valid(parent) || - tasks_nocpu_error(parent, cs, &new_cpus))) + if (is_local_partition(cs) && + (!is_partition_valid(parent) || + tasks_nocpu_error(parent, cs, &new_cpus) || + cpumask_empty(subpartitions_cpus))) partcmd = partcmd_invalidate; /* * On the other hand, an invalid partition root may be transitioned diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c index e12b946278b6c6..1ea6afffa985c4 100644 --- a/kernel/cgroup/dmem.c +++ b/kernel/cgroup/dmem.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -71,7 +72,9 @@ struct dmem_cgroup_pool_state { struct rcu_head rcu; struct page_counter cnt; + struct dmem_cgroup_pool_state *parent; + refcount_t ref; bool inited; }; @@ -88,6 +91,9 @@ struct dmem_cgroup_pool_state { static DEFINE_SPINLOCK(dmemcg_lock); static LIST_HEAD(dmem_cgroup_regions); +static void dmemcg_free_region(struct kref *ref); +static void dmemcg_pool_free_rcu(struct rcu_head *rcu); + static inline struct dmemcg_state * css_to_dmemcs(struct cgroup_subsys_state *css) { @@ -104,10 +110,38 @@ static struct dmemcg_state *parent_dmemcs(struct dmemcg_state *cg) return cg->css.parent ? css_to_dmemcs(cg->css.parent) : NULL; } +static void dmemcg_pool_get(struct dmem_cgroup_pool_state *pool) +{ + refcount_inc(&pool->ref); +} + +static bool dmemcg_pool_tryget(struct dmem_cgroup_pool_state *pool) +{ + return refcount_inc_not_zero(&pool->ref); +} + +static void dmemcg_pool_put(struct dmem_cgroup_pool_state *pool) +{ + if (!refcount_dec_and_test(&pool->ref)) + return; + + call_rcu(&pool->rcu, dmemcg_pool_free_rcu); +} + +static void dmemcg_pool_free_rcu(struct rcu_head *rcu) +{ + struct dmem_cgroup_pool_state *pool = container_of(rcu, typeof(*pool), rcu); + + if (pool->parent) + dmemcg_pool_put(pool->parent); + kref_put(&pool->region->ref, dmemcg_free_region); + kfree(pool); +} + static void free_cg_pool(struct dmem_cgroup_pool_state *pool) { list_del(&pool->region_node); - kfree(pool); + dmemcg_pool_put(pool); } static void @@ -342,6 +376,12 @@ alloc_pool_single(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region page_counter_init(&pool->cnt, ppool ? &ppool->cnt : NULL, true); reset_all_resource_limits(pool); + refcount_set(&pool->ref, 1); + kref_get(®ion->ref); + if (ppool && !pool->parent) { + pool->parent = ppool; + dmemcg_pool_get(ppool); + } list_add_tail_rcu(&pool->css_node, &dmemcs->pools); list_add_tail(&pool->region_node, ®ion->pools); @@ -389,6 +429,10 @@ get_cg_pool_locked(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *regio /* Fix up parent links, mark as inited. */ pool->cnt.parent = &ppool->cnt; + if (ppool && !pool->parent) { + pool->parent = ppool; + dmemcg_pool_get(ppool); + } pool->inited = true; pool = ppool; @@ -423,7 +467,7 @@ static void dmemcg_free_region(struct kref *ref) */ void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region) { - struct list_head *entry; + struct dmem_cgroup_pool_state *pool, *next; if (!region) return; @@ -433,11 +477,10 @@ void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region) /* Remove from global region list */ list_del_rcu(®ion->region_node); - list_for_each_rcu(entry, ®ion->pools) { - struct dmem_cgroup_pool_state *pool = - container_of(entry, typeof(*pool), region_node); - + list_for_each_entry_safe(pool, next, ®ion->pools, region_node) { list_del_rcu(&pool->css_node); + list_del(&pool->region_node); + dmemcg_pool_put(pool); } /* @@ -518,8 +561,10 @@ static struct dmem_cgroup_region *dmemcg_get_region_by_name(const char *name) */ void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool) { - if (pool) + if (pool) { css_put(&pool->cs->css); + dmemcg_pool_put(pool); + } } EXPORT_SYMBOL_GPL(dmem_cgroup_pool_state_put); @@ -533,6 +578,8 @@ get_cg_pool_unlocked(struct dmemcg_state *cg, struct dmem_cgroup_region *region) pool = find_cg_pool_locked(cg, region); if (pool && !READ_ONCE(pool->inited)) pool = NULL; + if (pool && !dmemcg_pool_tryget(pool)) + pool = NULL; rcu_read_unlock(); while (!pool) { @@ -541,6 +588,8 @@ get_cg_pool_unlocked(struct dmemcg_state *cg, struct dmem_cgroup_region *region) pool = get_cg_pool_locked(cg, region, &allocpool); else pool = ERR_PTR(-ENODEV); + if (!IS_ERR(pool)) + dmemcg_pool_get(pool); spin_unlock(&dmemcg_lock); if (pool == ERR_PTR(-ENOMEM)) { @@ -576,6 +625,7 @@ void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size) page_counter_uncharge(&pool->cnt, size); css_put(&pool->cs->css); + dmemcg_pool_put(pool); } EXPORT_SYMBOL_GPL(dmem_cgroup_uncharge); @@ -627,7 +677,9 @@ int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size, if (ret_limit_pool) { *ret_limit_pool = container_of(fail, struct dmem_cgroup_pool_state, cnt); css_get(&(*ret_limit_pool)->cs->css); + dmemcg_pool_get(*ret_limit_pool); } + dmemcg_pool_put(pool); ret = -EAGAIN; goto err; } @@ -700,6 +752,9 @@ static ssize_t dmemcg_limit_write(struct kernfs_open_file *of, if (!region_name[0]) continue; + if (!options || !*options) + return -EINVAL; + rcu_read_lock(); region = dmemcg_get_region_by_name(region_name); rcu_read_unlock(); @@ -719,6 +774,7 @@ static ssize_t dmemcg_limit_write(struct kernfs_open_file *of, /* And commit */ apply(pool, new_limit); + dmemcg_pool_put(pool); out_put: kref_put(®ion->ref, dmemcg_free_region); diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c index fdbe57578e6886..db9617556dd706 100644 --- a/kernel/cgroup/namespace.c +++ b/kernel/cgroup/namespace.c @@ -30,7 +30,6 @@ static struct cgroup_namespace *alloc_cgroup_ns(void) ret = ns_common_init(new_ns); if (ret) return ERR_PTR(ret); - ns_tree_add(new_ns); return no_free_ptr(new_ns); } @@ -86,6 +85,7 @@ struct cgroup_namespace *copy_cgroup_ns(u64 flags, new_ns->ucounts = ucounts; new_ns->root_cset = cset; + ns_tree_add(new_ns); return new_ns; } diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index a198e40c799b48..150e5871e66f25 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -71,7 +71,6 @@ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu) { struct llist_head *lhead; struct css_rstat_cpu *rstatc; - struct css_rstat_cpu __percpu *rstatc_pcpu; struct llist_node *self; /* @@ -104,18 +103,22 @@ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu) /* * This function can be renentered by irqs and nmis for the same cgroup * and may try to insert the same per-cpu lnode into the llist. Note - * that llist_add() does not protect against such scenarios. + * that llist_add() does not protect against such scenarios. In addition + * this same per-cpu lnode can be modified through init_llist_node() + * from css_rstat_flush() running on a different CPU. * * To protect against such stacked contexts of irqs/nmis, we use the * fact that lnode points to itself when not on a list and then use - * this_cpu_cmpxchg() to atomically set to NULL to select the winner + * try_cmpxchg() to atomically set to NULL to select the winner * which will call llist_add(). The losers can assume the insertion is * successful and the winner will eventually add the per-cpu lnode to * the llist. + * + * Please note that we can not use this_cpu_cmpxchg() here as on some + * archs it is not safe against modifications from multiple CPUs. */ self = &rstatc->lnode; - rstatc_pcpu = css->rstat_cpu; - if (this_cpu_cmpxchg(rstatc_pcpu->lnode.next, self, NULL) != self) + if (!try_cmpxchg(&rstatc->lnode.next, &self, NULL)) return; lhead = ss_lhead_cpu(css->ss, cpu); diff --git a/kernel/cpu.c b/kernel/cpu.c index db9f6c539b28ce..15000c7abc6599 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -249,6 +249,14 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, return ret; } +/* + * The former STARTING/DYING states, ran with IRQs disabled and must not fail. + */ +static bool cpuhp_is_atomic_state(enum cpuhp_state state) +{ + return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; +} + #ifdef CONFIG_SMP static bool cpuhp_is_ap_state(enum cpuhp_state state) { @@ -271,14 +279,6 @@ static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) complete(done); } -/* - * The former STARTING/DYING states, ran with IRQs disabled and must not fail. - */ -static bool cpuhp_is_atomic_state(enum cpuhp_state state) -{ - return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; -} - /* Synchronization state management */ enum cpuhp_sync_state { SYNC_STATE_DEAD, @@ -2364,7 +2364,14 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else - ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); + if (cpuhp_is_atomic_state(state)) { + guard(irqsave)(); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); + /* STARTING/DYING must not fail! */ + WARN_ON_ONCE(ret); + } else { + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); + } #endif BUG_ON(ret && !bringup); return ret; diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c index 87bf4d41eabba9..62e60e0223cff2 100644 --- a/kernel/crash_reserve.c +++ b/kernel/crash_reserve.c @@ -524,6 +524,9 @@ void __init reserve_crashkernel_cma(unsigned long long cma_size) #ifndef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY static __init int insert_crashkernel_resources(void) { + if (!arch_add_crash_res_to_iomem()) + return 0; + if (crashk_res.start < crashk_res.end) insert_resource(&iomem_resource, &crashk_res); diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index d9b9dcba6ff7cf..9071c08650e3ad 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -90,6 +90,16 @@ static int __init early_cma(char *p) } early_param("cma", early_cma); +/* + * cma_skip_dt_default_reserved_mem - This is called from the + * reserved_mem framework to detect if the default cma region is being + * set by the "cma=" kernel parameter. + */ +bool __init cma_skip_dt_default_reserved_mem(void) +{ + return size_cmdline != -1; +} + #ifdef CONFIG_DMA_NUMA_CMA static struct cma *dma_contiguous_numa_area[MAX_NUMNODES]; @@ -463,12 +473,6 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem) struct cma *cma; int err; - if (size_cmdline != -1 && default_cma) { - pr_info("Reserved memory: bypass %s node, using cmdline CMA params instead\n", - rmem->name); - return -EBUSY; - } - if (!of_get_flat_dt_prop(node, "reusable", NULL) || of_get_flat_dt_prop(node, "no-map", NULL)) return -EINVAL; diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index ee45dee33d4916..985d6aa102b675 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -93,7 +93,7 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size, page = dma_alloc_from_contiguous(NULL, 1 << order, order, false); if (!page) - page = alloc_pages(gfp, order); + page = alloc_pages(gfp | __GFP_NOWARN, order); } while (!page && order-- > 0); if (!page) goto out; @@ -268,15 +268,20 @@ struct page *dma_alloc_from_pool(struct device *dev, size_t size, { struct gen_pool *pool = NULL; struct page *page; + bool pool_found = false; while ((pool = dma_guess_pool(pool, gfp))) { + pool_found = true; page = __dma_alloc_from_pool(dev, size, pool, cpu_addr, phys_addr_ok); if (page) return page; } - WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev)); + if (pool_found) + WARN(!(gfp & __GFP_NOWARN), "DMA pool exhausted for %s\n", dev_name(dev)); + else + WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev)); return NULL; } diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 808c0d7a31faf0..575154dbd23194 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -246,7 +246,7 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user, if (user && !crosstask) { if (!user_mode(regs)) { - if (current->flags & (PF_KTHREAD | PF_USER_WORKER)) + if (!is_user_task(current)) goto exit_put; regs = task_pt_regs(current); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 2c35acc2722b0f..1d8ca8e34f5c4e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2316,8 +2316,6 @@ static void perf_group_detach(struct perf_event *event) perf_event__header_size(leader); } -static void sync_child_event(struct perf_event *child_event); - static void perf_child_detach(struct perf_event *event) { struct perf_event *parent_event = event->parent; @@ -2336,7 +2334,6 @@ static void perf_child_detach(struct perf_event *event) lockdep_assert_held(&parent_event->child_mutex); */ - sync_child_event(event); list_del_init(&event->child_list); } @@ -4587,6 +4584,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) static void perf_remove_from_owner(struct perf_event *event); static void perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx, + struct task_struct *task, bool revoke); /* @@ -4614,7 +4612,7 @@ static void perf_event_remove_on_exec(struct perf_event_context *ctx) modified = true; - perf_event_exit_event(event, ctx, false); + perf_event_exit_event(event, ctx, ctx->task, false); } raw_spin_lock_irqsave(&ctx->lock, flags); @@ -6998,6 +6996,15 @@ static int perf_mmap_rb(struct vm_area_struct *vma, struct perf_event *event, if (data_page_nr(event->rb) != nr_pages) return -EINVAL; + /* + * If this event doesn't have mmap_count, we're attempting to + * create an alias of another event's mmap(); this would mean + * both events will end up scribbling the same user_page; + * which makes no sense. + */ + if (!refcount_read(&event->mmap_count)) + return -EBUSY; + if (refcount_inc_not_zero(&event->rb->mmap_count)) { /* * Success -- managed to mmap() the same buffer @@ -7452,7 +7459,7 @@ static void perf_sample_regs_user(struct perf_regs *regs_user, if (user_mode(regs)) { regs_user->abi = perf_reg_abi(current); regs_user->regs = regs; - } else if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { + } else if (is_user_task(current)) { perf_get_regs_user(regs_user, regs); } else { regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE; @@ -8092,7 +8099,7 @@ static u64 perf_virt_to_phys(u64 virt) * Try IRQ-safe get_user_page_fast_only first. * If failed, leave phys_addr as 0. */ - if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { + if (is_user_task(current)) { struct page *p; pagefault_disable(); @@ -8205,7 +8212,7 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) { bool kernel = !event->attr.exclude_callchain_kernel; bool user = !event->attr.exclude_callchain_user && - !(current->flags & (PF_KTHREAD | PF_USER_WORKER)); + is_user_task(current); /* Disallow cross-task user callchains. */ bool crosstask = event->ctx->task && event->ctx->task != current; const u32 max_stack = event->attr.sample_max_stack; @@ -11837,6 +11844,11 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event) } } +static void perf_swevent_destroy_hrtimer(struct perf_event *event) +{ + hrtimer_cancel(&event->hw.hrtimer); +} + static void perf_swevent_init_hrtimer(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -11845,6 +11857,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event) return; hrtimer_setup(&hwc->hrtimer, perf_swevent_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + event->destroy = perf_swevent_destroy_hrtimer; /* * Since hrtimers have a fixed rate, we can do a static freq->period @@ -12447,7 +12460,7 @@ static void __pmu_detach_event(struct pmu *pmu, struct perf_event *event, /* * De-schedule the event and mark it REVOKED. */ - perf_event_exit_event(event, ctx, true); + perf_event_exit_event(event, ctx, ctx->task, true); /* * All _free_event() bits that rely on event->pmu: @@ -14004,14 +14017,13 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) } EXPORT_SYMBOL_GPL(perf_pmu_migrate_context); -static void sync_child_event(struct perf_event *child_event) +static void sync_child_event(struct perf_event *child_event, + struct task_struct *task) { struct perf_event *parent_event = child_event->parent; u64 child_val; if (child_event->attr.inherit_stat) { - struct task_struct *task = child_event->ctx->task; - if (task && task != TASK_TOMBSTONE) perf_event_read_event(child_event, task); } @@ -14030,7 +14042,9 @@ static void sync_child_event(struct perf_event *child_event) static void perf_event_exit_event(struct perf_event *event, - struct perf_event_context *ctx, bool revoke) + struct perf_event_context *ctx, + struct task_struct *task, + bool revoke) { struct perf_event *parent_event = event->parent; unsigned long detach_flags = DETACH_EXIT; @@ -14053,6 +14067,9 @@ perf_event_exit_event(struct perf_event *event, mutex_lock(&parent_event->child_mutex); /* PERF_ATTACH_ITRACE might be set concurrently */ attach_state = READ_ONCE(event->attach_state); + + if (attach_state & PERF_ATTACH_CHILD) + sync_child_event(event, task); } if (revoke) @@ -14144,7 +14161,7 @@ static void perf_event_exit_task_context(struct task_struct *task, bool exit) perf_event_task(task, ctx, 0); list_for_each_entry_safe(child_event, next, &ctx->event_list, event_entry) - perf_event_exit_event(child_event, ctx, false); + perf_event_exit_event(child_event, ctx, exit ? task : NULL, false); mutex_unlock(&ctx->mutex); diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 1e76358641247f..cdd6e025935d34 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -103,8 +103,11 @@ static char kallsyms_get_symbol_type(unsigned int off) { /* * Get just the first code, look it up in the token table, - * and return the first char from this token. + * and return the first char from this token. If MSB of length + * is 1, it is a "big" symbol, so needs an additional byte. */ + if (kallsyms_names[off] & 0x80) + off++; return kallsyms_token_table[kallsyms_token_index[kallsyms_names[off + 1]]]; } @@ -342,7 +345,7 @@ int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, return 1; } return !!module_address_lookup(addr, symbolsize, offset, NULL, NULL, namebuf) || - !!__bpf_address_lookup(addr, symbolsize, offset, namebuf); + !!bpf_address_lookup(addr, symbolsize, offset, namebuf); } static int kallsyms_lookup_buildid(unsigned long addr, @@ -374,12 +377,11 @@ static int kallsyms_lookup_buildid(unsigned long addr, ret = module_address_lookup(addr, symbolsize, offset, modname, modbuildid, namebuf); if (!ret) - ret = bpf_address_lookup(addr, symbolsize, - offset, modname, namebuf); + ret = bpf_address_lookup(addr, symbolsize, offset, namebuf); if (!ret) - ret = ftrace_mod_address_lookup(addr, symbolsize, - offset, modname, namebuf); + ret = ftrace_mod_address_lookup(addr, symbolsize, offset, + modname, modbuildid, namebuf); return ret; } diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index fa00b239c5d9ad..08ae3c64caca50 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -960,17 +960,24 @@ int kimage_load_segment(struct kimage *image, int idx) return result; } -void *kimage_map_segment(struct kimage *image, - unsigned long addr, unsigned long size) +void *kimage_map_segment(struct kimage *image, int idx) { + unsigned long addr, size, eaddr; unsigned long src_page_addr, dest_page_addr = 0; - unsigned long eaddr = addr + size; kimage_entry_t *ptr, entry; struct page **src_pages; unsigned int npages; + struct page *cma; void *vaddr = NULL; int i; + cma = image->segment_cma[idx]; + if (cma) + return page_address(cma); + + addr = image->segment[idx].mem; + size = image->segment[idx].memsz; + eaddr = addr + size; /* * Collect the source pages and map them in a contiguous VA range. */ @@ -1011,7 +1018,8 @@ void *kimage_map_segment(struct kimage *image, void kimage_unmap_segment(void *segment_buffer) { - vunmap(segment_buffer); + if (is_vmalloc_addr(segment_buffer)) + vunmap(segment_buffer); } struct kexec_load_limit { diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 0e73fac55f8ebe..4e7a5cbc40a917 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -88,8 +88,14 @@ static struct klp_func *klp_find_func(struct klp_object *obj, struct klp_func *func; klp_for_each_func(obj, func) { + /* + * Besides identical old_sympos, also consider old_sympos + * of 0 and 1 are identical. + */ if ((strcmp(old_func->old_name, func->old_name) == 0) && - (old_func->old_sympos == func->old_sympos)) { + ((old_func->old_sympos == func->old_sympos) || + (old_func->old_sympos == 0 && func->old_sympos == 1) || + (old_func->old_sympos == 1 && func->old_sympos == 0))) { return func; } } diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index 0e5e6ffe91a3fe..91a802fea0aa0f 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -121,7 +121,7 @@ enum { #define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) -#define AVG_LOCKDEP_CHAIN_DEPTH 5 +#define AVG_LOCKDEP_CHAIN_DEPTH 10 #define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS * AVG_LOCKDEP_CHAIN_DEPTH) extern struct lock_chain lock_chains[]; diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index ce0362f0a8719a..6567e5eeacc0e1 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -103,8 +103,8 @@ static const struct kernel_param_ops lt_bind_ops = { .get = param_get_cpumask, }; -module_param_cb(bind_readers, <_bind_ops, &bind_readers, 0644); -module_param_cb(bind_writers, <_bind_ops, &bind_writers, 0644); +module_param_cb(bind_readers, <_bind_ops, &bind_readers, 0444); +module_param_cb(bind_writers, <_bind_ops, &bind_writers, 0444); long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask, bool dowarn); @@ -1211,6 +1211,10 @@ static void lock_torture_cleanup(void) cxt.cur_ops->exit(); cxt.init_called = false; } + + free_cpumask_var(bind_readers); + free_cpumask_var(bind_writers); + torture_cleanup_end(); } diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c index 87b03d2e41dbbe..2338b3adfb55ff 100644 --- a/kernel/locking/spinlock_debug.c +++ b/kernel/locking/spinlock_debug.c @@ -184,8 +184,8 @@ void do_raw_read_unlock(rwlock_t *lock) static inline void debug_write_lock_before(rwlock_t *lock) { RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic"); - RWLOCK_BUG_ON(lock->owner == current, lock, "recursion"); - RWLOCK_BUG_ON(lock->owner_cpu == raw_smp_processor_id(), + RWLOCK_BUG_ON(READ_ONCE(lock->owner) == current, lock, "recursion"); + RWLOCK_BUG_ON(READ_ONCE(lock->owner_cpu) == raw_smp_processor_id(), lock, "cpu recursion"); } diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index 00a60796327c06..0fc11e45df9b91 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -334,13 +334,8 @@ int module_address_lookup(unsigned long addr, if (mod) { if (modname) *modname = mod->name; - if (modbuildid) { -#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) - *modbuildid = mod->build_id; -#else - *modbuildid = NULL; -#endif - } + if (modbuildid) + *modbuildid = module_buildid(mod); sym = find_kallsyms_symbol(mod, addr, size, offset); diff --git a/kernel/panic.c b/kernel/panic.c index 24cc3eec1805fe..b13f040680ac1c 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -131,7 +131,8 @@ static int proc_taint(const struct ctl_table *table, int write, static int sysctl_panic_print_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - panic_print_deprecated(); + if (write) + panic_print_deprecated(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } @@ -1010,7 +1011,6 @@ static int panic_print_set(const char *val, const struct kernel_param *kp) static int panic_print_get(char *val, const struct kernel_param *kp) { - panic_print_deprecated(); return param_get_ulong(val, kp); } diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 26e45f86b9554e..6503cda89645bc 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include "power.h" @@ -110,7 +111,8 @@ bool hibernation_available(void) { return nohibernate == 0 && !security_locked_down(LOCKDOWN_HIBERNATION) && - !secretmem_active() && !cxl_mem_active(); + !secretmem_active() && !cxl_mem_active() && + !of_machine_is_compatible("apple,arm-platform"); } /** diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 70ae21f7370d4c..f910a250ccddb9 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -897,8 +897,11 @@ static int save_compressed_image(struct swap_map_handle *handle, for (thr = 0; thr < nr_threads; thr++) { if (data[thr].thr) kthread_stop(data[thr].thr); - acomp_request_free(data[thr].cr); - crypto_free_acomp(data[thr].cc); + if (data[thr].cr) + acomp_request_free(data[thr].cr); + + if (!IS_ERR_OR_NULL(data[thr].cc)) + crypto_free_acomp(data[thr].cc); } vfree(data); } @@ -1519,8 +1522,11 @@ static int load_compressed_image(struct swap_map_handle *handle, for (thr = 0; thr < nr_threads; thr++) { if (data[thr].thr) kthread_stop(data[thr].thr); - acomp_request_free(data[thr].cr); - crypto_free_acomp(data[thr].cc); + if (data[thr].cr) + acomp_request_free(data[thr].cr); + + if (!IS_ERR_OR_NULL(data[thr].cc)) + crypto_free_acomp(data[thr].cc); } vfree(data); } diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index f72bbfa266d6c9..b20929b7d71f59 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -230,6 +230,8 @@ struct console_flush_type { bool legacy_offload; }; +extern bool console_irqwork_blocked; + /* * Identify which console flushing methods should be used in the context of * the caller. @@ -241,7 +243,7 @@ static inline void printk_get_console_flush_type(struct console_flush_type *ft) switch (nbcon_get_default_prio()) { case NBCON_PRIO_NORMAL: if (have_nbcon_console && !have_boot_console) { - if (printk_kthreads_running) + if (printk_kthreads_running && !console_irqwork_blocked) ft->nbcon_offload = true; else ft->nbcon_atomic = true; @@ -251,7 +253,7 @@ static inline void printk_get_console_flush_type(struct console_flush_type *ft) if (have_legacy_console || have_boot_console) { if (!is_printk_legacy_deferred()) ft->legacy_direct = true; - else + else if (!console_irqwork_blocked) ft->legacy_offload = true; } break; @@ -264,7 +266,7 @@ static inline void printk_get_console_flush_type(struct console_flush_type *ft) if (have_legacy_console || have_boot_console) { if (!is_printk_legacy_deferred()) ft->legacy_direct = true; - else + else if (!console_irqwork_blocked) ft->legacy_offload = true; } break; diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index 558ef317797603..730d14f6cbc582 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -1276,6 +1276,13 @@ void nbcon_kthreads_wake(void) if (!printk_kthreads_running) return; + /* + * It is not allowed to call this function when console irq_work + * is blocked. + */ + if (WARN_ON_ONCE(console_irqwork_blocked)) + return; + cookie = console_srcu_read_lock(); for_each_console_srcu(con) { if (!(console_srcu_read_flags(con) & CON_NBCON)) @@ -1849,7 +1856,7 @@ void nbcon_device_release(struct console *con) if (console_trylock()) console_unlock(); } else if (ft.legacy_offload) { - printk_trigger_flush(); + defer_console_output(); } } console_srcu_read_unlock(cookie); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 5aee9ffb16b9a5..c27fc7fc64eb51 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -462,6 +462,9 @@ bool have_boot_console; /* See printk_legacy_allow_panic_sync() for details. */ bool legacy_allow_panic_sync; +/* Avoid using irq_work when suspending. */ +bool console_irqwork_blocked; + #ifdef CONFIG_PRINTK DECLARE_WAIT_QUEUE_HEAD(log_wait); static DECLARE_WAIT_QUEUE_HEAD(legacy_wait); @@ -2390,7 +2393,7 @@ asmlinkage int vprintk_emit(int facility, int level, /* If called from the scheduler, we can not call up(). */ if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; - ft.legacy_offload |= ft.legacy_direct; + ft.legacy_offload |= ft.legacy_direct && !console_irqwork_blocked; ft.legacy_direct = false; } @@ -2426,7 +2429,7 @@ asmlinkage int vprintk_emit(int facility, int level, if (ft.legacy_offload) defer_console_output(); - else + else if (!console_irqwork_blocked) wake_up_klogd(); return printed_len; @@ -2730,10 +2733,20 @@ void console_suspend_all(void) { struct console *con; + if (console_suspend_enabled) + pr_info("Suspending console(s) (use no_console_suspend to debug)\n"); + + /* + * Flush any console backlog and then avoid queueing irq_work until + * console_resume_all(). Until then deferred printing is no longer + * triggered, NBCON consoles transition to atomic flushing, and + * any klogd waiters are not triggered. + */ + pr_flush(1000, true); + console_irqwork_blocked = true; + if (!console_suspend_enabled) return; - pr_info("Suspending console(s) (use no_console_suspend to debug)\n"); - pr_flush(1000, true); console_list_lock(); for_each_console(con) @@ -2754,26 +2767,34 @@ void console_resume_all(void) struct console_flush_type ft; struct console *con; - if (!console_suspend_enabled) - return; - - console_list_lock(); - for_each_console(con) - console_srcu_write_flags(con, con->flags & ~CON_SUSPENDED); - console_list_unlock(); - /* - * Ensure that all SRCU list walks have completed. All printing - * contexts must be able to see they are no longer suspended so - * that they are guaranteed to wake up and resume printing. + * Allow queueing irq_work. After restoring console state, deferred + * printing and any klogd waiters need to be triggered in case there + * is now a console backlog. */ - synchronize_srcu(&console_srcu); + console_irqwork_blocked = false; + + if (console_suspend_enabled) { + console_list_lock(); + for_each_console(con) + console_srcu_write_flags(con, con->flags & ~CON_SUSPENDED); + console_list_unlock(); + + /* + * Ensure that all SRCU list walks have completed. All printing + * contexts must be able to see they are no longer suspended so + * that they are guaranteed to wake up and resume printing. + */ + synchronize_srcu(&console_srcu); + } printk_get_console_flush_type(&ft); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_offload) defer_console_output(); + else + wake_up_klogd(); pr_flush(1000, true); } @@ -4511,6 +4532,13 @@ static void __wake_up_klogd(int val) if (!printk_percpu_data_ready()) return; + /* + * It is not allowed to call this function when console irq_work + * is blocked. + */ + if (WARN_ON_ONCE(console_irqwork_blocked)) + return; + preempt_disable(); /* * Guarantee any new records can be seen by tasks preparing to wait @@ -4567,9 +4595,30 @@ void defer_console_output(void) __wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT); } +/** + * printk_trigger_flush - Attempt to flush printk buffer to consoles. + * + * If possible, flush the printk buffer to all consoles in the caller's + * context. If offloading is available, trigger deferred printing. + * + * This is best effort. Depending on the system state, console states, + * and caller context, no actual flushing may result from this call. + */ void printk_trigger_flush(void) { - defer_console_output(); + struct console_flush_type ft; + + printk_get_console_flush_type(&ft); + if (ft.nbcon_atomic) + nbcon_atomic_flush_pending(); + if (ft.nbcon_offload) + nbcon_kthreads_wake(); + if (ft.legacy_direct) { + if (console_trylock()) + console_unlock(); + } + if (ft.legacy_offload) + defer_console_output(); } int vprintk_deferred(const char *fmt, va_list args) diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index b8bbe7960cda7a..2265b9c2906e1e 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -203,7 +203,7 @@ struct rcu_data { /* during and after the last grace */ /* period it is aware of. */ struct irq_work defer_qs_iw; /* Obtain later scheduler attention. */ - int defer_qs_iw_pending; /* Scheduler attention pending? */ + int defer_qs_pending; /* irqwork or softirq pending? */ struct work_struct strict_work; /* Schedule readers for strict GPs. */ /* 2) batch handling */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index d85763336b3c0f..cafb1cc8eff846 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -487,8 +487,8 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) union rcu_special special; rdp = this_cpu_ptr(&rcu_data); - if (rdp->defer_qs_iw_pending == DEFER_QS_PENDING) - rdp->defer_qs_iw_pending = DEFER_QS_IDLE; + if (rdp->defer_qs_pending == DEFER_QS_PENDING) + rdp->defer_qs_pending = DEFER_QS_IDLE; /* * If RCU core is waiting for this CPU to exit its critical section, @@ -645,7 +645,7 @@ static void rcu_preempt_deferred_qs_handler(struct irq_work *iwp) * 5. Deferred QS reporting does not happen. */ if (rcu_preempt_depth() > 0) - WRITE_ONCE(rdp->defer_qs_iw_pending, DEFER_QS_IDLE); + WRITE_ONCE(rdp->defer_qs_pending, DEFER_QS_IDLE); } /* @@ -747,7 +747,10 @@ static void rcu_read_unlock_special(struct task_struct *t) // Using softirq, safe to awaken, and either the // wakeup is free or there is either an expedited // GP in flight or a potential need to deboost. - raise_softirq_irqoff(RCU_SOFTIRQ); + if (rdp->defer_qs_pending != DEFER_QS_PENDING) { + rdp->defer_qs_pending = DEFER_QS_PENDING; + raise_softirq_irqoff(RCU_SOFTIRQ); + } } else { // Enabling BH or preempt does reschedule, so... // Also if no expediting and no possible deboosting, @@ -756,11 +759,11 @@ static void rcu_read_unlock_special(struct task_struct *t) set_tsk_need_resched(current); set_preempt_need_resched(); if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled && - needs_exp && rdp->defer_qs_iw_pending != DEFER_QS_PENDING && + needs_exp && rdp->defer_qs_pending != DEFER_QS_PENDING && cpu_online(rdp->cpu)) { // Get scheduler to re-evaluate and call hooks. // If !IRQ_WORK, FQS scan will eventually IPI. - rdp->defer_qs_iw_pending = DEFER_QS_PENDING; + rdp->defer_qs_pending = DEFER_QS_PENDING; irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu); } } diff --git a/kernel/resource.c b/kernel/resource.c index b9fa2a4ce089cf..e4e9bac12e6e17 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -341,6 +341,8 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, unsigned long flags, unsigned long desc, struct resource *res) { + /* Skip children until we find a top level range that matches */ + bool skip_children = true; struct resource *p; if (!res) @@ -351,7 +353,7 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, read_lock(&resource_lock); - for_each_resource(&iomem_resource, p, false) { + for_each_resource(&iomem_resource, p, skip_children) { /* If we passed the resource we are looking for, stop */ if (p->start > end) { p = NULL; @@ -362,6 +364,12 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, if (p->end < start) continue; + /* + * We found a top level range that matches what we are looking + * for. Time to start checking children too. + */ + skip_children = false; + /* Found a match, break */ if (is_type_match(p, flags, desc)) break; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f754a60de84849..582c3847f483a5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -119,8 +119,12 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(sched_entry_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(sched_exit_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(sched_set_need_resched_tp); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +DEFINE_PER_CPU(struct rnd_state, sched_rnd_state); #ifdef CONFIG_SCHED_PROXY_EXEC DEFINE_STATIC_KEY_TRUE(__sched_proxy_exec); @@ -1135,6 +1139,7 @@ void __trace_set_need_resched(struct task_struct *curr, int tif) { trace_sched_set_need_resched_tp(curr, smp_processor_id(), tif); } +EXPORT_SYMBOL_GPL(__trace_set_need_resched); void resched_curr(struct rq *rq) { @@ -7382,7 +7387,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) trace_sched_pi_setprio(p, pi_task); oldprio = p->prio; - if (oldprio == prio) + if (oldprio == prio && !dl_prio(prio)) queue_flag &= ~DEQUEUE_MOVE; prev_class = p->sched_class; @@ -8591,6 +8596,8 @@ void __init sched_init_smp(void) { sched_init_numa(NUMA_NO_NODE); + prandom_init_once(&sched_rnd_state); + /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index cdd740b3f77436..37b572cc8aca2e 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -166,12 +166,13 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, * cpudl_clear - remove a CPU from the cpudl max-heap * @cp: the cpudl max-heap context * @cpu: the target CPU + * @online: the online state of the deadline runqueue * * Notes: assumes cpu_rq(cpu)->lock is locked * * Returns: (void) */ -void cpudl_clear(struct cpudl *cp, int cpu) +void cpudl_clear(struct cpudl *cp, int cpu, bool online) { int old_idx, new_cpu; unsigned long flags; @@ -184,7 +185,7 @@ void cpudl_clear(struct cpudl *cp, int cpu) if (old_idx == IDX_INVALID) { /* * Nothing to remove if old_idx was invalid. - * This could happen if a rq_offline_dl is + * This could happen if rq_online_dl or rq_offline_dl is * called for a CPU without -dl tasks running. */ } else { @@ -195,9 +196,12 @@ void cpudl_clear(struct cpudl *cp, int cpu) cp->elements[new_cpu].idx = old_idx; cp->elements[cpu].idx = IDX_INVALID; cpudl_heapify(cp, old_idx); - - cpumask_set_cpu(cpu, cp->free_cpus); } + if (likely(online)) + __cpumask_set_cpu(cpu, cp->free_cpus); + else + __cpumask_clear_cpu(cpu, cp->free_cpus); + raw_spin_unlock_irqrestore(&cp->lock, flags); } @@ -228,7 +232,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl) cp->elements[new_idx].cpu = cpu; cp->elements[cpu].idx = new_idx; cpudl_heapify_up(cp, new_idx); - cpumask_clear_cpu(cpu, cp->free_cpus); + __cpumask_clear_cpu(cpu, cp->free_cpus); } else { cp->elements[old_idx].dl = dl; cpudl_heapify(cp, old_idx); @@ -237,26 +241,6 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl) raw_spin_unlock_irqrestore(&cp->lock, flags); } -/* - * cpudl_set_freecpu - Set the cpudl.free_cpus - * @cp: the cpudl max-heap context - * @cpu: rd attached CPU - */ -void cpudl_set_freecpu(struct cpudl *cp, int cpu) -{ - cpumask_set_cpu(cpu, cp->free_cpus); -} - -/* - * cpudl_clear_freecpu - Clear the cpudl.free_cpus - * @cp: the cpudl max-heap context - * @cpu: rd attached CPU - */ -void cpudl_clear_freecpu(struct cpudl *cp, int cpu) -{ - cpumask_clear_cpu(cpu, cp->free_cpus); -} - /* * cpudl_init - initialize the cpudl structure * @cp: the cpudl max-heap context diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h index 11c0f1faa7e11d..d7699468eedd57 100644 --- a/kernel/sched/cpudeadline.h +++ b/kernel/sched/cpudeadline.h @@ -19,8 +19,6 @@ struct cpudl { int cpudl_find(struct cpudl *cp, struct task_struct *p, struct cpumask *later_mask); void cpudl_set(struct cpudl *cp, int cpu, u64 dl); -void cpudl_clear(struct cpudl *cp, int cpu); +void cpudl_clear(struct cpudl *cp, int cpu, bool online); int cpudl_init(struct cpudl *cp); -void cpudl_set_freecpu(struct cpudl *cp, int cpu); -void cpudl_clear_freecpu(struct cpudl *cp, int cpu); void cpudl_cleanup(struct cpudl *cp); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 7b7671060bf9ed..72499cf2a1db5d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -761,8 +761,6 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - update_rq_clock(rq); - WARN_ON(is_dl_boosted(dl_se)); WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline)); @@ -1045,6 +1043,12 @@ static void update_dl_entity(struct sched_dl_entity *dl_se) return; } + /* + * When [4] D->A is followed by [1] A->B, dl_defer_running + * needs to be cleared, otherwise it will fail to properly + * start the zero-laxity timer. + */ + dl_se->dl_defer_running = 0; replenish_dl_new_period(dl_se, rq); } else if (dl_server(dl_se) && dl_se->dl_defer) { /* @@ -1575,6 +1579,206 @@ void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec) update_curr_dl_se(dl_se->rq, dl_se, delta_exec); } +/* + * dl_server && dl_defer: + * + * 6 + * +--------------------+ + * v | + * +-------------+ 4 +-----------+ 5 +------------------+ + * +-> | A:init | <--- | D:running | -----> | E:replenish-wait | + * | +-------------+ +-----------+ +------------------+ + * | | | 1 ^ ^ | + * | | 1 +----------+ | 3 | + * | v | | + * | +--------------------------------+ 2 | + * | | | ----+ | + * | 8 | B:zero_laxity-wait | | | + * | | | <---+ | + * | +--------------------------------+ | + * | | ^ ^ 2 | + * | | 7 | 2 +--------------------+ + * | v | + * | +-------------+ | + * +-- | C:idle-wait | -+ + * +-------------+ + * ^ 7 | + * +---------+ + * + * + * [A] - init + * dl_server_active = 0 + * dl_throttled = 0 + * dl_defer_armed = 0 + * dl_defer_running = 0/1 + * dl_defer_idle = 0 + * + * [B] - zero_laxity-wait + * dl_server_active = 1 + * dl_throttled = 1 + * dl_defer_armed = 1 + * dl_defer_running = 0 + * dl_defer_idle = 0 + * + * [C] - idle-wait + * dl_server_active = 1 + * dl_throttled = 1 + * dl_defer_armed = 1 + * dl_defer_running = 0 + * dl_defer_idle = 1 + * + * [D] - running + * dl_server_active = 1 + * dl_throttled = 0 + * dl_defer_armed = 0 + * dl_defer_running = 1 + * dl_defer_idle = 0 + * + * [E] - replenish-wait + * dl_server_active = 1 + * dl_throttled = 1 + * dl_defer_armed = 0 + * dl_defer_running = 1 + * dl_defer_idle = 0 + * + * + * [1] A->B, A->D + * dl_server_start() + * dl_server_active = 1; + * enqueue_dl_entity() + * update_dl_entity(WAKEUP) + * if (dl_time_before() || dl_entity_overflow()) + * dl_defer_running = 0; + * replenish_dl_new_period(); + * // fwd period + * dl_throttled = 1; + * dl_defer_armed = 1; + * if (!dl_defer_running) + * dl_defer_armed = 1; + * dl_throttled = 1; + * if (dl_throttled && start_dl_timer()) + * return; // [B] + * __enqueue_dl_entity(); + * // [D] + * + * // deplete server runtime from client-class + * [2] B->B, C->B, E->B + * dl_server_update() + * update_curr_dl_se() // idle = false + * if (dl_defer_idle) + * dl_defer_idle = 0; + * if (dl_defer && dl_throttled && dl_runtime_exceeded()) + * dl_defer_running = 0; + * hrtimer_try_to_cancel(); // stop timer + * replenish_dl_new_period() + * // fwd period + * dl_throttled = 1; + * dl_defer_armed = 1; + * start_dl_timer(); // restart timer + * // [B] + * + * // timer actually fires means we have runtime + * [3] B->D + * dl_server_timer() + * if (dl_defer_armed) + * dl_defer_running = 1; + * enqueue_dl_entity(REPLENISH) + * replenish_dl_entity() + * // fwd period + * if (dl_throttled) + * dl_throttled = 0; + * if (dl_defer_armed) + * dl_defer_armed = 0; + * __enqueue_dl_entity(); + * // [D] + * + * // schedule server + * [4] D->A + * pick_task_dl() + * p = server_pick_task(); + * if (!p) + * dl_server_stop() + * dequeue_dl_entity(); + * hrtimer_try_to_cancel(); + * dl_defer_armed = 0; + * dl_throttled = 0; + * dl_server_active = 0; + * // [A] + * return p; + * + * // server running + * [5] D->E + * update_curr_dl_se() + * if (dl_runtime_exceeded()) + * dl_throttled = 1; + * dequeue_dl_entity(); + * start_dl_timer(); + * // [E] + * + * // server replenished + * [6] E->D + * dl_server_timer() + * enqueue_dl_entity(REPLENISH) + * replenish_dl_entity() + * fwd-period + * if (dl_throttled) + * dl_throttled = 0; + * __enqueue_dl_entity(); + * // [D] + * + * // deplete server runtime from idle + * [7] B->C, C->C + * dl_server_update_idle() + * update_curr_dl_se() // idle = true + * if (dl_defer && dl_throttled && dl_runtime_exceeded()) + * if (dl_defer_idle) + * return; + * dl_defer_running = 0; + * hrtimer_try_to_cancel(); + * replenish_dl_new_period() + * // fwd period + * dl_throttled = 1; + * dl_defer_armed = 1; + * dl_defer_idle = 1; + * start_dl_timer(); // restart timer + * // [C] + * + * // stop idle server + * [8] C->A + * dl_server_timer() + * if (dl_defer_idle) + * dl_server_stop(); + * // [A] + * + * + * digraph dl_server { + * "A:init" -> "B:zero_laxity-wait" [label="1:dl_server_start"] + * "A:init" -> "D:running" [label="1:dl_server_start"] + * "B:zero_laxity-wait" -> "B:zero_laxity-wait" [label="2:dl_server_update"] + * "B:zero_laxity-wait" -> "C:idle-wait" [label="7:dl_server_update_idle"] + * "B:zero_laxity-wait" -> "D:running" [label="3:dl_server_timer"] + * "C:idle-wait" -> "A:init" [label="8:dl_server_timer"] + * "C:idle-wait" -> "B:zero_laxity-wait" [label="2:dl_server_update"] + * "C:idle-wait" -> "C:idle-wait" [label="7:dl_server_update_idle"] + * "D:running" -> "A:init" [label="4:pick_task_dl"] + * "D:running" -> "E:replenish-wait" [label="5:update_curr_dl_se"] + * "E:replenish-wait" -> "B:zero_laxity-wait" [label="2:dl_server_update"] + * "E:replenish-wait" -> "D:running" [label="6:dl_server_timer"] + * } + * + * + * Notes: + * + * - When there are fair tasks running the most likely loop is [2]->[2]. + * the dl_server never actually runs, the timer never fires. + * + * - When there is actual fair starvation; the timer fires and starts the + * dl_server. This will then throttle and replenish like a normal DL + * task. Notably it will not 'defer' again. + * + * - When idle it will push the actication forward once, and then wait + * for the timer to hit or a non-idle update to restart things. + */ void dl_server_start(struct sched_dl_entity *dl_se) { struct rq *rq = dl_se->rq; @@ -1623,6 +1827,7 @@ void sched_init_dl_servers(void) rq = cpu_rq(cpu); guard(rq_lock_irq)(rq); + update_rq_clock(rq); dl_se = &rq->fair_server; @@ -1811,7 +2016,7 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) if (!dl_rq->dl_nr_running) { dl_rq->earliest_dl.curr = 0; dl_rq->earliest_dl.next = 0; - cpudl_clear(&rq->rd->cpudl, rq->cpu); + cpudl_clear(&rq->rd->cpudl, rq->cpu, rq->online); cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr); } else { struct rb_node *leftmost = rb_first_cached(&dl_rq->root); @@ -2143,7 +2348,7 @@ static void yield_task_dl(struct rq *rq) * it and the bandwidth timer will wake it up and will give it * new scheduling parameters (thanks to dl_yielded=1). */ - rq->curr->dl.dl_yielded = 1; + rq->donor->dl.dl_yielded = 1; update_rq_clock(rq); update_curr_dl(rq); @@ -2883,9 +3088,10 @@ static void rq_online_dl(struct rq *rq) if (rq->dl.overloaded) dl_set_overload(rq); - cpudl_set_freecpu(&rq->rd->cpudl, rq->cpu); if (rq->dl.dl_nr_running > 0) cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr); + else + cpudl_clear(&rq->rd->cpudl, rq->cpu, true); } /* Assumes rq->lock is held */ @@ -2894,8 +3100,7 @@ static void rq_offline_dl(struct rq *rq) if (rq->dl.overloaded) dl_clear_overload(rq); - cpudl_clear(&rq->rd->cpudl, rq->cpu); - cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu); + cpudl_clear(&rq->rd->cpudl, rq->cpu, false); } void __init init_sched_dl_class(void) @@ -3386,6 +3591,9 @@ static void __dl_clear_params(struct sched_dl_entity *dl_se) dl_se->dl_non_contending = 0; dl_se->dl_overrun = 0; dl_se->dl_server = 0; + dl_se->dl_defer = 0; + dl_se->dl_defer_running = 0; + dl_se->dl_defer_armed = 0; #ifdef CONFIG_RT_MUTEXES dl_se->pi_se = dl_se; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 02e16b70a7901e..41caa22e0680a6 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -796,7 +796,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) { - s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, left_deadline = -1, spread; + s64 left_vruntime = -1, zero_vruntime, right_vruntime = -1, left_deadline = -1, spread; struct sched_entity *last, *first, *root; struct rq *rq = cpu_rq(cpu); unsigned long flags; @@ -819,15 +819,15 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) last = __pick_last_entity(cfs_rq); if (last) right_vruntime = last->vruntime; - min_vruntime = cfs_rq->min_vruntime; + zero_vruntime = cfs_rq->zero_vruntime; raw_spin_rq_unlock_irqrestore(rq, flags); SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_deadline", SPLIT_NS(left_deadline)); SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_vruntime", SPLIT_NS(left_vruntime)); - SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime", - SPLIT_NS(min_vruntime)); + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "zero_vruntime", + SPLIT_NS(zero_vruntime)); SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "avg_vruntime", SPLIT_NS(avg_vruntime(cfs_rq))); SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "right_vruntime", diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 979484dab2d3d1..2ff7034841c7cb 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -40,6 +40,13 @@ static bool scx_init_task_enabled; static bool scx_switching_all; DEFINE_STATIC_KEY_FALSE(__scx_switched_all); +/* + * Tracks whether scx_enable() called scx_bypass(true). Used to balance bypass + * depth on enable failure. Will be removed when bypass depth is moved into the + * sched instance. + */ +static bool scx_bypassed_for_enable; + static atomic_long_t scx_nr_rejected = ATOMIC_LONG_INIT(0); static atomic_long_t scx_hotplug_seq = ATOMIC_LONG_INIT(0); @@ -203,6 +210,14 @@ static struct scx_dispatch_q *find_user_dsq(struct scx_sched *sch, u64 dsq_id) return rhashtable_lookup_fast(&sch->dsq_hash, &dsq_id, dsq_hash_params); } +static const struct sched_class *scx_setscheduler_class(struct task_struct *p) +{ + if (p->sched_class == &stop_sched_class) + return &stop_sched_class; + + return __setscheduler_class(p->policy, p->prio); +} + /* * scx_kf_mask enforcement. Some kfuncs can only be called from specific SCX * ops. When invoking SCX ops, SCX_CALL_OP[_RET]() should be used to indicate @@ -906,6 +921,30 @@ static void refill_task_slice_dfl(struct scx_sched *sch, struct task_struct *p) __scx_add_event(sch, SCX_EV_REFILL_SLICE_DFL, 1); } +static void local_dsq_post_enq(struct scx_dispatch_q *dsq, struct task_struct *p, + u64 enq_flags) +{ + struct rq *rq = container_of(dsq, struct rq, scx.local_dsq); + bool preempt = false; + + /* + * If @rq is in balance, the CPU is already vacant and looking for the + * next task to run. No need to preempt or trigger resched after moving + * @p into its local DSQ. + */ + if (rq->scx.flags & SCX_RQ_IN_BALANCE) + return; + + if ((enq_flags & SCX_ENQ_PREEMPT) && p != rq->curr && + rq->curr->sched_class == &ext_sched_class) { + rq->curr->scx.slice = 0; + preempt = true; + } + + if (preempt || sched_class_above(&ext_sched_class, rq->curr->sched_class)) + resched_curr(rq); +} + static void dispatch_enqueue(struct scx_sched *sch, struct scx_dispatch_q *dsq, struct task_struct *p, u64 enq_flags) { @@ -1003,22 +1042,10 @@ static void dispatch_enqueue(struct scx_sched *sch, struct scx_dispatch_q *dsq, if (enq_flags & SCX_ENQ_CLEAR_OPSS) atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE); - if (is_local) { - struct rq *rq = container_of(dsq, struct rq, scx.local_dsq); - bool preempt = false; - - if ((enq_flags & SCX_ENQ_PREEMPT) && p != rq->curr && - rq->curr->sched_class == &ext_sched_class) { - rq->curr->scx.slice = 0; - preempt = true; - } - - if (preempt || sched_class_above(&ext_sched_class, - rq->curr->sched_class)) - resched_curr(rq); - } else { + if (is_local) + local_dsq_post_enq(dsq, p, enq_flags); + else raw_spin_unlock(&dsq->lock); - } } static void task_unlink_from_dsq(struct task_struct *p, @@ -1474,7 +1501,7 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags static void yield_task_scx(struct rq *rq) { struct scx_sched *sch = scx_root; - struct task_struct *p = rq->curr; + struct task_struct *p = rq->donor; if (SCX_HAS_OP(sch, yield)) SCX_CALL_OP_2TASKS_RET(sch, SCX_KF_REST, yield, rq, p, NULL); @@ -1485,7 +1512,7 @@ static void yield_task_scx(struct rq *rq) static bool yield_to_task_scx(struct rq *rq, struct task_struct *to) { struct scx_sched *sch = scx_root; - struct task_struct *from = rq->curr; + struct task_struct *from = rq->donor; if (SCX_HAS_OP(sch, yield)) return SCX_CALL_OP_2TASKS_RET(sch, SCX_KF_REST, yield, rq, @@ -1513,6 +1540,8 @@ static void move_local_task_to_local_dsq(struct task_struct *p, u64 enq_flags, dsq_mod_nr(dst_dsq, 1); p->scx.dsq = dst_dsq; + + local_dsq_post_enq(dst_dsq, p, enq_flags); } /** @@ -2277,12 +2306,6 @@ static void switch_class(struct rq *rq, struct task_struct *next) struct scx_sched *sch = scx_root; const struct sched_class *next_class = next->sched_class; - /* - * Pairs with the smp_load_acquire() issued by a CPU in - * kick_cpus_irq_workfn() who is waiting for this CPU to perform a - * resched. - */ - smp_store_release(&rq->scx.pnt_seq, rq->scx.pnt_seq + 1); if (!(sch->ops.flags & SCX_OPS_HAS_CPU_PREEMPT)) return; @@ -2322,6 +2345,10 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, struct task_struct *next) { struct scx_sched *sch = scx_root; + + /* see kick_cpus_irq_workfn() */ + smp_store_release(&rq->scx.pnt_seq, rq->scx.pnt_seq + 1); + update_curr_scx(rq); /* see dequeue_task_scx() on why we skip when !QUEUED */ @@ -2375,6 +2402,9 @@ static struct task_struct *pick_task_scx(struct rq *rq) bool keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP; bool kick_idle = false; + /* see kick_cpus_irq_workfn() */ + smp_store_release(&rq->scx.pnt_seq, rq->scx.pnt_seq + 1); + /* * WORKAROUND: * @@ -3508,7 +3538,7 @@ static void scx_sched_free_rcu_work(struct work_struct *work) int node; irq_work_sync(&sch->error_irq_work); - kthread_stop(sch->helper->task); + kthread_destroy_worker(sch->helper); free_percpu(sch->pcpu); @@ -3973,8 +4003,7 @@ static void scx_disable_workfn(struct kthread_work *work) scx_task_iter_start(&sti); while ((p = scx_task_iter_next_locked(&sti))) { const struct sched_class *old_class = p->sched_class; - const struct sched_class *new_class = - __setscheduler_class(p->policy, p->prio); + const struct sched_class *new_class = scx_setscheduler_class(p); struct sched_enq_and_set_ctx ctx; if (old_class != new_class && p->se.sched_delayed) @@ -4047,6 +4076,11 @@ static void scx_disable_workfn(struct kthread_work *work) scx_dsp_max_batch = 0; free_kick_pseqs(); + if (scx_bypassed_for_enable) { + scx_bypassed_for_enable = false; + scx_bypass(false); + } + mutex_unlock(&scx_enable_mutex); WARN_ON_ONCE(scx_set_enable_state(SCX_DISABLED) != SCX_DISABLING); @@ -4475,8 +4509,10 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops) } sch->pcpu = alloc_percpu(struct scx_sched_pcpu); - if (!sch->pcpu) + if (!sch->pcpu) { + ret = -ENOMEM; goto err_free_gdsqs; + } sch->helper = kthread_run_worker(0, "sched_ext_helper"); if (IS_ERR(sch->helper)) { @@ -4500,7 +4536,7 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops) return sch; err_stop_helper: - kthread_stop(sch->helper->task); + kthread_destroy_worker(sch->helper); err_free_pcpu: free_percpu(sch->pcpu); err_free_gdsqs: @@ -4672,6 +4708,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) * Init in bypass mode to guarantee forward progress. */ scx_bypass(true); + scx_bypassed_for_enable = true; for (i = SCX_OPI_NORMAL_BEGIN; i < SCX_OPI_NORMAL_END; i++) if (((void (**)(void))ops)[i]) @@ -4752,8 +4789,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) scx_task_iter_start(&sti); while ((p = scx_task_iter_next_locked(&sti))) { const struct sched_class *old_class = p->sched_class; - const struct sched_class *new_class = - __setscheduler_class(p->policy, p->prio); + const struct sched_class *new_class = scx_setscheduler_class(p); struct sched_enq_and_set_ctx ctx; if (!tryget_task_struct(p)) @@ -4776,6 +4812,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) scx_task_iter_stop(&sti); percpu_up_write(&scx_fork_rwsem); + scx_bypassed_for_enable = false; scx_bypass(false); if (!scx_tryset_enable_state(SCX_ENABLED, SCX_ENABLING)) { @@ -5128,25 +5165,34 @@ static bool kick_one_cpu(s32 cpu, struct rq *this_rq, unsigned long *pseqs) { struct rq *rq = cpu_rq(cpu); struct scx_rq *this_scx = &this_rq->scx; + const struct sched_class *cur_class; bool should_wait = false; unsigned long flags; raw_spin_rq_lock_irqsave(rq, flags); + cur_class = rq->curr->sched_class; /* * During CPU hotplug, a CPU may depend on kicking itself to make - * forward progress. Allow kicking self regardless of online state. + * forward progress. Allow kicking self regardless of online state. If + * @cpu is running a higher class task, we have no control over @cpu. + * Skip kicking. */ - if (cpu_online(cpu) || cpu == cpu_of(this_rq)) { + if ((cpu_online(cpu) || cpu == cpu_of(this_rq)) && + !sched_class_above(cur_class, &ext_sched_class)) { if (cpumask_test_cpu(cpu, this_scx->cpus_to_preempt)) { - if (rq->curr->sched_class == &ext_sched_class) + if (cur_class == &ext_sched_class) rq->curr->scx.slice = 0; cpumask_clear_cpu(cpu, this_scx->cpus_to_preempt); } if (cpumask_test_cpu(cpu, this_scx->cpus_to_wait)) { - pseqs[cpu] = rq->scx.pnt_seq; - should_wait = true; + if (cur_class == &ext_sched_class) { + pseqs[cpu] = rq->scx.pnt_seq; + should_wait = true; + } else { + cpumask_clear_cpu(cpu, this_scx->cpus_to_wait); + } } resched_curr(rq); @@ -5207,18 +5253,19 @@ static void kick_cpus_irq_workfn(struct irq_work *irq_work) for_each_cpu(cpu, this_scx->cpus_to_wait) { unsigned long *wait_pnt_seq = &cpu_rq(cpu)->scx.pnt_seq; - if (cpu != cpu_of(this_rq)) { - /* - * Pairs with smp_store_release() issued by this CPU in - * switch_class() on the resched path. - * - * We busy-wait here to guarantee that no other task can - * be scheduled on our core before the target CPU has - * entered the resched path. - */ - while (smp_load_acquire(wait_pnt_seq) == pseqs[cpu]) - cpu_relax(); - } + /* + * Busy-wait until the task running at the time of kicking is no + * longer running. This can be used to implement e.g. core + * scheduling. + * + * smp_cond_load_acquire() pairs with store_releases in + * pick_task_scx() and put_prev_task_scx(). The former breaks + * the wait if SCX's scheduling path is entered even if the same + * task is picked subsequently. The latter is necessary to break + * the wait when $cpu is taken by a higher sched class. + */ + if (cpu != cpu_of(this_rq)) + smp_cond_load_acquire(wait_pnt_seq, VAL != pseqs[cpu]); cpumask_clear_cpu(cpu, this_scx->cpus_to_wait); } diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h index b3617abed51081..601cfae8cc7656 100644 --- a/kernel/sched/ext_internal.h +++ b/kernel/sched/ext_internal.h @@ -986,8 +986,10 @@ enum scx_kick_flags { SCX_KICK_PREEMPT = 1LLU << 1, /* - * Wait for the CPU to be rescheduled. The scx_bpf_kick_cpu() call will - * return after the target CPU finishes picking the next task. + * The scx_bpf_kick_cpu() call will return after the current SCX task of + * the target CPU switches out. This can be used to implement e.g. core + * scheduling. This has no effect if the current task on the target CPU + * is not on SCX. */ SCX_KICK_WAIT = 1LLU << 2, }; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 5b752324270b08..82038166d7b0cf 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -554,7 +554,7 @@ static inline bool entity_before(const struct sched_entity *a, static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se) { - return (s64)(se->vruntime - cfs_rq->min_vruntime); + return (s64)(se->vruntime - cfs_rq->zero_vruntime); } #define __node_2_se(node) \ @@ -606,13 +606,13 @@ static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se) * * Which we track using: * - * v0 := cfs_rq->min_vruntime + * v0 := cfs_rq->zero_vruntime * \Sum (v_i - v0) * w_i := cfs_rq->avg_vruntime * \Sum w_i := cfs_rq->avg_load * - * Since min_vruntime is a monotonic increasing variable that closely tracks - * the per-task service, these deltas: (v_i - v), will be in the order of the - * maximal (virtual) lag induced in the system due to quantisation. + * Since zero_vruntime closely tracks the per-task service, these + * deltas: (v_i - v), will be in the order of the maximal (virtual) lag + * induced in the system due to quantisation. * * Also, we use scale_load_down() to reduce the size. * @@ -671,7 +671,7 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) avg = div_s64(avg, load); } - return cfs_rq->min_vruntime + avg; + return cfs_rq->zero_vruntime + avg; } /* @@ -732,7 +732,7 @@ static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime) load += weight; } - return avg >= (s64)(vruntime - cfs_rq->min_vruntime) * load; + return avg >= (s64)(vruntime - cfs_rq->zero_vruntime) * load; } int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -740,42 +740,14 @@ int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se) return vruntime_eligible(cfs_rq, se->vruntime); } -static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime) +static void update_zero_vruntime(struct cfs_rq *cfs_rq) { - u64 min_vruntime = cfs_rq->min_vruntime; - /* - * open coded max_vruntime() to allow updating avg_vruntime - */ - s64 delta = (s64)(vruntime - min_vruntime); - if (delta > 0) { - avg_vruntime_update(cfs_rq, delta); - min_vruntime = vruntime; - } - return min_vruntime; -} + u64 vruntime = avg_vruntime(cfs_rq); + s64 delta = (s64)(vruntime - cfs_rq->zero_vruntime); -static void update_min_vruntime(struct cfs_rq *cfs_rq) -{ - struct sched_entity *se = __pick_root_entity(cfs_rq); - struct sched_entity *curr = cfs_rq->curr; - u64 vruntime = cfs_rq->min_vruntime; + avg_vruntime_update(cfs_rq, delta); - if (curr) { - if (curr->on_rq) - vruntime = curr->vruntime; - else - curr = NULL; - } - - if (se) { - if (!curr) - vruntime = se->min_vruntime; - else - vruntime = min_vruntime(vruntime, se->min_vruntime); - } - - /* ensure we never gain time by being placed backwards. */ - cfs_rq->min_vruntime = __update_min_vruntime(cfs_rq, vruntime); + cfs_rq->zero_vruntime = vruntime; } static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq) @@ -848,6 +820,7 @@ RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity, static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) { avg_vruntime_add(cfs_rq, se); + update_zero_vruntime(cfs_rq); se->min_vruntime = se->vruntime; se->min_slice = se->slice; rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline, @@ -859,6 +832,7 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline, &min_vruntime_cb); avg_vruntime_sub(cfs_rq, se); + update_zero_vruntime(cfs_rq); } struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq) @@ -1226,7 +1200,6 @@ static void update_curr(struct cfs_rq *cfs_rq) curr->vruntime += calc_delta_fair(delta_exec, curr); resched = update_deadline(cfs_rq, curr); - update_min_vruntime(cfs_rq); if (entity_is_task(curr)) { /* @@ -3808,15 +3781,6 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, if (!curr) __enqueue_entity(cfs_rq, se); cfs_rq->nr_queued++; - - /* - * The entity's vruntime has been adjusted, so let's check - * whether the rq-wide min_vruntime needs updated too. Since - * the calculations above require stable min_vruntime rather - * than up-to-date one, we do the update at the end of the - * reweight process. - */ - update_min_vruntime(cfs_rq); } } @@ -4059,6 +4023,9 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) if (child_cfs_rq_on_list(cfs_rq)) return false; + if (cfs_rq->tg_load_avg_contrib) + return false; + return true; } @@ -5429,15 +5396,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) update_cfs_group(se); - /* - * Now advance min_vruntime if @se was the entity holding it back, - * except when: DEQUEUE_SAVE && !DEQUEUE_MOVE, in this case we'll be - * put back on, and if we advance min_vruntime, we'll be placed back - * further than we started -- i.e. we'll be penalized. - */ - if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE) - update_min_vruntime(cfs_rq); - if (flags & DEQUEUE_DELAYED) finish_delayed_dequeue_entity(se); @@ -8943,12 +8901,6 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf goto again; } - /* - * rq is about to be idle, check if we need to update the - * lost_idle_time of clock_pelt - */ - update_idle_rq_clock_pelt(rq); - return NULL; } @@ -8990,7 +8942,7 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct t */ static void yield_task_fair(struct rq *rq) { - struct task_struct *curr = rq->curr; + struct task_struct *curr = rq->donor; struct cfs_rq *cfs_rq = task_cfs_rq(curr); struct sched_entity *se = &curr->se; @@ -9014,7 +8966,18 @@ static void yield_task_fair(struct rq *rq) */ rq_clock_skip_update(rq); - se->deadline += calc_delta_fair(se->slice, se); + /* + * Forfeit the remaining vruntime, only if the entity is eligible. This + * condition is necessary because in core scheduling we prefer to run + * ineligible tasks rather than force idling. If this happens we may + * end up in a loop where the core scheduler picks the yielding task, + * which yields immediately again; without the condition the vruntime + * ends up quickly running away. + */ + if (entity_eligible(cfs_rq, se)) { + se->vruntime = se->deadline; + se->deadline += calc_delta_fair(se->slice, se); + } } static bool yield_to_task_fair(struct rq *rq, struct task_struct *p) @@ -11729,6 +11692,21 @@ static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd } } +/* + * This flag serializes load-balancing passes over large domains + * (above the NODE topology level) - only one load-balancing instance + * may run at a time, to reduce overhead on very large systems with + * lots of CPUs and large NUMA distances. + * + * - Note that load-balancing passes triggered while another one + * is executing are skipped and not re-tried. + * + * - Also note that this does not serialize rebalance_domains() + * execution, as non-SD_SERIALIZE domains will still be + * load-balanced in parallel. + */ +static atomic_t sched_balance_running = ATOMIC_INIT(0); + /* * Check this_cpu to ensure it is balanced within domain. Attempt to move * tasks if there is an imbalance. @@ -11754,6 +11732,7 @@ static int sched_balance_rq(int this_cpu, struct rq *this_rq, .fbq_type = all, .tasks = LIST_HEAD_INIT(env.tasks), }; + bool need_unlock = false; cpumask_and(cpus, sched_domain_span(sd), cpu_active_mask); @@ -11765,6 +11744,14 @@ static int sched_balance_rq(int this_cpu, struct rq *this_rq, goto out_balanced; } + if (!need_unlock && (sd->flags & SD_SERIALIZE)) { + int zero = 0; + if (!atomic_try_cmpxchg_acquire(&sched_balance_running, &zero, 1)) + goto out_balanced; + + need_unlock = true; + } + group = sched_balance_find_src_group(&env); if (!group) { schedstat_inc(sd->lb_nobusyg[idle]); @@ -12005,6 +11992,9 @@ static int sched_balance_rq(int this_cpu, struct rq *this_rq, sd->balance_interval < sd->max_interval) sd->balance_interval *= 2; out: + if (need_unlock) + atomic_set_release(&sched_balance_running, 0); + return ld_moved; } @@ -12129,21 +12119,6 @@ static int active_load_balance_cpu_stop(void *data) return 0; } -/* - * This flag serializes load-balancing passes over large domains - * (above the NODE topology level) - only one load-balancing instance - * may run at a time, to reduce overhead on very large systems with - * lots of CPUs and large NUMA distances. - * - * - Note that load-balancing passes triggered while another one - * is executing are skipped and not re-tried. - * - * - Also note that this does not serialize rebalance_domains() - * execution, as non-SD_SERIALIZE domains will still be - * load-balanced in parallel. - */ -static atomic_t sched_balance_running = ATOMIC_INIT(0); - /* * Scale the max sched_balance_rq interval with the number of CPUs in the system. * This trades load-balance latency on larger machines for less cross talk. @@ -12153,30 +12128,43 @@ void update_max_interval(void) max_load_balance_interval = HZ*num_online_cpus()/10; } -static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost) +static inline void update_newidle_stats(struct sched_domain *sd, unsigned int success) { + sd->newidle_call++; + sd->newidle_success += success; + + if (sd->newidle_call >= 1024) { + sd->newidle_ratio = sd->newidle_success; + sd->newidle_call /= 2; + sd->newidle_success /= 2; + } +} + +static inline bool +update_newidle_cost(struct sched_domain *sd, u64 cost, unsigned int success) +{ + unsigned long next_decay = sd->last_decay_max_lb_cost + HZ; + unsigned long now = jiffies; + + if (cost) + update_newidle_stats(sd, success); + if (cost > sd->max_newidle_lb_cost) { /* * Track max cost of a domain to make sure to not delay the * next wakeup on the CPU. - * - * sched_balance_newidle() bumps the cost whenever newidle - * balance fails, and we don't want things to grow out of - * control. Use the sysctl_sched_migration_cost as the upper - * limit, plus a litle extra to avoid off by ones. */ - sd->max_newidle_lb_cost = - min(cost, sysctl_sched_migration_cost + 200); - sd->last_decay_max_lb_cost = jiffies; - } else if (time_after(jiffies, sd->last_decay_max_lb_cost + HZ)) { + sd->max_newidle_lb_cost = cost; + sd->last_decay_max_lb_cost = now; + + } else if (time_after(now, next_decay)) { /* * Decay the newidle max times by ~1% per second to ensure that * it is not outdated and the current max cost is actually * shorter. */ sd->max_newidle_lb_cost = (sd->max_newidle_lb_cost * 253) / 256; - sd->last_decay_max_lb_cost = jiffies; - + sd->last_decay_max_lb_cost = now; return true; } @@ -12199,7 +12187,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle) /* Earliest time when we have to do rebalance again */ unsigned long next_balance = jiffies + 60*HZ; int update_next_balance = 0; - int need_serialize, need_decay = 0; + int need_decay = 0; u64 max_cost = 0; rcu_read_lock(); @@ -12208,7 +12196,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle) * Decay the newidle max times here because this is a regular * visit to all the domains. */ - need_decay = update_newidle_cost(sd, 0); + need_decay = update_newidle_cost(sd, 0, 0); max_cost += sd->max_newidle_lb_cost; /* @@ -12223,13 +12211,6 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle) } interval = get_sd_balance_interval(sd, busy); - - need_serialize = sd->flags & SD_SERIALIZE; - if (need_serialize) { - if (atomic_cmpxchg_acquire(&sched_balance_running, 0, 1)) - goto out; - } - if (time_after_eq(jiffies, sd->last_balance + interval)) { if (sched_balance_rq(cpu, rq, sd, idle, &continue_balancing)) { /* @@ -12243,9 +12224,6 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle) sd->last_balance = jiffies; interval = get_sd_balance_interval(sd, busy); } - if (need_serialize) - atomic_set_release(&sched_balance_running, 0); -out: if (time_after(next_balance, sd->last_balance + interval)) { next_balance = sd->last_balance + interval; update_next_balance = 1; @@ -12824,14 +12802,16 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf) rcu_read_lock(); sd = rcu_dereference_check_sched_domain(this_rq->sd); + if (!sd) { + rcu_read_unlock(); + goto out; + } if (!get_rd_overloaded(this_rq->rd) || - (sd && this_rq->avg_idle < sd->max_newidle_lb_cost)) { + this_rq->avg_idle < sd->max_newidle_lb_cost) { - if (sd) - update_next_balance(sd, &next_balance); + update_next_balance(sd, &next_balance); rcu_read_unlock(); - goto out; } rcu_read_unlock(); @@ -12851,6 +12831,22 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf) break; if (sd->flags & SD_BALANCE_NEWIDLE) { + unsigned int weight = 1; + + if (sched_feat(NI_RANDOM)) { + /* + * Throw a 1k sided dice; and only run + * newidle_balance according to the success + * rate. + */ + u32 d1k = sched_rng() % 1024; + weight = 1 + sd->newidle_ratio; + if (d1k > weight) { + update_newidle_stats(sd, 0); + continue; + } + weight = (1024 + weight/2) / weight; + } pulled_task = sched_balance_rq(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, @@ -12862,13 +12858,10 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf) t0 = t1; /* - * Failing newidle means it is not effective; - * bump the cost so we end up doing less of it. + * Track max cost of a domain to make sure to not delay the + * next wakeup on the CPU. */ - if (!pulled_task) - domain_cost = (3 * sd->max_newidle_lb_cost) / 2; - - update_newidle_cost(sd, domain_cost); + update_newidle_cost(sd, domain_cost, weight * !!pulled_task); } /* @@ -13012,7 +13005,170 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr) } /* - * se_fi_update - Update the cfs_rq->min_vruntime_fi in a CFS hierarchy if needed. + * Consider any infeasible weight scenario. Take for instance two tasks, + * each bound to their respective sibling, one with weight 1 and one with + * weight 2. Then the lower weight task will run ahead of the higher weight + * task without bound. + * + * This utterly destroys the concept of a shared time base. + * + * Remember; all this is about a proportionally fair scheduling, where each + * tasks receives: + * + * w_i + * dt_i = ---------- dt (1) + * \Sum_j w_j + * + * which we do by tracking a virtual time, s_i: + * + * 1 + * s_i = --- d[t]_i (2) + * w_i + * + * Where d[t] is a delta of discrete time, while dt is an infinitesimal. + * The immediate corollary is that the ideal schedule S, where (2) to use + * an infinitesimal delta, is: + * + * 1 + * S = ---------- dt (3) + * \Sum_i w_i + * + * From which we can define the lag, or deviation from the ideal, as: + * + * lag(i) = S - s_i (4) + * + * And since the one and only purpose is to approximate S, we get that: + * + * \Sum_i w_i lag(i) := 0 (5) + * + * If this were not so, we no longer converge to S, and we can no longer + * claim our scheduler has any of the properties we derive from S. This is + * exactly what you did above, you broke it! + * + * + * Let's continue for a while though; to see if there is anything useful to + * be learned. We can combine (1)-(3) or (4)-(5) and express S in s_i: + * + * \Sum_i w_i s_i + * S = -------------- (6) + * \Sum_i w_i + * + * Which gives us a way to compute S, given our s_i. Now, if you've read + * our code, you know that we do not in fact do this, the reason for this + * is two-fold. Firstly, computing S in that way requires a 64bit division + * for every time we'd use it (see 12), and secondly, this only describes + * the steady-state, it doesn't handle dynamics. + * + * Anyway, in (6): s_i -> x + (s_i - x), to get: + * + * \Sum_i w_i (s_i - x) + * S - x = -------------------- (7) + * \Sum_i w_i + * + * Which shows that S and s_i transform alike (which makes perfect sense + * given that S is basically the (weighted) average of s_i). + * + * So the thing to remember is that the above is strictly UP. It is + * possible to generalize to multiple runqueues -- however it gets really + * yuck when you have to add affinity support, as illustrated by our very + * first counter-example. + * + * Luckily I think we can avoid needing a full multi-queue variant for + * core-scheduling (or load-balancing). The crucial observation is that we + * only actually need this comparison in the presence of forced-idle; only + * then do we need to tell if the stalled rq has higher priority over the + * other. + * + * [XXX assumes SMT2; better consider the more general case, I suspect + * it'll work out because our comparison is always between 2 rqs and the + * answer is only interesting if one of them is forced-idle] + * + * And (under assumption of SMT2) when there is forced-idle, there is only + * a single queue, so everything works like normal. + * + * Let, for our runqueue 'k': + * + * T_k = \Sum_i w_i s_i + * W_k = \Sum_i w_i ; for all i of k (8) + * + * Then we can write (6) like: + * + * T_k + * S_k = --- (9) + * W_k + * + * From which immediately follows that: + * + * T_k + T_l + * S_k+l = --------- (10) + * W_k + W_l + * + * On which we can define a combined lag: + * + * lag_k+l(i) := S_k+l - s_i (11) + * + * And that gives us the tools to compare tasks across a combined runqueue. + * + * + * Combined this gives the following: + * + * a) when a runqueue enters force-idle, sync it against it's sibling rq(s) + * using (7); this only requires storing single 'time'-stamps. + * + * b) when comparing tasks between 2 runqueues of which one is forced-idle, + * compare the combined lag, per (11). + * + * Now, of course cgroups (I so hate them) make this more interesting in + * that a) seems to suggest we need to iterate all cgroup on a CPU at such + * boundaries, but I think we can avoid that. The force-idle is for the + * whole CPU, all it's rqs. So we can mark it in the root and lazily + * propagate downward on demand. + */ + +/* + * So this sync is basically a relative reset of S to 0. + * + * So with 2 queues, when one goes idle, we drop them both to 0 and one + * then increases due to not being idle, and the idle one builds up lag to + * get re-elected. So far so simple, right? + * + * When there's 3, we can have the situation where 2 run and one is idle, + * we sync to 0 and let the idle one build up lag to get re-election. Now + * suppose another one also drops idle. At this point dropping all to 0 + * again would destroy the built-up lag from the queue that was already + * idle, not good. + * + * So instead of syncing everything, we can: + * + * less := !((s64)(s_a - s_b) <= 0) + * + * (v_a - S_a) - (v_b - S_b) == v_a - v_b - S_a + S_b + * == v_a - (v_b - S_a + S_b) + * + * IOW, we can recast the (lag) comparison to a one-sided difference. + * So if then, instead of syncing the whole queue, sync the idle queue + * against the active queue with S_a + S_b at the point where we sync. + * + * (XXX consider the implication of living in a cyclic group: N / 2^n N) + * + * This gives us means of syncing single queues against the active queue, + * and for already idle queues to preserve their build-up lag. + * + * Of course, then we get the situation where there's 2 active and one + * going idle, who do we pick to sync against? Theory would have us sync + * against the combined S, but as we've already demonstrated, there is no + * such thing in infeasible weight scenarios. + * + * One thing I've considered; and this is where that core_active rudiment + * came from, is having active queues sync up between themselves after + * every tick. This limits the observed divergence due to the work + * conservancy. + * + * On top of that, we can improve upon things by employing (10) here. + */ + +/* + * se_fi_update - Update the cfs_rq->zero_vruntime_fi in a CFS hierarchy if needed. */ static void se_fi_update(const struct sched_entity *se, unsigned int fi_seq, bool forceidle) @@ -13026,7 +13182,7 @@ static void se_fi_update(const struct sched_entity *se, unsigned int fi_seq, cfs_rq->forceidle_seq = fi_seq; } - cfs_rq->min_vruntime_fi = cfs_rq->min_vruntime; + cfs_rq->zero_vruntime_fi = cfs_rq->zero_vruntime; } } @@ -13079,11 +13235,11 @@ bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b, /* * Find delta after normalizing se's vruntime with its cfs_rq's - * min_vruntime_fi, which would have been updated in prior calls + * zero_vruntime_fi, which would have been updated in prior calls * to se_fi_update(). */ delta = (s64)(sea->vruntime - seb->vruntime) + - (s64)(cfs_rqb->min_vruntime_fi - cfs_rqa->min_vruntime_fi); + (s64)(cfs_rqb->zero_vruntime_fi - cfs_rqa->zero_vruntime_fi); return delta > 0; } @@ -13319,7 +13475,7 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) void init_cfs_rq(struct cfs_rq *cfs_rq) { cfs_rq->tasks_timeline = RB_ROOT_CACHED; - cfs_rq->min_vruntime = (u64)(-(1LL << 20)); + cfs_rq->zero_vruntime = (u64)(-(1LL << 20)); raw_spin_lock_init(&cfs_rq->removed.lock); } diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 3c12d9f93331d6..136a6584be7974 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -121,3 +121,8 @@ SCHED_FEAT(WA_BIAS, true) SCHED_FEAT(UTIL_EST, true) SCHED_FEAT(LATENCY_WARN, false) + +/* + * Do newidle balancing proportional to its success rate using randomization. + */ +SCHED_FEAT(NI_RANDOM, true) diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index c39b089d4f09b6..ac9690805be4f3 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -464,6 +464,12 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir scx_update_idle(rq, true, true); schedstat_inc(rq->sched_goidle); next->se.exec_start = rq_clock_task(rq); + + /* + * rq is about to be idle, check if we need to update the + * lost_idle_time of clock_pelt + */ + update_idle_rq_clock_pelt(rq); } struct task_struct *pick_task_idle(struct rq *rq) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 7936d43337313c..d4d994fb8999a4 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1490,7 +1490,7 @@ static void requeue_task_rt(struct rq *rq, struct task_struct *p, int head) static void yield_task_rt(struct rq *rq) { - requeue_task_rt(rq, rq->curr, 0); + requeue_task_rt(rq, rq->donor, 0); } static int find_lowest_rq(struct task_struct *task); @@ -2100,6 +2100,7 @@ static void push_rt_tasks(struct rq *rq) */ static int rto_next_cpu(struct root_domain *rd) { + int this_cpu = smp_processor_id(); int next; int cpu; @@ -2123,6 +2124,10 @@ static int rto_next_cpu(struct root_domain *rd) rd->rto_cpu = cpu; + /* Do not send IPI to self */ + if (cpu == this_cpu) + continue; + if (cpu < nr_cpu_ids) return cpu; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index adfb6e3409d729..2f8b06b12a98f4 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -5,6 +5,7 @@ #ifndef _KERNEL_SCHED_SCHED_H #define _KERNEL_SCHED_SCHED_H +#include #include #include #include @@ -682,10 +683,10 @@ struct cfs_rq { s64 avg_vruntime; u64 avg_load; - u64 min_vruntime; + u64 zero_vruntime; #ifdef CONFIG_SCHED_CORE unsigned int forceidle_seq; - u64 min_vruntime_fi; + u64 zero_vruntime_fi; #endif struct rb_root_cached tasks_timeline; @@ -1349,6 +1350,12 @@ static inline bool is_migration_disabled(struct task_struct *p) } DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +DECLARE_PER_CPU(struct rnd_state, sched_rnd_state); + +static inline u32 sched_rng(void) +{ + return prandom_u32_state(this_cpu_ptr(&sched_rnd_state)); +} #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) #define this_rq() this_cpu_ptr(&runqueues) diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 26f3fd4d34cead..73bd6bca4d3107 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -180,8 +180,13 @@ static inline void psi_dequeue(struct task_struct *p, int flags) * avoid walking all ancestors twice, psi_task_switch() handles * TSK_RUNNING and TSK_IOWAIT for us when it moves TSK_ONCPU. * Do nothing here. + * + * In the SCHED_PROXY_EXECUTION case we may do sleeping + * dequeues that are not followed by a task switch, so check + * TSK_ONCPU is set to ensure the task switch is imminent. + * Otherwise clear the flags as usual. */ - if (flags & DEQUEUE_SLEEP) + if ((flags & DEQUEUE_SLEEP) && (p->psi_flags & TSK_ONCPU)) return; /* diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index 77ae87f36e8412..6805a63d47af70 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -688,7 +688,7 @@ int __sched_setscheduler(struct task_struct *p, * itself. */ newprio = rt_effective_prio(p, newprio); - if (newprio == oldprio) + if (newprio == oldprio && !dl_prio(newprio)) queue_flags &= ~DEQUEUE_MOVE; } @@ -1351,7 +1351,7 @@ static void do_sched_yield(void) rq = this_rq_lock_irq(&rf); schedstat_inc(rq->yld_count); - current->sched_class->yield_task(rq); + rq->donor->sched_class->yield_task(rq); preempt_disable(); rq_unlock_irq(rq, &rf); @@ -1420,12 +1420,13 @@ EXPORT_SYMBOL(yield); */ int __sched yield_to(struct task_struct *p, bool preempt) { - struct task_struct *curr = current; + struct task_struct *curr; struct rq *rq, *p_rq; int yielded = 0; scoped_guard (raw_spinlock_irqsave, &p->pi_lock) { rq = this_rq(); + curr = rq->donor; again: p_rq = task_rq(p); diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 444bdfdab73180..c7a4d2fff57189 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1662,6 +1662,12 @@ sd_init(struct sched_domain_topology_level *tl, .last_balance = jiffies, .balance_interval = sd_weight, + + /* 50% success rate */ + .newidle_call = 512, + .newidle_success = 256, + .newidle_ratio = 512, + .max_newidle_lb_cost = 0, .last_decay_max_lb_cost = jiffies, .child = child, diff --git a/kernel/scs.c b/kernel/scs.c index d7809affe74047..772488afd5b972 100644 --- a/kernel/scs.c +++ b/kernel/scs.c @@ -135,7 +135,7 @@ static void scs_check_usage(struct task_struct *tsk) if (!IS_ENABLED(CONFIG_DEBUG_STACK_USAGE)) return; - for (p = task_scs(tsk); p < __scs_magic(tsk); ++p) { + for (p = task_scs(tsk); p < __scs_magic(task_scs(tsk)); ++p) { if (!READ_ONCE_NOCHECK(*p)) break; used += sizeof(*p); diff --git a/kernel/sys.c b/kernel/sys.c index 8b58eece4e580b..93e4d60b6fead8 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include @@ -2515,6 +2516,16 @@ static int prctl_set_thp_disable(bool thp_disable, unsigned long flags, return 0; } +int __weak arch_prctl_mem_model_get(struct task_struct *t) +{ + return -EINVAL; +} + +int __weak arch_prctl_mem_model_set(struct task_struct *t, unsigned long val) +{ + return -EINVAL; +} + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2528,6 +2539,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = 0; switch (option) { + case PR_GET_MEM_MODEL: + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + error = arch_prctl_mem_model_get(me); + break; + case PR_SET_MEM_MODEL: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_prctl_mem_model_set(me, arg2); + break; case PR_SET_PDEATHSIG: if (!valid_signal(arg2)) { error = -EINVAL; diff --git a/kernel/task_work.c b/kernel/task_work.c index d1efec571a4a47..0f7519f8e7c93f 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -9,7 +9,12 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */ #ifdef CONFIG_IRQ_WORK static void task_work_set_notify_irq(struct irq_work *entry) { - test_and_set_tsk_thread_flag(current, TIF_NOTIFY_RESUME); + /* + * no-op IPI + * + * TWA_NMI_CURRENT will already have set the TIF flag, all + * this interrupt does it tickle the return-to-user path. + */ } static DEFINE_PER_CPU(struct irq_work, irq_work_NMI_resume) = IRQ_WORK_INIT_HARD(task_work_set_notify_irq); @@ -86,6 +91,7 @@ int task_work_add(struct task_struct *task, struct callback_head *work, break; #ifdef CONFIG_IRQ_WORK case TWA_NMI_CURRENT: + set_tsk_thread_flag(current, TIF_NOTIFY_RESUME); irq_work_queue(this_cpu_ptr(&irq_work_NMI_resume)); break; #endif diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index a1890a073196b1..df719496165849 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -252,7 +252,7 @@ enum wd_read_status { static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) { - int64_t md = 2 * watchdog->uncertainty_margin; + int64_t md = watchdog->uncertainty_margin; unsigned int nretries, max_retries; int64_t wd_delay, wd_seq_delay; u64 wd_end, wd_end2; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 88aa062b8a556d..21b6d934014803 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -913,7 +913,7 @@ static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base, return true; /* Extra check for softirq clock bases */ - if (base->clockid < HRTIMER_BASE_MONOTONIC_SOFT) + if (base->index < HRTIMER_BASE_MONOTONIC_SOFT) continue; if (cpu_base->softirq_activated) continue; @@ -1742,7 +1742,7 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, lockdep_assert_held(&cpu_base->lock); - debug_deactivate(timer); + debug_hrtimer_deactivate(timer); base->running = timer; /* diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index cc1afec306b3f0..425d429906d0d1 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -215,7 +215,7 @@ void sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) update_clock_read_data(&rd); - if (sched_clock_timer.function != NULL) { + if (ACCESS_PRIVATE(&sched_clock_timer, function) != NULL) { /* update timeout for clock wrap */ hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 4790da895203c2..340fef20bdcd0e 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2721,7 +2721,7 @@ static int __do_adjtimex(struct tk_data *tkd, struct __kernel_timex *txc, timekeeping_update_from_shadow(tkd, TK_CLOCK_WAS_SET); result->clock_set = true; } else { - tk_update_leap_state_all(&tk_core); + tk_update_leap_state_all(tkd); } /* Update the multiplier immediately if frequency was set directly */ diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index c0c54dc5314c3f..49635a2b7ee28d 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -420,6 +420,8 @@ static struct list_head *tmigr_level_list __read_mostly; static unsigned int tmigr_hierarchy_levels __read_mostly; static unsigned int tmigr_crossnode_level __read_mostly; +static struct tmigr_group *tmigr_root; + static DEFINE_PER_CPU(struct tmigr_cpu, tmigr_cpu); #define TMIGR_NONE 0xFF @@ -522,11 +524,9 @@ struct tmigr_walk { typedef bool (*up_f)(struct tmigr_group *, struct tmigr_group *, struct tmigr_walk *); -static void __walk_groups(up_f up, struct tmigr_walk *data, - struct tmigr_cpu *tmc) +static void __walk_groups_from(up_f up, struct tmigr_walk *data, + struct tmigr_group *child, struct tmigr_group *group) { - struct tmigr_group *child = NULL, *group = tmc->tmgroup; - do { WARN_ON_ONCE(group->level >= tmigr_hierarchy_levels); @@ -544,6 +544,12 @@ static void __walk_groups(up_f up, struct tmigr_walk *data, } while (group); } +static void __walk_groups(up_f up, struct tmigr_walk *data, + struct tmigr_cpu *tmc) +{ + __walk_groups_from(up, data, NULL, tmc->tmgroup); +} + static void walk_groups(up_f up, struct tmigr_walk *data, struct tmigr_cpu *tmc) { lockdep_assert_held(&tmc->lock); @@ -1498,21 +1504,6 @@ static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl, s.seq = 0; atomic_set(&group->migr_state, s.state); - /* - * If this is a new top-level, prepare its groupmask in advance. - * This avoids accidents where yet another new top-level is - * created in the future and made visible before the current groupmask. - */ - if (list_empty(&tmigr_level_list[lvl])) { - group->groupmask = BIT(0); - /* - * The previous top level has prepared its groupmask already, - * simply account it as the first child. - */ - if (lvl > 0) - group->num_children = 1; - } - timerqueue_init_head(&group->events); timerqueue_init(&group->groupevt.nextevt); group->groupevt.nextevt.expires = KTIME_MAX; @@ -1567,25 +1558,51 @@ static struct tmigr_group *tmigr_get_group(unsigned int cpu, int node, return group; } +static bool tmigr_init_root(struct tmigr_group *group, bool activate) +{ + if (!group->parent && group != tmigr_root) { + /* + * This is the new top-level, prepare its groupmask in advance + * to avoid accidents where yet another new top-level is + * created in the future and made visible before this groupmask. + */ + group->groupmask = BIT(0); + WARN_ON_ONCE(activate); + + return true; + } + + return false; + +} + static void tmigr_connect_child_parent(struct tmigr_group *child, struct tmigr_group *parent, bool activate) { - struct tmigr_walk data; - - raw_spin_lock_irq(&child->lock); - raw_spin_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING); + if (tmigr_init_root(parent, activate)) { + /* + * The previous top level had prepared its groupmask already, + * simply account it in advance as the first child. If some groups + * have been created between the old and new root due to node + * mismatch, the new root's child will be intialized accordingly. + */ + parent->num_children = 1; + } - if (activate) { + /* Connecting old root to new root ? */ + if (!parent->parent && activate) { /* - * @child is the old top and @parent the new one. In this - * case groupmask is pre-initialized and @child already - * accounted, along with its new sibling corresponding to the - * CPU going up. + * @child is the old top, or in case of node mismatch, some + * intermediate group between the old top and the new one in + * @parent. In this case the @child must be pre-accounted above + * as the first child. Its new inactive sibling corresponding + * to the CPU going up has been accounted as the second child. */ - WARN_ON_ONCE(child->groupmask != BIT(0) || parent->num_children != 2); + WARN_ON_ONCE(parent->num_children != 2); + child->groupmask = BIT(0); } else { - /* Adding @child for the CPU going up to @parent. */ + /* Common case adding @child for the CPU going up to @parent. */ child->groupmask = BIT(parent->num_children++); } @@ -1596,87 +1613,61 @@ static void tmigr_connect_child_parent(struct tmigr_group *child, */ smp_store_release(&child->parent, parent); - raw_spin_unlock(&parent->lock); - raw_spin_unlock_irq(&child->lock); - trace_tmigr_connect_child_parent(child); - - if (!activate) - return; - - /* - * To prevent inconsistent states, active children need to be active in - * the new parent as well. Inactive children are already marked inactive - * in the parent group: - * - * * When new groups were created by tmigr_setup_groups() starting from - * the lowest level (and not higher then one level below the current - * top level), then they are not active. They will be set active when - * the new online CPU comes active. - * - * * But if a new group above the current top level is required, it is - * mandatory to propagate the active state of the already existing - * child to the new parent. So tmigr_connect_child_parent() is - * executed with the formerly top level group (child) and the newly - * created group (parent). - * - * * It is ensured that the child is active, as this setup path is - * executed in hotplug prepare callback. This is exectued by an - * already connected and !idle CPU. Even if all other CPUs go idle, - * the CPU executing the setup will be responsible up to current top - * level group. And the next time it goes inactive, it will release - * the new childmask and parent to subsequent walkers through this - * @child. Therefore propagate active state unconditionally. - */ - data.childmask = child->groupmask; - - /* - * There is only one new level per time (which is protected by - * tmigr_mutex). When connecting the child and the parent and set the - * child active when the parent is inactive, the parent needs to be the - * uppermost level. Otherwise there went something wrong! - */ - WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent); } -static int tmigr_setup_groups(unsigned int cpu, unsigned int node) +static int tmigr_setup_groups(unsigned int cpu, unsigned int node, + struct tmigr_group *start, bool activate) { struct tmigr_group *group, *child, **stack; - int top = 0, err = 0, i = 0; - struct list_head *lvllist; + int i, top = 0, err = 0, start_lvl = 0; + bool root_mismatch = false; stack = kcalloc(tmigr_hierarchy_levels, sizeof(*stack), GFP_KERNEL); if (!stack) return -ENOMEM; - do { + if (start) { + stack[start->level] = start; + start_lvl = start->level + 1; + } + + if (tmigr_root) + root_mismatch = tmigr_root->numa_node != node; + + for (i = start_lvl; i < tmigr_hierarchy_levels; i++) { group = tmigr_get_group(cpu, node, i); if (IS_ERR(group)) { err = PTR_ERR(group); + i--; break; } top = i; - stack[i++] = group; + stack[i] = group; /* * When booting only less CPUs of a system than CPUs are - * available, not all calculated hierarchy levels are required. + * available, not all calculated hierarchy levels are required, + * unless a node mismatch is detected. * * The loop is aborted as soon as the highest level, which might * be different from tmigr_hierarchy_levels, contains only a - * single group. + * single group, unless the nodes mismatch below tmigr_crossnode_level */ - if (group->parent || list_is_singular(&tmigr_level_list[i - 1])) + if (group->parent) break; + if ((!root_mismatch || i >= tmigr_crossnode_level) && + list_is_singular(&tmigr_level_list[i])) + break; + } - } while (i < tmigr_hierarchy_levels); - - /* Assert single root */ - WARN_ON_ONCE(!err && !group->parent && !list_is_singular(&tmigr_level_list[top])); + /* Assert single root without parent */ + if (WARN_ON_ONCE(i >= tmigr_hierarchy_levels)) + return -EINVAL; - while (i > 0) { - group = stack[--i]; + for (; i >= start_lvl; i--) { + group = stack[i]; if (err < 0) { list_del(&group->list); @@ -1692,12 +1683,10 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) if (i == 0) { struct tmigr_cpu *tmc = per_cpu_ptr(&tmigr_cpu, cpu); - raw_spin_lock_irq(&group->lock); - tmc->tmgroup = group; tmc->groupmask = BIT(group->num_children++); - raw_spin_unlock_irq(&group->lock); + tmigr_init_root(group, activate); trace_tmigr_connect_cpu_parent(tmc); @@ -1705,42 +1694,55 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) continue; } else { child = stack[i - 1]; - /* Will be activated at online time */ - tmigr_connect_child_parent(child, group, false); + tmigr_connect_child_parent(child, group, activate); } + } - /* check if uppermost level was newly created */ - if (top != i) - continue; - - WARN_ON_ONCE(top == 0); + if (err < 0) + goto out; - lvllist = &tmigr_level_list[top]; + if (activate) { + struct tmigr_walk data; /* - * Newly created root level should have accounted the upcoming - * CPU's child group and pre-accounted the old root. + * To prevent inconsistent states, active children need to be active in + * the new parent as well. Inactive children are already marked inactive + * in the parent group: + * + * * When new groups were created by tmigr_setup_groups() starting from + * the lowest level, then they are not active. They will be set active + * when the new online CPU comes active. + * + * * But if new groups above the current top level are required, it is + * mandatory to propagate the active state of the already existing + * child to the new parents. So tmigr_active_up() activates the + * new parents while walking up from the old root to the new. + * + * * It is ensured that @start is active, as this setup path is + * executed in hotplug prepare callback. This is executed by an + * already connected and !idle CPU. Even if all other CPUs go idle, + * the CPU executing the setup will be responsible up to current top + * level group. And the next time it goes inactive, it will release + * the new childmask and parent to subsequent walkers through this + * @child. Therefore propagate active state unconditionally. */ - if (group->num_children == 2 && list_is_singular(lvllist)) { - /* - * The target CPU must never do the prepare work, except - * on early boot when the boot CPU is the target. Otherwise - * it may spuriously activate the old top level group inside - * the new one (nevertheless whether old top level group is - * active or not) and/or release an uninitialized childmask. - */ - WARN_ON_ONCE(cpu == raw_smp_processor_id()); - - lvllist = &tmigr_level_list[top - 1]; - list_for_each_entry(child, lvllist, list) { - if (child->parent) - continue; + WARN_ON_ONCE(!start->parent); + data.childmask = start->groupmask; + __walk_groups_from(tmigr_active_up, &data, start, start->parent); + } - tmigr_connect_child_parent(child, group, true); - } + /* Root update */ + if (list_is_singular(&tmigr_level_list[top])) { + group = list_first_entry(&tmigr_level_list[top], + typeof(*group), list); + WARN_ON_ONCE(group->parent); + if (tmigr_root) { + /* Old root should be the same or below */ + WARN_ON_ONCE(tmigr_root->level > top); } + tmigr_root = group; } - +out: kfree(stack); return err; @@ -1748,12 +1750,26 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) static int tmigr_add_cpu(unsigned int cpu) { + struct tmigr_group *old_root = tmigr_root; int node = cpu_to_node(cpu); int ret; - mutex_lock(&tmigr_mutex); - ret = tmigr_setup_groups(cpu, node); - mutex_unlock(&tmigr_mutex); + guard(mutex)(&tmigr_mutex); + + ret = tmigr_setup_groups(cpu, node, NULL, false); + + /* Root has changed? Connect the old one to the new */ + if (ret >= 0 && old_root && old_root != tmigr_root) { + /* + * The target CPU must never do the prepare work, except + * on early boot when the boot CPU is the target. Otherwise + * it may spuriously activate the old top level group inside + * the new one (nevertheless whether old top level group is + * active or not) and/or release an uninitialized childmask. + */ + WARN_ON_ONCE(cpu == raw_smp_processor_id()); + ret = tmigr_setup_groups(-1, old_root->numa_node, old_root, true); + } return ret; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 4f87c16d915a02..e7f1fe44352afe 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -965,7 +965,7 @@ static const struct bpf_func_proto bpf_d_path_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_d_path_btf_ids[0], - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .allowed = bpf_d_path_allowed, }; @@ -1022,7 +1022,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = { .func = bpf_snprintf_btf, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, @@ -1526,7 +1526,7 @@ static const struct bpf_func_proto bpf_read_branch_records_proto = { .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM_OR_NULL, + .arg2_type = ARG_PTR_TO_MEM_OR_NULL | MEM_WRITE, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; @@ -1661,7 +1661,7 @@ static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 484ad7a18463a9..599f2939cd940c 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -1019,6 +1019,7 @@ void fgraph_init_ops(struct ftrace_ops *dst_ops, mutex_init(&dst_ops->local_hash.regex_lock); INIT_LIST_HEAD(&dst_ops->subop_list); dst_ops->flags |= FTRACE_OPS_FL_INITIALIZED; + dst_ops->private = src_ops->private; } #endif } @@ -1376,6 +1377,13 @@ int register_ftrace_graph(struct fgraph_ops *gops) ftrace_graph_active++; + /* Always save the function, and reset at unregistering */ + gops->saved_func = gops->entryfunc; +#ifdef CONFIG_DYNAMIC_FTRACE + if (ftrace_pids_enabled(&gops->ops)) + gops->entryfunc = fgraph_pid_func; +#endif + if (ftrace_graph_active == 2) ftrace_graph_disable_direct(true); @@ -1395,8 +1403,6 @@ int register_ftrace_graph(struct fgraph_ops *gops) } else { init_task_vars(gops->idx); } - /* Always save the function, and reset at unregistering */ - gops->saved_func = gops->entryfunc; gops->ops.flags |= FTRACE_OPS_FL_GRAPH; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 59cfacb8a5bbdc..905f4d16795598 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1122,7 +1122,6 @@ struct ftrace_page { }; #define ENTRY_SIZE sizeof(struct dyn_ftrace) -#define ENTRIES_PER_PAGE (PAGE_SIZE / ENTRY_SIZE) static struct ftrace_page *ftrace_pages_start; static struct ftrace_page *ftrace_pages; @@ -3808,7 +3807,8 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) return 0; } -static int ftrace_allocate_records(struct ftrace_page *pg, int count) +static int ftrace_allocate_records(struct ftrace_page *pg, int count, + unsigned long *num_pages) { int order; int pages; @@ -3818,7 +3818,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) return -EINVAL; /* We want to fill as much as possible, with no empty pages */ - pages = DIV_ROUND_UP(count, ENTRIES_PER_PAGE); + pages = DIV_ROUND_UP(count * ENTRY_SIZE, PAGE_SIZE); order = fls(pages) - 1; again: @@ -3833,6 +3833,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) } ftrace_number_of_pages += 1 << order; + *num_pages += 1 << order; ftrace_number_of_groups++; cnt = (PAGE_SIZE << order) / ENTRY_SIZE; @@ -3861,12 +3862,14 @@ static void ftrace_free_pages(struct ftrace_page *pages) } static struct ftrace_page * -ftrace_allocate_pages(unsigned long num_to_init) +ftrace_allocate_pages(unsigned long num_to_init, unsigned long *num_pages) { struct ftrace_page *start_pg; struct ftrace_page *pg; int cnt; + *num_pages = 0; + if (!num_to_init) return NULL; @@ -3880,7 +3883,7 @@ ftrace_allocate_pages(unsigned long num_to_init) * waste as little space as possible. */ for (;;) { - cnt = ftrace_allocate_records(pg, num_to_init); + cnt = ftrace_allocate_records(pg, num_to_init, num_pages); if (cnt < 0) goto free_pages; @@ -7148,8 +7151,6 @@ static int ftrace_process_locs(struct module *mod, if (!count) return 0; - pages = DIV_ROUND_UP(count, ENTRIES_PER_PAGE); - /* * Sorting mcount in vmlinux at build time depend on * CONFIG_BUILDTIME_MCOUNT_SORT, while mcount loc in @@ -7162,7 +7163,7 @@ static int ftrace_process_locs(struct module *mod, test_is_sorted(start, count); } - start_pg = ftrace_allocate_pages(count); + start_pg = ftrace_allocate_pages(count, &pages); if (!start_pg) return -ENOMEM; @@ -7261,27 +7262,27 @@ static int ftrace_process_locs(struct module *mod, /* We should have used all pages unless we skipped some */ if (pg_unuse) { unsigned long pg_remaining, remaining = 0; - unsigned long skip; + long skip; /* Count the number of entries unused and compare it to skipped. */ - pg_remaining = (ENTRIES_PER_PAGE << pg->order) - pg->index; + pg_remaining = (PAGE_SIZE << pg->order) / ENTRY_SIZE - pg->index; if (!WARN(skipped < pg_remaining, "Extra allocated pages for ftrace")) { skip = skipped - pg_remaining; - for (pg = pg_unuse; pg; pg = pg->next) + for (pg = pg_unuse; pg && skip > 0; pg = pg->next) { remaining += 1 << pg->order; + skip -= (PAGE_SIZE << pg->order) / ENTRY_SIZE; + } pages -= remaining; - skip = DIV_ROUND_UP(skip, ENTRIES_PER_PAGE); - /* * Check to see if the number of pages remaining would * just fit the number of entries skipped. */ - WARN(skip != remaining, "Extra allocated pages for ftrace: %lu with %lu skipped", + WARN(pg || skip > 0, "Extra allocated pages for ftrace: %lu with %lu skipped", remaining, skipped); } /* Need to synchronize with ftrace_location_range() */ @@ -7708,7 +7709,8 @@ ftrace_func_address_lookup(struct ftrace_mod_map *mod_map, int ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, - unsigned long *off, char **modname, char *sym) + unsigned long *off, char **modname, + const unsigned char **modbuildid, char *sym) { struct ftrace_mod_map *mod_map; int ret = 0; @@ -7720,6 +7722,8 @@ ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, if (ret) { if (modname) *modname = mod_map->mod->name; + if (modbuildid) + *modbuildid = module_buildid(mod_map->mod); break; } } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index afcd3747264d2e..3ba08fc1b7d058 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3121,6 +3121,8 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, list) { list_del_init(&bpage->list); free_buffer_page(bpage); + + cond_resched(); } } out_err_unlock: diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 304e93597126e5..907923d5f8bbb9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -141,7 +141,7 @@ cpumask_var_t __read_mostly tracing_buffer_mask; * by commas. */ /* Set to string format zero to disable by default */ -char ftrace_dump_on_oops[MAX_TRACER_SIZE] = "0"; +static char ftrace_dump_on_oops[MAX_TRACER_SIZE] = "0"; /* When set, tracing will stop when a WARN*() is hit */ static int __disable_trace_on_warning; @@ -3003,6 +3003,11 @@ static void __ftrace_trace_stack(struct trace_array *tr, struct ftrace_stack *fstack; struct stack_entry *entry; int stackidx; + int bit; + + bit = trace_test_and_set_recursion(_THIS_IP_, _RET_IP_, TRACE_EVENT_START); + if (bit < 0) + return; /* * Add one, for this function and the call to save_stack_trace() @@ -3071,6 +3076,7 @@ static void __ftrace_trace_stack(struct trace_array *tr, /* Again, don't let gcc optimize things here */ barrier(); __this_cpu_dec(ftrace_stack_reserve); + trace_clear_recursion(bit); } static inline void ftrace_trace_stack(struct trace_array *tr, @@ -6055,10 +6061,10 @@ static int cmp_mod_entry(const void *key, const void *pivot) unsigned long addr = (unsigned long)key; const struct trace_mod_entry *ent = pivot; - if (addr >= ent[0].mod_addr && addr < ent[1].mod_addr) - return 0; - else - return addr - ent->mod_addr; + if (addr < ent[0].mod_addr) + return -1; + + return addr >= ent[1].mod_addr; } /** diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 85eabb454bee9f..ec372e0f2e716e 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -67,14 +67,17 @@ enum trace_type { #undef __field_fn #define __field_fn(type, item) type item; +#undef __field_packed +#define __field_packed(type, item) type item; + #undef __field_struct #define __field_struct(type, item) __field(type, item) #undef __field_desc #define __field_desc(type, container, item) -#undef __field_packed -#define __field_packed(type, container, item) +#undef __field_desc_packed +#define __field_desc_packed(type, container, item) #undef __array #define __array(type, item, size) type item[size]; diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index de294ae2c5c5a9..a649dfcf9b7cdc 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -79,8 +79,8 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry, F_STRUCT( __field_struct( struct ftrace_graph_ent, graph_ent ) - __field_packed( unsigned long, graph_ent, func ) - __field_packed( unsigned int, graph_ent, depth ) + __field_desc_packed(unsigned long, graph_ent, func ) + __field_desc_packed(unsigned int, graph_ent, depth ) __dynamic_array(unsigned long, args ) ), @@ -96,9 +96,9 @@ FTRACE_ENTRY_PACKED(fgraph_retaddr_entry, fgraph_retaddr_ent_entry, F_STRUCT( __field_struct( struct fgraph_retaddr_ent, graph_ent ) - __field_packed( unsigned long, graph_ent, func ) - __field_packed( unsigned int, graph_ent, depth ) - __field_packed( unsigned long, graph_ent, retaddr ) + __field_desc_packed( unsigned long, graph_ent, func ) + __field_desc_packed( unsigned int, graph_ent, depth ) + __field_desc_packed( unsigned long, graph_ent, retaddr ) ), F_printk("--> %ps (%u) <- %ps", (void *)__entry->func, __entry->depth, @@ -122,12 +122,12 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, F_STRUCT( __field_struct( struct ftrace_graph_ret, ret ) - __field_packed( unsigned long, ret, func ) - __field_packed( unsigned long, ret, retval ) - __field_packed( unsigned int, ret, depth ) - __field_packed( unsigned int, ret, overrun ) - __field(unsigned long long, calltime ) - __field(unsigned long long, rettime ) + __field_desc_packed( unsigned long, ret, func ) + __field_desc_packed( unsigned long, ret, retval ) + __field_desc_packed( unsigned int, ret, depth ) + __field_desc_packed( unsigned int, ret, overrun ) + __field_packed(unsigned long long, calltime) + __field_packed(unsigned long long, rettime ) ), F_printk("<-- %ps (%u) (start: %llx end: %llx) over: %u retval: %lx", @@ -145,11 +145,11 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, F_STRUCT( __field_struct( struct ftrace_graph_ret, ret ) - __field_packed( unsigned long, ret, func ) - __field_packed( unsigned int, ret, depth ) - __field_packed( unsigned int, ret, overrun ) - __field(unsigned long long, calltime ) - __field(unsigned long long, rettime ) + __field_desc_packed( unsigned long, ret, func ) + __field_desc_packed( unsigned int, ret, depth ) + __field_desc_packed( unsigned int, ret, overrun ) + __field_packed(unsigned long long, calltime ) + __field_packed(unsigned long long, rettime ) ), F_printk("<-- %ps (%u) (start: %llx end: %llx) over: %u", diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e00da4182deb78..5cf55a9c6fad4b 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -700,6 +700,8 @@ int trace_event_reg(struct trace_event_call *call, #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: + if (!call->class->perf_probe) + return -ENODEV; return tracepoint_probe_register(call->tp, call->class->perf_probe, call); @@ -3962,11 +3964,6 @@ void trace_put_event_file(struct trace_event_file *file) EXPORT_SYMBOL_GPL(trace_put_event_file); #ifdef CONFIG_DYNAMIC_FTRACE - -/* Avoid typos */ -#define ENABLE_EVENT_STR "enable_event" -#define DISABLE_EVENT_STR "disable_event" - struct event_probe_data { struct trace_event_file *file; unsigned long count; diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 6bfaf1210dd24e..45727c4cf9545d 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2057,6 +2057,15 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, hist_field->fn_num = HIST_FIELD_FN_RELDYNSTRING; else hist_field->fn_num = HIST_FIELD_FN_PSTRING; + } else if (field->filter_type == FILTER_STACKTRACE) { + flags |= HIST_FIELD_FL_STACKTRACE; + + hist_field->size = MAX_FILTER_STR_VAL; + hist_field->type = kstrdup_const(field->type, GFP_KERNEL); + if (!hist_field->type) + goto free; + + hist_field->fn_num = HIST_FIELD_FN_STACK; } else { hist_field->size = field->size; hist_field->is_signed = field->is_signed; @@ -6900,7 +6909,7 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops, remove_hist_vars(hist_data); - kfree(trigger_data); + trigger_data_free(trigger_data); destroy_hist_data(hist_data); goto out; diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index f24ee61f8884fc..934dafbb009e59 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -130,7 +130,9 @@ static int synth_event_define_fields(struct trace_event_call *call) struct synth_event *event = call->data; unsigned int i, size, n_u64; char *name, *type; + int filter_type; bool is_signed; + bool is_stack; int ret = 0; for (i = 0, n_u64 = 0; i < event->n_fields; i++) { @@ -138,8 +140,12 @@ static int synth_event_define_fields(struct trace_event_call *call) is_signed = event->fields[i]->is_signed; type = event->fields[i]->type; name = event->fields[i]->name; + is_stack = event->fields[i]->is_stack; + + filter_type = is_stack ? FILTER_STACKTRACE : FILTER_OTHER; + ret = trace_define_field(call, type, name, offset, size, - is_signed, FILTER_OTHER); + is_signed, filter_type); if (ret) break; @@ -375,7 +381,6 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter, n_u64++; } else { trace_seq_printf(s, print_fmt, se->fields[i]->name, - STR_VAR_LEN_MAX, (char *)&entry->fields[n_u64].as_u64, i == se->n_fields - 1 ? "" : " "); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 1698fc22afa0a5..32a42ef31855d8 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -42,11 +42,14 @@ static int ftrace_event_register(struct trace_event_call *call, #undef __field_fn #define __field_fn(type, item) type item; +#undef __field_packed +#define __field_packed(type, item) type item; + #undef __field_desc #define __field_desc(type, container, item) type item; -#undef __field_packed -#define __field_packed(type, container, item) type item; +#undef __field_desc_packed +#define __field_desc_packed(type, container, item) type item; #undef __array #define __array(type, item, size) type item[size]; @@ -104,11 +107,14 @@ static void __always_unused ____ftrace_check_##name(void) \ #undef __field_fn #define __field_fn(_type, _item) __field_ext(_type, _item, FILTER_TRACE_FN) +#undef __field_packed +#define __field_packed(_type, _item) __field_ext_packed(_type, _item, FILTER_OTHER) + #undef __field_desc #define __field_desc(_type, _container, _item) __field_ext(_type, _item, FILTER_OTHER) -#undef __field_packed -#define __field_packed(_type, _container, _item) __field_ext_packed(_type, _item, FILTER_OTHER) +#undef __field_desc_packed +#define __field_desc_packed(_type, _container, _item) __field_ext_packed(_type, _item, FILTER_OTHER) #undef __array #define __array(_type, _item, _len) { \ @@ -146,11 +152,14 @@ static struct trace_event_fields ftrace_event_fields_##name[] = { \ #undef __field_fn #define __field_fn(type, item) +#undef __field_packed +#define __field_packed(type, item) + #undef __field_desc #define __field_desc(type, container, item) -#undef __field_packed -#define __field_packed(type, container, item) +#undef __field_desc_packed +#define __field_desc_packed(type, container, item) #undef __array #define __array(type, item, len) diff --git a/kernel/ucount.c b/kernel/ucount.c index 586af49fc03e42..fc4a8f2d309651 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -47,7 +47,7 @@ static int set_permissions(struct ctl_table_header *head, int mode; /* Allow users with CAP_SYS_RESOURCE unrestrained access */ - if (ns_capable(user_ns, CAP_SYS_RESOURCE)) + if (ns_capable_noaudit(user_ns, CAP_SYS_RESOURCE)) mode = (table->mode & S_IRWXU) >> 6; else /* Allow all others at most read-only access */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 45320e27a16c4a..885a8b31f855ba 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -117,6 +117,8 @@ enum wq_internal_consts { MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ + RESCUER_BATCH = 16, /* process items per turn */ + /* * Rescue workers are used only on emergencies and shared by * all cpus. Give MIN_NICE. @@ -286,6 +288,7 @@ struct pool_workqueue { struct list_head pending_node; /* LN: node on wq_node_nr_active->pending_pwqs */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ + struct work_struct mayday_cursor; /* L: cursor on pool->worklist */ u64 stats[PWQ_NR_STATS]; @@ -1126,6 +1129,12 @@ static struct worker *find_worker_executing_work(struct worker_pool *pool, return NULL; } +static void mayday_cursor_func(struct work_struct *work) +{ + /* should not be processed, only for marking position */ + BUG(); +} + /** * move_linked_works - move linked works to a list * @work: start of series of works to be scheduled @@ -1188,6 +1197,16 @@ static bool assign_work(struct work_struct *work, struct worker *worker, lockdep_assert_held(&pool->lock); + /* The cursor work should not be processed */ + if (unlikely(work->func == mayday_cursor_func)) { + /* only worker_thread() can possibly take this branch */ + WARN_ON_ONCE(worker->rescue_wq); + if (nextp) + *nextp = list_next_entry(work, entry); + list_del_init(&work->entry); + return false; + } + /* * A single work shouldn't be executed concurrently by multiple workers. * __queue_work() ensures that @work doesn't jump to a different pool @@ -3443,6 +3462,35 @@ static int worker_thread(void *__worker) goto woke_up; } +static bool assign_rescuer_work(struct pool_workqueue *pwq, struct worker *rescuer) +{ + struct worker_pool *pool = pwq->pool; + struct work_struct *cursor = &pwq->mayday_cursor; + struct work_struct *work, *n; + + /* need rescue? */ + if (!pwq->nr_active || !need_to_create_worker(pool)) + return false; + + /* search from the start or cursor if available */ + if (list_empty(&cursor->entry)) + work = list_first_entry(&pool->worklist, struct work_struct, entry); + else + work = list_next_entry(cursor, entry); + + /* find the next work item to rescue */ + list_for_each_entry_safe_from(work, n, &pool->worklist, entry) { + if (get_work_pwq(work) == pwq && assign_work(work, rescuer, &n)) { + pwq->stats[PWQ_STAT_RESCUED]++; + /* put the cursor for next search */ + list_move_tail(&cursor->entry, &n->entry); + return true; + } + } + + return false; +} + /** * rescuer_thread - the rescuer thread function * @__rescuer: self @@ -3497,7 +3545,7 @@ static int rescuer_thread(void *__rescuer) struct pool_workqueue *pwq = list_first_entry(&wq->maydays, struct pool_workqueue, mayday_node); struct worker_pool *pool = pwq->pool; - struct work_struct *work, *n; + unsigned int count = 0; __set_current_state(TASK_RUNNING); list_del_init(&pwq->mayday_node); @@ -3508,30 +3556,18 @@ static int rescuer_thread(void *__rescuer) raw_spin_lock_irq(&pool->lock); - /* - * Slurp in all works issued via this workqueue and - * process'em. - */ WARN_ON_ONCE(!list_empty(&rescuer->scheduled)); - list_for_each_entry_safe(work, n, &pool->worklist, entry) { - if (get_work_pwq(work) == pwq && - assign_work(work, rescuer, &n)) - pwq->stats[PWQ_STAT_RESCUED]++; - } - if (!list_empty(&rescuer->scheduled)) { + while (assign_rescuer_work(pwq, rescuer)) { process_scheduled_works(rescuer); /* - * The above execution of rescued work items could - * have created more to rescue through - * pwq_activate_first_inactive() or chained - * queueing. Let's put @pwq back on mayday list so - * that such back-to-back work items, which may be - * being used to relieve memory pressure, don't - * incur MAYDAY_INTERVAL delay inbetween. + * If the per-turn work item limit is reached and other + * PWQs are in mayday, requeue mayday for this PWQ and + * let the rescuer handle the other PWQs first. */ - if (pwq->nr_active && need_to_create_worker(pool)) { + if (++count > RESCUER_BATCH && !list_empty(&pwq->wq->maydays) && + pwq->nr_active && need_to_create_worker(pool)) { raw_spin_lock(&wq_mayday_lock); /* * Queue iff we aren't racing destruction @@ -3542,9 +3578,14 @@ static int rescuer_thread(void *__rescuer) list_add_tail(&pwq->mayday_node, &wq->maydays); } raw_spin_unlock(&wq_mayday_lock); + break; } } + /* The cursor can not be left behind without the rescuer watching it. */ + if (!list_empty(&pwq->mayday_cursor.entry) && list_empty(&pwq->mayday_node)) + list_del_init(&pwq->mayday_cursor.entry); + /* * Leave this pool. Notify regular workers; otherwise, we end up * with 0 concurrency and stalling the execution. @@ -5163,6 +5204,19 @@ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); kthread_init_work(&pwq->release_work, pwq_release_workfn); + + /* + * Set the dummy cursor work with valid function and get_work_pwq(). + * + * The cursor work should only be in the pwq->pool->worklist, and + * should not be treated as a processable work item. + * + * WORK_STRUCT_PENDING and WORK_STRUCT_INACTIVE just make it less + * surprise for kernel debugging tools and reviewers. + */ + INIT_WORK(&pwq->mayday_cursor, mayday_cursor_func); + atomic_long_set(&pwq->mayday_cursor.data, (unsigned long)pwq | + WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | WORK_STRUCT_INACTIVE); } /* sync @pwq with the current state of its associated wq and link it */ diff --git a/lib/buildid.c b/lib/buildid.c index c4b0f376fb3410..ef112a7084ef17 100644 --- a/lib/buildid.c +++ b/lib/buildid.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #define BUILD_ID 3 @@ -65,20 +66,9 @@ static int freader_get_folio(struct freader *r, loff_t file_off) freader_put_folio(r); - /* reject secretmem folios created with memfd_secret() */ - if (secretmem_mapping(r->file->f_mapping)) - return -EFAULT; - + /* only use page cache lookup - fail if not already cached */ r->folio = filemap_get_folio(r->file->f_mapping, file_off >> PAGE_SHIFT); - /* if sleeping is allowed, wait for the page, if necessary */ - if (r->may_fault && (IS_ERR(r->folio) || !folio_test_uptodate(r->folio))) { - filemap_invalidate_lock_shared(r->file->f_mapping); - r->folio = read_cache_folio(r->file->f_mapping, file_off >> PAGE_SHIFT, - NULL, r->file); - filemap_invalidate_unlock_shared(r->file->f_mapping); - } - if (IS_ERR(r->folio) || !folio_test_uptodate(r->folio)) { if (!IS_ERR(r->folio)) folio_put(r->folio); @@ -116,6 +106,24 @@ static const void *freader_fetch(struct freader *r, loff_t file_off, size_t sz) return r->data + file_off; } + /* reject secretmem folios created with memfd_secret() */ + if (secretmem_mapping(r->file->f_mapping)) { + r->err = -EFAULT; + return NULL; + } + + /* use __kernel_read() for sleepable context */ + if (r->may_fault) { + ssize_t ret; + + ret = __kernel_read(r->file, r->buf, sz, &file_off); + if (ret != sz) { + r->err = (ret < 0) ? ret : -EIO; + return NULL; + } + return r->buf; + } + /* fetch or reuse folio for given file offset */ r->err = freader_get_folio(r, file_off); if (r->err) @@ -287,7 +295,7 @@ static int get_build_id_64(struct freader *r, unsigned char *build_id, __u32 *si /* enough for Elf64_Ehdr, Elf64_Phdr, and all the smaller requests */ #define MAX_FREADER_BUF_SZ 64 -static int __build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, +static int __build_id_parse(struct file *file, unsigned char *build_id, __u32 *size, bool may_fault) { const Elf32_Ehdr *ehdr; @@ -295,11 +303,7 @@ static int __build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, char buf[MAX_FREADER_BUF_SZ]; int ret; - /* only works for page backed storage */ - if (!vma->vm_file) - return -EINVAL; - - freader_init_from_file(&r, buf, sizeof(buf), vma->vm_file, may_fault); + freader_init_from_file(&r, buf, sizeof(buf), file, may_fault); /* fetch first 18 bytes of ELF header for checks */ ehdr = freader_fetch(&r, 0, offsetofend(Elf32_Ehdr, e_type)); @@ -327,8 +331,8 @@ static int __build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, return ret; } -/* - * Parse build ID of ELF file mapped to vma +/** + * build_id_parse_nofault() - Parse build ID of ELF file mapped to vma * @vma: vma object * @build_id: buffer to store build id, at least BUILD_ID_SIZE long * @size: returns actual build id size in case of success @@ -340,11 +344,14 @@ static int __build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, */ int build_id_parse_nofault(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size) { - return __build_id_parse(vma, build_id, size, false /* !may_fault */); + if (!vma->vm_file) + return -EINVAL; + + return __build_id_parse(vma->vm_file, build_id, size, false /* !may_fault */); } -/* - * Parse build ID of ELF file mapped to VMA +/** + * build_id_parse() - Parse build ID of ELF file mapped to VMA * @vma: vma object * @build_id: buffer to store build id, at least BUILD_ID_SIZE long * @size: returns actual build id size in case of success @@ -356,7 +363,26 @@ int build_id_parse_nofault(struct vm_area_struct *vma, unsigned char *build_id, */ int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size) { - return __build_id_parse(vma, build_id, size, true /* may_fault */); + if (!vma->vm_file) + return -EINVAL; + + return __build_id_parse(vma->vm_file, build_id, size, true /* may_fault */); +} + +/** + * build_id_parse_file() - Parse build ID of ELF file + * @file: file object + * @build_id: buffer to store build id, at least BUILD_ID_SIZE long + * @size: returns actual build id size in case of success + * + * Assumes faultable context and can cause page faults to bring in file data + * into page cache. + * + * Return: 0 on success; negative error, otherwise + */ +int build_id_parse_file(struct file *file, unsigned char *build_id, __u32 *size) +{ + return __build_id_parse(file, build_id, size, true /* may_fault */); } /** diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig index 16859c6226dd4b..fa882108ba62ca 100644 --- a/lib/crypto/Kconfig +++ b/lib/crypto/Kconfig @@ -50,7 +50,8 @@ config CRYPTO_LIB_CHACHA_ARCH default y if ARM64 && KERNEL_MODE_NEON default y if MIPS && CPU_MIPS32_R2 default y if PPC64 && CPU_LITTLE_ENDIAN && VSX - default y if RISCV && 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO + default y if RISCV && 64BIT && TOOLCHAIN_HAS_VECTOR_CRYPTO && \ + RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS default y if S390 default y if X86_64 @@ -161,7 +162,8 @@ config CRYPTO_LIB_SHA256_ARCH default y if ARM64 default y if MIPS && CPU_CAVIUM_OCTEON default y if PPC && SPE - default y if RISCV && 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO + default y if RISCV && 64BIT && TOOLCHAIN_HAS_VECTOR_CRYPTO && \ + RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS default y if S390 default y if SPARC64 default y if X86_64 @@ -179,7 +181,8 @@ config CRYPTO_LIB_SHA512_ARCH default y if ARM && !CPU_V7M default y if ARM64 default y if MIPS && CPU_CAVIUM_OCTEON - default y if RISCV && 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO + default y if RISCV && 64BIT && TOOLCHAIN_HAS_VECTOR_CRYPTO && \ + RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS default y if S390 default y if SPARC64 default y if X86_64 diff --git a/lib/crypto/aes.c b/lib/crypto/aes.c index b57fda3460f1b3..102aaa76bc8d76 100644 --- a/lib/crypto/aes.c +++ b/lib/crypto/aes.c @@ -13,7 +13,7 @@ * Emit the sbox as volatile const to prevent the compiler from doing * constant folding on sbox references involving fixed indexes. */ -static volatile const u8 __cacheline_aligned aes_sbox[] = { +static volatile const u8 ____cacheline_aligned aes_sbox[] = { 0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5, 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76, 0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, @@ -48,7 +48,7 @@ static volatile const u8 __cacheline_aligned aes_sbox[] = { 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16, }; -static volatile const u8 __cacheline_aligned aes_inv_sbox[] = { +static volatile const u8 ____cacheline_aligned aes_inv_sbox[] = { 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb, 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, diff --git a/lib/crypto/riscv/.gitignore b/lib/crypto/riscv/.gitignore new file mode 100644 index 00000000000000..0d47d4f21c6de9 --- /dev/null +++ b/lib/crypto/riscv/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +poly1305-core.S diff --git a/lib/crypto/riscv/chacha-riscv64-zvkb.S b/lib/crypto/riscv/chacha-riscv64-zvkb.S index b777d0b4e37969..3d183ec818f52a 100644 --- a/lib/crypto/riscv/chacha-riscv64-zvkb.S +++ b/lib/crypto/riscv/chacha-riscv64-zvkb.S @@ -60,7 +60,8 @@ #define VL t2 #define STRIDE t3 #define ROUND_CTR t4 -#define KEY0 s0 +#define KEY0 t5 +// Avoid s0/fp to allow for unwinding #define KEY1 s1 #define KEY2 s2 #define KEY3 s3 @@ -143,7 +144,6 @@ // The updated 32-bit counter is written back to state->x[12] before returning. SYM_FUNC_START(chacha_zvkb) addi sp, sp, -96 - sd s0, 0(sp) sd s1, 8(sp) sd s2, 16(sp) sd s3, 24(sp) @@ -280,7 +280,6 @@ SYM_FUNC_START(chacha_zvkb) bnez NBLOCKS, .Lblock_loop sw COUNTER, 48(STATEP) - ld s0, 0(sp) ld s1, 8(sp) ld s2, 16(sp) ld s3, 24(sp) diff --git a/lib/crypto/x86/blake2s-core.S b/lib/crypto/x86/blake2s-core.S index ef8e9f427aab34..093e7814f38796 100644 --- a/lib/crypto/x86/blake2s-core.S +++ b/lib/crypto/x86/blake2s-core.S @@ -52,7 +52,7 @@ SYM_FUNC_START(blake2s_compress_ssse3) movdqa ROT16(%rip),%xmm12 movdqa ROR328(%rip),%xmm13 movdqu 0x20(%rdi),%xmm14 - movq %rcx,%xmm15 + movd %ecx,%xmm15 leaq SIGMA+0xa0(%rip),%r8 jmp .Lbeginofloop .align 32 @@ -176,7 +176,7 @@ SYM_FUNC_START(blake2s_compress_avx512) vmovdqu (%rdi),%xmm0 vmovdqu 0x10(%rdi),%xmm1 vmovdqu 0x20(%rdi),%xmm4 - vmovq %rcx,%xmm5 + vmovd %ecx,%xmm5 vmovdqa IV(%rip),%xmm14 vmovdqa IV+16(%rip),%xmm15 jmp .Lblake2s_compress_avx512_mainloop diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c index 84ecccddc77182..012d5614efb9ab 100644 --- a/lib/flex_proportions.c +++ b/lib/flex_proportions.c @@ -64,13 +64,14 @@ void fprop_global_destroy(struct fprop_global *p) bool fprop_new_period(struct fprop_global *p, int periods) { s64 events = percpu_counter_sum(&p->events); + unsigned long flags; /* * Don't do anything if there are no events. */ if (events <= 1) return false; - preempt_disable_nested(); + local_irq_save(flags); write_seqcount_begin(&p->sequence); if (periods < 64) events -= events >> periods; @@ -78,7 +79,7 @@ bool fprop_new_period(struct fprop_global *p, int periods) percpu_counter_add(&p->events, -events); p->period += periods; write_seqcount_end(&p->sequence); - preempt_enable_nested(); + local_irq_restore(flags); return true; } diff --git a/lib/idr.c b/lib/idr.c index e2adc457abb4be..457430cff8c5e1 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -40,6 +40,8 @@ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid, if (WARN_ON_ONCE(!(idr->idr_rt.xa_flags & ROOT_IS_IDR))) idr->idr_rt.xa_flags |= IDR_RT_MARKER; + if (max < base) + return -ENOSPC; id = (id < base) ? 0 : id - base; radix_tree_iter_init(&iter, id); diff --git a/lib/kstrtox.c b/lib/kstrtox.c index bdde40cd69d789..97be2a39f53710 100644 --- a/lib/kstrtox.c +++ b/lib/kstrtox.c @@ -340,8 +340,8 @@ EXPORT_SYMBOL(kstrtos8); * @s: input string * @res: result * - * This routine returns 0 iff the first character is one of 'YyTt1NnFf0', or - * [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL. Value + * This routine returns 0 iff the first character is one of 'EeYyTt1DdNnFf0', + * or [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL. Value * pointed to by res is updated upon finding a match. */ noinline diff --git a/lib/objpool.c b/lib/objpool.c index b998b720c7329d..d98fadf1de169f 100644 --- a/lib/objpool.c +++ b/lib/objpool.c @@ -142,7 +142,7 @@ int objpool_init(struct objpool_head *pool, int nr_objs, int object_size, pool->gfp = gfp & ~__GFP_ZERO; pool->context = context; pool->release = release; - slot_size = nr_cpu_ids * sizeof(struct objpool_slot); + slot_size = nr_cpu_ids * sizeof(struct objpool_slot *); pool->cpu_slots = kzalloc(slot_size, pool->gfp); if (!pool->cpu_slots) return -ENOMEM; diff --git a/lib/vsprintf.c b/lib/vsprintf.c index eb0cb11d0d126f..a356965c1d7348 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1928,9 +1928,6 @@ char *rtc_str(char *buf, char *end, const struct rtc_time *tm, bool found = true; int count = 2; - if (check_pointer(&buf, end, tm, spec)) - return buf; - switch (fmt[count]) { case 'd': have_t = false; @@ -1996,6 +1993,9 @@ static noinline_for_stack char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { + if (check_pointer(&buf, end, ptr, spec)) + return buf; + switch (fmt[1]) { case 'R': return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt); diff --git a/lib/xarray.c b/lib/xarray.c index 9a8b4916540cf1..fe7f18d7194187 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1738,9 +1738,6 @@ void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) } EXPORT_SYMBOL(xa_store); -static inline void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index, - void *old, void *entry, gfp_t gfp); - /** * __xa_cmpxchg() - Conditionally replace an entry in the XArray. * @xa: XArray. @@ -1767,7 +1764,29 @@ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, } EXPORT_SYMBOL(__xa_cmpxchg); -static inline void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index, +/** + * __xa_cmpxchg_raw() - Conditionally replace an entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @old: Old value to test against. + * @entry: New value to place in array. + * @gfp: Memory allocation flags. + * + * You must already be holding the xa_lock when calling this function. + * It will drop the lock if needed to allocate memory, and then reacquire + * it afterwards. + * + * If the entry at @index is the same as @old, replace it with @entry. + * If the return value is equal to @old, then the exchange was successful. + * + * This function is the same as __xa_cmpxchg() except that it does not coerce + * XA_ZERO_ENTRY to NULL on egress. + * + * Context: Any context. Expects xa_lock to be held on entry. May + * release and reacquire xa_lock if @gfp flags permit. + * Return: The old value at this index or xa_err() if an error happened. + */ +void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); @@ -1787,6 +1806,7 @@ static inline void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index, return xas_result(&xas, curr); } +EXPORT_SYMBOL(__xa_cmpxchg_raw); /** * __xa_insert() - Store this entry in the XArray if no entry is present. diff --git a/mm/Kconfig b/mm/Kconfig index ca3f146bc7053a..76001e9ba04f1c 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -915,6 +915,9 @@ config HAVE_GIGANTIC_FOLIOS def_bool (HUGETLB_PAGE && ARCH_HAS_GIGANTIC_PAGE) || \ (ZONE_DEVICE && HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) +config ASYNC_KERNEL_PGTABLE_FREE + def_bool n + # TODO: Allow to be enabled without THP config ARCH_SUPPORTS_HUGE_PFNMAP def_bool n @@ -1135,10 +1138,14 @@ config ZONE_DEVICE Device memory hotplug support allows for establishing pmem, or other device driver discovered memory regions, in the memmap. This allows pfn_to_page() lookups of otherwise - "device-physical" addresses which is needed for using a DAX - mapping in an O_DIRECT operation, among other things. - - If FS_DAX is enabled, then say Y. + "device-physical" addresses which is needed for DAX, PCI_P2PDMA, and + DEVICE_PRIVATE features among others. + + Enabling this option will reduce the entropy of x86 KASLR memory + regions. For example - on a 46 bit system, the entropy goes down + from 16 bits to 15 bits. The actual reduction in entropy depends + on the physical address bits, on processor features, kernel config + (5 level page table) and physical memory present on the system. # # Helpers to mirror range of the CPU page tables of a process into device page diff --git a/mm/damon/core.c b/mm/damon/core.c index 109b050c795adb..b787cdb07cb25d 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1426,6 +1426,35 @@ bool damon_is_running(struct damon_ctx *ctx) return running; } +/* + * damon_call_handle_inactive_ctx() - handle DAMON call request that added to + * an inactive context. + * @ctx: The inactive DAMON context. + * @control: Control variable of the call request. + * + * This function is called in a case that @control is added to @ctx but @ctx is + * not running (inactive). See if @ctx handled @control or not, and cleanup + * @control if it was not handled. + * + * Returns 0 if @control was handled by @ctx, negative error code otherwise. + */ +static int damon_call_handle_inactive_ctx( + struct damon_ctx *ctx, struct damon_call_control *control) +{ + struct damon_call_control *c; + + mutex_lock(&ctx->call_controls_lock); + list_for_each_entry(c, &ctx->call_controls, list) { + if (c == control) { + list_del(&control->list); + mutex_unlock(&ctx->call_controls_lock); + return -EINVAL; + } + } + mutex_unlock(&ctx->call_controls_lock); + return 0; +} + /** * damon_call() - Invoke a given function on DAMON worker thread (kdamond). * @ctx: DAMON context to call the function for. @@ -1456,7 +1485,7 @@ int damon_call(struct damon_ctx *ctx, struct damon_call_control *control) list_add_tail(&control->list, &ctx->call_controls); mutex_unlock(&ctx->call_controls_lock); if (!damon_is_running(ctx)) - return -EINVAL; + return damon_call_handle_inactive_ctx(ctx, control); if (control->repeat) return 0; wait_for_completion(&control->completion); @@ -2704,13 +2733,13 @@ static int kdamond_fn(void *data) if (ctx->ops.cleanup) ctx->ops.cleanup(ctx); kfree(ctx->regions_score_histogram); + kdamond_call(ctx, true); pr_debug("kdamond (%d) finishes\n", current->pid); mutex_lock(&ctx->kdamond_lock); ctx->kdamond = NULL; mutex_unlock(&ctx->kdamond_lock); - kdamond_call(ctx, true); damos_walk_cancel(ctx); mutex_lock(&damon_lock); diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 6536f16006c90f..50d000d61c9076 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -2111,13 +2111,13 @@ static int damon_sysfs_scheme_add_dirs(struct damon_sysfs_scheme *scheme) return err; err = damos_sysfs_set_dests(scheme); if (err) - goto put_access_pattern_out; + goto rmdir_put_access_pattern_out; err = damon_sysfs_scheme_set_quotas(scheme); if (err) goto put_dests_out; err = damon_sysfs_scheme_set_watermarks(scheme); if (err) - goto put_quotas_access_pattern_out; + goto rmdir_put_quotas_access_pattern_out; err = damos_sysfs_set_filter_dirs(scheme); if (err) goto put_watermarks_quotas_access_pattern_out; @@ -2142,13 +2142,15 @@ static int damon_sysfs_scheme_add_dirs(struct damon_sysfs_scheme *scheme) put_watermarks_quotas_access_pattern_out: kobject_put(&scheme->watermarks->kobj); scheme->watermarks = NULL; -put_quotas_access_pattern_out: +rmdir_put_quotas_access_pattern_out: + damon_sysfs_quotas_rm_dirs(scheme->quotas); kobject_put(&scheme->quotas->kobj); scheme->quotas = NULL; put_dests_out: kobject_put(&scheme->dests->kobj); scheme->dests = NULL; -put_access_pattern_out: +rmdir_put_access_pattern_out: + damon_sysfs_access_pattern_rm_dirs(scheme->access_pattern); kobject_put(&scheme->access_pattern->kobj); scheme->access_pattern = NULL; return err; diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 3c0d727788c875..dec9f5d0d51237 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -764,7 +764,7 @@ static int damon_sysfs_attrs_add_dirs(struct damon_sysfs_attrs *attrs) nr_regions_range = damon_sysfs_ul_range_alloc(10, 1000); if (!nr_regions_range) { err = -ENOMEM; - goto put_intervals_out; + goto rmdir_put_intervals_out; } err = kobject_init_and_add(&nr_regions_range->kobj, @@ -778,6 +778,8 @@ static int damon_sysfs_attrs_add_dirs(struct damon_sysfs_attrs *attrs) put_nr_regions_intervals_out: kobject_put(&nr_regions_range->kobj); attrs->nr_regions_range = NULL; +rmdir_put_intervals_out: + damon_sysfs_intervals_rm_dirs(intervals); put_intervals_out: kobject_put(&intervals->kobj); attrs->intervals = NULL; @@ -920,7 +922,7 @@ static int damon_sysfs_context_add_dirs(struct damon_sysfs_context *context) err = damon_sysfs_context_set_targets(context); if (err) - goto put_attrs_out; + goto rmdir_put_attrs_out; err = damon_sysfs_context_set_schemes(context); if (err) @@ -930,7 +932,8 @@ static int damon_sysfs_context_add_dirs(struct damon_sysfs_context *context) put_targets_attrs_out: kobject_put(&context->targets->kobj); context->targets = NULL; -put_attrs_out: +rmdir_put_attrs_out: + damon_sysfs_attrs_rm_dirs(context->attrs); kobject_put(&context->attrs->kobj); context->attrs = NULL; return err; @@ -1264,7 +1267,7 @@ enum damon_sysfs_cmd { DAMON_SYSFS_CMD_UPDATE_SCHEMES_EFFECTIVE_QUOTAS, /* * @DAMON_SYSFS_CMD_UPDATE_TUNED_INTERVALS: Update the tuned monitoring - * intevals. + * intervals. */ DAMON_SYSFS_CMD_UPDATE_TUNED_INTERVALS, /* diff --git a/mm/damon/tests/core-kunit.h b/mm/damon/tests/core-kunit.h index 51369e35298b1c..66877787527287 100644 --- a/mm/damon/tests/core-kunit.h +++ b/mm/damon/tests/core-kunit.h @@ -20,11 +20,17 @@ static void damon_test_regions(struct kunit *test) struct damon_target *t; r = damon_new_region(1, 2); + if (!r) + kunit_skip(test, "region alloc fail"); KUNIT_EXPECT_EQ(test, 1ul, r->ar.start); KUNIT_EXPECT_EQ(test, 2ul, r->ar.end); KUNIT_EXPECT_EQ(test, 0u, r->nr_accesses); t = damon_new_target(); + if (!t) { + damon_free_region(r); + kunit_skip(test, "target alloc fail"); + } KUNIT_EXPECT_EQ(test, 0u, damon_nr_regions(t)); damon_add_region(r, t); @@ -52,7 +58,14 @@ static void damon_test_target(struct kunit *test) struct damon_ctx *c = damon_new_ctx(); struct damon_target *t; + if (!c) + kunit_skip(test, "ctx alloc fail"); + t = damon_new_target(); + if (!t) { + damon_destroy_ctx(c); + kunit_skip(test, "target alloc fail"); + } KUNIT_EXPECT_EQ(test, 0u, nr_damon_targets(c)); damon_add_target(c, t); @@ -84,8 +97,15 @@ static void damon_test_aggregate(struct kunit *test) struct damon_region *r; int it, ir; + if (!ctx) + kunit_skip(test, "ctx alloc fail"); + for (it = 0; it < 3; it++) { t = damon_new_target(); + if (!t) { + damon_destroy_ctx(ctx); + kunit_skip(test, "target alloc fail"); + } damon_add_target(ctx, t); } @@ -93,6 +113,10 @@ static void damon_test_aggregate(struct kunit *test) damon_for_each_target(t, ctx) { for (ir = 0; ir < 3; ir++) { r = damon_new_region(saddr[it][ir], eaddr[it][ir]); + if (!r) { + damon_destroy_ctx(ctx); + kunit_skip(test, "region alloc fail"); + } r->nr_accesses = accesses[it][ir]; r->nr_accesses_bp = accesses[it][ir] * 10000; damon_add_region(r, t); @@ -124,8 +148,19 @@ static void damon_test_split_at(struct kunit *test) struct damon_target *t; struct damon_region *r, *r_new; + if (!c) + kunit_skip(test, "ctx alloc fail"); t = damon_new_target(); + if (!t) { + damon_destroy_ctx(c); + kunit_skip(test, "target alloc fail"); + } r = damon_new_region(0, 100); + if (!r) { + damon_destroy_ctx(c); + damon_free_target(t); + kunit_skip(test, "region alloc fail"); + } r->nr_accesses_bp = 420000; r->nr_accesses = 42; r->last_nr_accesses = 15; @@ -153,11 +188,21 @@ static void damon_test_merge_two(struct kunit *test) int i; t = damon_new_target(); + if (!t) + kunit_skip(test, "target alloc fail"); r = damon_new_region(0, 100); + if (!r) { + damon_free_target(t); + kunit_skip(test, "region alloc fail"); + } r->nr_accesses = 10; r->nr_accesses_bp = 100000; damon_add_region(r, t); r2 = damon_new_region(100, 300); + if (!r2) { + damon_free_target(t); + kunit_skip(test, "second region alloc fail"); + } r2->nr_accesses = 20; r2->nr_accesses_bp = 200000; damon_add_region(r2, t); @@ -203,8 +248,14 @@ static void damon_test_merge_regions_of(struct kunit *test) int i; t = damon_new_target(); + if (!t) + kunit_skip(test, "target alloc fail"); for (i = 0; i < ARRAY_SIZE(sa); i++) { r = damon_new_region(sa[i], ea[i]); + if (!r) { + damon_free_target(t); + kunit_skip(test, "region alloc fail"); + } r->nr_accesses = nrs[i]; r->nr_accesses_bp = nrs[i] * 10000; damon_add_region(r, t); @@ -227,15 +278,35 @@ static void damon_test_split_regions_of(struct kunit *test) struct damon_target *t; struct damon_region *r; + if (!c) + kunit_skip(test, "ctx alloc fail"); t = damon_new_target(); + if (!t) { + damon_destroy_ctx(c); + kunit_skip(test, "target alloc fail"); + } r = damon_new_region(0, 22); + if (!r) { + damon_destroy_ctx(c); + damon_free_target(t); + kunit_skip(test, "region alloc fail"); + } damon_add_region(r, t); damon_split_regions_of(t, 2, DAMON_MIN_REGION); KUNIT_EXPECT_LE(test, damon_nr_regions(t), 2u); damon_free_target(t); t = damon_new_target(); + if (!t) { + damon_destroy_ctx(c); + kunit_skip(test, "second target alloc fail"); + } r = damon_new_region(0, 220); + if (!r) { + damon_destroy_ctx(c); + damon_free_target(t); + kunit_skip(test, "second region alloc fail"); + } damon_add_region(r, t); damon_split_regions_of(t, 4, DAMON_MIN_REGION); KUNIT_EXPECT_LE(test, damon_nr_regions(t), 4u); @@ -249,6 +320,9 @@ static void damon_test_ops_registration(struct kunit *test) struct damon_operations ops = {.id = DAMON_OPS_VADDR}, bak; bool need_cleanup = false; + if (!c) + kunit_skip(test, "ctx alloc fail"); + /* DAMON_OPS_VADDR is registered only if CONFIG_DAMON_VADDR is set */ if (!damon_is_registered_ops(DAMON_OPS_VADDR)) { bak.id = DAMON_OPS_VADDR; @@ -294,13 +368,26 @@ static void damon_test_ops_registration(struct kunit *test) static void damon_test_set_regions(struct kunit *test) { struct damon_target *t = damon_new_target(); - struct damon_region *r1 = damon_new_region(4, 16); - struct damon_region *r2 = damon_new_region(24, 32); + struct damon_region *r1, *r2; struct damon_addr_range range = {.start = 8, .end = 28}; unsigned long expects[] = {8, 16, 16, 24, 24, 28}; int expect_idx = 0; struct damon_region *r; + if (!t) + kunit_skip(test, "target alloc fail"); + r1 = damon_new_region(4, 16); + if (!r1) { + damon_free_target(t); + kunit_skip(test, "region alloc fail"); + } + r2 = damon_new_region(24, 32); + if (!r2) { + damon_free_target(t); + damon_free_region(r1); + kunit_skip(test, "second region alloc fail"); + } + damon_add_region(r1, t); damon_add_region(r2, t); damon_set_regions(t, &range, 1, DAMON_MIN_REGION); @@ -342,6 +429,9 @@ static void damon_test_update_monitoring_result(struct kunit *test) struct damon_attrs new_attrs; struct damon_region *r = damon_new_region(3, 7); + if (!r) + kunit_skip(test, "region alloc fail"); + r->nr_accesses = 15; r->nr_accesses_bp = 150000; r->age = 20; @@ -375,6 +465,9 @@ static void damon_test_set_attrs(struct kunit *test) .sample_interval = 5000, .aggr_interval = 100000,}; struct damon_attrs invalid_attrs; + if (!c) + kunit_skip(test, "ctx alloc fail"); + KUNIT_EXPECT_EQ(test, damon_set_attrs(c, &valid_attrs), 0); invalid_attrs = valid_attrs; @@ -412,6 +505,8 @@ static void damos_test_new_filter(struct kunit *test) struct damos_filter *filter; filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true, false); + if (!filter) + kunit_skip(test, "filter alloc fail"); KUNIT_EXPECT_EQ(test, filter->type, DAMOS_FILTER_TYPE_ANON); KUNIT_EXPECT_EQ(test, filter->matching, true); KUNIT_EXPECT_PTR_EQ(test, filter->list.prev, &filter->list); @@ -421,11 +516,16 @@ static void damos_test_new_filter(struct kunit *test) static void damos_test_commit_filter(struct kunit *test) { - struct damos_filter *src_filter = damos_new_filter( - DAMOS_FILTER_TYPE_ANON, true, true); - struct damos_filter *dst_filter = damos_new_filter( - DAMOS_FILTER_TYPE_ACTIVE, false, false); - + struct damos_filter *src_filter, *dst_filter; + + src_filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true, true); + if (!src_filter) + kunit_skip(test, "src filter alloc fail"); + dst_filter = damos_new_filter(DAMOS_FILTER_TYPE_ACTIVE, false, false); + if (!dst_filter) { + damos_destroy_filter(src_filter); + kunit_skip(test, "dst filter alloc fail"); + } damos_commit_filter(dst_filter, src_filter); KUNIT_EXPECT_EQ(test, dst_filter->type, src_filter->type); KUNIT_EXPECT_EQ(test, dst_filter->matching, src_filter->matching); @@ -442,11 +542,22 @@ static void damos_test_filter_out(struct kunit *test) struct damos_filter *f; f = damos_new_filter(DAMOS_FILTER_TYPE_ADDR, true, false); + if (!f) + kunit_skip(test, "filter alloc fail"); f->addr_range = (struct damon_addr_range){ .start = DAMON_MIN_REGION * 2, .end = DAMON_MIN_REGION * 6}; t = damon_new_target(); + if (!t) { + damos_destroy_filter(f); + kunit_skip(test, "target alloc fail"); + } r = damon_new_region(DAMON_MIN_REGION * 3, DAMON_MIN_REGION * 5); + if (!r) { + damos_destroy_filter(f); + damon_free_target(t); + kunit_skip(test, "region alloc fail"); + } damon_add_region(r, t); /* region in the range */ @@ -548,6 +659,8 @@ static void damon_test_set_filters_default_reject(struct kunit *test) KUNIT_EXPECT_EQ(test, scheme.ops_filters_default_reject, false); target_filter = damos_new_filter(DAMOS_FILTER_TYPE_TARGET, true, true); + if (!target_filter) + kunit_skip(test, "filter alloc fail"); damos_add_filter(&scheme, target_filter); damos_set_filters_default_reject(&scheme); /* @@ -573,6 +686,10 @@ static void damon_test_set_filters_default_reject(struct kunit *test) KUNIT_EXPECT_EQ(test, scheme.ops_filters_default_reject, false); anon_filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true, true); + if (!anon_filter) { + damos_free_filter(target_filter); + kunit_skip(test, "anon_filter alloc fail"); + } damos_add_filter(&scheme, anon_filter); damos_set_filters_default_reject(&scheme); @@ -598,6 +715,9 @@ static void damon_test_set_filters_default_reject(struct kunit *test) */ KUNIT_EXPECT_EQ(test, scheme.core_filters_default_reject, false); KUNIT_EXPECT_EQ(test, scheme.ops_filters_default_reject, true); + + damos_free_filter(anon_filter); + damos_free_filter(target_filter); } static struct kunit_case damon_test_cases[] = { diff --git a/mm/damon/tests/sysfs-kunit.h b/mm/damon/tests/sysfs-kunit.h index 7b5c7b307da99c..ce7218469f20b4 100644 --- a/mm/damon/tests/sysfs-kunit.h +++ b/mm/damon/tests/sysfs-kunit.h @@ -45,16 +45,41 @@ static void damon_sysfs_test_add_targets(struct kunit *test) struct damon_ctx *ctx; sysfs_targets = damon_sysfs_targets_alloc(); + if (!sysfs_targets) + kunit_skip(test, "sysfs_targets alloc fail"); sysfs_targets->nr = 1; sysfs_targets->targets_arr = kmalloc_array(1, sizeof(*sysfs_targets->targets_arr), GFP_KERNEL); + if (!sysfs_targets->targets_arr) { + kfree(sysfs_targets); + kunit_skip(test, "targets_arr alloc fail"); + } sysfs_target = damon_sysfs_target_alloc(); + if (!sysfs_target) { + kfree(sysfs_targets->targets_arr); + kfree(sysfs_targets); + kunit_skip(test, "sysfs_target alloc fail"); + } sysfs_target->pid = __damon_sysfs_test_get_any_pid(12, 100); sysfs_target->regions = damon_sysfs_regions_alloc(); + if (!sysfs_target->regions) { + kfree(sysfs_targets->targets_arr); + kfree(sysfs_targets); + kfree(sysfs_target); + kunit_skip(test, "sysfs_regions alloc fail"); + } + sysfs_targets->targets_arr[0] = sysfs_target; ctx = damon_new_ctx(); + if (!ctx) { + kfree(sysfs_targets->targets_arr); + kfree(sysfs_targets); + kfree(sysfs_target); + kfree(sysfs_target->regions); + kunit_skip(test, "ctx alloc fail"); + } damon_sysfs_add_targets(ctx, sysfs_targets); KUNIT_EXPECT_EQ(test, 1u, nr_damon_targets(ctx)); diff --git a/mm/damon/tests/vaddr-kunit.h b/mm/damon/tests/vaddr-kunit.h index fce38dd53cf8f8..30dc5459f1d2c0 100644 --- a/mm/damon/tests/vaddr-kunit.h +++ b/mm/damon/tests/vaddr-kunit.h @@ -136,8 +136,14 @@ static void damon_do_test_apply_three_regions(struct kunit *test, int i; t = damon_new_target(); + if (!t) + kunit_skip(test, "target alloc fail"); for (i = 0; i < nr_regions / 2; i++) { r = damon_new_region(regions[i * 2], regions[i * 2 + 1]); + if (!r) { + damon_destroy_target(t, NULL); + kunit_skip(test, "region alloc fail"); + } damon_add_region(r, t); } @@ -250,7 +256,16 @@ static void damon_test_split_evenly_fail(struct kunit *test, unsigned long start, unsigned long end, unsigned int nr_pieces) { struct damon_target *t = damon_new_target(); - struct damon_region *r = damon_new_region(start, end); + struct damon_region *r; + + if (!t) + kunit_skip(test, "target alloc fail"); + + r = damon_new_region(start, end); + if (!r) { + damon_free_target(t); + kunit_skip(test, "region alloc fail"); + } damon_add_region(r, t); KUNIT_EXPECT_EQ(test, @@ -269,10 +284,17 @@ static void damon_test_split_evenly_succ(struct kunit *test, unsigned long start, unsigned long end, unsigned int nr_pieces) { struct damon_target *t = damon_new_target(); - struct damon_region *r = damon_new_region(start, end); + struct damon_region *r; unsigned long expected_width = (end - start) / nr_pieces; unsigned long i = 0; + if (!t) + kunit_skip(test, "target alloc fail"); + r = damon_new_region(start, end); + if (!r) { + damon_free_target(t); + kunit_skip(test, "region alloc fail"); + } damon_add_region(r, t); KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, nr_pieces), 0); diff --git a/mm/gup.c b/mm/gup.c index a8ba5112e4d096..d2524fe09338fd 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2710,7 +2710,7 @@ EXPORT_SYMBOL(get_user_pages_unlocked); * * *) ptes can be read atomically by the architecture. * - * *) valid user addesses are below TASK_MAX_SIZE + * *) valid user addresses are below TASK_MAX_SIZE * * The last two assumptions can be relaxed by the addition of helper functions. * diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 6cba1cb14b23ac..8ad170b9855a5a 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1233,6 +1233,7 @@ static void map_anon_folio_pmd(struct folio *folio, pmd_t *pmd, count_vm_event(THP_FAULT_ALLOC); count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); + deferred_split_folio(folio, false); } static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf) @@ -1273,7 +1274,6 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf) pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); map_anon_folio_pmd(folio, vmf->pmd, vma, haddr); mm_inc_nr_ptes(vma->vm_mm); - deferred_split_folio(folio, false); spin_unlock(vmf->ptl); } @@ -3515,8 +3515,8 @@ static int __split_unmapped_folio(struct folio *folio, int new_order, return ret; } -bool non_uniform_split_supported(struct folio *folio, unsigned int new_order, - bool warns) +bool folio_split_supported(struct folio *folio, unsigned int new_order, + bool uniform_split, bool warns) { if (folio_test_anon(folio)) { /* order-1 is not supported for anonymous THP. */ @@ -3524,48 +3524,41 @@ bool non_uniform_split_supported(struct folio *folio, unsigned int new_order, "Cannot split to order-1 folio"); if (new_order == 1) return false; - } else if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && - !mapping_large_folio_support(folio->mapping)) { - /* - * No split if the file system does not support large folio. - * Note that we might still have THPs in such mappings due to - * CONFIG_READ_ONLY_THP_FOR_FS. But in that case, the mapping - * does not actually support large folios properly. - */ - VM_WARN_ONCE(warns, - "Cannot split file folio to non-0 order"); - return false; - } - - /* Only swapping a whole PMD-mapped folio is supported */ - if (folio_test_swapcache(folio)) { - VM_WARN_ONCE(warns, - "Cannot split swapcache folio to non-0 order"); - return false; - } - - return true; -} - -/* See comments in non_uniform_split_supported() */ -bool uniform_split_supported(struct folio *folio, unsigned int new_order, - bool warns) -{ - if (folio_test_anon(folio)) { - VM_WARN_ONCE(warns && new_order == 1, - "Cannot split to order-1 folio"); - if (new_order == 1) - return false; - } else if (new_order) { + } else if (!uniform_split || new_order) { if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !mapping_large_folio_support(folio->mapping)) { + /* + * We can always split a folio down to a single page + * (new_order == 0) uniformly. + * + * For any other scenario + * a) uniform split targeting a large folio + * (new_order > 0) + * b) any non-uniform split + * we must confirm that the file system supports large + * folios. + * + * Note that we might still have THPs in such + * mappings, which is created from khugepaged when + * CONFIG_READ_ONLY_THP_FOR_FS is enabled. But in that + * case, the mapping does not actually support large + * folios properly. + */ VM_WARN_ONCE(warns, "Cannot split file folio to non-0 order"); return false; } } - if (new_order && folio_test_swapcache(folio)) { + /* + * swapcache folio could only be split to order 0 + * + * non-uniform split creates after-split folios with orders from + * folio_order(folio) - 1 to new_order, making it not suitable for any + * swapcache folio split. Only uniform split to order-0 can be used + * here. + */ + if ((!uniform_split || new_order) && folio_test_swapcache(folio)) { VM_WARN_ONCE(warns, "Cannot split swapcache folio to non-0 order"); return false; @@ -3632,11 +3625,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order, if (new_order >= folio_order(folio)) return -EINVAL; - if (uniform_split && !uniform_split_supported(folio, new_order, true)) - return -EINVAL; - - if (!uniform_split && - !non_uniform_split_supported(folio, new_order, true)) + if (!folio_split_supported(folio, new_order, uniform_split, /* warn = */ true)) return -EINVAL; is_hzp = is_huge_zero_folio(folio); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0455119716ec0c..be0f935a8b1212 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2934,7 +2934,7 @@ typedef enum { * NOTE: This is mostly identical to MAP_CHG_NEEDED, except * that currently vma_needs_reservation() has an unwanted side * effect to either use end() or commit() to complete the - * transaction. Hence it needs to differenciate from NEEDED. + * transaction. Hence it needs to differentiate from NEEDED. */ MAP_CHG_ENFORCED = 2, } map_chg_state; @@ -5797,7 +5797,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, unsigned long last_addr_mask; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; - bool shared_pmd = false; + struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr, old_end); @@ -5807,6 +5807,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, * range. */ flush_cache_range(vma, range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); mmu_notifier_invalidate_range_start(&range); last_addr_mask = hugetlb_mask_last_page(h); @@ -5823,8 +5824,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, if (huge_pte_none(huge_ptep_get(mm, old_addr, src_pte))) continue; - if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) { - shared_pmd = true; + if (huge_pmd_unshare(&tlb, vma, old_addr, src_pte)) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; @@ -5835,15 +5835,16 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, break; move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); + tlb_remove_huge_tlb_entry(h, &tlb, src_pte, old_addr); } - if (shared_pmd) - flush_hugetlb_tlb_range(vma, range.start, range.end); - else - flush_hugetlb_tlb_range(vma, old_end - len, old_end); + tlb_flush_mmu_tlbonly(&tlb); + huge_pmd_unshare_flush(&tlb, vma); + mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); return len + old_addr - old_end; } @@ -5862,7 +5863,6 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); bool adjust_reservation; unsigned long last_addr_mask; - bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -5885,10 +5885,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, address, ptep)) { + if (huge_pmd_unshare(tlb, vma, address, ptep)) { spin_unlock(ptl); - tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); - force_flush = true; address |= last_addr_mask; continue; } @@ -6004,21 +6002,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } tlb_end_vma(tlb, vma); - /* - * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We - * could defer the flush until now, since by holding i_mmap_rwsem we - * guaranteed that the last refernece would not be dropped. But we must - * do the flushing before we return, as otherwise i_mmap_rwsem will be - * dropped and the last reference to the shared PMDs page might be - * dropped as well. - * - * In theory we could defer the freeing of the PMD pages as well, but - * huge_pmd_unshare() relies on the exact page_count for the PMD page to - * detect sharing, so we cannot defer the release of the page either. - * Instead, do flush now. - */ - if (force_flush) - tlb_flush_mmu_tlbonly(tlb); + huge_pmd_unshare_flush(tlb, vma); } void __hugetlb_zap_begin(struct vm_area_struct *vma, @@ -7111,11 +7095,11 @@ long hugetlb_change_protection(struct vm_area_struct *vma, pte_t pte; struct hstate *h = hstate_vma(vma); long pages = 0, psize = huge_page_size(h); - bool shared_pmd = false; struct mmu_notifier_range range; unsigned long last_addr_mask; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; + struct mmu_gather tlb; /* * In the case of shared PMDs, the area to flush could be beyond @@ -7128,6 +7112,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, BUG_ON(address >= end); flush_cache_range(vma, range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); @@ -7152,7 +7137,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, } } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, address, ptep)) { + if (huge_pmd_unshare(&tlb, vma, address, ptep)) { /* * When uffd-wp is enabled on the vma, unshare * shouldn't happen at all. Warn about it if it @@ -7161,7 +7146,6 @@ long hugetlb_change_protection(struct vm_area_struct *vma, WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); - shared_pmd = true; address |= last_addr_mask; continue; } @@ -7193,7 +7177,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, } else if (unlikely(is_pte_marker(pte))) { /* * Do nothing on a poison marker; page is - * corrupted, permissons do not apply. Here + * corrupted, permissions do not apply. Here * pte_marker_uffd_wp()==true implies !poison * because they're mutual exclusive. */ @@ -7213,6 +7197,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; + tlb_remove_huge_tlb_entry(h, &tlb, ptep, address); } else { /* None pte */ if (unlikely(uffd_wp)) @@ -7225,17 +7210,9 @@ long hugetlb_change_protection(struct vm_area_struct *vma, cond_resched(); } - /* - * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare - * may have cleared our pud entry and done put_page on the page table: - * once we release i_mmap_rwsem, another task can do the final put_page - * and that page table be reused and filled with junk. If we actually - * did unshare a page of pmds, flush the range corresponding to the pud. - */ - if (shared_pmd) - flush_hugetlb_tlb_range(vma, range.start, range.end); - else - flush_hugetlb_tlb_range(vma, start, end); + + tlb_flush_mmu_tlbonly(&tlb); + huge_pmd_unshare_flush(&tlb, vma); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are * downgrading page table protection not changing it to point to a new @@ -7246,6 +7223,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb); return pages > 0 ? (pages << h->order) : pages; } @@ -7598,18 +7576,27 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, return pte; } -/* - * unmap huge page backed by shared pte. +/** + * huge_pmd_unshare - Unmap a pmd table if it is shared by multiple users + * @tlb: the current mmu_gather. + * @vma: the vma covering the pmd table. + * @addr: the address we are trying to unshare. + * @ptep: pointer into the (pmd) page table. * - * Called with page table lock held. + * Called with the page table lock held, the i_mmap_rwsem held in write mode + * and the hugetlb vma lock held in write mode. * - * returns: 1 successfully unmapped a shared pte page - * 0 the underlying pte page is not shared, or it is the last user + * Note: The caller must call huge_pmd_unshare_flush() before dropping the + * i_mmap_rwsem. + * + * Returns: 1 if it was a shared PMD table and it got unmapped, or 0 if it + * was not a shared PMD table. */ -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { unsigned long sz = huge_page_size(hstate_vma(vma)); + struct mm_struct *mm = vma->vm_mm; pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); @@ -7621,18 +7608,36 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); pud_clear(pud); - /* - * Once our caller drops the rmap lock, some other process might be - * using this page table as a normal, non-hugetlb page table. - * Wait for pending gup_fast() in other threads to finish before letting - * that happen. - */ - tlb_remove_table_sync_one(); - ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); + + tlb_unshare_pmd_ptdesc(tlb, virt_to_ptdesc(ptep), addr); + mm_dec_nr_pmds(mm); return 1; } +/* + * huge_pmd_unshare_flush - Complete a sequence of huge_pmd_unshare() calls + * @tlb: the current mmu_gather. + * @vma: the vma covering the pmd table. + * + * Perform necessary TLB flushes or IPI broadcasts to synchronize PMD table + * unsharing with concurrent page table walkers. + * + * This function must be called after a sequence of huge_pmd_unshare() + * calls while still holding the i_mmap_rwsem. + */ +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + /* + * We must synchronize page table unsharing such that nobody will + * try reusing a previously-shared page table while it might still + * be in use by previous sharers (TLB, GUP_fast). + */ + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + + tlb_flush_unshared_tables(tlb); +} + #else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, @@ -7641,12 +7646,16 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, return NULL; } -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { return 0; } +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ +} + void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { @@ -7913,6 +7922,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; + struct mmu_gather tlb; unsigned long address; spinlock_t *ptl; pte_t *ptep; @@ -7924,6 +7934,8 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, return; flush_cache_range(vma, start, end); + tlb_gather_mmu_vma(&tlb, vma); + /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. @@ -7942,10 +7954,10 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); - huge_pmd_unshare(mm, vma, address, ptep); + huge_pmd_unshare(&tlb, vma, address, ptep); spin_unlock(ptl); } - flush_hugetlb_tlb_range(vma, start, end); + huge_pmd_unshare_flush(&tlb, vma); if (take_locks) { i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); @@ -7955,6 +7967,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb); } /* diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index ba0fb1b6a5a8eb..96ee2bd16ee153 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -75,7 +75,7 @@ static int vmemmap_split_pmd(pmd_t *pmd, struct page *head, unsigned long start, if (likely(pmd_leaf(*pmd))) { /* * Higher order allocations from buddy allocator must be able to - * be treated as indepdenent small pages (as they can be freed + * be treated as independent small pages (as they can be freed * individually). */ if (!PageReserved(head)) @@ -684,7 +684,7 @@ static void __hugetlb_vmemmap_optimize_folios(struct hstate *h, ret = hugetlb_vmemmap_split_folio(h, folio); /* - * Spliting the PMD requires allocating a page, thus lets fail + * Splitting the PMD requires allocating a page, thus let's fail * early once we encounter the first OOM. No point in retrying * as it can be dynamically done on remap with the memory * we get back from the vmemmap deduplication. @@ -715,7 +715,7 @@ static void __hugetlb_vmemmap_optimize_folios(struct hstate *h, /* * Pages to be freed may have been accumulated. If we * encounter an ENOMEM, free what we have and try again. - * This can occur in the case that both spliting fails + * This can occur in the case that both splitting fails * halfway and head page allocation also failed. In this * case __hugetlb_vmemmap_optimize_folio() would free memory * allowing more vmemmap remaps to occur. diff --git a/mm/internal.h b/mm/internal.h index 1561fc2ff5b832..c80c6f566c2d93 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -538,16 +538,8 @@ extern unsigned long highest_memmap_pfn; bool folio_isolate_lru(struct folio *folio); void folio_putback_lru(struct folio *folio); extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); -#ifdef CONFIG_NUMA int user_proactive_reclaim(char *buf, struct mem_cgroup *memcg, pg_data_t *pgdat); -#else -static inline int user_proactive_reclaim(char *buf, - struct mem_cgroup *memcg, pg_data_t *pgdat) -{ - return 0; -} -#endif /* * in mm/rmap.c: diff --git a/mm/kasan/common.c b/mm/kasan/common.c index d4c14359feaf9d..3341474507f954 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -28,6 +28,7 @@ #include #include #include +#include #include "kasan.h" #include "../slab.h" @@ -582,3 +583,55 @@ bool __kasan_check_byte(const void *address, unsigned long ip) } return true; } + +#ifdef CONFIG_KASAN_VMALLOC +void __kasan_unpoison_vmap_areas(struct vm_struct **vms, int nr_vms, + kasan_vmalloc_flags_t flags) +{ + unsigned long size; + void *addr; + int area; + u8 tag; + + /* + * If KASAN_VMALLOC_KEEP_TAG was set at this point, all vms[] pointers + * would be unpoisoned with the KASAN_TAG_KERNEL which would disable + * KASAN checks down the line. + */ + if (WARN_ON_ONCE(flags & KASAN_VMALLOC_KEEP_TAG)) + return; + + size = vms[0]->size; + addr = vms[0]->addr; + vms[0]->addr = __kasan_unpoison_vmalloc(addr, size, flags); + tag = get_tag(vms[0]->addr); + + for (area = 1 ; area < nr_vms ; area++) { + size = vms[area]->size; + addr = set_tag(vms[area]->addr, tag); + vms[area]->addr = + __kasan_unpoison_vmalloc(addr, size, flags | KASAN_VMALLOC_KEEP_TAG); + } +} + +void __kasan_vrealloc(const void *addr, unsigned long old_size, + unsigned long new_size) +{ + if (new_size < old_size) { + kasan_poison_last_granule(addr, new_size); + + new_size = round_up(new_size, KASAN_GRANULE_SIZE); + old_size = round_up(old_size, KASAN_GRANULE_SIZE); + if (new_size < old_size) + __kasan_poison_vmalloc(addr + new_size, + old_size - new_size); + } else if (new_size > old_size) { + old_size = round_down(old_size, KASAN_GRANULE_SIZE); + __kasan_unpoison_vmalloc(addr + old_size, + new_size - old_size, + KASAN_VMALLOC_PROT_NORMAL | + KASAN_VMALLOC_VM_ALLOC | + KASAN_VMALLOC_KEEP_TAG); + } +} +#endif diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 1c373cc4b3fa5a..cbef5e450954e3 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -361,7 +361,7 @@ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, return (void *)start; } - tag = kasan_random_tag(); + tag = (flags & KASAN_VMALLOC_KEEP_TAG) ? get_tag(start) : kasan_random_tag(); start = set_tag(start, tag); /* Unpoison and initialize memory up to size. */ diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 5d2a876035d656..5e47ae7fdd590e 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -648,7 +648,9 @@ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, !(flags & KASAN_VMALLOC_PROT_NORMAL)) return (void *)start; - start = set_tag(start, kasan_random_tag()); + if (unlikely(!(flags & KASAN_VMALLOC_KEEP_TAG))) + start = set_tag(start, kasan_random_tag()); + kasan_unpoison(start, size, false); return (void *)start; } diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 727c20c94ac596..6da35d477269f7 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -595,7 +595,7 @@ static void rcu_guarded_free(struct rcu_head *h) static unsigned long kfence_init_pool(void) { unsigned long addr, start_pfn; - int i; + int i, rand; if (!arch_kfence_init_pool()) return (unsigned long)__kfence_pool; @@ -645,13 +645,27 @@ static unsigned long kfence_init_pool(void) INIT_LIST_HEAD(&meta->list); raw_spin_lock_init(&meta->lock); meta->state = KFENCE_OBJECT_UNUSED; - meta->addr = addr; /* Initialize for validation in metadata_to_pageaddr(). */ - list_add_tail(&meta->list, &kfence_freelist); + /* Use addr to randomize the freelist. */ + meta->addr = i; /* Protect the right redzone. */ - if (unlikely(!kfence_protect(addr + PAGE_SIZE))) + if (unlikely(!kfence_protect(addr + 2 * i * PAGE_SIZE + PAGE_SIZE))) goto reset_slab; + } + + for (i = CONFIG_KFENCE_NUM_OBJECTS; i > 0; i--) { + rand = get_random_u32_below(i); + swap(kfence_metadata_init[i - 1].addr, kfence_metadata_init[rand].addr); + } + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + struct kfence_metadata *meta_1 = &kfence_metadata_init[i]; + struct kfence_metadata *meta_2 = &kfence_metadata_init[meta_1->addr]; + + list_add_tail(&meta_2->list, &kfence_freelist); + } + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + kfence_metadata_init[i].addr = addr; addr += 2 * PAGE_SIZE; } @@ -664,6 +678,7 @@ static unsigned long kfence_init_pool(void) return 0; reset_slab: + addr += 2 * i * PAGE_SIZE; for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { struct slab *slab; diff --git a/mm/kmsan/core.c b/mm/kmsan/core.c index 35ceaa8adb41eb..90f427b95a213e 100644 --- a/mm/kmsan/core.c +++ b/mm/kmsan/core.c @@ -33,7 +33,7 @@ bool kmsan_enabled __read_mostly; /* * Per-CPU KMSAN context to be used in interrupts, where current->kmsan is - * unavaliable. + * unavailable. */ DEFINE_PER_CPU(struct kmsan_ctx, kmsan_percpu_ctx); diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c index 55fdea199aaf01..8bd50f5b1092e7 100644 --- a/mm/kmsan/shadow.c +++ b/mm/kmsan/shadow.c @@ -207,7 +207,7 @@ void kmsan_free_page(struct page *page, unsigned int order) if (!kmsan_enabled || kmsan_in_runtime()) return; kmsan_enter_runtime(); - kmsan_internal_poison_memory(page_address(page), page_size(page), + kmsan_internal_poison_memory(page_address(page), PAGE_SIZE << order, GFP_KERNEL & ~(__GFP_RECLAIM), KMSAN_POISON_CHECK | KMSAN_POISON_FREE); kmsan_leave_runtime(); diff --git a/mm/ksm.c b/mm/ksm.c index c4e73040994999..4f672f4f21407d 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -389,7 +389,7 @@ static unsigned long ewma(unsigned long prev, unsigned long curr) * exponentially weighted moving average. The new pages_to_scan value is * multiplied with that change factor: * - * new_pages_to_scan *= change facor + * new_pages_to_scan *= change factor * * The new_pages_to_scan value is limited by the cpu min and max values. It * calculates the cpu percent for the last scan and calculates the new @@ -2712,8 +2712,14 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) spin_unlock(&ksm_mmlist_lock); mm_slot_free(mm_slot_cache, mm_slot); + /* + * Only clear MMF_VM_MERGEABLE. We must not clear + * MMF_VM_MERGE_ANY, because for those MMF_VM_MERGE_ANY process, + * perhaps their mm_struct has just been added to ksm_mm_slot + * list, and its process has not yet officially started running + * or has not yet performed mmap/brk to allocate anonymous VMAS. + */ mm_flags_clear(MMF_VM_MERGEABLE, mm); - mm_flags_clear(MMF_VM_MERGE_ANY, mm); mmap_read_unlock(mm); mmdrop(mm); } else { @@ -2831,12 +2837,20 @@ static int __ksm_del_vma(struct vm_area_struct *vma) * * Returns: @vm_flags possibly updated to mark mergeable. */ -vm_flags_t ksm_vma_flags(const struct mm_struct *mm, const struct file *file, +vm_flags_t ksm_vma_flags(struct mm_struct *mm, const struct file *file, vm_flags_t vm_flags) { if (mm_flags_test(MMF_VM_MERGE_ANY, mm) && - __ksm_should_add_vma(file, vm_flags)) + __ksm_should_add_vma(file, vm_flags)) { vm_flags |= VM_MERGEABLE; + /* + * Generally, the flags here always include MMF_VM_MERGEABLE. + * However, in rare cases, this flag may be cleared by ksmd who + * scans a cycle without finding any mergeable vma. + */ + if (unlikely(!mm_flags_test(MMF_VM_MERGEABLE, mm))) + __ksm_enter(mm); + } return vm_flags; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 3edebb0cda30b3..6e770bad79ce3b 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -684,6 +684,8 @@ static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift, unsigned long poisoned_pfn, struct to_kill *tk) { unsigned long pfn = 0; + unsigned long hwpoison_vaddr; + unsigned long mask; if (pte_present(pte)) { pfn = pte_pfn(pte); @@ -694,10 +696,12 @@ static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift, pfn = swp_offset_pfn(swp); } - if (!pfn || pfn != poisoned_pfn) + mask = ~((1UL << (shift - PAGE_SHIFT)) - 1); + if (!pfn || pfn != (poisoned_pfn & mask)) return 0; - set_to_kill(tk, addr, shift); + hwpoison_vaddr = addr + ((poisoned_pfn - pfn) << PAGE_SHIFT); + set_to_kill(tk, hwpoison_vaddr, shift); return 1; } @@ -1873,12 +1877,22 @@ static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag) return count; } -static int folio_set_hugetlb_hwpoison(struct folio *folio, struct page *page) +#define MF_HUGETLB_FREED 0 /* freed hugepage */ +#define MF_HUGETLB_IN_USED 1 /* in-use hugepage */ +#define MF_HUGETLB_NON_HUGEPAGE 2 /* not a hugepage */ +#define MF_HUGETLB_FOLIO_PRE_POISONED 3 /* folio already poisoned */ +#define MF_HUGETLB_PAGE_PRE_POISONED 4 /* exact page already poisoned */ +#define MF_HUGETLB_RETRY 5 /* hugepage is busy, retry */ +/* + * Set hugetlb folio as hwpoisoned, update folio private raw hwpoison list + * to keep track of the poisoned pages. + */ +static int hugetlb_update_hwpoison(struct folio *folio, struct page *page) { struct llist_head *head; struct raw_hwp_page *raw_hwp; struct raw_hwp_page *p; - int ret = folio_test_set_hwpoison(folio) ? -EHWPOISON : 0; + int ret = folio_test_set_hwpoison(folio) ? MF_HUGETLB_FOLIO_PRE_POISONED : 0; /* * Once the hwpoison hugepage has lost reliable raw error info, @@ -1886,20 +1900,17 @@ static int folio_set_hugetlb_hwpoison(struct folio *folio, struct page *page) * so skip to add additional raw error info. */ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) - return -EHWPOISON; + return MF_HUGETLB_FOLIO_PRE_POISONED; head = raw_hwp_list_head(folio); llist_for_each_entry(p, head->first, node) { if (p->page == page) - return -EHWPOISON; + return MF_HUGETLB_PAGE_PRE_POISONED; } raw_hwp = kmalloc(sizeof(struct raw_hwp_page), GFP_ATOMIC); if (raw_hwp) { raw_hwp->page = page; llist_add(&raw_hwp->node, head); - /* the first error event will be counted in action_result(). */ - if (ret) - num_poisoned_pages_inc(page_to_pfn(page)); } else { /* * Failed to save raw error info. We no longer trace all @@ -1947,42 +1958,39 @@ void folio_clear_hugetlb_hwpoison(struct folio *folio) /* * Called from hugetlb code with hugetlb_lock held. - * - * Return values: - * 0 - free hugepage - * 1 - in-use hugepage - * 2 - not a hugepage - * -EBUSY - the hugepage is busy (try to retry) - * -EHWPOISON - the hugepage is already hwpoisoned */ int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { struct page *page = pfn_to_page(pfn); struct folio *folio = page_folio(page); - int ret = 2; /* fallback to normal page handling */ bool count_increased = false; + int ret, rc; - if (!folio_test_hugetlb(folio)) + if (!folio_test_hugetlb(folio)) { + ret = MF_HUGETLB_NON_HUGEPAGE; goto out; - - if (flags & MF_COUNT_INCREASED) { - ret = 1; + } else if (flags & MF_COUNT_INCREASED) { + ret = MF_HUGETLB_IN_USED; count_increased = true; } else if (folio_test_hugetlb_freed(folio)) { - ret = 0; + ret = MF_HUGETLB_FREED; } else if (folio_test_hugetlb_migratable(folio)) { - ret = folio_try_get(folio); - if (ret) + if (folio_try_get(folio)) { + ret = MF_HUGETLB_IN_USED; count_increased = true; + } else { + ret = MF_HUGETLB_FREED; + } } else { - ret = -EBUSY; + ret = MF_HUGETLB_RETRY; if (!(flags & MF_NO_RETRY)) goto out; } - if (folio_set_hugetlb_hwpoison(folio, page)) { - ret = -EHWPOISON; + rc = hugetlb_update_hwpoison(folio, page); + if (rc >= MF_HUGETLB_FOLIO_PRE_POISONED) { + ret = rc; goto out; } @@ -2007,10 +2015,16 @@ int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, * with basic operations like hugepage allocation/free/demotion. * So some of prechecks for hwpoison (pinning, and testing/setting * PageHWPoison) should be done in single hugetlb_lock range. + * Returns: + * 0 - not hugetlb, or recovered + * -EBUSY - not recovered + * -EOPNOTSUPP - hwpoison_filter'ed + * -EHWPOISON - folio or exact page already poisoned + * -EFAULT - kill_accessing_process finds current->mm null */ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb) { - int res; + int res, rv; struct page *p = pfn_to_page(pfn); struct folio *folio; unsigned long page_flags; @@ -2019,22 +2033,29 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb *hugetlb = 1; retry: res = get_huge_page_for_hwpoison(pfn, flags, &migratable_cleared); - if (res == 2) { /* fallback to normal page handling */ + switch (res) { + case MF_HUGETLB_NON_HUGEPAGE: /* fallback to normal page handling */ *hugetlb = 0; return 0; - } else if (res == -EHWPOISON) { - if (flags & MF_ACTION_REQUIRED) { - folio = page_folio(p); - res = kill_accessing_process(current, folio_pfn(folio), flags); - } - action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); - return res; - } else if (res == -EBUSY) { + case MF_HUGETLB_RETRY: if (!(flags & MF_NO_RETRY)) { flags |= MF_NO_RETRY; goto retry; } return action_result(pfn, MF_MSG_GET_HWPOISON, MF_IGNORED); + case MF_HUGETLB_FOLIO_PRE_POISONED: + case MF_HUGETLB_PAGE_PRE_POISONED: + rv = -EHWPOISON; + if (flags & MF_ACTION_REQUIRED) + rv = kill_accessing_process(current, pfn, flags); + if (res == MF_HUGETLB_PAGE_PRE_POISONED) + action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); + else + action_result(pfn, MF_MSG_HUGE, MF_FAILED); + return rv; + default: + WARN_ON((res != MF_HUGETLB_FREED) && (res != MF_HUGETLB_IN_USED)); + break; } folio = page_folio(p); @@ -2045,7 +2066,7 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb if (migratable_cleared) folio_set_hugetlb_migratable(folio); folio_unlock(folio); - if (res == 1) + if (res == MF_HUGETLB_IN_USED) folio_put(folio); return -EOPNOTSUPP; } @@ -2054,7 +2075,7 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb * Handling free hugepage. The possible race with hugepage allocation * or demotion can be prevented by PageHWPoison flag. */ - if (res == 0) { + if (res == MF_HUGETLB_FREED) { folio_unlock(folio); if (__page_handle_poison(p) > 0) { page_ref_inc(p); diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index 0ea5c13f10a233..864811fff4093f 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -519,7 +519,7 @@ static inline void __init_node_memory_type(int node, struct memory_dev_type *mem * for each device getting added in the same NUMA node * with this specific memtype, bump the map count. We * Only take memtype device reference once, so that - * changing a node memtype can be done by droping the + * changing a node memtype can be done by dropping the * only reference count taken here. */ diff --git a/mm/memory.c b/mm/memory.c index b59ae7ce42ebc7..61748b762876f4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4328,7 +4328,7 @@ static inline bool should_try_to_free_swap(struct folio *folio, * If we want to map a page that's in the swapcache writable, we * have to detect via the refcount if we're really the exclusive * user. Try freeing the swapcache to get rid of the swapcache - * reference only in case it's likely that we'll be the exlusive user. + * reference only in case it's likely that we'll be the exclusive user. */ return (fault_flags & FAULT_FLAG_WRITE) && !folio_test_ksm(folio) && folio_ref_count(folio) == (1 + folio_nr_pages(folio)); @@ -5405,7 +5405,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct folio *folio, struct page *pa /** * set_pte_range - Set a range of PTEs to point to pages in a folio. - * @vmf: Fault decription. + * @vmf: Fault description. * @folio: The folio that contains @page. * @page: The first page to create a PTE for. * @nr: The number of PTEs to create. diff --git a/mm/migrate.c b/mm/migrate.c index c0e9f15be2a229..a936623d0b237c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1450,6 +1450,7 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, int page_was_mapped = 0; struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; + enum ttu_flags ttu = 0; if (folio_ref_count(src) == 1) { /* page was freed from under us. So we are done. */ @@ -1490,8 +1491,6 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, goto put_anon; if (folio_mapped(src)) { - enum ttu_flags ttu = 0; - if (!folio_test_anon(src)) { /* * In shared mappings, try_to_unmap could potentially @@ -1508,16 +1507,17 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, try_to_migrate(src, ttu); page_was_mapped = 1; - - if (ttu & TTU_RMAP_LOCKED) - i_mmap_unlock_write(mapping); } if (!folio_mapped(src)) rc = move_to_new_folio(dst, src, mode); if (page_was_mapped) - remove_migration_ptes(src, !rc ? dst : src, 0); + remove_migration_ptes(src, !rc ? dst : src, + ttu ? RMP_LOCKED : 0); + + if (ttu & TTU_RMAP_LOCKED) + i_mmap_unlock_write(mapping); unlock_put_anon: folio_unlock(dst); diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 374aa6f021c6b0..5619ee967f3c7d 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -426,6 +427,7 @@ static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, #endif tlb->vma_pfn = 0; + tlb->fully_unshared_tables = 0; __tlb_reset_range(tlb); inc_tlb_flush_pending(tlb->mm); } @@ -459,6 +461,31 @@ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) __tlb_gather_mmu(tlb, mm, true); } +/** + * tlb_gather_mmu_vma - initialize an mmu_gather structure for operating on a + * single VMA + * @tlb: the mmu_gather structure to initialize + * @vma: the vm_area_struct + * + * Called to initialize an (on-stack) mmu_gather structure for operating on + * a single VMA. In contrast to tlb_gather_mmu(), calling this function will + * not require another call to tlb_start_vma(). In contrast to tlb_start_vma(), + * this function will *not* call flush_cache_range(). + * + * For hugetlb VMAs, this function will also initialize the mmu_gather + * page_size accordingly, not requiring a separate call to + * tlb_change_page_size(). + * + */ +void tlb_gather_mmu_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + tlb_gather_mmu(tlb, vma->vm_mm); + tlb_update_vma_flags(tlb, vma); + if (is_vm_hugetlb_page(vma)) + /* All entries have the same size. */ + tlb_change_page_size(tlb, huge_page_size(hstate_vma(vma))); +} + /** * tlb_finish_mmu - finish an mmu_gather structure * @tlb: the mmu_gather structure to finish @@ -468,6 +495,12 @@ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) */ void tlb_finish_mmu(struct mmu_gather *tlb) { + /* + * We expect an earlier huge_pmd_unshare_flush() call to sort this out, + * due to complicated locking requirements with page table unsharing. + */ + VM_WARN_ON_ONCE(tlb->fully_unshared_tables); + /* * If there are parallel threads are doing PTE changes on same range * under non-exclusive lock (e.g., mmap_lock read-side) but defer TLB diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c index 5b009a9cd8b4c2..8f5735fda0a218 100644 --- a/mm/numa_memblks.c +++ b/mm/numa_memblks.c @@ -7,6 +7,8 @@ #include #include +#include + int numa_distance_cnt; static u8 *numa_distance; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ed82ee55e66aff..623f6e5b583ab6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -166,6 +166,33 @@ static DEFINE_MUTEX(pcp_batch_high_lock); #define pcp_spin_unlock(ptr) \ pcpu_spin_unlock(lock, ptr) +/* + * With the UP spinlock implementation, when we spin_lock(&pcp->lock) (for i.e. + * a potentially remote cpu drain) and get interrupted by an operation that + * attempts pcp_spin_trylock(), we can't rely on the trylock failure due to UP + * spinlock assumptions making the trylock a no-op. So we have to turn that + * spin_lock() to a spin_lock_irqsave(). This works because on UP there are no + * remote cpu's so we can only be locking the only existing local one. + */ +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) +static inline void __flags_noop(unsigned long *flags) { } +#define pcp_spin_lock_maybe_irqsave(ptr, flags) \ +({ \ + __flags_noop(&(flags)); \ + spin_lock(&(ptr)->lock); \ +}) +#define pcp_spin_unlock_maybe_irqrestore(ptr, flags) \ +({ \ + spin_unlock(&(ptr)->lock); \ + __flags_noop(&(flags)); \ +}) +#else +#define pcp_spin_lock_maybe_irqsave(ptr, flags) \ + spin_lock_irqsave(&(ptr)->lock, flags) +#define pcp_spin_unlock_maybe_irqrestore(ptr, flags) \ + spin_unlock_irqrestore(&(ptr)->lock, flags) +#endif + #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); EXPORT_PER_CPU_SYMBOL(numa_node); @@ -913,6 +940,17 @@ buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn, NULL) != NULL; } +static void change_pageblock_range(struct page *pageblock_page, + int start_order, int migratetype) +{ + int nr_pageblocks = 1 << (start_order - pageblock_order); + + while (nr_pageblocks--) { + set_pageblock_migratetype(pageblock_page, migratetype); + pageblock_page += pageblock_nr_pages; + } +} + /* * Freeing function for a buddy system allocator. * @@ -999,7 +1037,7 @@ static inline void __free_one_page(struct page *page, * expand() down the line puts the sub-blocks * on the right freelists. */ - set_pageblock_migratetype(buddy, migratetype); + change_pageblock_range(buddy, order, migratetype); } combined_pfn = buddy_pfn & pfn; @@ -2146,17 +2184,6 @@ bool pageblock_unisolate_and_move_free_pages(struct zone *zone, struct page *pag #endif /* CONFIG_MEMORY_ISOLATION */ -static void change_pageblock_range(struct page *pageblock_page, - int start_order, int migratetype) -{ - int nr_pageblocks = 1 << (start_order - pageblock_order); - - while (nr_pageblocks--) { - set_pageblock_migratetype(pageblock_page, migratetype); - pageblock_page += pageblock_nr_pages; - } -} - static inline bool boost_watermark(struct zone *zone) { unsigned long max_boost; @@ -2552,10 +2579,11 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * Called from the vmstat counter updater to decay the PCP high. * Return whether there are addition works to do. */ -int decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) +bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) { - int high_min, to_drain, batch; - int todo = 0; + int high_min, to_drain, to_drain_batched, batch; + unsigned long UP_flags; + bool todo = false; high_min = READ_ONCE(pcp->high_min); batch = READ_ONCE(pcp->batch); @@ -2568,15 +2596,18 @@ int decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) pcp->high = max3(pcp->count - (batch << CONFIG_PCP_BATCH_SCALE_MAX), pcp->high - (pcp->high >> 3), high_min); if (pcp->high > high_min) - todo++; + todo = true; } to_drain = pcp->count - pcp->high; - if (to_drain > 0) { - spin_lock(&pcp->lock); - free_pcppages_bulk(zone, to_drain, pcp, 0); - spin_unlock(&pcp->lock); - todo++; + while (to_drain > 0) { + to_drain_batched = min(to_drain, batch); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); + free_pcppages_bulk(zone, to_drain_batched, pcp, 0); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); + todo = true; + + to_drain -= to_drain_batched; } return todo; @@ -2590,14 +2621,15 @@ int decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) */ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) { + unsigned long UP_flags; int to_drain, batch; batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); if (to_drain > 0) { - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); free_pcppages_bulk(zone, to_drain, pcp, 0); - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); } } #endif @@ -2608,10 +2640,11 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) static void drain_pages_zone(unsigned int cpu, struct zone *zone) { struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + unsigned long UP_flags; int count; do { - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); count = pcp->count; if (count) { int to_drain = min(count, @@ -2620,7 +2653,7 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone) free_pcppages_bulk(zone, to_drain, pcp, 0); count -= to_drain; } - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); } while (count); } @@ -6078,6 +6111,7 @@ static void zone_pcp_update_cacheinfo(struct zone *zone, unsigned int cpu) { struct per_cpu_pages *pcp; struct cpu_cacheinfo *cci; + unsigned long UP_flags; pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); cci = get_cpu_cacheinfo(cpu); @@ -6088,12 +6122,12 @@ static void zone_pcp_update_cacheinfo(struct zone *zone, unsigned int cpu) * This can reduce zone lock contention without hurting * cache-hot pages sharing. */ - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); if ((cci->per_cpu_data_slice_size >> PAGE_SHIFT) > 3 * pcp->batch) pcp->flags |= PCPF_FREE_HIGH_BATCH; else pcp->flags &= ~PCPF_FREE_HIGH_BATCH; - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); } void setup_pcp_cacheinfo(unsigned int cpu) @@ -6611,11 +6645,19 @@ static int percpu_pagelist_high_fraction_sysctl_handler(const struct ctl_table * int old_percpu_pagelist_high_fraction; int ret; + /* + * Avoid using pcp_batch_high_lock for reads as the value is read + * atomically and a race with offlining is harmless. + */ + + if (!write) + return proc_dointvec_minmax(table, write, buffer, length, ppos); + mutex_lock(&pcp_batch_high_lock); old_percpu_pagelist_high_fraction = percpu_pagelist_high_fraction; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); - if (!write || ret < 0) + if (ret < 0) goto out; /* Sanity checking to avoid pcp imbalance */ diff --git a/mm/page_owner.c b/mm/page_owner.c index 589ec37c94aab9..bc26764142ba5f 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -936,7 +936,7 @@ static const struct file_operations page_owner_stack_operations = { .open = page_owner_stack_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; static int page_owner_threshold_get(void *data, u64 *val) diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 567e2d084071e3..8c22be79b73439 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -406,3 +407,41 @@ pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, pte_unmap_unlock(pte, ptl); goto again; } + +#ifdef CONFIG_ASYNC_KERNEL_PGTABLE_FREE +static void kernel_pgtable_work_func(struct work_struct *work); + +static struct { + struct list_head list; + /* protect above ptdesc lists */ + spinlock_t lock; + struct work_struct work; +} kernel_pgtable_work = { + .list = LIST_HEAD_INIT(kernel_pgtable_work.list), + .lock = __SPIN_LOCK_UNLOCKED(kernel_pgtable_work.lock), + .work = __WORK_INITIALIZER(kernel_pgtable_work.work, kernel_pgtable_work_func), +}; + +static void kernel_pgtable_work_func(struct work_struct *work) +{ + struct ptdesc *pt, *next; + LIST_HEAD(page_list); + + spin_lock(&kernel_pgtable_work.lock); + list_splice_tail_init(&kernel_pgtable_work.list, &page_list); + spin_unlock(&kernel_pgtable_work.lock); + + iommu_sva_invalidate_kva_range(PAGE_OFFSET, TLB_FLUSH_ALL); + list_for_each_entry_safe(pt, next, &page_list, pt_list) + __pagetable_free(pt); +} + +void pagetable_free_kernel(struct ptdesc *pt) +{ + spin_lock(&kernel_pgtable_work.lock); + list_add(&pt->pt_list, &kernel_pgtable_work.list); + spin_unlock(&kernel_pgtable_work.lock); + + schedule_work(&kernel_pgtable_work.work); +} +#endif diff --git a/mm/rmap.c b/mm/rmap.c index ac4f783d6ec2f5..f1e6a97cf46043 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -76,7 +76,7 @@ #include #include -#include +#include #define CREATE_TRACE_POINTS #include @@ -2019,26 +2019,25 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * if unsuccessful. */ if (!anon) { + struct mmu_gather tlb; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) goto walk_abort; - if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { + + tlb_gather_mmu_vma(&tlb, vma); + if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); - flush_tlb_range(vma, - range.start, range.end); + huge_pmd_unshare_flush(&tlb, vma); + tlb_finish_mmu(&tlb); /* - * The ref count of the PMD page was - * dropped which is part of the way map - * counting is done for shared PMDs. - * Return 'true' here. When there is - * no other sharing, huge_pmd_unshare - * returns false and we will unmap the - * actual page and drop map count - * to zero. + * The PMD table was unmapped, + * consequently unmapping the folio. */ goto walk_done; } hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) @@ -2404,31 +2403,29 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, * fail if unsuccessful. */ if (!anon) { + struct mmu_gather tlb; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } - if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { - hugetlb_vma_unlock_write(vma); - flush_tlb_range(vma, - range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); + if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { + hugetlb_vma_unlock_write(vma); + huge_pmd_unshare_flush(&tlb, vma); + tlb_finish_mmu(&tlb); /* - * The ref count of the PMD page was - * dropped which is part of the way map - * counting is done for shared PMDs. - * Return 'true' here. When there is - * no other sharing, huge_pmd_unshare - * returns false and we will unmap the - * actual page and drop map count - * to zero. + * The PMD table was unmapped, + * consequently unmapping the folio. */ page_vma_mapped_walk_done(&pvmw); break; } hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); diff --git a/mm/secretmem.c b/mm/secretmem.c index b59350daffe318..9b0f5d9ec6f4b1 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -227,7 +227,7 @@ SYSCALL_DEFINE1(memfd_secret, unsigned int, flags) struct file *file; int fd, err; - /* make sure local flags do not confict with global fcntl.h */ + /* make sure local flags do not conflict with global fcntl.h */ BUILD_BUG_ON(SECRETMEM_FLAGS_MASK & O_CLOEXEC); if (!secretmem_enable || !can_set_direct_map()) diff --git a/mm/shmem.c b/mm/shmem.c index 5a3f0f754dc0c6..94c5b0d78ac31e 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -944,17 +944,29 @@ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap) * being freed). */ static long shmem_free_swap(struct address_space *mapping, - pgoff_t index, void *radswap) + pgoff_t index, pgoff_t end, void *radswap) { - int order = xa_get_order(&mapping->i_pages, index); - void *old; + XA_STATE(xas, &mapping->i_pages, index); + unsigned int nr_pages = 0; + pgoff_t base; + void *entry; - old = xa_cmpxchg_irq(&mapping->i_pages, index, radswap, NULL, 0); - if (old != radswap) - return 0; - free_swap_and_cache_nr(radix_to_swp_entry(radswap), 1 << order); + xas_lock_irq(&xas); + entry = xas_load(&xas); + if (entry == radswap) { + nr_pages = 1 << xas_get_order(&xas); + base = round_down(xas.xa_index, nr_pages); + if (base < index || base + nr_pages - 1 > end) + nr_pages = 0; + else + xas_store(&xas, NULL); + } + xas_unlock_irq(&xas); + + if (nr_pages) + free_swap_and_cache_nr(radix_to_swp_entry(radswap), nr_pages); - return 1 << order; + return nr_pages; } /* @@ -1106,8 +1118,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (xa_is_value(folio)) { if (unfalloc) continue; - nr_swaps_freed += shmem_free_swap(mapping, - indices[i], folio); + nr_swaps_freed += shmem_free_swap(mapping, indices[i], + end - 1, folio); continue; } @@ -1173,14 +1185,30 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, folio = fbatch.folios[i]; if (xa_is_value(folio)) { + int order; long swaps_freed; if (unfalloc) continue; - swaps_freed = shmem_free_swap(mapping, indices[i], folio); + swaps_freed = shmem_free_swap(mapping, indices[i], + end - 1, folio); if (!swaps_freed) { - /* Swap was replaced by page: retry */ - index = indices[i]; + pgoff_t base = indices[i]; + + order = shmem_confirm_swap(mapping, indices[i], + radix_to_swp_entry(folio)); + /* + * If found a large swap entry cross the end or start + * border, skip it as the truncate_inode_partial_folio + * above should have at least zerod its content once. + */ + if (order > 0) { + base = round_down(base, 1 << order); + if (base < start || base + (1 << order) > end) + continue; + } + /* Swap was replaced by page or extended, retry */ + index = base; break; } nr_swaps_freed += swaps_freed; @@ -4039,6 +4067,7 @@ static int shmem_rename2(struct mnt_idmap *idmap, { struct inode *inode = d_inode(old_dentry); int they_are_dirs = S_ISDIR(inode->i_mode); + bool had_offset = false; int error; if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) @@ -4051,16 +4080,23 @@ static int shmem_rename2(struct mnt_idmap *idmap, if (!simple_empty(new_dentry)) return -ENOTEMPTY; + error = simple_offset_add(shmem_get_offset_ctx(new_dir), new_dentry); + if (error == -EBUSY) + had_offset = true; + else if (unlikely(error)) + return error; + if (flags & RENAME_WHITEOUT) { error = shmem_whiteout(idmap, old_dir, old_dentry); - if (error) + if (error) { + if (!had_offset) + simple_offset_remove(shmem_get_offset_ctx(new_dir), + new_dentry); return error; + } } - error = simple_offset_rename(old_dir, old_dentry, new_dir, new_dentry); - if (error) - return error; - + simple_offset_rename(old_dir, old_dentry, new_dir, new_dentry); if (d_really_is_positive(new_dentry)) { (void) shmem_unlink(new_dir, new_dentry); if (they_are_dirs) { diff --git a/mm/slab.h b/mm/slab.h index 078daecc7cf50a..bf9d8940b8f218 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -442,6 +442,7 @@ static inline bool is_kmalloc_normal(struct kmem_cache *s) bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj); void flush_all_rcu_sheaves(void); +void flush_rcu_sheaves_on_cache(struct kmem_cache *s); #define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \ SLAB_CACHE_DMA32 | SLAB_PANIC | \ diff --git a/mm/slab_common.c b/mm/slab_common.c index 932d13ada36c0d..87bde1d8916be6 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -259,7 +259,7 @@ static struct kmem_cache *create_cache(const char *name, * @object_size: The size of objects to be created in this cache. * @args: Additional arguments for the cache creation (see * &struct kmem_cache_args). - * @flags: See the desriptions of individual flags. The common ones are listed + * @flags: See the descriptions of individual flags. The common ones are listed * in the description below. * * Not to be called directly, use the kmem_cache_create() wrapper with the same @@ -492,7 +492,7 @@ void kmem_cache_destroy(struct kmem_cache *s) return; /* in-flight kfree_rcu()'s may include objects from our cache */ - kvfree_rcu_barrier(); + kvfree_rcu_barrier_on_cache(s); if (IS_ENABLED(CONFIG_SLUB_RCU_DEBUG) && (s->flags & SLAB_TYPESAFE_BY_RCU)) { @@ -2039,25 +2039,13 @@ void kvfree_call_rcu(struct rcu_head *head, void *ptr) } EXPORT_SYMBOL_GPL(kvfree_call_rcu); -/** - * kvfree_rcu_barrier - Wait until all in-flight kvfree_rcu() complete. - * - * Note that a single argument of kvfree_rcu() call has a slow path that - * triggers synchronize_rcu() following by freeing a pointer. It is done - * before the return from the function. Therefore for any single-argument - * call that will result in a kfree() to a cache that is to be destroyed - * during module exit, it is developer's responsibility to ensure that all - * such calls have returned before the call to kmem_cache_destroy(). - */ -void kvfree_rcu_barrier(void) +static inline void __kvfree_rcu_barrier(void) { struct kfree_rcu_cpu_work *krwp; struct kfree_rcu_cpu *krcp; bool queued; int i, cpu; - flush_all_rcu_sheaves(); - /* * Firstly we detach objects and queue them over an RCU-batch * for all CPUs. Finally queued works are flushed for each CPU. @@ -2119,8 +2107,43 @@ void kvfree_rcu_barrier(void) } } } + +/** + * kvfree_rcu_barrier - Wait until all in-flight kvfree_rcu() complete. + * + * Note that a single argument of kvfree_rcu() call has a slow path that + * triggers synchronize_rcu() following by freeing a pointer. It is done + * before the return from the function. Therefore for any single-argument + * call that will result in a kfree() to a cache that is to be destroyed + * during module exit, it is developer's responsibility to ensure that all + * such calls have returned before the call to kmem_cache_destroy(). + */ +void kvfree_rcu_barrier(void) +{ + flush_all_rcu_sheaves(); + __kvfree_rcu_barrier(); +} EXPORT_SYMBOL_GPL(kvfree_rcu_barrier); +/** + * kvfree_rcu_barrier_on_cache - Wait for in-flight kvfree_rcu() calls on a + * specific slab cache. + * @s: slab cache to wait for + * + * See the description of kvfree_rcu_barrier() for details. + */ +void kvfree_rcu_barrier_on_cache(struct kmem_cache *s) +{ + if (s->cpu_sheaves) + flush_rcu_sheaves_on_cache(s); + /* + * TODO: Introduce a version of __kvfree_rcu_barrier() that works + * on a specific slab cache. + */ + __kvfree_rcu_barrier(); +} +EXPORT_SYMBOL_GPL(kvfree_rcu_barrier_on_cache); + static unsigned long kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { @@ -2216,4 +2239,3 @@ void __init kvfree_rcu_init(void) } #endif /* CONFIG_KVFREE_RCU_BATCHED */ - diff --git a/mm/slub.c b/mm/slub.c index a0b905c2a557ef..896421a5555730 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2533,7 +2533,7 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init, memset((char *)kasan_reset_tag(x) + inuse, 0, s->size - inuse - rsize); /* - * Restore orig_size, otherwize kmalloc redzone overwritten + * Restore orig_size, otherwise kmalloc redzone overwritten * would be reported */ set_orig_size(s, x, orig_size); @@ -4118,42 +4118,47 @@ static void flush_rcu_sheaf(struct work_struct *w) /* needed for kvfree_rcu_barrier() */ -void flush_all_rcu_sheaves(void) +void flush_rcu_sheaves_on_cache(struct kmem_cache *s) { struct slub_flush_work *sfw; - struct kmem_cache *s; unsigned int cpu; - cpus_read_lock(); - mutex_lock(&slab_mutex); + mutex_lock(&flush_lock); - list_for_each_entry(s, &slab_caches, list) { - if (!s->cpu_sheaves) - continue; + for_each_online_cpu(cpu) { + sfw = &per_cpu(slub_flush, cpu); - mutex_lock(&flush_lock); + /* + * we don't check if rcu_free sheaf exists - racing + * __kfree_rcu_sheaf() might have just removed it. + * by executing flush_rcu_sheaf() on the cpu we make + * sure the __kfree_rcu_sheaf() finished its call_rcu() + */ - for_each_online_cpu(cpu) { - sfw = &per_cpu(slub_flush, cpu); + INIT_WORK(&sfw->work, flush_rcu_sheaf); + sfw->s = s; + queue_work_on(cpu, flushwq, &sfw->work); + } - /* - * we don't check if rcu_free sheaf exists - racing - * __kfree_rcu_sheaf() might have just removed it. - * by executing flush_rcu_sheaf() on the cpu we make - * sure the __kfree_rcu_sheaf() finished its call_rcu() - */ + for_each_online_cpu(cpu) { + sfw = &per_cpu(slub_flush, cpu); + flush_work(&sfw->work); + } - INIT_WORK(&sfw->work, flush_rcu_sheaf); - sfw->s = s; - queue_work_on(cpu, flushwq, &sfw->work); - } + mutex_unlock(&flush_lock); +} - for_each_online_cpu(cpu) { - sfw = &per_cpu(slub_flush, cpu); - flush_work(&sfw->work); - } +void flush_all_rcu_sheaves(void) +{ + struct kmem_cache *s; + + cpus_read_lock(); + mutex_lock(&slab_mutex); - mutex_unlock(&flush_lock); + list_for_each_entry(s, &slab_caches, list) { + if (!s->cpu_sheaves) + continue; + flush_rcu_sheaves_on_cache(s); } mutex_unlock(&slab_mutex); @@ -5687,8 +5692,12 @@ void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node) if (unlikely(!size)) return ZERO_SIZE_PTR; - if (IS_ENABLED(CONFIG_PREEMPT_RT) && (in_nmi() || in_hardirq())) - /* kmalloc_nolock() in PREEMPT_RT is not supported from irq */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) && !preemptible()) + /* + * kmalloc_nolock() in PREEMPT_RT is not supported from + * non-preemptible context because local_lock becomes a + * sleeping lock on RT. + */ return NULL; retry: if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) @@ -6223,11 +6232,29 @@ static void rcu_free_sheaf(struct rcu_head *head) free_empty_sheaf(s, sheaf); } +/* + * kvfree_call_rcu() can be called while holding a raw_spinlock_t. Since + * __kfree_rcu_sheaf() may acquire a spinlock_t (sleeping lock on PREEMPT_RT), + * this would violate lock nesting rules. Therefore, kvfree_call_rcu() avoids + * this problem by bypassing the sheaves layer entirely on PREEMPT_RT. + * + * However, lockdep still complains that it is invalid to acquire spinlock_t + * while holding raw_spinlock_t, even on !PREEMPT_RT where spinlock_t is a + * spinning lock. Tell lockdep that acquiring spinlock_t is valid here + * by temporarily raising the wait-type to LD_WAIT_CONFIG. + */ +static DEFINE_WAIT_OVERRIDE_MAP(kfree_rcu_sheaf_map, LD_WAIT_CONFIG); + bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj) { struct slub_percpu_sheaves *pcs; struct slab_sheaf *rcu_sheaf; + if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT))) + return false; + + lock_map_acquire_try(&kfree_rcu_sheaf_map); + if (!local_trylock(&s->cpu_sheaves->lock)) goto fail; @@ -6304,10 +6331,12 @@ bool __kfree_rcu_sheaf(struct kmem_cache *s, void *obj) local_unlock(&s->cpu_sheaves->lock); stat(s, FREE_RCU_SHEAF); + lock_map_release(&kfree_rcu_sheaf_map); return true; fail: stat(s, FREE_RCU_SHEAF_FAIL); + lock_map_release(&kfree_rcu_sheaf_map); return false; } @@ -6504,6 +6533,8 @@ static void defer_free(struct kmem_cache *s, void *head) guard(preempt)(); + head = kasan_reset_tag(head); + df = this_cpu_ptr(&defer_free_objects); if (llist_add(head + s->offset, &df->objects)) irq_work_queue(&df->work); @@ -6656,8 +6687,12 @@ void slab_free(struct kmem_cache *s, struct slab *slab, void *object, static noinline void memcg_alloc_abort_single(struct kmem_cache *s, void *object) { + struct slab *slab = virt_to_slab(object); + + alloc_tagging_slab_free_hook(s, slab, &object, 1); + if (likely(slab_free_hook(s, object, slab_want_init_on_free(s), false))) - do_slab_free(s, virt_to_slab(object), object, object, 1, _RET_IP_); + do_slab_free(s, slab, object, object, 1, _RET_IP_); } #endif diff --git a/mm/swap.h b/mm/swap.h index 8d8efdf1297a7f..c6bdc5d215934f 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -198,7 +198,7 @@ int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug); void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug); /* linux/mm/swap_state.c */ -extern struct address_space swap_space __ro_after_init; +extern struct address_space swap_space __read_mostly; static inline struct address_space *swap_address_space(swp_entry_t entry) { return &swap_space; diff --git a/mm/swap_state.c b/mm/swap_state.c index f4980dde5394b5..b8d7744b4436a0 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -37,8 +37,7 @@ static const struct address_space_operations swap_aops = { #endif }; -/* Set swap_space as read only as swap cache is handled by swap table */ -struct address_space swap_space __ro_after_init = { +struct address_space swap_space __read_mostly = { .a_ops = &swap_aops, }; diff --git a/mm/swapfile.c b/mm/swapfile.c index a1b4b9d80e3b59..89746abc473737 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1101,13 +1101,6 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o goto done; } - /* - * We don't have free cluster but have some clusters in discarding, - * do discard now and reclaim them. - */ - if ((si->flags & SWP_PAGE_DISCARD) && swap_do_scheduled_discard(si)) - goto new_cluster; - if (order) goto done; @@ -1394,6 +1387,33 @@ static bool swap_alloc_slow(swp_entry_t *entry, return false; } +/* + * Discard pending clusters in a synchronized way when under high pressure. + * Return: true if any cluster is discarded. + */ +static bool swap_sync_discard(void) +{ + bool ret = false; + int nid = numa_node_id(); + struct swap_info_struct *si, *next; + + spin_lock(&swap_avail_lock); + plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { + spin_unlock(&swap_avail_lock); + if (get_swap_device_info(si)) { + if (si->flags & SWP_PAGE_DISCARD) + ret = swap_do_scheduled_discard(si); + put_swap_device(si); + } + if (ret) + return true; + spin_lock(&swap_avail_lock); + } + spin_unlock(&swap_avail_lock); + + return false; +} + /** * folio_alloc_swap - allocate swap space for a folio * @folio: folio we want to move to swap @@ -1432,11 +1452,17 @@ int folio_alloc_swap(struct folio *folio, gfp_t gfp) } } +again: local_lock(&percpu_swap_cluster.lock); if (!swap_alloc_fast(&entry, order)) swap_alloc_slow(&entry, order); local_unlock(&percpu_swap_cluster.lock); + if (unlikely(!order && !entry.val)) { + if (swap_sync_discard()) + goto again; + } + /* Need to call this even if allocation failed, for MEMCG_SWAP_FAIL. */ if (mem_cgroup_try_charge_swap(folio, entry)) goto out_free; @@ -1677,7 +1703,7 @@ static bool swap_entries_put_map_nr(struct swap_info_struct *si, /* * Check if it's the last ref of swap entry in the freeing path. - * Qualified vlaue includes 1, SWAP_HAS_CACHE or SWAP_MAP_SHMEM. + * Qualified value includes 1, SWAP_HAS_CACHE or SWAP_MAP_SHMEM. */ static inline bool __maybe_unused swap_is_last_ref(unsigned char count) { diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index af61b95c89e4ec..0630f188c847c3 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1578,7 +1578,7 @@ static int validate_move_areas(struct userfaultfd_ctx *ctx, /* * For now, we keep it simple and only move between writable VMAs. - * Access flags are equal, therefore cheching only the source is enough. + * Access flags are equal, therefore checking only the source is enough. */ if (!(src_vma->vm_flags & VM_WRITE)) return -EINVAL; diff --git a/mm/vma.c b/mm/vma.c index abe0da33c84461..5815ae9e57703b 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -65,18 +65,13 @@ struct mmap_state { .state = VMA_MERGE_START, \ } -/* - * If, at any point, the VMA had unCoW'd mappings from parents, it will maintain - * more than one anon_vma_chain connecting it to more than one anon_vma. A merge - * would mean a wider range of folios sharing the root anon_vma lock, and thus - * potential lock contention, we do not wish to encourage merging such that this - * scales to a problem. - */ -static bool vma_had_uncowed_parents(struct vm_area_struct *vma) +/* Was this VMA ever forked from a parent, i.e. maybe contains CoW mappings? */ +static bool vma_is_fork_child(struct vm_area_struct *vma) { /* * The list_is_singular() test is to avoid merging VMA cloned from - * parents. This can improve scalability caused by anon_vma lock. + * parents. This can improve scalability caused by the anon_vma root + * lock. */ return vma && vma->anon_vma && !list_is_singular(&vma->anon_vma_chain); } @@ -109,7 +104,7 @@ static inline bool is_mergeable_vma(struct vma_merge_struct *vmg, bool merge_nex static bool is_mergeable_anon_vma(struct vma_merge_struct *vmg, bool merge_next) { struct vm_area_struct *tgt = merge_next ? vmg->next : vmg->prev; - struct vm_area_struct *src = vmg->middle; /* exisitng merge case. */ + struct vm_area_struct *src = vmg->middle; /* existing merge case. */ struct anon_vma *tgt_anon = tgt->anon_vma; struct anon_vma *src_anon = vmg->anon_vma; @@ -121,11 +116,19 @@ static bool is_mergeable_anon_vma(struct vma_merge_struct *vmg, bool merge_next) VM_WARN_ON(src && src_anon != src->anon_vma); /* Case 1 - we will dup_anon_vma() from src into tgt. */ - if (!tgt_anon && src_anon) - return !vma_had_uncowed_parents(src); + if (!tgt_anon && src_anon) { + struct vm_area_struct *copied_from = vmg->copied_from; + + if (vma_is_fork_child(src)) + return false; + if (vma_is_fork_child(copied_from)) + return false; + + return true; + } /* Case 2 - we will simply use tgt's anon_vma. */ if (tgt_anon && !src_anon) - return !vma_had_uncowed_parents(tgt); + return !vma_is_fork_child(tgt); /* Case 3 - the anon_vma's are already shared. */ return src_anon == tgt_anon; } @@ -798,7 +801,7 @@ static bool can_merge_remove_vma(struct vm_area_struct *vma) * Returns: The merged VMA if merge succeeds, or NULL otherwise. * * ASSUMPTIONS: - * - The caller must assign the VMA to be modifed to @vmg->middle. + * - The caller must assign the VMA to be modified to @vmg->middle. * - The caller must have set @vmg->prev to the previous VMA, if there is one. * - The caller must not set @vmg->next, as we determine this. * - The caller must hold a WRITE lock on the mm_struct->mmap_lock. @@ -835,6 +838,8 @@ static __must_check struct vm_area_struct *vma_merge_existing_range( VM_WARN_ON_VMG(middle && !(vma_iter_addr(vmg->vmi) >= middle->vm_start && vma_iter_addr(vmg->vmi) < middle->vm_end), vmg); + /* An existing merge can never be used by the mremap() logic. */ + VM_WARN_ON_VMG(vmg->copied_from, vmg); vmg->state = VMA_MERGE_NOMERGE; @@ -1101,6 +1106,33 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) return NULL; } +/* + * vma_merge_copied_range - Attempt to merge a VMA that is being copied by + * mremap() + * + * @vmg: Describes the VMA we are adding, in the copied-to range @vmg->start to + * @vmg->end (exclusive), which we try to merge with any adjacent VMAs if + * possible. + * + * vmg->prev, next, start, end, pgoff should all be relative to the COPIED TO + * range, i.e. the target range for the VMA. + * + * Returns: In instances where no merge was possible, NULL. Otherwise, a pointer + * to the VMA we expanded. + * + * ASSUMPTIONS: Same as vma_merge_new_range(), except vmg->middle must contain + * the copied-from VMA. + */ +static struct vm_area_struct *vma_merge_copied_range(struct vma_merge_struct *vmg) +{ + /* We must have a copied-from VMA. */ + VM_WARN_ON_VMG(!vmg->middle, vmg); + + vmg->copied_from = vmg->middle; + vmg->middle = NULL; + return vma_merge_new_range(vmg); +} + /* * vma_expand - Expand an existing VMA * @@ -1123,38 +1155,45 @@ int vma_expand(struct vma_merge_struct *vmg) bool remove_next = false; struct vm_area_struct *target = vmg->target; struct vm_area_struct *next = vmg->next; + int ret = 0; VM_WARN_ON_VMG(!target, vmg); mmap_assert_write_locked(vmg->mm); - vma_start_write(target); - if (next && (target != next) && (vmg->end == next->vm_end)) { - int ret; + if (next && target != next && vmg->end == next->vm_end) remove_next = true; - /* This should already have been checked by this point. */ - VM_WARN_ON_VMG(!can_merge_remove_vma(next), vmg); - vma_start_write(next); - /* - * In this case we don't report OOM, so vmg->give_up_on_mm is - * safe. - */ - ret = dup_anon_vma(target, next, &anon_dup); - if (ret) - return ret; - } + /* We must have a target. */ + VM_WARN_ON_VMG(!target, vmg); + /* This should have already been checked by this point. */ + VM_WARN_ON_VMG(remove_next && !can_merge_remove_vma(next), vmg); /* Not merging but overwriting any part of next is not handled. */ VM_WARN_ON_VMG(next && !remove_next && next != target && vmg->end > next->vm_start, vmg); - /* Only handles expanding */ + /* Only handles expanding. */ VM_WARN_ON_VMG(target->vm_start < vmg->start || target->vm_end > vmg->end, vmg); + /* + * If we are removing the next VMA or copying from a VMA + * (e.g. mremap()'ing), we must propagate anon_vma state. + * + * Note that, by convention, callers ignore OOM for this case, so + * we don't need to account for vmg->give_up_on_mm here. + */ if (remove_next) - vmg->__remove_next = true; + ret = dup_anon_vma(target, next, &anon_dup); + if (!ret && vmg->copied_from) + ret = dup_anon_vma(target, vmg->copied_from, &anon_dup); + if (ret) + return ret; + if (remove_next) { + vma_start_write(next); + vmg->__remove_next = true; + } if (commit_merge(vmg)) goto nomem; @@ -1837,10 +1876,9 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ - vmg.middle = NULL; /* New VMA range. */ vmg.pgoff = pgoff; vmg.next = vma_iter_next_rewind(&vmi, NULL); - new_vma = vma_merge_new_range(&vmg); + new_vma = vma_merge_copied_range(&vmg); if (new_vma) { /* diff --git a/mm/vma.h b/mm/vma.h index 9183fe54900907..d73e1b324bfd1a 100644 --- a/mm/vma.h +++ b/mm/vma.h @@ -106,6 +106,9 @@ struct vma_merge_struct { struct anon_vma_name *anon_name; enum vma_merge_state state; + /* If copied from (i.e. mremap()'d) the VMA from which we are copying. */ + struct vm_area_struct *copied_from; + /* Flags which callers can use to modify merge behaviour: */ /* diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 798b2ed21e4605..4fbd6e7dc479af 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -4167,7 +4167,7 @@ void *vrealloc_node_align_noprof(const void *p, size_t size, unsigned long align if (want_init_on_free() || want_init_on_alloc(flags)) memset((void *)p + size, 0, old_size - size); vm->requested_size = size; - kasan_poison_vmalloc(p + size, old_size - size); + kasan_vrealloc(p, old_size, size); return (void *)p; } @@ -4175,14 +4175,13 @@ void *vrealloc_node_align_noprof(const void *p, size_t size, unsigned long align * We already have the bytes available in the allocation; use them. */ if (size <= alloced_size) { - kasan_unpoison_vmalloc(p + old_size, size - old_size, - KASAN_VMALLOC_PROT_NORMAL); /* * No need to zero memory here, as unused memory will have * already been zeroed at initial allocation time or during * realloc shrink time. */ vm->requested_size = size; + kasan_vrealloc(p, old_size, size); return (void *)p; } @@ -4870,9 +4869,7 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ - for (area = 0; area < nr_vms; area++) - vms[area]->addr = kasan_unpoison_vmalloc(vms[area]->addr, - vms[area]->size, KASAN_VMALLOC_PROT_NORMAL); + kasan_unpoison_vmap_areas(vms, nr_vms, KASAN_VMALLOC_PROT_NORMAL); kfree(vas); return vms; diff --git a/mm/vmscan.c b/mm/vmscan.c index b2fc8b626d3dff..06071995dacc90 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -7740,6 +7740,17 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) return ret; } +#else + +static unsigned long __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, + unsigned long nr_pages, + struct scan_control *sc) +{ + return 0; +} + +#endif + enum { MEMORY_RECLAIM_SWAPPINESS = 0, MEMORY_RECLAIM_SWAPPINESS_MAX, @@ -7847,8 +7858,6 @@ int user_proactive_reclaim(char *buf, return 0; } -#endif - /** * check_move_unevictable_folios - Move evictable folios to appropriate zone * lru list diff --git a/mm/vmstat.c b/mm/vmstat.c index bb09c032eecfa2..98855f31294dd2 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -771,25 +771,25 @@ EXPORT_SYMBOL(dec_node_page_state); /* * Fold a differential into the global counters. - * Returns the number of counters updated. + * Returns whether counters were updated. */ static int fold_diff(int *zone_diff, int *node_diff) { int i; - int changes = 0; + bool changed = false; for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) if (zone_diff[i]) { atomic_long_add(zone_diff[i], &vm_zone_stat[i]); - changes++; + changed = true; } for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) if (node_diff[i]) { atomic_long_add(node_diff[i], &vm_node_stat[i]); - changes++; + changed = true; } - return changes; + return changed; } /* @@ -806,16 +806,16 @@ static int fold_diff(int *zone_diff, int *node_diff) * with the global counters. These could cause remote node cache line * bouncing and will have to be only done when necessary. * - * The function returns the number of global counters updated. + * The function returns whether global counters were updated. */ -static int refresh_cpu_vm_stats(bool do_pagesets) +static bool refresh_cpu_vm_stats(bool do_pagesets) { struct pglist_data *pgdat; struct zone *zone; int i; int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, }; - int changes = 0; + bool changed = false; for_each_populated_zone(zone) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; @@ -839,7 +839,8 @@ static int refresh_cpu_vm_stats(bool do_pagesets) if (do_pagesets) { cond_resched(); - changes += decay_pcp_high(zone, this_cpu_ptr(pcp)); + if (decay_pcp_high(zone, this_cpu_ptr(pcp))) + changed = true; #ifdef CONFIG_NUMA /* * Deal with draining the remote pageset of this @@ -861,13 +862,13 @@ static int refresh_cpu_vm_stats(bool do_pagesets) } if (__this_cpu_dec_return(pcp->expire)) { - changes++; + changed = true; continue; } if (__this_cpu_read(pcp->count)) { drain_zone_pages(zone, this_cpu_ptr(pcp)); - changes++; + changed = true; } #endif } @@ -887,8 +888,9 @@ static int refresh_cpu_vm_stats(bool do_pagesets) } } - changes += fold_diff(global_zone_diff, global_node_diff); - return changes; + if (fold_diff(global_zone_diff, global_node_diff)) + changed = true; + return changed; } /* diff --git a/mm/zswap.c b/mm/zswap.c index c1af782e54ec60..12fb0e3954129c 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -787,7 +787,7 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) return 0; fail: - if (acomp) + if (!IS_ERR_OR_NULL(acomp)) crypto_free_acomp(acomp); kfree(buffer); return ret; diff --git a/net/atm/signaling.c b/net/atm/signaling.c index e70ae2c113f954..358fbe5e4d1d06 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -22,6 +22,36 @@ struct atm_vcc *sigd = NULL; +/* + * find_get_vcc - validate and get a reference to a vcc pointer + * @vcc: the vcc pointer to validate + * + * This function validates that @vcc points to a registered VCC in vcc_hash. + * If found, it increments the socket reference count and returns the vcc. + * The caller must call sock_put(sk_atm(vcc)) when done. + * + * Returns the vcc pointer if valid, NULL otherwise. + */ +static struct atm_vcc *find_get_vcc(struct atm_vcc *vcc) +{ + int i; + + read_lock(&vcc_sklist_lock); + for (i = 0; i < VCC_HTABLE_SIZE; i++) { + struct sock *s; + + sk_for_each(s, &vcc_hash[i]) { + if (atm_sk(s) == vcc) { + sock_hold(s); + read_unlock(&vcc_sklist_lock); + return vcc; + } + } + } + read_unlock(&vcc_sklist_lock); + return NULL; +} + static void sigd_put_skb(struct sk_buff *skb) { if (!sigd) { @@ -69,7 +99,14 @@ static int sigd_send(struct atm_vcc *vcc, struct sk_buff *skb) msg = (struct atmsvc_msg *) skb->data; WARN_ON(refcount_sub_and_test(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc)); - vcc = *(struct atm_vcc **) &msg->vcc; + + vcc = find_get_vcc(*(struct atm_vcc **)&msg->vcc); + if (!vcc) { + pr_debug("invalid vcc pointer in msg\n"); + dev_kfree_skb(skb); + return -EINVAL; + } + pr_debug("%d (0x%lx)\n", (int)msg->type, (unsigned long)vcc); sk = sk_atm(vcc); @@ -100,7 +137,16 @@ static int sigd_send(struct atm_vcc *vcc, struct sk_buff *skb) clear_bit(ATM_VF_WAITING, &vcc->flags); break; case as_indicate: - vcc = *(struct atm_vcc **)&msg->listen_vcc; + /* Release the reference from msg->vcc, we'll use msg->listen_vcc instead */ + sock_put(sk); + + vcc = find_get_vcc(*(struct atm_vcc **)&msg->listen_vcc); + if (!vcc) { + pr_debug("invalid listen_vcc pointer in msg\n"); + dev_kfree_skb(skb); + return -EINVAL; + } + sk = sk_atm(vcc); pr_debug("as_indicate!!!\n"); lock_sock(sk); @@ -115,6 +161,8 @@ static int sigd_send(struct atm_vcc *vcc, struct sk_buff *skb) sk->sk_state_change(sk); as_indicate_complete: release_sock(sk); + /* Paired with find_get_vcc(msg->listen_vcc) above */ + sock_put(sk); return 0; case as_close: set_bit(ATM_VF_RELEASED, &vcc->flags); @@ -131,11 +179,15 @@ static int sigd_send(struct atm_vcc *vcc, struct sk_buff *skb) break; default: pr_alert("bad message type %d\n", (int)msg->type); + /* Paired with find_get_vcc(msg->vcc) above */ + sock_put(sk); return -EINVAL; } sk->sk_state_change(sk); out: dev_kfree_skb(skb); + /* Paired with find_get_vcc(msg->vcc) above */ + sock_put(sk); return 0; } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 6e76798ec786b1..f5896c023a9fac 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4402,6 +4402,7 @@ static int hci_le_set_event_mask_sync(struct hci_dev *hdev) if (bis_capable(hdev)) { events[1] |= 0x20; /* LE PA Report */ events[1] |= 0x40; /* LE PA Sync Established */ + events[1] |= 0x80; /* LE PA Sync Lost */ events[3] |= 0x04; /* LE Create BIG Complete */ events[3] |= 0x08; /* LE Terminate BIG Complete */ events[3] |= 0x10; /* LE BIG Sync Established */ diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 262bf984d2aafa..ee2dd26b1b82b1 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -849,6 +849,12 @@ static u32 get_supported_settings(struct hci_dev *hdev) if (cis_peripheral_capable(hdev)) settings |= MGMT_SETTING_CIS_PERIPHERAL; + if (bis_capable(hdev)) + settings |= MGMT_SETTING_ISO_BROADCASTER; + + if (sync_recv_capable(hdev)) + settings |= MGMT_SETTING_ISO_SYNC_RECEIVER; + if (ll_privacy_capable(hdev)) settings |= MGMT_SETTING_LL_PRIVACY; @@ -1948,6 +1954,7 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) } mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err); + mgmt_pending_free(cmd); return; } @@ -1966,6 +1973,7 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) sock_put(match.sk); hci_update_eir_sync(hdev); + mgmt_pending_free(cmd); } static int set_ssp_sync(struct hci_dev *hdev, void *data) @@ -6350,6 +6358,7 @@ static void set_advertising_complete(struct hci_dev *hdev, void *data, int err) hci_dev_clear_flag(hdev, HCI_ADVERTISING); settings_rsp(cmd, &match); + mgmt_pending_free(cmd); new_settings(hdev, match.sk); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 8b7d0b90fea76b..6b04f47301c1ef 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -939,6 +939,11 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) if (__skb->gso_segs > GSO_MAX_SEGS) return -EINVAL; + + /* Currently GSO type is zero/unset. If this gets extended with + * a small list of accepted GSO types in future, the filter for + * an unset GSO type in bpf_clone_redirect() can be lifted. + */ skb_shinfo(skb)->gso_segs = __skb->gso_segs; skb_shinfo(skb)->gso_size = __skb->gso_size; skb_shinfo(skb)->hwtstamps.hwtstamp = __skb->hwtstamp; @@ -1226,8 +1231,6 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, batch_size = NAPI_POLL_WEIGHT; else if (batch_size > TEST_XDP_MAX_BATCH) return -E2BIG; - - headroom += sizeof(struct xdp_page_head); } else if (batch_size) { return -EINVAL; } @@ -1240,16 +1243,26 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, /* There can't be user provided data before the meta data */ if (ctx->data_meta || ctx->data_end > kattr->test.data_size_in || ctx->data > ctx->data_end || - unlikely(xdp_metalen_invalid(ctx->data)) || (do_live && (kattr->test.data_out || kattr->test.ctx_out))) goto free_ctx; - /* Meta data is allocated from the headroom */ - headroom -= ctx->data; meta_sz = ctx->data; + if (xdp_metalen_invalid(meta_sz) || meta_sz > headroom - sizeof(struct xdp_frame)) + goto free_ctx; + + /* Meta data is allocated from the headroom */ + headroom -= meta_sz; linear_sz = ctx->data_end; } + /* The xdp_page_head structure takes up space in each page, limiting the + * size of the packet data; add the extra size to headroom here to make + * sure it's accounted in the length checks below, but not in the + * metadata size check above. + */ + if (do_live) + headroom += sizeof(struct xdp_page_head); + max_linear_sz = PAGE_SIZE - headroom - tailroom; linear_sz = min_t(u32, linear_sz, max_linear_sz); @@ -1287,13 +1300,13 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, if (sinfo->nr_frags == MAX_SKB_FRAGS) { ret = -ENOMEM; - goto out; + goto out_put_dev; } page = alloc_page(GFP_KERNEL); if (!page) { ret = -ENOMEM; - goto out; + goto out_put_dev; } frag = &sinfo->frags[sinfo->nr_frags++]; @@ -1305,7 +1318,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, if (copy_from_user(page_address(page), data_in + size, data_len)) { ret = -EFAULT; - goto out; + goto out_put_dev; } sinfo->xdp_frags_size += data_len; size += data_len; @@ -1320,6 +1333,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, ret = bpf_test_run_xdp_live(prog, &xdp, repeat, batch_size, &duration); else ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true); +out_put_dev: /* We convert the xdp_buff back to an xdp_md before checking the return * code so the reference count of any held netdevice will be decremented * even if the test run failed. diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 58d22e2b85fc35..0501ffcb8a3ddb 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -70,7 +70,7 @@ static inline int has_expired(const struct net_bridge *br, { return !test_bit(BR_FDB_STATIC, &fdb->flags) && !test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags) && - time_before_eq(fdb->updated + hold_time(br), jiffies); + time_before_eq(READ_ONCE(fdb->updated) + hold_time(br), jiffies); } static int fdb_to_nud(const struct net_bridge *br, @@ -126,9 +126,9 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, if (nla_put_u32(skb, NDA_FLAGS_EXT, ext_flags)) goto nla_put_failure; - ci.ndm_used = jiffies_to_clock_t(now - fdb->used); + ci.ndm_used = jiffies_to_clock_t(now - READ_ONCE(fdb->used)); ci.ndm_confirmed = 0; - ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); + ci.ndm_updated = jiffies_to_clock_t(now - READ_ONCE(fdb->updated)); ci.ndm_refcnt = 0; if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; @@ -551,7 +551,7 @@ void br_fdb_cleanup(struct work_struct *work) */ rcu_read_lock(); hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) { - unsigned long this_timer = f->updated + delay; + unsigned long this_timer = READ_ONCE(f->updated) + delay; if (test_bit(BR_FDB_STATIC, &f->flags) || test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &f->flags)) { @@ -924,6 +924,7 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, { struct net_bridge_fdb_entry *f; struct __fdb_entry *fe = buf; + unsigned long delta; int num = 0; memset(buf, 0, maxnum*sizeof(struct __fdb_entry)); @@ -953,8 +954,11 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, fe->port_hi = f->dst->port_no >> 8; fe->is_local = test_bit(BR_FDB_LOCAL, &f->flags); - if (!test_bit(BR_FDB_STATIC, &f->flags)) - fe->ageing_timer_value = jiffies_delta_to_clock_t(jiffies - f->updated); + if (!test_bit(BR_FDB_STATIC, &f->flags)) { + delta = jiffies - READ_ONCE(f->updated); + fe->ageing_timer_value = + jiffies_delta_to_clock_t(delta); + } ++fe; ++num; } @@ -1002,8 +1006,8 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, unsigned long now = jiffies; bool fdb_modified = false; - if (now != fdb->updated) { - fdb->updated = now; + if (now != READ_ONCE(fdb->updated)) { + WRITE_ONCE(fdb->updated, now); fdb_modified = __fdb_mark_active(fdb); } @@ -1242,10 +1246,10 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, if (fdb_handle_notify(fdb, notify)) modified = true; - fdb->used = jiffies; + WRITE_ONCE(fdb->used, jiffies); if (modified) { if (refresh) - fdb->updated = jiffies; + WRITE_ONCE(fdb->updated, jiffies); fdb_notify(br, fdb, RTM_NEWNEIGH, true); } @@ -1556,7 +1560,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, goto err_unlock; } - fdb->updated = jiffies; + WRITE_ONCE(fdb->updated, jiffies); if (READ_ONCE(fdb->dst) != p) { WRITE_ONCE(fdb->dst, p); @@ -1565,7 +1569,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (test_and_set_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) { /* Refresh entry */ - fdb->used = jiffies; + WRITE_ONCE(fdb->used, jiffies); } else { modified = true; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 777fa869c1a144..1405f1061a5493 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -221,8 +221,8 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (test_bit(BR_FDB_LOCAL, &dst->flags)) return br_pass_frame_up(skb, false); - if (now != dst->used) - dst->used = now; + if (now != READ_ONCE(dst->used)) + WRITE_ONCE(dst->used, now); br_forward(dst->dst, skb, local_rcv, false); } else { if (!mcast_hit) @@ -274,7 +274,7 @@ static int nf_hook_bridge_pre(struct sk_buff *skb, struct sk_buff **pskb) int ret; net = dev_net(skb->dev); -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL if (!static_key_false(&nf_hooks_needed[NFPROTO_BRIDGE][NF_BR_PRE_ROUTING])) goto frame_finish; #endif diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 22d12e54596685..5855eb0502085f 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -244,14 +244,11 @@ br_multicast_port_vid_to_port_ctx(struct net_bridge_port *port, u16 vid) lockdep_assert_held_once(&port->br->multicast_lock); - if (!br_opt_get(port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) - return NULL; - /* Take RCU to access the vlan. */ rcu_read_lock(); vlan = br_vlan_find(nbp_vlan_group_rcu(port), vid); - if (vlan && !br_multicast_port_ctx_vlan_disabled(&vlan->port_mcast_ctx)) + if (vlan) pmctx = &vlan->port_mcast_ctx; rcu_read_unlock(); @@ -701,7 +698,10 @@ br_multicast_port_ngroups_inc_one(struct net_bridge_mcast_port *pmctx, u32 max = READ_ONCE(pmctx->mdb_max_entries); u32 n = READ_ONCE(pmctx->mdb_n_entries); - if (max && n >= max) { + /* enforce the max limit when it's a port pmctx or a port-vlan pmctx + * with snooping enabled + */ + if (!br_multicast_port_ctx_vlan_disabled(pmctx) && max && n >= max) { NL_SET_ERR_MSG_FMT_MOD(extack, "%s is already in %u groups, and mcast_max_groups=%u", what, n, max); return -E2BIG; @@ -736,9 +736,7 @@ static int br_multicast_port_ngroups_inc(struct net_bridge_port *port, return err; } - /* Only count on the VLAN context if VID is given, and if snooping on - * that VLAN is enabled. - */ + /* Only count on the VLAN context if VID is given */ if (!group->vid) return 0; @@ -2011,6 +2009,18 @@ void br_multicast_port_ctx_init(struct net_bridge_port *port, timer_setup(&pmctx->ip6_own_query.timer, br_ip6_multicast_port_query_expired, 0); #endif + /* initialize mdb_n_entries if a new port vlan is being created */ + if (vlan) { + struct net_bridge_port_group *pg; + u32 n = 0; + + spin_lock_bh(&port->br->multicast_lock); + hlist_for_each_entry(pg, &port->mglist, mglist) + if (pg->key.addr.vid == vlan->vid) + n++; + WRITE_ONCE(pmctx->mdb_n_entries, n); + spin_unlock_bh(&port->br->multicast_lock); + } } void br_multicast_port_ctx_deinit(struct net_bridge_mcast_port *pmctx) @@ -2094,25 +2104,6 @@ static void __br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx) br_ip4_multicast_add_router(brmctx, pmctx); br_ip6_multicast_add_router(brmctx, pmctx); } - - if (br_multicast_port_ctx_is_vlan(pmctx)) { - struct net_bridge_port_group *pg; - u32 n = 0; - - /* The mcast_n_groups counter might be wrong. First, - * BR_VLFLAG_MCAST_ENABLED is toggled before temporary entries - * are flushed, thus mcast_n_groups after the toggle does not - * reflect the true values. And second, permanent entries added - * while BR_VLFLAG_MCAST_ENABLED was disabled, are not reflected - * either. Thus we have to refresh the counter. - */ - - hlist_for_each_entry(pg, &pmctx->port->mglist, mglist) { - if (pg->key.addr.vid == pmctx->vlan->vid) - n++; - } - WRITE_ONCE(pmctx->mdb_n_entries, n); - } } static void br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 7280c4e9305f36..b9b2981c484149 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -247,6 +247,7 @@ struct net_bridge_vlan { * struct net_bridge_vlan_group * * @vlan_hash: VLAN entry rhashtable + * @tunnel_hash: Hash table to map from tunnel key ID (e.g. VXLAN VNI) to VLAN * @vlan_list: sorted VLAN entry list * @num_vlans: number of total VLAN entries * @pvid: PVID VLAN id diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index a966a6ec826343..257cae9f156983 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -189,7 +189,6 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tunnel_dst; __be64 tunnel_id; - int err; if (!vlan) return 0; @@ -199,9 +198,13 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, return 0; skb_dst_drop(skb); - err = skb_vlan_pop(skb); - if (err) - return err; + /* For 802.1ad (QinQ), skb_vlan_pop() incorrectly moves the C-VLAN + * from payload to hwaccel after clearing S-VLAN. We only need to + * clear the hwaccel S-VLAN; the C-VLAN must stay in payload for + * correct VXLAN encapsulation. This is also correct for 802.1Q + * where no C-VLAN exists in payload. + */ + __vlan_hwaccel_clear_tag(skb); if (BR_INPUT_SKB_CB(skb)->backup_nhid) { __set_bit(IP_TUNNEL_KEY_BIT, flags); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 5697e3949a3652..a04fc175752897 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1299,7 +1299,7 @@ int ebt_register_template(const struct ebt_table *t, int (*table_init)(struct ne list_for_each_entry(tmpl, &template_tables, list) { if (WARN_ON_ONCE(strcmp(t->name, tmpl->name) == 0)) { mutex_unlock(&ebt_mutex); - return -EEXIST; + return -EBUSY; } } diff --git a/net/caif/cffrml.c b/net/caif/cffrml.c index 6651a8dc62e04d..d4d63586053ad4 100644 --- a/net/caif/cffrml.c +++ b/net/caif/cffrml.c @@ -92,8 +92,15 @@ static int cffrml_receive(struct cflayer *layr, struct cfpkt *pkt) len = le16_to_cpu(tmp); /* Subtract for FCS on length if FCS is not used. */ - if (!this->dofcs) + if (!this->dofcs) { + if (len < 2) { + ++cffrml_rcv_error; + pr_err("Invalid frame length (%d)\n", len); + cfpkt_destroy(pkt); + return -EPROTO; + } len -= 2; + } if (cfpkt_setlen(pkt, len) < 0) { ++cffrml_rcv_error; diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 88e7160d424896..e3ba2e9fc0e9b7 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -482,6 +482,12 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out_release_sock; } + if (ndev->reg_state != NETREG_REGISTERED) { + dev_put(ndev); + ret = -ENODEV; + goto out_release_sock; + } + can_ml = can_get_ml_priv(ndev); if (!can_ml) { dev_put(ndev); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index fbf5c8001c9df3..8656ab388c83e6 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1567,6 +1567,8 @@ int j1939_session_activate(struct j1939_session *session) if (active) { j1939_session_put(active); ret = -EAGAIN; + } else if (priv->ndev->reg_state != NETREG_REGISTERED) { + ret = -ENODEV; } else { WARN_ON_ONCE(session->state != J1939_SESSION_NEW); list_add_tail(&session->active_session_list_entry, @@ -1693,8 +1695,16 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session, j1939_session_timers_cancel(session); j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); - if (session->transmission) + if (session->transmission) { j1939_session_deactivate_activate_next(session); + } else if (session->state == J1939_SESSION_WAITING_ABORT) { + /* Force deactivation for the receiver. + * If we rely on the timer starting in j1939_session_cancel, + * a second RTS call here will cancel that timer and fail + * to restart it because the state is already WAITING_ABORT. + */ + j1939_session_deactivate_activate_next(session); + } return -EBUSY; } diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index 9e48623018a365..061eaa047f7651 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -2377,7 +2377,9 @@ static int process_auth_done(struct ceph_connection *con, void *p, void *end) ceph_decode_64_safe(&p, end, global_id, bad); ceph_decode_32_safe(&p, end, con->v2.con_mode, bad); + ceph_decode_32_safe(&p, end, payload_len, bad); + ceph_decode_need(&p, end, payload_len, bad); dout("%s con %p global_id %llu con_mode %d payload_len %d\n", __func__, con, global_id, con->v2.con_mode, payload_len); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index c227ececa9254c..fa8dd2a20f7d28 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1417,7 +1417,7 @@ static int mon_handle_auth_done(struct ceph_connection *con, if (!ret) finish_hunting(monc); mutex_unlock(&monc->mutex); - return 0; + return ret; } static int mon_handle_auth_bad_method(struct ceph_connection *con, diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 6664ea73ccf81b..6d7d8c7d7d3fed 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1588,6 +1588,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, struct ceph_pg_pool_info *pi; struct ceph_pg pgid, last_pgid; struct ceph_osds up, acting; + bool should_be_paused; bool is_read = t->flags & CEPH_OSD_FLAG_READ; bool is_write = t->flags & CEPH_OSD_FLAG_WRITE; bool force_resend = false; @@ -1656,10 +1657,16 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, &last_pgid)) force_resend = true; - if (t->paused && !target_should_be_paused(osdc, t, pi)) { - t->paused = false; + should_be_paused = target_should_be_paused(osdc, t, pi); + if (t->paused && !should_be_paused) { unpaused = true; } + if (t->paused != should_be_paused) { + dout("%s t %p paused %d -> %d\n", __func__, t, t->paused, + should_be_paused); + t->paused = should_be_paused; + } + legacy_change = ceph_pg_compare(&t->pgid, &pgid) || ceph_osds_changed(&t->acting, &acting, t->used_replica || any_change); @@ -4283,6 +4290,9 @@ static void osd_fault(struct ceph_connection *con) goto out_unlock; } + osd->o_sparse_op_idx = -1; + ceph_init_sparse_read(&osd->o_sparse_read); + if (!reopen_osd(osd)) kick_osd_requests(osd); maybe_request_map(osdc); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index d245fa508e1cc9..7c76eb9d6ceec5 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -241,22 +241,26 @@ static struct crush_choose_arg_map *alloc_choose_arg_map(void) static void free_choose_arg_map(struct crush_choose_arg_map *arg_map) { - if (arg_map) { - int i, j; + int i, j; - WARN_ON(!RB_EMPTY_NODE(&arg_map->node)); + if (!arg_map) + return; + WARN_ON(!RB_EMPTY_NODE(&arg_map->node)); + + if (arg_map->args) { for (i = 0; i < arg_map->size; i++) { struct crush_choose_arg *arg = &arg_map->args[i]; - - for (j = 0; j < arg->weight_set_size; j++) - kfree(arg->weight_set[j].weights); - kfree(arg->weight_set); + if (arg->weight_set) { + for (j = 0; j < arg->weight_set_size; j++) + kfree(arg->weight_set[j].weights); + kfree(arg->weight_set); + } kfree(arg->ids); } kfree(arg_map->args); - kfree(arg_map); } + kfree(arg_map); } DEFINE_RB_FUNCS(choose_arg_map, struct crush_choose_arg_map, choose_args_index, @@ -806,51 +810,49 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) ceph_decode_need(p, end, len, bad); pool_end = *p + len; + ceph_decode_need(p, end, 4 + 4 + 4, bad); pi->type = ceph_decode_8(p); pi->size = ceph_decode_8(p); pi->crush_ruleset = ceph_decode_8(p); pi->object_hash = ceph_decode_8(p); - pi->pg_num = ceph_decode_32(p); pi->pgp_num = ceph_decode_32(p); - *p += 4 + 4; /* skip lpg* */ - *p += 4; /* skip last_change */ - *p += 8 + 4; /* skip snap_seq, snap_epoch */ + /* lpg*, last_change, snap_seq, snap_epoch */ + ceph_decode_skip_n(p, end, 8 + 4 + 8 + 4, bad); /* skip snaps */ - num = ceph_decode_32(p); + ceph_decode_32_safe(p, end, num, bad); while (num--) { - *p += 8; /* snapid key */ - *p += 1 + 1; /* versions */ - len = ceph_decode_32(p); - *p += len; + /* snapid key, pool snap (with versions) */ + ceph_decode_skip_n(p, end, 8 + 2, bad); + ceph_decode_skip_string(p, end, bad); } - /* skip removed_snaps */ - num = ceph_decode_32(p); - *p += num * (8 + 8); + /* removed_snaps */ + ceph_decode_skip_map(p, end, 64, 64, bad); + ceph_decode_need(p, end, 8 + 8 + 4, bad); *p += 8; /* skip auid */ pi->flags = ceph_decode_64(p); *p += 4; /* skip crash_replay_interval */ if (ev >= 7) - pi->min_size = ceph_decode_8(p); + ceph_decode_8_safe(p, end, pi->min_size, bad); else pi->min_size = pi->size - pi->size / 2; if (ev >= 8) - *p += 8 + 8; /* skip quota_max_* */ + /* quota_max_* */ + ceph_decode_skip_n(p, end, 8 + 8, bad); if (ev >= 9) { - /* skip tiers */ - num = ceph_decode_32(p); - *p += num * 8; + /* tiers */ + ceph_decode_skip_set(p, end, 64, bad); + ceph_decode_need(p, end, 8 + 1 + 8 + 8, bad); *p += 8; /* skip tier_of */ *p += 1; /* skip cache_mode */ - pi->read_tier = ceph_decode_64(p); pi->write_tier = ceph_decode_64(p); } else { @@ -858,86 +860,76 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) pi->write_tier = -1; } - if (ev >= 10) { - /* skip properties */ - num = ceph_decode_32(p); - while (num--) { - len = ceph_decode_32(p); - *p += len; /* key */ - len = ceph_decode_32(p); - *p += len; /* val */ - } - } + if (ev >= 10) + /* properties */ + ceph_decode_skip_map(p, end, string, string, bad); if (ev >= 11) { - /* skip hit_set_params */ - *p += 1 + 1; /* versions */ - len = ceph_decode_32(p); - *p += len; + /* hit_set_params (with versions) */ + ceph_decode_skip_n(p, end, 2, bad); + ceph_decode_skip_string(p, end, bad); - *p += 4; /* skip hit_set_period */ - *p += 4; /* skip hit_set_count */ + /* hit_set_period, hit_set_count */ + ceph_decode_skip_n(p, end, 4 + 4, bad); } if (ev >= 12) - *p += 4; /* skip stripe_width */ + /* stripe_width */ + ceph_decode_skip_32(p, end, bad); - if (ev >= 13) { - *p += 8; /* skip target_max_bytes */ - *p += 8; /* skip target_max_objects */ - *p += 4; /* skip cache_target_dirty_ratio_micro */ - *p += 4; /* skip cache_target_full_ratio_micro */ - *p += 4; /* skip cache_min_flush_age */ - *p += 4; /* skip cache_min_evict_age */ - } + if (ev >= 13) + /* target_max_*, cache_target_*, cache_min_* */ + ceph_decode_skip_n(p, end, 16 + 8 + 8, bad); - if (ev >= 14) { - /* skip erasure_code_profile */ - len = ceph_decode_32(p); - *p += len; - } + if (ev >= 14) + /* erasure_code_profile */ + ceph_decode_skip_string(p, end, bad); /* * last_force_op_resend_preluminous, will be overridden if the * map was encoded with RESEND_ON_SPLIT */ if (ev >= 15) - pi->last_force_request_resend = ceph_decode_32(p); + ceph_decode_32_safe(p, end, pi->last_force_request_resend, bad); else pi->last_force_request_resend = 0; if (ev >= 16) - *p += 4; /* skip min_read_recency_for_promote */ + /* min_read_recency_for_promote */ + ceph_decode_skip_32(p, end, bad); if (ev >= 17) - *p += 8; /* skip expected_num_objects */ + /* expected_num_objects */ + ceph_decode_skip_64(p, end, bad); if (ev >= 19) - *p += 4; /* skip cache_target_dirty_high_ratio_micro */ + /* cache_target_dirty_high_ratio_micro */ + ceph_decode_skip_32(p, end, bad); if (ev >= 20) - *p += 4; /* skip min_write_recency_for_promote */ + /* min_write_recency_for_promote */ + ceph_decode_skip_32(p, end, bad); if (ev >= 21) - *p += 1; /* skip use_gmt_hitset */ + /* use_gmt_hitset */ + ceph_decode_skip_8(p, end, bad); if (ev >= 22) - *p += 1; /* skip fast_read */ + /* fast_read */ + ceph_decode_skip_8(p, end, bad); - if (ev >= 23) { - *p += 4; /* skip hit_set_grade_decay_rate */ - *p += 4; /* skip hit_set_search_last_n */ - } + if (ev >= 23) + /* hit_set_grade_decay_rate, hit_set_search_last_n */ + ceph_decode_skip_n(p, end, 4 + 4, bad); if (ev >= 24) { - /* skip opts */ - *p += 1 + 1; /* versions */ - len = ceph_decode_32(p); - *p += len; + /* opts (with versions) */ + ceph_decode_skip_n(p, end, 2, bad); + ceph_decode_skip_string(p, end, bad); } if (ev >= 25) - pi->last_force_request_resend = ceph_decode_32(p); + ceph_decode_32_safe(p, end, pi->last_force_request_resend, bad); /* ignore the rest */ @@ -1991,11 +1983,13 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, bool msgr2, sizeof(u64) + sizeof(u32), e_inval); ceph_decode_copy(p, &fsid, sizeof(fsid)); epoch = ceph_decode_32(p); - BUG_ON(epoch != map->epoch+1); ceph_decode_copy(p, &modified, sizeof(modified)); new_pool_max = ceph_decode_64(p); new_flags = ceph_decode_32(p); + if (epoch != map->epoch + 1) + goto e_inval; + /* full map? */ ceph_decode_32_safe(p, end, len, e_inval); if (len > 0) { diff --git a/net/core/dev.c b/net/core/dev.c index 2acfa44927daad..ff70c902a4196b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -478,15 +478,21 @@ static const unsigned short netdev_lock_type[] = { ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, + ARPHRD_CAN, ARPHRD_MCTP, ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, - ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, + ARPHRD_RAWHDLC, ARPHRD_RAWIP, + ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, - ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, - ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; + ARPHRD_IEEE80211_RADIOTAP, + ARPHRD_IEEE802154, ARPHRD_IEEE802154_MONITOR, + ARPHRD_PHONET, ARPHRD_PHONET_PIPE, + ARPHRD_CAIF, ARPHRD_IP6GRE, ARPHRD_NETLINK, ARPHRD_6LOWPAN, + ARPHRD_VSOCKMON, + ARPHRD_VOID, ARPHRD_NONE}; static const char *const netdev_lock_name[] = { "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", @@ -495,15 +501,21 @@ static const char *const netdev_lock_name[] = { "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", + "_xmit_CAN", "_xmit_MCTP", "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", - "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", + "_xmit_RAWHDLC", "_xmit_RAWIP", + "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", - "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", - "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; + "_xmit_IEEE80211_RADIOTAP", + "_xmit_IEEE802154", "_xmit_IEEE802154_MONITOR", + "_xmit_PHONET", "_xmit_PHONET_PIPE", + "_xmit_CAIF", "_xmit_IP6GRE", "_xmit_NETLINK", "_xmit_6LOWPAN", + "_xmit_VSOCKMON", + "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; @@ -516,6 +528,7 @@ static inline unsigned short netdev_lock_pos(unsigned short dev_type) if (netdev_lock_type[i] == dev_type) return i; /* the last key is used by default */ + WARN_ONCE(1, "netdev_lock_pos() could not find dev_type=%u\n", dev_type); return ARRAY_SIZE(netdev_lock_type) - 1; } @@ -725,7 +738,7 @@ static struct net_device_path *dev_fwd_path(struct net_device_path_stack *stack) { int k = stack->num_paths++; - if (WARN_ON_ONCE(k >= NET_DEVICE_PATH_STACK_MAX)) + if (k >= NET_DEVICE_PATH_STACK_MAX) return NULL; return &stack->path[k]; diff --git a/net/core/dev.h b/net/core/dev.h index 900880e8b5b4b9..df8a90fe89f8fc 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -29,7 +29,6 @@ struct napi_struct * netdev_napi_by_id_lock(struct net *net, unsigned int napi_id); struct net_device *dev_get_by_napi_id(unsigned int napi_id); -struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex); struct net_device *__netdev_put_lock(struct net_device *dev, struct net *net); struct net_device * netdev_xa_find_lock(struct net *net, struct net_device *dev, diff --git a/net/core/dst.c b/net/core/dst.c index e9d35f49c9e780..1dae26c51ebec0 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -68,6 +68,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, dst->lwtstate = NULL; rcuref_init(&dst->__rcuref, 1); INIT_LIST_HEAD(&dst->rt_uncached); + dst->rt_uncached_list = NULL; dst->__use = 0; dst->lastuse = jiffies; dst->flags = flags; diff --git a/net/core/filter.c b/net/core/filter.c index fa06c5a08e22f1..d93f7dea828e57 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2289,12 +2289,12 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, err = bpf_out_neigh_v6(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) - DEV_STATS_INC(dev, tx_errors); + dev_core_stats_tx_dropped_inc(dev); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: - DEV_STATS_INC(dev, tx_errors); + dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); out_xmit: return ret; @@ -2396,12 +2396,12 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, err = bpf_out_neigh_v4(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) - DEV_STATS_INC(dev, tx_errors); + dev_core_stats_tx_dropped_inc(dev); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: - DEV_STATS_INC(dev, tx_errors); + dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); out_xmit: return ret; @@ -2458,6 +2458,13 @@ BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return -EINVAL; + /* BPF test infra's convert___skb_to_skb() can create type-less + * GSO packets. gso_features_check() will detect this as a bad + * offload. However, lets not leak them out in the first place. + */ + if (unlikely(skb_is_gso(skb) && !skb_shinfo(skb)->gso_type)) + return -EBADMSG; + dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex); if (unlikely(!dev)) return -EINVAL; @@ -3345,6 +3352,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) shinfo->gso_type &= ~SKB_GSO_TCPV4; shinfo->gso_type |= SKB_GSO_TCPV6; } + shinfo->gso_type |= SKB_GSO_DODGY; } bpf_skb_change_protocol(skb, ETH_P_IPV6); @@ -3375,6 +3383,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) shinfo->gso_type &= ~SKB_GSO_TCPV6; shinfo->gso_type |= SKB_GSO_TCPV4; } + shinfo->gso_type |= SKB_GSO_DODGY; } bpf_skb_change_protocol(skb, ETH_P_IP); @@ -4124,7 +4133,7 @@ static const struct bpf_func_proto bpf_xdp_store_bytes_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, }; @@ -6316,7 +6325,7 @@ static const struct bpf_func_proto bpf_xdp_fib_lookup_proto = { .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; @@ -6371,7 +6380,7 @@ static const struct bpf_func_proto bpf_skb_fib_lookup_proto = { .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; @@ -6422,9 +6431,12 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, */ if (skb_is_gso(skb)) { ret = BPF_MTU_CHK_RET_SUCCESS; - if (flags & BPF_MTU_CHK_SEGS && - !skb_gso_validate_network_len(skb, mtu)) - ret = BPF_MTU_CHK_RET_SEGS_TOOBIG; + if (flags & BPF_MTU_CHK_SEGS) { + if (!skb_transport_header_was_set(skb)) + return -EINVAL; + if (!skb_gso_validate_network_len(skb, mtu)) + ret = BPF_MTU_CHK_RET_SEGS_TOOBIG; + } } out: *mtu_len = mtu; @@ -7922,9 +7934,9 @@ static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv4_proto = { .gpl_only = true, /* __cookie_v4_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_RDONLY, .arg1_size = sizeof(struct iphdr), - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -7954,9 +7966,9 @@ static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = { .gpl_only = true, /* __cookie_v6_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_RDONLY, .arg1_size = sizeof(struct ipv6hdr), - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -7974,9 +7986,9 @@ static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv4_proto = { .gpl_only = true, /* __cookie_v4_check is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_RDONLY, .arg1_size = sizeof(struct iphdr), - .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_RDONLY, .arg2_size = sizeof(struct tcphdr), }; @@ -7998,9 +8010,9 @@ static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv6_proto = { .gpl_only = true, /* __cookie_v6_check is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_RDONLY, .arg1_size = sizeof(struct ipv6hdr), - .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_RDONLY, .arg2_size = sizeof(struct tcphdr), }; #endif /* CONFIG_SYN_COOKIES */ diff --git a/net/core/gro.c b/net/core/gro.c index 76f9c371242210..482fa7d7f5981a 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -265,6 +265,8 @@ static void gro_complete(struct gro_node *gro, struct sk_buff *skb) goto out; } + /* NICs can feed encapsulated packets into GRO */ + skb->encapsulation = 0; rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { if (ptype->type != type || !ptype->callbacks.gro_complete) diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 212cde35affa7b..25c455c10a01cf 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -185,10 +185,6 @@ static void linkwatch_do_dev(struct net_device *dev) netif_state_change(dev); } - /* Note: our callers are responsible for calling netdev_tracker_free(). - * This is the reason we use __dev_put() instead of dev_put(). - */ - __dev_put(dev); } static void __linkwatch_run_queue(int urgent_only) @@ -243,6 +239,11 @@ static void __linkwatch_run_queue(int urgent_only) netdev_lock_ops(dev); linkwatch_do_dev(dev); netdev_unlock_ops(dev); + /* Use __dev_put() because netdev_tracker_free() was already + * called above. Must be after netdev_unlock_ops() to prevent + * netdev_run_todo() from freeing the device while still in use. + */ + __dev_put(dev); do_dev--; spin_lock_irq(&lweventlist_lock); } @@ -278,8 +279,13 @@ void __linkwatch_sync_dev(struct net_device *dev) { netdev_ops_assert_locked(dev); - if (linkwatch_clean_dev(dev)) + if (linkwatch_clean_dev(dev)) { linkwatch_do_dev(dev); + /* Use __dev_put() because netdev_tracker_free() was already + * called inside linkwatch_clean_dev(). + */ + __dev_put(dev); + } } void linkwatch_sync_dev(struct net_device *dev) @@ -288,6 +294,10 @@ void linkwatch_sync_dev(struct net_device *dev) netdev_lock_ops(dev); linkwatch_do_dev(dev); netdev_unlock_ops(dev); + /* Use __dev_put() because netdev_tracker_free() was already + * called inside linkwatch_clean_dev(). + */ + __dev_put(dev); } } diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 70e0e9a3b650c0..7dbfa6109f0b87 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -170,8 +170,14 @@ static const struct seq_operations softnet_seq_ops = { .show = softnet_seq_show, }; +struct ptype_iter_state { + struct seq_net_private p; + struct net_device *dev; +}; + static void *ptype_get_idx(struct seq_file *seq, loff_t pos) { + struct ptype_iter_state *iter = seq->private; struct list_head *ptype_list = NULL; struct packet_type *pt = NULL; struct net_device *dev; @@ -181,12 +187,16 @@ static void *ptype_get_idx(struct seq_file *seq, loff_t pos) for_each_netdev_rcu(seq_file_net(seq), dev) { ptype_list = &dev->ptype_all; list_for_each_entry_rcu(pt, ptype_list, list) { - if (i == pos) + if (i == pos) { + iter->dev = dev; return pt; + } ++i; } } + iter->dev = NULL; + list_for_each_entry_rcu(pt, &seq_file_net(seq)->ptype_all, list) { if (i == pos) return pt; @@ -218,6 +228,7 @@ static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { + struct ptype_iter_state *iter = seq->private; struct net *net = seq_file_net(seq); struct net_device *dev; struct packet_type *pt; @@ -229,19 +240,21 @@ static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) return ptype_get_idx(seq, 0); pt = v; - nxt = pt->list.next; - if (pt->dev) { - if (nxt != &pt->dev->ptype_all) + nxt = READ_ONCE(pt->list.next); + dev = iter->dev; + if (dev) { + if (nxt != &dev->ptype_all) goto found; - dev = pt->dev; for_each_netdev_continue_rcu(seq_file_net(seq), dev) { - if (!list_empty(&dev->ptype_all)) { - nxt = dev->ptype_all.next; + nxt = READ_ONCE(dev->ptype_all.next); + if (nxt != &dev->ptype_all) { + iter->dev = dev; goto found; } } - nxt = net->ptype_all.next; + iter->dev = NULL; + nxt = READ_ONCE(net->ptype_all.next); goto net_ptype_all; } @@ -252,20 +265,20 @@ static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (nxt == &net->ptype_all) { /* continue with ->ptype_specific if it's not empty */ - nxt = net->ptype_specific.next; + nxt = READ_ONCE(net->ptype_specific.next); if (nxt != &net->ptype_specific) goto found; } hash = 0; - nxt = ptype_base[0].next; + nxt = READ_ONCE(ptype_base[0].next); } else hash = ntohs(pt->type) & PTYPE_HASH_MASK; while (nxt == &ptype_base[hash]) { if (++hash >= PTYPE_HASH_SIZE) return NULL; - nxt = ptype_base[hash].next; + nxt = READ_ONCE(ptype_base[hash].next); } found: return list_entry(nxt, struct packet_type, list); @@ -279,19 +292,24 @@ static void ptype_seq_stop(struct seq_file *seq, void *v) static int ptype_seq_show(struct seq_file *seq, void *v) { + struct ptype_iter_state *iter = seq->private; struct packet_type *pt = v; + struct net_device *dev; - if (v == SEQ_START_TOKEN) + if (v == SEQ_START_TOKEN) { seq_puts(seq, "Type Device Function\n"); - else if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && - (!pt->dev || net_eq(dev_net(pt->dev), seq_file_net(seq)))) { + return 0; + } + dev = iter->dev; + if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && + (!dev || net_eq(dev_net(dev), seq_file_net(seq)))) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else seq_printf(seq, "%04x", ntohs(pt->type)); seq_printf(seq, " %-8s %ps\n", - pt->dev ? pt->dev->name : "", pt->func); + dev ? dev->name : "", pt->func); } return 0; @@ -315,7 +333,7 @@ static int __net_init dev_proc_net_init(struct net *net) &softnet_seq_ops)) goto out_dev; if (!proc_create_net("ptype", 0444, net->proc_net, &ptype_seq_ops, - sizeof(struct seq_net_private))) + sizeof(struct ptype_iter_state))) goto out_softnet; if (wext_proc_init(net)) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 331764845e8fa5..09f72f10813cc6 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -554,6 +554,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) int err; skb_queue_head_init(&np->skb_pool); + INIT_WORK(&np->refill_wq, refill_skbs_work_handler); if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { np_err(np, "%s doesn't support polling, aborting\n", @@ -591,7 +592,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) /* fill up the skb queue */ refill_skbs(np); - INIT_WORK(&np->refill_wq, refill_skbs_work_handler); /* last thing to do is link it to the net device structure */ rcu_assign_pointer(ndev->npinfo, npinfo); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6be01454f262a2..9a763d120925a8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4597,12 +4597,14 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, { struct sk_buff *list_skb = skb_shinfo(skb)->frag_list; unsigned int tnl_hlen = skb_tnl_header_len(skb); - unsigned int delta_truesize = 0; unsigned int delta_len = 0; struct sk_buff *tail = NULL; struct sk_buff *nskb, *tmp; int len_diff, err; + /* Only skb_gro_receive_list generated skbs arrive here */ + DEBUG_NET_WARN_ON_ONCE(!(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)); + skb_push(skb, -skb_network_offset(skb) + offset); /* Ensure the head is writeable before touching the shared info */ @@ -4616,8 +4618,9 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, nskb = list_skb; list_skb = list_skb->next; + DEBUG_NET_WARN_ON_ONCE(nskb->sk); + err = 0; - delta_truesize += nskb->truesize; if (skb_shared(nskb)) { tmp = skb_clone(nskb, GFP_ATOMIC); if (tmp) { @@ -4660,7 +4663,6 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, goto err_linearize; } - skb->truesize = skb->truesize - delta_truesize; skb->data_len = skb->data_len - delta_len; skb->len = skb->len - delta_len; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 2ac7731e1e0a74..ddde93dd8bc6d4 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -409,22 +409,26 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); -/* Receive sk_msg from psock->ingress_msg to @msg. */ -int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, - int len, int flags) +int __sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, + int len, int flags, int *copied_from_self) { struct iov_iter *iter = &msg->msg_iter; int peek = flags & MSG_PEEK; struct sk_msg *msg_rx; int i, copied = 0; + bool from_self; msg_rx = sk_psock_peek_msg(psock); + if (copied_from_self) + *copied_from_self = 0; + while (copied != len) { struct scatterlist *sge; if (unlikely(!msg_rx)) break; + from_self = msg_rx->sk == sk; i = msg_rx->sg.start; do { struct page *page; @@ -443,6 +447,9 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, } copied += copy; + if (from_self && copied_from_self) + *copied_from_self += copy; + if (likely(!peek)) { sge->offset += copy; sge->length -= copy; @@ -451,6 +458,7 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, atomic_sub(copy, &sk->sk_rmem_alloc); } msg_rx->sg.size -= copy; + sk_psock_msg_len_add(psock, -copy); if (!sge->length) { sk_msg_iter_var_next(i); @@ -487,6 +495,13 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, out: return copied; } + +/* Receive sk_msg from psock->ingress_msg to @msg. */ +int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, + int len, int flags) +{ + return __sk_msg_recvmsg(sk, psock, msg, len, flags, NULL); +} EXPORT_SYMBOL_GPL(sk_msg_recvmsg); bool sk_msg_is_readable(struct sock *sk) @@ -616,6 +631,12 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb if (unlikely(!msg)) return -EAGAIN; skb_set_owner_r(skb, sk); + + /* This is used in tcp_bpf_recvmsg_parser() to determine whether the + * data originates from the socket's own protocol stack. No need to + * refcount sk because msg's lifetime is bound to sk via the ingress_msg. + */ + msg->sk = sk; err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, take_ref); if (err < 0) kfree(msg); @@ -801,9 +822,11 @@ static void __sk_psock_purge_ingress_msg(struct sk_psock *psock) list_del(&msg->list); if (!msg->skb) atomic_sub(msg->sg.size, &psock->sk->sk_rmem_alloc); + sk_psock_msg_len_add(psock, -msg->sg.size); sk_msg_free(psock->sk, msg); kfree(msg); } + WARN_ON_ONCE(psock->msg_tot_len); } static void __sk_psock_zap_ingress(struct sk_psock *psock) @@ -909,6 +932,7 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, sk_msg_compute_data_pointers(msg); msg->sk = sk; ret = bpf_prog_run_pin_on_cpu(prog, msg); + msg->sk = NULL; ret = sk_psock_map_verd(ret, msg->sk_redir); psock->apply_bytes = msg->apply_bytes; if (ret == __SK_REDIRECT) { diff --git a/net/core/sock.c b/net/core/sock.c index dc03d4b5909a2a..5a38837a583843 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3836,7 +3836,7 @@ void sock_enable_timestamp(struct sock *sk, enum sock_flags flag) int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type) { - struct sock_exterr_skb *serr; + struct sock_extended_err ee; struct sk_buff *skb; int copied, err; @@ -3856,8 +3856,9 @@ int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, sock_recv_timestamp(msg, sk, skb); - serr = SKB_EXT_ERR(skb); - put_cmsg(msg, level, type, sizeof(serr->ee), &serr->ee); + /* We must use a bounce buffer for CONFIG_HARDENED_USERCOPY=y */ + ee = SKB_EXT_ERR(skb)->ee; + put_cmsg(msg, level, type, sizeof(ee), &ee); msg->msg_flags |= MSG_ERRQUEUE; err = copied; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 5b01a0e43ebe8a..0505e90033f234 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -157,7 +157,7 @@ unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) bridge_num = find_next_zero_bit(&dsa_fwd_offloading_bridges, DSA_MAX_NUM_OFFLOADING_BRIDGES, 1); - if (bridge_num >= max) + if (bridge_num > max) return 0; set_bit(bridge_num, &dsa_fwd_offloading_bridges); @@ -366,16 +366,10 @@ static struct dsa_port *dsa_tree_find_first_cpu(struct dsa_switch_tree *dst) struct net_device *dsa_tree_find_first_conduit(struct dsa_switch_tree *dst) { - struct device_node *ethernet; - struct net_device *conduit; struct dsa_port *cpu_dp; cpu_dp = dsa_tree_find_first_cpu(dst); - ethernet = of_parse_phandle(cpu_dp->dn, "ethernet", 0); - conduit = of_find_net_device_by_node(ethernet); - of_node_put(ethernet); - - return conduit; + return cpu_dp->conduit; } /* Assign the default CPU port (the first one in the tree) to all ports of the @@ -1252,14 +1246,25 @@ static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn) if (ethernet) { struct net_device *conduit; const char *user_protocol; + int err; + rtnl_lock(); conduit = of_find_net_device_by_node(ethernet); of_node_put(ethernet); - if (!conduit) + if (!conduit) { + rtnl_unlock(); return -EPROBE_DEFER; + } + + netdev_hold(conduit, &dp->conduit_tracker, GFP_KERNEL); + put_device(&conduit->dev); + rtnl_unlock(); user_protocol = of_get_property(dn, "dsa-tag-protocol", NULL); - return dsa_port_parse_cpu(dp, conduit, user_protocol); + err = dsa_port_parse_cpu(dp, conduit, user_protocol); + if (err) + netdev_put(conduit, &dp->conduit_tracker); + return err; } if (link) @@ -1392,37 +1397,30 @@ static struct device *dev_find_class(struct device *parent, char *class) return device_find_child(parent, class, dev_is_class); } -static struct net_device *dsa_dev_to_net_device(struct device *dev) -{ - struct device *d; - - d = dev_find_class(dev, "net"); - if (d != NULL) { - struct net_device *nd; - - nd = to_net_dev(d); - dev_hold(nd); - put_device(d); - - return nd; - } - - return NULL; -} - static int dsa_port_parse(struct dsa_port *dp, const char *name, struct device *dev) { if (!strcmp(name, "cpu")) { struct net_device *conduit; + struct device *d; + int err; - conduit = dsa_dev_to_net_device(dev); - if (!conduit) + rtnl_lock(); + d = dev_find_class(dev, "net"); + if (!d) { + rtnl_unlock(); return -EPROBE_DEFER; + } - dev_put(conduit); + conduit = to_net_dev(d); + netdev_hold(conduit, &dp->conduit_tracker, GFP_KERNEL); + put_device(d); + rtnl_unlock(); - return dsa_port_parse_cpu(dp, conduit, NULL); + err = dsa_port_parse_cpu(dp, conduit, NULL); + if (err) + netdev_put(conduit, &dp->conduit_tracker); + return err; } if (!strcmp(name, "dsa")) @@ -1490,6 +1488,9 @@ static void dsa_switch_release_ports(struct dsa_switch *ds) struct dsa_vlan *v, *n; dsa_switch_for_each_port_safe(dp, next, ds) { + if (dsa_port_is_cpu(dp) && dp->conduit) + netdev_put(dp->conduit, &dp->conduit_tracker); + /* These are either entries that upper layers lost track of * (probably due to bugs), or installed through interfaces * where one does not necessarily have to remove them, like @@ -1634,8 +1635,10 @@ void dsa_switch_shutdown(struct dsa_switch *ds) /* Disconnect from further netdevice notifiers on the conduit, * since netdev_uses_dsa() will now return false. */ - dsa_switch_for_each_cpu_port(dp, ds) + dsa_switch_for_each_cpu_port(dp, ds) { dp->conduit->dsa_ptr = NULL; + netdev_put(dp->conduit, &dp->conduit_tracker); + } rtnl_unlock(); out: diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 55223ebc2a7e62..146c7eaedc5acf 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -854,9 +854,6 @@ ethtool_rxfh_ctx_alloc(const struct ethtool_ops *ops, ctx->key_off = key_off; ctx->priv_size = ops->rxfh_priv_size; - ctx->hfunc = ETH_RSS_HASH_NO_CHANGE; - ctx->input_xfrm = RXH_XFRM_NO_CHANGE; - return ctx; } diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index fa83ddade4f817..9431e305b2333f 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2383,7 +2383,10 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) return -ENOMEM; WARN_ON_ONCE(!ret); - gstrings.len = ret; + if (gstrings.len && gstrings.len != ret) + gstrings.len = 0; + else + gstrings.len = ret; if (gstrings.len) { data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN)); @@ -2509,10 +2512,13 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) if (copy_from_user(&stats, useraddr, sizeof(stats))) return -EFAULT; - stats.n_stats = n_stats; + if (stats.n_stats && stats.n_stats != n_stats) + stats.n_stats = 0; + else + stats.n_stats = n_stats; - if (n_stats) { - data = vzalloc(array_size(n_stats, sizeof(u64))); + if (stats.n_stats) { + data = vzalloc(array_size(stats.n_stats, sizeof(u64))); if (!data) return -ENOMEM; ops->get_ethtool_stats(dev, &stats, data); @@ -2524,7 +2530,9 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) if (copy_to_user(useraddr, &stats, sizeof(stats))) goto out; useraddr += sizeof(stats); - if (n_stats && copy_to_user(useraddr, data, array_size(n_stats, sizeof(u64)))) + if (stats.n_stats && + copy_to_user(useraddr, data, + array_size(stats.n_stats, sizeof(u64)))) goto out; ret = 0; @@ -2560,6 +2568,10 @@ static int ethtool_get_phy_stats_phydev(struct phy_device *phydev, return -EOPNOTSUPP; n_stats = phy_ops->get_sset_count(phydev); + if (stats->n_stats && stats->n_stats != n_stats) { + stats->n_stats = 0; + return 0; + } ret = ethtool_vzalloc_stats_array(n_stats, data); if (ret) @@ -2580,6 +2592,10 @@ static int ethtool_get_phy_stats_ethtool(struct net_device *dev, return -EOPNOTSUPP; n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS); + if (stats->n_stats && stats->n_stats != n_stats) { + stats->n_stats = 0; + return 0; + } ret = ethtool_vzalloc_stats_array(n_stats, data); if (ret) @@ -2616,7 +2632,9 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) } useraddr += sizeof(stats); - if (copy_to_user(useraddr, data, array_size(stats.n_stats, sizeof(u64)))) + if (stats.n_stats && + copy_to_user(useraddr, data, + array_size(stats.n_stats, sizeof(u64)))) ret = -EFAULT; out: diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 4dced53be4b3bb..da5934cceb0757 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -824,8 +824,8 @@ rss_set_ctx_update(struct ethtool_rxfh_context *ctx, struct nlattr **tb, static int ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) { - bool indir_reset = false, indir_mod, xfrm_sym = false; struct rss_req_info *request = RSS_REQINFO(req_info); + bool indir_reset = false, indir_mod, xfrm_sym; struct ethtool_rxfh_context *ctx = NULL; struct net_device *dev = req_info->dev; bool mod = false, fields_mod = false; @@ -860,12 +860,7 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) rxfh.input_xfrm = data.input_xfrm; ethnl_update_u8(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], &mod); - /* For drivers which don't support input_xfrm it will be set to 0xff - * in the RSS context info. In all other case input_xfrm != 0 means - * symmetric hashing is requested. - */ - if (!request->rss_context || ops->rxfh_per_ctx_key) - xfrm_sym = rxfh.input_xfrm || data.input_xfrm; + xfrm_sym = rxfh.input_xfrm || data.input_xfrm; if (rxfh.input_xfrm == data.input_xfrm) rxfh.input_xfrm = RXH_XFRM_NO_CHANGE; diff --git a/net/handshake/request.c b/net/handshake/request.c index 274d2c89b6b207..6b7e3e0bf3996e 100644 --- a/net/handshake/request.c +++ b/net/handshake/request.c @@ -276,6 +276,8 @@ int handshake_req_submit(struct socket *sock, struct handshake_req *req, out_unlock: spin_unlock(&hn->hn_lock); out_err: + /* Restore original destructor so socket teardown still runs on failure */ + req->hr_sk->sk_destruct = req->hr_odestruct; trace_handshake_submit_err(net, req, req->hr_sk, ret); handshake_req_destroy(req); return ret; @@ -324,7 +326,11 @@ bool handshake_req_cancel(struct sock *sk) hn = handshake_pernet(net); if (hn && remove_pending(hn, req)) { - /* Request hadn't been accepted */ + /* Request hadn't been accepted - mark cancelled */ + if (test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) { + trace_handshake_cancel_busy(net, req, sk); + return false; + } goto out_true; } if (test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) { diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 492cbc78ab75a0..d1bfc49b5f017b 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -690,6 +690,26 @@ struct net_device *hsr_get_port_ndev(struct net_device *ndev, } EXPORT_SYMBOL(hsr_get_port_ndev); +int hsr_get_port_type(struct net_device *hsr_dev, struct net_device *dev, + enum hsr_port_type *type) +{ + struct hsr_priv *hsr = netdev_priv(hsr_dev); + struct hsr_port *port; + + rcu_read_lock(); + hsr_for_each_port(hsr, port) { + if (port->dev == dev) { + *type = port->type; + rcu_read_unlock(); + return 0; + } + } + rcu_read_unlock(); + + return -EINVAL; +} +EXPORT_SYMBOL(hsr_get_port_type); + /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 339f0d22021294..aefc9b6936ba0c 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -205,6 +205,8 @@ struct sk_buff *prp_get_untagged_frame(struct hsr_frame_info *frame, __pskb_copy(frame->skb_prp, skb_headroom(frame->skb_prp), GFP_ATOMIC); + if (!frame->skb_std) + return NULL; } else { /* Unexpected */ WARN_ONCE(1, "%s:%d: Unexpected frame received (port_src %s)\n", diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index 8177ac6c2d26de..afe06ba00ea447 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -207,14 +207,14 @@ int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, port->type = type; ether_addr_copy(port->original_macaddress, dev->dev_addr); + list_add_tail_rcu(&port->port_list, &hsr->ports); + if (type != HSR_PT_MASTER) { res = hsr_portdev_setup(hsr, dev, port, extack); if (res) goto fail_dev_setup; } - list_add_tail_rcu(&port->port_list, &hsr->ports); - master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); @@ -222,7 +222,8 @@ int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, return 0; fail_dev_setup: - kfree(port); + list_del_rcu(&port->port_list); + kfree_rcu(port, rcu); return res; } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 833f2cf97178ee..3ce1664e8632a0 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -564,7 +564,7 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, skb_reserve(skb, hlen); skb_reset_network_header(skb); - arp = skb_put(skb, arp_hdr_len(dev)); + skb_put(skb, arp_hdr_len(dev)); skb->dev = dev; skb->protocol = htons(ETH_P_ARP); if (!src_hw) @@ -572,12 +572,13 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, if (!dest_hw) dest_hw = dev->broadcast; - /* - * Fill the device header for the ARP frame + /* Fill the device header for the ARP frame. + * Note: skb->head can be changed. */ if (dev_hard_header(skb, dev, ptype, dest_hw, src_hw, skb->len) < 0) goto out; + arp = arp_hdr(skb); /* * Fill out the arp protocol part. * diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 05828d4cb6cdbb..abd77162f5e75e 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -122,8 +122,8 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, - XFRM_MODE_SKB_CB(skb)->protocol); + struct xfrm_offload *xo = xfrm_offload(skb); + const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, xo->proto); __be16 type = inner_mode->family == AF_INET6 ? htons(ETH_P_IPV6) : htons(ETH_P_IP); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index a5f3c8459758f1..0caf38e44c738c 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -2167,8 +2167,8 @@ void fib_select_multipath(struct fib_result *res, int hash, { struct fib_info *fi = res->fi; struct net *net = fi->fib_net; - bool found = false; bool use_neigh; + int score = -1; __be32 saddr; if (unlikely(res->fi->nh)) { @@ -2180,7 +2180,7 @@ void fib_select_multipath(struct fib_result *res, int hash, saddr = fl4 ? fl4->saddr : 0; change_nexthops(fi) { - int nh_upper_bound; + int nh_upper_bound, nh_score = 0; /* Nexthops without a carrier are assigned an upper bound of * minus one when "ignore_routes_with_linkdown" is set. @@ -2190,24 +2190,18 @@ void fib_select_multipath(struct fib_result *res, int hash, (use_neigh && !fib_good_nh(nexthop_nh))) continue; - if (!found) { + if (saddr && nexthop_nh->nh_saddr == saddr) + nh_score += 2; + if (hash <= nh_upper_bound) + nh_score++; + if (score < nh_score) { res->nh_sel = nhsel; res->nhc = &nexthop_nh->nh_common; - found = !saddr || nexthop_nh->nh_saddr == saddr; + if (nh_score == 3 || (!saddr && nh_score == 1)) + return; + score = nh_score; } - if (hash > nh_upper_bound) - continue; - - if (!saddr || nexthop_nh->nh_saddr == saddr) { - res->nh_sel = nhsel; - res->nhc = &nexthop_nh->nh_common; - return; - } - - if (found) - return; - } endfor_nexthops(fi); } #endif diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 59a6f0a9638f99..7e2c17fec3fc46 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2053,10 +2053,11 @@ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) continue; } - /* Do not flush error routes if network namespace is - * not being dismantled + /* When not flushing the entire table, skip error + * routes that are not marked for deletion. */ - if (!flush_all && fib_props[fa->fa_type].error) { + if (!flush_all && fib_props[fa->fa_type].error && + !(fi->fib_flags & RTNH_F_DEAD)) { slen = fa->fa_slen; continue; } diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c index 3970b6b7ace537..ab8f309f8925d6 100644 --- a/net/ipv4/fou_core.c +++ b/net/ipv4/fou_core.c @@ -215,6 +215,9 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) return gue_control_message(skb, guehdr); proto_ctype = guehdr->proto_ctype; + if (unlikely(!proto_ctype)) + goto drop; + __skb_pull(skb, sizeof(struct udphdr) + hdrlen); skb_reset_transport_header(skb); diff --git a/net/ipv4/fou_nl.c b/net/ipv4/fou_nl.c index 506260b4a4dc26..9ff7797ef7c4f9 100644 --- a/net/ipv4/fou_nl.c +++ b/net/ipv4/fou_nl.c @@ -14,7 +14,7 @@ const struct nla_policy fou_nl_policy[FOU_ATTR_IFINDEX + 1] = { [FOU_ATTR_PORT] = { .type = NLA_BE16, }, [FOU_ATTR_AF] = { .type = NLA_U8, }, - [FOU_ATTR_IPPROTO] = { .type = NLA_U8, }, + [FOU_ATTR_IPPROTO] = NLA_POLICY_MIN(NLA_U8, 1), [FOU_ATTR_TYPE] = { .type = NLA_U8, }, [FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, }, [FOU_ATTR_LOCAL_V4] = { .type = NLA_U32, }, diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 1b7fb5d935edfd..3e19a5d465b838 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -248,7 +248,8 @@ bool icmp_global_allow(struct net *net) if (delta < HZ / 50) return false; - incr = READ_ONCE(net->ipv4.sysctl_icmp_msgs_per_sec) * delta / HZ; + incr = READ_ONCE(net->ipv4.sysctl_icmp_msgs_per_sec); + incr = div_u64((u64)incr * delta, HZ); if (!incr) return false; @@ -554,6 +555,21 @@ static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, /* steal dst entry from skb_in, don't drop refcnt */ skb_dstref_steal(skb_in); skb_dstref_restore(skb_in, orefdst); + + /* + * At this point, fl4_dec.daddr should NOT be local (we + * checked fl4_dec.saddr above). However, a race condition + * may occur if the address is added to the interface + * concurrently. In that case, ip_route_input() returns a + * LOCAL route with dst.output=ip_rt_bug, which must not + * be used for output. + */ + if (!err && rt2 && rt2->rt_type == RTN_LOCAL) { + net_warn_ratelimited("detected local route for %pI4 during ICMP sending, src %pI4\n", + &fl4_dec.daddr, &fl4_dec.saddr); + dst_release(&rt2->dst); + err = -EINVAL; + } } if (err) @@ -843,16 +859,22 @@ static void icmp_socket_deliver(struct sk_buff *skb, u32 info) /* Checkin full IP header plus 8 bytes of protocol to * avoid additional coding at protocol handlers. */ - if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) { - __ICMP_INC_STATS(dev_net_rcu(skb->dev), ICMP_MIB_INERRORS); - return; - } + if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) + goto out; + + /* IPPROTO_RAW sockets are not supposed to receive anything. */ + if (protocol == IPPROTO_RAW) + goto out; raw_icmp_error(skb, protocol, info); ipprot = rcu_dereference(inet_protos[protocol]); if (ipprot && ipprot->err_handler) ipprot->err_handler(skb, info); + return; + +out: + __ICMP_INC_STATS(dev_net_rcu(skb->dev), ICMP_MIB_INERRORS); } static bool icmp_tag_validation(int proto) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 025895eb6ec597..4e6d7467ed444b 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -218,6 +218,41 @@ static int __init inet_frag_wq_init(void) pure_initcall(inet_frag_wq_init); +void fqdir_pre_exit(struct fqdir *fqdir) +{ + struct inet_frag_queue *fq; + struct rhashtable_iter hti; + + /* Prevent creation of new frags. + * Pairs with READ_ONCE() in inet_frag_find(). + */ + WRITE_ONCE(fqdir->high_thresh, 0); + + /* Pairs with READ_ONCE() in inet_frag_kill(), ip_expire() + * and ip6frag_expire_frag_queue(). + */ + WRITE_ONCE(fqdir->dead, true); + + rhashtable_walk_enter(&fqdir->rhashtable, &hti); + rhashtable_walk_start(&hti); + + while ((fq = rhashtable_walk_next(&hti))) { + if (IS_ERR(fq)) { + if (PTR_ERR(fq) != -EAGAIN) + break; + continue; + } + spin_lock_bh(&fq->lock); + if (!(fq->flags & INET_FRAG_COMPLETE)) + inet_frag_queue_flush(fq, 0); + spin_unlock_bh(&fq->lock); + } + + rhashtable_walk_stop(&hti); + rhashtable_walk_exit(&hti); +} +EXPORT_SYMBOL(fqdir_pre_exit); + void fqdir_exit(struct fqdir *fqdir) { INIT_WORK(&fqdir->destroy_work, fqdir_work_fn); @@ -263,8 +298,8 @@ static void inet_frag_destroy_rcu(struct rcu_head *head) kmem_cache_free(f->frags_cachep, q); } -unsigned int inet_frag_rbtree_purge(struct rb_root *root, - enum skb_drop_reason reason) +static unsigned int +inet_frag_rbtree_purge(struct rb_root *root, enum skb_drop_reason reason) { struct rb_node *p = rb_first(root); unsigned int sum = 0; @@ -284,7 +319,17 @@ unsigned int inet_frag_rbtree_purge(struct rb_root *root, } return sum; } -EXPORT_SYMBOL(inet_frag_rbtree_purge); + +void inet_frag_queue_flush(struct inet_frag_queue *q, + enum skb_drop_reason reason) +{ + unsigned int sum; + + reason = reason ?: SKB_DROP_REASON_FRAG_REASM_TIMEOUT; + sum = inet_frag_rbtree_purge(&q->rb_fragments, reason); + sub_frag_mem_limit(q->fqdir, sum); +} +EXPORT_SYMBOL(inet_frag_queue_flush); void inet_frag_destroy(struct inet_frag_queue *q) { @@ -327,7 +372,9 @@ static struct inet_frag_queue *inet_frag_alloc(struct fqdir *fqdir, timer_setup(&q->timer, f->frag_expire, 0); spin_lock_init(&q->lock); - /* One reference for the timer, one for the hash table. */ + /* One reference for the timer, one for the hash table. + * We never take any extra references, only decrement this field. + */ refcount_set(&q->refcnt, 2); return q; @@ -441,6 +488,8 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, } FRAG_CB(skb)->ip_defrag_offset = offset; + if (offset) + nf_reset_ct(skb); return IPFRAG_OK; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index f7012479713ba6..56b0f738d2f27b 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -134,11 +134,6 @@ static void ip_expire(struct timer_list *t) net = qp->q.fqdir->net; rcu_read_lock(); - - /* Paired with WRITE_ONCE() in fqdir_pre_exit(). */ - if (READ_ONCE(qp->q.fqdir->dead)) - goto out_rcu_unlock; - spin_lock(&qp->q.lock); if (qp->q.flags & INET_FRAG_COMPLETE) @@ -146,6 +141,13 @@ static void ip_expire(struct timer_list *t) qp->q.flags |= INET_FRAG_DROP; inet_frag_kill(&qp->q, &refs); + + /* Paired with WRITE_ONCE() in fqdir_pre_exit(). */ + if (READ_ONCE(qp->q.fqdir->dead)) { + inet_frag_queue_flush(&qp->q, 0); + goto out; + } + __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT); @@ -240,16 +242,10 @@ static int ip_frag_too_far(struct ipq *qp) static int ip_frag_reinit(struct ipq *qp) { - unsigned int sum_truesize = 0; - - if (!mod_timer(&qp->q.timer, jiffies + qp->q.fqdir->timeout)) { - refcount_inc(&qp->q.refcnt); + if (!mod_timer_pending(&qp->q.timer, jiffies + qp->q.fqdir->timeout)) return -ETIMEDOUT; - } - sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments, - SKB_DROP_REASON_FRAG_TOO_FAR); - sub_frag_mem_limit(qp->q.fqdir, sum_truesize); + inet_frag_queue_flush(&qp->q, SKB_DROP_REASON_FRAG_TOO_FAR); qp->q.flags = 0; qp->q.len = 0; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 761a53c6a89a64..e13244729ad8d5 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -330,6 +330,10 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (!tun_dst) return PACKET_REJECT; + /* MUST set options_len before referencing options */ + info = &tun_dst->u.tun_info; + info->options_len = sizeof(*md); + /* skb can be uncloned in __iptunnel_pull_header, so * old pkt_md is no longer valid and we need to reset * it @@ -344,10 +348,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); - info = &tun_dst->u.tun_info; __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); - info->options_len = sizeof(*md); } skb_reset_mac_header(skb); @@ -889,10 +891,17 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, const void *daddr, const void *saddr, unsigned int len) { struct ip_tunnel *t = netdev_priv(dev); - struct iphdr *iph; struct gre_base_hdr *greh; + struct iphdr *iph; + int needed; + + needed = t->hlen + sizeof(*iph); + if (skb_headroom(skb) < needed && + pskb_expand_head(skb, HH_DATA_ALIGN(needed - skb_headroom(skb)), + 0, GFP_ATOMIC)) + return -needed; - iph = skb_push(skb, t->hlen + sizeof(*iph)); + iph = skb_push(skb, needed); greh = (struct gre_base_hdr *)(iph+1); greh->flags = gre_tnl_flags_to_gre_flags(t->parms.o_flags); greh->protocol = htons(type); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 158a30ae7c5f2f..50d0f5fe4e4c6d 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1281,7 +1281,7 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], } EXPORT_SYMBOL_GPL(ip_tunnel_changelink); -int ip_tunnel_init(struct net_device *dev) +int __ip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -1308,10 +1308,9 @@ int ip_tunnel_init(struct net_device *dev) if (tunnel->collect_md) netif_keep_dst(dev); - netdev_lockdep_set_classes(dev); return 0; } -EXPORT_SYMBOL_GPL(ip_tunnel_init); +EXPORT_SYMBOL_GPL(__ip_tunnel_init); void ip_tunnel_uninit(struct net_device *dev) { diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 5321c5801c64dd..690f486173e01d 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -148,7 +148,7 @@ void ping_unhash(struct sock *sk) pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num); spin_lock(&ping_table.lock); if (sk_del_node_init_rcu(sk)) { - isk->inet_num = 0; + WRITE_ONCE(isk->inet_num, 0); isk->inet_sport = 0; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); } @@ -181,31 +181,35 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) } sk_for_each_rcu(sk, hslot) { + int bound_dev_if; + if (!net_eq(sock_net(sk), net)) continue; isk = inet_sk(sk); pr_debug("iterate\n"); - if (isk->inet_num != ident) + if (READ_ONCE(isk->inet_num) != ident) continue; + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); if (skb->protocol == htons(ETH_P_IP) && sk->sk_family == AF_INET) { + __be32 rcv_saddr = READ_ONCE(isk->inet_rcv_saddr); + pr_debug("found: %p: num=%d, daddr=%pI4, dif=%d\n", sk, - (int) isk->inet_num, &isk->inet_rcv_saddr, - sk->sk_bound_dev_if); + ident, &rcv_saddr, + bound_dev_if); - if (isk->inet_rcv_saddr && - isk->inet_rcv_saddr != ip_hdr(skb)->daddr) + if (rcv_saddr && rcv_saddr != ip_hdr(skb)->daddr) continue; #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6) && sk->sk_family == AF_INET6) { pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk, - (int) isk->inet_num, + ident, &sk->sk_v6_rcv_saddr, - sk->sk_bound_dev_if); + bound_dev_if); if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) && !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, @@ -216,8 +220,8 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) continue; } - if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif && - sk->sk_bound_dev_if != sdif) + if (bound_dev_if && bound_dev_if != dif && + bound_dev_if != sdif) continue; goto exit; @@ -392,7 +396,9 @@ static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr) if (saddr->sa_family == AF_INET) { struct inet_sock *isk = inet_sk(sk); struct sockaddr_in *addr = (struct sockaddr_in *) saddr; - isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr; + + isk->inet_saddr = addr->sin_addr.s_addr; + WRITE_ONCE(isk->inet_rcv_saddr, addr->sin_addr.s_addr); #if IS_ENABLED(CONFIG_IPV6) } else if (saddr->sa_family == AF_INET6) { struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr; @@ -828,10 +834,8 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) out_free: if (free) kfree(ipc.opt); - if (!err) { - icmp_out_count(sock_net(sk), user_icmph.type); + if (!err) return len; - } return err; do_confirm: @@ -851,7 +855,8 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, struct sk_buff *skb; int copied, err; - pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, isk->inet_num); + pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, + READ_ONCE(isk->inet_num)); err = -EOPNOTSUPP; if (flags & MSG_OOB) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b549d6a573073b..11d990703d31a9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1537,9 +1537,9 @@ void rt_add_uncached_list(struct rtable *rt) void rt_del_uncached_list(struct rtable *rt) { - if (!list_empty(&rt->dst.rt_uncached)) { - struct uncached_list *ul = rt->dst.rt_uncached_list; + struct uncached_list *ul = rt->dst.rt_uncached_list; + if (ul) { spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8a18aeca7ab074..e35825656e6ea9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -503,6 +503,9 @@ static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc) struct sk_buff *skb = tcp_write_queue_tail(sk); u32 tsflags = sockc->tsflags; + if (unlikely(!skb)) + skb = skb_rb_last(&sk->tcp_rtx_queue); + if (tsflags && skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); @@ -2651,10 +2654,8 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, if (sk->sk_state == TCP_LISTEN) goto out; - if (tp->recvmsg_inq) { + if (tp->recvmsg_inq) *cmsg_flags = TCP_CMSG_INQ; - msg->msg_get_inq = 1; - } timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); /* Urgent data needs to be handled specially. */ @@ -2928,10 +2929,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, ret = tcp_recvmsg_locked(sk, msg, len, flags, &tss, &cmsg_flags); release_sock(sk); - if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) { + if ((cmsg_flags | msg->msg_get_inq) && ret >= 0) { if (cmsg_flags & TCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); - if (msg->msg_get_inq) { + if ((cmsg_flags & TCP_CMSG_INQ) | msg->msg_get_inq) { msg->msg_inq = tcp_inq_hint(sk); if (cmsg_flags & TCP_CMSG_INQ) put_cmsg(msg, SOL_TCP, TCP_CM_INQ, diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index a268e1595b22aa..ca8a5cb8e569d7 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -10,6 +10,7 @@ #include #include +#include void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) { @@ -226,6 +227,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, int peek = flags & MSG_PEEK; struct sk_psock *psock; struct tcp_sock *tcp; + int copied_from_self = 0; int copied = 0; u32 seq; @@ -262,7 +264,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, } msg_bytes_ready: - copied = sk_msg_recvmsg(sk, psock, msg, len, flags); + copied = __sk_msg_recvmsg(sk, psock, msg, len, flags, &copied_from_self); /* The typical case for EFAULT is the socket was gracefully * shutdown with a FIN pkt. So check here the other case is * some error on copy_page_to_iter which would be unexpected. @@ -277,7 +279,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, goto out; } } - seq += copied; + seq += copied_from_self; if (!copied) { long timeo; int data; @@ -331,6 +333,24 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, return copied; } +static int tcp_bpf_ioctl(struct sock *sk, int cmd, int *karg) +{ + bool slow; + + if (cmd != SIOCINQ) + return tcp_ioctl(sk, cmd, karg); + + /* works similar as tcp_ioctl */ + if (sk->sk_state == TCP_LISTEN) + return -EINVAL; + + slow = lock_sock_fast(sk); + *karg = sk_psock_msg_inq(sk); + unlock_sock_fast(sk, slow); + + return 0; +} + static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { @@ -609,6 +629,7 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS], prot[TCP_BPF_BASE].close = sock_map_close; prot[TCP_BPF_BASE].recvmsg = tcp_bpf_recvmsg; prot[TCP_BPF_BASE].sock_is_readable = sk_msg_is_readable; + prot[TCP_BPF_BASE].ioctl = tcp_bpf_ioctl; prot[TCP_BPF_TX] = prot[TCP_BPF_BASE]; prot[TCP_BPF_TX].sendmsg = tcp_bpf_sendmsg; diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index df758adbb445f2..e9f6c77e063163 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -16,6 +16,7 @@ #include #include #include +#include #include static DEFINE_SPINLOCK(tcp_cong_list_lock); @@ -227,7 +228,7 @@ void tcp_assign_congestion_control(struct sock *sk) memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); else INET_ECN_dontxmit(sk); } @@ -257,7 +258,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); else INET_ECN_dontxmit(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e4a979b75cc663..ede266463d5d10 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6817,7 +6817,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tp->snd_wl1 = TCP_SKB_CB(skb)->seq; tp->max_window = tp->snd_wnd; - tcp_ecn_rcv_syn(tp, th, skb); + tcp_ecn_rcv_syn(sk, th, skb); tcp_mtup_init(sk); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); @@ -7222,7 +7222,8 @@ static void tcp_ecn_create_request(struct request_sock *req, u32 ecn_ok_dst; if (tcp_accecn_syn_requested(th) && - READ_ONCE(net->ipv4.sysctl_tcp_ecn) >= 3) { + (READ_ONCE(net->ipv4.sysctl_tcp_ecn) >= 3 || + tcp_ca_needs_accecn(listen_sk))) { inet_rsk(req)->ecn_ok = 1; tcp_rsk(req)->accecn_ok = 1; tcp_rsk(req)->syn_ect_rcv = TCP_SKB_CB(skb)->ip_dsfield & diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 2ec8c6f1cdccc0..1fade94813c622 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -488,9 +488,10 @@ static void tcp_ecn_openreq_child(struct sock *sk, tp->accecn_opt_demand = 1; tcp_ecn_received_counters_payload(sk, skb); } else { - tcp_ecn_mode_set(tp, inet_rsk(req)->ecn_ok ? - TCP_ECN_MODE_RFC3168 : - TCP_ECN_DISABLED); + if (inet_rsk(req)->ecn_ok && !tcp_ca_no_fallback_rfc3168(sk)) + tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168); + else + tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); } } diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 2cb93da93abc29..ed4bc3209c9730 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -107,7 +107,8 @@ static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb, if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) { struct tcphdr *th = tcp_hdr(skb); - if (skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) + if ((skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) && + !(skb_shinfo(skb)->gso_type & SKB_GSO_DODGY)) return __tcp4_gso_segment_list(skb, features); skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 30dfbf73729dad..860bd61ff047ff 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1851,6 +1851,7 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) sk_peek_offset_bwd(sk, len); if (!skb_shared(skb)) { + skb_orphan(skb); skb_attempt_defer_free(skb); return; } diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 0735d820e413f3..91233e37cd97a2 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -5,6 +5,7 @@ #include #include #include +#include #include "udp_impl.h" @@ -111,12 +112,26 @@ enum { static DEFINE_SPINLOCK(udpv6_prot_lock); static struct proto udp_bpf_prots[UDP_BPF_NUM_PROTS]; +static int udp_bpf_ioctl(struct sock *sk, int cmd, int *karg) +{ + if (cmd != SIOCINQ) + return udp_ioctl(sk, cmd, karg); + + /* Since we don't hold a lock, sk_receive_queue may contain data. + * BPF might only be processing this data at the moment. We only + * care about the data in the ingress_msg here. + */ + *karg = sk_msg_first_len(sk); + return 0; +} + static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base) { - *prot = *base; - prot->close = sock_map_close; - prot->recvmsg = udp_bpf_recvmsg; - prot->sock_is_readable = sk_msg_is_readable; + *prot = *base; + prot->close = sock_map_close; + prot->recvmsg = udp_bpf_recvmsg; + prot->sock_is_readable = sk_msg_is_readable; + prot->ioctl = udp_bpf_ioctl; } static void udp_bpf_check_v6_needs_rebuild(struct proto *ops) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 19d0b5b09ffae6..589456bd8b5f1b 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -514,7 +514,8 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) { /* Detect modified geometry and pass those to skb_segment. */ - if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) + if ((skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) && + !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_DODGY)) return __udp_gso_segment_list(gso_skb, features, is_ipv6); ret = __skb_linearize(gso_skb); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 40e9c336f6c55e..cad5e4ab8c3dbf 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3112,12 +3112,12 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, in6_ifa_hold(ifp); read_unlock_bh(&idev->lock); - ipv6_del_addr(ifp); - if (!(ifp->flags & IFA_F_TEMPORARY) && (ifp->flags & IFA_F_MANAGETEMPADDR)) delete_tempaddrs(idev, ifp); + ipv6_del_addr(ifp); + addrconf_verify_rtnl(net); if (ipv6_addr_is_multicast(pfx)) { ipv6_mc_config(net->ipv6.mc_autojoin_sk, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 1b0314644e0ccc..0e8f48835869cd 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -955,7 +955,7 @@ static int __net_init inet6_net_init(struct net *net) int err = 0; net->ipv6.sysctl.bindv6only = 0; - net->ipv6.sysctl.icmpv6_time = 1*HZ; + net->ipv6.sysctl.icmpv6_time = HZ / 10; net->ipv6.sysctl.icmpv6_echo_ignore_all = 0; net->ipv6.sysctl.icmpv6_echo_ignore_multicast = 0; net->ipv6.sysctl.icmpv6_echo_ignore_anycast = 0; diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index df1986973430c0..21f6ed126253a2 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -1342,7 +1342,8 @@ static int calipso_skbuff_setattr(struct sk_buff *skb, /* At this point new_end aligns to 4n, so (new_end & 4) pads to 8n */ pad = ((new_end & 4) + (end & 7)) & 7; len_delta = new_end - (int)end + pad; - ret_val = skb_cow(skb, skb_headroom(skb) + len_delta); + ret_val = skb_cow(skb, + skb_headroom(skb) + (len_delta > 0 ? len_delta : 0)); if (ret_val < 0) return ret_val; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 22410243ebe88d..22895521a57d09 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -158,8 +158,8 @@ static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, - XFRM_MODE_SKB_CB(skb)->protocol); + struct xfrm_offload *xo = xfrm_offload(skb); + const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, xo->proto); __be16 type = inner_mode->family == AF_INET ? htons(ETH_P_IP) : htons(ETH_P_IPV6); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 56c974cf75d151..35b32dcf581fff 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -217,14 +217,9 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, } else if (dev && (dev->flags & IFF_LOOPBACK)) { res = true; } else { - struct rt6_info *rt = dst_rt6_info(dst); - int tmo = net->ipv6.sysctl.icmpv6_time; + int tmo = READ_ONCE(net->ipv6.sysctl.icmpv6_time); struct inet_peer *peer; - /* Give more bandwidth to wider prefixes. */ - if (rt->rt6i_dst.plen < 128) - tmo >>= ((128 - rt->rt6i_dst.plen)>>5); - peer = inet_getpeer_v6(net->ipv6.peers, &fl6->daddr); res = inet_peer_xrlim_allow(peer, tmo); } @@ -769,7 +764,9 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb) fl6.daddr = ipv6_hdr(skb)->saddr; if (saddr) fl6.saddr = *saddr; - fl6.flowi6_oif = icmp6_iif(skb); + fl6.flowi6_oif = ipv6_addr_loopback(&fl6.daddr) ? + skb->dev->ifindex : + icmp6_iif(skb); fl6.fl6_icmp_type = type; fl6.flowi6_mark = mark; fl6.flowi6_uid = sock_net_uid(net, NULL); @@ -868,6 +865,12 @@ enum skb_drop_reason icmpv6_notify(struct sk_buff *skb, u8 type, if (reason != SKB_NOT_DROPPED_YET) goto out; + if (nexthdr == IPPROTO_RAW) { + /* Add a more specific reason later ? */ + reason = SKB_DROP_REASON_NOT_SPECIFIED; + goto out; + } + /* BUGGG_FUTURE: we should try to parse exthdrs in this packet. Without this we will not able f.e. to make source routed pmtu discovery. diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 02c16909f61822..cc149227b49f4a 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1138,6 +1138,11 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_set_expires(iter, rt->expires); fib6_add_gc_list(iter); } + if (!(rt->fib6_flags & (RTF_ADDRCONF | RTF_PREFIX_RT)) && + (iter->nh || !iter->fib6_nh->fib_nh_gw_family)) { + iter->fib6_flags &= ~RTF_ADDRCONF; + iter->fib6_flags &= ~RTF_PREFIX_RT; + } if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c82a75510c0e2f..d19d86ed43766b 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -535,6 +535,10 @@ static int ip6erspan_rcv(struct sk_buff *skb, if (!tun_dst) return PACKET_REJECT; + /* MUST set options_len before referencing options */ + info = &tun_dst->u.tun_info; + info->options_len = sizeof(*md); + /* skb can be uncloned in __iptunnel_pull_header, so * old pkt_md is no longer valid and we need to reset * it @@ -543,7 +547,6 @@ static int ip6erspan_rcv(struct sk_buff *skb, skb_network_header_len(skb); pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + sizeof(*ershdr)); - info = &tun_dst->u.tun_info; md = ip_tunnel_info_opts(info); md->version = ver; md2 = &md->u.md2; @@ -551,7 +554,6 @@ static int ip6erspan_rcv(struct sk_buff *skb, ERSPAN_V2_MDSIZE); __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); - info->options_len = sizeof(*md); ip6_tnl_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); @@ -1366,9 +1368,16 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, { struct ip6_tnl *t = netdev_priv(dev); struct ipv6hdr *ipv6h; + int needed; __be16 *p; - ipv6h = skb_push(skb, t->hlen + sizeof(*ipv6h)); + needed = t->hlen + sizeof(*ipv6h); + if (skb_headroom(skb) < needed && + pskb_expand_head(skb, HH_DATA_ALIGN(needed - skb_headroom(skb)), + 0, GFP_ATOMIC)) + return -needed; + + ipv6h = skb_push(skb, needed); ip6_flow_hdr(ipv6h, 0, ip6_make_flowlabel(dev_net(dev), skb, t->fl.u.ip6.flowlabel, true, &t->fl.u.ip6)); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 6405072050e0ef..c1f39735a23676 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -844,7 +844,7 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, skb_reset_network_header(skb); - if (!pskb_inet_may_pull(skb)) { + if (skb_vlan_inet_prepare(skb, true)) { DEV_STATS_INC(tunnel->dev, rx_length_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f427e41e9c49bf..0fd3f53dbb52e6 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1555,8 +1555,8 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu)); mtu = ntohl(n); - if (in6_dev->ra_mtu != mtu) { - in6_dev->ra_mtu = mtu; + if (READ_ONCE(in6_dev->ra_mtu) != mtu) { + WRITE_ONCE(in6_dev->ra_mtu, mtu); send_ifinfo_notify = true; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index aee6a10b112aac..e3a260a5564ba8 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -148,9 +148,9 @@ void rt6_uncached_list_add(struct rt6_info *rt) void rt6_uncached_list_del(struct rt6_info *rt) { - if (!list_empty(&rt->dst.rt_uncached)) { - struct uncached_list *ul = rt->dst.rt_uncached_list; + struct uncached_list *ul = rt->dst.rt_uncached_list; + if (ul) { spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); @@ -1470,7 +1470,18 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net, p = this_cpu_ptr(res->nh->rt6i_pcpu); prev = cmpxchg(p, NULL, pcpu_rt); - BUG_ON(prev); + if (unlikely(prev)) { + /* + * Another task on this CPU already installed a pcpu_rt. + * This can happen on PREEMPT_RT where preemption is possible. + * Free our allocation and return the existing one. + */ + WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_RT)); + + dst_dev_put(&pcpu_rt->dst); + dst_release(&pcpu_rt->dst); + return prev; + } if (res->f6i->fib6_destroying) { struct fib6_info *from; diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index effeba58630b5a..5670d32c27f80e 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -170,7 +170,8 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) { struct tcphdr *th = tcp_hdr(skb); - if (skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) + if ((skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) && + !(skb_shinfo(skb)->gso_type & SKB_GSO_DODGY)) return __tcp6_gso_segment_list(skb, features); skb->ip_summed = CHECKSUM_NONE; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 0710281dd95aac..a0682e63fc6375 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1086,8 +1086,10 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) tunnel = session->tunnel; /* Check protocol version */ - if (version != tunnel->version) + if (version != tunnel->version) { + l2tp_session_put(session); goto invalid; + } if (version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { @@ -1414,8 +1416,6 @@ static void l2tp_tunnel_del_work(struct work_struct *work) { struct l2tp_tunnel *tunnel = container_of(work, struct l2tp_tunnel, del_work); - struct sock *sk = tunnel->sock; - struct socket *sock = sk->sk_socket; l2tp_tunnel_closeall(tunnel); @@ -1423,6 +1423,8 @@ static void l2tp_tunnel_del_work(struct work_struct *work) * the sk API to release it here. */ if (tunnel->fd < 0) { + struct socket *sock = tunnel->sock->sk_socket; + if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c index 48c04f89de20af..65989c7dfc6809 100644 --- a/net/mac80211/aes_cmac.c +++ b/net/mac80211/aes_cmac.c @@ -22,50 +22,77 @@ static const u8 zero[CMAC_TLEN_256]; -void ieee80211_aes_cmac(struct crypto_shash *tfm, const u8 *aad, - const u8 *data, size_t data_len, u8 *mic) +int ieee80211_aes_cmac(struct crypto_shash *tfm, const u8 *aad, + const u8 *data, size_t data_len, u8 *mic) { + int err; SHASH_DESC_ON_STACK(desc, tfm); u8 out[AES_BLOCK_SIZE]; const __le16 *fc; desc->tfm = tfm; - crypto_shash_init(desc); - crypto_shash_update(desc, aad, AAD_LEN); + err = crypto_shash_init(desc); + if (err) + return err; + err = crypto_shash_update(desc, aad, AAD_LEN); + if (err) + return err; fc = (const __le16 *)aad; if (ieee80211_is_beacon(*fc)) { /* mask Timestamp field to zero */ - crypto_shash_update(desc, zero, 8); - crypto_shash_update(desc, data + 8, data_len - 8 - CMAC_TLEN); + err = crypto_shash_update(desc, zero, 8); + if (err) + return err; + err = crypto_shash_update(desc, data + 8, + data_len - 8 - CMAC_TLEN); + if (err) + return err; } else { - crypto_shash_update(desc, data, data_len - CMAC_TLEN); + err = crypto_shash_update(desc, data, + data_len - CMAC_TLEN); + if (err) + return err; } - crypto_shash_finup(desc, zero, CMAC_TLEN, out); - + err = crypto_shash_finup(desc, zero, CMAC_TLEN, out); + if (err) + return err; memcpy(mic, out, CMAC_TLEN); + + return 0; } -void ieee80211_aes_cmac_256(struct crypto_shash *tfm, const u8 *aad, - const u8 *data, size_t data_len, u8 *mic) +int ieee80211_aes_cmac_256(struct crypto_shash *tfm, const u8 *aad, + const u8 *data, size_t data_len, u8 *mic) { + int err; SHASH_DESC_ON_STACK(desc, tfm); const __le16 *fc; desc->tfm = tfm; - crypto_shash_init(desc); - crypto_shash_update(desc, aad, AAD_LEN); + err = crypto_shash_init(desc); + if (err) + return err; + err = crypto_shash_update(desc, aad, AAD_LEN); + if (err) + return err; fc = (const __le16 *)aad; if (ieee80211_is_beacon(*fc)) { /* mask Timestamp field to zero */ - crypto_shash_update(desc, zero, 8); - crypto_shash_update(desc, data + 8, - data_len - 8 - CMAC_TLEN_256); + err = crypto_shash_update(desc, zero, 8); + if (err) + return err; + err = crypto_shash_update(desc, data + 8, + data_len - 8 - CMAC_TLEN_256); + if (err) + return err; } else { - crypto_shash_update(desc, data, data_len - CMAC_TLEN_256); + err = crypto_shash_update(desc, data, data_len - CMAC_TLEN_256); + if (err) + return err; } - crypto_shash_finup(desc, zero, CMAC_TLEN_256, mic); + return crypto_shash_finup(desc, zero, CMAC_TLEN_256, mic); } struct crypto_shash *ieee80211_aes_cmac_key_setup(const u8 key[], diff --git a/net/mac80211/aes_cmac.h b/net/mac80211/aes_cmac.h index 76817446fb8384..f74150542142a6 100644 --- a/net/mac80211/aes_cmac.h +++ b/net/mac80211/aes_cmac.h @@ -11,10 +11,10 @@ struct crypto_shash *ieee80211_aes_cmac_key_setup(const u8 key[], size_t key_len); -void ieee80211_aes_cmac(struct crypto_shash *tfm, const u8 *aad, - const u8 *data, size_t data_len, u8 *mic); -void ieee80211_aes_cmac_256(struct crypto_shash *tfm, const u8 *aad, - const u8 *data, size_t data_len, u8 *mic); +int ieee80211_aes_cmac(struct crypto_shash *tfm, const u8 *aad, + const u8 *data, size_t data_len, u8 *mic); +int ieee80211_aes_cmac_256(struct crypto_shash *tfm, const u8 *aad, + const u8 *data, size_t data_len, u8 *mic); void ieee80211_aes_cmac_key_free(struct crypto_shash *tfm); #endif /* AES_CMAC_H */ diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index c52b0456039ddc..e18df59951a82d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1328,7 +1328,6 @@ ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, size = sizeof(*new) + new_head_len + new_tail_len; - /* new or old multiple BSSID elements? */ if (params->mbssid_ies) { mbssid = params->mbssid_ies; size += struct_size(new->mbssid_ies, elem, mbssid->cnt); @@ -1338,15 +1337,6 @@ ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, } size += ieee80211_get_mbssid_beacon_len(mbssid, rnr, mbssid->cnt); - } else if (old && old->mbssid_ies) { - mbssid = old->mbssid_ies; - size += struct_size(new->mbssid_ies, elem, mbssid->cnt); - if (old && old->rnr_ies) { - rnr = old->rnr_ies; - size += struct_size(new->rnr_ies, elem, rnr->cnt); - } - size += ieee80211_get_mbssid_beacon_len(mbssid, rnr, - mbssid->cnt); } new = kzalloc(size, GFP_KERNEL); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 878c3b14aeb806..5c0c833fcf7a93 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -451,8 +451,6 @@ struct ieee80211_mgd_assoc_data { struct ieee80211_conn_settings conn; u16 status; - - bool disabled; } link[IEEE80211_MLD_MAX_NUM_LINKS]; u8 ap_addr[ETH_ALEN] __aligned(2); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 0ca55b9655a7fc..72c129478da088 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -350,6 +350,8 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, /* we hold the RTNL here so can safely walk the list */ list_for_each_entry(nsdata, &local->interfaces, list) { if (nsdata != sdata && ieee80211_sdata_running(nsdata)) { + struct ieee80211_link_data *link; + /* * Only OCB and monitor mode may coexist */ @@ -376,8 +378,10 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, * will not add another interface while any channel * switch is active. */ - if (nsdata->vif.bss_conf.csa_active) - return -EBUSY; + for_each_link_data(nsdata, link) { + if (link->conf->csa_active) + return -EBUSY; + } /* * The remaining checks are only performed for interfaces diff --git a/net/mac80211/key.c b/net/mac80211/key.c index d5da7ccea66e0f..04c8809173d7f5 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -987,7 +987,8 @@ void ieee80211_reenable_keys(struct ieee80211_sub_if_data *sdata) if (ieee80211_sdata_running(sdata)) { list_for_each_entry(key, &sdata->key_list, list) { - increment_tailroom_need_count(sdata); + if (!(key->flags & KEY_FLAG_TAINTED)) + increment_tailroom_need_count(sdata); ieee80211_key_enable_hw_accel(key); } } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index f3138d15853533..8ba199cd38c0fe 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -8,7 +8,7 @@ * Copyright 2007, Michael Wu * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2025 Intel Corporation + * Copyright (C) 2018 - 2026 Intel Corporation */ #include @@ -1126,7 +1126,10 @@ ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata, while (!ieee80211_chandef_usable(sdata, &chanreq->oper, IEEE80211_CHAN_DISABLED)) { - if (WARN_ON(chanreq->oper.width == NL80211_CHAN_WIDTH_20_NOHT)) { + if (chanreq->oper.width == NL80211_CHAN_WIDTH_20_NOHT) { + link_id_info(sdata, link_id, + "unusable channel (%d MHz) for connection\n", + chanreq->oper.chan->center_freq); ret = -EINVAL; goto free; } @@ -6161,6 +6164,100 @@ static bool ieee80211_get_dtim(const struct cfg80211_bss_ies *ies, return true; } +static u16 ieee80211_get_ttlm(u8 bm_size, u8 *data) +{ + if (bm_size == 1) + return *data; + + return get_unaligned_le16(data); +} + +static int +ieee80211_parse_adv_t2l(struct ieee80211_sub_if_data *sdata, + const struct ieee80211_ttlm_elem *ttlm, + struct ieee80211_adv_ttlm_info *ttlm_info) +{ + /* The element size was already validated in + * ieee80211_tid_to_link_map_size_ok() + */ + u8 control, link_map_presence, map_size, tid; + u8 *pos; + + memset(ttlm_info, 0, sizeof(*ttlm_info)); + pos = (void *)ttlm->optional; + control = ttlm->control; + + if ((control & IEEE80211_TTLM_CONTROL_DIRECTION) != + IEEE80211_TTLM_DIRECTION_BOTH) { + sdata_info(sdata, "Invalid advertised T2L map direction\n"); + return -EINVAL; + } + + if (!(control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP)) { + link_map_presence = *pos; + pos++; + } + + if (control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT) { + ttlm_info->switch_time = get_unaligned_le16(pos); + + /* Since ttlm_info->switch_time == 0 means no switch time, bump + * it by 1. + */ + if (!ttlm_info->switch_time) + ttlm_info->switch_time = 1; + + pos += 2; + } + + if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) { + ttlm_info->duration = pos[0] | pos[1] << 8 | pos[2] << 16; + pos += 3; + } + + if (control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP) { + ttlm_info->map = 0xffff; + return 0; + } + + if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) + map_size = 1; + else + map_size = 2; + + /* According to Draft P802.11be_D3.0 clause 35.3.7.1.7, an AP MLD shall + * not advertise a TID-to-link mapping that does not map all TIDs to the + * same link set, reject frame if not all links have mapping + */ + if (link_map_presence != 0xff) { + sdata_info(sdata, + "Invalid advertised T2L mapping presence indicator\n"); + return -EINVAL; + } + + ttlm_info->map = ieee80211_get_ttlm(map_size, pos); + if (!ttlm_info->map) { + sdata_info(sdata, + "Invalid advertised T2L map for TID 0\n"); + return -EINVAL; + } + + pos += map_size; + + for (tid = 1; tid < 8; tid++) { + u16 map = ieee80211_get_ttlm(map_size, pos); + + if (map != ttlm_info->map) { + sdata_info(sdata, "Invalid advertised T2L map for tid %d\n", + tid); + return -EINVAL; + } + + pos += map_size; + } + return 0; +} + static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, struct ieee802_11_elems *elems, @@ -6192,8 +6289,6 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, continue; valid_links |= BIT(link_id); - if (assoc_data->link[link_id].disabled) - dormant_links |= BIT(link_id); if (link_id != assoc_data->assoc_link_id) { err = ieee80211_sta_allocate_link(sta, link_id); @@ -6202,6 +6297,33 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, } } + /* + * We do not support setting a negotiated TTLM during + * association. As such, we can assume that if there is a TTLM, + * then it is the currently active advertised TTLM. + * In that case, there must be exactly one TTLM that does not + * have a switch time set. This mapping should also leave us + * with at least one usable link. + */ + if (elems->ttlm_num > 1) { + sdata_info(sdata, + "More than one advertised TTLM in association response\n"); + goto out_err; + } else if (elems->ttlm_num == 1) { + if (ieee80211_parse_adv_t2l(sdata, elems->ttlm[0], + &sdata->u.mgd.ttlm_info) || + sdata->u.mgd.ttlm_info.switch_time != 0 || + !(valid_links & sdata->u.mgd.ttlm_info.map)) { + sdata_info(sdata, + "Invalid advertised TTLM in association response\n"); + goto out_err; + } + + sdata->u.mgd.ttlm_info.active = true; + dormant_links = + valid_links & ~sdata->u.mgd.ttlm_info.map; + } + ieee80211_vif_set_links(sdata, valid_links, dormant_links); } @@ -6991,95 +7113,6 @@ static void ieee80211_tid_to_link_map_work(struct wiphy *wiphy, sdata->u.mgd.ttlm_info.switch_time = 0; } -static u16 ieee80211_get_ttlm(u8 bm_size, u8 *data) -{ - if (bm_size == 1) - return *data; - else - return get_unaligned_le16(data); -} - -static int -ieee80211_parse_adv_t2l(struct ieee80211_sub_if_data *sdata, - const struct ieee80211_ttlm_elem *ttlm, - struct ieee80211_adv_ttlm_info *ttlm_info) -{ - /* The element size was already validated in - * ieee80211_tid_to_link_map_size_ok() - */ - u8 control, link_map_presence, map_size, tid; - u8 *pos; - - memset(ttlm_info, 0, sizeof(*ttlm_info)); - pos = (void *)ttlm->optional; - control = ttlm->control; - - if ((control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP) || - !(control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT)) - return 0; - - if ((control & IEEE80211_TTLM_CONTROL_DIRECTION) != - IEEE80211_TTLM_DIRECTION_BOTH) { - sdata_info(sdata, "Invalid advertised T2L map direction\n"); - return -EINVAL; - } - - link_map_presence = *pos; - pos++; - - ttlm_info->switch_time = get_unaligned_le16(pos); - - /* Since ttlm_info->switch_time == 0 means no switch time, bump it - * by 1. - */ - if (!ttlm_info->switch_time) - ttlm_info->switch_time = 1; - - pos += 2; - - if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) { - ttlm_info->duration = pos[0] | pos[1] << 8 | pos[2] << 16; - pos += 3; - } - - if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) - map_size = 1; - else - map_size = 2; - - /* According to Draft P802.11be_D3.0 clause 35.3.7.1.7, an AP MLD shall - * not advertise a TID-to-link mapping that does not map all TIDs to the - * same link set, reject frame if not all links have mapping - */ - if (link_map_presence != 0xff) { - sdata_info(sdata, - "Invalid advertised T2L mapping presence indicator\n"); - return -EINVAL; - } - - ttlm_info->map = ieee80211_get_ttlm(map_size, pos); - if (!ttlm_info->map) { - sdata_info(sdata, - "Invalid advertised T2L map for TID 0\n"); - return -EINVAL; - } - - pos += map_size; - - for (tid = 1; tid < 8; tid++) { - u16 map = ieee80211_get_ttlm(map_size, pos); - - if (map != ttlm_info->map) { - sdata_info(sdata, "Invalid advertised T2L map for tid %d\n", - tid); - return -EINVAL; - } - - pos += map_size; - } - return 0; -} - static void ieee80211_process_adv_ttlm(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems, u64 beacon_ts) @@ -9726,7 +9759,6 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, req, true, i, &assoc_data->link[i].conn); assoc_data->link[i].bss = link_cbss; - assoc_data->link[i].disabled = req->links[i].disabled; if (!bss->uapsd_supported) uapsd_supported = false; @@ -10708,8 +10740,6 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata, &data->link[link_id].conn); data->link[link_id].bss = link_cbss; - data->link[link_id].disabled = - req->add_links[link_id].disabled; data->link[link_id].elems = (u8 *)req->add_links[link_id].elems; data->link[link_id].elems_len = diff --git a/net/mac80211/ocb.c b/net/mac80211/ocb.c index a5d4358f122ae4..ebb4f4d88c237f 100644 --- a/net/mac80211/ocb.c +++ b/net/mac80211/ocb.c @@ -47,6 +47,9 @@ void ieee80211_ocb_rx_no_sta(struct ieee80211_sub_if_data *sdata, struct sta_info *sta; int band; + if (!ifocb->joined) + return; + /* XXX: Consider removing the least recently used entry and * allow new one to be added. */ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 5b4c3fe9970ad3..5091a3c15b0b49 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3428,6 +3428,11 @@ ieee80211_rx_h_mgmt_check(struct ieee80211_rx_data *rx) rx->skb->len < IEEE80211_MIN_ACTION_SIZE) return RX_DROP_U_RUNT_ACTION; + /* Drop non-broadcast Beacon frames */ + if (ieee80211_is_beacon(mgmt->frame_control) && + !is_broadcast_ether_addr(mgmt->da)) + return RX_DROP; + if (rx->sdata->vif.type == NL80211_IFTYPE_AP && ieee80211_is_beacon(mgmt->frame_control) && !(rx->flags & IEEE80211_RX_BEACON_REPORTED)) { diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index bb9563f50e7b47..1e06a465b49e36 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -343,8 +343,13 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) mgmt->da)) return; } else { - /* Beacons are expected only with broadcast address */ - if (!is_broadcast_ether_addr(mgmt->da)) + /* + * Non-S1G beacons are expected only with broadcast address. + * S1G beacons only carry the SA so no DA check is required + * nor possible. + */ + if (!ieee80211_is_s1g_beacon(mgmt->frame_control) && + !is_broadcast_ether_addr(mgmt->da)) return; } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f4d3b67fda062d..1a995bc301b19a 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1533,6 +1533,10 @@ static void __sta_info_destroy_part2(struct sta_info *sta, bool recalc) } } + sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL); + if (sinfo) + sta_set_sinfo(sta, sinfo, true); + if (sta->uploaded) { ret = drv_sta_state(local, sdata, sta, IEEE80211_STA_NONE, IEEE80211_STA_NOTEXIST); @@ -1541,9 +1545,6 @@ static void __sta_info_destroy_part2(struct sta_info *sta, bool recalc) sta_dbg(sdata, "Removed STA %pM\n", sta->sta.addr); - sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL); - if (sinfo) - sta_set_sinfo(sta, sinfo, true); cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL); kfree(sinfo); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index e7b141c55f7a90..160667be3f4d23 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2395,6 +2395,8 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, if (chanctx_conf) chandef = &chanctx_conf->def; + else if (local->emulate_chanctx) + chandef = &local->hw.conf.chandef; else goto fail_rcu; diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 40d5d9e4847916..bb0fa505cdcaee 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -869,8 +869,9 @@ ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx) /* * MIC = AES-128-CMAC(IGTK, AAD || Management Frame Body || MMIE, 64) */ - ieee80211_aes_cmac(key->u.aes_cmac.tfm, aad, - skb->data + 24, skb->len - 24, mmie->mic); + if (ieee80211_aes_cmac(key->u.aes_cmac.tfm, aad, + skb->data + 24, skb->len - 24, mmie->mic)) + return TX_DROP; return TX_CONTINUE; } @@ -916,8 +917,9 @@ ieee80211_crypto_aes_cmac_256_encrypt(struct ieee80211_tx_data *tx) /* MIC = AES-256-CMAC(IGTK, AAD || Management Frame Body || MMIE, 128) */ - ieee80211_aes_cmac_256(key->u.aes_cmac.tfm, aad, - skb->data + 24, skb->len - 24, mmie->mic); + if (ieee80211_aes_cmac_256(key->u.aes_cmac.tfm, aad, + skb->data + 24, skb->len - 24, mmie->mic)) + return TX_DROP; return TX_CONTINUE; } @@ -956,8 +958,9 @@ ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx) if (!(status->flag & RX_FLAG_DECRYPTED)) { /* hardware didn't decrypt/verify MIC */ bip_aad(skb, aad); - ieee80211_aes_cmac(key->u.aes_cmac.tfm, aad, - skb->data + 24, skb->len - 24, mic); + if (ieee80211_aes_cmac(key->u.aes_cmac.tfm, aad, + skb->data + 24, skb->len - 24, mic)) + return RX_DROP_U_DECRYPT_FAIL; if (crypto_memneq(mic, mmie->mic, sizeof(mmie->mic))) { key->u.aes_cmac.icverrors++; return RX_DROP_U_MIC_FAIL; @@ -1006,8 +1009,9 @@ ieee80211_crypto_aes_cmac_256_decrypt(struct ieee80211_rx_data *rx) if (!(status->flag & RX_FLAG_DECRYPTED)) { /* hardware didn't decrypt/verify MIC */ bip_aad(skb, aad); - ieee80211_aes_cmac_256(key->u.aes_cmac.tfm, aad, - skb->data + 24, skb->len - 24, mic); + if (ieee80211_aes_cmac_256(key->u.aes_cmac.tfm, aad, + skb->data + 24, skb->len - 24, mic)) + return RX_DROP_U_DECRYPT_FAIL; if (crypto_memneq(mic, mmie->mic, sizeof(mmie->mic))) { key->u.aes_cmac.icverrors++; return RX_DROP_U_MIC_FAIL; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index f24ae7d40e883a..43df4293f58bfb 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -408,6 +408,16 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, */ subflow->snd_isn = TCP_SKB_CB(skb)->end_seq; if (subflow->request_mptcp) { + if (unlikely(subflow_simultaneous_connect(sk))) { + WARN_ON_ONCE(!mptcp_try_fallback(sk, MPTCP_MIB_SIMULTCONNFALLBACK)); + + /* Ensure mptcp_finish_connect() will not process the + * MPC handshake. + */ + subflow->request_mptcp = 0; + return false; + } + opts->suboptions = OPTION_MPTCP_MPC_SYN; opts->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk)); opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk)); diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index 0a50fd5edc06db..1b517a81e02997 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -1276,16 +1276,26 @@ static void __reset_counters(struct pm_nl_pernet *pernet) int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); - LIST_HEAD(free_list); + struct list_head free_list; spin_lock_bh(&pernet->lock); - list_splice_init(&pernet->endp_list, &free_list); + free_list = pernet->endp_list; + INIT_LIST_HEAD_RCU(&pernet->endp_list); __reset_counters(pernet); pernet->next_id = 1; bitmap_zero(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); spin_unlock_bh(&pernet->lock); - mptcp_nl_flush_addrs_list(sock_net(skb->sk), &free_list); + + if (free_list.next == &pernet->endp_list) + return 0; + synchronize_rcu(); + + /* Adjust the pointers to free_list instead of pernet->endp_list */ + free_list.prev->next = &free_list; + free_list.next->prev = &free_list; + + mptcp_nl_flush_addrs_list(sock_net(skb->sk), &free_list); __flush_addrs(&free_list); return 0; } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index d5b383870f7995..7aa42de9c47b55 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -119,7 +119,8 @@ int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info, } if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) - entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]); + entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]) & + MPTCP_PM_ADDR_FLAGS_MASK; if (tb[MPTCP_PM_ADDR_ATTR_PORT]) entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 1e413426deeecf..8f18509204b675 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -224,9 +224,6 @@ static bool mptcp_rcvbuf_grow(struct sock *sk, u32 newval) do_div(grow, oldval); rcvwin += grow << 1; - if (!RB_EMPTY_ROOT(&msk->out_of_order_queue)) - rcvwin += MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq - msk->ack_seq; - cap = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]); rcvbuf = min_t(u32, mptcp_space_from_win(sk, rcvwin), cap); @@ -350,9 +347,6 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) end: skb_condense(skb); skb_set_owner_r(skb, sk); - /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */ - if (sk->sk_socket) - mptcp_rcvbuf_grow(sk, msk->rcvq_space.space); } static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset, @@ -784,11 +778,8 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) { - int err = sock_error(ssk); int ssk_state; - - if (!err) - return false; + int err; /* only propagate errors on fallen-back sockets or * on MPC connect @@ -796,6 +787,10 @@ static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(mptcp_sk(sk))) return false; + err = sock_error(ssk); + if (!err) + return false; + /* We need to propagate only transition to CLOSE state. * Orphaned socket will see such state change via * subflow_sched_work_if_closed() and that path will properly @@ -1597,7 +1592,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) struct mptcp_sendmsg_info info = { .flags = flags, }; - bool do_check_data_fin = false; + bool copied = false; int push_count = 1; while (mptcp_send_head(sk) && (push_count > 0)) { @@ -1639,7 +1634,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) push_count--; continue; } - do_check_data_fin = true; + copied = true; } } } @@ -1648,11 +1643,14 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) if (ssk) mptcp_push_release(ssk, &info); - /* ensure the rtx timer is running */ - if (!mptcp_rtx_timer_pending(sk)) - mptcp_reset_rtx_timer(sk); - if (do_check_data_fin) + /* Avoid scheduling the rtx timer if no data has been pushed; the timer + * will be updated on positive acks by __mptcp_cleanup_una(). + */ + if (copied) { + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); mptcp_check_send_data_fin(sk); + } } static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first) @@ -2058,8 +2056,8 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) msk->rcvq_space.copied += copied; - mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC); - time = tcp_stamp_us_delta(mstamp, msk->rcvq_space.time); + mstamp = mptcp_stamp(); + time = tcp_stamp_us_delta(mstamp, READ_ONCE(msk->rcvq_space.time)); rtt_us = msk->rcvq_space.rtt_us; if (rtt_us && time < (rtt_us >> 3)) @@ -2418,10 +2416,10 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) */ static void __mptcp_subflow_disconnect(struct sock *ssk, struct mptcp_subflow_context *subflow, - unsigned int flags) + bool fastclosing) { if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || - subflow->send_fastclose) { + fastclosing) { /* The MPTCP code never wait on the subflow sockets, TCP-level * disconnect should never fail */ @@ -2473,7 +2471,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { - __mptcp_subflow_disconnect(ssk, subflow, flags); + __mptcp_subflow_disconnect(ssk, subflow, msk->fastclosing); release_sock(ssk); goto out; @@ -2530,8 +2528,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow) { - /* The first subflow can already be closed and still in the list */ - if (subflow->close_event_done) + /* The first subflow can already be closed or disconnected */ + if (subflow->close_event_done || READ_ONCE(subflow->local_id) < 0) return; subflow->close_event_done = true; @@ -2690,10 +2688,13 @@ static void __mptcp_retrans(struct sock *sk) /* * make the whole retrans decision, xmit, disallow - * fallback atomic + * fallback atomic, note that we can't retrans even + * when an infinite fallback is in progress, i.e. new + * subflows are disallowed. */ spin_lock_bh(&msk->fallback_lock); - if (__mptcp_check_fallback(msk)) { + if (__mptcp_check_fallback(msk) || + !msk->allow_subflows) { spin_unlock_bh(&msk->fallback_lock); release_sock(ssk); goto clear_scheduled; @@ -2783,6 +2784,7 @@ static void mptcp_do_fastclose(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); mptcp_set_state(sk, TCP_CLOSE); + msk->fastclosing = 1; /* Explicitly send the fastclose reset as need */ if (__mptcp_check_fallback(msk)) @@ -3293,6 +3295,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->bytes_sent = 0; msk->bytes_retrans = 0; msk->rcvspace_init = 0; + msk->fastclosing = 0; WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); @@ -3418,6 +3421,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, __mptcp_propagate_sndbuf(nsk, ssk); mptcp_rcv_space_init(msk, ssk); + msk->rcvq_space.time = mptcp_stamp(); if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK) __mptcp_subflow_fully_established(msk, subflow, mp_opt); @@ -3435,8 +3439,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) msk->rcvq_space.copied = 0; msk->rcvq_space.rtt_us = 0; - msk->rcvq_space.time = tp->tcp_mstamp; - /* initial rcv_space offering made to peer */ msk->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND * tp->advmss); @@ -3649,6 +3651,7 @@ void mptcp_finish_connect(struct sock *ssk) * accessing the field below */ WRITE_ONCE(msk->local_key, subflow->local_key); + WRITE_ONCE(msk->rcvq_space.time, mptcp_stamp()); mptcp_pm_new_connection(msk, ssk, 0); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 6ca97096607c39..27b1698c5aa2d0 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -321,7 +321,8 @@ struct mptcp_sock { fastopening:1, in_accept_queue:1, free_first:1, - rcvspace_init:1; + rcvspace_init:1, + fastclosing:1; u32 notsent_lowat; int keepalive_cnt; int keepalive_idle; @@ -869,6 +870,11 @@ static inline bool mptcp_is_fully_established(struct sock *sk) READ_ONCE(mptcp_sk(sk)->fully_established); } +static inline u64 mptcp_stamp(void) +{ + return div_u64(tcp_clock_ns(), NSEC_PER_USEC); +} + void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk); void mptcp_data_ready(struct sock *sk, struct sock *ssk); bool mptcp_finish_join(struct sock *sk); @@ -1293,10 +1299,8 @@ static inline bool subflow_simultaneous_connect(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - return (1 << sk->sk_state) & - (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING) && - is_active_ssk(subflow) && - !subflow->conn_finished; + /* Note that the sk state implies !subflow->conn_finished. */ + return sk->sk_state == TCP_SYN_RECV && is_active_ssk(subflow); } #ifdef CONFIG_SYN_COOKIES diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index af707ce0f62445..a8c281bc53778c 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1856,12 +1856,6 @@ static void subflow_state_change(struct sock *sk) __subflow_state_change(sk); - if (subflow_simultaneous_connect(sk)) { - WARN_ON_ONCE(!mptcp_try_fallback(sk, MPTCP_MIB_SIMULTCONNFALLBACK)); - subflow->conn_finished = 1; - mptcp_propagate_state(parent, sk, subflow, NULL); - } - /* as recvmsg() does not acquire the subflow socket for ssk selection * a fin packet carrying a DSS can be unnoticed if we don't trigger * the data available machinery here. diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 95af252b29397d..ecbcdc43263d67 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -295,6 +295,12 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, return true; } +/* rt has device that is down */ +static bool rt_dev_is_down(const struct net_device *dev) +{ + return dev && !netif_running(dev); +} + /* Get route to destination or remote server */ static int __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, @@ -310,9 +316,11 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, if (dest) { dest_dst = __ip_vs_dst_check(dest); - if (likely(dest_dst)) + if (likely(dest_dst)) { rt = dst_rtable(dest_dst->dst_cache); - else { + if (ret_saddr) + *ret_saddr = dest_dst->dst_saddr.ip; + } else { dest_dst = ip_vs_dest_dst_alloc(); spin_lock_bh(&dest->dst_lock); if (!dest_dst) { @@ -328,14 +336,22 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, ip_vs_dest_dst_free(dest_dst); goto err_unreach; } - __ip_vs_dst_set(dest, dest_dst, &rt->dst, 0); + /* It is forbidden to attach dest->dest_dst if + * device is going down. + */ + if (!rt_dev_is_down(dst_dev_rcu(&rt->dst))) + __ip_vs_dst_set(dest, dest_dst, &rt->dst, 0); + else + noref = 0; spin_unlock_bh(&dest->dst_lock); IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d\n", &dest->addr.ip, &dest_dst->dst_saddr.ip, rcuref_read(&rt->dst.__rcuref)); + if (ret_saddr) + *ret_saddr = dest_dst->dst_saddr.ip; + if (!noref) + ip_vs_dest_dst_free(dest_dst); } - if (ret_saddr) - *ret_saddr = dest_dst->dst_saddr.ip; } else { noref = 0; @@ -409,6 +425,9 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, return -1; err_unreach: + if (!skb->dev) + skb->dev = skb_dst(skb)->dev; + dst_link_failure(skb); return -1; } @@ -469,9 +488,11 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, if (dest) { dest_dst = __ip_vs_dst_check(dest); - if (likely(dest_dst)) + if (likely(dest_dst)) { rt = dst_rt6_info(dest_dst->dst_cache); - else { + if (ret_saddr) + *ret_saddr = dest_dst->dst_saddr.in6; + } else { u32 cookie; dest_dst = ip_vs_dest_dst_alloc(); @@ -492,14 +513,22 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, } rt = dst_rt6_info(dst); cookie = rt6_get_cookie(rt); - __ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie); + /* It is forbidden to attach dest->dest_dst if + * device is going down. + */ + if (!rt_dev_is_down(dst_dev_rcu(&rt->dst))) + __ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie); + else + noref = 0; spin_unlock_bh(&dest->dst_lock); IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n", &dest->addr.in6, &dest_dst->dst_saddr.in6, rcuref_read(&rt->dst.__rcuref)); + if (ret_saddr) + *ret_saddr = dest_dst->dst_saddr.in6; + if (!noref) + ip_vs_dest_dst_free(dest_dst); } - if (ret_saddr) - *ret_saddr = dest_dst->dst_saddr.in6; } else { noref = 0; dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm, diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 913ede2f57f9a9..14e62b3263cd94 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -34,8 +34,9 @@ #define CONNCOUNT_SLOTS 256U -#define CONNCOUNT_GC_MAX_NODES 8 -#define MAX_KEYLEN 5 +#define CONNCOUNT_GC_MAX_NODES 8 +#define CONNCOUNT_GC_MAX_COLLECT 64 +#define MAX_KEYLEN 5 /* we will save the tuples of all connections we care about */ struct nf_conncount_tuple { @@ -122,32 +123,94 @@ find_or_evict(struct net *net, struct nf_conncount_list *list, return ERR_PTR(-EAGAIN); } +static bool get_ct_or_tuple_from_skb(struct net *net, + const struct sk_buff *skb, + u16 l3num, + struct nf_conn **ct, + struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone **zone, + bool *refcounted) +{ + const struct nf_conntrack_tuple_hash *h; + enum ip_conntrack_info ctinfo; + struct nf_conn *found_ct; + + found_ct = nf_ct_get(skb, &ctinfo); + if (found_ct && !nf_ct_is_template(found_ct)) { + *tuple = found_ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + *zone = nf_ct_zone(found_ct); + *ct = found_ct; + return true; + } + + if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), l3num, net, tuple)) + return false; + + if (found_ct) + *zone = nf_ct_zone(found_ct); + + h = nf_conntrack_find_get(net, *zone, tuple); + if (!h) + return true; + + found_ct = nf_ct_tuplehash_to_ctrack(h); + *refcounted = true; + *ct = found_ct; + + return true; +} + static int __nf_conncount_add(struct net *net, - struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone) + const struct sk_buff *skb, + u16 l3num, + struct nf_conncount_list *list) { + const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; const struct nf_conntrack_tuple_hash *found; struct nf_conncount_tuple *conn, *conn_n; + struct nf_conntrack_tuple tuple; + struct nf_conn *ct = NULL; struct nf_conn *found_ct; unsigned int collect = 0; + bool refcounted = false; + int err = 0; + + if (!get_ct_or_tuple_from_skb(net, skb, l3num, &ct, &tuple, &zone, &refcounted)) + return -ENOENT; + + if (ct && nf_ct_is_confirmed(ct)) { + /* local connections are confirmed in postrouting so confirmation + * might have happened before hitting connlimit + */ + if (skb->skb_iif != LOOPBACK_IFINDEX) { + err = -EEXIST; + goto out_put; + } + + /* this is likely a local connection, skip optimization to avoid + * adding duplicates from a 'packet train' + */ + goto check_connections; + } - if ((u32)jiffies == list->last_gc) + if ((u32)jiffies == list->last_gc && + (list->count - list->last_gc_count) < CONNCOUNT_GC_MAX_COLLECT) goto add_new_node; +check_connections: /* check the saved connections */ list_for_each_entry_safe(conn, conn_n, &list->head, node) { - if (collect > CONNCOUNT_GC_MAX_NODES) + if (collect > CONNCOUNT_GC_MAX_COLLECT) break; found = find_or_evict(net, list, conn); if (IS_ERR(found)) { /* Not found, but might be about to be confirmed */ if (PTR_ERR(found) == -EAGAIN) { - if (nf_ct_tuple_equal(&conn->tuple, tuple) && + if (nf_ct_tuple_equal(&conn->tuple, &tuple) && nf_ct_zone_id(&conn->zone, conn->zone.dir) == nf_ct_zone_id(zone, zone->dir)) - return 0; /* already exists */ + goto out_put; /* already exists */ } else { collect++; } @@ -156,7 +219,7 @@ static int __nf_conncount_add(struct net *net, found_ct = nf_ct_tuplehash_to_ctrack(found); - if (nf_ct_tuple_equal(&conn->tuple, tuple) && + if (nf_ct_tuple_equal(&conn->tuple, &tuple) && nf_ct_zone_equal(found_ct, zone, zone->dir)) { /* * We should not see tuples twice unless someone hooks @@ -165,7 +228,7 @@ static int __nf_conncount_add(struct net *net, * Attempt to avoid a re-add in this case. */ nf_ct_put(found_ct); - return 0; + goto out_put; } else if (already_closed(found_ct)) { /* * we do not care about connections which are @@ -179,53 +242,63 @@ static int __nf_conncount_add(struct net *net, nf_ct_put(found_ct); } + list->last_gc = (u32)jiffies; + list->last_gc_count = list->count; add_new_node: - if (WARN_ON_ONCE(list->count > INT_MAX)) - return -EOVERFLOW; + if (WARN_ON_ONCE(list->count > INT_MAX)) { + err = -EOVERFLOW; + goto out_put; + } conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC); - if (conn == NULL) - return -ENOMEM; + if (conn == NULL) { + err = -ENOMEM; + goto out_put; + } - conn->tuple = *tuple; + conn->tuple = tuple; conn->zone = *zone; conn->cpu = raw_smp_processor_id(); conn->jiffies32 = (u32)jiffies; list_add_tail(&conn->node, &list->head); list->count++; - list->last_gc = (u32)jiffies; - return 0; + +out_put: + if (refcounted) + nf_ct_put(ct); + return err; } -int nf_conncount_add(struct net *net, - struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone) +int nf_conncount_add_skb(struct net *net, + const struct sk_buff *skb, + u16 l3num, + struct nf_conncount_list *list) { int ret; /* check the saved connections */ spin_lock_bh(&list->list_lock); - ret = __nf_conncount_add(net, list, tuple, zone); + ret = __nf_conncount_add(net, skb, l3num, list); spin_unlock_bh(&list->list_lock); return ret; } -EXPORT_SYMBOL_GPL(nf_conncount_add); +EXPORT_SYMBOL_GPL(nf_conncount_add_skb); void nf_conncount_list_init(struct nf_conncount_list *list) { spin_lock_init(&list->list_lock); INIT_LIST_HEAD(&list->head); list->count = 0; + list->last_gc_count = 0; list->last_gc = (u32)jiffies; } EXPORT_SYMBOL_GPL(nf_conncount_list_init); /* Return true if the list is empty. Must be called with BH disabled. */ -bool nf_conncount_gc_list(struct net *net, - struct nf_conncount_list *list) +static bool __nf_conncount_gc_list(struct net *net, + struct nf_conncount_list *list) { const struct nf_conntrack_tuple_hash *found; struct nf_conncount_tuple *conn, *conn_n; @@ -237,10 +310,6 @@ bool nf_conncount_gc_list(struct net *net, if ((u32)jiffies == READ_ONCE(list->last_gc)) return false; - /* don't bother if other cpu is already doing GC */ - if (!spin_trylock(&list->list_lock)) - return false; - list_for_each_entry_safe(conn, conn_n, &list->head, node) { found = find_or_evict(net, list, conn); if (IS_ERR(found)) { @@ -262,14 +331,29 @@ bool nf_conncount_gc_list(struct net *net, } nf_ct_put(found_ct); - if (collected > CONNCOUNT_GC_MAX_NODES) + if (collected > CONNCOUNT_GC_MAX_COLLECT) break; } if (!list->count) ret = true; list->last_gc = (u32)jiffies; - spin_unlock(&list->list_lock); + list->last_gc_count = list->count; + + return ret; +} + +bool nf_conncount_gc_list(struct net *net, + struct nf_conncount_list *list) +{ + bool ret; + + /* don't bother if other cpu is already doing GC */ + if (!spin_trylock_bh(&list->list_lock)) + return false; + + ret = __nf_conncount_gc_list(net, list); + spin_unlock_bh(&list->list_lock); return ret; } @@ -309,19 +393,22 @@ static void schedule_gc_worker(struct nf_conncount_data *data, int tree) static unsigned int insert_tree(struct net *net, + const struct sk_buff *skb, + u16 l3num, struct nf_conncount_data *data, struct rb_root *root, unsigned int hash, - const u32 *key, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone) + const u32 *key) { struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES]; + const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; + bool do_gc = true, refcounted = false; + unsigned int count = 0, gc_count = 0; struct rb_node **rbnode, *parent; - struct nf_conncount_rb *rbconn; + struct nf_conntrack_tuple tuple; struct nf_conncount_tuple *conn; - unsigned int count = 0, gc_count = 0; - bool do_gc = true; + struct nf_conncount_rb *rbconn; + struct nf_conn *ct = NULL; spin_lock_bh(&nf_conncount_locks[hash]); restart: @@ -340,8 +427,8 @@ insert_tree(struct net *net, } else { int ret; - ret = nf_conncount_add(net, &rbconn->list, tuple, zone); - if (ret) + ret = nf_conncount_add_skb(net, skb, l3num, &rbconn->list); + if (ret && ret != -EEXIST) count = 0; /* hotdrop */ else count = rbconn->list.count; @@ -364,41 +451,45 @@ insert_tree(struct net *net, goto restart; } - /* expected case: match, insert new node */ - rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC); - if (rbconn == NULL) - goto out_unlock; + if (get_ct_or_tuple_from_skb(net, skb, l3num, &ct, &tuple, &zone, &refcounted)) { + /* expected case: match, insert new node */ + rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC); + if (rbconn == NULL) + goto out_unlock; - conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC); - if (conn == NULL) { - kmem_cache_free(conncount_rb_cachep, rbconn); - goto out_unlock; - } + conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC); + if (conn == NULL) { + kmem_cache_free(conncount_rb_cachep, rbconn); + goto out_unlock; + } - conn->tuple = *tuple; - conn->zone = *zone; - conn->cpu = raw_smp_processor_id(); - conn->jiffies32 = (u32)jiffies; - memcpy(rbconn->key, key, sizeof(u32) * data->keylen); + conn->tuple = tuple; + conn->zone = *zone; + conn->cpu = raw_smp_processor_id(); + conn->jiffies32 = (u32)jiffies; + memcpy(rbconn->key, key, sizeof(u32) * data->keylen); - nf_conncount_list_init(&rbconn->list); - list_add(&conn->node, &rbconn->list.head); - count = 1; - rbconn->list.count = count; + nf_conncount_list_init(&rbconn->list); + list_add(&conn->node, &rbconn->list.head); + count = 1; + rbconn->list.count = count; - rb_link_node_rcu(&rbconn->node, parent, rbnode); - rb_insert_color(&rbconn->node, root); + rb_link_node_rcu(&rbconn->node, parent, rbnode); + rb_insert_color(&rbconn->node, root); + } out_unlock: + if (refcounted) + nf_ct_put(ct); spin_unlock_bh(&nf_conncount_locks[hash]); return count; } static unsigned int count_tree(struct net *net, + const struct sk_buff *skb, + u16 l3num, struct nf_conncount_data *data, - const u32 *key, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone) + const u32 *key) { struct rb_root *root; struct rb_node *parent; @@ -422,7 +513,7 @@ count_tree(struct net *net, } else { int ret; - if (!tuple) { + if (!skb) { nf_conncount_gc_list(net, &rbconn->list); return rbconn->list.count; } @@ -437,19 +528,23 @@ count_tree(struct net *net, } /* same source network -> be counted! */ - ret = __nf_conncount_add(net, &rbconn->list, tuple, zone); + ret = __nf_conncount_add(net, skb, l3num, &rbconn->list); spin_unlock_bh(&rbconn->list.list_lock); - if (ret) + if (ret && ret != -EEXIST) { return 0; /* hotdrop */ - else + } else { + /* -EEXIST means add was skipped, update the list */ + if (ret == -EEXIST) + nf_conncount_gc_list(net, &rbconn->list); return rbconn->list.count; + } } } - if (!tuple) + if (!skb) return 0; - return insert_tree(net, data, root, hash, key, tuple, zone); + return insert_tree(net, skb, l3num, data, root, hash, key); } static void tree_gc_worker(struct work_struct *work) @@ -511,18 +606,19 @@ static void tree_gc_worker(struct work_struct *work) } /* Count and return number of conntrack entries in 'net' with particular 'key'. - * If 'tuple' is not null, insert it into the accounting data structure. - * Call with RCU read lock. + * If 'skb' is not null, insert the corresponding tuple into the accounting + * data structure. Call with RCU read lock. */ -unsigned int nf_conncount_count(struct net *net, - struct nf_conncount_data *data, - const u32 *key, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone) +unsigned int nf_conncount_count_skb(struct net *net, + const struct sk_buff *skb, + u16 l3num, + struct nf_conncount_data *data, + const u32 *key) { - return count_tree(net, data, key, tuple, zone); + return count_tree(net, skb, l3num, data, key); + } -EXPORT_SYMBOL_GPL(nf_conncount_count); +EXPORT_SYMBOL_GPL(nf_conncount_count_skb); struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int keylen) { diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 14f73872f64778..e35814d68ce30b 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -1186,13 +1186,13 @@ static struct nf_conntrack_expect *find_expect(struct nf_conn *ct, { struct net *net = nf_ct_net(ct); struct nf_conntrack_expect *exp; - struct nf_conntrack_tuple tuple; + struct nf_conntrack_tuple tuple = { + .src.l3num = nf_ct_l3num(ct), + .dst.protonum = IPPROTO_TCP, + .dst.u.tcp.port = port, + }; - memset(&tuple.src.u3, 0, sizeof(tuple.src.u3)); - tuple.src.u.tcp.port = 0; memcpy(&tuple.dst.u3, addr, sizeof(tuple.dst.u3)); - tuple.dst.u.tcp.port = port; - tuple.dst.protonum = IPPROTO_TCP; exp = __nf_ct_expect_find(net, nf_ct_zone(ct), &tuple); if (exp && exp->master == ct) diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 74cef8bf554c55..62cf6a30875e39 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -89,7 +89,7 @@ int nf_log_register(u_int8_t pf, struct nf_logger *logger) if (pf == NFPROTO_UNSPEC) { for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) { if (rcu_access_pointer(loggers[i][logger->type])) { - ret = -EEXIST; + ret = -EBUSY; goto unlock; } } @@ -97,7 +97,7 @@ int nf_log_register(u_int8_t pf, struct nf_logger *logger) rcu_assign_pointer(loggers[i][logger->type], logger); } else { if (rcu_access_pointer(loggers[pf][logger->type])) { - ret = -EEXIST; + ret = -EBUSY; goto unlock; } rcu_assign_pointer(loggers[pf][logger->type], logger); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 78a61dac4ade82..e6b24586d2fed5 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -294,25 +294,13 @@ nf_nat_used_tuple_new(const struct nf_conntrack_tuple *tuple, ct = nf_ct_tuplehash_to_ctrack(thash); - /* NB: IP_CT_DIR_ORIGINAL should be impossible because - * nf_nat_used_tuple() handles origin collisions. - * - * Handle remote chance other CPU confirmed its ct right after. - */ - if (thash->tuple.dst.dir != IP_CT_DIR_REPLY) - goto out; - /* clashing connection subject to NAT? Retry with new tuple. */ if (READ_ONCE(ct->status) & uses_nat) goto out; if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, - &ignored_ct->tuplehash[IP_CT_DIR_REPLY].tuple) && - nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, - &ignored_ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)) { + &ignored_ct->tuplehash[IP_CT_DIR_REPLY].tuple)) taken = false; - goto out; - } out: nf_ct_put(ct); return taken; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index eed434e0a9702e..d4babc4d3bff38 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -123,6 +123,29 @@ static void nft_validate_state_update(struct nft_table *table, u8 new_validate_s table->validate_state = new_validate_state; } + +static bool nft_chain_vstate_valid(const struct nft_ctx *ctx, + const struct nft_chain *chain) +{ + const struct nft_base_chain *base_chain; + enum nft_chain_types type; + u8 hooknum; + + if (WARN_ON_ONCE(!nft_is_base_chain(ctx->chain))) + return false; + + base_chain = nft_base_chain(ctx->chain); + hooknum = base_chain->ops.hooknum; + type = base_chain->type->type; + + /* chain is already validated for this call depth */ + if (chain->vstate.depth >= ctx->level && + chain->vstate.hook_mask[type] & BIT(hooknum)) + return true; + + return false; +} + static void nf_tables_trans_destroy_work(struct work_struct *w); static void nft_trans_gc_work(struct work_struct *work); @@ -2799,6 +2822,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 policy, err_register_hook: nft_chain_del(chain); + synchronize_rcu(); err_chain_add: nft_trans_destroy(trans); err_trans: @@ -4079,6 +4103,29 @@ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *r nf_tables_rule_destroy(ctx, rule); } +static void nft_chain_vstate_update(const struct nft_ctx *ctx, struct nft_chain *chain) +{ + const struct nft_base_chain *base_chain; + enum nft_chain_types type; + u8 hooknum; + + /* ctx->chain must hold the calling base chain. */ + if (WARN_ON_ONCE(!nft_is_base_chain(ctx->chain))) { + memset(&chain->vstate, 0, sizeof(chain->vstate)); + return; + } + + base_chain = nft_base_chain(ctx->chain); + hooknum = base_chain->ops.hooknum; + type = base_chain->type->type; + + BUILD_BUG_ON(BIT(NF_INET_NUMHOOKS) > U8_MAX); + + chain->vstate.hook_mask[type] |= BIT(hooknum); + if (chain->vstate.depth < ctx->level) + chain->vstate.depth = ctx->level; +} + /** nft_chain_validate - loop detection and hook validation * * @ctx: context containing call depth and base chain @@ -4088,15 +4135,25 @@ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *r * and set lookups until either the jump limit is hit or all reachable * chains have been validated. */ -int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) +int nft_chain_validate(const struct nft_ctx *ctx, struct nft_chain *chain) { struct nft_expr *expr, *last; struct nft_rule *rule; int err; + BUILD_BUG_ON(NFT_JUMP_STACK_SIZE > 255); if (ctx->level == NFT_JUMP_STACK_SIZE) return -EMLINK; + if (ctx->level > 0) { + /* jumps to base chains are not allowed. */ + if (nft_is_base_chain(chain)) + return -ELOOP; + + if (nft_chain_vstate_valid(ctx, chain)) + return 0; + } + list_for_each_entry(rule, &chain->rules, list) { if (fatal_signal_pending(current)) return -EINTR; @@ -4117,6 +4174,7 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) } } + nft_chain_vstate_update(ctx, chain); return 0; } EXPORT_SYMBOL_GPL(nft_chain_validate); @@ -4128,7 +4186,7 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) .net = net, .family = table->family, }; - int err; + int err = 0; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain)) @@ -4137,12 +4195,16 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) ctx.chain = chain; err = nft_chain_validate(&ctx, chain); if (err < 0) - return err; + goto err; cond_resched(); } - return 0; +err: + list_for_each_entry(chain, &table->chains, list) + memset(&chain->vstate, 0, sizeof(chain->vstate)); + + return err; } int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, @@ -4378,7 +4440,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, if (!nft_use_inc(&chain->use)) { err = -EMFILE; - goto err_release_rule; + goto err_destroy_flow; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { @@ -4428,6 +4490,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, err_destroy_flow_rule: nft_use_dec_restore(&chain->use); +err_destroy_flow: if (flow) nft_flow_rule_destroy(flow); err_release_rule: @@ -5855,7 +5918,7 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask)) + if (nft_set_elem_active(ext, genmask)) continue; nft_clear(ctx->net, ext); @@ -7209,7 +7272,8 @@ static u32 nft_set_maxsize(const struct nft_set *set) } static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, - const struct nlattr *attr, u32 nlmsg_flags) + const struct nlattr *attr, u32 nlmsg_flags, + bool last) { struct nft_expr *expr_array[NFT_SET_EXPR_MAX] = {}; struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; @@ -7495,6 +7559,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (flags) *nft_set_ext_flags(ext) = flags; + if (last) + elem.flags = NFT_SET_ELEM_INTERNAL_LAST; + else + elem.flags = 0; + if (obj) *nft_set_ext_obj(ext) = obj; @@ -7575,6 +7644,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, * and an existing one. */ err = -EEXIST; + } else if (err == -ECANCELED) { + /* ECANCELED reports an existing nul-element in + * interval sets. + */ + err = 0; } goto err_element_clash; } @@ -7653,7 +7727,8 @@ static int nf_tables_newsetelem(struct sk_buff *skb, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { - err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags); + err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags, + nla_is_last(attr, rem)); if (err < 0) { NL_SET_BAD_ATTR(extack, attr); return err; @@ -7746,7 +7821,8 @@ static bool nft_trans_elems_new_abort(const struct nft_ctx *ctx, continue; } - if (!te->set->ops->abort || nft_setelem_is_catchall(te->set, te->elems[i].priv)) + if (!te->set->ops->abort_skip_removal || + nft_setelem_is_catchall(te->set, te->elems[i].priv)) nft_setelem_remove(ctx->net, te->set, te->elems[i].priv); if (!nft_setelem_is_catchall(te->set, te->elems[i].priv)) @@ -7776,7 +7852,7 @@ static void nft_trans_elems_destroy_abort(const struct nft_ctx *ctx, } static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, - const struct nlattr *attr) + const struct nlattr *attr, bool last) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; struct nft_set_ext_tmpl tmpl; @@ -7844,6 +7920,11 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (flags) *nft_set_ext_flags(ext) = flags; + if (last) + elem.flags = NFT_SET_ELEM_INTERNAL_LAST; + else + elem.flags = 0; + trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set); if (trans == NULL) goto fail_trans; @@ -7991,7 +8072,8 @@ static int nf_tables_delsetelem(struct sk_buff *skb, return nft_set_flush(&ctx, set, genmask); nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { - err = nft_del_setelem(&ctx, set, attr); + err = nft_del_setelem(&ctx, set, attr, + nla_is_last(attr, rem)); if (err == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYSETELEM) continue; @@ -11476,6 +11558,13 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb, ret = __nf_tables_abort(net, action); nft_gc_seq_end(nft_net, gc_seq); + if (action == NFNL_ABORT_NONE) { + struct nft_table *table; + + list_for_each_entry(table, &nft_net->tables, list) + table->validate_state = NFT_VALIDATE_SKIP; + } + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); /* module autoload needs to happen after GC sequence update because it @@ -11678,21 +11767,10 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, enum nft_data_types type, unsigned int len) { - int err; - switch (reg) { case NFT_REG_VERDICT: if (type != NFT_DATA_VERDICT) return -EINVAL; - - if (data != NULL && - (data->verdict.code == NFT_GOTO || - data->verdict.code == NFT_JUMP)) { - err = nft_chain_validate(ctx, data->verdict.chain); - if (err < 0) - return err; - } - break; default: if (type != NFT_DATA_VALUE) diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 8b7b39d8a10913..34548213f2f14f 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -30,6 +30,8 @@ #include #include #include +#include +#include #include #include #include @@ -47,6 +49,8 @@ #endif #define NFQNL_QMAX_DEFAULT 1024 +#define NFQNL_HASH_MIN 1024 +#define NFQNL_HASH_MAX 1048576 /* We're using struct nlattr which has 16bit nla_len. Note that nla_len * includes the header length. Thus, the maximum packet length that we @@ -56,6 +60,26 @@ */ #define NFQNL_MAX_COPY_RANGE (0xffff - NLA_HDRLEN) +/* Composite key for packet lookup: (net, queue_num, packet_id) */ +struct nfqnl_packet_key { + possible_net_t net; + u32 packet_id; + u16 queue_num; +} __aligned(sizeof(u32)); /* jhash2 requires 32-bit alignment */ + +/* Global rhashtable - one for entire system, all netns */ +static struct rhashtable nfqnl_packet_map __read_mostly; + +/* Helper to initialize composite key */ +static inline void nfqnl_init_key(struct nfqnl_packet_key *key, + struct net *net, u32 packet_id, u16 queue_num) +{ + memset(key, 0, sizeof(*key)); + write_pnet(&key->net, net); + key->packet_id = packet_id; + key->queue_num = queue_num; +} + struct nfqnl_instance { struct hlist_node hlist; /* global list of queues */ struct rcu_head rcu; @@ -100,6 +124,39 @@ static inline u_int8_t instance_hashfn(u_int16_t queue_num) return ((queue_num >> 8) ^ queue_num) % INSTANCE_BUCKETS; } +/* Extract composite key from nf_queue_entry for hashing */ +static u32 nfqnl_packet_obj_hashfn(const void *data, u32 len, u32 seed) +{ + const struct nf_queue_entry *entry = data; + struct nfqnl_packet_key key; + + nfqnl_init_key(&key, entry->state.net, entry->id, entry->queue_num); + + return jhash2((u32 *)&key, sizeof(key) / sizeof(u32), seed); +} + +/* Compare stack-allocated key against entry */ +static int nfqnl_packet_obj_cmpfn(struct rhashtable_compare_arg *arg, + const void *obj) +{ + const struct nfqnl_packet_key *key = arg->key; + const struct nf_queue_entry *entry = obj; + + return !net_eq(entry->state.net, read_pnet(&key->net)) || + entry->queue_num != key->queue_num || + entry->id != key->packet_id; +} + +static const struct rhashtable_params nfqnl_rhashtable_params = { + .head_offset = offsetof(struct nf_queue_entry, hash_node), + .key_len = sizeof(struct nfqnl_packet_key), + .obj_hashfn = nfqnl_packet_obj_hashfn, + .obj_cmpfn = nfqnl_packet_obj_cmpfn, + .automatic_shrinking = true, + .min_size = NFQNL_HASH_MIN, + .max_size = NFQNL_HASH_MAX, +}; + static struct nfqnl_instance * instance_lookup(struct nfnl_queue_net *q, u_int16_t queue_num) { @@ -191,33 +248,45 @@ instance_destroy(struct nfnl_queue_net *q, struct nfqnl_instance *inst) spin_unlock(&q->instances_lock); } -static inline void +static int __enqueue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry) { - list_add_tail(&entry->list, &queue->queue_list); - queue->queue_total++; + int err; + + entry->queue_num = queue->queue_num; + + err = rhashtable_insert_fast(&nfqnl_packet_map, &entry->hash_node, + nfqnl_rhashtable_params); + if (unlikely(err)) + return err; + + list_add_tail(&entry->list, &queue->queue_list); + queue->queue_total++; + + return 0; } static void __dequeue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry) { + rhashtable_remove_fast(&nfqnl_packet_map, &entry->hash_node, + nfqnl_rhashtable_params); list_del(&entry->list); queue->queue_total--; } static struct nf_queue_entry * -find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id) +find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id, + struct net *net) { - struct nf_queue_entry *entry = NULL, *i; + struct nfqnl_packet_key key; + struct nf_queue_entry *entry; - spin_lock_bh(&queue->lock); + nfqnl_init_key(&key, net, id, queue->queue_num); - list_for_each_entry(i, &queue->queue_list, list) { - if (i->id == id) { - entry = i; - break; - } - } + spin_lock_bh(&queue->lock); + entry = rhashtable_lookup_fast(&nfqnl_packet_map, &key, + nfqnl_rhashtable_params); if (entry) __dequeue_entry(queue, entry); @@ -369,6 +438,34 @@ static void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) nf_queue_entry_free(entry); } +/* return true if the entry has an unconfirmed conntrack attached that isn't owned by us + * exclusively. + */ +static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry, bool *is_unconfirmed) +{ +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + struct nf_conn *ct = (void *)skb_nfct(entry->skb); + + if (!ct || nf_ct_is_confirmed(ct)) + return false; + + if (is_unconfirmed) + *is_unconfirmed = true; + + /* in some cases skb_clone() can occur after initial conntrack + * pickup, but conntrack assumes exclusive skb->_nfct ownership for + * unconfirmed entries. + * + * This happens for br_netfilter and with ip multicast routing. + * This can't be solved with serialization here because one clone + * could have been queued for local delivery or could be transmitted + * in parallel on another CPU. + */ + return refcount_read(&ct->ct_general.use) > 1; +#endif + return false; +} + static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) { const struct nf_ct_hook *ct_hook; @@ -396,6 +493,24 @@ static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) break; } } + + if (verdict != NF_DROP && entry->nf_ct_is_unconfirmed) { + /* If first queued segment was already reinjected then + * there is a good chance the ct entry is now confirmed. + * + * Handle the rare cases: + * - out-of-order verdict + * - threaded userspace reinjecting in parallel + * - first segment was dropped + * + * In all of those cases we can't handle this packet + * because we can't be sure that another CPU won't modify + * nf_conn->ext in parallel which isn't allowed. + */ + if (nf_ct_drop_unconfirmed(entry, NULL)) + verdict = NF_DROP; + } + nf_reinject(entry, verdict); } @@ -407,8 +522,7 @@ nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data) spin_lock_bh(&queue->lock); list_for_each_entry_safe(entry, next, &queue->queue_list, list) { if (!cmpfn || cmpfn(entry, data)) { - list_del(&entry->list); - queue->queue_total--; + __dequeue_entry(queue, entry); nfqnl_reinject(entry, NF_DROP); } } @@ -826,49 +940,6 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, return NULL; } -static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry) -{ -#if IS_ENABLED(CONFIG_NF_CONNTRACK) - static const unsigned long flags = IPS_CONFIRMED | IPS_DYING; - struct nf_conn *ct = (void *)skb_nfct(entry->skb); - unsigned long status; - unsigned int use; - - if (!ct) - return false; - - status = READ_ONCE(ct->status); - if ((status & flags) == IPS_DYING) - return true; - - if (status & IPS_CONFIRMED) - return false; - - /* in some cases skb_clone() can occur after initial conntrack - * pickup, but conntrack assumes exclusive skb->_nfct ownership for - * unconfirmed entries. - * - * This happens for br_netfilter and with ip multicast routing. - * We can't be solved with serialization here because one clone could - * have been queued for local delivery. - */ - use = refcount_read(&ct->ct_general.use); - if (likely(use == 1)) - return false; - - /* Can't decrement further? Exclusive ownership. */ - if (!refcount_dec_not_one(&ct->ct_general.use)) - return false; - - skb_set_nfct(entry->skb, 0); - /* No nf_ct_put(): we already decremented .use and it cannot - * drop down to 0. - */ - return true; -#endif - return false; -} - static int __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry) @@ -885,26 +956,23 @@ __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue, } spin_lock_bh(&queue->lock); - if (nf_ct_drop_unconfirmed(entry)) - goto err_out_free_nskb; + if (queue->queue_total >= queue->queue_maxlen) + goto err_out_queue_drop; - if (queue->queue_total >= queue->queue_maxlen) { - if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { - failopen = 1; - err = 0; - } else { - queue->queue_dropped++; - net_warn_ratelimited("nf_queue: full at %d entries, dropping packets(s)\n", - queue->queue_total); - } - goto err_out_free_nskb; - } entry->id = ++queue->id_sequence; *packet_id_ptr = htonl(entry->id); + /* Insert into hash BEFORE unicast. If failure don't send to userspace. */ + err = __enqueue_entry(queue, entry); + if (unlikely(err)) + goto err_out_queue_drop; + /* nfnetlink_unicast will either free the nskb or add it to a socket */ err = nfnetlink_unicast(nskb, net, queue->peer_portid); if (err < 0) { + /* Unicast failed - remove entry we just inserted */ + __dequeue_entry(queue, entry); + if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { failopen = 1; err = 0; @@ -914,12 +982,22 @@ __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue, goto err_out_unlock; } - __enqueue_entry(queue, entry); - spin_unlock_bh(&queue->lock); return 0; -err_out_free_nskb: +err_out_queue_drop: + if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { + failopen = 1; + err = 0; + } else { + queue->queue_dropped++; + + if (queue->queue_total >= queue->queue_maxlen) + net_warn_ratelimited("nf_queue: full at %d entries, dropping packets(s)\n", + queue->queue_total); + else + net_warn_ratelimited("nf_queue: hash insert failed: %d\n", err); + } kfree_skb(nskb); err_out_unlock: spin_unlock_bh(&queue->lock); @@ -998,9 +1076,10 @@ __nfqnl_enqueue_packet_gso(struct net *net, struct nfqnl_instance *queue, static int nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) { - unsigned int queued; - struct nfqnl_instance *queue; struct sk_buff *skb, *segs, *nskb; + bool ct_is_unconfirmed = false; + struct nfqnl_instance *queue; + unsigned int queued; int err = -ENOBUFS; struct net *net = entry->state.net; struct nfnl_queue_net *q = nfnl_queue_pernet(net); @@ -1024,6 +1103,15 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) break; } + /* Check if someone already holds another reference to + * unconfirmed ct. If so, we cannot queue the skb: + * concurrent modifications of nf_conn->ext are not + * allowed and we can't know if another CPU isn't + * processing the same nf_conn entry in parallel. + */ + if (nf_ct_drop_unconfirmed(entry, &ct_is_unconfirmed)) + return -EINVAL; + if (!skb_is_gso(skb) || ((queue->flags & NFQA_CFG_F_GSO) && !skb_is_gso_sctp(skb))) return __nfqnl_enqueue_packet(net, queue, entry); @@ -1037,7 +1125,23 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) goto out_err; queued = 0; err = 0; + skb_list_walk_safe(segs, segs, nskb) { + if (ct_is_unconfirmed && queued > 0) { + /* skb_gso_segment() increments the ct refcount. + * This is a problem for unconfirmed (not in hash) + * entries, those can race when reinjections happen + * in parallel. + * + * Annotate this for all queued entries except the + * first one. + * + * As long as the first one is reinjected first it + * will do the confirmation for us. + */ + entry->nf_ct_is_unconfirmed = ct_is_unconfirmed; + } + if (err == 0) err = __nfqnl_enqueue_packet_gso(net, queue, segs, entry); @@ -1430,7 +1534,7 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info, verdict = ntohl(vhdr->verdict); - entry = find_dequeue_entry(queue, ntohl(vhdr->id)); + entry = find_dequeue_entry(queue, ntohl(vhdr->id), info->net); if (entry == NULL) return -ENOENT; @@ -1781,10 +1885,14 @@ static int __init nfnetlink_queue_init(void) { int status; + status = rhashtable_init(&nfqnl_packet_map, &nfqnl_rhashtable_params); + if (status < 0) + return status; + status = register_pernet_subsys(&nfnl_queue_net_ops); if (status < 0) { pr_err("failed to register pernet ops\n"); - goto out; + goto cleanup_rhashtable; } netlink_register_notifier(&nfqnl_rtnl_notifier); @@ -1809,7 +1917,8 @@ static int __init nfnetlink_queue_init(void) cleanup_netlink_notifier: netlink_unregister_notifier(&nfqnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_queue_net_ops); -out: +cleanup_rhashtable: + rhashtable_destroy(&nfqnl_packet_map); return status; } @@ -1821,6 +1930,8 @@ static void __exit nfnetlink_queue_fini(void) netlink_unregister_notifier(&nfqnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_queue_net_ops); + rhashtable_destroy(&nfqnl_packet_map); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 72711d62fddfa4..08f620311b03f1 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -134,7 +134,8 @@ static void nft_target_eval_bridge(const struct nft_expr *expr, } static const struct nla_policy nft_target_policy[NFTA_TARGET_MAX + 1] = { - [NFTA_TARGET_NAME] = { .type = NLA_NUL_STRING }, + [NFTA_TARGET_NAME] = { .type = NLA_NUL_STRING, + .len = XT_EXTENSION_MAXNAMELEN, }, [NFTA_TARGET_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_TARGET_INFO] = { .type = NLA_BINARY }, }; @@ -434,7 +435,8 @@ static void nft_match_eval(const struct nft_expr *expr, } static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = { - [NFTA_MATCH_NAME] = { .type = NLA_NUL_STRING }, + [NFTA_MATCH_NAME] = { .type = NLA_NUL_STRING, + .len = XT_EXTENSION_MAXNAMELEN }, [NFTA_MATCH_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_MATCH_INFO] = { .type = NLA_BINARY }, }; @@ -693,7 +695,12 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, name = nla_data(tb[NFTA_COMPAT_NAME]); rev = ntohl(nla_get_be32(tb[NFTA_COMPAT_REV])); - target = ntohl(nla_get_be32(tb[NFTA_COMPAT_TYPE])); + /* x_tables api checks for 'target == 1' to mean target, + * everything else means 'match'. + * In x_tables world, the number is set by kernel, not + * userspace. + */ + target = nla_get_be32(tb[NFTA_COMPAT_TYPE]) == htonl(1); switch(family) { case AF_INET: diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index fc35a11cdca209..714a594859357f 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -24,28 +24,22 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, const struct nft_pktinfo *pkt, const struct nft_set_ext *ext) { - const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; - const struct nf_conntrack_tuple *tuple_ptr; - struct nf_conntrack_tuple tuple; - enum ip_conntrack_info ctinfo; - const struct nf_conn *ct; unsigned int count; + int err; - tuple_ptr = &tuple; - - ct = nf_ct_get(pkt->skb, &ctinfo); - if (ct != NULL) { - tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; - zone = nf_ct_zone(ct); - } else if (!nf_ct_get_tuplepr(pkt->skb, skb_network_offset(pkt->skb), - nft_pf(pkt), nft_net(pkt), &tuple)) { - regs->verdict.code = NF_DROP; - return; - } - - if (nf_conncount_add(nft_net(pkt), priv->list, tuple_ptr, zone)) { - regs->verdict.code = NF_DROP; - return; + err = nf_conncount_add_skb(nft_net(pkt), pkt->skb, nft_pf(pkt), priv->list); + if (err) { + if (err == -EEXIST) { + /* Call gc to update the list count if any connection has + * been closed already. This is useful for softlimit + * connections like limiting bandwidth based on a number + * of open connections. + */ + nf_conncount_gc_list(nft_net(pkt), priv->list); + } else { + regs->verdict.code = NF_DROP; + return; + } } count = READ_ONCE(priv->list->count); @@ -238,13 +232,8 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx, static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr) { struct nft_connlimit *priv = nft_expr_priv(expr); - bool ret; - - local_bh_disable(); - ret = nf_conncount_gc_list(net, priv->list); - local_bh_enable(); - return ret; + return nf_conncount_gc_list(net, priv->list); } static struct nft_expr_type nft_connlimit_type; diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index cc732532949630..0d70325280cc57 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -117,8 +117,8 @@ static void nft_counter_reset(struct nft_counter_percpu_priv *priv, nft_sync = this_cpu_ptr(&nft_counter_sync); u64_stats_update_begin(nft_sync); - u64_stats_add(&this_cpu->packets, -total->packets); - u64_stats_add(&this_cpu->bytes, -total->bytes); + u64_stats_sub(&this_cpu->packets, total->packets); + u64_stats_sub(&this_cpu->bytes, total->bytes); u64_stats_update_end(nft_sync); local_bh_enable(); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 14dd1c0698c3c9..e95e5f59a3d6a3 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -141,12 +141,19 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack, info->ingress_vlans |= BIT(info->num_encaps - 1); break; case DEV_PATH_BR_VLAN_TAG: + if (info->num_encaps >= NF_FLOW_TABLE_ENCAP_MAX) { + info->indev = NULL; + break; + } info->encap[info->num_encaps].id = path->bridge.vlan_id; info->encap[info->num_encaps].proto = path->bridge.vlan_proto; info->num_encaps++; break; case DEV_PATH_BR_VLAN_UNTAG: - info->num_encaps--; + if (WARN_ON_ONCE(info->num_encaps-- == 0)) { + info->indev = NULL; + break; + } break; case DEV_PATH_BR_VLAN_KEEP: break; diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index ba01ce75d6dea9..739b992bde591e 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -619,15 +619,20 @@ static struct nft_elem_priv * nft_hash_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { + const u32 *key = (const u32 *)&elem->key.val; struct nft_hash *priv = nft_set_priv(set); u8 genmask = nft_genmask_cur(net); struct nft_hash_elem *he; u32 hash; - hash = jhash(elem->key.val.data, set->klen, priv->seed); + if (set->klen == 4) + hash = jhash_1word(*key, priv->seed); + else + hash = jhash(key, set->klen, priv->seed); + hash = reciprocal_scale(hash, priv->buckets); hlist_for_each_entry_rcu(he, &priv->table[hash], node) { - if (!memcmp(nft_set_ext_key(&he->ext), elem->key.val.data, set->klen) && + if (!memcmp(nft_set_ext_key(&he->ext), key, set->klen) && nft_set_elem_active(&he->ext, genmask)) return &he->priv; } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 112fe46788b6fb..18e1903b1d3d0b 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1317,8 +1317,8 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, else dup_end = dup_key; - if (!memcmp(start, dup_key->data, sizeof(*dup_key->data)) && - !memcmp(end, dup_end->data, sizeof(*dup_end->data))) { + if (!memcmp(start, dup_key->data, set->klen) && + !memcmp(end, dup_end->data, set->klen)) { *elem_priv = &dup->priv; return -EEXIST; } @@ -2370,6 +2370,7 @@ const struct nft_set_type nft_set_pipapo_type = { .gc_init = nft_pipapo_gc_init, .commit = nft_pipapo_commit, .abort = nft_pipapo_abort, + .abort_skip_removal = true, .elemsize = offsetof(struct nft_pipapo_elem, ext), }, }; @@ -2394,6 +2395,7 @@ const struct nft_set_type nft_set_pipapo_avx2_type = { .gc_init = nft_pipapo_gc_init, .commit = nft_pipapo_commit, .abort = nft_pipapo_abort, + .abort_skip_removal = true, .elemsize = offsetof(struct nft_pipapo_elem, ext), }, }; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index ca594161b8402e..644d4b9167057c 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -10,21 +10,41 @@ #include #include #include +#include #include #include #include #include +struct nft_array_interval { + struct nft_set_ext *from; + struct nft_set_ext *to; +}; + +struct nft_array { + u32 max_intervals; + u32 num_intervals; + struct nft_array_interval *intervals; + struct rcu_head rcu_head; +}; + struct nft_rbtree { struct rb_root root; rwlock_t lock; - seqcount_rwlock_t count; + struct nft_array __rcu *array; + struct nft_array *array_next; + unsigned long start_rbe_cookie; unsigned long last_gc; + struct list_head expired; + u64 last_tstamp; }; struct nft_rbtree_elem { struct nft_elem_priv priv; - struct rb_node node; + union { + struct rb_node node; + struct list_head list; + }; struct nft_set_ext ext; }; @@ -39,6 +59,13 @@ static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe) return !nft_rbtree_interval_end(rbe); } +static bool nft_rbtree_interval_null(const struct nft_set *set, + const struct nft_rbtree_elem *rbe) +{ + return (!memchr_inv(nft_set_ext_key(&rbe->ext), 0, set->klen) && + nft_rbtree_interval_end(rbe)); +} + static int nft_rbtree_cmp(const struct nft_set *set, const struct nft_rbtree_elem *e1, const struct nft_rbtree_elem *e2) @@ -47,67 +74,33 @@ static int nft_rbtree_cmp(const struct nft_set *set, set->klen); } -static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe) -{ - return nft_set_elem_expired(&rbe->ext); -} +struct nft_array_lookup_ctx { + const u32 *key; + u32 klen; +}; -static const struct nft_set_ext * -__nft_rbtree_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, unsigned int seq) +static int nft_array_lookup_cmp(const void *pkey, const void *entry) { - struct nft_rbtree *priv = nft_set_priv(set); - const struct nft_rbtree_elem *rbe, *interval = NULL; - u8 genmask = nft_genmask_cur(net); - const struct rb_node *parent; - int d; + const struct nft_array_interval *interval = entry; + const struct nft_array_lookup_ctx *ctx = pkey; + int a, b; - parent = rcu_dereference_raw(priv->root.rb_node); - while (parent != NULL) { - if (read_seqcount_retry(&priv->count, seq)) - return NULL; - - rbe = rb_entry(parent, struct nft_rbtree_elem, node); + if (!interval->from) + return 1; - d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen); - if (d < 0) { - parent = rcu_dereference_raw(parent->rb_left); - if (interval && - !nft_rbtree_cmp(set, rbe, interval) && - nft_rbtree_interval_end(rbe) && - nft_rbtree_interval_start(interval)) - continue; - if (nft_set_elem_active(&rbe->ext, genmask) && - !nft_rbtree_elem_expired(rbe)) - interval = rbe; - } else if (d > 0) - parent = rcu_dereference_raw(parent->rb_right); - else { - if (!nft_set_elem_active(&rbe->ext, genmask)) { - parent = rcu_dereference_raw(parent->rb_left); - continue; - } - - if (nft_rbtree_elem_expired(rbe)) - return NULL; - - if (nft_rbtree_interval_end(rbe)) { - if (nft_set_is_anonymous(set)) - return NULL; - parent = rcu_dereference_raw(parent->rb_left); - interval = NULL; - continue; - } + a = memcmp(ctx->key, nft_set_ext_key(interval->from), ctx->klen); + if (!interval->to) + b = -1; + else + b = memcmp(ctx->key, nft_set_ext_key(interval->to), ctx->klen); - return &rbe->ext; - } - } + if (a >= 0 && b < 0) + return 0; - if (set->flags & NFT_SET_INTERVAL && interval != NULL && - nft_rbtree_interval_start(interval)) - return &interval->ext; + if (a < 0) + return -1; - return NULL; + return 1; } INDIRECT_CALLABLE_SCOPE @@ -116,83 +109,57 @@ nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key) { struct nft_rbtree *priv = nft_set_priv(set); - unsigned int seq = read_seqcount_begin(&priv->count); - const struct nft_set_ext *ext; - - ext = __nft_rbtree_lookup(net, set, key, seq); - if (ext || !read_seqcount_retry(&priv->count, seq)) - return ext; - - read_lock_bh(&priv->lock); - seq = read_seqcount_begin(&priv->count); - ext = __nft_rbtree_lookup(net, set, key, seq); - read_unlock_bh(&priv->lock); - - return ext; + struct nft_array *array = rcu_dereference(priv->array); + const struct nft_array_interval *interval; + struct nft_array_lookup_ctx ctx = { + .key = key, + .klen = set->klen, + }; + + if (!array) + return NULL; + + interval = bsearch(&ctx, array->intervals, array->num_intervals, + sizeof(struct nft_array_interval), + nft_array_lookup_cmp); + if (!interval || nft_set_elem_expired(interval->from)) + return NULL; + + return interval->from; } -static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, - const u32 *key, struct nft_rbtree_elem **elem, - unsigned int seq, unsigned int flags, u8 genmask) -{ - struct nft_rbtree_elem *rbe, *interval = NULL; - struct nft_rbtree *priv = nft_set_priv(set); - const struct rb_node *parent; - const void *this; - int d; - - parent = rcu_dereference_raw(priv->root.rb_node); - while (parent != NULL) { - if (read_seqcount_retry(&priv->count, seq)) - return false; - - rbe = rb_entry(parent, struct nft_rbtree_elem, node); - - this = nft_set_ext_key(&rbe->ext); - d = memcmp(this, key, set->klen); - if (d < 0) { - parent = rcu_dereference_raw(parent->rb_left); - if (!(flags & NFT_SET_ELEM_INTERVAL_END)) - interval = rbe; - } else if (d > 0) { - parent = rcu_dereference_raw(parent->rb_right); - if (flags & NFT_SET_ELEM_INTERVAL_END) - interval = rbe; - } else { - if (!nft_set_elem_active(&rbe->ext, genmask)) { - parent = rcu_dereference_raw(parent->rb_left); - continue; - } +struct nft_array_get_ctx { + const u32 *key; + unsigned int flags; + u32 klen; +}; - if (nft_set_elem_expired(&rbe->ext)) - return false; +static int nft_array_get_cmp(const void *pkey, const void *entry) +{ + const struct nft_array_interval *interval = entry; + const struct nft_array_get_ctx *ctx = pkey; + int a, b; - if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || - (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == - (flags & NFT_SET_ELEM_INTERVAL_END)) { - *elem = rbe; - return true; - } + if (!interval->from) + return 1; - if (nft_rbtree_interval_end(rbe)) - interval = NULL; + a = memcmp(ctx->key, nft_set_ext_key(interval->from), ctx->klen); + if (!interval->to) + b = -1; + else + b = memcmp(ctx->key, nft_set_ext_key(interval->to), ctx->klen); - parent = rcu_dereference_raw(parent->rb_left); - } + if (a >= 0) { + if (ctx->flags & NFT_SET_ELEM_INTERVAL_END && b <= 0) + return 0; + else if (b < 0) + return 0; } - if (set->flags & NFT_SET_INTERVAL && interval != NULL && - nft_set_elem_active(&interval->ext, genmask) && - !nft_set_elem_expired(&interval->ext) && - ((!nft_rbtree_interval_end(interval) && - !(flags & NFT_SET_ELEM_INTERVAL_END)) || - (nft_rbtree_interval_end(interval) && - (flags & NFT_SET_ELEM_INTERVAL_END)))) { - *elem = interval; - return true; - } + if (a < 0) + return -1; - return false; + return 1; } static struct nft_elem_priv * @@ -200,34 +167,41 @@ nft_rbtree_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { struct nft_rbtree *priv = nft_set_priv(set); - unsigned int seq = read_seqcount_begin(&priv->count); - struct nft_rbtree_elem *rbe = ERR_PTR(-ENOENT); - const u32 *key = (const u32 *)&elem->key.val; - u8 genmask = nft_genmask_cur(net); - bool ret; - - ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); - if (ret || !read_seqcount_retry(&priv->count, seq)) - return &rbe->priv; - - read_lock_bh(&priv->lock); - seq = read_seqcount_begin(&priv->count); - ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); - read_unlock_bh(&priv->lock); - - if (!ret) + struct nft_array *array = rcu_dereference(priv->array); + const struct nft_array_interval *interval; + struct nft_array_get_ctx ctx = { + .key = (const u32 *)&elem->key.val, + .flags = flags, + .klen = set->klen, + }; + struct nft_rbtree_elem *rbe; + + if (!array) return ERR_PTR(-ENOENT); + interval = bsearch(&ctx, array->intervals, array->num_intervals, + sizeof(struct nft_array_interval), nft_array_get_cmp); + if (!interval || nft_set_elem_expired(interval->from)) + return ERR_PTR(-ENOENT); + + if (flags & NFT_SET_ELEM_INTERVAL_END) + rbe = container_of(interval->to, struct nft_rbtree_elem, ext); + else + rbe = container_of(interval->from, struct nft_rbtree_elem, ext); + return &rbe->priv; } -static void nft_rbtree_gc_elem_remove(struct net *net, struct nft_set *set, - struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe) +static void nft_rbtree_gc_elem_move(struct net *net, struct nft_set *set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) { lockdep_assert_held_write(&priv->lock); nft_setelem_data_deactivate(net, set, &rbe->priv); rb_erase(&rbe->node, &priv->root); + + /* collected later on in commit callback */ + list_add(&rbe->list, &priv->expired); } static const struct nft_rbtree_elem * @@ -238,11 +212,6 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, struct rb_node *prev = rb_prev(&rbe->node); struct net *net = read_pnet(&set->net); struct nft_rbtree_elem *rbe_prev; - struct nft_trans_gc *gc; - - gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC); - if (!gc) - return ERR_PTR(-ENOMEM); /* search for end interval coming before this element. * end intervals don't carry a timeout extension, they @@ -260,28 +229,10 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, rbe_prev = NULL; if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); - nft_rbtree_gc_elem_remove(net, set, priv, rbe_prev); - - /* There is always room in this trans gc for this element, - * memory allocation never actually happens, hence, the warning - * splat in such case. No need to set NFT_SET_ELEM_DEAD_BIT, - * this is synchronous gc which never fails. - */ - gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); - if (WARN_ON_ONCE(!gc)) - return ERR_PTR(-ENOMEM); - - nft_trans_gc_elem_add(gc, rbe_prev); + nft_rbtree_gc_elem_move(net, set, priv, rbe_prev); } - nft_rbtree_gc_elem_remove(net, set, priv, rbe); - gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); - if (WARN_ON_ONCE(!gc)) - return ERR_PTR(-ENOMEM); - - nft_trans_gc_elem_add(gc, rbe); - - nft_trans_gc_queue_sync_done(gc); + nft_rbtree_gc_elem_move(net, set, priv, rbe); return rbe_prev; } @@ -302,16 +253,107 @@ static bool nft_rbtree_update_first(const struct nft_set *set, return false; } +/* Only for anonymous sets which do not allow updates, all element are active. */ +static struct nft_rbtree_elem *nft_rbtree_prev_active(struct nft_rbtree_elem *rbe) +{ + struct rb_node *node; + + node = rb_prev(&rbe->node); + if (!node) + return NULL; + + return rb_entry(node, struct nft_rbtree_elem, node); +} + +static struct nft_rbtree_elem * +__nft_rbtree_next_active(struct rb_node *node, u8 genmask) +{ + struct nft_rbtree_elem *next_rbe; + + while (node) { + next_rbe = rb_entry(node, struct nft_rbtree_elem, node); + if (!nft_set_elem_active(&next_rbe->ext, genmask)) { + node = rb_next(node); + continue; + } + + return next_rbe; + } + + return NULL; +} + +static struct nft_rbtree_elem * +nft_rbtree_next_active(struct nft_rbtree_elem *rbe, u8 genmask) +{ + return __nft_rbtree_next_active(rb_next(&rbe->node), genmask); +} + +static void nft_rbtree_maybe_reset_start_cookie(struct nft_rbtree *priv, + u64 tstamp) +{ + if (priv->last_tstamp != tstamp) { + priv->start_rbe_cookie = 0; + priv->last_tstamp = tstamp; + } +} + +static void nft_rbtree_set_start_cookie(struct nft_rbtree *priv, + const struct nft_rbtree_elem *rbe) +{ + priv->start_rbe_cookie = (unsigned long)rbe; +} + +static void nft_rbtree_set_start_cookie_open(struct nft_rbtree *priv, + const struct nft_rbtree_elem *rbe, + unsigned long open_interval) +{ + priv->start_rbe_cookie = (unsigned long)rbe | open_interval; +} + +#define NFT_RBTREE_OPEN_INTERVAL 1UL + +static bool nft_rbtree_cmp_start_cookie(struct nft_rbtree *priv, + const struct nft_rbtree_elem *rbe) +{ + return (priv->start_rbe_cookie & ~NFT_RBTREE_OPEN_INTERVAL) == (unsigned long)rbe; +} + +static bool nft_rbtree_insert_same_interval(const struct net *net, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) +{ + u8 genmask = nft_genmask_next(net); + struct nft_rbtree_elem *next_rbe; + + if (!priv->start_rbe_cookie) + return true; + + next_rbe = nft_rbtree_next_active(rbe, genmask); + if (next_rbe) { + /* Closest start element differs from last element added. */ + if (nft_rbtree_interval_start(next_rbe) && + nft_rbtree_cmp_start_cookie(priv, next_rbe)) { + priv->start_rbe_cookie = 0; + return true; + } + } + + priv->start_rbe_cookie = 0; + + return false; +} + static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, - struct nft_elem_priv **elem_priv) + struct nft_elem_priv **elem_priv, u64 tstamp, bool last) { - struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; + struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL, *rbe_prev; struct rb_node *node, *next, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 cur_genmask = nft_genmask_cur(net); u8 genmask = nft_genmask_next(net); - u64 tstamp = nft_net_tstamp(net); + unsigned long open_interval = 0; int d; /* Descend the tree to search for an existing element greater than the @@ -417,12 +459,46 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, } } + if (nft_rbtree_interval_null(set, new)) { + priv->start_rbe_cookie = 0; + } else if (nft_rbtree_interval_start(new) && priv->start_rbe_cookie) { + if (nft_set_is_anonymous(set)) { + priv->start_rbe_cookie = 0; + } else if (priv->start_rbe_cookie & NFT_RBTREE_OPEN_INTERVAL) { + /* Previous element is an open interval that partially + * overlaps with an existing non-open interval. + */ + return -ENOTEMPTY; + } + } + /* - new start element matching existing start element: full overlap * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. */ if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) && nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) { *elem_priv = &rbe_ge->priv; + + /* - Corner case: new start element of open interval (which + * comes as last element in the batch) overlaps the start of + * an existing interval with an end element: partial overlap. + */ + node = rb_first(&priv->root); + rbe = __nft_rbtree_next_active(node, genmask); + if (rbe && nft_rbtree_interval_end(rbe)) { + rbe = nft_rbtree_next_active(rbe, genmask); + if (rbe && + nft_rbtree_interval_start(rbe) && + !nft_rbtree_cmp(set, new, rbe)) { + if (last) + return -ENOTEMPTY; + + /* Maybe open interval? */ + open_interval = NFT_RBTREE_OPEN_INTERVAL; + } + } + nft_rbtree_set_start_cookie_open(priv, rbe_ge, open_interval); + return -EEXIST; } @@ -431,18 +507,37 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, */ if (rbe_le && !nft_rbtree_cmp(set, new, rbe_le) && nft_rbtree_interval_end(rbe_le) == nft_rbtree_interval_end(new)) { + /* - ignore null interval, otherwise NLM_F_CREATE bogusly + * reports EEXIST. + */ + if (nft_rbtree_interval_null(set, new)) + return -ECANCELED; + *elem_priv = &rbe_le->priv; + + /* - start and end element belong to the same interval. */ + if (!nft_rbtree_insert_same_interval(net, priv, rbe_le)) + return -ENOTEMPTY; + return -EEXIST; } /* - new start element with existing closest, less or equal key value * being a start element: partial overlap, reported as -ENOTEMPTY. * Anonymous sets allow for two consecutive start element since they - * are constant, skip them to avoid bogus overlap reports. + * are constant, but validate that this new start element does not + * sit in between an existing start and end elements: partial overlap, + * reported as -ENOTEMPTY. */ - if (!nft_set_is_anonymous(set) && rbe_le && - nft_rbtree_interval_start(rbe_le) && nft_rbtree_interval_start(new)) - return -ENOTEMPTY; + if (rbe_le && + nft_rbtree_interval_start(rbe_le) && nft_rbtree_interval_start(new)) { + if (!nft_set_is_anonymous(set)) + return -ENOTEMPTY; + + rbe_prev = nft_rbtree_prev_active(rbe_le); + if (rbe_prev && nft_rbtree_interval_end(rbe_prev)) + return -ENOTEMPTY; + } /* - new end element with existing closest, less or equal key value * being a end element: partial overlap, reported as -ENOTEMPTY. @@ -458,6 +553,12 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, nft_rbtree_interval_end(rbe_ge) && nft_rbtree_interval_end(new)) return -ENOTEMPTY; + /* - start element overlaps an open interval but end element is new: + * partial overlap, reported as -ENOEMPTY. + */ + if (!rbe_ge && priv->start_rbe_cookie && nft_rbtree_interval_end(new)) + return -ENOTEMPTY; + /* Accepted element: pick insertion point depending on key value */ parent = NULL; p = &priv->root.rb_node; @@ -481,14 +582,102 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, return 0; } +static int nft_array_intervals_alloc(struct nft_array *array, u32 max_intervals) +{ + struct nft_array_interval *intervals; + + intervals = kvcalloc(max_intervals, sizeof(struct nft_array_interval), + GFP_KERNEL_ACCOUNT); + if (!intervals) + return -ENOMEM; + + if (array->intervals) + kvfree(array->intervals); + + array->intervals = intervals; + array->max_intervals = max_intervals; + + return 0; +} + +static struct nft_array *nft_array_alloc(u32 max_intervals) +{ + struct nft_array *array; + + array = kzalloc(sizeof(*array), GFP_KERNEL_ACCOUNT); + if (!array) + return NULL; + + if (nft_array_intervals_alloc(array, max_intervals) < 0) { + kfree(array); + return NULL; + } + + return array; +} + +#define NFT_ARRAY_EXTRA_SIZE 10240 + +/* Similar to nft_rbtree_{u,k}size to hide details to userspace, but consider + * packed representation coming from userspace for anonymous sets too. + */ +static u32 nft_array_elems(const struct nft_set *set) +{ + u32 nelems = atomic_read(&set->nelems); + + /* Adjacent intervals are represented with a single start element in + * anonymous sets, use the current element counter as is. + */ + if (nft_set_is_anonymous(set)) + return nelems; + + /* Add extra room for never matching interval at the beginning and open + * interval at the end which only use a single element to represent it. + * The conversion to array will compact intervals, this allows reduce + * memory consumption. + */ + return (nelems / 2) + 2; +} + +static int nft_array_may_resize(const struct nft_set *set) +{ + u32 nelems = nft_array_elems(set), new_max_intervals; + struct nft_rbtree *priv = nft_set_priv(set); + struct nft_array *array; + + if (!priv->array_next) { + array = nft_array_alloc(nelems + NFT_ARRAY_EXTRA_SIZE); + if (!array) + return -ENOMEM; + + priv->array_next = array; + } + + if (nelems < priv->array_next->max_intervals) + return 0; + + new_max_intervals = priv->array_next->max_intervals + NFT_ARRAY_EXTRA_SIZE; + if (nft_array_intervals_alloc(priv->array_next, new_max_intervals) < 0) + return -ENOMEM; + + return 0; +} + static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, struct nft_elem_priv **elem_priv) { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem->priv); + bool last = !!(elem->flags & NFT_SET_ELEM_INTERNAL_LAST); struct nft_rbtree *priv = nft_set_priv(set); + u64 tstamp = nft_net_tstamp(net); int err; + nft_rbtree_maybe_reset_start_cookie(priv, tstamp); + + if (nft_array_may_resize(set) < 0) + return -ENOMEM; + do { if (fatal_signal_pending(current)) return -EINTR; @@ -496,10 +685,12 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, cond_resched(); write_lock_bh(&priv->lock); - write_seqcount_begin(&priv->count); - err = __nft_rbtree_insert(net, set, rbe, elem_priv); - write_seqcount_end(&priv->count); + err = __nft_rbtree_insert(net, set, rbe, elem_priv, tstamp, last); write_unlock_bh(&priv->lock); + + if (nft_rbtree_interval_end(rbe)) + priv->start_rbe_cookie = 0; + } while (err == -EAGAIN); return err; @@ -508,9 +699,7 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, static void nft_rbtree_erase(struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { write_lock_bh(&priv->lock); - write_seqcount_begin(&priv->count); rb_erase(&rbe->node, &priv->root); - write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); } @@ -533,6 +722,48 @@ static void nft_rbtree_activate(const struct net *net, nft_clear(net, &rbe->ext); } +static struct nft_rbtree_elem * +nft_rbtree_next_inactive(struct nft_rbtree_elem *rbe, u8 genmask) +{ + struct nft_rbtree_elem *next_rbe; + struct rb_node *node; + + node = rb_next(&rbe->node); + if (node) { + next_rbe = rb_entry(node, struct nft_rbtree_elem, node); + if (nft_rbtree_interval_start(next_rbe) && + !nft_set_elem_active(&next_rbe->ext, genmask)) + return next_rbe; + } + + return NULL; +} + +static bool nft_rbtree_deactivate_same_interval(const struct net *net, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) +{ + u8 genmask = nft_genmask_next(net); + struct nft_rbtree_elem *next_rbe; + + if (!priv->start_rbe_cookie) + return true; + + next_rbe = nft_rbtree_next_inactive(rbe, genmask); + if (next_rbe) { + /* Closest start element differs from last element added. */ + if (nft_rbtree_interval_start(next_rbe) && + nft_rbtree_cmp_start_cookie(priv, next_rbe)) { + priv->start_rbe_cookie = 0; + return true; + } + } + + priv->start_rbe_cookie = 0; + + return false; +} + static void nft_rbtree_flush(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) @@ -547,12 +778,22 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_rbtree_elem *rbe, *this = nft_elem_priv_cast(elem->priv); - const struct nft_rbtree *priv = nft_set_priv(set); + bool last = !!(elem->flags & NFT_SET_ELEM_INTERNAL_LAST); + struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent = priv->root.rb_node; u8 genmask = nft_genmask_next(net); u64 tstamp = nft_net_tstamp(net); int d; + nft_rbtree_maybe_reset_start_cookie(priv, tstamp); + + if (nft_rbtree_interval_start(this) || + nft_rbtree_interval_null(set, this)) + priv->start_rbe_cookie = 0; + + if (nft_array_may_resize(set) < 0) + return NULL; + while (parent != NULL) { rbe = rb_entry(parent, struct nft_rbtree_elem, node); @@ -577,6 +818,13 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set, parent = parent->rb_left; continue; } + + if (nft_rbtree_interval_start(rbe)) { + if (!last) + nft_rbtree_set_start_cookie(priv, rbe); + } else if (!nft_rbtree_deactivate_same_interval(net, priv, rbe)) + return NULL; + nft_rbtree_flush(net, set, &rbe->priv); return &rbe->priv; } @@ -615,6 +863,11 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, switch (iter->type) { case NFT_ITER_UPDATE: lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex); + + if (nft_array_may_resize(set) < 0) { + iter->err = -ENOMEM; + break; + } nft_rbtree_do_walk(ctx, set, iter); break; case NFT_ITER_READ: @@ -629,29 +882,13 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, } } -static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, - struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe) -{ - nft_setelem_data_deactivate(net, set, &rbe->priv); - nft_rbtree_erase(priv, rbe); -} - -static void nft_rbtree_gc(struct nft_set *set) +static void nft_rbtree_gc_scan(struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe, *rbe_end = NULL; struct net *net = read_pnet(&set->net); u64 tstamp = nft_net_tstamp(net); struct rb_node *node, *next; - struct nft_trans_gc *gc; - - set = nft_set_container_of(priv); - net = read_pnet(&set->net); - - gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); - if (!gc) - return; for (node = rb_first(&priv->root); node ; node = next) { next = rb_next(node); @@ -669,34 +906,46 @@ static void nft_rbtree_gc(struct nft_set *set) if (!__nft_set_elem_expired(&rbe->ext, tstamp)) continue; - gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); - if (!gc) - goto try_later; - /* end element needs to be removed first, it has * no timeout extension. */ + write_lock_bh(&priv->lock); if (rbe_end) { - nft_rbtree_gc_remove(net, set, priv, rbe_end); - nft_trans_gc_elem_add(gc, rbe_end); + nft_rbtree_gc_elem_move(net, set, priv, rbe_end); rbe_end = NULL; } - gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); - if (!gc) - goto try_later; - - nft_rbtree_gc_remove(net, set, priv, rbe); - nft_trans_gc_elem_add(gc, rbe); + nft_rbtree_gc_elem_move(net, set, priv, rbe); + write_unlock_bh(&priv->lock); } -try_later: + priv->last_gc = jiffies; +} + +static void nft_rbtree_gc_queue(struct nft_set *set) +{ + struct nft_rbtree *priv = nft_set_priv(set); + struct nft_rbtree_elem *rbe, *rbe_end; + struct nft_trans_gc *gc; - if (gc) { - gc = nft_trans_gc_catchall_sync(gc); - nft_trans_gc_queue_sync_done(gc); - priv->last_gc = jiffies; + if (list_empty(&priv->expired)) + return; + + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); + if (!gc) + return; + + list_for_each_entry_safe(rbe, rbe_end, &priv->expired, list) { + list_del(&rbe->list); + nft_trans_gc_elem_add(gc, rbe); + + gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); + if (!gc) + return; } + + gc = nft_trans_gc_catchall_sync(gc); + nft_trans_gc_queue_sync_done(gc); } static u64 nft_rbtree_privsize(const struct nlattr * const nla[], @@ -714,24 +963,45 @@ static int nft_rbtree_init(const struct nft_set *set, BUILD_BUG_ON(offsetof(struct nft_rbtree_elem, priv) != 0); rwlock_init(&priv->lock); - seqcount_rwlock_init(&priv->count, &priv->lock); priv->root = RB_ROOT; + INIT_LIST_HEAD(&priv->expired); + + priv->array = NULL; + priv->array_next = NULL; return 0; } +static void __nft_array_free(struct nft_array *array) +{ + kvfree(array->intervals); + kfree(array); +} + static void nft_rbtree_destroy(const struct nft_ctx *ctx, const struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); - struct nft_rbtree_elem *rbe; + struct nft_rbtree_elem *rbe, *next; + struct nft_array *array; struct rb_node *node; + list_for_each_entry_safe(rbe, next, &priv->expired, list) { + list_del(&rbe->list); + nf_tables_set_elem_destroy(ctx, set, &rbe->priv); + } + while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); nf_tables_set_elem_destroy(ctx, set, &rbe->priv); } + + array = rcu_dereference_protected(priv->array, true); + if (array) + __nft_array_free(array); + if (priv->array_next) + __nft_array_free(priv->array_next); } static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, @@ -752,12 +1022,105 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, return true; } +static void nft_array_free_rcu(struct rcu_head *rcu_head) +{ + struct nft_array *array = container_of(rcu_head, struct nft_array, rcu_head); + + __nft_array_free(array); +} + static void nft_rbtree_commit(struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); + struct nft_rbtree_elem *rbe, *prev_rbe; + struct nft_array *old; + u32 num_intervals = 0; + struct rb_node *node; + /* No changes, skip, eg. elements updates only. */ + if (!priv->array_next) + return; + + /* GC can be performed if the binary search blob is going + * to be rebuilt. It has to be done in two phases: first + * scan tree and move all expired elements to the expired + * list. + * + * Then, after blob has been re-built and published to other + * CPUs, queue collected entries for freeing. + */ if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) - nft_rbtree_gc(set); + nft_rbtree_gc_scan(set); + + /* Reverse walk to create an array from smaller to largest interval. */ + node = rb_last(&priv->root); + if (node) + prev_rbe = rb_entry(node, struct nft_rbtree_elem, node); + else + prev_rbe = NULL; + + while (prev_rbe) { + rbe = prev_rbe; + + if (nft_rbtree_interval_start(rbe)) + priv->array_next->intervals[num_intervals].from = &rbe->ext; + else if (nft_rbtree_interval_end(rbe)) + priv->array_next->intervals[num_intervals++].to = &rbe->ext; + + if (num_intervals >= priv->array_next->max_intervals) { + pr_warn_once("malformed interval set from userspace?"); + goto err_out; + } + + node = rb_prev(node); + if (!node) + break; + + prev_rbe = rb_entry(node, struct nft_rbtree_elem, node); + + /* For anonymous sets, when adjacent ranges are found, + * the end element is not added to the set to pack the set + * representation. Use next start element to complete this + * interval. + */ + if (nft_rbtree_interval_start(rbe) && + nft_rbtree_interval_start(prev_rbe) && + priv->array_next->intervals[num_intervals].from) + priv->array_next->intervals[num_intervals++].to = &prev_rbe->ext; + + if (num_intervals >= priv->array_next->max_intervals) { + pr_warn_once("malformed interval set from userspace?"); + goto err_out; + } + } + + if (priv->array_next->intervals[num_intervals].from) + num_intervals++; +err_out: + priv->array_next->num_intervals = num_intervals; + old = rcu_replace_pointer(priv->array, priv->array_next, + lockdep_is_held(&nft_pernet(read_pnet(&set->net))->commit_mutex)); + priv->array_next = NULL; + if (old) + call_rcu(&old->rcu_head, nft_array_free_rcu); + + /* New blob is public, queue collected entries for freeing. + * call_rcu ensures elements stay around until readers are done. + */ + nft_rbtree_gc_queue(set); +} + +static void nft_rbtree_abort(const struct nft_set *set) +{ + struct nft_rbtree *priv = nft_set_priv(set); + struct nft_array *array_next; + + if (!priv->array_next) + return; + + array_next = priv->array_next; + priv->array_next = NULL; + __nft_array_free(array_next); } static void nft_rbtree_gc_init(const struct nft_set *set) @@ -821,6 +1184,7 @@ const struct nft_set_type nft_set_rbtree_type = { .flush = nft_rbtree_flush, .activate = nft_rbtree_activate, .commit = nft_rbtree_commit, + .abort = nft_rbtree_abort, .gc_init = nft_rbtree_gc_init, .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 5d3e5182598596..4d3e5a31b4125d 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -48,7 +48,7 @@ static void nft_synproxy_eval_v4(const struct nft_synproxy *priv, struct tcphdr *_tcph, struct synproxy_options *opts) { - struct nf_synproxy_info info = priv->info; + struct nf_synproxy_info info = READ_ONCE(priv->info); struct net *net = nft_net(pkt); struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *skb = pkt->skb; @@ -79,7 +79,7 @@ static void nft_synproxy_eval_v6(const struct nft_synproxy *priv, struct tcphdr *_tcph, struct synproxy_options *opts) { - struct nf_synproxy_info info = priv->info; + struct nf_synproxy_info info = READ_ONCE(priv->info); struct net *net = nft_net(pkt); struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *skb = pkt->skb; @@ -340,7 +340,7 @@ static void nft_synproxy_obj_update(struct nft_object *obj, struct nft_synproxy *newpriv = nft_obj_data(newobj); struct nft_synproxy *priv = nft_obj_data(obj); - priv->info = newpriv->info; + WRITE_ONCE(priv->info, newpriv->info); } static struct nft_object_type nft_synproxy_obj_type; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 90b7630421c442..48105ea3df1522 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1764,7 +1764,7 @@ EXPORT_SYMBOL_GPL(xt_hook_ops_alloc); int xt_register_template(const struct xt_table *table, int (*table_init)(struct net *net)) { - int ret = -EEXIST, af = table->af; + int ret = -EBUSY, af = table->af; struct xt_template *t; mutex_lock(&xt[af].mutex); diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 0189f8b6b0bd15..848287ab79cfb1 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -31,8 +31,6 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) { struct net *net = xt_net(par); const struct xt_connlimit_info *info = par->matchinfo; - struct nf_conntrack_tuple tuple; - const struct nf_conntrack_tuple *tuple_ptr = &tuple; const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; enum ip_conntrack_info ctinfo; const struct nf_conn *ct; @@ -40,13 +38,8 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) u32 key[5]; ct = nf_ct_get(skb, &ctinfo); - if (ct != NULL) { - tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + if (ct) zone = nf_ct_zone(ct); - } else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), - xt_family(par), net, &tuple)) { - goto hotdrop; - } if (xt_family(par) == NFPROTO_IPV6) { const struct ipv6hdr *iph = ipv6_hdr(skb); @@ -69,10 +62,9 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) key[1] = zone->id; } - connections = nf_conncount_count(net, info->data, key, tuple_ptr, - zone); + connections = nf_conncount_count_skb(net, skb, xt_family(par), info->data, key); if (connections == 0) - /* kmalloc failed, drop it entirely */ + /* kmalloc failed or tuple couldn't be found, drop it entirely */ goto hotdrop; return (connections > info->limit) ^ !!(info->flags & XT_CONNLIMIT_INVERT); diff --git a/net/netrom/nr_out.c b/net/netrom/nr_out.c index 5e531394a724b7..2b3cbceb0b52d5 100644 --- a/net/netrom/nr_out.c +++ b/net/netrom/nr_out.c @@ -43,8 +43,10 @@ void nr_output(struct sock *sk, struct sk_buff *skb) frontlen = skb_headroom(skb); while (skb->len > 0) { - if ((skbn = sock_alloc_send_skb(sk, frontlen + NR_MAX_PACKET_SIZE, 0, &err)) == NULL) + if ((skbn = sock_alloc_send_skb(sk, frontlen + NR_MAX_PACKET_SIZE, 0, &err)) == NULL) { + kfree_skb(skb); return; + } skb_reserve(skbn, frontlen); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index b94cb2ffbaf8fa..9cc29ae85b06f5 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -752,7 +752,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) unsigned char *dptr; ax25_cb *ax25s; int ret; - struct sk_buff *skbn; + struct sk_buff *nskb, *oskb; /* * Reject malformed packets early. Check that it contains at least 2 @@ -811,14 +811,16 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) /* We are going to change the netrom headers so we should get our own skb, we also did not know until now how much header space we had to reserve... - RXQ */ - if ((skbn=skb_copy_expand(skb, dev->hard_header_len, 0, GFP_ATOMIC)) == NULL) { + nskb = skb_copy_expand(skb, dev->hard_header_len, 0, GFP_ATOMIC); + + if (!nskb) { nr_node_unlock(nr_node); nr_node_put(nr_node); dev_put(dev); return 0; } - kfree_skb(skb); - skb=skbn; + oskb = skb; + skb = nskb; skb->data[14]--; dptr = skb_push(skb, 1); @@ -837,6 +839,9 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) nr_node_unlock(nr_node); nr_node_put(nr_node); + if (ret) + kfree_skb(oskb); + return ret; } diff --git a/net/nfc/core.c b/net/nfc/core.c index ae1c842f9c6427..f50e5bab35d8ec 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -1147,12 +1147,13 @@ int nfc_register_device(struct nfc_dev *dev) EXPORT_SYMBOL(nfc_register_device); /** - * nfc_unregister_device - unregister a nfc device in the nfc subsystem + * nfc_unregister_rfkill - unregister a nfc device in the rfkill subsystem * * @dev: The nfc device to unregister */ -void nfc_unregister_device(struct nfc_dev *dev) +void nfc_unregister_rfkill(struct nfc_dev *dev) { + struct rfkill *rfk = NULL; int rc; pr_debug("dev_name=%s\n", dev_name(&dev->dev)); @@ -1164,13 +1165,26 @@ void nfc_unregister_device(struct nfc_dev *dev) device_lock(&dev->dev); if (dev->rfkill) { - rfkill_unregister(dev->rfkill); - rfkill_destroy(dev->rfkill); + rfk = dev->rfkill; dev->rfkill = NULL; } dev->shutting_down = true; device_unlock(&dev->dev); + if (rfk) { + rfkill_unregister(rfk); + rfkill_destroy(rfk); + } +} +EXPORT_SYMBOL(nfc_unregister_rfkill); + +/** + * nfc_remove_device - remove a nfc device in the nfc subsystem + * + * @dev: The nfc device to remove + */ +void nfc_remove_device(struct nfc_dev *dev) +{ if (dev->ops->check_presence) { timer_delete_sync(&dev->check_pres_timer); cancel_work_sync(&dev->check_pres_work); @@ -1183,6 +1197,18 @@ void nfc_unregister_device(struct nfc_dev *dev) device_del(&dev->dev); mutex_unlock(&nfc_devlist_mutex); } +EXPORT_SYMBOL(nfc_remove_device); + +/** + * nfc_unregister_device - unregister a nfc device in the nfc subsystem + * + * @dev: The nfc device to unregister + */ +void nfc_unregister_device(struct nfc_dev *dev) +{ + nfc_unregister_rfkill(dev); + nfc_remove_device(dev); +} EXPORT_SYMBOL(nfc_unregister_device); static int __init nfc_init(void) diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index 4fc37894860c9e..08c8aa1530d8a0 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -762,6 +762,14 @@ static void llc_shdlc_deinit(struct nfc_llc *llc) { struct llc_shdlc *shdlc = nfc_llc_get_data(llc); + timer_shutdown_sync(&shdlc->connect_timer); + timer_shutdown_sync(&shdlc->t1_timer); + timer_shutdown_sync(&shdlc->t2_timer); + shdlc->t1_active = false; + shdlc->t2_active = false; + + cancel_work_sync(&shdlc->sm_work); + skb_queue_purge(&shdlc->rcv_q); skb_queue_purge(&shdlc->send_q); skb_queue_purge(&shdlc->ack_pending_q); diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index e2680a3bef7995..b652323bc2c12b 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -778,8 +778,23 @@ int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap, if (likely(frag_len > 0)) skb_put_data(pdu, msg_ptr, frag_len); + spin_lock(&local->tx_queue.lock); + + if (list_empty(&local->list)) { + spin_unlock(&local->tx_queue.lock); + + kfree_skb(pdu); + + len -= remaining_len; + if (len == 0) + len = -ENXIO; + break; + } + /* No need to check for the peer RW for UI frames */ - skb_queue_tail(&local->tx_queue, pdu); + __skb_queue_tail(&local->tx_queue, pdu); + + spin_unlock(&local->tx_queue.lock); remaining_len -= frag_len; msg_ptr += frag_len; diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index beeb3b4d28caba..444a3774c8e806 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -316,7 +316,9 @@ static struct nfc_llcp_local *nfc_llcp_remove_local(struct nfc_dev *dev) spin_lock(&llcp_devices_lock); list_for_each_entry_safe(local, tmp, &llcp_devices, list) if (local->dev == dev) { - list_del(&local->list); + spin_lock(&local->tx_queue.lock); + list_del_init(&local->list); + spin_unlock(&local->tx_queue.lock); spin_unlock(&llcp_devices_lock); return local; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index fc921cd2cdffa5..e419e020a70a33 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1303,6 +1303,8 @@ void nci_unregister_device(struct nci_dev *ndev) { struct nci_conn_info *conn_info, *n; + nfc_unregister_rfkill(ndev->nfc_dev); + /* This set_bit is not protected with specialized barrier, * However, it is fine because the mutex_lock(&ndev->req_lock); * in nci_close_device() will help to emit one. @@ -1320,7 +1322,7 @@ void nci_unregister_device(struct nci_dev *ndev) /* conn_info is allocated with devm_kzalloc */ } - nfc_unregister_device(ndev->nfc_dev); + nfc_remove_device(ndev->nfc_dev); } EXPORT_SYMBOL(nci_unregister_device); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index e573e92213029c..a0811e1fba6563 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -928,8 +928,8 @@ static u32 ct_limit_get(const struct ovs_ct_limit_info *info, u16 zone) } static int ovs_ct_check_limit(struct net *net, - const struct ovs_conntrack_info *info, - const struct nf_conntrack_tuple *tuple) + const struct sk_buff *skb, + const struct ovs_conntrack_info *info) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); const struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; @@ -942,8 +942,9 @@ static int ovs_ct_check_limit(struct net *net, if (per_zone_limit == OVS_CT_LIMIT_UNLIMITED) return 0; - connections = nf_conncount_count(net, ct_limit_info->data, - &conncount_key, tuple, &info->zone); + connections = nf_conncount_count_skb(net, skb, info->family, + ct_limit_info->data, + &conncount_key); if (connections > per_zone_limit) return -ENOMEM; @@ -972,8 +973,7 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) if (static_branch_unlikely(&ovs_ct_limit_enabled)) { if (!nf_ct_is_confirmed(ct)) { - err = ovs_ct_check_limit(net, info, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + err = ovs_ct_check_limit(net, skb, info); if (err) { net_warn_ratelimited("openvswitch: zone: %u " "exceeds conntrack limit\n", @@ -1770,8 +1770,8 @@ static int __ovs_ct_limit_get_zone_limit(struct net *net, zone_limit.limit = limit; nf_ct_zone_init(&ct_zone, zone_id, NF_CT_DEFAULT_ZONE_DIR, 0); - zone_limit.count = nf_conncount_count(net, data, &conncount_key, NULL, - &ct_zone); + zone_limit.count = nf_conncount_count_skb(net, NULL, 0, data, + &conncount_key); return nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit); } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 1cb4f97335d87b..2d536901309ea9 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2802,13 +2802,20 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, return err; } -static bool validate_push_nsh(const struct nlattr *attr, bool log) +static bool validate_push_nsh(const struct nlattr *a, bool log) { + struct nlattr *nsh_key = nla_data(a); struct sw_flow_match match; struct sw_flow_key key; + /* There must be one and only one NSH header. */ + if (!nla_ok(nsh_key, nla_len(a)) || + nla_total_size(nla_len(nsh_key)) != nla_len(a) || + nla_type(nsh_key) != OVS_KEY_ATTR_NSH) + return false; + ovs_match_init(&match, &key, true, NULL); - return !nsh_key_put_from_nlattr(attr, &match, false, true, log); + return !nsh_key_put_from_nlattr(nsh_key, &match, false, true, log); } /* Return false if there are any non-masked bits set. @@ -3389,7 +3396,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return -EINVAL; } mac_proto = MAC_PROTO_NONE; - if (!validate_push_nsh(nla_data(a), log)) + if (!validate_push_nsh(a, log)) return -EINVAL; break; diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 91a11067e4588c..6574f9bcdc0268 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -160,10 +160,19 @@ void ovs_netdev_detach_dev(struct vport *vport) static void netdev_destroy(struct vport *vport) { - rtnl_lock(); - if (netif_is_ovs_port(vport->dev)) - ovs_netdev_detach_dev(vport); - rtnl_unlock(); + /* When called from ovs_db_notify_wq() after a dp_device_event(), the + * port has already been detached, so we can avoid taking the RTNL by + * checking this first. + */ + if (netif_is_ovs_port(vport->dev)) { + rtnl_lock(); + /* Check again while holding the lock to ensure we don't race + * with the netdev notifier and detach twice. + */ + if (netif_is_ovs_port(vport->dev)) + ovs_netdev_detach_dev(vport); + rtnl_unlock(); + } call_rcu(&vport->rcu, vport_netdev_free); } diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 6bbbc16ab77808..f0ce8ce1dce0e1 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -310,22 +310,23 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) */ int ovs_vport_get_upcall_stats(struct vport *vport, struct sk_buff *skb) { + u64 tx_success = 0, tx_fail = 0; struct nlattr *nla; int i; - __u64 tx_success = 0; - __u64 tx_fail = 0; - for_each_possible_cpu(i) { const struct vport_upcall_stats_percpu *stats; + u64 n_success, n_fail; unsigned int start; stats = per_cpu_ptr(vport->upcall_stats, i); do { start = u64_stats_fetch_begin(&stats->syncp); - tx_success += u64_stats_read(&stats->n_success); - tx_fail += u64_stats_read(&stats->n_fail); + n_success = u64_stats_read(&stats->n_success); + n_fail = u64_stats_read(&stats->n_fail); } while (u64_stats_fetch_retry(&stats->syncp, start)); + tx_success += n_success; + tx_fail += n_fail; } nla = nla_nest_start_noflag(skb, OVS_VPORT_ATTR_UPCALL_STATS); diff --git a/net/psp/Kconfig b/net/psp/Kconfig index 371e8771f3bd38..84d6b0f2546067 100644 --- a/net/psp/Kconfig +++ b/net/psp/Kconfig @@ -6,6 +6,7 @@ config INET_PSP bool "PSP Security Protocol support" depends on INET select SKB_DECRYPTED + select SKB_EXTENSIONS select SOCK_VALIDATE_XMIT help Enable kernel support for the PSP Security Protocol (PSP). diff --git a/net/rds/send.c b/net/rds/send.c index 0b3d0ef2f008b6..071c5dca969a23 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1382,9 +1382,11 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) else queue_delayed_work(rds_wq, &cpath->cp_send_w, 1); rcu_read_unlock(); + + if (ret) + goto out; } - if (ret) - goto out; + rds_message_put(rm); for (ind = 0; ind < vct.indx; ind++) diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 543f9e8ebb6937..fad6518e6e39be 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -205,7 +205,7 @@ static void rose_kill_by_device(struct net_device *dev) spin_unlock_bh(&rose_list_lock); for (i = 0; i < cnt; i++) { - sk = array[cnt]; + sk = array[i]; rose = rose_sk(sk); lock_sock(sk); spin_lock_bh(&rose_list_lock); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5b7342d4348692..36d6ca0d1089e1 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -387,7 +387,7 @@ struct rxrpc_peer { struct rb_root service_conns; /* Service connections */ struct list_head keepalive_link; /* Link in net->peer_keepalive[] */ unsigned long app_data; /* Application data (e.g. afs_server) */ - time64_t last_tx_at; /* Last time packet sent here */ + unsigned int last_tx_at; /* Last time packet sent here (time64_t LSW) */ seqlock_t service_conn_lock; spinlock_t lock; /* access lock */ int debug_id; /* debug ID for printks */ @@ -1379,6 +1379,13 @@ void rxrpc_peer_keepalive_worker(struct work_struct *); void rxrpc_input_probe_for_pmtud(struct rxrpc_connection *conn, rxrpc_serial_t acked_serial, bool sendmsg_fail); +/* Update the last transmission time on a peer for keepalive purposes. */ +static inline void rxrpc_peer_mark_tx(struct rxrpc_peer *peer) +{ + /* To avoid tearing on 32-bit systems, we only keep the LSW. */ + WRITE_ONCE(peer->last_tx_at, ktime_get_seconds()); +} + /* * peer_object.c */ diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 232b6986da83e2..98ad9b51ca2cdc 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -194,7 +194,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, } ret = kernel_sendmsg(conn->local->socket, &msg, iov, ioc, len); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); if (ret < 0) trace_rxrpc_tx_fail(chan->call_debug_id, serial, ret, rxrpc_tx_point_call_final_resend); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 8b5903b6e481ac..d70db367e358db 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -275,7 +275,7 @@ static void rxrpc_send_ack_packet(struct rxrpc_call *call, int nr_kv, size_t len rxrpc_local_dont_fragment(conn->local, why == rxrpc_propose_ack_ping_for_mtu_probe); ret = do_udp_sendmsg(conn->local->socket, &msg, len); - call->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(call->peer); if (ret < 0) { trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_ack); @@ -411,7 +411,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, sizeof(pkt)); ret = do_udp_sendmsg(conn->local->socket, &msg, sizeof(pkt)); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_abort); @@ -698,7 +698,7 @@ void rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req ret = 0; trace_rxrpc_tx_data(call, txb->seq, txb->serial, txb->flags, rxrpc_txdata_inject_loss); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); goto done; } } @@ -711,7 +711,7 @@ void rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req */ rxrpc_inc_stat(call->rxnet, stat_tx_data_send); ret = do_udp_sendmsg(conn->local->socket, &msg, len); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); if (ret == -EMSGSIZE) { rxrpc_inc_stat(call->rxnet, stat_tx_data_send_msgsize); @@ -797,7 +797,7 @@ void rxrpc_send_conn_abort(struct rxrpc_connection *conn) trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); } /* @@ -917,7 +917,7 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) trace_rxrpc_tx_packet(peer->debug_id, &whdr, rxrpc_tx_point_version_keepalive); - peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(peer); _leave(""); } @@ -973,7 +973,7 @@ void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *response if (ret < 0) goto fail; - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); return; fail: diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 7f4729234957e8..9d02448ac062c7 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -237,6 +237,21 @@ static void rxrpc_distribute_error(struct rxrpc_peer *peer, struct sk_buff *skb, spin_unlock_irq(&peer->lock); } +/* + * Reconstruct the last transmission time. The difference calculated should be + * valid provided no more than ~68 years elapsed since the last transmission. + */ +static time64_t rxrpc_peer_get_tx_mark(const struct rxrpc_peer *peer, time64_t base) +{ + s32 last_tx_at = READ_ONCE(peer->last_tx_at); + s32 base_lsw = base; + s32 diff = last_tx_at - base_lsw; + + diff = clamp(diff, -RXRPC_KEEPALIVE_TIME, RXRPC_KEEPALIVE_TIME); + + return diff + base; +} + /* * Perform keep-alive pings. */ @@ -265,7 +280,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, spin_unlock_bh(&rxnet->peer_hash_lock); if (use) { - keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME; + keepalive_at = rxrpc_peer_get_tx_mark(peer, base) + RXRPC_KEEPALIVE_TIME; slot = keepalive_at - base; _debug("%02x peer %u t=%d {%pISp}", cursor, peer->debug_id, slot, &peer->srx.transport); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index d803562ca0ac1d..59292f7f9205e7 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -296,13 +296,13 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) now = ktime_get_seconds(); seq_printf(seq, - "UDP %-47.47s %-47.47s %3u %4u %5u %6llus %8d %8d\n", + "UDP %-47.47s %-47.47s %3u %4u %5u %6ds %8d %8d\n", lbuff, rbuff, refcount_read(&peer->ref), peer->cong_ssthresh, peer->max_data, - now - peer->last_tx_at, + (s32)now - (s32)READ_ONCE(peer->last_tx_at), READ_ONCE(peer->recent_srtt_us), READ_ONCE(peer->recent_rto_us)); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 7fa7e77f6bb990..e1f7513a46dbe3 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -518,7 +518,8 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (rxrpc_call_has_failed(call)) goto call_failed; - if (!skb_queue_empty(&call->recvmsg_queue)) + if (!(flags & MSG_PEEK) && + !skb_queue_empty(&call->recvmsg_queue)) rxrpc_notify_socket(call); goto not_yet_complete; @@ -549,11 +550,21 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, error_requeue_call: if (!(flags & MSG_PEEK)) { spin_lock_irq(&rx->recvmsg_lock); - list_add(&call->recvmsg_link, &rx->recvmsg_q); - spin_unlock_irq(&rx->recvmsg_lock); + if (list_empty(&call->recvmsg_link)) { + list_add(&call->recvmsg_link, &rx->recvmsg_q); + rxrpc_see_call(call, rxrpc_call_see_recvmsg_requeue); + spin_unlock_irq(&rx->recvmsg_lock); + } else if (list_is_first(&call->recvmsg_link, &rx->recvmsg_q)) { + spin_unlock_irq(&rx->recvmsg_lock); + rxrpc_put_call(call, rxrpc_call_see_recvmsg_requeue_first); + } else { + list_move(&call->recvmsg_link, &rx->recvmsg_q); + spin_unlock_irq(&rx->recvmsg_lock); + rxrpc_put_call(call, rxrpc_call_see_recvmsg_requeue_move); + } trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_requeue, 0); } else { - rxrpc_put_call(call, rxrpc_call_put_recvmsg); + rxrpc_put_call(call, rxrpc_call_put_recvmsg_peek_nowait); } error_no_call: release_sock(&rx->sk); diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c index dce5a3d8a964f8..43cbf9efd89f18 100644 --- a/net/rxrpc/rxgk.c +++ b/net/rxrpc/rxgk.c @@ -678,7 +678,7 @@ static int rxgk_issue_challenge(struct rxrpc_connection *conn) ret = do_udp_sendmsg(conn->local->socket, &msg, len); if (ret > 0) - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); __free_page(page); if (ret < 0) { diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 3657c0661cdc7f..a756855a0a62d7 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -694,7 +694,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) return -EAGAIN; } - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_rxkad_challenge); _leave(" = 0"); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index ff6be5cfe2b050..e1ab0faeb8113e 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -940,6 +940,8 @@ void tcf_idrinfo_destroy(const struct tc_action_ops *ops, int ret; idr_for_each_entry_ul(idr, p, tmp, id) { + if (IS_ERR(p)) + continue; if (tc_act_in_hw(p) && !mutex_taken) { rtnl_lock(); mutex_taken = true; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 7c6975632fc2ec..8e8f6af731d51c 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -649,9 +649,9 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, memset(&opt, 0, sizeof(opt)); - opt.index = ife->tcf_index, - opt.refcnt = refcount_read(&ife->tcf_refcnt) - ref, - opt.bindcnt = atomic_read(&ife->tcf_bindcnt) - bind, + opt.index = ife->tcf_index; + opt.refcnt = refcount_read(&ife->tcf_refcnt) - ref; + opt.bindcnt = atomic_read(&ife->tcf_bindcnt) - bind; spin_lock_bh(&ife->tcf_lock); opt.action = ife->tcf_action; @@ -821,6 +821,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, /* could be stupid policy setup or mtu config * so lets be conservative.. */ if ((action == TC_ACT_SHOT) || exceed_mtu) { +drop: qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -829,6 +830,8 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, skb_push(skb, skb->dev->hard_header_len); ife_meta = ife_encode(skb, metalen); + if (!ife_meta) + goto drop; spin_lock(&ife->tcf_lock); @@ -844,8 +847,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, if (err < 0) { /* too corrupt to keep around if overwritten */ spin_unlock(&ife->tcf_lock); - qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); - return TC_ACT_SHOT; + goto drop; } skboff += err; } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 2a1c00048fd6f4..58e849c0acf412 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -161,10 +161,8 @@ TC_INDIRECT_SCOPE int u32_classify(struct sk_buff *skb, int toff = off + key->off + (off2 & key->offmask); __be32 *data, hdata; - if (skb_headroom(skb) + toff > INT_MAX) - goto out; - - data = skb_header_pointer(skb, toff, 4, &hdata); + data = skb_header_pointer_careful(skb, toff, 4, + &hdata); if (!data) goto out; if ((*data ^ key->val) & key->mask) { @@ -214,8 +212,9 @@ TC_INDIRECT_SCOPE int u32_classify(struct sk_buff *skb, if (ht->divisor) { __be32 *data, hdata; - data = skb_header_pointer(skb, off + n->sel.hoff, 4, - &hdata); + data = skb_header_pointer_careful(skb, + off + n->sel.hoff, + 4, &hdata); if (!data) goto out; sel = ht->divisor & u32_hash_fold(*data, &n->sel, @@ -229,7 +228,7 @@ TC_INDIRECT_SCOPE int u32_classify(struct sk_buff *skb, if (n->sel.flags & TC_U32_VAROFFSET) { __be16 *data, hdata; - data = skb_header_pointer(skb, + data = skb_header_pointer_careful(skb, off + n->sel.offoff, 2, &hdata); if (!data) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 32bacfc314c260..d325a90cde9ee6 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1597,7 +1597,6 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_OVERLIMIT); sch->q.qlen--; - qdisc_tree_reduce_backlog(sch, 1, len); cake_heapify(q, 0); @@ -1743,14 +1742,14 @@ static void cake_reconfigure(struct Qdisc *sch); static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + u32 idx, tin, prev_qlen, prev_backlog, drop_id; struct cake_sched_data *q = qdisc_priv(sch); - int len = qdisc_pkt_len(skb); - int ret; + int len = qdisc_pkt_len(skb), ret; struct sk_buff *ack = NULL; ktime_t now = ktime_get(); struct cake_tin_data *b; struct cake_flow *flow; - u32 idx, tin; + bool same_flow = false; /* choose flow to insert into */ idx = cake_classify(sch, &b, skb, q->flow_mode, &ret); @@ -1823,6 +1822,8 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, consume_skb(skb); } else { /* not splitting */ + int ack_pkt_len = 0; + cobalt_set_enqueue_time(skb, now); get_cobalt_cb(skb)->adjusted_len = cake_overhead(q, skb); flow_queue_add(flow, skb); @@ -1833,13 +1834,13 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (ack) { b->ack_drops++; sch->qstats.drops++; - b->bytes += qdisc_pkt_len(ack); - len -= qdisc_pkt_len(ack); + ack_pkt_len = qdisc_pkt_len(ack); + b->bytes += ack_pkt_len; q->buffer_used += skb->truesize - ack->truesize; if (q->rate_flags & CAKE_FLAG_INGRESS) cake_advance_shaper(q, b, ack, now, true); - qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(ack)); + qdisc_tree_reduce_backlog(sch, 1, ack_pkt_len); consume_skb(ack); } else { sch->q.qlen++; @@ -1848,11 +1849,11 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* stats */ b->packets++; - b->bytes += len; - b->backlogs[idx] += len; - b->tin_backlog += len; - sch->qstats.backlog += len; - q->avg_window_bytes += len; + b->bytes += len - ack_pkt_len; + b->backlogs[idx] += len - ack_pkt_len; + b->tin_backlog += len - ack_pkt_len; + sch->qstats.backlog += len - ack_pkt_len; + q->avg_window_bytes += len - ack_pkt_len; } if (q->overflow_timeout) @@ -1927,24 +1928,29 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (q->buffer_used > q->buffer_max_used) q->buffer_max_used = q->buffer_used; - if (q->buffer_used > q->buffer_limit) { - bool same_flow = false; - u32 dropped = 0; - u32 drop_id; + if (q->buffer_used <= q->buffer_limit) + return NET_XMIT_SUCCESS; - while (q->buffer_used > q->buffer_limit) { - dropped++; - drop_id = cake_drop(sch, to_free); + prev_qlen = sch->q.qlen; + prev_backlog = sch->qstats.backlog; - if ((drop_id >> 16) == tin && - (drop_id & 0xFFFF) == idx) - same_flow = true; - } - b->drop_overlimit += dropped; + while (q->buffer_used > q->buffer_limit) { + drop_id = cake_drop(sch, to_free); + if ((drop_id >> 16) == tin && + (drop_id & 0xFFFF) == idx) + same_flow = true; + } + + prev_qlen -= sch->q.qlen; + prev_backlog -= sch->qstats.backlog; + b->drop_overlimit += prev_qlen; - if (same_flow) - return NET_XMIT_CN; + if (same_flow) { + qdisc_tree_reduce_backlog(sch, prev_qlen - 1, + prev_backlog - len); + return NET_XMIT_CN; } + qdisc_tree_reduce_backlog(sch, prev_qlen, prev_backlog); return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 82635dd2cfa59f..306e046276d465 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -652,7 +652,7 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); for (i = nbands; i < oldbands; i++) { - if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) + if (cl_is_active(&q->classes[i])) list_del_init(&q->classes[i].alist); qdisc_purge_queue(q->classes[i].qdisc); } @@ -664,6 +664,10 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, q->classes[i].deficit = quanta[i]; } } + for (i = q->nstrict; i < nstrict; i++) { + if (cl_is_active(&q->classes[i])) + list_del_init(&q->classes[i].alist); + } WRITE_ONCE(q->nstrict, nstrict); memcpy(q->prio2band, priomap, sizeof(priomap)); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 2255355e51d350..f94c9c9c90424c 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -373,7 +373,7 @@ static void qfq_rm_from_agg(struct qfq_sched *q, struct qfq_class *cl) /* Deschedule class and remove it from its parent aggregate. */ static void qfq_deact_rm_from_agg(struct qfq_sched *q, struct qfq_class *cl) { - if (cl->qdisc->q.qlen > 0) /* class is active */ + if (cl_is_active(cl)) /* class is active */ qfq_deactivate_class(q, cl); qfq_rm_from_agg(q, cl); @@ -529,8 +529,10 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, return 0; destroy_class: - qdisc_put(cl->qdisc); - kfree(cl); + if (!existing) { + qdisc_put(cl->qdisc); + kfree(cl); + } return err; } @@ -1481,7 +1483,7 @@ static void qfq_reset_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { - if (cl->qdisc->q.qlen > 0) + if (cl_is_active(cl)) qfq_deactivate_class(q, cl); qdisc_reset(cl->qdisc); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 8badec6d82a247..6e4bdaa876ed68 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -178,6 +178,11 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt, if (m->dev == dev) return -ELOOP; + if (sch->parent != TC_H_ROOT) { + NL_SET_ERR_MSG_MOD(extack, "teql can only be used as root"); + return -EOPNOTSUPP; + } + q->m = m; skb_queue_head_init(&q->q); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 3755ba079d077c..7b823d75914191 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -603,6 +603,11 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, sctp_add_cmd_sf(commands, SCTP_CMD_PEER_INIT, SCTP_PEER_INIT(initchunk)); + /* SCTP-AUTH: generate the association shared keys so that + * we can potentially sign the COOKIE-ECHO. + */ + sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_SHKEY, SCTP_NULL()); + /* Reset init error count upon receipt of INIT-ACK. */ sctp_add_cmd_sf(commands, SCTP_CMD_INIT_COUNTER_RESET, SCTP_NULL()); @@ -617,11 +622,6 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_COOKIE_ECHOED)); - /* SCTP-AUTH: generate the association shared keys so that - * we can potentially sign the COOKIE-ECHO. - */ - sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_SHKEY, SCTP_NULL()); - /* 5.1 C) "A" shall then send the State Cookie received in the * INIT ACK chunk in a COOKIE ECHO chunk, ... */ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ed8293a3424029..d190e75e46454a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1553,8 +1553,6 @@ static void sctp_close(struct sock *sk, long timeout) spin_unlock_bh(&net->sctp.addr_wq_lock); sock_put(sk); - - SCTP_DBG_OBJCNT_DEC(sock); } /* Handle EPIPE error. */ @@ -5109,9 +5107,12 @@ static void sctp_destroy_sock(struct sock *sk) sp->do_auto_asconf = 0; list_del(&sp->auto_asconf_list); } + sctp_endpoint_free(sp->ep); + sk_sockets_allocated_dec(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + SCTP_DBG_OBJCNT_DEC(sock); } static void sctp_destruct_sock(struct sock *sk) diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 5c095cb8cb201e..bb3c3db2713b1f 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -39,6 +39,8 @@ static const struct rpc_authops authgss_ops; static const struct rpc_credops gss_credops; static const struct rpc_credops gss_nullops; +static void gss_free_callback(struct kref *kref); + #define GSS_RETRY_EXPIRED 5 static unsigned int gss_expired_cred_retry_delay = GSS_RETRY_EXPIRED; @@ -551,6 +553,7 @@ gss_alloc_msg(struct gss_auth *gss_auth, } return gss_msg; err_put_pipe_version: + kref_put(&gss_auth->kref, gss_free_callback); put_pipe_version(gss_auth->net); err_free_msg: kfree(gss_msg); diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index 7d2cdc2bd374e2..f320c0a8e60493 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -320,29 +320,47 @@ static int gssx_dec_status(struct xdr_stream *xdr, /* status->minor_status */ p = xdr_inline_decode(xdr, 8); - if (unlikely(p == NULL)) - return -ENOSPC; + if (unlikely(p == NULL)) { + err = -ENOSPC; + goto out_free_mech; + } p = xdr_decode_hyper(p, &status->minor_status); /* status->major_status_string */ err = gssx_dec_buffer(xdr, &status->major_status_string); if (err) - return err; + goto out_free_mech; /* status->minor_status_string */ err = gssx_dec_buffer(xdr, &status->minor_status_string); if (err) - return err; + goto out_free_major_status_string; /* status->server_ctx */ err = gssx_dec_buffer(xdr, &status->server_ctx); if (err) - return err; + goto out_free_minor_status_string; /* we assume we have no options for now, so simply consume them */ /* status->options */ err = dummy_dec_opt_array(xdr, &status->options); + if (err) + goto out_free_server_ctx; + return 0; + +out_free_server_ctx: + kfree(status->server_ctx.data); + status->server_ctx.data = NULL; +out_free_minor_status_string: + kfree(status->minor_status_string.data); + status->minor_status_string.data = NULL; +out_free_major_status_string: + kfree(status->major_status_string.data); + status->major_status_string.data = NULL; +out_free_mech: + kfree(status->mech.data); + status->mech.data = NULL; return err; } @@ -505,28 +523,35 @@ static int gssx_dec_name(struct xdr_stream *xdr, /* name->name_type */ err = gssx_dec_buffer(xdr, &dummy_netobj); if (err) - return err; + goto out_free_display_name; /* name->exported_name */ err = gssx_dec_buffer(xdr, &dummy_netobj); if (err) - return err; + goto out_free_display_name; /* name->exported_composite_name */ err = gssx_dec_buffer(xdr, &dummy_netobj); if (err) - return err; + goto out_free_display_name; /* we assume we have no attributes for now, so simply consume them */ /* name->name_attributes */ err = dummy_dec_nameattr_array(xdr, &dummy_name_attr_array); if (err) - return err; + goto out_free_display_name; /* we assume we have no options for now, so simply consume them */ /* name->extensions */ err = dummy_dec_opt_array(xdr, &dummy_option_array); + if (err) + goto out_free_display_name; + return 0; + +out_free_display_name: + kfree(name->display_name.data); + name->display_name.data = NULL; return err; } @@ -649,32 +674,34 @@ static int gssx_dec_ctx(struct xdr_stream *xdr, /* ctx->state */ err = gssx_dec_buffer(xdr, &ctx->state); if (err) - return err; + goto out_free_exported_context_token; /* ctx->need_release */ err = gssx_dec_bool(xdr, &ctx->need_release); if (err) - return err; + goto out_free_state; /* ctx->mech */ err = gssx_dec_buffer(xdr, &ctx->mech); if (err) - return err; + goto out_free_state; /* ctx->src_name */ err = gssx_dec_name(xdr, &ctx->src_name); if (err) - return err; + goto out_free_mech; /* ctx->targ_name */ err = gssx_dec_name(xdr, &ctx->targ_name); if (err) - return err; + goto out_free_src_name; /* ctx->lifetime */ p = xdr_inline_decode(xdr, 8+8); - if (unlikely(p == NULL)) - return -ENOSPC; + if (unlikely(p == NULL)) { + err = -ENOSPC; + goto out_free_targ_name; + } p = xdr_decode_hyper(p, &ctx->lifetime); /* ctx->ctx_flags */ @@ -683,17 +710,36 @@ static int gssx_dec_ctx(struct xdr_stream *xdr, /* ctx->locally_initiated */ err = gssx_dec_bool(xdr, &ctx->locally_initiated); if (err) - return err; + goto out_free_targ_name; /* ctx->open */ err = gssx_dec_bool(xdr, &ctx->open); if (err) - return err; + goto out_free_targ_name; /* we assume we have no options for now, so simply consume them */ /* ctx->options */ err = dummy_dec_opt_array(xdr, &ctx->options); + if (err) + goto out_free_targ_name; + + return 0; +out_free_targ_name: + kfree(ctx->targ_name.display_name.data); + ctx->targ_name.display_name.data = NULL; +out_free_src_name: + kfree(ctx->src_name.display_name.data); + ctx->src_name.display_name.data = NULL; +out_free_mech: + kfree(ctx->mech.data); + ctx->mech.data = NULL; +out_free_state: + kfree(ctx->state.data); + ctx->state.data = NULL; +out_free_exported_context_token: + kfree(ctx->exported_context_token.data); + ctx->exported_context_token.data = NULL; return err; } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index a8ec30759a184e..e2f0df8cdaa6a0 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1083,7 +1083,8 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, } length = min_t(unsigned int, inlen, (char *)xdr->end - (char *)xdr->p); - memcpy(page_address(in_token->pages[0]), xdr->p, length); + if (length) + memcpy(page_address(in_token->pages[0]), xdr->p, length); inlen -= length; to_offs = length; diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 661b3fe2779f0c..310de7a80be52a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -841,6 +841,9 @@ static int svc_rdma_copy_inline_range(struct svc_rqst *rqstp, for (page_no = 0; page_no < numpages; page_no++) { unsigned int page_len; + if (head->rc_curpage >= rqstp->rq_maxpages) + return -EINVAL; + page_len = min_t(unsigned int, remaining, PAGE_SIZE - head->rc_pageoff); @@ -848,7 +851,7 @@ static int svc_rdma_copy_inline_range(struct svc_rqst *rqstp, head->rc_page_count++; dst = page_address(rqstp->rq_pages[head->rc_curpage]); - memcpy(dst + head->rc_curpage, src + offset, page_len); + memcpy((unsigned char *)dst + head->rc_pageoff, src + offset, page_len); head->rc_readbytes += page_len; head->rc_pageoff += page_len; @@ -860,7 +863,7 @@ static int svc_rdma_copy_inline_range(struct svc_rqst *rqstp, offset += page_len; } - return -EINVAL; + return 0; } /** diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 3d7f1413df0233..12857381e86104 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -462,7 +462,10 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) newxprt->sc_max_bc_requests = 2; } - /* Arbitrary estimate of the needed number of rdma_rw contexts. + /* Estimate the needed number of rdma_rw contexts. The maximum + * Read and Write chunks have one segment each. Each request + * can involve one Read chunk and either a Write chunk or Reply + * chunk; thus a factor of three. */ maxpayload = min(xprt->xpt_server->sv_max_payload, RPCSVC_MAXPAYLOAD_RDMA); @@ -470,7 +473,8 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) rdma_rw_mr_factor(dev, newxprt->sc_port_num, maxpayload >> PAGE_SHIFT); - newxprt->sc_sq_depth = rq_depth + ctxts; + newxprt->sc_sq_depth = rq_depth + + rdma_rw_max_send_wr(dev, newxprt->sc_port_num, ctxts, 0); if (newxprt->sc_sq_depth > dev->attrs.max_qp_wr) newxprt->sc_sq_depth = dev->attrs.max_qp_wr; atomic_set(&newxprt->sc_sq_avail, newxprt->sc_sq_depth); diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 751904f10aab00..970db62bd029b2 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1219,7 +1219,7 @@ void tipc_crypto_key_flush(struct tipc_crypto *c) rx = c; tx = tipc_net(rx->net)->crypto_tx; if (cancel_delayed_work(&rx->work)) { - kfree(rx->skey); + kfree_sensitive(rx->skey); rx->skey = NULL; atomic_xchg(&rx->key_distr, 0); tipc_node_put(rx->node); @@ -2394,7 +2394,7 @@ static void tipc_crypto_work_rx(struct work_struct *work) break; default: synchronize_rcu(); - kfree(rx->skey); + kfree_sensitive(rx->skey); rx->skey = NULL; break; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 833c3616d2a2b4..9dad3af700af3e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1671,10 +1671,9 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); - /* First of all allocate resources. - * If we will make it after state is locked, - * we will have to recheck all again in any case. - */ + err = prepare_peercred(&peercred); + if (err) + goto out; /* create new sock for complete connection */ newsk = unix_create1(net, NULL, 0, sock->type); @@ -1683,10 +1682,6 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, goto out; } - err = prepare_peercred(&peercred); - if (err) - goto out; - /* Allocate skb for sending to listening sock */ skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL); if (!skb) { @@ -3111,12 +3106,15 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, mutex_unlock(&u->iolock); if (msg) { + bool do_cmsg = READ_ONCE(u->recvmsg_inq); + scm_recv_unix(sock, msg, &scm, flags); - if (READ_ONCE(u->recvmsg_inq) || msg->msg_get_inq) { + if ((do_cmsg | msg->msg_get_inq) && (copied ?: err) >= 0) { msg->msg_inq = READ_ONCE(u->inq_len); - put_cmsg(msg, SOL_SOCKET, SCM_INQ, - sizeof(msg->msg_inq), &msg->msg_inq); + if (do_cmsg) + put_cmsg(msg, SOL_SOCKET, SCM_INQ, + sizeof(msg->msg_inq), &msg->msg_inq); } } else { scm_destroy(&scm); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index a9ca9c3b87b31a..cbd649bf01459d 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1787,6 +1787,10 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, } else { newsock->state = SS_CONNECTED; sock_graft(connected, newsock); + + set_bit(SOCK_CUSTOM_SOCKOPT, + &connected->sk_socket->flags); + if (vsock_msgzerocopy_allow(vconnected->transport)) set_bit(SOCK_SUPPORT_ZC, &connected->sk_socket->flags); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index dcc8a1d5851e6a..d3e26025ef589a 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -28,6 +28,7 @@ static void virtio_transport_cancel_close_work(struct vsock_sock *vsk, bool cancel_timeout); +static s64 virtio_transport_has_space(struct virtio_vsock_sock *vvs); static const struct virtio_transport * virtio_transport_get_ops(struct vsock_sock *vsk) @@ -499,9 +500,7 @@ u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) return 0; spin_lock_bh(&vvs->tx_lock); - ret = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); - if (ret > credit) - ret = credit; + ret = min_t(u32, credit, virtio_transport_has_space(vvs)); vvs->tx_cnt += ret; vvs->bytes_unsent += ret; spin_unlock_bh(&vvs->tx_lock); @@ -822,6 +821,15 @@ virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, } EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue); +static u32 virtio_transport_tx_buf_size(struct virtio_vsock_sock *vvs) +{ + /* The peer advertises its receive buffer via peer_buf_alloc, but we + * cap it to our local buf_alloc so a remote peer cannot force us to + * queue more data than our own buffer configuration allows. + */ + return min(vvs->peer_buf_alloc, vvs->buf_alloc); +} + int virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, struct msghdr *msg, @@ -831,7 +839,7 @@ virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, spin_lock_bh(&vvs->tx_lock); - if (len > vvs->peer_buf_alloc) { + if (len > virtio_transport_tx_buf_size(vvs)) { spin_unlock_bh(&vvs->tx_lock); return -EMSGSIZE; } @@ -877,12 +885,16 @@ u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_has_data); -static s64 virtio_transport_has_space(struct vsock_sock *vsk) +static s64 virtio_transport_has_space(struct virtio_vsock_sock *vvs) { - struct virtio_vsock_sock *vvs = vsk->trans; s64 bytes; - bytes = (s64)vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + /* Use s64 arithmetic so if the peer shrinks peer_buf_alloc while + * we have bytes in flight (tx_cnt - peer_fwd_cnt), the subtraction + * does not underflow. + */ + bytes = (s64)virtio_transport_tx_buf_size(vvs) - + (vvs->tx_cnt - vvs->peer_fwd_cnt); if (bytes < 0) bytes = 0; @@ -895,7 +907,7 @@ s64 virtio_transport_stream_has_space(struct vsock_sock *vsk) s64 bytes; spin_lock_bh(&vvs->tx_lock); - bytes = virtio_transport_has_space(vsk); + bytes = virtio_transport_has_space(vvs); spin_unlock_bh(&vvs->tx_lock); return bytes; @@ -1359,9 +1371,11 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, /* Try to copy small packets into the buffer of last packet queued, * to avoid wasting memory queueing the entire buffer with a small - * payload. + * payload. Skip non-linear (e.g. zerocopy) skbs; these carry payload + * in skb_shinfo. */ - if (len <= GOOD_COPY_LEN && !skb_queue_empty(&vvs->rx_queue)) { + if (len <= GOOD_COPY_LEN && !skb_queue_empty(&vvs->rx_queue) && + !skb_is_nonlinear(skb)) { struct virtio_vsock_hdr *last_hdr; struct sk_buff *last_skb; @@ -1490,7 +1504,7 @@ static bool virtio_transport_space_update(struct sock *sk, spin_lock_bh(&vvs->tx_lock); vvs->peer_buf_alloc = le32_to_cpu(hdr->buf_alloc); vvs->peer_fwd_cnt = le32_to_cpu(hdr->fwd_cnt); - space_available = virtio_transport_has_space(vsk); + space_available = virtio_transport_has_space(vvs); spin_unlock_bh(&vvs->tx_lock); return space_available; } diff --git a/net/wireless/core.c b/net/wireless/core.c index 54a34d8d356e04..87f083d9247a43 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1365,6 +1365,7 @@ void cfg80211_leave(struct cfg80211_registered_device *rdev, cfg80211_pmsr_wdev_down(wdev); + cfg80211_stop_radar_detection(wdev); cfg80211_stop_background_radar_detection(wdev); switch (wdev->iftype) { @@ -1399,8 +1400,10 @@ void cfg80211_leave(struct cfg80211_registered_device *rdev, cfg80211_leave_ocb(rdev, dev); break; case NL80211_IFTYPE_P2P_DEVICE: + cfg80211_stop_p2p_device(rdev, wdev); + break; case NL80211_IFTYPE_NAN: - /* cannot happen, has no netdev */ + cfg80211_stop_nan(rdev, wdev); break; case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: diff --git a/net/wireless/core.h b/net/wireless/core.h index b6bd7f4d6385a1..d5d78752227af9 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -489,6 +489,7 @@ cfg80211_start_background_radar_detection(struct cfg80211_registered_device *rde struct wireless_dev *wdev, struct cfg80211_chan_def *chandef); +void cfg80211_stop_radar_detection(struct wireless_dev *wdev); void cfg80211_stop_background_radar_detection(struct wireless_dev *wdev); void cfg80211_background_cac_done_wk(struct work_struct *work); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 46394eb2086f6e..3fc175f9f86861 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -1295,6 +1295,25 @@ cfg80211_start_background_radar_detection(struct cfg80211_registered_device *rde return 0; } +void cfg80211_stop_radar_detection(struct wireless_dev *wdev) +{ + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + int link_id; + + for_each_valid_link(wdev, link_id) { + struct cfg80211_chan_def chandef; + + if (!wdev->links[link_id].cac_started) + continue; + + chandef = *wdev_chandef(wdev, link_id); + rdev_end_cac(rdev, wdev->netdev, link_id); + nl80211_radar_notify(rdev, &chandef, NL80211_RADAR_CAC_ABORTED, + wdev->netdev, GFP_KERNEL); + } +} + void cfg80211_stop_background_radar_detection(struct wireless_dev *wdev) { struct wiphy *wiphy = wdev->wiphy; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 90a9187a6b135e..9a0c02c23dc56c 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1959,7 +1959,7 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, ether_addr_copy(known->parent_bssid, new->parent_bssid); known->pub.max_bssid_indicator = new->pub.max_bssid_indicator; known->pub.bssid_index = new->pub.bssid_index; - known->pub.use_for &= new->pub.use_for; + known->pub.use_for = new->pub.use_for; known->pub.cannot_use_reasons = new->pub.cannot_use_reasons; known->bss_source = new->bss_source; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 3a028ff287fbbe..4e629ca305bcc3 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -910,7 +910,7 @@ void __cfg80211_connect_result(struct net_device *dev, ssid_len = min(ssid->datalen, IEEE80211_MAX_SSID_LEN); memcpy(wdev->u.client.ssid, ssid->data, ssid_len); - wdev->u.client.ssid_len = ssid->datalen; + wdev->u.client.ssid_len = ssid_len; break; } rcu_read_unlock(); diff --git a/net/wireless/util.c b/net/wireless/util.c index 56724b33af0455..81d6d27d273cc8 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1203,28 +1203,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, dev->ieee80211_ptr->use_4addr = false; rdev_set_qos_map(rdev, dev, NULL); - switch (otype) { - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_P2P_GO: - cfg80211_stop_ap(rdev, dev, -1, true); - break; - case NL80211_IFTYPE_ADHOC: - cfg80211_leave_ibss(rdev, dev, false); - break; - case NL80211_IFTYPE_STATION: - case NL80211_IFTYPE_P2P_CLIENT: - cfg80211_disconnect(rdev, dev, - WLAN_REASON_DEAUTH_LEAVING, true); - break; - case NL80211_IFTYPE_MESH_POINT: - /* mesh should be handled? */ - break; - case NL80211_IFTYPE_OCB: - cfg80211_leave_ocb(rdev, dev); - break; - default: - break; - } + cfg80211_leave(rdev, dev->ieee80211_ptr); cfg80211_process_rdev_events(rdev); cfg80211_mlme_purge_registrations(dev->ieee80211_ptr); @@ -1582,12 +1561,14 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) tmp = result; tmp *= SCALE; do_div(tmp, mcs_divisors[rate->mcs]); - result = tmp; /* and take NSS, DCM into account */ - result = (result * rate->nss) / 8; + tmp *= rate->nss; + do_div(tmp, 8); if (rate->he_dcm) - result /= 2; + do_div(tmp, 2); + + result = tmp; return result / 10000; } diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index c32a7c6903d536..7b8e94214b0722 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -1101,6 +1101,10 @@ static int compat_standard_call(struct net_device *dev, return ioctl_standard_call(dev, iwr, cmd, info, handler); iwp_compat = (struct compat_iw_point *) &iwr->u.data; + + /* struct iw_point has a 32bit hole on 64bit arches. */ + memset(&iwp, 0, sizeof(iwp)); + iwp.pointer = compat_ptr(iwp_compat->pointer); iwp.length = iwp_compat->length; iwp.flags = iwp_compat->flags; diff --git a/net/wireless/wext-priv.c b/net/wireless/wext-priv.c index 674d426a9d24f9..37d1147019c2ba 100644 --- a/net/wireless/wext-priv.c +++ b/net/wireless/wext-priv.c @@ -228,6 +228,10 @@ int compat_private_call(struct net_device *dev, struct iwreq *iwr, struct iw_point iwp; iwp_compat = (struct compat_iw_point *) &iwr->u.data; + + /* struct iw_point has a 32bit hole on 64bit arches. */ + memset(&iwp, 0, sizeof(iwp)); + iwp.pointer = compat_ptr(iwp_compat->pointer); iwp.length = iwp_compat->length; iwp.flags = iwp_compat->flags; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 9e14e453b55cc9..98b362d518363b 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -3151,6 +3151,7 @@ int __xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) int err; if (family == AF_INET && + (!x->dir || x->dir == XFRM_SA_DIR_OUT) && READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)) x->props.flags |= XFRM_STATE_NOPMTUDISC; diff --git a/rust/bindgen_parameters b/rust/bindgen_parameters index e13c6f9dd17b22..8d84acb7a15be7 100644 --- a/rust/bindgen_parameters +++ b/rust/bindgen_parameters @@ -12,9 +12,15 @@ # Packed type cannot transitively contain a `#[repr(align)]` type. --opaque-type alt_instr +--opaque-type snd_codec_options +--opaque-type snd_codec +--opaque-type snd_compr_params --opaque-type x86_msi_data --opaque-type x86_msi_addr_lo +# Packed types cannot have larger alignment than the maximal natural aligment of menbers +--opaque-type snd_dec_flac + # `try` is a reserved keyword since Rust 2018; solved in `bindgen` v0.59.2, # commit 2aed6b021680 ("context: Escape the try keyword properly"). --opaque-type kunit_try_catch diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index 2e43c66635a2c9..12c92a5d203571 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -31,9 +31,14 @@ #include #include #include +#include #include #include +#include +#include #include +#include +#include #include #include #include @@ -48,9 +53,13 @@ #include #include #include +#include #include #include +#include +#include #include +#include #include #include #include @@ -58,13 +67,19 @@ #include #include #include +#include +#include #include +#include #include #include #include #include #include +#include +#include #include +#include #include #include #include @@ -78,11 +93,16 @@ #include #include #include +#include +#include #include #include #include #include #include +#include +#include +#include #include #if defined(CONFIG_DRM_PANIC_SCREEN_QR_CODE) @@ -102,8 +122,16 @@ const gfp_t RUST_CONST_HELPER___GFP_ZERO = __GFP_ZERO; const gfp_t RUST_CONST_HELPER___GFP_HIGHMEM = ___GFP_HIGHMEM; const gfp_t RUST_CONST_HELPER___GFP_NOWARN = ___GFP_NOWARN; const blk_features_t RUST_CONST_HELPER_BLK_FEAT_ROTATIONAL = BLK_FEAT_ROTATIONAL; +const uint32_t RUST_CONST_HELPER_DRM_EXEC_INTERRUPTIBLE_WAIT = DRM_EXEC_INTERRUPTIBLE_WAIT; const fop_flags_t RUST_CONST_HELPER_FOP_UNSIGNED_OFFSET = FOP_UNSIGNED_OFFSET; +const u64 BINDINGS_SNDRV_PCM_FMTBIT_FLOAT_LE = SNDRV_PCM_FMTBIT_FLOAT_LE; + +const u32 BINDINGS_IIO_CHAN_INFO_RAW = IIO_CHAN_INFO_RAW; +const u32 BINDINGS_IIO_CHAN_INFO_PROCESSED = IIO_CHAN_INFO_PROCESSED; +const u32 BINDINGS_IIO_ANGL = IIO_ANGL; +const u32 BINDINGS_IIO_LIGHT = IIO_LIGHT; + const xa_mark_t RUST_CONST_HELPER_XA_PRESENT = XA_PRESENT; const gfp_t RUST_CONST_HELPER_XA_FLAGS_ALLOC = XA_FLAGS_ALLOC; diff --git a/rust/helpers/bitops.c b/rust/helpers/bitops.c index 5d0861d29d3f0d..e79ef9e6d98f96 100644 --- a/rust/helpers/bitops.c +++ b/rust/helpers/bitops.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include void rust_helper___set_bit(unsigned long nr, unsigned long *addr) { @@ -21,3 +22,44 @@ void rust_helper_clear_bit(unsigned long nr, volatile unsigned long *addr) { clear_bit(nr, addr); } + +/* + * The rust_helper_ prefix is intentionally omitted below so that the + * declarations in include/linux/find.h are compatible with these helpers. + * + * Note that the below #ifdefs mean that the helper is only created if C does + * not provide a definition. + */ +#ifdef find_first_zero_bit +__rust_helper +unsigned long _find_first_zero_bit(const unsigned long *p, unsigned long size) +{ + return find_first_zero_bit(p, size); +} +#endif /* find_first_zero_bit */ + +#ifdef find_next_zero_bit +__rust_helper +unsigned long _find_next_zero_bit(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + return find_next_zero_bit(addr, size, offset); +} +#endif /* find_next_zero_bit */ + +#ifdef find_first_bit +__rust_helper +unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) +{ + return find_first_bit(addr, size); +} +#endif /* find_first_bit */ + +#ifdef find_next_bit +__rust_helper +unsigned long _find_next_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + return find_next_bit(addr, size, offset); +} +#endif /* find_next_bit */ diff --git a/rust/helpers/device.c b/rust/helpers/device.c index 9a4316bafedfbc..41c3f4df8909e8 100644 --- a/rust/helpers/device.c +++ b/rust/helpers/device.c @@ -25,3 +25,13 @@ void rust_helper_dev_set_drvdata(struct device *dev, void *data) { dev_set_drvdata(dev, data); } + +void rust_helper_device_lock(struct device *dev) +{ + device_lock(dev); +} + +void rust_helper_device_unlock(struct device *dev) +{ + device_unlock(dev); +} diff --git a/rust/helpers/dma-fence.c b/rust/helpers/dma-fence.c new file mode 100644 index 00000000000000..6491016262934b --- /dev/null +++ b/rust/helpers/dma-fence.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +#ifdef CONFIG_DMA_SHARED_BUFFER + +void rust_helper_dma_fence_get(struct dma_fence *fence) +{ + dma_fence_get(fence); +} + +void rust_helper_dma_fence_put(struct dma_fence *fence) +{ + dma_fence_put(fence); +} + +struct dma_fence_chain *rust_helper_dma_fence_chain_alloc(void) +{ + return dma_fence_chain_alloc(); +} + +void rust_helper_dma_fence_chain_free(struct dma_fence_chain *chain) +{ + dma_fence_chain_free(chain); +} + +void rust_helper_dma_fence_set_error(struct dma_fence *fence, int error) +{ + dma_fence_set_error(fence, error); +} + +#endif diff --git a/rust/helpers/dma-mapping.c b/rust/helpers/dma-mapping.c new file mode 100644 index 00000000000000..0d795b1b0738dc --- /dev/null +++ b/rust/helpers/dma-mapping.c @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +int rust_helper_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return dma_mapping_error(dev, dma_addr); +} diff --git a/rust/helpers/dma-resv.c b/rust/helpers/dma-resv.c new file mode 100644 index 00000000000000..05501cb814513b --- /dev/null +++ b/rust/helpers/dma-resv.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +int rust_helper_dma_resv_lock(struct dma_resv *obj, struct ww_acquire_ctx *ctx) +{ + return dma_resv_lock(obj, ctx); +} + +void rust_helper_dma_resv_unlock(struct dma_resv *obj) +{ + dma_resv_unlock(obj); +} diff --git a/rust/helpers/dma.c b/rust/helpers/dma.c index 6e741c19724257..2afa32c21c946e 100644 --- a/rust/helpers/dma.c +++ b/rust/helpers/dma.c @@ -19,3 +19,24 @@ int rust_helper_dma_set_mask_and_coherent(struct device *dev, u64 mask) { return dma_set_mask_and_coherent(dev, mask); } + +int rust_helper_dma_set_mask(struct device *dev, u64 mask) +{ + return dma_set_mask(dev, mask); +} + +int rust_helper_dma_set_coherent_mask(struct device *dev, u64 mask) +{ + return dma_set_coherent_mask(dev, mask); +} + +int rust_helper_dma_map_sgtable(struct device *dev, struct sg_table *sgt, + enum dma_data_direction dir, unsigned long attrs) +{ + return dma_map_sgtable(dev, sgt, dir, attrs); +} + +size_t rust_helper_dma_max_mapping_size(struct device *dev) +{ + return dma_max_mapping_size(dev); +} diff --git a/rust/helpers/drm.c b/rust/helpers/drm.c index 450b406c6f2739..a4e997d0b47320 100644 --- a/rust/helpers/drm.c +++ b/rust/helpers/drm.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #ifdef CONFIG_DRM @@ -20,4 +21,49 @@ __u64 rust_helper_drm_vma_node_offset_addr(struct drm_vma_offset_node *node) return drm_vma_node_offset_addr(node); } -#endif +#ifdef CONFIG_DRM_GEM_SHMEM_HELPER +void rust_helper_drm_gem_shmem_object_free(struct drm_gem_object *obj) +{ + return drm_gem_shmem_object_free(obj); +} + +void rust_helper_drm_gem_shmem_object_print_info(struct drm_printer *p, unsigned int indent, + const struct drm_gem_object *obj) +{ + drm_gem_shmem_object_print_info(p, indent, obj); +} + +int rust_helper_drm_gem_shmem_object_pin(struct drm_gem_object *obj) +{ + return drm_gem_shmem_object_pin(obj); +} + +void rust_helper_drm_gem_shmem_object_unpin(struct drm_gem_object *obj) +{ + drm_gem_shmem_object_unpin(obj); +} + +struct sg_table *rust_helper_drm_gem_shmem_object_get_sg_table(struct drm_gem_object *obj) +{ + return drm_gem_shmem_object_get_sg_table(obj); +} + +int rust_helper_drm_gem_shmem_object_vmap(struct drm_gem_object *obj, + struct iosys_map *map) +{ + return drm_gem_shmem_object_vmap(obj, map); +} + +void rust_helper_drm_gem_shmem_object_vunmap(struct drm_gem_object *obj, + struct iosys_map *map) +{ + drm_gem_shmem_object_vunmap(obj, map); +} + +int rust_helper_drm_gem_shmem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) +{ + return drm_gem_shmem_object_mmap(obj, vma); +} + +#endif /* CONFIG_DRM_GEM_SHMEM_HELPER */ +#endif /* CONFIG_DRM */ diff --git a/rust/helpers/drm_gpuvm.c b/rust/helpers/drm_gpuvm.c new file mode 100644 index 00000000000000..1ed5b5841f68c2 --- /dev/null +++ b/rust/helpers/drm_gpuvm.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +#ifdef CONFIG_DRM +#ifdef CONFIG_DRM_GPUVM + +struct drm_gpuvm *rust_helper_drm_gpuvm_get(struct drm_gpuvm *obj) +{ + return drm_gpuvm_get(obj); +} + +void rust_helper_drm_gpuvm_exec_unlock(struct drm_gpuvm_exec *vm_exec) +{ + return drm_gpuvm_exec_unlock(vm_exec); +} + +void rust_helper_drm_gpuva_init_from_op(struct drm_gpuva *va, struct drm_gpuva_op_map *op) +{ + drm_gpuva_init_from_op(va, op); +} + +struct drm_gpuvm_bo *rust_helper_drm_gpuvm_bo_get(struct drm_gpuvm_bo *vm_bo) +{ + return drm_gpuvm_bo_get(vm_bo); +} + +bool rust_helper_drm_gpuvm_immediate_mode(struct drm_gpuvm *gpuvm) +{ + return drm_gpuvm_immediate_mode(gpuvm); +} + +bool rust_helper_drm_gpuvm_is_extobj(struct drm_gpuvm *gpuvm, struct drm_gem_object *obj) +{ + return drm_gpuvm_is_extobj(gpuvm, obj); +} + +#endif +#endif diff --git a/rust/helpers/drm_syncobj.c b/rust/helpers/drm_syncobj.c new file mode 100644 index 00000000000000..9e14c989edfd72 --- /dev/null +++ b/rust/helpers/drm_syncobj.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +#ifdef CONFIG_DRM + +void rust_helper_drm_syncobj_get(struct drm_syncobj *obj) +{ + drm_syncobj_get(obj); +} + +void rust_helper_drm_syncobj_put(struct drm_syncobj *obj) +{ + drm_syncobj_put(obj); +} + +struct dma_fence *rust_helper_drm_syncobj_fence_get(struct drm_syncobj *syncobj) +{ + return drm_syncobj_fence_get(syncobj); +} + +#endif diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c index 551da6c9b5064c..81c69e7ac46bf2 100644 --- a/rust/helpers/helpers.c +++ b/rust/helpers/helpers.c @@ -25,11 +25,17 @@ #include "cred.c" #include "device.c" #include "dma.c" +#include "dma-fence.c" +#include "dma-mapping.c" +#include "dma-resv.c" #include "drm.c" +#include "drm_gpuvm.c" +#include "drm_syncobj.c" #include "err.c" #include "irq.c" #include "fs.c" #include "io.c" +#include "iosys_map.c" #include "jump_label.c" #include "kunit.c" #include "maple_tree.c" diff --git a/rust/helpers/io.c b/rust/helpers/io.c index c475913c69e647..6b1b05ab977b0c 100644 --- a/rust/helpers/io.c +++ b/rust/helpers/io.c @@ -18,6 +18,16 @@ void rust_helper_iounmap(void __iomem *addr) iounmap(addr); } +void rust_helper_memcpy_fromio(void *to, const void __iomem *from, long count) +{ + memcpy_fromio(to, from, count); +} + +void rust_helper_memcpy_toio(void __iomem *to, const void *from, size_t count) +{ + memcpy_toio(to, from, count); +} + u8 rust_helper_readb(const void __iomem *addr) { return readb(addr); diff --git a/rust/helpers/iosys_map.c b/rust/helpers/iosys_map.c new file mode 100644 index 00000000000000..f99598367147ff --- /dev/null +++ b/rust/helpers/iosys_map.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +void rust_helper_iosys_map_memcpy_to(struct iosys_map *dst, size_t dst_offset, + const void *src, size_t len) +{ + iosys_map_memcpy_to(dst, dst_offset, src, len); +} + +void rust_helper_iosys_map_memcpy_from(void *dst, const struct iosys_map *src, + size_t src_offset, size_t len) +{ + iosys_map_memcpy_from(dst, src, src_offset, len); +} + +void rust_helper_iosys_map_memset(struct iosys_map *dst, size_t offset, + int value, size_t len) +{ + iosys_map_memset(dst, offset, value, len); +} diff --git a/rust/helpers/of.c b/rust/helpers/of.c index 86b51167c913f9..8c3958795357c0 100644 --- a/rust/helpers/of.c +++ b/rust/helpers/of.c @@ -1,8 +1,29 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include bool rust_helper_is_of_node(const struct fwnode_handle *fwnode) { return is_of_node(fwnode); } + +const struct of_device_id *rust_helper_of_match_device( + const struct of_device_id *matches, const struct device *dev) +{ + return of_match_device(matches, dev); +} + +#ifdef CONFIG_OF +bool rust_helper_of_node_is_root(const struct device_node *np) +{ + return of_node_is_root(np); +} +#endif + +struct device_node *rust_helper_of_parse_phandle(const struct device_node *np, + const char *phandle_name, + int index) +{ + return of_parse_phandle(np, phandle_name, index); +} diff --git a/rust/helpers/page.c b/rust/helpers/page.c index 7144de5a61dbdb..1e15bb4d525b59 100644 --- a/rust/helpers/page.c +++ b/rust/helpers/page.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include #include @@ -25,3 +26,28 @@ int rust_helper_page_to_nid(const struct page *page) return page_to_nid(page); } #endif + +struct page *rust_helper_phys_to_page(phys_addr_t phys) +{ + return phys_to_page(phys); +} + +phys_addr_t rust_helper_page_to_phys(struct page *page) +{ + return page_to_phys(page); +} + +unsigned long rust_helper_phys_to_pfn(phys_addr_t phys) +{ + return __phys_to_pfn(phys); +} + +struct page *rust_helper_pfn_to_page(unsigned long pfn) +{ + return pfn_to_page(pfn); +} + +bool rust_helper_pfn_valid(unsigned long pfn) +{ + return pfn_valid(pfn); +} diff --git a/rust/helpers/xarray.c b/rust/helpers/xarray.c index 60b299f11451d2..b6c078e6a343c2 100644 --- a/rust/helpers/xarray.c +++ b/rust/helpers/xarray.c @@ -2,6 +2,11 @@ #include +void *rust_helper_xa_zero_entry(void) +{ + return XA_ZERO_ENTRY; +} + int rust_helper_xa_err(void *entry) { return xa_err(entry); diff --git a/rust/kernel/addr.rs b/rust/kernel/addr.rs new file mode 100644 index 00000000000000..06aff10a033235 --- /dev/null +++ b/rust/kernel/addr.rs @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Kernel core address types. + +use bindings; +use core::ffi; + +/// A physical memory address (which may be wider than the CPU pointer size) +pub type PhysicalAddr = bindings::phys_addr_t; +/// A DMA memory address (which may be narrower than `PhysicalAddr` on some systems) +pub type DmaAddr = bindings::dma_addr_t; +/// A physical resource size, typically the same width as `PhysicalAddr` +pub type ResourceSize = bindings::resource_size_t; +/// A raw page frame number, not to be confused with the C `pfn_t` which also encodes flags. +pub type Pfn = ffi::c_ulong; diff --git a/rust/kernel/alloc.rs b/rust/kernel/alloc.rs index e38720349dcf7e..719927971f5796 100644 --- a/rust/kernel/alloc.rs +++ b/rust/kernel/alloc.rs @@ -18,6 +18,8 @@ pub use self::kvec::KVec; pub use self::kvec::VVec; pub use self::kvec::Vec; +use crate::types::declare_flags_type; + /// Indicates an allocation error. #[derive(Copy, Clone, PartialEq, Eq, Debug)] pub struct AllocError; @@ -25,45 +27,13 @@ pub struct AllocError; use crate::error::{code::EINVAL, Result}; use core::{alloc::Layout, ptr::NonNull}; -/// Flags to be used when allocating memory. -/// -/// They can be combined with the operators `|`, `&`, and `!`. -/// -/// Values can be used from the [`flags`] module. -#[derive(Clone, Copy, PartialEq)] -pub struct Flags(u32); - -impl Flags { - /// Get the raw representation of this flag. - pub(crate) fn as_raw(self) -> u32 { - self.0 - } - - /// Check whether `flags` is contained in `self`. - pub fn contains(self, flags: Flags) -> bool { - (self & flags) == flags - } -} - -impl core::ops::BitOr for Flags { - type Output = Self; - fn bitor(self, rhs: Self) -> Self::Output { - Self(self.0 | rhs.0) - } -} - -impl core::ops::BitAnd for Flags { - type Output = Self; - fn bitand(self, rhs: Self) -> Self::Output { - Self(self.0 & rhs.0) - } -} - -impl core::ops::Not for Flags { - type Output = Self; - fn not(self) -> Self::Output { - Self(!self.0) - } +declare_flags_type! { + /// Flags to be used when allocating memory. + /// + /// They can be combined with the operators `|`, `&`, and `!`. + /// + /// Values can be used from the [`flags`] module. + pub struct Flags(u32); } /// Allocation flags. diff --git a/rust/kernel/alloc/allocator.rs b/rust/kernel/alloc/allocator.rs index 63bfb91b36712a..1a53412c458dd3 100644 --- a/rust/kernel/alloc/allocator.rs +++ b/rust/kernel/alloc/allocator.rs @@ -1,4 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 +// FIXME +#![allow(clippy::undocumented_unsafe_blocks)] //! Allocator support. //! diff --git a/rust/kernel/alloc/kbox.rs b/rust/kernel/alloc/kbox.rs index 622b3529edfcbc..2684598cde4cbe 100644 --- a/rust/kernel/alloc/kbox.rs +++ b/rust/kernel/alloc/kbox.rs @@ -682,6 +682,16 @@ where } } +impl AsRef for Box +where + T: ?Sized, + A: Allocator, +{ + fn as_ref(&self) -> &T { + self + } +} + /// # Examples /// /// ``` diff --git a/rust/kernel/alloc/kvec.rs b/rust/kernel/alloc/kvec.rs index ac8d6f763ae81d..6cc48330515dd1 100644 --- a/rust/kernel/alloc/kvec.rs +++ b/rust/kernel/alloc/kvec.rs @@ -19,12 +19,15 @@ use core::{ ops::DerefMut, ops::Index, ops::IndexMut, + ops::{Range, RangeBounds}, ptr, ptr::NonNull, slice, slice::SliceIndex, }; +mod drain; +use self::drain::Drain; mod errors; pub use self::errors::{InsertError, PushError, RemoveError}; @@ -192,6 +195,19 @@ where self.len } + /// Forcefully sets `self.len` to `new_len`. + /// + /// # Safety + /// + /// - `new_len` must be less than or equal to [`Self::capacity`]. + /// - If `new_len` is greater than `self.len`, all elements within the interval + /// [`self.len`,`new_len`) must be initialized. + #[inline] + pub unsafe fn set_len(&mut self, new_len: usize) { + debug_assert!(new_len <= self.capacity()); + self.len = new_len; + } + /// Increments `self.len` by `additional`. /// /// # Safety @@ -733,6 +749,76 @@ where } self.truncate(num_kept); } + + /// Removes the specified range from the vector in bulk, returning all + /// removed elements as an iterator. If the iterator is dropped before + /// being fully consumed, it drops the remaining removed elements. + /// + /// The returned iterator keeps a mutable borrow on the vector to optimize + /// its implementation. + /// + /// # Panics + /// + /// Panics if the starting point is greater than the end point or if + /// the end point is greater than the length of the vector. + /// + /// # Leaking + /// + /// If the returned iterator goes out of scope without being dropped (due to + /// [`mem::forget`], for example), the vector may have lost and leaked + /// elements arbitrarily, including elements outside the range. + /// + /// # Examples + /// + /// ``` + /// let mut v = vec![1, 2, 3]; + /// let u: Vec<_> = v.drain(1..).collect(); + /// assert_eq!(v, &[1]); + /// assert_eq!(u, &[2, 3]); + /// + /// // A full range clears the vector, like `clear()` does + /// v.drain(..); + /// assert_eq!(v, &[]); + /// ``` + pub fn drain(&mut self, range: R) -> Drain<'_, T, A> + where + R: RangeBounds, + { + let len = self.len(); + let Range { start, end } = slice::range(range, ..len); + + unsafe { + // set self.vec length's to start, to be safe in case Drain is leaked + self.set_len(start); + let range_slice = slice::from_raw_parts(self.as_ptr().add(start), end - start); + Drain { + tail_start: end, + tail_len: len - end, + iter: range_slice.iter(), + vec: NonNull::from(self), + } + } + } + /// Removes an element from the vector and returns it. + /// + /// The removed element is replaced by the last element of the vector. + /// + /// This does not preserve ordering of the remaining elements, but is *O*(1). + /// If you need to preserve the element order, use [`remove`] instead. + pub fn swap_remove(&mut self, index: usize) -> T { + if index > self.len() { + panic!("Index out of range"); + } + // SAFETY: index is in range + // self.len() - 1 is in range since at last 1 element exists + unsafe { + let old = ptr::read(self.as_ptr().add(index)); + let last = ptr::read(self.as_ptr().add(self.len() - 1)); + ptr::write(self.as_mut_ptr().add(index), last); + self.dec_len(1); + old + } + } } impl Vec { @@ -1399,3 +1485,51 @@ mod tests { } } } + +// #[stable(feature = "array_try_from_vec", since = "1.48.0")] +impl TryFrom> for [T; N] { + type Error = Vec; + + /// Gets the entire contents of the `Vec` as an array, + /// if its size exactly matches that of the requested array. + /// + /// # Examples + /// + /// ``` + /// assert_eq!(vec![1, 2, 3].try_into(), Ok([1, 2, 3])); + /// assert_eq!(>::new().try_into(), Ok([])); + /// ``` + /// + /// If the length doesn't match, the input comes back in `Err`: + /// ``` + /// let r: Result<[i32; 4], _> = (0..10).collect::>().try_into(); + /// assert_eq!(r, Err(vec![0, 1, 2, 3, 4, 5, 6, 7, 8, 9])); + /// ``` + /// + /// If you're fine with just getting a prefix of the `Vec`, + /// you can call [`.truncate(N)`](Vec::truncate) first. + /// ``` + /// let mut v = String::from("hello world").into_bytes(); + /// v.sort(); + /// v.truncate(2); + /// let [a, b]: [_; 2] = v.try_into().unwrap(); + /// assert_eq!(a, b' '); + /// assert_eq!(b, b'd'); + /// ``` + fn try_from(mut vec: Vec) -> Result<[T; N], Vec> { + if vec.len() != N { + return Err(vec); + } + + // SAFETY: `.set_len(0)` is always sound. + unsafe { vec.dec_len(vec.len()) }; + + // SAFETY: A `Vec`'s pointer is always aligned properly, and + // the alignment the array needs is the same as the items. + // We checked earlier that we have sufficient items. + // The items will not double-drop as the `set_len` + // tells the `Vec` not to also drop them. + let array = unsafe { ptr::read(vec.as_ptr() as *const [T; N]) }; + Ok(array) + } +} diff --git a/rust/kernel/alloc/kvec/drain.rs b/rust/kernel/alloc/kvec/drain.rs new file mode 100644 index 00000000000000..035878fd112843 --- /dev/null +++ b/rust/kernel/alloc/kvec/drain.rs @@ -0,0 +1,181 @@ +//! Rust standard library vendored code. +//! +//! The contents of this file come from the Rust standard library, hosted in +//! the repository, licensed under +//! "Apache-2.0 OR MIT" and adapted for kernel use. For copyright details, +//! see . +#![allow(clippy::undocumented_unsafe_blocks)] + +use core::fmt; +use core::iter::FusedIterator; +use core::mem::{self, SizedTypeProperties}; +use core::ptr::{self, NonNull}; +use core::slice::{self}; + +use super::{Allocator, Vec}; + +/// A draining iterator for `Vec`. +/// +/// This `struct` is created by [`Vec::drain`]. +/// See its documentation for more. +/// +/// # Example +/// +/// ``` +/// let mut v = vec![0, 1, 2]; +/// let iter: std::vec::Drain<'_, _> = v.drain(..); +/// ``` +// #[stable(feature = "drain", since = "1.6.0")] +pub struct Drain< + 'a, + T, + A: Allocator, + // #[unstable(feature = "allocator_api", issue = "32838")] A: Allocator + 'a = Global, +> { + /// Index of tail to preserve + pub(super) tail_start: usize, + /// Length of tail + pub(super) tail_len: usize, + /// Current remaining range to remove + pub(super) iter: slice::Iter<'a, T>, + pub(super) vec: NonNull>, +} + +// #[stable(feature = "collection_debug", since = "1.17.0")] +impl fmt::Debug for Drain<'_, T, A> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + f.debug_tuple("Drain").field(&self.iter.as_slice()).finish() + } +} + +impl<'a, T, A: Allocator> Drain<'a, T, A> { + /// Returns the remaining items of this iterator as a slice. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec!['a', 'b', 'c']; + /// let mut drain = vec.drain(..); + /// assert_eq!(drain.as_slice(), &['a', 'b', 'c']); + /// let _ = drain.next().unwrap(); + /// assert_eq!(drain.as_slice(), &['b', 'c']); + /// ``` + #[must_use] + // #[stable(feature = "vec_drain_as_slice", since = "1.46.0")] + pub fn as_slice(&self) -> &[T] { + self.iter.as_slice() + } +} + +// #[stable(feature = "vec_drain_as_slice", since = "1.46.0")] +impl<'a, T, A: Allocator> AsRef<[T]> for Drain<'a, T, A> { + fn as_ref(&self) -> &[T] { + self.as_slice() + } +} + +// #[stable(feature = "drain", since = "1.6.0")] +unsafe impl Sync for Drain<'_, T, A> {} +// #[stable(feature = "drain", since = "1.6.0")] +unsafe impl Send for Drain<'_, T, A> {} + +// #[stable(feature = "drain", since = "1.6.0")] +impl Iterator for Drain<'_, T, A> { + type Item = T; + + #[inline] + fn next(&mut self) -> Option { + self.iter + .next() + .map(|elt| unsafe { ptr::read(elt as *const _) }) + } + + fn size_hint(&self) -> (usize, Option) { + self.iter.size_hint() + } +} + +// #[stable(feature = "drain", since = "1.6.0")] +impl DoubleEndedIterator for Drain<'_, T, A> { + #[inline] + fn next_back(&mut self) -> Option { + self.iter + .next_back() + .map(|elt| unsafe { ptr::read(elt as *const _) }) + } +} + +// #[stable(feature = "drain", since = "1.6.0")] +impl Drop for Drain<'_, T, A> { + fn drop(&mut self) { + /// Moves back the un-`Drain`ed elements to restore the original `Vec`. + struct DropGuard<'r, 'a, T, A: Allocator>(&'r mut Drain<'a, T, A>); + + impl<'r, 'a, T, A: Allocator> Drop for DropGuard<'r, 'a, T, A> { + fn drop(&mut self) { + if self.0.tail_len > 0 { + unsafe { + let source_vec = self.0.vec.as_mut(); + // memmove back untouched tail, update to new length + let start = source_vec.len(); + let tail = self.0.tail_start; + if tail != start { + let src = source_vec.as_ptr().add(tail); + let dst = source_vec.as_mut_ptr().add(start); + ptr::copy(src, dst, self.0.tail_len); + } + source_vec.set_len(start + self.0.tail_len); + } + } + } + } + + let iter = mem::take(&mut self.iter); + let drop_len = iter.len(); + + let mut vec = self.vec; + + if T::IS_ZST { + // ZSTs have no identity, so we don't need to move them around, we only need to drop the correct amount. + // this can be achieved by manipulating the Vec length instead of moving values out from `iter`. + unsafe { + let vec = vec.as_mut(); + let old_len = vec.len(); + vec.set_len(old_len + drop_len + self.tail_len); + vec.truncate(old_len + self.tail_len); + } + + return; + } + + // ensure elements are moved back into their appropriate places, even when drop_in_place panics + let _guard = DropGuard(self); + + if drop_len == 0 { + return; + } + + // as_slice() must only be called when iter.len() is > 0 because + // it also gets touched by vec::Splice which may turn it into a dangling pointer + // which would make it and the vec pointer point to different allocations which would + // lead to invalid pointer arithmetic below. + let drop_ptr = iter.as_slice().as_ptr(); + + unsafe { + // drop_ptr comes from a slice::Iter which only gives us a &[T] but for drop_in_place + // a pointer with mutable provenance is necessary. Therefore we must reconstruct + // it from the original vec but also avoid creating a &mut to the front since that could + // invalidate raw pointers to it which some unsafe code might rely on. + let vec_ptr = vec.as_mut().as_mut_ptr(); + #[cfg(not(version("1.87")))] + let drop_offset = drop_ptr.sub_ptr(vec_ptr); + #[cfg(version("1.87"))] + let drop_offset = drop_ptr.offset_from_unsigned(vec_ptr); + let to_drop = ptr::slice_from_raw_parts_mut(vec_ptr.add(drop_offset), drop_len); + ptr::drop_in_place(to_drop); + } + } +} + +// #[stable(feature = "fused", since = "1.26.0")] +impl FusedIterator for Drain<'_, T, A> {} diff --git a/rust/kernel/bits.rs b/rust/kernel/bits.rs index 553d5026588329..2daead125626ae 100644 --- a/rust/kernel/bits.rs +++ b/rust/kernel/bits.rs @@ -27,7 +27,8 @@ macro_rules! impl_bit_fn { /// /// This version is the default and should be used if `n` is known at /// compile time. - #[inline] + // Always inline to optimize out error path of `build_assert`. + #[inline(always)] pub const fn [](n: u32) -> $ty { build_assert!(n < <$ty>::BITS); (1 as $ty) << n @@ -75,7 +76,8 @@ macro_rules! impl_genmask_fn { /// This version is the default and should be used if the range is known /// at compile time. $(#[$genmask_ex])* - #[inline] + // Always inline to optimize out error path of `build_assert`. + #[inline(always)] pub const fn [](range: RangeInclusive) -> $ty { let start = *range.start(); let end = *range.end(); diff --git a/rust/kernel/devcoredump.rs b/rust/kernel/devcoredump.rs new file mode 100644 index 00000000000000..a4a42d862f63b5 --- /dev/null +++ b/rust/kernel/devcoredump.rs @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Device coredump support. +//! +//! C header: [`include/linux/devcoredump.h`](../../../../include/linux/devcoredump.h) + +use crate::{ + alloc, bindings, device, error::from_result, prelude::Result, time::Jiffies, + types::ForeignOwnable, ThisModule, +}; + +use core::ops::Deref; + +/// The default timeout for device coredumps. +pub const DEFAULT_TIMEOUT: Jiffies = bindings::DEVCD_TIMEOUT as Jiffies; + +/// Trait to implement reading from a device coredump. +/// +/// Users must implement this trait to provide device coredump support. +pub trait DevCoreDump { + /// Returns the IOVA (virtual address) of the buffer from RTKit's point of view, or an error if + /// unavailable. + fn read(&self, buf: &mut [u8], offset: usize) -> Result; +} + +unsafe extern "C" fn read_callback< + 'a, + T: ForeignOwnable: Deref>, + D: DevCoreDump, +>( + buffer: *mut crate::ffi::c_char, + offset: bindings::loff_t, + count: usize, + data: *mut crate::ffi::c_void, + _datalen: usize, +) -> isize { + // SAFETY: This pointer came from into_foreign() below. + let coredump = unsafe { T::borrow(data.cast()) }; + // SAFETY: The caller guarantees `buffer` points to at least `count` bytes. + let buf = unsafe { core::slice::from_raw_parts_mut(buffer, count) }; + + from_result(|| Ok(coredump.read(buf, offset.try_into()?)?.try_into()?)) +} + +unsafe extern "C" fn free_callback< + 'a, + T: ForeignOwnable: Deref>, + D: DevCoreDump, +>( + data: *mut crate::ffi::c_void, +) { + // SAFETY: This pointer came from into_foreign() below. + unsafe { + T::from_foreign(data.cast()); + } +} + +/// Registers a coredump for the given device. +pub fn dev_coredump<'a, T: ForeignOwnable: Deref>, D: DevCoreDump>( + dev: &device::Device, + module: &'static ThisModule, + coredump: T, + gfp: alloc::Flags, + timeout: Jiffies, +) { + // SAFETY: Call upholds dev_coredumpm lifetime requirements. + unsafe { + bindings::dev_coredumpm_timeout( + dev.as_raw(), + module.0, + coredump.into_foreign() as *mut _, + 0, + gfp.as_raw(), + Some(read_callback::<'a, T, D>), + Some(free_callback::<'a, T, D>), + timeout, + ) + } +} diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs index a849b7dde2fd91..f6a47fd208e771 100644 --- a/rust/kernel/device.rs +++ b/rust/kernel/device.rs @@ -6,8 +6,10 @@ use crate::{ bindings, fmt, + of, + prelude::*, sync::aref::ARef, - types::{ForeignOwnable, Opaque}, + types::{ForeignOwnable, NotThreadSafe, Opaque}, }; use core::{marker::PhantomData, ptr}; @@ -62,8 +64,9 @@ pub mod property; /// /// # Implementing Bus Devices /// -/// This section provides a guideline to implement bus specific devices, such as [`pci::Device`] or -/// [`platform::Device`]. +/// This section provides a guideline to implement bus specific devices, such as: +#[cfg_attr(CONFIG_PCI, doc = "* [`pci::Device`](kernel::pci::Device)")] +/// * [`platform::Device`] /// /// A bus specific device should be defined as follows. /// @@ -155,7 +158,6 @@ pub mod property; /// /// [`AlwaysRefCounted`]: kernel::types::AlwaysRefCounted /// [`impl_device_context_deref`]: kernel::impl_device_context_deref -/// [`pci::Device`]: kernel::pci::Device /// [`platform::Device`]: kernel::platform::Device #[repr(transparent)] pub struct Device(Opaque, PhantomData); @@ -245,13 +247,13 @@ impl Device { impl Device { /// Obtain the raw `struct device *`. - pub(crate) fn as_raw(&self) -> *mut bindings::device { + pub fn as_raw(&self) -> *mut bindings::device { self.0.get() } /// Returns a reference to the parent device, if any. #[cfg_attr(not(CONFIG_AUXILIARY_BUS), expect(dead_code))] - pub(crate) fn parent(&self) -> Option<&Device> { + pub fn parent(&self) -> Option<&Device> { // SAFETY: // - By the type invariant `self.as_raw()` is always valid. // - The parent device is only ever set at device creation. @@ -268,6 +270,13 @@ impl Device { } } + /// Returns the driver_data pointer. + pub fn get_drvdata(&self) -> *mut T { + // SAFETY: dev_get_drvdata returns a field of the device, + // pointer to which is valid by type invariant + unsafe { bindings::dev_get_drvdata(self.as_raw()) as *mut T } + } + /// Convert a raw C `struct device` pointer to a `&'a Device`. /// /// # Safety @@ -281,6 +290,13 @@ impl Device { unsafe { &*ptr.cast() } } + /// Gets the OpenFirmware node attached to this device + pub fn of_node(&self) -> Option { + let ptr = self.0.get(); + // SAFETY: This is safe as long as of_node is NULL or valid. + unsafe { of::Node::get_from_raw((*ptr).of_node) } + } + /// Prints an emergency-level message (level 0) prefixed with device information. /// /// More details are available from [`dev_emerg`]. @@ -399,6 +415,58 @@ impl Device { // defined as a `#[repr(transparent)]` wrapper around `fwnode_handle`. Some(unsafe { &*fwnode_handle.cast() }) } + + /// Locks the [`Device`] for exclusive access. + pub fn lock(&self) -> Guard<'_, Ctx> { + // SAFETY: `self` is always valid by the type invariant. + unsafe { bindings::device_lock(self.as_raw()) }; + + Guard { + dev: self, + _not_send: NotThreadSafe, + } + } + + /// ensure Device is bound + pub fn is_bound(&self) -> Option> { + let guard = self.lock(); + if !unsafe { bindings::device_is_bound(self.as_raw()) } { + return None; + } + Some(guard) + } + + /// excute closure while the device is bound + pub fn while_bound_with(&self, f: F) -> Result + where + F: FnOnce(&Device) -> Result, + { + let _guard = self.lock(); + if unsafe { !bindings::device_is_bound(self.as_raw()) } { + return Err(ENODEV); + } + let ptr: *const Self = self; + let ptr = ptr.cast::>(); + f(unsafe { &*ptr }) + } +} + +/// A lock guard. +/// +/// The lock is unlocked when the guard goes out of scope. +#[must_use = "the lock unlocks immediately when the guard is unused"] +pub struct Guard<'a, Ctx: DeviceContext = Normal> { + dev: &'a Device, + _not_send: NotThreadSafe, +} + +impl Drop for Guard<'_, Ctx> { + fn drop(&mut self) { + // SAFETY: + // - `self.xa.xa` is always valid by the type invariant. + // - The caller holds the lock, so it is safe to unlock it. + unsafe { bindings::device_unlock(self.dev.as_raw()) }; + } } // SAFETY: `Device` is a transparent wrapper of a type that doesn't depend on `Device`'s generic diff --git a/rust/kernel/device/property.rs b/rust/kernel/device/property.rs index 3a332a8c53a9eb..71bbce339949ee 100644 --- a/rust/kernel/device/property.rs +++ b/rust/kernel/device/property.rs @@ -58,7 +58,7 @@ impl FwNode { } /// Obtain the raw `struct fwnode_handle *`. - pub(crate) fn as_raw(&self) -> *mut bindings::fwnode_handle { + pub fn as_raw(&self) -> *mut bindings::fwnode_handle { self.0.get() } diff --git a/rust/kernel/devres.rs b/rust/kernel/devres.rs index 2392c281459eff..835d9c11948e7d 100644 --- a/rust/kernel/devres.rs +++ b/rust/kernel/devres.rs @@ -52,8 +52,20 @@ struct Inner { /// # Examples /// /// ```no_run -/// # use kernel::{bindings, device::{Bound, Device}, devres::Devres, io::{Io, IoRaw}}; -/// # use core::ops::Deref; +/// use kernel::{ +/// bindings, +/// device::{ +/// Bound, +/// Device, +/// }, +/// devres::Devres, +/// io::{ +/// Io, +/// IoRaw, +/// PhysAddr, +/// }, +/// }; +/// use core::ops::Deref; /// /// // See also [`pci::Bar`] for a real example. /// struct IoMem(IoRaw); @@ -66,7 +78,7 @@ struct Inner { /// unsafe fn new(paddr: usize) -> Result{ /// // SAFETY: By the safety requirements of this function [`paddr`, `paddr` + `SIZE`) is /// // valid for `ioremap`. -/// let addr = unsafe { bindings::ioremap(paddr as bindings::phys_addr_t, SIZE) }; +/// let addr = unsafe { bindings::ioremap(paddr as PhysAddr, SIZE) }; /// if addr.is_null() { /// return Err(ENOMEM); /// } diff --git a/rust/kernel/dma.rs b/rust/kernel/dma.rs index 4e0af3e1a3b9ad..777ea5c2431c7e 100644 --- a/rust/kernel/dma.rs +++ b/rust/kernel/dma.rs @@ -26,8 +26,9 @@ pub type DmaAddress = bindings::dma_addr_t; /// Trait to be implemented by DMA capable bus devices. /// /// The [`dma::Device`](Device) trait should be implemented by bus specific device representations, -/// where the underlying bus is DMA capable, such as [`pci::Device`](::kernel::pci::Device) or -/// [`platform::Device`](::kernel::platform::Device). +/// where the underlying bus is DMA capable, such as: +#[cfg_attr(CONFIG_PCI, doc = "* [`pci::Device`](kernel::pci::Device)")] +/// * [`platform::Device`](::kernel::platform::Device) pub trait Device: AsRef> { /// Set up the device's DMA streaming addressing capabilities. /// diff --git a/rust/kernel/dma_buf.rs b/rust/kernel/dma_buf.rs new file mode 100644 index 00000000000000..318518ff0b28f9 --- /dev/null +++ b/rust/kernel/dma_buf.rs @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! DMA buffer API +//! +//! C header: [`include/linux/dma-buf.h`](srctree/include/linux/dma-buf.h) + +use bindings; +use kernel::types::*; + +/// A DMA buffer object. +/// +/// # Invariants +/// +/// The data layout of this type is equivalent to that of `struct dma_buf`. +#[repr(transparent)] +pub struct DmaBuf(Opaque); + +// SAFETY: `struct dma_buf` is thread-safe +unsafe impl Send for DmaBuf {} +// SAFETY: `struct dma_buf` is thread-safe +unsafe impl Sync for DmaBuf {} + +impl DmaBuf { + /// Convert from a `*mut bindings::dma_buf` to a [`DmaBuf`]. + /// + /// # Safety + /// + /// The caller guarantees that `self_ptr` points to a valid initialized `struct dma_buf` for the + /// duration of the lifetime of `'a`, and promises to not violate rust's data aliasing rules + /// using the reference provided by this function. + pub(crate) unsafe fn as_ref<'a>(self_ptr: *mut bindings::dma_buf) -> &'a Self { + // SAFETY: Our data layout is equivalent to `dma_buf` . + unsafe { &*self_ptr.cast() } + } + + pub(crate) fn as_raw(&self) -> *mut bindings::dma_buf { + self.0.get() + } +} diff --git a/rust/kernel/dma_fence.rs b/rust/kernel/dma_fence.rs new file mode 100644 index 00000000000000..139451e75685f9 --- /dev/null +++ b/rust/kernel/dma_fence.rs @@ -0,0 +1,480 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! DMA fence abstraction. +//! +//! C header: [`include/linux/dma_fence.h`](../../include/linux/dma_fence.h) + +use crate::{ + bindings, + error::{to_result, Result}, + prelude::*, + sync::LockClassKey, + types::Opaque, +}; +use core::ops::{Deref, DerefMut}; +use core::ptr::addr_of_mut; +use core::sync::atomic::{AtomicU64, Ordering}; + +mod private { + /// Marker that a trait cannot be implemented outside of this mod + pub trait Sealed {} +} + +/// Any kind of DMA Fence Object +/// +/// # Invariants +/// raw() returns a valid pointer to a dma_fence and we own a reference to it. +pub trait RawDmaFence: private::Sealed { + /// Returns the raw `struct dma_fence` pointer. + fn raw(&self) -> *mut bindings::dma_fence; + + /// Returns the raw `struct dma_fence` pointer and consumes the object. + /// + /// The caller is responsible for dropping the reference. + fn into_raw(self) -> *mut bindings::dma_fence + where + Self: Sized, + { + let ptr = self.raw(); + core::mem::forget(self); + ptr + } + + /// Advances this fence to the chain node which will signal this sequence number. + /// If no sequence number is provided, this returns `self` again. + /// If the seqno has already been signaled, returns None. + fn chain_find_seqno(self, seqno: u64) -> Result> + where + Self: Sized, + { + let mut ptr = self.into_raw(); + + // SAFETY: This will safely fail if this DmaFence is not a chain. + // `ptr` is valid per the type invariant. + let ret = unsafe { bindings::dma_fence_chain_find_seqno(&mut ptr, seqno) }; + + if ret != 0 { + // SAFETY: This is either an owned reference or NULL, dma_fence_put can handle both. + unsafe { bindings::dma_fence_put(ptr) }; + Err(Error::from_errno(ret)) + } else if ptr.is_null() { + Ok(None) + } else { + // SAFETY: ptr is valid and non-NULL as checked above. + Ok(Some(unsafe { Fence::from_raw(ptr) })) + } + } + + /// Signal completion of this fence + fn signal(&self) -> Result { + // SAFETY: Safe to call on any valid dma_fence object + to_result(unsafe { bindings::dma_fence_signal(self.raw()) }) + } + + /// Set the error flag on this fence + fn set_error(&self, err: Error) { + // SAFETY: Safe to call on any valid dma_fence object + unsafe { bindings::dma_fence_set_error(self.raw(), err.to_errno()) }; + } +} + +/// A generic DMA Fence Object +/// +/// # Invariants +/// ptr is a valid pointer to a dma_fence and we own a reference to it. +pub struct Fence { + ptr: *mut bindings::dma_fence, +} + +impl Fence { + /// Create a new Fence object from a raw pointer to a dma_fence. + /// + /// # Safety + /// The caller must own a reference to the dma_fence, which is transferred to the new object. + pub(crate) unsafe fn from_raw(ptr: *mut bindings::dma_fence) -> Fence { + Fence { ptr } + } + + /// Create a new Fence object from a raw pointer to a dma_fence. + /// + /// # Safety + /// Takes a borrowed reference to the dma_fence, and increments the reference count. + pub(crate) unsafe fn get_raw(ptr: *mut bindings::dma_fence) -> Fence { + // SAFETY: Pointer is valid per the safety contract + unsafe { bindings::dma_fence_get(ptr) }; + Fence { ptr } + } + + /// Create a new Fence object from a RawDmaFence. + pub fn from_fence(fence: &dyn RawDmaFence) -> Fence { + // SAFETY: Pointer is valid per the RawDmaFence contract + unsafe { Self::get_raw(fence.raw()) } + } +} + +impl private::Sealed for Fence {} + +impl RawDmaFence for Fence { + fn raw(&self) -> *mut bindings::dma_fence { + self.ptr + } +} + +impl Drop for Fence { + fn drop(&mut self) { + // SAFETY: We own a reference to this syncobj. + unsafe { bindings::dma_fence_put(self.ptr) }; + } +} + +impl Clone for Fence { + fn clone(&self) -> Self { + // SAFETY: `ptr` is valid per the type invariant and we own a reference to it. + unsafe { + bindings::dma_fence_get(self.ptr); + Self::from_raw(self.ptr) + } + } +} + +// SAFETY: The API for these objects is thread safe +unsafe impl Sync for Fence {} +// SAFETY: The API for these objects is thread safe +unsafe impl Send for Fence {} + +/// Trait which must be implemented by driver-specific fence objects. +#[vtable] +pub trait FenceOps: Sized + Send + Sync { + /// Returns the driver name. This is a callback to allow drivers to compute the name at + /// runtime, without having it to store permanently for each fence, or build a cache of + /// some sort. + fn get_driver_name<'a>(self: &'a FenceObject) -> &'a CStr; + + /// Return the name of the context this fence belongs to. This is a callback to allow drivers + /// to compute the name at runtime, without having it to store permanently for each fence, or + /// build a cache of some sort. + fn get_timeline_name<'a>(self: &'a FenceObject) -> &'a CStr; + + /// Enable software signaling of fence. + fn enable_signaling(self: &FenceObject) -> bool { + false + } + + /// Peek whether the fence is signaled, as a fastpath optimization for e.g. dma_fence_wait() or + /// dma_fence_add_callback(). + fn signaled(self: &FenceObject) -> bool { + false + } +} + +unsafe extern "C" fn get_driver_name_cb( + fence: *mut bindings::dma_fence, +) -> *const crate::ffi::c_char { + // SAFETY: All of our fences are FenceObject. + let p = unsafe { crate::container_of!(fence, FenceObject, fence) as *mut FenceObject }; + + // SAFETY: The caller is responsible for passing a valid dma_fence subtype + T::get_driver_name(unsafe { &mut *p }).as_char_ptr() +} + +unsafe extern "C" fn get_timeline_name_cb( + fence: *mut bindings::dma_fence, +) -> *const crate::ffi::c_char { + // SAFETY: All of our fences are FenceObject. + let p = unsafe { crate::container_of!(fence, FenceObject, fence) as *mut FenceObject }; + + // SAFETY: The caller is responsible for passing a valid dma_fence subtype + T::get_timeline_name(unsafe { &mut *p }).as_char_ptr() +} + +unsafe extern "C" fn enable_signaling_cb(fence: *mut bindings::dma_fence) -> bool { + // SAFETY: All of our fences are FenceObject. + let p = unsafe { crate::container_of!(fence, FenceObject, fence) as *mut FenceObject }; + + // SAFETY: The caller is responsible for passing a valid dma_fence subtype + T::enable_signaling(unsafe { &mut *p }) +} + +unsafe extern "C" fn signaled_cb(fence: *mut bindings::dma_fence) -> bool { + // SAFETY: All of our fences are FenceObject. + let p = unsafe { crate::container_of!(fence, FenceObject, fence) as *mut FenceObject }; + + // SAFETY: The caller is responsible for passing a valid dma_fence subtype + T::signaled(unsafe { &mut *p }) +} + +unsafe extern "C" fn release_cb(fence: *mut bindings::dma_fence) { + // SAFETY: All of our fences are FenceObject. + let p = unsafe { crate::container_of!(fence, FenceObject, fence) as *mut FenceObject }; + + // SAFETY: p is never used after this + unsafe { + core::ptr::drop_in_place(&mut (*p).inner); + } + + // SAFETY: All of our fences are allocated using kmalloc, so this is safe. + unsafe { bindings::dma_fence_free(fence) }; +} + +/// A driver-specific DMA Fence Object +/// +/// # Invariants +/// ptr is a valid pointer to a dma_fence and we own a reference to it. +#[repr(C)] +pub struct FenceObject { + fence: bindings::dma_fence, + lock: Opaque, + inner: T, +} + +impl FenceObject { + const SIZE: usize = core::mem::size_of::(); + + const VTABLE: bindings::dma_fence_ops = bindings::dma_fence_ops { + get_driver_name: Some(get_driver_name_cb::), + get_timeline_name: Some(get_timeline_name_cb::), + enable_signaling: if T::HAS_ENABLE_SIGNALING { + Some(enable_signaling_cb::) + } else { + None + }, + signaled: if T::HAS_SIGNALED { + Some(signaled_cb::) + } else { + None + }, + wait: None, // Deprecated + release: Some(release_cb::), + set_deadline: None, + }; +} + +impl Deref for FenceObject { + type Target = T; + + fn deref(&self) -> &T { + &self.inner + } +} + +impl DerefMut for FenceObject { + fn deref_mut(&mut self) -> &mut T { + &mut self.inner + } +} + +impl private::Sealed for FenceObject {} +impl RawDmaFence for FenceObject { + fn raw(&self) -> *mut bindings::dma_fence { + &self.fence as *const _ as *mut _ + } +} + +/// A unique reference to a driver-specific fence object +pub struct UniqueFence(*mut FenceObject); + +impl Deref for UniqueFence { + type Target = FenceObject; + + fn deref(&self) -> &FenceObject { + // SAFETY: The pointer is always valid for UniqueFence objects + unsafe { &*self.0 } + } +} + +impl DerefMut for UniqueFence { + fn deref_mut(&mut self) -> &mut FenceObject { + // SAFETY: The pointer is always valid for UniqueFence objects + unsafe { &mut *self.0 } + } +} + +impl private::Sealed for UniqueFence {} +impl RawDmaFence for UniqueFence { + fn raw(&self) -> *mut bindings::dma_fence { + // SAFETY: The pointer is always valid for UniqueFence objects + unsafe { addr_of_mut!((*self.0).fence) } + } +} + +impl From> for UserFence { + fn from(value: UniqueFence) -> Self { + let ptr = value.0; + core::mem::forget(value); + + UserFence(ptr) + } +} + +impl Drop for UniqueFence { + fn drop(&mut self) { + // SAFETY: We own a reference to this fence. + unsafe { bindings::dma_fence_put(self.raw()) }; + } +} + +// SAFETY: The API for these objects is thread safe +unsafe impl Sync for UniqueFence {} +// SAFETY: The API for these objects is thread safe +unsafe impl Send for UniqueFence {} + +/// A shared reference to a driver-specific fence object +pub struct UserFence(*mut FenceObject); + +impl Deref for UserFence { + type Target = FenceObject; + + fn deref(&self) -> &FenceObject { + // SAFETY: The pointer is always valid for UserFence objects + unsafe { &*self.0 } + } +} + +impl Clone for UserFence { + fn clone(&self) -> Self { + // SAFETY: `ptr` is valid per the type invariant and we own a reference to it. + unsafe { + bindings::dma_fence_get(self.raw()); + Self(self.0) + } + } +} + +impl private::Sealed for UserFence {} +impl RawDmaFence for UserFence { + fn raw(&self) -> *mut bindings::dma_fence { + // SAFETY: The pointer is always valid for UserFence objects + unsafe { addr_of_mut!((*self.0).fence) } + } +} + +impl Drop for UserFence { + fn drop(&mut self) { + // SAFETY: We own a reference to this fence. + unsafe { bindings::dma_fence_put(self.raw()) }; + } +} + +// SAFETY: The API for these objects is thread safe +unsafe impl Sync for UserFence {} +// SAFETY: The API for these objects is thread safe +unsafe impl Send for UserFence {} + +/// An array of fence contexts, out of which fences can be created. +pub struct FenceContexts { + start: u64, + count: u32, + seqnos: KVec, + lock_name: &'static CStr, + lock_key: Pin<&'static LockClassKey>, +} + +impl FenceContexts { + /// Create a new set of fence contexts. + pub fn new( + count: u32, + name: &'static CStr, + key: Pin<&'static LockClassKey>, + ) -> Result { + let mut seqnos: KVec = KVec::new(); + + seqnos.reserve(count as usize, GFP_KERNEL)?; + + for _ in 0..count { + seqnos.push(Default::default(), GFP_KERNEL)?; + } + + // SAFETY: This is always safe to call + let start = unsafe { bindings::dma_fence_context_alloc(count as crate::ffi::c_uint) }; + + Ok(FenceContexts { + start, + count, + seqnos, + lock_name: name, + lock_key: key, + }) + } + + /// Create a new fence in a given context index. + pub fn new_fence(&self, context: u32, inner: T) -> Result> { + if context > self.count { + return Err(EINVAL); + } + + // SAFETY: krealloc is always safe to call like this + let p = unsafe { + bindings::krealloc_node_align( + core::ptr::null_mut(), + FenceObject::::SIZE, + 1, + bindings::GFP_KERNEL | bindings::__GFP_ZERO, + bindings::NUMA_NO_NODE, + ) as *mut FenceObject + }; + + if p.is_null() { + return Err(ENOMEM); + } + + let seqno = self.seqnos[context as usize].fetch_add(1, Ordering::Relaxed); + + // SAFETY: The pointer is valid, so pointers to members are too. + // After this, all fields are initialized. + unsafe { + addr_of_mut!((*p).inner).write(inner); + bindings::__spin_lock_init( + addr_of_mut!((*p).lock) as *mut _, + self.lock_name.as_char_ptr(), + self.lock_key.as_ptr(), + ); + bindings::dma_fence_init64( + addr_of_mut!((*p).fence), + &FenceObject::::VTABLE, + addr_of_mut!((*p).lock) as *mut _, + self.start + context as u64, + seqno, + ); + }; + + Ok(UniqueFence(p)) + } +} + +/// A DMA Fence Chain Object +/// +/// # Invariants +/// ptr is a valid pointer to a dma_fence_chain which we own. +pub struct FenceChain { + ptr: *mut bindings::dma_fence_chain, +} + +impl FenceChain { + /// Create a new DmaFenceChain object. + pub fn new() -> Result { + // SAFETY: This function is safe to call and takes no arguments. + let ptr = unsafe { bindings::dma_fence_chain_alloc() }; + + if ptr.is_null() { + Err(ENOMEM) + } else { + Ok(FenceChain { ptr }) + } + } + + /// Convert the DmaFenceChain into the underlying raw pointer. + /// + /// This assumes the caller will take ownership of the object. + pub(crate) fn into_raw(self) -> *mut bindings::dma_fence_chain { + let ptr = self.ptr; + core::mem::forget(self); + ptr + } +} + +impl Drop for FenceChain { + fn drop(&mut self) { + // SAFETY: We own this dma_fence_chain. + unsafe { bindings::dma_fence_chain_free(self.ptr) }; + } +} diff --git a/rust/kernel/driver.rs b/rust/kernel/driver.rs index 279e3af206822c..16931b94d0d48c 100644 --- a/rust/kernel/driver.rs +++ b/rust/kernel/driver.rs @@ -33,7 +33,14 @@ //! } //! ``` //! -//! For specific examples see [`auxiliary::Driver`], [`pci::Driver`] and [`platform::Driver`]. +//! For specific examples see: +//! +//! * [`platform::Driver`](kernel::platform::Driver) +#![cfg_attr( + CONFIG_AUXILIARY_BUS, + doc = "* [`auxiliary::Driver`](kernel::auxiliary::Driver)" +)] +#![cfg_attr(CONFIG_PCI, doc = "* [`pci::Driver`](kernel::pci::Driver)")] //! //! The `probe()` callback should return a `Result>>`, i.e. the driver's private //! data. The bus abstraction should store the pointer in the corresponding bus device. The generic @@ -79,7 +86,6 @@ //! //! For this purpose the generic infrastructure in [`device_id`] should be used. //! -//! [`auxiliary::Driver`]: kernel::auxiliary::Driver //! [`Core`]: device::Core //! [`Device`]: device::Device //! [`Device`]: device::Device @@ -87,8 +93,6 @@ //! [`DeviceContext`]: device::DeviceContext //! [`device_id`]: kernel::device_id //! [`module_driver`]: kernel::module_driver -//! [`pci::Driver`]: kernel::pci::Driver -//! [`platform::Driver`]: kernel::platform::Driver use crate::error::{Error, Result}; use crate::{acpi, device, of, str::CStr, try_pin_init, types::Opaque, ThisModule}; diff --git a/rust/kernel/drm/device.rs b/rust/kernel/drm/device.rs index 3ce8f62a005696..76625537f38023 100644 --- a/rust/kernel/drm/device.rs +++ b/rust/kernel/drm/device.rs @@ -86,7 +86,7 @@ impl Device { name: crate::str::as_char_ptr_in_const_context(T::INFO.name).cast_mut(), desc: crate::str::as_char_ptr_in_const_context(T::INFO.desc).cast_mut(), - driver_features: drm::driver::FEAT_GEM, + driver_features: T::FEATURES, ioctls: T::IOCTLS.as_ptr(), num_ioctls: T::IOCTLS.len() as i32, fops: &Self::GEM_FOPS, @@ -184,7 +184,10 @@ impl Device { // SAFETY: // - When `release` runs it is guaranteed that there is no further access to `this`. // - `this` is valid for dropping. - unsafe { core::ptr::drop_in_place(this) }; + // unsafe { core::ptr::drop_in_place(this) }; + // HACK: data might be uninitialized so leak the DRM device instead. The expected number + // of times the asahi device gets released is once at poweroff or reboot. + let _ = core::mem::ManuallyDrop::new(this); } } diff --git a/rust/kernel/drm/driver.rs b/rust/kernel/drm/driver.rs index f30ee4c6245cda..bb072b3a01817e 100644 --- a/rust/kernel/drm/driver.rs +++ b/rust/kernel/drm/driver.rs @@ -13,7 +13,16 @@ use crate::{ use macros::vtable; /// Driver use the GEM memory manager. This should be set for all modern drivers. -pub(crate) const FEAT_GEM: u32 = bindings::drm_driver_feature_DRIVER_GEM; +pub const FEAT_GEM: u32 = bindings::drm_driver_feature_DRIVER_GEM; +/// Driver supports dedicated render nodes. +pub const FEAT_RENDER: u32 = bindings::drm_driver_feature_DRIVER_RENDER; +/// Driver supports DRM sync objects for explicit synchronization of command submission. +pub const FEAT_SYNCOBJ: u32 = bindings::drm_driver_feature_DRIVER_SYNCOBJ; +/// Driver supports the timeline flavor of DRM sync objects for explicit synchronization of command +/// submission. +pub const FEAT_SYNCOBJ_TIMELINE: u32 = bindings::drm_driver_feature_DRIVER_SYNCOBJ_TIMELINE; +/// Driver supports user defined GPU VA bindings for GEM objects. +pub const FEAT_GEM_GPUVA: u32 = bindings::drm_driver_feature_DRIVER_GEM_GPUVA; /// Information data for a DRM Driver. pub struct DriverInfo { @@ -111,6 +120,9 @@ pub trait Driver { /// Driver metadata const INFO: DriverInfo; + /// Feature flags + const FEATURES: u32; + /// IOCTL list. See `kernel::drm::ioctl::declare_drm_ioctls!{}`. const IOCTLS: &'static [drm::ioctl::DrmIoctlDescriptor]; } diff --git a/rust/kernel/drm/file.rs b/rust/kernel/drm/file.rs index 8c46f8d519516a..9c7bcace70eef5 100644 --- a/rust/kernel/drm/file.rs +++ b/rust/kernel/drm/file.rs @@ -15,6 +15,9 @@ pub trait DriverFile { /// Open a new file (called when a client opens the DRM device). fn open(device: &drm::Device) -> Result>>; + + /// Get raw drm_file pointer + fn as_raw(&self) -> *mut bindings::drm_file; } /// An open DRM File. diff --git a/rust/kernel/drm/gem/mod.rs b/rust/kernel/drm/gem/mod.rs index 30c853988b9420..ddc8729e3bcdda 100644 --- a/rust/kernel/drm/gem/mod.rs +++ b/rust/kernel/drm/gem/mod.rs @@ -3,18 +3,59 @@ //! DRM GEM API //! //! C header: [`include/drm/drm_gem.h`](srctree/include/drm/drm_gem.h) +#[cfg(CONFIG_DRM_GEM_SHMEM_HELPER = "y")] +pub mod shmem; use crate::{ alloc::flags::*, bindings, drm, drm::driver::{AllocImpl, AllocOps}, - error::{to_result, Result}, + dma_buf, + error::{to_result, from_err_ptr, Result}, prelude::*, sync::aref::{ARef, AlwaysRefCounted}, types::Opaque, }; +use core::marker::PhantomData; use core::{ops::Deref, ptr::NonNull}; +/// A macro for implementing [`AlwaysRefCounted`] for any GEM object type. +/// +/// Since all GEM objects use the same refcounting scheme. +#[macro_export] +macro_rules! impl_aref_for_gem_obj { + ( + impl $( <$( $tparam_id:ident ),+> )? for $type:ty + $( + where + $( $bind_param:path : $bind_trait:path ),+ + )? + ) => { + // SAFETY: All gem objects are refcounted + unsafe impl $( <$( $tparam_id ),+> )? $crate::types::AlwaysRefCounted for $type + where + Self: IntoGEMObject, + $( $( $bind_param : $bind_trait ),+ )? + { + fn inc_ref(&self) { + // SAFETY: The existence of a shared reference guarantees that the refcount is + // non-zero. + unsafe { bindings::drm_gem_object_get(self.as_raw()) }; + } + + unsafe fn dec_ref(obj: core::ptr::NonNull) { + // SAFETY: `obj` is a valid pointer to an `Object`. + let obj = unsafe { obj.as_ref() }.as_raw(); + + // SAFETY: The safety requirements guarantee that the refcount is non-zero. + unsafe { bindings::drm_gem_object_put(obj) }; + } + } + }; +} + +pub(crate) use impl_aref_for_gem_obj; + /// A type alias for retrieving a [`Driver`]s [`DriverFile`] implementation from its /// [`DriverObject`] implementation. /// @@ -23,12 +64,20 @@ use core::{ops::Deref, ptr::NonNull}; pub type DriverFile = drm::File<<::Driver as drm::Driver>::File>; /// GEM object functions, which must be implemented by drivers. +#[vtable] pub trait DriverObject: Sync + Send + Sized { /// Parent `Driver` for this object. type Driver: drm::Driver; + /// The data type to use for passing arguments to [`DriverObject::new`]. + type Args; + /// Create a new driver data object for a GEM object of a given size. - fn new(dev: &drm::Device, size: usize) -> impl PinInit; + fn new( + dev: &drm::Device, + size: usize, + args: Self::Args, + ) -> impl PinInit; /// Open a new handle to an existing object, associated with a File. fn open(_obj: &::Object, _file: &DriverFile) -> Result { @@ -37,6 +86,11 @@ pub trait DriverObject: Sync + Send + Sized { /// Close a handle to an existing object, associated with a File. fn close(_obj: &::Object, _file: &DriverFile) {} + + /// Optional handle for exporting a gem object. + fn export(_obj: &::Object, _flags: u32) -> Result::Object>> { + unimplemented!() + } } /// Trait that represents a GEM object subtype @@ -55,26 +109,6 @@ pub trait IntoGEMObject: Sized + super::private::Sealed + AlwaysRefCounted { unsafe fn from_raw<'a>(self_ptr: *mut bindings::drm_gem_object) -> &'a Self; } -// SAFETY: All gem objects are refcounted. -unsafe impl AlwaysRefCounted for T { - fn inc_ref(&self) { - // SAFETY: The existence of a shared reference guarantees that the refcount is non-zero. - unsafe { bindings::drm_gem_object_get(self.as_raw()) }; - } - - unsafe fn dec_ref(obj: NonNull) { - // SAFETY: We either hold the only refcount on `obj`, or one of many - meaning that no one - // else could possibly hold a mutable reference to `obj` and thus this immutable reference - // is safe. - let obj = unsafe { obj.as_ref() }.as_raw(); - - // SAFETY: - // - The safety requirements guarantee that the refcount is non-zero. - // - We hold no references to `obj` now, making it safe for us to potentially deallocate it. - unsafe { bindings::drm_gem_object_put(obj) }; - } -} - extern "C" fn open_callback( raw_obj: *mut bindings::drm_gem_object, raw_file: *mut bindings::drm_file, @@ -106,6 +140,21 @@ extern "C" fn close_callback( T::close(obj, file); } +extern "C" fn export_callback( + raw_obj: *mut bindings::drm_gem_object, + flags: i32, +) -> *mut bindings::dma_buf { + // SAFETY: `export_callback` is specified in the AllocOps structure for `Object`, ensuring + // that `raw_obj` is contained within a `Object`. + let obj = unsafe { <::Object as IntoGEMObject>::from_raw(raw_obj) }; + + match T::export(obj, flags as _) { + // DRM takes a hold of the reference + Ok(buf) => buf.into_raw(), + Err(e) => e.to_ptr(), + } +} + impl IntoGEMObject for Object { fn as_raw(&self) -> *mut bindings::drm_gem_object { self.obj.get() @@ -170,6 +219,29 @@ pub trait BaseObject: IntoGEMObject { Ok(unsafe { ARef::from_raw(obj.into()) }) } + /// Export a [`DmaBuf`] for this GEM object using the DRM prime helper library. + /// + /// `flags` should be a set of flags from [`fs::file::flags`](kernel::fs::file::flags). + fn prime_export(&self, flags: u32) -> Result> { + // SAFETY: + // - `as_raw()` always returns a valid pointer to a `drm_gem_object`. + // - `drm_gem_prime_export()` returns either an error pointer, or a valid pointer to an + // initialized `dma_buf` on success. + let dma_ptr = from_err_ptr(unsafe { + bindings::drm_gem_prime_export(self.as_raw(), flags as _) + })?; + + // SAFETY: + // - We checked that dma_ptr is not an error, so it must point to an initialized dma_buf + // - We used drm_gem_prime_export(), so `dma_ptr` will remain valid until a call to + // `drm_gem_prime_release()` which we don't call here. + let dma_buf = unsafe { dma_buf::DmaBuf::as_ref(dma_ptr) }; + + // INVARIANT: We used drm_gem_prime_export() to create this dma_buf, fulfilling the + // invariant that this dma_buf came from a GEM object of type `Self`. + Ok(DmaBuf(dma_buf.into(), PhantomData)) + } + /// Creates an mmap offset to map the object from userspace. fn create_mmap_offset(&self) -> Result { // SAFETY: The arguments are valid per the type invariant. @@ -178,21 +250,44 @@ pub trait BaseObject: IntoGEMObject { // SAFETY: The arguments are valid per the type invariant. Ok(unsafe { bindings::drm_vma_node_offset_addr(&raw mut (*self.as_raw()).vma_node) }) } + + /// Lock the gpuva lock + fn lock_gpuva(&self) { + unsafe { + bindings::mutex_lock(&raw mut (*self.as_raw()).gpuva.lock); + } + } + + /// Lock the gpuva lock + fn unlock_gpuva(&self) { + unsafe { + bindings::mutex_unlock(&raw mut (*self.as_raw()).gpuva.lock); + } + } } impl BaseObject for T {} +/// Crate-private base operations shared by all GEM object classes. +pub(crate) trait BaseObjectPrivate: IntoGEMObject { + /// Return a pointer to this object's dma_resv. + fn raw_dma_resv(&self) -> *mut bindings::dma_resv { + // SAFETY: `as_gem_obj()` always returns a valid pointer to the base DRM gem object + unsafe { (*self.as_raw()).resv } + } +} + +impl BaseObjectPrivate for T {} + /// A base GEM object. /// -/// Invariants +/// # Invariants /// /// - `self.obj` is a valid instance of a `struct drm_gem_object`. -/// - `self.dev` is always a valid pointer to a `struct drm_device`. #[repr(C)] #[pin_data] pub struct Object { obj: Opaque, - dev: NonNull>, #[pin] data: T, } @@ -203,7 +298,11 @@ impl Object { open: Some(open_callback::), close: Some(close_callback::), print_info: None, - export: None, + export: if T::HAS_EXPORT { + Some(export_callback::) + } else { + None + }, pin: None, unpin: None, get_sg_table: None, @@ -217,14 +316,11 @@ impl Object { }; /// Create a new GEM object. - pub fn new(dev: &drm::Device, size: usize) -> Result> { + pub fn new(dev: &drm::Device, size: usize, args: T::Args) -> Result> { let obj: Pin> = KBox::pin_init( try_pin_init!(Self { obj: Opaque::new(bindings::drm_gem_object::default()), - data <- T::new(dev, size), - // INVARIANT: The drm subsystem guarantees that the `struct drm_device` will live - // as long as the GEM object lives. - dev: dev.into(), + data <- T::new(dev, size, args), }), GFP_KERNEL, )?; @@ -247,9 +343,13 @@ impl Object { /// Returns the `Device` that owns this GEM object. pub fn dev(&self) -> &drm::Device { - // SAFETY: The DRM subsystem guarantees that the `struct drm_device` will live as long as - // the GEM object lives, hence the pointer must be valid. - unsafe { self.dev.as_ref() } + // SAFETY: + // - `struct drm_gem_object.dev` is initialized and valid for as long as the GEM + // object lives. + // - The device we used for creating the gem object is passed as &drm::Device to + // Object::::new(), so we know that `T::Driver` is the right generic parameter to use + // here. + unsafe { drm::Device::from_raw((*self.as_raw()).dev) } } fn as_raw(&self) -> *mut bindings::drm_gem_object { @@ -273,6 +373,8 @@ impl Object { } } +impl_aref_for_gem_obj!(impl for Object where T: DriverObject); + impl super::private::Sealed for Object {} impl Deref for Object { @@ -297,6 +399,49 @@ impl AllocImpl for Object { }; } +/// A [`dma_buf::DmaBuf`] which has been exported from a GEM object. +/// +/// The [`dma_buf::DmaBuf`] will be released when this type is dropped. +/// +/// # Invariants +/// +/// - `self.0` points to a valid initialized [`dma_buf::DmaBuf`] for the lifetime of this object. +/// - The GEM object from which this [`dma_buf::DmaBuf`] was exported from is guaranteed to be of +/// type `T`. +pub struct DmaBuf(NonNull, PhantomData); + +impl Deref for DmaBuf { + type Target = dma_buf::DmaBuf; + + #[inline] + fn deref(&self) -> &Self::Target { + // SAFETY: This pointer is guaranteed to be valid by our type invariants. + unsafe { self.0.as_ref() } + } +} + +impl Drop for DmaBuf { + #[inline] + fn drop(&mut self) { + // SAFETY: + // - `dma_buf::DmaBuf` is guaranteed to have an identical layout to `struct dma_buf` + // by its type invariants. + // - We hold the last reference to this `DmaBuf`, making it safe to destroy. + unsafe { bindings::drm_gem_dmabuf_release(self.0.cast().as_ptr()) } + } +} + +impl DmaBuf { + /// Leak the reference for this [`DmaBuf`] and return a raw pointer to it. + #[inline] + pub(crate) fn into_raw(self) -> *mut bindings::dma_buf { + let dma_ptr = self.as_raw(); + + core::mem::forget(self); + dma_ptr + } +} + pub(super) const fn create_fops() -> bindings::file_operations { // SAFETY: As by the type invariant, it is safe to initialize `bindings::file_operations` // zeroed. diff --git a/rust/kernel/drm/gem/shmem.rs b/rust/kernel/drm/gem/shmem.rs new file mode 100644 index 00000000000000..bfb05e19cc4500 --- /dev/null +++ b/rust/kernel/drm/gem/shmem.rs @@ -0,0 +1,442 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! DRM GEM shmem helper objects +//! +//! C header: [`include/linux/drm/drm_gem_shmem_helper.h`](srctree/include/linux/drm/drm_gem_shmem_helper.h) + +// TODO: +// - There are a number of spots here that manually acquire/release the DMA reservation lock using +// dma_resv_(un)lock(). In the future we should add support for ww mutex, expose a method to +// acquire a reference to the WwMutex, and then use that directly instead of the C functions here. + +use crate::{ + container_of, + drm::{device, driver, gem, private::Sealed}, + error::{from_err_ptr, to_result}, + iosys_map::*, + prelude::*, + scatterlist, + transmute::*, + types::{ARef, Opaque}, +}; +use core::{ + mem::{self, MaybeUninit}, + ops::{Deref, DerefMut}, + ptr::NonNull, +}; +use gem::{BaseObject, BaseObjectPrivate, DriverObject, IntoGEMObject}; + +/// A struct for controlling the creation of shmem-backed GEM objects. +/// +/// This is used with [`Object::new()`] to control various properties that can only be set when +/// initially creating a shmem-backed GEM object. +#[derive(Default)] +pub struct ObjectConfig<'a, T: DriverObject> { + /// Whether to set the write-combine map flag. + pub map_wc: bool, + + /// Reuse the DMA reservation from another GEM object. + /// + /// The newly created [`Object`] will hold an owned refcount to `parent_resv_obj` if specified. + pub parent_resv_obj: Option<&'a Object>, +} + +/// A shmem-backed GEM object. +/// +/// # Invariants +/// +/// `obj` contains a valid initialized `struct drm_gem_shmem_object` for the lifetime of this +/// object. +#[repr(C)] +#[pin_data] +pub struct Object { + #[pin] + obj: Opaque, + // Parent object that owns this object's DMA reservation object + parent_resv_obj: Option>>, + #[pin] + inner: T, +} + +super::impl_aref_for_gem_obj!(impl for Object where T: DriverObject); + +// SAFETY: This object is thread-safe via our type invariants. +unsafe impl Send for Object {} +// SAFETY: This object is thread-safe via our type invariants. +unsafe impl Sync for Object {} + +impl Object { + /// `drm_gem_object_funcs` vtable suitable for GEM shmem objects. + const VTABLE: bindings::drm_gem_object_funcs = bindings::drm_gem_object_funcs { + free: Some(Self::free_callback), + open: Some(super::open_callback::), + close: Some(super::close_callback::), + print_info: Some(bindings::drm_gem_shmem_object_print_info), + export: if T::HAS_EXPORT { + Some(super::export_callback::) + } else { + None + }, + pin: Some(bindings::drm_gem_shmem_object_pin), + unpin: Some(bindings::drm_gem_shmem_object_unpin), + get_sg_table: Some(bindings::drm_gem_shmem_object_get_sg_table), + vmap: Some(bindings::drm_gem_shmem_object_vmap), + vunmap: Some(bindings::drm_gem_shmem_object_vunmap), + mmap: Some(bindings::drm_gem_shmem_object_mmap), + status: None, + rss: None, + // SAFETY: `drm_gem_shmem_vm_ops` is static const on the C side, so immutable references are + // safe here and such references shall be valid forever + vm_ops: unsafe { &bindings::drm_gem_shmem_vm_ops }, + evict: None, + }; + + /// Return a raw pointer to the embedded drm_gem_shmem_object. + fn as_shmem(&self) -> *mut bindings::drm_gem_shmem_object { + self.obj.get() + } + + /// Create a new shmem-backed DRM object of the given size. + /// + /// Additional config options can be specified using `config`. + pub fn new( + dev: &device::Device, + size: usize, + config: ObjectConfig<'_, T>, + args: T::Args, + ) -> Result> { + let new: Pin> = KBox::try_pin_init( + try_pin_init!(Self { + obj <- Opaque::init_zeroed(), + parent_resv_obj: config.parent_resv_obj.map(|p| p.into()), + inner <- T::new(dev, size, args), + }), + GFP_KERNEL, + )?; + + // SAFETY: `obj.as_raw()` is guaranteed to be valid by the initialization above. + unsafe { (*new.as_raw()).funcs = &Self::VTABLE }; + + // SAFETY: The arguments are all valid via the type invariants. + to_result(unsafe { bindings::drm_gem_shmem_init(dev.as_raw(), new.as_shmem(), size) })?; + + // SAFETY: We never move out of `self`. + let new = KBox::into_raw(unsafe { Pin::into_inner_unchecked(new) }); + + // SAFETY: We're taking over the owned refcount from `drm_gem_shmem_init`. + let obj = unsafe { ARef::from_raw(NonNull::new_unchecked(new)) }; + + // Start filling out values from `config` + if let Some(parent_resv) = config.parent_resv_obj { + // SAFETY: We have yet to expose the new gem object outside of this function, so it is + // safe to modify this field. + unsafe { (*obj.obj.get()).base.resv = parent_resv.raw_dma_resv() }; + } + + // SAFETY: We have yet to expose this object outside of this function, so we're guaranteed + // to have exclusive access - thus making this safe to hold a mutable reference to. + let shmem = unsafe { &mut *obj.as_shmem() }; + shmem.set_map_wc(config.map_wc); + + Ok(obj) + } + + /// Returns the `Device` that owns this GEM object. + pub fn dev(&self) -> &device::Device { + // SAFETY: `dev` will have been initialized in `Self::new()` by `drm_gem_shmem_init()`. + unsafe { device::Device::from_raw((*self.as_raw()).dev) } + } + + extern "C" fn free_callback(obj: *mut bindings::drm_gem_object) { + // SAFETY: + // - DRM always passes a valid gem object here + // - We used drm_gem_shmem_create() in our create_gem_object callback, so we know that + // `obj` is contained within a drm_gem_shmem_object + let this = unsafe { container_of!(obj, bindings::drm_gem_shmem_object, base) }; + + // SAFETY: + // - We're in free_callback - so this function is safe to call. + // - We won't be using the gem resources on `this` after this call. + unsafe { bindings::drm_gem_shmem_release(this) }; + + // SAFETY: + // - We verified above that `obj` is valid, which makes `this` valid + // - This function is set in AllocOps, so we know that `this` is contained within a + // `Object` + let this = unsafe { container_of!(Opaque::cast_from(this), Self, obj) }.cast_mut(); + + // SAFETY: We're recovering the Kbox<> we created in gem_create_object() + let _ = unsafe { KBox::from_raw(this) }; + } + + /// Creates (if necessary) and returns an immutable reference to a scatter-gather table of DMA + /// pages for this object. + /// + /// This will pin the object in memory. + #[inline] + pub fn sg_table(&self) -> Result<&scatterlist::SGTable> { + // SAFETY: + // - drm_gem_shmem_get_pages_sgt is thread-safe. + // - drm_gem_shmem_get_pages_sgt returns either a valid pointer to a scatterlist, or an + // error pointer. + let sgt = from_err_ptr(unsafe { bindings::drm_gem_shmem_get_pages_sgt(self.as_shmem()) })?; + + // SAFETY: We checked above that `sgt` is not an error pointer, so it must be a valid + // pointer to a scatterlist + Ok(unsafe { scatterlist::SGTable::from_raw(sgt) }) + } + + /// Creates (if necessary) and returns an owned reference to a scatter-gather table of DMA pages + /// for this object. + /// + /// This is the same as [`sg_table`](Self::sg_table), except that it instead returns an + /// [`shmem::SGTable`] which holds a reference to the associated gem object, instead of a + /// reference to an [`scatterlist::SGTable`]. + /// + /// This will pin the object in memory. + /// + /// [`shmem::SGTable`]: SGTable + pub fn owned_sg_table(&self) -> Result> { + Ok(SGTable { + sgt: self.sg_table()?.into(), + // INVARIANT: We take an owned refcount to `self` here, ensuring that `sgt` remains + // valid for as long as this `SGTable`. + _owner: self.into(), + }) + } + + /// Attempt to create a [`RawIoSysMap`] from the gem object. + fn raw_vmap(&self) -> Result> { + build_assert!( + mem::size_of::() > 0, + "It doesn't make sense for the mapping type to be a ZST" + ); + + let mut map: MaybeUninit = MaybeUninit::uninit(); + + // SAFETY: drm_gem_shmem_vmap can be called with the DMA reservation lock held + to_result(unsafe { + // TODO: see top of file + bindings::dma_resv_lock(self.raw_dma_resv(), core::ptr::null_mut()); + let ret = bindings::drm_gem_shmem_vmap_locked(self.as_shmem(), map.as_mut_ptr()); + bindings::dma_resv_unlock(self.raw_dma_resv()); + ret + })?; + + // SAFETY: if drm_gem_shmem_vmap did not fail, map is initialized now + Ok(unsafe { RawIoSysMap::from_raw(map.assume_init()) }) + } + + /// Unmap a [`RawIoSysMap`] from the gem object. + /// + /// # Safety + /// + /// - The caller promises that `map` came from a prior call to [`Self::raw_vmap`] on this gem + /// object. + /// - The caller promises that the memory pointed to by `map` will no longer be accesed through + /// this instance. + unsafe fn raw_vunmap(&self, map: &mut RawIoSysMap) { + let resv = self.raw_dma_resv(); + + // SAFETY: + // - This function is safe to call with the DMA reservation lock held + // - Our `ARef` is proof that the underlying gem object here is initialized and thus safe to + // dereference. + unsafe { + // TODO: see top of file + bindings::dma_resv_lock(resv, core::ptr::null_mut()); + bindings::drm_gem_shmem_vunmap_locked(self.as_shmem(), map.as_raw_mut()); + bindings::dma_resv_unlock(resv); + } + } + + /// Creates and returns a virtual kernel memory mapping for this object. + pub fn vmap(&self) -> Result> { + let map = self.raw_vmap()?; + + Ok(VMapRef { + // SAFETY: + // - The size of the vmap is the same as the size of the gem + // - The vmap will remain alive until this object is dropped. + map: unsafe { IoSysMapRef::new(map, self.size()) }, + owner: self, + }) + } + + /// Creates and returns an owned reference to a virtual kernel memory mapping for this object. + pub fn owned_vmap(&self) -> Result> { + Ok(VMap { + map: self.raw_vmap()?, + owner: self.into(), + }) + } +} + +impl Deref for Object { + type Target = T; + + fn deref(&self) -> &Self::Target { + &self.inner + } +} + +impl DerefMut for Object { + fn deref_mut(&mut self) -> &mut Self::Target { + &mut self.inner + } +} + +impl Sealed for Object {} + +impl gem::IntoGEMObject for Object { + fn as_raw(&self) -> *mut bindings::drm_gem_object { + // SAFETY: + // - Our immutable reference is proof that this is safe to dereference. + // - `obj` is always a valid drm_gem_shmem_object via our type invariants. + unsafe { &raw mut (*self.obj.get()).base } + } + + unsafe fn from_raw<'a>(obj: *mut bindings::drm_gem_object) -> &'a Object { + // SAFETY: The safety contract of from_gem_obj() guarantees that `obj` is contained within + // `Self` + unsafe { + let obj = Opaque::cast_from(container_of!(obj, bindings::drm_gem_shmem_object, base)); + + &*container_of!(obj, Object, obj) + } + } +} + +impl driver::AllocImpl for Object { + type Driver = T::Driver; + + const ALLOC_OPS: driver::AllocOps = driver::AllocOps { + gem_create_object: None, + prime_handle_to_fd: None, + prime_fd_to_handle: None, + gem_prime_import: None, + gem_prime_import_sg_table: Some(bindings::drm_gem_shmem_prime_import_sg_table), + dumb_create: Some(bindings::drm_gem_shmem_dumb_create), + dumb_map_offset: None, + }; +} + +/// A borrowed reference to a virtual mapping for a shmem-based GEM object in kernel address space. +pub struct VMapRef<'a, D: DriverObject, T: AsBytes + FromBytes> { + map: IoSysMapRef<'a, T>, + owner: &'a Object, +} + +impl<'a, D: DriverObject, T: AsBytes + FromBytes> Clone for VMapRef<'a, D, T> { + fn clone(&self) -> Self { + // SAFETY: We have a successful vmap already, so this can't fail + unsafe { self.owner.vmap().unwrap_unchecked() } + } +} + +impl<'a, D: DriverObject, T: AsBytes + FromBytes> Deref for VMapRef<'a, D, T> { + type Target = IoSysMapRef<'a, T>; + + fn deref(&self) -> &Self::Target { + &self.map + } +} + +impl<'a, D: DriverObject, T: AsBytes + FromBytes> DerefMut for VMapRef<'a, D, T> { + fn deref_mut(&mut self) -> &mut Self::Target { + &mut self.map + } +} + +impl<'a, D: DriverObject, T: AsBytes + FromBytes> Drop for VMapRef<'a, D, T> { + fn drop(&mut self) { + // SAFETY: Our existence is proof that this map was previously created using self.owner. + unsafe { self.owner.raw_vunmap(&mut self.map) }; + } +} + +/// An owned reference to a virtual mapping for a shmem-based GEM object in kernel address space. +/// +/// # Invariants +/// +/// - The memory pointed to by `map` is at least as large as `T`. +/// - The memory pointed to by `map` remains valid at least until this object is dropped. +pub struct VMap { + map: RawIoSysMap, + owner: ARef>, +} + +impl Clone for VMap { + fn clone(&self) -> Self { + // SAFETY: We have a successful vmap already, so this can't fail + unsafe { self.owner.owned_vmap().unwrap_unchecked() } + } +} + +impl<'a, D: DriverObject, T: AsBytes + FromBytes> From> for VMap { + fn from(value: VMapRef<'a, D, T>) -> Self { + let this = Self { + map: value.map.clone(), + owner: value.owner.into(), + }; + + mem::forget(value); + this + } +} + +impl VMap { + /// Return a reference to the iosys map for this `VMap`. + pub fn get(&self) -> IoSysMapRef<'_, T> { + // SAFETY: The size of the iosys_map is equivalent to the size of the gem object. + unsafe { IoSysMapRef::new(self.map.clone(), self.owner.size()) } + } + + /// Borrows a reference to the object that owns this virtual mapping. + pub fn owner(&self) -> &Object { + &self.owner + } +} + +impl Drop for VMap { + fn drop(&mut self) { + // SAFETY: Our existence is proof that this map was previously created using self.owner + unsafe { self.owner.raw_vunmap(&mut self.map) }; + } +} + +/// SAFETY: `iosys_map` objects are safe to send across threads. +unsafe impl Send for VMap {} +/// SAFETY: `iosys_map` objects are safe to send across threads. +unsafe impl Sync for VMap {} + +/// An owned reference to a scatter-gather table of DMA address spans for a GEM shmem object. +/// +/// This object holds an owned reference to the underlying GEM shmem object, ensuring that the +/// [`scatterlist::SGTable`] referenced by this type remains valid for the lifetime of this object. +/// +/// # Invariants +/// +/// - `sgt` is kept alive by `_owner`, ensuring it remains valid for as long as `Self`. +/// - `sgt` corresponds to the owned object in `_owner`. +/// - This object is only exposed in situations where we know the underlying `SGTable` will not be +/// modified for the lifetime of this object. Thus, it is safe to send/access this type across +/// threads. +pub struct SGTable { + sgt: NonNull, + _owner: ARef>, +} + +// SAFETY: This object is thread-safe via our type invariants. +unsafe impl Send for SGTable {} +// SAFETY: This object is thread-safe via our type invariants. +unsafe impl Sync for SGTable {} + +impl Deref for SGTable { + type Target = scatterlist::SGTable; + + fn deref(&self) -> &Self::Target { + // SAFETY: Creating an immutable reference to this is safe via our type invariants. + unsafe { self.sgt.as_ref() } + } +} diff --git a/rust/kernel/drm/gpuvm.rs b/rust/kernel/drm/gpuvm.rs new file mode 100644 index 00000000000000..e7b073cffe0a58 --- /dev/null +++ b/rust/kernel/drm/gpuvm.rs @@ -0,0 +1,846 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +//! DRM Sync Objects +//! +//! C header: [`include/drm/drm_gpuvm.h`](../../../../include/drm/drm_gpuvm.h) + +#![allow(missing_docs)] + +use crate::{ + bindings, drm, + drm::{ + device, + gem::{ + BaseObject, + IntoGEMObject, // + }, + }, + error::{ + code::{EINVAL, ENOMEM}, + from_result, to_result, Error, Result, + }, + prelude::*, + types::{ARef, AlwaysRefCounted, Opaque}, +}; + +use core::cell::UnsafeCell; +use core::marker::{PhantomData, PhantomPinned}; +use core::mem::ManuallyDrop; +use core::ops::{Deref, DerefMut, Range}; +use core::ptr::NonNull; +use pin_init; + +/// GpuVaFlags to be used for a GpuVa. +/// +/// They can be combined with the operators `|`, `&`, and `!`. +#[derive(Clone, Copy, PartialEq, Default)] +pub struct GpuVaFlags(u32); + +impl GpuVaFlags { + /// No GpuVaFlags (zero) + pub const NONE: GpuVaFlags = GpuVaFlags(0); + + /// The backing GEM is invalidated. + pub const INVALIDATED: GpuVaFlags = GpuVaFlags(bindings::drm_gpuva_flags_DRM_GPUVA_INVALIDATED); + + /// The GpuVa is a sparse mapping. + pub const SPARSE: GpuVaFlags = GpuVaFlags(bindings::drm_gpuva_flags_DRM_GPUVA_SPARSE); + + /// The GpuVa is a repeat mapping. + pub const REPEAT: GpuVaFlags = GpuVaFlags(bindings::drm_gpuva_flags_DRM_GPUVA_REPEAT); + + /// Construct a driver-specific GpuVaFlag. + /// + /// The argument must be a flag index in the range [0..28]. + pub const fn user_flag(index: u32) -> GpuVaFlags { + let flags = bindings::drm_gpuva_flags_DRM_GPUVA_USERBITS << index; + assert!(flags != 0); + GpuVaFlags(flags) + } + + /// Get the raw representation of this flag. + pub(crate) fn as_raw(self) -> u32 { + self.0 + } + + /// Check whether `flags` is contained in `self`. + pub fn contains(self, flags: GpuVaFlags) -> bool { + (self & flags) == flags + } +} + +impl core::ops::BitOr for GpuVaFlags { + type Output = Self; + fn bitor(self, rhs: Self) -> Self::Output { + Self(self.0 | rhs.0) + } +} + +impl core::ops::BitAnd for GpuVaFlags { + type Output = Self; + fn bitand(self, rhs: Self) -> Self::Output { + Self(self.0 & rhs.0) + } +} + +impl core::ops::Not for GpuVaFlags { + type Output = Self; + fn not(self) -> Self::Output { + Self(!self.0) + } +} + +/// Trait that must be implemented by DRM drivers to represent a DRM GpuVm (a GPU address space). +pub trait DriverGpuVm: Sized { + /// The parent `Driver` implementation for this `DriverGpuVm`. + type Driver: drm::Driver; + type GpuVa: DriverGpuVa = (); + type GpuVmBo: DriverGpuVmBo = (); + type StepContext = (); + + fn step_map( + self: &mut UpdatingGpuVm<'_, Self>, + op: &mut OpMap, + ctx: &mut Self::StepContext, + ) -> Result; + fn step_unmap( + self: &mut UpdatingGpuVm<'_, Self>, + op: &mut OpUnMap, + ctx: &mut Self::StepContext, + ) -> Result; + fn step_remap( + self: &mut UpdatingGpuVm<'_, Self>, + op: &mut OpReMap, + vm_bo: &GpuVmBo, + ctx: &mut Self::StepContext, + ) -> Result; +} + +struct StepContext<'a, T: DriverGpuVm> { + gpuvm: &'a GpuVm, + ctx: &'a mut T::StepContext, +} + +/// Trait that must be implemented by DRM drivers to represent a DRM GpuVa (a mapping in GPU address space). +pub trait DriverGpuVa: Sized {} + +impl DriverGpuVa for () {} + +/// Trait that must be implemented by DRM drivers to represent a DRM GpuVmBo (a connection between a BO and a VM). +pub trait DriverGpuVmBo: Sized { + fn new() -> impl PinInit; +} + +/// Provide a default implementation for trivial types +impl DriverGpuVmBo for T { + fn new() -> impl PinInit { + pin_init::default() + } +} + +/// A convenience type for the driver's GEM object. +type Object = <::Driver as drm::driver::Driver>::Object; + +#[repr(transparent)] +pub struct OpMap(bindings::drm_gpuva_op_map, PhantomData); +#[repr(transparent)] +pub struct OpUnMap(bindings::drm_gpuva_op_unmap, PhantomData); +#[repr(transparent)] +pub struct OpReMap(bindings::drm_gpuva_op_remap, PhantomData); + +impl OpMap { + pub fn addr(&self) -> u64 { + self.0.va.addr + } + pub fn range(&self) -> u64 { + self.0.va.range + } + pub fn offset(&self) -> u64 { + self.0.gem.offset + } + pub fn flags(&self) -> GpuVaFlags { + GpuVaFlags(self.0.flags) + } + pub fn object(&self) -> &Object { + let p = unsafe { + as IntoGEMObject>::from_raw(self.0.gem.obj) + }; + // SAFETY: The GEM object has an active reference for the lifetime of this op + &*p + } + pub fn map_and_link_va( + &mut self, + gpuvm: &mut UpdatingGpuVm<'_, T>, + gpuva: Pin>>, + gpuvmbo: &GpuVmBo, + ) -> Result<(), Pin>>> { + // SAFETY: We are handing off the GpuVa ownership and it will not be moved. + let p = KBox::leak(unsafe { Pin::into_inner_unchecked(gpuva) }); + // SAFETY: These C functions are called with the correct invariants + unsafe { + bindings::drm_gpuva_init_from_op(&mut p.gpuva, &mut self.0); + if bindings::drm_gpuva_insert(gpuvm.0.gpuvm() as *mut _, &mut p.gpuva) != 0 { + // EEXIST, return the GpuVa to the caller as an error + return Err(Pin::new_unchecked(KBox::from_raw(p))); + }; + // SAFETY: This takes a new reference to the gpuvmbo. + gpuvmbo.lock_gpuva(); + bindings::drm_gpuva_link(&mut p.gpuva, &gpuvmbo.bo as *const _ as *mut _); + gpuvmbo.unlock_gpuva(); + } + Ok(()) + } +} + +impl OpUnMap { + pub fn va(&self) -> Option<&GpuVa> { + if self.0.va.is_null() { + return None; + } + // SAFETY: Container invariant is guaranteed for ops structs created for our types. + let p = unsafe { crate::container_of!(self.0.va, GpuVa, gpuva) as *mut GpuVa }; + // SAFETY: The GpuVa object reference is valid per the op_unmap contract + Some(unsafe { &*p }) + } + pub fn unmap_and_unlink_va(&mut self) -> Option>>> { + self.do_unmap_and_unlink_va(false) + } + pub fn unmap_and_unlink_va_defer(&mut self) -> Option>>> { + self.do_unmap_and_unlink_va(true) + } + fn do_unmap_and_unlink_va(&mut self, defer: bool) -> Option>>> { + if self.0.va.is_null() { + return None; + } + // SAFETY: Container invariant is guaranteed for ops structs created for our types. + let p = unsafe { crate::container_of!(self.0.va, GpuVa, gpuva) as *mut GpuVa }; + + // SAFETY: The GpuVa object reference is valid per the op_unmap contract + unsafe { + bindings::drm_gpuva_unmap(&mut self.0); + if defer { + bindings::drm_gpuva_unlink_defer(self.0.va); + } else { + bindings::drm_gpuva_unlink(self.0.va); + } + } + + // Unlinking/unmapping relinquishes ownership of the GpuVa object, + // so clear the pointer + self.0.va = core::ptr::null_mut(); + // SAFETY: The GpuVa object reference is valid per the op_unmap contract + Some(unsafe { Pin::new_unchecked(KBox::from_raw(p)) }) + } +} + +impl OpReMap { + pub fn prev_map(&mut self) -> Option<&mut OpMap> { + // SAFETY: The prev pointer must be valid if not-NULL per the op_remap contract + unsafe { (self.0.prev as *mut OpMap).as_mut() } + } + pub fn next_map(&mut self) -> Option<&mut OpMap> { + // SAFETY: The next pointer must be valid if not-NULL per the op_remap contract + unsafe { (self.0.next as *mut OpMap).as_mut() } + } + pub fn unmap(&mut self) -> &mut OpUnMap { + // SAFETY: The unmap pointer is always valid per the op_remap contract + unsafe { (self.0.unmap as *mut OpUnMap).as_mut().unwrap() } + } +} + +/// A base GPU VA. +#[repr(C)] +#[pin_data] +pub struct GpuVa { + #[pin] + gpuva: bindings::drm_gpuva, + #[pin] + inner: T::GpuVa, + #[pin] + _p: PhantomPinned, +} + +impl GpuVa { + pub fn new(inner: impl PinInit) -> Result>>> + where + Error: From, + { + KBox::try_pin_init( + try_pin_init!(Self { + gpuva <- pin_init::init_zeroed(), + inner <- inner, + _p: PhantomPinned + }), + GFP_KERNEL, + ) + } + + pub fn addr(&self) -> u64 { + self.gpuva.va.addr + } + pub fn range(&self) -> u64 { + self.gpuva.va.range + } + pub fn offset(&self) -> u64 { + self.gpuva.gem.offset + } + pub fn flags(&self) -> GpuVaFlags { + GpuVaFlags(self.gpuva.flags) + } +} + +/// A base GpuVm BO. +#[repr(C)] +#[pin_data] +pub struct GpuVmBo { + #[pin] + bo: bindings::drm_gpuvm_bo, + #[pin] + inner: T::GpuVmBo, + #[pin] + _p: PhantomPinned, +} + +impl GpuVmBo { + /// Return a reference to the inner driver data for this GpuVmBo + pub fn inner(&self) -> &T::GpuVmBo { + &self.inner + } + /// Lock the GpuVmBo's gem boject gpuva lock + pub fn lock_gpuva(&self) { + unsafe { + let lock = &raw mut (*self.bo.obj).gpuva.lock; + bindings::mutex_lock(lock); + } + } + /// Unlock the GpuVmBo's gem boject gpuva lock + pub fn unlock_gpuva(&self) { + unsafe { + let lock = &raw mut (*self.bo.obj).gpuva.lock; + bindings::mutex_unlock(lock); + } + } +} + +// SAFETY: DRM GpuVmBo objects are always reference counted and the get/put functions +// satisfy the requirements. +unsafe impl AlwaysRefCounted for GpuVmBo { + fn inc_ref(&self) { + // SAFETY: The drm_gpuvm_get function satisfies the requirements for inc_ref(). + unsafe { bindings::drm_gpuvm_bo_get(&self.bo as *const _ as *mut _) }; + } + + unsafe fn dec_ref(mut obj: NonNull) { + // SAFETY: drm_gpuvm_bo_put() requires holding the gpuva lock, which is the dma_resv lock by default. + // The drm_gpuvm_put function satisfies the requirements for dec_ref(). + // (We do not support custom locks yet.) + unsafe { + let resv = (*obj.as_mut().bo.obj).resv; + bindings::dma_resv_lock(resv, core::ptr::null_mut()); + bindings::drm_gpuvm_bo_put(&mut obj.as_mut().bo); + bindings::dma_resv_unlock(resv); + } + } +} + +/// A base GPU VM. +#[repr(C)] +#[pin_data] +pub struct GpuVm { + #[pin] + gpuvm: Opaque, + #[pin] + inner: UnsafeCell, + #[pin] + _p: PhantomPinned, +} + +pub(super) unsafe extern "C" fn vm_free_callback( + raw_gpuvm: *mut bindings::drm_gpuvm, +) { + // SAFETY: Container invariant is guaranteed for objects using our callback. + let p = unsafe { + crate::container_of!( + raw_gpuvm as *mut Opaque, + GpuVm, + gpuvm + ) as *mut GpuVm + }; + + // SAFETY: p is guaranteed to be valid for drm_gpuvm objects using this callback. + unsafe { drop(KBox::from_raw(p)) }; +} + +pub(super) unsafe extern "C" fn vm_bo_alloc_callback() -> *mut bindings::drm_gpuvm_bo +{ + let obj: Result>>> = KBox::try_pin_init( + try_pin_init!(GpuVmBo:: { + bo <- pin_init::default(), + inner <- T::GpuVmBo::new(), + _p: PhantomPinned + }), + GFP_KERNEL, + ); + + match obj { + Ok(obj) => + // SAFETY: The DRM core will keep this object pinned + unsafe { + let p = KBox::leak(Pin::into_inner_unchecked(obj)); + &mut p.bo + }, + Err(_) => core::ptr::null_mut(), + } +} + +pub(super) unsafe extern "C" fn vm_bo_free_callback( + raw_vm_bo: *mut bindings::drm_gpuvm_bo, +) { + // SAFETY: Container invariant is guaranteed for objects using this callback. + let p = unsafe { crate::container_of!(raw_vm_bo, GpuVmBo, bo) as *mut GpuVmBo }; + + // SAFETY: p is guaranteed to be valid for drm_gpuvm_bo objects using this callback. + unsafe { drop(KBox::from_raw(p)) }; +} + +pub(super) unsafe extern "C" fn step_map_callback( + op: *mut bindings::drm_gpuva_op, + _priv: *mut core::ffi::c_void, +) -> core::ffi::c_int { + // SAFETY: We know this is a map op, and OpMap is a transparent wrapper. + let map = unsafe { &mut *((&mut (*op).__bindgen_anon_1.map) as *mut _ as *mut OpMap) }; + // SAFETY: This is a pointer to a StepContext created inline in sm_map(), which is + // guaranteed to outlive this function. + let ctx = unsafe { &mut *(_priv as *mut StepContext<'_, T>) }; + + from_result(|| { + UpdatingGpuVm(ctx.gpuvm).step_map(map, ctx.ctx)?; + Ok(0) + }) +} + +pub(super) unsafe extern "C" fn step_remap_callback( + op: *mut bindings::drm_gpuva_op, + _priv: *mut core::ffi::c_void, +) -> core::ffi::c_int { + // SAFETY: We know this is a map op, and OpReMap is a transparent wrapper. + let remap = unsafe { &mut *((&mut (*op).__bindgen_anon_1.remap) as *mut _ as *mut OpReMap) }; + // SAFETY: This is a pointer to a StepContext created inline in sm_map(), which is + // guaranteed to outlive this function. + let ctx = unsafe { &mut *(_priv as *mut StepContext<'_, T>) }; + + let p_vm_bo = remap.unmap().va().unwrap().gpuva.vm_bo; + + let res = { + // SAFETY: vm_bo pointer must be valid and non-null by the step_remap invariants. + // Since we grab a ref, this reference's lifetime is until the decref. + let vm_bo_ref = unsafe { + bindings::drm_gpuvm_bo_get(p_vm_bo); + &*(crate::container_of!(p_vm_bo, GpuVmBo, bo) as *mut GpuVmBo) + }; + + from_result(|| { + UpdatingGpuVm(ctx.gpuvm).step_remap(remap, vm_bo_ref, ctx.ctx)?; + Ok(0) + }) + }; + + // SAFETY: We incremented the refcount above, and the Rust reference we took is + // no longer in scope. + unsafe { bindings::drm_gpuvm_bo_put_deferred(p_vm_bo) }; + + res +} +pub(super) unsafe extern "C" fn step_unmap_callback( + op: *mut bindings::drm_gpuva_op, + _priv: *mut core::ffi::c_void, +) -> core::ffi::c_int { + // SAFETY: We know this is a map op, and OpUnMap is a transparent wrapper. + let unmap = unsafe { &mut *((&mut (*op).__bindgen_anon_1.unmap) as *mut _ as *mut OpUnMap) }; + // SAFETY: This is a pointer to a StepContext created inline in sm_map(), which is + // guaranteed to outlive this function. + let ctx = unsafe { &mut *(_priv as *mut StepContext<'_, T>) }; + + from_result(|| { + UpdatingGpuVm(ctx.gpuvm).step_unmap(unmap, ctx.ctx)?; + Ok(0) + }) +} + +pub(super) unsafe extern "C" fn exec_lock_gem_object( + vm_exec: *mut bindings::drm_gpuvm_exec, +) -> core::ffi::c_int { + // SAFETY: The gpuvm_exec object is valid and priv_ is a GEM object pointer + // when this callback is used + unsafe { bindings::drm_exec_lock_obj(&mut (*vm_exec).exec, (*vm_exec).extra.priv_ as *mut _) } +} + +impl GpuVm { + const OPS: bindings::drm_gpuvm_ops = bindings::drm_gpuvm_ops { + vm_free: Some(vm_free_callback::), + op_alloc: None, + op_free: None, + vm_bo_alloc: Some(vm_bo_alloc_callback::), + vm_bo_free: Some(vm_bo_free_callback::), + vm_bo_validate: None, + sm_step_map: Some(step_map_callback::), + sm_step_remap: Some(step_remap_callback::), + sm_step_unmap: Some(step_unmap_callback::), + sm_can_merge_flags: None, + }; + + fn gpuvm(&self) -> *const bindings::drm_gpuvm { + self.gpuvm.get() + } + + pub fn new( + name: &'static CStr, + flags: bindings::drm_gpuvm_flags, + dev: &device::Device, + r_obj: ARef>, + range: Range, + reserve_range: Range, + inner: impl PinInit, + ) -> Result>> + where + Error: From, + { + let obj: Pin> = KBox::try_pin_init( + try_pin_init!(Self { + // SAFETY: drm_gpuvm_init cannot fail and always initializes the member + gpuvm <- unsafe { + pin_init::pin_init_from_closure(move |slot: *mut Opaque | { + // Zero-init required by drm_gpuvm_init + *slot = Opaque::zeroed(); + bindings::drm_gpuvm_init( + Opaque::cast_into(slot), + name.as_char_ptr(), + flags, + dev.as_raw(), + r_obj.as_raw() as *const _ as *mut _, + range.start, + range.end - range.start, + reserve_range.start, + reserve_range.end - reserve_range.start, + &Self::OPS + ); + Ok(()) + }) + }, + // SAFETY: Just passing through to the initializer argument + inner <- unsafe { + pin_init::pin_init_from_closure(move |slot: *mut UnsafeCell | { + inner.__pinned_init(slot as *mut _) + }) + }, + _p: PhantomPinned + }), + GFP_KERNEL, + )?; + + // SAFETY: We never move out of the object + let vm_ref = unsafe { + ARef::from_raw(NonNull::new_unchecked(KBox::leak( + Pin::into_inner_unchecked(obj), + ))) + }; + + Ok(vm_ref) + } + + pub fn exec_lock<'a, 'b>( + &'a self, + obj: Option<&'b Object>, + interruptible: bool, + ) -> Result> { + // Do not try to lock the object if it is internal (since it is already locked). + let is_ext = obj.map(|a| self.is_extobj(a)).unwrap_or(false); + + let mut guard = ManuallyDrop::new(LockedGpuVm { + gpuvm: self, + // vm_exec needs to be pinned, so stick it in a Box. + vm_exec: KBox::init( + init!(bindings::drm_gpuvm_exec { + vm: self.gpuvm() as *mut _, + flags: if interruptible { + bindings::DRM_EXEC_INTERRUPTIBLE_WAIT + } else { + 0 + }, + exec: Default::default(), + extra: match (is_ext, obj) { + (true, Some(obj)) => bindings::drm_gpuvm_exec__bindgen_ty_1 { + fn_: Some(exec_lock_gem_object), + priv_: obj.as_raw() as *const _ as *mut _, + }, + _ => Default::default(), + }, + num_fences: 0, + }), + GFP_KERNEL, + )?, + obj, + }); + + // SAFETY: The object is valid and was initialized above + to_result(unsafe { bindings::drm_gpuvm_exec_lock(&mut *guard.vm_exec) })?; + + Ok(ManuallyDrop::into_inner(guard)) + } + + /// Returns true if the given object is external to the GPUVM + /// (that is, if it does not share the DMA reservation object of the GPUVM). + pub fn is_extobj(&self, obj: &impl IntoGEMObject) -> bool { + let gem = obj.as_raw() as *const _ as *mut _; + // SAFETY: This is safe to call as long as the arguments are valid pointers. + unsafe { bindings::drm_gpuvm_is_extobj(self.gpuvm() as *mut _, gem) } + } + + pub fn bo_deferred_cleanup(&self) { + unsafe { bindings::drm_gpuvm_bo_deferred_cleanup(self.gpuvm() as *mut _) } + } + + pub fn find_bo(& self, + obj: &Object + ) -> Option>> { + obj.lock_gpuva(); + // SAFETY: drm_gem_object.gpuva.lock was just locked. + let p = unsafe { + bindings::drm_gpuvm_bo_find( + self.gpuvm() as *mut _, + obj.as_raw() as *const _ as *mut _, + ) + }; + obj.unlock_gpuva(); + if p.is_null() { + None + } else { + // SAFETY: All the drm_gpuvm_bo objects in this GpuVm are always allocated by us as GpuVmBo. + let p = unsafe { crate::container_of!(p, GpuVmBo, bo) as *mut GpuVmBo }; + // SAFETY: We checked for NULL above, and the types ensure that + // this object was created by vm_bo_alloc_callback. + Some(unsafe { ARef::from_raw(NonNull::new_unchecked(p)) }) + } + } + + pub fn obtain_bo(& self, + obj: &Object) -> Result>> { + obj.lock_gpuva(); + // SAFETY: drm_gem_object.gpuva.lock was just locked. + let p = unsafe { + bindings::drm_gpuvm_bo_obtain( + self.gpuvm() as *mut _, + obj.as_raw() as *const _ as *mut _, + ) + }; + obj.unlock_gpuva(); + if p.is_null() { + Err(ENOMEM) + } else { + // SAFETY: Container invariant is guaranteed for GpuVmBo objects for this GpuVm. + let p = unsafe { crate::container_of!(p, GpuVmBo, bo) as *mut GpuVmBo }; + // SAFETY: We checked for NULL above, and the types ensure that + // this object was created by vm_bo_alloc_callback. + Ok(unsafe { ARef::from_raw(NonNull::new_unchecked(p)) }) + } + } + + pub fn bo_unmap(& self, ctx: &mut T::StepContext, bo: &GpuVmBo) -> Result { + let mut ctx = StepContext { + ctx, + gpuvm: self, + }; + // SAFETY: LockedGpuVm implies the right locks are held. + to_result(unsafe { + bindings::drm_gpuvm_bo_unmap(&bo.bo as *const _ as *mut _, &mut ctx as *mut _ as *mut _) + }) + } +} + +// SAFETY: DRM GpuVm objects are always reference counted and the get/put functions +// satisfy the requirements. +unsafe impl AlwaysRefCounted for GpuVm { + fn inc_ref(&self) { + // SAFETY: The drm_gpuvm_get function satisfies the requirements for inc_ref(). + unsafe { bindings::drm_gpuvm_get(&self.gpuvm as *const _ as *mut _) }; + } + + unsafe fn dec_ref(obj: NonNull) { + // SAFETY: The drm_gpuvm_put function satisfies the requirements for dec_ref(). + unsafe { bindings::drm_gpuvm_put(Opaque::cast_into(&(*obj.as_ptr()).gpuvm)) }; + } +} + +pub struct LockedGpuVm<'a, 'b, T: DriverGpuVm> { + gpuvm: &'a GpuVm, + vm_exec: KBox, + obj: Option<&'b Object>, +} + +impl LockedGpuVm<'_, '_, T> { + pub fn find_bo(&mut self) -> Option>> { + let obj = self.obj?; + // SAFETY: LockedGpuVm implies the right locks are held. + let p = unsafe { + bindings::drm_gpuvm_bo_find( + self.gpuvm.gpuvm() as *mut _, + obj.as_raw() as *const _ as *mut _, + ) + }; + if p.is_null() { + None + } else { + // SAFETY: All the drm_gpuvm_bo objects in this GpuVm are always allocated by us as GpuVmBo. + let p = unsafe { crate::container_of!(p, GpuVmBo, bo) as *mut GpuVmBo }; + // SAFETY: We checked for NULL above, and the types ensure that + // this object was created by vm_bo_alloc_callback. + Some(unsafe { ARef::from_raw(NonNull::new_unchecked(p)) }) + } + } + + pub fn obtain_bo(&mut self) -> Result>> { + let obj = self.obj.ok_or(EINVAL)?; + // SAFETY: LockedGpuVm implies the right locks are held. + let p = unsafe { + bindings::drm_gpuvm_bo_obtain( + self.gpuvm.gpuvm() as *mut _, + obj.as_raw() as *const _ as *mut _, + ) + }; + if p.is_null() { + Err(ENOMEM) + } else { + // SAFETY: Container invariant is guaranteed for GpuVmBo objects for this GpuVm. + let p = unsafe { crate::container_of!(p, GpuVmBo, bo) as *mut GpuVmBo }; + // SAFETY: We checked for NULL above, and the types ensure that + // this object was created by vm_bo_alloc_callback. + Ok(unsafe { ARef::from_raw(NonNull::new_unchecked(p)) }) + } + } + + pub fn sm_map( + &mut self, + ctx: &mut T::StepContext, + req_addr: u64, + req_range: u64, + req_offset: u64, + req_gem_range: u32, + flags: GpuVaFlags, + ) -> Result { + let obj = self.obj.ok_or(EINVAL)?; + let mut ctx = StepContext { + ctx, + gpuvm: self.gpuvm, + }; + + let req = bindings::drm_gpuvm_map_req { + map: bindings::drm_gpuva_op_map { + va: bindings::drm_gpuva_op_map__bindgen_ty_1 { + addr: req_addr, + range: req_range, + }, + gem: bindings::drm_gpuva_op_map__bindgen_ty_2 { + offset: req_offset, + range: req_gem_range, + obj: obj.as_raw(), + }, + flags: flags.as_raw(), + } + }; + + // SAFETY: LockedGpuVm implies the right locks are held. + to_result(unsafe { + bindings::drm_gpuvm_sm_map( + self.gpuvm.gpuvm() as *mut _, + &mut ctx as *mut _ as *mut _, + &raw const req, + ) + }) + } + + pub fn sm_unmap(&mut self, ctx: &mut T::StepContext, req_addr: u64, req_range: u64) -> Result { + let mut ctx = StepContext { + ctx, + gpuvm: self.gpuvm, + }; + // SAFETY: LockedGpuVm implies the right locks are held. + to_result(unsafe { + bindings::drm_gpuvm_sm_unmap( + self.gpuvm.gpuvm() as *mut _, + &mut ctx as *mut _ as *mut _, + req_addr, + req_range, + ) + }) + } + + pub fn bo_unmap(&mut self, ctx: &mut T::StepContext, bo: &GpuVmBo) -> Result { + let mut ctx = StepContext { + ctx, + gpuvm: self.gpuvm, + }; + // SAFETY: LockedGpuVm implies the right locks are held. + to_result(unsafe { + bindings::drm_gpuvm_bo_unmap(&bo.bo as *const _ as *mut _, &mut ctx as *mut _ as *mut _) + }) + } +} + +impl Deref for LockedGpuVm<'_, '_, T> { + type Target = T; + + fn deref(&self) -> &T { + // SAFETY: The existence of this LockedGpuVm implies the lock is held, + // so this is the only reference + unsafe { &*self.gpuvm.inner.get() } + } +} + +impl DerefMut for LockedGpuVm<'_, '_, T> { + fn deref_mut(&mut self) -> &mut T { + // SAFETY: The existence of this UpdatingGpuVm implies the lock is held, + // so this is the only reference + unsafe { &mut *self.gpuvm.inner.get() } + } +} + +impl Drop for LockedGpuVm<'_, '_, T> { + fn drop(&mut self) { + // SAFETY: We hold the lock, so it's safe to unlock + unsafe { + bindings::drm_gpuvm_exec_unlock(&mut *self.vm_exec); + } + } +} + +pub struct UpdatingGpuVm<'a, T: DriverGpuVm>(&'a GpuVm); + +impl UpdatingGpuVm<'_, T> {} + +impl Deref for UpdatingGpuVm<'_, T> { + type Target = T; + + fn deref(&self) -> &T { + // SAFETY: The existence of this UpdatingGpuVm implies the lock is held, + // so this is the only reference + unsafe { &*self.0.inner.get() } + } +} + +impl DerefMut for UpdatingGpuVm<'_, T> { + fn deref_mut(&mut self) -> &mut T { + // SAFETY: The existence of this UpdatingGpuVm implies the lock is held, + // so this is the only reference + unsafe { &mut *self.0.inner.get() } + } +} + +// SAFETY: All our trait methods take locks +unsafe impl Sync for GpuVm {} +// SAFETY: All our trait methods take locks +unsafe impl Send for GpuVm {} + +// SAFETY: All our trait methods take locks +unsafe impl Sync for GpuVmBo {} +// SAFETY: All our trait methods take locks +unsafe impl Send for GpuVmBo {} diff --git a/rust/kernel/drm/mm.rs b/rust/kernel/drm/mm.rs new file mode 100644 index 00000000000000..7b13cfd7d53095 --- /dev/null +++ b/rust/kernel/drm/mm.rs @@ -0,0 +1,310 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +//! DRM MM range allocator +//! +//! C header: [`include/drm/drm_mm.h`](../../../../include/drm/drm_mm.h) + +use crate::{ + alloc::flags::*, + bindings, + error::{to_result, Result}, + sync::{new_mutex, Arc, Mutex, UniqueArc}, + types::Opaque, +}; + +use crate::init::InPlaceInit; +use crate::prelude::KBox; + +use core::{ + marker::{PhantomData, PhantomPinned}, + ops::Deref, + pin::Pin, +}; + +/// Type alias representing a DRM MM node. +pub type Node = Pin>>; + +/// Trait which must be implemented by the inner allocator state type provided by the user. +pub trait AllocInner { + /// Notification that a node was dropped from the allocator. + fn drop_object(&mut self, _start: u64, _size: u64, _color: usize, _object: &mut T) {} +} + +impl AllocInner for () {} + +/// Wrapper type for a `struct drm_mm` plus user AllocInner object. +/// +/// # Invariants +/// The `drm_mm` struct is valid and initialized. +struct MmInner, T>(Opaque, A, PhantomData); + +/// Represents a single allocated node in the MM allocator +pub struct NodeData, T> { + node: bindings::drm_mm_node, + mm: Arc>>, + valid: bool, + /// A drm_mm_node needs to be pinned because nodes reference each other in a linked list. + _pin: PhantomPinned, + inner: T, +} + +// SAFETY: Allocator ops take the mutex, and there are no mutable actions on the node. +unsafe impl, T: Send> Send for NodeData {} +// SAFETY: Allocator ops take the mutex, and there are no mutable actions on the node. +unsafe impl, T: Sync> Sync for NodeData {} + +/// Available MM node insertion modes +#[repr(u32)] +pub enum InsertMode { + /// Search for the smallest hole (within the search range) that fits the desired node. + /// + /// Allocates the node from the bottom of the found hole. + Best = bindings::drm_mm_insert_mode_DRM_MM_INSERT_BEST, + + /// Search for the lowest hole (address closest to 0, within the search range) that fits the + /// desired node. + /// + /// Allocates the node from the bottom of the found hole. + Low = bindings::drm_mm_insert_mode_DRM_MM_INSERT_LOW, + + /// Search for the highest hole (address closest to U64_MAX, within the search range) that fits + /// the desired node. + /// + /// Allocates the node from the top of the found hole. The specified alignment for the node is + /// applied to the base of the node (`Node.start()`). + High = bindings::drm_mm_insert_mode_DRM_MM_INSERT_HIGH, + + /// Search for the most recently evicted hole (within the search range) that fits the desired + /// node. This is appropriate for use immediately after performing an eviction scan and removing + /// the selected nodes to form a hole. + /// + /// Allocates the node from the bottom of the found hole. + Evict = bindings::drm_mm_insert_mode_DRM_MM_INSERT_EVICT, +} + +/// A clonable, interlocked reference to the allocator state. +/// +/// This is useful to perform actions on the user-supplied `AllocInner` type given just a Node, +/// without immediately taking the lock. +#[derive(Clone)] +pub struct InnerRef, T>(Arc>>); + +impl, T> InnerRef { + /// Operate on the user `AllocInner` implementation, taking the lock. + pub fn with(&self, cb: impl FnOnce(&mut A) -> RetVal) -> RetVal { + let mut l = self.0.lock(); + cb(&mut l.1) + } +} + +impl, T> NodeData { + /// Returns the color of the node (an opaque value) + pub fn color(&self) -> usize { + self.node.color as usize + } + + /// Returns the start address of the node + pub fn start(&self) -> u64 { + self.node.start + } + + /// Returns the size of the node in bytes + pub fn size(&self) -> u64 { + self.node.size + } + + /// Operate on the user `AllocInner` implementation associated with this node's allocator. + pub fn with_inner(&self, cb: impl FnOnce(&mut A) -> RetVal) -> RetVal { + let mut l = self.mm.lock(); + cb(&mut l.1) + } + + /// Return a clonable, detached reference to the allocator inner data. + pub fn alloc_ref(&self) -> InnerRef { + InnerRef(self.mm.clone()) + } + + /// Return a mutable reference to the inner data. + pub fn inner_mut(self: Pin<&mut Self>) -> &mut T { + // SAFETY: This is okay because inner is not structural + unsafe { &mut self.get_unchecked_mut().inner } + } +} + +impl, T> Deref for NodeData { + type Target = T; + + fn deref(&self) -> &Self::Target { + &self.inner + } +} + +impl, T> Drop for NodeData { + fn drop(&mut self) { + if self.valid { + let mut guard = self.mm.lock(); + + // Inform the user allocator that a node is being dropped. + guard + .1 + .drop_object(self.start(), self.size(), self.color(), &mut self.inner); + // SAFETY: The MM lock is still taken, so we can safely remove the node. + unsafe { bindings::drm_mm_remove_node(&mut self.node) }; + } + } +} + +/// An instance of a DRM MM range allocator. +pub struct Allocator, T> { + mm: Arc>>, + _p: PhantomData, +} + +impl, T> Allocator { + /// Create a new range allocator for the given start and size range of addresses. + /// + /// The user may optionally provide an inner object representing allocator state, which will + /// be protected by the same lock. If not required, `()` can be used. + #[track_caller] + pub fn new(start: u64, size: u64, inner: A) -> Result> { + // SAFETY: We call `Mutex::init_lock` below. + let mm = UniqueArc::pin_init( + new_mutex!(MmInner(Opaque::uninit(), inner, PhantomData)), + GFP_KERNEL, + )?; + + // SAFETY: The Opaque instance provides a valid pointer, and it is initialized after + // this call. + unsafe { + bindings::drm_mm_init(mm.lock().0.get(), start, size); + } + + Ok(Allocator { + mm: mm.into(), + _p: PhantomData, + }) + } + + /// Insert a new node into the allocator of a given size. + /// + /// `node` is the user `T` type data to store into the node. + pub fn insert_node(&mut self, node: T, size: u64) -> Result> { + self.insert_node_generic(node, size, 0, 0, InsertMode::Best) + } + + /// Insert a new node into the allocator of a given size, with configurable alignment, + /// color, and insertion mode. + /// + /// `node` is the user `T` type data to store into the node. + pub fn insert_node_generic( + &mut self, + node: T, + size: u64, + alignment: u64, + color: usize, + mode: InsertMode, + ) -> Result> { + self.insert_node_in_range(node, size, alignment, color, 0, u64::MAX, mode) + } + + /// Insert a new node into the allocator of a given size, with configurable alignment, + /// color, insertion mode, and sub-range to allocate from. + /// + /// `node` is the user `T` type data to store into the node. + #[allow(clippy::too_many_arguments)] + pub fn insert_node_in_range( + &mut self, + node: T, + size: u64, + alignment: u64, + color: usize, + start: u64, + end: u64, + mode: InsertMode, + ) -> Result> { + let mut mm_node = KBox::new( + NodeData { + // SAFETY: This C struct should be zero-initialized. + node: unsafe { core::mem::zeroed() }, + valid: false, + inner: node, + mm: self.mm.clone(), + _pin: PhantomPinned, + }, + GFP_KERNEL, + )?; + + let guard = self.mm.lock(); + // SAFETY: We hold the lock and all pointers are valid. + to_result(unsafe { + bindings::drm_mm_insert_node_in_range( + guard.0.get(), + &mut mm_node.node, + size, + alignment, + color, + start, + end, + mode as u32, + ) + })?; + + mm_node.valid = true; + + Ok(Pin::from(mm_node)) + } + + /// Insert a node into the allocator at a fixed start address. + /// + /// `node` is the user `T` type data to store into the node. + pub fn reserve_node( + &mut self, + node: T, + start: u64, + size: u64, + color: usize, + ) -> Result> { + let mut mm_node = KBox::new( + NodeData { + // SAFETY: This C struct should be zero-initialized. + node: unsafe { core::mem::zeroed() }, + valid: false, + inner: node, + mm: self.mm.clone(), + _pin: PhantomPinned, + }, + GFP_KERNEL, + )?; + + mm_node.node.start = start; + mm_node.node.size = size; + mm_node.node.color = color as crate::ffi::c_ulong; + + let guard = self.mm.lock(); + // SAFETY: We hold the lock and all pointers are valid. + to_result(unsafe { bindings::drm_mm_reserve_node(guard.0.get(), &mut mm_node.node) })?; + + mm_node.valid = true; + + Ok(Pin::from(mm_node)) + } + + /// Operate on the inner user type `A`, taking the allocator lock + pub fn with_inner(&self, cb: impl FnOnce(&mut A) -> RetVal) -> RetVal { + let mut guard = self.mm.lock(); + cb(&mut guard.1) + } +} + +impl, T> Drop for MmInner { + fn drop(&mut self) { + // SAFETY: If the MmInner is dropped then all nodes are gone (since they hold references), + // so it is safe to tear down the allocator. + unsafe { + bindings::drm_mm_takedown(self.0.get()); + } + } +} + +// SAFETY: MmInner is safely Send if the AllocInner user type is Send. +unsafe impl, T> Send for MmInner {} diff --git a/rust/kernel/drm/mod.rs b/rust/kernel/drm/mod.rs index 1b82b6945edf25..882841415aa414 100644 --- a/rust/kernel/drm/mod.rs +++ b/rust/kernel/drm/mod.rs @@ -6,7 +6,12 @@ pub mod device; pub mod driver; pub mod file; pub mod gem; +#[cfg(CONFIG_DRM_GPUVM = "y")] +pub mod gpuvm; pub mod ioctl; +pub mod mm; +pub mod sched; +pub mod syncobj; pub use self::device::Device; pub use self::driver::Driver; diff --git a/rust/kernel/drm/sched.rs b/rust/kernel/drm/sched.rs new file mode 100644 index 00000000000000..e2f5cd96014f93 --- /dev/null +++ b/rust/kernel/drm/sched.rs @@ -0,0 +1,391 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +//! DRM Scheduler +//! +//! C header: [`include/drm/gpu_scheduler.h`](../../../../include/drm/gpu_scheduler.h) + +use crate::{ + bindings, device, + dma_fence::*, + error::{to_result, Result}, + prelude::*, + sync::{Arc, UniqueArc}, + time::{self, msecs_to_jiffies}, +}; +use core::marker::PhantomData; +use core::mem::MaybeUninit; +use core::ops::{Deref, DerefMut}; +use core::ptr::{addr_of, addr_of_mut}; + +/// Scheduler status after timeout recovery +#[repr(u32)] +pub enum Status { + /// Device recovered from the timeout and can execute jobs again + Nominal = bindings::drm_gpu_sched_stat_DRM_GPU_SCHED_STAT_RESET, + /// Device is no longer available + NoDevice = bindings::drm_gpu_sched_stat_DRM_GPU_SCHED_STAT_ENODEV, +} + +/// Scheduler priorities +#[repr(u32)] +pub enum Priority { + /// Low userspace priority + Low = bindings::drm_sched_priority_DRM_SCHED_PRIORITY_LOW, + /// Normal userspace priority + Normal = bindings::drm_sched_priority_DRM_SCHED_PRIORITY_NORMAL, + /// High userspace priority + High = bindings::drm_sched_priority_DRM_SCHED_PRIORITY_HIGH, + /// Kernel priority (highest) + Kernel = bindings::drm_sched_priority_DRM_SCHED_PRIORITY_KERNEL, +} + +/// Trait to be implemented by driver job objects. +pub trait JobImpl: Sized { + /// Called when the scheduler is considering scheduling this job next, to get another Fence + /// for this job to block on. Once it returns None, run() may be called. + fn prepare(_job: &mut Job) -> Option { + None // Equivalent to NULL function pointer + } + + /// Called to execute the job once all of the dependencies have been resolved. This may be + /// called multiple times, if timed_out() has happened and drm_sched_job_recovery() decides + /// to try it again. + fn run(job: &mut Job) -> Result>; + + /// Called when a job has taken too long to execute, to trigger GPU recovery. + /// + /// This method is called in a workqueue context. + fn timed_out(job: &mut Job) -> Status; + + /// Called for remaining jobs in drm_sched_fini() to ensure the job's fences + /// get signalled before the scheduler is torn down. + fn cancel(job: &mut Job); +} + +unsafe extern "C" fn prepare_job_cb( + sched_job: *mut bindings::drm_sched_job, + _s_entity: *mut bindings::drm_sched_entity, +) -> *mut bindings::dma_fence { + // SAFETY: All of our jobs are Job. + let p = unsafe { crate::container_of!(sched_job, Job, job) as *mut Job }; + + // SAFETY: All of our jobs are Job. + match T::prepare(unsafe { &mut *p }) { + None => core::ptr::null_mut(), + Some(fence) => fence.into_raw(), + } +} + +unsafe extern "C" fn run_job_cb( + sched_job: *mut bindings::drm_sched_job, +) -> *mut bindings::dma_fence { + // SAFETY: All of our jobs are Job. + let p = unsafe { crate::container_of!(sched_job, Job, job) as *mut Job }; + + // SAFETY: All of our jobs are Job. + match T::run(unsafe { &mut *p }) { + Err(e) => e.to_ptr(), + Ok(None) => core::ptr::null_mut(), + Ok(Some(fence)) => fence.into_raw(), + } +} + +unsafe extern "C" fn timedout_job_cb( + sched_job: *mut bindings::drm_sched_job, +) -> bindings::drm_gpu_sched_stat { + // SAFETY: All of our jobs are Job. + let p = unsafe { crate::container_of!(sched_job, Job, job) as *mut Job }; + + // SAFETY: All of our jobs are Job. + T::timed_out(unsafe { &mut *p }) as bindings::drm_gpu_sched_stat +} + +unsafe extern "C" fn free_job_cb(sched_job: *mut bindings::drm_sched_job) { + // SAFETY: All of our jobs are Job. + let p = unsafe { crate::container_of!(sched_job, Job, job) as *mut Job }; + + // Convert the job back to a Box and drop it + // SAFETY: All of our Jobs are created inside a box. + unsafe { drop(KBox::from_raw(p)) }; +} + +unsafe extern "C" fn cancel_job_cb(sched_job: *mut bindings::drm_sched_job) { + // SAFETY: All of our jobs are Job. + let p = unsafe { crate::container_of!(sched_job, Job, job) as *mut Job }; + + // SAFETY: All of our jobs are Job. + T::cancel(unsafe { &mut *p }); + + let fence = unsafe { Fence::get_raw(&mut (*(*sched_job).s_fence).finished) }; + fence.set_error(ECANCELED); + let _ = fence.signal(); +} + +/// A DRM scheduler job. +pub struct Job { + job: bindings::drm_sched_job, + inner: T, +} + +impl Deref for Job { + type Target = T; + + fn deref(&self) -> &Self::Target { + &self.inner + } +} + +impl DerefMut for Job { + fn deref_mut(&mut self) -> &mut Self::Target { + &mut self.inner + } +} + +impl Drop for Job { + fn drop(&mut self) { + // SAFETY: At this point the job has either been submitted and this is being called from + // `free_job_cb` above, or it hasn't and it is safe to call `drm_sched_job_cleanup`. + unsafe { bindings::drm_sched_job_cleanup(&mut self.job) }; + } +} + +/// A pending DRM scheduler job (not yet armed) +pub struct PendingJob<'a, T: JobImpl>(KBox>, PhantomData<&'a T>); + +impl<'a, T: JobImpl> PendingJob<'a, T> { + /// Add a fence as a dependency to the job + pub fn add_dependency(&mut self, fence: Fence) -> Result { + // SAFETY: C call with correct arguments + to_result(unsafe { + bindings::drm_sched_job_add_dependency(&mut self.0.job, fence.into_raw()) + }) + } + + /// Arm the job to make it ready for execution + pub fn arm(mut self) -> ArmedJob<'a, T> { + // SAFETY: C call with correct arguments + unsafe { bindings::drm_sched_job_arm(&mut self.0.job) }; + ArmedJob(self.0, PhantomData) + } +} + +impl<'a, T: JobImpl> Deref for PendingJob<'a, T> { + type Target = Job; + + fn deref(&self) -> &Self::Target { + &self.0 + } +} + +impl<'a, T: JobImpl> DerefMut for PendingJob<'a, T> { + fn deref_mut(&mut self) -> &mut Self::Target { + &mut self.0 + } +} + +/// An armed DRM scheduler job (not yet submitted) +pub struct ArmedJob<'a, T: JobImpl>(KBox>, PhantomData<&'a T>); + +impl<'a, T: JobImpl> ArmedJob<'a, T> { + /// Returns the job fences + pub fn fences(&mut self) -> JobFences<'_> { + // SAFETY: s_fence is always a valid drm_sched_fence pointer + JobFences(unsafe { &mut *self.0.job.s_fence }) + } + + /// Push the job for execution into the scheduler + pub fn push(self) { + // After this point, the job is submitted and owned by the scheduler + let ptr = match self { + ArmedJob(job, _) => KBox::>::into_raw(job), + }; + + // SAFETY: We are passing in ownership of a valid Box raw pointer. + unsafe { bindings::drm_sched_entity_push_job(addr_of_mut!((*ptr).job)) }; + } +} +impl<'a, T: JobImpl> Deref for ArmedJob<'a, T> { + type Target = Job; + + fn deref(&self) -> &Self::Target { + &self.0 + } +} + +impl<'a, T: JobImpl> DerefMut for ArmedJob<'a, T> { + fn deref_mut(&mut self) -> &mut Self::Target { + &mut self.0 + } +} + +/// Reference to the bundle of fences attached to a DRM scheduler job +pub struct JobFences<'a>(&'a mut bindings::drm_sched_fence); + +impl<'a> JobFences<'a> { + /// Returns a new reference to the job scheduled fence. + pub fn scheduled(&mut self) -> Fence { + // SAFETY: self.0.scheduled is always a valid fence + unsafe { Fence::get_raw(&mut self.0.scheduled) } + } + + /// Returns a new reference to the job finished fence. + pub fn finished(&mut self) -> Fence { + // SAFETY: self.0.finished is always a valid fence + unsafe { Fence::get_raw(&mut self.0.finished) } + } +} + +struct EntityInner { + entity: bindings::drm_sched_entity, + // TODO: Allow users to share guilty flag between entities + sched: Arc>, + guilty: bindings::atomic_t, + _p: PhantomData, +} + +impl Drop for EntityInner { + fn drop(&mut self) { + // SAFETY: The EntityInner is initialized. This will cancel/free all jobs. + unsafe { bindings::drm_sched_entity_destroy(&mut self.entity) }; + } +} + +// SAFETY: TODO +unsafe impl Sync for EntityInner {} +// SAFETY: TODO +unsafe impl Send for EntityInner {} + +/// A DRM scheduler entity. +pub struct Entity(Pin>>); + +impl Entity { + /// Create a new scheduler entity. + pub fn new(sched: &Scheduler, priority: Priority) -> Result { + let mut entity: KBox>> = + KBox::new_uninit(GFP_KERNEL | __GFP_ZERO)?; + + let mut sched_ptr = &sched.0.sched as *const _ as *mut _; + + // SAFETY: The Box is allocated above and valid. + unsafe { + bindings::drm_sched_entity_init( + addr_of_mut!((*entity.as_mut_ptr()).entity), + priority as _, + &mut sched_ptr, + 1, + addr_of_mut!((*entity.as_mut_ptr()).guilty), + ) + }; + + // SAFETY: The Box is allocated above and valid. + unsafe { addr_of_mut!((*entity.as_mut_ptr()).sched).write(sched.0.clone()) }; + + // SAFETY: entity is now initialized. + Ok(Self(Pin::from(unsafe { entity.assume_init() }))) + } + + /// Create a new job on this entity. + /// + /// The entity must outlive the pending job until it transitions into the submitted state, + /// after which the scheduler owns it. Since jobs must be submitted in creation order, + /// this requires a mutable reference to the entity, ensuring that only one new job can be + /// in flight at once. + pub fn new_job(&mut self, credits: u32, inner: T) -> Result> { + let mut job: KBox>> = Box::new_uninit(GFP_KERNEL | __GFP_ZERO)?; + + // SAFETY: We hold a reference to the entity (which is a valid pointer), + // and the job object was just allocated above. + to_result(unsafe { + bindings::drm_sched_job_init( + addr_of_mut!((*job.as_mut_ptr()).job), + &self.0.as_ref().get_ref().entity as *const _ as *mut _, + credits, + core::ptr::null_mut(), + 0, + ) + })?; + + // SAFETY: The Box pointer is valid, and this initializes the inner member. + unsafe { addr_of_mut!((*job.as_mut_ptr()).inner).write(inner) }; + + // SAFETY: All fields of the Job are now initialized. + Ok(PendingJob(unsafe { job.assume_init() }, PhantomData)) + } +} + +/// DRM scheduler inner data +pub struct SchedulerInner { + sched: bindings::drm_gpu_scheduler, + _p: PhantomData, +} + +impl Drop for SchedulerInner { + fn drop(&mut self) { + // SAFETY: The scheduler is valid. This assumes drm_sched_fini() will take care of + // freeing all in-progress jobs. + unsafe { bindings::drm_sched_stop(&mut self.sched, core::ptr::null_mut()) }; + unsafe { bindings::drm_sched_fini(&mut self.sched) }; + } +} + +// SAFETY: TODO +unsafe impl Sync for SchedulerInner {} +// SAFETY: TODO +unsafe impl Send for SchedulerInner {} + +/// A DRM Scheduler +pub struct Scheduler(Arc>); + +impl Scheduler { + const OPS: bindings::drm_sched_backend_ops = bindings::drm_sched_backend_ops { + prepare_job: Some(prepare_job_cb::), + run_job: Some(run_job_cb::), + timedout_job: Some(timedout_job_cb::), + free_job: Some(free_job_cb::), + cancel_job: Some(cancel_job_cb::), + }; + /// Creates a new DRM Scheduler object + // TODO: Shared timeout workqueues & scores + pub fn new( + device: &device::Device, + num_rqs: u32, + credit_limit: u32, + hang_limit: u32, + timeout_ms: time::Msecs, + name: &'static CStr, + ) -> Result> { + let mut sched: UniqueArc>> = + UniqueArc::new_uninit(GFP_KERNEL)?; + + // SAFETY: zero sched->sched_rq as drm_sched_init() uses it to exit early withoput initialisation + // TODO: allocate sched zzeroed instead + unsafe { + (*sched.as_mut_ptr()).sched.sched_rq = core::ptr::null_mut(); + }; + + let init_ops = bindings::drm_sched_init_args { + ops: &Self::OPS, + submit_wq: core::ptr::null_mut(), + timeout_wq: core::ptr::null_mut(), + num_rqs, + credit_limit, + hang_limit, + timeout: msecs_to_jiffies(timeout_ms).try_into()?, + score: core::ptr::null_mut(), + name: name.as_char_ptr(), + dev: device.as_raw(), + }; + + // SAFETY: The drm_sched pointer is valid and pinned as it was just allocated above. + // `device` is valid by its type invarants + to_result(unsafe { + bindings::drm_sched_init( + addr_of_mut!((*sched.as_mut_ptr()).sched), + addr_of!(init_ops), + ) + })?; + + // SAFETY: All fields of SchedulerInner are now initialized. + Ok(Scheduler(unsafe { sched.assume_init() }.into())) + } +} diff --git a/rust/kernel/drm/syncobj.rs b/rust/kernel/drm/syncobj.rs new file mode 100644 index 00000000000000..a022e08223588b --- /dev/null +++ b/rust/kernel/drm/syncobj.rs @@ -0,0 +1,83 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +//! DRM Sync Objects +//! +//! C header: [`include/drm/drm_syncobj.h`](../../../../include/drm/drm_syncobj.h) + +use crate::{bindings, dma_fence::*, drm, error::Result, prelude::*}; + +/// A DRM Sync Object +/// +/// # Invariants +/// ptr is a valid pointer to a drm_syncobj and we own a reference to it. +pub struct SyncObj { + ptr: *mut bindings::drm_syncobj, +} + +impl SyncObj { + /// Looks up a sync object by its handle for a given `File`. + pub fn lookup_handle( + file: &drm::File, + handle: u32, + ) -> Result { + // SAFETY: The arguments are all valid per the type invariants. + let ptr = unsafe { bindings::drm_syncobj_find(file.as_raw() as *mut _, handle) }; + + if ptr.is_null() { + Err(ENOENT) + } else { + Ok(SyncObj { ptr }) + } + } + + /// Returns the DMA fence associated with this sync object, if any. + pub fn fence_get(&self) -> Option { + // SAFETY: self.ptr is always valid + let fence = unsafe { bindings::drm_syncobj_fence_get(self.ptr) }; + if fence.is_null() { + None + } else { + // SAFETY: The pointer is non-NULL and drm_syncobj_fence_get acquired an + // additional reference. + Some(unsafe { Fence::from_raw(fence) }) + } + } + + /// Replaces the DMA fence with a new one, or removes it if fence is None. + pub fn replace_fence(&self, fence: Option<&Fence>) { + // SAFETY: All arguments should be valid per the respective type invariants. + unsafe { + bindings::drm_syncobj_replace_fence( + self.ptr, + fence.map_or(core::ptr::null_mut(), |a| a.raw()), + ) + }; + } + + /// Adds a new timeline point to the syncobj. + pub fn add_point(&self, chain: FenceChain, fence: &Fence, point: u64) { + // SAFETY: All arguments should be valid per the respective type invariants. + // This takes over the FenceChain ownership. + unsafe { bindings::drm_syncobj_add_point(self.ptr, chain.into_raw(), fence.raw(), point) }; + } +} + +impl Drop for SyncObj { + fn drop(&mut self) { + // SAFETY: We own a reference to this syncobj. + unsafe { bindings::drm_syncobj_put(self.ptr) }; + } +} + +impl Clone for SyncObj { + fn clone(&self) -> Self { + // SAFETY: `ptr` is valid per the type invariant and we own a reference to it. + unsafe { bindings::drm_syncobj_get(self.ptr) }; + SyncObj { ptr: self.ptr } + } +} + +// SAFETY: drm_syncobj operations are internally locked. +unsafe impl Sync for SyncObj {} +// SAFETY: drm_syncobj operations are internally locked. +unsafe impl Send for SyncObj {} diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 1c0e0e241daa91..ee3b58268b3d51 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -66,8 +66,11 @@ pub mod code { declare_err!(EPIPE, "Broken pipe."); declare_err!(EDOM, "Math argument out of domain of func."); declare_err!(ERANGE, "Math result not representable."); + declare_err!(ENOSYS, "Invalid system call number."); + declare_err!(ENODATA, "No data available."); declare_err!(EOVERFLOW, "Value too large for defined data type."); declare_err!(ETIMEDOUT, "Connection timed out."); + declare_err!(ECANCELED, "Operation Canceled."); declare_err!(ERESTARTSYS, "Restart the system call."); declare_err!(ERESTARTNOINTR, "System call was interrupted by a signal and will be restarted."); declare_err!(ERESTARTNOHAND, "Restart if no handler."); diff --git a/rust/kernel/iio/common/aop_sensors.rs b/rust/kernel/iio/common/aop_sensors.rs new file mode 100644 index 00000000000000..de0835784b66a8 --- /dev/null +++ b/rust/kernel/iio/common/aop_sensors.rs @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Apple AOP sensors common code +//! +//! Copyright (C) The Asahi Linux Contributors + +use core::marker::{PhantomData, PhantomPinned}; +use core::ptr; +use core::sync::atomic::{AtomicU32, Ordering}; + +use kernel::{ + bindings, device, + prelude::*, + soc::apple::aop::FakehidListener, + sync::Arc, + types::{ARef, ForeignOwnable}, + ThisModule, +}; + +/// TODO: add documentation +pub trait MessageProcessor { + /// TODO: add documentation + fn process(&self, message: &[u8]) -> u32; +} + +/// TODO: add documentation +pub struct AopSensorData { + dev: ARef, + ty: u32, + value: AtomicU32, + msg_proc: T, +} + +impl AopSensorData { + /// TODO: add documentation + pub fn new(dev: ARef, ty: u32, msg_proc: T) -> Result>> { + Ok(Arc::new( + AopSensorData { + dev, + ty, + value: AtomicU32::new(0), + msg_proc, + }, + GFP_KERNEL, + )?) + } +} + +impl FakehidListener for AopSensorData { + fn process_fakehid_report(&self, data: &[u8]) -> Result<()> { + self.value + .store(self.msg_proc.process(data), Ordering::Relaxed); + Ok(()) + } +} + +unsafe extern "C" fn aop_read_raw( + dev: *mut bindings::iio_dev, + chan: *const bindings::iio_chan_spec, + val: *mut i32, + _: *mut i32, + mask: isize, +) -> i32 { + let data = unsafe { Arc::>::borrow((*dev).priv_.cast()) }; + let ty = unsafe { (*chan).type_ }; + if mask != bindings::BINDINGS_IIO_CHAN_INFO_PROCESSED as isize + && mask != bindings::BINDINGS_IIO_CHAN_INFO_RAW as isize + { + return EINVAL.to_errno(); + } + if data.ty != ty { + return EINVAL.to_errno(); + } + let value = data.value.load(Ordering::Relaxed); + unsafe { + *val = value as i32; + } + bindings::IIO_VAL_INT as i32 +} + +struct IIOSpec { + spec: [bindings::iio_chan_spec; 1], + vtable: bindings::iio_info, + _p: PhantomPinned, +} + +/// TODO: add documentation +pub struct IIORegistration { + dev: *mut bindings::iio_dev, + spec: Pin>, + registered: bool, + _p: PhantomData>, +} + +impl IIORegistration { + /// TODO: add documentation + pub fn new( + data: Arc>, + name: &'static CStr, + ty: u32, + info_mask: usize, + module: &ThisModule, + ) -> Result { + let spec = KBox::pin( + IIOSpec { + spec: [bindings::iio_chan_spec { + type_: ty, + __bindgen_anon_1: bindings::iio_chan_spec__bindgen_ty_1 { + scan_type: bindings::iio_scan_type { + sign: b'u' as _, + realbits: 32, + storagebits: 32, + ..Default::default() + }, + }, + info_mask_separate: info_mask, + ..Default::default() + }], + vtable: bindings::iio_info { + read_raw: Some(aop_read_raw::), + ..Default::default() + }, + _p: PhantomPinned, + }, + GFP_KERNEL, + )?; + let mut this = IIORegistration { + dev: ptr::null_mut(), + spec, + registered: false, + _p: PhantomData, + }; + this.dev = unsafe { bindings::iio_device_alloc(data.dev.as_raw(), 0) }; + unsafe { + (*this.dev).priv_ = data.clone().into_foreign().cast(); + (*this.dev).name = name.as_ptr() as _; + // spec is now pinned + (*this.dev).channels = this.spec.spec.as_ptr(); + (*this.dev).num_channels = this.spec.spec.len() as i32; + (*this.dev).info = &this.spec.vtable; + } + let ret = unsafe { bindings::__iio_device_register(this.dev, module.as_ptr()) }; + if ret < 0 { + dev_err!(data.dev, "Unable to register iio sensor"); + return Err(Error::from_errno(ret)); + } + this.registered = true; + Ok(this) + } +} + +impl Drop for IIORegistration { + fn drop(&mut self) { + if self.dev != ptr::null_mut() { + unsafe { + if self.registered { + bindings::iio_device_unregister(self.dev); + } + Arc::>::from_foreign((*self.dev).priv_.cast()); + bindings::iio_device_free(self.dev); + } + } + } +} + +unsafe impl Send for IIORegistration {} +unsafe impl Sync for IIORegistration {} diff --git a/rust/kernel/iio/common/mod.rs b/rust/kernel/iio/common/mod.rs new file mode 100644 index 00000000000000..b789e9bf44c9bf --- /dev/null +++ b/rust/kernel/iio/common/mod.rs @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +//! IIO common modules + +#[cfg(any(CONFIG_IIO_AOP_SENSOR_LAS, CONFIG_IIO_AOP_SENSOR_ALS,))] +pub mod aop_sensors; diff --git a/rust/kernel/iio/mod.rs b/rust/kernel/iio/mod.rs new file mode 100644 index 00000000000000..b0cb308f0b454c --- /dev/null +++ b/rust/kernel/iio/mod.rs @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +//! Industrial IO drivers + +pub mod common; diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 4949047af8d7fd..e34958ea9922a7 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -220,17 +220,17 @@ pub trait InPlaceInit: Sized { /// [`Error`]: crate::error::Error #[macro_export] macro_rules! try_init { - ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + ($(&$this:ident in)? $t:ident $(::$p:ident)* $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }) => { - ::pin_init::try_init!($(&$this in)? $t $(::<$($generics),*>)? { + ::pin_init::try_init!($(&$this in)? $t $(::$p)* $(::<$($generics),*>)? { $($fields)* }? $crate::error::Error) }; - ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + ($(&$this:ident in)? $t:ident $(::$p:ident)* $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }? $err:ty) => { - ::pin_init::try_init!($(&$this in)? $t $(::<$($generics),*>)? { + ::pin_init::try_init!($(&$this in)? $t $(::$p)* $(::<$($generics),*>)? { $($fields)* }? $err) }; @@ -280,17 +280,17 @@ macro_rules! try_init { /// [`Error`]: crate::error::Error #[macro_export] macro_rules! try_pin_init { - ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + ($(&$this:ident in)? $t:ident $(::$p:ident)* $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }) => { - ::pin_init::try_pin_init!($(&$this in)? $t $(::<$($generics),*>)? { + ::pin_init::try_pin_init!($(&$this in)? $t $(::$p)* $(::<$($generics),*>)? { $($fields)* }? $crate::error::Error) }; - ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + ($(&$this:ident in)? $t:ident $(::$p:ident)* $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }? $err:ty) => { - ::pin_init::try_pin_init!($(&$this in)? $t $(::<$($generics),*>)? { + ::pin_init::try_pin_init!($(&$this in)? $t $(::$p)* $(::<$($generics),*>)? { $($fields)* }? $err) }; diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs index ee182b0b5452df..e32403d7e179e1 100644 --- a/rust/kernel/io.rs +++ b/rust/kernel/io.rs @@ -13,6 +13,18 @@ pub mod resource; pub use resource::Resource; +/// Physical address type. +/// +/// This is a type alias to either `u32` or `u64` depending on the config option +/// `CONFIG_PHYS_ADDR_T_64BIT`, and it can be a u64 even on 32-bit architectures. +pub type PhysAddr = bindings::phys_addr_t; + +/// Resource Size type. +/// +/// This is a type alias to either `u32` or `u64` depending on the config option +/// `CONFIG_PHYS_ADDR_T_64BIT`, and it can be a u64 even on 32-bit architectures. +pub type ResourceSize = bindings::resource_size_t; + /// Raw representation of an MMIO region. /// /// By itself, the existence of an instance of this structure does not provide any guarantees that @@ -62,8 +74,16 @@ impl IoRaw { /// # Examples /// /// ```no_run -/// # use kernel::{bindings, ffi::c_void, io::{Io, IoRaw}}; -/// # use core::ops::Deref; +/// use kernel::{ +/// bindings, +/// ffi::c_void, +/// io::{ +/// Io, +/// IoRaw, +/// PhysAddr, +/// }, +/// }; +/// use core::ops::Deref; /// /// // See also [`pci::Bar`] for a real example. /// struct IoMem(IoRaw); @@ -76,7 +96,7 @@ impl IoRaw { /// unsafe fn new(paddr: usize) -> Result{ /// // SAFETY: By the safety requirements of this function [`paddr`, `paddr` + `SIZE`) is /// // valid for `ioremap`. -/// let addr = unsafe { bindings::ioremap(paddr as bindings::phys_addr_t, SIZE) }; +/// let addr = unsafe { bindings::ioremap(paddr as PhysAddr, SIZE) }; /// if addr.is_null() { /// return Err(ENOMEM); /// } @@ -120,7 +140,8 @@ macro_rules! define_read { /// Bound checks are performed on compile time, hence if the offset is not known at compile /// time, the build will fail. $(#[$attr])* - #[inline] + // Always inline to optimize out error path of `io_addr_assert`. + #[inline(always)] pub fn $name(&self, offset: usize) -> $type_name { let addr = self.io_addr_assert::<$type_name>(offset); @@ -149,7 +170,8 @@ macro_rules! define_write { /// Bound checks are performed on compile time, hence if the offset is not known at compile /// time, the build will fail. $(#[$attr])* - #[inline] + // Always inline to optimize out error path of `io_addr_assert`. + #[inline(always)] pub fn $name(&self, value: $type_name, offset: usize) { let addr = self.io_addr_assert::<$type_name>(offset); @@ -206,6 +228,15 @@ impl Io { } } + #[inline] + const fn length_valid(offset: usize, length: usize, size: usize) -> bool { + if let Some(end) = offset.checked_add(length) { + end <= size + } else { + false + } + } + #[inline] fn io_addr(&self, offset: usize) -> Result { if !Self::offset_valid::(offset, self.maxsize()) { @@ -217,13 +248,75 @@ impl Io { self.addr().checked_add(offset).ok_or(EINVAL) } - #[inline] + // Always inline to optimize out error path of `build_assert`. + #[inline(always)] fn io_addr_assert(&self, offset: usize) -> usize { build_assert!(Self::offset_valid::(offset, SIZE)); self.addr() + offset } + /// Copy memory block from an i/o memory by filling the specified buffer with it. + /// + /// # Examples + /// ``` + /// use kernel::io::mem::IoMem; + /// use kernel::io::mem::Resource; + /// + /// fn test(device: &Device, res: Resource) -> Result { + /// // Create an i/o memory block of at least 100 bytes. + /// let devres_mem = IoMem::<100>::new(res, device)?; + /// // aquire access to memory block + /// let mem = devres_mem.try_access()?; + /// + /// let mut buffer: [u8; 32] = [0; 32]; + /// + /// // Memcpy 16 bytes from an offset 10 of i/o memory block into the buffer. + /// mem.try_memcpy_fromio(&mut buffer[..16], 10)?; + /// + /// Ok(()) + /// } + /// ``` + pub fn try_memcpy_fromio(&self, buffer: &mut [u8], offset: usize) -> Result { + if buffer.len() == 0 || !Self::length_valid(offset, buffer.len(), self.maxsize()) { + return Err(EINVAL); + } + let addr = self.io_addr::(offset)?; + + // SAFETY: + // - The type invariants guarantee that `adr` is a valid pointer. + // - The bounds of `buffer` are checked with a call to `length_valid`. + unsafe { + bindings::memcpy_fromio( + buffer.as_mut_ptr() as *mut _, + addr as *const _, + buffer.len() as _, + ) + }; + Ok(()) + } + + /// Copy memory block to i/o memory from the specified buffer. + pub fn try_memcpy_toio(&self, offset: usize, buffer: &[u8]) -> Result { + if buffer.len() == 0 || !Self::length_valid(offset, buffer.len(), self.maxsize()) { + return Err(EINVAL); + } + // no need to check since offset + buffer.len() - 1 is valid + let addr = self.io_addr::(offset)?; + + // SAFETY: + // - The type invariants guarantee that `adr` is a valid pointer. + // - The bounds of `buffer` are checked with a call to `length_valid`. + unsafe { + bindings::memcpy_toio( + addr as *mut _, + buffer.as_ptr() as *const _, + buffer.len() as _, + ) + }; + Ok(()) + } + define_read!(read8, try_read8, readb -> u8); define_read!(read16, try_read16, readw -> u16); define_read!(read32, try_read32, readl -> u32); diff --git a/rust/kernel/io/mem.rs b/rust/kernel/io/mem.rs index 6f99510bfc3a63..6b0daff2561087 100644 --- a/rust/kernel/io/mem.rs +++ b/rust/kernel/io/mem.rs @@ -3,6 +3,7 @@ //! Generic memory-mapped IO. use core::ops::Deref; +use core::ptr::NonNull; use crate::c_str; use crate::device::Bound; @@ -14,6 +15,7 @@ use crate::io::resource::Resource; use crate::io::Io; use crate::io::IoRaw; use crate::prelude::*; +use crate::types::declare_flags_type; /// An IO request for a specific device and resource. pub struct IoRequest<'a> { @@ -277,3 +279,104 @@ impl Deref for IoMem { unsafe { Io::from_raw(&self.io) } } } + +declare_flags_type! { + /// Flags to be used when remapping memory. + /// + /// They can be combined with the operators `|`, `&`, and `!`. + pub struct MemFlags(crate::ffi::c_ulong) = 0; +} + +impl MemFlags { + /// Matches the default mapping for System RAM on the architecture. + /// + /// This is usually a read-allocate write-back cache. Moreover, if this flag is specified and + /// the requested remap region is RAM, memremap() will bypass establishing a new mapping and + /// instead return a pointer into the direct map. + pub const WB: MemFlags = MemFlags(bindings::MEMREMAP_WB as _); + + /// Establish a mapping whereby writes either bypass the cache or are written through to memory + /// and never exist in a cache-dirty state with respect to program visibility. + /// + /// Attempts to map System RAM with this mapping type will fail. + pub const WT: MemFlags = MemFlags(bindings::MEMREMAP_WT as _); + /// Establish a writecombine mapping, whereby writes may be coalesced together (e.g. in the + /// CPU's write buffers), but is otherwise uncached. + /// + /// Attempts to map System RAM with this mapping type will fail. + pub const WC: MemFlags = MemFlags(bindings::MEMREMAP_WC as _); + + // Note: Skipping MEMREMAP_ENC/DEC since they are under-documented and have zero + // users outside of arch/x86. +} + +/// Represents a non-MMIO memory block. This is like [`IoMem`], but for cases where it is known +/// that the resource being mapped does not have I/O side effects. +// Invariants: +// `ptr` is a non-null and valid address of at least `usize` bytes and returned by a `memremap` +// call. +// ``` +pub struct Mem { + ptr: NonNull, + size: usize, +} + +impl Mem { + /// Tries to create a new instance of a memory block from a Resource. + /// + /// The resource described by `res` is mapped into the CPU's address space so that it can be + /// accessed directly. It is also consumed by this function so that it can't be mapped again + /// to a different address. + /// + /// If multiple caching flags are specified, the different mapping types will be attempted in + /// the order [`MemFlags::WB`], [`MemFlags::WT`], [`MemFlags::WC`]. + /// + /// # Flags + /// + /// * [`MemFlags::WB`]: Matches the default mapping for System RAM on the architecture. + /// This is usually a read-allocate write-back cache. Moreover, if this flag is specified and + /// the requested remap region is RAM, memremap() will bypass establishing a new mapping and + /// instead return a pointer into the direct map. + /// + /// * [`MemFlags::WT`]: Establish a mapping whereby writes either bypass the cache or are written + /// through to memory and never exist in a cache-dirty state with respect to program visibility. + /// Attempts to map System RAM with this mapping type will fail. + /// * [`MemFlags::WC`]: Establish a writecombine mapping, whereby writes may be coalesced together + /// (e.g. in the CPU's write buffers), but is otherwise uncached. Attempts to map System RAM with + /// this mapping type will fail. + /// + /// # Safety + /// + /// Callers must ensure that either (a) the resulting interface cannot be used to initiate DMA + /// operations, or (b) that DMA operations initiated via the returned interface use DMA handles + /// allocated through the `dma` module. + pub unsafe fn try_new(res: Resource, flags: MemFlags) -> Result { + let size: usize = res.size().try_into()?; + + let addr = unsafe { bindings::memremap(res.start(), size, flags.as_raw()) }; + let ptr = NonNull::new(addr).ok_or(ENOMEM)?; + // INVARIANT: `ptr` is non-null and was returned by `memremap`, so it is valid. + Ok(Self { ptr, size }) + } + + /// Returns the base address of the memory mapping as a raw pointer. + /// + /// It is up to the caller to use this pointer safely, depending on the requirements of the + /// hardware backing this memory block. + pub fn ptr(&self) -> *mut u8 { + self.ptr.cast().as_ptr() + } + + /// Returns the size of this mapped memory block. + pub fn size(&self) -> usize { + self.size + } +} + +impl Drop for Mem { + fn drop(&mut self) { + // SAFETY: By the type invariant, `self.ptr` is a value returned by a previous successful + // call to `memremap`. + unsafe { bindings::memunmap(self.ptr.as_ptr()) }; + } +} diff --git a/rust/kernel/io/resource.rs b/rust/kernel/io/resource.rs index bea3ee0ed87b51..1140eec6dfa092 100644 --- a/rust/kernel/io/resource.rs +++ b/rust/kernel/io/resource.rs @@ -12,11 +12,10 @@ use crate::prelude::*; use crate::str::{CStr, CString}; use crate::types::Opaque; -/// Resource Size type. -/// -/// This is a type alias to either `u32` or `u64` depending on the config option -/// `CONFIG_PHYS_ADDR_T_64BIT`, and it can be a u64 even on 32-bit architectures. -pub type ResourceSize = bindings::phys_addr_t; +pub use super::{ + PhysAddr, + ResourceSize, // +}; /// A region allocated from a parent [`Resource`]. /// @@ -76,6 +75,18 @@ unsafe impl Sync for Region {} pub struct Resource(Opaque); impl Resource { + /// Create a new zeroed [`Resource`] + pub(crate) fn zeroed() -> Self { + Resource { + 0: Opaque::::zeroed(), + } + } + + /// Gets the raw pointer to the wrapped `bindings::resource`. + pub(crate) fn as_raw(&self) -> *mut bindings::resource { + self.0.get() + } + /// Creates a reference to a [`Resource`] from a valid pointer. /// /// # Safety @@ -97,7 +108,7 @@ impl Resource { /// the region, or a part of it, is already in use. pub fn request_region( &self, - start: ResourceSize, + start: PhysAddr, size: ResourceSize, name: CString, flags: Flags, @@ -131,7 +142,7 @@ impl Resource { } /// Returns the start address of the resource. - pub fn start(&self) -> ResourceSize { + pub fn start(&self) -> PhysAddr { let inner = self.0.get(); // SAFETY: Safe as per the invariants of `Resource`. unsafe { (*inner).start } @@ -223,6 +234,8 @@ impl Flags { /// Resource represents a memory region that must be ioremaped using `ioremap_np`. pub const IORESOURCE_MEM_NONPOSTED: Flags = Flags::new(bindings::IORESOURCE_MEM_NONPOSTED); + // Always inline to optimize out error path of `build_assert`. + #[inline(always)] const fn new(value: u32) -> Self { crate::build_assert!(value as u64 <= c_ulong::MAX as u64); Flags(value as c_ulong) diff --git a/rust/kernel/iosys_map.rs b/rust/kernel/iosys_map.rs new file mode 100644 index 00000000000000..039137c051a2f1 --- /dev/null +++ b/rust/kernel/iosys_map.rs @@ -0,0 +1,647 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! IO-agnostic memory mapping interfaces. +//! +//! This crate provides bindings for the `struct iosys_map` type, which provides a common interface +//! for memory mappings which can reside within coherent memory, or within IO memory. +//! +//! C header: [`include/linux/iosys-map.h`](srctree/include/linux/pci.h) + +use crate::{ + prelude::*, + transmute::{AsBytes, FromBytes}, +}; +use bindings; +use core::{ + marker::PhantomData, + mem::{self, MaybeUninit}, + ops::{Deref, DerefMut, Range}, +}; + +/// Raw unsized representation of a `struct iosys_map`. +/// +/// This struct is a transparent wrapper around `struct iosys_map`. The C API does not provide the +/// size of the mapping by default, and thus this type also does not include the size of the +/// mapping. As such, it cannot be used for actually accessing the underlying data pointed to by the +/// mapping. +/// +/// With the exception of kernel crates which may provide their own wrappers around `RawIoSysMap`, +/// users will typically not interact with this type directly. +pub struct RawIoSysMap(bindings::iosys_map, PhantomData); + +impl RawIoSysMap { + /// Convert from a raw `bindings::iosys_map`. + #[allow(unused)] + #[inline] + pub(crate) fn from_raw(val: bindings::iosys_map) -> Self { + Self(val, PhantomData) + } + + /// Convert from a `RawIoSysMap` to a raw `bindings::iosys_map` ref. + #[inline] + pub(crate) fn as_raw(&self) -> &bindings::iosys_map { + &self.0 + } + + /// Convert from a `RawIoSysMap` to a raw mutable `bindings::iosys_map` ref. + #[inline] + pub(crate) fn as_raw_mut(&mut self) -> &mut bindings::iosys_map { + &mut self.0 + } + + /// Returns whether the mapping is within IO memory space or not. + #[inline] + pub fn is_iomem(&self) -> bool { + self.0.is_iomem + } + + /// Returns the size of a single item in this mapping. + pub const fn item_size(&self) -> usize { + mem::size_of::() + } + + /// Returns a mutable address to the memory pointed to by this iosys map. + /// + /// Note that this address is not guaranteed to reside in system memory, and may reside in IO + /// memory. + #[inline] + pub fn as_mut_ptr(&self) -> *mut T { + if self.is_iomem() { + // SAFETY: We confirmed above that this iosys map is contained within iomem, so it's + // safe to read vaddr_iomem + unsafe { self.0.__bindgen_anon_1.vaddr_iomem } + } else { + // SAFETY: We confirmed above that this iosys map is not contaned within iomem, so it's + // safe to read vaddr. + unsafe { self.0.__bindgen_anon_1.vaddr } + } + .cast() + } + + /// Returns an immutable address to the memory pointed to by this iosys map. + /// + /// Note that this address is not guaranteed to reside in system memory, and may reside in IO + /// memory. + #[inline] + pub fn as_ptr(&self) -> *const T { + self.as_mut_ptr().cast_const() + } +} + +// SAFETY: As we make no guarantees about the validity of the mapping, there's no issue with sending +// this type between threads. +unsafe impl Send for RawIoSysMap {} + +impl Clone for RawIoSysMap { + fn clone(&self) -> Self { + Self(self.0, PhantomData) + } +} + +/// A sized version of a [`RawIoSysMap`]. +/// +/// Since this type includes the size of the [`RawIoSysMap`], it can be used for accessing the +/// underlying data pointed to by it. +/// +/// # Invariants +/// +/// - The iosys mapping referenced by this type is guaranteed to be of at least `size` bytes in +/// size +/// - The iosys mapping referenced by this type is valid for the lifetime `'a`. +#[derive(Clone)] +pub struct IoSysMapRef<'a, T: AsBytes + FromBytes> { + map: RawIoSysMap, + size: usize, + _p: PhantomData<&'a T>, +} + +impl<'a, T: AsBytes + FromBytes> IoSysMapRef<'a, T> { + /// Create a new [`IoSysMapRef`] from a [`RawIoSysMap`]. + /// + /// # Safety + /// + /// - The caller guarantees that the mapping referenced by `map` is of at least `size` bytes in + /// size. + /// - The caller guarantees that the mapping referenced by `map` remains valid for the lifetime + /// of `'a`. + #[allow(unused)] + pub(crate) unsafe fn new(map: RawIoSysMap, size: usize) -> IoSysMapRef<'a, T> { + // INVARIANT: Our safety contract fulfills the type invariants of `IoSysMapRef`. + IoSysMapRef { + map, + size, + _p: PhantomData, + } + } + + /// Return the size of the `IoSysMapRef`. + #[inline] + pub fn size(&self) -> usize { + self.size + } + + /// Writes `src` to the region starting from `offset`. + /// + /// `offset` is in units of `T`, not the number of bytes. + /// + /// This function can return the following errors: + /// + /// * [`EOVERFLOW`] if calculating the length of the slice results in an overflow. + /// * [`EINVAL`] if the slice would go out of bounds of the memory region. + /// + /// # Examples + /// + /// ``` + /// use kernel::iosys_map::*; + /// + /// # fn test() -> Result { + /// # let mut map = tests::VecIoSysMap::new(&[0; 3])?; + /// # { + /// # let mut map = map.get(); + /// map.write(&[1, 2, 3], 0)?; // (now [1, 2, 3]) + /// map.write(&[4], 2)?; // (now [1, 2, 4]) + /// # } + /// # + /// # map.assert_eq(&[1, 2, 4]); + /// # + /// # Ok::<(), Error>(()) } + /// # assert!(test().is_ok()); + /// ``` + pub fn write(&mut self, src: &[T], offset: usize) -> Result { + let range = self.compute_range(offset, src.len())?; + + // SAFETY: + // - The address pointed to by this iosys_map is guaranteed to be valid via IoSysMapRef's + // type invariants. + // - We checked that this range of memory is within bounds above + unsafe { + bindings::iosys_map_memcpy_to( + self.as_raw_mut(), + range.start, + src.as_ptr().cast(), + range.len(), + ) + }; + + Ok(()) + } + + /// Memset the region starting from `offset`. + /// + /// `offset` and `len` are in units of `T`, not the number of bytes. + /// + /// This function can return the following errors: + /// + /// * [`EOVERFLOW`] if calculating the length of the slice results in an overflow. + /// * [`EINVAL`] if the slice would go out of bounds of the memory region. + /// + /// # Examples + /// + /// ``` + /// use kernel::iosys_map::*; + /// + /// # fn test() -> Result { + /// # let mut map = tests::VecIoSysMap::new(&[0u8; 3])?; + /// # { + /// # let mut map = map.get(); + /// map.memset(7)?; // (now [7, 7, 7]) + /// # } + /// # + /// # map.assert_eq(&[7, 7, 7]); + /// # + /// # Ok::<(), Error>(()) } + /// # assert!(test().is_ok()); + /// ``` + pub fn memset(&mut self, value: i32) { + // SAFETY: + // - The address pointed to by this iosys_map is guaranteed to be valid via IoSysMapRef's + // type invariants. + unsafe { bindings::iosys_map_memset(self.as_raw_mut(), 0, value, self.size()) }; + } + + /// Attempt to compute the offset of an item within the iosys map using its index. + /// + /// Returns an error if an overflow occurs. + /// + /// # Safety + /// + /// This function checks for overflows, but it explicitly does not check if the offset goes out + /// of bounds. It is the caller's responsibility to check for this before using the returned + /// offset with the iosys_map API. + unsafe fn item_from_index(&self, idx: usize) -> Result { + self.item_size().checked_mul(idx).ok_or(EOVERFLOW) + } + + /// Compute the range within this mapping a specific data type at a given offset would occupy. + /// + /// This function returns the computed range if it doesn't overflow, but does not check whether + /// or not the range is within the bounds of the allocated region pointed to by this iosys + /// mapping. + /// + /// On success, the range returned by this function is guaranteed: + /// + /// * To be a valid range of memory within the virtual mapping for this gem object. + /// * To be properly aligned to [`RawIoSysMap::item_size()`]. + fn compute_range(&self, offset: usize, count: usize) -> Result> { + // SAFETY: If the offset is out of bounds, we'll catch this via overflow checks or when + // checking range_end. + let offset = unsafe { self.item_from_index(offset)? }; + let range_size = count.checked_mul(self.item_size()).ok_or(EOVERFLOW)?; + let range_end = offset.checked_add(range_size).ok_or(EOVERFLOW)?; + + if range_end > self.size { + return Err(EINVAL); + } + + // INVARIANT: Since `offset` and `count` are both in units of `T`, we're guaranteed that the + // range returned here is properly aligned to `T`. + Ok(offset..range_end) + } + + /// Common helper to compute the memory address of an item within the iosys mapping. + /// + /// Public but hidden, since it should only be used from [`iosys_map_read`] and + /// [`iosys_map_write`]. + #[doc(hidden)] + pub fn ptr_from_index(&self, offset: usize) -> Result<*mut T> { + // SAFETY: We check if the resulting offset goes out of bounds below. + let offset = unsafe { self.item_from_index(offset)? }; + + if offset.checked_add(self.item_size()).ok_or(EOVERFLOW)? > self.size() { + return Err(EINVAL); + } + + // SAFETY: We confirmed that `offset` + the item size does not go out of bounds above. + Ok(unsafe { self.as_mut_ptr().byte_add(offset) }) + } + + // TODO: + // This function is currently needed for making the iosys_map_read!() and iosys_map_write!() + // macros work due to a combination of a few limitations: + // + // * The current C API for iosys_map requires that we use offsets for reading/writing + // iosys_maps. + // * Calculating the offset of a field within a struct requires that we either: + // * Use field projection for calculating the offset of the field. We don't have this yet. + // * Explicitly specify the type of the struct, which would be cumbersome to require in the + // read/write macros. + // * Provide a typed pointer (or other reference) to the struct in question, allowing the + // use of &raw const and &raw mut. + // * Keep in mind: we can't simply cast the offset of an item in the iosys map into a typed + // pointer to fulfill the third option. While having invalid memory addresses as pointers + // is ok, adding an offset to a pointer in rust requires that the resulting memory address + // is within the same allocation. Since an invalid pointer has no allocation, we can't + // make that guarantee. + // + // So, until we have field projection the way we workaround this: + // + // * Calculate the offset (self.item_from_index()) of the struct within the iosys map + // * Calculate the memory address of the struct using the offset from the last step + // (self.ptr_from_index()). + // * Use that memory address with &raw const/&raw mut in order to calculate the memory address + // of the desired field, ensuring it remains in the same allocation (happens within the + // macros). + // * Convert the address from the last step back into an offset within the iosys map + // (offset_from_ptr()). + // + // Once we do get field projection, this silly code should be removed. + // + /// Convert a pointer to an item within the iosys map back into an offset. + /// + /// # Safety + /// + /// `ptr` must be a valid pointer to data within the iosys map. + unsafe fn offset_from_ptr(&self, ptr: *const F) -> usize { + // SAFETY: `ptr` always points to data within the memory pointed to by the iosys map, + // meaning it is within the same memory allocation. + // + // Additionally, since `ptr` is within the iosys mapping, the offset here will always be + // positive and safe to cast to a usize. + // (TODO: replace this with byte_offset_from_unsigned once it's available in the kernel) + unsafe { ptr.byte_offset_from(self.as_ptr()) as usize } + } + + /// Reads the value of `field` and ensures that its type is [`FromBytes`]. + /// + /// # Safety + /// + /// This must be called from the [`iosys_map_read`] macro which ensures that the `field` + /// pointer is validated beforehand. + /// + /// Public but hidden since it should only be used from the [`iosys_map_read`] macro. + #[doc(hidden)] + pub unsafe fn field_read(&self, field: *const F) -> F { + let mut field_val = MaybeUninit::::uninit(); + + // SAFETY: `field` is guaranteed valid via our safety contract. + let offset = unsafe { self.offset_from_ptr(field) }; + + // SAFETY: Since we verified `field` is valid above, `offset_from_ptr` will always return a + // valid offset within the iosys map. + unsafe { + bindings::iosys_map_memcpy_from( + field_val.as_mut_ptr().cast(), + self.as_raw(), + offset, + mem::size_of::(), + ) + } + + // SAFETY: We just initialized `field_val` above. + unsafe { field_val.assume_init() } + } + + /// Writes the value of `field` and ensures that its type is [`AsBytes`]. + /// + /// # Safety + /// + /// This must be called from the [`iosys_map_write`] macro which ensures that the `field` + /// pointers validated beforehand. + /// + /// Public but hidden since it should only be used from the [`iosys_map_write`] macro. + #[doc(hidden)] + pub unsafe fn field_write(&mut self, field: *mut F, val: F) { + // SAFETY: `field` is guaranteed valid via our safety contract. + let offset = unsafe { self.offset_from_ptr(field) }; + + // SAFETY: `offset_from_ptr` always returns a valid offset within the iosys map. + unsafe { + bindings::iosys_map_memcpy_to( + self.as_raw_mut(), + offset, + core::ptr::from_ref(&val).cast(), + mem::size_of::(), + ) + } + } +} + +impl<'a, T: AsBytes + FromBytes> Deref for IoSysMapRef<'a, T> { + type Target = RawIoSysMap; + + fn deref(&self) -> &Self::Target { + &self.map + } +} + +impl<'a, T: AsBytes + FromBytes> DerefMut for IoSysMapRef<'a, T> { + fn deref_mut(&mut self) -> &mut Self::Target { + &mut self.map + } +} + +/// Reads from a field of an item from an iosys map ref. +/// +/// # Examples +/// +/// ``` +/// use kernel::{iosys_map::*, transmute::*}; +/// +/// #[derive(Copy, Clone, Debug, PartialEq, Eq)] +/// struct MyStruct { a: u32, b: u16 } +/// +/// // SAFETY: All bit patterns are acceptable values for `MyStruct`. +/// unsafe impl FromBytes for MyStruct {}; +/// // SAFETY: Instances of `MyStruct` have no uninitialized portions. +/// unsafe impl AsBytes for MyStruct {}; +/// +/// # fn test() -> Result { +/// # let mut map = tests::VecIoSysMap::new(&[MyStruct { a: 42, b: 2 }; 3])?; +/// # let map = map.get(); +/// let whole = kernel::iosys_map_read!(map[2])?; +/// assert_eq!(whole, MyStruct { a: 42, b: 2 }); +/// +/// let field = kernel::iosys_map_read!(map[1].b)?; +/// assert_eq!(field, 2); +/// # Ok::<(), Error>(()) } +/// # assert!(test().is_ok()); +/// ``` +#[macro_export] +macro_rules! iosys_map_read { + ($map:expr, $idx:expr, $($field:tt)*) => {{ + (|| -> ::core::result::Result<_, $crate::error::Error> { + let map = &$map; + let item = $crate::iosys_map::IoSysMapRef::ptr_from_index(map, $idx)?; + + // SAFETY: `ptr_from_index()` ensures that `item` is always a valid (although + // potentially not dereferenceable, which is fine here) pointer to within the iosys + // mapping. + unsafe { + let ptr_field = &raw const (*item) $($field)*; + ::core::result::Result::Ok( + $crate::iosys_map::IoSysMapRef::field_read(map, ptr_field) + ) + } + })() + }}; + ($map:ident [ $idx: expr ] $($field:tt)* ) => { + $crate::iosys_map_read!($map, $idx, $($field)*) + }; + ($($map:ident).* [ $idx:expr ] $($field:tt)* ) => { + $crate::iosys_map_read!($($map).*, $idx, $($field)*) + }; +} + +/// Writes to a field of an item from an iosys map ref. +/// +/// # Examples +/// +/// ``` +/// use kernel::{iosys_map::*, transmute::*}; +/// +/// #[derive(Copy, Clone, Debug, PartialEq, Eq)] +/// struct MyStruct { a: u32, b: u16 }; +/// +/// // SAFETY: All bit patterns are acceptable values for `MyStruct`. +/// unsafe impl FromBytes for MyStruct {}; +/// // SAFETY: Instances of `MyStruct` have no uninitialized portions. +/// unsafe impl AsBytes for MyStruct {}; +/// +/// # fn test() -> Result { +/// # let mut map = tests::VecIoSysMap::new(&[MyStruct { a: 42, b: 2 }; 3])?; +/// # let mut map = map.get(); +/// kernel::iosys_map_write!(map[2].b = 1337)?; +/// # assert_eq!(kernel::iosys_map_read!(map[2].b)?, 1337); +/// +/// kernel::iosys_map_write!(map[1] = MyStruct { a: 10, b: 20 })?; +/// # assert_eq!(kernel::iosys_map_read!(map[1])?, MyStruct { a: 10, b: 20 }); +/// # Ok::<(), Error>(()) } +/// # assert!(test().is_ok()); +/// ``` +#[macro_export] +macro_rules! iosys_map_write { + ($map:ident [ $idx:expr ] $($field:tt)*) => {{ + $crate::iosys_map_write!($map, $idx, $($field)*) + }}; + ($($map:ident).* [ $idx:expr ] $($field:tt)* ) => {{ + $crate::iosys_map_write!($($map).*, $idx, $($field)*) + }}; + ($map:expr, $idx:expr, = $val:expr) => { + (|| -> ::core::result::Result<_, $crate::error::Error> { + // (expand these outside of the unsafe block (clippy::macro-metavars-in-unsafe) + let map = &mut $map; + let val = $val; + + let item = $crate::iosys_map::IoSysMapRef::ptr_from_index(map, $idx)?; + // SAFETY: `item_from_index` ensures that `item` is always a valid item. + unsafe { $crate::iosys_map::IoSysMapRef::field_write(map, item, val) }; + ::core::result::Result::Ok(()) + })() + }; + ($map:expr, $idx:expr, $(.$field:ident)* = $val:expr) => { + (|| -> ::core::result::Result<_, $crate::error::Error> { + // (expand these outside of the unsafe block (clippy::macro-metavars-in-unsafe) + let map = &mut $map; + let val = $val; + + let item = $crate::iosys_map::IoSysMapRef::ptr_from_index(map, $idx)?; + + // SAFETY: `ptr_from_index()` ensures that `item` is always a valid (although + // potentially not dereferenceable, which is fine here) pointer to within the iosys + // mapping. + unsafe { + let ptr_field = &raw mut (*item) $(.$field)*; + $crate::iosys_map::IoSysMapRef::field_write(map, ptr_field, val) + }; + ::core::result::Result::Ok(()) + })() + }; +} + +#[doc(hidden)] +#[kunit_tests(rust_iosys_map)] +pub mod tests { + use super::*; + + /// A helper struct for managed IoSysMapRef structs which point to a [`Vec`]. + pub struct VecIoSysMap { + map: RawIoSysMap, + vec: KVec, + } + + impl VecIoSysMap { + pub fn new(src: &[T]) -> Result { + let mut vec = KVec::::new(); + + vec.extend_from_slice(src, GFP_KERNEL)?; + + let map = RawIoSysMap( + bindings::iosys_map { + is_iomem: false, + __bindgen_anon_1: bindings::iosys_map__bindgen_ty_1 { + vaddr: vec.as_mut_ptr().cast(), + }, + }, + PhantomData, + ); + + Ok(Self { map, vec }) + } + + pub fn get(&mut self) -> IoSysMapRef<'_, T> { + // SAFETY: + // * `map` points to `vec`, so the size of `map` is the size of the `vec`. + unsafe { IoSysMapRef::new(self.map.clone(), self.vec.len() * self.map.item_size()) } + } + + /// Assert whether or not the contents of this struct match src. + pub fn assert_eq(&self, src: &[T]) { + assert_eq!(*self.vec.as_ref(), *src) + } + } + + #[test] + fn basic() -> Result { + let mut map = VecIoSysMap::new(&[0; 3])?; + + map.get().write(&[1, 2, 3], 0)?; + map.assert_eq(&[1, 2, 3]); + + map.get().write(&[42], 1)?; + map.assert_eq(&[1, 42, 3]); + + Ok(()) + } + + #[test] + fn oob_accesses() -> Result { + let mut map = VecIoSysMap::new(&[0; 3])?; + + assert!(map.get().write(&[1, 2, 3, 69], 0).is_err()); + assert!(map.get().write(&[1, 2, 3], 69).is_err()); + map.assert_eq(&[0; 3]); + + Ok(()) + } + + #[test] + fn overflows() -> Result { + let mut map = VecIoSysMap::new(&[0; 3])?; + + assert!(map.get().write(&[1], usize::MAX).is_err()); + map.assert_eq(&[0; 3]); + + Ok(()) + } + + #[derive(Copy, Clone, Debug, PartialEq, Eq)] + struct TestStruct { + a: u32, + b: u64, + } + + // SAFETY: All bit patterns are acceptable values for `TestStruct`. + unsafe impl FromBytes for TestStruct {} + // SAFETY: Instances of `TestStruct` have no uninitialized portions. + unsafe impl AsBytes for TestStruct {} + + #[test] + fn basic_macro() -> Result { + let mut expected = [TestStruct { a: 1, b: 2 }; 5]; + let mut map = VecIoSysMap::new(&expected)?; + + { + let mut map_ref = map.get(); + + iosys_map_write!(map_ref[3].a = u32::MAX)?; + expected[3].a = u32::MAX; + + assert_eq!(iosys_map_read!(map_ref[3].a)?, u32::MAX); + assert_eq!( + iosys_map_read!(map_ref[3])?, + TestStruct { a: u32::MAX, b: 2 } + ); + } + + // Compare the entire array, so that we catch any mis-sized writes. + map.assert_eq(&expected); + + Ok(()) + } + + #[test] + fn macro_oob_accesses() -> Result { + let mut map = VecIoSysMap::new(&[TestStruct { a: 1, b: 2 }; 3])?; + let mut map = map.get(); + + assert!(iosys_map_read!(map[5].b).is_err()); + assert!(iosys_map_read!(map[1000]).is_err()); + assert!(iosys_map_write!(map[6969].a = 999).is_err()); + assert!(iosys_map_write!(map[243] = TestStruct { a: 99, b: 22 }).is_err()); + + Ok(()) + } + + #[test] + fn macro_overflows() -> Result { + let mut map = VecIoSysMap::new(&[TestStruct { a: 1, b: 2 }; 3])?; + let mut map = map.get(); + + assert!(iosys_map_read!(map[usize::MAX]).is_err()); + assert!(iosys_map_read!(map[usize::MAX].b).is_err()); + assert!(iosys_map_write!(map[usize::MAX] = TestStruct { a: 1, b: 1 }).is_err()); + assert!(iosys_map_write!(map[usize::MAX].b = 1).is_err()); + + Ok(()) + } +} diff --git a/rust/kernel/irq/flags.rs b/rust/kernel/irq/flags.rs index adfde96ec47cf4..d26e25af06eea8 100644 --- a/rust/kernel/irq/flags.rs +++ b/rust/kernel/irq/flags.rs @@ -96,6 +96,8 @@ impl Flags { self.0 } + // Always inline to optimize out error path of `build_assert`. + #[inline(always)] const fn new(value: u32) -> Self { build_assert!(value as u64 <= c_ulong::MAX as u64); Self(value as c_ulong) diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 3dd7bebe78882a..052f9adcd6b242 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -16,6 +16,21 @@ // Please see https://github.com/Rust-for-Linux/linux/issues/2 for details on // the unstable features in use. // +// ============ start asahi downstream features =========== +#![feature(associated_type_defaults)] +// +#![feature(cfg_version)] +// +// Stable since Rust 1.87.0. +#![feature(ptr_sub_ptr)] +// +#![feature(sized_type_properties)] +// +#![feature(slice_range)] +// +#![cfg_attr(CONFIG_RUSTC_HAS_COERCE_POINTEE, feature(pin_coerce_unsized_trait))] +// ============ end asahi dowanstream features ============ +// // Stable since Rust 1.79.0. #![feature(generic_nonzero)] #![feature(inline_const)] @@ -62,6 +77,7 @@ extern crate self as kernel; pub use ffi; pub mod acpi; +pub mod addr; pub mod alloc; #[cfg(CONFIG_AUXILIARY_BUS)] pub mod auxiliary; @@ -81,10 +97,15 @@ pub mod cpufreq; pub mod cpumask; pub mod cred; pub mod debugfs; +#[cfg(CONFIG_DEV_COREDUMP)] +pub mod devcoredump; pub mod device; pub mod device_id; pub mod devres; pub mod dma; +pub mod dma_buf; +#[cfg(CONFIG_DMA_SHARED_BUFFER)] +pub mod dma_fence; pub mod driver; #[cfg(CONFIG_DRM = "y")] pub mod drm; @@ -95,9 +116,12 @@ pub mod firmware; pub mod fmt; pub mod fs; pub mod id_pool; +#[cfg(CONFIG_IIO)] +pub mod iio; pub mod init; pub mod io; pub mod ioctl; +pub mod iosys_map; pub mod iov; pub mod irq; pub mod jump_label; @@ -107,6 +131,7 @@ pub mod list; pub mod maple_tree; pub mod miscdevice; pub mod mm; +pub mod module_param; #[cfg(CONFIG_NET)] pub mod net; pub mod of; @@ -128,6 +153,7 @@ pub mod scatterlist; pub mod security; pub mod seq_file; pub mod sizes; +pub mod soc; mod static_assert; #[doc(hidden)] pub mod std_vendor; diff --git a/rust/kernel/maple_tree.rs b/rust/kernel/maple_tree.rs index e72eec56bf5772..265d6396a78a17 100644 --- a/rust/kernel/maple_tree.rs +++ b/rust/kernel/maple_tree.rs @@ -265,7 +265,16 @@ impl MapleTree { loop { // This uses the raw accessor because we're destroying pointers without removing them // from the maple tree, which is only valid because this is the destructor. - let ptr = ma_state.mas_find_raw(usize::MAX); + // + // Take the rcu lock because mas_find_raw() requires that you hold either the spinlock + // or the rcu read lock. This is only really required if memory reclaim might + // reallocate entries in the tree, as we otherwise have exclusive access. That feature + // doesn't exist yet, so for now, taking the rcu lock only serves the purpose of + // silencing lockdep. + let ptr = { + let _rcu = kernel::sync::rcu::Guard::new(); + ma_state.mas_find_raw(usize::MAX) + }; if ptr.is_null() { break; } diff --git a/rust/kernel/module_param.rs b/rust/kernel/module_param.rs new file mode 100644 index 00000000000000..e7d5c930a467d2 --- /dev/null +++ b/rust/kernel/module_param.rs @@ -0,0 +1,181 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Support for module parameters. +//! +//! C header: [`include/linux/moduleparam.h`](srctree/include/linux/moduleparam.h) + +use crate::prelude::*; +use crate::str::BStr; +use bindings; +use kernel::sync::SetOnce; + +/// Newtype to make `bindings::kernel_param` [`Sync`]. +#[repr(transparent)] +#[doc(hidden)] +pub struct KernelParam(bindings::kernel_param); + +impl KernelParam { + #[doc(hidden)] + pub const fn new(val: bindings::kernel_param) -> Self { + Self(val) + } +} + +// SAFETY: C kernel handles serializing access to this type. We never access it +// from Rust module. +unsafe impl Sync for KernelParam {} + +/// Types that can be used for module parameters. +// NOTE: This trait is `Copy` because drop could produce unsoundness during teardown. +pub trait ModuleParam: Sized + Copy { + /// Parse a parameter argument into the parameter value. + fn try_from_param_arg(arg: &BStr) -> Result; +} + +/// Set the module parameter from a string. +/// +/// Used to set the parameter value at kernel initialization, when loading +/// the module or when set through `sysfs`. +/// +/// See `struct kernel_param_ops.set`. +/// +/// # Safety +/// +/// - If `val` is non-null then it must point to a valid null-terminated string that must be valid +/// for reads for the duration of the call. +/// - `param` must be a pointer to a `bindings::kernel_param` initialized by the rust module macro. +/// The pointee must be valid for reads for the duration of the call. +/// +/// # Note +/// +/// - The safety requirements are satisfied by C API contract when this function is invoked by the +/// module subsystem C code. +/// - Currently, we only support read-only parameters that are not readable from `sysfs`. Thus, this +/// function is only called at kernel initialization time, or at module load time, and we have +/// exclusive access to the parameter for the duration of the function. +/// +/// [`module!`]: macros::module +unsafe extern "C" fn set_param(val: *const c_char, param: *const bindings::kernel_param) -> c_int +where + T: ModuleParam, +{ + // NOTE: If we start supporting arguments without values, val _is_ allowed + // to be null here. + if val.is_null() { + // TODO: Use pr_warn_once available. + crate::pr_warn!("Null pointer passed to `module_param::set_param`"); + return EINVAL.to_errno(); + } + + // SAFETY: By function safety requirement, val is non-null, null-terminated + // and valid for reads for the duration of this function. + let arg = unsafe { CStr::from_char_ptr(val) }; + + crate::error::from_result(|| { + let new_value = T::try_from_param_arg(arg)?; + + // SAFETY: By function safety requirements, this access is safe. + let container = unsafe { &*((*param).__bindgen_anon_1.arg.cast::>()) }; + + container + .populate(new_value) + .then_some(0) + .ok_or(kernel::error::code::EEXIST) + }) +} + +macro_rules! impl_int_module_param { + ($ty:ident) => { + impl ModuleParam for $ty { + fn try_from_param_arg(arg: &BStr) -> Result { + <$ty as crate::str::parse_int::ParseInt>::from_str(arg) + } + } + }; +} + +impl_int_module_param!(i8); +impl_int_module_param!(u8); +impl_int_module_param!(i16); +impl_int_module_param!(u16); +impl_int_module_param!(i32); +impl_int_module_param!(u32); +impl_int_module_param!(i64); +impl_int_module_param!(u64); +impl_int_module_param!(isize); +impl_int_module_param!(usize); + +/// A wrapper for kernel parameters. +/// +/// This type is instantiated by the [`module!`] macro when module parameters are +/// defined. You should never need to instantiate this type directly. +/// +/// Note: This type is `pub` because it is used by module crates to access +/// parameter values. +pub struct ModuleParamAccess { + value: SetOnce, + default: T, +} + +// SAFETY: We only create shared references to the contents of this container, +// so if `T` is `Sync`, so is `ModuleParamAccess`. +unsafe impl Sync for ModuleParamAccess {} + +impl ModuleParamAccess { + #[doc(hidden)] + pub const fn new(default: T) -> Self { + Self { + value: SetOnce::new(), + default, + } + } + + /// Get a shared reference to the parameter value. + // Note: When sysfs access to parameters are enabled, we have to pass in a + // held lock guard here. + pub fn value(&self) -> &T { + self.value.as_ref().unwrap_or(&self.default) + } + + /// Get a mutable pointer to `self`. + /// + /// NOTE: In most cases it is not safe deref the returned pointer. + pub const fn as_void_ptr(&self) -> *mut c_void { + core::ptr::from_ref(self).cast_mut().cast() + } +} + +#[doc(hidden)] +/// Generate a static [`kernel_param_ops`](srctree/include/linux/moduleparam.h) struct. +/// +/// # Examples +/// +/// ```ignore +/// make_param_ops!( +/// /// Documentation for new param ops. +/// PARAM_OPS_MYTYPE, // Name for the static. +/// MyType // A type which implements [`ModuleParam`]. +/// ); +/// ``` +macro_rules! make_param_ops { + ($ops:ident, $ty:ty) => { + #[doc(hidden)] + pub static $ops: $crate::bindings::kernel_param_ops = $crate::bindings::kernel_param_ops { + flags: 0, + set: Some(set_param::<$ty>), + get: None, + free: None, + }; + }; +} + +make_param_ops!(PARAM_OPS_I8, i8); +make_param_ops!(PARAM_OPS_U8, u8); +make_param_ops!(PARAM_OPS_I16, i16); +make_param_ops!(PARAM_OPS_U16, u16); +make_param_ops!(PARAM_OPS_I32, i32); +make_param_ops!(PARAM_OPS_U32, u32); +make_param_ops!(PARAM_OPS_I64, i64); +make_param_ops!(PARAM_OPS_U64, u64); +make_param_ops!(PARAM_OPS_ISIZE, isize); +make_param_ops!(PARAM_OPS_USIZE, usize); diff --git a/rust/kernel/of.rs b/rust/kernel/of.rs index 58b20c367f993f..80c604ee831452 100644 --- a/rust/kernel/of.rs +++ b/rust/kernel/of.rs @@ -8,6 +8,17 @@ use crate::{ prelude::*, }; +// Note: Most OF functions turn into inline dummies with CONFIG_OF(_*) disabled. +// We have to either add config conditionals to helpers.c or here; let's do it +// here for now. In the future, once bindgen can auto-generate static inline +// helpers, this can go away if desired. + +use core::marker::PhantomData; +use core::num::NonZeroU32; + +use crate::error::to_result; +use crate::io::resource::Resource; + /// IdTable type for OF drivers. pub type IdTable = &'static dyn kernel::device_id::IdTable; @@ -50,6 +61,518 @@ impl DeviceId { } } +/// Type alias for an OF phandle +pub type PHandle = bindings::phandle; + +/// An OF device tree node. +/// +/// # Invariants +/// +/// `raw_node` points to a valid OF node, and we hold a reference to it. +pub struct Node { + raw_node: *mut bindings::device_node, +} + +#[allow(dead_code)] +impl Node { + /// Creates a `Node` from a raw C pointer. The pointer must be owned (the caller + /// gives up its reference). If the pointer is NULL, returns None. + pub(crate) unsafe fn from_raw(raw_node: *mut bindings::device_node) -> Option { + if raw_node.is_null() { + None + } else { + // INVARIANT: `raw_node` is valid per the above contract, and non-null per the + // above check. + Some(Node { raw_node }) + } + } + + /// Creates a `Node` from a raw C pointer. The pointer must be borrowed (the caller + /// retains its reference, which must be valid for the duration of the call). If the + /// pointer is NULL, returns None. + pub(crate) unsafe fn get_from_raw(raw_node: *mut bindings::device_node) -> Option { + // SAFETY: `raw_node` is valid or NULL per the above contract. `of_node_get` can handle + // NULL. + unsafe { + #[cfg(CONFIG_OF_DYNAMIC)] + bindings::of_node_get(raw_node); + Node::from_raw(raw_node) + } + } + + /// Returns a reference to the underlying C `device_node` structure. + pub(crate) fn node(&self) -> &bindings::device_node { + // SAFETY: `raw_node` is valid per the type invariant. + unsafe { &*self.raw_node } + } + + /// Returns the name of the node. + pub(crate) fn name(&self) -> &CStr { + // SAFETY: The lifetime of the `CStr` is the same as the lifetime of this `Node`. + unsafe { CStr::from_char_ptr(self.node().name) } + } + + /// Returns the phandle for this node. + pub(crate) fn phandle(&self) -> PHandle { + self.node().phandle + } + + /// Returns the full name (with address) for this node. + pub(crate) fn full_name(&self) -> &CStr { + // SAFETY: The lifetime of the `CStr` is the same as the lifetime of this `Node`. + unsafe { CStr::from_char_ptr(self.node().full_name) } + } + + /// Returns `true` if the node is the root node. + pub(crate) fn is_root(&self) -> bool { + #[cfg(not(CONFIG_OF))] + { + false + } + #[cfg(CONFIG_OF)] + // SAFETY: `raw_node` is valid per the type invariant + unsafe { + bindings::of_node_is_root(self.raw_node) + } + } + + /// Returns the parent node, if any. + pub(crate) fn parent(&self) -> Option { + #[cfg(not(CONFIG_OF))] + { + None + } + #[cfg(CONFIG_OF)] + // SAFETY: `raw_node` is valid per the type invariant, and `of_get_parent()` takes a + // new reference to the parent (or returns NULL). + unsafe { + Node::from_raw(bindings::of_get_parent(self.raw_node)) + } + } + + /// Returns an iterator over the node's children. + // TODO: use type alias for return type once type_alias_impl_trait is stable + pub fn children( + &self, + ) -> NodeIterator<'_, impl Fn(*mut bindings::device_node) -> *mut bindings::device_node + '_> + { + #[cfg(not(CONFIG_OF))] + { + NodeIterator::new(|_prev| core::ptr::null_mut()) + } + #[cfg(CONFIG_OF)] + // SAFETY: `raw_node` is valid per the type invariant, and the lifetime of the `NodeIterator` + // does not exceed the lifetime of the `Node` so it can borrow its reference. + NodeIterator::new(|prev| unsafe { bindings::of_get_next_child(self.raw_node, prev) }) + } + + /// Find a child by its name and return it, or None if not found. + #[allow(unused_variables)] + pub(crate) fn get_child_by_name(&self, name: &CStr) -> Option { + #[cfg(not(CONFIG_OF))] + { + None + } + #[cfg(CONFIG_OF)] + // SAFETY: `raw_node` is valid per the type invariant. + unsafe { + Node::from_raw(bindings::of_get_child_by_name( + self.raw_node, + name.as_char_ptr(), + )) + } + } + + /// Checks whether the node is compatible with the given compatible string. + /// + /// Returns `None` if there is no match, or `Some` if there is, with the value + /// representing as match score (higher values for more specific compatible matches). + #[allow(unused_variables)] + pub(crate) fn is_compatible(&self, compatible: &CStr) -> Option { + #[cfg(not(CONFIG_OF))] + let ret = 0; + #[cfg(CONFIG_OF)] + let ret = + // SAFETY: `raw_node` is valid per the type invariant. + unsafe { bindings::of_device_is_compatible(self.raw_node, compatible.as_char_ptr()) }; + + NonZeroU32::new(ret.try_into().ok()?) + } + + /// Parse a phandle property and return the Node referenced at a given index, if any. + /// + /// Used only for phandle properties with no arguments. + #[allow(unused_variables)] + pub fn parse_phandle(&self, name: &CStr, index: usize) -> Option { + #[cfg(not(CONFIG_OF))] + { + None + } + #[cfg(CONFIG_OF)] + // SAFETY: `raw_node` is valid per the type invariant. `of_parse_phandle` returns an + // owned reference. + unsafe { + Node::from_raw(bindings::of_parse_phandle( + self.raw_node, + name.as_char_ptr(), + index.try_into().ok()?, + )) + } + } + + #[allow(unused_variables)] + /// Get a reserved memory region as a resource + pub fn reserved_mem_region_to_resource_byname(&self, name: &CStr) -> Result { + #[cfg(not(CONFIG_OF))] + { + Err(ENOENT) + } + #[cfg(CONFIG_OF)] + { + let res = Resource::zeroed(); + // SAFETY: This function is safe to call as long as the arguments are valid pointers. + let ret = unsafe { + bindings::of_reserved_mem_region_to_resource_byname( + self.raw_node, + name.as_char_ptr(), + res.as_raw(), + ) + }; + to_result(ret)?; + + Ok(res) + } + } + + #[allow(unused_variables)] + /// Look up a node property by name, returning a `Property` object if found. + pub(crate) fn find_property(&self, propname: &CStr) -> Option> { + #[cfg(not(CONFIG_OF))] + { + None + } + #[cfg(CONFIG_OF)] + // SAFETY: `raw_node` is valid per the type invariant. The property structure + // returned borrows the reference to the owning node, and so has the same + // lifetime. + unsafe { + Property::from_raw(bindings::of_find_property( + self.raw_node, + propname.as_char_ptr(), + core::ptr::null_mut(), + )) + } + } + + /// Look up a mandatory node property by name, and decode it into a value type. + /// + /// Returns `Err(ENOENT)` if the property is not found. + /// + /// The type `T` must implement `TryFrom>`. + pub fn get_property<'a, T: TryFrom>>(&'a self, propname: &CStr) -> Result + where + crate::error::Error: From<>>::Error>, + { + Ok(self.find_property(propname).ok_or(ENOENT)?.try_into()?) + } + + /// Look up an optional node property by name, and decode it into a value type. + /// + /// Returns `Ok(None)` if the property is not found. + /// + /// The type `T` must implement `TryFrom>`. + pub fn get_opt_property<'a, T: TryFrom>>( + &'a self, + propname: &CStr, + ) -> Result> + where + crate::error::Error: From<>>::Error>, + { + self.find_property(propname) + .map_or(Ok(None), |p| Ok(Some(p.try_into()?))) + } +} + +/// A property attached to a device tree `Node`. +/// +/// # Invariants +/// +/// `raw` must be valid and point to a property that outlives the lifetime of this object. +#[derive(Copy, Clone)] +pub struct Property<'a> { + raw: *mut bindings::property, + _p: PhantomData<&'a Node>, +} + +impl<'a> Property<'a> { + #[cfg(CONFIG_OF)] + /// Create a `Property` object from a raw C pointer. Returns `None` if NULL. + /// + /// The passed pointer must be valid and outlive the lifetime argument, or NULL. + unsafe fn from_raw(raw: *mut bindings::property) -> Option> { + if raw.is_null() { + None + } else { + Some(Property { + raw, + _p: PhantomData, + }) + } + } + + /// Returns the name of the property as a `CStr`. + pub fn name(&self) -> &CStr { + // SAFETY: `raw` is valid per the type invariant, and the lifetime of the `CStr` does not + // outlive it. + unsafe { CStr::from_char_ptr((*self.raw).name) } + } + + /// Returns the name of the property as a `&[u8]`. + pub fn value(&self) -> &[u8] { + // SAFETY: `raw` is valid per the type invariant, and the lifetime of the slice does not + // outlive it. + unsafe { core::slice::from_raw_parts((*self.raw).value as *const u8, self.len()) } + } + + /// Returns the length of the property in bytes. + pub fn len(&self) -> usize { + // SAFETY: `raw` is valid per the type invariant. + unsafe { (*self.raw).length.try_into().unwrap() } + } + + /// Returns true if the property is empty (zero-length), which typically represents boolean true. + pub fn is_empty(&self) -> bool { + self.len() == 0 + } +} + +/// A trait that represents a value decodable from a property with a fixed unit size. +/// +/// This allows us to auto-derive property decode implementations for `Vec`. +pub trait PropertyUnit: Sized { + /// The size in bytes of a single data unit. + const UNIT_SIZE: usize; + + /// Decode this data unit from a byte slice. The passed slice will have a length of `UNIT_SIZE`. + fn from_bytes(data: &[u8]) -> Result; +} + +// This doesn't work... +// impl<'a, T: PropertyUnit> TryFrom> for T { +// type Error = Error; +// +// fn try_from(p: Property<'_>) -> core::result::Result { +// if p.value().len() != T::UNIT_SIZE { +// Err(EINVAL) +// } else { +// Ok(T::from_bytes(p.value())?) +// } +// } +// } + +impl<'a, T: PropertyUnit> TryFrom> for KVec { + type Error = Error; + + fn try_from(p: Property<'_>) -> core::result::Result, Self::Error> { + if p.len() % T::UNIT_SIZE != 0 { + return Err(EINVAL); + } + + let mut v = Vec::new(); + let val = p.value(); + for off in (0..p.len()).step_by(T::UNIT_SIZE) { + v.push(T::from_bytes(&val[off..off + T::UNIT_SIZE])?, GFP_KERNEL)?; + } + Ok(v) + } +} + +macro_rules! prop_int_type ( + ($type:ty) => { + impl<'a> TryFrom> for $type { + type Error = Error; + + fn try_from(p: Property<'_>) -> core::result::Result<$type, Self::Error> { + Ok(<$type>::from_be_bytes(p.value().try_into().or(Err(EINVAL))?)) + } + } + + impl PropertyUnit for $type { + const UNIT_SIZE: usize = <$type>::BITS as usize / 8; + + fn from_bytes(data: &[u8]) -> Result { + Ok(<$type>::from_be_bytes(data.try_into().or(Err(EINVAL))?)) + } + } + } +); + +prop_int_type!(u8); +prop_int_type!(u16); +prop_int_type!(u32); +prop_int_type!(u64); +prop_int_type!(i8); +prop_int_type!(i16); +prop_int_type!(i32); +prop_int_type!(i64); + +/// An iterator across a collection of Node objects. +/// +/// # Invariants +/// +/// `cur` must be NULL or a valid node owned reference. If NULL, it represents either the first +/// or last position of the iterator. +/// +/// If `done` is true, `cur` must be NULL. +/// +/// fn_next must be a callback that iterates from one node to the next, and it must not capture +/// values that exceed the lifetime of the iterator. It must return owned references and also +/// take owned references. +pub struct NodeIterator<'a, T> +where + T: Fn(*mut bindings::device_node) -> *mut bindings::device_node, +{ + cur: *mut bindings::device_node, + done: bool, + fn_next: T, + _p: PhantomData<&'a T>, +} + +impl<'a, T> NodeIterator<'a, T> +where + T: Fn(*mut bindings::device_node) -> *mut bindings::device_node, +{ + fn new(next: T) -> NodeIterator<'a, T> { + // INVARIANT: `cur` is initialized to NULL to represent the initial state. + NodeIterator { + cur: core::ptr::null_mut(), + done: false, + fn_next: next, + _p: PhantomData, + } + } +} + +impl<'a, T> Iterator for NodeIterator<'a, T> +where + T: Fn(*mut bindings::device_node) -> *mut bindings::device_node, +{ + type Item = Node; + + fn next(&mut self) -> Option { + if self.done { + None + } else { + // INVARIANT: if the new `cur` is NULL, then the iterator has reached its end and we + // set `done` to `true`. + self.cur = (self.fn_next)(self.cur); + self.done = self.cur.is_null(); + // SAFETY: `fn_next` must return an owned reference per the iterator contract. + // The iterator itself is considered to own this reference, so we take another one. + unsafe { Node::get_from_raw(self.cur) } + } + } +} + +// Drop impl to ensure we drop the current node being iterated on, if any. +impl<'a, T> Drop for NodeIterator<'a, T> +where + T: Fn(*mut bindings::device_node) -> *mut bindings::device_node, +{ + fn drop(&mut self) { + // SAFETY: `cur` is valid or NULL, and `of_node_put()` can handle NULL. + #[cfg(CONFIG_OF_DYNAMIC)] + unsafe { + bindings::of_node_put(self.cur) + }; + } +} + +/// Returns the root node of the OF device tree (if any). +pub fn root() -> Option { + #[cfg(not(CONFIG_OF))] + { + None + } + #[cfg(CONFIG_OF)] + // SAFETY: bindings::of_root is always valid or NULL + unsafe { + Node::get_from_raw(bindings::of_root) + } +} + +/// Returns the /chosen node of the OF device tree (if any). +pub fn chosen() -> Option { + #[cfg(not(CONFIG_OF))] + { + None + } + #[cfg(CONFIG_OF)] + // SAFETY: bindings::of_chosen is always valid or NULL + unsafe { + Node::get_from_raw(bindings::of_chosen) + } +} + +/// Returns the /aliases node of the OF device tree (if any). +pub fn aliases() -> Option { + #[cfg(not(CONFIG_OF))] + { + None + } + #[cfg(CONFIG_OF)] + // SAFETY: bindings::of_aliases is always valid or NULL + unsafe { + Node::get_from_raw(bindings::of_aliases) + } +} + +/// Returns the system stdout node of the OF device tree (if any). +pub fn stdout() -> Option { + #[cfg(not(CONFIG_OF))] + { + None + } + #[cfg(CONFIG_OF)] + // SAFETY: bindings::of_stdout is always valid or NULL + unsafe { + Node::get_from_raw(bindings::of_stdout) + } +} + +#[allow(unused_variables)] +/// Looks up a node in the device tree by phandle. +pub fn find_node_by_phandle(handle: PHandle) -> Option { + #[cfg(not(CONFIG_OF))] + { + None + } + #[cfg(CONFIG_OF)] + // SAFETY: bindings::of_find_node_by_phandle always returns a valid pointer or NULL + unsafe { + #[allow(dead_code)] + Node::from_raw(bindings::of_find_node_by_phandle(handle)) + } +} + +impl Clone for Node { + fn clone(&self) -> Node { + // SAFETY: `raw_node` is valid and non-NULL per the type invariant, + // so this can never return None. + unsafe { Node::get_from_raw(self.raw_node).unwrap() } + } +} + +impl Drop for Node { + fn drop(&mut self) { + #[cfg(CONFIG_OF_DYNAMIC)] + // SAFETY: `raw_node` is valid per the type invariant. + unsafe { + bindings::of_node_put(self.raw_node) + }; + } +} + /// Create an OF `IdTable` with an "alias" for modpost. #[macro_export] macro_rules! of_device_table { diff --git a/rust/kernel/page.rs b/rust/kernel/page.rs index 432fc0297d4a85..c57311c2a64fed 100644 --- a/rust/kernel/page.rs +++ b/rust/kernel/page.rs @@ -3,10 +3,12 @@ //! Kernel page allocation and management. use crate::{ + addr::*, alloc::{AllocError, Flags}, bindings, error::code::*, error::Result, + types::{Opaque, Ownable, Owned}, uaccess::UserSliceReader, }; use core::{ @@ -77,7 +79,7 @@ pub const fn page_align(addr: usize) -> usize { /// /// [`VBox`]: kernel::alloc::VBox /// [`Vmalloc`]: kernel::alloc::allocator::Vmalloc -pub struct BorrowedPage<'a>(ManuallyDrop, PhantomData<&'a Page>); +pub struct BorrowedPage<'a>(ManuallyDrop>, PhantomData<&'a Page>); impl<'a> BorrowedPage<'a> { /// Constructs a [`BorrowedPage`] from a raw pointer to a `struct page`. @@ -87,7 +89,7 @@ impl<'a> BorrowedPage<'a> { /// - `ptr` must point to a valid `bindings::page`. /// - `ptr` must remain valid for the entire lifetime `'a`. pub unsafe fn from_raw(ptr: NonNull) -> Self { - let page = Page { page: ptr }; + let page = unsafe { Page::from_phys(bindings::page_to_phys(ptr.as_ptr())) }; // INVARIANT: The safety requirements guarantee that `ptr` is valid for the entire lifetime // `'a`. @@ -120,8 +122,9 @@ pub trait AsPageIter { /// # Invariants /// /// The pointer is valid, and has ownership over the page. +#[repr(transparent)] pub struct Page { - page: NonNull, + page: Opaque, } // SAFETY: Pages have no logic that relies on them staying on a given thread, so moving them across @@ -155,19 +158,20 @@ impl Page { /// # Ok::<(), kernel::alloc::AllocError>(()) /// ``` #[inline] - pub fn alloc_page(flags: Flags) -> Result { + pub fn alloc_page(flags: Flags) -> Result, AllocError> { // SAFETY: Depending on the value of `gfp_flags`, this call may sleep. Other than that, it // is always safe to call this method. let page = unsafe { bindings::alloc_pages(flags.as_raw(), 0) }; let page = NonNull::new(page).ok_or(AllocError)?; - // INVARIANT: We just successfully allocated a page, so we now have ownership of the newly - // allocated page. We transfer that ownership to the new `Page` object. - Ok(Self { page }) + // SAFETY: We just successfully allocated a page, so we now have ownership of the newly + // allocated page. We transfer that ownership to the new `Owned` object. + // Since `Page` is transparent, we can cast the pointer directly. + Ok(unsafe { Owned::from_raw(page.cast()) }) } /// Returns a raw pointer to the page. pub fn as_ptr(&self) -> *mut bindings::page { - self.page.as_ptr() + Opaque::cast_into(&self.page) } /// Get the node id containing this page. @@ -192,7 +196,7 @@ impl Page { /// different addresses. However, even if the addresses are different, the underlying memory is /// still the same for these purposes (e.g., it's still a data race if they both write to the /// same underlying byte at the same time). - fn with_page_mapped(&self, f: impl FnOnce(*mut u8) -> T) -> T { + pub fn with_page_mapped(&self, f: impl FnOnce(*mut u8) -> T) -> T { // SAFETY: `page` is valid due to the type invariants on `Page`. let mapped_addr = unsafe { bindings::kmap_local_page(self.as_ptr()) }; @@ -233,7 +237,7 @@ impl Page { /// different addresses. However, even if the addresses are different, the underlying memory is /// still the same for these purposes (e.g., it's still a data race if they both write to the /// same underlying byte at the same time). - fn with_pointer_into_page( + pub fn with_pointer_into_page( &self, off: usize, len: usize, @@ -340,12 +344,77 @@ impl Page { reader.read_raw(unsafe { core::slice::from_raw_parts_mut(dst.cast(), len) }) }) } + + /// Returns the physical address of this page. + pub fn phys(&self) -> PhysicalAddr { + // SAFETY: `page` is valid due to the type invariants on `Page`. + unsafe { bindings::page_to_phys(self.as_ptr()) } + } + + /// Converts a Rust-owned Page into its physical address. + /// The caller is responsible for calling `from_phys()` to avoid + /// leaking memory. + pub fn into_phys(this: Owned) -> PhysicalAddr { + ManuallyDrop::new(this).phys() + } + + /// Converts a physical address to a Rust-owned Page. + /// + /// SAFETY: + /// The caller must ensure that the physical address was previously returned + /// by a call to `Page::into_phys()`, and that the physical address is no + /// longer used after this call, nor is `from_phys()` called again on it. + pub unsafe fn from_phys(phys: PhysicalAddr) -> Owned { + // SAFETY: By the safety requirements, the physical address must be valid and + // have come from `into_phys()`, so phys_to_page() cannot fail and + // must return the original struct page pointer. + unsafe { Owned::from_raw(NonNull::new_unchecked(bindings::phys_to_page(phys)).cast()) } + } + + /// Borrows a Page from a physical address, without taking over ownership. + /// + /// If the physical address does not have a `struct page` entry or is not + /// part of the System RAM region, returns None. + /// + /// SAFETY: + /// The caller must ensure that the physical address, if it is backed by a + /// `struct page`, remains available for the duration of the borrowed + /// lifetime. + pub unsafe fn borrow_phys(phys: &PhysicalAddr) -> Option<&Self> { + // SAFETY: This is always safe, as it is just arithmetic + let pfn = unsafe { bindings::phys_to_pfn(*phys) }; + // SAFETY: This function is safe to call with any pfn + if !unsafe { bindings::pfn_valid(pfn) && bindings::page_is_ram(pfn) != 0 } { + None + } else { + // SAFETY: We have just checked that the pfn is valid above, so it must + // have a corresponding struct page. By the safety requirements, we can + // return a borrowed reference to it. + Some(unsafe { &*(bindings::pfn_to_page(pfn) as *mut Self as *const Self) }) + } + } + + /// Borrows a Page from a physical address, without taking over ownership + /// nor checking for validity. + /// + /// SAFETY: + /// The caller must ensure that the physical address is backed by a + /// `struct page` and corresponds to System RAM. + pub unsafe fn borrow_phys_unchecked(phys: &PhysicalAddr) -> &Self { + // SAFETY: This is always safe, as it is just arithmetic + let pfn = unsafe { bindings::phys_to_pfn(*phys) }; + // SAFETY: The caller guarantees that the pfn is valid. By the safety + // requirements, we can return a borrowed reference to it. + unsafe { &*(bindings::pfn_to_page(pfn) as *mut Self as *const Self) } + } } -impl Drop for Page { +// SAFETY: See below. +unsafe impl Ownable for Page { #[inline] - fn drop(&mut self) { + unsafe fn release(this: NonNull) { // SAFETY: By the type invariants, we have ownership of the page and can free it. - unsafe { bindings::__free_pages(self.page.as_ptr(), 0) }; + // Since Page is transparent, we can cast the raw pointer directly. + unsafe { bindings::__free_pages(this.cast().as_ptr(), 0) }; } } diff --git a/rust/kernel/platform.rs b/rust/kernel/platform.rs index 7205fe3416d36c..b197884ed3df93 100644 --- a/rust/kernel/platform.rs +++ b/rust/kernel/platform.rs @@ -265,6 +265,20 @@ impl Device { // returned by `platform_get_resource`. Some(unsafe { Resource::from_raw(resource) }) } + + /// excute closure while the device is bound + pub fn while_bound_with(&self, f: F) -> Result + where + F: FnOnce(&Device) -> Result, + { + let _guard = self.as_ref().lock(); + if unsafe { !bindings::device_is_bound(self.as_ref().as_raw()) } { + return Err(ENODEV); + } + let ptr: *const Self = self; + let ptr = ptr.cast::>(); + f(unsafe { &*ptr }) + } } impl Device { diff --git a/rust/kernel/rbtree.rs b/rust/kernel/rbtree.rs index b8fe6be6fcc41a..9e178dacddf1d0 100644 --- a/rust/kernel/rbtree.rs +++ b/rust/kernel/rbtree.rs @@ -835,7 +835,7 @@ impl<'a, K, V> Cursor<'a, K, V> { self.peek(Direction::Prev) } - /// Access the previous node without moving the cursor. + /// Access the next node without moving the cursor. pub fn peek_next(&self) -> Option<(&K, &V)> { self.peek(Direction::Next) } diff --git a/rust/kernel/soc/apple/aop.rs b/rust/kernel/soc/apple/aop.rs new file mode 100644 index 00000000000000..da46ce0bcb027d --- /dev/null +++ b/rust/kernel/soc/apple/aop.rs @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Common code for AOP endpoint drivers + +use kernel::{prelude::*, sync::Arc}; + +/// Representation of an "EPIC" service. +#[derive(Clone, Copy, PartialEq, Eq)] +#[repr(C)] +pub struct EPICService { + /// Channel id + pub channel: u32, + /// RTKit endpoint + pub endpoint: u8, +} + +/// Listener for the "HID" events sent by aop +pub trait FakehidListener { + /// Process the event. + fn process_fakehid_report(&self, data: &[u8]) -> Result<()>; +} + +/// AOP communications manager. +pub trait AOP: Send + Sync { + /// Calls a method on a specified service + fn epic_call(&self, svc: &EPICService, subtype: u16, msg_bytes: &[u8]) -> Result; + /// Just like epic_call, but also returns a value + fn epic_call_ret( + &self, + svc: &EPICService, + subtype: u16, + msg_bytes: &[u8], + ret_len: usize, + ) -> Result<(u32, KVec)>; + + /// Adds the listener for the specified service + fn add_fakehid_listener( + &self, + svc: EPICService, + listener: Arc, + ) -> Result<()>; + /// Remove the listener for the specified service + fn remove_fakehid_listener(&self, svc: &EPICService) -> bool; + /// Internal method to detach the device. + fn remove(&self); +} + +/// Converts a text representation of a FourCC to u32 +pub const fn from_fourcc(b: &[u8]) -> u32 { + b[3] as u32 | (b[2] as u32) << 8 | (b[1] as u32) << 16 | (b[0] as u32) << 24 +} diff --git a/rust/kernel/soc/apple/mailbox.rs b/rust/kernel/soc/apple/mailbox.rs new file mode 100644 index 00000000000000..19cc924e9396f1 --- /dev/null +++ b/rust/kernel/soc/apple/mailbox.rs @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Support for Apple ASC Mailbox. +//! +//! C header: [`include/linux/soc/apple/mailbox.h`](../../../../include/linux/gpio/driver.h) + +use crate::{ + bindings, device, + error::{from_err_ptr, to_result, Result}, + str::CStr, + types::{ForeignOwnable, ScopeGuard}, +}; + +use core::marker::PhantomData; + +/// 96-bit message. What it means is up to the upper layer +pub type Message = bindings::apple_mbox_msg; + +/// Mailbox receive callback +pub trait MailCallback { + /// Callback context + type Data: ForeignOwnable + Send + Sync; + + /// The actual callback. Called in an interrupt context. + fn recv_message(data: ::Borrowed<'_>, msg: Message); +} + +/// Wrapper over `struct apple_mbox *` +#[repr(transparent)] +pub struct Mailbox { + mbox: *mut bindings::apple_mbox, + _p: PhantomData, +} + +extern "C" fn mailbox_rx_callback( + _mbox: *mut bindings::apple_mbox, + msg: Message, + cookie: *mut crate::ffi::c_void, +) { + // SAFETY: cookie came from a call to `into_foreign` + T::recv_message(unsafe { T::Data::borrow(cookie.cast()) }, msg); +} + +impl Mailbox { + /// Creates a mailbox for the specified name. + pub fn new_byname( + dev: &device::Device, + mbox_name: &'static CStr, + data: T::Data, + ) -> Result> { + let ptr: *mut crate::ffi::c_void = data.into_foreign().cast(); + let guard = ScopeGuard::new(|| { + // SAFETY: `ptr` came from a previous call to `into_foreign`. + unsafe { T::Data::from_foreign(ptr.cast()) }; + }); + // SAFETY: Just calling the c function, all values are valid. + let mbox = unsafe { + from_err_ptr(bindings::apple_mbox_get_byname( + dev.as_raw(), + mbox_name.as_char_ptr(), + ))? + }; + // SAFETY: mbox is a valid pointer + unsafe { + (*mbox).cookie = ptr; + (*mbox).rx = Some(mailbox_rx_callback::); + to_result(bindings::apple_mbox_start(mbox))?; + } + guard.dismiss(); + Ok(Mailbox { + mbox, + _p: PhantomData, + }) + } + /// Sends the specified message + pub fn send(&self, msg: Message, atomic: bool) -> Result<()> { + // SAFETY: Calling the c function, `mbox` is a valid pointer + to_result(unsafe { bindings::apple_mbox_send(self.mbox, msg, atomic) }) + } +} + +impl Drop for Mailbox { + fn drop(&mut self) { + // SAFETY: mbox is a valid pointer + unsafe { bindings::apple_mbox_stop(self.mbox) }; + // SAFETY: `cookie` came from `into_foreign` + unsafe { T::Data::from_foreign((*self.mbox).cookie.cast()) }; + } +} + +unsafe impl Sync for Mailbox +where + T: MailCallback, + T::Data: Sync, +{ +} + +unsafe impl Send for Mailbox +where + T: MailCallback, + T::Data: Send, +{ +} diff --git a/rust/kernel/soc/apple/mod.rs b/rust/kernel/soc/apple/mod.rs new file mode 100644 index 00000000000000..e77eba782a5867 --- /dev/null +++ b/rust/kernel/soc/apple/mod.rs @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Apple SoC drivers + +#[cfg(CONFIG_RUST_APPLE_RTKIT = "y")] +pub mod rtkit; + +#[cfg(any(CONFIG_APPLE_AOP = "y", CONFIG_APPLE_AOP = "m"))] +pub mod aop; + +#[cfg(CONFIG_RUST_APPLE_MAILBOX = "y")] +pub mod mailbox; diff --git a/rust/kernel/soc/apple/rtkit.rs b/rust/kernel/soc/apple/rtkit.rs new file mode 100644 index 00000000000000..c5d6e3d4b6c4d9 --- /dev/null +++ b/rust/kernel/soc/apple/rtkit.rs @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT + +//! Support for Apple RTKit coprocessors. +//! +//! C header: [`include/linux/soc/apple/rtkit.h`](../../../../include/linux/gpio/driver.h) + +use crate::{ + alloc::flags::*, + bindings, device, + error::{code::*, from_err_ptr, from_result, to_result, Result}, + iosys_map::IoSysMapRef, + prelude::KBox, + str::CStr, + types::{ForeignOwnable, ScopeGuard}, +}; + +use core::marker::PhantomData; +use core::ptr; +use macros::vtable; + +/// Trait to represent allocatable buffers for the RTKit core. +/// +/// Users must implement this trait for their own representation of those allocations. +pub trait Buffer { + /// Returns the IOVA (virtual address) of the buffer from RTKit's point of view, or an error if + /// unavailable. + fn iova(&self) -> Result; + + /// Returns a mutable byte slice of the buffer contents, or an + /// error if unavailable. + fn buf(&mut self) -> Result>; +} + +/// Callback operations for an RTKit client. +#[vtable] +pub trait Operations { + /// Arbitrary user context type. + type Data: ForeignOwnable + Send + Sync; + + /// Type representing an allocated buffer for RTKit. + type Buffer: Buffer; + + /// Called when RTKit crashes. + fn crashed(_data: ::Borrowed<'_>, _crashlog: Option<&[u8]>) {} + + /// Called when a message was received on a non-system endpoint. Called in non-IRQ context. + fn recv_message( + _data: ::Borrowed<'_>, + _endpoint: u8, + _message: u64, + ) { + } + + /// Called in IRQ context when a message was received on a non-system endpoint. + /// + /// Must return `true` if the message is handled, or `false` to process it in + /// the handling thread. + fn recv_message_early( + _data: ::Borrowed<'_>, + _endpoint: u8, + _message: u64, + ) -> bool { + false + } + + /// Allocate a buffer for use by RTKit. + fn shmem_alloc( + _data: ::Borrowed<'_>, + _size: usize, + ) -> Result { + Err(EINVAL) + } + + /// Map an existing buffer used by RTKit at a device-specified virtual address. + fn shmem_map( + _data: ::Borrowed<'_>, + _iova: usize, + _size: usize, + ) -> Result { + Err(EINVAL) + } +} + +/// Represents `struct apple_rtkit *`. +/// +/// # Invariants +/// +/// The rtk pointer is valid. +/// The data pointer is a valid pointer from T::Data::into_foreign(). +pub struct RtKit { + rtk: *mut bindings::apple_rtkit, + data: *mut core::ffi::c_void, + _p: PhantomData, +} + +unsafe extern "C" fn crashed_callback( + cookie: *mut core::ffi::c_void, + crashlog: *const core::ffi::c_void, + crashlog_size: usize, +) { + let crashlog = if !crashlog.is_null() && crashlog_size > 0 { + // SAFETY: The crashlog is either missing or a byte buffer of the specified size + Some(unsafe { core::slice::from_raw_parts(crashlog as *const u8, crashlog_size) }) + } else { + None + }; + // SAFETY: cookie is always a T::Data in this API + T::crashed(unsafe { T::Data::borrow(cookie.cast()) }, crashlog); +} + +unsafe extern "C" fn recv_message_callback( + cookie: *mut core::ffi::c_void, + endpoint: u8, + message: u64, +) { + // SAFETY: cookie is always a T::Data in this API + T::recv_message(unsafe { T::Data::borrow(cookie.cast()) }, endpoint, message); +} + +unsafe extern "C" fn recv_message_early_callback( + cookie: *mut core::ffi::c_void, + endpoint: u8, + message: u64, +) -> bool { + // SAFETY: cookie is always a T::Data in this API + T::recv_message_early(unsafe { T::Data::borrow(cookie.cast()) }, endpoint, message) +} + +unsafe extern "C" fn shmem_setup_callback( + cookie: *mut core::ffi::c_void, + bfr: *mut bindings::apple_rtkit_shmem, +) -> core::ffi::c_int { + // SAFETY: `bfr` is a valid buffer + let bfr_mut = unsafe { &mut *bfr }; + + from_result(|| { + let mut buf = if bfr_mut.iova != 0 { + bfr_mut.is_mapped = true; + T::shmem_map( + // SAFETY: `cookie` came from a previous call to `into_foreign`. + unsafe { T::Data::borrow(cookie.cast()) }, + bfr_mut.iova as usize, + bfr_mut.size, + )? + } else { + bfr_mut.is_mapped = false; + // SAFETY: `cookie` came from a previous call to `into_foreign`. + T::shmem_alloc(unsafe { T::Data::borrow(cookie.cast()) }, bfr_mut.size)? + }; + + let iova = buf.iova()?; + let iosys_map = buf.buf()?; + + if iosys_map.size() < bfr_mut.size { + return Err(ENOMEM); + } + + bfr_mut.iova = iova as u64; + bfr_mut.buffer = iosys_map.as_mut_ptr() as *mut _; + + // Now box the returned buffer type and stash it in the private pointer of the + // `apple_rtkit_shmem` struct for safekeeping. + let boxed = KBox::new(buf, GFP_KERNEL)?; + bfr_mut.private = KBox::into_raw(boxed) as *mut _; + Ok(0) + }) +} + +unsafe extern "C" fn shmem_destroy_callback( + _cookie: *mut core::ffi::c_void, + bfr: *mut bindings::apple_rtkit_shmem, +) { + // SAFETY: `bfr` is a valid buffer + let bfr_mut = unsafe { &mut *bfr }; + if !bfr_mut.private.is_null() { + // SAFETY: Per shmem_setup_callback, this has to be a pointer to a Buffer if it is set. + unsafe { + core::mem::drop(KBox::from_raw(bfr_mut.private as *mut T::Buffer)); + } + bfr_mut.private = core::ptr::null_mut(); + } +} + +impl RtKit { + const VTABLE: bindings::apple_rtkit_ops = bindings::apple_rtkit_ops { + crashed: Some(crashed_callback::), + recv_message: Some(recv_message_callback::), + recv_message_early: Some(recv_message_early_callback::), + shmem_setup: if T::HAS_SHMEM_ALLOC || T::HAS_SHMEM_MAP { + Some(shmem_setup_callback::) + } else { + None + }, + shmem_destroy: if T::HAS_SHMEM_ALLOC || T::HAS_SHMEM_MAP { + Some(shmem_destroy_callback::) + } else { + None + }, + }; + + /// Creates a new RTKit client for a given device and optional mailbox name or index. + pub fn new( + dev: &device::Device, + mbox_name: Option<&'static CStr>, + mbox_idx: usize, + data: T::Data, + ) -> Result { + let ptr: *mut crate::ffi::c_void = data.into_foreign().cast(); + let guard = ScopeGuard::new(|| { + // SAFETY: `ptr` came from a previous call to `into_foreign`. + unsafe { T::Data::from_foreign(ptr.cast()) }; + }); + // SAFETY: `dev` is valid by its type invarants and otherwise his just + // calls the C init function. + let rtk = unsafe { + from_err_ptr(bindings::apple_rtkit_init( + dev.as_raw(), + ptr, + match mbox_name { + Some(s) => s.as_char_ptr(), + None => ptr::null(), + }, + mbox_idx.try_into()?, + &Self::VTABLE, + )) + }?; + + guard.dismiss(); + // INVARIANT: `rtk` and `data` are valid here. + Ok(Self { + rtk, + data: ptr, + _p: PhantomData, + }) + } + + /// Boots (wakes up) the RTKit coprocessor. + pub fn wake(&mut self) -> Result { + // SAFETY: `rtk` is valid per the type invariant. + to_result(unsafe { bindings::apple_rtkit_wake(self.rtk) }) + } + + /// Waits for the RTKit coprocessor to finish booting. + pub fn boot(&mut self) -> Result { + // SAFETY: `rtk` is valid per the type invariant. + to_result(unsafe { bindings::apple_rtkit_boot(self.rtk) }) + } + + /// Starts a non-system endpoint. + pub fn start_endpoint(&mut self, endpoint: u8) -> Result { + // SAFETY: `rtk` is valid per the type invariant. + to_result(unsafe { bindings::apple_rtkit_start_ep(self.rtk, endpoint) }) + } + + /// Sends a message to a given endpoint. + pub fn send_message(&mut self, endpoint: u8, message: u64) -> Result { + // SAFETY: `rtk` is valid per the type invariant. + to_result(unsafe { + bindings::apple_rtkit_send_message(self.rtk, endpoint, message, ptr::null_mut(), false) + }) + } + + /// Checks if an endpoint is present + pub fn has_endpoint(&self, endpoint: u8) -> bool { + unsafe { bindings::apple_rtkit_has_endpoint(self.rtk, endpoint) } + } +} + +// SAFETY: `RtKit` operations require a mutable reference +unsafe impl Sync for RtKit {} + +// SAFETY: `RtKit` operations require a mutable reference +unsafe impl Send for RtKit {} + +impl Drop for RtKit { + fn drop(&mut self) { + // SAFETY: The pointer is valid by the type invariant. + unsafe { bindings::apple_rtkit_free(self.rtk) }; + + // Free context data. + // + // SAFETY: This matches the call to `into_foreign` from `new` in the success case. + unsafe { T::Data::from_foreign(self.data.cast()) }; + } +} diff --git a/rust/kernel/soc/mod.rs b/rust/kernel/soc/mod.rs new file mode 100644 index 00000000000000..e3024042e74f0d --- /dev/null +++ b/rust/kernel/soc/mod.rs @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! SoC drivers + +pub mod apple; diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs index 5c74e5f776014a..a1a3581eb54656 100644 --- a/rust/kernel/str.rs +++ b/rust/kernel/str.rs @@ -13,6 +13,8 @@ use core::{ ops::{self, Deref, DerefMut, Index}, }; +pub mod parse_int; + /// Byte string without UTF-8 validity guarantee. #[repr(transparent)] pub struct BStr([u8]); diff --git a/rust/kernel/str/parse_int.rs b/rust/kernel/str/parse_int.rs new file mode 100644 index 00000000000000..48eb4c202984c3 --- /dev/null +++ b/rust/kernel/str/parse_int.rs @@ -0,0 +1,148 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Integer parsing functions. +//! +//! Integer parsing functions for parsing signed and unsigned integers +//! potentially prefixed with `0x`, `0o`, or `0b`. + +use crate::prelude::*; +use crate::str::BStr; +use core::ops::Deref; + +// Make `FromStrRadix` a public type with a private name. This seals +// `ParseInt`, that is, prevents downstream users from implementing the +// trait. +mod private { + use crate::prelude::*; + use crate::str::BStr; + + /// Trait that allows parsing a [`&BStr`] to an integer with a radix. + pub trait FromStrRadix: Sized { + /// Parse `src` to [`Self`] using radix `radix`. + fn from_str_radix(src: &BStr, radix: u32) -> Result; + + /// Tries to convert `value` into [`Self`] and negates the resulting value. + fn from_u64_negated(value: u64) -> Result; + } +} + +/// Extract the radix from an integer literal optionally prefixed with +/// one of `0x`, `0X`, `0o`, `0O`, `0b`, `0B`, `0`. +fn strip_radix(src: &BStr) -> (u32, &BStr) { + match src.deref() { + [b'0', b'x' | b'X', rest @ ..] => (16, rest.as_ref()), + [b'0', b'o' | b'O', rest @ ..] => (8, rest.as_ref()), + [b'0', b'b' | b'B', rest @ ..] => (2, rest.as_ref()), + // NOTE: We are including the leading zero to be able to parse + // literal `0` here. If we removed it as a radix prefix, we would + // not be able to parse `0`. + [b'0', ..] => (8, src), + _ => (10, src), + } +} + +/// Trait for parsing string representations of integers. +/// +/// Strings beginning with `0x`, `0o`, or `0b` are parsed as hex, octal, or +/// binary respectively. Strings beginning with `0` otherwise are parsed as +/// octal. Anything else is parsed as decimal. A leading `+` or `-` is also +/// permitted. Any string parsed by [`kstrtol()`] or [`kstrtoul()`] will be +/// successfully parsed. +/// +/// [`kstrtol()`]: https://docs.kernel.org/core-api/kernel-api.html#c.kstrtol +/// [`kstrtoul()`]: https://docs.kernel.org/core-api/kernel-api.html#c.kstrtoul +/// +/// # Examples +/// +/// ``` +/// # use kernel::str::parse_int::ParseInt; +/// # use kernel::b_str; +/// +/// assert_eq!(Ok(0u8), u8::from_str(b_str!("0"))); +/// +/// assert_eq!(Ok(0xa2u8), u8::from_str(b_str!("0xa2"))); +/// assert_eq!(Ok(-0xa2i32), i32::from_str(b_str!("-0xa2"))); +/// +/// assert_eq!(Ok(-0o57i8), i8::from_str(b_str!("-0o57"))); +/// assert_eq!(Ok(0o57i8), i8::from_str(b_str!("057"))); +/// +/// assert_eq!(Ok(0b1001i16), i16::from_str(b_str!("0b1001"))); +/// assert_eq!(Ok(-0b1001i16), i16::from_str(b_str!("-0b1001"))); +/// +/// assert_eq!(Ok(127i8), i8::from_str(b_str!("127"))); +/// assert!(i8::from_str(b_str!("128")).is_err()); +/// assert_eq!(Ok(-128i8), i8::from_str(b_str!("-128"))); +/// assert!(i8::from_str(b_str!("-129")).is_err()); +/// assert_eq!(Ok(255u8), u8::from_str(b_str!("255"))); +/// assert!(u8::from_str(b_str!("256")).is_err()); +/// ``` +pub trait ParseInt: private::FromStrRadix + TryFrom { + /// Parse a string according to the description in [`Self`]. + fn from_str(src: &BStr) -> Result { + match src.deref() { + [b'-', rest @ ..] => { + let (radix, digits) = strip_radix(rest.as_ref()); + // 2's complement values range from -2^(b-1) to 2^(b-1)-1. + // So if we want to parse negative numbers as positive and + // later multiply by -1, we have to parse into a larger + // integer. We choose `u64` as sufficiently large. + // + // NOTE: 128 bit integers are not available on all + // platforms, hence the choice of 64 bits. + let val = + u64::from_str_radix(core::str::from_utf8(digits).map_err(|_| EINVAL)?, radix) + .map_err(|_| EINVAL)?; + Self::from_u64_negated(val) + } + _ => { + let (radix, digits) = strip_radix(src); + Self::from_str_radix(digits, radix).map_err(|_| EINVAL) + } + } + } +} + +macro_rules! impl_parse_int { + ($($ty:ty),*) => { + $( + impl private::FromStrRadix for $ty { + fn from_str_radix(src: &BStr, radix: u32) -> Result { + <$ty>::from_str_radix(core::str::from_utf8(src).map_err(|_| EINVAL)?, radix) + .map_err(|_| EINVAL) + } + + fn from_u64_negated(value: u64) -> Result { + const ABS_MIN: u64 = { + #[allow(unused_comparisons)] + if <$ty>::MIN < 0 { + 1u64 << (<$ty>::BITS - 1) + } else { + 0 + } + }; + + if value > ABS_MIN { + return Err(EINVAL); + } + + if value == ABS_MIN { + return Ok(<$ty>::MIN); + } + + // SAFETY: The above checks guarantee that `value` fits into `Self`: + // - if `Self` is unsigned, then `ABS_MIN == 0` and thus we have returned above + // (either `EINVAL` or `MIN`). + // - if `Self` is signed, then we have that `0 <= value < ABS_MIN`. And since + // `ABS_MIN - 1` fits into `Self` by construction, `value` also does. + let value: Self = unsafe { value.try_into().unwrap_unchecked() }; + + Ok((!value).wrapping_add(1)) + } + } + + impl ParseInt for $ty {} + )* + }; +} + +impl_parse_int![i8, u8, i16, u16, i32, u32, i64, u64, isize, usize]; diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs index cf5b638a097d99..3f957ad3a9f0af 100644 --- a/rust/kernel/sync.rs +++ b/rust/kernel/sync.rs @@ -20,6 +20,7 @@ mod locked_by; pub mod poll; pub mod rcu; mod refcount; +mod set_once; pub use arc::{Arc, ArcBorrow, UniqueArc}; pub use completion::Completion; @@ -29,6 +30,7 @@ pub use lock::mutex::{new_mutex, Mutex, MutexGuard}; pub use lock::spinlock::{new_spinlock, SpinLock, SpinLockGuard}; pub use locked_by::LockedBy; pub use refcount::Refcount; +pub use set_once::SetOnce; /// Represents a lockdep class. It's a wrapper around C's `lock_class_key`. #[repr(transparent)] diff --git a/rust/kernel/sync/atomic/predefine.rs b/rust/kernel/sync/atomic/predefine.rs index 45a17985cda45e..0fca1ba3c2dbd1 100644 --- a/rust/kernel/sync/atomic/predefine.rs +++ b/rust/kernel/sync/atomic/predefine.rs @@ -35,12 +35,23 @@ unsafe impl super::AtomicAdd for i64 { // as `isize` and `usize`, and `isize` and `usize` are always bi-directional transmutable to // `isize_atomic_repr`, which also always implements `AtomicImpl`. #[allow(non_camel_case_types)] +#[cfg(not(testlib))] #[cfg(not(CONFIG_64BIT))] type isize_atomic_repr = i32; #[allow(non_camel_case_types)] +#[cfg(not(testlib))] #[cfg(CONFIG_64BIT)] type isize_atomic_repr = i64; +#[allow(non_camel_case_types)] +#[cfg(testlib)] +#[cfg(target_pointer_width = "32")] +type isize_atomic_repr = i32; +#[allow(non_camel_case_types)] +#[cfg(testlib)] +#[cfg(target_pointer_width = "64")] +type isize_atomic_repr = i64; + // Ensure size and alignment requirements are checked. static_assert!(size_of::() == size_of::()); static_assert!(align_of::() == align_of::()); diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs index 27202beef90c88..7bedcd31a28a2b 100644 --- a/rust/kernel/sync/lock.rs +++ b/rust/kernel/sync/lock.rs @@ -8,6 +8,7 @@ use super::LockClassKey; use crate::{ str::CStr, + try_pin_init, types::{NotThreadSafe, Opaque, ScopeGuard}, }; use core::{cell::UnsafeCell, marker::PhantomPinned, pin::Pin}; @@ -115,6 +116,7 @@ pub struct Lock { _pin: PhantomPinned, /// The data protected by the lock. + #[pin] pub(crate) data: UnsafeCell, } @@ -138,6 +140,31 @@ impl Lock { }), }) } + + /// Constructs a new lock initialiser taking an initialiser. + pub fn pin_init( + t: impl PinInit, + name: &'static CStr, + key: &'static LockClassKey, + ) -> impl PinInit + where + E: core::convert::From, + { + try_pin_init!(Self { + // SAFETY: We are just forwarding the initialization across a + // cast away from UnsafeCell, so the pin_init_from_closure and + // __pinned_init() requirements are in sync. + data <- unsafe { pin_init::pin_init_from_closure(move |slot: *mut UnsafeCell| { + t.__pinned_init(slot as *mut T) + })}, + _pin: PhantomPinned, + // SAFETY: `slot` is valid while the closure is called and both `name` and `key` have + // static lifetimes so they live indefinitely. + state <- Opaque::ffi_init(|slot| unsafe { + B::init(slot, name.as_char_ptr(), key.as_ptr()) + }), + }? E) + } } impl Lock<(), B> { diff --git a/rust/kernel/sync/lock/mutex.rs b/rust/kernel/sync/lock/mutex.rs index 581cee7ab842ad..45a1c4c6483e90 100644 --- a/rust/kernel/sync/lock/mutex.rs +++ b/rust/kernel/sync/lock/mutex.rs @@ -17,6 +17,19 @@ macro_rules! new_mutex { } pub use new_mutex; +/// Creates a [`Mutex`] initialiser with the given name and a newly-created lock class, +/// given an initialiser for the inner type. +/// +/// It uses the name if one is given, otherwise it generates one based on the file name and line +/// number. +#[macro_export] +macro_rules! new_mutex_pinned { + ($inner:expr $(, $name:literal)? $(,)?) => { + $crate::sync::Mutex::pin_init( + $inner, $crate::optional_name!($($name)?), $crate::static_lock_class!()) + }; +} + /// A mutual exclusion primitive. /// /// Exposes the kernel's [`struct mutex`]. When multiple threads attempt to lock the same mutex, diff --git a/rust/kernel/sync/refcount.rs b/rust/kernel/sync/refcount.rs index 19236a5bccdeb0..6c7ae8b05a0b85 100644 --- a/rust/kernel/sync/refcount.rs +++ b/rust/kernel/sync/refcount.rs @@ -23,7 +23,8 @@ impl Refcount { /// Construct a new [`Refcount`] from an initial value. /// /// The initial value should be non-saturated. - #[inline] + // Always inline to optimize out error path of `build_assert`. + #[inline(always)] pub fn new(value: i32) -> Self { build_assert!(value >= 0, "initial value saturated"); // SAFETY: There are no safety requirements for this FFI call. diff --git a/rust/kernel/sync/set_once.rs b/rust/kernel/sync/set_once.rs new file mode 100644 index 00000000000000..bdba601807d8b3 --- /dev/null +++ b/rust/kernel/sync/set_once.rs @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! A container that can be initialized at most once. + +use super::atomic::{ + ordering::{Acquire, Relaxed, Release}, + Atomic, +}; +use core::{cell::UnsafeCell, mem::MaybeUninit}; + +/// A container that can be populated at most once. Thread safe. +/// +/// Once the a [`SetOnce`] is populated, it remains populated by the same object for the +/// lifetime `Self`. +/// +/// # Invariants +/// +/// - `init` may only increase in value. +/// - `init` may only assume values in the range `0..=2`. +/// - `init == 0` if and only if `value` is uninitialized. +/// - `init == 1` if and only if there is exactly one thread with exclusive +/// access to `self.value`. +/// - `init == 2` if and only if `value` is initialized and valid for shared +/// access. +/// +/// # Example +/// +/// ``` +/// # use kernel::sync::SetOnce; +/// let value = SetOnce::new(); +/// assert_eq!(None, value.as_ref()); +/// +/// let status = value.populate(42u8); +/// assert_eq!(true, status); +/// assert_eq!(Some(&42u8), value.as_ref()); +/// assert_eq!(Some(42u8), value.copy()); +/// +/// let status = value.populate(101u8); +/// assert_eq!(false, status); +/// assert_eq!(Some(&42u8), value.as_ref()); +/// assert_eq!(Some(42u8), value.copy()); +/// ``` +pub struct SetOnce { + init: Atomic, + value: UnsafeCell>, +} + +impl Default for SetOnce { + fn default() -> Self { + Self::new() + } +} + +impl SetOnce { + /// Create a new [`SetOnce`]. + /// + /// The returned instance will be empty. + pub const fn new() -> Self { + // INVARIANT: The container is empty and we initialize `init` to `0`. + Self { + value: UnsafeCell::new(MaybeUninit::uninit()), + init: Atomic::new(0), + } + } + + /// Get a reference to the contained object. + /// + /// Returns [`None`] if this [`SetOnce`] is empty. + pub fn as_ref(&self) -> Option<&T> { + if self.init.load(Acquire) == 2 { + // SAFETY: By the type invariants of `Self`, `self.init == 2` means that `self.value` + // is initialized and valid for shared access. + Some(unsafe { &*self.value.get().cast() }) + } else { + None + } + } + + /// Populate the [`SetOnce`]. + /// + /// Returns `true` if the [`SetOnce`] was successfully populated. + pub fn populate(&self, value: T) -> bool { + // INVARIANT: If the swap succeeds: + // - We increase `init`. + // - We write the valid value `1` to `init`. + // - Only one thread can succeed in this write, so we have exclusive access after the + // write. + if let Ok(0) = self.init.cmpxchg(0, 1, Relaxed) { + // SAFETY: By the type invariants of `Self`, the fact that we succeeded in writing `1` + // to `self.init` means we obtained exclusive access to `self.value`. + unsafe { core::ptr::write(self.value.get().cast(), value) }; + // INVARIANT: + // - We increase `init`. + // - We write the valid value `2` to `init`. + // - We release our exclusive access to `self.value` and it is now valid for shared + // access. + self.init.store(2, Release); + true + } else { + false + } + } + + /// Get a copy of the contained object. + /// + /// Returns [`None`] if the [`SetOnce`] is empty. + pub fn copy(&self) -> Option + where + T: Copy, + { + self.as_ref().copied() + } +} + +impl Drop for SetOnce { + fn drop(&mut self) { + if *self.init.get_mut() == 2 { + let value = self.value.get_mut(); + // SAFETY: By the type invariants of `Self`, `self.init == 2` means that `self.value` + // contains a valid value. We have exclusive access, as we hold a `mut` reference to + // `self`. + unsafe { value.assume_init_drop() }; + } + } +} diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs index 49fad6de06740a..cc907fb531bcee 100644 --- a/rust/kernel/task.rs +++ b/rust/kernel/task.rs @@ -204,18 +204,6 @@ impl Task { self.0.get() } - /// Returns the group leader of the given task. - pub fn group_leader(&self) -> &Task { - // SAFETY: The group leader of a task never changes after initialization, so reading this - // field is not a data race. - let ptr = unsafe { *ptr::addr_of!((*self.as_ptr()).group_leader) }; - - // SAFETY: The lifetime of the returned task reference is tied to the lifetime of `self`, - // and given that a task has a reference to its group leader, we know it must be valid for - // the lifetime of the returned task reference. - unsafe { &*ptr.cast() } - } - /// Returns the PID of the given task. pub fn pid(&self) -> Pid { // SAFETY: The pid of a task never changes after initialization, so reading this field is @@ -345,6 +333,18 @@ impl CurrentTask { // `release_task()` call. Some(unsafe { PidNamespace::from_ptr(active_ns) }) } + + /// Returns the group leader of the current task. + pub fn group_leader(&self) -> &Task { + // SAFETY: The group leader of a task never changes while the task is running, and `self` + // is the current task, which is guaranteed running. + let ptr = unsafe { (*self.as_ptr()).group_leader }; + + // SAFETY: `current->group_leader` stays valid for at least the duration in which `current` + // is running, and the signature of this function ensures that the returned `&Task` can + // only be used while `current` is still valid, thus still running. + unsafe { &*ptr.cast() } + } } // SAFETY: The type invariants guarantee that `Task` is always refcounted. diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs index dc0a02f5c3cfc5..05387d41727cc0 100644 --- a/rust/kernel/types.rs +++ b/rust/kernel/types.rs @@ -6,8 +6,9 @@ use crate::ffi::c_void; use core::{ cell::UnsafeCell, marker::{PhantomData, PhantomPinned}, - mem::MaybeUninit, + mem::{ManuallyDrop, MaybeUninit}, ops::{Deref, DerefMut}, + ptr::NonNull, }; use pin_init::{PinInit, Wrapper, Zeroable}; @@ -423,6 +424,114 @@ impl Wrapper for Opaque { } } +/// Types that may be owned by Rust code or borrowed, but have a lifetime managed by C code. +/// +/// It allows such types to define their own custom destructor function to be called when +/// a Rust-owned reference is dropped. +/// +/// This is usually implemented by wrappers to existing structures on the C side of the code. +/// +/// # Safety +/// +/// Implementers must ensure that any objects borrowed directly stay alive for the duration +/// of the borrow lifetime, and that any objects deemed owned by Rust stay alive while +/// that owned reference exists, until the [`Ownable::release()`] function is called. +pub unsafe trait Ownable { + /// Releases the object (frees it or returns it to foreign ownership). + /// + /// # Safety + /// + /// Callers must ensure that the object is no longer referenced after this call. + unsafe fn release(this: NonNull); +} + +/// A subtrait of Ownable that asserts that an Owned Rust reference is not only unique +/// within Rust, but also follows the same rules in kernel C code. That is, the kernel +/// will never mutate the contents of the object while Rust owns it. +/// +/// When this type is implemented for an Ownable type, it allows Owned to be dereferenced +/// into a &mut T. + +/// # Safety +/// +/// Implementers must ensure that the kernel never mutates the underlying type while +/// Rust owns it. +pub unsafe trait OwnableMut: Ownable {} + +/// An owned reference to an ownable kernel object. +/// +/// The object is automatically freed or released when an instance of [`Owned`] is +/// dropped. +/// +/// # Invariants +/// +/// The pointer stored in `ptr` is non-null and valid for the lifetime of the [`Owned`] instance. +pub struct Owned { + ptr: NonNull, + _p: PhantomData, +} + +// SAFETY: It is safe to send `Owned` to another thread when the underlying `T` is `Send` because +// it effectively means sharing `&mut T` (which is safe because `T` is `Send`). +unsafe impl Send for Owned {} + +// SAFETY: It is safe to send `&Owned` to another thread when the underlying `T` is `Sync` +// because it effectively means sharing `&T` (which is safe because `T` is `Sync`). +unsafe impl Sync for Owned {} + +impl Owned { + /// Creates a new instance of [`Owned`]. + /// + /// It takes over ownership of the underlying object. + /// + /// # Safety + /// + /// Callers must ensure that the underlying object is acquired and can be considered owned by + /// Rust. + pub unsafe fn from_raw(ptr: NonNull) -> Self { + // INVARIANT: The safety requirements guarantee that the new instance now owns the + // reference. + Self { + ptr, + _p: PhantomData, + } + } + + /// Consumes the `Owned`, returning a raw pointer. + /// + /// This function does not actually relinquish ownership of the object. + /// After calling this function, the caller is responsible for ownership previously managed + /// by the `Owned`. + pub fn into_raw(me: Self) -> NonNull { + ManuallyDrop::new(me).ptr + } +} + +impl Deref for Owned { + type Target = T; + + fn deref(&self) -> &Self::Target { + // SAFETY: The type invariants guarantee that the object is valid. + unsafe { self.ptr.as_ref() } + } +} + +impl DerefMut for Owned { + fn deref_mut(&mut self) -> &mut Self::Target { + // SAFETY: The type invariants guarantee that the object is valid, + // and that we can safely return a mutable reference to it. + unsafe { self.ptr.as_mut() } + } +} + +impl Drop for Owned { + fn drop(&mut self) { + // SAFETY: The type invariants guarantee that the `Owned` owns the object we're about to + // release. + unsafe { T::release(self.ptr) }; + } +} + /// Zero-sized type to mark types not [`Send`]. /// /// Add this type as a field to your struct if your type should not be sent to a different task. @@ -443,3 +552,86 @@ pub type NotThreadSafe = PhantomData<*mut ()>; /// [`NotThreadSafe`]: type@NotThreadSafe #[allow(non_upper_case_globals)] pub const NotThreadSafe: NotThreadSafe = PhantomData; + +/// Helper macro to declare a bitfield style type. The type will automatically +/// gain boolean operator implementations, as well as the `as_raw()` and `contains()` +/// methods, Debug, Copy, Clone, and PartialEq implementations. +/// +/// Optionally, a default value can be specified with `= value` syntax, which +/// will add a Default trait implementation. +/// +/// # Examples +/// +/// ``` +/// declare_flags_type! { +/// /// Flags to be used for foo. +/// pub struct FooFlags(u32); +/// } +/// +/// declare_flags_type! { +/// /// Flags to be used for bar. +/// pub struct BarFlags(u32) = 0; +/// } +/// ``` +macro_rules! declare_flags_type ( + ( + $(#[$outer:meta])* + $v:vis struct $t:ident ( $base:ty ); + $($rest:tt)* + ) => { + $(#[$outer])* + #[derive(Debug, Clone, Copy, PartialEq)] + $v struct $t($base); + + impl $t { + /// Get the raw representation of this flag. + pub(crate) fn as_raw(self) -> $base { + self.0 + } + + /// Check whether `flags` is contained in `self`. + pub fn contains(self, flags: Self) -> bool { + (self & flags) == flags + } + } + + impl core::ops::BitOr for $t { + type Output = Self; + fn bitor(self, rhs: Self) -> Self::Output { + Self(self.0 | rhs.0) + } + } + + impl core::ops::BitAnd for $t { + type Output = Self; + fn bitand(self, rhs: Self) -> Self::Output { + Self(self.0 & rhs.0) + } + } + + impl core::ops::Not for $t { + type Output = Self; + fn not(self) -> Self::Output { + Self(!self.0) + } + } + }; + ( + $(#[$outer:meta])* + $v:vis struct $t:ident ( $base:ty ) = $default:expr; + $($rest:tt)* + ) => { + declare_flags_type! { + $(#[$outer])* + $v struct $t ($base); + $($rest)* + } + impl Default for $t { + fn default() -> Self { + Self($default) + } + } + }; +); + +pub(crate) use declare_flags_type; diff --git a/rust/kernel/xarray.rs b/rust/kernel/xarray.rs index a49d6db2884588..e1f7e2d9b629f0 100644 --- a/rust/kernel/xarray.rs +++ b/rust/kernel/xarray.rs @@ -5,17 +5,20 @@ //! C header: [`include/linux/xarray.h`](srctree/include/linux/xarray.h) use crate::{ - alloc, bindings, build_assert, - error::{Error, Result}, - ffi::c_void, - types::{ForeignOwnable, NotThreadSafe, Opaque}, + alloc, + prelude::*, + types::{ForeignOwnable, NotThreadSafe, Opaque, ScopeGuard}, +}; +use core::{ + fmt, iter, + marker::PhantomData, + mem, ops, + ptr::{null_mut, NonNull}, }; -use core::{iter, marker::PhantomData, pin::Pin, ptr::NonNull}; -use pin_init::{pin_data, pin_init, pinned_drop, PinInit}; /// An array which efficiently maps sparse integer indices to owned objects. /// -/// This is similar to a [`crate::alloc::kvec::Vec>`], but more efficient when there are +/// This is similar to a [`Vec>`], but more efficient when there are /// holes in the index space, and can be efficiently grown. /// /// # Invariants @@ -26,10 +29,11 @@ use pin_init::{pin_data, pin_init, pinned_drop, PinInit}; /// # Examples /// /// ```rust -/// use kernel::alloc::KBox; -/// use kernel::xarray::{AllocKind, XArray}; +/// # use kernel::alloc::KBox; +/// # use kernel::xarray::XArray; +/// # use pin_init::stack_pin_init; /// -/// let xa = KBox::pin_init(XArray::new(AllocKind::Alloc1), GFP_KERNEL)?; +/// stack_pin_init!(let xa = XArray::new(Default::default())); /// /// let dead = KBox::new(0xdead, GFP_KERNEL)?; /// let beef = KBox::new(0xbeef, GFP_KERNEL)?; @@ -77,8 +81,10 @@ impl PinnedDrop for XArray { } /// Flags passed to [`XArray::new`] to configure the array's allocation tracking behavior. +#[derive(Default)] pub enum AllocKind { /// Consider the first element to be at index 0. + #[default] Alloc, /// Consider the first element to be at index 1. Alloc1, @@ -105,19 +111,69 @@ impl XArray { fn iter(&self) -> impl Iterator> + '_ { let mut index = 0; - // SAFETY: `self.xa` is always valid by the type invariant. - iter::once(unsafe { - bindings::xa_find(self.xa.get(), &mut index, usize::MAX, bindings::XA_PRESENT) - }) - .chain(iter::from_fn(move || { + core::iter::Iterator::chain( // SAFETY: `self.xa` is always valid by the type invariant. - Some(unsafe { - bindings::xa_find_after(self.xa.get(), &mut index, usize::MAX, bindings::XA_PRESENT) - }) - })) + iter::once(unsafe { + bindings::xa_find(self.xa.get(), &mut index, usize::MAX, bindings::XA_PRESENT) + }), + iter::from_fn(move || { + // SAFETY: `self.xa` is always valid by the type invariant. + Some(unsafe { + bindings::xa_find_after( + self.xa.get(), + &mut index, + usize::MAX, + bindings::XA_PRESENT, + ) + }) + }), + ) .map_while(|ptr| NonNull::new(ptr.cast())) } + /// Looks up and returns a reference to the lowest entry in the array between index and max, + /// returning a tuple of its index and a `Guard` if one exists. + /// + /// This guard blocks all other actions on the `XArray`. Callers are expected to drop the + /// `Guard` eagerly to avoid blocking other users, such as by taking a clone of the value. + pub fn find(&self, index: usize, max: usize) -> Option<(usize, ValueGuard<'_, T>)> { + let mut index: usize = index; + + // SAFETY: `self.xa` is always valid by the type invariant. + unsafe { bindings::xa_lock(self.xa.get()) }; + + // SAFETY: `self.xa` is always valid by the type invariant. + let guard = ScopeGuard::new(|| unsafe { bindings::xa_unlock(self.xa.get()) }); + + // SAFETY: `self.xa` is always valid by the type invariant. + let p = unsafe { bindings::xa_find(self.xa.get(), &mut index, max, bindings::XA_PRESENT) }; + + NonNull::new(p as *mut T).map(|ptr| { + guard.dismiss(); + ( + index, + ValueGuard { + xa: self, + ptr, + _not_send: NotThreadSafe, + }, + ) + }) + } + + fn with_guard(&self, guard: Option<&mut Guard<'_, T>>, f: F) -> U + where + F: FnOnce(&mut Guard<'_, T>) -> U, + { + match guard { + None => f(&mut self.lock()), + Some(guard) => { + assert_eq!(guard.xa.xa.get(), self.xa.get()); + f(guard) + } + } + } + /// Attempts to lock the [`XArray`] for exclusive access. pub fn try_lock(&self) -> Option> { // SAFETY: `self.xa` is always valid by the type invariant. @@ -141,6 +197,12 @@ impl XArray { _not_send: NotThreadSafe, } } + + /// Removes and returns the element at the given index. + pub fn remove(&self, index: usize) -> Option { + let mut guard = self.lock(); + guard.remove(index) + } } /// A lock guard. @@ -161,9 +223,41 @@ impl Drop for Guard<'_, T> { } } +/// A lock guard. +/// +/// The lock is unlocked when the guard goes out of scope. +#[must_use = "the lock unlocks immediately when the guard is unused"] +pub struct ValueGuard<'a, T: ForeignOwnable> { + xa: &'a XArray, + ptr: NonNull, + _not_send: NotThreadSafe, +} + +impl<'a, T: ForeignOwnable> ValueGuard<'a, T> { + /// Borrow the underlying value wrapped by the `Guard`. + /// + /// Returns a `T::Borrowed` type for the owned `ForeignOwnable` type. + pub fn borrow(&self) -> T::Borrowed<'_> { + // SAFETY: The value is owned by the `XArray`, the lifetime it is borrowed for must not + // outlive the `XArray` itself, nor the Guard that holds the lock ensuring the value + // remains in the `XArray`. + unsafe { T::borrow(self.ptr.as_ptr() as _) } + } +} + +impl Drop for ValueGuard<'_, T> { + fn drop(&mut self) { + // SAFETY: + // - `self.xa.xa` is always valid by the type invariant. + // - The caller holds the lock, so it is safe to unlock it. + unsafe { bindings::xa_unlock(self.xa.xa.get()) }; + } +} + /// The error returned by [`store`](Guard::store). /// /// Contains the underlying error and the value that was not stored. +#[derive(Debug)] pub struct StoreError { /// The error that occurred. pub error: Error, @@ -177,6 +271,11 @@ impl From> for Error { } } +fn to_usize(i: u32) -> usize { + i.try_into() + .unwrap_or_else(|_| build_error!("cannot convert u32 to usize")) +} + impl<'a, T: ForeignOwnable> Guard<'a, T> { fn load(&self, index: usize, f: F) -> Option where @@ -211,7 +310,7 @@ impl<'a, T: ForeignOwnable> Guard<'a, T> { // - The caller holds the lock. let ptr = unsafe { bindings::__xa_erase(self.xa.xa.get(), index) }.cast(); // SAFETY: - // - `ptr` is either NULL or came from `T::into_foreign`. + // - `ptr` is either `NULL` or came from `T::into_foreign`. // - `&mut self` guarantees that the lifetimes of [`T::Borrowed`] and [`T::BorrowedMut`] // borrowed from `self` have ended. unsafe { T::try_from_foreign(ptr) } @@ -259,13 +358,272 @@ impl<'a, T: ForeignOwnable> Guard<'a, T> { }) } else { let old = old.cast(); - // SAFETY: `ptr` is either NULL or came from `T::into_foreign`. + // SAFETY: `ptr` is either `NULL` or came from `T::into_foreign`. // // NB: `XA_ZERO_ENTRY` is never returned by functions belonging to the Normal XArray // API; such entries present as `NULL`. Ok(unsafe { T::try_from_foreign(old) }) } } + + /// Stores an element at the given index if no entry is present. + /// + /// May drop the lock if needed to allocate memory, and then reacquire it afterwards. + /// + /// On failure, returns the element which was attempted to be stored. + pub fn insert( + &mut self, + index: usize, + value: T, + gfp: alloc::Flags, + ) -> Result<(), StoreError> { + build_assert!( + T::FOREIGN_ALIGN >= 4, + "pointers stored in XArray must be 4-byte aligned" + ); + let ptr = value.into_foreign(); + // SAFETY: `self.xa` is always valid by the type invariant. + // + // INVARIANT: `ptr` came from `T::into_foreign`. + match unsafe { bindings::__xa_insert(self.xa.xa.get(), index, ptr.cast(), gfp.as_raw()) } { + 0 => Ok(()), + errno => { + // SAFETY: `ptr` came from `T::into_foreign` and `__xa_insert` does not take + // ownership of the value on error. + let value = unsafe { T::from_foreign(ptr) }; + Err(StoreError { + value, + error: Error::from_errno(errno), + }) + } + } + } + + /// Wrapper around `__xa_alloc`. + /// + /// On success, takes ownership of pointers passed in `op`. + /// + /// On failure, ownership returns to the caller. + /// + /// # Safety + /// + /// `ptr` must be `NULL` or have come from a previous call to `T::into_foreign`. + unsafe fn alloc( + &mut self, + limit: impl ops::RangeBounds, + ptr: *mut c_void, + gfp: alloc::Flags, + ) -> Result { + // NB: `xa_limit::{max,min}` are inclusive. + let limit = bindings::xa_limit { + max: match limit.end_bound() { + ops::Bound::Included(&end) => end, + ops::Bound::Excluded(&end) => end - 1, + ops::Bound::Unbounded => u32::MAX, + }, + min: match limit.start_bound() { + ops::Bound::Included(&start) => start, + ops::Bound::Excluded(&start) => start + 1, + ops::Bound::Unbounded => 0, + }, + }; + + let mut index = u32::MAX; + + // SAFETY: + // - `self.xa` is always valid by the type invariant. + // - `self.xa` was initialized with `XA_FLAGS_ALLOC` or `XA_FLAGS_ALLOC1`. + // + // INVARIANT: `ptr` is either `NULL` or came from `T::into_foreign`. + match unsafe { + bindings::__xa_alloc( + self.xa.xa.get(), + &mut index, + ptr.cast(), + limit, + gfp.as_raw(), + ) + } { + 0 => Ok(to_usize(index)), + errno => Err(Error::from_errno(errno)), + } + } + + /// Allocates an entry somewhere in the array. + /// + /// On success, returns the index at which the entry was stored. + /// + /// On failure, returns the entry which was attempted to be stored. + pub fn insert_limit( + &mut self, + limit: impl ops::RangeBounds, + value: T, + gfp: alloc::Flags, + ) -> Result> { + build_assert!( + T::FOREIGN_ALIGN >= 4, + "pointers stored in XArray must be 4-byte aligned" + ); + let ptr = value.into_foreign(); + // SAFETY: `ptr` came from `T::into_foreign`. + unsafe { self.alloc(limit, ptr, gfp) }.map_err(|error| { + // SAFETY: `ptr` came from `T::into_foreign` and `self.alloc` does not take ownership of + // the value on error. + let value = unsafe { T::from_foreign(ptr) }; + StoreError { value, error } + }) + } + + /// Reserves an entry in the array. + pub fn reserve(&mut self, index: usize, gfp: alloc::Flags) -> Result> { + // NB: `__xa_insert` internally coerces `NULL` to `XA_ZERO_ENTRY` on ingress. + let ptr = null_mut(); + // SAFETY: `self.xa` is always valid by the type invariant. + // + // INVARIANT: `ptr` is `NULL`. + match unsafe { bindings::__xa_insert(self.xa.xa.get(), index, ptr, gfp.as_raw()) } { + 0 => Ok(Reservation { xa: self.xa, index }), + errno => Err(Error::from_errno(errno)), + } + } + + /// Reserves an entry somewhere in the array. + pub fn reserve_limit( + &mut self, + limit: impl ops::RangeBounds, + gfp: alloc::Flags, + ) -> Result> { + // NB: `__xa_alloc` internally coerces `NULL` to `XA_ZERO_ENTRY` on ingress. + let ptr = null_mut(); + // SAFETY: `ptr` is `NULL`. + unsafe { self.alloc(limit, ptr, gfp) }.map(|index| Reservation { xa: self.xa, index }) + } +} + +/// A reserved slot in an array. +/// +/// The slot is released when the reservation goes out of scope. +/// +/// Note that the array lock *must not* be held when the reservation is filled or dropped as this +/// will lead to deadlock. [`Reservation::fill_locked`] and [`Reservation::release_locked`] can be +/// used in context where the array lock is held. +#[must_use = "the reservation is released immediately when the reservation is unused"] +pub struct Reservation<'a, T: ForeignOwnable> { + xa: &'a XArray, + index: usize, +} + +impl fmt::Debug for Reservation<'_, T> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + f.debug_struct("Reservation") + .field("index", &self.index()) + .finish() + } +} + +impl Reservation<'_, T> { + /// Returns the index of the reservation. + pub fn index(&self) -> usize { + self.index + } + + /// Replaces the reserved entry with the given entry. + /// + /// # Safety + /// + /// `ptr` must be `NULL` or have come from a previous call to `T::into_foreign`. + unsafe fn replace(guard: &mut Guard<'_, T>, index: usize, ptr: *mut c_void) -> Result { + // SAFETY: `xa_zero_entry` wraps `XA_ZERO_ENTRY` which is always safe to use. + let old = unsafe { bindings::xa_zero_entry() }; + + // NB: `__xa_cmpxchg_raw` is used over `__xa_cmpxchg` because the latter coerces + // `XA_ZERO_ENTRY` to `NULL` on egress, which would prevent us from determining whether a + // replacement was made. + // + // SAFETY: `self.xa` is always valid by the type invariant. + // + // INVARIANT: `ptr` is either `NULL` or came from `T::into_foreign` and `old` is + // `XA_ZERO_ENTRY`. + let ret = + unsafe { bindings::__xa_cmpxchg_raw(guard.xa.xa.get(), index, old, ptr.cast(), 0) }; + + // SAFETY: `__xa_cmpxchg_raw` returns the old entry at this index on success or `xa_err` if + // an error happened. + match unsafe { bindings::xa_err(ret) } { + 0 => { + if ret == old { + Ok(()) + } else { + Err(EBUSY) + } + } + errno => Err(Error::from_errno(errno)), + } + } + + fn fill_inner(&self, guard: Option<&mut Guard<'_, T>>, value: T) -> Result<(), StoreError> { + let Self { xa, index } = self; + let index = *index; + + let ptr = value.into_foreign(); + xa.with_guard(guard, |guard| { + // SAFETY: `ptr` came from `T::into_foreign`. + unsafe { Self::replace(guard, index, ptr) } + }) + .map_err(|error| { + // SAFETY: `ptr` came from `T::into_foreign` and `Self::replace` does not take ownership + // of the value on error. + let value = unsafe { T::from_foreign(ptr) }; + StoreError { value, error } + }) + } + + /// Fills the reservation. + pub fn fill(self, value: T) -> Result<(), StoreError> { + let result = self.fill_inner(None, value); + mem::forget(self); + result + } + + /// Fills the reservation without acquiring the array lock. + /// + /// # Panics + /// + /// Panics if the passed guard locks a different array. + pub fn fill_locked(self, guard: &mut Guard<'_, T>, value: T) -> Result<(), StoreError> { + let result = self.fill_inner(Some(guard), value); + mem::forget(self); + result + } + + fn release_inner(&self, guard: Option<&mut Guard<'_, T>>) -> Result { + let Self { xa, index } = self; + let index = *index; + + xa.with_guard(guard, |guard| { + let ptr = null_mut(); + // SAFETY: `ptr` is `NULL`. + unsafe { Self::replace(guard, index, ptr) } + }) + } + + /// Releases the reservation without acquiring the array lock. + /// + /// # Panics + /// + /// Panics if the passed guard locks a different array. + pub fn release_locked(self, guard: &mut Guard<'_, T>) -> Result { + let result = self.release_inner(Some(guard)); + mem::forget(self); + result + } +} + +impl Drop for Reservation<'_, T> { + fn drop(&mut self) { + // NB: Errors here are possible since `Guard::store` does not honor reservations. + let _: Result = self.release_inner(None); + } } // SAFETY: `XArray` has no shared mutable state so it is `Send` iff `T` is `Send`. @@ -274,3 +632,133 @@ unsafe impl Send for XArray {} // SAFETY: `XArray` serialises the interior mutability it provides so it is `Sync` iff `T` is // `Send`. unsafe impl Sync for XArray {} + +#[macros::kunit_tests(rust_xarray_kunit)] +mod tests { + use super::*; + use pin_init::stack_pin_init; + + fn new_kbox(value: T) -> Result> { + KBox::new(value, GFP_KERNEL).map_err(Into::into) + } + + #[test] + fn test_alloc_kind_alloc() -> Result { + test_alloc_kind(AllocKind::Alloc, 0) + } + + #[test] + fn test_alloc_kind_alloc1() -> Result { + test_alloc_kind(AllocKind::Alloc1, 1) + } + + fn test_alloc_kind(kind: AllocKind, expected_index: usize) -> Result { + stack_pin_init!(let xa = XArray::new(kind)); + let mut guard = xa.lock(); + + let reservation = guard.reserve_limit(.., GFP_KERNEL)?; + assert_eq!(reservation.index(), expected_index); + reservation.release_locked(&mut guard)?; + + let insertion = guard.insert_limit(.., new_kbox(0x1337)?, GFP_KERNEL); + assert!(insertion.is_ok()); + let insertion_index = insertion.unwrap(); + assert_eq!(insertion_index, expected_index); + + Ok(()) + } + + const IDX: usize = 0x1337; + + fn insert(guard: &mut Guard<'_, T>, value: T) -> Result<(), StoreError> { + guard.insert(IDX, value, GFP_KERNEL) + } + + fn reserve<'a, T: ForeignOwnable>(guard: &mut Guard<'a, T>) -> Result> { + guard.reserve(IDX, GFP_KERNEL) + } + + #[track_caller] + fn check_not_vacant<'a>(guard: &mut Guard<'a, KBox>) -> Result { + // Insertion fails. + { + let beef = new_kbox(0xbeef)?; + let ret = insert(guard, beef); + assert!(ret.is_err()); + let StoreError { error, value } = ret.unwrap_err(); + assert_eq!(error, EBUSY); + assert_eq!(*value, 0xbeef); + } + + // Reservation fails. + { + let ret = reserve(guard); + assert!(ret.is_err()); + assert_eq!(ret.unwrap_err(), EBUSY); + } + + Ok(()) + } + + #[test] + fn test_insert_and_reserve_interaction() -> Result { + stack_pin_init!(let xa = XArray::new(Default::default())); + let mut guard = xa.lock(); + + // Vacant. + assert_eq!(guard.get(IDX), None); + + // Reservation succeeds. + let reservation = { + let ret = reserve(&mut guard); + assert!(ret.is_ok()); + ret.unwrap() + }; + + // Reserved presents as vacant. + assert_eq!(guard.get(IDX), None); + + check_not_vacant(&mut guard)?; + + // Release reservation. + { + let ret = reservation.release_locked(&mut guard); + assert!(ret.is_ok()); + let () = ret.unwrap(); + } + + // Vacant again. + assert_eq!(guard.get(IDX), None); + + // Insert succeeds. + { + let dead = new_kbox(0xdead)?; + let ret = insert(&mut guard, dead); + assert!(ret.is_ok()); + let () = ret.unwrap(); + } + + check_not_vacant(&mut guard)?; + + // Remove. + assert_eq!(guard.remove(IDX).as_deref(), Some(&0xdead)); + + // Reserve and fill. + { + let beef = new_kbox(0xbeef)?; + let ret = reserve(&mut guard); + assert!(ret.is_ok()); + let reservation = ret.unwrap(); + let ret = reservation.fill_locked(&mut guard, beef); + assert!(ret.is_ok()); + let () = ret.unwrap(); + }; + + check_not_vacant(&mut guard)?; + + // Remove. + assert_eq!(guard.remove(IDX).as_deref(), Some(&0xbeef)); + + Ok(()) + } +} diff --git a/rust/macros/helpers.rs b/rust/macros/helpers.rs index e2602be402c105..365d7eb499c085 100644 --- a/rust/macros/helpers.rs +++ b/rust/macros/helpers.rs @@ -10,6 +10,17 @@ pub(crate) fn try_ident(it: &mut token_stream::IntoIter) -> Option { } } +pub(crate) fn try_sign(it: &mut token_stream::IntoIter) -> Option { + let peek = it.clone().next(); + match peek { + Some(TokenTree::Punct(punct)) if punct.as_char() == '-' => { + let _ = it.next(); + Some(punct.as_char()) + } + _ => None, + } +} + pub(crate) fn try_literal(it: &mut token_stream::IntoIter) -> Option { if let Some(TokenTree::Literal(literal)) = it.next() { Some(literal.to_string()) @@ -103,3 +114,17 @@ pub(crate) fn file() -> String { proc_macro::Span::call_site().file() } } + +/// Parse a token stream of the form `expected_name: "value",` and return the +/// string in the position of "value". +/// +/// # Panics +/// +/// - On parse error. +pub(crate) fn expect_string_field(it: &mut token_stream::IntoIter, expected_name: &str) -> String { + assert_eq!(expect_ident(it), expected_name); + assert_eq!(expect_punct(it), ':'); + let string = expect_string(it); + assert_eq!(expect_punct(it), ','); + string +} diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs index fa847cf3a9b5f4..65fc6691a0c94a 100644 --- a/rust/macros/lib.rs +++ b/rust/macros/lib.rs @@ -19,6 +19,7 @@ mod helpers; mod kunit; mod module; mod paste; +mod versions; mod vtable; use proc_macro::TokenStream; @@ -28,6 +29,30 @@ use proc_macro::TokenStream; /// The `type` argument should be a type which implements the [`Module`] /// trait. Also accepts various forms of kernel metadata. /// +/// The `params` field describe module parameters. Each entry has the form +/// +/// ```ignore +/// parameter_name: type { +/// default: default_value, +/// description: "Description", +/// } +/// ``` +/// +/// `type` may be one of +/// +/// - [`i8`] +/// - [`u8`] +/// - [`i8`] +/// - [`u8`] +/// - [`i16`] +/// - [`u16`] +/// - [`i32`] +/// - [`u32`] +/// - [`i64`] +/// - [`u64`] +/// - [`isize`] +/// - [`usize`] +/// /// C header: [`include/linux/moduleparam.h`](srctree/include/linux/moduleparam.h) /// /// [`Module`]: ../kernel/trait.Module.html @@ -44,6 +69,12 @@ use proc_macro::TokenStream; /// description: "My very own kernel module!", /// license: "GPL", /// alias: ["alternate_module_name"], +/// params: { +/// my_parameter: i64 { +/// default: 1, +/// description: "This parameter has a default of 1", +/// }, +/// }, /// } /// /// struct MyModule(i32); @@ -52,6 +83,7 @@ use proc_macro::TokenStream; /// fn init(_module: &'static ThisModule) -> Result { /// let foo: i32 = 42; /// pr_info!("I contain: {}\n", foo); +/// pr_info!("i32 param is: {}\n", module_parameters::my_parameter.read()); /// Ok(Self(foo)) /// } /// } @@ -103,6 +135,12 @@ pub fn module(ts: TokenStream) -> TokenStream { module::module(ts) } +/// Declares multiple variants of a structure or impl code +#[proc_macro_attribute] +pub fn versions(attr: TokenStream, item: TokenStream) -> TokenStream { + versions::versions(attr, item) +} + /// Declares or implements a vtable trait. /// /// Linux's use of pure vtables is very close to Rust traits, but they differ diff --git a/rust/macros/module.rs b/rust/macros/module.rs index 5ee54a00c0b656..d62e9c1e2a8982 100644 --- a/rust/macros/module.rs +++ b/rust/macros/module.rs @@ -26,6 +26,7 @@ struct ModInfoBuilder<'a> { module: &'a str, counter: usize, buffer: String, + param_buffer: String, } impl<'a> ModInfoBuilder<'a> { @@ -34,10 +35,11 @@ impl<'a> ModInfoBuilder<'a> { module, counter: 0, buffer: String::new(), + param_buffer: String::new(), } } - fn emit_base(&mut self, field: &str, content: &str, builtin: bool) { + fn emit_base(&mut self, field: &str, content: &str, builtin: bool, param: bool) { let string = if builtin { // Built-in modules prefix their modinfo strings by `module.`. format!( @@ -51,8 +53,14 @@ impl<'a> ModInfoBuilder<'a> { format!("{field}={content}\0") }; + let buffer = if param { + &mut self.param_buffer + } else { + &mut self.buffer + }; + write!( - &mut self.buffer, + buffer, " {cfg} #[doc(hidden)] @@ -75,20 +83,119 @@ impl<'a> ModInfoBuilder<'a> { self.counter += 1; } - fn emit_only_builtin(&mut self, field: &str, content: &str) { - self.emit_base(field, content, true) + fn emit_only_builtin(&mut self, field: &str, content: &str, param: bool) { + self.emit_base(field, content, true, param) } - fn emit_only_loadable(&mut self, field: &str, content: &str) { - self.emit_base(field, content, false) + fn emit_only_loadable(&mut self, field: &str, content: &str, param: bool) { + self.emit_base(field, content, false, param) } fn emit(&mut self, field: &str, content: &str) { - self.emit_only_builtin(field, content); - self.emit_only_loadable(field, content); + self.emit_internal(field, content, false); + } + + fn emit_internal(&mut self, field: &str, content: &str, param: bool) { + self.emit_only_builtin(field, content, param); + self.emit_only_loadable(field, content, param); + } + + fn emit_param(&mut self, field: &str, param: &str, content: &str) { + let content = format!("{param}:{content}", param = param, content = content); + self.emit_internal(field, &content, true); + } + + fn emit_params(&mut self, info: &ModuleInfo) { + let Some(params) = &info.params else { + return; + }; + + for param in params { + let ops = param_ops_path(¶m.ptype); + + // Note: The spelling of these fields is dictated by the user space + // tool `modinfo`. + self.emit_param("parmtype", ¶m.name, ¶m.ptype); + self.emit_param("parm", ¶m.name, ¶m.description); + + write!( + self.param_buffer, + " + pub(crate) static {param_name}: + ::kernel::module_param::ModuleParamAccess<{param_type}> = + ::kernel::module_param::ModuleParamAccess::new({param_default}); + + const _: () = {{ + #[link_section = \"__param\"] + #[used] + static __{module_name}_{param_name}_struct: + ::kernel::module_param::KernelParam = + ::kernel::module_param::KernelParam::new( + ::kernel::bindings::kernel_param {{ + name: if ::core::cfg!(MODULE) {{ + ::kernel::c_str!(\"{param_name}\").as_bytes_with_nul() + }} else {{ + ::kernel::c_str!(\"{module_name}.{param_name}\") + .as_bytes_with_nul() + }}.as_ptr(), + // SAFETY: `__this_module` is constructed by the kernel at load + // time and will not be freed until the module is unloaded. + #[cfg(MODULE)] + mod_: unsafe {{ + core::ptr::from_ref(&::kernel::bindings::__this_module) + .cast_mut() + }}, + #[cfg(not(MODULE))] + mod_: ::core::ptr::null_mut(), + ops: core::ptr::from_ref(&{ops}), + perm: 0, // Will not appear in sysfs + level: -1, + flags: 0, + __bindgen_anon_1: ::kernel::bindings::kernel_param__bindgen_ty_1 {{ + arg: {param_name}.as_void_ptr() + }}, + }} + ); + }}; + ", + module_name = info.name, + param_type = param.ptype, + param_default = param.default, + param_name = param.name, + ops = ops, + ) + .unwrap(); + } + } +} + +fn param_ops_path(param_type: &str) -> &'static str { + match param_type { + "i8" => "::kernel::module_param::PARAM_OPS_I8", + "u8" => "::kernel::module_param::PARAM_OPS_U8", + "i16" => "::kernel::module_param::PARAM_OPS_I16", + "u16" => "::kernel::module_param::PARAM_OPS_U16", + "i32" => "::kernel::module_param::PARAM_OPS_I32", + "u32" => "::kernel::module_param::PARAM_OPS_U32", + "i64" => "::kernel::module_param::PARAM_OPS_I64", + "u64" => "::kernel::module_param::PARAM_OPS_U64", + "isize" => "::kernel::module_param::PARAM_OPS_ISIZE", + "usize" => "::kernel::module_param::PARAM_OPS_USIZE", + t => panic!("Unsupported parameter type {}", t), } } +fn expect_param_default(param_it: &mut token_stream::IntoIter) -> String { + assert_eq!(expect_ident(param_it), "default"); + assert_eq!(expect_punct(param_it), ':'); + let sign = try_sign(param_it); + let default = try_literal(param_it).expect("Expected default param value"); + assert_eq!(expect_punct(param_it), ','); + let mut value = sign.map(String::from).unwrap_or_default(); + value.push_str(&default); + value +} + #[derive(Debug, Default)] struct ModuleInfo { type_: String, @@ -98,6 +205,50 @@ struct ModuleInfo { description: Option, alias: Option>, firmware: Option>, + params: Option>, +} + +#[derive(Debug)] +struct Parameter { + name: String, + ptype: String, + default: String, + description: String, +} + +fn expect_params(it: &mut token_stream::IntoIter) -> Vec { + let params = expect_group(it); + assert_eq!(params.delimiter(), Delimiter::Brace); + let mut it = params.stream().into_iter(); + let mut parsed = Vec::new(); + + loop { + let param_name = match it.next() { + Some(TokenTree::Ident(ident)) => ident.to_string(), + Some(_) => panic!("Expected Ident or end"), + None => break, + }; + + assert_eq!(expect_punct(&mut it), ':'); + let param_type = expect_ident(&mut it); + let group = expect_group(&mut it); + assert_eq!(group.delimiter(), Delimiter::Brace); + assert_eq!(expect_punct(&mut it), ','); + + let mut param_it = group.stream().into_iter(); + let param_default = expect_param_default(&mut param_it); + let param_description = expect_string_field(&mut param_it, "description"); + expect_end(&mut param_it); + + parsed.push(Parameter { + name: param_name, + ptype: param_type, + default: param_default, + description: param_description, + }) + } + + parsed } impl ModuleInfo { @@ -112,6 +263,7 @@ impl ModuleInfo { "license", "alias", "firmware", + "params", ]; const REQUIRED_KEYS: &[&str] = &["type", "name", "license"]; let mut seen_keys = Vec::new(); @@ -137,6 +289,7 @@ impl ModuleInfo { "license" => info.license = expect_string_ascii(it), "alias" => info.alias = Some(expect_string_array(it)), "firmware" => info.firmware = Some(expect_string_array(it)), + "params" => info.params = Some(expect_params(it)), _ => panic!("Unknown key \"{key}\". Valid keys are: {EXPECTED_KEYS:?}."), } @@ -176,30 +329,32 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { // Rust does not allow hyphens in identifiers, use underscore instead. let ident = info.name.replace('-', "_"); let mut modinfo = ModInfoBuilder::new(ident.as_ref()); - if let Some(authors) = info.authors { + if let Some(authors) = &info.authors { for author in authors { - modinfo.emit("author", &author); + modinfo.emit("author", author); } } - if let Some(description) = info.description { - modinfo.emit("description", &description); + if let Some(description) = &info.description { + modinfo.emit("description", description); } modinfo.emit("license", &info.license); - if let Some(aliases) = info.alias { + if let Some(aliases) = &info.alias { for alias in aliases { - modinfo.emit("alias", &alias); + modinfo.emit("alias", alias); } } - if let Some(firmware) = info.firmware { + if let Some(firmware) = &info.firmware { for fw in firmware { - modinfo.emit("firmware", &fw); + modinfo.emit("firmware", fw); } } // Built-in modules also export the `file` modinfo string. let file = std::env::var("RUST_MODFILE").expect("Unable to fetch RUST_MODFILE environmental variable"); - modinfo.emit_only_builtin("file", &file); + modinfo.emit_only_builtin("file", &file, false); + + modinfo.emit_params(&info); format!( " @@ -363,15 +518,18 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { __MOD.assume_init_drop(); }} }} - {modinfo} }} }} + mod module_parameters {{ + {params} + }} ", type_ = info.type_, name = info.name, ident = ident, modinfo = modinfo.buffer, + params = modinfo.param_buffer, initcall_section = ".initcall6.init" ) .parse() diff --git a/rust/macros/versions.rs b/rust/macros/versions.rs new file mode 100644 index 00000000000000..b13a5d55c0e17b --- /dev/null +++ b/rust/macros/versions.rs @@ -0,0 +1,341 @@ +use proc_macro::{Delimiter, Group, Ident, Punct, Spacing, Span, TokenStream, TokenTree}; + +//use crate::helpers::expect_punct; + +fn expect_group(it: &mut impl Iterator) -> Group { + if let Some(TokenTree::Group(group)) = it.next() { + group + } else { + panic!("Expected Group") + } +} + +fn expect_punct(it: &mut impl Iterator) -> String { + if let Some(TokenTree::Punct(punct)) = it.next() { + punct.to_string() + } else { + panic!("Expected Group") + } +} + +fn drop_until_punct(it: &mut impl Iterator, delimiter: &str, is_struct: bool) { + let mut depth: isize = 0; + let mut colons: isize = 0; + for token in it.by_ref() { + if let TokenTree::Punct(punct) = token { + match punct.as_char() { + ':' => { + colons += 1; + } + '<' => { + if depth > 0 || colons == 2 || is_struct { + depth += 1; + } + colons = 0; + } + '>' => { + if depth > 0 { + depth -= 1; + } + colons = 0; + } + _ => { + colons = 0; + if depth == 0 && delimiter.contains(&punct.to_string()) { + break; + } + } + } + } + } +} + +fn drop_until_braces(it: &mut impl Iterator) { + let mut depth: isize = 0; + let mut colons: isize = 0; + for token in it.by_ref() { + match token { + TokenTree::Punct(punct) => match punct.as_char() { + ':' => { + colons += 1; + } + '<' => { + if depth > 0 || colons == 2 { + depth += 1; + } + colons = 0; + } + '>' => { + if depth > 0 { + depth -= 1; + } + colons = 0; + } + _ => colons = 0, + }, + TokenTree::Group(group) if group.delimiter() == Delimiter::Brace => { + if depth == 0 { + break; + } + } + _ => (), + } + } +} + +struct VersionConfig { + fields: &'static [&'static str], + enums: &'static [&'static [&'static str]], + versions: &'static [&'static [&'static str]], +} + +static AGX_VERSIONS: VersionConfig = VersionConfig { + fields: &["G", "V"], + enums: &[ + &["G13", "G14", "G14X"], + &["V12_3", "V12_4", "V13_0B4", "V13_2", "V13_3", "V13_5"], + ], + versions: &[ + &["G13", "V12_3"], + &["G14", "V12_4"], + &["G13", "V13_5"], + &["G14", "V13_5"], + &["G14X", "V13_5"], + ], +}; + +fn check_version( + config: &VersionConfig, + ver: &[usize], + it: &mut impl Iterator, +) -> bool { + let first = it.next().unwrap(); + let val: bool = match &first { + TokenTree::Group(group) => check_version(config, ver, &mut group.stream().into_iter()), + TokenTree::Ident(ident) => { + let key = config + .fields + .iter() + .position(|&r| r == ident.to_string()) + .unwrap_or_else(|| panic!("Unknown field {}", ident)); + let mut operator = expect_punct(it); + let mut rhs_token = it.next().unwrap(); + if let TokenTree::Punct(punct) = &rhs_token { + operator.extend(std::iter::once(punct.as_char())); + rhs_token = it.next().unwrap(); + } + let rhs_name = if let TokenTree::Ident(ident) = &rhs_token { + ident.to_string() + } else { + panic!("Unexpected token {}", ident) + }; + + let rhs = config.enums[key] + .iter() + .position(|&r| r == rhs_name) + .unwrap_or_else(|| panic!("Unknown value for {}:{}", ident, rhs_name)); + let lhs = ver[key]; + + match operator.as_str() { + "==" => lhs == rhs, + "!=" => lhs != rhs, + ">" => lhs > rhs, + ">=" => lhs >= rhs, + "<" => lhs < rhs, + "<=" => lhs <= rhs, + _ => panic!("Unknown operator {}", operator), + } + } + _ => { + panic!("Unknown token {}", first) + } + }; + + let boolop = it.next(); + match boolop { + Some(TokenTree::Punct(punct)) => { + let right = expect_punct(it); + if right != punct.to_string() { + panic!("Unexpected op {}{}", punct, right); + } + match punct.as_char() { + '&' => val && check_version(config, ver, it), + '|' => val || check_version(config, ver, it), + _ => panic!("Unexpected op {}{}", right, right), + } + } + Some(a) => panic!("Unexpected op {}", a), + None => val, + } +} + +fn filter_versions( + config: &VersionConfig, + tag: &str, + ver: &[usize], + tree: impl IntoIterator, + is_struct: bool, +) -> Vec { + let mut out = Vec::::new(); + let mut it = tree.into_iter(); + + while let Some(token) = it.next() { + let mut tail: Option = None; + match &token { + TokenTree::Punct(punct) if punct.to_string() == "#" => { + let group = expect_group(&mut it); + let mut grp_it = group.stream().into_iter(); + let attr = grp_it.next().unwrap(); + match attr { + TokenTree::Ident(ident) if ident.to_string() == "ver" => { + if check_version(config, ver, &mut grp_it) { + } else if is_struct { + drop_until_punct(&mut it, ",", true); + } else { + let first = it.next().unwrap(); + match &first { + TokenTree::Ident(ident) + if ["while", "for", "loop", "if", "match", "unsafe", "fn"] + .contains(&ident.to_string().as_str()) => + { + drop_until_braces(&mut it); + } + TokenTree::Group(_) => (), + _ => { + drop_until_punct(&mut it, ",;", false); + } + } + } + } + _ => { + out.push(token.clone()); + out.push(TokenTree::Group(group.clone())); + } + } + continue; + } + TokenTree::Punct(punct) if punct.to_string() == ":" => { + let next = it.next(); + match next { + Some(TokenTree::Punct(punct)) if punct.to_string() == ":" => { + let next = it.next(); + match next { + Some(TokenTree::Ident(idtag)) if idtag.to_string() == "ver" => { + let ident = match out.pop() { + Some(TokenTree::Ident(ident)) => ident, + a => panic!("$ver not following ident: {:?}", a), + }; + let name = ident.to_string() + tag; + let new_ident = Ident::new(name.as_str(), ident.span()); + out.push(TokenTree::Ident(new_ident)); + continue; + } + Some(a) => { + out.push(token.clone()); + out.push(token.clone()); + tail = Some(a); + } + None => { + out.push(token.clone()); + out.push(token.clone()); + } + } + } + Some(a) => { + out.push(token.clone()); + tail = Some(a); + } + None => { + out.push(token.clone()); + continue; + } + } + } + _ => { + tail = Some(token); + } + } + match &tail { + Some(TokenTree::Group(group)) => { + let new_body = + filter_versions(config, tag, ver, group.stream().into_iter(), is_struct); + let mut stream = TokenStream::new(); + stream.extend(new_body); + let mut filtered_group = Group::new(group.delimiter(), stream); + filtered_group.set_span(group.span()); + out.push(TokenTree::Group(filtered_group)); + } + Some(token) => { + out.push(token.clone()); + } + None => {} + } + } + + out +} + +pub(crate) fn versions(attr: TokenStream, item: TokenStream) -> TokenStream { + let config = match attr.to_string().as_str() { + "AGX" => &AGX_VERSIONS, + _ => panic!("Unknown version group {}", attr), + }; + + let mut it = item.into_iter(); + let mut out = TokenStream::new(); + let mut body: Vec = Vec::new(); + let mut is_struct = false; + + while let Some(token) = it.next() { + match token { + TokenTree::Punct(punct) if punct.to_string() == "#" => { + body.push(TokenTree::Punct(punct)); + body.push(it.next().unwrap()); + } + TokenTree::Ident(ident) + if ["struct", "enum", "union", "const", "type"] + .contains(&ident.to_string().as_str()) => + { + is_struct = ident.to_string() != "const"; + body.push(TokenTree::Ident(ident)); + body.push(it.next().unwrap()); + // This isn't valid syntax in a struct definition, so add it for the user + body.push(TokenTree::Punct(Punct::new(':', Spacing::Joint))); + body.push(TokenTree::Punct(Punct::new(':', Spacing::Alone))); + body.push(TokenTree::Ident(Ident::new("ver", Span::call_site()))); + break; + } + TokenTree::Ident(ident) if ident.to_string() == "impl" => { + body.push(TokenTree::Ident(ident)); + break; + } + TokenTree::Ident(ident) if ident.to_string() == "fn" => { + body.push(TokenTree::Ident(ident)); + break; + } + _ => { + body.push(token); + } + } + } + + body.extend(it); + + for ver in config.versions { + let tag = ver.join(""); + let mut ver_num = Vec::::new(); + for (i, comp) in ver.iter().enumerate() { + let idx = config.enums[i].iter().position(|&r| r == *comp).unwrap(); + ver_num.push(idx); + } + out.extend(filter_versions( + config, + &tag, + &ver_num, + body.clone(), + is_struct, + )); + } + + out +} diff --git a/rust/pin-init/src/lib.rs b/rust/pin-init/src/lib.rs index dd553212836e0d..adb31130e98184 100644 --- a/rust/pin-init/src/lib.rs +++ b/rust/pin-init/src/lib.rs @@ -780,10 +780,10 @@ macro_rules! stack_try_pin_init { // module `macros` inside of `macros.rs`. #[macro_export] macro_rules! pin_init { - ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + ($(&$this:ident in)? $t:ident $(::$p:ident)* $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }) => { - $crate::try_pin_init!($(&$this in)? $t $(::<$($generics),*>)? { + $crate::try_pin_init!($(&$this in)? $t $(::$p)* $(::<$($generics),*>)? { $($fields)* }? ::core::convert::Infallible) }; @@ -831,12 +831,12 @@ macro_rules! pin_init { // module `macros` inside of `macros.rs`. #[macro_export] macro_rules! try_pin_init { - ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + ($(&$this:ident in)? $t:ident $(::$p:ident)* $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }? $err:ty) => { $crate::__init_internal!( @this($($this)?), - @typ($t $(::<$($generics),*>)? ), + @typ($t $(::$p)* $(::<$($generics),*>)? ), @fields($($fields)*), @error($err), @data(PinData, use_data), @@ -887,10 +887,10 @@ macro_rules! try_pin_init { // module `macros` inside of `macros.rs`. #[macro_export] macro_rules! init { - ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + ($(&$this:ident in)? $t:ident $(::$p:ident)* $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }) => { - $crate::try_init!($(&$this in)? $t $(::<$($generics),*>)? { + $crate::try_init!($(&$this in)? $t $(::$p)* $(::<$($generics),*>)? { $($fields)* }? ::core::convert::Infallible) } @@ -936,12 +936,12 @@ macro_rules! init { // module `macros` inside of `macros.rs`. #[macro_export] macro_rules! try_init { - ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + ($(&$this:ident in)? $t:ident $(::$p:ident)* $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }? $err:ty) => { $crate::__init_internal!( @this($($this)?), - @typ($t $(::<$($generics),*>)?), + @typ($t $(::$p)* $(::<$($generics),*>)?), @fields($($fields)*), @error($err), @data(InitData, /*no use_data*/), @@ -1487,6 +1487,21 @@ pub unsafe trait PinnedDrop: __internal::HasPinData { fn drop(self: Pin<&mut Self>, only_call_from_drop: __internal::OnlyCallFromDrop); } +/// Create a new default T. +/// +/// The returned initializer will use Default::default to initialize the `slot`. +#[inline] +pub fn default() -> impl Init { + // SAFETY: Because `T: Default`, T cannot require pinning and + // we can just move the data into the slot. + unsafe { + init_from_closure(|slot: *mut T| { + *slot = Default::default(); + Ok(()) + }) + } +} + /// Marker trait for types that can be initialized by writing just zeroes. /// /// # Safety diff --git a/rust/pin-init/src/macros.rs b/rust/pin-init/src/macros.rs index d6acf2cd291e03..130f571fdb4d70 100644 --- a/rust/pin-init/src/macros.rs +++ b/rust/pin-init/src/macros.rs @@ -1353,8 +1353,8 @@ macro_rules! __init_internal { // - the field is not structurally pinned, since the line above must compile, // - the field has been initialized, // - the reference is only valid until the end of the initializer. - #[allow(unused_variables)] - let $field = unsafe { &mut (*$slot).$field }; + // #[allow(unused_variables)] + // let $field = unsafe { &mut (*$slot).$field }; // Create the drop guard: // @@ -1395,7 +1395,7 @@ macro_rules! __init_internal { // initializer, // - the field has been initialized, // - the reference is only valid until the end of the initializer. - let $field = unsafe { &mut (*$slot).$field }; + // let $field = unsafe { &mut (*$slot).$field }; // Create the drop guard: // diff --git a/rust/uapi/uapi_helper.h b/rust/uapi/uapi_helper.h index 06d7d1a2e8daba..512ac0aea08fde 100644 --- a/rust/uapi/uapi_helper.h +++ b/rust/uapi/uapi_helper.h @@ -7,10 +7,13 @@ */ #include +#include #include #include #include #include +#include +#include #include #include #include diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c index da3a9f2091f55b..1ba1927b548ee9 100644 --- a/samples/ftrace/ftrace-direct-modify.c +++ b/samples/ftrace/ftrace-direct-modify.c @@ -176,8 +176,8 @@ asm ( " st.d $t0, $sp, 0\n" " st.d $ra, $sp, 8\n" " bl my_direct_func1\n" -" ld.d $t0, $sp, 0\n" -" ld.d $ra, $sp, 8\n" +" ld.d $ra, $sp, 0\n" +" ld.d $t0, $sp, 8\n" " addi.d $sp, $sp, 16\n" " jr $t0\n" " .size my_tramp1, .-my_tramp1\n" @@ -189,8 +189,8 @@ asm ( " st.d $t0, $sp, 0\n" " st.d $ra, $sp, 8\n" " bl my_direct_func2\n" -" ld.d $t0, $sp, 0\n" -" ld.d $ra, $sp, 8\n" +" ld.d $ra, $sp, 0\n" +" ld.d $t0, $sp, 8\n" " addi.d $sp, $sp, 16\n" " jr $t0\n" " .size my_tramp2, .-my_tramp2\n" diff --git a/samples/ftrace/ftrace-direct-multi-modify.c b/samples/ftrace/ftrace-direct-multi-modify.c index 8f7986d698d874..7a7822dfeb50ab 100644 --- a/samples/ftrace/ftrace-direct-multi-modify.c +++ b/samples/ftrace/ftrace-direct-multi-modify.c @@ -199,8 +199,8 @@ asm ( " move $a0, $t0\n" " bl my_direct_func1\n" " ld.d $a0, $sp, 0\n" -" ld.d $t0, $sp, 8\n" -" ld.d $ra, $sp, 16\n" +" ld.d $ra, $sp, 8\n" +" ld.d $t0, $sp, 16\n" " addi.d $sp, $sp, 32\n" " jr $t0\n" " .size my_tramp1, .-my_tramp1\n" @@ -215,8 +215,8 @@ asm ( " move $a0, $t0\n" " bl my_direct_func2\n" " ld.d $a0, $sp, 0\n" -" ld.d $t0, $sp, 8\n" -" ld.d $ra, $sp, 16\n" +" ld.d $ra, $sp, 8\n" +" ld.d $t0, $sp, 16\n" " addi.d $sp, $sp, 32\n" " jr $t0\n" " .size my_tramp2, .-my_tramp2\n" diff --git a/samples/ftrace/ftrace-direct-multi.c b/samples/ftrace/ftrace-direct-multi.c index db326c81a27ddd..3fe6ddaf0b69f7 100644 --- a/samples/ftrace/ftrace-direct-multi.c +++ b/samples/ftrace/ftrace-direct-multi.c @@ -131,8 +131,8 @@ asm ( " move $a0, $t0\n" " bl my_direct_func\n" " ld.d $a0, $sp, 0\n" -" ld.d $t0, $sp, 8\n" -" ld.d $ra, $sp, 16\n" +" ld.d $ra, $sp, 8\n" +" ld.d $t0, $sp, 16\n" " addi.d $sp, $sp, 32\n" " jr $t0\n" " .size my_tramp, .-my_tramp\n" diff --git a/samples/ftrace/ftrace-direct-too.c b/samples/ftrace/ftrace-direct-too.c index 3d0fa260332d47..bf2411aa6fd7ad 100644 --- a/samples/ftrace/ftrace-direct-too.c +++ b/samples/ftrace/ftrace-direct-too.c @@ -143,8 +143,8 @@ asm ( " ld.d $a0, $sp, 0\n" " ld.d $a1, $sp, 8\n" " ld.d $a2, $sp, 16\n" -" ld.d $t0, $sp, 24\n" -" ld.d $ra, $sp, 32\n" +" ld.d $ra, $sp, 24\n" +" ld.d $t0, $sp, 32\n" " addi.d $sp, $sp, 48\n" " jr $t0\n" " .size my_tramp, .-my_tramp\n" diff --git a/samples/ftrace/ftrace-direct.c b/samples/ftrace/ftrace-direct.c index 956834b0d19ac6..5368c8c39cbb44 100644 --- a/samples/ftrace/ftrace-direct.c +++ b/samples/ftrace/ftrace-direct.c @@ -124,8 +124,8 @@ asm ( " st.d $ra, $sp, 16\n" " bl my_direct_func\n" " ld.d $a0, $sp, 0\n" -" ld.d $t0, $sp, 8\n" -" ld.d $ra, $sp, 16\n" +" ld.d $ra, $sp, 8\n" +" ld.d $t0, $sp, 16\n" " addi.d $sp, $sp, 32\n" " jr $t0\n" " .size my_tramp, .-my_tramp\n" diff --git a/samples/rust/rust_driver_pci.rs b/samples/rust/rust_driver_pci.rs index 55a683c39ed910..ea3063e558b1a3 100644 --- a/samples/rust/rust_driver_pci.rs +++ b/samples/rust/rust_driver_pci.rs @@ -48,7 +48,7 @@ impl SampleDriver { // Select the test. bar.write8(index.0, Regs::TEST); - let offset = u32::from_le(bar.read32(Regs::OFFSET)) as usize; + let offset = bar.read32(Regs::OFFSET) as usize; let data = bar.read8(Regs::DATA); // Write `data` to `offset` to increase `count` by one. diff --git a/samples/rust/rust_minimal.rs b/samples/rust/rust_minimal.rs index 1fc7a1be6b6d75..8eb9583571d726 100644 --- a/samples/rust/rust_minimal.rs +++ b/samples/rust/rust_minimal.rs @@ -10,6 +10,12 @@ module! { authors: ["Rust for Linux Contributors"], description: "Rust minimal sample", license: "GPL", + params: { + test_parameter: i64 { + default: 1, + description: "This parameter has a default of 1", + }, + }, } struct RustMinimal { @@ -20,6 +26,10 @@ impl kernel::Module for RustMinimal { fn init(_module: &'static ThisModule) -> Result { pr_info!("Rust minimal sample (init)\n"); pr_info!("Am I built-in? {}\n", !cfg!(MODULE)); + pr_info!( + "test_parameter: {}\n", + *module_parameters::test_parameter.value() + ); let mut numbers = KVec::new(); numbers.push(72, GFP_KERNEL)?; diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 52c08c4eb0b9af..1dac14fa1a1321 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -319,6 +319,9 @@ $(obj)/%.lst: $(obj)/%.c FORCE # the unstable features in use. rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,offset_of_nested,raw_ref_op,used_with_arg +# additional rust features used by the downstream asahi kernel +rust_allowed_features := $(rust_allowed_features),ptr_sub_ptr + # `--out-dir` is required to avoid temporaries being created by `rustc` in the # current working directory, which may be not accessible in the out-of-tree # modules case. @@ -356,7 +359,7 @@ $(obj)/%.o: $(obj)/%.rs FORCE quiet_cmd_rustc_rsi_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@ cmd_rustc_rsi_rs = \ $(rust_common_cmd) -Zunpretty=expanded $< >$@; \ - command -v $(RUSTFMT) >/dev/null && $(RUSTFMT) $@ + command -v $(RUSTFMT) >/dev/null && $(RUSTFMT) --config-path $(srctree)/.rustfmt.toml $@ $(obj)/%.rsi: $(obj)/%.rs FORCE +$(call if_changed_dep,rustc_rsi_rs) @@ -527,18 +530,6 @@ ifneq ($(userprogs),) include $(srctree)/scripts/Makefile.userprogs endif -ifneq ($(need-dtbslist)$(dtb-y)$(dtb-)$(filter %.dtb %.dtb.o %.dtbo.o,$(targets)),) -include $(srctree)/scripts/Makefile.dtbs -endif - -# Build -# --------------------------------------------------------------------------- - -$(obj)/: $(if $(KBUILD_BUILTIN), $(targets-for-builtin)) \ - $(if $(KBUILD_MODULES), $(targets-for-modules)) \ - $(subdir-ym) $(always-y) - @: - # Single targets # --------------------------------------------------------------------------- @@ -568,6 +559,20 @@ FORCE: targets += $(filter-out $(single-subdir-goals), $(MAKECMDGOALS)) targets := $(filter-out $(PHONY), $(targets)) +# Now that targets is fully known, include dtb rules if needed +ifneq ($(need-dtbslist)$(dtb-y)$(dtb-)$(filter %.dtb %.dtb.o %.dtbo.o,$(targets)),) +include $(srctree)/scripts/Makefile.dtbs +endif + +# Build +# Needs to be after the include of Makefile.dtbs, which updates always-y +# --------------------------------------------------------------------------- + +$(obj)/: $(if $(KBUILD_BUILTIN), $(targets-for-builtin)) \ + $(if $(KBUILD_MODULES), $(targets-for-modules)) \ + $(subdir-ym) $(always-y) + @: + # Read all saved command lines and dependencies for the $(targets) we # may be building above, using $(if_changed{,_dep}). As an # optimization, we don't need to read them if the target does not diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst index 1628198f3e8309..9ba45e5b32b183 100644 --- a/scripts/Makefile.modinst +++ b/scripts/Makefile.modinst @@ -100,7 +100,7 @@ endif # Don't stop modules_install even if we can't sign external modules. # ifeq ($(filter pkcs11:%, $(CONFIG_MODULE_SIG_KEY)),) -sig-key := $(if $(wildcard $(CONFIG_MODULE_SIG_KEY)),,$(srctree)/)$(CONFIG_MODULE_SIG_KEY) +sig-key := $(if $(wildcard $(CONFIG_MODULE_SIG_KEY)),,$(objtree)/)$(CONFIG_MODULE_SIG_KEY) else sig-key := $(CONFIG_MODULE_SIG_KEY) endif diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux index cd788cac9d91da..276c3134a563ad 100644 --- a/scripts/Makefile.vmlinux +++ b/scripts/Makefile.vmlinux @@ -113,7 +113,8 @@ vmlinux: vmlinux.unstripped FORCE # what kmod expects to parse. quiet_cmd_modules_builtin_modinfo = GEN $@ cmd_modules_builtin_modinfo = $(cmd_objcopy); \ - sed -i 's/\x00\+$$/\x00/g' $@ + sed -i 's/\x00\+$$/\x00/g' $@; \ + chmod -x $@ OBJCOPYFLAGS_modules.builtin.modinfo := -j .modinfo -O binary diff --git a/scripts/cc-can-link.sh b/scripts/cc-can-link.sh index 6efcead3198989..e67fd8d7b6841e 100755 --- a/scripts/cc-can-link.sh +++ b/scripts/cc-can-link.sh @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 -cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1 +cat << "END" | $@ -Werror -Wl,--fatal-warnings -x c - -o /dev/null >/dev/null 2>&1 #include int main(void) { diff --git a/scripts/dtc/data.c b/scripts/dtc/data.c index 5b25aa06041613..ce449824c80a06 100644 --- a/scripts/dtc/data.c +++ b/scripts/dtc/data.c @@ -184,6 +184,33 @@ struct data data_append_integer(struct data d, uint64_t value, int bits) } } +struct data data_append_float(struct data d, double value, int bits) +{ + float f32; + uint32_t u32; + double f64; + uint64_t u64; + fdt32_t value_32; + fdt64_t value_64; + + switch (bits) { + case 32: + f32 = value; + memcpy(&u32, &f32, sizeof(u32)); + value_32 = cpu_to_fdt32(u32); + return data_append_data(d, &value_32, 4); + + case 64: + f64 = value; + memcpy(&u64, &f64, sizeof(u64)); + value_64 = cpu_to_fdt64(u64); + return data_append_data(d, &value_64, 8); + + default: + die("Invalid literal size (%d)\n", bits); + } +} + struct data data_append_re(struct data d, uint64_t address, uint64_t size) { struct fdt_reserve_entry re; diff --git a/scripts/dtc/dtc-lexer.l b/scripts/dtc/dtc-lexer.l index 15d585c8079802..bd750717aa3a54 100644 --- a/scripts/dtc/dtc-lexer.l +++ b/scripts/dtc/dtc-lexer.l @@ -151,6 +151,28 @@ static void PRINTF(1, 2) lexical_error(const char *fmt, ...); return DT_LABEL; } +[-+]?(([0-9]+\.[0-9]*)|([0-9]*\.[0-9]+))(e[-+]?[0-9]+)?f? { + char *e; + DPRINT("Floating-point Literal: '%s'\n", yytext); + + errno = 0; + yylval.floating = strtod(yytext, &e); + + if (*e && (*e != 'f' || e[1])) { + lexical_error("Bad floating-point literal '%s'", + yytext); + } + + if (errno == ERANGE) + lexical_error("Floating-point literal '%s' out of range", + yytext); + else + /* ERANGE is the only strtod error triggerable + * by strings matching the pattern */ + assert(errno == 0); + return DT_FP_LITERAL; + } + {LABEL} { /* Missed includes or macro definitions while * preprocessing can lead to unexpected identifiers in diff --git a/scripts/dtc/dtc-parser.y b/scripts/dtc/dtc-parser.y index 4d5eece5262434..225a6b41b14fcf 100644 --- a/scripts/dtc/dtc-parser.y +++ b/scripts/dtc/dtc-parser.y @@ -48,6 +48,7 @@ static bool is_ref_relative(const char *ref) struct node *nodelist; struct reserve_info *re; uint64_t integer; + double floating; unsigned int flags; } @@ -61,6 +62,7 @@ static bool is_ref_relative(const char *ref) %token DT_OMIT_NO_REF %token DT_PROPNODENAME %token DT_LITERAL +%token DT_FP_LITERAL %token DT_CHAR_LITERAL %token DT_BYTE %token DT_STRING @@ -86,6 +88,7 @@ static bool is_ref_relative(const char *ref) %type subnode %type subnodes +%type floating_prim %type integer_prim %type integer_unary %type integer_mul @@ -395,6 +398,15 @@ arrayprefix: $$.data = data_add_marker(empty_data, TYPE_UINT32, NULL); $$.bits = 32; } + | arrayprefix floating_prim + { + if ($1.bits < 32) { + ERROR(&@2, "Floating-point values must be" + " 32-bit or 64-bit"); + } + + $$.data = data_append_float($1.data, $2, $1.bits); + } | arrayprefix integer_prim { if ($1.bits < 64) { @@ -439,6 +451,10 @@ arrayprefix: } ; +floating_prim: + DT_FP_LITERAL + ; + integer_prim: DT_LITERAL | DT_CHAR_LITERAL diff --git a/scripts/dtc/dtc.h b/scripts/dtc/dtc.h index 3a220b9afc99f9..cad8be1440bd69 100644 --- a/scripts/dtc/dtc.h +++ b/scripts/dtc/dtc.h @@ -177,6 +177,7 @@ struct data data_insert_at_marker(struct data d, struct marker *m, struct data data_merge(struct data d1, struct data d2); struct data data_append_cell(struct data d, cell_t word); struct data data_append_integer(struct data d, uint64_t word, int bits); +struct data data_append_float(struct data d, double value, int bits); struct data data_append_re(struct data d, uint64_t address, uint64_t size); struct data data_append_addr(struct data d, uint64_t addr); struct data data_append_byte(struct data d, uint8_t byte); diff --git a/scripts/faddr2line b/scripts/faddr2line index 1fa6beef9f978e..477b6d2aa31794 100755 --- a/scripts/faddr2line +++ b/scripts/faddr2line @@ -107,14 +107,19 @@ find_dir_prefix() { run_readelf() { local objfile=$1 - local out=$(${READELF} --file-header --section-headers --symbols --wide $objfile) + local tmpfile + tmpfile=$(mktemp) + + ${READELF} --file-header --section-headers --symbols --wide "$objfile" > "$tmpfile" # This assumes that readelf first prints the file header, then the section headers, then the symbols. # Note: It seems that GNU readelf does not prefix section headers with the "There are X section headers" # line when multiple options are given, so let's also match with the "Section Headers:" line. - ELF_FILEHEADER=$(echo "${out}" | sed -n '/There are [0-9]* section headers, starting at offset\|Section Headers:/q;p') - ELF_SECHEADERS=$(echo "${out}" | sed -n '/There are [0-9]* section headers, starting at offset\|Section Headers:/,$p' | sed -n '/Symbol table .* contains [0-9]* entries:/q;p') - ELF_SYMS=$(echo "${out}" | sed -n '/Symbol table .* contains [0-9]* entries:/,$p') + ELF_FILEHEADER=$(sed -n '/There are [0-9]* section headers, starting at offset\|Section Headers:/q;p' "$tmpfile") + ELF_SECHEADERS=$(sed -n '/There are [0-9]* section headers, starting at offset\|Section Headers:/,$p' "$tmpfile" | sed -n '/Symbol table .* contains [0-9]* entries:/q;p') + ELF_SYMS=$(sed -n '/Symbol table .* contains [0-9]* entries:/,$p' "$tmpfile") + + rm -f -- "$tmpfile" } check_vmlinux() { diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py index fc27f0cca752d3..852444352657ed 100755 --- a/scripts/generate_rust_analyzer.py +++ b/scripts/generate_rust_analyzer.py @@ -61,7 +61,6 @@ def append_sysroot_crate( display_name, deps, cfg=[], - edition="2021", ): append_crate( display_name, @@ -69,13 +68,37 @@ def append_sysroot_crate( deps, cfg, is_workspace_member=False, - edition=edition, + # Miguel Ojeda writes: + # + # > ... in principle even the sysroot crates may have different + # > editions. + # > + # > For instance, in the move to 2024, it seems all happened at once + # > in 1.87.0 in these upstream commits: + # > + # > 0e071c2c6a58 ("Migrate core to Rust 2024") + # > f505d4e8e380 ("Migrate alloc to Rust 2024") + # > 0b2489c226c3 ("Migrate proc_macro to Rust 2024") + # > 993359e70112 ("Migrate std to Rust 2024") + # > + # > But in the previous move to 2021, `std` moved in 1.59.0, while + # > the others in 1.60.0: + # > + # > b656384d8398 ("Update stdlib to the 2021 edition") + # > 06a1c14d52a8 ("Switch all libraries to the 2021 edition") + # + # Link: https://lore.kernel.org/all/CANiq72kd9bHdKaAm=8xCUhSHMy2csyVed69bOc4dXyFAW4sfuw@mail.gmail.com/ + # + # At the time of writing all rust versions we support build the + # sysroot crates with the same edition. We may need to relax this + # assumption if future edition moves span multiple rust versions. + edition=core_edition, ) # NB: sysroot crates reexport items from one another so setting up our transitive dependencies # here is important for ensuring that rust-analyzer can resolve symbols. The sources of truth # for this dependency graph are `(sysroot_src / crate / "Cargo.toml" for crate in crates)`. - append_sysroot_crate("core", [], cfg=crates_cfgs.get("core", []), edition=core_edition) + append_sysroot_crate("core", [], cfg=crates_cfgs.get("core", [])) append_sysroot_crate("alloc", ["core"]) append_sysroot_crate("std", ["alloc", "core"]) append_sysroot_crate("proc_macro", ["core", "std"]) @@ -83,7 +106,7 @@ def append_sysroot_crate( append_crate( "compiler_builtins", srctree / "rust" / "compiler_builtins.rs", - [], + ["core"], ) append_crate( @@ -102,7 +125,7 @@ def append_sysroot_crate( append_crate( "pin_init_internal", srctree / "rust" / "pin-init" / "internal" / "src" / "lib.rs", - [], + ["std", "proc_macro"], cfg=["kernel"], is_proc_macro=True, ) @@ -110,7 +133,7 @@ def append_sysroot_crate( append_crate( "pin_init", srctree / "rust" / "pin-init" / "src" / "lib.rs", - ["core", "pin_init_internal", "macros"], + ["core", "compiler_builtins", "pin_init_internal", "macros"], cfg=["kernel"], ) @@ -169,7 +192,7 @@ def is_root_crate(build_file, target): append_crate( name, path, - ["core", "kernel"], + ["core", "kernel", "pin_init"], cfg=cfg, ) @@ -192,9 +215,6 @@ def main(): level=logging.INFO if args.verbose else logging.WARNING ) - # Making sure that the `sysroot` and `sysroot_src` belong to the same toolchain. - assert args.sysroot in args.sysroot_src.parents - rust_project = { "crates": generate_crates(args.srctree, args.objtree, args.sysroot_src, args.exttree, args.cfgs, args.core_edition), "sysroot": str(args.sysroot), diff --git a/scripts/kconfig/nconf-cfg.sh b/scripts/kconfig/nconf-cfg.sh index a20290b1a37d89..4d08453f9bdb7f 100755 --- a/scripts/kconfig/nconf-cfg.sh +++ b/scripts/kconfig/nconf-cfg.sh @@ -6,8 +6,9 @@ set -eu cflags=$1 libs=$2 -PKG="ncursesw menuw panelw" -PKG2="ncurses menu panel" +# Keep library order for static linking (HOSTCC='cc -static') +PKG="menuw panelw ncursesw" +PKG2="menu panel ncurses" if [ -n "$(command -v ${HOSTPKG_CONFIG})" ]; then if ${HOSTPKG_CONFIG} --exists $PKG; then @@ -28,19 +29,19 @@ fi # find ncurses by pkg-config.) if [ -f /usr/include/ncursesw/ncurses.h ]; then echo -D_GNU_SOURCE -I/usr/include/ncursesw > ${cflags} - echo -lncursesw -lmenuw -lpanelw > ${libs} + echo -lmenuw -lpanelw -lncursesw > ${libs} exit 0 fi if [ -f /usr/include/ncurses/ncurses.h ]; then echo -D_GNU_SOURCE -I/usr/include/ncurses > ${cflags} - echo -lncurses -lmenu -lpanel > ${libs} + echo -lmenu -lpanel -lncurses > ${libs} exit 0 fi if [ -f /usr/include/ncurses.h ]; then echo -D_GNU_SOURCE > ${cflags} - echo -lncurses -lmenu -lpanel > ${libs} + echo -lmenu -lpanel -lncurses > ${libs} exit 0 fi diff --git a/scripts/lib/kdoc/kdoc_parser.py b/scripts/lib/kdoc/kdoc_parser.py index 2376f180b1fa97..89d920e0b65ca0 100644 --- a/scripts/lib/kdoc/kdoc_parser.py +++ b/scripts/lib/kdoc/kdoc_parser.py @@ -350,6 +350,7 @@ def dump_section(self, start_new=True): self.section = SECTION_DEFAULT self._contents = [] +python_warning = False class KernelDoc: """ @@ -383,9 +384,13 @@ def __init__(self, config, fname): # We need Python 3.7 for its "dicts remember the insertion # order" guarantee # - if sys.version_info.major == 3 and sys.version_info.minor < 7: + global python_warning + if (not python_warning and + sys.version_info.major == 3 and sys.version_info.minor < 7): + self.emit_msg(0, 'Python 3.7 or later is required for correct results') + python_warning = True def emit_msg(self, ln, msg, warning=True): """Emit a message""" diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index d3d00e85edf735..0470ba7c796d4a 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -198,6 +198,9 @@ int main(void) DEVID(cpu_feature); DEVID_FIELD(cpu_feature, feature); + DEVID(mcb_device_id); + DEVID_FIELD(mcb_device_id, device); + DEVID(mei_cl_device_id); DEVID_FIELD(mei_cl_device_id, name); DEVID_FIELD(mei_cl_device_id, uuid); diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index b3333560b95ee9..4e99393a35f152 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -1110,6 +1110,14 @@ static void do_cpu_entry(struct module *mod, void *symval) module_alias_printf(mod, false, "cpu:type:*:feature:*%04X*", feature); } +/* Looks like: mcb:16zN */ +static void do_mcb_entry(struct module *mod, void *symval) +{ + DEF_FIELD(symval, mcb_device_id, device); + + module_alias_printf(mod, false, "mcb:16z%03d", device); +} + /* Looks like: mei:S:uuid:N:* */ static void do_mei_entry(struct module *mod, void *symval) { @@ -1444,6 +1452,7 @@ static const struct devtable devtable[] = { {"mipscdmm", SIZE_mips_cdmm_device_id, do_mips_cdmm_entry}, {"x86cpu", SIZE_x86_cpu_id, do_x86cpu_entry}, {"cpu", SIZE_cpu_feature, do_cpu_entry}, + {"mcb", SIZE_mcb_device_id, do_mcb_entry}, {"mei", SIZE_mei_cl_device_id, do_mei_entry}, {"rapidio", SIZE_rio_device_id, do_rio_entry}, {"ulpi", SIZE_ulpi_device_id, do_ulpi_entry}, diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build index 054fdf45cc37a8..2576cf7902dbbf 100755 --- a/scripts/package/install-extmod-build +++ b/scripts/package/install-extmod-build @@ -63,7 +63,7 @@ if [ "${CC}" != "${HOSTCC}" ]; then # Clear VPATH and srcroot because the source files reside in the output # directory. # shellcheck disable=SC2016 # $(MAKE) and $(build) will be expanded by Make - "${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC='"${CC}"' VPATH= srcroot=. $(build)='"$(realpath --relative-to=. "${destdir}")"/scripts + "${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC="'"${CC}"'" VPATH= srcroot=. $(build)='"$(realpath --relative-to=. "${destdir}")"/scripts rm -f "${destdir}/scripts/Kbuild" fi diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec index 98f206cb7c6079..0f1c8de1bd95f8 100644 --- a/scripts/package/kernel.spec +++ b/scripts/package/kernel.spec @@ -2,6 +2,8 @@ %{!?_arch: %define _arch dummy} %{!?make: %define make make} %define makeflags %{?_smp_mflags} ARCH=%{ARCH} +%define __spec_install_post /usr/lib/rpm/brp-compress || : +%define debug_package %{nil} Name: kernel Summary: The Linux Kernel @@ -46,34 +48,12 @@ against the %{version} kernel package. %endif %if %{with_debuginfo} -# list of debuginfo-related options taken from distribution kernel.spec -# files -%undefine _include_minidebuginfo -%undefine _find_debuginfo_dwz_opts -%undefine _unique_build_ids -%undefine _unique_debug_names -%undefine _unique_debug_srcs -%undefine _debugsource_packages -%undefine _debuginfo_subpackages -%global _find_debuginfo_opts -r -%global _missing_build_ids_terminate_build 1 -%global _no_recompute_build_ids 1 -%{debug_package} +%package debuginfo +Summary: Debug information package for the Linux kernel +%description debuginfo +This package provides debug information for the kernel image and modules from the +%{version} package. %endif -# some (but not all) versions of rpmbuild emit %%debug_package with -# %%install. since we've already emitted it manually, that would cause -# a package redefinition error. ensure that doesn't happen -%define debug_package %{nil} - -# later, we make all modules executable so that find-debuginfo.sh strips -# them up. but they don't actually need to be executable, so remove the -# executable bit, taking care to do it _after_ find-debuginfo.sh has run -%define __spec_install_post \ - %{?__debug_package:%{__debug_install_post}} \ - %{__arch_install_post} \ - %{__os_install_post} \ - find %{buildroot}/lib/modules/%{KERNELRELEASE} -name "*.ko" -type f \\\ - | xargs --no-run-if-empty chmod u-x %prep %setup -q -n linux @@ -87,7 +67,7 @@ patch -p1 < %{SOURCE2} mkdir -p %{buildroot}/lib/modules/%{KERNELRELEASE} cp $(%{make} %{makeflags} -s image_name) %{buildroot}/lib/modules/%{KERNELRELEASE}/vmlinuz # DEPMOD=true makes depmod no-op. We do not package depmod-generated files. -%{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} DEPMOD=true modules_install +%{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} INSTALL_MOD_STRIP=1 DEPMOD=true modules_install %{make} %{makeflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install cp System.map %{buildroot}/lib/modules/%{KERNELRELEASE} cp .config %{buildroot}/lib/modules/%{KERNELRELEASE}/config @@ -118,22 +98,31 @@ ln -fns /usr/src/kernels/%{KERNELRELEASE} %{buildroot}/lib/modules/%{KERNELRELEA echo "%exclude /lib/modules/%{KERNELRELEASE}/build" } > %{buildroot}/kernel.list -# make modules executable so that find-debuginfo.sh strips them. this -# will be undone later in %%__spec_install_post -find %{buildroot}/lib/modules/%{KERNELRELEASE} -name "*.ko" -type f \ - | xargs --no-run-if-empty chmod u+x - %if %{with_debuginfo} # copying vmlinux directly to the debug directory means it will not get # stripped (but its source paths will still be collected + fixed up) mkdir -p %{buildroot}/usr/lib/debug/lib/modules/%{KERNELRELEASE} cp vmlinux %{buildroot}/usr/lib/debug/lib/modules/%{KERNELRELEASE} + +echo /usr/lib/debug/lib/modules/%{KERNELRELEASE}/vmlinux > %{buildroot}/debuginfo.list + +while read -r mod; do + mod="${mod%.o}.ko" + dbg="%{buildroot}/usr/lib/debug/lib/modules/%{KERNELRELEASE}/kernel/${mod}" + buildid=$("${READELF}" -n "${mod}" | sed -n 's@^.*Build ID: \(..\)\(.*\)@\1/\2@p') + link="%{buildroot}/usr/lib/debug/.build-id/${buildid}.debug" + + mkdir -p "${dbg%/*}" "${link%/*}" + "${OBJCOPY}" --only-keep-debug "${mod}" "${dbg}" + ln -sf --relative "${dbg}" "${link}" + + echo "${dbg#%{buildroot}}" >> %{buildroot}/debuginfo.list + echo "${link#%{buildroot}}" >> %{buildroot}/debuginfo.list +done < modules.order %endif %clean rm -rf %{buildroot} -rm -f debugfiles.list debuglinks.list debugsourcefiles.list debugsources.list \ - elfbins.list %post if [ -x /usr/bin/kernel-install ]; then @@ -172,3 +161,9 @@ fi /usr/src/kernels/%{KERNELRELEASE} /lib/modules/%{KERNELRELEASE}/build %endif + +%if %{with_debuginfo} +%files -f %{buildroot}/debuginfo.list debuginfo +%defattr (-, root, root) +%exclude /debuginfo.list +%endif diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 391a586d0557f0..7803b973b4c427 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -1639,6 +1639,15 @@ static const char *rawdata_get_link_base(struct dentry *dentry, label = aa_get_label_rcu(&proxy->label); profile = labels_profile(label); + + /* rawdata can be null when aa_g_export_binary is unset during + * runtime and a profile is replaced + */ + if (!profile->rawdata) { + aa_put_label(label); + return ERR_PTR(-ENOENT); + } + depth = profile_depth(profile); target = gen_symlink_name(depth, profile->rawdata->name, name); aa_put_label(label); diff --git a/security/apparmor/file.c b/security/apparmor/file.c index c758204028780f..7de23e85cd5d01 100644 --- a/security/apparmor/file.c +++ b/security/apparmor/file.c @@ -154,8 +154,12 @@ static int path_name(const char *op, const struct cred *subj_cred, const char *info = NULL; int error; - error = aa_path_name(path, flags, buffer, name, &info, - labels_profile(label)->disconnected); + /* don't reaudit files closed during inheritance */ + if (unlikely(path->dentry == aa_null.dentry)) + error = -EACCES; + else + error = aa_path_name(path, flags, buffer, name, &info, + labels_profile(label)->disconnected); if (error) { fn_for_each_confined(label, profile, aa_audit_file(subj_cred, @@ -578,6 +582,9 @@ static bool __unix_needs_revalidation(struct file *file, struct aa_label *label, return false; if (request & NET_PEER_MASK) return false; + /* sock and sock->sk can be NULL for sockets being set up or torn down */ + if (!sock || !sock->sk) + return false; if (sock->sk->sk_family == PF_UNIX) { struct aa_sk_ctx *ctx = aa_sock(sock->sk); @@ -613,6 +620,10 @@ int aa_file_perm(const char *op, const struct cred *subj_cred, AA_BUG(!label); AA_BUG(!file); + /* don't reaudit files closed during inheritance */ + if (unlikely(file->f_path.dentry == aa_null.dentry)) + return -EACCES; + fctx = file_ctx(file); rcu_read_lock(); diff --git a/security/apparmor/include/match.h b/security/apparmor/include/match.h index 1fbe82f5021b16..0dde8eda3d1a59 100644 --- a/security/apparmor/include/match.h +++ b/security/apparmor/include/match.h @@ -104,16 +104,18 @@ struct aa_dfa { struct table_header *tables[YYTD_ID_TSIZE]; }; -#define byte_to_byte(X) (X) - #define UNPACK_ARRAY(TABLE, BLOB, LEN, TTYPE, BTYPE, NTOHX) \ do { \ typeof(LEN) __i; \ TTYPE *__t = (TTYPE *) TABLE; \ BTYPE *__b = (BTYPE *) BLOB; \ - for (__i = 0; __i < LEN; __i++) { \ - __t[__i] = NTOHX(__b[__i]); \ - } \ + BUILD_BUG_ON(sizeof(TTYPE) != sizeof(BTYPE)); \ + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) \ + memcpy(__t, __b, (LEN) * sizeof(BTYPE)); \ + else /* copy & convert from big-endian */ \ + for (__i = 0; __i < LEN; __i++) { \ + __t[__i] = NTOHX(&__b[__i]); \ + } \ } while (0) static inline size_t table_size(size_t len, size_t el_size) diff --git a/security/apparmor/label.c b/security/apparmor/label.c index 913678f199c358..dd6c58f595ba8d 100644 --- a/security/apparmor/label.c +++ b/security/apparmor/label.c @@ -1278,7 +1278,7 @@ static inline aa_state_t match_component(struct aa_profile *profile, * @request: permissions to request * @perms: perms struct to set * - * Returns: 0 on success else ERROR + * Returns: state match stopped at or DFA_NOMATCH if aborted early * * For the label A//&B//&C this does the perm match for A//&B//&C * @perms should be preinitialized with allperms OR a previous permission @@ -1305,7 +1305,7 @@ static int label_compound_match(struct aa_profile *profile, /* no component visible */ *perms = allperms; - return 0; + return state; next: label_for_each_cont(i, label, tp) { @@ -1317,15 +1317,11 @@ static int label_compound_match(struct aa_profile *profile, goto fail; } *perms = *aa_lookup_perms(rules->policy, state); - aa_apply_modes_to_perms(profile, perms); - if ((perms->allow & request) != request) - return -EACCES; - - return 0; + return state; fail: *perms = nullperms; - return state; + return DFA_NOMATCH; } /** @@ -1338,7 +1334,7 @@ static int label_compound_match(struct aa_profile *profile, * @request: permissions to request * @perms: an initialized perms struct to add accumulation to * - * Returns: 0 on success else ERROR + * Returns: the state the match finished in, may be the none matching state * * For the label A//&B//&C this does the perm match for each of A and B and C * @perms should be preinitialized with allperms OR a previous permission @@ -1366,11 +1362,10 @@ static int label_components_match(struct aa_profile *profile, } /* no subcomponents visible - no change in perms */ - return 0; + return state; next: tmp = *aa_lookup_perms(rules->policy, state); - aa_apply_modes_to_perms(profile, &tmp); aa_perms_accum(perms, &tmp); label_for_each_cont(i, label, tp) { if (!aa_ns_visible(profile->ns, tp->ns, subns)) @@ -1379,18 +1374,17 @@ static int label_components_match(struct aa_profile *profile, if (!state) goto fail; tmp = *aa_lookup_perms(rules->policy, state); - aa_apply_modes_to_perms(profile, &tmp); aa_perms_accum(perms, &tmp); } if ((perms->allow & request) != request) - return -EACCES; + return DFA_NOMATCH; - return 0; + return state; fail: *perms = nullperms; - return -EACCES; + return DFA_NOMATCH; } /** @@ -1409,11 +1403,12 @@ int aa_label_match(struct aa_profile *profile, struct aa_ruleset *rules, struct aa_label *label, aa_state_t state, bool subns, u32 request, struct aa_perms *perms) { - int error = label_compound_match(profile, rules, label, state, subns, - request, perms); - if (!error) - return error; + aa_state_t tmp = label_compound_match(profile, rules, label, state, subns, + request, perms); + if ((perms->allow & request) == request) + return tmp; + /* failed compound_match try component matches */ *perms = allperms; return label_components_match(profile, rules, label, state, subns, request, perms); diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index b3f7a3258a2cf7..13c9bfdf65ff57 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -519,33 +519,26 @@ static void apparmor_file_free_security(struct file *file) aa_put_label(rcu_access_pointer(ctx->label)); } -static int common_file_perm(const char *op, struct file *file, u32 mask, - bool in_atomic) +static int common_file_perm(const char *op, struct file *file, u32 mask) { struct aa_label *label; int error = 0; - bool needput; - - /* don't reaudit files closed during inheritance */ - if (unlikely(file->f_path.dentry == aa_null.dentry)) - return -EACCES; - label = __begin_current_label_crit_section(&needput); - error = aa_file_perm(op, current_cred(), label, file, mask, in_atomic); - __end_current_label_crit_section(label, needput); + label = begin_current_label_crit_section(); + error = aa_file_perm(op, current_cred(), label, file, mask, false); + end_current_label_crit_section(label); return error; } static int apparmor_file_receive(struct file *file) { - return common_file_perm(OP_FRECEIVE, file, aa_map_file_to_perms(file), - false); + return common_file_perm(OP_FRECEIVE, file, aa_map_file_to_perms(file)); } static int apparmor_file_permission(struct file *file, int mask) { - return common_file_perm(OP_FPERM, file, mask, false); + return common_file_perm(OP_FPERM, file, mask); } static int apparmor_file_lock(struct file *file, unsigned int cmd) @@ -555,11 +548,11 @@ static int apparmor_file_lock(struct file *file, unsigned int cmd) if (cmd == F_WRLCK) mask |= MAY_WRITE; - return common_file_perm(OP_FLOCK, file, mask, false); + return common_file_perm(OP_FLOCK, file, mask); } static int common_mmap(const char *op, struct file *file, unsigned long prot, - unsigned long flags, bool in_atomic) + unsigned long flags) { int mask = 0; @@ -577,21 +570,20 @@ static int common_mmap(const char *op, struct file *file, unsigned long prot, if (prot & PROT_EXEC) mask |= AA_EXEC_MMAP; - return common_file_perm(op, file, mask, in_atomic); + return common_file_perm(op, file, mask); } static int apparmor_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { - return common_mmap(OP_FMMAP, file, prot, flags, GFP_ATOMIC); + return common_mmap(OP_FMMAP, file, prot, flags); } static int apparmor_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { return common_mmap(OP_FMPROT, vma->vm_file, prot, - !(vma->vm_flags & VM_SHARED) ? MAP_PRIVATE : 0, - false); + !(vma->vm_flags & VM_SHARED) ? MAP_PRIVATE : 0); } #ifdef CONFIG_IO_URING @@ -2144,7 +2136,8 @@ char *aa_get_buffer(bool in_atomic) if (!list_empty(&cache->head)) { aa_buf = list_first_entry(&cache->head, union aa_buffer, list); list_del(&aa_buf->list); - cache->hold--; + if (cache->hold) + cache->hold--; cache->count--; put_cpu_ptr(&aa_local_buffers); return &aa_buf->buffer[0]; diff --git a/security/apparmor/match.c b/security/apparmor/match.c index c5a91600842a16..bbeb3be68572f1 100644 --- a/security/apparmor/match.c +++ b/security/apparmor/match.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "include/lib.h" #include "include/match.h" @@ -42,11 +43,11 @@ static struct table_header *unpack_table(char *blob, size_t bsize) /* loaded td_id's start at 1, subtract 1 now to avoid doing * it every time we use td_id as an index */ - th.td_id = be16_to_cpu(*(__be16 *) (blob)) - 1; + th.td_id = get_unaligned_be16(blob) - 1; if (th.td_id > YYTD_ID_MAX) goto out; - th.td_flags = be16_to_cpu(*(__be16 *) (blob + 2)); - th.td_lolen = be32_to_cpu(*(__be32 *) (blob + 8)); + th.td_flags = get_unaligned_be16(blob + 2); + th.td_lolen = get_unaligned_be32(blob + 8); blob += sizeof(struct table_header); if (!(th.td_flags == YYTD_DATA16 || th.td_flags == YYTD_DATA32 || @@ -66,14 +67,13 @@ static struct table_header *unpack_table(char *blob, size_t bsize) table->td_flags = th.td_flags; table->td_lolen = th.td_lolen; if (th.td_flags == YYTD_DATA8) - UNPACK_ARRAY(table->td_data, blob, th.td_lolen, - u8, u8, byte_to_byte); + memcpy(table->td_data, blob, th.td_lolen); else if (th.td_flags == YYTD_DATA16) UNPACK_ARRAY(table->td_data, blob, th.td_lolen, - u16, __be16, be16_to_cpu); + u16, __be16, get_unaligned_be16); else if (th.td_flags == YYTD_DATA32) UNPACK_ARRAY(table->td_data, blob, th.td_lolen, - u32, __be32, be32_to_cpu); + u32, __be32, get_unaligned_be32); else goto fail; /* if table was vmalloced make sure the page tables are synced @@ -313,14 +313,14 @@ struct aa_dfa *aa_dfa_unpack(void *blob, size_t size, int flags) if (size < sizeof(struct table_set_header)) goto fail; - if (ntohl(*(__be32 *) data) != YYTH_MAGIC) + if (get_unaligned_be32(data) != YYTH_MAGIC) goto fail; - hsize = ntohl(*(__be32 *) (data + 4)); + hsize = get_unaligned_be32(data + 4); if (size < hsize) goto fail; - dfa->flags = ntohs(*(__be16 *) (data + 12)); + dfa->flags = get_unaligned_be16(data + 12); if (dfa->flags & ~(YYTH_FLAGS)) goto fail; @@ -329,7 +329,7 @@ struct aa_dfa *aa_dfa_unpack(void *blob, size_t size, int flags) * if (dfa->flags & YYTH_FLAGS_OOB_TRANS) { * if (hsize < 16 + 4) * goto fail; - * dfa->max_oob = ntol(*(__be32 *) (data + 16)); + * dfa->max_oob = get_unaligned_be32(data + 16); * if (dfa->max <= MAX_OOB_SUPPORTED) { * pr_err("AppArmor DFA OOB greater than supported\n"); * goto fail; diff --git a/security/apparmor/net.c b/security/apparmor/net.c index 45cf25605c345b..44c04102062f3d 100644 --- a/security/apparmor/net.c +++ b/security/apparmor/net.c @@ -326,8 +326,10 @@ int aa_sock_file_perm(const struct cred *subj_cred, struct aa_label *label, struct socket *sock = (struct socket *) file->private_data; AA_BUG(!label); - AA_BUG(!sock); - AA_BUG(!sock->sk); + + /* sock && sock->sk can be NULL for sockets being set up or torn down */ + if (!sock || !sock->sk) + return 0; if (sock->sk->sk_family == PF_UNIX) return aa_unix_file_perm(subj_cred, label, op, request, file); diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 7523971e37d9c0..dd602bd5fca998 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -687,8 +687,10 @@ static ssize_t unpack_perms_table(struct aa_ext *e, struct aa_perms **perms) if (!aa_unpack_array(e, NULL, &size)) goto fail_reset; *perms = kcalloc(size, sizeof(struct aa_perms), GFP_KERNEL); - if (!*perms) - goto fail_reset; + if (!*perms) { + e->pos = pos; + return -ENOMEM; + } for (i = 0; i < size; i++) { if (!unpack_perm(e, version, &(*perms)[i])) goto fail; diff --git a/security/apparmor/resource.c b/security/apparmor/resource.c index 8e80db3ae21c09..64212b39ba4bbc 100644 --- a/security/apparmor/resource.c +++ b/security/apparmor/resource.c @@ -196,6 +196,11 @@ void __aa_transition_rlimits(struct aa_label *old_l, struct aa_label *new_l) rules->rlimits.limits[j].rlim_max); /* soft limit should not exceed hard limit */ rlim->rlim_cur = min(rlim->rlim_cur, rlim->rlim_max); + if (j == RLIMIT_CPU && + rlim->rlim_cur != RLIM_INFINITY && + IS_ENABLED(CONFIG_POSIX_TIMERS)) + (void) update_rlimit_cpu(current->group_leader, + rlim->rlim_cur); } } } diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c index a5e730ffda57fb..5a8cef45bacf01 100644 --- a/security/integrity/evm/evm_crypto.c +++ b/security/integrity/evm/evm_crypto.c @@ -401,6 +401,7 @@ int evm_init_hmac(struct inode *inode, const struct xattr *xattrs, { struct shash_desc *desc; const struct xattr *xattr; + struct xattr_list *xattr_entry; desc = init_desc(EVM_XATTR_HMAC, HASH_ALGO_SHA1); if (IS_ERR(desc)) { @@ -408,11 +409,16 @@ int evm_init_hmac(struct inode *inode, const struct xattr *xattrs, return PTR_ERR(desc); } - for (xattr = xattrs; xattr->name; xattr++) { - if (!evm_protected_xattr(xattr->name)) - continue; + list_for_each_entry_lockless(xattr_entry, &evm_config_xattrnames, + list) { + for (xattr = xattrs; xattr->name; xattr++) { + if (strcmp(xattr_entry->name + + XATTR_SECURITY_PREFIX_LEN, xattr->name) != 0) + continue; - crypto_shash_update(desc, xattr->value, xattr->value_len); + crypto_shash_update(desc, xattr->value, + xattr->value_len); + } } hmac_add_misc(desc, inode, EVM_XATTR_HMAC, hmac_val); diff --git a/security/integrity/ima/ima_kexec.c b/security/integrity/ima/ima_kexec.c index 7362f68f2d8b17..5beb69edd12fd2 100644 --- a/security/integrity/ima/ima_kexec.c +++ b/security/integrity/ima/ima_kexec.c @@ -250,9 +250,7 @@ void ima_kexec_post_load(struct kimage *image) if (!image->ima_buffer_addr) return; - ima_kexec_buffer = kimage_map_segment(image, - image->ima_buffer_addr, - image->ima_buffer_size); + ima_kexec_buffer = kimage_map_segment(image, image->ima_segment_index); if (!ima_kexec_buffer) { pr_err("Could not map measurements buffer.\n"); return; diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index cdd225f65a6295..ebaebccfbe9ab1 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -573,18 +573,41 @@ static int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, */ static int ima_bprm_check(struct linux_binprm *bprm) { - int ret; struct lsm_prop prop; security_current_getlsmprop_subj(&prop); - ret = process_measurement(bprm->file, current_cred(), - &prop, NULL, 0, MAY_EXEC, BPRM_CHECK); - if (ret) - return ret; - - security_cred_getlsmprop(bprm->cred, &prop); - return process_measurement(bprm->file, bprm->cred, &prop, NULL, 0, - MAY_EXEC, CREDS_CHECK); + return process_measurement(bprm->file, current_cred(), + &prop, NULL, 0, MAY_EXEC, BPRM_CHECK); +} + +/** + * ima_creds_check - based on policy, collect/store measurement. + * @bprm: contains the linux_binprm structure + * @file: contains the file descriptor of the binary being executed + * + * The OS protects against an executable file, already open for write, + * from being executed in deny_write_access() and an executable file, + * already open for execute, from being modified in get_write_access(). + * So we can be certain that what we verify and measure here is actually + * what is being executed. + * + * The difference from ima_bprm_check() is that ima_creds_check() is invoked + * only after determining the final binary to be executed without interpreter, + * and not when searching for intermediate binaries. The reason is that since + * commit 56305aa9b6fab ("exec: Compute file based creds only once"), the + * credentials to be applied to the process are calculated only at that stage + * (bprm_creds_from_file security hook instead of bprm_check_security). + * + * On success return 0. On integrity appraisal error, assuming the file + * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. + */ +static int ima_creds_check(struct linux_binprm *bprm, const struct file *file) +{ + struct lsm_prop prop; + + security_current_getlsmprop_subj(&prop); + return process_measurement((struct file *)file, bprm->cred, &prop, NULL, + 0, MAY_EXEC, CREDS_CHECK); } /** @@ -1242,6 +1265,7 @@ static int __init init_ima(void) static struct security_hook_list ima_hooks[] __ro_after_init = { LSM_HOOK_INIT(bprm_check_security, ima_bprm_check), LSM_HOOK_INIT(bprm_creds_for_exec, ima_bprm_creds_for_exec), + LSM_HOOK_INIT(bprm_creds_from_file, ima_creds_check), LSM_HOOK_INIT(file_post_open, ima_file_check), LSM_HOOK_INIT(inode_post_create_tmpfile, ima_post_create_tmpfile), LSM_HOOK_INIT(file_release, ima_file_free), diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 128fab8979308a..db6d55af5a80b2 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -674,7 +674,7 @@ static bool ima_match_rules(struct ima_rule_entry *rule, goto retry; } } - if (!rc) { + if (rc <= 0) { result = false; goto out; } diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index 024be262702fed..74cea80ed9be5e 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -283,7 +283,10 @@ int tpm2_seal_trusted(struct tpm_chip *chip, goto out_put; } - tpm_buf_append_name(chip, &buf, options->keyhandle, NULL); + rc = tpm_buf_append_name(chip, &buf, options->keyhandle, NULL); + if (rc) + goto out; + tpm_buf_append_hmac_session(chip, &buf, TPM2_SA_DECRYPT, options->keyauth, TPM_DIGEST_SIZE); @@ -331,7 +334,10 @@ int tpm2_seal_trusted(struct tpm_chip *chip, goto out; } - tpm_buf_fill_hmac_session(chip, &buf); + rc = tpm_buf_fill_hmac_session(chip, &buf); + if (rc) + goto out; + rc = tpm_transmit_cmd(chip, &buf, 4, "sealing data"); rc = tpm_buf_check_hmac_response(chip, &buf, rc); if (rc) @@ -387,6 +393,7 @@ static int tpm2_load_cmd(struct tpm_chip *chip, struct trusted_key_options *options, u32 *blob_handle) { + u8 *blob_ref __free(kfree) = NULL; struct tpm_buf buf; unsigned int private_len; unsigned int public_len; @@ -400,6 +407,9 @@ static int tpm2_load_cmd(struct tpm_chip *chip, /* old form */ blob = payload->blob; payload->old_format = 1; + } else { + /* Bind for cleanup: */ + blob_ref = blob; } /* new format carries keyhandle but old format doesn't */ @@ -444,7 +454,10 @@ static int tpm2_load_cmd(struct tpm_chip *chip, return rc; } - tpm_buf_append_name(chip, &buf, options->keyhandle, NULL); + rc = tpm_buf_append_name(chip, &buf, options->keyhandle, NULL); + if (rc) + goto out; + tpm_buf_append_hmac_session(chip, &buf, 0, options->keyauth, TPM_DIGEST_SIZE); @@ -456,7 +469,10 @@ static int tpm2_load_cmd(struct tpm_chip *chip, goto out; } - tpm_buf_fill_hmac_session(chip, &buf); + rc = tpm_buf_fill_hmac_session(chip, &buf); + if (rc) + goto out; + rc = tpm_transmit_cmd(chip, &buf, 4, "loading blob"); rc = tpm_buf_check_hmac_response(chip, &buf, rc); if (!rc) @@ -464,8 +480,6 @@ static int tpm2_load_cmd(struct tpm_chip *chip, (__be32 *) &buf.data[TPM_HEADER_SIZE]); out: - if (blob != payload->blob) - kfree(blob); tpm_buf_destroy(&buf); if (rc > 0) @@ -475,7 +489,7 @@ static int tpm2_load_cmd(struct tpm_chip *chip, } /** - * tpm2_unseal_cmd() - execute a TPM2_Unload command + * tpm2_unseal_cmd() - execute a TPM2_Unseal command * * @chip: TPM chip to use * @payload: the key data in clear and encrypted form @@ -506,7 +520,9 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip, return rc; } - tpm_buf_append_name(chip, &buf, blob_handle, NULL); + rc = tpm_buf_append_name(chip, &buf, blob_handle, NULL); + if (rc) + goto out; if (!options->policyhandle) { tpm_buf_append_hmac_session(chip, &buf, TPM2_SA_ENCRYPT, @@ -531,7 +547,10 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip, NULL, 0); } - tpm_buf_fill_hmac_session(chip, &buf); + rc = tpm_buf_fill_hmac_session(chip, &buf); + if (rc) + goto out; + rc = tpm_transmit_cmd(chip, &buf, 6, "unsealing"); rc = tpm_buf_check_hmac_response(chip, &buf, rc); if (rc > 0) diff --git a/security/landlock/audit.c b/security/landlock/audit.c index c52d079cdb77ba..e899995f1fd595 100644 --- a/security/landlock/audit.c +++ b/security/landlock/audit.c @@ -191,7 +191,7 @@ static size_t get_denied_layer(const struct landlock_ruleset *const domain, long youngest_layer = -1; for_each_set_bit(access_bit, &access_req, layer_masks_size) { - const access_mask_t mask = (*layer_masks)[access_bit]; + const layer_mask_t mask = (*layer_masks)[access_bit]; long layer; if (!mask) diff --git a/security/landlock/errata/abi-1.h b/security/landlock/errata/abi-1.h new file mode 100644 index 00000000000000..e8a2bff2e5b6a8 --- /dev/null +++ b/security/landlock/errata/abi-1.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +/** + * DOC: erratum_3 + * + * Erratum 3: Disconnected directory handling + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * This fix addresses an issue with disconnected directories that occur when a + * directory is moved outside the scope of a bind mount. The change ensures + * that evaluated access rights include both those from the disconnected file + * hierarchy down to its filesystem root and those from the related mount point + * hierarchy. This prevents access right widening through rename or link + * actions. + */ +LANDLOCK_ERRATUM(3) diff --git a/security/landlock/fs.c b/security/landlock/fs.c index d9c12b993fa7dd..a2ed0e76938aa1 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -909,21 +909,31 @@ static bool is_access_to_paths_allowed( break; } } + if (unlikely(IS_ROOT(walker_path.dentry))) { - /* - * Stops at disconnected root directories. Only allows - * access to internal filesystems (e.g. nsfs, which is - * reachable through /proc//ns/). - */ - if (walker_path.mnt->mnt_flags & MNT_INTERNAL) { + if (likely(walker_path.mnt->mnt_flags & MNT_INTERNAL)) { + /* + * Stops and allows access when reaching disconnected root + * directories that are part of internal filesystems (e.g. nsfs, + * which is reachable through /proc//ns/). + */ allowed_parent1 = true; allowed_parent2 = true; + break; } - break; + + /* + * We reached a disconnected root directory from a bind mount. + * Let's continue the walk with the mount point we missed. + */ + dput(walker_path.dentry); + walker_path.dentry = walker_path.mnt->mnt_root; + dget(walker_path.dentry); + } else { + parent_dentry = dget_parent(walker_path.dentry); + dput(walker_path.dentry); + walker_path.dentry = parent_dentry; } - parent_dentry = dget_parent(walker_path.dentry); - dput(walker_path.dentry); - walker_path.dentry = parent_dentry; } path_put(&walker_path); @@ -1021,6 +1031,9 @@ static access_mask_t maybe_remove(const struct dentry *const dentry) * file. While walking from @dir to @mnt_root, we record all the domain's * allowed accesses in @layer_masks_dom. * + * Because of disconnected directories, this walk may not reach @mnt_dir. In + * this case, the walk will continue to @mnt_dir after this call. + * * This is similar to is_access_to_paths_allowed() but much simpler because it * only handles walking on the same mount point and only checks one set of * accesses. @@ -1062,8 +1075,11 @@ static bool collect_domain_accesses( break; } - /* We should not reach a root other than @mnt_root. */ - if (dir == mnt_root || WARN_ON_ONCE(IS_ROOT(dir))) + /* + * Stops at the mount point or the filesystem root for a disconnected + * directory. + */ + if (dir == mnt_root || unlikely(IS_ROOT(dir))) break; parent_dentry = dget_parent(dir); diff --git a/security/landlock/net.c b/security/landlock/net.c index 1f3915a90a808b..e6367e30e5b0ec 100644 --- a/security/landlock/net.c +++ b/security/landlock/net.c @@ -71,6 +71,61 @@ static int current_check_access_socket(struct socket *const sock, switch (address->sa_family) { case AF_UNSPEC: + if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP) { + /* + * Connecting to an address with AF_UNSPEC dissolves + * the TCP association, which have the same effect as + * closing the connection while retaining the socket + * object (i.e., the file descriptor). As for dropping + * privileges, closing connections is always allowed. + * + * For a TCP access control system, this request is + * legitimate. Let the network stack handle potential + * inconsistencies and return -EINVAL if needed. + */ + return 0; + } else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP) { + /* + * Binding to an AF_UNSPEC address is treated + * differently by IPv4 and IPv6 sockets. The socket's + * family may change under our feet due to + * setsockopt(IPV6_ADDRFORM), but that's ok: we either + * reject entirely or require + * %LANDLOCK_ACCESS_NET_BIND_TCP for the given port, so + * it cannot be used to bypass the policy. + * + * IPv4 sockets map AF_UNSPEC to AF_INET for + * retrocompatibility for bind accesses, only if the + * address is INADDR_ANY (cf. __inet_bind). IPv6 + * sockets always reject it. + * + * Checking the address is required to not wrongfully + * return -EACCES instead of -EAFNOSUPPORT or -EINVAL. + * We could return 0 and let the network stack handle + * these checks, but it is safer to return a proper + * error and test consistency thanks to kselftest. + */ + if (sock->sk->__sk_common.skc_family == AF_INET) { + const struct sockaddr_in *const sockaddr = + (struct sockaddr_in *)address; + + if (addrlen < sizeof(struct sockaddr_in)) + return -EINVAL; + + if (sockaddr->sin_addr.s_addr != + htonl(INADDR_ANY)) + return -EAFNOSUPPORT; + } else { + if (addrlen < SIN6_LEN_RFC2133) + return -EINVAL; + else + return -EAFNOSUPPORT; + } + } else { + WARN_ON_ONCE(1); + } + /* Only for bind(AF_UNSPEC+INADDR_ANY) on IPv4 socket. */ + fallthrough; case AF_INET: { const struct sockaddr_in *addr4; @@ -119,57 +174,18 @@ static int current_check_access_socket(struct socket *const sock, return 0; } - /* Specific AF_UNSPEC handling. */ - if (address->sa_family == AF_UNSPEC) { - /* - * Connecting to an address with AF_UNSPEC dissolves the TCP - * association, which have the same effect as closing the - * connection while retaining the socket object (i.e., the file - * descriptor). As for dropping privileges, closing - * connections is always allowed. - * - * For a TCP access control system, this request is legitimate. - * Let the network stack handle potential inconsistencies and - * return -EINVAL if needed. - */ - if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP) - return 0; - - /* - * For compatibility reason, accept AF_UNSPEC for bind - * accesses (mapped to AF_INET) only if the address is - * INADDR_ANY (cf. __inet_bind). Checking the address is - * required to not wrongfully return -EACCES instead of - * -EAFNOSUPPORT. - * - * We could return 0 and let the network stack handle these - * checks, but it is safer to return a proper error and test - * consistency thanks to kselftest. - */ - if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP) { - /* addrlen has already been checked for AF_UNSPEC. */ - const struct sockaddr_in *const sockaddr = - (struct sockaddr_in *)address; - - if (sock->sk->__sk_common.skc_family != AF_INET) - return -EINVAL; - - if (sockaddr->sin_addr.s_addr != htonl(INADDR_ANY)) - return -EAFNOSUPPORT; - } - } else { - /* - * Checks sa_family consistency to not wrongfully return - * -EACCES instead of -EINVAL. Valid sa_family changes are - * only (from AF_INET or AF_INET6) to AF_UNSPEC. - * - * We could return 0 and let the network stack handle this - * check, but it is safer to return a proper error and test - * consistency thanks to kselftest. - */ - if (address->sa_family != sock->sk->__sk_common.skc_family) - return -EINVAL; - } + /* + * Checks sa_family consistency to not wrongfully return + * -EACCES instead of -EINVAL. Valid sa_family changes are + * only (from AF_INET or AF_INET6) to AF_UNSPEC. + * + * We could return 0 and let the network stack handle this + * check, but it is safer to return a proper error and test + * consistency thanks to kselftest. + */ + if (address->sa_family != sock->sk->__sk_common.skc_family && + address->sa_family != AF_UNSPEC) + return -EINVAL; id.key.data = (__force uintptr_t)port; BUILD_BUG_ON(sizeof(port) > sizeof(id.key.data)); diff --git a/security/smack/smack.h b/security/smack/smack.h index bf6a6ed3946cec..759343a6bbaeb0 100644 --- a/security/smack/smack.h +++ b/security/smack/smack.h @@ -286,9 +286,12 @@ int smk_tskacc(struct task_smack *, struct smack_known *, int smk_curacc(struct smack_known *, u32, struct smk_audit_info *); int smack_str_from_perm(char *string, int access); struct smack_known *smack_from_secid(const u32); +int smk_parse_label_len(const char *string, int len); char *smk_parse_smack(const char *string, int len); int smk_netlbl_mls(int, char *, struct netlbl_lsm_secattr *, int); struct smack_known *smk_import_entry(const char *, int); +struct smack_known *smk_import_valid_label(const char *label, int label_len, + gfp_t gfp); void smk_insert_entry(struct smack_known *skp); struct smack_known *smk_find_entry(const char *); bool smack_privileged(int cap); diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c index 2e4a0cb22782b4..a289cb6672bd42 100644 --- a/security/smack/smack_access.c +++ b/security/smack/smack_access.c @@ -443,19 +443,19 @@ struct smack_known *smk_find_entry(const char *string) } /** - * smk_parse_smack - parse smack label from a text string - * @string: a text string that might contain a Smack label - * @len: the maximum size, or zero if it is NULL terminated. + * smk_parse_label_len - calculate the length of the starting segment + * in the string that constitutes a valid smack label + * @string: a text string that might contain a Smack label at the beginning + * @len: the maximum size to look into, may be zero if string is null-terminated * - * Returns a pointer to the clean label or an error code. + * Returns the length of the segment (0 < L < SMK_LONGLABEL) or an error code. */ -char *smk_parse_smack(const char *string, int len) +int smk_parse_label_len(const char *string, int len) { - char *smack; int i; - if (len <= 0) - len = strlen(string) + 1; + if (len <= 0 || len > SMK_LONGLABEL) + len = SMK_LONGLABEL; /* * Reserve a leading '-' as an indicator that @@ -463,7 +463,7 @@ char *smk_parse_smack(const char *string, int len) * including /smack/cipso and /smack/cipso2 */ if (string[0] == '-') - return ERR_PTR(-EINVAL); + return -EINVAL; for (i = 0; i < len; i++) if (string[i] > '~' || string[i] <= ' ' || string[i] == '/' || @@ -471,6 +471,25 @@ char *smk_parse_smack(const char *string, int len) break; if (i == 0 || i >= SMK_LONGLABEL) + return -EINVAL; + + return i; +} + +/** + * smk_parse_smack - copy the starting segment in the string + * that constitutes a valid smack label + * @string: a text string that might contain a Smack label at the beginning + * @len: the maximum size to look into, may be zero if string is null-terminated + * + * Returns a pointer to the copy of the label or an error code. + */ +char *smk_parse_smack(const char *string, int len) +{ + char *smack; + int i = smk_parse_label_len(string, len); + + if (i < 0) return ERR_PTR(-EINVAL); smack = kstrndup(string, i, GFP_NOFS); @@ -554,31 +573,25 @@ int smack_populate_secattr(struct smack_known *skp) } /** - * smk_import_entry - import a label, return the list entry - * @string: a text string that might be a Smack label - * @len: the maximum size, or zero if it is NULL terminated. + * smk_import_valid_allocated_label - import a label, return the list entry + * @smack: a text string that is a valid Smack label and may be kfree()ed. + * It is consumed: either becomes a part of the entry or kfree'ed. * - * Returns a pointer to the entry in the label list that - * matches the passed string, adding it if necessary, - * or an error code. + * Returns: see description of smk_import_entry() */ -struct smack_known *smk_import_entry(const char *string, int len) +static struct smack_known * +smk_import_allocated_label(char *smack, gfp_t gfp) { struct smack_known *skp; - char *smack; int rc; - smack = smk_parse_smack(string, len); - if (IS_ERR(smack)) - return ERR_CAST(smack); - mutex_lock(&smack_known_lock); skp = smk_find_entry(smack); if (skp != NULL) goto freeout; - skp = kzalloc(sizeof(*skp), GFP_NOFS); + skp = kzalloc(sizeof(*skp), gfp); if (skp == NULL) { skp = ERR_PTR(-ENOMEM); goto freeout; @@ -608,6 +621,42 @@ struct smack_known *smk_import_entry(const char *string, int len) return skp; } +/** + * smk_import_entry - import a label, return the list entry + * @string: a text string that might contain a Smack label at the beginning + * @len: the maximum size to look into, may be zero if string is null-terminated + * + * Returns a pointer to the entry in the label list that + * matches the passed string, adding it if necessary, + * or an error code. + */ +struct smack_known *smk_import_entry(const char *string, int len) +{ + char *smack = smk_parse_smack(string, len); + + if (IS_ERR(smack)) + return ERR_CAST(smack); + + return smk_import_allocated_label(smack, GFP_NOFS); +} + +/** + * smk_import_valid_label - import a label, return the list entry + * @label a text string that is a valid Smack label, not null-terminated + * + * Returns: see description of smk_import_entry() + */ +struct smack_known * +smk_import_valid_label(const char *label, int label_len, gfp_t gfp) +{ + char *smack = kstrndup(label, label_len, gfp); + + if (!smack) + return ERR_PTR(-ENOMEM); + + return smk_import_allocated_label(smack, gfp); +} + /** * smack_from_secid - find the Smack label associated with a secid * @secid: an integer that might be associated with a Smack label diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index af986587841d8c..7fd8a60b8be908 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -962,6 +962,42 @@ static int smack_inode_alloc_security(struct inode *inode) return 0; } +/** + * smk_rule_transmutes - does access rule for (subject,object) contain 't'? + * @subject: a pointer to the subject's Smack label entry + * @object: a pointer to the object's Smack label entry + */ +static bool +smk_rule_transmutes(struct smack_known *subject, + const struct smack_known *object) +{ + int may; + + rcu_read_lock(); + may = smk_access_entry(subject->smk_known, object->smk_known, + &subject->smk_rules); + rcu_read_unlock(); + return (may > 0) && (may & MAY_TRANSMUTE); +} + +static int +xattr_dupval(struct xattr *xattrs, int *xattr_count, + const char *name, const void *value, unsigned int vallen) +{ + struct xattr * const xattr = lsm_get_xattr_slot(xattrs, xattr_count); + + if (!xattr) + return 0; + + xattr->value = kmemdup(value, vallen, GFP_NOFS); + if (!xattr->value) + return -ENOMEM; + + xattr->value_len = vallen; + xattr->name = name; + return 0; +} + /** * smack_inode_init_security - copy out the smack from an inode * @inode: the newly created inode @@ -977,23 +1013,30 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir, struct xattr *xattrs, int *xattr_count) { struct task_smack *tsp = smack_cred(current_cred()); - struct inode_smack *issp = smack_inode(inode); - struct smack_known *skp = smk_of_task(tsp); - struct smack_known *isp = smk_of_inode(inode); + struct inode_smack * const issp = smack_inode(inode); struct smack_known *dsp = smk_of_inode(dir); - struct xattr *xattr = lsm_get_xattr_slot(xattrs, xattr_count); - int may; + int rc = 0; + int transflag = 0; + bool trans_cred; + bool trans_rule; + /* + * UNIX domain sockets use lower level socket data. Let + * UDS inode have fixed * label to keep smack_inode_permission() calm + * when called from unix_find_bsd() + */ + if (S_ISSOCK(inode->i_mode)) { + /* forced label, no need to save to xattrs */ + issp->smk_inode = &smack_known_star; + goto instant_inode; + } /* * If equal, transmuting already occurred in * smack_dentry_create_files_as(). No need to check again. */ - if (tsp->smk_task != tsp->smk_transmuted) { - rcu_read_lock(); - may = smk_access_entry(skp->smk_known, dsp->smk_known, - &skp->smk_rules); - rcu_read_unlock(); - } + trans_cred = (tsp->smk_task == tsp->smk_transmuted); + if (!trans_cred) + trans_rule = smk_rule_transmutes(smk_of_task(tsp), dsp); /* * In addition to having smk_task equal to smk_transmuted, @@ -1001,47 +1044,38 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir, * requests transmutation then by all means transmute. * Mark the inode as changed. */ - if ((tsp->smk_task == tsp->smk_transmuted) || - (may > 0 && ((may & MAY_TRANSMUTE) != 0) && - smk_inode_transmutable(dir))) { - struct xattr *xattr_transmute; - + if (trans_cred || (trans_rule && smk_inode_transmutable(dir))) { /* * The caller of smack_dentry_create_files_as() * should have overridden the current cred, so the * inode label was already set correctly in * smack_inode_alloc_security(). */ - if (tsp->smk_task != tsp->smk_transmuted) - isp = issp->smk_inode = dsp; - - issp->smk_flags |= SMK_INODE_TRANSMUTE; - xattr_transmute = lsm_get_xattr_slot(xattrs, - xattr_count); - if (xattr_transmute) { - xattr_transmute->value = kmemdup(TRANS_TRUE, - TRANS_TRUE_SIZE, - GFP_NOFS); - if (!xattr_transmute->value) - return -ENOMEM; + if (!trans_cred) + issp->smk_inode = dsp; - xattr_transmute->value_len = TRANS_TRUE_SIZE; - xattr_transmute->name = XATTR_SMACK_TRANSMUTE; + if (S_ISDIR(inode->i_mode)) { + transflag = SMK_INODE_TRANSMUTE; + + if (xattr_dupval(xattrs, xattr_count, + XATTR_SMACK_TRANSMUTE, + TRANS_TRUE, + TRANS_TRUE_SIZE + )) + rc = -ENOMEM; } } - issp->smk_flags |= SMK_INODE_INSTANT; - - if (xattr) { - xattr->value = kstrdup(isp->smk_known, GFP_NOFS); - if (!xattr->value) - return -ENOMEM; - - xattr->value_len = strlen(isp->smk_known); - xattr->name = XATTR_SMACK_SUFFIX; - } - - return 0; + if (rc == 0) + if (xattr_dupval(xattrs, xattr_count, + XATTR_SMACK_SUFFIX, + issp->smk_inode->smk_known, + strlen(issp->smk_inode->smk_known) + )) + rc = -ENOMEM; +instant_inode: + issp->smk_flags |= (SMK_INODE_INSTANT | transflag); + return rc; } /** @@ -1315,13 +1349,23 @@ static int smack_inode_setxattr(struct mnt_idmap *idmap, int check_import = 0; int check_star = 0; int rc = 0; + umode_t const i_mode = d_backing_inode(dentry)->i_mode; /* * Check label validity here so import won't fail in post_setxattr */ - if (strcmp(name, XATTR_NAME_SMACK) == 0 || - strcmp(name, XATTR_NAME_SMACKIPIN) == 0 || - strcmp(name, XATTR_NAME_SMACKIPOUT) == 0) { + if (strcmp(name, XATTR_NAME_SMACK) == 0) { + /* + * UDS inode has fixed label + */ + if (S_ISSOCK(i_mode)) { + rc = -EINVAL; + } else { + check_priv = 1; + check_import = 1; + } + } else if (strcmp(name, XATTR_NAME_SMACKIPIN) == 0 || + strcmp(name, XATTR_NAME_SMACKIPOUT) == 0) { check_priv = 1; check_import = 1; } else if (strcmp(name, XATTR_NAME_SMACKEXEC) == 0 || @@ -1331,7 +1375,7 @@ static int smack_inode_setxattr(struct mnt_idmap *idmap, check_star = 1; } else if (strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0) { check_priv = 1; - if (!S_ISDIR(d_backing_inode(dentry)->i_mode) || + if (!S_ISDIR(i_mode) || size != TRANS_TRUE_SIZE || strncmp(value, TRANS_TRUE, TRANS_TRUE_SIZE) != 0) rc = -EINVAL; @@ -1462,12 +1506,15 @@ static int smack_inode_removexattr(struct mnt_idmap *idmap, * Don't do anything special for these. * XATTR_NAME_SMACKIPIN * XATTR_NAME_SMACKIPOUT + * XATTR_NAME_SMACK if S_ISSOCK (UDS inode has fixed label) */ if (strcmp(name, XATTR_NAME_SMACK) == 0) { - struct super_block *sbp = dentry->d_sb; - struct superblock_smack *sbsp = smack_superblock(sbp); + if (!S_ISSOCK(d_backing_inode(dentry)->i_mode)) { + struct super_block *sbp = dentry->d_sb; + struct superblock_smack *sbsp = smack_superblock(sbp); - isp->smk_inode = sbsp->smk_default; + isp->smk_inode = sbsp->smk_default; + } } else if (strcmp(name, XATTR_NAME_SMACKEXEC) == 0) isp->smk_task = NULL; else if (strcmp(name, XATTR_NAME_SMACKMMAP) == 0) @@ -3585,7 +3632,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode) */ /* - * UNIX domain sockets use lower level socket data. + * UDS inode has fixed label (*) */ if (S_ISSOCK(inode->i_mode)) { final = &smack_known_star; @@ -3663,7 +3710,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode) * @attr: which attribute to fetch * @ctx: buffer to receive the result * @size: available size in, actual size out - * @flags: unused + * @flags: reserved, currently zero * * Fill the passed user space @ctx with the details of the requested * attribute. @@ -3724,47 +3771,55 @@ static int smack_getprocattr(struct task_struct *p, const char *name, char **val * Sets the Smack value of the task. Only setting self * is permitted and only with privilege * - * Returns the length of the smack label or an error code + * Returns zero on success or an error code */ -static int do_setattr(u64 attr, void *value, size_t size) +static int do_setattr(unsigned int attr, void *value, size_t size) { struct task_smack *tsp = smack_cred(current_cred()); struct cred *new; struct smack_known *skp; - struct smack_known_list_elem *sklep; - int rc; - - if (!smack_privileged(CAP_MAC_ADMIN) && list_empty(&tsp->smk_relabel)) - return -EPERM; + int label_len; + /* + * let unprivileged user validate input, check permissions later + */ if (value == NULL || size == 0 || size >= SMK_LONGLABEL) return -EINVAL; - if (attr != LSM_ATTR_CURRENT) - return -EOPNOTSUPP; - - skp = smk_import_entry(value, size); - if (IS_ERR(skp)) - return PTR_ERR(skp); + label_len = smk_parse_label_len(value, size); + if (label_len < 0 || label_len != size) + return -EINVAL; /* * No process is ever allowed the web ("@") label * and the star ("*") label. */ - if (skp == &smack_known_web || skp == &smack_known_star) - return -EINVAL; + if (label_len == 1 /* '@', '*' */) { + const char c = *(const char *)value; + + if (c == *smack_known_web.smk_known || + c == *smack_known_star.smk_known) + return -EPERM; + } if (!smack_privileged(CAP_MAC_ADMIN)) { - rc = -EPERM; - list_for_each_entry(sklep, &tsp->smk_relabel, list) - if (sklep->smk_label == skp) { - rc = 0; - break; - } - if (rc) - return rc; + const struct smack_known_list_elem *sklep; + list_for_each_entry(sklep, &tsp->smk_relabel, list) { + const char *cp = sklep->smk_label->smk_known; + + if (strlen(cp) == label_len && + strncmp(cp, value, label_len) == 0) + goto in_relabel; + } + return -EPERM; +in_relabel: + ; } + skp = smk_import_valid_label(value, label_len, GFP_KERNEL); + if (IS_ERR(skp)) + return PTR_ERR(skp); + new = prepare_creds(); if (new == NULL) return -ENOMEM; @@ -3777,7 +3832,7 @@ static int do_setattr(u64 attr, void *value, size_t size) smk_destroy_label_list(&tsp->smk_relabel); commit_creds(new); - return size; + return 0; } /** @@ -3785,7 +3840,7 @@ static int do_setattr(u64 attr, void *value, size_t size) * @attr: which attribute to set * @ctx: buffer containing the data * @size: size of @ctx - * @flags: unused + * @flags: reserved, must be zero * * Fill the passed user space @ctx with the details of the requested * attribute. @@ -3795,12 +3850,26 @@ static int do_setattr(u64 attr, void *value, size_t size) static int smack_setselfattr(unsigned int attr, struct lsm_ctx *ctx, u32 size, u32 flags) { - int rc; + if (attr != LSM_ATTR_CURRENT) + return -EOPNOTSUPP; - rc = do_setattr(attr, ctx->ctx, ctx->ctx_len); - if (rc > 0) - return 0; - return rc; + if (ctx->flags) + return -EINVAL; + /* + * string must have \0 terminator, included in ctx->ctx + * (see description of struct lsm_ctx) + */ + if (ctx->ctx_len == 0) + return -EINVAL; + + if (ctx->ctx[ctx->ctx_len - 1] != '\0') + return -EINVAL; + /* + * other do_setattr() caller, smack_setprocattr(), + * does not count \0 into size, so + * decreasing length by 1 to accommodate the divergence. + */ + return do_setattr(attr, ctx->ctx, ctx->ctx_len - 1); } /** @@ -3812,15 +3881,39 @@ static int smack_setselfattr(unsigned int attr, struct lsm_ctx *ctx, * Sets the Smack value of the task. Only setting self * is permitted and only with privilege * - * Returns the length of the smack label or an error code + * Returns the size of the input value or an error code */ static int smack_setprocattr(const char *name, void *value, size_t size) { - int attr = lsm_name_to_attr(name); + size_t realsize = size; + unsigned int attr = lsm_name_to_attr(name); - if (attr != LSM_ATTR_UNDEF) - return do_setattr(attr, value, size); - return -EINVAL; + switch (attr) { + case LSM_ATTR_UNDEF: return -EINVAL; + default: return -EOPNOTSUPP; + case LSM_ATTR_CURRENT: + ; + } + + /* + * The value for the "current" attribute is the label + * followed by one of the 4 trailers: none, \0, \n, \n\0 + * + * I.e. following inputs are accepted as 3-characters long label "foo": + * + * "foo" (3 characters) + * "foo\0" (4 characters) + * "foo\n" (4 characters) + * "foo\n\0" (5 characters) + */ + + if (realsize && (((const char *)value)[realsize - 1] == '\0')) + --realsize; + + if (realsize && (((const char *)value)[realsize - 1] == '\n')) + --realsize; + + return do_setattr(attr, value, realsize) ? : size; } /** @@ -4850,6 +4943,11 @@ static int smack_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) static int smack_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { + /* + * UDS inode has fixed label. Ignore nfs label. + */ + if (S_ISSOCK(inode->i_mode)) + return 0; return smack_inode_setsecurity(inode, XATTR_SMACK_SUFFIX, ctx, ctxlen, 0); } @@ -4915,7 +5013,6 @@ static int smack_dentry_create_files_as(struct dentry *dentry, int mode, struct task_smack *otsp = smack_cred(old); struct task_smack *ntsp = smack_cred(new); struct inode_smack *isp; - int may; /* * Use the process credential unless all of @@ -4929,18 +5026,12 @@ static int smack_dentry_create_files_as(struct dentry *dentry, int mode, isp = smack_inode(d_inode(dentry->d_parent)); if (isp->smk_flags & SMK_INODE_TRANSMUTE) { - rcu_read_lock(); - may = smk_access_entry(otsp->smk_task->smk_known, - isp->smk_inode->smk_known, - &otsp->smk_task->smk_rules); - rcu_read_unlock(); - /* * If the directory is transmuting and the rule * providing access is transmuting use the containing * directory label instead of the process label. */ - if (may > 0 && (may & MAY_TRANSMUTE)) { + if (smk_rule_transmutes(otsp->smk_task, isp->smk_inode)) { ntsp->smk_task = isp->smk_inode; ntsp->smk_transmuted = ntsp->smk_task; } diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index b1e5e62f5cbd1f..d27d9140dda2f3 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -70,6 +70,7 @@ enum smk_inos { static DEFINE_MUTEX(smack_cipso_lock); static DEFINE_MUTEX(smack_ambient_lock); static DEFINE_MUTEX(smk_net4addr_lock); +static DEFINE_MUTEX(smk_cipso_doi_lock); #if IS_ENABLED(CONFIG_IPV6) static DEFINE_MUTEX(smk_net6addr_lock); #endif /* CONFIG_IPV6 */ @@ -141,7 +142,7 @@ struct smack_parsed_rule { int smk_access2; }; -static int smk_cipso_doi_value = SMACK_CIPSO_DOI_DEFAULT; +static u32 smk_cipso_doi_value = CIPSO_V4_DOI_UNKNOWN; /* * Values for parsing cipso rules @@ -663,43 +664,60 @@ static const struct file_operations smk_load_ops = { }; /** - * smk_cipso_doi - initialize the CIPSO domain + * smk_cipso_doi - set netlabel maps + * @ndoi: new value for our CIPSO DOI + * @gfp_flags: kmalloc allocation context */ -static void smk_cipso_doi(void) +static int +smk_cipso_doi(u32 ndoi, gfp_t gfp_flags) { - int rc; + int rc = 0; struct cipso_v4_doi *doip; struct netlbl_audit nai; - smk_netlabel_audit_set(&nai); + mutex_lock(&smk_cipso_doi_lock); - rc = netlbl_cfg_map_del(NULL, PF_INET, NULL, NULL, &nai); - if (rc != 0) - printk(KERN_WARNING "%s:%d remove rc = %d\n", - __func__, __LINE__, rc); + if (smk_cipso_doi_value == ndoi) + goto clr_doi_lock; + + smk_netlabel_audit_set(&nai); - doip = kmalloc(sizeof(struct cipso_v4_doi), GFP_KERNEL | __GFP_NOFAIL); + doip = kmalloc(sizeof(struct cipso_v4_doi), gfp_flags); + if (!doip) { + rc = -ENOMEM; + goto clr_doi_lock; + } doip->map.std = NULL; - doip->doi = smk_cipso_doi_value; + doip->doi = ndoi; doip->type = CIPSO_V4_MAP_PASS; doip->tags[0] = CIPSO_V4_TAG_RBITMAP; for (rc = 1; rc < CIPSO_V4_TAG_MAXCNT; rc++) doip->tags[rc] = CIPSO_V4_TAG_INVALID; rc = netlbl_cfg_cipsov4_add(doip, &nai); - if (rc != 0) { - printk(KERN_WARNING "%s:%d cipso add rc = %d\n", - __func__, __LINE__, rc); + if (rc) { kfree(doip); - return; + goto clr_doi_lock; } - rc = netlbl_cfg_cipsov4_map_add(doip->doi, NULL, NULL, NULL, &nai); - if (rc != 0) { - printk(KERN_WARNING "%s:%d map add rc = %d\n", - __func__, __LINE__, rc); - netlbl_cfg_cipsov4_del(doip->doi, &nai); - return; + + if (smk_cipso_doi_value != CIPSO_V4_DOI_UNKNOWN) { + rc = netlbl_cfg_map_del(NULL, PF_INET, NULL, NULL, &nai); + if (rc && rc != -ENOENT) + goto clr_ndoi_def; + + netlbl_cfg_cipsov4_del(smk_cipso_doi_value, &nai); } + + rc = netlbl_cfg_cipsov4_map_add(ndoi, NULL, NULL, NULL, &nai); + if (rc) { + smk_cipso_doi_value = CIPSO_V4_DOI_UNKNOWN; // no default map +clr_ndoi_def: netlbl_cfg_cipsov4_del(ndoi, &nai); + } else + smk_cipso_doi_value = ndoi; + +clr_doi_lock: + mutex_unlock(&smk_cipso_doi_lock); + return rc; } /** @@ -1562,7 +1580,7 @@ static ssize_t smk_read_doi(struct file *filp, char __user *buf, if (*ppos != 0) return 0; - sprintf(temp, "%d", smk_cipso_doi_value); + sprintf(temp, "%lu", (unsigned long)smk_cipso_doi_value); rc = simple_read_from_buffer(buf, count, ppos, temp, strlen(temp)); return rc; @@ -1581,7 +1599,7 @@ static ssize_t smk_write_doi(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char temp[80]; - int i; + unsigned long u; if (!smack_privileged(CAP_MAC_ADMIN)) return -EPERM; @@ -1594,14 +1612,13 @@ static ssize_t smk_write_doi(struct file *file, const char __user *buf, temp[count] = '\0'; - if (sscanf(temp, "%d", &i) != 1) + if (kstrtoul(temp, 10, &u)) return -EINVAL; - smk_cipso_doi_value = i; - - smk_cipso_doi(); + if (u == CIPSO_V4_DOI_UNKNOWN || u > U32_MAX) + return -EINVAL; - return count; + return smk_cipso_doi(u, GFP_KERNEL) ? : count; } static const struct file_operations smk_doi_ops = { @@ -2982,6 +2999,7 @@ static int __init init_smk_fs(void) { int err; int rc; + struct netlbl_audit nai; if (smack_enabled == 0) return 0; @@ -3000,7 +3018,10 @@ static int __init init_smk_fs(void) } } - smk_cipso_doi(); + smk_netlabel_audit_set(&nai); + (void) netlbl_cfg_map_del(NULL, PF_INET, NULL, NULL, &nai); + (void) smk_cipso_doi(SMACK_CIPSO_DOI_DEFAULT, + GFP_KERNEL | __GFP_NOFAIL); smk_unlbl_ambient(NULL); rc = smack_populate_secattr(&smack_known_floor); diff --git a/sound/ac97/bus.c b/sound/ac97/bus.c index f4254703d29f75..bb9b795e022626 100644 --- a/sound/ac97/bus.c +++ b/sound/ac97/bus.c @@ -298,6 +298,7 @@ static void ac97_adapter_release(struct device *dev) idr_remove(&ac97_adapter_idr, ac97_ctrl->nr); dev_dbg(&ac97_ctrl->adap, "adapter unregistered by %s\n", dev_name(ac97_ctrl->parent)); + kfree(ac97_ctrl); } static const struct device_type ac97_adapter_type = { @@ -319,7 +320,9 @@ static int ac97_add_adapter(struct ac97_controller *ac97_ctrl) ret = device_register(&ac97_ctrl->adap); if (ret) put_device(&ac97_ctrl->adap); - } + } else + kfree(ac97_ctrl); + if (!ret) { list_add(&ac97_ctrl->controllers, &ac97_controllers); dev_dbg(&ac97_ctrl->adap, "adapter registered by %s\n", @@ -361,14 +364,11 @@ struct ac97_controller *snd_ac97_controller_register( ret = ac97_add_adapter(ac97_ctrl); if (ret) - goto err; + return ERR_PTR(ret); ac97_bus_reset(ac97_ctrl); ac97_bus_scan(ac97_ctrl); return ac97_ctrl; -err: - kfree(ac97_ctrl); - return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(snd_ac97_controller_register); diff --git a/sound/core/control.c b/sound/core/control.c index 9c3fd5113a6173..6ade3bfa11d891 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -123,10 +123,12 @@ static int snd_ctl_release(struct inode *inode, struct file *file) scoped_guard(rwsem_write, &card->controls_rwsem) { list_for_each_entry(control, &card->controls, list) for (idx = 0; idx < control->count; idx++) - if (control->vd[idx].owner == ctl) + if (control->vd[idx].owner == ctl) { control->vd[idx].owner = NULL; + if (control->unlock) + control->unlock(control); + } } - snd_fasync_free(ctl->fasync); snd_ctl_empty_read_queue(ctl); put_pid(ctl->pid); @@ -303,6 +305,8 @@ struct snd_kcontrol *snd_ctl_new1(const struct snd_kcontrol_new *ncontrol, kctl->info = ncontrol->info; kctl->get = ncontrol->get; kctl->put = ncontrol->put; + kctl->lock = ncontrol->lock; + kctl->unlock = ncontrol->unlock; kctl->tlv.p = ncontrol->tlv.p; kctl->private_value = ncontrol->private_value; @@ -1359,6 +1363,12 @@ static int snd_ctl_elem_lock(struct snd_ctl_file *file, vd = &kctl->vd[snd_ctl_get_ioff(kctl, &id)]; if (vd->owner) return -EBUSY; + + if (kctl->lock) { + int err = kctl->lock(kctl, file); + if (err < 0) + return err; + } vd->owner = file; return 0; } @@ -1383,6 +1393,8 @@ static int snd_ctl_elem_unlock(struct snd_ctl_file *file, if (vd->owner != file) return -EPERM; vd->owner = NULL; + if (kctl->unlock) + kctl->unlock(kctl); return 0; } diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index a82dd155e1d3a6..b12df5b5ddfc17 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -1074,7 +1074,9 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream) runtime->oss.params = 0; runtime->oss.prepare = 1; runtime->oss.buffer_used = 0; - snd_pcm_runtime_buffer_set_silence(runtime); + err = snd_pcm_runtime_buffer_set_silence(runtime); + if (err < 0) + goto failure; runtime->oss.period_frames = snd_pcm_alsa_frames(substream, oss_period_size); diff --git a/sound/core/pcm.c b/sound/core/pcm.c index 283aac441fa0a7..0b512085eb63f2 100644 --- a/sound/core/pcm.c +++ b/sound/core/pcm.c @@ -328,13 +328,13 @@ static const char *snd_pcm_oss_format_name(int format) static void snd_pcm_proc_info_read(struct snd_pcm_substream *substream, struct snd_info_buffer *buffer) { - struct snd_pcm_info *info __free(kfree) = NULL; int err; if (! substream) return; - info = kmalloc(sizeof(*info), GFP_KERNEL); + struct snd_pcm_info *info __free(kfree) = + kmalloc(sizeof(*info), GFP_KERNEL); if (!info) return; diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index 54eb9bd8eb2188..e86f68f1f23c1e 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -235,7 +235,6 @@ static int snd_pcm_ioctl_hw_params_compat(struct snd_pcm_substream *substream, int refine, struct snd_pcm_hw_params32 __user *data32) { - struct snd_pcm_hw_params *data __free(kfree) = NULL; struct snd_pcm_runtime *runtime; int err; @@ -243,7 +242,8 @@ static int snd_pcm_ioctl_hw_params_compat(struct snd_pcm_substream *substream, if (!runtime) return -ENOTTY; - data = kmalloc(sizeof(*data), GFP_KERNEL); + struct snd_pcm_hw_params *data __free(kfree) = + kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; @@ -332,7 +332,6 @@ static int snd_pcm_ioctl_xfern_compat(struct snd_pcm_substream *substream, compat_caddr_t buf; compat_caddr_t __user *bufptr; u32 frames; - void __user **bufs __free(kfree) = NULL; int err, ch, i; if (! substream->runtime) @@ -349,7 +348,9 @@ static int snd_pcm_ioctl_xfern_compat(struct snd_pcm_substream *substream, get_user(frames, &data32->frames)) return -EFAULT; bufptr = compat_ptr(buf); - bufs = kmalloc_array(ch, sizeof(void __user *), GFP_KERNEL); + + void __user **bufs __free(kfree) = + kmalloc_array(ch, sizeof(void __user *), GFP_KERNEL); if (bufs == NULL) return -ENOMEM; for (i = 0; i < ch; i++) { diff --git a/sound/core/pcm_dmaengine.c b/sound/core/pcm_dmaengine.c index f0c17503df425d..805191876fc923 100644 --- a/sound/core/pcm_dmaengine.c +++ b/sound/core/pcm_dmaengine.c @@ -22,6 +22,8 @@ struct dmaengine_pcm_runtime_data { struct dma_chan *dma_chan; dma_cookie_t cookie; + struct work_struct complete_wq; /* for nonatomic PCM */ + struct snd_pcm_substream *substream; unsigned int pos; }; @@ -147,6 +149,21 @@ static void dmaengine_pcm_dma_complete(void *arg) snd_pcm_period_elapsed(substream); } +static void dmaengine_pcm_dma_complete_nonatomic(struct work_struct *wq) +{ + struct dmaengine_pcm_runtime_data *prtd = \ + container_of(wq, struct dmaengine_pcm_runtime_data, complete_wq); + struct snd_pcm_substream *substream = prtd->substream; + dmaengine_pcm_dma_complete(substream); +} + +static void dmaengine_pcm_dma_complete_nonatomic_callback(void *arg) +{ + struct snd_pcm_substream *substream = arg; + struct dmaengine_pcm_runtime_data *prtd = substream_to_prtd(substream); + schedule_work(&prtd->complete_wq); +} + static int dmaengine_pcm_prepare_and_submit(struct snd_pcm_substream *substream) { struct dmaengine_pcm_runtime_data *prtd = substream_to_prtd(substream); @@ -169,7 +186,11 @@ static int dmaengine_pcm_prepare_and_submit(struct snd_pcm_substream *substream) if (!desc) return -ENOMEM; - desc->callback = dmaengine_pcm_dma_complete; + if (substream->pcm->nonatomic) + desc->callback = dmaengine_pcm_dma_complete_nonatomic_callback; + else + desc->callback = dmaengine_pcm_dma_complete; + desc->callback_param = substream; prtd->cookie = dmaengine_submit(desc); @@ -322,6 +343,10 @@ int snd_dmaengine_pcm_open(struct snd_pcm_substream *substream, if (!prtd) return -ENOMEM; + if (substream->pcm->nonatomic) + INIT_WORK(&prtd->complete_wq, dmaengine_pcm_dma_complete_nonatomic); + + prtd->substream = substream; prtd->dma_chan = chan; substream->runtime->private_data = prtd; @@ -355,7 +380,14 @@ static void __snd_dmaengine_pcm_close(struct snd_pcm_substream *substream, if (status == DMA_PAUSED) dmaengine_terminate_async(prtd->dma_chan); + /* + * The PCM might have been closed while suspended, which would + * skip the STOP trigger. Make sure we terminate. + */ + dmaengine_terminate_async(prtd->dma_chan); dmaengine_synchronize(prtd->dma_chan); + if (substream->pcm->nonatomic) + flush_work(&prtd->complete_wq); if (release_channel) dma_release_channel(prtd->dma_chan); kfree(prtd); diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 6eaa950504cfc0..d0df847152f0dd 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1149,6 +1149,43 @@ static int snd_interval_step(struct snd_interval *i, unsigned int step) return changed; } +/** + * snd_interval_rate_bits - refine the rate interval from a rate bitmask + * @i: the rate interval to refine + * @mask: the rate bitmask + * + * Refines the interval value, assumed to be the sample rate, according to + * a bitmask of available rates (an ORed combination of SNDRV_PCM_RATE_*). + * + * Return: Positive if the value is changed, zero if it's not changed, or a + * negative error code. + */ +int snd_interval_rate_bits(struct snd_interval *i, unsigned int mask) +{ + unsigned int k; + struct snd_interval mask_range; + + if (!mask) + return -EINVAL; + + snd_interval_any(&mask_range); + mask_range.min = UINT_MAX; + mask_range.max = 0; + for (k = 0; k < snd_pcm_known_rates.count; k++) { + unsigned int rate = snd_pcm_known_rates.list[k]; + if (!(mask & (1 << k))) + continue; + + if (rate > mask_range.max) + mask_range.max = rate; + + if (rate < mask_range.min) + mask_range.min = rate; + } + return snd_interval_refine(i, &mask_range); +} +EXPORT_SYMBOL(snd_interval_rate_bits); + /* Info constraints helpers */ /** diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 68bee40c9adafd..257fa9a1f6fae6 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -242,10 +242,10 @@ int snd_pcm_info(struct snd_pcm_substream *substream, struct snd_pcm_info *info) int snd_pcm_info_user(struct snd_pcm_substream *substream, struct snd_pcm_info __user * _info) { - struct snd_pcm_info *info __free(kfree) = NULL; int err; + struct snd_pcm_info *info __free(kfree) = + kmalloc(sizeof(*info), GFP_KERNEL); - info = kmalloc(sizeof(*info), GFP_KERNEL); if (! info) return -ENOMEM; err = snd_pcm_info(substream, info); @@ -364,7 +364,6 @@ static int constrain_params_by_rules(struct snd_pcm_substream *substream, struct snd_pcm_hw_constraints *constrs = &substream->runtime->hw_constraints; unsigned int k; - unsigned int *rstamps __free(kfree) = NULL; unsigned int vstamps[SNDRV_PCM_HW_PARAM_LAST_INTERVAL + 1]; unsigned int stamp; struct snd_pcm_hw_rule *r; @@ -380,7 +379,8 @@ static int constrain_params_by_rules(struct snd_pcm_substream *substream, * Each member of 'rstamps' array represents the sequence number of * recent application of corresponding rule. */ - rstamps = kcalloc(constrs->rules_num, sizeof(unsigned int), GFP_KERNEL); + unsigned int *rstamps __free(kfree) = + kcalloc(constrs->rules_num, sizeof(unsigned int), GFP_KERNEL); if (!rstamps) return -ENOMEM; @@ -583,10 +583,10 @@ EXPORT_SYMBOL(snd_pcm_hw_refine); static int snd_pcm_hw_refine_user(struct snd_pcm_substream *substream, struct snd_pcm_hw_params __user * _params) { - struct snd_pcm_hw_params *params __free(kfree) = NULL; int err; + struct snd_pcm_hw_params *params __free(kfree) = + memdup_user(_params, sizeof(*params)); - params = memdup_user(_params, sizeof(*params)); if (IS_ERR(params)) return PTR_ERR(params); @@ -730,13 +730,18 @@ static void snd_pcm_buffer_access_unlock(struct snd_pcm_runtime *runtime) } /* fill the PCM buffer with the current silence format; called from pcm_oss.c */ -void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime) +int snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime) { - snd_pcm_buffer_access_lock(runtime); + int err; + + err = snd_pcm_buffer_access_lock(runtime); + if (err < 0) + return err; if (runtime->dma_area) snd_pcm_format_set_silence(runtime->format, runtime->dma_area, bytes_to_samples(runtime, runtime->dma_bytes)); snd_pcm_buffer_access_unlock(runtime); + return 0; } EXPORT_SYMBOL_GPL(snd_pcm_runtime_buffer_set_silence); @@ -884,10 +889,10 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream, static int snd_pcm_hw_params_user(struct snd_pcm_substream *substream, struct snd_pcm_hw_params __user * _params) { - struct snd_pcm_hw_params *params __free(kfree) = NULL; int err; + struct snd_pcm_hw_params *params __free(kfree) = + memdup_user(_params, sizeof(*params)); - params = memdup_user(_params, sizeof(*params)); if (IS_ERR(params)) return PTR_ERR(params); @@ -939,8 +944,9 @@ static int snd_pcm_hw_free(struct snd_pcm_substream *substream) goto unlock; result = do_hw_free(substream); snd_pcm_set_state(substream, SNDRV_PCM_STATE_OPEN); - cpu_latency_qos_remove_request(&substream->latency_pm_qos_req); - unlock: + if (cpu_latency_qos_request_active(&substream->latency_pm_qos_req)) + cpu_latency_qos_remove_request(&substream->latency_pm_qos_req); +unlock: snd_pcm_buffer_access_unlock(runtime); return result; } @@ -2262,7 +2268,6 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) { struct snd_pcm_file *pcm_file; struct snd_pcm_substream *substream1; - struct snd_pcm_group *group __free(kfree) = NULL; struct snd_pcm_group *target_group; bool nonatomic = substream->pcm->nonatomic; CLASS(fd, f)(fd); @@ -2278,7 +2283,8 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) if (substream == substream1) return -EINVAL; - group = kzalloc(sizeof(*group), GFP_KERNEL); + struct snd_pcm_group *group __free(kfree) = + kzalloc(sizeof(*group), GFP_KERNEL); if (!group) return -ENOMEM; snd_pcm_group_init(group); @@ -2452,6 +2458,7 @@ const struct snd_pcm_hw_constraint_list snd_pcm_known_rates = { .count = ARRAY_SIZE(rates), .list = rates, }; +EXPORT_SYMBOL_GPL(snd_pcm_known_rates); static int snd_pcm_hw_rule_rate(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) @@ -3286,7 +3293,6 @@ static int snd_pcm_xfern_frames_ioctl(struct snd_pcm_substream *substream, { struct snd_xfern xfern; struct snd_pcm_runtime *runtime = substream->runtime; - void *bufs __free(kfree) = NULL; snd_pcm_sframes_t result; if (runtime->state == SNDRV_PCM_STATE_OPEN) @@ -3298,7 +3304,8 @@ static int snd_pcm_xfern_frames_ioctl(struct snd_pcm_substream *substream, if (copy_from_user(&xfern, _xfern, sizeof(xfern))) return -EFAULT; - bufs = memdup_array_user(xfern.bufs, runtime->channels, sizeof(void *)); + void *bufs __free(kfree) = + memdup_array_user(xfern.bufs, runtime->channels, sizeof(void *)); if (IS_ERR(bufs)) return PTR_ERR(bufs); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) @@ -3572,7 +3579,6 @@ static ssize_t snd_pcm_readv(struct kiocb *iocb, struct iov_iter *to) struct snd_pcm_runtime *runtime; snd_pcm_sframes_t result; unsigned long i; - void __user **bufs __free(kfree) = NULL; snd_pcm_uframes_t frames; const struct iovec *iov = iter_iov(to); @@ -3591,7 +3597,9 @@ static ssize_t snd_pcm_readv(struct kiocb *iocb, struct iov_iter *to) if (!frame_aligned(runtime, iov->iov_len)) return -EINVAL; frames = bytes_to_samples(runtime, iov->iov_len); - bufs = kmalloc_array(to->nr_segs, sizeof(void *), GFP_KERNEL); + + void __user **bufs __free(kfree) = + kmalloc_array(to->nr_segs, sizeof(void *), GFP_KERNEL); if (bufs == NULL) return -ENOMEM; for (i = 0; i < to->nr_segs; ++i) { @@ -3611,7 +3619,6 @@ static ssize_t snd_pcm_writev(struct kiocb *iocb, struct iov_iter *from) struct snd_pcm_runtime *runtime; snd_pcm_sframes_t result; unsigned long i; - void __user **bufs __free(kfree) = NULL; snd_pcm_uframes_t frames; const struct iovec *iov = iter_iov(from); @@ -3629,7 +3636,9 @@ static ssize_t snd_pcm_writev(struct kiocb *iocb, struct iov_iter *from) !frame_aligned(runtime, iov->iov_len)) return -EINVAL; frames = bytes_to_samples(runtime, iov->iov_len); - bufs = kmalloc_array(from->nr_segs, sizeof(void *), GFP_KERNEL); + + void __user **bufs __free(kfree) = + kmalloc_array(from->nr_segs, sizeof(void *), GFP_KERNEL); if (bufs == NULL) return -ENOMEM; for (i = 0; i < from->nr_segs; ++i) { @@ -4101,15 +4110,15 @@ static void snd_pcm_hw_convert_to_old_params(struct snd_pcm_hw_params_old *opara static int snd_pcm_hw_refine_old_user(struct snd_pcm_substream *substream, struct snd_pcm_hw_params_old __user * _oparams) { - struct snd_pcm_hw_params *params __free(kfree) = NULL; - struct snd_pcm_hw_params_old *oparams __free(kfree) = NULL; int err; - params = kmalloc(sizeof(*params), GFP_KERNEL); + struct snd_pcm_hw_params *params __free(kfree) = + kmalloc(sizeof(*params), GFP_KERNEL); if (!params) return -ENOMEM; - oparams = memdup_user(_oparams, sizeof(*oparams)); + struct snd_pcm_hw_params_old *oparams __free(kfree) = + memdup_user(_oparams, sizeof(*oparams)); if (IS_ERR(oparams)) return PTR_ERR(oparams); snd_pcm_hw_convert_from_old_params(params, oparams); @@ -4130,15 +4139,15 @@ static int snd_pcm_hw_refine_old_user(struct snd_pcm_substream *substream, static int snd_pcm_hw_params_old_user(struct snd_pcm_substream *substream, struct snd_pcm_hw_params_old __user * _oparams) { - struct snd_pcm_hw_params *params __free(kfree) = NULL; - struct snd_pcm_hw_params_old *oparams __free(kfree) = NULL; int err; - params = kmalloc(sizeof(*params), GFP_KERNEL); + struct snd_pcm_hw_params *params __free(kfree) = + kmalloc(sizeof(*params), GFP_KERNEL); if (!params) return -ENOMEM; - oparams = memdup_user(_oparams, sizeof(*oparams)); + struct snd_pcm_hw_params_old *oparams __free(kfree) = + memdup_user(_oparams, sizeof(*oparams)); if (IS_ERR(oparams)) return PTR_ERR(oparams); diff --git a/sound/core/vmaster.c b/sound/core/vmaster.c index c657659b236c42..76cc64245f5df4 100644 --- a/sound/core/vmaster.c +++ b/sound/core/vmaster.c @@ -56,10 +56,10 @@ struct link_follower { static int follower_update(struct link_follower *follower) { - struct snd_ctl_elem_value *uctl __free(kfree) = NULL; int err, ch; + struct snd_ctl_elem_value *uctl __free(kfree) = + kzalloc(sizeof(*uctl), GFP_KERNEL); - uctl = kzalloc(sizeof(*uctl), GFP_KERNEL); if (!uctl) return -ENOMEM; uctl->id = follower->follower.id; @@ -74,7 +74,6 @@ static int follower_update(struct link_follower *follower) /* get the follower ctl info and save the initial values */ static int follower_init(struct link_follower *follower) { - struct snd_ctl_elem_info *uinfo __free(kfree) = NULL; int err; if (follower->info.count) { @@ -84,7 +83,8 @@ static int follower_init(struct link_follower *follower) return 0; } - uinfo = kmalloc(sizeof(*uinfo), GFP_KERNEL); + struct snd_ctl_elem_info *uinfo __free(kfree) = + kmalloc(sizeof(*uinfo), GFP_KERNEL); if (!uinfo) return -ENOMEM; uinfo->id = follower->follower.id; @@ -341,9 +341,9 @@ static int master_get(struct snd_kcontrol *kcontrol, static int sync_followers(struct link_master *master, int old_val, int new_val) { struct link_follower *follower; - struct snd_ctl_elem_value *uval __free(kfree) = NULL; + struct snd_ctl_elem_value *uval __free(kfree) = + kmalloc(sizeof(*uval), GFP_KERNEL); - uval = kmalloc(sizeof(*uval), GFP_KERNEL); if (!uval) return -ENOMEM; list_for_each_entry(follower, &master->followers, list) { diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c index 64ef03b2d579c9..aa0d2fcb1a180c 100644 --- a/sound/drivers/aloop.c +++ b/sound/drivers/aloop.c @@ -336,37 +336,43 @@ static bool is_access_interleaved(snd_pcm_access_t access) static int loopback_check_format(struct loopback_cable *cable, int stream) { + struct loopback_pcm *dpcm_play, *dpcm_capt; struct snd_pcm_runtime *runtime, *cruntime; struct loopback_setup *setup; struct snd_card *card; + bool stop_capture = false; int check; - if (cable->valid != CABLE_VALID_BOTH) { - if (stream == SNDRV_PCM_STREAM_PLAYBACK) - goto __notify; - return 0; - } - runtime = cable->streams[SNDRV_PCM_STREAM_PLAYBACK]-> - substream->runtime; - cruntime = cable->streams[SNDRV_PCM_STREAM_CAPTURE]-> - substream->runtime; - check = runtime->format != cruntime->format || - runtime->rate != cruntime->rate || - runtime->channels != cruntime->channels || - is_access_interleaved(runtime->access) != - is_access_interleaved(cruntime->access); - if (!check) - return 0; - if (stream == SNDRV_PCM_STREAM_CAPTURE) { - return -EIO; - } else { - snd_pcm_stop(cable->streams[SNDRV_PCM_STREAM_CAPTURE]-> - substream, SNDRV_PCM_STATE_DRAINING); - __notify: - runtime = cable->streams[SNDRV_PCM_STREAM_PLAYBACK]-> - substream->runtime; - setup = get_setup(cable->streams[SNDRV_PCM_STREAM_PLAYBACK]); - card = cable->streams[SNDRV_PCM_STREAM_PLAYBACK]->loopback->card; + scoped_guard(spinlock_irqsave, &cable->lock) { + dpcm_play = cable->streams[SNDRV_PCM_STREAM_PLAYBACK]; + dpcm_capt = cable->streams[SNDRV_PCM_STREAM_CAPTURE]; + + if (cable->valid != CABLE_VALID_BOTH) { + if (stream == SNDRV_PCM_STREAM_CAPTURE || !dpcm_play) + return 0; + } else { + if (!dpcm_play || !dpcm_capt) + return -EIO; + runtime = dpcm_play->substream->runtime; + cruntime = dpcm_capt->substream->runtime; + if (!runtime || !cruntime) + return -EIO; + check = runtime->format != cruntime->format || + runtime->rate != cruntime->rate || + runtime->channels != cruntime->channels || + is_access_interleaved(runtime->access) != + is_access_interleaved(cruntime->access); + if (!check) + return 0; + if (stream == SNDRV_PCM_STREAM_CAPTURE) + return -EIO; + else if (cruntime->state == SNDRV_PCM_STATE_RUNNING) + stop_capture = true; + } + + setup = get_setup(dpcm_play); + card = dpcm_play->loopback->card; + runtime = dpcm_play->substream->runtime; if (setup->format != runtime->format) { snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &setup->format_id); @@ -389,6 +395,10 @@ static int loopback_check_format(struct loopback_cable *cable, int stream) setup->access = runtime->access; } } + + if (stop_capture) + snd_pcm_stop(dpcm_capt->substream, SNDRV_PCM_STATE_DRAINING); + return 0; } diff --git a/sound/firewire/dice/dice-extension.c b/sound/firewire/dice/dice-extension.c index 02f4a8318e38e7..48bfb3ad93ce55 100644 --- a/sound/firewire/dice/dice-extension.c +++ b/sound/firewire/dice/dice-extension.c @@ -116,7 +116,7 @@ static int detect_stream_formats(struct snd_dice *dice, u64 section_addr) break; base_offset += EXT_APP_STREAM_ENTRIES; - stream_count = be32_to_cpu(reg[0]); + stream_count = min_t(unsigned int, be32_to_cpu(reg[0]), MAX_STREAMS); err = read_stream_entries(dice, section_addr, base_offset, stream_count, mode, dice->tx_pcm_chs, @@ -125,7 +125,7 @@ static int detect_stream_formats(struct snd_dice *dice, u64 section_addr) break; base_offset += stream_count * EXT_APP_STREAM_ENTRY_SIZE; - stream_count = be32_to_cpu(reg[1]); + stream_count = min_t(unsigned int, be32_to_cpu(reg[1]), MAX_STREAMS); err = read_stream_entries(dice, section_addr, base_offset, stream_count, mode, dice->rx_pcm_chs, diff --git a/sound/firewire/motu/motu-hwdep.c b/sound/firewire/motu/motu-hwdep.c index 981c19430cb0fe..89dc436a065299 100644 --- a/sound/firewire/motu/motu-hwdep.c +++ b/sound/firewire/motu/motu-hwdep.c @@ -75,7 +75,7 @@ static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count, while (consumed < count && snd_motu_register_dsp_message_parser_copy_event(motu, &ev)) { ptr = (u32 __user *)(buf + consumed); - if (put_user(ev, ptr)) + if (consumed + sizeof(ev) > count || put_user(ev, ptr)) return -EFAULT; consumed += sizeof(ev); } @@ -83,10 +83,11 @@ static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count, event.motu_register_dsp_change.type = SNDRV_FIREWIRE_EVENT_MOTU_REGISTER_DSP_CHANGE; event.motu_register_dsp_change.count = (consumed - sizeof(event.motu_register_dsp_change)) / 4; - if (copy_to_user(buf, &event, sizeof(event.motu_register_dsp_change))) + if (copy_to_user(buf, &event, + min_t(long, count, sizeof(event.motu_register_dsp_change)))) return -EFAULT; - count = consumed; + count = min_t(long, count, consumed); } else { spin_unlock_irq(&motu->lock); diff --git a/sound/hda/codecs/conexant.c b/sound/hda/codecs/conexant.c index 5fcbc1312c6971..0c517378a6d28f 100644 --- a/sound/hda/codecs/conexant.c +++ b/sound/hda/codecs/conexant.c @@ -299,6 +299,7 @@ enum { CXT_PINCFG_SWS_JS201D, CXT_PINCFG_TOP_SPEAKER, CXT_FIXUP_HP_A_U, + CXT_FIXUP_ACER_SWIFT_HP, }; /* for hda_fixup_thinkpad_acpi() */ @@ -1024,6 +1025,14 @@ static const struct hda_fixup cxt_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = cxt_fixup_hp_a_u, }, + [CXT_FIXUP_ACER_SWIFT_HP] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x16, 0x0321403f }, /* Headphone */ + { 0x19, 0x40f001f0 }, /* Mic */ + { } + }, + }, }; static const struct hda_quirk cxt5045_fixups[] = { @@ -1073,6 +1082,7 @@ static const struct hda_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x1025, 0x0543, "Acer Aspire One 522", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_ASPIRE_DMIC), SND_PCI_QUIRK(0x1025, 0x054f, "Acer Aspire 4830T", CXT_FIXUP_ASPIRE_DMIC), + SND_PCI_QUIRK(0x1025, 0x136d, "Acer Swift SF314", CXT_FIXUP_ACER_SWIFT_HP), SND_PCI_QUIRK(0x103c, 0x8079, "HP EliteBook 840 G3", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x807C, "HP EliteBook 820 G3", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x80FD, "HP ProBook 640 G2", CXT_FIXUP_HP_DOCK), @@ -1081,6 +1091,7 @@ static const struct hda_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE), SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x8231, "HP ProBook 450 G4", CXT_FIXUP_MUTE_LED_GPIO), + SND_PCI_QUIRK(0x103c, 0x826b, "HP ZBook Studio G4", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x828c, "HP EliteBook 840 G4", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE), diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index b45fcc9a3785e9..66da4584aa7a5f 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -3371,11 +3371,22 @@ static void alc287_alc1318_playback_pcm_hook(struct hda_pcm_stream *hinfo, struct snd_pcm_substream *substream, int action) { + static const struct coef_fw dis_coefs[] = { + WRITE_COEF(0x24, 0x0013), WRITE_COEF(0x25, 0x0000), WRITE_COEF(0x26, 0xC203), + WRITE_COEF(0x28, 0x0004), WRITE_COEF(0x29, 0xb023), + }; /* Disable AMP silence detection */ + static const struct coef_fw en_coefs[] = { + WRITE_COEF(0x24, 0x0013), WRITE_COEF(0x25, 0x0000), WRITE_COEF(0x26, 0xC203), + WRITE_COEF(0x28, 0x0084), WRITE_COEF(0x29, 0xb023), + }; /* Enable AMP silence detection */ + switch (action) { case HDA_GEN_PCM_ACT_OPEN: + alc_process_coef_fw(codec, dis_coefs); alc_write_coefex_idx(codec, 0x5a, 0x00, 0x954f); /* write gpio3 to high */ break; case HDA_GEN_PCM_ACT_CLOSE: + alc_process_coef_fw(codec, en_coefs); alc_write_coefex_idx(codec, 0x5a, 0x00, 0x554f); /* write gpio3 as default value */ break; } @@ -3674,6 +3685,7 @@ enum { ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE, ALC287_FIXUP_YOGA7_14ITL_SPEAKERS, ALC298_FIXUP_LENOVO_C940_DUET7, + ALC287_FIXUP_LENOVO_YOGA_BOOK_9I, ALC287_FIXUP_13S_GEN2_SPEAKERS, ALC256_FIXUP_SET_COEF_DEFAULTS, ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE, @@ -3703,6 +3715,7 @@ enum { ALC295_FIXUP_DELL_TAS2781_I2C, ALC245_FIXUP_TAS2781_SPI_2, ALC287_FIXUP_TXNW2781_I2C, + ALC287_FIXUP_TXNW2781_I2C_ASUS, ALC287_FIXUP_YOGA7_14ARB7_I2C, ALC245_FIXUP_HP_MUTE_LED_COEFBIT, ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT, @@ -3756,6 +3769,23 @@ static void alc298_fixup_lenovo_c940_duet7(struct hda_codec *codec, __snd_hda_apply_fixup(codec, id, action, 0); } +/* A special fixup for Lenovo Yoga 9i and Yoga Book 9i 13IRU8 + * both have the very same PCI SSID and vendor ID, so we need + * to apply different fixups depending on the subsystem ID + */ +static void alc287_fixup_lenovo_yoga_book_9i(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + int id; + + if (codec->core.subsystem_id == 0x17aa3881) + id = ALC287_FIXUP_TAS2781_I2C; /* Yoga Book 9i 13IRU8 */ + else + id = ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP; /* Yoga 9i */ + __snd_hda_apply_fixup(codec, id, action, 0); +} + static const struct hda_fixup alc269_fixups[] = { [ALC269_FIXUP_GPIO2] = { .type = HDA_FIXUP_FUNC, @@ -5763,6 +5793,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc298_fixup_lenovo_c940_duet7, }, + [ALC287_FIXUP_LENOVO_YOGA_BOOK_9I] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_lenovo_yoga_book_9i, + }, [ALC287_FIXUP_13S_GEN2_SPEAKERS] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -5993,6 +6027,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC285_FIXUP_THINKPAD_HEADSET_JACK, }, + [ALC287_FIXUP_TXNW2781_I2C_ASUS] = { + .type = HDA_FIXUP_FUNC, + .v.func = tas2781_fixup_txnw_i2c, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_SPK, + }, [ALC287_FIXUP_YOGA7_14ARB7_I2C] = { .type = HDA_FIXUP_FUNC, .v.func = yoga7_14arb7_fixup_i2c, @@ -6231,7 +6271,9 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC), SND_PCI_QUIRK(0x1025, 0x1534, "Acer Predator PH315-54", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1025, 0x1539, "Acer Nitro 5 AN515-57", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x159c, "Acer Nitro 5 AN515-58", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x1597, "Acer Nitro 5 AN517-55", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x1826, "Acer Helios ZPC", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), SND_PCI_QUIRK(0x1025, 0x182c, "Acer Helios ZPD", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), @@ -6419,6 +6461,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x863e, "HP Spectre x360 15-df1xxx", ALC285_FIXUP_HP_SPECTRE_X360_DF1), SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), SND_PCI_QUIRK(0x103c, 0x86f9, "HP Spectre x360 13-aw0xxx", ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x8706, "HP Laptop 15s-eq1xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8716, "HP Elite Dragonfly G2 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8720, "HP EliteBook x360 1040 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8724, "HP EliteBook 850 G7", ALC285_FIXUP_HP_GPIO_LED), @@ -6522,6 +6565,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8a2e, "HP Envy 16", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8a30, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8a31, "HP Envy 15", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8a34, "HP Pavilion x360 2-in-1 Laptop 14-ek0xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a4f, "HP Victus 15-fa0xxx (MB 8A4F)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a6e, "HP EDNA 360", ALC287_FIXUP_CS35L41_I2C_4), SND_PCI_QUIRK(0x103c, 0x8a74, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), @@ -6623,6 +6667,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c8c, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c8d, "HP ProBook 440 G11", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c8e, "HP ProBook 460 G11", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c8f, "HP EliteBook 630 G11", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c90, "HP EliteBook 640", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c91, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), @@ -6736,6 +6781,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1314, "ASUS GA605K", ALC285_FIXUP_ASUS_GA605K_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1384, "ASUS RC73XA", ALC287_FIXUP_TXNW2781_I2C_ASUS), + SND_PCI_QUIRK(0x1043, 0x1394, "ASUS RC73YA", ALC287_FIXUP_TXNW2781_I2C_ASUS), SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650PY/PZ/PV/PU/PYV/PZV/PIV/PVV", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC), @@ -6752,6 +6799,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA/XJ/XQ/XU/XV/XI", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301VV/VQ/VU/VJ/VA/VC/VE/VVC/VQC/VUC/VJC/VEC/VCC", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1584, "ASUS UM3406GA ", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1652, "ASUS ROG Zephyrus Do 15 SE", ALC289_FIXUP_ASUS_ZEPHYRUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZI/ZJ/ZQ/ZU/ZV", ALC285_FIXUP_ASUS_HEADSET_MIC), @@ -6895,6 +6943,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc830, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc832, "Samsung Galaxy Book Flex Alpha (NP730QCJ)", ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), + SND_PCI_QUIRK(0x144d, 0xc876, "Samsung 730QED (NP730QED-KA2US)", ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xca03, "Samsung Galaxy Book2 Pro 360 (NP930QED)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xca06, "Samsung Galaxy Book3 360 (NP730QFG)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc868, "Samsung Galaxy Book2 Pro (NP930XED)", ALC298_FIXUP_SAMSUNG_AMP), @@ -6902,7 +6951,9 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc872, "Samsung Galaxy Book2 Pro (NP950XEE)", ALC298_FIXUP_SAMSUNG_AMP_V2_2_AMPS), SND_PCI_QUIRK(0x144d, 0xc886, "Samsung Galaxy Book3 Pro (NP964XFG)", ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS), SND_PCI_QUIRK(0x144d, 0xc1ca, "Samsung Galaxy Book3 Pro 360 (NP960QFG)", ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS), + SND_PCI_QUIRK(0x144d, 0xc1cb, "Samsung Galaxy Book3 Pro 360 (NP965QFG)", ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS), SND_PCI_QUIRK(0x144d, 0xc1cc, "Samsung Galaxy Book3 Ultra (NT960XFH)", ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS), + SND_PCI_QUIRK(0x1458, 0x900e, "Gigabyte G5 KF5 (2023)", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), @@ -7073,7 +7124,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), SND_PCI_QUIRK(0x17aa, 0x3834, "Lenovo IdeaPad Slim 9i 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x383d, "Legion Y9000X 2019", ALC285_FIXUP_LEGION_Y9000X_SPEAKERS), - SND_PCI_QUIRK(0x17aa, 0x3843, "Yoga 9i", ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP), + SND_PCI_QUIRK(0x17aa, 0x3843, "Lenovo Yoga 9i / Yoga Book 9i", ALC287_FIXUP_LENOVO_YOGA_BOOK_9I), SND_PCI_QUIRK(0x17aa, 0x3847, "Legion 7 16ACHG6", ALC287_FIXUP_LEGION_16ACHG6), SND_PCI_QUIRK(0x17aa, 0x384a, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3852, "Lenovo Yoga 7 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), @@ -7195,15 +7246,18 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d05, 0x1409, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d05, 0x300f, "TongFang X6AR5xxY", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d05, 0x3019, "TongFang X6FR5xxY", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1d05, 0x3031, "TongFang X6AR55xU", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), + SND_PCI_QUIRK(0x1e39, 0xca14, "MEDION NM14LNL", ALC233_FIXUP_MEDION_MTL_SPK), SND_PCI_QUIRK(0x1ee7, 0x2078, "HONOR BRB-X M1010", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1f66, 0x0105, "Ayaneo Portable Game Player", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x2014, 0x800a, "Positivo ARN50", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x2039, 0x0001, "Inspur S14-G1", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x2782, 0x0214, "VAIO VJFE-CL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x2782, 0x0228, "Infinix ZERO BOOK 13", ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13), SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO), diff --git a/sound/hda/codecs/side-codecs/cirrus_scodec_test.c b/sound/hda/codecs/side-codecs/cirrus_scodec_test.c index 3cca750857b689..dc35932b6b22f1 100644 --- a/sound/hda/codecs/side-codecs/cirrus_scodec_test.c +++ b/sound/hda/codecs/side-codecs/cirrus_scodec_test.c @@ -103,6 +103,7 @@ static int cirrus_scodec_test_gpio_probe(struct platform_device *pdev) /* GPIO core modifies our struct gpio_chip so use a copy */ gpio_priv->chip = cirrus_scodec_test_gpio_chip; + gpio_priv->chip.parent = &pdev->dev; ret = devm_gpiochip_add_data(&pdev->dev, &gpio_priv->chip, gpio_priv); if (ret) return dev_err_probe(&pdev->dev, ret, "Failed to add gpiochip\n"); @@ -319,7 +320,7 @@ static struct kunit_case cirrus_scodec_test_cases[] = { }; static struct kunit_suite cirrus_scodec_test_suite = { - .name = "snd-hda-scodec-cs35l56-test", + .name = "snd-hda-cirrus-scodec-test", .init = cirrus_scodec_test_case_init, .test_cases = cirrus_scodec_test_cases, }; diff --git a/sound/hda/codecs/side-codecs/cs35l41_hda.c b/sound/hda/codecs/side-codecs/cs35l41_hda.c index c0f2a3ff77a1b6..21e00055c0c443 100644 --- a/sound/hda/codecs/side-codecs/cs35l41_hda.c +++ b/sound/hda/codecs/side-codecs/cs35l41_hda.c @@ -1901,6 +1901,8 @@ static int cs35l41_hda_read_acpi(struct cs35l41_hda *cs35l41, const char *hid, i cs35l41->dacpi = adev; physdev = get_device(acpi_get_first_physical_node(adev)); + if (!physdev) + return -ENODEV; sub = acpi_get_subsystem_id(ACPI_HANDLE(physdev)); if (IS_ERR(sub)) diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c index 0357401a602349..624a822341bb71 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c @@ -2,7 +2,7 @@ // // TAS2781 HDA I2C driver // -// Copyright 2023 - 2025 Texas Instruments, Inc. +// Copyright 2023 - 2026 Texas Instruments, Inc. // // Author: Shenghao Ding // Current maintainer: Baojun Xu @@ -60,6 +60,7 @@ struct tas2781_hda_i2c_priv { int (*save_calibration)(struct tas2781_hda *h); int hda_chip_id; + bool skip_calibration; }; static int tas2781_get_i2c_res(struct acpi_resource *ares, void *data) @@ -87,6 +88,7 @@ static const struct acpi_gpio_mapping tas2781_speaker_id_gpios[] = { static int tas2781_read_acpi(struct tasdevice_priv *p, const char *hid) { + struct gpio_desc *speaker_id; struct acpi_device *adev; struct device *physdev; LIST_HEAD(resources); @@ -110,8 +112,10 @@ static int tas2781_read_acpi(struct tasdevice_priv *p, const char *hid) sub = acpi_get_subsystem_id(ACPI_HANDLE(physdev)); if (IS_ERR(sub)) { /* No subsys id in older tas2563 projects. */ - if (!strncmp(hid, "INT8866", sizeof("INT8866"))) + if (!strncmp(hid, "INT8866", sizeof("INT8866"))) { + p->speaker_id = -1; goto end_2563; + } dev_err(p->dev, "Failed to get SUBSYS ID.\n"); ret = PTR_ERR(sub); goto err; @@ -119,19 +123,31 @@ static int tas2781_read_acpi(struct tasdevice_priv *p, const char *hid) /* Speaker id was needed for ASUS projects. */ ret = kstrtou32(sub, 16, &subid); if (!ret && upper_16_bits(subid) == PCI_VENDOR_ID_ASUSTEK) { - ret = devm_acpi_dev_add_driver_gpios(p->dev, - tas2781_speaker_id_gpios); - if (ret < 0) + ret = acpi_dev_add_driver_gpios(adev, tas2781_speaker_id_gpios); + if (ret < 0) { dev_err(p->dev, "Failed to add driver gpio %d.\n", ret); - p->speaker_id = devm_gpiod_get(p->dev, "speakerid", GPIOD_IN); - if (IS_ERR(p->speaker_id)) { - dev_err(p->dev, "Failed to get Speaker id.\n"); - ret = PTR_ERR(p->speaker_id); - goto err; + p->speaker_id = -1; + goto end_2563; } + + speaker_id = fwnode_gpiod_get_index(acpi_fwnode_handle(adev), + "speakerid", 0, GPIOD_IN, NULL); + if (!IS_ERR(speaker_id)) { + p->speaker_id = gpiod_get_value_cansleep(speaker_id); + dev_dbg(p->dev, "Got speaker id gpio from ACPI: %d.\n", + p->speaker_id); + gpiod_put(speaker_id); + } else { + p->speaker_id = -1; + ret = PTR_ERR(speaker_id); + dev_err(p->dev, "Get speaker id gpio failed %d.\n", + ret); + } + + acpi_dev_remove_driver_gpios(adev); } else { - p->speaker_id = NULL; + p->speaker_id = -1; } end_2563: @@ -432,23 +448,16 @@ static void tasdevice_dspfw_init(void *context) struct tas2781_hda *tas_hda = dev_get_drvdata(tas_priv->dev); struct tas2781_hda_i2c_priv *hda_priv = tas_hda->hda_priv; struct hda_codec *codec = tas_priv->codec; - int ret, spk_id; + int ret; tasdevice_dsp_remove(tas_priv); tas_priv->fw_state = TASDEVICE_DSP_FW_PENDING; - if (tas_priv->speaker_id != NULL) { - // Speaker id need to be checked for ASUS only. - spk_id = gpiod_get_value(tas_priv->speaker_id); - if (spk_id < 0) { - // Speaker id is not valid, use default. - dev_dbg(tas_priv->dev, "Wrong spk_id = %d\n", spk_id); - spk_id = 0; - } + if (tas_priv->speaker_id >= 0) { snprintf(tas_priv->coef_binaryname, sizeof(tas_priv->coef_binaryname), "TAS2XXX%04X%d.bin", lower_16_bits(codec->core.subsystem_id), - spk_id); + tas_priv->speaker_id); } else { snprintf(tas_priv->coef_binaryname, sizeof(tas_priv->coef_binaryname), @@ -483,7 +492,8 @@ static void tasdevice_dspfw_init(void *context) /* If calibrated data occurs error, dsp will still works with default * calibrated data inside algo. */ - hda_priv->save_calibration(tas_hda); + if (!hda_priv->skip_calibration) + hda_priv->save_calibration(tas_hda); } static void tasdev_fw_ready(const struct firmware *fmw, void *context) @@ -540,6 +550,7 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, void *master_data) { struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + struct tas2781_hda_i2c_priv *hda_priv = tas_hda->hda_priv; struct hda_component_parent *parent = master_data; struct hda_component *comp; struct hda_codec *codec; @@ -560,11 +571,22 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, case 0x1028: tas_hda->catlog_id = DELL; break; + case 0x103C: + tas_hda->catlog_id = HP; + break; default: tas_hda->catlog_id = LENOVO; break; } + /* + * Using ASUS ROG Xbox Ally X (RC73XA) UEFI calibration data + * causes audio dropouts during playback, use fallback data + * from DSP firmware as a workaround. + */ + if (codec->core.subsystem_id == 0x10431384) + hda_priv->skip_calibration = true; + pm_runtime_get_sync(dev); comp->dev = dev; diff --git a/sound/hda/core/intel-dsp-config.c b/sound/hda/core/intel-dsp-config.c index 2a9e35cddcf7c6..ddb349bc46bbd0 100644 --- a/sound/hda/core/intel-dsp-config.c +++ b/sound/hda/core/intel-dsp-config.c @@ -710,7 +710,8 @@ int snd_intel_dsp_driver_probe(struct pci_dev *pci) /* find the configuration for the specific device */ cfg = snd_intel_dsp_find_config(pci, config_table, ARRAY_SIZE(config_table)); if (!cfg) - return SND_INTEL_DSP_DRIVER_ANY; + return IS_ENABLED(CONFIG_SND_HDA_INTEL) ? + SND_INTEL_DSP_DRIVER_LEGACY : SND_INTEL_DSP_DRIVER_ANY; if (cfg->flags & FLAG_SOF) { if (cfg->flags & FLAG_SOF_ONLY_IF_SOUNDWIRE && diff --git a/sound/isa/wavefront/wavefront_midi.c b/sound/isa/wavefront/wavefront_midi.c index 1250ecba659a05..69d87c4cafaedf 100644 --- a/sound/isa/wavefront/wavefront_midi.c +++ b/sound/isa/wavefront/wavefront_midi.c @@ -278,6 +278,7 @@ static int snd_wavefront_midi_input_close(struct snd_rawmidi_substream *substrea return -EIO; guard(spinlock_irqsave)(&midi->open); + midi->substream_input[mpu] = NULL; midi->mode[mpu] &= ~MPU401_MODE_INPUT; return 0; @@ -300,6 +301,7 @@ static int snd_wavefront_midi_output_close(struct snd_rawmidi_substream *substre return -EIO; guard(spinlock_irqsave)(&midi->open); + midi->substream_output[mpu] = NULL; midi->mode[mpu] &= ~MPU401_MODE_OUTPUT; return 0; } diff --git a/sound/isa/wavefront/wavefront_synth.c b/sound/isa/wavefront/wavefront_synth.c index cd5c177943aa0d..0d78533e1cfd6b 100644 --- a/sound/isa/wavefront/wavefront_synth.c +++ b/sound/isa/wavefront/wavefront_synth.c @@ -950,9 +950,9 @@ wavefront_send_sample (snd_wavefront_t *dev, if (header->size) { dev->freemem = wavefront_freemem (dev); - if (dev->freemem < (int)header->size) { + if (dev->freemem < 0 || dev->freemem < header->size) { dev_err(dev->card->dev, - "insufficient memory to load %d byte sample.\n", + "insufficient memory to load %u byte sample.\n", header->size); return -ENOMEM; } diff --git a/sound/pci/ctxfi/ctamixer.c b/sound/pci/ctxfi/ctamixer.c index bb465859263693..c30162be27ee94 100644 --- a/sound/pci/ctxfi/ctamixer.c +++ b/sound/pci/ctxfi/ctamixer.c @@ -205,6 +205,7 @@ static int amixer_rsc_init(struct amixer *amixer, /* Set amixer specific operations */ amixer->rsc.ops = &amixer_basic_rsc_ops; + amixer->rsc.conj = 0; amixer->ops = &amixer_ops; amixer->input = NULL; amixer->sum = NULL; @@ -367,6 +368,7 @@ static int sum_rsc_init(struct sum *sum, return err; sum->rsc.ops = &sum_basic_rsc_ops; + sum->rsc.conj = 0; return 0; } diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf.c b/sound/pcmcia/pdaudiocf/pdaudiocf.c index 13419837dfb7ce..a3291e626440e0 100644 --- a/sound/pcmcia/pdaudiocf/pdaudiocf.c +++ b/sound/pcmcia/pdaudiocf/pdaudiocf.c @@ -131,7 +131,13 @@ static int snd_pdacf_probe(struct pcmcia_device *link) link->config_index = 1; link->config_regs = PRESENT_OPTION; - return pdacf_config(link); + err = pdacf_config(link); + if (err < 0) { + card_list[i] = NULL; + snd_card_free(card); + return err; + } + return 0; } diff --git a/sound/pcmcia/vx/vxpocket.c b/sound/pcmcia/vx/vxpocket.c index 2e09f2a513a6a0..9a5c9aa8eec4a0 100644 --- a/sound/pcmcia/vx/vxpocket.c +++ b/sound/pcmcia/vx/vxpocket.c @@ -284,7 +284,13 @@ static int vxpocket_probe(struct pcmcia_device *p_dev) vxp->p_dev = p_dev; - return vxpocket_config(p_dev); + err = vxpocket_config(p_dev); + if (err < 0) { + card_alloc &= ~(1 << i); + snd_card_free(card); + return err; + } + return 0; } static void vxpocket_detach(struct pcmcia_device *link) diff --git a/sound/soc/amd/acp/acp-i2s.c b/sound/soc/amd/acp/acp-i2s.c index 4ba0a66981ea9d..283a674c7e2c32 100644 --- a/sound/soc/amd/acp/acp-i2s.c +++ b/sound/soc/amd/acp/acp-i2s.c @@ -157,6 +157,8 @@ static int acp_i2s_set_tdm_slot(struct snd_soc_dai *dai, u32 tx_mask, u32 rx_mas spin_lock_irq(&chip->acp_lock); list_for_each_entry(stream, &chip->stream_list, list) { + if (dai->id != stream->dai_id) + continue; switch (chip->acp_rev) { case ACP_RN_PCI_ID: case ACP_RMB_PCI_ID: diff --git a/sound/soc/amd/acp/acp-legacy-common.c b/sound/soc/amd/acp/acp-legacy-common.c index 3078f459e0050b..4e477c48d4bdd1 100644 --- a/sound/soc/amd/acp/acp-legacy-common.c +++ b/sound/soc/amd/acp/acp-legacy-common.c @@ -219,7 +219,10 @@ static int set_acp_i2s_dma_fifo(struct snd_pcm_substream *substream, SP_PB_FIFO_ADDR_OFFSET; reg_fifo_addr = ACP_I2S_TX_FIFOADDR(chip); reg_fifo_size = ACP_I2S_TX_FIFOSIZE(chip); - phy_addr = I2S_SP_TX_MEM_WINDOW_START + stream->reg_offset; + if (chip->acp_rev >= ACP70_PCI_ID) + phy_addr = ACP7x_I2S_SP_TX_MEM_WINDOW_START; + else + phy_addr = I2S_SP_TX_MEM_WINDOW_START + stream->reg_offset; writel(phy_addr, chip->base + ACP_I2S_TX_RINGBUFADDR(chip)); } else { reg_dma_size = ACP_I2S_RX_DMA_SIZE(chip); @@ -227,7 +230,10 @@ static int set_acp_i2s_dma_fifo(struct snd_pcm_substream *substream, SP_CAPT_FIFO_ADDR_OFFSET; reg_fifo_addr = ACP_I2S_RX_FIFOADDR(chip); reg_fifo_size = ACP_I2S_RX_FIFOSIZE(chip); - phy_addr = I2S_SP_RX_MEM_WINDOW_START + stream->reg_offset; + if (chip->acp_rev >= ACP70_PCI_ID) + phy_addr = ACP7x_I2S_SP_RX_MEM_WINDOW_START; + else + phy_addr = I2S_SP_RX_MEM_WINDOW_START + stream->reg_offset; writel(phy_addr, chip->base + ACP_I2S_RX_RINGBUFADDR(chip)); } break; @@ -238,7 +244,10 @@ static int set_acp_i2s_dma_fifo(struct snd_pcm_substream *substream, BT_PB_FIFO_ADDR_OFFSET; reg_fifo_addr = ACP_BT_TX_FIFOADDR(chip); reg_fifo_size = ACP_BT_TX_FIFOSIZE(chip); - phy_addr = I2S_BT_TX_MEM_WINDOW_START + stream->reg_offset; + if (chip->acp_rev >= ACP70_PCI_ID) + phy_addr = ACP7x_I2S_BT_TX_MEM_WINDOW_START; + else + phy_addr = I2S_BT_TX_MEM_WINDOW_START + stream->reg_offset; writel(phy_addr, chip->base + ACP_BT_TX_RINGBUFADDR(chip)); } else { reg_dma_size = ACP_BT_RX_DMA_SIZE(chip); @@ -246,7 +255,10 @@ static int set_acp_i2s_dma_fifo(struct snd_pcm_substream *substream, BT_CAPT_FIFO_ADDR_OFFSET; reg_fifo_addr = ACP_BT_RX_FIFOADDR(chip); reg_fifo_size = ACP_BT_RX_FIFOSIZE(chip); - phy_addr = I2S_BT_TX_MEM_WINDOW_START + stream->reg_offset; + if (chip->acp_rev >= ACP70_PCI_ID) + phy_addr = ACP7x_I2S_BT_RX_MEM_WINDOW_START; + else + phy_addr = I2S_BT_RX_MEM_WINDOW_START + stream->reg_offset; writel(phy_addr, chip->base + ACP_BT_RX_RINGBUFADDR(chip)); } break; @@ -257,7 +269,10 @@ static int set_acp_i2s_dma_fifo(struct snd_pcm_substream *substream, HS_PB_FIFO_ADDR_OFFSET; reg_fifo_addr = ACP_HS_TX_FIFOADDR; reg_fifo_size = ACP_HS_TX_FIFOSIZE; - phy_addr = I2S_HS_TX_MEM_WINDOW_START + stream->reg_offset; + if (chip->acp_rev >= ACP70_PCI_ID) + phy_addr = ACP7x_I2S_HS_TX_MEM_WINDOW_START; + else + phy_addr = I2S_HS_TX_MEM_WINDOW_START + stream->reg_offset; writel(phy_addr, chip->base + ACP_HS_TX_RINGBUFADDR); } else { reg_dma_size = ACP_HS_RX_DMA_SIZE; @@ -265,7 +280,10 @@ static int set_acp_i2s_dma_fifo(struct snd_pcm_substream *substream, HS_CAPT_FIFO_ADDR_OFFSET; reg_fifo_addr = ACP_HS_RX_FIFOADDR; reg_fifo_size = ACP_HS_RX_FIFOSIZE; - phy_addr = I2S_HS_RX_MEM_WINDOW_START + stream->reg_offset; + if (chip->acp_rev >= ACP70_PCI_ID) + phy_addr = ACP7x_I2S_HS_RX_MEM_WINDOW_START; + else + phy_addr = I2S_HS_RX_MEM_WINDOW_START + stream->reg_offset; writel(phy_addr, chip->base + ACP_HS_RX_RINGBUFADDR); } break; diff --git a/sound/soc/amd/renoir/acp3x-pdm-dma.c b/sound/soc/amd/renoir/acp3x-pdm-dma.c index 95ac8c68003750..a560d06097d5e3 100644 --- a/sound/soc/amd/renoir/acp3x-pdm-dma.c +++ b/sound/soc/amd/renoir/acp3x-pdm-dma.c @@ -301,9 +301,11 @@ static int acp_pdm_dma_close(struct snd_soc_component *component, struct snd_pcm_substream *substream) { struct pdm_dev_data *adata = dev_get_drvdata(component->dev); + struct pdm_stream_instance *rtd = substream->runtime->private_data; disable_pdm_interrupts(adata->acp_base); adata->capture_stream = NULL; + kfree(rtd); return 0; } diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index f210a253da9f56..67f2fee1939804 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -416,6 +416,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "M6500RC"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M6500RE"), + } + }, { .driver_data = &acp6x_card, .matches = { @@ -535,6 +542,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "15NBC1011"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK PM1503CDA"), + } + }, { .driver_data = &acp6x_card, .matches = { @@ -626,6 +640,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_BOARD_NAME, "8BD6"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HP"), + DMI_MATCH(DMI_BOARD_NAME, "8EE4"), + } + }, { .driver_data = &acp6x_card, .matches = { @@ -661,6 +682,21 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 C7UCX"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HONOR"), + DMI_MATCH(DMI_PRODUCT_NAME, "GOH-X"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "RB"), + DMI_MATCH(DMI_BOARD_NAME, "XyloD5_RBU"), + } + }, + {} }; diff --git a/sound/soc/apple/Kconfig b/sound/soc/apple/Kconfig index d8dc2f1ccc83e0..d47b189e0d611d 100644 --- a/sound/soc/apple/Kconfig +++ b/sound/soc/apple/Kconfig @@ -1,5 +1,16 @@ menu "Apple" +config SND_SOC_APPLE_AOP_AUDIO + tristate "AOP audio driver" + depends on ARCH_APPLE || COMPILE_TEST + depends on RUST + select APPLE_AOP + select SND_DMAENGINE_PCM + help + This option enables an ASoC driver for sound devices connected to the AOP + co-processor on ARM Macs. This includes the built-in microphone on those + machines. + config SND_SOC_APPLE_MCA tristate "Apple Silicon MCA driver" depends on ARCH_APPLE || COMPILE_TEST @@ -8,4 +19,21 @@ config SND_SOC_APPLE_MCA This option enables an ASoC platform driver for MCA peripherals found on Apple Silicon SoCs. +config SND_SOC_APPLE_MACAUDIO + tristate "Sound support for Apple Silicon Macs" + depends on ARCH_APPLE || COMPILE_TEST + select SND_SOC_APPLE_MCA + select SND_SIMPLE_CARD_UTILS + select APPLE_ADMAC if DMADEVICES + select COMMON_CLK_APPLE_NCO if COMMON_CLK + select SND_SOC_TAS2764 if I2C + select SND_SOC_TAS2770 if I2C + select SND_SOC_CS42L83 if I2C + select SND_SOC_CS42L84 if I2C + select REGULATOR_FIXED_VOLTAGE if REGULATOR + help + This option enables an ASoC machine-level driver for Apple Silicon Macs + and it also enables the required SoC and codec drivers for overall + sound support on these machines. + endmenu diff --git a/sound/soc/apple/Makefile b/sound/soc/apple/Makefile index 1eb8fbef60c617..7d4901f407014d 100644 --- a/sound/soc/apple/Makefile +++ b/sound/soc/apple/Makefile @@ -1,3 +1,10 @@ +snd-soc-aop-y := aop_audio.o +obj-$(CONFIG_SND_SOC_APPLE_AOP_AUDIO) += snd-soc-aop.o + snd-soc-apple-mca-y := mca.o obj-$(CONFIG_SND_SOC_APPLE_MCA) += snd-soc-apple-mca.o + +snd-soc-macaudio-objs := macaudio.o + +obj-$(CONFIG_SND_SOC_APPLE_MACAUDIO) += snd-soc-macaudio.o diff --git a/sound/soc/apple/aop_audio.rs b/sound/soc/apple/aop_audio.rs new file mode 100644 index 00000000000000..8fff165fa9d5b9 --- /dev/null +++ b/sound/soc/apple/aop_audio.rs @@ -0,0 +1,711 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +#![recursion_limit = "2048"] + +//! Apple AOP audio driver +//! +//! Copyright (C) The Asahi Linux Contributors + +use core::sync::atomic::{AtomicU32, Ordering}; +use core::{mem, ptr, slice}; + +use kernel::{ + bindings, c_str, device, + device::property::FwNode, + device::Core, + error::from_err_ptr, + module_platform_driver, of, platform, + prelude::*, + soc::apple::aop::{from_fourcc, EPICService, AOP}, + str::CString, + sync::Arc, + types::{ARef, ForeignOwnable}, +}; + +use pin_init::Zeroable; + +const EPIC_SUBTYPE_WRAPPED_CALL: u16 = 0x20; +const CALLTYPE_AUDIO_ATTACH_DEVICE: u32 = 0xc3000002; +const CALLTYPE_AUDIO_SET_PROP: u32 = 0xc3000005; +const PDM_NUM_COEFFS: usize = 120; +const DECIMATION_RATIOS: [u8; 3] = [0xf, 5, 2]; +const COEFFICIENTS: [u8; PDM_NUM_COEFFS * mem::size_of::()] = [ + 0x88, 0x03, 0x00, 0x00, 0x82, 0x08, 0x00, 0x00, 0x51, 0x12, 0x00, 0x00, 0x0a, 0x23, 0x00, 0x00, + 0xce, 0x3d, 0x00, 0x00, 0x97, 0x66, 0x00, 0x00, 0x43, 0xa2, 0x00, 0x00, 0x9c, 0xf6, 0x00, 0x00, + 0x53, 0x6a, 0x01, 0x00, 0xe6, 0x04, 0x02, 0x00, 0x7e, 0xce, 0x02, 0x00, 0xae, 0xcf, 0x03, 0x00, + 0x2e, 0x11, 0x05, 0x00, 0x7d, 0x9b, 0x06, 0x00, 0x75, 0x76, 0x08, 0x00, 0xd8, 0xa8, 0x0a, 0x00, + 0xd2, 0x37, 0x0d, 0x00, 0x82, 0x26, 0x10, 0x00, 0x86, 0x75, 0x13, 0x00, 0x97, 0x22, 0x17, 0x00, + 0x39, 0x28, 0x1b, 0x00, 0x89, 0x7d, 0x1f, 0x00, 0x2e, 0x16, 0x24, 0x00, 0x69, 0xe2, 0x28, 0x00, + 0x56, 0xcf, 0x2d, 0x00, 0x51, 0xc7, 0x32, 0x00, 0x80, 0xb2, 0x37, 0x00, 0x87, 0x77, 0x3c, 0x00, + 0x4c, 0xfc, 0x40, 0x00, 0xd9, 0x26, 0x45, 0x00, 0x47, 0xde, 0x48, 0x00, 0xa0, 0x0b, 0x4c, 0x00, + 0xc1, 0x9a, 0x4e, 0x00, 0x1f, 0x7b, 0x50, 0x00, 0x68, 0xa0, 0x51, 0x00, 0x06, 0x03, 0x52, 0x00, + 0x4a, 0x25, 0x00, 0x00, 0x4c, 0xaf, 0x00, 0x00, 0xc0, 0x07, 0x02, 0x00, 0x45, 0x99, 0x04, 0x00, + 0x9a, 0x84, 0x08, 0x00, 0x7d, 0x38, 0x0d, 0x00, 0x5f, 0x1a, 0x11, 0x00, 0xd9, 0x81, 0x11, 0x00, + 0x80, 0x44, 0x0b, 0x00, 0x8e, 0xe5, 0xfb, 0xff, 0xca, 0x32, 0xe3, 0xff, 0x52, 0xc7, 0xc4, 0xff, + 0xa6, 0xbc, 0xa8, 0xff, 0x83, 0xe6, 0x9a, 0xff, 0xb8, 0x5b, 0xa8, 0xff, 0x6b, 0xae, 0xdb, 0xff, + 0xe7, 0xd8, 0x38, 0x00, 0x24, 0x42, 0xba, 0x00, 0x33, 0x20, 0x50, 0x01, 0x6e, 0xdc, 0xe2, 0x01, + 0x42, 0x23, 0x58, 0x02, 0x2c, 0x50, 0x99, 0x02, 0xcf, 0xfa, 0xff, 0xff, 0x53, 0x0a, 0xff, 0xff, + 0x66, 0x23, 0xfb, 0xff, 0xa0, 0x3e, 0xf4, 0xff, 0xe6, 0x68, 0xf0, 0xff, 0xb8, 0x35, 0xf7, 0xff, + 0x56, 0xec, 0x04, 0x00, 0x37, 0xa3, 0x09, 0x00, 0x00, 0xd4, 0xfe, 0xff, 0x78, 0xa3, 0xf5, 0xff, + 0x03, 0xbf, 0xfe, 0xff, 0x84, 0xd5, 0x0b, 0x00, 0xbe, 0x0b, 0x04, 0x00, 0x52, 0x54, 0xf2, 0xff, + 0x6d, 0x3f, 0xf8, 0xff, 0xc5, 0x7f, 0x0f, 0x00, 0xe6, 0x9e, 0x0c, 0x00, 0x79, 0x03, 0xef, 0xff, + 0xd5, 0x33, 0xed, 0xff, 0xec, 0xd1, 0x11, 0x00, 0x7d, 0x69, 0x1a, 0x00, 0xd6, 0x55, 0xee, 0xff, + 0x88, 0x66, 0xdc, 0xff, 0x57, 0x26, 0x10, 0x00, 0xc7, 0x8d, 0x2e, 0x00, 0x82, 0x2e, 0xf3, 0xff, + 0x63, 0x69, 0xc4, 0xff, 0xcd, 0x08, 0x07, 0x00, 0x35, 0x34, 0x4b, 0x00, 0xaf, 0x21, 0x02, 0x00, + 0x83, 0xb6, 0xa1, 0xff, 0xe2, 0xd5, 0xef, 0xff, 0x94, 0x9b, 0x76, 0x00, 0xf3, 0xd7, 0x25, 0x00, + 0xff, 0xfc, 0x67, 0xff, 0xe3, 0xac, 0xb6, 0xff, 0x52, 0x1b, 0xcc, 0x00, 0x3c, 0x8a, 0x8b, 0x00, + 0x9f, 0x0c, 0xcd, 0xfe, 0x5c, 0x68, 0xcc, 0xfe, 0x4d, 0xc5, 0x98, 0x02, 0x82, 0xcf, 0xfb, 0x06, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +]; +const FILTER_LENGTHS: u32 = 0x542c47; +const AUDIO_DEV_PDM0: u32 = from_fourcc(b"pdm0"); +const AUDIO_DEV_LPAI: u32 = from_fourcc(b"lpai"); +const AUDIO_DEV_HPAI: u32 = from_fourcc(b"hpai"); +const POWER_STATE_OFF: u32 = from_fourcc(b"idle"); +const POWER_STATE_IDLE: u32 = from_fourcc(b"pw1 "); +const POWER_STATE_ON: u32 = from_fourcc(b"pwrd"); + +#[repr(C, packed)] +#[derive(Clone, Copy, Default)] +struct AudioAttachDevice { + _zero0: u32, + unk0: u32, + calltype: u32, + _zero1: u64, + _zero2: u64, + _pad0: u32, + len: u64, + dev_id: u32, + _pad1: u32, +} + +impl AudioAttachDevice { + fn new(dev_id: u32) -> AudioAttachDevice { + AudioAttachDevice { + unk0: 0xFFFFFFFF, + calltype: CALLTYPE_AUDIO_ATTACH_DEVICE, + dev_id, + len: 0x2c, + ..AudioAttachDevice::default() + } + } +} + +#[repr(C, packed)] +#[derive(Clone, Copy, Default)] +struct LpaiChannelConfig { + unk1: u32, + unk2: u32, + unk3: u32, + unk4: u32, +} + +#[repr(C, packed)] +#[derive(Debug, Copy, Clone)] +struct PDMConfig { + bytes_per_sample: u32, + clock_source: u32, + pdm_frequency: u32, + pdmc_frequency: u32, + slow_clock_speed: u32, + fast_clock_speed: u32, + channel_polarity_select: u32, + channel_phase_select: u32, + unk1: u32, + unk2: u16, + ratio1: u8, + ratio2: u8, + ratio3: u8, + _pad0: u8, + filter_lengths: u32, + coeff_bulk: u32, + coeffs: [u8; PDM_NUM_COEFFS * mem::size_of::()], + unk3: u32, + mic_turn_on_time_ms: u32, + _zero0: u64, + _zero1: u64, + unk4: u32, + mic_settle_time_ms: u32, + _zero2: [u8; 69], // ????? +} + +unsafe impl Zeroable for PDMConfig {} + +#[repr(C, packed)] +#[derive(Debug, Copy, Clone)] +struct DecimatorConfig { + latency: u32, + ratio1: u8, + ratio2: u8, + ratio3: u8, + _pad0: u8, + filter_lengths: u32, + coeff_bulk: u32, + coeffs: [u8; PDM_NUM_COEFFS * mem::size_of::()], +} + +unsafe impl Zeroable for DecimatorConfig {} + +#[repr(C, packed)] +#[derive(Clone, Copy, Default, Debug)] +struct PowerSetting { + dev_id: u32, + cookie: u32, + _unk0: u32, + _zero0: u64, + target_pstate: u32, + unk1: u32, + _zero1: [u8; 20], +} + +impl PowerSetting { + fn new(dev_id: u32, cookie: u32, target_pstate: u32, unk1: u32) -> PowerSetting { + PowerSetting { + dev_id, + cookie, + target_pstate, + unk1, + ..PowerSetting::default() + } + } +} + +#[repr(C, packed)] +#[derive(Clone, Copy, Default, Debug)] +struct AudioSetDeviceProp { + _zero0: u32, + unk0: u32, + calltype: u32, + _zero1: u64, + _zero2: u64, + _pad0: u32, + len: u64, + dev_id: u32, + modifier: u32, + len2: u32, + data: T, +} + +impl AudioSetDeviceProp { + fn new(dev_id: u32, modifier: u32, data: T) -> AudioSetDeviceProp { + AudioSetDeviceProp { + unk0: 0xFFFFFFFF, + calltype: CALLTYPE_AUDIO_SET_PROP, + dev_id, + modifier, + len: mem::size_of::() as u64 + 0x30, + len2: mem::size_of::() as u32, + data, + ..AudioSetDeviceProp::default() + } + } +} + +unsafe impl Zeroable for AudioSetDeviceProp {} + +impl AudioSetDeviceProp { + fn try_init( + dev_id: u32, + modifier: u32, + data: impl Init, + ) -> impl Init, Error> + where + Error: From, + { + try_init!( + AudioSetDeviceProp { + unk0: 0xFFFFFFFF, + calltype: CALLTYPE_AUDIO_SET_PROP, + dev_id, + modifier, + len: mem::size_of::() as u64 + 0x30, + len2: mem::size_of::() as u32, + data <- data, + ..Zeroable::init_zeroed() + } + ) + } +} + +struct SndSocAopData { + dev: ARef, + adata: Arc, + service: EPICService, + pstate_cookie: AtomicU32, + fwnode: ARef, +} + +impl SndSocAopData { + fn new( + dev: ARef, + adata: Arc, + service: EPICService, + fwnode: ARef, + ) -> Result> { + Ok(Arc::new( + SndSocAopData { + dev, + adata, + service, + fwnode, + pstate_cookie: AtomicU32::new(1), + }, + GFP_KERNEL, + )?) + } + fn set_pdm_config(&self) -> Result<()> { + let pdm_cfg = init!(PDMConfig { + bytes_per_sample: 2, + clock_source: 0x706c6c20, // 'pll ' + pdm_frequency: 2400000, + pdmc_frequency: 24000000, + slow_clock_speed: 24000000, + fast_clock_speed: 24000000, + channel_polarity_select: 256, + channel_phase_select: 0, + unk1: 0xf7600, + unk2: 0, + ratio1: DECIMATION_RATIOS[0], + ratio2: DECIMATION_RATIOS[1], + ratio3: DECIMATION_RATIOS[2], + filter_lengths: FILTER_LENGTHS, + coeff_bulk: PDM_NUM_COEFFS as u32, + coeffs: COEFFICIENTS, + unk3: 1, + mic_turn_on_time_ms: 20, + unk4: 1, + mic_settle_time_ms: 50, + ..Zeroable::init_zeroed() + }); + let set_prop = AudioSetDeviceProp::::try_init(AUDIO_DEV_PDM0, 200, pdm_cfg); + let msg = KBox::try_init(set_prop, GFP_KERNEL)?; + let ret = self.epic_wrapped_call(msg.as_ref())?; + if ret != 0 { + dev_err!(self.dev, "Unable to set pdm config, return code {}", ret); + return Err(EIO); + } else { + Ok(()) + } + } + fn set_decimator_config(&self) -> Result<()> { + let pdm_cfg = init!(DecimatorConfig { + latency: 15, + ratio1: DECIMATION_RATIOS[0], + ratio2: DECIMATION_RATIOS[1], + ratio3: DECIMATION_RATIOS[2], + filter_lengths: FILTER_LENGTHS, + coeff_bulk: PDM_NUM_COEFFS as u32, + coeffs: COEFFICIENTS, + ..Zeroable::init_zeroed() + }); + let set_prop = + AudioSetDeviceProp::::try_init(AUDIO_DEV_PDM0, 210, pdm_cfg); + let msg = KBox::try_init(set_prop, GFP_KERNEL)?; + let ret = self.epic_wrapped_call(msg.as_ref())?; + if ret != 0 { + dev_err!( + self.dev, + "Unable to set decimator config, return code {}", + ret + ); + return Err(EIO); + } else { + Ok(()) + } + } + fn set_lpai_channel_cfg(&self) -> Result<()> { + let cfg = LpaiChannelConfig { + unk1: 7, + unk2: 7, + unk3: 1, + unk4: 7, + }; + let msg = AudioSetDeviceProp::new(AUDIO_DEV_LPAI, 301, cfg); + let ret = self.epic_wrapped_call(&msg)?; + if ret != 0 { + dev_err!( + self.dev, + "Unable to set lpai channel config, return code {}", + ret + ); + return Err(EIO); + } else { + Ok(()) + } + } + fn audio_attach_device(&self, dev_id: u32) -> Result<()> { + let msg = AudioAttachDevice::new(dev_id); + let ret = self.epic_wrapped_call(&msg)?; + if ret != 0 { + dev_err!( + self.dev, + "Unable to attach device {:?}, return code {}", + dev_id, + ret + ); + return Err(EIO); + } else { + Ok(()) + } + } + fn set_audio_power(&self, pstate: u32, unk1: u32) -> Result<()> { + let set_pstate = PowerSetting::new( + AUDIO_DEV_HPAI, + self.pstate_cookie.fetch_add(1, Ordering::Relaxed), + pstate, + unk1, + ); + let msg = AudioSetDeviceProp::new(AUDIO_DEV_HPAI, 202, set_pstate); + let ret = self.epic_wrapped_call(&msg)?; + if ret != 0 { + dev_err!( + self.dev, + "Unable to set power state {:?}, return code {}", + pstate, + ret + ); + return Err(EIO); + } else { + Ok(()) + } + } + fn epic_wrapped_call(&self, data: &T) -> Result { + let msg_bytes = + unsafe { slice::from_raw_parts(data as *const T as *const u8, mem::size_of::()) }; + self.adata + .epic_call(&self.service, EPIC_SUBTYPE_WRAPPED_CALL, msg_bytes) + } + fn request_dma_channel(&self) -> Result<*mut bindings::dma_chan> { + let res = unsafe { + from_err_ptr(bindings::dma_request_chan( + self.dev.as_raw(), + c_str!("dma").as_ptr() as _, + )) + }; + if res.is_err() { + dev_err!(self.dev, "Unable to get dma channel"); + } + res + } +} + +#[repr(transparent)] +struct SndSocAopDriver(*mut bindings::snd_card); + +fn copy_str(target: &mut [u8], source: &[u8]) { + for i in 0..source.len() { + target[i] = source[i]; + } +} + +unsafe fn dmaengine_slave_config( + chan: *mut bindings::dma_chan, + config: *mut bindings::dma_slave_config, +) -> i32 { + unsafe { + match (*(*chan).device).device_config { + Some(dc) => dc(chan, config), + None => ENOSYS.to_errno(), + } + } +} + +unsafe extern "C" fn aop_hw_params( + substream: *mut bindings::snd_pcm_substream, + params: *mut bindings::snd_pcm_hw_params, +) -> i32 { + let chan = unsafe { bindings::snd_dmaengine_pcm_get_chan(substream) }; + let mut slave_config = bindings::dma_slave_config::default(); + let ret = + unsafe { bindings::snd_hwparams_to_dma_slave_config(substream, params, &mut slave_config) }; + if ret < 0 { + return ret; + } + slave_config.src_port_window_size = 4; + unsafe { dmaengine_slave_config(chan, &mut slave_config) } +} + +unsafe extern "C" fn aop_pcm_open(substream: *mut bindings::snd_pcm_substream) -> i32 { + let data = unsafe { Arc::::borrow((*substream).private_data.cast()) }; + if let Err(e) = data.set_audio_power(POWER_STATE_IDLE, 0) { + dev_err!(data.dev, "Unable to enter 'pw1 ' state"); + return e.to_errno(); + } + let mut hwparams = bindings::snd_pcm_hardware { + info: bindings::SNDRV_PCM_INFO_MMAP + | bindings::SNDRV_PCM_INFO_MMAP_VALID + | bindings::SNDRV_PCM_INFO_INTERLEAVED, + formats: bindings::BINDINGS_SNDRV_PCM_FMTBIT_FLOAT_LE, + subformats: 0, + rates: bindings::SNDRV_PCM_RATE_48000, + rate_min: 48000, + rate_max: 48000, + channels_min: 3, + channels_max: 3, + periods_min: 2, + buffer_bytes_max: usize::MAX, + period_bytes_max: 0x4000, + periods_max: u32::MAX, + period_bytes_min: 256, + fifo_size: 16, + }; + let dma_chan = match data.request_dma_channel() { + Ok(dc) => dc, + Err(e) => return e.to_errno(), + }; + + if unsafe { (*substream).dma_buffer.dev.type_ == bindings::SNDRV_DMA_TYPE_UNKNOWN as _ } { + let ret = unsafe { + bindings::snd_pcm_set_managed_buffer( + substream, + bindings::SNDRV_DMA_TYPE_DEV_IRAM as i32, + (*(*dma_chan).device).dev, + 0, + 0, + ) + }; + if ret < 0 { + dev_err!(data.dev, "Unable to allocate dma buffers"); + unsafe { + bindings::dma_release_channel(dma_chan); + } + return ret; + } + } + + let ret = unsafe { + let mut dai_data = bindings::snd_dmaengine_dai_dma_data::default(); + bindings::snd_dmaengine_pcm_refine_runtime_hwparams( + substream, + &mut dai_data, + &mut hwparams, + dma_chan, + ) + }; + if ret != 0 { + dev_err!(data.dev, "Unable to refine hwparams"); + return ret; + } + if let Err(e) = data.set_audio_power(POWER_STATE_ON, 1) { + dev_err!(data.dev, "Unable to power mic on"); + return e.to_errno(); + } + unsafe { + (*(*substream).runtime).hw = hwparams; + bindings::snd_dmaengine_pcm_open(substream, dma_chan) + } +} + +unsafe extern "C" fn aop_pcm_prepare(_: *mut bindings::snd_pcm_substream) -> i32 { + 0 +} + +unsafe extern "C" fn aop_pcm_close(substream: *mut bindings::snd_pcm_substream) -> i32 { + let data = unsafe { Arc::::borrow((*substream).private_data.cast()) }; + if let Err(e) = data.set_audio_power(POWER_STATE_IDLE, 1) { + dev_err!(data.dev, "Unable to power mic off"); + return e.to_errno(); + } + let ret = unsafe { bindings::snd_dmaengine_pcm_close_release_chan(substream) }; + if ret != 0 { + dev_err!(data.dev, "Unable to close channel"); + return ret; + } + if let Err(e) = data.set_audio_power(POWER_STATE_OFF, 0) { + dev_err!(data.dev, "Unable to enter 'idle' power state"); + return e.to_errno(); + } + 0 +} + +unsafe extern "C" fn aop_pcm_free_private(pcm: *mut bindings::snd_pcm) { + unsafe { + Arc::::from_foreign((*pcm).private_data.cast()); + } +} + +impl SndSocAopDriver { + const VTABLE: bindings::snd_pcm_ops = bindings::snd_pcm_ops { + open: Some(aop_pcm_open), + close: Some(aop_pcm_close), + prepare: Some(aop_pcm_prepare), + trigger: Some(bindings::snd_dmaengine_pcm_trigger), + pointer: Some(bindings::snd_dmaengine_pcm_pointer), + ioctl: None, + hw_params: Some(aop_hw_params), + hw_free: None, + sync_stop: None, + get_time_info: None, + fill_silence: None, + copy: None, + page: None, + mmap: None, + ack: None, + }; + fn new(data: Arc) -> Result { + let mut this = SndSocAopDriver(ptr::null_mut()); + let ret = unsafe { + bindings::snd_card_new( + data.dev.as_raw(), + -1, + ptr::null(), + THIS_MODULE.as_ptr(), + 0, + &mut this.0, + ) + }; + if ret < 0 { + dev_err!(data.dev, "Unable to allocate sound card"); + return Err(Error::from_errno(ret)); + } + let chassis = data + .fwnode + .property_read::(c_str!("apple,chassis-name")) + .required_by(&data.dev)?; + let machine_kind = data + .fwnode + .property_read::(c_str!("apple,machine-kind")) + .required_by(&data.dev)?; + unsafe { + let name = b"aop_audio\0"; + let target = (*this.0).driver.as_mut(); + copy_str(target, name.as_ref()); + } + unsafe { + let prefix = b"Apple"; + let target = (*this.0).id.as_mut(); + copy_str(target, prefix.as_ref()); + let mut ptr = prefix.len(); + copy_str(&mut target[ptr..], chassis.as_bytes_with_nul()); + ptr += chassis.len(); + let suffix = b"HPAI\0"; + copy_str(&mut target[ptr..], suffix); + } + let longname_suffix = b"High-Power Audio Interface\0"; + let mut machine_name = KVec::with_capacity( + chassis.len() + 2 + machine_kind.len() + longname_suffix.len(), + GFP_KERNEL, + )?; + machine_name.extend_from_slice(machine_kind.as_bytes_with_nul(), GFP_KERNEL)?; + let last_item = machine_name.len() - 1; + machine_name[last_item] = b' '; + machine_name.extend_from_slice(chassis.as_bytes_with_nul(), GFP_KERNEL)?; + let last_item = machine_name.len() - 1; + machine_name[last_item] = b' '; + unsafe { + let target = (*this.0).shortname.as_mut(); + copy_str(target, machine_name.as_ref()); + let ptr = machine_name.len(); + let suffix = b"HPAI\0"; + copy_str(&mut target[ptr..], suffix); + } + machine_name.extend_from_slice(longname_suffix, GFP_KERNEL)?; + unsafe { + let target = (*this.0).longname.as_mut(); + copy_str(target, machine_name.as_ref()); + } + + let mut pcm = ptr::null_mut(); + let ret = + unsafe { bindings::snd_pcm_new(this.0, machine_name.as_ptr() as _, 0, 0, 1, &mut pcm) }; + if ret < 0 { + dev_err!(data.dev, "Unable to allocate PCM device"); + return Err(Error::from_errno(ret)); + } + + unsafe { + bindings::snd_pcm_set_ops( + pcm, + bindings::SNDRV_PCM_STREAM_CAPTURE as i32, + &Self::VTABLE, + ); + } + + unsafe { + (*pcm).private_data = data.clone().into_foreign() as _; + (*pcm).private_free = Some(aop_pcm_free_private); + (*pcm).info_flags = 0; + let name = c_str!("aop_audio"); + copy_str((*pcm).name.as_mut(), name.as_ref()); + } + + let ret = unsafe { bindings::snd_card_register(this.0) }; + if ret < 0 { + dev_err!(data.dev, "Unable to register sound card"); + return Err(Error::from_errno(ret)); + } + Ok(this) + } +} + +impl Drop for SndSocAopDriver { + fn drop(&mut self) { + if self.0 != ptr::null_mut() { + unsafe { + bindings::snd_card_free(self.0); + } + } + } +} + +unsafe impl Send for SndSocAopDriver {} +unsafe impl Sync for SndSocAopDriver {} + +kernel::of_device_table!( + OF_TABLE, + MODULE_OF_TABLE, + (), + [(of::DeviceId::new(c_str!("apple,aop-audio")), ())] +); + +impl platform::Driver for SndSocAopDriver { + type IdInfo = (); + + const OF_ID_TABLE: Option> = Some(&OF_TABLE); + + fn probe( + pdev: &platform::Device, + _info: Option<&()>, + ) -> Result>> { + let dev = ARef::::from(pdev.as_ref()); + let parent = pdev.as_ref().parent().unwrap(); + // SAFETY: our parent is AOP, and AopDriver is repr(transparent) for Arc + let adata_ptr = unsafe { Pin::>>::borrow(parent.get_drvdata()) }; + let adata = (&*adata_ptr).clone(); + // SAFETY: AOP sets the platform data correctly + let svc = unsafe { *((*dev.as_raw()).platform_data as *const EPICService) }; + let parent_fwnode = parent.fwnode().ok_or(ENOENT)?; + let fwnode = parent_fwnode + .get_child_by_name(c_str!("audio")) + .ok_or(EIO)?; + let audio = *module_parameters::mic_check_123.value() != 0; + if !audio && parent_fwnode.property_present(c_str!("apple,no-beamforming")) { + return Err(ENODEV); + } + let data = SndSocAopData::new(dev, adata, svc, fwnode)?; + for dev in [AUDIO_DEV_PDM0, AUDIO_DEV_HPAI, AUDIO_DEV_LPAI] { + data.audio_attach_device(dev)?; + } + data.set_lpai_channel_cfg()?; + data.set_pdm_config()?; + data.set_decimator_config()?; + Ok(Box::pin(SndSocAopDriver::new(data)?, GFP_KERNEL)?) + } +} + +module_platform_driver! { + type: SndSocAopDriver, + name: "snd_soc_apple_aop", + description: "AOP microphone capture driver", + license: "Dual MIT/GPL", + alias: ["platform:snd_soc_apple_aop"], + params: { + mic_check_123: u8 { + default: 0, + description: "Enable mics without user space handling", + }, + }, +} diff --git a/sound/soc/apple/macaudio.c b/sound/soc/apple/macaudio.c new file mode 100644 index 00000000000000..1a32679f41ea90 --- /dev/null +++ b/sound/soc/apple/macaudio.c @@ -0,0 +1,1684 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * ASoC machine driver for Apple Silicon Macs + * + * Copyright (C) The Asahi Linux Contributors + * + * Based on sound/soc/qcom/{sc7180.c|common.c} + * Copyright (c) 2018, Linaro Limited. + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + * + * + * The platform driver has independent frontend and backend DAIs with the + * option of routing backends to any of the frontends. The platform + * driver configures the routing based on DPCM couplings in ASoC runtime + * structures, which in turn are determined from DAPM paths by ASoC. But the + * platform driver doesn't supply relevant DAPM paths and leaves that up for + * the machine driver to fill in. The filled-in virtual topology can be + * anything as long as any backend isn't connected to more than one frontend + * at any given time. (The limitation is due to the unsupported case of + * reparenting of live BEs.) + */ + +/* #define DEBUG */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRIVER_NAME "snd-soc-macaudio" + +/* + * CPU side is bit and frame clock provider + * I2S has both clocks inverted + */ +#define MACAUDIO_DAI_FMT (SND_SOC_DAIFMT_I2S | \ + SND_SOC_DAIFMT_CBC_CFC | \ + SND_SOC_DAIFMT_GATED | \ + SND_SOC_DAIFMT_IB_IF) +#define MACAUDIO_JACK_MASK (SND_JACK_HEADSET | SND_JACK_HEADPHONE) +#define MACAUDIO_SLOTWIDTH 32 +/* + * Maximum BCLK frequency + * + * Codec maximums: + * CS42L42 26.0 MHz + * TAS2770 27.1 MHz + * TAS2764 24.576 MHz + */ +#define MACAUDIO_MAX_BCLK_FREQ 24576000 + +#define SPEAKER_MAGIC_VALUE (s32)0xdec1be15 +/* milliseconds */ +#define SPEAKER_LOCK_TIMEOUT 250 + +enum macaudio_amp_type { + AMP_NONE, + AMP_TAS5770, + AMP_SN012776, + AMP_SSM3515, +}; + +enum macaudio_spkr_config { + SPKR_NONE, /* No speakers */ + SPKR_1W, /* 1 woofer / ch */ + SPKR_2W, /* 2 woofers / ch */ + SPKR_1W1T, /* 1 woofer + 1 tweeter / ch */ + SPKR_2W1T, /* 2 woofers + 1 tweeter / ch */ +}; + +struct macaudio_platform_cfg { + bool enable_speakers; + enum macaudio_amp_type amp; + enum macaudio_spkr_config speakers; + bool stereo; + int amp_gain; + int safe_vol; +}; + +static const char *volume_control_names[] = { + [AMP_TAS5770] = "* Speaker Playback Volume", + [AMP_SN012776] = "* Speaker Volume", + [AMP_SSM3515] = "* DAC Playback Volume", +}; + +#define SN012776_0DB 201 +#define SN012776_DB(x) (SN012776_0DB + 2 * (x)) +/* Same as SN012776 */ +#define TAS5770_0DB SN012776_0DB +#define TAS5770_DB(x) SN012776_DB(x) + +#define SSM3515_0DB (255 - 64) /* +24dB max, steps of 3/8 dB */ +#define SSM3515_DB(x) (SSM3515_0DB + (8 * (x) / 3)) + +struct macaudio_snd_data { + struct snd_soc_card card; + struct snd_soc_jack jack; + int jack_plugin_state; + + const struct macaudio_platform_cfg *cfg; + bool has_speakers; + bool has_sense; + bool has_safety; + unsigned int max_channels; + + struct macaudio_link_props { + /* frontend props */ + unsigned int bclk_ratio; + bool is_sense; + + /* backend props */ + bool is_speakers; + bool is_headphones; + unsigned int tdm_mask; + } *link_props; + + int speaker_sample_rate; + struct snd_kcontrol *speaker_sample_rate_kctl; + + struct mutex volume_lock_mutex; + bool speaker_volume_unlocked; + bool speaker_volume_was_locked; + struct snd_kcontrol *speaker_lock_kctl; + struct snd_ctl_file *speaker_lock_owner; + u64 bes_active; + bool speaker_lock_timeout_enabled; + ktime_t speaker_lock_timeout; + ktime_t speaker_lock_remain; + struct delayed_work lock_timeout_work; + struct work_struct lock_update_work; + +}; + +static int please_blow_up_my_speakers; +module_param(please_blow_up_my_speakers, int, 0644); +MODULE_PARM_DESC(please_blow_up_my_speakers, "Allow unsafe or untested operating configurations"); + +SND_SOC_DAILINK_DEFS(primary, + DAILINK_COMP_ARRAY(COMP_CPU("mca-pcm-0")), // CPU + DAILINK_COMP_ARRAY(COMP_DUMMY()), // CODEC + DAILINK_COMP_ARRAY(COMP_EMPTY())); // platform (filled at runtime) + +SND_SOC_DAILINK_DEFS(secondary, + DAILINK_COMP_ARRAY(COMP_CPU("mca-pcm-1")), // CPU + DAILINK_COMP_ARRAY(COMP_DUMMY()), // CODEC + DAILINK_COMP_ARRAY(COMP_EMPTY())); + +SND_SOC_DAILINK_DEFS(sense, + DAILINK_COMP_ARRAY(COMP_CPU("mca-pcm-2")), // CPU + DAILINK_COMP_ARRAY(COMP_DUMMY()), // CODEC + DAILINK_COMP_ARRAY(COMP_EMPTY())); + +static struct snd_soc_dai_link macaudio_fe_links[] = { + { + .name = "Primary", + .stream_name = "Primary", + .dynamic = 1, + .dpcm_merged_rate = 1, + .dpcm_merged_chan = 1, + .dpcm_merged_format = 1, + .dai_fmt = MACAUDIO_DAI_FMT, + SND_SOC_DAILINK_REG(primary), + }, + { + .name = "Secondary", + .stream_name = "Secondary", + .dynamic = 1, + .dpcm_merged_rate = 1, + .dpcm_merged_chan = 1, + .dpcm_merged_format = 1, + .dai_fmt = MACAUDIO_DAI_FMT, + .playback_only = 1, + SND_SOC_DAILINK_REG(secondary), + }, + { + .name = "Speaker Sense", + .stream_name = "Speaker Sense", + .capture_only = 1, + .dynamic = 1, + .dai_fmt = (SND_SOC_DAIFMT_I2S | \ + SND_SOC_DAIFMT_CBP_CFP | \ + SND_SOC_DAIFMT_GATED | \ + SND_SOC_DAIFMT_IB_IF), + SND_SOC_DAILINK_REG(sense), + }, +}; + +static struct macaudio_link_props macaudio_fe_link_props[] = { + { + /* + * Primary FE + * + * The bclk ratio at 64 for the primary frontend is important + * to ensure that the headphones codec's idea of left and right + * in a stereo stream over I2S fits in nicely with everyone else's. + * (This is until the headphones codec's driver supports + * set_tdm_slot.) + * + * The low bclk ratio precludes transmitting more than two + * channels over I2S, but that's okay since there is the secondary + * FE for speaker arrays anyway. + */ + .bclk_ratio = 64, + }, + { + /* + * Secondary FE + * + * Here we want frames plenty long to be able to drive all + * those fancy speaker arrays. + */ + .bclk_ratio = 256, + }, + { + .is_sense = 1, + } +}; + +static void macaudio_vlimit_unlock(struct macaudio_snd_data *ma, bool unlock) +{ + int ret, max; + const char *name = volume_control_names[ma->cfg->amp]; + + if (!name) { + WARN_ON_ONCE(1); + return; + } + + switch (ma->cfg->amp) { + case AMP_NONE: + WARN_ON_ONCE(1); + return; + case AMP_TAS5770: + if (unlock) + max = TAS5770_0DB; + else + max = 1; //TAS5770_DB(ma->cfg->safe_vol); + break; + case AMP_SN012776: + if (unlock) + max = SN012776_0DB; + else + max = 1; //SN012776_DB(ma->cfg->safe_vol); + break; + case AMP_SSM3515: + if (unlock) + max = SSM3515_0DB; + else + max = SSM3515_DB(ma->cfg->safe_vol); + break; + } + + ret = snd_soc_limit_volume(&ma->card, name, max); + if (ret < 0) + dev_err(ma->card.dev, "Failed to %slock volume %s: %d\n", + unlock ? "un" : "", name, ret); +} + +static void macaudio_vlimit_update(struct macaudio_snd_data *ma) +{ + int i; + bool unlock = true; + struct snd_kcontrol *kctl; + const char *reason; + + /* Do nothing if there is no safety configured */ + if (!ma->has_safety) + return; + + /* Check that someone is holding the main lock */ + if (!ma->speaker_lock_owner) { + reason = "Main control not locked"; + unlock = false; + } + + /* Check that the control has been pinged within the timeout */ + if (ma->speaker_lock_remain <= 0) { + reason = "Lock timeout"; + unlock = false; + } + + /* Check that *every* limited control is locked by the same owner */ + list_for_each_entry(kctl, &ma->card.snd_card->controls, list) { + if(!snd_soc_control_matches(kctl, volume_control_names[ma->cfg->amp])) + continue; + + for (i = 0; i < kctl->count; i++) { + if (kctl->vd[i].owner != ma->speaker_lock_owner) { + reason = "Not all child controls locked by the same process"; + unlock = false; + } + } + } + + + if (unlock != ma->speaker_volume_unlocked) { + if (unlock) { + dev_info(ma->card.dev, "Speaker volumes unlocked\n"); + } else { + dev_info(ma->card.dev, "Speaker volumes locked: %s\n", reason); + ma->speaker_volume_was_locked = true; + } + + macaudio_vlimit_unlock(ma, unlock); + ma->speaker_volume_unlocked = unlock; + snd_ctl_notify(ma->card.snd_card, SNDRV_CTL_EVENT_MASK_VALUE, + &ma->speaker_lock_kctl->id); + } +} + +static void macaudio_vlimit_enable_timeout(struct macaudio_snd_data *ma) +{ + mutex_lock(&ma->volume_lock_mutex); + + if (ma->speaker_lock_timeout_enabled) { + mutex_unlock(&ma->volume_lock_mutex); + return; + } + + if (ma->speaker_lock_remain > 0) { + ma->speaker_lock_timeout = ktime_add(ktime_get(), ma->speaker_lock_remain); + schedule_delayed_work(&ma->lock_timeout_work, usecs_to_jiffies(ktime_to_us(ma->speaker_lock_remain))); + dev_dbg(ma->card.dev, "Enabling volume limit timeout: %ld us left\n", + (long)ktime_to_us(ma->speaker_lock_remain)); + } + + macaudio_vlimit_update(ma); + + ma->speaker_lock_timeout_enabled = true; + mutex_unlock(&ma->volume_lock_mutex); +} + +static void macaudio_vlimit_disable_timeout(struct macaudio_snd_data *ma) +{ + ktime_t now; + + mutex_lock(&ma->volume_lock_mutex); + + if (!ma->speaker_lock_timeout_enabled) { + mutex_unlock(&ma->volume_lock_mutex); + return; + } + + now = ktime_get(); + + cancel_delayed_work(&ma->lock_timeout_work); + + if (ktime_after(now, ma->speaker_lock_timeout)) + ma->speaker_lock_remain = 0; + else if (ma->speaker_lock_remain > 0) + ma->speaker_lock_remain = ktime_sub(ma->speaker_lock_timeout, now); + + dev_dbg(ma->card.dev, "Disabling volume limit timeout: %ld us left\n", + (long)ktime_to_us(ma->speaker_lock_remain)); + + macaudio_vlimit_update(ma); + + ma->speaker_lock_timeout_enabled = false; + + mutex_unlock(&ma->volume_lock_mutex); +} + +static void macaudio_vlimit_timeout_work(struct work_struct *wrk) +{ + struct macaudio_snd_data *ma = container_of(to_delayed_work(wrk), + struct macaudio_snd_data, lock_timeout_work); + + mutex_lock(&ma->volume_lock_mutex); + + ma->speaker_lock_remain = 0; + macaudio_vlimit_update(ma); + + mutex_unlock(&ma->volume_lock_mutex); +} + +static void macaudio_vlimit_update_work(struct work_struct *wrk) +{ + struct macaudio_snd_data *ma = container_of(wrk, + struct macaudio_snd_data, lock_update_work); + + if (ma->bes_active) + macaudio_vlimit_enable_timeout(ma); + else + macaudio_vlimit_disable_timeout(ma); +} + +static int macaudio_copy_link(struct device *dev, struct snd_soc_dai_link *target, + struct snd_soc_dai_link *source) +{ + memcpy(target, source, sizeof(struct snd_soc_dai_link)); + + target->cpus = devm_kmemdup(dev, target->cpus, + sizeof(*target->cpus) * target->num_cpus, + GFP_KERNEL); + target->codecs = devm_kmemdup(dev, target->codecs, + sizeof(*target->codecs) * target->num_codecs, + GFP_KERNEL); + target->platforms = devm_kmemdup(dev, target->platforms, + sizeof(*target->platforms) * target->num_platforms, + GFP_KERNEL); + + if (!target->cpus || !target->codecs || !target->platforms) + return -ENOMEM; + + return 0; +} + +static int macaudio_parse_of_component(struct device_node *node, int index, + struct snd_soc_dai_link_component *comp) +{ + struct of_phandle_args args; + int ret; + + ret = of_parse_phandle_with_args(node, "sound-dai", "#sound-dai-cells", + index, &args); + if (ret) + return ret; + comp->of_node = args.np; + return snd_soc_get_dai_name(&args, &comp->dai_name); +} + +/* + * Parse one DPCM backend from the devicetree. This means taking one + * of the CPU DAIs and combining it with one or more CODEC DAIs. + */ +static int macaudio_parse_of_be_dai_link(struct macaudio_snd_data *ma, + struct snd_soc_dai_link *link, + int be_index, int ncodecs_per_be, + struct device_node *cpu, + struct device_node *codec) +{ + struct snd_soc_dai_link_component *comp; + struct device *dev = ma->card.dev; + int codec_base = be_index * ncodecs_per_be; + int ret, i; + + link->no_pcm = 1; + + link->dai_fmt = MACAUDIO_DAI_FMT; + + link->num_codecs = ncodecs_per_be; + link->codecs = devm_kcalloc(dev, ncodecs_per_be, + sizeof(*comp), GFP_KERNEL); + link->num_cpus = 1; + link->cpus = devm_kzalloc(dev, sizeof(*comp), GFP_KERNEL); + + if (!link->codecs || !link->cpus) + return -ENOMEM; + + link->num_platforms = 0; + + for_each_link_codecs(link, i, comp) { + ret = macaudio_parse_of_component(codec, codec_base + i, comp); + if (ret) + return dev_err_probe(ma->card.dev, ret, "parsing CODEC DAI of link '%s' at %pOF\n", + link->name, codec); + } + + ret = macaudio_parse_of_component(cpu, be_index, link->cpus); + if (ret) + return dev_err_probe(ma->card.dev, ret, "parsing CPU DAI of link '%s' at %pOF\n", + link->name, codec); + + link->name = link->cpus[0].dai_name; + + return 0; +} + +static int macaudio_parse_of(struct macaudio_snd_data *ma) +{ + struct device_node *codec = NULL; + struct device_node *cpu = NULL; + struct device_node *np = NULL; + struct device_node *platform = NULL; + struct snd_soc_dai_link *link = NULL; + struct snd_soc_card *card = &ma->card; + struct device *dev = card->dev; + struct macaudio_link_props *link_props; + int ret, num_links, i; + + ret = snd_soc_of_parse_card_name(card, "model"); + if (ret) { + dev_err_probe(dev, ret, "parsing card name\n"); + return ret; + } + /* + * Set long_name to prevent snd_soc_set_dmi_name() from setting one from + * make believe data u-boot provides in its SMBIOS emulation. + */ + card->long_name = card->name; + + /* Populate links, start with the fixed number of FE links */ + num_links = ARRAY_SIZE(macaudio_fe_links); + + /* Now add together the (dynamic) number of BE links */ + for_each_available_child_of_node(dev->of_node, np) { + int num_cpus; + + cpu = of_get_child_by_name(np, "cpu"); + if (!cpu) { + ret = dev_err_probe(dev, -EINVAL, + "missing CPU DAI node at %pOF\n", np); + goto err_free; + } + + num_cpus = of_count_phandle_with_args(cpu, "sound-dai", + "#sound-dai-cells"); + + if (num_cpus <= 0) { + ret = dev_err_probe(card->dev, -EINVAL, + "missing sound-dai property at %pOF\n", cpu); + goto err_free; + } + of_node_put(cpu); + cpu = NULL; + + /* Each CPU specified counts as one BE link */ + num_links += num_cpus; + } + + /* Allocate the DAI link array */ + card->dai_link = devm_kcalloc(dev, num_links, sizeof(*link), GFP_KERNEL); + ma->link_props = devm_kcalloc(dev, num_links, sizeof(*ma->link_props), GFP_KERNEL); + if (!card->dai_link || !ma->link_props) + return -ENOMEM; + + link = card->dai_link; + link_props = ma->link_props; + + for (i = 0; i < ARRAY_SIZE(macaudio_fe_links); i++) { + ret = macaudio_copy_link(dev, link, &macaudio_fe_links[i]); + if (ret) + goto err_free; + + memcpy(link_props, &macaudio_fe_link_props[i], sizeof(struct macaudio_link_props)); + link++; link_props++; + } + + for (i = 0; i < num_links; i++) + card->dai_link[i].id = i; + + /* We might disable the speakers, so count again */ + num_links = ARRAY_SIZE(macaudio_fe_links); + + /* Fill in the BEs */ + for_each_available_child_of_node(dev->of_node, np) { + const char *link_name; + bool speakers; + int be_index, num_codecs, num_bes, ncodecs_per_cpu, nchannels; + unsigned int left_mask, right_mask; + + ret = of_property_read_string(np, "link-name", &link_name); + if (ret) { + dev_err_probe(card->dev, ret, "missing link name\n"); + goto err_free; + } + + dev_dbg(ma->card.dev, "parsing link '%s'\n", link_name); + + speakers = !strcmp(link_name, "Speaker") + || !strcmp(link_name, "Speakers"); + if (speakers) { + if (!ma->cfg->enable_speakers && !please_blow_up_my_speakers) { + dev_err(card->dev, "driver can't assure safety on this model, disabling speakers\n"); + continue; + } + ma->has_speakers = 1; + if (ma->cfg->amp != AMP_SSM3515 && ma->cfg->safe_vol != 0) + ma->has_sense = 1; + } + + cpu = of_get_child_by_name(np, "cpu"); + codec = of_get_child_by_name(np, "codec"); + + if (!codec || !cpu) { + ret = dev_err_probe(dev, -EINVAL, + "missing DAI specifications for '%s'\n", link_name); + goto err_free; + } + + num_bes = of_count_phandle_with_args(cpu, "sound-dai", + "#sound-dai-cells"); + if (num_bes <= 0) { + ret = dev_err_probe(card->dev, -EINVAL, + "missing sound-dai property at %pOF\n", cpu); + goto err_free; + } + + num_codecs = of_count_phandle_with_args(codec, "sound-dai", + "#sound-dai-cells"); + if (num_codecs <= 0) { + ret = dev_err_probe(card->dev, -EINVAL, + "missing sound-dai property at %pOF\n", codec); + goto err_free; + } + + dev_dbg(ma->card.dev, "link '%s': %d CPUs %d CODECs\n", + link_name, num_bes, num_codecs); + + if (num_codecs % num_bes != 0) { + ret = dev_err_probe(card->dev, -EINVAL, + "bad combination of CODEC (%d) and CPU (%d) number at %pOF\n", + num_codecs, num_bes, np); + goto err_free; + } + + /* + * Now parse the cpu/codec lists into a number of DPCM backend links. + * In each link there will be one DAI from the cpu list paired with + * an evenly distributed number of DAIs from the codec list. (As is + * the binding semantics.) + */ + ncodecs_per_cpu = num_codecs / num_bes; + nchannels = num_codecs * (speakers ? 1 : 2); + + /* Save the max number of channels on the platform */ + if (nchannels > ma->max_channels) + ma->max_channels = nchannels; + + /* + * If there is a single speaker, assign two channels to it, because + * it can do downmix. + */ + if (nchannels < 2) + nchannels = 2; + + left_mask = 0; + for (i = 0; i < nchannels; i += 2) + left_mask = left_mask << 2 | 1; + right_mask = left_mask << 1; + + for (be_index = 0; be_index < num_bes; be_index++) { + /* + * Set initial link name to be overwritten by a BE-specific + * name later so that we can use at least use the provisional + * name in error messages. + */ + link->name = link_name; + + ret = macaudio_parse_of_be_dai_link(ma, link, be_index, + ncodecs_per_cpu, cpu, codec); + if (ret) + goto err_free; + + link_props->is_speakers = speakers; + link_props->is_headphones = !speakers; + + if (num_bes == 2) + /* This sound peripheral is split between left and right BE */ + link_props->tdm_mask = be_index ? right_mask : left_mask; + else + /* One BE covers all of the peripheral */ + link_props->tdm_mask = left_mask | right_mask; + + /* Steal platform OF reference for use in FE links later */ + platform = link->cpus->of_node; + + link++; link_props++; + } + + of_node_put(codec); + of_node_put(cpu); + cpu = codec = NULL; + + num_links += num_bes; + } + + for (i = 0; i < ARRAY_SIZE(macaudio_fe_links); i++) + card->dai_link[i].platforms->of_node = platform; + + /* Skip the speaker sense PCM link if this amp has no sense (or no speakers) */ + if (!ma->has_sense) { + for (i = 0; i < ARRAY_SIZE(macaudio_fe_links); i++) { + if (ma->link_props[i].is_sense) { + memmove(&card->dai_link[i], &card->dai_link[i + 1], + (num_links - i - 1) * sizeof (struct snd_soc_dai_link)); + num_links--; + break; + } + } + } + + card->num_links = num_links; + + return 0; + +err_free: + of_node_put(codec); + of_node_put(cpu); + of_node_put(np); + + if (!card->dai_link) + return ret; + + for (i = 0; i < num_links; i++) { + /* + * TODO: If we don't go through this path are the references + * freed inside ASoC? + */ + snd_soc_of_put_dai_link_codecs(&card->dai_link[i]); + snd_soc_of_put_dai_link_cpus(&card->dai_link[i]); + } + + return ret; +} + +static int macaudio_get_runtime_bclk_ratio(struct snd_pcm_substream *substream) +{ + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(rtd->card); + struct snd_soc_dpcm *dpcm; + + /* + * If this is a FE, look it up in link_props directly. + * If this is a BE, look it up in the respective FE. + */ + if (!rtd->dai_link->no_pcm) + return ma->link_props[rtd->dai_link->id].bclk_ratio; + + for_each_dpcm_fe(rtd, substream->stream, dpcm) { + int fe_id = dpcm->fe->dai_link->id; + + return ma->link_props[fe_id].bclk_ratio; + } + + return 0; +} + +static int macaudio_dpcm_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params) +{ + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(rtd->card); + struct macaudio_link_props *props = &ma->link_props[rtd->dai_link->id]; + struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, 0); + struct snd_interval *rate = hw_param_interval(params, + SNDRV_PCM_HW_PARAM_RATE); + int bclk_ratio = macaudio_get_runtime_bclk_ratio(substream); + int i; + + if (props->is_sense) { + rate->min = rate->max = cpu_dai->symmetric_rate; + return 0; + } + + /* Speakers BE */ + if (props->is_speakers) { + if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) { + /* Sense PCM: keep the existing BE rate (0 if not already running) */ + rate->min = rate->max = cpu_dai->symmetric_rate; + + return 0; + } else { + /* + * Set the sense PCM rate control to inform userspace of the + * new sample rate. + */ + ma->speaker_sample_rate = params_rate(params); + snd_ctl_notify(ma->card.snd_card, SNDRV_CTL_EVENT_MASK_VALUE, + &ma->speaker_sample_rate_kctl->id); + } + } + + if (bclk_ratio) { + struct snd_soc_dai *dai; + int mclk = params_rate(params) * bclk_ratio; + + for_each_rtd_codec_dais(rtd, i, dai) { + snd_soc_dai_set_sysclk(dai, 0, mclk, SND_SOC_CLOCK_IN); + snd_soc_dai_set_bclk_ratio(dai, bclk_ratio); + } + + snd_soc_dai_set_sysclk(cpu_dai, 0, mclk, SND_SOC_CLOCK_OUT); + snd_soc_dai_set_bclk_ratio(cpu_dai, bclk_ratio); + } + + return 0; +} + +static int macaudio_fe_startup(struct snd_pcm_substream *substream) +{ + + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(rtd->card); + struct macaudio_link_props *props = &ma->link_props[rtd->dai_link->id]; + int max_rate, ret; + + if (props->is_sense) { + /* + * Sense stream will not return data while playback is inactive, + * so do not time out. + */ + substream->wait_time = MAX_SCHEDULE_TIMEOUT; + return 0; + } + + ret = snd_pcm_hw_constraint_minmax(substream->runtime, + SNDRV_PCM_HW_PARAM_CHANNELS, + 0, ma->max_channels); + if (ret < 0) + return ret; + + max_rate = MACAUDIO_MAX_BCLK_FREQ / props->bclk_ratio; + ret = snd_pcm_hw_constraint_minmax(substream->runtime, + SNDRV_PCM_HW_PARAM_RATE, + 0, max_rate); + if (ret < 0) + return ret; + + return 0; +} + +static int macaudio_fe_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params) +{ + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); + struct snd_soc_pcm_runtime *be; + struct snd_soc_dpcm *dpcm; + + be = NULL; + for_each_dpcm_be(rtd, substream->stream, dpcm) { + be = dpcm->be; + break; + } + + if (!be) { + dev_err(rtd->dev, "opening PCM device '%s' with no audio route configured by the user\n", + rtd->dai_link->name); + return -EINVAL; + } + + return macaudio_dpcm_hw_params(substream, params); +} + + +static void macaudio_dpcm_shutdown(struct snd_pcm_substream *substream) +{ + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); + struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, 0); + struct snd_soc_dai *dai; + int bclk_ratio = macaudio_get_runtime_bclk_ratio(substream); + int i; + + if (bclk_ratio) { + for_each_rtd_codec_dais(rtd, i, dai) + snd_soc_dai_set_sysclk(dai, 0, 0, SND_SOC_CLOCK_IN); + + snd_soc_dai_set_sysclk(cpu_dai, 0, 0, SND_SOC_CLOCK_OUT); + } +} + +static int macaudio_be_hw_free(struct snd_pcm_substream *substream) +{ + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(rtd->card); + struct macaudio_link_props *props = &ma->link_props[rtd->dai_link->id]; + struct snd_soc_dai *dai; + int i; + + if (props->is_speakers && substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + /* + * Clear the DAI rates, so the next open can change the sample rate. + * This won't happen automatically if the sense PCM is open. + */ + for_each_rtd_dais(rtd, i, dai) { + dai->symmetric_rate = 0; + } + + /* Notify userspace that the speakers are closed */ + ma->speaker_sample_rate = 0; + snd_ctl_notify(ma->card.snd_card, SNDRV_CTL_EVENT_MASK_VALUE, + &ma->speaker_sample_rate_kctl->id); + } + + return 0; +} + +static int macaudio_be_trigger(struct snd_pcm_substream *substream, int cmd) +{ + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(rtd->card); + struct macaudio_link_props *props = &ma->link_props[rtd->dai_link->id]; + + if (props->is_speakers && substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + switch (cmd) { + case SNDRV_PCM_TRIGGER_START: + case SNDRV_PCM_TRIGGER_RESUME: + case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: + ma->bes_active |= BIT(rtd->dai_link->id); + break; + case SNDRV_PCM_TRIGGER_SUSPEND: + case SNDRV_PCM_TRIGGER_PAUSE_PUSH: + case SNDRV_PCM_TRIGGER_STOP: + ma->bes_active &= ~BIT(rtd->dai_link->id); + break; + default: + return -EINVAL; + } + + schedule_work(&ma->lock_update_work); + } + + return 0; +} + +static const struct snd_soc_ops macaudio_fe_ops = { + .startup = macaudio_fe_startup, + .shutdown = macaudio_dpcm_shutdown, + .hw_params = macaudio_fe_hw_params, +}; + +static const struct snd_soc_ops macaudio_be_ops = { + .hw_free = macaudio_be_hw_free, + .shutdown = macaudio_dpcm_shutdown, + .hw_params = macaudio_dpcm_hw_params, + .trigger = macaudio_be_trigger, +}; + +static int macaudio_be_assign_tdm(struct snd_soc_pcm_runtime *rtd) +{ + struct snd_soc_card *card = rtd->card; + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(card); + struct macaudio_link_props *props = &ma->link_props[rtd->dai_link->id]; + struct snd_soc_dai *dai; + unsigned int mask; + int nslots, ret, i; + + if (!props->tdm_mask) + return 0; + + mask = props->tdm_mask; + nslots = __fls(mask) + 1; + + if (rtd->dai_link->num_codecs == 1) { + ret = snd_soc_dai_set_tdm_slot(snd_soc_rtd_to_codec(rtd, 0), mask, + 0, nslots, MACAUDIO_SLOTWIDTH); + + /* + * Headphones get a pass on -ENOTSUPP (see the comment + * around bclk_ratio value for primary FE). + */ + if (ret == -ENOTSUPP && props->is_headphones) + return 0; + + return ret; + } + + for_each_rtd_codec_dais(rtd, i, dai) { + int slot = __ffs(mask); + + mask &= ~(1 << slot); + ret = snd_soc_dai_set_tdm_slot(dai, 1 << slot, 0, nslots, + MACAUDIO_SLOTWIDTH); + if (ret) + return ret; + } + + return 0; +} + +static int macaudio_be_init(struct snd_soc_pcm_runtime *rtd) +{ + struct snd_soc_card *card = rtd->card; + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(card); + struct macaudio_link_props *props = &ma->link_props[rtd->dai_link->id]; + struct snd_soc_dai *dai; + int i, ret; + + ret = macaudio_be_assign_tdm(rtd); + if (ret < 0) + return ret; + + if (props->is_headphones) { + for_each_rtd_codec_dais(rtd, i, dai) + snd_soc_component_set_jack(dai->component, &ma->jack, NULL); + } + + return 0; +} + +static void macaudio_be_exit(struct snd_soc_pcm_runtime *rtd) +{ + struct snd_soc_card *card = rtd->card; + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(card); + struct macaudio_link_props *props = &ma->link_props[rtd->dai_link->id]; + struct snd_soc_dai *dai; + int i; + + if (props->is_headphones) { + for_each_rtd_codec_dais(rtd, i, dai) + snd_soc_component_set_jack(dai->component, NULL, NULL); + } +} + +static int macaudio_fe_init(struct snd_soc_pcm_runtime *rtd) +{ + struct snd_soc_card *card = rtd->card; + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(card); + struct macaudio_link_props *props = &ma->link_props[rtd->dai_link->id]; + int nslots = props->bclk_ratio / MACAUDIO_SLOTWIDTH; + + if (props->is_sense) + return snd_soc_dai_set_tdm_slot(snd_soc_rtd_to_cpu(rtd, 0), 0, 0xffff, 16, 16); + + return snd_soc_dai_set_tdm_slot(snd_soc_rtd_to_cpu(rtd, 0), (1 << nslots) - 1, + (1 << nslots) - 1, nslots, MACAUDIO_SLOTWIDTH); +} + +static struct snd_soc_jack_pin macaudio_jack_pins[] = { + { + .pin = "Headphone", + .mask = SND_JACK_HEADPHONE, + }, + { + .pin = "Headset Mic", + .mask = SND_JACK_MICROPHONE, + }, +}; + +static int macaudio_probe(struct snd_soc_card *card) +{ + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(card); + int ret; + + dev_dbg(card->dev, "%s!\n", __func__); + + ret = snd_soc_card_jack_new_pins(card, "Headphone Jack", + SND_JACK_HEADSET | SND_JACK_HEADPHONE, + &ma->jack, macaudio_jack_pins, + ARRAY_SIZE(macaudio_jack_pins)); + if (ret < 0) { + dev_err(card->dev, "jack creation failed: %d\n", ret); + return ret; + } + + return ret; +} + +static int macaudio_add_backend_dai_route(struct snd_soc_card *card, struct snd_soc_dai *dai, + bool is_speakers) +{ + struct snd_soc_dapm_route routes[2]; + struct snd_soc_dapm_route *r; + int nroutes = 0; + int ret; + + memset(routes, 0, sizeof(routes)); + + dev_dbg(card->dev, "adding routes for '%s'\n", dai->name); + + r = &routes[nroutes++]; + if (is_speakers) + r->source = "Speaker Playback"; + else + r->source = "Headphone Playback"; + r->sink = dai->stream[SNDRV_PCM_STREAM_PLAYBACK].widget->name; + + /* If headphone jack, add capture path */ + if (!is_speakers) { + r = &routes[nroutes++]; + r->source = dai->stream[SNDRV_PCM_STREAM_CAPTURE].widget->name; + r->sink = "Headset Capture"; + } + + /* If speakers, add sense capture path */ + if (is_speakers) { + r = &routes[nroutes++]; + r->source = dai->stream[SNDRV_PCM_STREAM_CAPTURE].widget->name; + r->sink = "Speaker Sense Capture"; + } + + ret = snd_soc_dapm_add_routes(&card->dapm, routes, nroutes); + if (ret) + dev_err(card->dev, "failed adding dynamic DAPM routes for %s\n", + dai->name); + return ret; +} + +static int macaudio_add_pin_routes(struct snd_soc_card *card, struct snd_soc_component *component, + bool is_speakers) +{ + struct snd_soc_dapm_route routes[2]; + struct snd_soc_dapm_route *r; + int nroutes = 0; + char buf[32]; + int ret; + + memset(routes, 0, sizeof(routes)); + + /* Connect the far ends of CODECs to pins */ + if (is_speakers) { + r = &routes[nroutes++]; + r->source = "OUT"; + if (component->name_prefix) { + snprintf(buf, sizeof(buf) - 1, "%s OUT", component->name_prefix); + r->source = buf; + } + r->sink = "Speaker"; + } else { + r = &routes[nroutes++]; + r->source = "Jack HP"; + r->sink = "Headphone"; + r = &routes[nroutes++]; + r->source = "Headset Mic"; + r->sink = "Jack HS"; + } + + ret = snd_soc_dapm_add_routes(&card->dapm, routes, nroutes); + if (ret) + dev_err(card->dev, "failed adding dynamic DAPM routes for %s\n", + component->name); + return ret; +} + +static int macaudio_late_probe(struct snd_soc_card *card) +{ + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(card); + struct snd_soc_pcm_runtime *rtd; + struct snd_soc_dai *dai; + int ret, i; + + /* Add the dynamic DAPM routes */ + for_each_card_rtds(card, rtd) { + struct macaudio_link_props *props = &ma->link_props[rtd->dai_link->id]; + + if (!rtd->dai_link->no_pcm) + continue; + + for_each_rtd_cpu_dais(rtd, i, dai) { + ret = macaudio_add_backend_dai_route(card, dai, props->is_speakers); + + if (ret) + return ret; + } + + for_each_rtd_codec_dais(rtd, i, dai) { + ret = macaudio_add_pin_routes(card, dai->component, + props->is_speakers); + + if (ret) + return ret; + } + } + + if (ma->has_speakers) + ma->speaker_sample_rate_kctl = snd_soc_card_get_kcontrol(card, + "Speaker Sample Rate"); + if (ma->has_safety) { + ma->speaker_lock_kctl = snd_soc_card_get_kcontrol(card, + "Speaker Volume Unlock"); + + mutex_lock(&ma->volume_lock_mutex); + macaudio_vlimit_unlock(ma, false); + mutex_unlock(&ma->volume_lock_mutex); + } + + return 0; +} + +#define CHECK(call, pattern, value, min) \ + { \ + int ret = call(card, pattern, value); \ + int err = (ret >= 0 && ret < min) ? -ERANGE : ret; \ + if (err < 0) { \ + dev_err(card->dev, "%s on '%s': %d\n", #call, pattern, \ + ret); \ + if (please_blow_up_my_speakers < 2) \ + return err; \ + } else { \ + dev_dbg(card->dev, "%s on '%s': %d hits\n", #call, \ + pattern, ret); \ + } \ + } + +#define CHECK_CONCAT(call, suffix, value) \ + { \ + snprintf(buf, sizeof(buf), "%s%s", prefix, suffix); \ + CHECK(call, buf, value, 1); \ + } + +static int macaudio_set_speaker(struct snd_soc_card *card, const char *prefix, bool tweeter) +{ + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(card); + char buf[256]; + + if (!ma->has_speakers) + return 0; + + switch (ma->cfg->amp) { + case AMP_TAS5770: + if (ma->cfg->stereo) { + CHECK_CONCAT(snd_soc_set_enum_kctl, "ASI1 Sel", "Left"); + CHECK_CONCAT(snd_soc_deactivate_kctl, "ASI1 Sel", 0); + } + + CHECK_CONCAT(snd_soc_limit_volume, "Amp Gain Volume", ma->cfg->amp_gain); + break; + case AMP_SN012776: + if (ma->cfg->stereo) { + CHECK_CONCAT(snd_soc_set_enum_kctl, "ASI1 Sel", "Left"); + CHECK_CONCAT(snd_soc_deactivate_kctl, "ASI1 Sel", 0); + } + + CHECK_CONCAT(snd_soc_limit_volume, "Amp Gain Volume", ma->cfg->amp_gain); + CHECK_CONCAT(snd_soc_set_enum_kctl, "HPF Corner Frequency", + tweeter ? "800 Hz" : "2 Hz"); + + if (please_blow_up_my_speakers < 2) + CHECK_CONCAT(snd_soc_deactivate_kctl, "HPF Corner Frequency", 0); + + CHECK_CONCAT(snd_soc_set_enum_kctl, "OCE Handling", "Retry"); + CHECK_CONCAT(snd_soc_deactivate_kctl, "OCE Handling", 0); + break; + case AMP_SSM3515: + /* TODO: check */ + CHECK_CONCAT(snd_soc_set_enum_kctl, "DAC Analog Gain Select", "8.4 V Span"); + + if (please_blow_up_my_speakers < 2) + CHECK_CONCAT(snd_soc_deactivate_kctl, "DAC Analog Gain Select", 0); + + /* TODO: HPF, needs new call to set */ + break; + default: + return -EINVAL; + } + + return 0; +} + +static int macaudio_fixup_controls(struct snd_soc_card *card) +{ + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(card); + const char *p; + + /* Set the card ID early to avoid races with udev */ + p = strrchr(card->name, ' '); + if (p) { + snprintf(card->snd_card->id, sizeof(card->snd_card->id), + "Apple%s", p + 1); + } + + if (!ma->has_speakers) + return 0; + + /* + * This needs some care to avoid matches against cs42l84's + * "Jack HPF Corner Frequency". + */ + switch(ma->cfg->speakers) { + case SPKR_NONE: + WARN_ON(please_blow_up_my_speakers < 2); + return please_blow_up_my_speakers >= 2 ? 0 : -EINVAL; + case SPKR_1W: + /* only 1W stereo system (J313) is uses cs42l83 */ + if (ma->cfg->stereo) { + CHECK(macaudio_set_speaker, "* ", false, 0); + } else { + CHECK(macaudio_set_speaker, "", false, 0); + } + break; + case SPKR_2W: + CHECK(macaudio_set_speaker, "* Front ", false, 0); + CHECK(macaudio_set_speaker, "* Rear ", false, 0); + break; + case SPKR_1W1T: + CHECK(macaudio_set_speaker, "* Tweeter ", true, 0); + CHECK(macaudio_set_speaker, "* Woofer ", false, 0); + break; + case SPKR_2W1T: + CHECK(macaudio_set_speaker, "* Tweeter ", true, 0); + CHECK(macaudio_set_speaker, "* Woofer 1 ", false, 0); + CHECK(macaudio_set_speaker, "* Woofer 2 ", false, 0); + break; + } + + return 0; +} + +static const char * const macaudio_spk_mux_texts[] = { + "Primary", + "Secondary" +}; + +SOC_ENUM_SINGLE_VIRT_DECL(macaudio_spk_mux_enum, macaudio_spk_mux_texts); + +static const struct snd_kcontrol_new macaudio_spk_mux = + SOC_DAPM_ENUM("Speaker Playback Mux", macaudio_spk_mux_enum); + +static const char * const macaudio_hp_mux_texts[] = { + "Primary", + "Secondary" +}; + +SOC_ENUM_SINGLE_VIRT_DECL(macaudio_hp_mux_enum, macaudio_hp_mux_texts); + +static const struct snd_kcontrol_new macaudio_hp_mux = + SOC_DAPM_ENUM("Headphones Playback Mux", macaudio_hp_mux_enum); + +static const struct snd_soc_dapm_widget macaudio_snd_widgets[] = { + SND_SOC_DAPM_SPK("Speaker", NULL), + SND_SOC_DAPM_SPK("Speaker (Static)", NULL), + SND_SOC_DAPM_HP("Headphone", NULL), + SND_SOC_DAPM_MIC("Headset Mic", NULL), + + SND_SOC_DAPM_MUX("Speaker Playback Mux", SND_SOC_NOPM, 0, 0, &macaudio_spk_mux), + SND_SOC_DAPM_MUX("Headphone Playback Mux", SND_SOC_NOPM, 0, 0, &macaudio_hp_mux), + + SND_SOC_DAPM_AIF_OUT("Speaker Playback", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("Headphone Playback", NULL, 0, SND_SOC_NOPM, 0, 0), + + SND_SOC_DAPM_AIF_IN("Headset Capture", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("Speaker Sense Capture", NULL, 0, SND_SOC_NOPM, 0, 0), +}; + +static int macaudio_sss_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) +{ + uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; + uinfo->count = 1; + uinfo->value.integer.min = 0; + uinfo->value.integer.max = 192000; + + return 0; +} + +static int macaudio_sss_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *uvalue) +{ + struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(card); + + /* + * TODO: Check if any locking is in order here. I would + * assume there is some ALSA-level lock, but DAPM implementations + * of kcontrol ops do explicit locking, so look into it. + */ + uvalue->value.integer.value[0] = ma->speaker_sample_rate; + + return 0; +} + +static int macaudio_slk_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) +{ + uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; + uinfo->count = 1; + uinfo->value.integer.min = INT_MIN; + uinfo->value.integer.max = INT_MAX; + + return 0; +} + +static int macaudio_slk_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *uvalue) +{ + struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(card); + + if (!ma->speaker_lock_owner) + return -EPERM; + + if (uvalue->value.integer.value[0] != SPEAKER_MAGIC_VALUE) + return -EINVAL; + + /* Serves as a notification that the lock was lost at some point */ + if (ma->speaker_volume_was_locked) { + ma->speaker_volume_was_locked = false; + return -ETIMEDOUT; + } + + mutex_lock(&ma->volume_lock_mutex); + + cancel_delayed_work(&ma->lock_timeout_work); + + ma->speaker_lock_remain = ms_to_ktime(SPEAKER_LOCK_TIMEOUT); + ma->speaker_lock_timeout = ktime_add(ktime_get(), ma->speaker_lock_remain); + macaudio_vlimit_update(ma); + + if (ma->speaker_lock_timeout_enabled) { + dev_dbg(ma->card.dev, "Volume limit timeout ping: %ld us left\n", + (long)ktime_to_us(ma->speaker_lock_remain)); + schedule_delayed_work(&ma->lock_timeout_work, usecs_to_jiffies(ktime_to_us(ma->speaker_lock_remain))); + } + + mutex_unlock(&ma->volume_lock_mutex); + + return 0; +} + +static int macaudio_slk_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *uvalue) +{ + struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(card); + + uvalue->value.integer.value[0] = ma->speaker_volume_unlocked ? 1 : 0; + + return 0; +} + +static int macaudio_slk_lock(struct snd_kcontrol *kcontrol, struct snd_ctl_file *owner) +{ + struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(card); + + mutex_lock(&ma->volume_lock_mutex); + ma->speaker_lock_owner = owner; + macaudio_vlimit_update(ma); + + /* + * Reset the unintended lock flag when the control is first locked. + * At this point the state is locked and cannot be unlocked until + * userspace writes to this control, so this cannot spuriously become + * true again until that point. + */ + ma->speaker_volume_was_locked = false; + + mutex_unlock(&ma->volume_lock_mutex); + + return 0; +} + +static void macaudio_slk_unlock(struct snd_kcontrol *kcontrol) +{ + struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); + struct macaudio_snd_data *ma = snd_soc_card_get_drvdata(card); + + ma->speaker_lock_owner = NULL; + ma->speaker_lock_timeout = 0; + macaudio_vlimit_update(ma); +} + +/* + * Speaker limit controls go last. We only drop the unlock control, + * leaving sample rate, since that can be useful for safety + * bring-up before the kernel-side caps are ready. + */ +#define MACAUDIO_NUM_SPEAKER_LIMIT_CONTROLS 1 +/* + * If there are no speakers configured at all, we can drop both + * controls. + */ +#define MACAUDIO_NUM_SPEAKER_CONTROLS 2 + +static const struct snd_kcontrol_new macaudio_controls[] = { + SOC_DAPM_PIN_SWITCH("Speaker"), + SOC_DAPM_PIN_SWITCH("Headphone"), + SOC_DAPM_PIN_SWITCH("Headset Mic"), + { + .iface = SNDRV_CTL_ELEM_IFACE_MIXER, + .access = SNDRV_CTL_ELEM_ACCESS_READ | + SNDRV_CTL_ELEM_ACCESS_VOLATILE, + .name = "Speaker Sample Rate", + .info = macaudio_sss_info, .get = macaudio_sss_get, + }, + { + .iface = SNDRV_CTL_ELEM_IFACE_MIXER, + .access = SNDRV_CTL_ELEM_ACCESS_READ | + SNDRV_CTL_ELEM_ACCESS_WRITE | + SNDRV_CTL_ELEM_ACCESS_VOLATILE, + .name = "Speaker Volume Unlock", + .info = macaudio_slk_info, + .put = macaudio_slk_put, .get = macaudio_slk_get, + .lock = macaudio_slk_lock, .unlock = macaudio_slk_unlock, + }, +}; + +static const struct snd_soc_dapm_route macaudio_dapm_routes[] = { + /* Playback paths */ + { "Speaker Playback Mux", "Primary", "PCM0 TX" }, + { "Speaker Playback Mux", "Secondary", "PCM1 TX" }, + { "Speaker Playback", NULL, "Speaker Playback Mux"}, + + { "Headphone Playback Mux", "Primary", "PCM0 TX" }, + { "Headphone Playback Mux", "Secondary", "PCM1 TX" }, + { "Headphone Playback", NULL, "Headphone Playback Mux"}, + /* + * Additional paths (to specific I2S ports) are added dynamically. + */ + + /* Capture paths */ + { "PCM0 RX", NULL, "Headset Capture" }, + + /* Sense paths */ + { "PCM2 RX", NULL, "Speaker Sense Capture" }, +}; + +/* enable amp speakers stereo gain safe_vol */ +struct macaudio_platform_cfg macaudio_j180_cfg = { + false, AMP_SN012776, SPKR_1W1T, false, 10, -20, +}; +struct macaudio_platform_cfg macaudio_j274_cfg = { + true, AMP_TAS5770, SPKR_1W, false, 20, -20, +}; + +struct macaudio_platform_cfg macaudio_j293_cfg = { + true, AMP_TAS5770, SPKR_2W, true, 15, -20, +}; + +struct macaudio_platform_cfg macaudio_j313_cfg = { + true, AMP_TAS5770, SPKR_1W, true, 10, -20, +}; + +struct macaudio_platform_cfg macaudio_j314_cfg = { + true, AMP_SN012776, SPKR_2W1T, true, 15, -20, +}; + +struct macaudio_platform_cfg macaudio_j316_cfg = { + true, AMP_SN012776, SPKR_2W1T, true, 15, -20, +}; + +struct macaudio_platform_cfg macaudio_j37x_j47x_cfg = { + true, AMP_SN012776, SPKR_1W, false, 20, -20, +}; + +struct macaudio_platform_cfg macaudio_j413_cfg = { + true, AMP_SN012776, SPKR_1W1T, true, 15, -20, +}; + +struct macaudio_platform_cfg macaudio_j415_cfg = { + true, AMP_SN012776, SPKR_2W1T, true, 15, -20, +}; + +struct macaudio_platform_cfg macaudio_j45x_cfg = { + false, AMP_SSM3515, SPKR_1W1T, true, 9, -20, /* TODO: gain?? */ +}; + +struct macaudio_platform_cfg macaudio_j493_cfg = { + true, AMP_SN012776, SPKR_2W, true, 15, -20, +}; + +struct macaudio_platform_cfg macaudio_fallback_cfg = { + false, AMP_NONE, SPKR_NONE, false, 0, 0, +}; + +/* + * DT compatible/ID table rules: + * + * 1. Machines with **identical** speaker configurations (amps, models, chassis) + * are allowed to declare compatibility with the first model (chronologically), + * and are not enumerated in this array. + * + * 2. Machines with identical amps and speakers (=identical speaker protection + * rules) but a different chassis must use different compatibles, but may share + * the private data structure here. They are explicitly enumerated. + * + * 3. Machines with different amps or speaker layouts must use separate + * data structures. + * + * 4. Machines with identical speaker layouts and amps (but possibly different + * speaker models/chassis) may share the data structure, since only userspace + * cares about that (assuming our general -20dB safe level standard holds). + */ +static const struct of_device_id macaudio_snd_device_id[] = { + /* Model ID Amp Gain Speakers */ + /* j180 AID19 sn012776 10 1× 1W+1T */ + { .compatible = "apple,j180-macaudio", .data = &macaudio_j180_cfg }, + /* j274 AID6 tas5770 20 1× 1W */ + { .compatible = "apple,j274-macaudio", .data = &macaudio_j274_cfg }, + /* j293 AID3 tas5770 15 2× 2W */ + { .compatible = "apple,j293-macaudio", .data = &macaudio_j293_cfg }, + /* j313 AID4 tas5770 10 2× 1W */ + { .compatible = "apple,j313-macaudio", .data = &macaudio_j313_cfg }, + /* j314 AID8 sn012776 15 2× 2W+1T */ + { .compatible = "apple,j314-macaudio", .data = &macaudio_j314_cfg }, + /* j316 AID9 sn012776 15 2× 2W+1T */ + { .compatible = "apple,j316-macaudio", .data = &macaudio_j316_cfg }, + /* j375 AID10 sn012776 15 1× 1W */ + { .compatible = "apple,j375-macaudio", .data = &macaudio_j37x_j47x_cfg }, + /* j413 AID13 sn012776 15 2× 1W+1T */ + { .compatible = "apple,j413-macaudio", .data = &macaudio_j413_cfg }, + /* j414 AID14 sn012776 15 2× 2W+1T Compat: apple,j314-macaudio */ + /* j415 AID27 sn012776 15 2× 2W+1T */ + { .compatible = "apple,j415-macaudio", .data = &macaudio_j415_cfg }, + /* j416 AID15 sn012776 15 2× 2W+1T Compat: apple,j316-macaudio */ + /* j456 AID5 ssm3515 15 2× 1W+1T */ + { .compatible = "apple,j456-macaudio", .data = &macaudio_j45x_cfg }, + /* j457 AID7 ssm3515 15 2× 1W+1T Compat: apple,j456-macaudio */ + /* j473 AID12 sn012776 20 1× 1W */ + { .compatible = "apple,j473-macaudio", .data = &macaudio_j37x_j47x_cfg }, + /* j474 AID26 sn012776 20 1× 1W Compat: apple,j473-macaudio */ + /* j475 AID25 sn012776 20 1× 1W Compat: apple,j375-macaudio */ + /* j493 AID18 sn012776 15 2× 2W */ + { .compatible = "apple,j493-macaudio", .data = &macaudio_j493_cfg }, + /* Fallback, jack only */ + { .compatible = "apple,macaudio"}, + { } +}; +MODULE_DEVICE_TABLE(of, macaudio_snd_device_id); + +static int macaudio_snd_platform_probe(struct platform_device *pdev) +{ + struct snd_soc_card *card; + struct macaudio_snd_data *data; + struct device *dev = &pdev->dev; + struct snd_soc_dai_link *link; + const struct of_device_id *of_id; + int ret; + int i; + + of_id = of_match_device(macaudio_snd_device_id, dev); + if (!of_id) + return -EINVAL; + + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + card = &data->card; + snd_soc_card_set_drvdata(card, data); + dev_set_drvdata(&pdev->dev, data); + mutex_init(&data->volume_lock_mutex); + + card->owner = THIS_MODULE; + card->driver_name = "macaudio"; + card->dev = dev; + card->dapm_widgets = macaudio_snd_widgets; + card->num_dapm_widgets = ARRAY_SIZE(macaudio_snd_widgets); + card->dapm_routes = macaudio_dapm_routes; + card->num_dapm_routes = ARRAY_SIZE(macaudio_dapm_routes); + card->controls = macaudio_controls; + card->num_controls = ARRAY_SIZE(macaudio_controls); + card->probe = macaudio_probe; + card->late_probe = macaudio_late_probe; + card->component_chaining = true; + card->fully_routed = true; + + if (of_id->data) + data->cfg = of_id->data; + else + data->cfg = &macaudio_fallback_cfg; + + card->fixup_controls = macaudio_fixup_controls; + + ret = macaudio_parse_of(data); + if (ret) + return ret; + + /* Remove useless controls */ + if (!data->has_speakers) /* No speakers, remove both */ + card->num_controls -= MACAUDIO_NUM_SPEAKER_CONTROLS; + else if (!data->cfg->safe_vol) /* No safety, remove unlock */ + card->num_controls -= MACAUDIO_NUM_SPEAKER_LIMIT_CONTROLS; + else /* Speakers with safety, mark us as such */ + data->has_safety = true; + + for_each_card_prelinks(card, i, link) { + if (link->no_pcm) { + link->ops = &macaudio_be_ops; + link->init = macaudio_be_init; + link->exit = macaudio_be_exit; + } else { + link->ops = &macaudio_fe_ops; + link->init = macaudio_fe_init; + } + } + + INIT_WORK(&data->lock_update_work, macaudio_vlimit_update_work); + INIT_DELAYED_WORK(&data->lock_timeout_work, macaudio_vlimit_timeout_work); + + return devm_snd_soc_register_card(dev, card); +} + +static void macaudio_snd_platform_remove(struct platform_device *pdev) +{ + struct macaudio_snd_data *ma = dev_get_drvdata(&pdev->dev); + + cancel_delayed_work_sync(&ma->lock_timeout_work); +} + +static struct platform_driver macaudio_snd_driver = { + .probe = macaudio_snd_platform_probe, + .remove = macaudio_snd_platform_remove, + .driver = { + .name = DRIVER_NAME, + .of_match_table = macaudio_snd_device_id, + .pm = &snd_soc_pm_ops, + }, +}; +module_platform_driver(macaudio_snd_driver); + +MODULE_AUTHOR("Martin Povišer "); +MODULE_DESCRIPTION("Apple Silicon Macs machine-level sound driver"); +MODULE_LICENSE("GPL"); diff --git a/sound/soc/apple/mca.c b/sound/soc/apple/mca.c index c4dcb2b545912c..01dacd10bd39ce 100644 --- a/sound/soc/apple/mca.c +++ b/sound/soc/apple/mca.c @@ -133,12 +133,17 @@ struct mca_cluster { struct clk *clk_parent; struct dma_chan *dma_chans[SNDRV_PCM_STREAM_LAST + 1]; - bool port_started[SNDRV_PCM_STREAM_LAST + 1]; - int port_driver; /* The cluster driving this cluster's port */ + bool clk_provider; + + bool port_clk_started[SNDRV_PCM_STREAM_LAST + 1]; + int port_clk_driver; /* The cluster driving this cluster's port */ bool clocks_in_use[SNDRV_PCM_STREAM_LAST + 1]; struct device_link *pd_link; + /* In case of clock consumer FE */ + int syncgen_in_use; + unsigned int bclk_ratio; /* Masks etc. picked up via the set_tdm_slot method */ @@ -157,7 +162,7 @@ struct mca_data { struct reset_control *rstc; struct device_link *pd_link; - /* Mutex for accessing port_driver of foreign clusters */ + /* Mutex for accessing port_clk_driver of foreign clusters */ struct mutex port_mutex; int nclusters; @@ -211,15 +216,21 @@ static void mca_fe_early_trigger(struct snd_pcm_substream *substream, int cmd, SERDES_STATUS_RST); /* * Experiments suggest that it takes at most ~1 us - * for the bit to clear, so wait 2 us for good measure. + * for the bit to clear, so wait 5 us for good measure. */ - udelay(2); + udelay(50); WARN_ON(readl_relaxed(cl->base + serdes_unit + REG_SERDES_STATUS) & SERDES_STATUS_RST); mca_modify(cl, serdes_conf, SERDES_CONF_SYNC_SEL, FIELD_PREP(SERDES_CONF_SYNC_SEL, 0)); mca_modify(cl, serdes_conf, SERDES_CONF_SYNC_SEL, FIELD_PREP(SERDES_CONF_SYNC_SEL, cl->no + 1)); + /* + * ADMAC gets started right after this. This delay seems + * to be needed for that to be reliable, e.g. ensure the + * clock is stable? + */ + udelay(100); break; default: break; @@ -256,11 +267,28 @@ static int mca_fe_trigger(struct snd_pcm_substream *substream, int cmd, return 0; } +static int mca_fe_get_portmask(struct snd_pcm_substream *substream) +{ + struct snd_soc_pcm_runtime *fe = snd_soc_substream_to_rtd(substream); + struct snd_soc_dpcm *dpcm; + int mask = 0; + + for_each_dpcm_be(fe, substream->stream, dpcm) { + int no = mca_dai_to_cluster(snd_soc_rtd_to_cpu(dpcm->be, 0))->no; + mask |= 1 << no; + } + + return mask; +} + static int mca_fe_enable_clocks(struct mca_cluster *cl) { struct mca_data *mca = cl->host; int ret; + if (!cl->clk_provider) + return -EINVAL; + ret = clk_prepare_enable(cl->clk_parent); if (ret) { dev_err(mca->dev, @@ -274,6 +302,7 @@ static int mca_fe_enable_clocks(struct mca_cluster *cl) * the power state driver would error out on seeing the device * as clock-gated. */ + WARN_ON(cl->pd_link); cl->pd_link = device_link_add(mca->dev, cl->pd_dev, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); @@ -297,7 +326,11 @@ static void mca_fe_disable_clocks(struct mca_cluster *cl) mca_modify(cl, REG_SYNCGEN_STATUS, SYNCGEN_STATUS_EN, 0); mca_modify(cl, REG_STATUS, STATUS_MCLK_EN, 0); - device_link_del(cl->pd_link); + if (cl->pd_link) { + device_link_del(cl->pd_link); + cl->pd_link = NULL; + } + clk_disable_unprepare(cl->clk_parent); } @@ -311,7 +344,7 @@ static bool mca_fe_clocks_in_use(struct mca_cluster *cl) for (i = 0; i < mca->nclusters; i++) { be_cl = &mca->clusters[i]; - if (be_cl->port_driver != cl->no) + if (be_cl->port_clk_driver != cl->no) continue; for_each_pcm_streams(stream) { @@ -325,59 +358,55 @@ static bool mca_fe_clocks_in_use(struct mca_cluster *cl) return false; } -static int mca_be_prepare(struct snd_pcm_substream *substream, +static int mca_fe_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct mca_cluster *cl = mca_dai_to_cluster(dai); struct mca_data *mca = cl->host; - struct mca_cluster *fe_cl; - int ret; - if (cl->port_driver < 0) - return -EINVAL; + if (cl->clk_provider) + return 0; - fe_cl = &mca->clusters[cl->port_driver]; + if (!cl->syncgen_in_use) { + int port = ffs(mca_fe_get_portmask(substream)) - 1; - /* - * Typically the CODECs we are paired with will require clocks - * to be present at time of unmute with the 'mute_stream' op - * or at time of DAPM widget power-up. We need to enable clocks - * here at the latest (frontend prepare would be too late). - */ - if (!mca_fe_clocks_in_use(fe_cl)) { - ret = mca_fe_enable_clocks(fe_cl); - if (ret < 0) - return ret; - } + WARN_ON(cl->pd_link); + cl->pd_link = device_link_add(mca->dev, cl->pd_dev, + DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | + DL_FLAG_RPM_ACTIVE); + if (!cl->pd_link) { + dev_err(mca->dev, + "cluster %d: unable to prop-up power domain\n", cl->no); + return -EINVAL; + } - cl->clocks_in_use[substream->stream] = true; + writel_relaxed(port + 6 + 1, + cl->base + REG_SYNCGEN_MCLK_SEL); + mca_modify(cl, REG_SYNCGEN_STATUS, SYNCGEN_STATUS_EN, + SYNCGEN_STATUS_EN); + } + cl->syncgen_in_use |= 1 << substream->stream; return 0; } -static int mca_be_hw_free(struct snd_pcm_substream *substream, +static int mca_fe_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct mca_cluster *cl = mca_dai_to_cluster(dai); - struct mca_data *mca = cl->host; - struct mca_cluster *fe_cl; - - if (cl->port_driver < 0) - return -EINVAL; - /* - * We are operating on a foreign cluster here, but since we - * belong to the same PCM, accesses should have been - * synchronized at ASoC level. - */ - fe_cl = &mca->clusters[cl->port_driver]; - if (!mca_fe_clocks_in_use(fe_cl)) - return 0; /* Nothing to do */ + if (cl->clk_provider) + return 0; - cl->clocks_in_use[substream->stream] = false; + cl->syncgen_in_use &= ~(1 << substream->stream); + if (cl->syncgen_in_use) + return 0; - if (!mca_fe_clocks_in_use(fe_cl)) - mca_fe_disable_clocks(fe_cl); + mca_modify(cl, REG_SYNCGEN_STATUS, SYNCGEN_STATUS_EN, 0); + if (cl->pd_link) { + device_link_del(cl->pd_link); + cl->pd_link = NULL; + } return 0; } @@ -392,7 +421,7 @@ static unsigned int mca_crop_mask(unsigned int mask, int nchans) static int mca_configure_serdes(struct mca_cluster *cl, int serdes_unit, unsigned int mask, int slots, int nchans, - int slot_width, bool is_tx, int port) + int slot_width, bool is_tx, int portmask) { __iomem void *serdes_base = cl->base + serdes_unit; u32 serdes_conf, serdes_conf_mask; @@ -451,7 +480,7 @@ static int mca_configure_serdes(struct mca_cluster *cl, int serdes_unit, serdes_base + REG_RX_SERDES_SLOTMASK); writel_relaxed(~((u32)mca_crop_mask(mask, nchans)), serdes_base + REG_RX_SERDES_SLOTMASK + 0x4); - writel_relaxed(1 << port, + writel_relaxed(portmask, serdes_base + REG_RX_SERDES_PORT); } @@ -507,9 +536,18 @@ static int mca_fe_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) u32 serdes_conf = 0; u32 bitstart; - if ((fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) != - SND_SOC_DAIFMT_BP_FP) + switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) { + case SND_SOC_DAIFMT_BP_FP: + cl->clk_provider = true; + break; + + case SND_SOC_DAIFMT_BC_FC: + cl->clk_provider = false; + break; + + default: goto err; + } switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_I2S: @@ -566,24 +604,6 @@ static int mca_set_bclk_ratio(struct snd_soc_dai *dai, unsigned int ratio) return 0; } -static int mca_fe_get_port(struct snd_pcm_substream *substream) -{ - struct snd_soc_pcm_runtime *fe = snd_soc_substream_to_rtd(substream); - struct snd_soc_pcm_runtime *be; - struct snd_soc_dpcm *dpcm; - - be = NULL; - for_each_dpcm_be(fe, substream->stream, dpcm) { - be = dpcm->be; - break; - } - - if (!be) - return -EINVAL; - - return mca_dai_to_cluster(snd_soc_rtd_to_cpu(be, 0))->no; -} - static int mca_fe_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) @@ -597,7 +617,7 @@ static int mca_fe_hw_params(struct snd_pcm_substream *substream, unsigned long bclk_ratio; unsigned int tdm_slots, tdm_slot_width, tdm_mask; u32 regval, pad; - int ret, port, nchans_ceiled; + int ret, portmask, nchans_ceiled; if (!cl->tdm_slot_width) { /* @@ -646,13 +666,13 @@ static int mca_fe_hw_params(struct snd_pcm_substream *substream, tdm_mask = (1 << tdm_slots) - 1; } - port = mca_fe_get_port(substream); - if (port < 0) - return port; + portmask = mca_fe_get_portmask(substream); + if (!portmask) + return -EINVAL; ret = mca_configure_serdes(cl, is_tx ? CLUSTER_TX_OFF : CLUSTER_RX_OFF, tdm_mask, tdm_slots, params_channels(params), - tdm_slot_width, is_tx, port); + tdm_slot_width, is_tx, portmask); if (ret) return ret; @@ -708,67 +728,123 @@ static const struct snd_soc_dai_ops mca_fe_ops = { .set_tdm_slot = mca_fe_set_tdm_slot, .hw_params = mca_fe_hw_params, .trigger = mca_fe_trigger, + .prepare = mca_fe_prepare, + .hw_free = mca_fe_hw_free, }; -static bool mca_be_started(struct mca_cluster *cl) +/* + * Is there a FE attached which will be feeding this port's clocks? + */ +static bool mca_be_clk_started(struct mca_cluster *cl) { int stream; for_each_pcm_streams(stream) - if (cl->port_started[stream]) + if (cl->port_clk_started[stream]) return true; return false; } -static int mca_be_startup(struct snd_pcm_substream *substream, +static struct snd_soc_pcm_runtime *mca_be_get_fe(struct snd_soc_pcm_runtime *be, + int stream) +{ + struct snd_soc_pcm_runtime *fe = NULL; + struct snd_soc_dpcm *dpcm; + + for_each_dpcm_fe(be, stream, dpcm) { + if (fe && dpcm->fe != fe) { + dev_err(be->dev, "many FE per one BE unsupported\n"); + return NULL; + } + + fe = dpcm->fe; + } + + return fe; +} + +static int mca_be_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct snd_soc_pcm_runtime *be = snd_soc_substream_to_rtd(substream); - struct snd_soc_pcm_runtime *fe; + struct snd_soc_pcm_runtime *fe = mca_be_get_fe(be, substream->stream); struct mca_cluster *cl = mca_dai_to_cluster(dai); - struct mca_cluster *fe_cl; struct mca_data *mca = cl->host; - struct snd_soc_dpcm *dpcm; + struct mca_cluster *fe_cl, *fe_clk_cl; + int ret; - fe = NULL; + fe_cl = mca_dai_to_cluster(snd_soc_rtd_to_cpu(fe, 0)); - for_each_dpcm_fe(be, substream->stream, dpcm) { - if (fe && dpcm->fe != fe) { - dev_err(mca->dev, "many FE per one BE unsupported\n"); - return -EINVAL; - } + if (!fe_cl->clk_provider) + return 0; - fe = dpcm->fe; + if (cl->port_clk_driver < 0) + return 0; + + fe_clk_cl = &mca->clusters[cl->port_clk_driver]; + + /* + * Typically the CODECs we are paired with will require clocks + * to be present at time of unmute with the 'mute_stream' op + * or at time of DAPM widget power-up. We need to enable clocks + * here at the latest (frontend prepare would be too late). + */ + if (!mca_fe_clocks_in_use(fe_clk_cl)) { + ret = mca_fe_enable_clocks(fe_clk_cl); + if (ret < 0) + return ret; } + cl->clocks_in_use[substream->stream] = true; + + return 0; +} + +static int mca_be_startup(struct snd_pcm_substream *substream, + struct snd_soc_dai *dai) +{ + struct snd_soc_pcm_runtime *be = snd_soc_substream_to_rtd(substream); + struct snd_soc_pcm_runtime *fe = mca_be_get_fe(be, substream->stream); + struct mca_cluster *cl = mca_dai_to_cluster(dai); + struct mca_cluster *fe_cl; + struct mca_data *mca = cl->host; + if (!fe) return -EINVAL; - fe_cl = mca_dai_to_cluster(snd_soc_rtd_to_cpu(fe, 0)); - if (mca_be_started(cl)) { + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + writel_relaxed(PORT_DATA_SEL_TXA(fe_cl->no), + cl->base + REG_PORT_DATA_SEL); + mca_modify(cl, REG_PORT_ENABLES, PORT_ENABLES_TX_DATA, + PORT_ENABLES_TX_DATA); + } + + if (!fe_cl->clk_provider) + return 0; + + if (mca_be_clk_started(cl)) { /* * Port is already started in the other direction. * Make sure there isn't a conflict with another cluster - * driving the port. + * driving the port clocks. */ - if (cl->port_driver != fe_cl->no) + if (cl->port_clk_driver != fe_cl->no) return -EINVAL; - cl->port_started[substream->stream] = true; + cl->port_clk_started[substream->stream] = true; return 0; } - writel_relaxed(PORT_ENABLES_CLOCKS | PORT_ENABLES_TX_DATA, - cl->base + REG_PORT_ENABLES); writel_relaxed(FIELD_PREP(PORT_CLOCK_SEL, fe_cl->no + 1), cl->base + REG_PORT_CLOCK_SEL); - writel_relaxed(PORT_DATA_SEL_TXA(fe_cl->no), - cl->base + REG_PORT_DATA_SEL); + mca_modify(cl, REG_PORT_ENABLES, PORT_ENABLES_CLOCKS, + PORT_ENABLES_CLOCKS); + mutex_lock(&mca->port_mutex); - cl->port_driver = fe_cl->no; + cl->port_clk_driver = fe_cl->no; mutex_unlock(&mca->port_mutex); - cl->port_started[substream->stream] = true; + cl->port_clk_started[substream->stream] = true; return 0; } @@ -776,27 +852,60 @@ static int mca_be_startup(struct snd_pcm_substream *substream, static void mca_be_shutdown(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { + struct snd_soc_pcm_runtime *be = snd_soc_substream_to_rtd(substream); + struct snd_soc_pcm_runtime *fe = mca_be_get_fe(be, substream->stream); struct mca_cluster *cl = mca_dai_to_cluster(dai); + struct mca_cluster *fe_cl; struct mca_data *mca = cl->host; - cl->port_started[substream->stream] = false; + if (cl->clocks_in_use[substream->stream] && + !WARN_ON(cl->port_clk_driver < 0)) { + struct mca_cluster *fe_cl = &mca->clusters[cl->port_clk_driver]; - if (!mca_be_started(cl)) { /* - * Were we the last direction to shutdown? - * Turn off the lights. + * Typically the CODECs we are paired with will require clocks + * to be present at time of mute with the 'mute_stream' op. + * We need to disable the clocks here at the earliest (hw_free + * would be too early). + * + * We are operating on a foreign cluster here, but since we + * belong to the same PCM, accesses should have been + * synchronized at ASoC level. */ - writel_relaxed(0, cl->base + REG_PORT_ENABLES); + cl->clocks_in_use[substream->stream] = false; + + if (!mca_fe_clocks_in_use(fe_cl)) + mca_fe_disable_clocks(fe_cl); + } + + if (!fe) + return; + fe_cl = mca_dai_to_cluster(snd_soc_rtd_to_cpu(fe, 0)); + + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + mca_modify(cl, REG_PORT_ENABLES, PORT_ENABLES_TX_DATA, 0); writel_relaxed(0, cl->base + REG_PORT_DATA_SEL); + } + + if (!fe_cl->clk_provider) + return; + + cl->port_clk_started[substream->stream] = false; + if (!mca_be_clk_started(cl)) { + /* + * Were we the last direction to shutdown? + * Turn off the lights (clocks). + */ + mca_modify(cl, REG_PORT_ENABLES, PORT_ENABLES_CLOCKS, 0); + writel_relaxed(0, cl->base + REG_PORT_CLOCK_SEL); mutex_lock(&mca->port_mutex); - cl->port_driver = -1; + cl->port_clk_driver = -1; mutex_unlock(&mca->port_mutex); } } static const struct snd_soc_dai_ops mca_be_ops = { .prepare = mca_be_prepare, - .hw_free = mca_be_hw_free, .startup = mca_be_startup, .shutdown = mca_be_shutdown, }; @@ -1020,8 +1129,10 @@ static void apple_mca_release(struct mca_data *mca) dev_pm_domain_detach(cl->pd_dev, true); } - if (mca->pd_link) + if (mca->pd_link) { device_link_del(mca->pd_link); + mca->pd_link = NULL; + } if (!IS_ERR_OR_NULL(mca->pd_dev)) dev_pm_domain_detach(mca->pd_dev, true); @@ -1096,7 +1207,7 @@ static int apple_mca_probe(struct platform_device *pdev) cl->host = mca; cl->no = i; cl->base = base + CLUSTER_STRIDE * i; - cl->port_driver = -1; + cl->port_clk_driver = -1; cl->clk_parent = of_clk_get(pdev->dev.of_node, i); if (IS_ERR(cl->clk_parent)) { dev_err(&pdev->dev, "unable to obtain clock %d: %ld\n", diff --git a/sound/soc/bcm/bcm63xx-pcm-whistler.c b/sound/soc/bcm/bcm63xx-pcm-whistler.c index e3a4fcc63a56dc..efeb06ddabeb3b 100644 --- a/sound/soc/bcm/bcm63xx-pcm-whistler.c +++ b/sound/soc/bcm/bcm63xx-pcm-whistler.c @@ -358,7 +358,9 @@ static int bcm63xx_soc_pcm_new(struct snd_soc_component *component, i2s_priv = dev_get_drvdata(snd_soc_rtd_to_cpu(rtd, 0)->dev); - of_dma_configure(pcm->card->dev, pcm->card->dev->of_node, 1); + ret = of_dma_configure(pcm->card->dev, pcm->card->dev->of_node, 1); + if (ret) + return ret; ret = dma_coerce_mask_and_coherent(pcm->card->dev, DMA_BIT_MASK(32)); if (ret) diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 160c07699a8b72..91ac99bc3edb2e 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -170,6 +170,7 @@ config SND_SOC_ALL_CODECS imply SND_SOC_MT6359 imply SND_SOC_MT6660 imply SND_SOC_NAU8315 + imply SND_SOC_NAU8325 imply SND_SOC_NAU8540 imply SND_SOC_NAU8810 imply SND_SOC_NAU8821 @@ -2715,6 +2716,10 @@ config SND_SOC_MT6660 config SND_SOC_NAU8315 tristate "Nuvoton Technology Corporation NAU8315 CODEC" +config SND_SOC_NAU8325 + tristate "Nuvoton Technology Corporation NAU8325 CODEC" + depends on I2C + config SND_SOC_NAU8540 tristate "Nuvoton Technology Corporation NAU85L40 CODEC" depends on I2C diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile index bd95a7c911d5c1..da4077463278e3 100644 --- a/sound/soc/codecs/Makefile +++ b/sound/soc/codecs/Makefile @@ -192,6 +192,7 @@ snd-soc-mt6359-y := mt6359.o snd-soc-mt6359-accdet-y := mt6359-accdet.o snd-soc-mt6660-y := mt6660.o snd-soc-nau8315-y := nau8315.o +snd-soc-nau8325-y := nau8325.o snd-soc-nau8540-y := nau8540.o snd-soc-nau8810-y := nau8810.o snd-soc-nau8821-y := nau8821.o @@ -618,6 +619,7 @@ obj-$(CONFIG_SND_SOC_MT6359) += snd-soc-mt6359.o obj-$(CONFIG_SND_SOC_MT6359_ACCDET) += mt6359-accdet.o obj-$(CONFIG_SND_SOC_MT6660) += snd-soc-mt6660.o obj-$(CONFIG_SND_SOC_NAU8315) += snd-soc-nau8315.o +obj-$(CONFIG_SND_SOC_NAU8325) += snd-soc-nau8325.o obj-$(CONFIG_SND_SOC_NAU8540) += snd-soc-nau8540.o obj-$(CONFIG_SND_SOC_NAU8810) += snd-soc-nau8810.o obj-$(CONFIG_SND_SOC_NAU8821) += snd-soc-nau8821.o diff --git a/sound/soc/codecs/ak4458.c b/sound/soc/codecs/ak4458.c index 57cf601d3df354..abe742edb10fe5 100644 --- a/sound/soc/codecs/ak4458.c +++ b/sound/soc/codecs/ak4458.c @@ -671,7 +671,15 @@ static int ak4458_runtime_resume(struct device *dev) regcache_cache_only(ak4458->regmap, false); regcache_mark_dirty(ak4458->regmap); - return regcache_sync(ak4458->regmap); + ret = regcache_sync(ak4458->regmap); + if (ret) + goto err; + + return 0; +err: + regcache_cache_only(ak4458->regmap, true); + regulator_bulk_disable(ARRAY_SIZE(ak4458->supplies), ak4458->supplies); + return ret; } static const struct snd_soc_component_driver soc_codec_dev_ak4458 = { @@ -775,16 +783,12 @@ static int ak4458_i2c_probe(struct i2c_client *i2c) pm_runtime_enable(&i2c->dev); regcache_cache_only(ak4458->regmap, true); - ak4458_reset(ak4458, false); return 0; } static void ak4458_i2c_remove(struct i2c_client *i2c) { - struct ak4458_priv *ak4458 = i2c_get_clientdata(i2c); - - ak4458_reset(ak4458, true); pm_runtime_disable(&i2c->dev); } diff --git a/sound/soc/codecs/ak5558.c b/sound/soc/codecs/ak5558.c index 683f3e472f5000..73684fc5beb1a7 100644 --- a/sound/soc/codecs/ak5558.c +++ b/sound/soc/codecs/ak5558.c @@ -372,7 +372,15 @@ static int ak5558_runtime_resume(struct device *dev) regcache_cache_only(ak5558->regmap, false); regcache_mark_dirty(ak5558->regmap); - return regcache_sync(ak5558->regmap); + ret = regcache_sync(ak5558->regmap); + if (ret) + goto err; + + return 0; +err: + regcache_cache_only(ak5558->regmap, true); + regulator_bulk_disable(ARRAY_SIZE(ak5558->supplies), ak5558->supplies); + return ret; } static const struct dev_pm_ops ak5558_pm = { diff --git a/sound/soc/codecs/aw88261.c b/sound/soc/codecs/aw88261.c index de11ae8dd9d9f7..124c0a58d08bd2 100644 --- a/sound/soc/codecs/aw88261.c +++ b/sound/soc/codecs/aw88261.c @@ -423,9 +423,10 @@ static int aw88261_dev_reg_update(struct aw88261 *aw88261, if (ret) break; + /* keep all three bits from current hw status */ read_val &= (~AW88261_AMPPD_MASK) | (~AW88261_PWDN_MASK) | (~AW88261_HMUTE_MASK); - reg_val &= (AW88261_AMPPD_MASK | AW88261_PWDN_MASK | AW88261_HMUTE_MASK); + reg_val &= (AW88261_AMPPD_MASK & AW88261_PWDN_MASK & AW88261_HMUTE_MASK); reg_val |= read_val; /* enable uls hmute */ diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c index 173d7c59b7254d..5001a546a3e750 100644 --- a/sound/soc/codecs/cs35l41.c +++ b/sound/soc/codecs/cs35l41.c @@ -1188,13 +1188,14 @@ static int cs35l41_get_system_name(struct cs35l41_private *cs35l41) } } -err: if (sub) { cs35l41->dsp.system_name = sub; dev_info(cs35l41->dev, "Subsystem ID: %s\n", cs35l41->dsp.system_name); - } else - dev_warn(cs35l41->dev, "Subsystem ID not found\n"); + return 0; + } +err: + dev_warn(cs35l41->dev, "Subsystem ID not found\n"); return ret; } diff --git a/sound/soc/codecs/cs35l45.c b/sound/soc/codecs/cs35l45.c index d4dcdf37bb709a..9b1eff4e9bb717 100644 --- a/sound/soc/codecs/cs35l45.c +++ b/sound/soc/codecs/cs35l45.c @@ -455,7 +455,7 @@ static const struct snd_soc_dapm_widget cs35l45_dapm_widgets[] = { SND_SOC_DAPM_AIF_OUT("ASP_TX2", NULL, 1, CS35L45_ASP_ENABLES1, CS35L45_ASP_TX2_EN_SHIFT, 0), SND_SOC_DAPM_AIF_OUT("ASP_TX3", NULL, 2, CS35L45_ASP_ENABLES1, CS35L45_ASP_TX3_EN_SHIFT, 0), SND_SOC_DAPM_AIF_OUT("ASP_TX4", NULL, 3, CS35L45_ASP_ENABLES1, CS35L45_ASP_TX4_EN_SHIFT, 0), - SND_SOC_DAPM_AIF_OUT("ASP_TX5", NULL, 3, CS35L45_ASP_ENABLES1, CS35L45_ASP_TX5_EN_SHIFT, 0), + SND_SOC_DAPM_AIF_OUT("ASP_TX5", NULL, 4, CS35L45_ASP_ENABLES1, CS35L45_ASP_TX5_EN_SHIFT, 0), SND_SOC_DAPM_MUX("ASP_TX1 Source", SND_SOC_NOPM, 0, 0, &cs35l45_asp_muxes[0]), SND_SOC_DAPM_MUX("ASP_TX2 Source", SND_SOC_NOPM, 0, 0, &cs35l45_asp_muxes[1]), diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index 78bb093fa0cc0d..8502a1fbdc52d2 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -1148,7 +1148,6 @@ struct snd_soc_dai_driver cs42l42_dai = { .formats = CS42L42_FORMATS, }, .symmetric_rate = 1, - .symmetric_sample_bits = 1, .ops = &cs42l42_ops, }; EXPORT_SYMBOL_NS_GPL(cs42l42_dai, "SND_SOC_CS42L42_CORE"); @@ -1676,7 +1675,7 @@ irqreturn_t cs42l42_irq_thread(int irq, void *data) return IRQ_NONE; } - /* Read sticky registers to clear interurpt */ + /* Read sticky registers to clear interrupt */ for (i = 0; i < ARRAY_SIZE(stickies); i++) { regmap_read(cs42l42->regmap, irq_params_table[i].status_addr, &(stickies[i])); @@ -2419,6 +2418,16 @@ int cs42l42_init(struct cs42l42_private *cs42l42) (1 << CS42L42_ADC_PDN_SHIFT) | (0 << CS42L42_PDN_ALL_SHIFT)); + /* + * Configure a faster digital ramp time, to avoid an audible + * fade-in when streams start. + */ + regmap_update_bits(cs42l42->regmap, CS42L42_SFTRAMP_RATE, + CS42L42_SFTRAMP_ASR_RATE_MASK | + CS42L42_SFTRAMP_DSR_RATE_MASK, + (10 << CS42L42_SFTRAMP_ASR_RATE_SHIFT) | + (1 << CS42L42_SFTRAMP_DSR_RATE_SHIFT)); + ret = cs42l42_handle_device_data(cs42l42->dev, cs42l42); if (ret != 0) goto err_shutdown; diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c index 867e23d4fb8d8b..744488f371ea43 100644 --- a/sound/soc/codecs/cs42l43-jack.c +++ b/sound/soc/codecs/cs42l43-jack.c @@ -496,7 +496,23 @@ void cs42l43_bias_sense_timeout(struct work_struct *work) pm_runtime_put_autosuspend(priv->dev); } -static void cs42l43_start_load_detect(struct cs42l43_codec *priv) +static const struct reg_sequence cs42l43_3pole_patch[] = { + { 0x4000, 0x00000055 }, + { 0x4000, 0x000000AA }, + { 0x17420, 0x8500F300 }, + { 0x17424, 0x36003E00 }, + { 0x4000, 0x00000000 }, +}; + +static const struct reg_sequence cs42l43_4pole_patch[] = { + { 0x4000, 0x00000055 }, + { 0x4000, 0x000000AA }, + { 0x17420, 0x7800E600 }, + { 0x17424, 0x36003800 }, + { 0x4000, 0x00000000 }, +}; + +static void cs42l43_start_load_detect(struct cs42l43_codec *priv, bool mic) { struct cs42l43 *cs42l43 = priv->core; @@ -520,6 +536,15 @@ static void cs42l43_start_load_detect(struct cs42l43_codec *priv) dev_err(priv->dev, "Load detect HP power down timed out\n"); } + if (mic) + regmap_multi_reg_write_bypassed(cs42l43->regmap, + cs42l43_4pole_patch, + ARRAY_SIZE(cs42l43_4pole_patch)); + else + regmap_multi_reg_write_bypassed(cs42l43->regmap, + cs42l43_3pole_patch, + ARRAY_SIZE(cs42l43_3pole_patch)); + regmap_update_bits(cs42l43->regmap, CS42L43_BLOCK_EN3, CS42L43_ADC1_EN_MASK | CS42L43_ADC2_EN_MASK, 0); regmap_update_bits(cs42l43->regmap, CS42L43_DACCNFG2, CS42L43_HP_HPF_EN_MASK, 0); @@ -598,7 +623,7 @@ static int cs42l43_run_load_detect(struct cs42l43_codec *priv, bool mic) reinit_completion(&priv->load_detect); - cs42l43_start_load_detect(priv); + cs42l43_start_load_detect(priv, mic); time_left = wait_for_completion_timeout(&priv->load_detect, msecs_to_jiffies(CS42L43_LOAD_TIMEOUT_MS)); cs42l43_stop_load_detect(priv); @@ -622,11 +647,11 @@ static int cs42l43_run_load_detect(struct cs42l43_codec *priv, bool mic) } switch (val & CS42L43_AMP3_RES_DET_MASK) { - case 0x0: // low impedance - case 0x1: // high impedance + case 0x0: // < 22 Ohm impedance + case 0x1: // < 150 Ohm impedance + case 0x2: // < 1000 Ohm impedance return CS42L43_JACK_HEADPHONE; - case 0x2: // lineout - case 0x3: // Open circuit + case 0x3: // > 1000 Ohm impedance return CS42L43_JACK_LINEOUT; default: return -EINVAL; diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c index 1da34cb3505f35..c7d4dc553e6aad 100644 --- a/sound/soc/codecs/lpass-tx-macro.c +++ b/sound/soc/codecs/lpass-tx-macro.c @@ -2473,7 +2473,8 @@ static const struct tx_macro_data lpass_ver_9_2 = { }; static const struct tx_macro_data lpass_ver_10_sm6115 = { - .flags = LPASS_MACRO_FLAG_HAS_NPL_CLOCK, + .flags = LPASS_MACRO_FLAG_HAS_NPL_CLOCK | + LPASS_MACRO_FLAG_RESET_SWR, .ver = LPASS_VER_10_0_0, .extra_widgets = tx_macro_dapm_widgets_v9_2, .extra_widgets_num = ARRAY_SIZE(tx_macro_dapm_widgets_v9_2), diff --git a/sound/soc/codecs/nau8325.c b/sound/soc/codecs/nau8325.c index 2266f320a8f228..d396160213f5db 100644 --- a/sound/soc/codecs/nau8325.c +++ b/sound/soc/codecs/nau8325.c @@ -386,7 +386,8 @@ static int nau8325_clksrc_choose(struct nau8325 *nau8325, const struct nau8325_srate_attr **srate_table, int *n1_sel, int *mult_sel, int *n2_sel) { - int i, j, mclk, mclk_max, ratio, ratio_sel, n2_max; + int i, j, mclk, ratio; + int mclk_max = 0, ratio_sel = 0, n2_max = 0; if (!nau8325->mclk || !nau8325->fs) goto proc_err; @@ -408,7 +409,6 @@ static int nau8325_clksrc_choose(struct nau8325 *nau8325, } /* Get MCLK_SRC through 1/N, Multiplier, and then 1/N2. */ - mclk_max = 0; for (i = 0; i < ARRAY_SIZE(mclk_n1_div); i++) { for (j = 0; j < ARRAY_SIZE(mclk_n3_mult); j++) { mclk = nau8325->mclk << mclk_n3_mult[j].param; @@ -829,8 +829,7 @@ static int nau8325_read_device_properties(struct device *dev, return 0; } -static int nau8325_i2c_probe(struct i2c_client *i2c, - const struct i2c_device_id *id) +static int nau8325_i2c_probe(struct i2c_client *i2c) { struct device *dev = &i2c->dev; struct nau8325 *nau8325 = dev_get_platdata(dev); diff --git a/sound/soc/codecs/nau8821.c b/sound/soc/codecs/nau8821.c index 4fa9a785513e52..dfb9630bffe29c 100644 --- a/sound/soc/codecs/nau8821.c +++ b/sound/soc/codecs/nau8821.c @@ -1661,8 +1661,13 @@ int nau8821_enable_jack_detect(struct snd_soc_component *component, int ret; nau8821->jack = jack; + + if (nau8821->jdet_active) + return 0; + /* Initiate jack detection work queue */ INIT_DELAYED_WORK(&nau8821->jdet_work, nau8821_jdet_work); + nau8821->jdet_active = true; ret = devm_request_threaded_irq(nau8821->dev, nau8821->irq, NULL, nau8821_interrupt, IRQF_TRIGGER_LOW | IRQF_ONESHOT, diff --git a/sound/soc/codecs/nau8821.h b/sound/soc/codecs/nau8821.h index 88602923780d85..f9d7cd8cbd2116 100644 --- a/sound/soc/codecs/nau8821.h +++ b/sound/soc/codecs/nau8821.h @@ -562,6 +562,7 @@ struct nau8821 { struct snd_soc_dapm_context *dapm; struct snd_soc_jack *jack; struct delayed_work jdet_work; + bool jdet_active; int irq; int clk_id; int micbias_voltage; diff --git a/sound/soc/codecs/pm4125.c b/sound/soc/codecs/pm4125.c index 706fc668ffe2a3..3d7b07624ee614 100644 --- a/sound/soc/codecs/pm4125.c +++ b/sound/soc/codecs/pm4125.c @@ -70,7 +70,7 @@ struct pm4125_priv { struct wcd_mbhc_config mbhc_cfg; struct wcd_mbhc_intr intr_ids; struct irq_domain *virq; - const struct regmap_irq_chip *pm4125_regmap_irq_chip; + const struct regmap_irq_chip *chip_desc; struct regmap_irq_chip_data *irq_chip; struct snd_soc_jack *jack; unsigned long status_mask; @@ -179,7 +179,7 @@ static const u32 pm4125_config_regs[] = { PM4125_DIG_SWR_INTR_LEVEL_0, }; -static struct regmap_irq_chip pm4125_regmap_irq_chip = { +static const struct regmap_irq_chip pm4125_regmap_irq_chip = { .name = "pm4125", .irqs = pm4125_irqs, .num_irqs = ARRAY_SIZE(pm4125_irqs), @@ -1320,10 +1320,8 @@ static int pm4125_irq_init(struct pm4125_priv *pm4125, struct device *dev) return -EINVAL; } - pm4125_regmap_irq_chip.irq_drv_data = pm4125; - return devm_regmap_add_irq_chip(dev, pm4125->regmap, irq_create_mapping(pm4125->virq, 0), - IRQF_ONESHOT, 0, &pm4125_regmap_irq_chip, + IRQF_ONESHOT, 0, pm4125->chip_desc, &pm4125->irq_chip); } @@ -1551,6 +1549,10 @@ static int pm4125_bind(struct device *dev) struct device_link *devlink; int ret; + /* Initialize device pointers to NULL for safe cleanup */ + pm4125->rxdev = NULL; + pm4125->txdev = NULL; + /* Give the soundwire subdevices some more time to settle */ usleep_range(15000, 15010); @@ -1574,7 +1576,7 @@ static int pm4125_bind(struct device *dev) if (!pm4125->txdev) { dev_err(dev, "could not find txslave with matching of node\n"); ret = -EINVAL; - goto error_unbind_all; + goto error_put_rx; } pm4125->sdw_priv[AIF1_CAP] = dev_get_drvdata(pm4125->txdev); @@ -1584,7 +1586,7 @@ static int pm4125_bind(struct device *dev) if (!pm4125->tx_sdw_dev) { dev_err(dev, "could not get txslave with matching of dev\n"); ret = -EINVAL; - goto error_unbind_all; + goto error_put_tx; } /* @@ -1596,7 +1598,7 @@ static int pm4125_bind(struct device *dev) if (!devlink) { dev_err(dev, "Could not devlink TX and RX\n"); ret = -EINVAL; - goto error_unbind_all; + goto error_put_tx; } devlink = device_link_add(dev, pm4125->txdev, @@ -1650,6 +1652,10 @@ static int pm4125_bind(struct device *dev) device_link_remove(dev, pm4125->txdev); link_remove_rx_tx: device_link_remove(pm4125->rxdev, pm4125->txdev); +error_put_tx: + put_device(pm4125->txdev); +error_put_rx: + put_device(pm4125->rxdev); error_unbind_all: component_unbind_all(dev, pm4125); return ret; @@ -1660,9 +1666,18 @@ static void pm4125_unbind(struct device *dev) struct pm4125_priv *pm4125 = dev_get_drvdata(dev); snd_soc_unregister_component(dev); + devm_regmap_del_irq_chip(dev, irq_find_mapping(pm4125->virq, 0), + pm4125->irq_chip); device_link_remove(dev, pm4125->txdev); device_link_remove(dev, pm4125->rxdev); device_link_remove(pm4125->rxdev, pm4125->txdev); + + /* Release device references acquired in bind */ + if (pm4125->txdev) + put_device(pm4125->txdev); + if (pm4125->rxdev) + put_device(pm4125->rxdev); + component_unbind_all(dev, pm4125); } @@ -1695,6 +1710,7 @@ static int pm4125_probe(struct platform_device *pdev) { struct component_match *match = NULL; struct device *dev = &pdev->dev; + struct regmap_irq_chip *chip_desc; struct pm4125_priv *pm4125; struct wcd_mbhc_config *cfg; int ret; @@ -1705,6 +1721,14 @@ static int pm4125_probe(struct platform_device *pdev) dev_set_drvdata(dev, pm4125); + chip_desc = devm_kmemdup(dev, &pm4125_regmap_irq_chip, + sizeof(pm4125_regmap_irq_chip), + GFP_KERNEL); + if (!chip_desc) + return -ENOMEM; + chip_desc->irq_drv_data = pm4125; + pm4125->chip_desc = chip_desc; + ret = devm_regulator_bulk_get_enable(dev, ARRAY_SIZE(pm4125_power_supplies), pm4125_power_supplies); if (ret) diff --git a/sound/soc/codecs/tas2764.c b/sound/soc/codecs/tas2764.c index 36e25e48b35463..a458458128aa89 100644 --- a/sound/soc/codecs/tas2764.c +++ b/sound/soc/codecs/tas2764.c @@ -34,6 +34,7 @@ struct tas2764_priv { struct snd_soc_component *component; struct gpio_desc *reset_gpio; struct gpio_desc *sdz_gpio; + struct regulator *sdz_reg; struct regmap *regmap; struct device *dev; int irq; @@ -41,6 +42,7 @@ struct tas2764_priv { int v_sense_slot; int i_sense_slot; + u32 sdout_zero_mask; bool dac_powered; bool unmuted; @@ -152,6 +154,8 @@ static int tas2764_codec_suspend(struct snd_soc_component *component) if (tas2764->sdz_gpio) gpiod_set_value_cansleep(tas2764->sdz_gpio, 0); + regulator_disable(tas2764->sdz_reg); + regcache_cache_only(tas2764->regmap, true); regcache_mark_dirty(tas2764->regmap); @@ -165,19 +169,26 @@ static int tas2764_codec_resume(struct snd_soc_component *component) struct tas2764_priv *tas2764 = snd_soc_component_get_drvdata(component); int ret; + ret = regulator_enable(tas2764->sdz_reg); + + if (ret) { + dev_err(tas2764->dev, "Failed to enable regulator\n"); + return ret; + } + if (tas2764->sdz_gpio) { gpiod_set_value_cansleep(tas2764->sdz_gpio, 1); - usleep_range(1000, 2000); } - ret = tas2764_update_pwr_ctrl(tas2764); + usleep_range(1000, 2000); + regcache_cache_only(tas2764->regmap, false); + + ret = regcache_sync(tas2764->regmap); if (ret < 0) return ret; - regcache_cache_only(tas2764->regmap, false); - - return regcache_sync(tas2764->regmap); + return tas2764_update_pwr_ctrl(tas2764); } #else #define tas2764_codec_suspend NULL @@ -210,7 +221,7 @@ static const struct snd_soc_dapm_widget tas2764_dapm_widgets[] = { SND_SOC_DAPM_DAC("DAC", NULL, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_OUTPUT("OUT"), SND_SOC_DAPM_SIGGEN("VMON"), - SND_SOC_DAPM_SIGGEN("IMON") + SND_SOC_DAPM_SIGGEN("IMON"), }; static const struct snd_soc_dapm_route tas2764_audio_map[] = { @@ -261,7 +272,6 @@ static int tas2764_mute(struct snd_soc_dai *dai, int mute, int direction) static int tas2764_set_bitwidth(struct tas2764_priv *tas2764, int bitwidth) { struct snd_soc_component *component = tas2764->component; - int sense_en; int val; int ret; @@ -296,28 +306,6 @@ static int tas2764_set_bitwidth(struct tas2764_priv *tas2764, int bitwidth) if (val < 0) return val; - if (val & (1 << TAS2764_VSENSE_POWER_EN)) - sense_en = 0; - else - sense_en = TAS2764_TDM_CFG5_VSNS_ENABLE; - - ret = snd_soc_component_update_bits(tas2764->component, TAS2764_TDM_CFG5, - TAS2764_TDM_CFG5_VSNS_ENABLE, - sense_en); - if (ret < 0) - return ret; - - if (val & (1 << TAS2764_ISENSE_POWER_EN)) - sense_en = 0; - else - sense_en = TAS2764_TDM_CFG6_ISNS_ENABLE; - - ret = snd_soc_component_update_bits(tas2764->component, TAS2764_TDM_CFG6, - TAS2764_TDM_CFG6_ISNS_ENABLE, - sense_en); - if (ret < 0) - return ret; - return 0; } @@ -373,6 +361,44 @@ static int tas2764_hw_params(struct snd_pcm_substream *substream, return tas2764_set_samplerate(tas2764, params_rate(params)); } +static int tas2764_write_sdout_zero_mask(struct tas2764_priv *tas2764, int bclk_ratio) +{ + struct snd_soc_component *component = tas2764->component; + int nsense_slots = bclk_ratio / 8; + u32 cropped_mask; + int i, ret; + + if (!tas2764->sdout_zero_mask) + return 0; + + cropped_mask = tas2764->sdout_zero_mask & GENMASK(nsense_slots - 1, 0); + + for (i = 0; i < 4; i++) { + ret = snd_soc_component_write(component, TAS2764_SDOUT_HIZ_1 + i, + (cropped_mask >> (i * 8)) & 0xff); + + if (ret < 0) + return ret; + } + + ret = snd_soc_component_update_bits(component, TAS2764_SDOUT_HIZ_9, + TAS2764_SDOUT_HIZ_9_FORCE_0_EN, + TAS2764_SDOUT_HIZ_9_FORCE_0_EN); + + if (ret < 0) + return ret; + + return 0; +} + +static int tas2764_set_bclk_ratio(struct snd_soc_dai *dai, unsigned int ratio) +{ + struct snd_soc_component *component = dai->component; + struct tas2764_priv *tas2764 = snd_soc_component_get_drvdata(component); + + return tas2764_write_sdout_zero_mask(tas2764, ratio); +} + static int tas2764_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) { struct snd_soc_component *component = dai->component; @@ -447,7 +473,6 @@ static int tas2764_set_dai_tdm_slot(struct snd_soc_dai *dai, int slots, int slot_width) { struct snd_soc_component *component = dai->component; - struct tas2764_priv *tas2764 = snd_soc_component_get_drvdata(component); int left_slot, right_slot; int slots_cfg; int slot_size; @@ -494,15 +519,26 @@ static int tas2764_set_dai_tdm_slot(struct snd_soc_dai *dai, if (ret < 0) return ret; - ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG5, + return 0; +} + +static int tas2764_set_ivsense_transmit(struct tas2764_priv *tas2764, int i_slot, int v_slot) +{ + int ret; + + ret = snd_soc_component_update_bits(tas2764->component, TAS2764_TDM_CFG5, + TAS2764_TDM_CFG5_VSNS_ENABLE | TAS2764_TDM_CFG5_50_MASK, - tas2764->v_sense_slot); + TAS2764_TDM_CFG5_VSNS_ENABLE | + v_slot); if (ret < 0) return ret; - ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG6, + ret = snd_soc_component_update_bits(tas2764->component, TAS2764_TDM_CFG6, + TAS2764_TDM_CFG6_ISNS_ENABLE | TAS2764_TDM_CFG6_50_MASK, - tas2764->i_sense_slot); + TAS2764_TDM_CFG6_ISNS_ENABLE | + i_slot); if (ret < 0) return ret; @@ -512,6 +548,7 @@ static int tas2764_set_dai_tdm_slot(struct snd_soc_dai *dai, static const struct snd_soc_dai_ops tas2764_dai_ops = { .mute_stream = tas2764_mute, .hw_params = tas2764_hw_params, + .set_bclk_ratio = tas2764_set_bclk_ratio, .set_fmt = tas2764_set_fmt, .set_tdm_slot = tas2764_set_dai_tdm_slot, .no_capture_mute = 1, @@ -659,11 +696,18 @@ static int tas2764_codec_probe(struct snd_soc_component *component) tas2764->component = component; + ret = regulator_enable(tas2764->sdz_reg); + if (ret != 0) { + dev_err(tas2764->dev, "Failed to enable regulator: %d\n", ret); + return ret; + } + if (tas2764->sdz_gpio) { gpiod_set_value_cansleep(tas2764->sdz_gpio, 1); - usleep_range(1000, 2000); } + usleep_range(1000, 2000); + tas2764_reset(tas2764); regmap_reinit_cache(tas2764->regmap, &tas2764_i2c_regmap); @@ -695,18 +739,33 @@ static int tas2764_codec_probe(struct snd_soc_component *component) dev_warn(tas2764->dev, "failed to request IRQ: %d\n", ret); } - ret = snd_soc_component_update_bits(tas2764->component, TAS2764_TDM_CFG5, - TAS2764_TDM_CFG5_VSNS_ENABLE, 0); - if (ret < 0) - return ret; + if (tas2764->i_sense_slot != -1 && tas2764->v_sense_slot != -1) { + ret = tas2764_set_ivsense_transmit(tas2764, tas2764->i_sense_slot, + tas2764->v_sense_slot); - ret = snd_soc_component_update_bits(tas2764->component, TAS2764_TDM_CFG6, - TAS2764_TDM_CFG6_ISNS_ENABLE, 0); - if (ret < 0) - return ret; + if (ret < 0) + return ret; + } switch (tas2764->devid) { case DEVID_SN012776: + if (tas2764->sdout_zero_mask) { + for (i = 0; i < 4; i++) { + ret = snd_soc_component_write(component, TAS2764_SDOUT_HIZ_1 + i, + (tas2764->sdout_zero_mask >> (i * 8)) & 0xff); + + if (ret < 0) + return ret; + } + + ret = snd_soc_component_update_bits(component, TAS2764_SDOUT_HIZ_9, + TAS2764_SDOUT_HIZ_9_FORCE_0_EN, + TAS2764_SDOUT_HIZ_9_FORCE_0_EN); + + if (ret < 0) + return ret; + } + ret = snd_soc_component_update_bits(component, TAS2764_PWR_CTRL, TAS2764_PWR_CTRL_BOP_SRC, TAS2764_PWR_CTRL_BOP_SRC); @@ -736,6 +795,13 @@ static int tas2764_codec_probe(struct snd_soc_component *component) return 0; } +static void tas2764_codec_remove(struct snd_soc_component *component) +{ + struct tas2764_priv *tas2764 = snd_soc_component_get_drvdata(component); + + regulator_disable(tas2764->sdz_reg); +} + static DECLARE_TLV_DB_SCALE(tas2764_digital_tlv, 1100, 50, 0); static DECLARE_TLV_DB_SCALE(tas2764_playback_volume, -10050, 50, 1); @@ -767,6 +833,7 @@ static const struct snd_kcontrol_new tas2764_snd_controls[] = { static const struct snd_soc_component_driver soc_component_driver_tas2764 = { .probe = tas2764_codec_probe, + .remove = tas2764_codec_remove, .suspend = tas2764_codec_suspend, .resume = tas2764_codec_resume, .controls = tas2764_snd_controls, @@ -836,6 +903,11 @@ static int tas2764_parse_dt(struct device *dev, struct tas2764_priv *tas2764) { int ret = 0; + tas2764->sdz_reg = devm_regulator_get(dev, "SDZ"); + if (IS_ERR(tas2764->sdz_reg)) + return dev_err_probe(dev, PTR_ERR(tas2764->sdz_reg), + "Failed to get SDZ supply\n"); + tas2764->reset_gpio = devm_gpiod_get_optional(tas2764->dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(tas2764->reset_gpio)) { @@ -856,12 +928,17 @@ static int tas2764_parse_dt(struct device *dev, struct tas2764_priv *tas2764) ret = fwnode_property_read_u32(dev->fwnode, "ti,imon-slot-no", &tas2764->i_sense_slot); if (ret) - tas2764->i_sense_slot = 0; + tas2764->i_sense_slot = -1; ret = fwnode_property_read_u32(dev->fwnode, "ti,vmon-slot-no", &tas2764->v_sense_slot); if (ret) - tas2764->v_sense_slot = 2; + tas2764->v_sense_slot = -1; + + ret = fwnode_property_read_u32(dev->fwnode, "ti,sdout-force-zero-mask", + &tas2764->sdout_zero_mask); + if (ret) + tas2764->sdout_zero_mask = 0; return 0; } diff --git a/sound/soc/codecs/tas2764.h b/sound/soc/codecs/tas2764.h index 538290ed3d92ac..4a419c11d4b08e 100644 --- a/sound/soc/codecs/tas2764.h +++ b/sound/soc/codecs/tas2764.h @@ -126,4 +126,15 @@ #define TAS2764_BOP_CFG0 TAS2764_REG(0X0, 0x1d) +#define TAS2764_SDOUT_HIZ_1 TAS2764_REG(0x1, 0x3d) +#define TAS2764_SDOUT_HIZ_2 TAS2764_REG(0x1, 0x3e) +#define TAS2764_SDOUT_HIZ_3 TAS2764_REG(0x1, 0x3f) +#define TAS2764_SDOUT_HIZ_4 TAS2764_REG(0x1, 0x40) +#define TAS2764_SDOUT_HIZ_5 TAS2764_REG(0x1, 0x41) +#define TAS2764_SDOUT_HIZ_6 TAS2764_REG(0x1, 0x42) +#define TAS2764_SDOUT_HIZ_7 TAS2764_REG(0x1, 0x43) +#define TAS2764_SDOUT_HIZ_8 TAS2764_REG(0x1, 0x44) +#define TAS2764_SDOUT_HIZ_9 TAS2764_REG(0x1, 0x45) +#define TAS2764_SDOUT_HIZ_9_FORCE_0_EN BIT(7) + #endif /* __TAS2764__ */ diff --git a/sound/soc/codecs/tas2770.c b/sound/soc/codecs/tas2770.c index 6f878b01716f72..e72027cf340bfe 100644 --- a/sound/soc/codecs/tas2770.c +++ b/sound/soc/codecs/tas2770.c @@ -71,23 +71,21 @@ static int tas2770_codec_suspend(struct snd_soc_component *component) struct tas2770_priv *tas2770 = snd_soc_component_get_drvdata(component); int ret = 0; - regcache_cache_only(tas2770->regmap, true); - regcache_mark_dirty(tas2770->regmap); + ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL, + TAS2770_PWR_CTRL_MASK, + TAS2770_PWR_CTRL_SHUTDOWN); + if (ret < 0) + return ret; - if (tas2770->sdz_gpio) { + if (tas2770->sdz_gpio) gpiod_set_value_cansleep(tas2770->sdz_gpio, 0); - } else { - ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL, - TAS2770_PWR_CTRL_MASK, - TAS2770_PWR_CTRL_SHUTDOWN); - if (ret < 0) { - regcache_cache_only(tas2770->regmap, false); - regcache_sync(tas2770->regmap); - return ret; - } - ret = 0; - } + regulator_disable(tas2770->sdz_reg); + + regcache_cache_only(tas2770->regmap, true); + regcache_mark_dirty(tas2770->regmap); + + usleep_range(6000, 7000); return ret; } @@ -97,18 +95,26 @@ static int tas2770_codec_resume(struct snd_soc_component *component) struct tas2770_priv *tas2770 = snd_soc_component_get_drvdata(component); int ret; - if (tas2770->sdz_gpio) { - gpiod_set_value_cansleep(tas2770->sdz_gpio, 1); - usleep_range(1000, 2000); - } else { - ret = tas2770_update_pwr_ctrl(tas2770); - if (ret < 0) - return ret; + ret = regulator_enable(tas2770->sdz_reg); + + if (ret) { + dev_err(tas2770->dev, "Failed to enable regulator\n"); + return ret; } + if (tas2770->sdz_gpio) + gpiod_set_value_cansleep(tas2770->sdz_gpio, 1); + + + usleep_range(1000, 2000); + regcache_cache_only(tas2770->regmap, false); - return regcache_sync(tas2770->regmap); + ret = regcache_sync(tas2770->regmap); + if (ret < 0) + return ret; + + return tas2770_update_pwr_ctrl(tas2770); } #else #define tas2770_codec_suspend NULL @@ -623,11 +629,18 @@ static int tas2770_codec_probe(struct snd_soc_component *component) tas2770->component = component; + ret = regulator_enable(tas2770->sdz_reg); + if (ret != 0) { + dev_err(tas2770->dev, "Failed to enable regulator: %d\n", ret); + return ret; + } + if (tas2770->sdz_gpio) { gpiod_set_value_cansleep(tas2770->sdz_gpio, 1); - usleep_range(1000, 2000); } + usleep_range(1000, 2000); + tas2770_reset(tas2770); regmap_reinit_cache(tas2770->regmap, &tas2770_i2c_regmap); @@ -641,14 +654,34 @@ static int tas2770_codec_probe(struct snd_soc_component *component) if (tas2770->pdm_slot != -1) { ret = tas2770_set_pdm_transmit(tas2770, tas2770->pdm_slot); - if (ret < 0) return ret; } + ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG4, + TAS2770_TDM_CFG_REG4_TX_FILL, + tas2770->sdout_zfill ? 0 : + TAS2770_TDM_CFG_REG4_TX_FILL); + if (ret < 0) + return ret; + + ret = snd_soc_component_update_bits(component, TAS2770_DIN_PD, + TAS2770_DIN_PD_SDOUT, + tas2770->sdout_pd ? + TAS2770_DIN_PD_SDOUT : 0); + if (ret < 0) + return ret; + return 0; } +static void tas2770_codec_remove(struct snd_soc_component *component) +{ + struct tas2770_priv *tas2770 = snd_soc_component_get_drvdata(component); + + regulator_disable(tas2770->sdz_reg); +} + static DECLARE_TLV_DB_SCALE(tas2770_digital_tlv, 1100, 50, 0); static DECLARE_TLV_DB_SCALE(tas2770_playback_volume, -10050, 50, 0); @@ -661,6 +694,7 @@ static const struct snd_kcontrol_new tas2770_snd_controls[] = { static const struct snd_soc_component_driver soc_component_driver_tas2770 = { .probe = tas2770_codec_probe, + .remove = tas2770_codec_remove, .suspend = tas2770_codec_suspend, .resume = tas2770_codec_resume, .controls = tas2770_snd_controls, @@ -790,6 +824,14 @@ static int tas2770_parse_dt(struct device *dev, struct tas2770_priv *tas2770) if (rc) tas2770->pdm_slot = -1; + tas2770->sdout_pd = fwnode_property_read_bool(dev->fwnode, "ti,sdout-pull-down"); + tas2770->sdout_zfill = fwnode_property_read_bool(dev->fwnode, "ti,sdout-zero-fill"); + + tas2770->sdz_reg = devm_regulator_get(dev, "SDZ"); + if (IS_ERR(tas2770->sdz_reg)) + return dev_err_probe(dev, PTR_ERR(tas2770->sdz_reg), + "Failed to get SDZ supply\n"); + tas2770->sdz_gpio = devm_gpiod_get_optional(dev, "shutdown", GPIOD_OUT_HIGH); if (IS_ERR(tas2770->sdz_gpio)) { if (PTR_ERR(tas2770->sdz_gpio) == -EPROBE_DEFER) diff --git a/sound/soc/codecs/tas2770.h b/sound/soc/codecs/tas2770.h index 3fd2e7003c50b6..b309d19c58e1da 100644 --- a/sound/soc/codecs/tas2770.h +++ b/sound/soc/codecs/tas2770.h @@ -67,6 +67,14 @@ #define TAS2770_TDM_CFG_REG3_RXS_SHIFT 0x4 #define TAS2770_TDM_CFG_REG3_30_MASK GENMASK(3, 0) #define TAS2770_TDM_CFG_REG3_30_SHIFT 0 + /* TDM Configuration Reg4 */ +#define TAS2770_TDM_CFG_REG4 TAS2770_REG(0X0, 0x0E) +#define TAS2770_TDM_CFG_REG4_TX_LSB_CFG BIT(7) +#define TAS2770_TDM_CFG_REG4_TX_KEEPER_CFG BIT(6) +#define TAS2770_TDM_CFG_REG4_TX_KEEPER BIT(5) +#define TAS2770_TDM_CFG_REG4_TX_FILL BIT(4) +#define TAS2770_TDM_CFG_REG4_TX_OFFSET_MASK GENMASK(3, 1) +#define TAS2770_TDM_CFG_REG4_TX_EDGE_FALLING BIT(0) /* TDM Configuration Reg5 */ #define TAS2770_TDM_CFG_REG5 TAS2770_REG(0X0, 0x0F) #define TAS2770_TDM_CFG_REG5_VSNS_MASK BIT(6) @@ -115,6 +123,9 @@ #define TAS2770_TEMP_LSB TAS2770_REG(0X0, 0x2A) /* Interrupt Configuration */ #define TAS2770_INT_CFG TAS2770_REG(0X0, 0x30) + /* Data In Pull-Down */ +#define TAS2770_DIN_PD TAS2770_REG(0X0, 0x31) +#define TAS2770_DIN_PD_SDOUT BIT(7) /* Misc IRQ */ #define TAS2770_MISC_IRQ TAS2770_REG(0X0, 0x32) /* Clock Configuration */ @@ -139,11 +150,14 @@ struct tas2770_priv { struct snd_soc_component *component; struct gpio_desc *reset_gpio; struct gpio_desc *sdz_gpio; + struct regulator *sdz_reg; struct regmap *regmap; struct device *dev; int v_sense_slot; int i_sense_slot; int pdm_slot; + bool sdout_pd; + bool sdout_zfill; bool dac_powered; bool unmuted; }; diff --git a/sound/soc/codecs/tas2781-comlib-i2c.c b/sound/soc/codecs/tas2781-comlib-i2c.c index b3fd7350143bdb..e24d56a14cfda1 100644 --- a/sound/soc/codecs/tas2781-comlib-i2c.c +++ b/sound/soc/codecs/tas2781-comlib-i2c.c @@ -320,7 +320,7 @@ void tasdevice_reset(struct tasdevice_priv *tas_dev) for (i = 0; i < tas_dev->ndev; i++) { ret = tasdevice_dev_write(tas_dev, i, TASDEVICE_REG_SWRESET, - tas_dev->chip_id >= TAS5825 ? + tas_dev->chip_id >= TAS5802 ? TAS5825_REG_SWRESET_RESET : TASDEVICE_REG_SWRESET_RESET); if (ret < 0) diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index 8f37aa00e62ee7..a3b4d2c3b47892 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -1391,7 +1391,7 @@ static int tasdevice_create_cali_ctrls(struct tasdevice_priv *priv) /* * Alloc kcontrol via devm_kzalloc(), which don't manually - * free the kcontrol。 + * free the kcontrol. */ cali_ctrls = devm_kcalloc(priv->dev, nctrls, sizeof(cali_ctrls[0]), GFP_KERNEL); diff --git a/sound/soc/codecs/tlv320adcx140.c b/sound/soc/codecs/tlv320adcx140.c index d594bf166c0e79..1565727ca2f3d2 100644 --- a/sound/soc/codecs/tlv320adcx140.c +++ b/sound/soc/codecs/tlv320adcx140.c @@ -23,7 +23,6 @@ #include "tlv320adcx140.h" struct adcx140_priv { - struct snd_soc_component *component; struct regulator *supply_areg; struct gpio_desc *gpio_reset; struct regmap *regmap; @@ -701,7 +700,6 @@ static void adcx140_pwr_ctrl(struct adcx140_priv *adcx140, bool power_state) { int pwr_ctrl = 0; int ret = 0; - struct snd_soc_component *component = adcx140->component; if (power_state) pwr_ctrl = ADCX140_PWR_CFG_ADC_PDZ | ADCX140_PWR_CFG_PLL_PDZ; @@ -713,7 +711,7 @@ static void adcx140_pwr_ctrl(struct adcx140_priv *adcx140, bool power_state) ret = regmap_write(adcx140->regmap, ADCX140_PHASE_CALIB, adcx140->phase_calib_on ? 0x00 : 0x40); if (ret) - dev_err(component->dev, "%s: register write error %d\n", + dev_err(adcx140->dev, "%s: register write error %d\n", __func__, ret); } @@ -729,7 +727,7 @@ static int adcx140_hw_params(struct snd_pcm_substream *substream, struct adcx140_priv *adcx140 = snd_soc_component_get_drvdata(component); u8 data = 0; - switch (params_width(params)) { + switch (params_physical_width(params)) { case 16: data = ADCX140_16_BIT_WORD; break; @@ -744,7 +742,7 @@ static int adcx140_hw_params(struct snd_pcm_substream *substream, break; default: dev_err(component->dev, "%s: Unsupported width %d\n", - __func__, params_width(params)); + __func__, params_physical_width(params)); return -EINVAL; } @@ -1158,6 +1156,9 @@ static int adcx140_i2c_probe(struct i2c_client *i2c) adcx140->gpio_reset = devm_gpiod_get_optional(adcx140->dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(adcx140->gpio_reset)) + return dev_err_probe(&i2c->dev, PTR_ERR(adcx140->gpio_reset), + "Failed to get Reset GPIO\n"); + if (!adcx140->gpio_reset) dev_info(&i2c->dev, "Reset GPIO not defined\n"); adcx140->supply_areg = devm_regulator_get_optional(adcx140->dev, diff --git a/sound/soc/codecs/wcd937x.c b/sound/soc/codecs/wcd937x.c index 421ec7a2d6bdc8..ed0ff45a89649b 100644 --- a/sound/soc/codecs/wcd937x.c +++ b/sound/soc/codecs/wcd937x.c @@ -2748,7 +2748,8 @@ static int wcd937x_bind(struct device *dev) wcd937x->rxdev = of_sdw_find_device_by_node(wcd937x->rxnode); if (!wcd937x->rxdev) { dev_err(dev, "could not find slave with matching of node\n"); - return -EINVAL; + ret = -EINVAL; + goto err_component_unbind; } wcd937x->sdw_priv[AIF1_PB] = dev_get_drvdata(wcd937x->rxdev); @@ -2757,7 +2758,8 @@ static int wcd937x_bind(struct device *dev) wcd937x->txdev = of_sdw_find_device_by_node(wcd937x->txnode); if (!wcd937x->txdev) { dev_err(dev, "could not find txslave with matching of node\n"); - return -EINVAL; + ret = -EINVAL; + goto err_put_rxdev; } wcd937x->sdw_priv[AIF1_CAP] = dev_get_drvdata(wcd937x->txdev); @@ -2765,7 +2767,8 @@ static int wcd937x_bind(struct device *dev) wcd937x->tx_sdw_dev = dev_to_sdw_dev(wcd937x->txdev); if (!wcd937x->tx_sdw_dev) { dev_err(dev, "could not get txslave with matching of dev\n"); - return -EINVAL; + ret = -EINVAL; + goto err_put_txdev; } /* @@ -2775,31 +2778,35 @@ static int wcd937x_bind(struct device *dev) if (!device_link_add(wcd937x->rxdev, wcd937x->txdev, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME)) { dev_err(dev, "Could not devlink TX and RX\n"); - return -EINVAL; + ret = -EINVAL; + goto err_put_txdev; } if (!device_link_add(dev, wcd937x->txdev, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME)) { dev_err(dev, "Could not devlink WCD and TX\n"); - return -EINVAL; + ret = -EINVAL; + goto err_remove_link1; } if (!device_link_add(dev, wcd937x->rxdev, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME)) { dev_err(dev, "Could not devlink WCD and RX\n"); - return -EINVAL; + ret = -EINVAL; + goto err_remove_link2; } wcd937x->regmap = wcd937x->sdw_priv[AIF1_CAP]->regmap; if (!wcd937x->regmap) { dev_err(dev, "could not get TX device regmap\n"); - return -EINVAL; + ret = -EINVAL; + goto err_remove_link3; } ret = wcd937x_irq_init(wcd937x, dev); if (ret) { dev_err(dev, "IRQ init failed: %d\n", ret); - return ret; + goto err_remove_link3; } wcd937x->sdw_priv[AIF1_PB]->slave_irq = wcd937x->virq; @@ -2809,10 +2816,26 @@ static int wcd937x_bind(struct device *dev) ret = snd_soc_register_component(dev, &soc_codec_dev_wcd937x, wcd937x_dais, ARRAY_SIZE(wcd937x_dais)); - if (ret) + if (ret) { dev_err(dev, "Codec registration failed\n"); + goto err_remove_link3; + } return ret; + +err_remove_link3: + device_link_remove(dev, wcd937x->rxdev); +err_remove_link2: + device_link_remove(dev, wcd937x->txdev); +err_remove_link1: + device_link_remove(wcd937x->rxdev, wcd937x->txdev); +err_put_txdev: + put_device(wcd937x->txdev); +err_put_rxdev: + put_device(wcd937x->rxdev); +err_component_unbind: + component_unbind_all(dev, wcd937x); + return ret; } static void wcd937x_unbind(struct device *dev) @@ -2825,6 +2848,8 @@ static void wcd937x_unbind(struct device *dev) device_link_remove(wcd937x->rxdev, wcd937x->txdev); component_unbind_all(dev, wcd937x); mutex_destroy(&wcd937x->micb_lock); + put_device(wcd937x->txdev); + put_device(wcd937x->rxdev); } static const struct component_master_ops wcd937x_comp_ops = { diff --git a/sound/soc/codecs/wcd939x-sdw.c b/sound/soc/codecs/wcd939x-sdw.c index d369100a245742..da342a0c95a52b 100644 --- a/sound/soc/codecs/wcd939x-sdw.c +++ b/sound/soc/codecs/wcd939x-sdw.c @@ -1400,12 +1400,18 @@ static int wcd9390_probe(struct sdw_slave *pdev, const struct sdw_device_id *id) ret = component_add(dev, &wcd_sdw_component_ops); if (ret) - return ret; + goto err_free_regmap; /* Set suspended until aggregate device is bind */ pm_runtime_set_suspended(dev); return 0; + +err_free_regmap: + if (wcd->regmap) + regmap_exit(wcd->regmap); + + return ret; } static int wcd9390_remove(struct sdw_slave *pdev) diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index 636e59abc3772f..561950ecb8cc7c 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -678,6 +678,7 @@ struct wsa881x_priv { */ unsigned int sd_n_val; int active_ports; + bool hw_init; bool port_prepared[WSA881X_MAX_SWR_PORTS]; bool port_enable[WSA881X_MAX_SWR_PORTS]; }; @@ -687,6 +688,9 @@ static void wsa881x_init(struct wsa881x_priv *wsa881x) struct regmap *rm = wsa881x->regmap; unsigned int val = 0; + if (wsa881x->hw_init) + return; + regmap_register_patch(wsa881x->regmap, wsa881x_rev_2_0, ARRAY_SIZE(wsa881x_rev_2_0)); @@ -724,6 +728,8 @@ static void wsa881x_init(struct wsa881x_priv *wsa881x) regmap_update_bits(rm, WSA881X_OTP_REG_28, 0x3F, 0x3A); regmap_update_bits(rm, WSA881X_BONGO_RESRV_REG1, 0xFF, 0xB2); regmap_update_bits(rm, WSA881X_BONGO_RESRV_REG2, 0xFF, 0x05); + + wsa881x->hw_init = true; } static int wsa881x_component_probe(struct snd_soc_component *comp) @@ -1067,6 +1073,9 @@ static int wsa881x_update_status(struct sdw_slave *slave, { struct wsa881x_priv *wsa881x = dev_get_drvdata(&slave->dev); + if (status == SDW_SLAVE_UNATTACHED) + wsa881x->hw_init = false; + if (status == SDW_SLAVE_ATTACHED && slave->dev_num > 0) wsa881x_init(wsa881x); diff --git a/sound/soc/codecs/wsa883x.c b/sound/soc/codecs/wsa883x.c index ca4520ade79aa2..5f2ced650dcc81 100644 --- a/sound/soc/codecs/wsa883x.c +++ b/sound/soc/codecs/wsa883x.c @@ -475,6 +475,7 @@ struct wsa883x_priv { int active_ports; int dev_mode; int comp_offset; + bool hw_init; /* * Protects temperature reading code (related to speaker protection) and * fields: temperature and pa_on. @@ -1043,6 +1044,9 @@ static int wsa883x_init(struct wsa883x_priv *wsa883x) struct regmap *regmap = wsa883x->regmap; int variant, version, ret; + if (wsa883x->hw_init) + return 0; + ret = regmap_read(regmap, WSA883X_OTP_REG_0, &variant); if (ret) return ret; @@ -1085,6 +1089,8 @@ static int wsa883x_init(struct wsa883x_priv *wsa883x) wsa883x->comp_offset); } + wsa883x->hw_init = true; + return 0; } @@ -1093,6 +1099,9 @@ static int wsa883x_update_status(struct sdw_slave *slave, { struct wsa883x_priv *wsa883x = dev_get_drvdata(&slave->dev); + if (status == SDW_SLAVE_UNATTACHED) + wsa883x->hw_init = false; + if (status == SDW_SLAVE_ATTACHED && slave->dev_num > 0) return wsa883x_init(wsa883x); diff --git a/sound/soc/codecs/wsa884x.c b/sound/soc/codecs/wsa884x.c index 2484d4b8e2d947..5ecd7962d77ae1 100644 --- a/sound/soc/codecs/wsa884x.c +++ b/sound/soc/codecs/wsa884x.c @@ -1534,7 +1534,7 @@ static void wsa884x_init(struct wsa884x_priv *wsa884x) wsa884x_set_gain_parameters(wsa884x); - wsa884x->hw_init = false; + wsa884x->hw_init = true; } static int wsa884x_update_status(struct sdw_slave *slave, @@ -2109,7 +2109,6 @@ static int wsa884x_probe(struct sdw_slave *pdev, /* Start in cache-only until device is enumerated */ regcache_cache_only(wsa884x->regmap, true); - wsa884x->hw_init = true; if (IS_REACHABLE(CONFIG_HWMON)) { struct device *hwmon; diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 72bfc91e21b9b4..2fa14fbdfe1a83 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -917,8 +917,14 @@ static int fsl_sai_startup(struct snd_pcm_substream *substream, tx ? sai->dma_params_tx.maxburst : sai->dma_params_rx.maxburst); - ret = snd_pcm_hw_constraint_list(substream->runtime, 0, - SNDRV_PCM_HW_PARAM_RATE, &sai->constraint_rates); + if (sai->is_consumer_mode[tx]) + ret = snd_pcm_hw_constraint_list(substream->runtime, 0, + SNDRV_PCM_HW_PARAM_RATE, + &fsl_sai_rate_constraints); + else + ret = snd_pcm_hw_constraint_list(substream->runtime, 0, + SNDRV_PCM_HW_PARAM_RATE, + &sai->constraint_rates); return ret; } @@ -1075,6 +1081,7 @@ static const struct reg_default fsl_sai_reg_defaults_ofs0[] = { {FSL_SAI_TDR6, 0}, {FSL_SAI_TDR7, 0}, {FSL_SAI_TMR, 0}, + {FSL_SAI_TTCTL, 0}, {FSL_SAI_RCR1(0), 0}, {FSL_SAI_RCR2(0), 0}, {FSL_SAI_RCR3(0), 0}, @@ -1098,12 +1105,14 @@ static const struct reg_default fsl_sai_reg_defaults_ofs8[] = { {FSL_SAI_TDR6, 0}, {FSL_SAI_TDR7, 0}, {FSL_SAI_TMR, 0}, + {FSL_SAI_TTCTL, 0}, {FSL_SAI_RCR1(8), 0}, {FSL_SAI_RCR2(8), 0}, {FSL_SAI_RCR3(8), 0}, {FSL_SAI_RCR4(8), 0}, {FSL_SAI_RCR5(8), 0}, {FSL_SAI_RMR, 0}, + {FSL_SAI_RTCTL, 0}, {FSL_SAI_MCTL, 0}, {FSL_SAI_MDIV, 0}, }; diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c index 5d804860f7d8c8..58db4906a01d50 100644 --- a/sound/soc/fsl/fsl_xcvr.c +++ b/sound/soc/fsl/fsl_xcvr.c @@ -1421,7 +1421,7 @@ static irqreturn_t irq0_isr(int irq, void *devid) bitrev32(val); } /* clear CS control register */ - memset_io(reg_ctrl, 0, sizeof(val)); + writel_relaxed(0, reg_ctrl); } } else { regmap_read(xcvr->regmap, FSL_XCVR_RX_CS_DATA_0, diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c index 28699d7b75ca04..05b4e971a36618 100644 --- a/sound/soc/fsl/imx-card.c +++ b/sound/soc/fsl/imx-card.c @@ -346,7 +346,6 @@ static int imx_aif_hw_params(struct snd_pcm_substream *substream, SND_SOC_DAIFMT_PDM; } else { slots = 2; - slot_width = params_physical_width(params); fmt = (rtd->dai_link->dai_fmt & ~SND_SOC_DAIFMT_FORMAT_MASK) | SND_SOC_DAIFMT_I2S; } diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 355f7ec8943c24..bdc02e85b089fe 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -1179,9 +1179,9 @@ void graph_util_parse_link_direction(struct device_node *np, bool is_playback_only = of_property_read_bool(np, "playback-only"); bool is_capture_only = of_property_read_bool(np, "capture-only"); - if (playback_only) + if (np && playback_only) *playback_only = is_playback_only; - if (capture_only) + if (np && capture_only) *capture_only = is_capture_only; } EXPORT_SYMBOL_GPL(graph_util_parse_link_direction); diff --git a/sound/soc/intel/boards/sof_es8336.c b/sound/soc/intel/boards/sof_es8336.c index 10b189ea88dba8..cf50de5c2edd8d 100644 --- a/sound/soc/intel/boards/sof_es8336.c +++ b/sound/soc/intel/boards/sof_es8336.c @@ -120,7 +120,7 @@ static void pcm_pop_work_events(struct work_struct *work) gpiod_set_value_cansleep(priv->gpio_speakers, priv->speaker_en); if (quirk & SOF_ES8336_HEADPHONE_GPIO) - gpiod_set_value_cansleep(priv->gpio_headphone, priv->speaker_en); + gpiod_set_value_cansleep(priv->gpio_headphone, !priv->speaker_en); } @@ -332,6 +332,15 @@ static int sof_es8336_quirk_cb(const struct dmi_system_id *id) * if the topology file is modified as well. */ static const struct dmi_system_id sof_es8336_quirk_table[] = { + { + .callback = sof_es8336_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HUAWEI"), + DMI_MATCH(DMI_PRODUCT_NAME, "BOD-WXX9"), + }, + .driver_data = (void *)(SOF_ES8336_HEADPHONE_GPIO | + SOF_ES8336_ENABLE_DMIC) + }, { .callback = sof_es8336_quirk_cb, .matches = { diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index c013e31d098e71..6c95b1f8fc1a59 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -750,6 +750,14 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { .driver_data = (void *)(SOC_SDW_CODEC_SPKR), }, /* Pantherlake devices*/ + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0DD6") + }, + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS), + }, { .callback = sof_sdw_quirk_cb, .matches = { @@ -794,6 +802,7 @@ static const struct snd_pci_quirk sof_sdw_ssid_quirk_table[] = { SND_PCI_QUIRK(0x17aa, 0x2347, "Lenovo P16", SOC_SDW_CODEC_MIC), SND_PCI_QUIRK(0x17aa, 0x2348, "Lenovo P16", SOC_SDW_CODEC_MIC), SND_PCI_QUIRK(0x17aa, 0x2349, "Lenovo P1", SOC_SDW_CODEC_MIC), + SND_PCI_QUIRK(0x17aa, 0x3821, "Lenovo 0x3821", SOC_SDW_SIDECAR_AMPS), {} }; diff --git a/sound/soc/intel/catpt/pcm.c b/sound/soc/intel/catpt/pcm.c index bf734c69c4e095..eb03cecdee281c 100644 --- a/sound/soc/intel/catpt/pcm.c +++ b/sound/soc/intel/catpt/pcm.c @@ -417,8 +417,10 @@ static int catpt_dai_hw_params(struct snd_pcm_substream *substream, return CATPT_IPC_ERROR(ret); ret = catpt_dai_apply_usettings(dai, stream); - if (ret) + if (ret) { + catpt_ipc_free_stream(cdev, stream->info.stream_hw_id); return ret; + } stream->allocated = true; return 0; diff --git a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c index 4853f4f31786f8..55505625b36095 100644 --- a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c @@ -418,7 +418,7 @@ static const struct snd_soc_acpi_adr_device rt1320_2_group2_adr[] = { .adr = 0x000230025D132001ull, .num_endpoints = 1, .endpoints = &spk_r_endpoint, - .name_prefix = "rt1320-1" + .name_prefix = "rt1320-2" } }; diff --git a/sound/soc/mediatek/mt8188/mt8188-mt6359.c b/sound/soc/mediatek/mt8188/mt8188-mt6359.c index c6e7461e8f764c..7f4b9eabf41129 100644 --- a/sound/soc/mediatek/mt8188/mt8188-mt6359.c +++ b/sound/soc/mediatek/mt8188/mt8188-mt6359.c @@ -1277,7 +1277,7 @@ static struct snd_soc_dai_link mt8188_mt6359_dai_links[] = { }, }; -static void mt8188_fixup_controls(struct snd_soc_card *card) +static int mt8188_fixup_controls(struct snd_soc_card *card) { struct mtk_soc_card_data *soc_card_data = snd_soc_card_get_drvdata(card); struct mtk_platform_card_data *card_data = soc_card_data->card_data; @@ -1299,6 +1299,8 @@ static void mt8188_fixup_controls(struct snd_soc_card *card) else dev_warn(card->dev, "Cannot find ctl : Headphone Switch\n"); } + + return 0; } static struct snd_soc_card mt8188_mt6359_soc_card = { diff --git a/sound/soc/qcom/qdsp6/q6adm.c b/sound/soc/qcom/qdsp6/q6adm.c index 1530e98df16564..75a029a696ac92 100644 --- a/sound/soc/qcom/qdsp6/q6adm.c +++ b/sound/soc/qcom/qdsp6/q6adm.c @@ -109,11 +109,75 @@ static struct q6copp *q6adm_find_copp(struct q6adm *adm, int port_idx, } +static int q6adm_apr_send_copp_pkt(struct q6adm *adm, struct q6copp *copp, + struct apr_pkt *pkt, uint32_t rsp_opcode) +{ + struct device *dev = adm->dev; + uint32_t opcode = pkt->hdr.opcode; + int ret; + + mutex_lock(&adm->lock); + copp->result.opcode = 0; + copp->result.status = 0; + ret = apr_send_pkt(adm->apr, pkt); + if (ret < 0) { + dev_err(dev, "Failed to send APR packet\n"); + ret = -EINVAL; + goto err; + } + + /* Wait for the callback with copp id */ + if (rsp_opcode) + ret = wait_event_timeout(copp->wait, + (copp->result.opcode == opcode) || + (copp->result.opcode == rsp_opcode), + msecs_to_jiffies(TIMEOUT_MS)); + else + ret = wait_event_timeout(copp->wait, + (copp->result.opcode == opcode), + msecs_to_jiffies(TIMEOUT_MS)); + + if (!ret) { + dev_err(dev, "ADM copp cmd timedout\n"); + ret = -ETIMEDOUT; + } else if (copp->result.status > 0) { + dev_err(dev, "DSP returned error[%d]\n", + copp->result.status); + ret = -EINVAL; + } + +err: + mutex_unlock(&adm->lock); + return ret; +} + +static int q6adm_device_close(struct q6adm *adm, struct q6copp *copp, + int port_id, int copp_idx) +{ + struct apr_pkt close; + + close.hdr.hdr_field = APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD, + APR_HDR_LEN(APR_HDR_SIZE), + APR_PKT_VER); + close.hdr.pkt_size = sizeof(close); + close.hdr.src_port = port_id; + close.hdr.dest_port = copp->id; + close.hdr.token = port_id << 16 | copp_idx; + close.hdr.opcode = ADM_CMD_DEVICE_CLOSE_V5; + + return q6adm_apr_send_copp_pkt(adm, copp, &close, 0); +} + static void q6adm_free_copp(struct kref *ref) { struct q6copp *c = container_of(ref, struct q6copp, refcount); struct q6adm *adm = c->adm; unsigned long flags; + int ret; + + ret = q6adm_device_close(adm, c, c->afe_port, c->copp_idx); + if (ret < 0) + dev_err(adm->dev, "Failed to close copp %d\n", ret); spin_lock_irqsave(&adm->copps_list_lock, flags); clear_bit(c->copp_idx, &adm->copp_bitmap[c->afe_port]); @@ -155,13 +219,13 @@ static int q6adm_callback(struct apr_device *adev, struct apr_resp_pkt *data) switch (result->opcode) { case ADM_CMD_DEVICE_OPEN_V5: case ADM_CMD_DEVICE_CLOSE_V5: - copp = q6adm_find_copp(adm, port_idx, copp_idx); - if (!copp) - return 0; - - copp->result = *result; - wake_up(&copp->wait); - kref_put(&copp->refcount, q6adm_free_copp); + list_for_each_entry(copp, &adm->copps_list, node) { + if ((port_idx == copp->afe_port) && (copp_idx == copp->copp_idx)) { + copp->result = *result; + wake_up(&copp->wait); + break; + } + } break; case ADM_CMD_MATRIX_MAP_ROUTINGS_V5: adm->result = *result; @@ -234,65 +298,6 @@ static struct q6copp *q6adm_alloc_copp(struct q6adm *adm, int port_idx) return c; } -static int q6adm_apr_send_copp_pkt(struct q6adm *adm, struct q6copp *copp, - struct apr_pkt *pkt, uint32_t rsp_opcode) -{ - struct device *dev = adm->dev; - uint32_t opcode = pkt->hdr.opcode; - int ret; - - mutex_lock(&adm->lock); - copp->result.opcode = 0; - copp->result.status = 0; - ret = apr_send_pkt(adm->apr, pkt); - if (ret < 0) { - dev_err(dev, "Failed to send APR packet\n"); - ret = -EINVAL; - goto err; - } - - /* Wait for the callback with copp id */ - if (rsp_opcode) - ret = wait_event_timeout(copp->wait, - (copp->result.opcode == opcode) || - (copp->result.opcode == rsp_opcode), - msecs_to_jiffies(TIMEOUT_MS)); - else - ret = wait_event_timeout(copp->wait, - (copp->result.opcode == opcode), - msecs_to_jiffies(TIMEOUT_MS)); - - if (!ret) { - dev_err(dev, "ADM copp cmd timedout\n"); - ret = -ETIMEDOUT; - } else if (copp->result.status > 0) { - dev_err(dev, "DSP returned error[%d]\n", - copp->result.status); - ret = -EINVAL; - } - -err: - mutex_unlock(&adm->lock); - return ret; -} - -static int q6adm_device_close(struct q6adm *adm, struct q6copp *copp, - int port_id, int copp_idx) -{ - struct apr_pkt close; - - close.hdr.hdr_field = APR_HDR_FIELD(APR_MSG_TYPE_SEQ_CMD, - APR_HDR_LEN(APR_HDR_SIZE), - APR_PKT_VER); - close.hdr.pkt_size = sizeof(close); - close.hdr.src_port = port_id; - close.hdr.dest_port = copp->id; - close.hdr.token = port_id << 16 | copp_idx; - close.hdr.opcode = ADM_CMD_DEVICE_CLOSE_V5; - - return q6adm_apr_send_copp_pkt(adm, copp, &close, 0); -} - static struct q6copp *q6adm_find_matching_copp(struct q6adm *adm, int port_id, int topology, int mode, int rate, @@ -567,15 +572,6 @@ EXPORT_SYMBOL_GPL(q6adm_matrix_map); */ int q6adm_close(struct device *dev, struct q6copp *copp) { - struct q6adm *adm = dev_get_drvdata(dev->parent); - int ret = 0; - - ret = q6adm_device_close(adm, copp, copp->afe_port, copp->copp_idx); - if (ret < 0) { - dev_err(adm->dev, "Failed to close copp %d\n", ret); - return ret; - } - kref_put(&copp->refcount, q6adm_free_copp); return 0; diff --git a/sound/soc/qcom/qdsp6/q6apm-dai.c b/sound/soc/qcom/qdsp6/q6apm-dai.c index 4ecaff45c51860..786ab3222515c3 100644 --- a/sound/soc/qcom/qdsp6/q6apm-dai.c +++ b/sound/soc/qcom/qdsp6/q6apm-dai.c @@ -86,6 +86,7 @@ static const struct snd_pcm_hardware q6apm_dai_hardware_capture = { .info = (SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_BLOCK_TRANSFER | SNDRV_PCM_INFO_MMAP_VALID | SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_PAUSE | SNDRV_PCM_INFO_RESUME | + SNDRV_PCM_INFO_NO_REWINDS | SNDRV_PCM_INFO_SYNC_APPLPTR | SNDRV_PCM_INFO_BATCH), .formats = (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE), .rates = SNDRV_PCM_RATE_8000_48000, @@ -105,6 +106,7 @@ static const struct snd_pcm_hardware q6apm_dai_hardware_playback = { .info = (SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_BLOCK_TRANSFER | SNDRV_PCM_INFO_MMAP_VALID | SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_PAUSE | SNDRV_PCM_INFO_RESUME | + SNDRV_PCM_INFO_NO_REWINDS | SNDRV_PCM_INFO_SYNC_APPLPTR | SNDRV_PCM_INFO_BATCH), .formats = (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE), .rates = SNDRV_PCM_RATE_8000_192000, diff --git a/sound/soc/qcom/qdsp6/q6asm-dai.c b/sound/soc/qcom/qdsp6/q6asm-dai.c index b616ce316d2f13..0eae8c6e42b8aa 100644 --- a/sound/soc/qcom/qdsp6/q6asm-dai.c +++ b/sound/soc/qcom/qdsp6/q6asm-dai.c @@ -233,13 +233,14 @@ static int q6asm_dai_prepare(struct snd_soc_component *component, prtd->pcm_count = snd_pcm_lib_period_bytes(substream); prtd->pcm_irq_pos = 0; /* rate and channels are sent to audio driver */ - if (prtd->state) { + if (prtd->state == Q6ASM_STREAM_RUNNING) { /* clear the previous setup if any */ q6asm_cmd(prtd->audio_client, prtd->stream_id, CMD_CLOSE); q6asm_unmap_memory_regions(substream->stream, prtd->audio_client); q6routing_stream_close(soc_prtd->dai_link->id, substream->stream); + prtd->state = Q6ASM_STREAM_STOPPED; } ret = q6asm_map_memory_regions(substream->stream, prtd->audio_client, @@ -403,13 +404,13 @@ static int q6asm_dai_open(struct snd_soc_component *component, } ret = snd_pcm_hw_constraint_step(runtime, 0, - SNDRV_PCM_HW_PARAM_PERIOD_BYTES, 32); + SNDRV_PCM_HW_PARAM_PERIOD_SIZE, 480); if (ret < 0) { dev_err(dev, "constraint for period bytes step ret = %d\n", ret); } ret = snd_pcm_hw_constraint_step(runtime, 0, - SNDRV_PCM_HW_PARAM_BUFFER_BYTES, 32); + SNDRV_PCM_HW_PARAM_BUFFER_SIZE, 480); if (ret < 0) { dev_err(dev, "constraint for buffer bytes step ret = %d\n", ret); diff --git a/sound/soc/qcom/sc7280.c b/sound/soc/qcom/sc7280.c index af412bd0c89ff5..c444dae563c75d 100644 --- a/sound/soc/qcom/sc7280.c +++ b/sound/soc/qcom/sc7280.c @@ -317,7 +317,7 @@ static void sc7280_snd_shutdown(struct snd_pcm_substream *substream) struct snd_soc_card *card = rtd->card; struct sc7280_snd_data *data = snd_soc_card_get_drvdata(card); struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, 0); - struct sdw_stream_runtime *sruntime = data->sruntime[cpu_dai->id]; + struct sdw_stream_runtime *sruntime = qcom_snd_sdw_get_stream(substream); switch (cpu_dai->id) { case MI2S_PRIMARY: diff --git a/sound/soc/qcom/sc8280xp.c b/sound/soc/qcom/sc8280xp.c index 187f37ffe32837..ed8b04c6022e9f 100644 --- a/sound/soc/qcom/sc8280xp.c +++ b/sound/soc/qcom/sc8280xp.c @@ -73,7 +73,7 @@ static void sc8280xp_snd_shutdown(struct snd_pcm_substream *substream) struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, 0); struct sc8280xp_snd_data *pdata = snd_soc_card_get_drvdata(rtd->card); - struct sdw_stream_runtime *sruntime = pdata->sruntime[cpu_dai->id]; + struct sdw_stream_runtime *sruntime = qcom_snd_sdw_get_stream(substream); pdata->sruntime[cpu_dai->id] = NULL; sdw_release_stream(sruntime); diff --git a/sound/soc/qcom/sdw.c b/sound/soc/qcom/sdw.c index 7d7981d4295b48..7b2cae92c81296 100644 --- a/sound/soc/qcom/sdw.c +++ b/sound/soc/qcom/sdw.c @@ -7,6 +7,37 @@ #include #include "sdw.h" +static bool qcom_snd_is_sdw_dai(int id) +{ + switch (id) { + case WSA_CODEC_DMA_RX_0: + case WSA_CODEC_DMA_TX_0: + case WSA_CODEC_DMA_RX_1: + case WSA_CODEC_DMA_TX_1: + case WSA_CODEC_DMA_TX_2: + case RX_CODEC_DMA_RX_0: + case TX_CODEC_DMA_TX_0: + case RX_CODEC_DMA_RX_1: + case TX_CODEC_DMA_TX_1: + case RX_CODEC_DMA_RX_2: + case TX_CODEC_DMA_TX_2: + case RX_CODEC_DMA_RX_3: + case TX_CODEC_DMA_TX_3: + case RX_CODEC_DMA_RX_4: + case TX_CODEC_DMA_TX_4: + case RX_CODEC_DMA_RX_5: + case TX_CODEC_DMA_TX_5: + case RX_CODEC_DMA_RX_6: + case RX_CODEC_DMA_RX_7: + case SLIMBUS_0_RX...SLIMBUS_6_TX: + return true; + default: + break; + } + + return false; +} + /** * qcom_snd_sdw_startup() - Helper to start Soundwire stream for SoC audio card * @substream: The PCM substream from audio, as passed to snd_soc_ops->startup() @@ -29,6 +60,9 @@ int qcom_snd_sdw_startup(struct snd_pcm_substream *substream) u32 rx_ch_cnt = 0, tx_ch_cnt = 0; int ret, i, j; + if (!qcom_snd_is_sdw_dai(cpu_dai->id)) + return 0; + sruntime = sdw_alloc_stream(cpu_dai->name, SDW_STREAM_PCM); if (!sruntime) return -ENOMEM; @@ -89,19 +123,8 @@ int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream, if (!sruntime) return 0; - switch (cpu_dai->id) { - case WSA_CODEC_DMA_RX_0: - case WSA_CODEC_DMA_RX_1: - case RX_CODEC_DMA_RX_0: - case RX_CODEC_DMA_RX_1: - case TX_CODEC_DMA_TX_0: - case TX_CODEC_DMA_TX_1: - case TX_CODEC_DMA_TX_2: - case TX_CODEC_DMA_TX_3: - break; - default: + if (!qcom_snd_is_sdw_dai(cpu_dai->id)) return 0; - } if (*stream_prepared) return 0; @@ -129,9 +152,7 @@ int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream, } EXPORT_SYMBOL_GPL(qcom_snd_sdw_prepare); -int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params, - struct sdw_stream_runtime **psruntime) +struct sdw_stream_runtime *qcom_snd_sdw_get_stream(struct snd_pcm_substream *substream) { struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); struct snd_soc_dai *codec_dai; @@ -139,21 +160,23 @@ int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream, struct sdw_stream_runtime *sruntime; int i; - switch (cpu_dai->id) { - case WSA_CODEC_DMA_RX_0: - case RX_CODEC_DMA_RX_0: - case RX_CODEC_DMA_RX_1: - case TX_CODEC_DMA_TX_0: - case TX_CODEC_DMA_TX_1: - case TX_CODEC_DMA_TX_2: - case TX_CODEC_DMA_TX_3: - for_each_rtd_codec_dais(rtd, i, codec_dai) { - sruntime = snd_soc_dai_get_stream(codec_dai, substream->stream); - if (sruntime != ERR_PTR(-ENOTSUPP)) - *psruntime = sruntime; - } - break; + if (!qcom_snd_is_sdw_dai(cpu_dai->id)) + return NULL; + + for_each_rtd_codec_dais(rtd, i, codec_dai) { + sruntime = snd_soc_dai_get_stream(codec_dai, substream->stream); + if (sruntime != ERR_PTR(-ENOTSUPP)) + return sruntime; } + return NULL; +} +EXPORT_SYMBOL_GPL(qcom_snd_sdw_get_stream); + +int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params, + struct sdw_stream_runtime **psruntime) +{ + *psruntime = qcom_snd_sdw_get_stream(substream); return 0; @@ -166,23 +189,13 @@ int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream, struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, 0); - switch (cpu_dai->id) { - case WSA_CODEC_DMA_RX_0: - case WSA_CODEC_DMA_RX_1: - case RX_CODEC_DMA_RX_0: - case RX_CODEC_DMA_RX_1: - case TX_CODEC_DMA_TX_0: - case TX_CODEC_DMA_TX_1: - case TX_CODEC_DMA_TX_2: - case TX_CODEC_DMA_TX_3: - if (sruntime && *stream_prepared) { - sdw_disable_stream(sruntime); - sdw_deprepare_stream(sruntime); - *stream_prepared = false; - } - break; - default: - break; + if (!qcom_snd_is_sdw_dai(cpu_dai->id)) + return 0; + + if (sruntime && *stream_prepared) { + sdw_disable_stream(sruntime); + sdw_deprepare_stream(sruntime); + *stream_prepared = false; } return 0; diff --git a/sound/soc/qcom/sdw.h b/sound/soc/qcom/sdw.h index 392e3455f1b198..b8bc5beb052230 100644 --- a/sound/soc/qcom/sdw.h +++ b/sound/soc/qcom/sdw.h @@ -10,6 +10,7 @@ int qcom_snd_sdw_startup(struct snd_pcm_substream *substream); int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream, struct sdw_stream_runtime *runtime, bool *stream_prepared); +struct sdw_stream_runtime *qcom_snd_sdw_get_stream(struct snd_pcm_substream *stream); int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct sdw_stream_runtime **psruntime); diff --git a/sound/soc/qcom/sm8250.c b/sound/soc/qcom/sm8250.c index f5b75a06e5bd20..ce5b0059207f1c 100644 --- a/sound/soc/qcom/sm8250.c +++ b/sound/soc/qcom/sm8250.c @@ -117,7 +117,7 @@ static void sm8250_snd_shutdown(struct snd_pcm_substream *substream) struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, 0); struct sm8250_snd_data *data = snd_soc_card_get_drvdata(rtd->card); - struct sdw_stream_runtime *sruntime = data->sruntime[cpu_dai->id]; + struct sdw_stream_runtime *sruntime = qcom_snd_sdw_get_stream(substream); data->sruntime[cpu_dai->id] = NULL; sdw_release_stream(sruntime); diff --git a/sound/soc/qcom/x1e80100.c b/sound/soc/qcom/x1e80100.c index 444f2162889f7d..2e3599516aa2ae 100644 --- a/sound/soc/qcom/x1e80100.c +++ b/sound/soc/qcom/x1e80100.c @@ -55,7 +55,7 @@ static void x1e80100_snd_shutdown(struct snd_pcm_substream *substream) struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, 0); struct x1e80100_snd_data *data = snd_soc_card_get_drvdata(rtd->card); - struct sdw_stream_runtime *sruntime = data->sruntime[cpu_dai->id]; + struct sdw_stream_runtime *sruntime = qcom_snd_sdw_get_stream(substream); data->sruntime[cpu_dai->id] = NULL; sdw_release_stream(sruntime); diff --git a/sound/soc/renesas/rz-ssi.c b/sound/soc/renesas/rz-ssi.c index 81b883e8ac92aa..f4dc2f68deadac 100644 --- a/sound/soc/renesas/rz-ssi.c +++ b/sound/soc/renesas/rz-ssi.c @@ -13,6 +13,7 @@ #include #include #include +#include #include /* REGISTER OFFSET */ @@ -87,7 +88,6 @@ struct rz_ssi_stream { int dma_buffer_pos; /* The address for the next DMA descriptor */ int completed_dma_buf_pos; /* The address of the last completed DMA descriptor. */ int period_counter; /* for keeping track of periods transferred */ - int sample_width; int buffer_pos; /* current frame position in the buffer */ int running; /* 0=stopped, 1=running */ @@ -133,6 +133,12 @@ struct rz_ssi_priv { bool bckp_rise; /* Bit clock polarity (SSICR.BCKP) */ bool dma_rt; + struct { + bool tx_active; + bool rx_active; + bool one_stream_triggered; + } dup; + /* Full duplex communication support */ struct { unsigned int rate; @@ -211,10 +217,7 @@ static inline bool rz_ssi_is_stream_running(struct rz_ssi_stream *strm) static void rz_ssi_stream_init(struct rz_ssi_stream *strm, struct snd_pcm_substream *substream) { - struct snd_pcm_runtime *runtime = substream->runtime; - rz_ssi_set_substream(strm, substream); - strm->sample_width = samples_to_bytes(runtime, 1); strm->dma_buffer_pos = 0; strm->completed_dma_buf_pos = 0; strm->period_counter = 0; @@ -332,13 +335,12 @@ static int rz_ssi_start(struct rz_ssi_priv *ssi, struct rz_ssi_stream *strm) bool is_full_duplex; u32 ssicr, ssifcr; - is_full_duplex = rz_ssi_is_stream_running(&ssi->playback) || - rz_ssi_is_stream_running(&ssi->capture); + is_full_duplex = ssi->dup.tx_active && ssi->dup.rx_active; ssicr = rz_ssi_reg_readl(ssi, SSICR); ssifcr = rz_ssi_reg_readl(ssi, SSIFCR); if (!is_full_duplex) { ssifcr &= ~0xF; - } else { + } else if (ssi->dup.one_stream_triggered) { rz_ssi_reg_mask_setl(ssi, SSICR, SSICR_TEN | SSICR_REN, 0); rz_ssi_set_idle(ssi); ssifcr &= ~SSIFCR_FIFO_RST; @@ -374,12 +376,16 @@ static int rz_ssi_start(struct rz_ssi_priv *ssi, struct rz_ssi_stream *strm) SSISR_RUIRQ), 0); strm->running = 1; - if (is_full_duplex) - ssicr |= SSICR_TEN | SSICR_REN; - else + if (!is_full_duplex) { ssicr |= is_play ? SSICR_TEN : SSICR_REN; - - rz_ssi_reg_writel(ssi, SSICR, ssicr); + rz_ssi_reg_writel(ssi, SSICR, ssicr); + } else if (ssi->dup.one_stream_triggered) { + ssicr |= SSICR_TEN | SSICR_REN; + rz_ssi_reg_writel(ssi, SSICR, ssicr); + ssi->dup.one_stream_triggered = false; + } else { + ssi->dup.one_stream_triggered = true; + } return 0; } @@ -915,6 +921,30 @@ static int rz_ssi_dai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) return 0; } +static int rz_ssi_startup(struct snd_pcm_substream *substream, + struct snd_soc_dai *dai) +{ + struct rz_ssi_priv *ssi = snd_soc_dai_get_drvdata(dai); + + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + ssi->dup.tx_active = true; + else + ssi->dup.rx_active = true; + + return 0; +} + +static void rz_ssi_shutdown(struct snd_pcm_substream *substream, + struct snd_soc_dai *dai) +{ + struct rz_ssi_priv *ssi = snd_soc_dai_get_drvdata(dai); + + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + ssi->dup.tx_active = false; + else + ssi->dup.rx_active = false; +} + static bool rz_ssi_is_valid_hw_params(struct rz_ssi_priv *ssi, unsigned int rate, unsigned int channels, unsigned int sample_width, @@ -945,9 +975,9 @@ static int rz_ssi_dai_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct rz_ssi_priv *ssi = snd_soc_dai_get_drvdata(dai); - struct rz_ssi_stream *strm = rz_ssi_stream_get(ssi, substream); unsigned int sample_bits = hw_param_interval(params, SNDRV_PCM_HW_PARAM_SAMPLE_BITS)->min; + unsigned int sample_width = params_width(params); unsigned int channels = params_channels(params); unsigned int rate = params_rate(params); int ret; @@ -966,16 +996,14 @@ static int rz_ssi_dai_hw_params(struct snd_pcm_substream *substream, if (rz_ssi_is_stream_running(&ssi->playback) || rz_ssi_is_stream_running(&ssi->capture)) { - if (rz_ssi_is_valid_hw_params(ssi, rate, channels, - strm->sample_width, sample_bits)) + if (rz_ssi_is_valid_hw_params(ssi, rate, channels, sample_width, sample_bits)) return 0; dev_err(ssi->dev, "Full duplex needs same HW params\n"); return -EINVAL; } - rz_ssi_cache_hw_params(ssi, rate, channels, strm->sample_width, - sample_bits); + rz_ssi_cache_hw_params(ssi, rate, channels, sample_width, sample_bits); ret = rz_ssi_swreset(ssi); if (ret) @@ -985,6 +1013,8 @@ static int rz_ssi_dai_hw_params(struct snd_pcm_substream *substream, } static const struct snd_soc_dai_ops rz_ssi_dai_ops = { + .startup = rz_ssi_startup, + .shutdown = rz_ssi_shutdown, .trigger = rz_ssi_dai_trigger, .set_fmt = rz_ssi_dai_set_fmt, .hw_params = rz_ssi_dai_hw_params, diff --git a/sound/soc/rockchip/rockchip_i2s_tdm.c b/sound/soc/rockchip/rockchip_i2s_tdm.c index d9a1fab7f40310..e4697ee0addc87 100644 --- a/sound/soc/rockchip/rockchip_i2s_tdm.c +++ b/sound/soc/rockchip/rockchip_i2s_tdm.c @@ -22,6 +22,7 @@ #define DRV_NAME "rockchip-i2s-tdm" +#define DEFAULT_MCLK_FS 256 #define CH_GRP_MAX 4 /* The max channel 8 / 2 */ #define MULTIPLEX_CH_MAX 10 @@ -665,6 +666,15 @@ static int rockchip_i2s_tdm_hw_params(struct snd_pcm_substream *substream, mclk_rate = i2s_tdm->mclk_rx_freq; } + /* + * When the dai/component driver doesn't need to set mclk-fs for a specific + * clock, it can skip the call to set_sysclk() for that clock. + * In that case, simply use the clock rate from the params and multiply it by + * the default mclk-fs value. + */ + if (!mclk_rate) + mclk_rate = DEFAULT_MCLK_FS * params_rate(params); + err = clk_set_rate(mclk, mclk_rate); if (err) return err; diff --git a/sound/soc/rockchip/rockchip_pdm.c b/sound/soc/rockchip/rockchip_pdm.c index c1ee470ec6079d..c69cdd6f24994c 100644 --- a/sound/soc/rockchip/rockchip_pdm.c +++ b/sound/soc/rockchip/rockchip_pdm.c @@ -580,7 +580,7 @@ static int rockchip_pdm_probe(struct platform_device *pdev) if (!pdm) return -ENOMEM; - pdm->version = (enum rk_pdm_version)device_get_match_data(&pdev->dev); + pdm->version = (unsigned long)device_get_match_data(&pdev->dev); if (pdm->version == RK_PDM_RK3308) { pdm->reset = devm_reset_control_get(&pdev->dev, "pdm-m"); if (IS_ERR(pdm->reset)) diff --git a/sound/soc/sdca/sdca_asoc.c b/sound/soc/sdca/sdca_asoc.c index c493ec530cc5c8..197a592ec2f166 100644 --- a/sound/soc/sdca/sdca_asoc.c +++ b/sound/soc/sdca/sdca_asoc.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -795,7 +796,6 @@ static int control_limit_kctl(struct device *dev, struct sdca_control_range *range; int min, max, step; unsigned int *tlv; - int shift; if (control->type != SDCA_CTL_DATATYPE_Q7P8DB) return 0; @@ -814,37 +814,22 @@ static int control_limit_kctl(struct device *dev, min = sign_extend32(min, control->nbits - 1); max = sign_extend32(max, control->nbits - 1); - /* - * FIXME: Only support power of 2 step sizes as this can be supported - * by a simple shift. - */ - if (hweight32(step) != 1) { - dev_err(dev, "%s: %s: currently unsupported step size\n", - entity->label, control->label); - return -EINVAL; - } - - /* - * The SDCA volumes are in steps of 1/256th of a dB, a step down of - * 64 (shift of 6) gives 1/4dB. 1/4dB is the smallest unit that is also - * representable in the ALSA TLVs which are in 1/100ths of a dB. - */ - shift = max(ffs(step) - 1, 6); - tlv = devm_kcalloc(dev, 4, sizeof(*tlv), GFP_KERNEL); if (!tlv) return -ENOMEM; - tlv[0] = SNDRV_CTL_TLVT_DB_SCALE; + tlv[0] = SNDRV_CTL_TLVT_DB_MINMAX; tlv[1] = 2 * sizeof(*tlv); tlv[2] = (min * 100) >> 8; - tlv[3] = ((1 << shift) * 100) >> 8; + tlv[3] = (max * 100) >> 8; - mc->min = min >> shift; - mc->max = max >> shift; - mc->shift = shift; - mc->rshift = shift; - mc->sign_bit = 15 - shift; + step = (step * 100) >> 8; + + mc->min = ((int)tlv[2] / step); + mc->max = ((int)tlv[3] / step); + mc->shift = step; + mc->sign_bit = 15; + mc->sdca_q78 = 1; kctl->tlv.p = tlv; kctl->access |= SNDRV_CTL_ELEM_ACCESS_TLV_READ; @@ -852,6 +837,48 @@ static int control_limit_kctl(struct device *dev, return 0; } +static int volatile_get_volsw(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); + struct device *dev = component->dev; + int ret; + + ret = pm_runtime_resume_and_get(dev); + if (ret < 0) { + dev_err(dev, "failed to resume reading %s: %d\n", + kcontrol->id.name, ret); + return ret; + } + + ret = snd_soc_get_volsw(kcontrol, ucontrol); + + pm_runtime_put(dev); + + return ret; +} + +static int volatile_put_volsw(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); + struct device *dev = component->dev; + int ret; + + ret = pm_runtime_resume_and_get(dev); + if (ret < 0) { + dev_err(dev, "failed to resume writing %s: %d\n", + kcontrol->id.name, ret); + return ret; + } + + ret = snd_soc_put_volsw(kcontrol, ucontrol); + + pm_runtime_put(dev); + + return ret; +} + static int populate_control(struct device *dev, struct sdca_function_data *function, struct sdca_entity *entity, @@ -906,8 +933,13 @@ static int populate_control(struct device *dev, (*kctl)->private_value = (unsigned long)mc; (*kctl)->iface = SNDRV_CTL_ELEM_IFACE_MIXER; (*kctl)->info = snd_soc_info_volsw; - (*kctl)->get = snd_soc_get_volsw; - (*kctl)->put = snd_soc_put_volsw; + if (control->is_volatile) { + (*kctl)->get = volatile_get_volsw; + (*kctl)->put = volatile_put_volsw; + } else { + (*kctl)->get = snd_soc_get_volsw; + (*kctl)->put = snd_soc_put_volsw; + } if (readonly_control(control)) (*kctl)->access = SNDRV_CTL_ELEM_ACCESS_READ; @@ -1535,7 +1567,7 @@ static int set_usage(struct device *dev, struct regmap *regmap, unsigned int rate = sdca_range(range, SDCA_USAGE_SAMPLE_RATE, i); unsigned int width = sdca_range(range, SDCA_USAGE_SAMPLE_WIDTH, i); - if ((!rate || rate == target_rate) && width == target_width) { + if ((!rate || rate == target_rate) && (!width || width == target_width)) { unsigned int usage = sdca_range(range, SDCA_USAGE_NUMBER, i); unsigned int reg = SDW_SDCA_CTL(function->desc->adr, entity->id, sel, 0); diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c index 0ccb6775f4de3d..4417278e39bb1a 100644 --- a/sound/soc/sdca/sdca_functions.c +++ b/sound/soc/sdca/sdca_functions.c @@ -779,6 +779,62 @@ find_sdca_control_datatype(const struct sdca_entity *entity, } } +static bool find_sdca_control_volatile(const struct sdca_entity *entity, + const struct sdca_control *control) +{ + switch (control->mode) { + case SDCA_ACCESS_MODE_DC: + return false; + case SDCA_ACCESS_MODE_RO: + case SDCA_ACCESS_MODE_RW1S: + case SDCA_ACCESS_MODE_RW1C: + return true; + default: + break; + } + + switch (SDCA_CTL_TYPE(entity->type, control->sel)) { + case SDCA_CTL_TYPE_S(XU, FDL_CURRENTOWNER): + case SDCA_CTL_TYPE_S(XU, FDL_MESSAGEOFFSET): + case SDCA_CTL_TYPE_S(XU, FDL_MESSAGELENGTH): + case SDCA_CTL_TYPE_S(XU, FDL_STATUS): + case SDCA_CTL_TYPE_S(XU, FDL_HOST_REQUEST): + case SDCA_CTL_TYPE_S(SPE, AUTHTX_CURRENTOWNER): + case SDCA_CTL_TYPE_S(SPE, AUTHTX_MESSAGEOFFSET): + case SDCA_CTL_TYPE_S(SPE, AUTHTX_MESSAGELENGTH): + case SDCA_CTL_TYPE_S(SPE, AUTHRX_CURRENTOWNER): + case SDCA_CTL_TYPE_S(SPE, AUTHRX_MESSAGEOFFSET): + case SDCA_CTL_TYPE_S(SPE, AUTHRX_MESSAGELENGTH): + case SDCA_CTL_TYPE_S(MFPU, AE_CURRENTOWNER): + case SDCA_CTL_TYPE_S(MFPU, AE_MESSAGEOFFSET): + case SDCA_CTL_TYPE_S(MFPU, AE_MESSAGELENGTH): + case SDCA_CTL_TYPE_S(SMPU, HIST_CURRENTOWNER): + case SDCA_CTL_TYPE_S(SMPU, HIST_MESSAGEOFFSET): + case SDCA_CTL_TYPE_S(SMPU, HIST_MESSAGELENGTH): + case SDCA_CTL_TYPE_S(SMPU, DTODTX_CURRENTOWNER): + case SDCA_CTL_TYPE_S(SMPU, DTODTX_MESSAGEOFFSET): + case SDCA_CTL_TYPE_S(SMPU, DTODTX_MESSAGELENGTH): + case SDCA_CTL_TYPE_S(SMPU, DTODRX_CURRENTOWNER): + case SDCA_CTL_TYPE_S(SMPU, DTODRX_MESSAGEOFFSET): + case SDCA_CTL_TYPE_S(SMPU, DTODRX_MESSAGELENGTH): + case SDCA_CTL_TYPE_S(SAPU, DTODTX_CURRENTOWNER): + case SDCA_CTL_TYPE_S(SAPU, DTODTX_MESSAGEOFFSET): + case SDCA_CTL_TYPE_S(SAPU, DTODTX_MESSAGELENGTH): + case SDCA_CTL_TYPE_S(SAPU, DTODRX_CURRENTOWNER): + case SDCA_CTL_TYPE_S(SAPU, DTODRX_MESSAGEOFFSET): + case SDCA_CTL_TYPE_S(SAPU, DTODRX_MESSAGELENGTH): + case SDCA_CTL_TYPE_S(HIDE, HIDTX_CURRENTOWNER): + case SDCA_CTL_TYPE_S(HIDE, HIDTX_MESSAGEOFFSET): + case SDCA_CTL_TYPE_S(HIDE, HIDTX_MESSAGELENGTH): + case SDCA_CTL_TYPE_S(HIDE, HIDRX_CURRENTOWNER): + case SDCA_CTL_TYPE_S(HIDE, HIDRX_MESSAGEOFFSET): + case SDCA_CTL_TYPE_S(HIDE, HIDRX_MESSAGELENGTH): + return true; + default: + return false; + } +} + static int find_sdca_control_range(struct device *dev, struct fwnode_handle *control_node, struct sdca_control_range *range) @@ -854,10 +910,6 @@ static int find_sdca_control_value(struct device *dev, struct sdca_entity *entit return 0; } -/* - * TODO: Add support for -cn- properties, allowing different channels to have - * different defaults etc. - */ static int find_sdca_entity_control(struct device *dev, struct sdca_entity *entity, struct fwnode_handle *control_node, struct sdca_control *control) @@ -931,6 +983,8 @@ static int find_sdca_entity_control(struct device *dev, struct sdca_entity *enti break; } + control->is_volatile = find_sdca_control_volatile(entity, control); + ret = find_sdca_control_range(dev, control_node, &control->range); if (ret) { dev_err(dev, "%s: control %#x: range missing: %d\n", @@ -1263,7 +1317,7 @@ find_sdca_entity_hide(struct device *dev, struct fwnode_handle *function_node, unsigned char *report_desc = NULL; ret = fwnode_property_read_u32(entity_node, - "mipi-sdca-RxUMP-ownership-transition-maxdelay", &delay); + "mipi-sdca-RxUMP-ownership-transition-max-delay", &delay); if (!ret) hide->max_delay = delay; diff --git a/sound/soc/sdca/sdca_regmap.c b/sound/soc/sdca/sdca_regmap.c index 72f893e00ff506..8fa138fca00ffb 100644 --- a/sound/soc/sdca/sdca_regmap.c +++ b/sound/soc/sdca/sdca_regmap.c @@ -147,14 +147,7 @@ bool sdca_regmap_volatile(struct sdca_function_data *function, unsigned int reg) if (!control) return false; - switch (control->mode) { - case SDCA_ACCESS_MODE_RO: - case SDCA_ACCESS_MODE_RW1S: - case SDCA_ACCESS_MODE_RW1C: - return true; - default: - return false; - } + return control->is_volatile; } EXPORT_SYMBOL_NS(sdca_regmap_volatile, "SND_SOC_SDCA"); diff --git a/sound/soc/sdw_utils/soc_sdw_cs42l43.c b/sound/soc/sdw_utils/soc_sdw_cs42l43.c index b415d45d520d0c..3e8e2e3bdf7c5c 100644 --- a/sound/soc/sdw_utils/soc_sdw_cs42l43.c +++ b/sound/soc/sdw_utils/soc_sdw_cs42l43.c @@ -44,7 +44,7 @@ static const struct snd_soc_dapm_route cs42l43_dmic_map[] = { static struct snd_soc_jack_pin soc_jack_pins[] = { { .pin = "Headphone", - .mask = SND_JACK_HEADPHONE, + .mask = SND_JACK_HEADPHONE | SND_JACK_LINEOUT, }, { .pin = "Headset Mic", diff --git a/sound/soc/soc-card.c b/sound/soc/soc-card.c index 235427d6906173..bc02c7b864e295 100644 --- a/sound/soc/soc-card.c +++ b/sound/soc/soc-card.c @@ -184,10 +184,16 @@ int snd_soc_card_late_probe(struct snd_soc_card *card) return 0; } -void snd_soc_card_fixup_controls(struct snd_soc_card *card) +int snd_soc_card_fixup_controls(struct snd_soc_card *card) { - if (card->fixup_controls) - card->fixup_controls(card); + if (card->fixup_controls) { + int ret = card->fixup_controls(card); + + if (ret < 0) + return soc_card_ret(card, ret); + } + + return 0; } int snd_soc_card_remove(struct snd_soc_card *card) diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 9dd84d73046be7..3f6db1f1a50820 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2284,7 +2284,10 @@ static int snd_soc_bind_card(struct snd_soc_card *card) goto probe_end; snd_soc_dapm_new_widgets(card); - snd_soc_card_fixup_controls(card); + + ret = snd_soc_card_fixup_controls(card); + if (ret < 0) + goto probe_end; ret = snd_card_register(card->snd_card); if (ret < 0) { diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 51fb09d56c5a17..a93071cce13fcd 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -2512,6 +2512,141 @@ static const struct file_operations dapm_bias_fops = { .llseek = default_llseek, }; +static ssize_t dapm_graph_read_file(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct snd_soc_card *card = file->private_data; + struct snd_soc_dapm_context *dapm; + struct snd_soc_dapm_path *p; + struct snd_soc_dapm_widget *w; + struct snd_soc_pcm_runtime *rtd; + struct snd_soc_dapm_widget *wdone[16]; + struct snd_soc_dai *dai; + int i, num_wdone = 0, cluster = 0; + char *buf; + ssize_t bufsize; + ssize_t ret = 0; + + bufsize = 1024 * card->num_dapm_widgets; + buf = kmalloc(bufsize, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + mutex_lock(&card->dapm_mutex); + +#define bufprintf(...) \ + ret += scnprintf(buf + ret, bufsize - ret, __VA_ARGS__) + + bufprintf("digraph dapm {\n"); + + /* + * Print the user-visible devices of the card. + */ + bufprintf("subgraph cluster_%d {\n", cluster++); + bufprintf("label=\"Devices\";style=filled;fillcolor=gray;\n"); + for_each_card_rtds(card, rtd) { + if (rtd->dai_link->no_pcm) + continue; + + bufprintf("w%pK [label=\"%d: %s\"];\n", rtd, + rtd->pcm->device, rtd->dai_link->name); + } + bufprintf("};\n"); + + /* + * Print the playback/capture widgets of DAIs just next to + * the user-visible devices. Keep the list of already printed + * widgets in 'wdone', so they will be skipped later. + */ + for_each_card_rtds(card, rtd) { + for_each_rtd_cpu_dais(rtd, i, dai) { + if (dai->stream[SNDRV_PCM_STREAM_PLAYBACK].widget) { + w = dai->stream[SNDRV_PCM_STREAM_PLAYBACK].widget; + bufprintf("w%pK [label=\"%s\"];\n", w, w->name); + if (!rtd->dai_link->no_pcm) + bufprintf("w%pK -> w%pK;\n", rtd, w); + if (num_wdone < ARRAY_SIZE(wdone)) { + wdone[num_wdone] = w; + num_wdone++; + } + } + + if (dai->stream[SNDRV_PCM_STREAM_CAPTURE].widget) { + w = dai->stream[SNDRV_PCM_STREAM_CAPTURE].widget; + bufprintf("w%pK [label=\"%s\"];\n", w, w->name); + if (!rtd->dai_link->no_pcm) + bufprintf("w%pK -> w%pK;\n", w, rtd); + if (num_wdone < ARRAY_SIZE(wdone)) { + wdone[num_wdone] = w; + num_wdone++; + } + } + } + } + + for_each_card_dapms(card, dapm) { + const char *prefix = soc_dapm_prefix(dapm); + + if (dapm != &card->dapm) { + bufprintf("subgraph cluster_%d {\n", cluster++); + if (prefix) + bufprintf("label=\"%s\";\n", prefix); + else if (dapm->component) + bufprintf("label=\"%s\";\n", + dapm->component->name); + } + + for_each_card_widgets(dapm->card, w) { + const char *name = w->name; + bool skip = false; + + if (w->dapm != dapm) + continue; + + if (list_empty(&w->edges[0]) && list_empty(&w->edges[1])) + continue; + + for (i = 0; i < num_wdone; i++) + if (wdone[i] == w) + skip = true; + if (skip) + continue; + + if (prefix && strlen(name) > strlen(prefix) + 1) + name += strlen(prefix) + 1; + + bufprintf("w%pK [label=\"%s\"];\n", w, name); + } + + if (dapm != &card->dapm) + bufprintf("}\n"); + } + + list_for_each_entry(p, &card->paths, list) { + if (p->name) + bufprintf("w%pK -> w%pK [label=\"%s\"];\n", + p->source, p->sink, p->name); + else + bufprintf("w%pK -> w%pK;\n", p->source, p->sink); + } + + bufprintf("}\n"); +#undef bufprintf + + mutex_unlock(&card->dapm_mutex); + + ret = simple_read_from_buffer(user_buf, count, ppos, buf, ret); + + kfree(buf); + return ret; +} + +static const struct file_operations dapm_graph_fops = { + .open = simple_open, + .read = dapm_graph_read_file, + .llseek = default_llseek, +}; + void snd_soc_dapm_debugfs_init(struct snd_soc_dapm_context *dapm, struct dentry *parent) { @@ -2522,6 +2657,10 @@ void snd_soc_dapm_debugfs_init(struct snd_soc_dapm_context *dapm, debugfs_create_file("bias_level", 0444, dapm->debugfs_dapm, dapm, &dapm_bias_fops); + + if (dapm == &dapm->card->dapm) + debugfs_create_file("graph.dot", 0444, dapm->debugfs_dapm, + dapm->card, &dapm_graph_fops); } static void dapm_debugfs_add_widget(struct snd_soc_dapm_widget *w) diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index d2b6fb8e0b6c69..0a3ff993a62639 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -110,21 +110,58 @@ int snd_soc_put_enum_double(struct snd_kcontrol *kcontrol, } EXPORT_SYMBOL_GPL(snd_soc_put_enum_double); +static int sdca_soc_q78_reg_to_ctl(struct soc_mixer_control *mc, unsigned int reg_val, + unsigned int mask, unsigned int shift, int max, + bool sx) +{ + int val = reg_val; + + if (WARN_ON(!mc->shift)) + return -EINVAL; + + val = sign_extend32(val, mc->sign_bit); + val = (((val * 100) >> 8) / (int)mc->shift); + val -= mc->min; + + return val & mask; +} + +static unsigned int sdca_soc_q78_ctl_to_reg(struct soc_mixer_control *mc, int val, + unsigned int mask, unsigned int shift, int max) +{ + unsigned int ret_val; + int reg_val; + + if (WARN_ON(!mc->shift)) + return -EINVAL; + + reg_val = val + mc->min; + ret_val = (int)((reg_val * mc->shift) << 8) / 100; + + return ret_val & mask; +} + static int soc_mixer_reg_to_ctl(struct soc_mixer_control *mc, unsigned int reg_val, - unsigned int mask, unsigned int shift, int max) + unsigned int mask, unsigned int shift, int max, + bool sx) { int val = (reg_val >> shift) & mask; if (mc->sign_bit) val = sign_extend32(val, mc->sign_bit); - val = clamp(val, mc->min, mc->max); - val -= mc->min; + if (sx) { + val -= mc->min; // SX controls intentionally can overflow here + val = min_t(unsigned int, val & mask, max); + } else { + val = clamp(val, mc->min, mc->max); + val -= mc->min; + } if (mc->invert) val = max - val; - return val & mask; + return val; } static unsigned int soc_mixer_ctl_to_reg(struct soc_mixer_control *mc, int val, @@ -197,19 +234,27 @@ static int soc_put_volsw(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol, struct soc_mixer_control *mc, int mask, int max) { + unsigned int (*ctl_to_reg)(struct soc_mixer_control *, int, unsigned int, unsigned int, int); struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); unsigned int val1, val_mask; unsigned int val2 = 0; bool double_r = false; int ret; + if (mc->sdca_q78) { + ctl_to_reg = sdca_soc_q78_ctl_to_reg; + val_mask = mask; + } else { + ctl_to_reg = soc_mixer_ctl_to_reg; + val_mask = mask << mc->shift; + } + ret = soc_mixer_valid_ctl(mc, ucontrol->value.integer.value[0], max); if (ret) return ret; - val1 = soc_mixer_ctl_to_reg(mc, ucontrol->value.integer.value[0], + val1 = ctl_to_reg(mc, ucontrol->value.integer.value[0], mask, mc->shift, max); - val_mask = mask << mc->shift; if (snd_soc_volsw_is_stereo(mc)) { ret = soc_mixer_valid_ctl(mc, ucontrol->value.integer.value[1], max); @@ -217,14 +262,10 @@ static int soc_put_volsw(struct snd_kcontrol *kcontrol, return ret; if (mc->reg == mc->rreg) { - val1 |= soc_mixer_ctl_to_reg(mc, - ucontrol->value.integer.value[1], - mask, mc->rshift, max); + val1 |= ctl_to_reg(mc, ucontrol->value.integer.value[1], mask, mc->rshift, max); val_mask |= mask << mc->rshift; } else { - val2 = soc_mixer_ctl_to_reg(mc, - ucontrol->value.integer.value[1], - mask, mc->shift, max); + val2 = ctl_to_reg(mc, ucontrol->value.integer.value[1], mask, mc->shift, max); double_r = true; } } @@ -246,23 +287,30 @@ static int soc_put_volsw(struct snd_kcontrol *kcontrol, static int soc_get_volsw(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol, - struct soc_mixer_control *mc, int mask, int max) + struct soc_mixer_control *mc, int mask, int max, bool sx) { + int (*reg_to_ctl)(struct soc_mixer_control *, unsigned int, unsigned int, + unsigned int, int, bool); struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); unsigned int reg_val; int val; + if (mc->sdca_q78) + reg_to_ctl = sdca_soc_q78_reg_to_ctl; + else + reg_to_ctl = soc_mixer_reg_to_ctl; + reg_val = snd_soc_component_read(component, mc->reg); - val = soc_mixer_reg_to_ctl(mc, reg_val, mask, mc->shift, max); + val = reg_to_ctl(mc, reg_val, mask, mc->shift, max, sx); ucontrol->value.integer.value[0] = val; if (snd_soc_volsw_is_stereo(mc)) { if (mc->reg == mc->rreg) { - val = soc_mixer_reg_to_ctl(mc, reg_val, mask, mc->rshift, max); + val = reg_to_ctl(mc, reg_val, mask, mc->rshift, max, sx); } else { reg_val = snd_soc_component_read(component, mc->rreg); - val = soc_mixer_reg_to_ctl(mc, reg_val, mask, mc->shift, max); + val = reg_to_ctl(mc, reg_val, mask, mc->shift, max, sx); } ucontrol->value.integer.value[1] = val; @@ -331,7 +379,7 @@ int snd_soc_get_volsw(struct snd_kcontrol *kcontrol, (struct soc_mixer_control *)kcontrol->private_value; unsigned int mask = soc_mixer_mask(mc); - return soc_get_volsw(kcontrol, ucontrol, mc, mask, mc->max - mc->min); + return soc_get_volsw(kcontrol, ucontrol, mc, mask, mc->max - mc->min, false); } EXPORT_SYMBOL_GPL(snd_soc_get_volsw); @@ -373,7 +421,7 @@ int snd_soc_get_volsw_sx(struct snd_kcontrol *kcontrol, (struct soc_mixer_control *)kcontrol->private_value; unsigned int mask = soc_mixer_sx_mask(mc); - return soc_get_volsw(kcontrol, ucontrol, mc, mask, mc->max); + return soc_get_volsw(kcontrol, ucontrol, mc, mask, mc->max, true); } EXPORT_SYMBOL_GPL(snd_soc_get_volsw_sx); @@ -397,6 +445,30 @@ int snd_soc_put_volsw_sx(struct snd_kcontrol *kcontrol, } EXPORT_SYMBOL_GPL(snd_soc_put_volsw_sx); +bool snd_soc_control_matches(struct snd_kcontrol *kctl, + const char *pattern) +{ + const char *name = kctl->id.name; + + if (pattern[0] == '*') { + int namelen; + int patternlen; + + pattern++; + if (pattern[0] == ' ') + pattern++; + + namelen = strlen(name); + patternlen = strlen(pattern); + + if (namelen > patternlen) + name += namelen - patternlen; + } + + return !strcmp(name, pattern); +} +EXPORT_SYMBOL_GPL(snd_soc_control_matches); + static int snd_soc_clip_to_platform_max(struct snd_kcontrol *kctl) { struct soc_mixer_control *mc = (struct soc_mixer_control *)kctl->private_value; @@ -428,39 +500,165 @@ static int snd_soc_clip_to_platform_max(struct snd_kcontrol *kctl) return ret; } +static int soc_limit_volume(struct snd_kcontrol *kctl, int max) +{ + struct soc_mixer_control *mc = (struct soc_mixer_control *)kctl->private_value; + + if (max <= 0 || max > mc->max - mc->min) + return -EINVAL; + mc->platform_max = max; + return snd_soc_clip_to_platform_max(kctl); +} + /** - * snd_soc_limit_volume - Set new limit to an existing volume control. + * snd_soc_limit_volume - Set new limit to existing volume controls * * @card: where to look for the control - * @name: Name of the control + * @name: name pattern * @max: new maximum limit + * + * Finds controls matching the given name (which can be either a name + * verbatim, or a pattern starting with the wildcard '*') and sets + * a platform volume limit on them. * - * Return 0 for success, else error. + * Return number of matching controls on success, else error. At least + * one control needs to match the pattern. */ int snd_soc_limit_volume(struct snd_soc_card *card, const char *name, int max) { struct snd_kcontrol *kctl; - int ret = -EINVAL; + int hits = 0; + int ret; - /* Sanity check for name and max */ - if (unlikely(!name || max <= 0)) + /* Sanity check for name */ + if (unlikely(!name)) return -EINVAL; - kctl = snd_soc_card_get_kcontrol(card, name); - if (kctl) { - struct soc_mixer_control *mc = - (struct soc_mixer_control *)kctl->private_value; + list_for_each_entry(kctl, &card->snd_card->controls, list) { + if (!snd_soc_control_matches(kctl, name)) + continue; - if (max <= mc->max - mc->min) { - mc->platform_max = max; - ret = snd_soc_clip_to_platform_max(kctl); - } + ret = soc_limit_volume(kctl, max); + if (ret < 0) + return ret; + hits++; } - return ret; + if (!hits) + return -EINVAL; + + return hits; } EXPORT_SYMBOL_GPL(snd_soc_limit_volume); +/** + * snd_soc_deactivate_kctl - Activate/deactive controls matching a pattern + * + * @card: where to look for the controls + * @name: name pattern + * @active: non-zero to activate, zero to deactivate + * + * Return number of matching controls on success, else error. + * No controls need to match. + */ +int snd_soc_deactivate_kctl(struct snd_soc_card *card, + const char *name, int active) +{ + struct snd_kcontrol *kctl; + int hits = 0; + int ret; + + /* Sanity check for name */ + if (unlikely(!name)) + return -EINVAL; + + list_for_each_entry(kctl, &card->snd_card->controls, list) { + if (!snd_soc_control_matches(kctl, name)) + continue; + + ret = snd_ctl_activate_id(card->snd_card, &kctl->id, active); + if (ret < 0) + return ret; + hits++; + } + + if (!hits) + return -EINVAL; + + return hits; +} +EXPORT_SYMBOL_GPL(snd_soc_deactivate_kctl); + +static int soc_set_enum_kctl(struct snd_kcontrol *kctl, const char *strval) +{ + struct snd_ctl_elem_value value; + struct snd_ctl_elem_info info; + int sel, i, ret; + + ret = kctl->info(kctl, &info); + if (ret < 0) + return ret; + + if (info.type != SNDRV_CTL_ELEM_TYPE_ENUMERATED) + return -EINVAL; + + for (sel = 0; sel < info.value.enumerated.items; sel++) { + info.value.enumerated.item = sel; + ret = kctl->info(kctl, &info); + if (ret < 0) + return ret; + + if (!strcmp(strval, info.value.enumerated.name)) + break; + } + + if (sel == info.value.enumerated.items) + return -EINVAL; + + for (i = 0; i < info.count; i++) + value.value.enumerated.item[i] = sel; + + return kctl->put(kctl, &value); +} + +/** + * snd_soc_set_enum_kctl - Set enumerated controls matching a pattern + * + * @card: where to look for the controls + * @name: name pattern + * @value: string value to set the controls to + * + * Return number of matching and set controls on success, else error. + * No controls need to match. + */ +int snd_soc_set_enum_kctl(struct snd_soc_card *card, + const char *name, const char *value) +{ + struct snd_kcontrol *kctl; + int hits = 0; + int ret; + + /* Sanity check for name */ + if (unlikely(!name)) + return -EINVAL; + + list_for_each_entry(kctl, &card->snd_card->controls, list) { + if (!snd_soc_control_matches(kctl, name)) + continue; + + ret = soc_set_enum_kctl(kctl, value); + if (ret < 0) + return ret; + hits++; + } + + if (!hits) + return -EINVAL; + + return hits; +} +EXPORT_SYMBOL_GPL(snd_soc_set_enum_kctl); + int snd_soc_bytes_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c index 221e9d4052b8f0..32b628e2fe29b5 100644 --- a/sound/soc/sof/ipc4-topology.c +++ b/sound/soc/sof/ipc4-topology.c @@ -1752,11 +1752,9 @@ snd_sof_get_nhlt_endpoint_data(struct snd_sof_dev *sdev, struct snd_sof_dai *dai channel_count = params_channels(params); sample_rate = params_rate(params); bit_depth = params_width(params); - /* - * Look for 32-bit blob first instead of 16-bit if copier - * supports multiple formats - */ - if (bit_depth == 16 && !single_bitdepth) { + + /* Prefer 32-bit blob if copier supports multiple formats */ + if (bit_depth <= 16 && !single_bitdepth) { dev_dbg(sdev->dev, "Looking for 32-bit blob first for DMIC\n"); format_change = true; bit_depth = 32; @@ -1799,10 +1797,18 @@ snd_sof_get_nhlt_endpoint_data(struct snd_sof_dev *sdev, struct snd_sof_dai *dai if (format_change) { /* * The 32-bit blob was not found in NHLT table, try to - * look for one based on the params + * look for 16-bit for DMIC or based on the params for + * SSP */ - bit_depth = params_width(params); - format_change = false; + if (linktype == SOF_DAI_INTEL_DMIC) { + bit_depth = 16; + if (params_width(params) == 16) + format_change = false; + } else { + bit_depth = params_width(params); + format_change = false; + } + get_new_blob = true; } else if (linktype == SOF_DAI_INTEL_DMIC && !single_bitdepth) { /* @@ -1837,7 +1843,7 @@ snd_sof_get_nhlt_endpoint_data(struct snd_sof_dev *sdev, struct snd_sof_dai *dai *len = cfg->size >> 2; *dst = (u32 *)cfg->caps; - if (format_change) { + if (format_change || params_format(params) == SNDRV_PCM_FORMAT_FLOAT_LE) { /* * Update the params to reflect that different blob was loaded * instead of the requested bit depth (16 -> 32 or 32 -> 16). diff --git a/sound/soc/stm/stm32_sai.c b/sound/soc/stm/stm32_sai.c index fa821e3fb427e3..00cf24ceca2d4a 100644 --- a/sound/soc/stm/stm32_sai.c +++ b/sound/soc/stm/stm32_sai.c @@ -138,30 +138,24 @@ static int stm32_sai_set_sync(struct stm32_sai_data *sai_client, if (!pdev) { dev_err(&sai_client->pdev->dev, "Device not found for node %pOFn\n", np_provider); - of_node_put(np_provider); return -ENODEV; } sai_provider = platform_get_drvdata(pdev); + put_device(&pdev->dev); if (!sai_provider) { dev_err(&sai_client->pdev->dev, "SAI sync provider data not found\n"); - ret = -EINVAL; - goto error; + return -EINVAL; } /* Configure sync client */ ret = stm32_sai_sync_conf_client(sai_client, synci); if (ret < 0) - goto error; + return ret; /* Configure sync provider */ - ret = stm32_sai_sync_conf_provider(sai_provider, synco); - -error: - put_device(&pdev->dev); - of_node_put(np_provider); - return ret; + return stm32_sai_sync_conf_provider(sai_provider, synco); } static int stm32_sai_get_parent_clk(struct stm32_sai_data *sai) diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c index 0ae1eae2a59e2f..5ae4d2577f28b7 100644 --- a/sound/soc/stm/stm32_sai_sub.c +++ b/sound/soc/stm/stm32_sai_sub.c @@ -1586,7 +1586,8 @@ static int stm32_sai_sub_parse_of(struct platform_device *pdev, dev_err(&pdev->dev, "External synchro not supported\n"); of_node_put(args.np); - return -EINVAL; + ret = -EINVAL; + goto err_put_sync_provider; } sai->sync = SAI_SYNC_EXTERNAL; @@ -1595,7 +1596,8 @@ static int stm32_sai_sub_parse_of(struct platform_device *pdev, (sai->synci > (SAI_GCR_SYNCIN_MAX + 1))) { dev_err(&pdev->dev, "Wrong SAI index\n"); of_node_put(args.np); - return -EINVAL; + ret = -EINVAL; + goto err_put_sync_provider; } if (of_property_match_string(args.np, "compatible", @@ -1609,7 +1611,8 @@ static int stm32_sai_sub_parse_of(struct platform_device *pdev, if (!sai->synco) { dev_err(&pdev->dev, "Unknown SAI sub-block\n"); of_node_put(args.np); - return -EINVAL; + ret = -EINVAL; + goto err_put_sync_provider; } } @@ -1619,13 +1622,15 @@ static int stm32_sai_sub_parse_of(struct platform_device *pdev, of_node_put(args.np); sai->sai_ck = devm_clk_get(&pdev->dev, "sai_ck"); - if (IS_ERR(sai->sai_ck)) - return dev_err_probe(&pdev->dev, PTR_ERR(sai->sai_ck), - "Missing kernel clock sai_ck\n"); + if (IS_ERR(sai->sai_ck)) { + ret = dev_err_probe(&pdev->dev, PTR_ERR(sai->sai_ck), + "Missing kernel clock sai_ck\n"); + goto err_put_sync_provider; + } ret = clk_prepare(sai->pdata->pclk); if (ret < 0) - return ret; + goto err_put_sync_provider; if (STM_SAI_IS_F4(sai->pdata)) return 0; @@ -1634,14 +1639,23 @@ static int stm32_sai_sub_parse_of(struct platform_device *pdev, if (of_property_present(np, "#clock-cells")) { ret = stm32_sai_add_mclk_provider(sai); if (ret < 0) - return ret; + goto err_unprepare_pclk; } else { sai->sai_mclk = devm_clk_get_optional(&pdev->dev, "MCLK"); - if (IS_ERR(sai->sai_mclk)) - return PTR_ERR(sai->sai_mclk); + if (IS_ERR(sai->sai_mclk)) { + ret = PTR_ERR(sai->sai_mclk); + goto err_unprepare_pclk; + } } return 0; + +err_unprepare_pclk: + clk_unprepare(sai->pdata->pclk); +err_put_sync_provider: + of_node_put(sai->np_sync_provider); + + return ret; } static int stm32_sai_sub_probe(struct platform_device *pdev) @@ -1688,26 +1702,34 @@ static int stm32_sai_sub_probe(struct platform_device *pdev) IRQF_SHARED, dev_name(&pdev->dev), sai); if (ret) { dev_err(&pdev->dev, "IRQ request returned %d\n", ret); - return ret; + goto err_unprepare_pclk; } if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) conf = &stm32_sai_pcm_config_spdif; ret = snd_dmaengine_pcm_register(&pdev->dev, conf, 0); - if (ret) - return dev_err_probe(&pdev->dev, ret, "Could not register pcm dma\n"); + if (ret) { + ret = dev_err_probe(&pdev->dev, ret, "Could not register pcm dma\n"); + goto err_unprepare_pclk; + } ret = snd_soc_register_component(&pdev->dev, &stm32_component, &sai->cpu_dai_drv, 1); if (ret) { snd_dmaengine_pcm_unregister(&pdev->dev); - return ret; + goto err_unprepare_pclk; } pm_runtime_enable(&pdev->dev); return 0; + +err_unprepare_pclk: + clk_unprepare(sai->pdata->pclk); + of_node_put(sai->np_sync_provider); + + return ret; } static void stm32_sai_sub_remove(struct platform_device *pdev) @@ -1718,6 +1740,7 @@ static void stm32_sai_sub_remove(struct platform_device *pdev) snd_dmaengine_pcm_unregister(&pdev->dev); snd_soc_unregister_component(&pdev->dev); pm_runtime_disable(&pdev->dev); + of_node_put(sai->np_sync_provider); } static int stm32_sai_sub_suspend(struct device *dev) diff --git a/sound/soc/tegra/tegra210_ahub.c b/sound/soc/tegra/tegra210_ahub.c index 21aeaeba0b1079..01d60a74ad1c3b 100644 --- a/sound/soc/tegra/tegra210_ahub.c +++ b/sound/soc/tegra/tegra210_ahub.c @@ -2049,6 +2049,61 @@ static const struct snd_soc_component_driver tegra264_ahub_component = { .num_dapm_routes = ARRAY_SIZE(tegra264_ahub_routes), }; +static bool tegra210_ahub_wr_reg(struct device *dev, unsigned int reg) +{ + int part; + + if (reg % TEGRA210_XBAR_RX_STRIDE) + return false; + + for (part = 0; part < TEGRA210_XBAR_UPDATE_MAX_REG; part++) { + switch (reg & ~(part * TEGRA210_XBAR_PART1_RX)) { + case TEGRA210_AXBAR_PART_0_ADMAIF_RX1_0 ... TEGRA210_AXBAR_PART_0_ADMAIF_RX10_0: + case TEGRA210_AXBAR_PART_0_I2S1_RX1_0 ... TEGRA210_AXBAR_PART_0_I2S5_RX1_0: + case TEGRA210_AXBAR_PART_0_SFC1_RX1_0 ... TEGRA210_AXBAR_PART_0_SFC4_RX1_0: + case TEGRA210_AXBAR_PART_0_MIXER1_RX1_0 ... TEGRA210_AXBAR_PART_0_MIXER1_RX10_0: + case TEGRA210_AXBAR_PART_0_SPDIF1_RX1_0 ... TEGRA210_AXBAR_PART_0_SPDIF1_RX2_0: + case TEGRA210_AXBAR_PART_0_AFC1_RX1_0 ... TEGRA210_AXBAR_PART_0_AFC6_RX1_0: + case TEGRA210_AXBAR_PART_0_OPE1_RX1_0 ... TEGRA210_AXBAR_PART_0_OPE2_RX1_0: + case TEGRA210_AXBAR_PART_0_SPKPROT1_RX1_0: + case TEGRA210_AXBAR_PART_0_MVC1_RX1_0 ... TEGRA210_AXBAR_PART_0_MVC2_RX1_0: + case TEGRA210_AXBAR_PART_0_AMX1_RX1_0 ... TEGRA210_AXBAR_PART_0_ADX2_RX1_0: + return true; + default: + break; + } + } + + return false; +} + +static bool tegra186_ahub_wr_reg(struct device *dev, unsigned int reg) +{ + int part; + + if (reg % TEGRA210_XBAR_RX_STRIDE) + return false; + + for (part = 0; part < TEGRA186_XBAR_UPDATE_MAX_REG; part++) { + switch (reg & ~(part * TEGRA210_XBAR_PART1_RX)) { + case TEGRA210_AXBAR_PART_0_ADMAIF_RX1_0 ... TEGRA186_AXBAR_PART_0_I2S6_RX1_0: + case TEGRA210_AXBAR_PART_0_SFC1_RX1_0 ... TEGRA210_AXBAR_PART_0_SFC4_RX1_0: + case TEGRA210_AXBAR_PART_0_MIXER1_RX1_0 ... TEGRA210_AXBAR_PART_0_MIXER1_RX10_0: + case TEGRA186_AXBAR_PART_0_DSPK1_RX1_0 ... TEGRA186_AXBAR_PART_0_DSPK2_RX1_0: + case TEGRA210_AXBAR_PART_0_AFC1_RX1_0 ... TEGRA210_AXBAR_PART_0_AFC6_RX1_0: + case TEGRA210_AXBAR_PART_0_OPE1_RX1_0: + case TEGRA186_AXBAR_PART_0_MVC1_RX1_0 ... TEGRA186_AXBAR_PART_0_MVC2_RX1_0: + case TEGRA186_AXBAR_PART_0_AMX1_RX1_0 ... TEGRA186_AXBAR_PART_0_AMX3_RX4_0: + case TEGRA210_AXBAR_PART_0_ADX1_RX1_0 ... TEGRA186_AXBAR_PART_0_ASRC1_RX7_0: + return true; + default: + break; + } + } + + return false; +} + static bool tegra264_ahub_wr_reg(struct device *dev, unsigned int reg) { int part; @@ -2076,6 +2131,7 @@ static const struct regmap_config tegra210_ahub_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, + .writeable_reg = tegra210_ahub_wr_reg, .max_register = TEGRA210_MAX_REGISTER_ADDR, .cache_type = REGCACHE_FLAT, }; @@ -2084,6 +2140,7 @@ static const struct regmap_config tegra186_ahub_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, + .writeable_reg = tegra186_ahub_wr_reg, .max_register = TEGRA186_MAX_REGISTER_ADDR, .cache_type = REGCACHE_FLAT, }; diff --git a/sound/soc/tegra/tegra210_ahub.h b/sound/soc/tegra/tegra210_ahub.h index f355b2cfd19b22..acbe640dd3b572 100644 --- a/sound/soc/tegra/tegra210_ahub.h +++ b/sound/soc/tegra/tegra210_ahub.h @@ -68,6 +68,36 @@ #define TEGRA210_MAX_REGISTER_ADDR (TEGRA210_XBAR_PART2_RX + \ (TEGRA210_XBAR_RX_STRIDE * (TEGRA210_XBAR_AUDIO_RX_COUNT - 1))) +/* AXBAR register offsets */ +#define TEGRA186_AXBAR_PART_0_AMX1_RX1_0 0x120 +#define TEGRA186_AXBAR_PART_0_AMX3_RX4_0 0x14c +#define TEGRA186_AXBAR_PART_0_ASRC1_RX7_0 0x1a8 +#define TEGRA186_AXBAR_PART_0_DSPK1_RX1_0 0xc0 +#define TEGRA186_AXBAR_PART_0_DSPK2_RX1_0 0xc4 +#define TEGRA186_AXBAR_PART_0_I2S6_RX1_0 0x54 +#define TEGRA186_AXBAR_PART_0_MVC1_RX1_0 0x110 +#define TEGRA186_AXBAR_PART_0_MVC2_RX1_0 0x114 +#define TEGRA210_AXBAR_PART_0_ADMAIF_RX10_0 0x24 +#define TEGRA210_AXBAR_PART_0_ADMAIF_RX1_0 0x0 +#define TEGRA210_AXBAR_PART_0_ADX1_RX1_0 0x160 +#define TEGRA210_AXBAR_PART_0_ADX2_RX1_0 0x164 +#define TEGRA210_AXBAR_PART_0_AFC1_RX1_0 0xd0 +#define TEGRA210_AXBAR_PART_0_AFC6_RX1_0 0xe4 +#define TEGRA210_AXBAR_PART_0_AMX1_RX1_0 0x140 +#define TEGRA210_AXBAR_PART_0_I2S1_RX1_0 0x40 +#define TEGRA210_AXBAR_PART_0_I2S5_RX1_0 0x50 +#define TEGRA210_AXBAR_PART_0_MIXER1_RX10_0 0xa4 +#define TEGRA210_AXBAR_PART_0_MIXER1_RX1_0 0x80 +#define TEGRA210_AXBAR_PART_0_MVC1_RX1_0 0x120 +#define TEGRA210_AXBAR_PART_0_MVC2_RX1_0 0x124 +#define TEGRA210_AXBAR_PART_0_OPE1_RX1_0 0x100 +#define TEGRA210_AXBAR_PART_0_OPE2_RX1_0 0x104 +#define TEGRA210_AXBAR_PART_0_SFC1_RX1_0 0x60 +#define TEGRA210_AXBAR_PART_0_SFC4_RX1_0 0x6c +#define TEGRA210_AXBAR_PART_0_SPDIF1_RX1_0 0xc0 +#define TEGRA210_AXBAR_PART_0_SPDIF1_RX2_0 0xc4 +#define TEGRA210_AXBAR_PART_0_SPKPROT1_RX1_0 0x110 + #define MUX_REG(id) (TEGRA210_XBAR_RX_STRIDE * (id)) #define MUX_VALUE(npart, nbit) (1 + (nbit) + (npart) * 32) diff --git a/sound/soc/ti/davinci-evm.c b/sound/soc/ti/davinci-evm.c index 2a2f5bc95576ea..a55a369ce71c27 100644 --- a/sound/soc/ti/davinci-evm.c +++ b/sound/soc/ti/davinci-evm.c @@ -193,27 +193,32 @@ static int davinci_evm_probe(struct platform_device *pdev) return -EINVAL; dai->cpus->of_node = of_parse_phandle(np, "ti,mcasp-controller", 0); - if (!dai->cpus->of_node) - return -EINVAL; + if (!dai->cpus->of_node) { + ret = -EINVAL; + goto err_put; + } dai->platforms->of_node = dai->cpus->of_node; evm_soc_card.dev = &pdev->dev; ret = snd_soc_of_parse_card_name(&evm_soc_card, "ti,model"); if (ret) - return ret; + goto err_put; mclk = devm_clk_get(&pdev->dev, "mclk"); if (PTR_ERR(mclk) == -EPROBE_DEFER) { - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto err_put; } else if (IS_ERR(mclk)) { dev_dbg(&pdev->dev, "mclk not found.\n"); mclk = NULL; } drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL); - if (!drvdata) - return -ENOMEM; + if (!drvdata) { + ret = -ENOMEM; + goto err_put; + } drvdata->mclk = mclk; @@ -223,7 +228,8 @@ static int davinci_evm_probe(struct platform_device *pdev) if (!drvdata->mclk) { dev_err(&pdev->dev, "No clock or clock rate defined.\n"); - return -EINVAL; + ret = -EINVAL; + goto err_put; } drvdata->sysclk = clk_get_rate(drvdata->mclk); } else if (drvdata->mclk) { @@ -239,8 +245,25 @@ static int davinci_evm_probe(struct platform_device *pdev) snd_soc_card_set_drvdata(&evm_soc_card, drvdata); ret = devm_snd_soc_register_card(&pdev->dev, &evm_soc_card); - if (ret) + if (ret) { dev_err(&pdev->dev, "snd_soc_register_card failed (%d)\n", ret); + goto err_put; + } + + return ret; + +err_put: + dai->platforms->of_node = NULL; + + if (dai->cpus->of_node) { + of_node_put(dai->cpus->of_node); + dai->cpus->of_node = NULL; + } + + if (dai->codecs->of_node) { + of_node_put(dai->codecs->of_node); + dai->codecs->of_node = NULL; + } return ret; } diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 3af71d42b9b9aa..bfe15b1cb66c5c 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1813,11 +1813,10 @@ static void __build_feature_ctl(struct usb_mixer_interface *mixer, range = (cval->max - cval->min) / cval->res; /* - * Are there devices with volume range more than 255? I use a bit more - * to be sure. 384 is a resolution magic number found on Logitech - * devices. It will definitively catch all buggy Logitech devices. + * There are definitely devices with a range of ~20,000, so let's be + * conservative and allow for a bit more. */ - if (range > 384) { + if (range > 65535) { usb_audio_warn(mixer->chip, "Warning! Unlikely big volume range (=%u), cval->res is probably wrong.", range); @@ -2946,10 +2945,23 @@ static int parse_audio_unit(struct mixer_build *state, int unitid) static void snd_usb_mixer_free(struct usb_mixer_interface *mixer) { + struct usb_mixer_elem_list *list, *next; + int id; + /* kill pending URBs */ snd_usb_mixer_disconnect(mixer); - kfree(mixer->id_elems); + /* Unregister controls first, snd_ctl_remove() frees the element */ + if (mixer->id_elems) { + for (id = 0; id < MAX_ID_ELEMS; id++) { + for (list = mixer->id_elems[id]; list; list = next) { + next = list->next_id_elem; + if (list->kctl) + snd_ctl_remove(mixer->chip->card, list->kctl); + } + } + kfree(mixer->id_elems); + } if (mixer->urb) { kfree(mixer->urb->transfer_buffer); usb_free_urb(mixer->urb); diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 828af3095b86ee..4873b5e7480161 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -311,13 +311,8 @@ static int snd_audigy2nx_led_update(struct usb_mixer_interface *mixer, if (pm.err < 0) return pm.err; - if (chip->usb_id == USB_ID(0x041e, 0x3042)) - err = snd_usb_ctl_msg(chip->dev, - usb_sndctrlpipe(chip->dev, 0), 0x24, - USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_OTHER, - !value, 0, NULL, 0); - /* USB X-Fi S51 Pro */ - if (chip->usb_id == USB_ID(0x041e, 0x30df)) + if (chip->usb_id == USB_ID(0x041e, 0x3042) || /* USB X-Fi S51 */ + chip->usb_id == USB_ID(0x041e, 0x30df)) /* USB X-Fi S51 Pro */ err = snd_usb_ctl_msg(chip->dev, usb_sndctrlpipe(chip->dev, 0), 0x24, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_OTHER, diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index f2446bf3982c66..bef8c9e544dd3d 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -2533,13 +2533,13 @@ static int scarlett2_usb_get_config( err = scarlett2_usb_get(mixer, config_item->offset, buf, size); if (err < 0) return err; - if (size == 2) { + if (config_item->size == 16) { u16 *buf_16 = buf; for (i = 0; i < count; i++, buf_16++) *buf_16 = le16_to_cpu(*(__le16 *)buf_16); - } else if (size == 4) { - u32 *buf_32 = buf; + } else if (config_item->size == 32) { + u32 *buf_32 = (u32 *)buf; for (i = 0; i < count; i++, buf_32++) *buf_32 = le32_to_cpu(*(__le32 *)buf_32); diff --git a/sound/usb/mixer_us16x08.c b/sound/usb/mixer_us16x08.c index 1c5712c31f5e20..f9df40730effd1 100644 --- a/sound/usb/mixer_us16x08.c +++ b/sound/usb/mixer_us16x08.c @@ -655,17 +655,25 @@ static void get_meter_levels_from_urb(int s, u8 *meter_urb) { int val = MUC2(meter_urb, s) + (MUC3(meter_urb, s) << 8); + int ch = MUB2(meter_urb, s) - 1; + + if (ch < 0) + return; if (MUA0(meter_urb, s) == 0x61 && MUA1(meter_urb, s) == 0x02 && MUA2(meter_urb, s) == 0x04 && MUB0(meter_urb, s) == 0x62) { - if (MUC0(meter_urb, s) == 0x72) - store->meter_level[MUB2(meter_urb, s) - 1] = val; - if (MUC0(meter_urb, s) == 0xb2) - store->comp_level[MUB2(meter_urb, s) - 1] = val; + if (ch < SND_US16X08_MAX_CHANNELS) { + if (MUC0(meter_urb, s) == 0x72) + store->meter_level[ch] = val; + if (MUC0(meter_urb, s) == 0xb2) + store->comp_level[ch] = val; + } } if (MUA0(meter_urb, s) == 0x61 && MUA1(meter_urb, s) == 0x02 && - MUA2(meter_urb, s) == 0x02 && MUB0(meter_urb, s) == 0x62) - store->master_level[MUB2(meter_urb, s) - 1] = val; + MUA2(meter_urb, s) == 0x02 && MUB0(meter_urb, s) == 0x62) { + if (ch < ARRAY_SIZE(store->master_level)) + store->master_level[ch] = val; + } } /* Function to retrieve current meter values from the device. diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 54d01dfd820fa7..682b6c1fe76bac 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -1553,7 +1553,8 @@ static int prepare_playback_urb(struct snd_usb_substream *subs, for (i = 0; i < ctx->packets; i++) { counts = snd_usb_endpoint_next_packet_size(ep, ctx, i, avail); - if (counts < 0) + if (counts < 0 || + (frames + counts) * stride > ctx->buffer_size) break; /* set up descriptor */ urb->iso_frame_desc[i].offset = frames * stride; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 61bd61ffb1b230..8a646891ebb44f 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2230,6 +2230,12 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { DEVICE_FLG(0x0644, 0x806b, /* TEAC UD-701 */ QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY | QUIRK_FLAG_IFACE_DELAY), + DEVICE_FLG(0x0644, 0x807d, /* TEAC UD-507 */ + QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY | + QUIRK_FLAG_IFACE_DELAY), + DEVICE_FLG(0x0644, 0x806c, /* Esoteric XD */ + QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY | + QUIRK_FLAG_IFACE_DELAY), DEVICE_FLG(0x06f8, 0xb000, /* Hercules DJ Console (Windows Edition) */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x06f8, 0xd002, /* Hercules DJ Console (Macintosh Edition) */ @@ -2384,10 +2390,14 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x2d99, 0x0026, /* HECATE G2 GAMING HEADSET */ QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE), + DEVICE_FLG(0x2fc6, 0xf06b, /* MOONDROP Moonriver2 Ti */ + QUIRK_FLAG_CTL_MSG_DELAY), DEVICE_FLG(0x2fc6, 0xf0b7, /* iBasso DC07 Pro */ QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */ QUIRK_FLAG_IGNORE_CTL_ERROR), + DEVICE_FLG(0x3255, 0x0000, /* Luxman D-10X */ + QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY), DEVICE_FLG(0x339b, 0x3a07, /* Synaptics HONOR USB-C HEADSET */ QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE), DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */ @@ -2431,6 +2441,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x2622, /* IAG Limited devices */ QUIRK_FLAG_DSD_RAW), + VENDOR_FLG(0x2772, /* Musical Fidelity devices */ + QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x278b, /* Rotel? */ QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x292b, /* Gustard/Ess based devices */ diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index cfc6f944f7c33a..1a06b0b5eef350 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -156,7 +156,7 @@ static int netlink_recv(int sock, __u32 nl_pid, __u32 seq, bool multipart = true; struct nlmsgerr *err; struct nlmsghdr *nh; - char buf[4096]; + char buf[8192]; int len, ret; while (multipart) { @@ -201,6 +201,9 @@ static int netlink_recv(int sock, __u32 nl_pid, __u32 seq, return ret; } } + + if (len) + p_err("Invalid message or trailing data in Netlink response: %d bytes left", len); } ret = 0; done: diff --git a/tools/bpf/bpftool/sign.c b/tools/bpf/bpftool/sign.c index b34f74d210e9cd..f9b742f4bb104b 100644 --- a/tools/bpf/bpftool/sign.c +++ b/tools/bpf/bpftool/sign.c @@ -28,6 +28,12 @@ #define OPEN_SSL_ERR_BUF_LEN 256 +/* Use deprecated in 3.0 ERR_get_error_line_data for openssl < 3 */ +#if !defined(OPENSSL_VERSION_MAJOR) || (OPENSSL_VERSION_MAJOR < 3) +#define ERR_get_error_all(file, line, func, data, flags) \ + ERR_get_error_line_data(file, line, data, flags) +#endif + static void display_openssl_errors(int l) { char buf[OPEN_SSL_ERR_BUF_LEN]; diff --git a/tools/include/nolibc/arch-x86.h b/tools/include/nolibc/arch-x86.h index d3efc0c3b8adcf..c8b0c3e624a518 100644 --- a/tools/include/nolibc/arch-x86.h +++ b/tools/include/nolibc/arch-x86.h @@ -351,7 +351,7 @@ void *memcpy(void *dst, const void *src, size_t len); void *memset(void *dst, int c, size_t len); __asm__ ( -".section .text.nolibc_memmove_memcpy\n" +".pushsection .text.nolibc_memmove_memcpy\n" ".weak memmove\n" ".weak memcpy\n" "memmove:\n" @@ -371,8 +371,9 @@ __asm__ ( "rep movsb\n\t" "cld\n\t" "retq\n" +".popsection\n" -".section .text.nolibc_memset\n" +".pushsection .text.nolibc_memset\n" ".weak memset\n" "memset:\n" "xchgl %eax, %esi\n\t" @@ -381,6 +382,7 @@ __asm__ ( "rep stosb\n\t" "popq %rax\n\t" "retq\n" +".popsection\n" ); #endif /* !defined(__x86_64__) */ diff --git a/tools/include/nolibc/dirent.h b/tools/include/nolibc/dirent.h index 758b95c48e7a4c..61a122a60327d2 100644 --- a/tools/include/nolibc/dirent.h +++ b/tools/include/nolibc/dirent.h @@ -86,9 +86,9 @@ int readdir_r(DIR *dirp, struct dirent *entry, struct dirent **result) * readdir() can only return one entry at a time. * Make sure the non-returned ones are not skipped. */ - ret = lseek(fd, ldir->d_off, SEEK_SET); - if (ret == -1) - return errno; + ret = sys_lseek(fd, ldir->d_off, SEEK_SET); + if (ret < 0) + return -ret; entry->d_ino = ldir->d_ino; /* the destination should always be big enough */ diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h index 7630234408c584..724d05ce69624f 100644 --- a/tools/include/nolibc/stdio.h +++ b/tools/include/nolibc/stdio.h @@ -600,7 +600,11 @@ int sscanf(const char *str, const char *format, ...) static __attribute__((unused)) void perror(const char *msg) { +#ifdef NOLIBC_IGNORE_ERRNO + fprintf(stderr, "%s%sunknown error\n", (msg && *msg) ? msg : "", (msg && *msg) ? ": " : ""); +#else fprintf(stderr, "%s%serrno=%d\n", (msg && *msg) ? msg : "", (msg && *msg) ? ": " : "", errno); +#endif } static __attribute__((unused)) diff --git a/tools/include/nolibc/sys/wait.h b/tools/include/nolibc/sys/wait.h index 4e66e1f7a03e45..9d9319ba92cbd3 100644 --- a/tools/include/nolibc/sys/wait.h +++ b/tools/include/nolibc/sys/wait.h @@ -65,23 +65,29 @@ pid_t waitpid(pid_t pid, int *status, int options) switch (info.si_code) { case 0: - *status = 0; + if (status) + *status = 0; break; case CLD_EXITED: - *status = (info.si_status & 0xff) << 8; + if (status) + *status = (info.si_status & 0xff) << 8; break; case CLD_KILLED: - *status = info.si_status & 0x7f; + if (status) + *status = info.si_status & 0x7f; break; case CLD_DUMPED: - *status = (info.si_status & 0x7f) | 0x80; + if (status) + *status = (info.si_status & 0x7f) | 0x80; break; case CLD_STOPPED: case CLD_TRAPPED: - *status = (info.si_status << 8) + 0x7f; + if (status) + *status = (info.si_status << 8) + 0x7f; break; case CLD_CONTINUED: - *status = 0xffff; + if (status) + *status = 0xffff; break; default: return -1; diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 18907f0fcf9f01..9f141395c074e3 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1061,7 +1061,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf, b if (base_btf) { btf->base_btf = base_btf; btf->start_id = btf__type_cnt(base_btf); - btf->start_str_off = base_btf->hdr->str_len; + btf->start_str_off = base_btf->hdr->str_len + base_btf->start_str_off; } if (is_mmap) { @@ -5818,7 +5818,7 @@ void btf_set_base_btf(struct btf *btf, const struct btf *base_btf) { btf->base_btf = (struct btf *)base_btf; btf->start_id = btf__type_cnt(base_btf); - btf->start_str_off = base_btf->hdr->str_len; + btf->start_str_off = base_btf->hdr->str_len + base_btf->start_str_off; } int btf__relocate(struct btf *btf, const struct btf *base_btf) diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 6388392f49a0b5..53c6624161d797 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -1762,9 +1762,18 @@ static int btf_dump_get_bitfield_value(struct btf_dump *d, __u16 left_shift_bits, right_shift_bits; const __u8 *bytes = data; __u8 nr_copy_bits; + __u8 start_bit, nr_bytes; __u64 num = 0; int i; + /* Calculate how many bytes cover the bitfield */ + start_bit = bits_offset % 8; + nr_bytes = (start_bit + bit_sz + 7) / 8; + + /* Bound check */ + if (data + nr_bytes > d->typed_dump->data_end) + return -E2BIG; + /* Maximum supported bitfield size is 64 bits */ if (t->size > 8) { pr_warn("unexpected bitfield size %d\n", t->size); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index dd3b2f57082d2d..9c98c6adb6d05e 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -8245,7 +8245,7 @@ static int kallsyms_cb(unsigned long long sym_addr, char sym_type, struct bpf_object *obj = ctx; const struct btf_type *t; struct extern_desc *ext; - char *res; + const char *res; res = strstr(sym_name, ".llvm."); if (sym_type == 'd' && res) @@ -11574,7 +11574,8 @@ static int avail_kallsyms_cb(unsigned long long sym_addr, char sym_type, * * [0] fb6a421fb615 ("kallsyms: Match symbols exactly with CONFIG_LTO_CLANG") */ - char sym_trim[256], *psym_trim = sym_trim, *sym_sfx; + char sym_trim[256], *psym_trim = sym_trim; + const char *sym_sfx; if (!(sym_sfx = strstr(sym_name, ".llvm."))) return 0; @@ -12159,7 +12160,7 @@ static int resolve_full_path(const char *file, char *result, size_t result_sz) if (!search_paths[i]) continue; for (s = search_paths[i]; s != NULL; s = strchr(s, ':')) { - char *next_path; + const char *next_path; int seg_len; if (s[0] == ':') diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 56ae77047bc367..b86b8ae3b63416 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -581,7 +581,7 @@ int bpf_linker__add_buf(struct bpf_linker *linker, void *buf, size_t buf_sz, written = 0; while (written < buf_sz) { - ret = write(fd, buf, buf_sz); + ret = write(fd, buf + written, buf_sz - written); if (ret < 0) { ret = -errno; pr_warn("failed to write '%s': %s\n", filename, errstr(ret)); diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index c997e69d507fef..c9a78fb16f115a 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -143,7 +143,7 @@ static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq, struct nlmsghdr *nh; int len, ret; - ret = alloc_iov(&iov, 4096); + ret = alloc_iov(&iov, 8192); if (ret) goto done; @@ -212,6 +212,8 @@ static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq, } } } + if (len) + pr_warn("Invalid message or trailing data in Netlink response: %d bytes left\n", len); } ret = 0; done: diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index b20a5280f2b333..2bbbe1c782b8a4 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -368,10 +368,12 @@ struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map) .cpu = -1 }; - // cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well. - return __perf_cpu_map__nr(map) > 0 - ? __perf_cpu_map__cpu(map, __perf_cpu_map__nr(map) - 1) - : result; + if (!map) + return result; + + // The CPUs are always sorted and nr is always > 0 as 0 length map is + // encoded as NULL. + return __perf_cpu_map__cpu(map, __perf_cpu_map__nr(map) - 1); } /** Is 'b' a subset of 'a'. */ diff --git a/tools/mm/page_owner_sort.c b/tools/mm/page_owner_sort.c index 880e36df0c1189..82d6f6b31348cf 100644 --- a/tools/mm/page_owner_sort.c +++ b/tools/mm/page_owner_sort.c @@ -183,7 +183,11 @@ static int compare_ts(const void *p1, const void *p2) { const struct block_list *l1 = p1, *l2 = p2; - return l1->ts_nsec < l2->ts_nsec ? -1 : 1; + if (l1->ts_nsec < l2->ts_nsec) + return -1; + if (l1->ts_nsec > l2->ts_nsec) + return 1; + return 0; } static int compare_cull_condition(const void *p1, const void *p2) diff --git a/tools/net/sunrpc/xdrgen/generators/__init__.py b/tools/net/sunrpc/xdrgen/generators/__init__.py index b98574a36a4ac3..a2eb6652ac900e 100644 --- a/tools/net/sunrpc/xdrgen/generators/__init__.py +++ b/tools/net/sunrpc/xdrgen/generators/__init__.py @@ -6,7 +6,7 @@ from jinja2 import Environment, FileSystemLoader, Template from xdr_ast import _XdrAst, Specification, _RpcProgram, _XdrTypeSpecifier -from xdr_ast import public_apis, pass_by_reference, get_header_name +from xdr_ast import public_apis, pass_by_reference, structs, get_header_name from xdr_parse import get_xdr_annotate @@ -22,6 +22,7 @@ def create_jinja2_environment(language: str, xdr_type: str) -> Environment: environment.globals["annotate"] = get_xdr_annotate() environment.globals["public_apis"] = public_apis environment.globals["pass_by_reference"] = pass_by_reference + environment.globals["structs"] = structs return environment case _: raise NotImplementedError("Language not supported") diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/decoder/argument.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/decoder/argument.j2 index 0b1709cca0d4a4..19b219dd276d3e 100644 --- a/tools/net/sunrpc/xdrgen/templates/C/program/decoder/argument.j2 +++ b/tools/net/sunrpc/xdrgen/templates/C/program/decoder/argument.j2 @@ -14,7 +14,11 @@ bool {{ program }}_svc_decode_{{ argument }}(struct svc_rqst *rqstp, struct xdr_ {% if argument == 'void' %} return xdrgen_decode_void(xdr); {% else %} +{% if argument in structs %} struct {{ argument }} *argp = rqstp->rq_argp; +{% else %} + {{ argument }} *argp = rqstp->rq_argp; +{% endif %} return xdrgen_decode_{{ argument }}(xdr, argp); {% endif %} diff --git a/tools/net/sunrpc/xdrgen/templates/C/program/encoder/result.j2 b/tools/net/sunrpc/xdrgen/templates/C/program/encoder/result.j2 index 6fc61a5d47b7f5..746592cfda5628 100644 --- a/tools/net/sunrpc/xdrgen/templates/C/program/encoder/result.j2 +++ b/tools/net/sunrpc/xdrgen/templates/C/program/encoder/result.j2 @@ -14,8 +14,14 @@ bool {{ program }}_svc_encode_{{ result }}(struct svc_rqst *rqstp, struct xdr_st {% if result == 'void' %} return xdrgen_encode_void(xdr); {% else %} +{% if result in structs %} struct {{ result }} *resp = rqstp->rq_resp; return xdrgen_encode_{{ result }}(xdr, resp); +{% else %} + {{ result }} *resp = rqstp->rq_resp; + + return xdrgen_encode_{{ result }}(xdr, *resp); +{% endif %} {% endif %} } diff --git a/tools/net/sunrpc/xdrgen/templates/C/source_top/client.j2 b/tools/net/sunrpc/xdrgen/templates/C/source_top/client.j2 index c5518c519854a0..df3598c38b2c29 100644 --- a/tools/net/sunrpc/xdrgen/templates/C/source_top/client.j2 +++ b/tools/net/sunrpc/xdrgen/templates/C/source_top/client.j2 @@ -8,6 +8,5 @@ #include #include #include -#include #include diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index 81b4ecd8910068..d9809276db9826 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -21,7 +21,7 @@ files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\|user\)') for f in $files; do # params: 0 1 2 3 # $YAML YNL-GEN kernel $mode - params=( $(git grep -B1 -h '/\* YNL-GEN' $f | sed 's@/\*\(.*\)\*/@\1@') ) + params=( $(git grep --no-line-number -B1 -h '/\* YNL-GEN' $f | sed 's@/\*\(.*\)\*/@\1@') ) args=$(sed -n 's@/\* YNL-ARG \(.*\) \*/@\1@p' $f) if [ $f -nt ${params[0]} -a -z "$force" ]; then diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 8c20361dd100ef..99d3897e046c66 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -7,6 +7,8 @@ srctree := $(patsubst %/,%,$(dir $(CURDIR))) srctree := $(patsubst %/,%,$(dir $(srctree))) endif +RM ?= rm -f + LIBSUBCMD_DIR = $(srctree)/tools/lib/subcmd/ ifneq ($(OUTPUT),) LIBSUBCMD_OUTPUT = $(abspath $(OUTPUT))/libsubcmd diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 9004fbc0676939..6059a546fb759b 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2564,7 +2564,8 @@ static int decode_sections(struct objtool_file *file) * Must be before add_jump_destinations(), which depends on 'func' * being set for alternatives, to enable proper sibling call detection. */ - if (opts.stackval || opts.orc || opts.uaccess || opts.noinstr) { + if (opts.stackval || opts.orc || opts.uaccess || opts.noinstr || + opts.hack_jump_label) { ret = add_special_section_alts(file); if (ret) return ret; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index ca5d77db692a23..9cb51fcde7986e 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -108,7 +108,7 @@ struct symbol_hole { }; /* - * Find !section symbol where @offset is after it. + * Find the last symbol before @offset. */ static int symbol_hole_by_offset(const void *key, const struct rb_node *node) { @@ -119,8 +119,7 @@ static int symbol_hole_by_offset(const void *key, const struct rb_node *node) return -1; if (sh->key >= s->offset + s->len) { - if (s->type != STT_SECTION) - sh->sym = s; + sh->sym = s; return 1; } @@ -412,7 +411,8 @@ static void elf_add_symbol(struct elf *elf, struct symbol *sym) sym->len = sym->sym.st_size; __sym_for_each(iter, &sym->sec->symbol_tree, sym->offset, sym->offset) { - if (iter->offset == sym->offset && iter->type == sym->type) + if (iter->offset == sym->offset && iter->type == sym->type && + iter->len == sym->len) iter->alias = sym; } diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index f0f285763f190a..c61369d54dd9d0 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -2014,7 +2014,7 @@ static int __cmd_record(const char *file_name, int argc, const char **argv) for (j = 1; j < argc; j++, i++) rec_argv[i] = STRDUP_FAIL_EXIT(argv[j]); - BUG_ON(i != rec_argc); + BUG_ON(i + 2 != rec_argc); ret = kvm_add_default_arch_event(&i, rec_argv); if (ret) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index d76f01956e33b4..b1fb87016d5aa9 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -2883,11 +2883,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) rec->bytes_written += off_cpu_write(rec->session); record__read_lost_samples(rec); - record__synthesize(rec, true); /* this will be recalculated during process_buildids() */ rec->samples = 0; if (!err) { + record__synthesize(rec, true); if (!rec->timestamp_filename) { record__finish_output(rec); } else { diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 7006f848f87a63..b6533dcf5465b1 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -856,7 +856,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) goto err_out; } } - if (!has_supported_counters) { + if (!has_supported_counters && !stat_config.null_run) { evsel__open_strerror(evlist__first(evsel_list), &target, open_err, msg, sizeof(msg)); ui__error("No supported events found.\n%s\n", msg); @@ -2540,6 +2540,7 @@ int cmd_stat(int argc, const char **argv) unsigned int interval, timeout; const char * const stat_subcommands[] = { "record", "report" }; char errbuf[BUFSIZ]; + struct evsel *counter; setlocale(LC_ALL, ""); @@ -2797,6 +2798,18 @@ int cmd_stat(int argc, const char **argv) evlist__warn_user_requested_cpus(evsel_list, target.cpu_list); + evlist__for_each_entry(evsel_list, counter) { + /* + * Setup BPF counters to require CPUs as any(-1) isn't + * supported. evlist__create_maps below will propagate this + * information to the evsels. Note, evsel__is_bperf isn't yet + * set up, and this change must happen early, so directly use + * the bpf_counter variable and target information. + */ + if ((counter->bpf_counter || target.use_bpf) && !target__has_cpu(&target)) + counter->core.requires_cpu = true; + } + if (evlist__create_maps(evsel_list, &target) < 0) { if (target__has_task(&target)) { pr_err("Problems finding threads of monitor\n"); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index a2e34f149a074a..1d6900033b3a0c 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1021,7 +1021,7 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, int err, nr; err = evsel__get_arch(evsel, &arch); - if (err < 0) + if (err) return err; if (parch) diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c index 80561630253dd5..1a1ffe50ee73ab 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c @@ -371,31 +371,20 @@ static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet, arm_spe_pkt_out_string(&err, &buf, &buf_len, " AR"); } - switch (SPE_OP_PKT_LDST_SUBCLASS_GET(payload)) { - case SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP: + if (SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP(payload)) arm_spe_pkt_out_string(&err, &buf, &buf_len, " SIMD-FP"); - break; - case SPE_OP_PKT_LDST_SUBCLASS_GP_REG: + else if (SPE_OP_PKT_LDST_SUBCLASS_GP_REG(payload)) arm_spe_pkt_out_string(&err, &buf, &buf_len, " GP-REG"); - break; - case SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG: + else if (SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG(payload)) arm_spe_pkt_out_string(&err, &buf, &buf_len, " UNSPEC-REG"); - break; - case SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG: + else if (SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG(payload)) arm_spe_pkt_out_string(&err, &buf, &buf_len, " NV-SYSREG"); - break; - case SPE_OP_PKT_LDST_SUBCLASS_MTE_TAG: + else if (SPE_OP_PKT_LDST_SUBCLASS_MTE_TAG(payload)) arm_spe_pkt_out_string(&err, &buf, &buf_len, " MTE-TAG"); - break; - case SPE_OP_PKT_LDST_SUBCLASS_MEMCPY: + else if (SPE_OP_PKT_LDST_SUBCLASS_MEMCPY(payload)) arm_spe_pkt_out_string(&err, &buf, &buf_len, " MEMCPY"); - break; - case SPE_OP_PKT_LDST_SUBCLASS_MEMSET: + else if (SPE_OP_PKT_LDST_SUBCLASS_MEMSET(payload)) arm_spe_pkt_out_string(&err, &buf, &buf_len, " MEMSET"); - break; - default: - break; - } if (SPE_OP_PKT_IS_LDST_SVE(payload)) { /* SVE effective vector length */ diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h index d00c2481712dcc..75e355fe3438cc 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h @@ -125,14 +125,13 @@ enum arm_spe_events { #define SPE_OP_PKT_IS_OTHER_SVE_OP(v) (((v) & (BIT(7) | BIT(3) | BIT(0))) == 0x8) -#define SPE_OP_PKT_LDST_SUBCLASS_GET(v) ((v) & GENMASK_ULL(7, 1)) -#define SPE_OP_PKT_LDST_SUBCLASS_GP_REG 0x0 -#define SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP 0x4 -#define SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG 0x10 -#define SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG 0x30 -#define SPE_OP_PKT_LDST_SUBCLASS_MTE_TAG 0x14 -#define SPE_OP_PKT_LDST_SUBCLASS_MEMCPY 0x20 -#define SPE_OP_PKT_LDST_SUBCLASS_MEMSET 0x25 +#define SPE_OP_PKT_LDST_SUBCLASS_GP_REG(v) (((v) & GENMASK_ULL(7, 1)) == 0x0) +#define SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP(v) (((v) & GENMASK_ULL(7, 1)) == 0x4) +#define SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG(v) (((v) & GENMASK_ULL(7, 1)) == 0x10) +#define SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG(v) (((v) & GENMASK_ULL(7, 1)) == 0x30) +#define SPE_OP_PKT_LDST_SUBCLASS_MTE_TAG(v) (((v) & GENMASK_ULL(7, 1)) == 0x14) +#define SPE_OP_PKT_LDST_SUBCLASS_MEMCPY(v) (((v) & GENMASK_ULL(7, 1)) == 0x20) +#define SPE_OP_PKT_LDST_SUBCLASS_MEMSET(v) (((v) & GENMASK_ULL(7, 0)) == 0x25) #define SPE_OP_PKT_IS_LDST_ATOMIC(v) (((v) & (GENMASK_ULL(7, 5) | BIT(1))) == 0x2) diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index ca5d01b9017dba..a5882b5822057b 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -460,6 +460,7 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, struct bperf_leader_bpf *skel = bperf_leader_bpf__open(); int link_fd, diff_map_fd, err; struct bpf_link *link = NULL; + struct perf_thread_map *threads; if (!skel) { pr_err("Failed to open leader skeleton\n"); @@ -495,7 +496,11 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, * following evsel__open_per_cpu call */ evsel->leader_skel = skel; - evsel__open(evsel, evsel->core.cpus, evsel->core.threads); + assert(!perf_cpu_map__has_any_cpu_or_is_empty(evsel->core.cpus)); + /* Always open system wide. */ + threads = thread_map__new_by_tid(-1); + evsel__open(evsel, evsel->core.cpus, threads); + perf_thread_map__put(threads); out: bperf_leader_bpf__destroy(skel); diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index 60b81d586323f3..7b5671f13c5352 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -184,6 +184,9 @@ int lock_contention_prepare(struct lock_contention *con) struct evlist *evlist = con->evlist; struct target *target = con->target; + /* make sure it loads the kernel map before lookup */ + map__load(machine__kernel_map(con->machine)); + skel = lock_contention_bpf__open(); if (!skel) { pr_err("Failed to open lock-contention BPF skeleton\n"); @@ -749,9 +752,6 @@ int lock_contention_read(struct lock_contention *con) bpf_prog_test_run_opts(prog_fd, &opts); } - /* make sure it loads the kernel map */ - maps__load_first(machine->kmaps); - prev_key = NULL; while (!bpf_map_get_next_key(fd, prev_key, &key)) { s64 ls_key; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 56ebefd075f2e3..9df9818e370139 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2473,7 +2473,7 @@ static bool evsel__detect_missing_features(struct evsel *evsel, struct perf_cpu /* Please add new feature detection here. */ attr.inherit = true; - attr.sample_type = PERF_SAMPLE_READ; + attr.sample_type = PERF_SAMPLE_READ | PERF_SAMPLE_TID; if (has_attr_feature(&attr, /*flags=*/0)) goto found; perf_missing_features.inherit_sample_read = true; diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index 591548b10e34ef..a1cd5196f4ec8f 100644 --- a/tools/perf/util/genelf.c +++ b/tools/perf/util/genelf.c @@ -173,6 +173,8 @@ jit_write_elf(int fd, uint64_t load_addr __maybe_unused, const char *sym, Elf_Shdr *shdr; uint64_t eh_frame_base_offset; char *strsym = NULL; + void *build_id_data = NULL, *tmp; + int build_id_data_len; int symlen; int retval = -1; @@ -251,6 +253,14 @@ jit_write_elf(int fd, uint64_t load_addr __maybe_unused, const char *sym, shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC; shdr->sh_entsize = 0; + build_id_data = malloc(csize); + if (build_id_data == NULL) { + warnx("cannot allocate build-id data"); + goto error; + } + memcpy(build_id_data, code, csize); + build_id_data_len = csize; + /* * Setup .eh_frame_hdr and .eh_frame */ @@ -334,6 +344,15 @@ jit_write_elf(int fd, uint64_t load_addr __maybe_unused, const char *sym, shdr->sh_entsize = sizeof(Elf_Sym); shdr->sh_link = unwinding ? 6 : 4; /* index of .strtab section */ + tmp = realloc(build_id_data, build_id_data_len + sizeof(symtab)); + if (tmp == NULL) { + warnx("cannot allocate build-id data"); + goto error; + } + memcpy(tmp + build_id_data_len, symtab, sizeof(symtab)); + build_id_data = tmp; + build_id_data_len += sizeof(symtab); + /* * setup symbols string table * 2 = 1 for 0 in 1st entry, 1 for the 0 at end of symbol for 2nd entry @@ -376,6 +395,15 @@ jit_write_elf(int fd, uint64_t load_addr __maybe_unused, const char *sym, shdr->sh_flags = 0; shdr->sh_entsize = 0; + tmp = realloc(build_id_data, build_id_data_len + symlen); + if (tmp == NULL) { + warnx("cannot allocate build-id data"); + goto error; + } + memcpy(tmp + build_id_data_len, strsym, symlen); + build_id_data = tmp; + build_id_data_len += symlen; + /* * setup build-id section */ @@ -394,7 +422,7 @@ jit_write_elf(int fd, uint64_t load_addr __maybe_unused, const char *sym, /* * build-id generation */ - sha1(code, csize, bnote.build_id); + sha1(build_id_data, build_id_data_len, bnote.build_id); bnote.desc.namesz = sizeof(bnote.name); /* must include 0 termination */ bnote.desc.descsz = sizeof(bnote.build_id); bnote.desc.type = NT_GNU_BUILD_ID; @@ -439,7 +467,7 @@ jit_write_elf(int fd, uint64_t load_addr __maybe_unused, const char *sym, (void)elf_end(e); free(strsym); - + free(build_id_data); return retval; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 64ff427040c341..ef4b569f7df463 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -608,10 +608,8 @@ static int hist_entry__init(struct hist_entry *he, map_symbol__exit(&he->branch_info->to.ms); zfree(&he->branch_info); } - if (he->mem_info) { - map_symbol__exit(&mem_info__iaddr(he->mem_info)->ms); - map_symbol__exit(&mem_info__daddr(he->mem_info)->ms); - } + if (he->mem_info) + mem_info__zput(he->mem_info); err: map_symbol__exit(&he->ms); zfree(&he->stat_acc); diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c index 416dfea9ffff61..5c27256a220a51 100644 --- a/tools/perf/util/hwmon_pmu.c +++ b/tools/perf/util/hwmon_pmu.c @@ -742,8 +742,7 @@ int perf_pmus__read_hwmon_pmus(struct list_head *pmus) continue; } io__init(&io, name_fd, buf2, sizeof(buf2)); - io__getline(&io, &line, &line_len); - if (line_len > 0 && line[line_len - 1] == '\n') + if (io__getline(&io, &line, &line_len) > 0 && line[line_len - 1] == '\n') line[line_len - 1] = '\0'; hwmon_pmu__new(pmus, buf, class_hwmon_ent->d_name, line); close(name_fd); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index da73d686f6b937..4723c2955f22ec 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -286,8 +286,11 @@ __add_event(struct list_head *list, int *idx, event_attr_init(attr); evsel = evsel__new_idx(attr, *idx); - if (!evsel) - goto out_err; + if (!evsel) { + perf_cpu_map__put(cpus); + perf_cpu_map__put(pmu_cpus); + return NULL; + } if (name) { evsel->name = strdup(name); @@ -475,8 +478,10 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state, int parse_events_add_cache(struct list_head *list, int *idx, const char *name, struct parse_events_state *parse_state, - struct parse_events_terms *parsed_terms) + struct parse_events_terms *parsed_terms, + void *loc_) { + YYLTYPE *loc = loc_; struct perf_pmu *pmu = NULL; bool found_supported = false; const char *config_name = get_config_name(parsed_terms); @@ -497,12 +502,36 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name, * The PMU has the event so add as not a legacy cache * event. */ + struct parse_events_terms temp_terms; + struct parse_events_term *term; + char *config = strdup(name); + + if (!config) + goto out_err; + + parse_events_terms__init(&temp_terms); + if (!parsed_terms) + parsed_terms = &temp_terms; + + if (parse_events_term__num(&term, + PARSE_EVENTS__TERM_TYPE_USER, + config, /*num=*/1, /*novalue=*/true, + loc, /*loc_val=*/NULL) < 0) { + zfree(&config); + goto out_err; + } + list_add(&term->list, &parsed_terms->terms); + ret = parse_events_add_pmu(parse_state, list, pmu, parsed_terms, first_wildcard_match, /*alternate_hw_config=*/PERF_COUNT_HW_MAX); + list_del_init(&term->list); + parse_events_term__delete(term); + parse_events_terms__exit(&temp_terms); if (ret) goto out_err; + found_supported = true; if (first_wildcard_match == NULL) first_wildcard_match = container_of(list->prev, struct evsel, core.node); @@ -2095,14 +2124,18 @@ static int evlist__cmp(void *_fg_idx, const struct list_head *l, const struct li * event's index is used. An index may be forced for events that * must be in the same group, namely Intel topdown events. */ - if (*force_grouped_idx != -1 && arch_evsel__must_be_in_group(lhs)) { + if (lhs->dont_regroup) { + lhs_sort_idx = lhs_core->idx; + } else if (*force_grouped_idx != -1 && arch_evsel__must_be_in_group(lhs)) { lhs_sort_idx = *force_grouped_idx; } else { bool lhs_has_group = lhs_core->leader != lhs_core || lhs_core->nr_members > 1; lhs_sort_idx = lhs_has_group ? lhs_core->leader->idx : lhs_core->idx; } - if (*force_grouped_idx != -1 && arch_evsel__must_be_in_group(rhs)) { + if (rhs->dont_regroup) { + rhs_sort_idx = rhs_core->idx; + } else if (*force_grouped_idx != -1 && arch_evsel__must_be_in_group(rhs)) { rhs_sort_idx = *force_grouped_idx; } else { bool rhs_has_group = rhs_core->leader != rhs_core || rhs_core->nr_members > 1; @@ -2200,10 +2233,10 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) */ idx = 0; list_for_each_entry(pos, list, core.node) { - const struct evsel *pos_leader = evsel__leader(pos); + struct evsel *pos_leader = evsel__leader(pos); const char *pos_pmu_name = pos->group_pmu_name; const char *cur_leader_pmu_name; - bool pos_force_grouped = force_grouped_idx != -1 && + bool pos_force_grouped = force_grouped_idx != -1 && !pos->dont_regroup && arch_evsel__must_be_in_group(pos); /* Reset index and nr_members. */ @@ -2217,8 +2250,8 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) * groups can't span PMUs. */ if (!cur_leader || pos->dont_regroup) { - cur_leader = pos; - cur_leaders_grp = &pos->core; + cur_leader = pos->dont_regroup ? pos_leader : pos; + cur_leaders_grp = &cur_leader->core; if (pos_force_grouped) force_grouped_leader = pos; } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 8f8c8e7fbcf186..8af19dec6a17da 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -237,7 +237,8 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, bool wildcard); int parse_events_add_cache(struct list_head *list, int *idx, const char *name, struct parse_events_state *parse_state, - struct parse_events_terms *parsed_terms); + struct parse_events_terms *parsed_terms, + void *loc); int parse_events__decode_legacy_cache(const char *name, int pmu_type, __u64 *config); int parse_events_add_breakpoint(struct parse_events_state *parse_state, struct list_head *list, diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index a2361c0040d759..ced26c549c33ac 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -353,7 +353,7 @@ PE_LEGACY_CACHE opt_event_config if (!list) YYNOMEM; - err = parse_events_add_cache(list, &parse_state->idx, $1, parse_state, $2); + err = parse_events_add_cache(list, &parse_state->idx, $1, parse_state, $2, &@1); parse_events_terms__delete($2); free($1); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 948d3e8ad782bc..f6c268c588a569 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -964,11 +964,11 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, if (dso__kernel(dso) == DSO_SPACE__KERNEL_GUEST) snprintf(dso_name, sizeof(dso_name), "[guest.kernel].%d", - kernel_range++); + kernel_range); else snprintf(dso_name, sizeof(dso_name), "[kernel].%d", - kernel_range++); + kernel_range); ndso = dso__new(dso_name); map__zput(curr_map); @@ -976,6 +976,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, return -1; dso__set_kernel(ndso, dso__kernel(dso)); + dso__set_loaded(ndso); curr_map = map__new2(pos->start, ndso); if (curr_map == NULL) { diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index 0ce251b8d46652..a7d54dfd3c68b6 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -950,9 +950,11 @@ int isolate_cpus(struct isst_id *id, int mask_size, cpu_set_t *cpu_mask, int lev ret = write(fd, "member", strlen("member")); if (ret == -1) { printf("Can't update to member\n"); + close(fd); return ret; } + close(fd); return 0; } diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index f2512d78bcbd8f..1b5ca2f4e92ff2 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -3285,13 +3285,13 @@ int format_counters(PER_THREAD_PARAMS) /* Added counters */ for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW || mp->format == FORMAT_AVERAGE) { + if (mp->format == FORMAT_RAW) { if (mp->width == 32) outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int)t->counter[i]); else outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), t->counter[i]); - } else if (mp->format == FORMAT_DELTA) { + } else if (mp->format == FORMAT_DELTA || mp->format == FORMAT_AVERAGE) { if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->counter[i]); else @@ -3382,13 +3382,13 @@ int format_counters(PER_THREAD_PARAMS) outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), c->core_throt_cnt); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW || mp->format == FORMAT_AVERAGE) { + if (mp->format == FORMAT_RAW) { if (mp->width == 32) outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int)c->counter[i]); else outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), c->counter[i]); - } else if (mp->format == FORMAT_DELTA) { + } else if (mp->format == FORMAT_DELTA || mp->format == FORMAT_AVERAGE) { if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), c->counter[i]); else @@ -3581,7 +3581,7 @@ int format_counters(PER_THREAD_PARAMS) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->uncore_mhz); for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW || mp->format == FORMAT_AVERAGE) { + if (mp->format == FORMAT_RAW) { if (mp->width == 32) outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int)p->counter[i]); @@ -3758,7 +3758,7 @@ int delta_package(struct pkg_data *new, struct pkg_data *old) new->rapl_dram_perf_status.raw_value - old->rapl_dram_perf_status.raw_value; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW || mp->format == FORMAT_AVERAGE) + if (mp->format == FORMAT_RAW) old->counter[i] = new->counter[i]; else if (mp->format == FORMAT_AVERAGE) old->counter[i] = new->counter[i]; diff --git a/tools/sched_ext/scx_show_state.py b/tools/sched_ext/scx_show_state.py index 7cdcc6729ea4ee..aec4a4498140fe 100644 --- a/tools/sched_ext/scx_show_state.py +++ b/tools/sched_ext/scx_show_state.py @@ -27,10 +27,13 @@ def read_static_key(name): def state_str(state): return prog['scx_enable_state_str'][state].string_().decode() -ops = prog['scx_ops'] +root = prog['scx_root'] enable_state = read_atomic("scx_enable_state_var") -print(f'ops : {ops.name.string_().decode()}') +if root: + print(f'ops : {root.ops.name.string_().decode()}') +else: + print('ops : ') print(f'enabled : {read_static_key("__scx_enabled")}') print(f'switching_all : {read_int("scx_switching_all")}') print(f'switched_all : {read_static_key("__scx_switched_all")}') diff --git a/tools/spi/.gitignore b/tools/spi/.gitignore index 14ddba3d21957b..038261b34ed83c 100644 --- a/tools/spi/.gitignore +++ b/tools/spi/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only spidev_fdx spidev_test +include/ diff --git a/tools/testing/ktest/config-bisect.pl b/tools/testing/ktest/config-bisect.pl index 6fd86493531959..bee7cb34a289c0 100755 --- a/tools/testing/ktest/config-bisect.pl +++ b/tools/testing/ktest/config-bisect.pl @@ -741,9 +741,9 @@ sub config_bisect { die "Can not find file $bad\n"; } if ($val eq "good") { - run_command "cp $output_config $good" or die "failed to copy $config to $good\n"; + run_command "cp $output_config $good" or die "failed to copy $output_config to $good\n"; } elsif ($val eq "bad") { - run_command "cp $output_config $bad" or die "failed to copy $config to $bad\n"; + run_command "cp $output_config $bad" or die "failed to copy $output_config to $bad\n"; } } diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index cfd4378e2129b2..f87e9f251d1310 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -670,6 +670,7 @@ static int nfit_test_search_spa(struct nvdimm_bus *bus, .addr = spa->spa, .region = NULL, }; + struct nfit_mem *nfit_mem; u64 dpa; ret = device_for_each_child(&bus->dev, &ctx, @@ -687,8 +688,12 @@ static int nfit_test_search_spa(struct nvdimm_bus *bus, */ nd_mapping = &nd_region->mapping[nd_region->ndr_mappings - 1]; nvdimm = nd_mapping->nvdimm; + nfit_mem = nvdimm_provider_data(nvdimm); + if (!nfit_mem) + return -EINVAL; - spa->devices[0].nfit_device_handle = handle[nvdimm->id]; + spa->devices[0].nfit_device_handle = + __to_nfit_memdev(nfit_mem)->device_handle; spa->num_nvdimms = 1; spa->devices[0].dpa = dpa; diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index 2f830ff8396cc4..945144e9850724 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -57,6 +57,26 @@ void idr_alloc_test(void) idr_destroy(&idr); } +void idr_alloc2_test(void) +{ + int id; + struct idr idr = IDR_INIT_BASE(idr, 1); + + id = idr_alloc(&idr, idr_alloc2_test, 0, 1, GFP_KERNEL); + assert(id == -ENOSPC); + + id = idr_alloc(&idr, idr_alloc2_test, 1, 2, GFP_KERNEL); + assert(id == 1); + + id = idr_alloc(&idr, idr_alloc2_test, 0, 1, GFP_KERNEL); + assert(id == -ENOSPC); + + id = idr_alloc(&idr, idr_alloc2_test, 0, 2, GFP_KERNEL); + assert(id == -ENOSPC); + + idr_destroy(&idr); +} + void idr_replace_test(void) { DEFINE_IDR(idr); @@ -409,6 +429,7 @@ void idr_checks(void) idr_replace_test(); idr_alloc_test(); + idr_alloc2_test(); idr_null_test(); idr_nowait_test(); idr_get_next_test(0); diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index be1ee7ba7ce031..ca557e5668fd84 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -23,6 +23,7 @@ test_tcpnotify_user test_libbpf xdping test_cpp +test_progs_verification_cert *.d *.subskel.h *.skel.h diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index f00587d4ede68e..591e7e77f89ba5 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -721,7 +721,8 @@ $(VERIFICATION_CERT) $(PRIVATE_KEY): $(VERIFY_SIG_SETUP) $(Q)$(VERIFY_SIG_SETUP) genkey $(BUILD_DIR) $(VERIFY_SIG_HDR): $(VERIFICATION_CERT) - $(Q)xxd -i -n test_progs_verification_cert $< > $@ + $(Q)ln -fs $< test_progs_verification_cert && \ + xxd -i test_progs_verification_cert > $@ # Define test_progs test runner. TRUNNER_TESTS_DIR := prog_tests @@ -804,7 +805,7 @@ $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT) # Include find_bit.c to compile xskxceiver. EXTRA_SRC := $(TOOLSDIR)/lib/find_bit.c -$(OUTPUT)/xskxceiver: $(EXTRA_SRC) xskxceiver.c xskxceiver.h $(OUTPUT)/network_helpers.o $(OUTPUT)/xsk.o $(OUTPUT)/xsk_xdp_progs.skel.h $(BPFOBJ) | $(OUTPUT) +$(OUTPUT)/xskxceiver: $(EXTRA_SRC) test_xsk.c test_xsk.h xskxceiver.c xskxceiver.h $(OUTPUT)/network_helpers.o $(OUTPUT)/xsk.o $(OUTPUT)/xsk_xdp_progs.skel.h $(BPFOBJ) | $(OUTPUT) $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ @@ -893,7 +894,8 @@ EXTRA_CLEAN := $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ $(addprefix $(OUTPUT)/,*.o *.d *.skel.h *.lskel.h *.subskel.h \ no_alu32 cpuv4 bpf_gcc \ liburandom_read.so) \ - $(OUTPUT)/FEATURE-DUMP.selftests + $(OUTPUT)/FEATURE-DUMP.selftests \ + test_progs_verification_cert .PHONY: docs docs-clean diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c index 2a9a30650350ed..65b4512967e746 100644 --- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c +++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c @@ -153,6 +153,26 @@ static void test_check_mtu_run_tc(struct test_check_mtu *skel, ASSERT_EQ(mtu_result, mtu_expect, "MTU-compare-user"); } +static void test_chk_segs_flag(struct test_check_mtu *skel, __u32 mtu) +{ + int err, prog_fd = bpf_program__fd(skel->progs.tc_chk_segs_flag); + struct __sk_buff skb = { + .gso_size = 10, + }; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .ctx_in = &skb, + .ctx_size_in = sizeof(skb), + ); + + /* Lower the mtu to test the BPF_MTU_CHK_SEGS */ + SYS_NOFAIL("ip link set dev lo mtu 10"); + err = bpf_prog_test_run_opts(prog_fd, &topts); + SYS_NOFAIL("ip link set dev lo mtu %u", mtu); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, BPF_OK, "retval"); +} static void test_check_mtu_tc(__u32 mtu, __u32 ifindex) { @@ -177,11 +197,12 @@ static void test_check_mtu_tc(__u32 mtu, __u32 ifindex) test_check_mtu_run_tc(skel, skel->progs.tc_minus_delta, mtu); test_check_mtu_run_tc(skel, skel->progs.tc_input_len, mtu); test_check_mtu_run_tc(skel, skel->progs.tc_input_len_exceed, mtu); + test_chk_segs_flag(skel, mtu); cleanup: test_check_mtu__destroy(skel); } -void serial_test_check_mtu(void) +void test_ns_check_mtu(void) { int mtu_lo; diff --git a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c index 1de14b111931aa..6e35e13c20220e 100644 --- a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c @@ -57,7 +57,8 @@ static void subtest_kmem_cache_iter_check_slabinfo(struct kmem_cache_iter *skel) if (!ASSERT_OK(ret, "kmem_cache_lookup")) break; - ASSERT_STREQ(r.name, name, "kmem_cache_name"); + ASSERT_STRNEQ(r.name, name, sizeof(r.name) - 1, + "kmem_cache_name"); ASSERT_EQ(r.obj_size, objsize, "kmem_cache_objsize"); seen++; diff --git a/tools/testing/selftests/bpf/prog_tests/perf_branches.c b/tools/testing/selftests/bpf/prog_tests/perf_branches.c index bc24f83339d642..0a7ef770c487c8 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_branches.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_branches.c @@ -15,6 +15,10 @@ static void check_good_sample(struct test_perf_branches *skel) int pbe_size = sizeof(struct perf_branch_entry); int duration = 0; + if (CHECK(!skel->bss->run_cnt, "invalid run_cnt", + "checked sample validity before prog run")) + return; + if (CHECK(!skel->bss->valid, "output not valid", "no valid sample from prog")) return; @@ -45,6 +49,10 @@ static void check_bad_sample(struct test_perf_branches *skel) int written_stack = skel->bss->written_stack_out; int duration = 0; + if (CHECK(!skel->bss->run_cnt, "invalid run_cnt", + "checked sample validity before prog run")) + return; + if (CHECK(!skel->bss->valid, "output not valid", "no valid sample from prog")) return; @@ -83,8 +91,12 @@ static void test_perf_branches_common(int perf_fd, err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set); if (CHECK(err, "set_affinity", "cpu #0, err %d\n", err)) goto out_destroy; - /* spin the loop for a while (random high number) */ - for (i = 0; i < 1000000; ++i) + + /* Spin the loop for a while by using a high iteration count, and by + * checking whether the specific run count marker has been explicitly + * incremented at least once by the backing perf_event BPF program. + */ + for (i = 0; i < 100000000 && !*(volatile int *)&skel->bss->run_cnt; ++i) ++j; test_perf_branches__detach(skel); @@ -116,11 +128,11 @@ static void test_perf_branches_hw(void) pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); /* - * Some setups don't support branch records (virtual machines, !x86), - * so skip test in this case. + * Some setups don't support LBR (virtual machines, !x86, AMD Milan Zen + * 3 which only supports BRS), so skip test in this case. */ if (pfd < 0) { - if (errno == ENOENT || errno == EOPNOTSUPP) { + if (errno == ENOENT || errno == EOPNOTSUPP || errno == EINVAL) { printf("%s:SKIP:no PERF_SAMPLE_BRANCH_STACK\n", __func__); test__skip(); diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 1702aa592c2c21..7ac4d5a488aa54 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -206,6 +206,11 @@ static void test_send_signal_common(struct perf_event_attr *attr, skel_open_load_failure: close(pipe_c2p[0]); close(pipe_p2c[1]); + /* + * Child is either about to exit cleanly or stuck in case of errors. + * Nudge it to exit. + */ + kill(pid, SIGKILL); wait(NULL); } diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c index c9efdd2a5b18a5..c93718dafd9b63 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c @@ -74,11 +74,20 @@ static void test_stacktrace_ips_kprobe_multi(bool retprobe) load_kallsyms(); - check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 4, - ksym_get_addr("bpf_testmod_stacktrace_test_3"), - ksym_get_addr("bpf_testmod_stacktrace_test_2"), - ksym_get_addr("bpf_testmod_stacktrace_test_1"), - ksym_get_addr("bpf_testmod_test_read")); + if (retprobe) { + check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 4, + ksym_get_addr("bpf_testmod_stacktrace_test_3"), + ksym_get_addr("bpf_testmod_stacktrace_test_2"), + ksym_get_addr("bpf_testmod_stacktrace_test_1"), + ksym_get_addr("bpf_testmod_test_read")); + } else { + check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 5, + ksym_get_addr("bpf_testmod_stacktrace_test"), + ksym_get_addr("bpf_testmod_stacktrace_test_3"), + ksym_get_addr("bpf_testmod_stacktrace_test_2"), + ksym_get_addr("bpf_testmod_stacktrace_test_1"), + ksym_get_addr("bpf_testmod_test_read")); + } cleanup: stacktrace_ips__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/wq.c b/tools/testing/selftests/bpf/prog_tests/wq.c index 99e438fe12acd5..15ac8e6d17450d 100644 --- a/tools/testing/selftests/bpf/prog_tests/wq.c +++ b/tools/testing/selftests/bpf/prog_tests/wq.c @@ -16,12 +16,12 @@ void serial_test_wq(void) /* re-run the success test to check if the timer was actually executed */ wq_skel = wq__open_and_load(); - if (!ASSERT_OK_PTR(wq_skel, "wq_skel_load")) + if (!ASSERT_OK_PTR(wq_skel, "wq__open_and_load")) return; err = wq__attach(wq_skel); if (!ASSERT_OK(err, "wq_attach")) - return; + goto clean_up; prog_fd = bpf_program__fd(wq_skel->progs.test_syscall_array_sleepable); err = bpf_prog_test_run_opts(prog_fd, &topts); @@ -31,6 +31,7 @@ void serial_test_wq(void) usleep(50); /* 10 usecs should be enough, but give it extra */ ASSERT_EQ(wq_skel->bss->ok_sleepable, (1 << 1), "ok_sleepable"); +clean_up: wq__destroy(wq_skel); } diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h index a5c74d31a2444c..6e1918deaf2627 100644 --- a/tools/testing/selftests/bpf/progs/strobemeta.h +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -330,9 +330,9 @@ static void *calc_location(struct strobe_value_loc *loc, void *tls_base) } bpf_probe_read_user(&tls_ptr, sizeof(void *), dtv); /* if pointer has (void *)-1 value, then TLS wasn't initialized yet */ - return tls_ptr && tls_ptr != (void *)-1 - ? tls_ptr + tls_index.offset - : NULL; + if (!tls_ptr || tls_ptr == (void *)-1) + return NULL; + return tls_ptr + tls_index.offset; } #ifdef SUBPROGS diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c index 2ec1de11a3ae4a..7b6b2b342c1de1 100644 --- a/tools/testing/selftests/bpf/progs/test_check_mtu.c +++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c @@ -7,6 +7,7 @@ #include #include +#include char _license[] SEC("license") = "GPL"; @@ -288,3 +289,14 @@ int tc_input_len_exceed(struct __sk_buff *ctx) global_bpf_mtu_xdp = mtu_len; return retval; } + +SEC("tc") +int tc_chk_segs_flag(struct __sk_buff *ctx) +{ + __u32 mtu_len = 0; + int err; + + err = bpf_check_mtu(ctx, GLOBAL_USER_IFINDEX, &mtu_len, 0, BPF_MTU_CHK_SEGS); + + return err == -EINVAL ? BPF_OK : BPF_DROP; +} diff --git a/tools/testing/selftests/bpf/progs/test_perf_branches.c b/tools/testing/selftests/bpf/progs/test_perf_branches.c index a1ccc831c882f6..05ac9410cd68c9 100644 --- a/tools/testing/selftests/bpf/progs/test_perf_branches.c +++ b/tools/testing/selftests/bpf/progs/test_perf_branches.c @@ -8,6 +8,7 @@ #include int valid = 0; +int run_cnt = 0; int required_size_out = 0; int written_stack_out = 0; int written_global_out = 0; @@ -24,6 +25,8 @@ int perf_branches(void *ctx) __u64 entries[4 * 3] = {0}; int required_size, written_stack, written_global; + ++run_cnt; + /* write to stack */ written_stack = bpf_read_branch_records(ctx, entries, sizeof(entries), 0); /* ignore spurious events */ diff --git a/tools/testing/selftests/bpf/test_tag.c b/tools/testing/selftests/bpf/test_tag.c index 5546b05a048661..f1300047c1e0a9 100644 --- a/tools/testing/selftests/bpf/test_tag.c +++ b/tools/testing/selftests/bpf/test_tag.c @@ -116,7 +116,7 @@ static void tag_from_alg(int insns, uint8_t *tag, uint32_t len) static const struct sockaddr_alg alg = { .salg_family = AF_ALG, .salg_type = "hash", - .salg_name = "sha1", + .salg_name = "sha256", }; int fd_base, fd_alg, ret; ssize_t size; diff --git a/tools/testing/selftests/bpf/test_xsk.c b/tools/testing/selftests/bpf/test_xsk.c new file mode 100644 index 00000000000000..55d318c5c5e593 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xsk.c @@ -0,0 +1,2422 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "network_helpers.h" +#include "test_xsk.h" +#include "xsk_xdp_common.h" +#include "xsk_xdp_progs.skel.h" + +#define DEFAULT_BATCH_SIZE 64 +#define MIN_PKT_SIZE 64 +#define MAX_ETH_JUMBO_SIZE 9000 +#define MAX_INTERFACES 2 +#define MAX_TEARDOWN_ITER 10 +#define MAX_TX_BUDGET_DEFAULT 32 +#define PKT_DUMP_NB_TO_PRINT 16 +/* Just to align the data in the packet */ +#define PKT_HDR_SIZE (sizeof(struct ethhdr) + 2) +#define POLL_TMOUT 1000 +#define THREAD_TMOUT 3 +#define UMEM_HEADROOM_TEST_SIZE 128 +#define XSK_DESC__INVALID_OPTION (0xffff) +#define XSK_UMEM__INVALID_FRAME_SIZE (MAX_ETH_JUMBO_SIZE + 1) +#define XSK_UMEM__LARGE_FRAME_SIZE (3 * 1024) +#define XSK_UMEM__MAX_FRAME_SIZE (4 * 1024) + +static const u8 g_mac[ETH_ALEN] = {0x55, 0x44, 0x33, 0x22, 0x11, 0x00}; + +bool opt_verbose; +pthread_barrier_t barr; +pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER; + +int pkts_in_flight; + +/* The payload is a word consisting of a packet sequence number in the upper + * 16-bits and a intra packet data sequence number in the lower 16 bits. So the 3rd packet's + * 5th word of data will contain the number (2<<16) | 4 as they are numbered from 0. + */ +static void write_payload(void *dest, u32 pkt_nb, u32 start, u32 size) +{ + u32 *ptr = (u32 *)dest, i; + + start /= sizeof(*ptr); + size /= sizeof(*ptr); + for (i = 0; i < size; i++) + ptr[i] = htonl(pkt_nb << 16 | (i + start)); +} + +static void gen_eth_hdr(struct xsk_socket_info *xsk, struct ethhdr *eth_hdr) +{ + memcpy(eth_hdr->h_dest, xsk->dst_mac, ETH_ALEN); + memcpy(eth_hdr->h_source, xsk->src_mac, ETH_ALEN); + eth_hdr->h_proto = htons(ETH_P_LOOPBACK); +} + +static bool is_umem_valid(struct ifobject *ifobj) +{ + return !!ifobj->umem->umem; +} + +static u32 mode_to_xdp_flags(enum test_mode mode) +{ + return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; +} + +static u64 umem_size(struct xsk_umem_info *umem) +{ + return umem->num_frames * umem->frame_size; +} + +int xsk_configure_umem(struct ifobject *ifobj, struct xsk_umem_info *umem, void *buffer, + u64 size) +{ + struct xsk_umem_config cfg = { + .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, + .frame_size = umem->frame_size, + .frame_headroom = umem->frame_headroom, + .flags = XSK_UMEM__DEFAULT_FLAGS + }; + int ret; + + if (umem->fill_size) + cfg.fill_size = umem->fill_size; + + if (umem->comp_size) + cfg.comp_size = umem->comp_size; + + if (umem->unaligned_mode) + cfg.flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG; + + ret = xsk_umem__create(&umem->umem, buffer, size, + &umem->fq, &umem->cq, &cfg); + if (ret) + return ret; + + umem->buffer = buffer; + if (ifobj->shared_umem && ifobj->rx_on) { + umem->base_addr = umem_size(umem); + umem->next_buffer = umem_size(umem); + } + + return 0; +} + +static u64 umem_alloc_buffer(struct xsk_umem_info *umem) +{ + u64 addr; + + addr = umem->next_buffer; + umem->next_buffer += umem->frame_size; + if (umem->next_buffer >= umem->base_addr + umem_size(umem)) + umem->next_buffer = umem->base_addr; + + return addr; +} + +static void umem_reset_alloc(struct xsk_umem_info *umem) +{ + umem->next_buffer = 0; +} + +static void enable_busy_poll(struct xsk_socket_info *xsk) +{ + int sock_opt; + + sock_opt = 1; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_PREFER_BUSY_POLL, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + exit_with_error(errno); + + sock_opt = 20; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + exit_with_error(errno); + + sock_opt = xsk->batch_size; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL_BUDGET, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + exit_with_error(errno); +} + +int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, + struct ifobject *ifobject, bool shared) +{ + struct xsk_socket_config cfg = {}; + struct xsk_ring_cons *rxr; + struct xsk_ring_prod *txr; + + xsk->umem = umem; + cfg.rx_size = xsk->rxqsize; + cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; + cfg.bind_flags = ifobject->bind_flags; + if (shared) + cfg.bind_flags |= XDP_SHARED_UMEM; + if (ifobject->mtu > MAX_ETH_PKT_SIZE) + cfg.bind_flags |= XDP_USE_SG; + if (umem->comp_size) + cfg.tx_size = umem->comp_size; + if (umem->fill_size) + cfg.rx_size = umem->fill_size; + + txr = ifobject->tx_on ? &xsk->tx : NULL; + rxr = ifobject->rx_on ? &xsk->rx : NULL; + return xsk_socket__create(&xsk->xsk, ifobject->ifindex, 0, umem->umem, rxr, txr, &cfg); +} + +#define MAX_SKB_FRAGS_PATH "/proc/sys/net/core/max_skb_frags" +static unsigned int get_max_skb_frags(void) +{ + unsigned int max_skb_frags = 0; + FILE *file; + + file = fopen(MAX_SKB_FRAGS_PATH, "r"); + if (!file) { + ksft_print_msg("Error opening %s\n", MAX_SKB_FRAGS_PATH); + return 0; + } + + if (fscanf(file, "%u", &max_skb_frags) != 1) + ksft_print_msg("Error reading %s\n", MAX_SKB_FRAGS_PATH); + + fclose(file); + return max_skb_frags; +} + +static int set_ring_size(struct ifobject *ifobj) +{ + int ret; + u32 ctr = 0; + + while (ctr++ < SOCK_RECONF_CTR) { + ret = set_hw_ring_size(ifobj->ifname, &ifobj->ring); + if (!ret) + break; + + /* Retry if it fails */ + if (ctr >= SOCK_RECONF_CTR || errno != EBUSY) + return -errno; + + usleep(USLEEP_MAX); + } + + return ret; +} + +int hw_ring_size_reset(struct ifobject *ifobj) +{ + ifobj->ring.tx_pending = ifobj->set_ring.default_tx; + ifobj->ring.rx_pending = ifobj->set_ring.default_rx; + return set_ring_size(ifobj); +} + +static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, + struct ifobject *ifobj_rx) +{ + u32 i, j; + + for (i = 0; i < MAX_INTERFACES; i++) { + struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; + + ifobj->xsk = &ifobj->xsk_arr[0]; + ifobj->use_poll = false; + ifobj->use_fill_ring = true; + ifobj->release_rx = true; + ifobj->validation_func = NULL; + ifobj->use_metadata = false; + + if (i == 0) { + ifobj->rx_on = false; + ifobj->tx_on = true; + } else { + ifobj->rx_on = true; + ifobj->tx_on = false; + } + + memset(ifobj->umem, 0, sizeof(*ifobj->umem)); + ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS; + ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; + + for (j = 0; j < MAX_SOCKETS; j++) { + memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j])); + ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; + ifobj->xsk_arr[j].batch_size = DEFAULT_BATCH_SIZE; + if (i == 0) + ifobj->xsk_arr[j].pkt_stream = test->tx_pkt_stream_default; + else + ifobj->xsk_arr[j].pkt_stream = test->rx_pkt_stream_default; + + memcpy(ifobj->xsk_arr[j].src_mac, g_mac, ETH_ALEN); + memcpy(ifobj->xsk_arr[j].dst_mac, g_mac, ETH_ALEN); + ifobj->xsk_arr[j].src_mac[5] += ((j * 2) + 0); + ifobj->xsk_arr[j].dst_mac[5] += ((j * 2) + 1); + } + } + + if (ifobj_tx->hw_ring_size_supp) + hw_ring_size_reset(ifobj_tx); + + test->ifobj_tx = ifobj_tx; + test->ifobj_rx = ifobj_rx; + test->current_step = 0; + test->total_steps = 1; + test->nb_sockets = 1; + test->fail = false; + test->set_ring = false; + test->adjust_tail = false; + test->adjust_tail_support = false; + test->mtu = MAX_ETH_PKT_SIZE; + test->xdp_prog_rx = ifobj_rx->xdp_progs->progs.xsk_def_prog; + test->xskmap_rx = ifobj_rx->xdp_progs->maps.xsk; + test->xdp_prog_tx = ifobj_tx->xdp_progs->progs.xsk_def_prog; + test->xskmap_tx = ifobj_tx->xdp_progs->maps.xsk; +} + +void test_init(struct test_spec *test, struct ifobject *ifobj_tx, + struct ifobject *ifobj_rx, enum test_mode mode, + const struct test_spec *test_to_run) +{ + struct pkt_stream *tx_pkt_stream; + struct pkt_stream *rx_pkt_stream; + u32 i; + + tx_pkt_stream = test->tx_pkt_stream_default; + rx_pkt_stream = test->rx_pkt_stream_default; + memset(test, 0, sizeof(*test)); + test->tx_pkt_stream_default = tx_pkt_stream; + test->rx_pkt_stream_default = rx_pkt_stream; + + for (i = 0; i < MAX_INTERFACES; i++) { + struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; + + ifobj->bind_flags = XDP_USE_NEED_WAKEUP; + if (mode == TEST_MODE_ZC) + ifobj->bind_flags |= XDP_ZEROCOPY; + else + ifobj->bind_flags |= XDP_COPY; + } + + memcpy(test->name, test_to_run->name, MAX_TEST_NAME_SIZE); + test->test_func = test_to_run->test_func; + test->mode = mode; + __test_spec_init(test, ifobj_tx, ifobj_rx); +} + +static void test_spec_reset(struct test_spec *test) +{ + __test_spec_init(test, test->ifobj_tx, test->ifobj_rx); +} + +static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *xdp_prog_rx, + struct bpf_program *xdp_prog_tx, struct bpf_map *xskmap_rx, + struct bpf_map *xskmap_tx) +{ + test->xdp_prog_rx = xdp_prog_rx; + test->xdp_prog_tx = xdp_prog_tx; + test->xskmap_rx = xskmap_rx; + test->xskmap_tx = xskmap_tx; +} + +static int test_spec_set_mtu(struct test_spec *test, int mtu) +{ + int err; + + if (test->ifobj_rx->mtu != mtu) { + err = xsk_set_mtu(test->ifobj_rx->ifindex, mtu); + if (err) + return err; + test->ifobj_rx->mtu = mtu; + } + if (test->ifobj_tx->mtu != mtu) { + err = xsk_set_mtu(test->ifobj_tx->ifindex, mtu); + if (err) + return err; + test->ifobj_tx->mtu = mtu; + } + + return 0; +} + +void pkt_stream_reset(struct pkt_stream *pkt_stream) +{ + if (pkt_stream) { + pkt_stream->current_pkt_nb = 0; + pkt_stream->nb_rx_pkts = 0; + } +} + +static struct pkt *pkt_stream_get_next_tx_pkt(struct pkt_stream *pkt_stream) +{ + if (pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) + return NULL; + + return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; +} + +static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream, u32 *pkts_sent) +{ + while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) { + (*pkts_sent)++; + if (pkt_stream->pkts[pkt_stream->current_pkt_nb].valid) + return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; + pkt_stream->current_pkt_nb++; + } + return NULL; +} + +void pkt_stream_delete(struct pkt_stream *pkt_stream) +{ + free(pkt_stream->pkts); + free(pkt_stream); +} + +void pkt_stream_restore_default(struct test_spec *test) +{ + struct pkt_stream *tx_pkt_stream = test->ifobj_tx->xsk->pkt_stream; + struct pkt_stream *rx_pkt_stream = test->ifobj_rx->xsk->pkt_stream; + + if (tx_pkt_stream != test->tx_pkt_stream_default) { + pkt_stream_delete(test->ifobj_tx->xsk->pkt_stream); + test->ifobj_tx->xsk->pkt_stream = test->tx_pkt_stream_default; + } + + if (rx_pkt_stream != test->rx_pkt_stream_default) { + pkt_stream_delete(test->ifobj_rx->xsk->pkt_stream); + test->ifobj_rx->xsk->pkt_stream = test->rx_pkt_stream_default; + } +} + +static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts) +{ + struct pkt_stream *pkt_stream; + + pkt_stream = calloc(1, sizeof(*pkt_stream)); + if (!pkt_stream) + return NULL; + + pkt_stream->pkts = calloc(nb_pkts, sizeof(*pkt_stream->pkts)); + if (!pkt_stream->pkts) { + free(pkt_stream); + return NULL; + } + + pkt_stream->nb_pkts = nb_pkts; + return pkt_stream; +} + +static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pkt *pkt) +{ + u32 nb_frags = 1, next_frag; + + if (!pkt) + return 1; + + if (!pkt_stream->verbatim) { + if (!pkt->valid || !pkt->len) + return 1; + return ceil_u32(pkt->len, frame_size); + } + + /* Search for the end of the packet in verbatim mode */ + if (!pkt_continues(pkt->options) || !pkt->valid) + return nb_frags; + + next_frag = pkt_stream->current_pkt_nb; + pkt++; + while (next_frag++ < pkt_stream->nb_pkts) { + nb_frags++; + if (!pkt_continues(pkt->options) || !pkt->valid) + break; + pkt++; + } + return nb_frags; +} + +static bool set_pkt_valid(int offset, u32 len) +{ + return len <= MAX_ETH_JUMBO_SIZE; +} + +static void pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len) +{ + pkt->offset = offset; + pkt->len = len; + pkt->valid = set_pkt_valid(offset, len); +} + +static void pkt_stream_pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len) +{ + bool prev_pkt_valid = pkt->valid; + + pkt_set(pkt_stream, pkt, offset, len); + pkt_stream->nb_valid_entries += pkt->valid - prev_pkt_valid; +} + +static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len) +{ + return ceil_u32(len, umem->frame_size) * umem->frame_size; +} + +static struct pkt_stream *__pkt_stream_generate(u32 nb_pkts, u32 pkt_len, u32 nb_start, u32 nb_off) +{ + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = __pkt_stream_alloc(nb_pkts); + if (!pkt_stream) + exit_with_error(ENOMEM); + + pkt_stream->nb_pkts = nb_pkts; + pkt_stream->max_pkt_len = pkt_len; + for (i = 0; i < nb_pkts; i++) { + struct pkt *pkt = &pkt_stream->pkts[i]; + + pkt_stream_pkt_set(pkt_stream, pkt, 0, pkt_len); + pkt->pkt_nb = nb_start + i * nb_off; + } + + return pkt_stream; +} + +struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len) +{ + return __pkt_stream_generate(nb_pkts, pkt_len, 0, 1); +} + +static struct pkt_stream *pkt_stream_clone(struct pkt_stream *pkt_stream) +{ + return pkt_stream_generate(pkt_stream->nb_pkts, pkt_stream->pkts[0].len); +} + +static void pkt_stream_replace_ifobject(struct ifobject *ifobj, u32 nb_pkts, u32 pkt_len) +{ + ifobj->xsk->pkt_stream = pkt_stream_generate(nb_pkts, pkt_len); +} + +static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len) +{ + pkt_stream_replace_ifobject(test->ifobj_tx, nb_pkts, pkt_len); + pkt_stream_replace_ifobject(test->ifobj_rx, nb_pkts, pkt_len); +} + +static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len, + int offset) +{ + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = pkt_stream_clone(ifobj->xsk->pkt_stream); + for (i = 1; i < ifobj->xsk->pkt_stream->nb_pkts; i += 2) + pkt_stream_pkt_set(pkt_stream, &pkt_stream->pkts[i], offset, pkt_len); + + ifobj->xsk->pkt_stream = pkt_stream; +} + +static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset) +{ + __pkt_stream_replace_half(test->ifobj_tx, pkt_len, offset); + __pkt_stream_replace_half(test->ifobj_rx, pkt_len, offset); +} + +static void pkt_stream_receive_half(struct test_spec *test) +{ + struct pkt_stream *pkt_stream = test->ifobj_tx->xsk->pkt_stream; + u32 i; + + test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(pkt_stream->nb_pkts, + pkt_stream->pkts[0].len); + pkt_stream = test->ifobj_rx->xsk->pkt_stream; + for (i = 1; i < pkt_stream->nb_pkts; i += 2) + pkt_stream->pkts[i].valid = false; + + pkt_stream->nb_valid_entries /= 2; +} + +static void pkt_stream_even_odd_sequence(struct test_spec *test) +{ + struct pkt_stream *pkt_stream; + u32 i; + + for (i = 0; i < test->nb_sockets; i++) { + pkt_stream = test->ifobj_tx->xsk_arr[i].pkt_stream; + pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2, + pkt_stream->pkts[0].len, i, 2); + test->ifobj_tx->xsk_arr[i].pkt_stream = pkt_stream; + + pkt_stream = test->ifobj_rx->xsk_arr[i].pkt_stream; + pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2, + pkt_stream->pkts[0].len, i, 2); + test->ifobj_rx->xsk_arr[i].pkt_stream = pkt_stream; + } +} + +static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem) +{ + if (!pkt->valid) + return pkt->offset; + return pkt->offset + umem_alloc_buffer(umem); +} + +static void pkt_stream_cancel(struct pkt_stream *pkt_stream) +{ + pkt_stream->current_pkt_nb--; +} + +static void pkt_generate(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, u64 addr, u32 len, + u32 pkt_nb, u32 bytes_written) +{ + void *data = xsk_umem__get_data(umem->buffer, addr); + + if (len < MIN_PKT_SIZE) + return; + + if (!bytes_written) { + gen_eth_hdr(xsk, data); + + len -= PKT_HDR_SIZE; + data += PKT_HDR_SIZE; + } else { + bytes_written -= PKT_HDR_SIZE; + } + + write_payload(data, pkt_nb, bytes_written, len); +} + +static struct pkt_stream *__pkt_stream_generate_custom(struct ifobject *ifobj, struct pkt *frames, + u32 nb_frames, bool verbatim) +{ + u32 i, len = 0, pkt_nb = 0, payload = 0; + struct pkt_stream *pkt_stream; + + pkt_stream = __pkt_stream_alloc(nb_frames); + if (!pkt_stream) + exit_with_error(ENOMEM); + + for (i = 0; i < nb_frames; i++) { + struct pkt *pkt = &pkt_stream->pkts[pkt_nb]; + struct pkt *frame = &frames[i]; + + pkt->offset = frame->offset; + if (verbatim) { + *pkt = *frame; + pkt->pkt_nb = payload; + if (!frame->valid || !pkt_continues(frame->options)) + payload++; + } else { + if (frame->valid) + len += frame->len; + if (frame->valid && pkt_continues(frame->options)) + continue; + + pkt->pkt_nb = pkt_nb; + pkt->len = len; + pkt->valid = frame->valid; + pkt->options = 0; + + len = 0; + } + + print_verbose("offset: %d len: %u valid: %u options: %u pkt_nb: %u\n", + pkt->offset, pkt->len, pkt->valid, pkt->options, pkt->pkt_nb); + + if (pkt->valid && pkt->len > pkt_stream->max_pkt_len) + pkt_stream->max_pkt_len = pkt->len; + + if (pkt->valid) + pkt_stream->nb_valid_entries++; + + pkt_nb++; + } + + pkt_stream->nb_pkts = pkt_nb; + pkt_stream->verbatim = verbatim; + return pkt_stream; +} + +static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, u32 nb_pkts) +{ + struct pkt_stream *pkt_stream; + + pkt_stream = __pkt_stream_generate_custom(test->ifobj_tx, pkts, nb_pkts, true); + test->ifobj_tx->xsk->pkt_stream = pkt_stream; + + pkt_stream = __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts, false); + test->ifobj_rx->xsk->pkt_stream = pkt_stream; +} + +static void pkt_print_data(u32 *data, u32 cnt) +{ + u32 i; + + for (i = 0; i < cnt; i++) { + u32 seqnum, pkt_nb; + + seqnum = ntohl(*data) & 0xffff; + pkt_nb = ntohl(*data) >> 16; + ksft_print_msg("%u:%u ", pkt_nb, seqnum); + data++; + } +} + +static void pkt_dump(void *pkt, u32 len, bool eth_header) +{ + struct ethhdr *ethhdr = pkt; + u32 i, *data; + + if (eth_header) { + /*extract L2 frame */ + ksft_print_msg("DEBUG>> L2: dst mac: "); + for (i = 0; i < ETH_ALEN; i++) + ksft_print_msg("%02X", ethhdr->h_dest[i]); + + ksft_print_msg("\nDEBUG>> L2: src mac: "); + for (i = 0; i < ETH_ALEN; i++) + ksft_print_msg("%02X", ethhdr->h_source[i]); + + data = pkt + PKT_HDR_SIZE; + } else { + data = pkt; + } + + /*extract L5 frame */ + ksft_print_msg("\nDEBUG>> L5: seqnum: "); + pkt_print_data(data, PKT_DUMP_NB_TO_PRINT); + ksft_print_msg("...."); + if (len > PKT_DUMP_NB_TO_PRINT * sizeof(u32)) { + ksft_print_msg("\n.... "); + pkt_print_data(data + len / sizeof(u32) - PKT_DUMP_NB_TO_PRINT, + PKT_DUMP_NB_TO_PRINT); + } + ksft_print_msg("\n---------------------------------------\n"); +} + +static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr) +{ + u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom; + u32 offset = addr % umem->frame_size, expected_offset; + int pkt_offset = pkt->valid ? pkt->offset : 0; + + if (!umem->unaligned_mode) + pkt_offset = 0; + + expected_offset = (pkt_offset + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; + + if (offset == expected_offset) + return true; + + ksft_print_msg("[%s] expected [%u], got [%u]\n", __func__, expected_offset, offset); + return false; +} + +static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) +{ + void *data = xsk_umem__get_data(buffer, addr); + struct xdp_info *meta = data - sizeof(struct xdp_info); + + if (meta->count != pkt->pkt_nb) { + ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%llu]\n", + __func__, pkt->pkt_nb, + (unsigned long long)meta->count); + return false; + } + + return true; +} + +static bool is_adjust_tail_supported(struct xsk_xdp_progs *skel_rx) +{ + struct bpf_map *data_map; + int adjust_value = 0; + int key = 0; + int ret; + + data_map = bpf_object__find_map_by_name(skel_rx->obj, "xsk_xdp_.bss"); + if (!data_map || !bpf_map__is_internal(data_map)) { + ksft_print_msg("Error: could not find bss section of XDP program\n"); + exit_with_error(errno); + } + + ret = bpf_map_lookup_elem(bpf_map__fd(data_map), &key, &adjust_value); + if (ret) { + ksft_print_msg("Error: bpf_map_lookup_elem failed with error %d\n", ret); + exit_with_error(errno); + } + + /* Set the 'adjust_value' variable to -EOPNOTSUPP in the XDP program if the adjust_tail + * helper is not supported. Skip the adjust_tail test case in this scenario. + */ + return adjust_value != -EOPNOTSUPP; +} + +static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 expected_pkt_nb, + u32 bytes_processed) +{ + u32 seqnum, pkt_nb, *pkt_data, words_to_end, expected_seqnum; + void *data = xsk_umem__get_data(umem->buffer, addr); + + addr -= umem->base_addr; + + if (addr >= umem->num_frames * umem->frame_size || + addr + len > umem->num_frames * umem->frame_size) { + ksft_print_msg("Frag invalid addr: %llx len: %u\n", + (unsigned long long)addr, len); + return false; + } + if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) { + ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n", + (unsigned long long)addr, len); + return false; + } + + pkt_data = data; + if (!bytes_processed) { + pkt_data += PKT_HDR_SIZE / sizeof(*pkt_data); + len -= PKT_HDR_SIZE; + } else { + bytes_processed -= PKT_HDR_SIZE; + } + + expected_seqnum = bytes_processed / sizeof(*pkt_data); + seqnum = ntohl(*pkt_data) & 0xffff; + pkt_nb = ntohl(*pkt_data) >> 16; + + if (expected_pkt_nb != pkt_nb) { + ksft_print_msg("[%s] expected pkt_nb [%u], got pkt_nb [%u]\n", + __func__, expected_pkt_nb, pkt_nb); + goto error; + } + if (expected_seqnum != seqnum) { + ksft_print_msg("[%s] expected seqnum at start [%u], got seqnum [%u]\n", + __func__, expected_seqnum, seqnum); + goto error; + } + + words_to_end = len / sizeof(*pkt_data) - 1; + pkt_data += words_to_end; + seqnum = ntohl(*pkt_data) & 0xffff; + expected_seqnum += words_to_end; + if (expected_seqnum != seqnum) { + ksft_print_msg("[%s] expected seqnum at end [%u], got seqnum [%u]\n", + __func__, expected_seqnum, seqnum); + goto error; + } + + return true; + +error: + pkt_dump(data, len, !bytes_processed); + return false; +} + +static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) +{ + if (pkt->len != len) { + ksft_print_msg("[%s] expected packet length [%d], got length [%d]\n", + __func__, pkt->len, len); + pkt_dump(xsk_umem__get_data(buffer, addr), len, true); + return false; + } + + return true; +} + +static u32 load_value(u32 *counter) +{ + return __atomic_load_n(counter, __ATOMIC_ACQUIRE); +} + +static bool kick_tx_with_check(struct xsk_socket_info *xsk, int *ret) +{ + u32 max_budget = MAX_TX_BUDGET_DEFAULT; + u32 cons, ready_to_send; + int delta; + + cons = load_value(xsk->tx.consumer); + ready_to_send = load_value(xsk->tx.producer) - cons; + *ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + + delta = load_value(xsk->tx.consumer) - cons; + /* By default, xsk should consume exact @max_budget descs at one + * send in this case where hitting the max budget limit in while + * loop is triggered in __xsk_generic_xmit(). Please make sure that + * the number of descs to be sent is larger than @max_budget, or + * else the tx.consumer will be updated in xskq_cons_peek_desc() + * in time which hides the issue we try to verify. + */ + if (ready_to_send > max_budget && delta != max_budget) + return false; + + return true; +} + +int kick_tx(struct xsk_socket_info *xsk) +{ + int ret; + + if (xsk->check_consumer) { + if (!kick_tx_with_check(xsk, &ret)) + return TEST_FAILURE; + } else { + ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + } + if (ret >= 0) + return TEST_PASS; + if (errno == ENOBUFS || errno == EAGAIN || errno == EBUSY || errno == ENETDOWN) { + usleep(100); + return TEST_PASS; + } + return TEST_FAILURE; +} + +int kick_rx(struct xsk_socket_info *xsk) +{ + int ret; + + ret = recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL); + if (ret < 0) + return TEST_FAILURE; + + return TEST_PASS; +} + +static int complete_pkts(struct xsk_socket_info *xsk, int batch_size) +{ + unsigned int rcvd; + u32 idx; + int ret; + + if (xsk_ring_prod__needs_wakeup(&xsk->tx)) { + ret = kick_tx(xsk); + if (ret) + return TEST_FAILURE; + } + + rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx); + if (rcvd) { + if (rcvd > xsk->outstanding_tx) { + u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1); + + ksft_print_msg("[%s] Too many packets completed\n", __func__); + ksft_print_msg("Last completion address: %llx\n", + (unsigned long long)addr); + return TEST_FAILURE; + } + + xsk_ring_cons__release(&xsk->umem->cq, rcvd); + xsk->outstanding_tx -= rcvd; + } + + return TEST_PASS; +} + +static int __receive_pkts(struct test_spec *test, struct xsk_socket_info *xsk) +{ + u32 frags_processed = 0, nb_frags = 0, pkt_len = 0; + u32 idx_rx = 0, idx_fq = 0, rcvd, pkts_sent = 0; + struct pkt_stream *pkt_stream = xsk->pkt_stream; + struct ifobject *ifobj = test->ifobj_rx; + struct xsk_umem_info *umem = xsk->umem; + struct pollfd fds = { }; + struct pkt *pkt; + u64 first_addr = 0; + int ret; + + fds.fd = xsk_socket__fd(xsk->xsk); + fds.events = POLLIN; + + ret = kick_rx(xsk); + if (ret) + return TEST_FAILURE; + + if (ifobj->use_poll) { + ret = poll(&fds, 1, POLL_TMOUT); + if (ret < 0) + return TEST_FAILURE; + + if (!ret) { + if (!is_umem_valid(test->ifobj_tx)) + return TEST_PASS; + + ksft_print_msg("ERROR: [%s] Poll timed out\n", __func__); + return TEST_CONTINUE; + } + + if (!(fds.revents & POLLIN)) + return TEST_CONTINUE; + } + + rcvd = xsk_ring_cons__peek(&xsk->rx, xsk->batch_size, &idx_rx); + if (!rcvd) + return TEST_CONTINUE; + + if (ifobj->use_fill_ring) { + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); + while (ret != rcvd) { + if (xsk_ring_prod__needs_wakeup(&umem->fq)) { + ret = poll(&fds, 1, POLL_TMOUT); + if (ret < 0) + return TEST_FAILURE; + } + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); + } + } + + while (frags_processed < rcvd) { + const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++); + u64 addr = desc->addr, orig; + + orig = xsk_umem__extract_addr(addr); + addr = xsk_umem__add_offset_to_addr(addr); + + if (!nb_frags) { + pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent); + if (!pkt) { + ksft_print_msg("[%s] received too many packets addr: %lx len %u\n", + __func__, addr, desc->len); + return TEST_FAILURE; + } + } + + print_verbose("Rx: addr: %lx len: %u options: %u pkt_nb: %u valid: %u\n", + addr, desc->len, desc->options, pkt->pkt_nb, pkt->valid); + + if (!is_frag_valid(umem, addr, desc->len, pkt->pkt_nb, pkt_len) || + !is_offset_correct(umem, pkt, addr) || (ifobj->use_metadata && + !is_metadata_correct(pkt, umem->buffer, addr))) + return TEST_FAILURE; + + if (!nb_frags++) + first_addr = addr; + frags_processed++; + pkt_len += desc->len; + if (ifobj->use_fill_ring) + *xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig; + + if (pkt_continues(desc->options)) + continue; + + /* The complete packet has been received */ + if (!is_pkt_valid(pkt, umem->buffer, first_addr, pkt_len) || + !is_offset_correct(umem, pkt, addr)) + return TEST_FAILURE; + + pkt_stream->nb_rx_pkts++; + nb_frags = 0; + pkt_len = 0; + } + + if (nb_frags) { + /* In the middle of a packet. Start over from beginning of packet. */ + idx_rx -= nb_frags; + xsk_ring_cons__cancel(&xsk->rx, nb_frags); + if (ifobj->use_fill_ring) { + idx_fq -= nb_frags; + xsk_ring_prod__cancel(&umem->fq, nb_frags); + } + frags_processed -= nb_frags; + pkt_stream_cancel(pkt_stream); + pkts_sent--; + } + + if (ifobj->use_fill_ring) + xsk_ring_prod__submit(&umem->fq, frags_processed); + if (ifobj->release_rx) + xsk_ring_cons__release(&xsk->rx, frags_processed); + + pthread_mutex_lock(&pacing_mutex); + pkts_in_flight -= pkts_sent; + pthread_mutex_unlock(&pacing_mutex); + pkts_sent = 0; + + return TEST_CONTINUE; +} + +bool all_packets_received(struct test_spec *test, struct xsk_socket_info *xsk, u32 sock_num, + unsigned long *bitmap) +{ + struct pkt_stream *pkt_stream = xsk->pkt_stream; + + if (!pkt_stream) { + __set_bit(sock_num, bitmap); + return false; + } + + if (pkt_stream->nb_rx_pkts == pkt_stream->nb_valid_entries) { + __set_bit(sock_num, bitmap); + if (bitmap_full(bitmap, test->nb_sockets)) + return true; + } + + return false; +} + +static int receive_pkts(struct test_spec *test) +{ + struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0}; + DECLARE_BITMAP(bitmap, test->nb_sockets); + struct xsk_socket_info *xsk; + u32 sock_num = 0; + int res, ret; + + ret = gettimeofday(&tv_now, NULL); + if (ret) + exit_with_error(errno); + + timeradd(&tv_now, &tv_timeout, &tv_end); + + while (1) { + xsk = &test->ifobj_rx->xsk_arr[sock_num]; + + if ((all_packets_received(test, xsk, sock_num, bitmap))) + break; + + res = __receive_pkts(test, xsk); + if (!(res == TEST_PASS || res == TEST_CONTINUE)) + return res; + + ret = gettimeofday(&tv_now, NULL); + if (ret) + exit_with_error(errno); + + if (timercmp(&tv_now, &tv_end, >)) { + ksft_print_msg("ERROR: [%s] Receive loop timed out\n", __func__); + return TEST_FAILURE; + } + sock_num = (sock_num + 1) % test->nb_sockets; + } + + return TEST_PASS; +} + +static int __send_pkts(struct ifobject *ifobject, struct xsk_socket_info *xsk, bool timeout) +{ + u32 i, idx = 0, valid_pkts = 0, valid_frags = 0, buffer_len; + struct pkt_stream *pkt_stream = xsk->pkt_stream; + struct xsk_umem_info *umem = ifobject->umem; + bool use_poll = ifobject->use_poll; + struct pollfd fds = { }; + int ret; + + buffer_len = pkt_get_buffer_len(umem, pkt_stream->max_pkt_len); + /* pkts_in_flight might be negative if many invalid packets are sent */ + if (pkts_in_flight >= (int)((umem_size(umem) - xsk->batch_size * buffer_len) / + buffer_len)) { + ret = kick_tx(xsk); + if (ret) + return TEST_FAILURE; + return TEST_CONTINUE; + } + + fds.fd = xsk_socket__fd(xsk->xsk); + fds.events = POLLOUT; + + while (xsk_ring_prod__reserve(&xsk->tx, xsk->batch_size, &idx) < xsk->batch_size) { + if (use_poll) { + ret = poll(&fds, 1, POLL_TMOUT); + if (timeout) { + if (ret < 0) { + ksft_print_msg("ERROR: [%s] Poll error %d\n", + __func__, errno); + return TEST_FAILURE; + } + if (ret == 0) + return TEST_PASS; + break; + } + if (ret <= 0) { + ksft_print_msg("ERROR: [%s] Poll error %d\n", + __func__, errno); + return TEST_FAILURE; + } + } + + complete_pkts(xsk, xsk->batch_size); + } + + for (i = 0; i < xsk->batch_size; i++) { + struct pkt *pkt = pkt_stream_get_next_tx_pkt(pkt_stream); + u32 nb_frags_left, nb_frags, bytes_written = 0; + + if (!pkt) + break; + + nb_frags = pkt_nb_frags(umem->frame_size, pkt_stream, pkt); + if (nb_frags > xsk->batch_size - i) { + pkt_stream_cancel(pkt_stream); + xsk_ring_prod__cancel(&xsk->tx, xsk->batch_size - i); + break; + } + nb_frags_left = nb_frags; + + while (nb_frags_left--) { + struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); + + tx_desc->addr = pkt_get_addr(pkt, ifobject->umem); + if (pkt_stream->verbatim) { + tx_desc->len = pkt->len; + tx_desc->options = pkt->options; + } else if (nb_frags_left) { + tx_desc->len = umem->frame_size; + tx_desc->options = XDP_PKT_CONTD; + } else { + tx_desc->len = pkt->len - bytes_written; + tx_desc->options = 0; + } + if (pkt->valid) + pkt_generate(xsk, umem, tx_desc->addr, tx_desc->len, pkt->pkt_nb, + bytes_written); + bytes_written += tx_desc->len; + + print_verbose("Tx addr: %llx len: %u options: %u pkt_nb: %u\n", + tx_desc->addr, tx_desc->len, tx_desc->options, pkt->pkt_nb); + + if (nb_frags_left) { + i++; + if (pkt_stream->verbatim) + pkt = pkt_stream_get_next_tx_pkt(pkt_stream); + } + } + + if (pkt && pkt->valid) { + valid_pkts++; + valid_frags += nb_frags; + } + } + + pthread_mutex_lock(&pacing_mutex); + pkts_in_flight += valid_pkts; + pthread_mutex_unlock(&pacing_mutex); + + xsk_ring_prod__submit(&xsk->tx, i); + xsk->outstanding_tx += valid_frags; + + if (use_poll) { + ret = poll(&fds, 1, POLL_TMOUT); + if (ret <= 0) { + if (ret == 0 && timeout) + return TEST_PASS; + + ksft_print_msg("ERROR: [%s] Poll error %d\n", __func__, ret); + return TEST_FAILURE; + } + } + + if (!timeout) { + if (complete_pkts(xsk, i)) + return TEST_FAILURE; + + usleep(10); + return TEST_PASS; + } + + return TEST_CONTINUE; +} + +static int wait_for_tx_completion(struct xsk_socket_info *xsk) +{ + struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0}; + int ret; + + ret = gettimeofday(&tv_now, NULL); + if (ret) + exit_with_error(errno); + timeradd(&tv_now, &tv_timeout, &tv_end); + + while (xsk->outstanding_tx) { + ret = gettimeofday(&tv_now, NULL); + if (ret) + exit_with_error(errno); + if (timercmp(&tv_now, &tv_end, >)) { + ksft_print_msg("ERROR: [%s] Transmission loop timed out\n", __func__); + return TEST_FAILURE; + } + + complete_pkts(xsk, xsk->batch_size); + } + + return TEST_PASS; +} + +bool all_packets_sent(struct test_spec *test, unsigned long *bitmap) +{ + return bitmap_full(bitmap, test->nb_sockets); +} + +static int send_pkts(struct test_spec *test, struct ifobject *ifobject) +{ + bool timeout = !is_umem_valid(test->ifobj_rx); + DECLARE_BITMAP(bitmap, test->nb_sockets); + u32 i, ret; + + while (!(all_packets_sent(test, bitmap))) { + for (i = 0; i < test->nb_sockets; i++) { + struct pkt_stream *pkt_stream; + + pkt_stream = ifobject->xsk_arr[i].pkt_stream; + if (!pkt_stream || pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) { + __set_bit(i, bitmap); + continue; + } + ret = __send_pkts(ifobject, &ifobject->xsk_arr[i], timeout); + if (ret == TEST_CONTINUE && !test->fail) + continue; + + if ((ret || test->fail) && !timeout) + return TEST_FAILURE; + + if (ret == TEST_PASS && timeout) + return ret; + + ret = wait_for_tx_completion(&ifobject->xsk_arr[i]); + if (ret) + return TEST_FAILURE; + } + } + + return TEST_PASS; +} + +static int get_xsk_stats(struct xsk_socket *xsk, struct xdp_statistics *stats) +{ + int fd = xsk_socket__fd(xsk), err; + socklen_t optlen, expected_len; + + optlen = sizeof(*stats); + err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, stats, &optlen); + if (err) { + ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n", + __func__, -err, strerror(-err)); + return TEST_FAILURE; + } + + expected_len = sizeof(struct xdp_statistics); + if (optlen != expected_len) { + ksft_print_msg("[%s] getsockopt optlen error. Expected: %u got: %u\n", + __func__, expected_len, optlen); + return TEST_FAILURE; + } + + return TEST_PASS; +} + +static int validate_rx_dropped(struct ifobject *ifobject) +{ + struct xsk_socket *xsk = ifobject->xsk->xsk; + struct xdp_statistics stats; + int err; + + err = kick_rx(ifobject->xsk); + if (err) + return TEST_FAILURE; + + err = get_xsk_stats(xsk, &stats); + if (err) + return TEST_FAILURE; + + /* The receiver calls getsockopt after receiving the last (valid) + * packet which is not the final packet sent in this test (valid and + * invalid packets are sent in alternating fashion with the final + * packet being invalid). Since the last packet may or may not have + * been dropped already, both outcomes must be allowed. + */ + if (stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 || + stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 - 1) + return TEST_PASS; + + return TEST_FAILURE; +} + +static int validate_rx_full(struct ifobject *ifobject) +{ + struct xsk_socket *xsk = ifobject->xsk->xsk; + struct xdp_statistics stats; + int err; + + usleep(1000); + err = kick_rx(ifobject->xsk); + if (err) + return TEST_FAILURE; + + err = get_xsk_stats(xsk, &stats); + if (err) + return TEST_FAILURE; + + if (stats.rx_ring_full) + return TEST_PASS; + + return TEST_FAILURE; +} + +static int validate_fill_empty(struct ifobject *ifobject) +{ + struct xsk_socket *xsk = ifobject->xsk->xsk; + struct xdp_statistics stats; + int err; + + usleep(1000); + err = kick_rx(ifobject->xsk); + if (err) + return TEST_FAILURE; + + err = get_xsk_stats(xsk, &stats); + if (err) + return TEST_FAILURE; + + if (stats.rx_fill_ring_empty_descs) + return TEST_PASS; + + return TEST_FAILURE; +} + +static int validate_tx_invalid_descs(struct ifobject *ifobject) +{ + struct xsk_socket *xsk = ifobject->xsk->xsk; + int fd = xsk_socket__fd(xsk); + struct xdp_statistics stats; + socklen_t optlen; + int err; + + optlen = sizeof(stats); + err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen); + if (err) { + ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n", + __func__, -err, strerror(-err)); + return TEST_FAILURE; + } + + if (stats.tx_invalid_descs != ifobject->xsk->pkt_stream->nb_pkts / 2) { + ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%llu] expected [%u]\n", + __func__, + (unsigned long long)stats.tx_invalid_descs, + ifobject->xsk->pkt_stream->nb_pkts); + return TEST_FAILURE; + } + + return TEST_PASS; +} + +static void xsk_configure(struct test_spec *test, struct ifobject *ifobject, + struct xsk_umem_info *umem, bool tx) +{ + int i, ret; + + for (i = 0; i < test->nb_sockets; i++) { + bool shared = (ifobject->shared_umem && tx) ? true : !!i; + u32 ctr = 0; + + while (ctr++ < SOCK_RECONF_CTR) { + ret = xsk_configure_socket(&ifobject->xsk_arr[i], umem, + ifobject, shared); + if (!ret) + break; + + /* Retry if it fails as xsk_socket__create() is asynchronous */ + if (ctr >= SOCK_RECONF_CTR) + exit_with_error(-ret); + usleep(USLEEP_MAX); + } + if (ifobject->busy_poll) + enable_busy_poll(&ifobject->xsk_arr[i]); + } +} + +static void thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobject) +{ + xsk_configure(test, ifobject, test->ifobj_rx->umem, true); + ifobject->xsk = &ifobject->xsk_arr[0]; + ifobject->xskmap = test->ifobj_rx->xskmap; + memcpy(ifobject->umem, test->ifobj_rx->umem, sizeof(struct xsk_umem_info)); + ifobject->umem->base_addr = 0; +} + +static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, + bool fill_up) +{ + u32 rx_frame_size = umem->frame_size - XDP_PACKET_HEADROOM; + u32 idx = 0, filled = 0, buffers_to_fill, nb_pkts; + int ret; + + if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) + buffers_to_fill = umem->num_frames; + else + buffers_to_fill = umem->fill_size; + + ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx); + if (ret != buffers_to_fill) + exit_with_error(ENOSPC); + + while (filled < buffers_to_fill) { + struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &nb_pkts); + u64 addr; + u32 i; + + for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt_stream, pkt); i++) { + if (!pkt) { + if (!fill_up) + break; + addr = filled * umem->frame_size + umem->base_addr; + } else if (pkt->offset >= 0) { + addr = pkt->offset % umem->frame_size + umem_alloc_buffer(umem); + } else { + addr = pkt->offset + umem_alloc_buffer(umem); + } + + *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; + if (++filled >= buffers_to_fill) + break; + } + } + xsk_ring_prod__submit(&umem->fq, filled); + xsk_ring_prod__cancel(&umem->fq, buffers_to_fill - filled); + + pkt_stream_reset(pkt_stream); + umem_reset_alloc(umem); +} + +static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) +{ + LIBBPF_OPTS(bpf_xdp_query_opts, opts); + int mmap_flags; + u64 umem_sz; + void *bufs; + int ret; + u32 i; + + umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; + mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE; + + if (ifobject->umem->unaligned_mode) + mmap_flags |= MAP_HUGETLB | MAP_HUGE_2MB; + + if (ifobject->shared_umem) + umem_sz *= 2; + + bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); + if (bufs == MAP_FAILED) + exit_with_error(errno); + + ret = xsk_configure_umem(ifobject, ifobject->umem, bufs, umem_sz); + if (ret) + exit_with_error(-ret); + + xsk_configure(test, ifobject, ifobject->umem, false); + + ifobject->xsk = &ifobject->xsk_arr[0]; + + if (!ifobject->rx_on) + return; + + xsk_populate_fill_ring(ifobject->umem, ifobject->xsk->pkt_stream, ifobject->use_fill_ring); + + for (i = 0; i < test->nb_sockets; i++) { + ifobject->xsk = &ifobject->xsk_arr[i]; + ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, i); + if (ret) + exit_with_error(errno); + } +} + +void *worker_testapp_validate_tx(void *arg) +{ + struct test_spec *test = (struct test_spec *)arg; + struct ifobject *ifobject = test->ifobj_tx; + int err; + + if (test->current_step == 1) { + if (!ifobject->shared_umem) + thread_common_ops(test, ifobject); + else + thread_common_ops_tx(test, ifobject); + } + + err = send_pkts(test, ifobject); + + if (!err && ifobject->validation_func) + err = ifobject->validation_func(ifobject); + if (err) + test->fail = true; + + pthread_exit(NULL); +} + +void *worker_testapp_validate_rx(void *arg) +{ + struct test_spec *test = (struct test_spec *)arg; + struct ifobject *ifobject = test->ifobj_rx; + int err; + + if (test->current_step == 1) { + thread_common_ops(test, ifobject); + } else { + xsk_clear_xskmap(ifobject->xskmap); + err = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, 0); + if (err) { + ksft_print_msg("Error: Failed to update xskmap, error %s\n", + strerror(-err)); + exit_with_error(-err); + } + } + + pthread_barrier_wait(&barr); + + err = receive_pkts(test); + + if (!err && ifobject->validation_func) + err = ifobject->validation_func(ifobject); + + if (err) { + if (test->adjust_tail && !is_adjust_tail_supported(ifobject->xdp_progs)) + test->adjust_tail_support = false; + else + test->fail = true; + } + + pthread_exit(NULL); +} + +static void testapp_clean_xsk_umem(struct ifobject *ifobj) +{ + u64 umem_sz = ifobj->umem->num_frames * ifobj->umem->frame_size; + + if (ifobj->shared_umem) + umem_sz *= 2; + + umem_sz = ceil_u64(umem_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; + xsk_umem__delete(ifobj->umem->umem); + munmap(ifobj->umem->buffer, umem_sz); +} + +static void handler(int signum) +{ + pthread_exit(NULL); +} + +static bool xdp_prog_changed_rx(struct test_spec *test) +{ + struct ifobject *ifobj = test->ifobj_rx; + + return ifobj->xdp_prog != test->xdp_prog_rx || ifobj->mode != test->mode; +} + +static bool xdp_prog_changed_tx(struct test_spec *test) +{ + struct ifobject *ifobj = test->ifobj_tx; + + return ifobj->xdp_prog != test->xdp_prog_tx || ifobj->mode != test->mode; +} + +static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_prog, + struct bpf_map *xskmap, enum test_mode mode) +{ + int err; + + xsk_detach_xdp_program(ifobj->ifindex, mode_to_xdp_flags(ifobj->mode)); + err = xsk_attach_xdp_program(xdp_prog, ifobj->ifindex, mode_to_xdp_flags(mode)); + if (err) { + ksft_print_msg("Error attaching XDP program\n"); + exit_with_error(-err); + } + + if (ifobj->mode != mode && (mode == TEST_MODE_DRV || mode == TEST_MODE_ZC)) + if (!xsk_is_in_mode(ifobj->ifindex, XDP_FLAGS_DRV_MODE)) { + ksft_print_msg("ERROR: XDP prog not in DRV mode\n"); + exit_with_error(EINVAL); + } + + ifobj->xdp_prog = xdp_prog; + ifobj->xskmap = xskmap; + ifobj->mode = mode; +} + +static void xsk_attach_xdp_progs(struct test_spec *test, struct ifobject *ifobj_rx, + struct ifobject *ifobj_tx) +{ + if (xdp_prog_changed_rx(test)) + xsk_reattach_xdp(ifobj_rx, test->xdp_prog_rx, test->xskmap_rx, test->mode); + + if (!ifobj_tx || ifobj_tx->shared_umem) + return; + + if (xdp_prog_changed_tx(test)) + xsk_reattach_xdp(ifobj_tx, test->xdp_prog_tx, test->xskmap_tx, test->mode); +} + +static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *ifobj1, + struct ifobject *ifobj2) +{ + pthread_t t0, t1; + int err; + + if (test->mtu > MAX_ETH_PKT_SIZE) { + if (test->mode == TEST_MODE_ZC && (!ifobj1->multi_buff_zc_supp || + (ifobj2 && !ifobj2->multi_buff_zc_supp))) { + ksft_print_msg("Multi buffer for zero-copy not supported.\n"); + return TEST_SKIP; + } + if (test->mode != TEST_MODE_ZC && (!ifobj1->multi_buff_supp || + (ifobj2 && !ifobj2->multi_buff_supp))) { + ksft_print_msg("Multi buffer not supported.\n"); + return TEST_SKIP; + } + } + err = test_spec_set_mtu(test, test->mtu); + if (err) { + ksft_print_msg("Error, could not set mtu.\n"); + exit_with_error(err); + } + + if (ifobj2) { + if (pthread_barrier_init(&barr, NULL, 2)) + exit_with_error(errno); + pkt_stream_reset(ifobj2->xsk->pkt_stream); + } + + test->current_step++; + pkt_stream_reset(ifobj1->xsk->pkt_stream); + pkts_in_flight = 0; + + signal(SIGUSR1, handler); + /*Spawn RX thread */ + pthread_create(&t0, NULL, ifobj1->func_ptr, test); + + if (ifobj2) { + pthread_barrier_wait(&barr); + if (pthread_barrier_destroy(&barr)) + exit_with_error(errno); + + /*Spawn TX thread */ + pthread_create(&t1, NULL, ifobj2->func_ptr, test); + + pthread_join(t1, NULL); + } + + if (!ifobj2) + pthread_kill(t0, SIGUSR1); + else + pthread_join(t0, NULL); + + if (test->total_steps == test->current_step || test->fail) { + u32 i; + + if (ifobj2) + for (i = 0; i < test->nb_sockets; i++) + xsk_socket__delete(ifobj2->xsk_arr[i].xsk); + + for (i = 0; i < test->nb_sockets; i++) + xsk_socket__delete(ifobj1->xsk_arr[i].xsk); + + testapp_clean_xsk_umem(ifobj1); + if (ifobj2 && !ifobj2->shared_umem) + testapp_clean_xsk_umem(ifobj2); + } + + return !!test->fail; +} + +static int testapp_validate_traffic(struct test_spec *test) +{ + struct ifobject *ifobj_rx = test->ifobj_rx; + struct ifobject *ifobj_tx = test->ifobj_tx; + + if ((ifobj_rx->umem->unaligned_mode && !ifobj_rx->unaligned_supp) || + (ifobj_tx->umem->unaligned_mode && !ifobj_tx->unaligned_supp)) { + ksft_print_msg("No huge pages present.\n"); + return TEST_SKIP; + } + + if (test->set_ring) { + if (ifobj_tx->hw_ring_size_supp) { + if (set_ring_size(ifobj_tx)) { + ksft_print_msg("Failed to change HW ring size.\n"); + return TEST_FAILURE; + } + } else { + ksft_print_msg("Changing HW ring size not supported.\n"); + return TEST_SKIP; + } + } + + xsk_attach_xdp_progs(test, ifobj_rx, ifobj_tx); + return __testapp_validate_traffic(test, ifobj_rx, ifobj_tx); +} + +static int testapp_validate_traffic_single_thread(struct test_spec *test, struct ifobject *ifobj) +{ + return __testapp_validate_traffic(test, ifobj, NULL); +} + +int testapp_teardown(struct test_spec *test) +{ + int i; + + for (i = 0; i < MAX_TEARDOWN_ITER; i++) { + if (testapp_validate_traffic(test)) + return TEST_FAILURE; + test_spec_reset(test); + } + + return TEST_PASS; +} + +static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) +{ + thread_func_t tmp_func_ptr = (*ifobj1)->func_ptr; + struct ifobject *tmp_ifobj = (*ifobj1); + + (*ifobj1)->func_ptr = (*ifobj2)->func_ptr; + (*ifobj2)->func_ptr = tmp_func_ptr; + + *ifobj1 = *ifobj2; + *ifobj2 = tmp_ifobj; +} + +int testapp_bidirectional(struct test_spec *test) +{ + int res; + + test->ifobj_tx->rx_on = true; + test->ifobj_rx->tx_on = true; + test->total_steps = 2; + if (testapp_validate_traffic(test)) + return TEST_FAILURE; + + print_verbose("Switching Tx/Rx direction\n"); + swap_directions(&test->ifobj_rx, &test->ifobj_tx); + res = __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx); + + swap_directions(&test->ifobj_rx, &test->ifobj_tx); + return res; +} + +static int swap_xsk_resources(struct test_spec *test) +{ + int ret; + + test->ifobj_tx->xsk_arr[0].pkt_stream = NULL; + test->ifobj_rx->xsk_arr[0].pkt_stream = NULL; + test->ifobj_tx->xsk_arr[1].pkt_stream = test->tx_pkt_stream_default; + test->ifobj_rx->xsk_arr[1].pkt_stream = test->rx_pkt_stream_default; + test->ifobj_tx->xsk = &test->ifobj_tx->xsk_arr[1]; + test->ifobj_rx->xsk = &test->ifobj_rx->xsk_arr[1]; + + ret = xsk_update_xskmap(test->ifobj_rx->xskmap, test->ifobj_rx->xsk->xsk, 0); + if (ret) + return TEST_FAILURE; + + return TEST_PASS; +} + +int testapp_xdp_prog_cleanup(struct test_spec *test) +{ + test->total_steps = 2; + test->nb_sockets = 2; + if (testapp_validate_traffic(test)) + return TEST_FAILURE; + + if (swap_xsk_resources(test)) + return TEST_FAILURE; + return testapp_validate_traffic(test); +} + +int testapp_headroom(struct test_spec *test) +{ + test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE; + return testapp_validate_traffic(test); +} + +int testapp_stats_rx_dropped(struct test_spec *test) +{ + if (test->mode == TEST_MODE_ZC) { + ksft_print_msg("Can not run RX_DROPPED test for ZC mode\n"); + return TEST_SKIP; + } + + pkt_stream_replace_half(test, MIN_PKT_SIZE * 4, 0); + test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size - + XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 3; + pkt_stream_receive_half(test); + test->ifobj_rx->validation_func = validate_rx_dropped; + return testapp_validate_traffic(test); +} + +int testapp_stats_tx_invalid_descs(struct test_spec *test) +{ + pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0); + test->ifobj_tx->validation_func = validate_tx_invalid_descs; + return testapp_validate_traffic(test); +} + +int testapp_stats_rx_full(struct test_spec *test) +{ + pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); + test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); + + test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS; + test->ifobj_rx->release_rx = false; + test->ifobj_rx->validation_func = validate_rx_full; + return testapp_validate_traffic(test); +} + +int testapp_stats_fill_empty(struct test_spec *test) +{ + pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); + test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); + + test->ifobj_rx->use_fill_ring = false; + test->ifobj_rx->validation_func = validate_fill_empty; + return testapp_validate_traffic(test); +} + +int testapp_send_receive_unaligned(struct test_spec *test) +{ + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + /* Let half of the packets straddle a 4K buffer boundary */ + pkt_stream_replace_half(test, MIN_PKT_SIZE, -MIN_PKT_SIZE / 2); + + return testapp_validate_traffic(test); +} + +int testapp_send_receive_unaligned_mb(struct test_spec *test) +{ + test->mtu = MAX_ETH_JUMBO_SIZE; + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE); + return testapp_validate_traffic(test); +} + +int testapp_single_pkt(struct test_spec *test) +{ + struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}}; + + pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); + return testapp_validate_traffic(test); +} + +int testapp_send_receive_mb(struct test_spec *test) +{ + test->mtu = MAX_ETH_JUMBO_SIZE; + pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE); + + return testapp_validate_traffic(test); +} + +int testapp_invalid_desc_mb(struct test_spec *test) +{ + struct xsk_umem_info *umem = test->ifobj_tx->umem; + u64 umem_size = umem->num_frames * umem->frame_size; + struct pkt pkts[] = { + /* Valid packet for synch to start with */ + {0, MIN_PKT_SIZE, 0, true, 0}, + /* Zero frame len is not legal */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, 0, 0, false, 0}, + /* Invalid address in the second frame */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {umem_size, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + /* Invalid len in the middle */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + /* Invalid options in the middle */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XSK_DESC__INVALID_OPTION}, + /* Transmit 2 frags, receive 3 */ + {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, XDP_PKT_CONTD}, + {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, 0}, + /* Middle frame crosses chunk boundary with small length */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {-MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false, 0}, + /* Valid packet for synch so that something is received */ + {0, MIN_PKT_SIZE, 0, true, 0}}; + + if (umem->unaligned_mode) { + /* Crossing a chunk boundary allowed */ + pkts[12].valid = true; + pkts[13].valid = true; + } + + test->mtu = MAX_ETH_JUMBO_SIZE; + pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); + return testapp_validate_traffic(test); +} + +int testapp_invalid_desc(struct test_spec *test) +{ + struct xsk_umem_info *umem = test->ifobj_tx->umem; + u64 umem_size = umem->num_frames * umem->frame_size; + struct pkt pkts[] = { + /* Zero packet address allowed */ + {0, MIN_PKT_SIZE, 0, true}, + /* Allowed packet */ + {0, MIN_PKT_SIZE, 0, true}, + /* Straddling the start of umem */ + {-2, MIN_PKT_SIZE, 0, false}, + /* Packet too large */ + {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, + /* Up to end of umem allowed */ + {umem_size - MIN_PKT_SIZE - 2 * umem->frame_size, MIN_PKT_SIZE, 0, true}, + /* After umem ends */ + {umem_size, MIN_PKT_SIZE, 0, false}, + /* Straddle the end of umem */ + {umem_size - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, + /* Straddle a 4K boundary */ + {0x1000 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, + /* Straddle a 2K boundary */ + {0x800 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, true}, + /* Valid packet for synch so that something is received */ + {0, MIN_PKT_SIZE, 0, true}}; + + if (umem->unaligned_mode) { + /* Crossing a page boundary allowed */ + pkts[7].valid = true; + } + if (umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { + /* Crossing a 2K frame size boundary not allowed */ + pkts[8].valid = false; + } + + if (test->ifobj_tx->shared_umem) { + pkts[4].offset += umem_size; + pkts[5].offset += umem_size; + pkts[6].offset += umem_size; + } + + pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); + return testapp_validate_traffic(test); +} + +int testapp_xdp_drop(struct test_spec *test) +{ + struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; + struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; + + test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_drop, skel_tx->progs.xsk_xdp_drop, + skel_rx->maps.xsk, skel_tx->maps.xsk); + + pkt_stream_receive_half(test); + return testapp_validate_traffic(test); +} + +int testapp_xdp_metadata_copy(struct test_spec *test) +{ + struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; + struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; + + test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_populate_metadata, + skel_tx->progs.xsk_xdp_populate_metadata, + skel_rx->maps.xsk, skel_tx->maps.xsk); + test->ifobj_rx->use_metadata = true; + + skel_rx->bss->count = 0; + + return testapp_validate_traffic(test); +} + +int testapp_xdp_shared_umem(struct test_spec *test) +{ + struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; + struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; + + test->total_steps = 1; + test->nb_sockets = 2; + + test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_shared_umem, + skel_tx->progs.xsk_xdp_shared_umem, + skel_rx->maps.xsk, skel_tx->maps.xsk); + + pkt_stream_even_odd_sequence(test); + + return testapp_validate_traffic(test); +} + +int testapp_poll_txq_tmout(struct test_spec *test) +{ + test->ifobj_tx->use_poll = true; + /* create invalid frame by set umem frame_size and pkt length equal to 2048 */ + test->ifobj_tx->umem->frame_size = 2048; + pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048); + return testapp_validate_traffic_single_thread(test, test->ifobj_tx); +} + +int testapp_poll_rxq_tmout(struct test_spec *test) +{ + test->ifobj_rx->use_poll = true; + return testapp_validate_traffic_single_thread(test, test->ifobj_rx); +} + +int testapp_too_many_frags(struct test_spec *test) +{ + struct pkt *pkts; + u32 max_frags, i; + int ret; + + if (test->mode == TEST_MODE_ZC) { + max_frags = test->ifobj_tx->xdp_zc_max_segs; + } else { + max_frags = get_max_skb_frags(); + if (!max_frags) { + ksft_print_msg("Can't get MAX_SKB_FRAGS from system, using default (17)\n"); + max_frags = 17; + } + max_frags += 1; + } + + pkts = calloc(2 * max_frags + 2, sizeof(struct pkt)); + if (!pkts) + return TEST_FAILURE; + + test->mtu = MAX_ETH_JUMBO_SIZE; + + /* Valid packet for synch */ + pkts[0].len = MIN_PKT_SIZE; + pkts[0].valid = true; + + /* One valid packet with the max amount of frags */ + for (i = 1; i < max_frags + 1; i++) { + pkts[i].len = MIN_PKT_SIZE; + pkts[i].options = XDP_PKT_CONTD; + pkts[i].valid = true; + } + pkts[max_frags].options = 0; + + /* An invalid packet with the max amount of frags but signals packet + * continues on the last frag + */ + for (i = max_frags + 1; i < 2 * max_frags + 1; i++) { + pkts[i].len = MIN_PKT_SIZE; + pkts[i].options = XDP_PKT_CONTD; + pkts[i].valid = false; + } + + /* Valid packet for synch */ + pkts[2 * max_frags + 1].len = MIN_PKT_SIZE; + pkts[2 * max_frags + 1].valid = true; + + pkt_stream_generate_custom(test, pkts, 2 * max_frags + 2); + ret = testapp_validate_traffic(test); + + free(pkts); + return ret; +} + +static int xsk_load_xdp_programs(struct ifobject *ifobj) +{ + ifobj->xdp_progs = xsk_xdp_progs__open_and_load(); + if (libbpf_get_error(ifobj->xdp_progs)) + return libbpf_get_error(ifobj->xdp_progs); + + return 0; +} + +/* Simple test */ +static bool hugepages_present(void) +{ + size_t mmap_sz = 2 * DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE; + void *bufs; + + bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, MAP_HUGE_2MB); + if (bufs == MAP_FAILED) + return false; + + mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; + munmap(bufs, mmap_sz); + return true; +} + +void init_iface(struct ifobject *ifobj, thread_func_t func_ptr) +{ + LIBBPF_OPTS(bpf_xdp_query_opts, query_opts); + int err; + + ifobj->func_ptr = func_ptr; + + err = xsk_load_xdp_programs(ifobj); + if (err) { + ksft_print_msg("Error loading XDP program\n"); + exit_with_error(err); + } + + if (hugepages_present()) + ifobj->unaligned_supp = true; + + err = bpf_xdp_query(ifobj->ifindex, XDP_FLAGS_DRV_MODE, &query_opts); + if (err) { + ksft_print_msg("Error querying XDP capabilities\n"); + exit_with_error(-err); + } + if (query_opts.feature_flags & NETDEV_XDP_ACT_RX_SG) + ifobj->multi_buff_supp = true; + if (query_opts.feature_flags & NETDEV_XDP_ACT_XSK_ZEROCOPY) { + if (query_opts.xdp_zc_max_segs > 1) { + ifobj->multi_buff_zc_supp = true; + ifobj->xdp_zc_max_segs = query_opts.xdp_zc_max_segs; + } else { + ifobj->xdp_zc_max_segs = 0; + } + } +} + +int testapp_send_receive(struct test_spec *test) +{ + return testapp_validate_traffic(test); +} + +int testapp_send_receive_2k_frame(struct test_spec *test) +{ + test->ifobj_tx->umem->frame_size = 2048; + test->ifobj_rx->umem->frame_size = 2048; + pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE); + return testapp_validate_traffic(test); +} + +int testapp_poll_rx(struct test_spec *test) +{ + test->ifobj_rx->use_poll = true; + return testapp_validate_traffic(test); +} + +int testapp_poll_tx(struct test_spec *test) +{ + test->ifobj_tx->use_poll = true; + return testapp_validate_traffic(test); +} + +int testapp_aligned_inv_desc(struct test_spec *test) +{ + return testapp_invalid_desc(test); +} + +int testapp_aligned_inv_desc_2k_frame(struct test_spec *test) +{ + test->ifobj_tx->umem->frame_size = 2048; + test->ifobj_rx->umem->frame_size = 2048; + return testapp_invalid_desc(test); +} + +int testapp_unaligned_inv_desc(struct test_spec *test) +{ + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + return testapp_invalid_desc(test); +} + +int testapp_unaligned_inv_desc_4001_frame(struct test_spec *test) +{ + u64 page_size, umem_size; + + /* Odd frame size so the UMEM doesn't end near a page boundary. */ + test->ifobj_tx->umem->frame_size = 4001; + test->ifobj_rx->umem->frame_size = 4001; + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + /* This test exists to test descriptors that staddle the end of + * the UMEM but not a page. + */ + page_size = sysconf(_SC_PAGESIZE); + umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size; + assert(umem_size % page_size > MIN_PKT_SIZE); + assert(umem_size % page_size < page_size - MIN_PKT_SIZE); + + return testapp_invalid_desc(test); +} + +int testapp_aligned_inv_desc_mb(struct test_spec *test) +{ + return testapp_invalid_desc_mb(test); +} + +int testapp_unaligned_inv_desc_mb(struct test_spec *test) +{ + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + return testapp_invalid_desc_mb(test); +} + +int testapp_xdp_metadata(struct test_spec *test) +{ + return testapp_xdp_metadata_copy(test); +} + +int testapp_xdp_metadata_mb(struct test_spec *test) +{ + test->mtu = MAX_ETH_JUMBO_SIZE; + return testapp_xdp_metadata_copy(test); +} + +int testapp_hw_sw_min_ring_size(struct test_spec *test) +{ + int ret; + + test->set_ring = true; + test->total_steps = 2; + test->ifobj_tx->ring.tx_pending = DEFAULT_BATCH_SIZE; + test->ifobj_tx->ring.rx_pending = DEFAULT_BATCH_SIZE * 2; + test->ifobj_tx->xsk->batch_size = 1; + test->ifobj_rx->xsk->batch_size = 1; + ret = testapp_validate_traffic(test); + if (ret) + return ret; + + /* Set batch size to hw_ring_size - 1 */ + test->ifobj_tx->xsk->batch_size = DEFAULT_BATCH_SIZE - 1; + test->ifobj_rx->xsk->batch_size = DEFAULT_BATCH_SIZE - 1; + return testapp_validate_traffic(test); +} + +int testapp_hw_sw_max_ring_size(struct test_spec *test) +{ + u32 max_descs = XSK_RING_PROD__DEFAULT_NUM_DESCS * 4; + int ret; + + test->set_ring = true; + test->total_steps = 2; + test->ifobj_tx->ring.tx_pending = test->ifobj_tx->ring.tx_max_pending; + test->ifobj_tx->ring.rx_pending = test->ifobj_tx->ring.rx_max_pending; + test->ifobj_rx->umem->num_frames = max_descs; + test->ifobj_rx->umem->fill_size = max_descs; + test->ifobj_rx->umem->comp_size = max_descs; + test->ifobj_tx->xsk->batch_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; + test->ifobj_rx->xsk->batch_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; + + ret = testapp_validate_traffic(test); + if (ret) + return ret; + + /* Set batch_size to 8152 for testing, as the ice HW ignores the 3 lowest bits when + * updating the Rx HW tail register. + */ + test->ifobj_tx->xsk->batch_size = test->ifobj_tx->ring.tx_max_pending - 8; + test->ifobj_rx->xsk->batch_size = test->ifobj_tx->ring.tx_max_pending - 8; + pkt_stream_replace(test, max_descs, MIN_PKT_SIZE); + return testapp_validate_traffic(test); +} + +static int testapp_xdp_adjust_tail(struct test_spec *test, int adjust_value) +{ + struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; + struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; + + test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_adjust_tail, + skel_tx->progs.xsk_xdp_adjust_tail, + skel_rx->maps.xsk, skel_tx->maps.xsk); + + skel_rx->bss->adjust_value = adjust_value; + + return testapp_validate_traffic(test); +} + +static int testapp_adjust_tail(struct test_spec *test, u32 value, u32 pkt_len) +{ + int ret; + + test->adjust_tail_support = true; + test->adjust_tail = true; + test->total_steps = 1; + + pkt_stream_replace_ifobject(test->ifobj_tx, DEFAULT_BATCH_SIZE, pkt_len); + pkt_stream_replace_ifobject(test->ifobj_rx, DEFAULT_BATCH_SIZE, pkt_len + value); + + ret = testapp_xdp_adjust_tail(test, value); + if (ret) + return ret; + + if (!test->adjust_tail_support) { + ksft_print_msg("%s %sResize pkt with bpf_xdp_adjust_tail() not supported\n", + mode_string(test), busy_poll_string(test)); + return TEST_SKIP; + } + + return 0; +} + +int testapp_adjust_tail_shrink(struct test_spec *test) +{ + /* Shrink by 4 bytes for testing purpose */ + return testapp_adjust_tail(test, -4, MIN_PKT_SIZE * 2); +} + +int testapp_adjust_tail_shrink_mb(struct test_spec *test) +{ + test->mtu = MAX_ETH_JUMBO_SIZE; + /* Shrink by the frag size */ + return testapp_adjust_tail(test, -XSK_UMEM__MAX_FRAME_SIZE, XSK_UMEM__LARGE_FRAME_SIZE * 2); +} + +int testapp_adjust_tail_grow(struct test_spec *test) +{ + /* Grow by 4 bytes for testing purpose */ + return testapp_adjust_tail(test, 4, MIN_PKT_SIZE * 2); +} + +int testapp_adjust_tail_grow_mb(struct test_spec *test) +{ + test->mtu = MAX_ETH_JUMBO_SIZE; + /* Grow by (frag_size - last_frag_Size) - 1 to stay inside the last fragment */ + return testapp_adjust_tail(test, (XSK_UMEM__MAX_FRAME_SIZE / 2) - 1, + XSK_UMEM__LARGE_FRAME_SIZE * 2); +} + +int testapp_tx_queue_consumer(struct test_spec *test) +{ + int nr_packets; + + if (test->mode == TEST_MODE_ZC) { + ksft_print_msg("Can not run TX_QUEUE_CONSUMER test for ZC mode\n"); + return TEST_SKIP; + } + + nr_packets = MAX_TX_BUDGET_DEFAULT + 1; + pkt_stream_replace(test, nr_packets, MIN_PKT_SIZE); + test->ifobj_tx->xsk->batch_size = nr_packets; + test->ifobj_tx->xsk->check_consumer = true; + + return testapp_validate_traffic(test); +} + +struct ifobject *ifobject_create(void) +{ + struct ifobject *ifobj; + + ifobj = calloc(1, sizeof(struct ifobject)); + if (!ifobj) + return NULL; + + ifobj->xsk_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->xsk_arr)); + if (!ifobj->xsk_arr) + goto out_xsk_arr; + + ifobj->umem = calloc(1, sizeof(*ifobj->umem)); + if (!ifobj->umem) + goto out_umem; + + return ifobj; + +out_umem: + free(ifobj->xsk_arr); +out_xsk_arr: + free(ifobj); + return NULL; +} + +void ifobject_delete(struct ifobject *ifobj) +{ + free(ifobj->umem); + free(ifobj->xsk_arr); + free(ifobj); +} diff --git a/tools/testing/selftests/bpf/test_xsk.h b/tools/testing/selftests/bpf/test_xsk.h new file mode 100644 index 00000000000000..fb546cab39fdfb --- /dev/null +++ b/tools/testing/selftests/bpf/test_xsk.h @@ -0,0 +1,297 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef TEST_XSK_H_ +#define TEST_XSK_H_ + +#include +#include + +#include "../kselftest.h" +#include "xsk.h" + +#ifndef SO_PREFER_BUSY_POLL +#define SO_PREFER_BUSY_POLL 69 +#endif + +#ifndef SO_BUSY_POLL_BUDGET +#define SO_BUSY_POLL_BUDGET 70 +#endif + +#define TEST_PASS 0 +#define TEST_FAILURE -1 +#define TEST_CONTINUE 1 +#define TEST_SKIP 2 + +#define DEFAULT_PKT_CNT (4 * 1024) +#define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4) +#define HUGEPAGE_SIZE (2 * 1024 * 1024) +#define MIN_PKT_SIZE 64 +#define MAX_ETH_PKT_SIZE 1518 +#define MAX_INTERFACE_NAME_CHARS 16 +#define MAX_TEST_NAME_SIZE 48 +#define SOCK_RECONF_CTR 10 +#define USLEEP_MAX 10000 + +extern bool opt_verbose; +#define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0) + +static void __exit_with_error(int error, const char *file, const char *func, int line) +{ + ksft_test_result_fail("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, error, + strerror(error)); + ksft_exit_xfail(); +} +#define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__) + +static inline u32 ceil_u32(u32 a, u32 b) +{ + return (a + b - 1) / b; +} + +static inline u64 ceil_u64(u64 a, u64 b) +{ + return (a + b - 1) / b; +} + +/* Simple test */ +enum test_mode { + TEST_MODE_SKB, + TEST_MODE_DRV, + TEST_MODE_ZC, + TEST_MODE_ALL +}; + +struct ifobject; +struct test_spec; +typedef int (*validation_func_t)(struct ifobject *ifobj); +typedef void *(*thread_func_t)(void *arg); +typedef int (*test_func_t)(struct test_spec *test); + +struct xsk_socket_info { + struct xsk_ring_cons rx; + struct xsk_ring_prod tx; + struct xsk_umem_info *umem; + struct xsk_socket *xsk; + struct pkt_stream *pkt_stream; + u32 outstanding_tx; + u32 rxqsize; + u32 batch_size; + u8 dst_mac[ETH_ALEN]; + u8 src_mac[ETH_ALEN]; + bool check_consumer; +}; + +int kick_rx(struct xsk_socket_info *xsk); +int kick_tx(struct xsk_socket_info *xsk); + +struct xsk_umem_info { + struct xsk_ring_prod fq; + struct xsk_ring_cons cq; + struct xsk_umem *umem; + u64 next_buffer; + u32 num_frames; + u32 frame_headroom; + void *buffer; + u32 frame_size; + u32 base_addr; + u32 fill_size; + u32 comp_size; + bool unaligned_mode; +}; + +struct set_hw_ring { + u32 default_tx; + u32 default_rx; +}; + +int hw_ring_size_reset(struct ifobject *ifobj); + +struct ifobject { + char ifname[MAX_INTERFACE_NAME_CHARS]; + struct xsk_socket_info *xsk; + struct xsk_socket_info *xsk_arr; + struct xsk_umem_info *umem; + thread_func_t func_ptr; + validation_func_t validation_func; + struct xsk_xdp_progs *xdp_progs; + struct bpf_map *xskmap; + struct bpf_program *xdp_prog; + struct ethtool_ringparam ring; + struct set_hw_ring set_ring; + enum test_mode mode; + int ifindex; + int mtu; + u32 bind_flags; + u32 xdp_zc_max_segs; + bool tx_on; + bool rx_on; + bool use_poll; + bool busy_poll; + bool use_fill_ring; + bool release_rx; + bool shared_umem; + bool use_metadata; + bool unaligned_supp; + bool multi_buff_supp; + bool multi_buff_zc_supp; + bool hw_ring_size_supp; +}; +struct ifobject *ifobject_create(void); +void ifobject_delete(struct ifobject *ifobj); +void init_iface(struct ifobject *ifobj, thread_func_t func_ptr); + +int xsk_configure_umem(struct ifobject *ifobj, struct xsk_umem_info *umem, void *buffer, u64 size); +int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, + struct ifobject *ifobject, bool shared); + + +struct pkt { + int offset; + u32 len; + u32 pkt_nb; + bool valid; + u16 options; +}; + +struct pkt_stream { + u32 nb_pkts; + u32 current_pkt_nb; + struct pkt *pkts; + u32 max_pkt_len; + u32 nb_rx_pkts; + u32 nb_valid_entries; + bool verbatim; +}; + +static inline bool pkt_continues(u32 options) +{ + return options & XDP_PKT_CONTD; +} + +struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len); +void pkt_stream_delete(struct pkt_stream *pkt_stream); +void pkt_stream_reset(struct pkt_stream *pkt_stream); +void pkt_stream_restore_default(struct test_spec *test); + +struct test_spec { + struct ifobject *ifobj_tx; + struct ifobject *ifobj_rx; + struct pkt_stream *tx_pkt_stream_default; + struct pkt_stream *rx_pkt_stream_default; + struct bpf_program *xdp_prog_rx; + struct bpf_program *xdp_prog_tx; + struct bpf_map *xskmap_rx; + struct bpf_map *xskmap_tx; + test_func_t test_func; + int mtu; + u16 total_steps; + u16 current_step; + u16 nb_sockets; + bool fail; + bool set_ring; + bool adjust_tail; + bool adjust_tail_support; + enum test_mode mode; + char name[MAX_TEST_NAME_SIZE]; +}; + +#define busy_poll_string(test) (test)->ifobj_tx->busy_poll ? "BUSY-POLL " : "" +static inline char *mode_string(struct test_spec *test) +{ + switch (test->mode) { + case TEST_MODE_SKB: + return "SKB"; + case TEST_MODE_DRV: + return "DRV"; + case TEST_MODE_ZC: + return "ZC"; + default: + return "BOGUS"; + } +} + +void test_init(struct test_spec *test, struct ifobject *ifobj_tx, + struct ifobject *ifobj_rx, enum test_mode mode, + const struct test_spec *test_to_run); + +int testapp_adjust_tail_grow(struct test_spec *test); +int testapp_adjust_tail_grow_mb(struct test_spec *test); +int testapp_adjust_tail_shrink(struct test_spec *test); +int testapp_adjust_tail_shrink_mb(struct test_spec *test); +int testapp_aligned_inv_desc(struct test_spec *test); +int testapp_aligned_inv_desc_2k_frame(struct test_spec *test); +int testapp_aligned_inv_desc_mb(struct test_spec *test); +int testapp_bidirectional(struct test_spec *test); +int testapp_headroom(struct test_spec *test); +int testapp_hw_sw_max_ring_size(struct test_spec *test); +int testapp_hw_sw_min_ring_size(struct test_spec *test); +int testapp_poll_rx(struct test_spec *test); +int testapp_poll_rxq_tmout(struct test_spec *test); +int testapp_poll_tx(struct test_spec *test); +int testapp_poll_txq_tmout(struct test_spec *test); +int testapp_send_receive(struct test_spec *test); +int testapp_send_receive_2k_frame(struct test_spec *test); +int testapp_send_receive_mb(struct test_spec *test); +int testapp_send_receive_unaligned(struct test_spec *test); +int testapp_send_receive_unaligned_mb(struct test_spec *test); +int testapp_single_pkt(struct test_spec *test); +int testapp_stats_fill_empty(struct test_spec *test); +int testapp_stats_rx_dropped(struct test_spec *test); +int testapp_stats_tx_invalid_descs(struct test_spec *test); +int testapp_stats_rx_full(struct test_spec *test); +int testapp_teardown(struct test_spec *test); +int testapp_too_many_frags(struct test_spec *test); +int testapp_tx_queue_consumer(struct test_spec *test); +int testapp_unaligned_inv_desc(struct test_spec *test); +int testapp_unaligned_inv_desc_4001_frame(struct test_spec *test); +int testapp_unaligned_inv_desc_mb(struct test_spec *test); +int testapp_xdp_drop(struct test_spec *test); +int testapp_xdp_metadata(struct test_spec *test); +int testapp_xdp_metadata_mb(struct test_spec *test); +int testapp_xdp_prog_cleanup(struct test_spec *test); +int testapp_xdp_shared_umem(struct test_spec *test); + +void *worker_testapp_validate_rx(void *arg); +void *worker_testapp_validate_tx(void *arg); + +static const struct test_spec tests[] = { + {.name = "SEND_RECEIVE", .test_func = testapp_send_receive}, + {.name = "SEND_RECEIVE_2K_FRAME", .test_func = testapp_send_receive_2k_frame}, + {.name = "SEND_RECEIVE_SINGLE_PKT", .test_func = testapp_single_pkt}, + {.name = "POLL_RX", .test_func = testapp_poll_rx}, + {.name = "POLL_TX", .test_func = testapp_poll_tx}, + {.name = "POLL_RXQ_FULL", .test_func = testapp_poll_rxq_tmout}, + {.name = "POLL_TXQ_FULL", .test_func = testapp_poll_txq_tmout}, + {.name = "SEND_RECEIVE_UNALIGNED", .test_func = testapp_send_receive_unaligned}, + {.name = "ALIGNED_INV_DESC", .test_func = testapp_aligned_inv_desc}, + {.name = "ALIGNED_INV_DESC_2K_FRAME_SIZE", .test_func = testapp_aligned_inv_desc_2k_frame}, + {.name = "UNALIGNED_INV_DESC", .test_func = testapp_unaligned_inv_desc}, + {.name = "UNALIGNED_INV_DESC_4001_FRAME_SIZE", + .test_func = testapp_unaligned_inv_desc_4001_frame}, + {.name = "UMEM_HEADROOM", .test_func = testapp_headroom}, + {.name = "TEARDOWN", .test_func = testapp_teardown}, + {.name = "BIDIRECTIONAL", .test_func = testapp_bidirectional}, + {.name = "STAT_RX_DROPPED", .test_func = testapp_stats_rx_dropped}, + {.name = "STAT_TX_INVALID", .test_func = testapp_stats_tx_invalid_descs}, + {.name = "STAT_RX_FULL", .test_func = testapp_stats_rx_full}, + {.name = "STAT_FILL_EMPTY", .test_func = testapp_stats_fill_empty}, + {.name = "XDP_PROG_CLEANUP", .test_func = testapp_xdp_prog_cleanup}, + {.name = "XDP_DROP_HALF", .test_func = testapp_xdp_drop}, + {.name = "XDP_SHARED_UMEM", .test_func = testapp_xdp_shared_umem}, + {.name = "XDP_METADATA_COPY", .test_func = testapp_xdp_metadata}, + {.name = "XDP_METADATA_COPY_MULTI_BUFF", .test_func = testapp_xdp_metadata_mb}, + {.name = "SEND_RECEIVE_9K_PACKETS", .test_func = testapp_send_receive_mb}, + {.name = "SEND_RECEIVE_UNALIGNED_9K_PACKETS", + .test_func = testapp_send_receive_unaligned_mb}, + {.name = "ALIGNED_INV_DESC_MULTI_BUFF", .test_func = testapp_aligned_inv_desc_mb}, + {.name = "UNALIGNED_INV_DESC_MULTI_BUFF", .test_func = testapp_unaligned_inv_desc_mb}, + {.name = "TOO_MANY_FRAGS", .test_func = testapp_too_many_frags}, + {.name = "HW_SW_MIN_RING_SIZE", .test_func = testapp_hw_sw_min_ring_size}, + {.name = "HW_SW_MAX_RING_SIZE", .test_func = testapp_hw_sw_max_ring_size}, + {.name = "XDP_ADJUST_TAIL_SHRINK", .test_func = testapp_adjust_tail_shrink}, + {.name = "XDP_ADJUST_TAIL_SHRINK_MULTI_BUFF", .test_func = testapp_adjust_tail_shrink_mb}, + {.name = "XDP_ADJUST_TAIL_GROW", .test_func = testapp_adjust_tail_grow}, + {.name = "XDP_ADJUST_TAIL_GROW_MULTI_BUFF", .test_func = testapp_adjust_tail_grow_mb}, + {.name = "TX_QUEUE_CONSUMER", .test_func = testapp_tx_queue_consumer}, + }; + +#endif /* TEST_XSK_H_ */ diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index e962f133250c7d..1be1e353d40a7b 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -2580,7 +2580,7 @@ static void output_stats(const struct verif_stats *s, enum resfmt fmt, bool last if (last && fmt == RESFMT_TABLE) { output_header_underlines(); printf("Done. Processed %d files, %d programs. Skipped %d files, %d programs.\n", - env.files_processed, env.files_skipped, env.progs_processed, env.progs_skipped); + env.files_processed, env.progs_processed, env.files_skipped, env.progs_skipped); } } diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index 352adc8df2d1cd..8e108e3162695d 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -74,31 +74,23 @@ #define _GNU_SOURCE #include #include -#include #include #include #include #include #include -#include #include #include #include #include -#include -#include -#include #include #include #include -#include #include #include -#include -#include #include -#include +#include "test_xsk.h" #include "xsk_xdp_progs.skel.h" #include "xsk.h" #include "xskxceiver.h" @@ -109,181 +101,12 @@ #include -#define MAX_TX_BUDGET_DEFAULT 32 - -static bool opt_verbose; static bool opt_print_tests; static enum test_mode opt_mode = TEST_MODE_ALL; static u32 opt_run_test = RUN_ALL_TESTS; void test__fail(void) { /* for network_helpers.c */ } -static void __exit_with_error(int error, const char *file, const char *func, int line) -{ - ksft_test_result_fail("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, error, - strerror(error)); - ksft_exit_xfail(); -} - -#define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__) -#define busy_poll_string(test) (test)->ifobj_tx->busy_poll ? "BUSY-POLL " : "" -static char *mode_string(struct test_spec *test) -{ - switch (test->mode) { - case TEST_MODE_SKB: - return "SKB"; - case TEST_MODE_DRV: - return "DRV"; - case TEST_MODE_ZC: - return "ZC"; - default: - return "BOGUS"; - } -} - -static void report_failure(struct test_spec *test) -{ - if (test->fail) - return; - - ksft_test_result_fail("FAIL: %s %s%s\n", mode_string(test), busy_poll_string(test), - test->name); - test->fail = true; -} - -/* The payload is a word consisting of a packet sequence number in the upper - * 16-bits and a intra packet data sequence number in the lower 16 bits. So the 3rd packet's - * 5th word of data will contain the number (2<<16) | 4 as they are numbered from 0. - */ -static void write_payload(void *dest, u32 pkt_nb, u32 start, u32 size) -{ - u32 *ptr = (u32 *)dest, i; - - start /= sizeof(*ptr); - size /= sizeof(*ptr); - for (i = 0; i < size; i++) - ptr[i] = htonl(pkt_nb << 16 | (i + start)); -} - -static void gen_eth_hdr(struct xsk_socket_info *xsk, struct ethhdr *eth_hdr) -{ - memcpy(eth_hdr->h_dest, xsk->dst_mac, ETH_ALEN); - memcpy(eth_hdr->h_source, xsk->src_mac, ETH_ALEN); - eth_hdr->h_proto = htons(ETH_P_LOOPBACK); -} - -static bool is_umem_valid(struct ifobject *ifobj) -{ - return !!ifobj->umem->umem; -} - -static u32 mode_to_xdp_flags(enum test_mode mode) -{ - return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; -} - -static u64 umem_size(struct xsk_umem_info *umem) -{ - return umem->num_frames * umem->frame_size; -} - -static int xsk_configure_umem(struct ifobject *ifobj, struct xsk_umem_info *umem, void *buffer, - u64 size) -{ - struct xsk_umem_config cfg = { - .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, - .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, - .frame_size = umem->frame_size, - .frame_headroom = umem->frame_headroom, - .flags = XSK_UMEM__DEFAULT_FLAGS - }; - int ret; - - if (umem->fill_size) - cfg.fill_size = umem->fill_size; - - if (umem->comp_size) - cfg.comp_size = umem->comp_size; - - if (umem->unaligned_mode) - cfg.flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG; - - ret = xsk_umem__create(&umem->umem, buffer, size, - &umem->fq, &umem->cq, &cfg); - if (ret) - return ret; - - umem->buffer = buffer; - if (ifobj->shared_umem && ifobj->rx_on) { - umem->base_addr = umem_size(umem); - umem->next_buffer = umem_size(umem); - } - - return 0; -} - -static u64 umem_alloc_buffer(struct xsk_umem_info *umem) -{ - u64 addr; - - addr = umem->next_buffer; - umem->next_buffer += umem->frame_size; - if (umem->next_buffer >= umem->base_addr + umem_size(umem)) - umem->next_buffer = umem->base_addr; - - return addr; -} - -static void umem_reset_alloc(struct xsk_umem_info *umem) -{ - umem->next_buffer = 0; -} - -static void enable_busy_poll(struct xsk_socket_info *xsk) -{ - int sock_opt; - - sock_opt = 1; - if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_PREFER_BUSY_POLL, - (void *)&sock_opt, sizeof(sock_opt)) < 0) - exit_with_error(errno); - - sock_opt = 20; - if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL, - (void *)&sock_opt, sizeof(sock_opt)) < 0) - exit_with_error(errno); - - sock_opt = xsk->batch_size; - if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL_BUDGET, - (void *)&sock_opt, sizeof(sock_opt)) < 0) - exit_with_error(errno); -} - -static int __xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, - struct ifobject *ifobject, bool shared) -{ - struct xsk_socket_config cfg = {}; - struct xsk_ring_cons *rxr; - struct xsk_ring_prod *txr; - - xsk->umem = umem; - cfg.rx_size = xsk->rxqsize; - cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - cfg.bind_flags = ifobject->bind_flags; - if (shared) - cfg.bind_flags |= XDP_SHARED_UMEM; - if (ifobject->mtu > MAX_ETH_PKT_SIZE) - cfg.bind_flags |= XDP_USE_SG; - if (umem->comp_size) - cfg.tx_size = umem->comp_size; - if (umem->fill_size) - cfg.rx_size = umem->fill_size; - - txr = ifobject->tx_on ? &xsk->tx : NULL; - rxr = ifobject->rx_on ? &xsk->rx : NULL; - return xsk_socket__create(&xsk->xsk, ifobject->ifindex, 0, umem->umem, rxr, txr, &cfg); -} - static bool ifobj_zc_avail(struct ifobject *ifobject) { size_t umem_sz = DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE; @@ -314,7 +137,7 @@ static bool ifobj_zc_avail(struct ifobject *ifobject) ifobject->bind_flags = XDP_USE_NEED_WAKEUP | XDP_ZEROCOPY; ifobject->rx_on = true; xsk->rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; - ret = __xsk_configure_socket(xsk, umem, ifobject, false); + ret = xsk_configure_socket(xsk, umem, ifobject, false); if (!ret) zc_avail = true; @@ -327,25 +150,6 @@ static bool ifobj_zc_avail(struct ifobject *ifobject) return zc_avail; } -#define MAX_SKB_FRAGS_PATH "/proc/sys/net/core/max_skb_frags" -static unsigned int get_max_skb_frags(void) -{ - unsigned int max_skb_frags = 0; - FILE *file; - - file = fopen(MAX_SKB_FRAGS_PATH, "r"); - if (!file) { - ksft_print_msg("Error opening %s\n", MAX_SKB_FRAGS_PATH); - return 0; - } - - if (fscanf(file, "%u", &max_skb_frags) != 1) - ksft_print_msg("Error reading %s\n", MAX_SKB_FRAGS_PATH); - - fclose(file); - return max_skb_frags; -} - static struct option long_options[] = { {"interface", required_argument, 0, 'i'}, {"busy-poll", no_argument, 0, 'b'}, @@ -446,2327 +250,66 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj } } -static int set_ring_size(struct ifobject *ifobj) -{ - int ret; - u32 ctr = 0; - - while (ctr++ < SOCK_RECONF_CTR) { - ret = set_hw_ring_size(ifobj->ifname, &ifobj->ring); - if (!ret) - break; - - /* Retry if it fails */ - if (ctr >= SOCK_RECONF_CTR || errno != EBUSY) - return -errno; - - usleep(USLEEP_MAX); - } - - return ret; -} - -static int hw_ring_size_reset(struct ifobject *ifobj) -{ - ifobj->ring.tx_pending = ifobj->set_ring.default_tx; - ifobj->ring.rx_pending = ifobj->set_ring.default_rx; - return set_ring_size(ifobj); -} - -static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, - struct ifobject *ifobj_rx) +static void xsk_unload_xdp_programs(struct ifobject *ifobj) { - u32 i, j; - - for (i = 0; i < MAX_INTERFACES; i++) { - struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; - - ifobj->xsk = &ifobj->xsk_arr[0]; - ifobj->use_poll = false; - ifobj->use_fill_ring = true; - ifobj->release_rx = true; - ifobj->validation_func = NULL; - ifobj->use_metadata = false; - - if (i == 0) { - ifobj->rx_on = false; - ifobj->tx_on = true; - } else { - ifobj->rx_on = true; - ifobj->tx_on = false; - } - - memset(ifobj->umem, 0, sizeof(*ifobj->umem)); - ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS; - ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; - - for (j = 0; j < MAX_SOCKETS; j++) { - memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j])); - ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; - ifobj->xsk_arr[j].batch_size = DEFAULT_BATCH_SIZE; - if (i == 0) - ifobj->xsk_arr[j].pkt_stream = test->tx_pkt_stream_default; - else - ifobj->xsk_arr[j].pkt_stream = test->rx_pkt_stream_default; - - memcpy(ifobj->xsk_arr[j].src_mac, g_mac, ETH_ALEN); - memcpy(ifobj->xsk_arr[j].dst_mac, g_mac, ETH_ALEN); - ifobj->xsk_arr[j].src_mac[5] += ((j * 2) + 0); - ifobj->xsk_arr[j].dst_mac[5] += ((j * 2) + 1); - } - } - - if (ifobj_tx->hw_ring_size_supp) - hw_ring_size_reset(ifobj_tx); - - test->ifobj_tx = ifobj_tx; - test->ifobj_rx = ifobj_rx; - test->current_step = 0; - test->total_steps = 1; - test->nb_sockets = 1; - test->fail = false; - test->set_ring = false; - test->adjust_tail = false; - test->adjust_tail_support = false; - test->mtu = MAX_ETH_PKT_SIZE; - test->xdp_prog_rx = ifobj_rx->xdp_progs->progs.xsk_def_prog; - test->xskmap_rx = ifobj_rx->xdp_progs->maps.xsk; - test->xdp_prog_tx = ifobj_tx->xdp_progs->progs.xsk_def_prog; - test->xskmap_tx = ifobj_tx->xdp_progs->maps.xsk; + xsk_xdp_progs__destroy(ifobj->xdp_progs); } -static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, - struct ifobject *ifobj_rx, enum test_mode mode, - const struct test_spec *test_to_run) +static void run_pkt_test(struct test_spec *test) { - struct pkt_stream *tx_pkt_stream; - struct pkt_stream *rx_pkt_stream; - u32 i; - - tx_pkt_stream = test->tx_pkt_stream_default; - rx_pkt_stream = test->rx_pkt_stream_default; - memset(test, 0, sizeof(*test)); - test->tx_pkt_stream_default = tx_pkt_stream; - test->rx_pkt_stream_default = rx_pkt_stream; + int ret; - for (i = 0; i < MAX_INTERFACES; i++) { - struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; + ret = test->test_func(test); - ifobj->bind_flags = XDP_USE_NEED_WAKEUP; - if (mode == TEST_MODE_ZC) - ifobj->bind_flags |= XDP_ZEROCOPY; - else - ifobj->bind_flags |= XDP_COPY; + switch (ret) { + case TEST_PASS: + ksft_test_result_pass("PASS: %s %s%s\n", mode_string(test), busy_poll_string(test), + test->name); + break; + case TEST_SKIP: + ksft_test_result_skip("SKIP: %s %s%s\n", mode_string(test), busy_poll_string(test), + test->name); + break; + case TEST_FAILURE: + ksft_test_result_fail("FAIL: %s %s%s\n", mode_string(test), busy_poll_string(test), + test->name); + break; + default: + ksft_test_result_fail("FAIL: %s %s%s -- Unexpected returned value (%d)\n", + mode_string(test), busy_poll_string(test), test->name, ret); } - strncpy(test->name, test_to_run->name, MAX_TEST_NAME_SIZE); - test->test_func = test_to_run->test_func; - test->mode = mode; - __test_spec_init(test, ifobj_tx, ifobj_rx); -} - -static void test_spec_reset(struct test_spec *test) -{ - __test_spec_init(test, test->ifobj_tx, test->ifobj_rx); + pkt_stream_restore_default(test); } -static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *xdp_prog_rx, - struct bpf_program *xdp_prog_tx, struct bpf_map *xskmap_rx, - struct bpf_map *xskmap_tx) +static bool is_xdp_supported(int ifindex) { - test->xdp_prog_rx = xdp_prog_rx; - test->xdp_prog_tx = xdp_prog_tx; - test->xskmap_rx = xskmap_rx; - test->xskmap_tx = xskmap_tx; -} + int flags = XDP_FLAGS_DRV_MODE; -static int test_spec_set_mtu(struct test_spec *test, int mtu) -{ + LIBBPF_OPTS(bpf_link_create_opts, opts, .flags = flags); + struct bpf_insn insns[2] = { + BPF_MOV64_IMM(BPF_REG_0, XDP_PASS), + BPF_EXIT_INSN() + }; + int prog_fd, insn_cnt = ARRAY_SIZE(insns); int err; - if (test->ifobj_rx->mtu != mtu) { - err = xsk_set_mtu(test->ifobj_rx->ifindex, mtu); - if (err) - return err; - test->ifobj_rx->mtu = mtu; - } - if (test->ifobj_tx->mtu != mtu) { - err = xsk_set_mtu(test->ifobj_tx->ifindex, mtu); - if (err) - return err; - test->ifobj_tx->mtu = mtu; - } - - return 0; -} - -static void pkt_stream_reset(struct pkt_stream *pkt_stream) -{ - if (pkt_stream) { - pkt_stream->current_pkt_nb = 0; - pkt_stream->nb_rx_pkts = 0; - } -} - -static struct pkt *pkt_stream_get_next_tx_pkt(struct pkt_stream *pkt_stream) -{ - if (pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) - return NULL; - - return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; -} - -static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream, u32 *pkts_sent) -{ - while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) { - (*pkts_sent)++; - if (pkt_stream->pkts[pkt_stream->current_pkt_nb].valid) - return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; - pkt_stream->current_pkt_nb++; - } - return NULL; -} - -static void pkt_stream_delete(struct pkt_stream *pkt_stream) -{ - free(pkt_stream->pkts); - free(pkt_stream); -} - -static void pkt_stream_restore_default(struct test_spec *test) -{ - struct pkt_stream *tx_pkt_stream = test->ifobj_tx->xsk->pkt_stream; - struct pkt_stream *rx_pkt_stream = test->ifobj_rx->xsk->pkt_stream; - - if (tx_pkt_stream != test->tx_pkt_stream_default) { - pkt_stream_delete(test->ifobj_tx->xsk->pkt_stream); - test->ifobj_tx->xsk->pkt_stream = test->tx_pkt_stream_default; - } - - if (rx_pkt_stream != test->rx_pkt_stream_default) { - pkt_stream_delete(test->ifobj_rx->xsk->pkt_stream); - test->ifobj_rx->xsk->pkt_stream = test->rx_pkt_stream_default; - } -} - -static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts) -{ - struct pkt_stream *pkt_stream; - - pkt_stream = calloc(1, sizeof(*pkt_stream)); - if (!pkt_stream) - return NULL; - - pkt_stream->pkts = calloc(nb_pkts, sizeof(*pkt_stream->pkts)); - if (!pkt_stream->pkts) { - free(pkt_stream); - return NULL; - } - - pkt_stream->nb_pkts = nb_pkts; - return pkt_stream; -} - -static bool pkt_continues(u32 options) -{ - return options & XDP_PKT_CONTD; -} - -static u32 ceil_u32(u32 a, u32 b) -{ - return (a + b - 1) / b; -} - -static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pkt *pkt) -{ - u32 nb_frags = 1, next_frag; - - if (!pkt) - return 1; - - if (!pkt_stream->verbatim) { - if (!pkt->valid || !pkt->len) - return 1; - return ceil_u32(pkt->len, frame_size); - } - - /* Search for the end of the packet in verbatim mode */ - if (!pkt_continues(pkt->options)) - return nb_frags; - - next_frag = pkt_stream->current_pkt_nb; - pkt++; - while (next_frag++ < pkt_stream->nb_pkts) { - nb_frags++; - if (!pkt_continues(pkt->options) || !pkt->valid) - break; - pkt++; - } - return nb_frags; -} - -static bool set_pkt_valid(int offset, u32 len) -{ - return len <= MAX_ETH_JUMBO_SIZE; -} - -static void pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len) -{ - pkt->offset = offset; - pkt->len = len; - pkt->valid = set_pkt_valid(offset, len); -} - -static void pkt_stream_pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len) -{ - bool prev_pkt_valid = pkt->valid; - - pkt_set(pkt_stream, pkt, offset, len); - pkt_stream->nb_valid_entries += pkt->valid - prev_pkt_valid; -} - -static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len) -{ - return ceil_u32(len, umem->frame_size) * umem->frame_size; -} - -static struct pkt_stream *__pkt_stream_generate(u32 nb_pkts, u32 pkt_len, u32 nb_start, u32 nb_off) -{ - struct pkt_stream *pkt_stream; - u32 i; - - pkt_stream = __pkt_stream_alloc(nb_pkts); - if (!pkt_stream) - exit_with_error(ENOMEM); - - pkt_stream->nb_pkts = nb_pkts; - pkt_stream->max_pkt_len = pkt_len; - for (i = 0; i < nb_pkts; i++) { - struct pkt *pkt = &pkt_stream->pkts[i]; - - pkt_stream_pkt_set(pkt_stream, pkt, 0, pkt_len); - pkt->pkt_nb = nb_start + i * nb_off; - } - - return pkt_stream; -} - -static struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len) -{ - return __pkt_stream_generate(nb_pkts, pkt_len, 0, 1); -} - -static struct pkt_stream *pkt_stream_clone(struct pkt_stream *pkt_stream) -{ - return pkt_stream_generate(pkt_stream->nb_pkts, pkt_stream->pkts[0].len); -} - -static void pkt_stream_replace_ifobject(struct ifobject *ifobj, u32 nb_pkts, u32 pkt_len) -{ - ifobj->xsk->pkt_stream = pkt_stream_generate(nb_pkts, pkt_len); -} - -static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len) -{ - pkt_stream_replace_ifobject(test->ifobj_tx, nb_pkts, pkt_len); - pkt_stream_replace_ifobject(test->ifobj_rx, nb_pkts, pkt_len); -} - -static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len, - int offset) -{ - struct pkt_stream *pkt_stream; - u32 i; - - pkt_stream = pkt_stream_clone(ifobj->xsk->pkt_stream); - for (i = 1; i < ifobj->xsk->pkt_stream->nb_pkts; i += 2) - pkt_stream_pkt_set(pkt_stream, &pkt_stream->pkts[i], offset, pkt_len); - - ifobj->xsk->pkt_stream = pkt_stream; -} - -static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset) -{ - __pkt_stream_replace_half(test->ifobj_tx, pkt_len, offset); - __pkt_stream_replace_half(test->ifobj_rx, pkt_len, offset); -} - -static void pkt_stream_receive_half(struct test_spec *test) -{ - struct pkt_stream *pkt_stream = test->ifobj_tx->xsk->pkt_stream; - u32 i; - - test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(pkt_stream->nb_pkts, - pkt_stream->pkts[0].len); - pkt_stream = test->ifobj_rx->xsk->pkt_stream; - for (i = 1; i < pkt_stream->nb_pkts; i += 2) - pkt_stream->pkts[i].valid = false; - - pkt_stream->nb_valid_entries /= 2; -} - -static void pkt_stream_even_odd_sequence(struct test_spec *test) -{ - struct pkt_stream *pkt_stream; - u32 i; - - for (i = 0; i < test->nb_sockets; i++) { - pkt_stream = test->ifobj_tx->xsk_arr[i].pkt_stream; - pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2, - pkt_stream->pkts[0].len, i, 2); - test->ifobj_tx->xsk_arr[i].pkt_stream = pkt_stream; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL); + if (prog_fd < 0) + return false; - pkt_stream = test->ifobj_rx->xsk_arr[i].pkt_stream; - pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2, - pkt_stream->pkts[0].len, i, 2); - test->ifobj_rx->xsk_arr[i].pkt_stream = pkt_stream; + err = bpf_xdp_attach(ifindex, prog_fd, flags, NULL); + if (err) { + close(prog_fd); + return false; } -} - -static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem) -{ - if (!pkt->valid) - return pkt->offset; - return pkt->offset + umem_alloc_buffer(umem); -} -static void pkt_stream_cancel(struct pkt_stream *pkt_stream) -{ - pkt_stream->current_pkt_nb--; -} - -static void pkt_generate(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, u64 addr, u32 len, - u32 pkt_nb, u32 bytes_written) -{ - void *data = xsk_umem__get_data(umem->buffer, addr); - - if (len < MIN_PKT_SIZE) - return; - - if (!bytes_written) { - gen_eth_hdr(xsk, data); - - len -= PKT_HDR_SIZE; - data += PKT_HDR_SIZE; - } else { - bytes_written -= PKT_HDR_SIZE; - } + bpf_xdp_detach(ifindex, flags, NULL); + close(prog_fd); - write_payload(data, pkt_nb, bytes_written, len); + return true; } -static struct pkt_stream *__pkt_stream_generate_custom(struct ifobject *ifobj, struct pkt *frames, - u32 nb_frames, bool verbatim) -{ - u32 i, len = 0, pkt_nb = 0, payload = 0; - struct pkt_stream *pkt_stream; - - pkt_stream = __pkt_stream_alloc(nb_frames); - if (!pkt_stream) - exit_with_error(ENOMEM); - - for (i = 0; i < nb_frames; i++) { - struct pkt *pkt = &pkt_stream->pkts[pkt_nb]; - struct pkt *frame = &frames[i]; - - pkt->offset = frame->offset; - if (verbatim) { - *pkt = *frame; - pkt->pkt_nb = payload; - if (!frame->valid || !pkt_continues(frame->options)) - payload++; - } else { - if (frame->valid) - len += frame->len; - if (frame->valid && pkt_continues(frame->options)) - continue; - - pkt->pkt_nb = pkt_nb; - pkt->len = len; - pkt->valid = frame->valid; - pkt->options = 0; - - len = 0; - } - - print_verbose("offset: %d len: %u valid: %u options: %u pkt_nb: %u\n", - pkt->offset, pkt->len, pkt->valid, pkt->options, pkt->pkt_nb); - - if (pkt->valid && pkt->len > pkt_stream->max_pkt_len) - pkt_stream->max_pkt_len = pkt->len; - - if (pkt->valid) - pkt_stream->nb_valid_entries++; - - pkt_nb++; - } - - pkt_stream->nb_pkts = pkt_nb; - pkt_stream->verbatim = verbatim; - return pkt_stream; -} - -static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, u32 nb_pkts) -{ - struct pkt_stream *pkt_stream; - - pkt_stream = __pkt_stream_generate_custom(test->ifobj_tx, pkts, nb_pkts, true); - test->ifobj_tx->xsk->pkt_stream = pkt_stream; - - pkt_stream = __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts, false); - test->ifobj_rx->xsk->pkt_stream = pkt_stream; -} - -static void pkt_print_data(u32 *data, u32 cnt) -{ - u32 i; - - for (i = 0; i < cnt; i++) { - u32 seqnum, pkt_nb; - - seqnum = ntohl(*data) & 0xffff; - pkt_nb = ntohl(*data) >> 16; - ksft_print_msg("%u:%u ", pkt_nb, seqnum); - data++; - } -} - -static void pkt_dump(void *pkt, u32 len, bool eth_header) -{ - struct ethhdr *ethhdr = pkt; - u32 i, *data; - - if (eth_header) { - /*extract L2 frame */ - ksft_print_msg("DEBUG>> L2: dst mac: "); - for (i = 0; i < ETH_ALEN; i++) - ksft_print_msg("%02X", ethhdr->h_dest[i]); - - ksft_print_msg("\nDEBUG>> L2: src mac: "); - for (i = 0; i < ETH_ALEN; i++) - ksft_print_msg("%02X", ethhdr->h_source[i]); - - data = pkt + PKT_HDR_SIZE; - } else { - data = pkt; - } - - /*extract L5 frame */ - ksft_print_msg("\nDEBUG>> L5: seqnum: "); - pkt_print_data(data, PKT_DUMP_NB_TO_PRINT); - ksft_print_msg("...."); - if (len > PKT_DUMP_NB_TO_PRINT * sizeof(u32)) { - ksft_print_msg("\n.... "); - pkt_print_data(data + len / sizeof(u32) - PKT_DUMP_NB_TO_PRINT, - PKT_DUMP_NB_TO_PRINT); - } - ksft_print_msg("\n---------------------------------------\n"); -} - -static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr) -{ - u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom; - u32 offset = addr % umem->frame_size, expected_offset; - int pkt_offset = pkt->valid ? pkt->offset : 0; - - if (!umem->unaligned_mode) - pkt_offset = 0; - - expected_offset = (pkt_offset + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; - - if (offset == expected_offset) - return true; - - ksft_print_msg("[%s] expected [%u], got [%u]\n", __func__, expected_offset, offset); - return false; -} - -static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) -{ - void *data = xsk_umem__get_data(buffer, addr); - struct xdp_info *meta = data - sizeof(struct xdp_info); - - if (meta->count != pkt->pkt_nb) { - ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%llu]\n", - __func__, pkt->pkt_nb, - (unsigned long long)meta->count); - return false; - } - - return true; -} - -static bool is_adjust_tail_supported(struct xsk_xdp_progs *skel_rx) -{ - struct bpf_map *data_map; - int adjust_value = 0; - int key = 0; - int ret; - - data_map = bpf_object__find_map_by_name(skel_rx->obj, "xsk_xdp_.bss"); - if (!data_map || !bpf_map__is_internal(data_map)) { - ksft_print_msg("Error: could not find bss section of XDP program\n"); - exit_with_error(errno); - } - - ret = bpf_map_lookup_elem(bpf_map__fd(data_map), &key, &adjust_value); - if (ret) { - ksft_print_msg("Error: bpf_map_lookup_elem failed with error %d\n", ret); - exit_with_error(errno); - } - - /* Set the 'adjust_value' variable to -EOPNOTSUPP in the XDP program if the adjust_tail - * helper is not supported. Skip the adjust_tail test case in this scenario. - */ - return adjust_value != -EOPNOTSUPP; -} - -static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 expected_pkt_nb, - u32 bytes_processed) -{ - u32 seqnum, pkt_nb, *pkt_data, words_to_end, expected_seqnum; - void *data = xsk_umem__get_data(umem->buffer, addr); - - addr -= umem->base_addr; - - if (addr >= umem->num_frames * umem->frame_size || - addr + len > umem->num_frames * umem->frame_size) { - ksft_print_msg("Frag invalid addr: %llx len: %u\n", - (unsigned long long)addr, len); - return false; - } - if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) { - ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n", - (unsigned long long)addr, len); - return false; - } - - pkt_data = data; - if (!bytes_processed) { - pkt_data += PKT_HDR_SIZE / sizeof(*pkt_data); - len -= PKT_HDR_SIZE; - } else { - bytes_processed -= PKT_HDR_SIZE; - } - - expected_seqnum = bytes_processed / sizeof(*pkt_data); - seqnum = ntohl(*pkt_data) & 0xffff; - pkt_nb = ntohl(*pkt_data) >> 16; - - if (expected_pkt_nb != pkt_nb) { - ksft_print_msg("[%s] expected pkt_nb [%u], got pkt_nb [%u]\n", - __func__, expected_pkt_nb, pkt_nb); - goto error; - } - if (expected_seqnum != seqnum) { - ksft_print_msg("[%s] expected seqnum at start [%u], got seqnum [%u]\n", - __func__, expected_seqnum, seqnum); - goto error; - } - - words_to_end = len / sizeof(*pkt_data) - 1; - pkt_data += words_to_end; - seqnum = ntohl(*pkt_data) & 0xffff; - expected_seqnum += words_to_end; - if (expected_seqnum != seqnum) { - ksft_print_msg("[%s] expected seqnum at end [%u], got seqnum [%u]\n", - __func__, expected_seqnum, seqnum); - goto error; - } - - return true; - -error: - pkt_dump(data, len, !bytes_processed); - return false; -} - -static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) -{ - if (pkt->len != len) { - ksft_print_msg("[%s] expected packet length [%d], got length [%d]\n", - __func__, pkt->len, len); - pkt_dump(xsk_umem__get_data(buffer, addr), len, true); - return false; - } - - return true; -} - -static u32 load_value(u32 *counter) -{ - return __atomic_load_n(counter, __ATOMIC_ACQUIRE); -} - -static bool kick_tx_with_check(struct xsk_socket_info *xsk, int *ret) -{ - u32 max_budget = MAX_TX_BUDGET_DEFAULT; - u32 cons, ready_to_send; - int delta; - - cons = load_value(xsk->tx.consumer); - ready_to_send = load_value(xsk->tx.producer) - cons; - *ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); - - delta = load_value(xsk->tx.consumer) - cons; - /* By default, xsk should consume exact @max_budget descs at one - * send in this case where hitting the max budget limit in while - * loop is triggered in __xsk_generic_xmit(). Please make sure that - * the number of descs to be sent is larger than @max_budget, or - * else the tx.consumer will be updated in xskq_cons_peek_desc() - * in time which hides the issue we try to verify. - */ - if (ready_to_send > max_budget && delta != max_budget) - return false; - - return true; -} - -static int kick_tx(struct xsk_socket_info *xsk) -{ - int ret; - - if (xsk->check_consumer) { - if (!kick_tx_with_check(xsk, &ret)) - return TEST_FAILURE; - } else { - ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); - } - if (ret >= 0) - return TEST_PASS; - if (errno == ENOBUFS || errno == EAGAIN || errno == EBUSY || errno == ENETDOWN) { - usleep(100); - return TEST_PASS; - } - return TEST_FAILURE; -} - -static int kick_rx(struct xsk_socket_info *xsk) -{ - int ret; - - ret = recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL); - if (ret < 0) - return TEST_FAILURE; - - return TEST_PASS; -} - -static int complete_pkts(struct xsk_socket_info *xsk, int batch_size) -{ - unsigned int rcvd; - u32 idx; - int ret; - - if (xsk_ring_prod__needs_wakeup(&xsk->tx)) { - ret = kick_tx(xsk); - if (ret) - return TEST_FAILURE; - } - - rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx); - if (rcvd) { - if (rcvd > xsk->outstanding_tx) { - u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1); - - ksft_print_msg("[%s] Too many packets completed\n", __func__); - ksft_print_msg("Last completion address: %llx\n", - (unsigned long long)addr); - return TEST_FAILURE; - } - - xsk_ring_cons__release(&xsk->umem->cq, rcvd); - xsk->outstanding_tx -= rcvd; - } - - return TEST_PASS; -} - -static int __receive_pkts(struct test_spec *test, struct xsk_socket_info *xsk) -{ - u32 frags_processed = 0, nb_frags = 0, pkt_len = 0; - u32 idx_rx = 0, idx_fq = 0, rcvd, pkts_sent = 0; - struct pkt_stream *pkt_stream = xsk->pkt_stream; - struct ifobject *ifobj = test->ifobj_rx; - struct xsk_umem_info *umem = xsk->umem; - struct pollfd fds = { }; - struct pkt *pkt; - u64 first_addr = 0; - int ret; - - fds.fd = xsk_socket__fd(xsk->xsk); - fds.events = POLLIN; - - ret = kick_rx(xsk); - if (ret) - return TEST_FAILURE; - - if (ifobj->use_poll) { - ret = poll(&fds, 1, POLL_TMOUT); - if (ret < 0) - return TEST_FAILURE; - - if (!ret) { - if (!is_umem_valid(test->ifobj_tx)) - return TEST_PASS; - - ksft_print_msg("ERROR: [%s] Poll timed out\n", __func__); - return TEST_CONTINUE; - } - - if (!(fds.revents & POLLIN)) - return TEST_CONTINUE; - } - - rcvd = xsk_ring_cons__peek(&xsk->rx, xsk->batch_size, &idx_rx); - if (!rcvd) - return TEST_CONTINUE; - - if (ifobj->use_fill_ring) { - ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); - while (ret != rcvd) { - if (xsk_ring_prod__needs_wakeup(&umem->fq)) { - ret = poll(&fds, 1, POLL_TMOUT); - if (ret < 0) - return TEST_FAILURE; - } - ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); - } - } - - while (frags_processed < rcvd) { - const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++); - u64 addr = desc->addr, orig; - - orig = xsk_umem__extract_addr(addr); - addr = xsk_umem__add_offset_to_addr(addr); - - if (!nb_frags) { - pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent); - if (!pkt) { - ksft_print_msg("[%s] received too many packets addr: %lx len %u\n", - __func__, addr, desc->len); - return TEST_FAILURE; - } - } - - print_verbose("Rx: addr: %lx len: %u options: %u pkt_nb: %u valid: %u\n", - addr, desc->len, desc->options, pkt->pkt_nb, pkt->valid); - - if (!is_frag_valid(umem, addr, desc->len, pkt->pkt_nb, pkt_len) || - !is_offset_correct(umem, pkt, addr) || (ifobj->use_metadata && - !is_metadata_correct(pkt, umem->buffer, addr))) - return TEST_FAILURE; - - if (!nb_frags++) - first_addr = addr; - frags_processed++; - pkt_len += desc->len; - if (ifobj->use_fill_ring) - *xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig; - - if (pkt_continues(desc->options)) - continue; - - /* The complete packet has been received */ - if (!is_pkt_valid(pkt, umem->buffer, first_addr, pkt_len) || - !is_offset_correct(umem, pkt, addr)) - return TEST_FAILURE; - - pkt_stream->nb_rx_pkts++; - nb_frags = 0; - pkt_len = 0; - } - - if (nb_frags) { - /* In the middle of a packet. Start over from beginning of packet. */ - idx_rx -= nb_frags; - xsk_ring_cons__cancel(&xsk->rx, nb_frags); - if (ifobj->use_fill_ring) { - idx_fq -= nb_frags; - xsk_ring_prod__cancel(&umem->fq, nb_frags); - } - frags_processed -= nb_frags; - } - - if (ifobj->use_fill_ring) - xsk_ring_prod__submit(&umem->fq, frags_processed); - if (ifobj->release_rx) - xsk_ring_cons__release(&xsk->rx, frags_processed); - - pthread_mutex_lock(&pacing_mutex); - pkts_in_flight -= pkts_sent; - pthread_mutex_unlock(&pacing_mutex); - pkts_sent = 0; - -return TEST_CONTINUE; -} - -bool all_packets_received(struct test_spec *test, struct xsk_socket_info *xsk, u32 sock_num, - unsigned long *bitmap) -{ - struct pkt_stream *pkt_stream = xsk->pkt_stream; - - if (!pkt_stream) { - __set_bit(sock_num, bitmap); - return false; - } - - if (pkt_stream->nb_rx_pkts == pkt_stream->nb_valid_entries) { - __set_bit(sock_num, bitmap); - if (bitmap_full(bitmap, test->nb_sockets)) - return true; - } - - return false; -} - -static int receive_pkts(struct test_spec *test) -{ - struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0}; - DECLARE_BITMAP(bitmap, test->nb_sockets); - struct xsk_socket_info *xsk; - u32 sock_num = 0; - int res, ret; - - ret = gettimeofday(&tv_now, NULL); - if (ret) - exit_with_error(errno); - - timeradd(&tv_now, &tv_timeout, &tv_end); - - while (1) { - xsk = &test->ifobj_rx->xsk_arr[sock_num]; - - if ((all_packets_received(test, xsk, sock_num, bitmap))) - break; - - res = __receive_pkts(test, xsk); - if (!(res == TEST_PASS || res == TEST_CONTINUE)) - return res; - - ret = gettimeofday(&tv_now, NULL); - if (ret) - exit_with_error(errno); - - if (timercmp(&tv_now, &tv_end, >)) { - ksft_print_msg("ERROR: [%s] Receive loop timed out\n", __func__); - return TEST_FAILURE; - } - sock_num = (sock_num + 1) % test->nb_sockets; - } - - return TEST_PASS; -} - -static int __send_pkts(struct ifobject *ifobject, struct xsk_socket_info *xsk, bool timeout) -{ - u32 i, idx = 0, valid_pkts = 0, valid_frags = 0, buffer_len; - struct pkt_stream *pkt_stream = xsk->pkt_stream; - struct xsk_umem_info *umem = ifobject->umem; - bool use_poll = ifobject->use_poll; - struct pollfd fds = { }; - int ret; - - buffer_len = pkt_get_buffer_len(umem, pkt_stream->max_pkt_len); - /* pkts_in_flight might be negative if many invalid packets are sent */ - if (pkts_in_flight >= (int)((umem_size(umem) - xsk->batch_size * buffer_len) / - buffer_len)) { - ret = kick_tx(xsk); - if (ret) - return TEST_FAILURE; - return TEST_CONTINUE; - } - - fds.fd = xsk_socket__fd(xsk->xsk); - fds.events = POLLOUT; - - while (xsk_ring_prod__reserve(&xsk->tx, xsk->batch_size, &idx) < xsk->batch_size) { - if (use_poll) { - ret = poll(&fds, 1, POLL_TMOUT); - if (timeout) { - if (ret < 0) { - ksft_print_msg("ERROR: [%s] Poll error %d\n", - __func__, errno); - return TEST_FAILURE; - } - if (ret == 0) - return TEST_PASS; - break; - } - if (ret <= 0) { - ksft_print_msg("ERROR: [%s] Poll error %d\n", - __func__, errno); - return TEST_FAILURE; - } - } - - complete_pkts(xsk, xsk->batch_size); - } - - for (i = 0; i < xsk->batch_size; i++) { - struct pkt *pkt = pkt_stream_get_next_tx_pkt(pkt_stream); - u32 nb_frags_left, nb_frags, bytes_written = 0; - - if (!pkt) - break; - - nb_frags = pkt_nb_frags(umem->frame_size, pkt_stream, pkt); - if (nb_frags > xsk->batch_size - i) { - pkt_stream_cancel(pkt_stream); - xsk_ring_prod__cancel(&xsk->tx, xsk->batch_size - i); - break; - } - nb_frags_left = nb_frags; - - while (nb_frags_left--) { - struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); - - tx_desc->addr = pkt_get_addr(pkt, ifobject->umem); - if (pkt_stream->verbatim) { - tx_desc->len = pkt->len; - tx_desc->options = pkt->options; - } else if (nb_frags_left) { - tx_desc->len = umem->frame_size; - tx_desc->options = XDP_PKT_CONTD; - } else { - tx_desc->len = pkt->len - bytes_written; - tx_desc->options = 0; - } - if (pkt->valid) - pkt_generate(xsk, umem, tx_desc->addr, tx_desc->len, pkt->pkt_nb, - bytes_written); - bytes_written += tx_desc->len; - - print_verbose("Tx addr: %llx len: %u options: %u pkt_nb: %u\n", - tx_desc->addr, tx_desc->len, tx_desc->options, pkt->pkt_nb); - - if (nb_frags_left) { - i++; - if (pkt_stream->verbatim) - pkt = pkt_stream_get_next_tx_pkt(pkt_stream); - } - } - - if (pkt && pkt->valid) { - valid_pkts++; - valid_frags += nb_frags; - } - } - - pthread_mutex_lock(&pacing_mutex); - pkts_in_flight += valid_pkts; - pthread_mutex_unlock(&pacing_mutex); - - xsk_ring_prod__submit(&xsk->tx, i); - xsk->outstanding_tx += valid_frags; - - if (use_poll) { - ret = poll(&fds, 1, POLL_TMOUT); - if (ret <= 0) { - if (ret == 0 && timeout) - return TEST_PASS; - - ksft_print_msg("ERROR: [%s] Poll error %d\n", __func__, ret); - return TEST_FAILURE; - } - } - - if (!timeout) { - if (complete_pkts(xsk, i)) - return TEST_FAILURE; - - usleep(10); - return TEST_PASS; - } - - return TEST_CONTINUE; -} - -static int wait_for_tx_completion(struct xsk_socket_info *xsk) -{ - struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0}; - int ret; - - ret = gettimeofday(&tv_now, NULL); - if (ret) - exit_with_error(errno); - timeradd(&tv_now, &tv_timeout, &tv_end); - - while (xsk->outstanding_tx) { - ret = gettimeofday(&tv_now, NULL); - if (ret) - exit_with_error(errno); - if (timercmp(&tv_now, &tv_end, >)) { - ksft_print_msg("ERROR: [%s] Transmission loop timed out\n", __func__); - return TEST_FAILURE; - } - - complete_pkts(xsk, xsk->batch_size); - } - - return TEST_PASS; -} - -bool all_packets_sent(struct test_spec *test, unsigned long *bitmap) -{ - return bitmap_full(bitmap, test->nb_sockets); -} - -static int send_pkts(struct test_spec *test, struct ifobject *ifobject) -{ - bool timeout = !is_umem_valid(test->ifobj_rx); - DECLARE_BITMAP(bitmap, test->nb_sockets); - u32 i, ret; - - while (!(all_packets_sent(test, bitmap))) { - for (i = 0; i < test->nb_sockets; i++) { - struct pkt_stream *pkt_stream; - - pkt_stream = ifobject->xsk_arr[i].pkt_stream; - if (!pkt_stream || pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) { - __set_bit(i, bitmap); - continue; - } - ret = __send_pkts(ifobject, &ifobject->xsk_arr[i], timeout); - if (ret == TEST_CONTINUE && !test->fail) - continue; - - if ((ret || test->fail) && !timeout) - return TEST_FAILURE; - - if (ret == TEST_PASS && timeout) - return ret; - - ret = wait_for_tx_completion(&ifobject->xsk_arr[i]); - if (ret) - return TEST_FAILURE; - } - } - - return TEST_PASS; -} - -static int get_xsk_stats(struct xsk_socket *xsk, struct xdp_statistics *stats) -{ - int fd = xsk_socket__fd(xsk), err; - socklen_t optlen, expected_len; - - optlen = sizeof(*stats); - err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, stats, &optlen); - if (err) { - ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n", - __func__, -err, strerror(-err)); - return TEST_FAILURE; - } - - expected_len = sizeof(struct xdp_statistics); - if (optlen != expected_len) { - ksft_print_msg("[%s] getsockopt optlen error. Expected: %u got: %u\n", - __func__, expected_len, optlen); - return TEST_FAILURE; - } - - return TEST_PASS; -} - -static int validate_rx_dropped(struct ifobject *ifobject) -{ - struct xsk_socket *xsk = ifobject->xsk->xsk; - struct xdp_statistics stats; - int err; - - err = kick_rx(ifobject->xsk); - if (err) - return TEST_FAILURE; - - err = get_xsk_stats(xsk, &stats); - if (err) - return TEST_FAILURE; - - /* The receiver calls getsockopt after receiving the last (valid) - * packet which is not the final packet sent in this test (valid and - * invalid packets are sent in alternating fashion with the final - * packet being invalid). Since the last packet may or may not have - * been dropped already, both outcomes must be allowed. - */ - if (stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 || - stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 - 1) - return TEST_PASS; - - return TEST_FAILURE; -} - -static int validate_rx_full(struct ifobject *ifobject) -{ - struct xsk_socket *xsk = ifobject->xsk->xsk; - struct xdp_statistics stats; - int err; - - usleep(1000); - err = kick_rx(ifobject->xsk); - if (err) - return TEST_FAILURE; - - err = get_xsk_stats(xsk, &stats); - if (err) - return TEST_FAILURE; - - if (stats.rx_ring_full) - return TEST_PASS; - - return TEST_FAILURE; -} - -static int validate_fill_empty(struct ifobject *ifobject) -{ - struct xsk_socket *xsk = ifobject->xsk->xsk; - struct xdp_statistics stats; - int err; - - usleep(1000); - err = kick_rx(ifobject->xsk); - if (err) - return TEST_FAILURE; - - err = get_xsk_stats(xsk, &stats); - if (err) - return TEST_FAILURE; - - if (stats.rx_fill_ring_empty_descs) - return TEST_PASS; - - return TEST_FAILURE; -} - -static int validate_tx_invalid_descs(struct ifobject *ifobject) -{ - struct xsk_socket *xsk = ifobject->xsk->xsk; - int fd = xsk_socket__fd(xsk); - struct xdp_statistics stats; - socklen_t optlen; - int err; - - optlen = sizeof(stats); - err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen); - if (err) { - ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n", - __func__, -err, strerror(-err)); - return TEST_FAILURE; - } - - if (stats.tx_invalid_descs != ifobject->xsk->pkt_stream->nb_pkts / 2) { - ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%llu] expected [%u]\n", - __func__, - (unsigned long long)stats.tx_invalid_descs, - ifobject->xsk->pkt_stream->nb_pkts); - return TEST_FAILURE; - } - - return TEST_PASS; -} - -static void xsk_configure_socket(struct test_spec *test, struct ifobject *ifobject, - struct xsk_umem_info *umem, bool tx) -{ - int i, ret; - - for (i = 0; i < test->nb_sockets; i++) { - bool shared = (ifobject->shared_umem && tx) ? true : !!i; - u32 ctr = 0; - - while (ctr++ < SOCK_RECONF_CTR) { - ret = __xsk_configure_socket(&ifobject->xsk_arr[i], umem, - ifobject, shared); - if (!ret) - break; - - /* Retry if it fails as xsk_socket__create() is asynchronous */ - if (ctr >= SOCK_RECONF_CTR) - exit_with_error(-ret); - usleep(USLEEP_MAX); - } - if (ifobject->busy_poll) - enable_busy_poll(&ifobject->xsk_arr[i]); - } -} - -static void thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobject) -{ - xsk_configure_socket(test, ifobject, test->ifobj_rx->umem, true); - ifobject->xsk = &ifobject->xsk_arr[0]; - ifobject->xskmap = test->ifobj_rx->xskmap; - memcpy(ifobject->umem, test->ifobj_rx->umem, sizeof(struct xsk_umem_info)); - ifobject->umem->base_addr = 0; -} - -static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, - bool fill_up) -{ - u32 rx_frame_size = umem->frame_size - XDP_PACKET_HEADROOM; - u32 idx = 0, filled = 0, buffers_to_fill, nb_pkts; - int ret; - - if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) - buffers_to_fill = umem->num_frames; - else - buffers_to_fill = umem->fill_size; - - ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx); - if (ret != buffers_to_fill) - exit_with_error(ENOSPC); - - while (filled < buffers_to_fill) { - struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &nb_pkts); - u64 addr; - u32 i; - - for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt_stream, pkt); i++) { - if (!pkt) { - if (!fill_up) - break; - addr = filled * umem->frame_size + umem->base_addr; - } else if (pkt->offset >= 0) { - addr = pkt->offset % umem->frame_size + umem_alloc_buffer(umem); - } else { - addr = pkt->offset + umem_alloc_buffer(umem); - } - - *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; - if (++filled >= buffers_to_fill) - break; - } - } - xsk_ring_prod__submit(&umem->fq, filled); - xsk_ring_prod__cancel(&umem->fq, buffers_to_fill - filled); - - pkt_stream_reset(pkt_stream); - umem_reset_alloc(umem); -} - -static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) -{ - u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; - int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE; - LIBBPF_OPTS(bpf_xdp_query_opts, opts); - void *bufs; - int ret; - u32 i; - - if (ifobject->umem->unaligned_mode) - mmap_flags |= MAP_HUGETLB | MAP_HUGE_2MB; - - if (ifobject->shared_umem) - umem_sz *= 2; - - bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); - if (bufs == MAP_FAILED) - exit_with_error(errno); - - ret = xsk_configure_umem(ifobject, ifobject->umem, bufs, umem_sz); - if (ret) - exit_with_error(-ret); - - xsk_configure_socket(test, ifobject, ifobject->umem, false); - - ifobject->xsk = &ifobject->xsk_arr[0]; - - if (!ifobject->rx_on) - return; - - xsk_populate_fill_ring(ifobject->umem, ifobject->xsk->pkt_stream, ifobject->use_fill_ring); - - for (i = 0; i < test->nb_sockets; i++) { - ifobject->xsk = &ifobject->xsk_arr[i]; - ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, i); - if (ret) - exit_with_error(errno); - } -} - -static void *worker_testapp_validate_tx(void *arg) -{ - struct test_spec *test = (struct test_spec *)arg; - struct ifobject *ifobject = test->ifobj_tx; - int err; - - if (test->current_step == 1) { - if (!ifobject->shared_umem) - thread_common_ops(test, ifobject); - else - thread_common_ops_tx(test, ifobject); - } - - err = send_pkts(test, ifobject); - - if (!err && ifobject->validation_func) - err = ifobject->validation_func(ifobject); - if (err) - report_failure(test); - - pthread_exit(NULL); -} - -static void *worker_testapp_validate_rx(void *arg) -{ - struct test_spec *test = (struct test_spec *)arg; - struct ifobject *ifobject = test->ifobj_rx; - int err; - - if (test->current_step == 1) { - thread_common_ops(test, ifobject); - } else { - xsk_clear_xskmap(ifobject->xskmap); - err = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, 0); - if (err) { - ksft_print_msg("Error: Failed to update xskmap, error %s\n", - strerror(-err)); - exit_with_error(-err); - } - } - - pthread_barrier_wait(&barr); - - err = receive_pkts(test); - - if (!err && ifobject->validation_func) - err = ifobject->validation_func(ifobject); - - if (err) { - if (test->adjust_tail && !is_adjust_tail_supported(ifobject->xdp_progs)) - test->adjust_tail_support = false; - else - report_failure(test); - } - - pthread_exit(NULL); -} - -static u64 ceil_u64(u64 a, u64 b) -{ - return (a + b - 1) / b; -} - -static void testapp_clean_xsk_umem(struct ifobject *ifobj) -{ - u64 umem_sz = ifobj->umem->num_frames * ifobj->umem->frame_size; - - if (ifobj->shared_umem) - umem_sz *= 2; - - umem_sz = ceil_u64(umem_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; - xsk_umem__delete(ifobj->umem->umem); - munmap(ifobj->umem->buffer, umem_sz); -} - -static void handler(int signum) -{ - pthread_exit(NULL); -} - -static bool xdp_prog_changed_rx(struct test_spec *test) -{ - struct ifobject *ifobj = test->ifobj_rx; - - return ifobj->xdp_prog != test->xdp_prog_rx || ifobj->mode != test->mode; -} - -static bool xdp_prog_changed_tx(struct test_spec *test) -{ - struct ifobject *ifobj = test->ifobj_tx; - - return ifobj->xdp_prog != test->xdp_prog_tx || ifobj->mode != test->mode; -} - -static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_prog, - struct bpf_map *xskmap, enum test_mode mode) -{ - int err; - - xsk_detach_xdp_program(ifobj->ifindex, mode_to_xdp_flags(ifobj->mode)); - err = xsk_attach_xdp_program(xdp_prog, ifobj->ifindex, mode_to_xdp_flags(mode)); - if (err) { - ksft_print_msg("Error attaching XDP program\n"); - exit_with_error(-err); - } - - if (ifobj->mode != mode && (mode == TEST_MODE_DRV || mode == TEST_MODE_ZC)) - if (!xsk_is_in_mode(ifobj->ifindex, XDP_FLAGS_DRV_MODE)) { - ksft_print_msg("ERROR: XDP prog not in DRV mode\n"); - exit_with_error(EINVAL); - } - - ifobj->xdp_prog = xdp_prog; - ifobj->xskmap = xskmap; - ifobj->mode = mode; -} - -static void xsk_attach_xdp_progs(struct test_spec *test, struct ifobject *ifobj_rx, - struct ifobject *ifobj_tx) -{ - if (xdp_prog_changed_rx(test)) - xsk_reattach_xdp(ifobj_rx, test->xdp_prog_rx, test->xskmap_rx, test->mode); - - if (!ifobj_tx || ifobj_tx->shared_umem) - return; - - if (xdp_prog_changed_tx(test)) - xsk_reattach_xdp(ifobj_tx, test->xdp_prog_tx, test->xskmap_tx, test->mode); -} - -static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *ifobj1, - struct ifobject *ifobj2) -{ - pthread_t t0, t1; - int err; - - if (test->mtu > MAX_ETH_PKT_SIZE) { - if (test->mode == TEST_MODE_ZC && (!ifobj1->multi_buff_zc_supp || - (ifobj2 && !ifobj2->multi_buff_zc_supp))) { - ksft_test_result_skip("Multi buffer for zero-copy not supported.\n"); - return TEST_SKIP; - } - if (test->mode != TEST_MODE_ZC && (!ifobj1->multi_buff_supp || - (ifobj2 && !ifobj2->multi_buff_supp))) { - ksft_test_result_skip("Multi buffer not supported.\n"); - return TEST_SKIP; - } - } - err = test_spec_set_mtu(test, test->mtu); - if (err) { - ksft_print_msg("Error, could not set mtu.\n"); - exit_with_error(err); - } - - if (ifobj2) { - if (pthread_barrier_init(&barr, NULL, 2)) - exit_with_error(errno); - pkt_stream_reset(ifobj2->xsk->pkt_stream); - } - - test->current_step++; - pkt_stream_reset(ifobj1->xsk->pkt_stream); - pkts_in_flight = 0; - - signal(SIGUSR1, handler); - /*Spawn RX thread */ - pthread_create(&t0, NULL, ifobj1->func_ptr, test); - - if (ifobj2) { - pthread_barrier_wait(&barr); - if (pthread_barrier_destroy(&barr)) - exit_with_error(errno); - - /*Spawn TX thread */ - pthread_create(&t1, NULL, ifobj2->func_ptr, test); - - pthread_join(t1, NULL); - } - - if (!ifobj2) - pthread_kill(t0, SIGUSR1); - else - pthread_join(t0, NULL); - - if (test->total_steps == test->current_step || test->fail) { - u32 i; - - if (ifobj2) - for (i = 0; i < test->nb_sockets; i++) - xsk_socket__delete(ifobj2->xsk_arr[i].xsk); - - for (i = 0; i < test->nb_sockets; i++) - xsk_socket__delete(ifobj1->xsk_arr[i].xsk); - - testapp_clean_xsk_umem(ifobj1); - if (ifobj2 && !ifobj2->shared_umem) - testapp_clean_xsk_umem(ifobj2); - } - - return !!test->fail; -} - -static int testapp_validate_traffic(struct test_spec *test) -{ - struct ifobject *ifobj_rx = test->ifobj_rx; - struct ifobject *ifobj_tx = test->ifobj_tx; - - if ((ifobj_rx->umem->unaligned_mode && !ifobj_rx->unaligned_supp) || - (ifobj_tx->umem->unaligned_mode && !ifobj_tx->unaligned_supp)) { - ksft_test_result_skip("No huge pages present.\n"); - return TEST_SKIP; - } - - if (test->set_ring) { - if (ifobj_tx->hw_ring_size_supp) { - if (set_ring_size(ifobj_tx)) { - ksft_test_result_skip("Failed to change HW ring size.\n"); - return TEST_FAILURE; - } - } else { - ksft_test_result_skip("Changing HW ring size not supported.\n"); - return TEST_SKIP; - } - } - - xsk_attach_xdp_progs(test, ifobj_rx, ifobj_tx); - return __testapp_validate_traffic(test, ifobj_rx, ifobj_tx); -} - -static int testapp_validate_traffic_single_thread(struct test_spec *test, struct ifobject *ifobj) -{ - return __testapp_validate_traffic(test, ifobj, NULL); -} - -static int testapp_teardown(struct test_spec *test) -{ - int i; - - for (i = 0; i < MAX_TEARDOWN_ITER; i++) { - if (testapp_validate_traffic(test)) - return TEST_FAILURE; - test_spec_reset(test); - } - - return TEST_PASS; -} - -static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) -{ - thread_func_t tmp_func_ptr = (*ifobj1)->func_ptr; - struct ifobject *tmp_ifobj = (*ifobj1); - - (*ifobj1)->func_ptr = (*ifobj2)->func_ptr; - (*ifobj2)->func_ptr = tmp_func_ptr; - - *ifobj1 = *ifobj2; - *ifobj2 = tmp_ifobj; -} - -static int testapp_bidirectional(struct test_spec *test) -{ - int res; - - test->ifobj_tx->rx_on = true; - test->ifobj_rx->tx_on = true; - test->total_steps = 2; - if (testapp_validate_traffic(test)) - return TEST_FAILURE; - - print_verbose("Switching Tx/Rx direction\n"); - swap_directions(&test->ifobj_rx, &test->ifobj_tx); - res = __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx); - - swap_directions(&test->ifobj_rx, &test->ifobj_tx); - return res; -} - -static int swap_xsk_resources(struct test_spec *test) -{ - int ret; - - test->ifobj_tx->xsk_arr[0].pkt_stream = NULL; - test->ifobj_rx->xsk_arr[0].pkt_stream = NULL; - test->ifobj_tx->xsk_arr[1].pkt_stream = test->tx_pkt_stream_default; - test->ifobj_rx->xsk_arr[1].pkt_stream = test->rx_pkt_stream_default; - test->ifobj_tx->xsk = &test->ifobj_tx->xsk_arr[1]; - test->ifobj_rx->xsk = &test->ifobj_rx->xsk_arr[1]; - - ret = xsk_update_xskmap(test->ifobj_rx->xskmap, test->ifobj_rx->xsk->xsk, 0); - if (ret) - return TEST_FAILURE; - - return TEST_PASS; -} - -static int testapp_xdp_prog_cleanup(struct test_spec *test) -{ - test->total_steps = 2; - test->nb_sockets = 2; - if (testapp_validate_traffic(test)) - return TEST_FAILURE; - - if (swap_xsk_resources(test)) - return TEST_FAILURE; - return testapp_validate_traffic(test); -} - -static int testapp_headroom(struct test_spec *test) -{ - test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE; - return testapp_validate_traffic(test); -} - -static int testapp_stats_rx_dropped(struct test_spec *test) -{ - if (test->mode == TEST_MODE_ZC) { - ksft_test_result_skip("Can not run RX_DROPPED test for ZC mode\n"); - return TEST_SKIP; - } - - pkt_stream_replace_half(test, MIN_PKT_SIZE * 4, 0); - test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size - - XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 3; - pkt_stream_receive_half(test); - test->ifobj_rx->validation_func = validate_rx_dropped; - return testapp_validate_traffic(test); -} - -static int testapp_stats_tx_invalid_descs(struct test_spec *test) -{ - pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0); - test->ifobj_tx->validation_func = validate_tx_invalid_descs; - return testapp_validate_traffic(test); -} - -static int testapp_stats_rx_full(struct test_spec *test) -{ - pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); - test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); - - test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS; - test->ifobj_rx->release_rx = false; - test->ifobj_rx->validation_func = validate_rx_full; - return testapp_validate_traffic(test); -} - -static int testapp_stats_fill_empty(struct test_spec *test) -{ - pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); - test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); - - test->ifobj_rx->use_fill_ring = false; - test->ifobj_rx->validation_func = validate_fill_empty; - return testapp_validate_traffic(test); -} - -static int testapp_send_receive_unaligned(struct test_spec *test) -{ - test->ifobj_tx->umem->unaligned_mode = true; - test->ifobj_rx->umem->unaligned_mode = true; - /* Let half of the packets straddle a 4K buffer boundary */ - pkt_stream_replace_half(test, MIN_PKT_SIZE, -MIN_PKT_SIZE / 2); - - return testapp_validate_traffic(test); -} - -static int testapp_send_receive_unaligned_mb(struct test_spec *test) -{ - test->mtu = MAX_ETH_JUMBO_SIZE; - test->ifobj_tx->umem->unaligned_mode = true; - test->ifobj_rx->umem->unaligned_mode = true; - pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE); - return testapp_validate_traffic(test); -} - -static int testapp_single_pkt(struct test_spec *test) -{ - struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}}; - - pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - return testapp_validate_traffic(test); -} - -static int testapp_send_receive_mb(struct test_spec *test) -{ - test->mtu = MAX_ETH_JUMBO_SIZE; - pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE); - - return testapp_validate_traffic(test); -} - -static int testapp_invalid_desc_mb(struct test_spec *test) -{ - struct xsk_umem_info *umem = test->ifobj_tx->umem; - u64 umem_size = umem->num_frames * umem->frame_size; - struct pkt pkts[] = { - /* Valid packet for synch to start with */ - {0, MIN_PKT_SIZE, 0, true, 0}, - /* Zero frame len is not legal */ - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {0, 0, 0, false, 0}, - /* Invalid address in the second frame */ - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {umem_size, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - /* Invalid len in the middle */ - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - /* Invalid options in the middle */ - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XSK_DESC__INVALID_OPTION}, - /* Transmit 2 frags, receive 3 */ - {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, XDP_PKT_CONTD}, - {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, 0}, - /* Middle frame crosses chunk boundary with small length */ - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {-MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false, 0}, - /* Valid packet for synch so that something is received */ - {0, MIN_PKT_SIZE, 0, true, 0}}; - - if (umem->unaligned_mode) { - /* Crossing a chunk boundary allowed */ - pkts[12].valid = true; - pkts[13].valid = true; - } - - test->mtu = MAX_ETH_JUMBO_SIZE; - pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - return testapp_validate_traffic(test); -} - -static int testapp_invalid_desc(struct test_spec *test) -{ - struct xsk_umem_info *umem = test->ifobj_tx->umem; - u64 umem_size = umem->num_frames * umem->frame_size; - struct pkt pkts[] = { - /* Zero packet address allowed */ - {0, MIN_PKT_SIZE, 0, true}, - /* Allowed packet */ - {0, MIN_PKT_SIZE, 0, true}, - /* Straddling the start of umem */ - {-2, MIN_PKT_SIZE, 0, false}, - /* Packet too large */ - {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, - /* Up to end of umem allowed */ - {umem_size - MIN_PKT_SIZE - 2 * umem->frame_size, MIN_PKT_SIZE, 0, true}, - /* After umem ends */ - {umem_size, MIN_PKT_SIZE, 0, false}, - /* Straddle the end of umem */ - {umem_size - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, - /* Straddle a 4K boundary */ - {0x1000 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, - /* Straddle a 2K boundary */ - {0x800 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, true}, - /* Valid packet for synch so that something is received */ - {0, MIN_PKT_SIZE, 0, true}}; - - if (umem->unaligned_mode) { - /* Crossing a page boundary allowed */ - pkts[7].valid = true; - } - if (umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { - /* Crossing a 2K frame size boundary not allowed */ - pkts[8].valid = false; - } - - if (test->ifobj_tx->shared_umem) { - pkts[4].offset += umem_size; - pkts[5].offset += umem_size; - pkts[6].offset += umem_size; - } - - pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - return testapp_validate_traffic(test); -} - -static int testapp_xdp_drop(struct test_spec *test) -{ - struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; - struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; - - test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_drop, skel_tx->progs.xsk_xdp_drop, - skel_rx->maps.xsk, skel_tx->maps.xsk); - - pkt_stream_receive_half(test); - return testapp_validate_traffic(test); -} - -static int testapp_xdp_metadata_copy(struct test_spec *test) -{ - struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; - struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; - - test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_populate_metadata, - skel_tx->progs.xsk_xdp_populate_metadata, - skel_rx->maps.xsk, skel_tx->maps.xsk); - test->ifobj_rx->use_metadata = true; - - skel_rx->bss->count = 0; - - return testapp_validate_traffic(test); -} - -static int testapp_xdp_shared_umem(struct test_spec *test) -{ - struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; - struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; - - test->total_steps = 1; - test->nb_sockets = 2; - - test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_shared_umem, - skel_tx->progs.xsk_xdp_shared_umem, - skel_rx->maps.xsk, skel_tx->maps.xsk); - - pkt_stream_even_odd_sequence(test); - - return testapp_validate_traffic(test); -} - -static int testapp_poll_txq_tmout(struct test_spec *test) -{ - test->ifobj_tx->use_poll = true; - /* create invalid frame by set umem frame_size and pkt length equal to 2048 */ - test->ifobj_tx->umem->frame_size = 2048; - pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048); - return testapp_validate_traffic_single_thread(test, test->ifobj_tx); -} - -static int testapp_poll_rxq_tmout(struct test_spec *test) -{ - test->ifobj_rx->use_poll = true; - return testapp_validate_traffic_single_thread(test, test->ifobj_rx); -} - -static int testapp_too_many_frags(struct test_spec *test) -{ - struct pkt *pkts; - u32 max_frags, i; - int ret; - - if (test->mode == TEST_MODE_ZC) { - max_frags = test->ifobj_tx->xdp_zc_max_segs; - } else { - max_frags = get_max_skb_frags(); - if (!max_frags) { - ksft_print_msg("Couldn't retrieve MAX_SKB_FRAGS from system, using default (17) value\n"); - max_frags = 17; - } - max_frags += 1; - } - - pkts = calloc(2 * max_frags + 2, sizeof(struct pkt)); - if (!pkts) - return TEST_FAILURE; - - test->mtu = MAX_ETH_JUMBO_SIZE; - - /* Valid packet for synch */ - pkts[0].len = MIN_PKT_SIZE; - pkts[0].valid = true; - - /* One valid packet with the max amount of frags */ - for (i = 1; i < max_frags + 1; i++) { - pkts[i].len = MIN_PKT_SIZE; - pkts[i].options = XDP_PKT_CONTD; - pkts[i].valid = true; - } - pkts[max_frags].options = 0; - - /* An invalid packet with the max amount of frags but signals packet - * continues on the last frag - */ - for (i = max_frags + 1; i < 2 * max_frags + 1; i++) { - pkts[i].len = MIN_PKT_SIZE; - pkts[i].options = XDP_PKT_CONTD; - pkts[i].valid = false; - } - - /* Valid packet for synch */ - pkts[2 * max_frags + 1].len = MIN_PKT_SIZE; - pkts[2 * max_frags + 1].valid = true; - - pkt_stream_generate_custom(test, pkts, 2 * max_frags + 2); - ret = testapp_validate_traffic(test); - - free(pkts); - return ret; -} - -static int xsk_load_xdp_programs(struct ifobject *ifobj) -{ - ifobj->xdp_progs = xsk_xdp_progs__open_and_load(); - if (libbpf_get_error(ifobj->xdp_progs)) - return libbpf_get_error(ifobj->xdp_progs); - - return 0; -} - -static void xsk_unload_xdp_programs(struct ifobject *ifobj) -{ - xsk_xdp_progs__destroy(ifobj->xdp_progs); -} - -/* Simple test */ -static bool hugepages_present(void) -{ - size_t mmap_sz = 2 * DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE; - void *bufs; - - bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, MAP_HUGE_2MB); - if (bufs == MAP_FAILED) - return false; - - mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; - munmap(bufs, mmap_sz); - return true; -} - -static void init_iface(struct ifobject *ifobj, thread_func_t func_ptr) -{ - LIBBPF_OPTS(bpf_xdp_query_opts, query_opts); - int err; - - ifobj->func_ptr = func_ptr; - - err = xsk_load_xdp_programs(ifobj); - if (err) { - ksft_print_msg("Error loading XDP program\n"); - exit_with_error(err); - } - - if (hugepages_present()) - ifobj->unaligned_supp = true; - - err = bpf_xdp_query(ifobj->ifindex, XDP_FLAGS_DRV_MODE, &query_opts); - if (err) { - ksft_print_msg("Error querying XDP capabilities\n"); - exit_with_error(-err); - } - if (query_opts.feature_flags & NETDEV_XDP_ACT_RX_SG) - ifobj->multi_buff_supp = true; - if (query_opts.feature_flags & NETDEV_XDP_ACT_XSK_ZEROCOPY) { - if (query_opts.xdp_zc_max_segs > 1) { - ifobj->multi_buff_zc_supp = true; - ifobj->xdp_zc_max_segs = query_opts.xdp_zc_max_segs; - } else { - ifobj->xdp_zc_max_segs = 0; - } - } -} - -static int testapp_send_receive(struct test_spec *test) -{ - return testapp_validate_traffic(test); -} - -static int testapp_send_receive_2k_frame(struct test_spec *test) -{ - test->ifobj_tx->umem->frame_size = 2048; - test->ifobj_rx->umem->frame_size = 2048; - pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE); - return testapp_validate_traffic(test); -} - -static int testapp_poll_rx(struct test_spec *test) -{ - test->ifobj_rx->use_poll = true; - return testapp_validate_traffic(test); -} - -static int testapp_poll_tx(struct test_spec *test) -{ - test->ifobj_tx->use_poll = true; - return testapp_validate_traffic(test); -} - -static int testapp_aligned_inv_desc(struct test_spec *test) -{ - return testapp_invalid_desc(test); -} - -static int testapp_aligned_inv_desc_2k_frame(struct test_spec *test) -{ - test->ifobj_tx->umem->frame_size = 2048; - test->ifobj_rx->umem->frame_size = 2048; - return testapp_invalid_desc(test); -} - -static int testapp_unaligned_inv_desc(struct test_spec *test) -{ - test->ifobj_tx->umem->unaligned_mode = true; - test->ifobj_rx->umem->unaligned_mode = true; - return testapp_invalid_desc(test); -} - -static int testapp_unaligned_inv_desc_4001_frame(struct test_spec *test) -{ - u64 page_size, umem_size; - - /* Odd frame size so the UMEM doesn't end near a page boundary. */ - test->ifobj_tx->umem->frame_size = 4001; - test->ifobj_rx->umem->frame_size = 4001; - test->ifobj_tx->umem->unaligned_mode = true; - test->ifobj_rx->umem->unaligned_mode = true; - /* This test exists to test descriptors that staddle the end of - * the UMEM but not a page. - */ - page_size = sysconf(_SC_PAGESIZE); - umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size; - assert(umem_size % page_size > MIN_PKT_SIZE); - assert(umem_size % page_size < page_size - MIN_PKT_SIZE); - - return testapp_invalid_desc(test); -} - -static int testapp_aligned_inv_desc_mb(struct test_spec *test) -{ - return testapp_invalid_desc_mb(test); -} - -static int testapp_unaligned_inv_desc_mb(struct test_spec *test) -{ - test->ifobj_tx->umem->unaligned_mode = true; - test->ifobj_rx->umem->unaligned_mode = true; - return testapp_invalid_desc_mb(test); -} - -static int testapp_xdp_metadata(struct test_spec *test) -{ - return testapp_xdp_metadata_copy(test); -} - -static int testapp_xdp_metadata_mb(struct test_spec *test) -{ - test->mtu = MAX_ETH_JUMBO_SIZE; - return testapp_xdp_metadata_copy(test); -} - -static int testapp_hw_sw_min_ring_size(struct test_spec *test) -{ - int ret; - - test->set_ring = true; - test->total_steps = 2; - test->ifobj_tx->ring.tx_pending = DEFAULT_BATCH_SIZE; - test->ifobj_tx->ring.rx_pending = DEFAULT_BATCH_SIZE * 2; - test->ifobj_tx->xsk->batch_size = 1; - test->ifobj_rx->xsk->batch_size = 1; - ret = testapp_validate_traffic(test); - if (ret) - return ret; - - /* Set batch size to hw_ring_size - 1 */ - test->ifobj_tx->xsk->batch_size = DEFAULT_BATCH_SIZE - 1; - test->ifobj_rx->xsk->batch_size = DEFAULT_BATCH_SIZE - 1; - return testapp_validate_traffic(test); -} - -static int testapp_hw_sw_max_ring_size(struct test_spec *test) -{ - u32 max_descs = XSK_RING_PROD__DEFAULT_NUM_DESCS * 4; - int ret; - - test->set_ring = true; - test->total_steps = 2; - test->ifobj_tx->ring.tx_pending = test->ifobj_tx->ring.tx_max_pending; - test->ifobj_tx->ring.rx_pending = test->ifobj_tx->ring.rx_max_pending; - test->ifobj_rx->umem->num_frames = max_descs; - test->ifobj_rx->umem->fill_size = max_descs; - test->ifobj_rx->umem->comp_size = max_descs; - test->ifobj_tx->xsk->batch_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - test->ifobj_rx->xsk->batch_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - - ret = testapp_validate_traffic(test); - if (ret) - return ret; - - /* Set batch_size to 8152 for testing, as the ice HW ignores the 3 lowest bits when - * updating the Rx HW tail register. - */ - test->ifobj_tx->xsk->batch_size = test->ifobj_tx->ring.tx_max_pending - 8; - test->ifobj_rx->xsk->batch_size = test->ifobj_tx->ring.tx_max_pending - 8; - pkt_stream_replace(test, max_descs, MIN_PKT_SIZE); - return testapp_validate_traffic(test); -} - -static int testapp_xdp_adjust_tail(struct test_spec *test, int adjust_value) -{ - struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; - struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; - - test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_adjust_tail, - skel_tx->progs.xsk_xdp_adjust_tail, - skel_rx->maps.xsk, skel_tx->maps.xsk); - - skel_rx->bss->adjust_value = adjust_value; - - return testapp_validate_traffic(test); -} - -static int testapp_adjust_tail(struct test_spec *test, u32 value, u32 pkt_len) -{ - int ret; - - test->adjust_tail_support = true; - test->adjust_tail = true; - test->total_steps = 1; - - pkt_stream_replace_ifobject(test->ifobj_tx, DEFAULT_BATCH_SIZE, pkt_len); - pkt_stream_replace_ifobject(test->ifobj_rx, DEFAULT_BATCH_SIZE, pkt_len + value); - - ret = testapp_xdp_adjust_tail(test, value); - if (ret) - return ret; - - if (!test->adjust_tail_support) { - ksft_test_result_skip("%s %sResize pkt with bpf_xdp_adjust_tail() not supported\n", - mode_string(test), busy_poll_string(test)); - return TEST_SKIP; - } - - return 0; -} - -static int testapp_adjust_tail_shrink(struct test_spec *test) -{ - /* Shrink by 4 bytes for testing purpose */ - return testapp_adjust_tail(test, -4, MIN_PKT_SIZE * 2); -} - -static int testapp_adjust_tail_shrink_mb(struct test_spec *test) -{ - test->mtu = MAX_ETH_JUMBO_SIZE; - /* Shrink by the frag size */ - return testapp_adjust_tail(test, -XSK_UMEM__MAX_FRAME_SIZE, XSK_UMEM__LARGE_FRAME_SIZE * 2); -} - -static int testapp_adjust_tail_grow(struct test_spec *test) -{ - /* Grow by 4 bytes for testing purpose */ - return testapp_adjust_tail(test, 4, MIN_PKT_SIZE * 2); -} - -static int testapp_adjust_tail_grow_mb(struct test_spec *test) -{ - test->mtu = MAX_ETH_JUMBO_SIZE; - /* Grow by (frag_size - last_frag_Size) - 1 to stay inside the last fragment */ - return testapp_adjust_tail(test, (XSK_UMEM__MAX_FRAME_SIZE / 2) - 1, - XSK_UMEM__LARGE_FRAME_SIZE * 2); -} - -static int testapp_tx_queue_consumer(struct test_spec *test) -{ - int nr_packets; - - if (test->mode == TEST_MODE_ZC) { - ksft_test_result_skip("Can not run TX_QUEUE_CONSUMER test for ZC mode\n"); - return TEST_SKIP; - } - - nr_packets = MAX_TX_BUDGET_DEFAULT + 1; - pkt_stream_replace(test, nr_packets, MIN_PKT_SIZE); - test->ifobj_tx->xsk->batch_size = nr_packets; - test->ifobj_tx->xsk->check_consumer = true; - - return testapp_validate_traffic(test); -} - -static void run_pkt_test(struct test_spec *test) -{ - int ret; - - ret = test->test_func(test); - - if (ret == TEST_PASS) - ksft_test_result_pass("PASS: %s %s%s\n", mode_string(test), busy_poll_string(test), - test->name); - pkt_stream_restore_default(test); -} - -static struct ifobject *ifobject_create(void) -{ - struct ifobject *ifobj; - - ifobj = calloc(1, sizeof(struct ifobject)); - if (!ifobj) - return NULL; - - ifobj->xsk_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->xsk_arr)); - if (!ifobj->xsk_arr) - goto out_xsk_arr; - - ifobj->umem = calloc(1, sizeof(*ifobj->umem)); - if (!ifobj->umem) - goto out_umem; - - return ifobj; - -out_umem: - free(ifobj->xsk_arr); -out_xsk_arr: - free(ifobj); - return NULL; -} - -static void ifobject_delete(struct ifobject *ifobj) -{ - free(ifobj->umem); - free(ifobj->xsk_arr); - free(ifobj); -} - -static bool is_xdp_supported(int ifindex) -{ - int flags = XDP_FLAGS_DRV_MODE; - - LIBBPF_OPTS(bpf_link_create_opts, opts, .flags = flags); - struct bpf_insn insns[2] = { - BPF_MOV64_IMM(BPF_REG_0, XDP_PASS), - BPF_EXIT_INSN() - }; - int prog_fd, insn_cnt = ARRAY_SIZE(insns); - int err; - - prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL); - if (prog_fd < 0) - return false; - - err = bpf_xdp_attach(ifindex, prog_fd, flags, NULL); - if (err) { - close(prog_fd); - return false; - } - - bpf_xdp_detach(ifindex, flags, NULL); - close(prog_fd); - - return true; -} - -static const struct test_spec tests[] = { - {.name = "SEND_RECEIVE", .test_func = testapp_send_receive}, - {.name = "SEND_RECEIVE_2K_FRAME", .test_func = testapp_send_receive_2k_frame}, - {.name = "SEND_RECEIVE_SINGLE_PKT", .test_func = testapp_single_pkt}, - {.name = "POLL_RX", .test_func = testapp_poll_rx}, - {.name = "POLL_TX", .test_func = testapp_poll_tx}, - {.name = "POLL_RXQ_FULL", .test_func = testapp_poll_rxq_tmout}, - {.name = "POLL_TXQ_FULL", .test_func = testapp_poll_txq_tmout}, - {.name = "SEND_RECEIVE_UNALIGNED", .test_func = testapp_send_receive_unaligned}, - {.name = "ALIGNED_INV_DESC", .test_func = testapp_aligned_inv_desc}, - {.name = "ALIGNED_INV_DESC_2K_FRAME_SIZE", .test_func = testapp_aligned_inv_desc_2k_frame}, - {.name = "UNALIGNED_INV_DESC", .test_func = testapp_unaligned_inv_desc}, - {.name = "UNALIGNED_INV_DESC_4001_FRAME_SIZE", - .test_func = testapp_unaligned_inv_desc_4001_frame}, - {.name = "UMEM_HEADROOM", .test_func = testapp_headroom}, - {.name = "TEARDOWN", .test_func = testapp_teardown}, - {.name = "BIDIRECTIONAL", .test_func = testapp_bidirectional}, - {.name = "STAT_RX_DROPPED", .test_func = testapp_stats_rx_dropped}, - {.name = "STAT_TX_INVALID", .test_func = testapp_stats_tx_invalid_descs}, - {.name = "STAT_RX_FULL", .test_func = testapp_stats_rx_full}, - {.name = "STAT_FILL_EMPTY", .test_func = testapp_stats_fill_empty}, - {.name = "XDP_PROG_CLEANUP", .test_func = testapp_xdp_prog_cleanup}, - {.name = "XDP_DROP_HALF", .test_func = testapp_xdp_drop}, - {.name = "XDP_SHARED_UMEM", .test_func = testapp_xdp_shared_umem}, - {.name = "XDP_METADATA_COPY", .test_func = testapp_xdp_metadata}, - {.name = "XDP_METADATA_COPY_MULTI_BUFF", .test_func = testapp_xdp_metadata_mb}, - {.name = "SEND_RECEIVE_9K_PACKETS", .test_func = testapp_send_receive_mb}, - {.name = "SEND_RECEIVE_UNALIGNED_9K_PACKETS", - .test_func = testapp_send_receive_unaligned_mb}, - {.name = "ALIGNED_INV_DESC_MULTI_BUFF", .test_func = testapp_aligned_inv_desc_mb}, - {.name = "UNALIGNED_INV_DESC_MULTI_BUFF", .test_func = testapp_unaligned_inv_desc_mb}, - {.name = "TOO_MANY_FRAGS", .test_func = testapp_too_many_frags}, - {.name = "HW_SW_MIN_RING_SIZE", .test_func = testapp_hw_sw_min_ring_size}, - {.name = "HW_SW_MAX_RING_SIZE", .test_func = testapp_hw_sw_max_ring_size}, - {.name = "XDP_ADJUST_TAIL_SHRINK", .test_func = testapp_adjust_tail_shrink}, - {.name = "XDP_ADJUST_TAIL_SHRINK_MULTI_BUFF", .test_func = testapp_adjust_tail_shrink_mb}, - {.name = "XDP_ADJUST_TAIL_GROW", .test_func = testapp_adjust_tail_grow}, - {.name = "XDP_ADJUST_TAIL_GROW_MULTI_BUFF", .test_func = testapp_adjust_tail_grow_mb}, - {.name = "TX_QUEUE_CONSUMER", .test_func = testapp_tx_queue_consumer}, - }; - static void print_tests(void) { u32 i; @@ -2833,7 +376,7 @@ int main(int argc, char **argv) init_iface(ifobj_rx, worker_testapp_validate_rx); init_iface(ifobj_tx, worker_testapp_validate_tx); - test_spec_init(&test, ifobj_tx, ifobj_rx, 0, &tests[0]); + test_init(&test, ifobj_tx, ifobj_rx, 0, &tests[0]); tx_pkt_stream_default = pkt_stream_generate(DEFAULT_PKT_CNT, MIN_PKT_SIZE); rx_pkt_stream_default = pkt_stream_generate(DEFAULT_PKT_CNT, MIN_PKT_SIZE); if (!tx_pkt_stream_default || !rx_pkt_stream_default) @@ -2868,7 +411,7 @@ int main(int argc, char **argv) if (opt_run_test != RUN_ALL_TESTS && j != opt_run_test) continue; - test_spec_init(&test, ifobj_tx, ifobj_rx, i, &tests[j]); + test_init(&test, ifobj_tx, ifobj_rx, i, &tests[j]); run_pkt_test(&test); usleep(USLEEP_MAX); diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h index 4df3a5d329acf8..3ca518df23adaf 100644 --- a/tools/testing/selftests/bpf/xskxceiver.h +++ b/tools/testing/selftests/bpf/xskxceiver.h @@ -22,169 +22,13 @@ #define PF_XDP AF_XDP #endif -#ifndef SO_BUSY_POLL_BUDGET -#define SO_BUSY_POLL_BUDGET 70 -#endif - -#ifndef SO_PREFER_BUSY_POLL -#define SO_PREFER_BUSY_POLL 69 -#endif - -#define TEST_PASS 0 -#define TEST_FAILURE -1 -#define TEST_CONTINUE 1 -#define TEST_SKIP 2 -#define MAX_INTERFACES 2 -#define MAX_INTERFACE_NAME_CHARS 16 -#define MAX_TEST_NAME_SIZE 48 #define MAX_TEARDOWN_ITER 10 -#define PKT_HDR_SIZE (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */ -#define MIN_PKT_SIZE 64 -#define MAX_ETH_PKT_SIZE 1518 #define MAX_ETH_JUMBO_SIZE 9000 -#define USLEEP_MAX 10000 #define SOCK_RECONF_CTR 10 -#define DEFAULT_BATCH_SIZE 64 -#define POLL_TMOUT 1000 -#define THREAD_TMOUT 3 -#define DEFAULT_PKT_CNT (4 * 1024) -#define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4) #define RX_FULL_RXQSIZE 32 #define UMEM_HEADROOM_TEST_SIZE 128 #define XSK_UMEM__INVALID_FRAME_SIZE (MAX_ETH_JUMBO_SIZE + 1) -#define XSK_UMEM__LARGE_FRAME_SIZE (3 * 1024) -#define XSK_UMEM__MAX_FRAME_SIZE (4 * 1024) -#define XSK_DESC__INVALID_OPTION (0xffff) -#define HUGEPAGE_SIZE (2 * 1024 * 1024) -#define PKT_DUMP_NB_TO_PRINT 16 #define RUN_ALL_TESTS UINT_MAX #define NUM_MAC_ADDRESSES 4 -#define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0) - -enum test_mode { - TEST_MODE_SKB, - TEST_MODE_DRV, - TEST_MODE_ZC, - TEST_MODE_ALL -}; - -struct xsk_umem_info { - struct xsk_ring_prod fq; - struct xsk_ring_cons cq; - struct xsk_umem *umem; - u64 next_buffer; - u32 num_frames; - u32 frame_headroom; - void *buffer; - u32 frame_size; - u32 base_addr; - u32 fill_size; - u32 comp_size; - bool unaligned_mode; -}; - -struct xsk_socket_info { - struct xsk_ring_cons rx; - struct xsk_ring_prod tx; - struct xsk_umem_info *umem; - struct xsk_socket *xsk; - struct pkt_stream *pkt_stream; - u32 outstanding_tx; - u32 rxqsize; - u32 batch_size; - u8 dst_mac[ETH_ALEN]; - u8 src_mac[ETH_ALEN]; - bool check_consumer; -}; - -struct pkt { - int offset; - u32 len; - u32 pkt_nb; - bool valid; - u16 options; -}; - -struct pkt_stream { - u32 nb_pkts; - u32 current_pkt_nb; - struct pkt *pkts; - u32 max_pkt_len; - u32 nb_rx_pkts; - u32 nb_valid_entries; - bool verbatim; -}; - -struct set_hw_ring { - u32 default_tx; - u32 default_rx; -}; - -struct ifobject; -struct test_spec; -typedef int (*validation_func_t)(struct ifobject *ifobj); -typedef void *(*thread_func_t)(void *arg); -typedef int (*test_func_t)(struct test_spec *test); - -struct ifobject { - char ifname[MAX_INTERFACE_NAME_CHARS]; - struct xsk_socket_info *xsk; - struct xsk_socket_info *xsk_arr; - struct xsk_umem_info *umem; - thread_func_t func_ptr; - validation_func_t validation_func; - struct xsk_xdp_progs *xdp_progs; - struct bpf_map *xskmap; - struct bpf_program *xdp_prog; - struct ethtool_ringparam ring; - struct set_hw_ring set_ring; - enum test_mode mode; - int ifindex; - int mtu; - u32 bind_flags; - u32 xdp_zc_max_segs; - bool tx_on; - bool rx_on; - bool use_poll; - bool busy_poll; - bool use_fill_ring; - bool release_rx; - bool shared_umem; - bool use_metadata; - bool unaligned_supp; - bool multi_buff_supp; - bool multi_buff_zc_supp; - bool hw_ring_size_supp; -}; - -struct test_spec { - struct ifobject *ifobj_tx; - struct ifobject *ifobj_rx; - struct pkt_stream *tx_pkt_stream_default; - struct pkt_stream *rx_pkt_stream_default; - struct bpf_program *xdp_prog_rx; - struct bpf_program *xdp_prog_tx; - struct bpf_map *xskmap_rx; - struct bpf_map *xskmap_tx; - test_func_t test_func; - int mtu; - u16 total_steps; - u16 current_step; - u16 nb_sockets; - bool fail; - bool set_ring; - bool adjust_tail; - bool adjust_tail_support; - enum test_mode mode; - char name[MAX_TEST_NAME_SIZE]; -}; - -pthread_barrier_t barr; -pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER; - -int pkts_in_flight; - -static const u8 g_mac[ETH_ALEN] = {0x55, 0x44, 0x33, 0x22, 0x11, 0x00}; - #endif /* XSKXCEIVER_H_ */ diff --git a/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh index c4711272fe45d5..559f300f965aa2 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh @@ -30,6 +30,7 @@ check_connection() local message=${3} RET=0 + sleep 0.25 ip netns exec ${ns} ping ${target} -c 4 -i 0.1 &>/dev/null check_err $? "ping failed" log_test "${bond_mode}/${xvlan_type}_${xvlan_mode}: ${message}" diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py index fb010a48a5a196..a86f5c311fdcba 100644 --- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py @@ -22,7 +22,7 @@ NlError, RtnlFamily, DevlinkFamily, PSPFamily from net.lib.py import CmdExitFailure from net.lib.py import bkg, cmd, bpftool, bpftrace, defer, ethtool, \ - fd_read_timeout, ip, rand_port, wait_port_listen, wait_file + fd_read_timeout, ip, rand_port, wait_port_listen, wait_file, tool from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \ ksft_setup @@ -37,7 +37,7 @@ "CmdExitFailure", "bkg", "cmd", "bpftool", "bpftrace", "defer", "ethtool", "fd_read_timeout", "ip", "rand_port", - "wait_port_listen", "wait_file", + "wait_port_listen", "wait_file", "tool", "KsftSkipEx", "KsftFailEx", "KsftXfailEx", "ksft_disruptive", "ksft_exit", "ksft_pr", "ksft_run", "ksft_setup", diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh index 87f89fd92f8c11..64d3941576d5db 100644 --- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh +++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh @@ -247,9 +247,9 @@ function listen_port_and_save_to() { SOCAT_MODE="UDP6-LISTEN" fi - # Just wait for 2 seconds - timeout 2 ip netns exec "${NAMESPACE}" \ - socat "${SOCAT_MODE}":"${PORT}",fork "${OUTPUT}" + # Just wait for 3 seconds + timeout 3 ip netns exec "${NAMESPACE}" \ + socat "${SOCAT_MODE}":"${PORT}",fork "${OUTPUT}" 2> /dev/null } # Only validate that the message arrived properly diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh index 0441a18f098b10..aac8ef490feb80 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh @@ -317,7 +317,7 @@ police_limits_test() tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ flower skip_sw \ - action police rate 0.5kbit burst 1m conform-exceed drop/ok + action police rate 0.5kbit burst 2k conform-exceed drop/ok check_fail $? "Incorrect success to add police action with too low rate" tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ @@ -327,7 +327,7 @@ police_limits_test() tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \ flower skip_sw \ - action police rate 1.5kbit burst 1m conform-exceed drop/ok + action police rate 1.5kbit burst 2k conform-exceed drop/ok check_err $? "Failed to add police action with low rate" tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower diff --git a/tools/testing/selftests/drivers/net/psp.py b/tools/testing/selftests/drivers/net/psp.py index 4ae7a785ff10a3..473573e216e34e 100755 --- a/tools/testing/selftests/drivers/net/psp.py +++ b/tools/testing/selftests/drivers/net/psp.py @@ -560,8 +560,9 @@ def psp_ip_ver_test_builder(name, test_func, psp_ver, ipver): """Build test cases for each combo of PSP version and IP version""" def test_case(cfg): cfg.require_ipver(ipver) - test_case.__name__ = f"{name}_v{psp_ver}_ip{ipver}" test_func(cfg, psp_ver, ipver) + + test_case.__name__ = f"{name}_v{psp_ver}_ip{ipver}" return test_case @@ -569,8 +570,9 @@ def ipver_test_builder(name, test_func, ipver): """Build test cases for each IP version""" def test_case(cfg): cfg.require_ipver(ipver) - test_case.__name__ = f"{name}_ip{ipver}" test_func(cfg, ipver) + + test_case.__name__ = f"{name}_ip{ipver}" return test_case diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc index aee22289536b1b..1b57771dbfdf07 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc @@ -90,9 +90,10 @@ if [ $on != "0" ]; then fail "Tracing is not off" fi -csum1=`md5sum trace` +# Cannot rely on names being around as they are only cached, strip them +csum1=`cat trace | sed -e 's/^ *[^ ]*\(-[0-9][0-9]*\)/\1/' | md5sum` sleep $SLEEP_TIME -csum2=`md5sum trace` +csum2=`cat trace | sed -e 's/^ *[^ ]*\(-[0-9][0-9]*\)/\1/' | md5sum` if [ "$csum1" != "$csum2" ]; then fail "Tracing file is still changing" diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index bb4d33dde3c899..1f52140d9d9ee3 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -758,9 +758,6 @@ TEST_F(iommufd_ioas, get_hw_info) struct iommu_test_hw_info info; uint64_t trailing_bytes; } buffer_larger; - struct iommu_test_hw_info_buffer_smaller { - __u32 flags; - } buffer_smaller; if (self->device_id) { uint8_t max_pasid = 0; @@ -792,8 +789,9 @@ TEST_F(iommufd_ioas, get_hw_info) * the fields within the size range still gets updated. */ test_cmd_get_hw_info(self->device_id, - IOMMU_HW_INFO_TYPE_DEFAULT, - &buffer_smaller, sizeof(buffer_smaller)); + IOMMU_HW_INFO_TYPE_DEFAULT, &buffer_exact, + offsetofend(struct iommu_test_hw_info, + flags)); test_cmd_get_hw_info_pasid(self->device_id, &max_pasid); ASSERT_EQ(0, max_pasid); if (variant->pasid_capable) { diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index d9fffe06d3eae4..f2b223072b626a 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -6,7 +6,7 @@ ARCH ?= $(SUBARCH) ifeq ($(ARCH),$(filter $(ARCH),arm64 s390 riscv x86 x86_64 loongarch)) # Top-level selftests allows ARCH=x86_64 :-( ifeq ($(ARCH),x86_64) - ARCH := x86 + override ARCH := x86 endif include Makefile.kvm else diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index 148d427ff24bef..1715efe9d5b0d2 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -245,6 +245,7 @@ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -Wno-gnu-variable-sized-type-not-at-end -MD -MP -DCONFIG_64BIT \ + -U_FORTIFY_SOURCE \ -fno-builtin-memcmp -fno-builtin-memcpy \ -fno-builtin-memset -fno-builtin-strnlen \ -fno-stack-protector -fno-PIE -fno-strict-aliasing \ diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c index 1375fca80bcdbe..f80ad6b47d16b0 100644 --- a/tools/testing/selftests/kvm/rseq_test.c +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -215,6 +215,7 @@ int main(int argc, char *argv[]) switch (opt) { case 'u': skip_sanity_check = true; + break; case 'l': latency = atoi_paranoid(optarg); break; diff --git a/tools/testing/selftests/kvm/x86/amx_test.c b/tools/testing/selftests/kvm/x86/amx_test.c index f4ce5a185a7ddf..bee56c1f783399 100644 --- a/tools/testing/selftests/kvm/x86/amx_test.c +++ b/tools/testing/selftests/kvm/x86/amx_test.c @@ -124,6 +124,20 @@ static void set_tilecfg(struct tile_config *cfg) } } +enum { + /* Retrieve TMM0 from guest, stash it for TEST_RESTORE_TILEDATA */ + TEST_SAVE_TILEDATA = 1, + + /* Check TMM0 against tiledata */ + TEST_COMPARE_TILEDATA = 2, + + /* Restore TMM0 from earlier save */ + TEST_RESTORE_TILEDATA = 4, + + /* Full VM save/restore */ + TEST_SAVE_RESTORE = 8, +}; + static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, struct tile_data *tiledata, struct xstate *xstate) @@ -131,20 +145,29 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE) && this_cpu_has(X86_FEATURE_OSXSAVE)); check_xtile_info(); - GUEST_SYNC(1); + GUEST_SYNC(TEST_SAVE_RESTORE); /* xfd=0, enable amx */ wrmsr(MSR_IA32_XFD, 0); - GUEST_SYNC(2); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == 0); set_tilecfg(amx_cfg); __ldtilecfg(amx_cfg); - GUEST_SYNC(3); + GUEST_SYNC(TEST_SAVE_RESTORE); /* Check save/restore when trap to userspace */ __tileloadd(tiledata); - GUEST_SYNC(4); + GUEST_SYNC(TEST_SAVE_TILEDATA | TEST_COMPARE_TILEDATA | TEST_SAVE_RESTORE); + + /* xfd=0x40000, disable amx tiledata */ + wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA); + + /* host tries setting tiledata while guest XFD is set */ + GUEST_SYNC(TEST_RESTORE_TILEDATA); + GUEST_SYNC(TEST_SAVE_RESTORE); + + wrmsr(MSR_IA32_XFD, 0); __tilerelease(); - GUEST_SYNC(5); + GUEST_SYNC(TEST_SAVE_RESTORE); /* * After XSAVEC, XTILEDATA is cleared in the xstate_bv but is set in * the xcomp_bv. @@ -154,6 +177,8 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); GUEST_ASSERT(xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA); + /* #NM test */ + /* xfd=0x40000, disable amx tiledata */ wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA); @@ -166,13 +191,13 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); GUEST_ASSERT((xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA)); - GUEST_SYNC(6); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); set_tilecfg(amx_cfg); __ldtilecfg(amx_cfg); /* Trigger #NM exception */ __tileloadd(tiledata); - GUEST_SYNC(10); + GUEST_SYNC(TEST_COMPARE_TILEDATA | TEST_SAVE_RESTORE); GUEST_DONE(); } @@ -180,18 +205,18 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, void guest_nm_handler(struct ex_regs *regs) { /* Check if #NM is triggered by XFEATURE_MASK_XTILE_DATA */ - GUEST_SYNC(7); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(!(get_cr0() & X86_CR0_TS)); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); - GUEST_SYNC(8); + GUEST_SYNC(TEST_SAVE_RESTORE); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); /* Clear xfd_err */ wrmsr(MSR_IA32_XFD_ERR, 0); /* xfd=0, enable amx */ wrmsr(MSR_IA32_XFD, 0); - GUEST_SYNC(9); + GUEST_SYNC(TEST_SAVE_RESTORE); } int main(int argc, char *argv[]) @@ -200,10 +225,10 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_x86_state *state; + struct kvm_x86_state *tile_state = NULL; int xsave_restore_size; vm_vaddr_t amx_cfg, tiledata, xstate; struct ucall uc; - u32 amx_offset; int ret; /* @@ -244,6 +269,7 @@ int main(int argc, char *argv[]) memset(addr_gva2hva(vm, xstate), 0, PAGE_SIZE * DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xstate); + int iter = 0; for (;;) { vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); @@ -253,37 +279,47 @@ int main(int argc, char *argv[]) REPORT_GUEST_ASSERT(uc); /* NOT REACHED */ case UCALL_SYNC: - switch (uc.args[1]) { - case 1: - case 2: - case 3: - case 5: - case 6: - case 7: - case 8: - fprintf(stderr, "GUEST_SYNC(%ld)\n", uc.args[1]); - break; - case 4: - case 10: - fprintf(stderr, - "GUEST_SYNC(%ld), check save/restore status\n", uc.args[1]); + ++iter; + if (uc.args[1] & TEST_SAVE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, save tiledata\n", iter); + tile_state = vcpu_save_state(vcpu); + } + if (uc.args[1] & TEST_COMPARE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, check TMM0 contents\n", iter); /* Compacted mode, get amx offset by xsave area * size subtract 8K amx size. */ - amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE; - state = vcpu_save_state(vcpu); - void *amx_start = (void *)state->xsave + amx_offset; + u32 amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE; + void *amx_start = (void *)tile_state->xsave + amx_offset; void *tiles_data = (void *)addr_gva2hva(vm, tiledata); /* Only check TMM0 register, 1 tile */ ret = memcmp(amx_start, tiles_data, TILE_SIZE); TEST_ASSERT(ret == 0, "memcmp failed, ret=%d", ret); + } + if (uc.args[1] & TEST_RESTORE_TILEDATA) { + fprintf(stderr, "GUEST_SYNC #%d, before KVM_SET_XSAVE\n", iter); + vcpu_xsave_set(vcpu, tile_state->xsave); + fprintf(stderr, "GUEST_SYNC #%d, after KVM_SET_XSAVE\n", iter); + } + if (uc.args[1] & TEST_SAVE_RESTORE) { + fprintf(stderr, "GUEST_SYNC #%d, save/restore VM state\n", iter); + state = vcpu_save_state(vcpu); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vcpu, ®s1); + + kvm_vm_release(vm); + + /* Restore state in a new VM. */ + vcpu = vm_recreate_with_one_vcpu(vm); + vcpu_load_state(vcpu, state); kvm_x86_state_cleanup(state); - break; - case 9: - fprintf(stderr, - "GUEST_SYNC(%ld), #NM exception and enable amx\n", uc.args[1]); - break; + + memset(®s2, 0, sizeof(regs2)); + vcpu_regs_get(vcpu, ®s2); + TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), + "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", + (ulong) regs2.rdi, (ulong) regs2.rsi); } break; case UCALL_DONE: @@ -293,22 +329,6 @@ int main(int argc, char *argv[]) TEST_FAIL("Unknown ucall %lu", uc.cmd); } - state = vcpu_save_state(vcpu); - memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vcpu, ®s1); - - kvm_vm_release(vm); - - /* Restore state in a new VM. */ - vcpu = vm_recreate_with_one_vcpu(vm); - vcpu_load_state(vcpu, state); - kvm_x86_state_cleanup(state); - - memset(®s2, 0, sizeof(regs2)); - vcpu_regs_get(vcpu, ®s2); - TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), - "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", - (ulong) regs2.rdi, (ulong) regs2.rsi); } done: kvm_vm_free(vm); diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile index a3f449914bf93a..044b83bde16ebe 100644 --- a/tools/testing/selftests/landlock/Makefile +++ b/tools/testing/selftests/landlock/Makefile @@ -4,7 +4,7 @@ CFLAGS += -Wall -O2 $(KHDR_INCLUDES) -LOCAL_HDRS += common.h +LOCAL_HDRS += $(wildcard *.h) src_test := $(wildcard *_test.c) diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h index 9acecae36f51ba..98c2362954e210 100644 --- a/tools/testing/selftests/landlock/common.h +++ b/tools/testing/selftests/landlock/common.h @@ -237,6 +237,7 @@ struct service_fixture { struct sockaddr_un unix_addr; socklen_t unix_addr_len; }; + struct sockaddr_storage _largest; }; }; diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index fa0f18ec62c41e..29cdbb8367358c 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -4375,9 +4375,6 @@ TEST_F_FORK(layout1, named_unix_domain_socket_ioctl) cli_fd = socket(AF_UNIX, SOCK_STREAM, 0); ASSERT_LE(0, cli_fd); - size = offsetof(struct sockaddr_un, sun_path) + strlen(cli_un.sun_path); - ASSERT_EQ(0, bind(cli_fd, (struct sockaddr *)&cli_un, size)); - bzero(&cli_un, sizeof(cli_un)); cli_un.sun_family = AF_UNIX; strncpy(cli_un.sun_path, path, sizeof(cli_un.sun_path)); @@ -4388,7 +4385,8 @@ TEST_F_FORK(layout1, named_unix_domain_socket_ioctl) /* FIONREAD and other IOCTLs should not be forbidden. */ EXPECT_EQ(0, test_fionread_ioctl(cli_fd)); - ASSERT_EQ(0, close(cli_fd)); + EXPECT_EQ(0, close(cli_fd)); + EXPECT_EQ(0, close(srv_fd)); } /* clang-format off */ diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c index 2a45208551e61a..3bbc0508420b1c 100644 --- a/tools/testing/selftests/landlock/net_test.c +++ b/tools/testing/selftests/landlock/net_test.c @@ -121,6 +121,10 @@ static socklen_t get_addrlen(const struct service_fixture *const srv, { switch (srv->protocol.domain) { case AF_UNSPEC: + if (minimal) + return sizeof(sa_family_t); + return sizeof(struct sockaddr_storage); + case AF_INET: return sizeof(srv->ipv4_addr); @@ -758,6 +762,11 @@ TEST_F(protocol, bind_unspec) bind_fd = socket_variant(&self->srv0); ASSERT_LE(0, bind_fd); + /* Tries to bind with too small addrlen. */ + EXPECT_EQ(-EINVAL, bind_variant_addrlen( + bind_fd, &self->unspec_any0, + get_addrlen(&self->unspec_any0, true) - 1)); + /* Allowed bind on AF_UNSPEC/INADDR_ANY. */ ret = bind_variant(bind_fd, &self->unspec_any0); if (variant->prot.domain == AF_INET) { @@ -766,6 +775,8 @@ TEST_F(protocol, bind_unspec) TH_LOG("Failed to bind to unspec/any socket: %s", strerror(errno)); } + } else if (variant->prot.domain == AF_INET6) { + EXPECT_EQ(-EAFNOSUPPORT, ret); } else { EXPECT_EQ(-EINVAL, ret); } @@ -792,6 +803,8 @@ TEST_F(protocol, bind_unspec) } else { EXPECT_EQ(0, ret); } + } else if (variant->prot.domain == AF_INET6) { + EXPECT_EQ(-EAFNOSUPPORT, ret); } else { EXPECT_EQ(-EINVAL, ret); } @@ -801,7 +814,8 @@ TEST_F(protocol, bind_unspec) bind_fd = socket_variant(&self->srv0); ASSERT_LE(0, bind_fd); ret = bind_variant(bind_fd, &self->unspec_srv0); - if (variant->prot.domain == AF_INET) { + if (variant->prot.domain == AF_INET || + variant->prot.domain == AF_INET6) { EXPECT_EQ(-EAFNOSUPPORT, ret); } else { EXPECT_EQ(-EINVAL, ret) diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 5b993924cc3f5b..2ca07ea7202a5f 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -18,6 +18,9 @@ #include #include #include +#include +#include +#include #include #include @@ -39,6 +42,20 @@ F_SEAL_EXEC) #define MFD_NOEXEC_SEAL 0x0008U +union semun { + int val; + struct semid_ds *buf; + unsigned short int *array; + struct seminfo *__buf; +}; + +/* + * we use semaphores on nested wait tasks due the use of CLONE_NEWPID: the + * child will be PID 1 and can't send SIGSTOP to themselves due special + * treatment of the init task, so the SIGSTOP/SIGCONT synchronization + * approach can't be used here. + */ +#define SEM_KEY 0xdeadbeef /* * Default is not to test hugetlbfs @@ -1333,8 +1350,22 @@ static int sysctl_nested(void *arg) static int sysctl_nested_wait(void *arg) { - /* Wait for a SIGCONT. */ - kill(getpid(), SIGSTOP); + int sem = semget(SEM_KEY, 1, 0600); + struct sembuf sembuf; + + if (sem < 0) { + perror("semget:"); + abort(); + } + sembuf.sem_num = 0; + sembuf.sem_flg = 0; + sembuf.sem_op = 0; + + if (semop(sem, &sembuf, 1) < 0) { + perror("semop:"); + abort(); + } + return sysctl_nested(arg); } @@ -1355,7 +1386,9 @@ static void test_sysctl_sysctl2_failset(void) static int sysctl_nested_child(void *arg) { - int pid; + int pid, sem; + union semun semun; + struct sembuf sembuf; printf("%s nested sysctl 0\n", memfd_str); sysctl_assert_write("0"); @@ -1389,23 +1422,53 @@ static int sysctl_nested_child(void *arg) test_sysctl_sysctl2_failset); join_thread(pid); + sem = semget(SEM_KEY, 1, IPC_CREAT | 0600); + if (sem < 0) { + perror("semget:"); + return 1; + } + semun.val = 1; + sembuf.sem_op = -1; + sembuf.sem_flg = 0; + sembuf.sem_num = 0; + /* Verify that the rules are actually inherited after fork. */ printf("%s nested sysctl 0 -> 1 after fork\n", memfd_str); sysctl_assert_write("0"); + if (semctl(sem, 0, SETVAL, semun) < 0) { + perror("semctl:"); + return 1; + } + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, test_sysctl_sysctl1_failset); sysctl_assert_write("1"); - kill(pid, SIGCONT); + + /* Allow child to continue */ + if (semop(sem, &sembuf, 1) < 0) { + perror("semop:"); + return 1; + } join_thread(pid); printf("%s nested sysctl 0 -> 2 after fork\n", memfd_str); sysctl_assert_write("0"); + if (semctl(sem, 0, SETVAL, semun) < 0) { + perror("semctl:"); + return 1; + } + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, test_sysctl_sysctl2_failset); sysctl_assert_write("2"); - kill(pid, SIGCONT); + + /* Allow child to continue */ + if (semop(sem, &sembuf, 1) < 0) { + perror("semop:"); + return 1; + } join_thread(pid); /* @@ -1415,28 +1478,62 @@ static int sysctl_nested_child(void *arg) */ printf("%s nested sysctl 2 -> 1 after fork\n", memfd_str); sysctl_assert_write("2"); + + if (semctl(sem, 0, SETVAL, semun) < 0) { + perror("semctl:"); + return 1; + } + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, test_sysctl_sysctl2); sysctl_assert_write("1"); - kill(pid, SIGCONT); + + /* Allow child to continue */ + if (semop(sem, &sembuf, 1) < 0) { + perror("semop:"); + return 1; + } join_thread(pid); printf("%s nested sysctl 2 -> 0 after fork\n", memfd_str); sysctl_assert_write("2"); + + if (semctl(sem, 0, SETVAL, semun) < 0) { + perror("semctl:"); + return 1; + } + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, test_sysctl_sysctl2); sysctl_assert_write("0"); - kill(pid, SIGCONT); + + /* Allow child to continue */ + if (semop(sem, &sembuf, 1) < 0) { + perror("semop:"); + return 1; + } join_thread(pid); printf("%s nested sysctl 1 -> 0 after fork\n", memfd_str); sysctl_assert_write("1"); + + if (semctl(sem, 0, SETVAL, semun) < 0) { + perror("semctl:"); + return 1; + } + pid = spawn_thread(CLONE_NEWPID, sysctl_nested_wait, test_sysctl_sysctl1); sysctl_assert_write("0"); - kill(pid, SIGCONT); + /* Allow child to continue */ + if (semop(sem, &sembuf, 1) < 0) { + perror("semop:"); + return 1; + } join_thread(pid); + semctl(sem, 0, IPC_RMID); + return 0; } diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 6560c26f47d1fe..0df61422467da0 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -1612,8 +1612,8 @@ static void run_with_huge_zeropage(non_anon_test_fn fn, const char *desc) * the first sub-page and test if we get another sub-page populated * automatically. */ - FORCE_READ(mem); - FORCE_READ(smem); + FORCE_READ(*mem); + FORCE_READ(*smem); if (!pagemap_is_populated(pagemap_fd, mem + pagesize) || !pagemap_is_populated(pagemap_fd, smem + pagesize)) { ksft_test_result_skip("Did not get THPs populated\n"); @@ -1663,8 +1663,8 @@ static void run_with_memfd(non_anon_test_fn fn, const char *desc) } /* Fault the page in. */ - FORCE_READ(mem); - FORCE_READ(smem); + FORCE_READ(*mem); + FORCE_READ(*smem); fn(mem, smem, pagesize); munmap: @@ -1719,8 +1719,8 @@ static void run_with_tmpfile(non_anon_test_fn fn, const char *desc) } /* Fault the page in. */ - FORCE_READ(mem); - FORCE_READ(smem); + FORCE_READ(*mem); + FORCE_READ(*smem); fn(mem, smem, pagesize); munmap: @@ -1773,8 +1773,8 @@ static void run_with_memfd_hugetlb(non_anon_test_fn fn, const char *desc, } /* Fault the page in. */ - FORCE_READ(mem); - FORCE_READ(smem); + FORCE_READ(*mem); + FORCE_READ(*smem); fn(mem, smem, hugetlbsize); munmap: diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c index 268dadb8ce4385..e15fdd5c62d682 100644 --- a/tools/testing/selftests/mm/gup_longterm.c +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -179,7 +179,7 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared) if (rw && shared && fs_is_unknown(fs_type)) { ksft_print_msg("Unknown filesystem\n"); result = KSFT_SKIP; - return; + break; } /* * R/O pinning or pinning in a private mapping is always diff --git a/tools/testing/selftests/mm/merge.c b/tools/testing/selftests/mm/merge.c index cc4253f47f10b4..cd0e6cc06a0251 100644 --- a/tools/testing/selftests/mm/merge.c +++ b/tools/testing/selftests/mm/merge.c @@ -22,12 +22,37 @@ FIXTURE(merge) struct procmap_fd procmap; }; +static char *map_carveout(unsigned int page_size) +{ + return mmap(NULL, 30 * page_size, PROT_NONE, + MAP_ANON | MAP_PRIVATE, -1, 0); +} + +static pid_t do_fork(struct procmap_fd *procmap) +{ + pid_t pid = fork(); + + if (pid == -1) + return -1; + if (pid != 0) { + wait(NULL); + return pid; + } + + /* Reopen for child. */ + if (close_procmap(procmap)) + return -1; + if (open_self_procmap(procmap)) + return -1; + + return 0; +} + FIXTURE_SETUP(merge) { self->page_size = psize(); /* Carve out PROT_NONE region to map over. */ - self->carveout = mmap(NULL, 30 * self->page_size, PROT_NONE, - MAP_ANON | MAP_PRIVATE, -1, 0); + self->carveout = map_carveout(self->page_size); ASSERT_NE(self->carveout, MAP_FAILED); /* Setup PROCMAP_QUERY interface. */ ASSERT_EQ(open_self_procmap(&self->procmap), 0); @@ -36,7 +61,8 @@ FIXTURE_SETUP(merge) FIXTURE_TEARDOWN(merge) { ASSERT_EQ(munmap(self->carveout, 30 * self->page_size), 0); - ASSERT_EQ(close_procmap(&self->procmap), 0); + /* May fail for parent of forked process. */ + close_procmap(&self->procmap); /* * Clear unconditionally, as some tests set this. It is no issue if this * fails (KSM may be disabled for instance). @@ -44,6 +70,44 @@ FIXTURE_TEARDOWN(merge) prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); } +FIXTURE(merge_with_fork) +{ + unsigned int page_size; + char *carveout; + struct procmap_fd procmap; +}; + +FIXTURE_VARIANT(merge_with_fork) +{ + bool forked; +}; + +FIXTURE_VARIANT_ADD(merge_with_fork, forked) +{ + .forked = true, +}; + +FIXTURE_VARIANT_ADD(merge_with_fork, unforked) +{ + .forked = false, +}; + +FIXTURE_SETUP(merge_with_fork) +{ + self->page_size = psize(); + self->carveout = map_carveout(self->page_size); + ASSERT_NE(self->carveout, MAP_FAILED); + ASSERT_EQ(open_self_procmap(&self->procmap), 0); +} + +FIXTURE_TEARDOWN(merge_with_fork) +{ + ASSERT_EQ(munmap(self->carveout, 30 * self->page_size), 0); + ASSERT_EQ(close_procmap(&self->procmap), 0); + /* See above. */ + prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); +} + TEST_F(merge, mprotect_unfaulted_left) { unsigned int page_size = self->page_size; @@ -322,8 +386,8 @@ TEST_F(merge, forked_target_vma) unsigned int page_size = self->page_size; char *carveout = self->carveout; struct procmap_fd *procmap = &self->procmap; - pid_t pid; char *ptr, *ptr2; + pid_t pid; int i; /* @@ -344,19 +408,10 @@ TEST_F(merge, forked_target_vma) */ ptr[0] = 'x'; - pid = fork(); + pid = do_fork(&self->procmap); ASSERT_NE(pid, -1); - - if (pid != 0) { - wait(NULL); + if (pid != 0) return; - } - - /* Child process below: */ - - /* Reopen for child. */ - ASSERT_EQ(close_procmap(&self->procmap), 0); - ASSERT_EQ(open_self_procmap(&self->procmap), 0); /* unCOWing everything does not cause the AVC to go away. */ for (i = 0; i < 5 * page_size; i += page_size) @@ -386,8 +441,8 @@ TEST_F(merge, forked_source_vma) unsigned int page_size = self->page_size; char *carveout = self->carveout; struct procmap_fd *procmap = &self->procmap; - pid_t pid; char *ptr, *ptr2; + pid_t pid; int i; /* @@ -408,19 +463,10 @@ TEST_F(merge, forked_source_vma) */ ptr[0] = 'x'; - pid = fork(); + pid = do_fork(&self->procmap); ASSERT_NE(pid, -1); - - if (pid != 0) { - wait(NULL); + if (pid != 0) return; - } - - /* Child process below: */ - - /* Reopen for child. */ - ASSERT_EQ(close_procmap(&self->procmap), 0); - ASSERT_EQ(open_self_procmap(&self->procmap), 0); /* unCOWing everything does not cause the AVC to go away. */ for (i = 0; i < 5 * page_size; i += page_size) @@ -1171,4 +1217,288 @@ TEST_F(merge, mremap_correct_placed_faulted) ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); } +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b; + + /* + * mremap() such that A and B merge: + * + * |------------| + * | \ | + * |-----------| | / |---------| + * | unfaulted | v \ | faulted | + * |-----------| / |---------| + * B \ A + */ + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size + 3 * page_size], + 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + /* Fault it in. */ + ptr_a[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMA B in position, + * unfaulted. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* + * Now move VMA A into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + + offset = variant->forked ? 3 * page_size : 6 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + offset); +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b; + + /* + * mremap() such that A and B merge: + * + * |---------------------------| + * | \ | + * | |-----------| / |---------| + * v | unfaulted | \ | faulted | + * |-----------| / |---------| + * B \ A + * + * Then unmap VMA A to trigger the bug. + */ + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + /* Fault it in. */ + ptr_a[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMA B in position, + * unfaulted. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size + 3 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* + * Now move VMA A into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + offset = variant->forked ? 3 * page_size : 6 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + offset); +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev_unfaulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b, *ptr_c; + + /* + * mremap() with MREMAP_DONTUNMAP such that A, B and C merge: + * + * |---------------------------| + * | \ | + * |-----------| | |-----------| / |---------| + * | unfaulted | v | unfaulted | \ | faulted | + * |-----------| |-----------| / |---------| + * A C \ B + */ + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size + 3 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + /* Fault it in. */ + ptr_b[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMAs A, C in position, + * unfaulted. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* Map VMA A into place. */ + + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA C into place. */ + ptr_c = mmap(&self->carveout[page_size + 3 * page_size + 3 * page_size], + 3 * page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_c, MAP_FAILED); + + /* + * Now move VMA B into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + offset = variant->forked ? 3 * page_size : 9 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + offset); + + /* If forked, B and C should also not have merged. */ + if (variant->forked) { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + 3 * page_size); + } +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev_faulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + char *ptr_a, *ptr_b, *ptr_bc; + + /* + * mremap() with MREMAP_DONTUNMAP such that A, B and C merge: + * + * |---------------------------| + * | \ | + * |-----------| | |-----------| / |---------| + * | unfaulted | v | faulted | \ | faulted | + * |-----------| |-----------| / |---------| + * A C \ B + */ + + /* + * Map VMA B and C into place. We have to map them together so their + * anon_vma is the same and the vma->vm_pgoff's are correctly aligned. + */ + ptr_bc = mmap(&self->carveout[page_size + 3 * page_size], + 3 * page_size + 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_bc, MAP_FAILED); + + /* Fault it in. */ + ptr_bc[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move VMA B out the way (splitting VMA BC) so we can place VMA A + * in position, unfaulted, and leave the remainder of the VMA we just + * moved in place, faulted, as VMA C. + */ + ptr_b = mremap(ptr_bc, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* + * Now move VMA B into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* The VMAs should have merged. A,B,C if unforked, B, C if forked. */ + if (variant->forked) { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + 6 * page_size); + } else { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + 9 * page_size); + } +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index f917b4c4c94369..44627d4010f249 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -1317,7 +1317,7 @@ static thread_state thread_state_get(pid_t tid) p = strstr(tmp, header); if (p) { /* For example, "State:\tD (disk sleep)" */ - c = *(p + sizeof(header) - 1); + c = *(p + strlen(header)); return c == 'D' ? THR_STATE_UNINTERRUPTIBLE : THR_STATE_UNKNOWN; } diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 528d14c598bb59..2889403e354680 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,4 +1,9 @@ -CFLAGS += $(KHDR_INCLUDES) -Wall -Wflex-array-member-not-at-end +top_srcdir := ../../../../.. +include $(top_srcdir)/scripts/Makefile.compiler + +cc-option = $(call __cc-option, $(CC),,$(1),$(2)) + +CFLAGS += $(KHDR_INCLUDES) -Wall $(call cc-option,-Wflex-array-member-not-at-end) TEST_GEN_PROGS := \ diag_uid \ diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh index 3ef209cacb8ed3..663744305e5219 100755 --- a/tools/testing/selftests/net/amt.sh +++ b/tools/testing/selftests/net/amt.sh @@ -73,6 +73,8 @@ # +------------------------+ #============================================================================== +source lib.sh + readonly LISTENER=$(mktemp -u listener-XXXXXXXX) readonly GATEWAY=$(mktemp -u gateway-XXXXXXXX) readonly RELAY=$(mktemp -u relay-XXXXXXXX) @@ -246,14 +248,15 @@ test_ipv6_forward() send_mcast4() { - sleep 2 + sleep 5 + wait_local_port_listen ${LISTENER} 4000 udp ip netns exec "${SOURCE}" bash -c \ 'printf "%s %128s" 172.17.0.2 | nc -w 1 -u 239.0.0.1 4000' & } send_mcast6() { - sleep 2 + wait_local_port_listen ${LISTENER} 6000 udp ip netns exec "${SOURCE}" bash -c \ 'printf "%s %128s" 2001:db8:3::2 | nc -w 1 -u ff0e::5:6 6000' & } diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh index ec2d6ceb1f08d3..c01be076b210dd 100755 --- a/tools/testing/selftests/net/fib-onlink-tests.sh +++ b/tools/testing/selftests/net/fib-onlink-tests.sh @@ -120,7 +120,7 @@ log_subsection() run_cmd() { - local cmd="$*" + local cmd="$1" local out local rc @@ -145,7 +145,7 @@ get_linklocal() local pfx local addr - addr=$(${pfx} ip -6 -br addr show dev ${dev} | \ + addr=$(${pfx} ${IP} -6 -br addr show dev ${dev} | \ awk '{ for (i = 3; i <= NF; ++i) { if ($i ~ /^fe80/) @@ -173,58 +173,48 @@ setup() set -e - # create namespace - setup_ns PEER_NS + # create namespaces + setup_ns ns1 + IP="ip -netns $ns1" + setup_ns ns2 # add vrf table - ip li add ${VRF} type vrf table ${VRF_TABLE} - ip li set ${VRF} up - ip ro add table ${VRF_TABLE} unreachable default metric 8192 - ip -6 ro add table ${VRF_TABLE} unreachable default metric 8192 + ${IP} li add ${VRF} type vrf table ${VRF_TABLE} + ${IP} li set ${VRF} up + ${IP} ro add table ${VRF_TABLE} unreachable default metric 8192 + ${IP} -6 ro add table ${VRF_TABLE} unreachable default metric 8192 # create test interfaces - ip li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]} - ip li add ${NETIFS[p3]} type veth peer name ${NETIFS[p4]} - ip li add ${NETIFS[p5]} type veth peer name ${NETIFS[p6]} - ip li add ${NETIFS[p7]} type veth peer name ${NETIFS[p8]} + ${IP} li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]} + ${IP} li add ${NETIFS[p3]} type veth peer name ${NETIFS[p4]} + ${IP} li add ${NETIFS[p5]} type veth peer name ${NETIFS[p6]} + ${IP} li add ${NETIFS[p7]} type veth peer name ${NETIFS[p8]} # enslave vrf interfaces for n in 5 7; do - ip li set ${NETIFS[p${n}]} vrf ${VRF} + ${IP} li set ${NETIFS[p${n}]} vrf ${VRF} done # add addresses for n in 1 3 5 7; do - ip li set ${NETIFS[p${n}]} up - ip addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} - ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad + ${IP} li set ${NETIFS[p${n}]} up + ${IP} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} + ${IP} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad done # move peer interfaces to namespace and add addresses for n in 2 4 6 8; do - ip li set ${NETIFS[p${n}]} netns ${PEER_NS} up - ip -netns ${PEER_NS} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} - ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad + ${IP} li set ${NETIFS[p${n}]} netns ${ns2} up + ip -netns $ns2 addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} + ip -netns $ns2 addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad done - ip -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64} - ip -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64} + ${IP} -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64} + ${IP} -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64} set +e } -cleanup() -{ - # make sure we start from a clean slate - cleanup_ns ${PEER_NS} 2>/dev/null - for n in 1 3 5 7; do - ip link del ${NETIFS[p${n}]} 2>/dev/null - done - ip link del ${VRF} 2>/dev/null - ip ro flush table ${VRF_TABLE} - ip -6 ro flush table ${VRF_TABLE} -} - ################################################################################ # IPv4 tests # @@ -241,7 +231,7 @@ run_ip() # dev arg may be empty [ -n "${dev}" ] && dev="dev ${dev}" - run_cmd ip ro add table "${table}" "${prefix}"/32 via "${gw}" "${dev}" onlink + run_cmd "${IP} ro add table ${table} ${prefix}/32 via ${gw} ${dev} onlink" log_test $? ${exp_rc} "${desc}" } @@ -257,8 +247,8 @@ run_ip_mpath() # dev arg may be empty [ -n "${dev}" ] && dev="dev ${dev}" - run_cmd ip ro add table "${table}" "${prefix}"/32 \ - nexthop via ${nh1} nexthop via ${nh2} + run_cmd "${IP} ro add table ${table} ${prefix}/32 \ + nexthop via ${nh1} nexthop via ${nh2}" log_test $? ${exp_rc} "${desc}" } @@ -339,7 +329,7 @@ run_ip6() # dev arg may be empty [ -n "${dev}" ] && dev="dev ${dev}" - run_cmd ip -6 ro add table "${table}" "${prefix}"/128 via "${gw}" "${dev}" onlink + run_cmd "${IP} -6 ro add table ${table} ${prefix}/128 via ${gw} ${dev} onlink" log_test $? ${exp_rc} "${desc}" } @@ -353,8 +343,8 @@ run_ip6_mpath() local exp_rc="$6" local desc="$7" - run_cmd ip -6 ro add table "${table}" "${prefix}"/128 "${opts}" \ - nexthop via ${nh1} nexthop via ${nh2} + run_cmd "${IP} -6 ro add table ${table} ${prefix}/128 ${opts} \ + nexthop via ${nh1} nexthop via ${nh2}" log_test $? ${exp_rc} "${desc}" } @@ -491,10 +481,9 @@ do esac done -cleanup setup run_onlink_tests -cleanup +cleanup_ns ${ns1} ${ns2} if [ "$TESTS" != "none" ]; then printf "\nTests passed: %3d\n" ${nsuccess} diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index ea89e558672db0..86edbc7e2489b3 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -223,7 +223,7 @@ mirred_egress_to_ingress_tcp_test() ip_proto icmp \ action drop - ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & + ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 > $mirred_e2i_tf2 & local rpid=$! ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 wait -n $rpid diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh index b43816dd998cab..457f41d5e584b5 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh @@ -567,6 +567,21 @@ vxlan_encapped_ping_do() local inner_tos=$1; shift local outer_tos=$1; shift + local ipv4hdr=$(: + )"45:"$( : IP version + IHL + )"$inner_tos:"$( : IP TOS + )"00:54:"$( : IP total length + )"99:83:"$( : IP identification + )"40:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"01:"$( : IP proto + )"CHECKSUM:"$( : IP header csum + )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 + )"c0:00:02:01"$( : IP daddr: 192.0.2.1 + ) + local checksum=$(payload_template_calc_checksum "$ipv4hdr") + ipv4hdr=$(payload_template_expand_checksum "$ipv4hdr" $checksum) + $MZ $dev -c $count -d 100msec -q \ -b $next_hop_mac -B $dest_ip \ -t udp tos=$outer_tos,sp=23456,dp=$VXPORT,p=$(: @@ -577,16 +592,7 @@ vxlan_encapped_ping_do() )"$dest_mac:"$( : ETH daddr )"$(mac_get w2):"$( : ETH saddr )"08:00:"$( : ETH type - )"45:"$( : IP version + IHL - )"$inner_tos:"$( : IP TOS - )"00:54:"$( : IP total length - )"99:83:"$( : IP identification - )"40:00:"$( : IP flags + frag off - )"40:"$( : IP TTL - )"01:"$( : IP proto - )"00:00:"$( : IP header csum - )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 - )"c0:00:02:01:"$( : IP daddr: 192.0.2.1 + )"$ipv4hdr:"$( : IPv4 header )"08:"$( : ICMP type )"00:"$( : ICMP code )"8b:f2:"$( : ICMP csum diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh index a603f7b0a08f07..e642feeada0e7e 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh @@ -695,7 +695,7 @@ vxlan_encapped_ping_do() )"6"$( : IP version )"$inner_tos"$( : Traffic class )"0:00:00:"$( : Flow label - )"00:08:"$( : Payload length + )"00:03:"$( : Payload length )"3a:"$( : Next header )"04:"$( : Hop limit )"$saddr:"$( : IP saddr diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index f448bafb3f208e..d0306b27fe95ef 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -576,7 +576,7 @@ ip_link_has_flag() local flag=$1; shift local state=$(ip -j link show "$name" | - jq --arg flag "$flag" 'any(.[].flags.[]; . == $flag)') + jq --arg flag "$flag" 'any(.[].flags[]; . == $flag)') [[ $state == true ]] } diff --git a/tools/testing/selftests/net/lib/ksft.h b/tools/testing/selftests/net/lib/ksft.h index 17dc34a612c64e..03912902a6d30c 100644 --- a/tools/testing/selftests/net/lib/ksft.h +++ b/tools/testing/selftests/net/lib/ksft.h @@ -24,7 +24,8 @@ static inline void ksft_ready(void) fd = STDOUT_FILENO; } - write(fd, msg, sizeof(msg)); + if (write(fd, msg, sizeof(msg)) < 0) + perror("write()"); if (fd != STDOUT_FILENO) close(fd); } @@ -48,7 +49,8 @@ static inline void ksft_wait(void) fd = STDIN_FILENO; } - read(fd, &byte, sizeof(byte)); + if (read(fd, &byte, sizeof(byte)) < 0) + perror("read()"); if (fd != STDIN_FILENO) close(fd); } diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py index 97b7cf2b20eb93..8f2da17d535106 100644 --- a/tools/testing/selftests/net/lib/py/__init__.py +++ b/tools/testing/selftests/net/lib/py/__init__.py @@ -12,7 +12,7 @@ from .netns import NetNS, NetNSEnter from .nsim import NetdevSim, NetdevSimDev from .utils import CmdExitFailure, fd_read_timeout, cmd, bkg, defer, \ - bpftool, ip, ethtool, bpftrace, rand_port, wait_port_listen, wait_file + bpftool, ip, ethtool, bpftrace, rand_port, wait_port_listen, wait_file, tool from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily from .ynl import NetshaperFamily, DevlinkFamily, PSPFamily @@ -25,7 +25,7 @@ "NetNS", "NetNSEnter", "CmdExitFailure", "fd_read_timeout", "cmd", "bkg", "defer", "bpftool", "ip", "ethtool", "bpftrace", "rand_port", - "wait_port_listen", "wait_file", + "wait_port_listen", "wait_file", "tool", "NetdevSim", "NetdevSimDev", "NetshaperFamily", "DevlinkFamily", "PSPFamily", "NlError", "YnlFamily", "EthtoolFamily", "NetdevFamily", "RtnlFamily", diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 43f31f8d587fe1..9a95830005061d 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2305,17 +2305,16 @@ signal_address_tests() ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 # It is not directly linked to the commit introducing this # symbol but for the parent one which is linked anyway. - if ! mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then - chk_join_nr 3 3 2 - chk_add_nr 4 4 - else - chk_join_nr 3 3 3 + if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then # the server will not signal the address terminating # the MPC subflow chk_add_nr 3 3 + else + chk_add_nr 4 4 fi fi } @@ -3692,21 +3691,28 @@ userspace_pm_chk_get_addr() fi } -# $1: ns ; $2: event type ; $3: count +# $1: ns ; $2: event type ; $3: count ; [ $4: attr ; $5: attr count ] chk_evt_nr() { local ns=${1} local evt_name="${2}" local exp="${3}" + local attr="${4}" + local attr_exp="${5}" local evts="${evts_ns1}" local evt="${!evt_name}" + local attr_name local count + if [ -n "${attr}" ]; then + attr_name=", ${attr}: ${attr_exp}" + fi + evt_name="${evt_name:16}" # without MPTCP_LIB_EVENT_ [ "${ns}" == "ns2" ] && evts="${evts_ns2}" - print_check "event ${ns} ${evt_name} (${exp})" + print_check "event ${ns} ${evt_name} (${exp}${attr_name})" if [[ "${evt_name}" = "LISTENER_"* ]] && ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then @@ -3717,11 +3723,42 @@ chk_evt_nr() count=$(grep -cw "type:${evt}" "${evts}") if [ "${count}" != "${exp}" ]; then fail_test "got ${count} events, expected ${exp}" + cat "${evts}" + return + elif [ -z "${attr}" ]; then + print_ok + return + fi + + count=$(grep -w "type:${evt}" "${evts}" | grep -c ",${attr}:") + if [ "${count}" != "${attr_exp}" ]; then + fail_test "got ${count} event attributes, expected ${attr_exp}" + grep -w "type:${evt}" "${evts}" else print_ok fi } +# $1: ns ; $2: event type ; $3: expected count +wait_event() +{ + local ns="${1}" + local evt_name="${2}" + local exp="${3}" + + local evt="${!evt_name}" + local evts="${evts_ns1}" + local count + + [ "${ns}" == "ns2" ] && evts="${evts_ns2}" + + for _ in $(seq 100); do + count=$(grep -cw "type:${evt}" "${evts}") + [ "${count}" -ge "${exp}" ] && break + sleep 0.1 + done +} + userspace_tests() { # userspace pm type prevents add_addr @@ -3930,6 +3967,36 @@ userspace_tests() kill_events_pids mptcp_lib_kill_group_wait $tests_pid fi + + # userspace pm no duplicated spurious close events after an error + if reset_with_events "userspace pm no dup close events after error" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + set_userspace_pm $ns2 + pm_nl_set_limits $ns1 0 2 + { timeout_test=120 test_linkfail=128 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null + local tests_pid=$! + wait_event ns2 MPTCP_LIB_EVENT_ESTABLISHED 1 + userspace_pm_add_sf $ns2 10.0.3.2 20 + chk_mptcp_info subflows 1 subflows 1 + chk_subflows_total 2 2 + + # force quick loss + ip netns exec $ns2 sysctl -q net.ipv4.tcp_syn_retries=1 + if ip netns exec "${ns1}" ${iptables} -A INPUT -s "10.0.1.2" \ + -p tcp --tcp-option 30 -j REJECT --reject-with tcp-reset && + ip netns exec "${ns2}" ${iptables} -A INPUT -d "10.0.1.2" \ + -p tcp --tcp-option 30 -j REJECT --reject-with tcp-reset; then + wait_event ns2 MPTCP_LIB_EVENT_SUB_CLOSED 1 + wait_event ns1 MPTCP_LIB_EVENT_SUB_CLOSED 1 + chk_subflows_total 1 1 + userspace_pm_add_sf $ns2 10.0.1.2 0 + wait_event ns2 MPTCP_LIB_EVENT_SUB_CLOSED 2 + chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_CLOSED 2 error 2 + fi + kill_events_pids + mptcp_lib_kill_group_wait $tests_pid + fi } endpoint_tests() diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index ec6a8758819194..123d9d7a0278cd 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -192,6 +192,10 @@ check "show_endpoints" \ flush_endpoint check "show_endpoints" "" "flush addrs" +add_endpoint 10.0.1.1 flags unknown +check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" "ignore unknown flags" +flush_endpoint + set_limits 9 1 2>/dev/null check "get_limits" "${default_limits}" "rcv addrs above hard limit" diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 65b374232ff5ac..99eecccbf0c876 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -24,6 +24,8 @@ #define IPPROTO_MPTCP 262 #endif +#define MPTCP_PM_ADDR_FLAG_UNKNOWN _BITUL(7) + static void syntax(char *argv[]) { fprintf(stderr, "%s add|ann|rem|csf|dsf|get|set|del|flush|dump|events|listen|accept []\n", argv[0]); @@ -836,6 +838,8 @@ int add_addr(int fd, int pm_family, int argc, char *argv[]) flags |= MPTCP_PM_ADDR_FLAG_BACKUP; else if (!strcmp(tok, "fullmesh")) flags |= MPTCP_PM_ADDR_FLAG_FULLMESH; + else if (!strcmp(tok, "unknown")) + flags |= MPTCP_PM_ADDR_FLAG_UNKNOWN; else error(1, errno, "unknown flag %s", argv[arg]); @@ -1048,6 +1052,13 @@ static void print_addr(struct rtattr *attrs, int len) printf(","); } + if (flags & MPTCP_PM_ADDR_FLAG_UNKNOWN) { + printf("unknown"); + flags &= ~MPTCP_PM_ADDR_FLAG_UNKNOWN; + if (flags) + printf(","); + } + /* bump unknown flags, if any */ if (flags) printf("0x%x", flags); diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh index 7fc6c5dbd5516e..84b8eb12143ae7 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_clash.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh @@ -116,7 +116,7 @@ run_one_clash_test() # not a failure: clash resolution logic did not trigger. # With right timing, xmit completed sequentially and # no parallel insertion occurs. - return $ksft_skip + return $ksft_xfail } run_clash_test() @@ -133,12 +133,12 @@ run_clash_test() if [ $rv -eq 0 ];then echo "PASS: clash resolution test for $daddr:$dport on attempt $i" return 0 - elif [ $rv -eq $ksft_skip ]; then + elif [ $rv -eq $ksft_xfail ]; then softerr=1 fi done - [ $softerr -eq 1 ] && echo "SKIP: clash resolution for $daddr:$dport did not trigger" + [ $softerr -eq 1 ] && echo "XFAIL: clash resolution for $daddr:$dport did not trigger" } ip link add veth0 netns "$nsclient1" type veth peer name veth0 netns "$nsrouter" @@ -167,8 +167,7 @@ load_simple_ruleset "$nsclient2" run_clash_test "$nsclient2" "$nsclient2" 127.0.0.1 9001 if [ $clash_resolution_active -eq 0 ];then - [ "$ret" -eq 0 ] && ret=$ksft_skip - echo "SKIP: Clash resolution did not trigger" + [ "$ret" -eq 0 ] && ret=$ksft_xfail fi exit $ret diff --git a/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.c b/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.c index 507930cee8cb69..462d628cc3bdba 100644 --- a/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.c +++ b/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.c @@ -33,9 +33,14 @@ static void die(const char *e) exit(111); } -static void die_port(uint16_t got, uint16_t want) +static void die_port(const struct sockaddr_in *sin, uint16_t want) { - fprintf(stderr, "Port number changed, wanted %d got %d\n", want, ntohs(got)); + uint16_t got = ntohs(sin->sin_port); + char str[INET_ADDRSTRLEN]; + + inet_ntop(AF_INET, &sin->sin_addr, str, sizeof(str)); + + fprintf(stderr, "Port number changed, wanted %d got %d from %s\n", want, got, str); exit(1); } @@ -100,7 +105,7 @@ int main(int argc, char *argv[]) die("child recvfrom"); if (peer.sin_port != htons(PORT)) - die_port(peer.sin_port, PORT); + die_port(&peer, PORT); } else { if (sendto(s2, buf, LEN, 0, (struct sockaddr *)&sa1, sizeof(sa1)) != LEN) continue; @@ -109,7 +114,7 @@ int main(int argc, char *argv[]) die("parent recvfrom"); if (peer.sin_port != htons((PORT + 1))) - die_port(peer.sin_port, PORT + 1); + die_port(&peer, PORT + 1); } } diff --git a/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.sh index a24c896347a889..dc7e9d6da0624c 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.sh @@ -45,6 +45,8 @@ if ip netns exec "$ns0" ./conntrack_reverse_clash; then echo "PASS: No SNAT performed for null bindings" else echo "ERROR: SNAT performed without any matching snat rule" + ip netns exec "$ns0" conntrack -L + ip netns exec "$ns0" conntrack -S exit 1 fi diff --git a/tools/testing/selftests/net/netfilter/packetdrill/conntrack_syn_challenge_ack.pkt b/tools/testing/selftests/net/netfilter/packetdrill/conntrack_syn_challenge_ack.pkt index 3442cd29bc9320..cdb3910af95b4d 100644 --- a/tools/testing/selftests/net/netfilter/packetdrill/conntrack_syn_challenge_ack.pkt +++ b/tools/testing/selftests/net/netfilter/packetdrill/conntrack_syn_challenge_ack.pkt @@ -26,7 +26,7 @@ +0.01 > R 643160523:643160523(0) win 0 -+0.01 `conntrack -f $NFCT_IP_VERSION -L -p tcp --dport 8080 2>/dev/null | grep UNREPLIED | grep -q SYN_SENT` ++0.1 `conntrack -f $NFCT_IP_VERSION -L -p tcp --dport 8080 2>/dev/null | grep UNREPLIED | grep -q SYN_SENT` // Must go through. +0.01 > S 0:0(0) win 65535 diff --git a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt index b2b2cdf27e20f6..454441e7ecff6b 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt @@ -1,6 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 // Test that we correctly skip zero-length IOVs. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt index a82c8899d36bf4..0a0700afdaa38d 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt @@ -4,6 +4,8 @@ // send a packet with MSG_ZEROCOPY and receive the notification ID // repeat and verify IDs are consecutive +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt index c01915e7f4a15a..df91675d2991c3 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt @@ -3,6 +3,8 @@ // // send multiple packets, then read one range of all notifications. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt index 6509882932e916..2963cfcb14dfd7 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Minimal client-side zerocopy test +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt index 2cd78755cb2ac3..ea0c2fa73c2d66 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt @@ -7,6 +7,8 @@ // First send on a closed socket and wait for (absent) notification. // Then connect and send and verify that notification nr. is zero. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt index 7671c20e01cf64..4df978a9b82e70 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt @@ -7,6 +7,9 @@ // fire two sends with MSG_ZEROCOPY and receive the acks. confirm that EPOLLERR // is correctly fired only once, when EPOLLET is set. send another packet with // MSG_ZEROCOPY. confirm that EPOLLERR is correctly fired again only once. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt index fadc480fdb7fe0..36b6edc4858c4d 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt @@ -8,6 +8,9 @@ // fire two sends with MSG_ZEROCOPY and receive the acks. confirm that EPOLLERR // is correctly fired only once, when EPOLLET is set. send another packet with // MSG_ZEROCOPY. confirm that EPOLLERR is correctly fired again only once. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt index 5bfa0d1d2f4a31..1bea6f3b4558df 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt @@ -8,6 +8,9 @@ // is correctly fired only once, when EPOLLONESHOT is set. send another packet // with MSG_ZEROCOPY. confirm that EPOLLERR is not fired. Rearm the FD and // confirm that EPOLLERR is correctly set. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt index 4a73bbf4696108..e27c21ff5d18d9 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt @@ -8,6 +8,8 @@ // one will have no data in the initial send. On return 0 the // zerocopy notification counter is not incremented. Verify this too. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` // Send a FastOpen request, no cookie yet so no data in SYN diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt index 36086c5877ce7d..b1fa77c77dfa77 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt @@ -4,6 +4,8 @@ // send data with MSG_FASTOPEN | MSG_ZEROCOPY and verify that the // kernel returns the notification ID. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh ./set_sysctls.py /proc/sys/net/ipv4/tcp_fastopen=0x207` diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt index 672f817faca0d1..2f5317d0a9fab5 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt @@ -7,6 +7,8 @@ // because each iovec element becomes a frag // 3) the PSH bit is set on an skb when it runs out of fragments +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt index a9a1ac0aea4f4e..9d5272c6b20790 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt @@ -4,6 +4,8 @@ // verify that SO_EE_CODE_ZEROCOPY_COPIED is set on zerocopy // packets of all sizes, including the smallest payload, 1B. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/tap.c b/tools/testing/selftests/net/tap.c index 247c3b3ac1c97c..51a209014f1cf8 100644 --- a/tools/testing/selftests/net/tap.c +++ b/tools/testing/selftests/net/tap.c @@ -56,18 +56,12 @@ static void rtattr_end(struct nlmsghdr *nh, struct rtattr *attr) static struct rtattr *rtattr_add_str(struct nlmsghdr *nh, unsigned short type, const char *s) { - struct rtattr *rta = rtattr_add(nh, type, strlen(s)); + unsigned int strsz = strlen(s) + 1; + struct rtattr *rta; - memcpy(RTA_DATA(rta), s, strlen(s)); - return rta; -} - -static struct rtattr *rtattr_add_strsz(struct nlmsghdr *nh, unsigned short type, - const char *s) -{ - struct rtattr *rta = rtattr_add(nh, type, strlen(s) + 1); + rta = rtattr_add(nh, type, strsz); - strcpy(RTA_DATA(rta), s); + memcpy(RTA_DATA(rta), s, strsz); return rta; } @@ -119,7 +113,7 @@ static int dev_create(const char *dev, const char *link_type, link_info = rtattr_begin(&req.nh, IFLA_LINKINFO); - rtattr_add_strsz(&req.nh, IFLA_INFO_KIND, link_type); + rtattr_add_str(&req.nh, IFLA_INFO_KIND, link_type); if (fill_info_data) { info_data = rtattr_begin(&req.nh, IFLA_INFO_DATA); diff --git a/tools/testing/selftests/net/tfo.c b/tools/testing/selftests/net/tfo.c index eb3cac5e583c9d..8d82140f0f7679 100644 --- a/tools/testing/selftests/net/tfo.c +++ b/tools/testing/selftests/net/tfo.c @@ -81,7 +81,8 @@ static void run_server(void) if (getsockopt(connfd, SOL_SOCKET, SO_INCOMING_NAPI_ID, &opt, &len) < 0) error(1, errno, "getsockopt(SO_INCOMING_NAPI_ID)"); - read(connfd, buf, 64); + if (read(connfd, buf, 64) < 0) + perror("read()"); fprintf(outfile, "%d\n", opt); fclose(outfile); diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/net/toeplitz.c index 9ba03164d73a69..5099157f01b9ab 100644 --- a/tools/testing/selftests/net/toeplitz.c +++ b/tools/testing/selftests/net/toeplitz.c @@ -473,8 +473,8 @@ static void parse_rps_bitmap(const char *arg) bitmap = strtoul(arg, NULL, 0); - if (bitmap & ~(RPS_MAX_CPUS - 1)) - error(1, 0, "rps bitmap 0x%lx out of bounds 0..%lu", + if (bitmap & ~((1UL << RPS_MAX_CPUS) - 1)) + error(1, 0, "rps bitmap 0x%lx out of bounds, max cpu %lu", bitmap, RPS_MAX_CPUS - 1); for (i = 0; i < RPS_MAX_CPUS; i++) diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 195f04c4d15868..b9c1bfb6cc029a 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -243,6 +243,16 @@ int snc_nodes_per_l3_cache(void) } snc_mode = cache_cpus / node_cpus; + /* + * On some platforms (e.g. Hygon), + * cache_cpus < node_cpus, the calculated snc_mode is 0. + * + * Set snc_mode = 1 to indicate that SNC mode is not + * supported on the platform. + */ + if (!snc_mode) + snc_mode = 1; + if (snc_mode > 1) ksft_print_msg("SNC-%d mode discovered.\n", snc_mode); } diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index 6b8123c12a7ae6..cbd23444c8a987 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -718,7 +718,7 @@ static int ublk_thread_is_idle(struct ublk_thread *t) static int ublk_thread_is_done(struct ublk_thread *t) { - return (t->state & UBLKS_T_STOPPING) && ublk_thread_is_idle(t); + return (t->state & UBLKS_T_STOPPING) && ublk_thread_is_idle(t) && !t->cmd_inflight; } static inline void ublksrv_handle_tgt_cqe(struct ublk_thread *t, @@ -1002,7 +1002,9 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) } if (ret < 0) { ublk_err("%s: ublk_ctrl_start_dev failed: %d\n", __func__, ret); - goto fail; + /* stop device so that inflight uring_cmd can be cancelled */ + ublk_ctrl_stop_dev(dev); + goto fail_start; } ublk_ctrl_get_info(dev); @@ -1010,7 +1012,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) ublk_ctrl_dump(dev); else ublk_send_dev_event(ctx, dev, dev->dev_info.dev_id); - +fail_start: /* wait until we are terminated */ for (i = 0; i < dev->nthreads; i++) pthread_join(dev->threads[i].thread, &thread_ret); @@ -1219,7 +1221,7 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) } ret = ublk_start_daemon(ctx, dev); - ublk_dbg(UBLK_DBG_DEV, "%s: daemon exit %d\b", ret); + ublk_dbg(UBLK_DBG_DEV, "%s: daemon exit %d\n", __func__, ret); if (ret < 0) ublk_ctrl_del_dev(dev); @@ -1564,6 +1566,7 @@ int main(int argc, char *argv[]) int option_idx, opt; const char *cmd = argv[1]; struct dev_ctx ctx = { + ._evtfd = -1, .queue_depth = 128, .nr_hw_queues = 2, .dev_id = -1, diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h index 5e55484fb0aa26..1b8833a4006436 100644 --- a/tools/testing/selftests/ublk/kublk.h +++ b/tools/testing/selftests/ublk/kublk.h @@ -393,19 +393,19 @@ static inline int ublk_completed_tgt_io(struct ublk_thread *t, return --io->tgt_ios == 0; } -static inline int ublk_queue_use_zc(const struct ublk_queue *q) +static inline bool ublk_queue_use_zc(const struct ublk_queue *q) { - return q->flags & UBLK_F_SUPPORT_ZERO_COPY; + return !!(q->flags & UBLK_F_SUPPORT_ZERO_COPY); } -static inline int ublk_queue_use_auto_zc(const struct ublk_queue *q) +static inline bool ublk_queue_use_auto_zc(const struct ublk_queue *q) { - return q->flags & UBLK_F_AUTO_BUF_REG; + return !!(q->flags & UBLK_F_AUTO_BUF_REG); } -static inline int ublk_queue_auto_zc_fallback(const struct ublk_queue *q) +static inline bool ublk_queue_auto_zc_fallback(const struct ublk_queue *q) { - return q->flags & UBLKS_Q_AUTO_BUF_REG_FALLBACK; + return !!(q->flags & UBLKS_Q_AUTO_BUF_REG_FALLBACK); } static inline int ublk_queue_no_buf(const struct ublk_queue *q) diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index d843643ced6b7f..9430ef5b8bc3ea 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -511,6 +511,18 @@ void run_tests(const struct test_case *test_cases, printf("ok\n"); } + + printf("All tests have been executed. Waiting other peer..."); + fflush(stdout); + + /* + * Final full barrier, to ensure that all tests have been run and + * that even the last one has been successful on both sides. + */ + control_writeln("COMPLETED"); + control_expectln("COMPLETED"); + + printf("ok\n"); } void list_tests(const struct test_case *test_cases) diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index 142c02a6834acb..bf633cde82b073 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -25,7 +25,7 @@ enum transport { }; static const char * const transport_ksyms[] = { - #define x(name, symbol) "d " symbol "_transport", + #define x(name, symbol) " " symbol "_transport", KNOWN_TRANSPORTS(x) #undef x }; diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index d4517386e551e3..667f6f0ad6afae 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -351,6 +351,7 @@ static void test_stream_msg_peek_server(const struct test_opts *opts) static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) { + unsigned long long sock_buf_size; unsigned long curr_hash; size_t max_msg_size; int page_size; @@ -363,6 +364,16 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) exit(EXIT_FAILURE); } + sock_buf_size = SOCK_BUF_SIZE; + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); + /* Wait, until receiver sets buffer size. */ control_expectln("SRVREADY"); diff --git a/tools/tracing/rtla/Makefile.rtla b/tools/tracing/rtla/Makefile.rtla index 08c1b40883d3aa..1743d91829d460 100644 --- a/tools/tracing/rtla/Makefile.rtla +++ b/tools/tracing/rtla/Makefile.rtla @@ -18,7 +18,7 @@ export CC AR STRIP PKG_CONFIG LD_SO_CONF_PATH LDCONFIG FOPTS := -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \ -fasynchronous-unwind-tables -fstack-clash-protection WOPTS := -O -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 \ - -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized + -Wp,-D_GLIBCXX_ASSERTIONS ifeq ($(CC),clang) FOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(FOPTS)) diff --git a/tools/tracing/rtla/src/common.c b/tools/tracing/rtla/src/common.c index 2e6e3dac1897f1..b197037fc58b37 100644 --- a/tools/tracing/rtla/src/common.c +++ b/tools/tracing/rtla/src/common.c @@ -268,6 +268,10 @@ int top_main_loop(struct osnoise_tool *tool) tool->ops->print_stats(tool); if (osnoise_trace_is_off(tool, record)) { + if (stop_tracing) + /* stop tracing requested, do not perform actions */ + return 0; + actions_perform(¶ms->threshold_actions); if (!params->threshold_actions.continue_flag) @@ -315,20 +319,22 @@ int hist_main_loop(struct osnoise_tool *tool) } if (osnoise_trace_is_off(tool, tool->record)) { + if (stop_tracing) + /* stop tracing requested, do not perform actions */ + break; + actions_perform(¶ms->threshold_actions); - if (!params->threshold_actions.continue_flag) { + if (!params->threshold_actions.continue_flag) /* continue flag not set, break */ break; - /* continue action reached, re-enable tracing */ - if (tool->record) - trace_instance_start(&tool->record->trace); - if (tool->aa) - trace_instance_start(&tool->aa->trace); - trace_instance_start(&tool->trace); - } - break; + /* continue action reached, re-enable tracing */ + if (tool->record) + trace_instance_start(&tool->record->trace); + if (tool->aa) + trace_instance_start(&tool->aa->trace); + trace_instance_start(&tool->trace); } /* is there still any user-threads ? */ diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c index dffb6d0a98d7d9..d22feb4d6cc9dc 100644 --- a/tools/tracing/rtla/src/osnoise_hist.c +++ b/tools/tracing/rtla/src/osnoise_hist.c @@ -557,7 +557,8 @@ static struct common_params params->threshold = 1; /* set trace */ - trace_output = "osnoise_trace.txt"; + if (!trace_output) + trace_output = "osnoise_trace.txt"; break; case 'b': diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index 95418f7ecc9613..a8d31030c41229 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -397,7 +397,8 @@ struct common_params *osnoise_top_parse_args(int argc, char **argv) params->threshold = 1; /* set trace */ - trace_output = "osnoise_trace.txt"; + if (!trace_output) + trace_output = "osnoise_trace.txt"; break; case 'c': diff --git a/tools/tracing/rtla/src/timerlat.bpf.c b/tools/tracing/rtla/src/timerlat.bpf.c index 084cd10c21fc49..e2265b5d649100 100644 --- a/tools/tracing/rtla/src/timerlat.bpf.c +++ b/tools/tracing/rtla/src/timerlat.bpf.c @@ -148,6 +148,9 @@ int handle_timerlat_sample(struct trace_event_raw_timerlat_sample *tp_args) } else { update_main_hist(&hist_user, bucket); update_summary(&summary_user, latency, bucket); + + if (thread_threshold != 0 && latency_us >= thread_threshold) + set_stop_tracing(); } return 0; diff --git a/tools/tracing/rtla/src/timerlat.c b/tools/tracing/rtla/src/timerlat.c index b6921287412794..11ad447a8dd78b 100644 --- a/tools/tracing/rtla/src/timerlat.c +++ b/tools/tracing/rtla/src/timerlat.c @@ -215,7 +215,8 @@ void timerlat_analyze(struct osnoise_tool *tool, bool stopped) void timerlat_free(struct osnoise_tool *tool) { struct timerlat_params *params = to_timerlat_params(tool->params); - int nr_cpus, i; + int nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + int i; timerlat_aa_destroy(); if (dma_latency_fd >= 0) diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index 606c1688057b27..3d56df3d5fa0d4 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -878,7 +878,8 @@ static struct common_params params->print_stack = auto_thresh; /* set trace */ - trace_output = "timerlat_trace.txt"; + if (!trace_output) + trace_output = "timerlat_trace.txt"; break; case 'c': diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index fc479a0dcb597a..6cc9a3607c6653 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -628,7 +628,8 @@ static struct common_params params->print_stack = auto_thresh; /* set trace */ - trace_output = "timerlat_trace.txt"; + if (!trace_output) + trace_output = "timerlat_trace.txt"; break; case '5': diff --git a/tools/tracing/rtla/tests/osnoise.t b/tools/tracing/rtla/tests/osnoise.t index e3c89d45a6bb04..39633460892074 100644 --- a/tools/tracing/rtla/tests/osnoise.t +++ b/tools/tracing/rtla/tests/osnoise.t @@ -37,11 +37,11 @@ check "multiple actions" \ check "hist stop at failed action" \ "osnoise hist -S 2 --on-threshold shell,command='echo -n 1; false' --on-threshold shell,command='echo -n 2'" 2 "^1# RTLA osnoise histogram$" check "top stop at failed action" \ - "timerlat top -T 2 --on-threshold shell,command='echo -n abc; false' --on-threshold shell,command='echo -n defgh'" 2 "^abc" "defgh" + "osnoise top -S 2 --on-threshold shell,command='echo -n abc; false' --on-threshold shell,command='echo -n defgh'" 2 "^abc" "defgh" check "hist with continue" \ - "osnoise hist -S 2 -d 1s --on-threshold shell,command='echo TestOutput' --on-threshold continue" 0 "^TestOutput$" + "osnoise hist -S 2 -d 5s --on-threshold shell,command='echo TestOutput' --on-threshold continue" 0 "^TestOutput$" check "top with continue" \ - "osnoise top -q -S 2 -d 1s --on-threshold shell,command='echo TestOutput' --on-threshold continue" 0 "^TestOutput$" + "osnoise top -q -S 2 -d 5s --on-threshold shell,command='echo TestOutput' --on-threshold continue" 0 "^TestOutput$" check "hist with trace output at end" \ "osnoise hist -d 1s --on-end trace" 0 "^ Saving trace to osnoise_trace.txt$" check "top with trace output at end" \ diff --git a/tools/tracing/rtla/tests/timerlat.t b/tools/tracing/rtla/tests/timerlat.t index b5d1e7260a9bed..b550a6ae24456f 100644 --- a/tools/tracing/rtla/tests/timerlat.t +++ b/tools/tracing/rtla/tests/timerlat.t @@ -60,9 +60,9 @@ check "hist stop at failed action" \ check "top stop at failed action" \ "timerlat top -T 2 --on-threshold shell,command='echo -n 1; false' --on-threshold shell,command='echo -n 2'" 2 "^1ALL" check "hist with continue" \ - "timerlat hist -T 2 -d 1s --on-threshold shell,command='echo TestOutput' --on-threshold continue" 0 "^TestOutput$" + "timerlat hist -T 2 -d 5s --on-threshold shell,command='echo TestOutput' --on-threshold continue" 0 "^TestOutput$" check "top with continue" \ - "timerlat top -q -T 2 -d 1s --on-threshold shell,command='echo TestOutput' --on-threshold continue" 0 "^TestOutput$" + "timerlat top -q -T 2 -d 5s --on-threshold shell,command='echo TestOutput' --on-threshold continue" 0 "^TestOutput$" check "hist with trace output at end" \ "timerlat hist -d 1s --on-end trace" 0 "^ Saving trace to timerlat_trace.txt$" check "top with trace output at end" \ diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index a7794ffdb97619..1a64266341b193 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -157,21 +157,28 @@ irqfd_shutdown(struct work_struct *work) } -/* assumes kvm->irqfds.lock is held */ -static bool -irqfd_is_active(struct kvm_kernel_irqfd *irqfd) +static bool irqfd_is_active(struct kvm_kernel_irqfd *irqfd) { + /* + * Assert that either irqfds.lock or SRCU is held, as irqfds.lock must + * be held to prevent false positives (on the irqfd being active), and + * while false negatives are impossible as irqfds are never added back + * to the list once they're deactivated, the caller must at least hold + * SRCU to guard against routing changes if the irqfd is deactivated. + */ + lockdep_assert_once(lockdep_is_held(&irqfd->kvm->irqfds.lock) || + srcu_read_lock_held(&irqfd->kvm->irq_srcu)); + return list_empty(&irqfd->list) ? false : true; } /* * Mark the irqfd as inactive and schedule it for removal - * - * assumes kvm->irqfds.lock is held */ -static void -irqfd_deactivate(struct kvm_kernel_irqfd *irqfd) +static void irqfd_deactivate(struct kvm_kernel_irqfd *irqfd) { + lockdep_assert_held(&irqfd->kvm->irqfds.lock); + BUG_ON(!irqfd_is_active(irqfd)); list_del_init(&irqfd->list); @@ -217,8 +224,15 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) seq = read_seqcount_begin(&irqfd->irq_entry_sc); irq = irqfd->irq_entry; } while (read_seqcount_retry(&irqfd->irq_entry_sc, seq)); - /* An event has been signaled, inject an interrupt */ - if (kvm_arch_set_irq_inatomic(&irq, kvm, + + /* + * An event has been signaled, inject an interrupt unless the + * irqfd is being deassigned (isn't active), in which case the + * routing information may be stale (once the irqfd is removed + * from the list, it will stop receiving routing updates). + */ + if (unlikely(!irqfd_is_active(irqfd)) || + kvm_arch_set_irq_inatomic(&irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1, false) == -EWOULDBLOCK) schedule_work(&irqfd->inject); @@ -585,18 +599,8 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args) spin_lock_irq(&kvm->irqfds.lock); list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) { - if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) { - /* - * This clearing of irq_entry.type is needed for when - * another thread calls kvm_irq_routing_update before - * we flush workqueue below (we synchronize with - * kvm_irq_routing_update using irqfds.lock). - */ - write_seqcount_begin(&irqfd->irq_entry_sc); - irqfd->irq_entry.type = 0; - write_seqcount_end(&irqfd->irq_entry_sc); + if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) irqfd_deactivate(irqfd); - } } spin_unlock_irq(&kvm->irqfds.lock); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index b7a0ae2a7b205c..7fea6ba91c1ef3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2085,7 +2085,7 @@ static int kvm_set_memory_region(struct kvm *kvm, return -EINVAL; if ((mem->userspace_addr != old->userspace_addr) || (npages != old->npages) || - ((mem->flags ^ old->flags) & KVM_MEM_READONLY)) + ((mem->flags ^ old->flags) & (KVM_MEM_READONLY | KVM_MEM_GUEST_MEMFD))) return -EINVAL; if (base_gfn != old->base_gfn) @@ -4026,7 +4026,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) yielded = kvm_vcpu_yield_to(vcpu); if (yielded > 0) { - WRITE_ONCE(kvm->last_boosted_vcpu, i); + WRITE_ONCE(kvm->last_boosted_vcpu, idx); break; } else if (yielded < 0 && !--try) { break;